From 7945505345a60bb354f8c2fd24d01c2d77e68524 Mon Sep 17 00:00:00 2001 From: HarelM Date: Wed, 16 Sep 2026 13:20:38 +0300 Subject: [PATCH] Add missing joining types and decomposition file and parsers. --- data/10.0.0-derived-joining-type.txt | 496 +++ data/11.0.0-derived-joining-type.txt | 516 +++ data/12.0.0-derived-joining-type.txt | 523 +++ data/12.1.0-derived-joining-type.txt | 523 +++ data/13.0.0-derived-joining-type.txt | 547 +++ data/14.0.0-derived-joining-type.txt | 563 +++ data/15.0.0-derived-joining-type.txt | 573 +++ data/15.1.0-derived-joining-type.txt | 573 +++ data/16.0.0-derived-joining-type.txt | 586 +++ data/17.0.0-derived-joining-type.txt | 596 ++++ data/18.0.0-derived-joining-type.txt | 600 ++++ data/4.1.0-derived-joining-type.txt | 234 ++ data/5.0.0-derived-joining-type.txt | 248 ++ data/5.1.0-derived-joining-type.txt | 283 ++ data/5.2.0-derived-joining-type.txt | 318 ++ data/6.0.0-derived-joining-type.txt | 327 ++ data/6.1.0-derived-joining-type.txt | 356 ++ data/6.2.0-derived-joining-type.txt | 356 ++ data/6.3.0-derived-joining-type.txt | 374 ++ data/7.0.0-derived-joining-type.txt | 441 +++ data/8.0.0-derived-joining-type.txt | 451 +++ data/9.0.0-derived-joining-type.txt | 475 +++ data/resources.mjs | 44 + index.mjs | 11 +- scripts/download.mjs | 1 + scripts/parse-arabic-shaping.mjs | 39 - scripts/parse-decomposition-mapping.mjs | 61 + scripts/parse-joining-type.mjs | 74 + scripts/utils.mjs | 6 +- templates/README.md | 2 +- tests/tests.mjs | 10 + tests/tests.mjs.snapshot | 4359 ++++++++++++++++++++--- 32 files changed, 14110 insertions(+), 456 deletions(-) create mode 100644 data/10.0.0-derived-joining-type.txt create mode 100644 data/11.0.0-derived-joining-type.txt create mode 100644 data/12.0.0-derived-joining-type.txt create mode 100644 data/12.1.0-derived-joining-type.txt create mode 100644 data/13.0.0-derived-joining-type.txt create mode 100644 data/14.0.0-derived-joining-type.txt create mode 100644 data/15.0.0-derived-joining-type.txt create mode 100644 data/15.1.0-derived-joining-type.txt create mode 100644 data/16.0.0-derived-joining-type.txt create mode 100644 data/17.0.0-derived-joining-type.txt create mode 100644 data/18.0.0-derived-joining-type.txt create mode 100644 data/4.1.0-derived-joining-type.txt create mode 100644 data/5.0.0-derived-joining-type.txt create mode 100644 data/5.1.0-derived-joining-type.txt create mode 100644 data/5.2.0-derived-joining-type.txt create mode 100644 data/6.0.0-derived-joining-type.txt create mode 100644 data/6.1.0-derived-joining-type.txt create mode 100644 data/6.2.0-derived-joining-type.txt create mode 100644 data/6.3.0-derived-joining-type.txt create mode 100644 data/7.0.0-derived-joining-type.txt create mode 100644 data/8.0.0-derived-joining-type.txt create mode 100644 data/9.0.0-derived-joining-type.txt delete mode 100644 scripts/parse-arabic-shaping.mjs create mode 100644 scripts/parse-decomposition-mapping.mjs create mode 100644 scripts/parse-joining-type.mjs diff --git a/data/10.0.0-derived-joining-type.txt b/data/10.0.0-derived-joining-type.txt new file mode 100644 index 0000000..ea351f5 --- /dev/null +++ b/data/10.0.0-derived-joining-type.txt @@ -0,0 +1,496 @@ +# DerivedJoiningType-10.0.0.txt +# Date: 2017-03-08, 08:41:50 GMT +# © 2017 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +180A ; C # Po MONGOLIAN NIRUGU +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 4 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0848 ; D # Lo MANDAIC LETTER ATT +084A..0853 ; D # Lo [10] MANDAIC LETTER AK..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +0860 ; D # Lo SYRIAC LETTER MALAYALAM NGA +0862..0865 ; D # Lo [4] SYRIAC LETTER MALAYALAM NYA..SYRIAC LETTER MALAYALAM NNNA +0868 ; D # Lo SYRIAC LETTER MALAYALAM LLA +08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE +08B3..08B4 ; D # Lo [2] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08B8 ; D # Lo [3] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER TEH WITH SMALL TEH ABOVE +08BA..08BD ; D # Lo [4] ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE..ARABIC LETTER AFRICAN NOON +1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER +1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1877 ; D # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA +1887..18A8 ; D # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; D # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA +10AC0..10AC4 ; D # Lo [5] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER GHIMEL +10AD3..10AD6 ; D # Lo [4] MANICHAEAN LETTER LAMEDH..MANICHAEAN LETTER MEM +10AD8..10ADC ; D # Lo [5] MANICHAEAN LETTER SAMEKH..MANICHAEAN LETTER FE +10ADE..10AE0 ; D # Lo [3] MANICHAEAN LETTER QOPH..MANICHAEAN LETTER QHOPH +10AEB..10AEE ; D # No [4] MANICHAEAN NUMBER ONE..MANICHAEAN NUMBER TWENTY +10B80 ; D # Lo PSALTER PAHLAVI LETTER ALEPH +10B82 ; D # Lo PSALTER PAHLAVI LETTER GIMEL +10B86..10B88 ; D # Lo [3] PSALTER PAHLAVI LETTER ZAYIN..PSALTER PAHLAVI LETTER YODH +10B8A..10B8B ; D # Lo [2] PSALTER PAHLAVI LETTER LAMEDH..PSALTER PAHLAVI LETTER MEM-QOPH +10B8D ; D # Lo PSALTER PAHLAVI LETTER SAMEKH +10B90 ; D # Lo PSALTER PAHLAVI LETTER SHIN +10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY +1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA + +# Total code points: 507 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846..0847 ; R # Lo [2] MANDAIC LETTER AZ..MANDAIC LETTER IT +0849 ; R # Lo MANDAIC LETTER AKSA +0854 ; R # Lo MANDAIC LETTER ASH +0867 ; R # Lo SYRIAC LETTER MALAYALAM RA +0869..086A ; R # Lo [2] SYRIAC LETTER MALAYALAM LLLA..SYRIAC LETTER MALAYALAM SSA +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH +08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW +08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE +08B9 ; R # Lo ARABIC LETTER REH WITH SMALL NOON ABOVE +10AC5 ; R # Lo MANICHAEAN LETTER DALETH +10AC7 ; R # Lo MANICHAEAN LETTER WAW +10AC9..10ACA ; R # Lo [2] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER ZHAYIN +10ACE..10AD2 ; R # Lo [5] MANICHAEAN LETTER TETH..MANICHAEAN LETTER KHAPH +10ADD ; R # Lo MANICHAEAN LETTER SADHE +10AE1 ; R # Lo MANICHAEAN LETTER RESH +10AE4 ; R # Lo MANICHAEAN LETTER TAW +10AEF ; R # No MANICHAEAN NUMBER ONE HUNDRED +10B81 ; R # Lo PSALTER PAHLAVI LETTER BETH +10B83..10B85 ; R # Lo [3] PSALTER PAHLAVI LETTER DALETH..PSALTER PAHLAVI LETTER WAW-AYIN-RESH +10B89 ; R # Lo PSALTER PAHLAVI LETTER KAPH +10B8C ; R # Lo PSALTER PAHLAVI LETTER NUN +10B8E..10B8F ; R # Lo [2] PSALTER PAHLAVI LETTER PE..PSALTER PAHLAVI LETTER SADHE +10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW +10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR + +# Total code points: 115 + +# ================================================ + +# Joining_Type=Left_Joining + +A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA +10ACD ; L # Lo MANICHAEAN LETTER HETH +10AD7 ; L # Lo MANICHAEAN LETTER NUN + +# Total code points: 3 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; T # Cf ARABIC LETTER MARK +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08D4..08E1 ; T # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA +08E3..0902 ; T # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; T # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B56 ; T # Mn ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C00 ; T # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C81 ; T # Mn KANNADA SIGN CANDRABINDU +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D00..0D01 ; T # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; T # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EB9 ; T # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; T # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +1885..1886 ; T # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; T # Mn BUGINESE VOWEL SIGN AE +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; T # Me COMBINING PARENTHESES OVERLAY +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB..1BAD ; T # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1DC0..1DF9 ; T # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; T # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69E..A69F ; T # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A8C4..A8C5 ; T # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC ; T # Mn JAVANESE VOWEL SIGN PEPET +A9E5 ; T # Mn MYANMAR SIGN SHAN SAW +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AA7C ; T # Mn MYANMAR SIGN TAI LAING TONE-2 +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE2F ; T # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +102E0 ; T # Mn COPTIC EPACT THOUSANDS MARK +10376..1037A ; T # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +10AE5..10AE6 ; T # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +1107F..11081 ; T # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110BD ; T # Cf KAITHI NUMBER SIGN +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11173 ; T # Mn MAHAJANI SIGN NUKTA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +111CA..111CC ; T # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK +1122F..11231 ; T # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11234 ; T # Mn KHOJKI SIGN ANUSVARA +11236..11237 ; T # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; T # Mn KHOJKI SIGN SUKUN +112DF ; T # Mn KHUDAWADI SIGN ANUSVARA +112E3..112EA ; T # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +11300..11301 ; T # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU +1133C ; T # Mn GRANTHA SIGN NUKTA +11340 ; T # Mn GRANTHA VOWEL SIGN II +11366..1136C ; T # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; T # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11438..1143F ; T # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; T # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; T # Mn NEWA SIGN NUKTA +114B3..114B8 ; T # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114BA ; T # Mn TIRHUTA VOWEL SIGN SHORT E +114BF..114C0 ; T # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C2..114C3 ; T # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +115B2..115B5 ; T # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115BC..115BD ; T # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BF..115C0 ; T # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +115DC..115DD ; T # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU +11633..1163A ; T # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163D ; T # Mn MODI SIGN ANUSVARA +1163F..11640 ; T # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +1171D..1171F ; T # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA +11722..11725 ; T # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU +11727..1172B ; T # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11A01..11A06 ; T # Mn [6] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL SIGN O +11A09..11A0A ; T # Mn [2] ZANABAZAR SQUARE VOWEL SIGN REVERSED I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; T # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; T # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; T # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; T # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; T # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; T # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; T # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C30..11C36 ; T # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; T # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; T # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; T # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; T # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; T # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; T # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; T # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; T # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; T # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; T # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; T # Mn MASARAM GONDI RA-KARA +16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +1BC9D..1BC9E ; T # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1BCA0..1BCA3 ; T # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1DA00..1DA36 ; T # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN +1DA3B..1DA6C ; T # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT +1DA75 ; T # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS +1DA84 ; T # Mn SIGNWRITING LOCATION HEAD NECK +1DA9B..1DA9F ; T # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 +1DAA1..1DAAF ; T # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; T # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; T # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; T # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; T # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; T # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; T # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 1912 + +# EOF diff --git a/data/11.0.0-derived-joining-type.txt b/data/11.0.0-derived-joining-type.txt new file mode 100644 index 0000000..d4d382b --- /dev/null +++ b/data/11.0.0-derived-joining-type.txt @@ -0,0 +1,516 @@ +# DerivedJoiningType-11.0.0.txt +# Date: 2018-02-21, 05:34:05 GMT +# © 2018 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +180A ; C # Po MONGOLIAN NIRUGU +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 4 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0848 ; D # Lo MANDAIC LETTER ATT +084A..0853 ; D # Lo [10] MANDAIC LETTER AK..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +0860 ; D # Lo SYRIAC LETTER MALAYALAM NGA +0862..0865 ; D # Lo [4] SYRIAC LETTER MALAYALAM NYA..SYRIAC LETTER MALAYALAM NNNA +0868 ; D # Lo SYRIAC LETTER MALAYALAM LLA +08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE +08B3..08B4 ; D # Lo [2] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08B8 ; D # Lo [3] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER TEH WITH SMALL TEH ABOVE +08BA..08BD ; D # Lo [4] ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE..ARABIC LETTER AFRICAN NOON +1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER +1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1878 ; D # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS +1887..18A8 ; D # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; D # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA +10AC0..10AC4 ; D # Lo [5] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER GHIMEL +10AD3..10AD6 ; D # Lo [4] MANICHAEAN LETTER LAMEDH..MANICHAEAN LETTER MEM +10AD8..10ADC ; D # Lo [5] MANICHAEAN LETTER SAMEKH..MANICHAEAN LETTER FE +10ADE..10AE0 ; D # Lo [3] MANICHAEAN LETTER QOPH..MANICHAEAN LETTER QHOPH +10AEB..10AEE ; D # No [4] MANICHAEAN NUMBER ONE..MANICHAEAN NUMBER TWENTY +10B80 ; D # Lo PSALTER PAHLAVI LETTER ALEPH +10B82 ; D # Lo PSALTER PAHLAVI LETTER GIMEL +10B86..10B88 ; D # Lo [3] PSALTER PAHLAVI LETTER ZAYIN..PSALTER PAHLAVI LETTER YODH +10B8A..10B8B ; D # Lo [2] PSALTER PAHLAVI LETTER LAMEDH..PSALTER PAHLAVI LETTER MEM-QOPH +10B8D ; D # Lo PSALTER PAHLAVI LETTER SAMEKH +10B90 ; D # Lo PSALTER PAHLAVI LETTER SHIN +10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY +10D01..10D21 ; D # Lo [33] HANIFI ROHINGYA LETTER BA..HANIFI ROHINGYA VOWEL O +10D23 ; D # Lo HANIFI ROHINGYA MARK NA KHONNA +10F30..10F32 ; D # Lo [3] SOGDIAN LETTER ALEPH..SOGDIAN LETTER GIMEL +10F34..10F44 ; D # Lo [17] SOGDIAN LETTER WAW..SOGDIAN LETTER LESH +10F51..10F53 ; D # No [3] SOGDIAN NUMBER ONE..SOGDIAN NUMBER TWENTY +1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA + +# Total code points: 565 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846..0847 ; R # Lo [2] MANDAIC LETTER AZ..MANDAIC LETTER IT +0849 ; R # Lo MANDAIC LETTER AKSA +0854 ; R # Lo MANDAIC LETTER ASH +0867 ; R # Lo SYRIAC LETTER MALAYALAM RA +0869..086A ; R # Lo [2] SYRIAC LETTER MALAYALAM LLLA..SYRIAC LETTER MALAYALAM SSA +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH +08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW +08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE +08B9 ; R # Lo ARABIC LETTER REH WITH SMALL NOON ABOVE +10AC5 ; R # Lo MANICHAEAN LETTER DALETH +10AC7 ; R # Lo MANICHAEAN LETTER WAW +10AC9..10ACA ; R # Lo [2] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER ZHAYIN +10ACE..10AD2 ; R # Lo [5] MANICHAEAN LETTER TETH..MANICHAEAN LETTER KHAPH +10ADD ; R # Lo MANICHAEAN LETTER SADHE +10AE1 ; R # Lo MANICHAEAN LETTER RESH +10AE4 ; R # Lo MANICHAEAN LETTER TAW +10AEF ; R # No MANICHAEAN NUMBER ONE HUNDRED +10B81 ; R # Lo PSALTER PAHLAVI LETTER BETH +10B83..10B85 ; R # Lo [3] PSALTER PAHLAVI LETTER DALETH..PSALTER PAHLAVI LETTER WAW-AYIN-RESH +10B89 ; R # Lo PSALTER PAHLAVI LETTER KAPH +10B8C ; R # Lo PSALTER PAHLAVI LETTER NUN +10B8E..10B8F ; R # Lo [2] PSALTER PAHLAVI LETTER PE..PSALTER PAHLAVI LETTER SADHE +10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW +10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR +10D22 ; R # Lo HANIFI ROHINGYA MARK SAKIN +10F33 ; R # Lo SOGDIAN LETTER HE +10F54 ; R # No SOGDIAN NUMBER ONE HUNDRED + +# Total code points: 118 + +# ================================================ + +# Joining_Type=Left_Joining + +A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA +10ACD ; L # Lo MANICHAEAN LETTER HETH +10AD7 ; L # Lo MANICHAEAN LETTER NUN +10D00 ; L # Lo HANIFI ROHINGYA LETTER A + +# Total code points: 4 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; T # Cf ARABIC LETTER MARK +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +07FD ; T # Mn NKO DANTAYALAN +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08D3..08E1 ; T # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +08E3..0902 ; T # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09FE ; T # Mn BENGALI SANDHI MARK +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; T # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B56 ; T # Mn ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C00 ; T # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C04 ; T # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C81 ; T # Mn KANNADA SIGN CANDRABINDU +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D00..0D01 ; T # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; T # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EB9 ; T # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; T # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +1885..1886 ; T # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; T # Mn BUGINESE VOWEL SIGN AE +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; T # Me COMBINING PARENTHESES OVERLAY +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB..1BAD ; T # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1DC0..1DF9 ; T # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; T # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69E..A69F ; T # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A8C4..A8C5 ; T # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A8FF ; T # Mn DEVANAGARI VOWEL SIGN AY +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC ; T # Mn JAVANESE VOWEL SIGN PEPET +A9E5 ; T # Mn MYANMAR SIGN SHAN SAW +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AA7C ; T # Mn MYANMAR SIGN TAI LAING TONE-2 +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE2F ; T # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +102E0 ; T # Mn COPTIC EPACT THOUSANDS MARK +10376..1037A ; T # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +10AE5..10AE6 ; T # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +10D24..10D27 ; T # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10F46..10F50 ; T # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +1107F..11081 ; T # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11173 ; T # Mn MAHAJANI SIGN NUKTA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +111C9..111CC ; T # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK +1122F..11231 ; T # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11234 ; T # Mn KHOJKI SIGN ANUSVARA +11236..11237 ; T # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; T # Mn KHOJKI SIGN SUKUN +112DF ; T # Mn KHUDAWADI SIGN ANUSVARA +112E3..112EA ; T # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +11300..11301 ; T # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU +1133B..1133C ; T # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA +11340 ; T # Mn GRANTHA VOWEL SIGN II +11366..1136C ; T # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; T # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11438..1143F ; T # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; T # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; T # Mn NEWA SIGN NUKTA +1145E ; T # Mn NEWA SANDHI MARK +114B3..114B8 ; T # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114BA ; T # Mn TIRHUTA VOWEL SIGN SHORT E +114BF..114C0 ; T # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C2..114C3 ; T # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +115B2..115B5 ; T # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115BC..115BD ; T # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BF..115C0 ; T # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +115DC..115DD ; T # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU +11633..1163A ; T # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163D ; T # Mn MODI SIGN ANUSVARA +1163F..11640 ; T # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +1171D..1171F ; T # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA +11722..11725 ; T # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU +11727..1172B ; T # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +1182F..11837 ; T # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA +11839..1183A ; T # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA +11A01..11A0A ; T # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; T # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; T # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; T # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; T # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; T # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; T # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; T # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C30..11C36 ; T # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; T # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; T # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; T # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; T # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; T # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; T # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; T # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; T # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; T # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; T # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; T # Mn MASARAM GONDI RA-KARA +11D90..11D91 ; T # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D95 ; T # Mn GUNJALA GONDI SIGN ANUSVARA +11D97 ; T # Mn GUNJALA GONDI VIRAMA +11EF3..11EF4 ; T # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U +16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +1BC9D..1BC9E ; T # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1BCA0..1BCA3 ; T # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1DA00..1DA36 ; T # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN +1DA3B..1DA6C ; T # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT +1DA75 ; T # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS +1DA84 ; T # Mn SIGNWRITING LOCATION HEAD NECK +1DA9B..1DA9F ; T # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 +1DAA1..1DAAF ; T # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; T # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; T # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; T # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; T # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; T # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; T # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 1953 + +# EOF diff --git a/data/12.0.0-derived-joining-type.txt b/data/12.0.0-derived-joining-type.txt new file mode 100644 index 0000000..6fc7cf9 --- /dev/null +++ b/data/12.0.0-derived-joining-type.txt @@ -0,0 +1,523 @@ +# DerivedJoiningType-12.0.0.txt +# Date: 2019-01-22, 08:18:28 GMT +# © 2019 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +180A ; C # Po MONGOLIAN NIRUGU +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 4 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0848 ; D # Lo MANDAIC LETTER ATT +084A..0853 ; D # Lo [10] MANDAIC LETTER AK..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +0860 ; D # Lo SYRIAC LETTER MALAYALAM NGA +0862..0865 ; D # Lo [4] SYRIAC LETTER MALAYALAM NYA..SYRIAC LETTER MALAYALAM NNNA +0868 ; D # Lo SYRIAC LETTER MALAYALAM LLA +08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE +08B3..08B4 ; D # Lo [2] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08B8 ; D # Lo [3] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER TEH WITH SMALL TEH ABOVE +08BA..08BD ; D # Lo [4] ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE..ARABIC LETTER AFRICAN NOON +1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER +1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1878 ; D # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS +1887..18A8 ; D # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; D # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA +10AC0..10AC4 ; D # Lo [5] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER GHIMEL +10AD3..10AD6 ; D # Lo [4] MANICHAEAN LETTER LAMEDH..MANICHAEAN LETTER MEM +10AD8..10ADC ; D # Lo [5] MANICHAEAN LETTER SAMEKH..MANICHAEAN LETTER FE +10ADE..10AE0 ; D # Lo [3] MANICHAEAN LETTER QOPH..MANICHAEAN LETTER QHOPH +10AEB..10AEE ; D # No [4] MANICHAEAN NUMBER ONE..MANICHAEAN NUMBER TWENTY +10B80 ; D # Lo PSALTER PAHLAVI LETTER ALEPH +10B82 ; D # Lo PSALTER PAHLAVI LETTER GIMEL +10B86..10B88 ; D # Lo [3] PSALTER PAHLAVI LETTER ZAYIN..PSALTER PAHLAVI LETTER YODH +10B8A..10B8B ; D # Lo [2] PSALTER PAHLAVI LETTER LAMEDH..PSALTER PAHLAVI LETTER MEM-QOPH +10B8D ; D # Lo PSALTER PAHLAVI LETTER SAMEKH +10B90 ; D # Lo PSALTER PAHLAVI LETTER SHIN +10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY +10D01..10D21 ; D # Lo [33] HANIFI ROHINGYA LETTER BA..HANIFI ROHINGYA VOWEL O +10D23 ; D # Lo HANIFI ROHINGYA MARK NA KHONNA +10F30..10F32 ; D # Lo [3] SOGDIAN LETTER ALEPH..SOGDIAN LETTER GIMEL +10F34..10F44 ; D # Lo [17] SOGDIAN LETTER WAW..SOGDIAN LETTER LESH +10F51..10F53 ; D # No [3] SOGDIAN NUMBER ONE..SOGDIAN NUMBER TWENTY +1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA + +# Total code points: 565 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846..0847 ; R # Lo [2] MANDAIC LETTER AZ..MANDAIC LETTER IT +0849 ; R # Lo MANDAIC LETTER AKSA +0854 ; R # Lo MANDAIC LETTER ASH +0867 ; R # Lo SYRIAC LETTER MALAYALAM RA +0869..086A ; R # Lo [2] SYRIAC LETTER MALAYALAM LLLA..SYRIAC LETTER MALAYALAM SSA +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH +08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW +08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE +08B9 ; R # Lo ARABIC LETTER REH WITH SMALL NOON ABOVE +10AC5 ; R # Lo MANICHAEAN LETTER DALETH +10AC7 ; R # Lo MANICHAEAN LETTER WAW +10AC9..10ACA ; R # Lo [2] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER ZHAYIN +10ACE..10AD2 ; R # Lo [5] MANICHAEAN LETTER TETH..MANICHAEAN LETTER KHAPH +10ADD ; R # Lo MANICHAEAN LETTER SADHE +10AE1 ; R # Lo MANICHAEAN LETTER RESH +10AE4 ; R # Lo MANICHAEAN LETTER TAW +10AEF ; R # No MANICHAEAN NUMBER ONE HUNDRED +10B81 ; R # Lo PSALTER PAHLAVI LETTER BETH +10B83..10B85 ; R # Lo [3] PSALTER PAHLAVI LETTER DALETH..PSALTER PAHLAVI LETTER WAW-AYIN-RESH +10B89 ; R # Lo PSALTER PAHLAVI LETTER KAPH +10B8C ; R # Lo PSALTER PAHLAVI LETTER NUN +10B8E..10B8F ; R # Lo [2] PSALTER PAHLAVI LETTER PE..PSALTER PAHLAVI LETTER SADHE +10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW +10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR +10D22 ; R # Lo HANIFI ROHINGYA MARK SAKIN +10F33 ; R # Lo SOGDIAN LETTER HE +10F54 ; R # No SOGDIAN NUMBER ONE HUNDRED + +# Total code points: 118 + +# ================================================ + +# Joining_Type=Left_Joining + +A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA +10ACD ; L # Lo MANICHAEAN LETTER HETH +10AD7 ; L # Lo MANICHAEAN LETTER NUN +10D00 ; L # Lo HANIFI ROHINGYA LETTER A + +# Total code points: 4 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; T # Cf ARABIC LETTER MARK +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +07FD ; T # Mn NKO DANTAYALAN +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08D3..08E1 ; T # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +08E3..0902 ; T # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09FE ; T # Mn BENGALI SANDHI MARK +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; T # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B56 ; T # Mn ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C00 ; T # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C04 ; T # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C81 ; T # Mn KANNADA SIGN CANDRABINDU +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D00..0D01 ; T # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; T # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EBC ; T # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +1885..1886 ; T # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; T # Mn BUGINESE VOWEL SIGN AE +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; T # Me COMBINING PARENTHESES OVERLAY +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB..1BAD ; T # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1DC0..1DF9 ; T # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; T # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69E..A69F ; T # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A8C4..A8C5 ; T # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A8FF ; T # Mn DEVANAGARI VOWEL SIGN AY +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC..A9BD ; T # Mn [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET +A9E5 ; T # Mn MYANMAR SIGN SHAN SAW +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AA7C ; T # Mn MYANMAR SIGN TAI LAING TONE-2 +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE2F ; T # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +102E0 ; T # Mn COPTIC EPACT THOUSANDS MARK +10376..1037A ; T # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +10AE5..10AE6 ; T # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +10D24..10D27 ; T # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10F46..10F50 ; T # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +1107F..11081 ; T # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11173 ; T # Mn MAHAJANI SIGN NUKTA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +111C9..111CC ; T # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK +1122F..11231 ; T # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11234 ; T # Mn KHOJKI SIGN ANUSVARA +11236..11237 ; T # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; T # Mn KHOJKI SIGN SUKUN +112DF ; T # Mn KHUDAWADI SIGN ANUSVARA +112E3..112EA ; T # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +11300..11301 ; T # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU +1133B..1133C ; T # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA +11340 ; T # Mn GRANTHA VOWEL SIGN II +11366..1136C ; T # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; T # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11438..1143F ; T # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; T # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; T # Mn NEWA SIGN NUKTA +1145E ; T # Mn NEWA SANDHI MARK +114B3..114B8 ; T # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114BA ; T # Mn TIRHUTA VOWEL SIGN SHORT E +114BF..114C0 ; T # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C2..114C3 ; T # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +115B2..115B5 ; T # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115BC..115BD ; T # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BF..115C0 ; T # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +115DC..115DD ; T # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU +11633..1163A ; T # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163D ; T # Mn MODI SIGN ANUSVARA +1163F..11640 ; T # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +1171D..1171F ; T # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA +11722..11725 ; T # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU +11727..1172B ; T # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +1182F..11837 ; T # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA +11839..1183A ; T # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA +119D4..119D7 ; T # Mn [4] NANDINAGARI VOWEL SIGN U..NANDINAGARI VOWEL SIGN VOCALIC RR +119DA..119DB ; T # Mn [2] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN AI +119E0 ; T # Mn NANDINAGARI SIGN VIRAMA +11A01..11A0A ; T # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; T # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; T # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; T # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; T # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; T # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; T # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; T # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C30..11C36 ; T # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; T # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; T # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; T # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; T # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; T # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; T # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; T # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; T # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; T # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; T # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; T # Mn MASARAM GONDI RA-KARA +11D90..11D91 ; T # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D95 ; T # Mn GUNJALA GONDI SIGN ANUSVARA +11D97 ; T # Mn GUNJALA GONDI VIRAMA +11EF3..11EF4 ; T # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U +13430..13438 ; T # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT +16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16F4F ; T # Mn MIAO SIGN CONSONANT MODIFIER BAR +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +1BC9D..1BC9E ; T # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1BCA0..1BCA3 ; T # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1DA00..1DA36 ; T # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN +1DA3B..1DA6C ; T # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT +1DA75 ; T # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS +1DA84 ; T # Mn SIGNWRITING LOCATION HEAD NECK +1DA9B..1DA9F ; T # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 +1DAA1..1DAAF ; T # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; T # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; T # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; T # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; T # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; T # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E130..1E136 ; T # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2EC..1E2EF ; T # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI +1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; T # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1E94B ; T # Lm ADLAM NASALIZATION MARK +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 1984 + +# EOF diff --git a/data/12.1.0-derived-joining-type.txt b/data/12.1.0-derived-joining-type.txt new file mode 100644 index 0000000..d07525c --- /dev/null +++ b/data/12.1.0-derived-joining-type.txt @@ -0,0 +1,523 @@ +# DerivedJoiningType-12.1.0.txt +# Date: 2019-03-10, 10:53:08 GMT +# © 2019 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +180A ; C # Po MONGOLIAN NIRUGU +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 4 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0848 ; D # Lo MANDAIC LETTER ATT +084A..0853 ; D # Lo [10] MANDAIC LETTER AK..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +0860 ; D # Lo SYRIAC LETTER MALAYALAM NGA +0862..0865 ; D # Lo [4] SYRIAC LETTER MALAYALAM NYA..SYRIAC LETTER MALAYALAM NNNA +0868 ; D # Lo SYRIAC LETTER MALAYALAM LLA +08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE +08B3..08B4 ; D # Lo [2] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08B8 ; D # Lo [3] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER TEH WITH SMALL TEH ABOVE +08BA..08BD ; D # Lo [4] ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE..ARABIC LETTER AFRICAN NOON +1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER +1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1878 ; D # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS +1887..18A8 ; D # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; D # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA +10AC0..10AC4 ; D # Lo [5] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER GHIMEL +10AD3..10AD6 ; D # Lo [4] MANICHAEAN LETTER LAMEDH..MANICHAEAN LETTER MEM +10AD8..10ADC ; D # Lo [5] MANICHAEAN LETTER SAMEKH..MANICHAEAN LETTER FE +10ADE..10AE0 ; D # Lo [3] MANICHAEAN LETTER QOPH..MANICHAEAN LETTER QHOPH +10AEB..10AEE ; D # No [4] MANICHAEAN NUMBER ONE..MANICHAEAN NUMBER TWENTY +10B80 ; D # Lo PSALTER PAHLAVI LETTER ALEPH +10B82 ; D # Lo PSALTER PAHLAVI LETTER GIMEL +10B86..10B88 ; D # Lo [3] PSALTER PAHLAVI LETTER ZAYIN..PSALTER PAHLAVI LETTER YODH +10B8A..10B8B ; D # Lo [2] PSALTER PAHLAVI LETTER LAMEDH..PSALTER PAHLAVI LETTER MEM-QOPH +10B8D ; D # Lo PSALTER PAHLAVI LETTER SAMEKH +10B90 ; D # Lo PSALTER PAHLAVI LETTER SHIN +10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY +10D01..10D21 ; D # Lo [33] HANIFI ROHINGYA LETTER BA..HANIFI ROHINGYA VOWEL O +10D23 ; D # Lo HANIFI ROHINGYA MARK NA KHONNA +10F30..10F32 ; D # Lo [3] SOGDIAN LETTER ALEPH..SOGDIAN LETTER GIMEL +10F34..10F44 ; D # Lo [17] SOGDIAN LETTER WAW..SOGDIAN LETTER LESH +10F51..10F53 ; D # No [3] SOGDIAN NUMBER ONE..SOGDIAN NUMBER TWENTY +1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA + +# Total code points: 565 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846..0847 ; R # Lo [2] MANDAIC LETTER AZ..MANDAIC LETTER IT +0849 ; R # Lo MANDAIC LETTER AKSA +0854 ; R # Lo MANDAIC LETTER ASH +0867 ; R # Lo SYRIAC LETTER MALAYALAM RA +0869..086A ; R # Lo [2] SYRIAC LETTER MALAYALAM LLLA..SYRIAC LETTER MALAYALAM SSA +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH +08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW +08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE +08B9 ; R # Lo ARABIC LETTER REH WITH SMALL NOON ABOVE +10AC5 ; R # Lo MANICHAEAN LETTER DALETH +10AC7 ; R # Lo MANICHAEAN LETTER WAW +10AC9..10ACA ; R # Lo [2] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER ZHAYIN +10ACE..10AD2 ; R # Lo [5] MANICHAEAN LETTER TETH..MANICHAEAN LETTER KHAPH +10ADD ; R # Lo MANICHAEAN LETTER SADHE +10AE1 ; R # Lo MANICHAEAN LETTER RESH +10AE4 ; R # Lo MANICHAEAN LETTER TAW +10AEF ; R # No MANICHAEAN NUMBER ONE HUNDRED +10B81 ; R # Lo PSALTER PAHLAVI LETTER BETH +10B83..10B85 ; R # Lo [3] PSALTER PAHLAVI LETTER DALETH..PSALTER PAHLAVI LETTER WAW-AYIN-RESH +10B89 ; R # Lo PSALTER PAHLAVI LETTER KAPH +10B8C ; R # Lo PSALTER PAHLAVI LETTER NUN +10B8E..10B8F ; R # Lo [2] PSALTER PAHLAVI LETTER PE..PSALTER PAHLAVI LETTER SADHE +10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW +10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR +10D22 ; R # Lo HANIFI ROHINGYA MARK SAKIN +10F33 ; R # Lo SOGDIAN LETTER HE +10F54 ; R # No SOGDIAN NUMBER ONE HUNDRED + +# Total code points: 118 + +# ================================================ + +# Joining_Type=Left_Joining + +A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA +10ACD ; L # Lo MANICHAEAN LETTER HETH +10AD7 ; L # Lo MANICHAEAN LETTER NUN +10D00 ; L # Lo HANIFI ROHINGYA LETTER A + +# Total code points: 4 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; T # Cf ARABIC LETTER MARK +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +07FD ; T # Mn NKO DANTAYALAN +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08D3..08E1 ; T # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +08E3..0902 ; T # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09FE ; T # Mn BENGALI SANDHI MARK +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; T # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B56 ; T # Mn ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C00 ; T # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C04 ; T # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C81 ; T # Mn KANNADA SIGN CANDRABINDU +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D00..0D01 ; T # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; T # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EBC ; T # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +1885..1886 ; T # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; T # Mn BUGINESE VOWEL SIGN AE +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; T # Me COMBINING PARENTHESES OVERLAY +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB..1BAD ; T # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1DC0..1DF9 ; T # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; T # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69E..A69F ; T # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A8C4..A8C5 ; T # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A8FF ; T # Mn DEVANAGARI VOWEL SIGN AY +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC..A9BD ; T # Mn [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET +A9E5 ; T # Mn MYANMAR SIGN SHAN SAW +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AA7C ; T # Mn MYANMAR SIGN TAI LAING TONE-2 +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE2F ; T # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +102E0 ; T # Mn COPTIC EPACT THOUSANDS MARK +10376..1037A ; T # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +10AE5..10AE6 ; T # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +10D24..10D27 ; T # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10F46..10F50 ; T # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +1107F..11081 ; T # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11173 ; T # Mn MAHAJANI SIGN NUKTA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +111C9..111CC ; T # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK +1122F..11231 ; T # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11234 ; T # Mn KHOJKI SIGN ANUSVARA +11236..11237 ; T # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; T # Mn KHOJKI SIGN SUKUN +112DF ; T # Mn KHUDAWADI SIGN ANUSVARA +112E3..112EA ; T # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +11300..11301 ; T # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU +1133B..1133C ; T # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA +11340 ; T # Mn GRANTHA VOWEL SIGN II +11366..1136C ; T # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; T # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11438..1143F ; T # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; T # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; T # Mn NEWA SIGN NUKTA +1145E ; T # Mn NEWA SANDHI MARK +114B3..114B8 ; T # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114BA ; T # Mn TIRHUTA VOWEL SIGN SHORT E +114BF..114C0 ; T # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C2..114C3 ; T # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +115B2..115B5 ; T # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115BC..115BD ; T # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BF..115C0 ; T # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +115DC..115DD ; T # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU +11633..1163A ; T # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163D ; T # Mn MODI SIGN ANUSVARA +1163F..11640 ; T # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +1171D..1171F ; T # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA +11722..11725 ; T # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU +11727..1172B ; T # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +1182F..11837 ; T # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA +11839..1183A ; T # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA +119D4..119D7 ; T # Mn [4] NANDINAGARI VOWEL SIGN U..NANDINAGARI VOWEL SIGN VOCALIC RR +119DA..119DB ; T # Mn [2] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN AI +119E0 ; T # Mn NANDINAGARI SIGN VIRAMA +11A01..11A0A ; T # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; T # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; T # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; T # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; T # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; T # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; T # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; T # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C30..11C36 ; T # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; T # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; T # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; T # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; T # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; T # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; T # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; T # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; T # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; T # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; T # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; T # Mn MASARAM GONDI RA-KARA +11D90..11D91 ; T # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D95 ; T # Mn GUNJALA GONDI SIGN ANUSVARA +11D97 ; T # Mn GUNJALA GONDI VIRAMA +11EF3..11EF4 ; T # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U +13430..13438 ; T # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT +16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16F4F ; T # Mn MIAO SIGN CONSONANT MODIFIER BAR +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +1BC9D..1BC9E ; T # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1BCA0..1BCA3 ; T # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1DA00..1DA36 ; T # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN +1DA3B..1DA6C ; T # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT +1DA75 ; T # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS +1DA84 ; T # Mn SIGNWRITING LOCATION HEAD NECK +1DA9B..1DA9F ; T # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 +1DAA1..1DAAF ; T # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; T # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; T # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; T # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; T # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; T # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E130..1E136 ; T # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2EC..1E2EF ; T # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI +1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; T # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1E94B ; T # Lm ADLAM NASALIZATION MARK +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 1984 + +# EOF diff --git a/data/13.0.0-derived-joining-type.txt b/data/13.0.0-derived-joining-type.txt new file mode 100644 index 0000000..57229cc --- /dev/null +++ b/data/13.0.0-derived-joining-type.txt @@ -0,0 +1,547 @@ +# DerivedJoiningType-13.0.0.txt +# Date: 2020-01-21, 07:36:28 GMT +# © 2020 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +180A ; C # Po MONGOLIAN NIRUGU +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 4 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0848 ; D # Lo MANDAIC LETTER ATT +084A..0853 ; D # Lo [10] MANDAIC LETTER AK..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +0860 ; D # Lo SYRIAC LETTER MALAYALAM NGA +0862..0865 ; D # Lo [4] SYRIAC LETTER MALAYALAM NYA..SYRIAC LETTER MALAYALAM NNNA +0868 ; D # Lo SYRIAC LETTER MALAYALAM LLA +08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE +08B3..08B4 ; D # Lo [2] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08B8 ; D # Lo [3] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER TEH WITH SMALL TEH ABOVE +08BA..08C7 ; D # Lo [14] ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE..ARABIC LETTER LAM WITH SMALL ARABIC LETTER TAH ABOVE +1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER +1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1878 ; D # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS +1887..18A8 ; D # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; D # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA +10AC0..10AC4 ; D # Lo [5] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER GHIMEL +10AD3..10AD6 ; D # Lo [4] MANICHAEAN LETTER LAMEDH..MANICHAEAN LETTER MEM +10AD8..10ADC ; D # Lo [5] MANICHAEAN LETTER SAMEKH..MANICHAEAN LETTER FE +10ADE..10AE0 ; D # Lo [3] MANICHAEAN LETTER QOPH..MANICHAEAN LETTER QHOPH +10AEB..10AEE ; D # No [4] MANICHAEAN NUMBER ONE..MANICHAEAN NUMBER TWENTY +10B80 ; D # Lo PSALTER PAHLAVI LETTER ALEPH +10B82 ; D # Lo PSALTER PAHLAVI LETTER GIMEL +10B86..10B88 ; D # Lo [3] PSALTER PAHLAVI LETTER ZAYIN..PSALTER PAHLAVI LETTER YODH +10B8A..10B8B ; D # Lo [2] PSALTER PAHLAVI LETTER LAMEDH..PSALTER PAHLAVI LETTER MEM-QOPH +10B8D ; D # Lo PSALTER PAHLAVI LETTER SAMEKH +10B90 ; D # Lo PSALTER PAHLAVI LETTER SHIN +10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY +10D01..10D21 ; D # Lo [33] HANIFI ROHINGYA LETTER BA..HANIFI ROHINGYA VOWEL O +10D23 ; D # Lo HANIFI ROHINGYA MARK NA KHONNA +10F30..10F32 ; D # Lo [3] SOGDIAN LETTER ALEPH..SOGDIAN LETTER GIMEL +10F34..10F44 ; D # Lo [17] SOGDIAN LETTER WAW..SOGDIAN LETTER LESH +10F51..10F53 ; D # No [3] SOGDIAN NUMBER ONE..SOGDIAN NUMBER TWENTY +10FB0 ; D # Lo CHORASMIAN LETTER ALEPH +10FB2..10FB3 ; D # Lo [2] CHORASMIAN LETTER BETH..CHORASMIAN LETTER GIMEL +10FB8 ; D # Lo CHORASMIAN LETTER ZAYIN +10FBB..10FBC ; D # Lo [2] CHORASMIAN LETTER KAPH..CHORASMIAN LETTER LAMEDH +10FBE..10FBF ; D # Lo [2] CHORASMIAN LETTER NUN..CHORASMIAN LETTER SAMEKH +10FC1 ; D # Lo CHORASMIAN LETTER PE +10FC4 ; D # Lo CHORASMIAN LETTER TAW +10FCA ; D # No CHORASMIAN NUMBER TWENTY +1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA + +# Total code points: 586 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846..0847 ; R # Lo [2] MANDAIC LETTER AZ..MANDAIC LETTER IT +0849 ; R # Lo MANDAIC LETTER AKSA +0854 ; R # Lo MANDAIC LETTER ASH +0856..0858 ; R # Lo [3] MANDAIC LETTER DUSHENNA..MANDAIC LETTER AIN +0867 ; R # Lo SYRIAC LETTER MALAYALAM RA +0869..086A ; R # Lo [2] SYRIAC LETTER MALAYALAM LLLA..SYRIAC LETTER MALAYALAM SSA +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH +08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW +08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE +08B9 ; R # Lo ARABIC LETTER REH WITH SMALL NOON ABOVE +10AC5 ; R # Lo MANICHAEAN LETTER DALETH +10AC7 ; R # Lo MANICHAEAN LETTER WAW +10AC9..10ACA ; R # Lo [2] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER ZHAYIN +10ACE..10AD2 ; R # Lo [5] MANICHAEAN LETTER TETH..MANICHAEAN LETTER KHAPH +10ADD ; R # Lo MANICHAEAN LETTER SADHE +10AE1 ; R # Lo MANICHAEAN LETTER RESH +10AE4 ; R # Lo MANICHAEAN LETTER TAW +10AEF ; R # No MANICHAEAN NUMBER ONE HUNDRED +10B81 ; R # Lo PSALTER PAHLAVI LETTER BETH +10B83..10B85 ; R # Lo [3] PSALTER PAHLAVI LETTER DALETH..PSALTER PAHLAVI LETTER WAW-AYIN-RESH +10B89 ; R # Lo PSALTER PAHLAVI LETTER KAPH +10B8C ; R # Lo PSALTER PAHLAVI LETTER NUN +10B8E..10B8F ; R # Lo [2] PSALTER PAHLAVI LETTER PE..PSALTER PAHLAVI LETTER SADHE +10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW +10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR +10D22 ; R # Lo HANIFI ROHINGYA MARK SAKIN +10F33 ; R # Lo SOGDIAN LETTER HE +10F54 ; R # No SOGDIAN NUMBER ONE HUNDRED +10FB4..10FB6 ; R # Lo [3] CHORASMIAN LETTER DALETH..CHORASMIAN LETTER WAW +10FB9..10FBA ; R # Lo [2] CHORASMIAN LETTER HETH..CHORASMIAN LETTER YODH +10FBD ; R # Lo CHORASMIAN LETTER MEM +10FC2..10FC3 ; R # Lo [2] CHORASMIAN LETTER RESH..CHORASMIAN LETTER SHIN +10FC9 ; R # No CHORASMIAN NUMBER TEN + +# Total code points: 130 + +# ================================================ + +# Joining_Type=Left_Joining + +A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA +10ACD ; L # Lo MANICHAEAN LETTER HETH +10AD7 ; L # Lo MANICHAEAN LETTER NUN +10D00 ; L # Lo HANIFI ROHINGYA LETTER A +10FCB ; L # No CHORASMIAN NUMBER ONE HUNDRED + +# Total code points: 5 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; T # Cf ARABIC LETTER MARK +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +07FD ; T # Mn NKO DANTAYALAN +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08D3..08E1 ; T # Mn [15] ARABIC SMALL LOW WAW..ARABIC SMALL HIGH SIGN SAFHA +08E3..0902 ; T # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09FE ; T # Mn BENGALI SANDHI MARK +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; T # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B55..0B56 ; T # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C00 ; T # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C04 ; T # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C81 ; T # Mn KANNADA SIGN CANDRABINDU +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D00..0D01 ; T # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; T # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0D81 ; T # Mn SINHALA SIGN CANDRABINDU +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EBC ; T # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +1885..1886 ; T # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; T # Mn BUGINESE VOWEL SIGN AE +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; T # Me COMBINING PARENTHESES OVERLAY +1ABF..1AC0 ; T # Mn [2] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER TURNED W BELOW +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB..1BAD ; T # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1DC0..1DF9 ; T # Mn [58] COMBINING DOTTED GRAVE ACCENT..COMBINING WIDE INVERTED BRIDGE BELOW +1DFB..1DFF ; T # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69E..A69F ; T # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A82C ; T # Mn SYLOTI NAGRI SIGN ALTERNATE HASANTA +A8C4..A8C5 ; T # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A8FF ; T # Mn DEVANAGARI VOWEL SIGN AY +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC..A9BD ; T # Mn [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET +A9E5 ; T # Mn MYANMAR SIGN SHAN SAW +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AA7C ; T # Mn MYANMAR SIGN TAI LAING TONE-2 +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE2F ; T # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +102E0 ; T # Mn COPTIC EPACT THOUSANDS MARK +10376..1037A ; T # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +10AE5..10AE6 ; T # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +10D24..10D27 ; T # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10EAB..10EAC ; T # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK +10F46..10F50 ; T # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +1107F..11081 ; T # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11173 ; T # Mn MAHAJANI SIGN NUKTA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +111C9..111CC ; T # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK +111CF ; T # Mn SHARADA SIGN INVERTED CANDRABINDU +1122F..11231 ; T # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11234 ; T # Mn KHOJKI SIGN ANUSVARA +11236..11237 ; T # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; T # Mn KHOJKI SIGN SUKUN +112DF ; T # Mn KHUDAWADI SIGN ANUSVARA +112E3..112EA ; T # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +11300..11301 ; T # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU +1133B..1133C ; T # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA +11340 ; T # Mn GRANTHA VOWEL SIGN II +11366..1136C ; T # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; T # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11438..1143F ; T # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; T # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; T # Mn NEWA SIGN NUKTA +1145E ; T # Mn NEWA SANDHI MARK +114B3..114B8 ; T # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114BA ; T # Mn TIRHUTA VOWEL SIGN SHORT E +114BF..114C0 ; T # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C2..114C3 ; T # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +115B2..115B5 ; T # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115BC..115BD ; T # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BF..115C0 ; T # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +115DC..115DD ; T # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU +11633..1163A ; T # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163D ; T # Mn MODI SIGN ANUSVARA +1163F..11640 ; T # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +1171D..1171F ; T # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA +11722..11725 ; T # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU +11727..1172B ; T # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +1182F..11837 ; T # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA +11839..1183A ; T # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA +1193B..1193C ; T # Mn [2] DIVES AKURU SIGN ANUSVARA..DIVES AKURU SIGN CANDRABINDU +1193E ; T # Mn DIVES AKURU VIRAMA +11943 ; T # Mn DIVES AKURU SIGN NUKTA +119D4..119D7 ; T # Mn [4] NANDINAGARI VOWEL SIGN U..NANDINAGARI VOWEL SIGN VOCALIC RR +119DA..119DB ; T # Mn [2] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN AI +119E0 ; T # Mn NANDINAGARI SIGN VIRAMA +11A01..11A0A ; T # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; T # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; T # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; T # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; T # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; T # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; T # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; T # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C30..11C36 ; T # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; T # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; T # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; T # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; T # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; T # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; T # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; T # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; T # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; T # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; T # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; T # Mn MASARAM GONDI RA-KARA +11D90..11D91 ; T # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D95 ; T # Mn GUNJALA GONDI SIGN ANUSVARA +11D97 ; T # Mn GUNJALA GONDI VIRAMA +11EF3..11EF4 ; T # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U +13430..13438 ; T # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT +16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16F4F ; T # Mn MIAO SIGN CONSONANT MODIFIER BAR +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +16FE4 ; T # Mn KHITAN SMALL SCRIPT FILLER +1BC9D..1BC9E ; T # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1BCA0..1BCA3 ; T # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1DA00..1DA36 ; T # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN +1DA3B..1DA6C ; T # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT +1DA75 ; T # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS +1DA84 ; T # Mn SIGNWRITING LOCATION HEAD NECK +1DA9B..1DA9F ; T # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 +1DAA1..1DAAF ; T # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; T # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; T # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; T # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; T # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; T # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E130..1E136 ; T # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2EC..1E2EF ; T # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI +1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; T # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1E94B ; T # Lm ADLAM NASALIZATION MARK +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 1997 + +# EOF diff --git a/data/14.0.0-derived-joining-type.txt b/data/14.0.0-derived-joining-type.txt new file mode 100644 index 0000000..7c36d02 --- /dev/null +++ b/data/14.0.0-derived-joining-type.txt @@ -0,0 +1,563 @@ +# DerivedJoiningType-14.0.0.txt +# Date: 2021-05-28, 21:49:06 GMT +# © 2021 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +0883..0885 ; C # Lo [3] ARABIC TATWEEL WITH OVERSTRUCK HAMZA..ARABIC TATWEEL WITH TWO DOTS BELOW +180A ; C # Po MONGOLIAN NIRUGU +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 7 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0848 ; D # Lo MANDAIC LETTER ATT +084A..0853 ; D # Lo [10] MANDAIC LETTER AK..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +0860 ; D # Lo SYRIAC LETTER MALAYALAM NGA +0862..0865 ; D # Lo [4] SYRIAC LETTER MALAYALAM NYA..SYRIAC LETTER MALAYALAM NNNA +0868 ; D # Lo SYRIAC LETTER MALAYALAM LLA +0886 ; D # Lo ARABIC LETTER THIN YEH +0889..088D ; D # Lo [5] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER KEHEH WITH TWO DOTS VERTICALLY BELOW +08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE +08B3..08B8 ; D # Lo [6] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER TEH WITH SMALL TEH ABOVE +08BA..08C8 ; D # Lo [15] ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE..ARABIC LETTER GRAF +1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER +1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1878 ; D # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS +1887..18A8 ; D # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; D # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA +10AC0..10AC4 ; D # Lo [5] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER GHIMEL +10AD3..10AD6 ; D # Lo [4] MANICHAEAN LETTER LAMEDH..MANICHAEAN LETTER MEM +10AD8..10ADC ; D # Lo [5] MANICHAEAN LETTER SAMEKH..MANICHAEAN LETTER FE +10ADE..10AE0 ; D # Lo [3] MANICHAEAN LETTER QOPH..MANICHAEAN LETTER QHOPH +10AEB..10AEE ; D # No [4] MANICHAEAN NUMBER ONE..MANICHAEAN NUMBER TWENTY +10B80 ; D # Lo PSALTER PAHLAVI LETTER ALEPH +10B82 ; D # Lo PSALTER PAHLAVI LETTER GIMEL +10B86..10B88 ; D # Lo [3] PSALTER PAHLAVI LETTER ZAYIN..PSALTER PAHLAVI LETTER YODH +10B8A..10B8B ; D # Lo [2] PSALTER PAHLAVI LETTER LAMEDH..PSALTER PAHLAVI LETTER MEM-QOPH +10B8D ; D # Lo PSALTER PAHLAVI LETTER SAMEKH +10B90 ; D # Lo PSALTER PAHLAVI LETTER SHIN +10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY +10D01..10D21 ; D # Lo [33] HANIFI ROHINGYA LETTER BA..HANIFI ROHINGYA VOWEL O +10D23 ; D # Lo HANIFI ROHINGYA MARK NA KHONNA +10F30..10F32 ; D # Lo [3] SOGDIAN LETTER ALEPH..SOGDIAN LETTER GIMEL +10F34..10F44 ; D # Lo [17] SOGDIAN LETTER WAW..SOGDIAN LETTER LESH +10F51..10F53 ; D # No [3] SOGDIAN NUMBER ONE..SOGDIAN NUMBER TWENTY +10F70..10F73 ; D # Lo [4] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER WAW +10F76..10F81 ; D # Lo [12] OLD UYGHUR LETTER YODH..OLD UYGHUR LETTER LESH +10FB0 ; D # Lo CHORASMIAN LETTER ALEPH +10FB2..10FB3 ; D # Lo [2] CHORASMIAN LETTER BETH..CHORASMIAN LETTER GIMEL +10FB8 ; D # Lo CHORASMIAN LETTER ZAYIN +10FBB..10FBC ; D # Lo [2] CHORASMIAN LETTER KAPH..CHORASMIAN LETTER LAMEDH +10FBE..10FBF ; D # Lo [2] CHORASMIAN LETTER NUN..CHORASMIAN LETTER SAMEKH +10FC1 ; D # Lo CHORASMIAN LETTER PE +10FC4 ; D # Lo CHORASMIAN LETTER TAW +10FCA ; D # No CHORASMIAN NUMBER TWENTY +1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA + +# Total code points: 610 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846..0847 ; R # Lo [2] MANDAIC LETTER AZ..MANDAIC LETTER IT +0849 ; R # Lo MANDAIC LETTER AKSA +0854 ; R # Lo MANDAIC LETTER ASH +0856..0858 ; R # Lo [3] MANDAIC LETTER DUSHENNA..MANDAIC LETTER AIN +0867 ; R # Lo SYRIAC LETTER MALAYALAM RA +0869..086A ; R # Lo [2] SYRIAC LETTER MALAYALAM LLLA..SYRIAC LETTER MALAYALAM SSA +0870..0882 ; R # Lo [19] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC LETTER ALEF WITH ATTACHED LEFT HAMZA +088E ; R # Lo ARABIC VERTICAL TAIL +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH +08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW +08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE +08B9 ; R # Lo ARABIC LETTER REH WITH SMALL NOON ABOVE +10AC5 ; R # Lo MANICHAEAN LETTER DALETH +10AC7 ; R # Lo MANICHAEAN LETTER WAW +10AC9..10ACA ; R # Lo [2] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER ZHAYIN +10ACE..10AD2 ; R # Lo [5] MANICHAEAN LETTER TETH..MANICHAEAN LETTER KHAPH +10ADD ; R # Lo MANICHAEAN LETTER SADHE +10AE1 ; R # Lo MANICHAEAN LETTER RESH +10AE4 ; R # Lo MANICHAEAN LETTER TAW +10AEF ; R # No MANICHAEAN NUMBER ONE HUNDRED +10B81 ; R # Lo PSALTER PAHLAVI LETTER BETH +10B83..10B85 ; R # Lo [3] PSALTER PAHLAVI LETTER DALETH..PSALTER PAHLAVI LETTER WAW-AYIN-RESH +10B89 ; R # Lo PSALTER PAHLAVI LETTER KAPH +10B8C ; R # Lo PSALTER PAHLAVI LETTER NUN +10B8E..10B8F ; R # Lo [2] PSALTER PAHLAVI LETTER PE..PSALTER PAHLAVI LETTER SADHE +10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW +10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR +10D22 ; R # Lo HANIFI ROHINGYA MARK SAKIN +10F33 ; R # Lo SOGDIAN LETTER HE +10F54 ; R # No SOGDIAN NUMBER ONE HUNDRED +10F74..10F75 ; R # Lo [2] OLD UYGHUR LETTER ZAYIN..OLD UYGHUR LETTER FINAL HETH +10FB4..10FB6 ; R # Lo [3] CHORASMIAN LETTER DALETH..CHORASMIAN LETTER WAW +10FB9..10FBA ; R # Lo [2] CHORASMIAN LETTER HETH..CHORASMIAN LETTER YODH +10FBD ; R # Lo CHORASMIAN LETTER MEM +10FC2..10FC3 ; R # Lo [2] CHORASMIAN LETTER RESH..CHORASMIAN LETTER SHIN +10FC9 ; R # No CHORASMIAN NUMBER TEN + +# Total code points: 152 + +# ================================================ + +# Joining_Type=Left_Joining + +A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA +10ACD ; L # Lo MANICHAEAN LETTER HETH +10AD7 ; L # Lo MANICHAEAN LETTER NUN +10D00 ; L # Lo HANIFI ROHINGYA LETTER A +10FCB ; L # No CHORASMIAN NUMBER ONE HUNDRED + +# Total code points: 5 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; T # Cf ARABIC LETTER MARK +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +07FD ; T # Mn NKO DANTAYALAN +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +0898..089F ; T # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; T # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA +08E3..0902 ; T # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09FE ; T # Mn BENGALI SANDHI MARK +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; T # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B55..0B56 ; T # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C00 ; T # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C04 ; T # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; T # Mn TELUGU SIGN NUKTA +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C81 ; T # Mn KANNADA SIGN CANDRABINDU +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D00..0D01 ; T # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; T # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0D81 ; T # Mn SINHALA SIGN CANDRABINDU +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EBC ; T # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1733 ; T # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; T # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR +1885..1886 ; T # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; T # Mn BUGINESE VOWEL SIGN AE +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; T # Me COMBINING PARENTHESES OVERLAY +1ABF..1ACE ; T # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB..1BAD ; T # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1DC0..1DFF ; T # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69E..A69F ; T # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A82C ; T # Mn SYLOTI NAGRI SIGN ALTERNATE HASANTA +A8C4..A8C5 ; T # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A8FF ; T # Mn DEVANAGARI VOWEL SIGN AY +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC..A9BD ; T # Mn [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET +A9E5 ; T # Mn MYANMAR SIGN SHAN SAW +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AA7C ; T # Mn MYANMAR SIGN TAI LAING TONE-2 +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE2F ; T # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +102E0 ; T # Mn COPTIC EPACT THOUSANDS MARK +10376..1037A ; T # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +10AE5..10AE6 ; T # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +10D24..10D27 ; T # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10EAB..10EAC ; T # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK +10F46..10F50 ; T # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; T # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; T # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; T # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +1107F..11081 ; T # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; T # Mn KAITHI VOWEL SIGN VOCALIC R +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11173 ; T # Mn MAHAJANI SIGN NUKTA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +111C9..111CC ; T # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK +111CF ; T # Mn SHARADA SIGN INVERTED CANDRABINDU +1122F..11231 ; T # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11234 ; T # Mn KHOJKI SIGN ANUSVARA +11236..11237 ; T # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; T # Mn KHOJKI SIGN SUKUN +112DF ; T # Mn KHUDAWADI SIGN ANUSVARA +112E3..112EA ; T # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +11300..11301 ; T # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU +1133B..1133C ; T # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA +11340 ; T # Mn GRANTHA VOWEL SIGN II +11366..1136C ; T # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; T # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11438..1143F ; T # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; T # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; T # Mn NEWA SIGN NUKTA +1145E ; T # Mn NEWA SANDHI MARK +114B3..114B8 ; T # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114BA ; T # Mn TIRHUTA VOWEL SIGN SHORT E +114BF..114C0 ; T # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C2..114C3 ; T # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +115B2..115B5 ; T # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115BC..115BD ; T # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BF..115C0 ; T # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +115DC..115DD ; T # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU +11633..1163A ; T # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163D ; T # Mn MODI SIGN ANUSVARA +1163F..11640 ; T # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +1171D..1171F ; T # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA +11722..11725 ; T # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU +11727..1172B ; T # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +1182F..11837 ; T # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA +11839..1183A ; T # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA +1193B..1193C ; T # Mn [2] DIVES AKURU SIGN ANUSVARA..DIVES AKURU SIGN CANDRABINDU +1193E ; T # Mn DIVES AKURU VIRAMA +11943 ; T # Mn DIVES AKURU SIGN NUKTA +119D4..119D7 ; T # Mn [4] NANDINAGARI VOWEL SIGN U..NANDINAGARI VOWEL SIGN VOCALIC RR +119DA..119DB ; T # Mn [2] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN AI +119E0 ; T # Mn NANDINAGARI SIGN VIRAMA +11A01..11A0A ; T # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; T # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; T # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; T # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; T # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; T # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; T # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; T # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C30..11C36 ; T # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; T # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; T # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; T # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; T # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; T # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; T # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; T # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; T # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; T # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; T # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; T # Mn MASARAM GONDI RA-KARA +11D90..11D91 ; T # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D95 ; T # Mn GUNJALA GONDI SIGN ANUSVARA +11D97 ; T # Mn GUNJALA GONDI VIRAMA +11EF3..11EF4 ; T # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U +13430..13438 ; T # Cf [9] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END SEGMENT +16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16F4F ; T # Mn MIAO SIGN CONSONANT MODIFIER BAR +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +16FE4 ; T # Mn KHITAN SMALL SCRIPT FILLER +1BC9D..1BC9E ; T # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1BCA0..1BCA3 ; T # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CF00..1CF2D ; T # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; T # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1DA00..1DA36 ; T # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN +1DA3B..1DA6C ; T # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT +1DA75 ; T # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS +1DA84 ; T # Mn SIGNWRITING LOCATION HEAD NECK +1DA9B..1DA9F ; T # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 +1DAA1..1DAAF ; T # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; T # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; T # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; T # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; T # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; T # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E130..1E136 ; T # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; T # Mn TOTO SIGN RISING TONE +1E2EC..1E2EF ; T # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI +1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; T # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1E94B ; T # Lm ADLAM NASALIZATION MARK +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 2108 + +# EOF diff --git a/data/15.0.0-derived-joining-type.txt b/data/15.0.0-derived-joining-type.txt new file mode 100644 index 0000000..62ce8a0 --- /dev/null +++ b/data/15.0.0-derived-joining-type.txt @@ -0,0 +1,573 @@ +# DerivedJoiningType-15.0.0.txt +# Date: 2022-04-26, 23:14:36 GMT +# © 2022 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see https://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see https://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +0883..0885 ; C # Lo [3] ARABIC TATWEEL WITH OVERSTRUCK HAMZA..ARABIC TATWEEL WITH TWO DOTS BELOW +180A ; C # Po MONGOLIAN NIRUGU +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 7 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0848 ; D # Lo MANDAIC LETTER ATT +084A..0853 ; D # Lo [10] MANDAIC LETTER AK..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +0860 ; D # Lo SYRIAC LETTER MALAYALAM NGA +0862..0865 ; D # Lo [4] SYRIAC LETTER MALAYALAM NYA..SYRIAC LETTER MALAYALAM NNNA +0868 ; D # Lo SYRIAC LETTER MALAYALAM LLA +0886 ; D # Lo ARABIC LETTER THIN YEH +0889..088D ; D # Lo [5] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER KEHEH WITH TWO DOTS VERTICALLY BELOW +08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE +08B3..08B8 ; D # Lo [6] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER TEH WITH SMALL TEH ABOVE +08BA..08C8 ; D # Lo [15] ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE..ARABIC LETTER GRAF +1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER +1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1878 ; D # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS +1887..18A8 ; D # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; D # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA +10AC0..10AC4 ; D # Lo [5] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER GHIMEL +10AD3..10AD6 ; D # Lo [4] MANICHAEAN LETTER LAMEDH..MANICHAEAN LETTER MEM +10AD8..10ADC ; D # Lo [5] MANICHAEAN LETTER SAMEKH..MANICHAEAN LETTER FE +10ADE..10AE0 ; D # Lo [3] MANICHAEAN LETTER QOPH..MANICHAEAN LETTER QHOPH +10AEB..10AEE ; D # No [4] MANICHAEAN NUMBER ONE..MANICHAEAN NUMBER TWENTY +10B80 ; D # Lo PSALTER PAHLAVI LETTER ALEPH +10B82 ; D # Lo PSALTER PAHLAVI LETTER GIMEL +10B86..10B88 ; D # Lo [3] PSALTER PAHLAVI LETTER ZAYIN..PSALTER PAHLAVI LETTER YODH +10B8A..10B8B ; D # Lo [2] PSALTER PAHLAVI LETTER LAMEDH..PSALTER PAHLAVI LETTER MEM-QOPH +10B8D ; D # Lo PSALTER PAHLAVI LETTER SAMEKH +10B90 ; D # Lo PSALTER PAHLAVI LETTER SHIN +10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY +10D01..10D21 ; D # Lo [33] HANIFI ROHINGYA LETTER BA..HANIFI ROHINGYA VOWEL O +10D23 ; D # Lo HANIFI ROHINGYA MARK NA KHONNA +10F30..10F32 ; D # Lo [3] SOGDIAN LETTER ALEPH..SOGDIAN LETTER GIMEL +10F34..10F44 ; D # Lo [17] SOGDIAN LETTER WAW..SOGDIAN LETTER LESH +10F51..10F53 ; D # No [3] SOGDIAN NUMBER ONE..SOGDIAN NUMBER TWENTY +10F70..10F73 ; D # Lo [4] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER WAW +10F76..10F81 ; D # Lo [12] OLD UYGHUR LETTER YODH..OLD UYGHUR LETTER LESH +10FB0 ; D # Lo CHORASMIAN LETTER ALEPH +10FB2..10FB3 ; D # Lo [2] CHORASMIAN LETTER BETH..CHORASMIAN LETTER GIMEL +10FB8 ; D # Lo CHORASMIAN LETTER ZAYIN +10FBB..10FBC ; D # Lo [2] CHORASMIAN LETTER KAPH..CHORASMIAN LETTER LAMEDH +10FBE..10FBF ; D # Lo [2] CHORASMIAN LETTER NUN..CHORASMIAN LETTER SAMEKH +10FC1 ; D # Lo CHORASMIAN LETTER PE +10FC4 ; D # Lo CHORASMIAN LETTER TAW +10FCA ; D # No CHORASMIAN NUMBER TWENTY +1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA + +# Total code points: 610 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846..0847 ; R # Lo [2] MANDAIC LETTER AZ..MANDAIC LETTER IT +0849 ; R # Lo MANDAIC LETTER AKSA +0854 ; R # Lo MANDAIC LETTER ASH +0856..0858 ; R # Lo [3] MANDAIC LETTER DUSHENNA..MANDAIC LETTER AIN +0867 ; R # Lo SYRIAC LETTER MALAYALAM RA +0869..086A ; R # Lo [2] SYRIAC LETTER MALAYALAM LLLA..SYRIAC LETTER MALAYALAM SSA +0870..0882 ; R # Lo [19] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC LETTER ALEF WITH ATTACHED LEFT HAMZA +088E ; R # Lo ARABIC VERTICAL TAIL +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH +08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW +08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE +08B9 ; R # Lo ARABIC LETTER REH WITH SMALL NOON ABOVE +10AC5 ; R # Lo MANICHAEAN LETTER DALETH +10AC7 ; R # Lo MANICHAEAN LETTER WAW +10AC9..10ACA ; R # Lo [2] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER ZHAYIN +10ACE..10AD2 ; R # Lo [5] MANICHAEAN LETTER TETH..MANICHAEAN LETTER KHAPH +10ADD ; R # Lo MANICHAEAN LETTER SADHE +10AE1 ; R # Lo MANICHAEAN LETTER RESH +10AE4 ; R # Lo MANICHAEAN LETTER TAW +10AEF ; R # No MANICHAEAN NUMBER ONE HUNDRED +10B81 ; R # Lo PSALTER PAHLAVI LETTER BETH +10B83..10B85 ; R # Lo [3] PSALTER PAHLAVI LETTER DALETH..PSALTER PAHLAVI LETTER WAW-AYIN-RESH +10B89 ; R # Lo PSALTER PAHLAVI LETTER KAPH +10B8C ; R # Lo PSALTER PAHLAVI LETTER NUN +10B8E..10B8F ; R # Lo [2] PSALTER PAHLAVI LETTER PE..PSALTER PAHLAVI LETTER SADHE +10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW +10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR +10D22 ; R # Lo HANIFI ROHINGYA MARK SAKIN +10F33 ; R # Lo SOGDIAN LETTER HE +10F54 ; R # No SOGDIAN NUMBER ONE HUNDRED +10F74..10F75 ; R # Lo [2] OLD UYGHUR LETTER ZAYIN..OLD UYGHUR LETTER FINAL HETH +10FB4..10FB6 ; R # Lo [3] CHORASMIAN LETTER DALETH..CHORASMIAN LETTER WAW +10FB9..10FBA ; R # Lo [2] CHORASMIAN LETTER HETH..CHORASMIAN LETTER YODH +10FBD ; R # Lo CHORASMIAN LETTER MEM +10FC2..10FC3 ; R # Lo [2] CHORASMIAN LETTER RESH..CHORASMIAN LETTER SHIN +10FC9 ; R # No CHORASMIAN NUMBER TEN + +# Total code points: 152 + +# ================================================ + +# Joining_Type=Left_Joining + +A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA +10ACD ; L # Lo MANICHAEAN LETTER HETH +10AD7 ; L # Lo MANICHAEAN LETTER NUN +10D00 ; L # Lo HANIFI ROHINGYA LETTER A +10FCB ; L # No CHORASMIAN NUMBER ONE HUNDRED + +# Total code points: 5 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; T # Cf ARABIC LETTER MARK +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +07FD ; T # Mn NKO DANTAYALAN +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +0898..089F ; T # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; T # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA +08E3..0902 ; T # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09FE ; T # Mn BENGALI SANDHI MARK +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; T # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B55..0B56 ; T # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C00 ; T # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C04 ; T # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; T # Mn TELUGU SIGN NUKTA +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C81 ; T # Mn KANNADA SIGN CANDRABINDU +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D00..0D01 ; T # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; T # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0D81 ; T # Mn SINHALA SIGN CANDRABINDU +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EBC ; T # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO +0EC8..0ECE ; T # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1733 ; T # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; T # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR +1885..1886 ; T # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; T # Mn BUGINESE VOWEL SIGN AE +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; T # Me COMBINING PARENTHESES OVERLAY +1ABF..1ACE ; T # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB..1BAD ; T # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1DC0..1DFF ; T # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69E..A69F ; T # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A82C ; T # Mn SYLOTI NAGRI SIGN ALTERNATE HASANTA +A8C4..A8C5 ; T # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A8FF ; T # Mn DEVANAGARI VOWEL SIGN AY +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC..A9BD ; T # Mn [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET +A9E5 ; T # Mn MYANMAR SIGN SHAN SAW +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AA7C ; T # Mn MYANMAR SIGN TAI LAING TONE-2 +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE2F ; T # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +102E0 ; T # Mn COPTIC EPACT THOUSANDS MARK +10376..1037A ; T # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +10AE5..10AE6 ; T # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +10D24..10D27 ; T # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10EAB..10EAC ; T # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK +10EFD..10EFF ; T # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA +10F46..10F50 ; T # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; T # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; T # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; T # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +1107F..11081 ; T # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; T # Mn KAITHI VOWEL SIGN VOCALIC R +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11173 ; T # Mn MAHAJANI SIGN NUKTA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +111C9..111CC ; T # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK +111CF ; T # Mn SHARADA SIGN INVERTED CANDRABINDU +1122F..11231 ; T # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11234 ; T # Mn KHOJKI SIGN ANUSVARA +11236..11237 ; T # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; T # Mn KHOJKI SIGN SUKUN +11241 ; T # Mn KHOJKI VOWEL SIGN VOCALIC R +112DF ; T # Mn KHUDAWADI SIGN ANUSVARA +112E3..112EA ; T # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +11300..11301 ; T # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU +1133B..1133C ; T # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA +11340 ; T # Mn GRANTHA VOWEL SIGN II +11366..1136C ; T # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; T # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11438..1143F ; T # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; T # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; T # Mn NEWA SIGN NUKTA +1145E ; T # Mn NEWA SANDHI MARK +114B3..114B8 ; T # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114BA ; T # Mn TIRHUTA VOWEL SIGN SHORT E +114BF..114C0 ; T # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C2..114C3 ; T # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +115B2..115B5 ; T # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115BC..115BD ; T # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BF..115C0 ; T # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +115DC..115DD ; T # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU +11633..1163A ; T # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163D ; T # Mn MODI SIGN ANUSVARA +1163F..11640 ; T # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +1171D..1171F ; T # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA +11722..11725 ; T # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU +11727..1172B ; T # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +1182F..11837 ; T # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA +11839..1183A ; T # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA +1193B..1193C ; T # Mn [2] DIVES AKURU SIGN ANUSVARA..DIVES AKURU SIGN CANDRABINDU +1193E ; T # Mn DIVES AKURU VIRAMA +11943 ; T # Mn DIVES AKURU SIGN NUKTA +119D4..119D7 ; T # Mn [4] NANDINAGARI VOWEL SIGN U..NANDINAGARI VOWEL SIGN VOCALIC RR +119DA..119DB ; T # Mn [2] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN AI +119E0 ; T # Mn NANDINAGARI SIGN VIRAMA +11A01..11A0A ; T # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; T # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; T # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; T # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; T # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; T # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; T # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; T # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C30..11C36 ; T # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; T # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; T # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; T # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; T # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; T # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; T # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; T # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; T # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; T # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; T # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; T # Mn MASARAM GONDI RA-KARA +11D90..11D91 ; T # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D95 ; T # Mn GUNJALA GONDI SIGN ANUSVARA +11D97 ; T # Mn GUNJALA GONDI VIRAMA +11EF3..11EF4 ; T # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U +11F00..11F01 ; T # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA +11F36..11F3A ; T # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R +11F40 ; T # Mn KAWI VOWEL SIGN EU +11F42 ; T # Mn KAWI CONJOINER +13430..1343F ; T # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE +13440 ; T # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY +13447..13455 ; T # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED +16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16F4F ; T # Mn MIAO SIGN CONSONANT MODIFIER BAR +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +16FE4 ; T # Mn KHITAN SMALL SCRIPT FILLER +1BC9D..1BC9E ; T # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1BCA0..1BCA3 ; T # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CF00..1CF2D ; T # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; T # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1DA00..1DA36 ; T # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN +1DA3B..1DA6C ; T # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT +1DA75 ; T # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS +1DA84 ; T # Mn SIGNWRITING LOCATION HEAD NECK +1DA9B..1DA9F ; T # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 +1DAA1..1DAAF ; T # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; T # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; T # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; T # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; T # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; T # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E08F ; T # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +1E130..1E136 ; T # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; T # Mn TOTO SIGN RISING TONE +1E2EC..1E2EF ; T # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI +1E4EC..1E4EF ; T # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; T # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1E94B ; T # Lm ADLAM NASALIZATION MARK +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 2150 + +# EOF diff --git a/data/15.1.0-derived-joining-type.txt b/data/15.1.0-derived-joining-type.txt new file mode 100644 index 0000000..a4e01e7 --- /dev/null +++ b/data/15.1.0-derived-joining-type.txt @@ -0,0 +1,573 @@ +# DerivedJoiningType-15.1.0.txt +# Date: 2023-01-05, 20:34:38 GMT +# © 2023 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see https://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see https://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +0883..0885 ; C # Lo [3] ARABIC TATWEEL WITH OVERSTRUCK HAMZA..ARABIC TATWEEL WITH TWO DOTS BELOW +180A ; C # Po MONGOLIAN NIRUGU +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 7 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0848 ; D # Lo MANDAIC LETTER ATT +084A..0853 ; D # Lo [10] MANDAIC LETTER AK..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +0860 ; D # Lo SYRIAC LETTER MALAYALAM NGA +0862..0865 ; D # Lo [4] SYRIAC LETTER MALAYALAM NYA..SYRIAC LETTER MALAYALAM NNNA +0868 ; D # Lo SYRIAC LETTER MALAYALAM LLA +0886 ; D # Lo ARABIC LETTER THIN YEH +0889..088D ; D # Lo [5] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER KEHEH WITH TWO DOTS VERTICALLY BELOW +08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE +08B3..08B8 ; D # Lo [6] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER TEH WITH SMALL TEH ABOVE +08BA..08C8 ; D # Lo [15] ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE..ARABIC LETTER GRAF +1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER +1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1878 ; D # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS +1887..18A8 ; D # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; D # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA +10AC0..10AC4 ; D # Lo [5] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER GHIMEL +10AD3..10AD6 ; D # Lo [4] MANICHAEAN LETTER LAMEDH..MANICHAEAN LETTER MEM +10AD8..10ADC ; D # Lo [5] MANICHAEAN LETTER SAMEKH..MANICHAEAN LETTER FE +10ADE..10AE0 ; D # Lo [3] MANICHAEAN LETTER QOPH..MANICHAEAN LETTER QHOPH +10AEB..10AEE ; D # No [4] MANICHAEAN NUMBER ONE..MANICHAEAN NUMBER TWENTY +10B80 ; D # Lo PSALTER PAHLAVI LETTER ALEPH +10B82 ; D # Lo PSALTER PAHLAVI LETTER GIMEL +10B86..10B88 ; D # Lo [3] PSALTER PAHLAVI LETTER ZAYIN..PSALTER PAHLAVI LETTER YODH +10B8A..10B8B ; D # Lo [2] PSALTER PAHLAVI LETTER LAMEDH..PSALTER PAHLAVI LETTER MEM-QOPH +10B8D ; D # Lo PSALTER PAHLAVI LETTER SAMEKH +10B90 ; D # Lo PSALTER PAHLAVI LETTER SHIN +10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY +10D01..10D21 ; D # Lo [33] HANIFI ROHINGYA LETTER BA..HANIFI ROHINGYA VOWEL O +10D23 ; D # Lo HANIFI ROHINGYA MARK NA KHONNA +10F30..10F32 ; D # Lo [3] SOGDIAN LETTER ALEPH..SOGDIAN LETTER GIMEL +10F34..10F44 ; D # Lo [17] SOGDIAN LETTER WAW..SOGDIAN LETTER LESH +10F51..10F53 ; D # No [3] SOGDIAN NUMBER ONE..SOGDIAN NUMBER TWENTY +10F70..10F73 ; D # Lo [4] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER WAW +10F76..10F81 ; D # Lo [12] OLD UYGHUR LETTER YODH..OLD UYGHUR LETTER LESH +10FB0 ; D # Lo CHORASMIAN LETTER ALEPH +10FB2..10FB3 ; D # Lo [2] CHORASMIAN LETTER BETH..CHORASMIAN LETTER GIMEL +10FB8 ; D # Lo CHORASMIAN LETTER ZAYIN +10FBB..10FBC ; D # Lo [2] CHORASMIAN LETTER KAPH..CHORASMIAN LETTER LAMEDH +10FBE..10FBF ; D # Lo [2] CHORASMIAN LETTER NUN..CHORASMIAN LETTER SAMEKH +10FC1 ; D # Lo CHORASMIAN LETTER PE +10FC4 ; D # Lo CHORASMIAN LETTER TAW +10FCA ; D # No CHORASMIAN NUMBER TWENTY +1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA + +# Total code points: 610 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846..0847 ; R # Lo [2] MANDAIC LETTER AZ..MANDAIC LETTER IT +0849 ; R # Lo MANDAIC LETTER AKSA +0854 ; R # Lo MANDAIC LETTER ASH +0856..0858 ; R # Lo [3] MANDAIC LETTER DUSHENNA..MANDAIC LETTER AIN +0867 ; R # Lo SYRIAC LETTER MALAYALAM RA +0869..086A ; R # Lo [2] SYRIAC LETTER MALAYALAM LLLA..SYRIAC LETTER MALAYALAM SSA +0870..0882 ; R # Lo [19] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC LETTER ALEF WITH ATTACHED LEFT HAMZA +088E ; R # Lo ARABIC VERTICAL TAIL +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH +08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW +08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE +08B9 ; R # Lo ARABIC LETTER REH WITH SMALL NOON ABOVE +10AC5 ; R # Lo MANICHAEAN LETTER DALETH +10AC7 ; R # Lo MANICHAEAN LETTER WAW +10AC9..10ACA ; R # Lo [2] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER ZHAYIN +10ACE..10AD2 ; R # Lo [5] MANICHAEAN LETTER TETH..MANICHAEAN LETTER KHAPH +10ADD ; R # Lo MANICHAEAN LETTER SADHE +10AE1 ; R # Lo MANICHAEAN LETTER RESH +10AE4 ; R # Lo MANICHAEAN LETTER TAW +10AEF ; R # No MANICHAEAN NUMBER ONE HUNDRED +10B81 ; R # Lo PSALTER PAHLAVI LETTER BETH +10B83..10B85 ; R # Lo [3] PSALTER PAHLAVI LETTER DALETH..PSALTER PAHLAVI LETTER WAW-AYIN-RESH +10B89 ; R # Lo PSALTER PAHLAVI LETTER KAPH +10B8C ; R # Lo PSALTER PAHLAVI LETTER NUN +10B8E..10B8F ; R # Lo [2] PSALTER PAHLAVI LETTER PE..PSALTER PAHLAVI LETTER SADHE +10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW +10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR +10D22 ; R # Lo HANIFI ROHINGYA MARK SAKIN +10F33 ; R # Lo SOGDIAN LETTER HE +10F54 ; R # No SOGDIAN NUMBER ONE HUNDRED +10F74..10F75 ; R # Lo [2] OLD UYGHUR LETTER ZAYIN..OLD UYGHUR LETTER FINAL HETH +10FB4..10FB6 ; R # Lo [3] CHORASMIAN LETTER DALETH..CHORASMIAN LETTER WAW +10FB9..10FBA ; R # Lo [2] CHORASMIAN LETTER HETH..CHORASMIAN LETTER YODH +10FBD ; R # Lo CHORASMIAN LETTER MEM +10FC2..10FC3 ; R # Lo [2] CHORASMIAN LETTER RESH..CHORASMIAN LETTER SHIN +10FC9 ; R # No CHORASMIAN NUMBER TEN + +# Total code points: 152 + +# ================================================ + +# Joining_Type=Left_Joining + +A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA +10ACD ; L # Lo MANICHAEAN LETTER HETH +10AD7 ; L # Lo MANICHAEAN LETTER NUN +10D00 ; L # Lo HANIFI ROHINGYA LETTER A +10FCB ; L # No CHORASMIAN NUMBER ONE HUNDRED + +# Total code points: 5 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; T # Cf ARABIC LETTER MARK +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +07FD ; T # Mn NKO DANTAYALAN +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +0898..089F ; T # Mn [8] ARABIC SMALL HIGH WORD AL-JUZ..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; T # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA +08E3..0902 ; T # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09FE ; T # Mn BENGALI SANDHI MARK +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; T # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B55..0B56 ; T # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C00 ; T # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C04 ; T # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; T # Mn TELUGU SIGN NUKTA +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C81 ; T # Mn KANNADA SIGN CANDRABINDU +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D00..0D01 ; T # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; T # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0D81 ; T # Mn SINHALA SIGN CANDRABINDU +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EBC ; T # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO +0EC8..0ECE ; T # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1733 ; T # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; T # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR +1885..1886 ; T # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; T # Mn BUGINESE VOWEL SIGN AE +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; T # Me COMBINING PARENTHESES OVERLAY +1ABF..1ACE ; T # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB..1BAD ; T # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1DC0..1DFF ; T # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69E..A69F ; T # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A82C ; T # Mn SYLOTI NAGRI SIGN ALTERNATE HASANTA +A8C4..A8C5 ; T # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A8FF ; T # Mn DEVANAGARI VOWEL SIGN AY +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC..A9BD ; T # Mn [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET +A9E5 ; T # Mn MYANMAR SIGN SHAN SAW +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AA7C ; T # Mn MYANMAR SIGN TAI LAING TONE-2 +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE2F ; T # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +102E0 ; T # Mn COPTIC EPACT THOUSANDS MARK +10376..1037A ; T # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +10AE5..10AE6 ; T # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +10D24..10D27 ; T # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10EAB..10EAC ; T # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK +10EFD..10EFF ; T # Mn [3] ARABIC SMALL LOW WORD SAKTA..ARABIC SMALL LOW WORD MADDA +10F46..10F50 ; T # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; T # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; T # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; T # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +1107F..11081 ; T # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; T # Mn KAITHI VOWEL SIGN VOCALIC R +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11173 ; T # Mn MAHAJANI SIGN NUKTA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +111C9..111CC ; T # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK +111CF ; T # Mn SHARADA SIGN INVERTED CANDRABINDU +1122F..11231 ; T # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11234 ; T # Mn KHOJKI SIGN ANUSVARA +11236..11237 ; T # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; T # Mn KHOJKI SIGN SUKUN +11241 ; T # Mn KHOJKI VOWEL SIGN VOCALIC R +112DF ; T # Mn KHUDAWADI SIGN ANUSVARA +112E3..112EA ; T # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +11300..11301 ; T # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU +1133B..1133C ; T # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA +11340 ; T # Mn GRANTHA VOWEL SIGN II +11366..1136C ; T # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; T # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11438..1143F ; T # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; T # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; T # Mn NEWA SIGN NUKTA +1145E ; T # Mn NEWA SANDHI MARK +114B3..114B8 ; T # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114BA ; T # Mn TIRHUTA VOWEL SIGN SHORT E +114BF..114C0 ; T # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C2..114C3 ; T # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +115B2..115B5 ; T # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115BC..115BD ; T # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BF..115C0 ; T # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +115DC..115DD ; T # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU +11633..1163A ; T # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163D ; T # Mn MODI SIGN ANUSVARA +1163F..11640 ; T # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +1171D..1171F ; T # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA +11722..11725 ; T # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU +11727..1172B ; T # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +1182F..11837 ; T # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA +11839..1183A ; T # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA +1193B..1193C ; T # Mn [2] DIVES AKURU SIGN ANUSVARA..DIVES AKURU SIGN CANDRABINDU +1193E ; T # Mn DIVES AKURU VIRAMA +11943 ; T # Mn DIVES AKURU SIGN NUKTA +119D4..119D7 ; T # Mn [4] NANDINAGARI VOWEL SIGN U..NANDINAGARI VOWEL SIGN VOCALIC RR +119DA..119DB ; T # Mn [2] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN AI +119E0 ; T # Mn NANDINAGARI SIGN VIRAMA +11A01..11A0A ; T # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; T # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; T # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; T # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; T # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; T # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; T # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; T # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C30..11C36 ; T # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; T # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; T # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; T # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; T # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; T # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; T # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; T # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; T # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; T # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; T # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; T # Mn MASARAM GONDI RA-KARA +11D90..11D91 ; T # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D95 ; T # Mn GUNJALA GONDI SIGN ANUSVARA +11D97 ; T # Mn GUNJALA GONDI VIRAMA +11EF3..11EF4 ; T # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U +11F00..11F01 ; T # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA +11F36..11F3A ; T # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R +11F40 ; T # Mn KAWI VOWEL SIGN EU +11F42 ; T # Mn KAWI CONJOINER +13430..1343F ; T # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE +13440 ; T # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY +13447..13455 ; T # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED +16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16F4F ; T # Mn MIAO SIGN CONSONANT MODIFIER BAR +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +16FE4 ; T # Mn KHITAN SMALL SCRIPT FILLER +1BC9D..1BC9E ; T # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1BCA0..1BCA3 ; T # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CF00..1CF2D ; T # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; T # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1DA00..1DA36 ; T # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN +1DA3B..1DA6C ; T # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT +1DA75 ; T # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS +1DA84 ; T # Mn SIGNWRITING LOCATION HEAD NECK +1DA9B..1DA9F ; T # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 +1DAA1..1DAAF ; T # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; T # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; T # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; T # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; T # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; T # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E08F ; T # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +1E130..1E136 ; T # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; T # Mn TOTO SIGN RISING TONE +1E2EC..1E2EF ; T # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI +1E4EC..1E4EF ; T # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; T # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1E94B ; T # Lm ADLAM NASALIZATION MARK +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 2150 + +# EOF diff --git a/data/16.0.0-derived-joining-type.txt b/data/16.0.0-derived-joining-type.txt new file mode 100644 index 0000000..3841a92 --- /dev/null +++ b/data/16.0.0-derived-joining-type.txt @@ -0,0 +1,586 @@ +# DerivedJoiningType-16.0.0.txt +# Date: 2024-04-30, 21:48:18 GMT +# © 2024 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use and license, see https://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see https://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +0883..0885 ; C # Lo [3] ARABIC TATWEEL WITH OVERSTRUCK HAMZA..ARABIC TATWEEL WITH TWO DOTS BELOW +180A ; C # Po MONGOLIAN NIRUGU +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 7 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0848 ; D # Lo MANDAIC LETTER ATT +084A..0853 ; D # Lo [10] MANDAIC LETTER AK..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +0860 ; D # Lo SYRIAC LETTER MALAYALAM NGA +0862..0865 ; D # Lo [4] SYRIAC LETTER MALAYALAM NYA..SYRIAC LETTER MALAYALAM NNNA +0868 ; D # Lo SYRIAC LETTER MALAYALAM LLA +0886 ; D # Lo ARABIC LETTER THIN YEH +0889..088D ; D # Lo [5] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER KEHEH WITH TWO DOTS VERTICALLY BELOW +08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE +08B3..08B8 ; D # Lo [6] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER TEH WITH SMALL TEH ABOVE +08BA..08C8 ; D # Lo [15] ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE..ARABIC LETTER GRAF +1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER +1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1878 ; D # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS +1887..18A8 ; D # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; D # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA +10AC0..10AC4 ; D # Lo [5] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER GHIMEL +10AD3..10AD6 ; D # Lo [4] MANICHAEAN LETTER LAMEDH..MANICHAEAN LETTER MEM +10AD8..10ADC ; D # Lo [5] MANICHAEAN LETTER SAMEKH..MANICHAEAN LETTER FE +10ADE..10AE0 ; D # Lo [3] MANICHAEAN LETTER QOPH..MANICHAEAN LETTER QHOPH +10AEB..10AEE ; D # No [4] MANICHAEAN NUMBER ONE..MANICHAEAN NUMBER TWENTY +10B80 ; D # Lo PSALTER PAHLAVI LETTER ALEPH +10B82 ; D # Lo PSALTER PAHLAVI LETTER GIMEL +10B86..10B88 ; D # Lo [3] PSALTER PAHLAVI LETTER ZAYIN..PSALTER PAHLAVI LETTER YODH +10B8A..10B8B ; D # Lo [2] PSALTER PAHLAVI LETTER LAMEDH..PSALTER PAHLAVI LETTER MEM-QOPH +10B8D ; D # Lo PSALTER PAHLAVI LETTER SAMEKH +10B90 ; D # Lo PSALTER PAHLAVI LETTER SHIN +10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY +10D01..10D21 ; D # Lo [33] HANIFI ROHINGYA LETTER BA..HANIFI ROHINGYA VOWEL O +10D23 ; D # Lo HANIFI ROHINGYA MARK NA KHONNA +10EC3..10EC4 ; D # Lo [2] ARABIC LETTER TAH WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10F30..10F32 ; D # Lo [3] SOGDIAN LETTER ALEPH..SOGDIAN LETTER GIMEL +10F34..10F44 ; D # Lo [17] SOGDIAN LETTER WAW..SOGDIAN LETTER LESH +10F51..10F53 ; D # No [3] SOGDIAN NUMBER ONE..SOGDIAN NUMBER TWENTY +10F70..10F73 ; D # Lo [4] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER WAW +10F76..10F81 ; D # Lo [12] OLD UYGHUR LETTER YODH..OLD UYGHUR LETTER LESH +10FB0 ; D # Lo CHORASMIAN LETTER ALEPH +10FB2..10FB3 ; D # Lo [2] CHORASMIAN LETTER BETH..CHORASMIAN LETTER GIMEL +10FB8 ; D # Lo CHORASMIAN LETTER ZAYIN +10FBB..10FBC ; D # Lo [2] CHORASMIAN LETTER KAPH..CHORASMIAN LETTER LAMEDH +10FBE..10FBF ; D # Lo [2] CHORASMIAN LETTER NUN..CHORASMIAN LETTER SAMEKH +10FC1 ; D # Lo CHORASMIAN LETTER PE +10FC4 ; D # Lo CHORASMIAN LETTER TAW +10FCA ; D # No CHORASMIAN NUMBER TWENTY +1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA + +# Total code points: 612 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846..0847 ; R # Lo [2] MANDAIC LETTER AZ..MANDAIC LETTER IT +0849 ; R # Lo MANDAIC LETTER AKSA +0854 ; R # Lo MANDAIC LETTER ASH +0856..0858 ; R # Lo [3] MANDAIC LETTER DUSHENNA..MANDAIC LETTER AIN +0867 ; R # Lo SYRIAC LETTER MALAYALAM RA +0869..086A ; R # Lo [2] SYRIAC LETTER MALAYALAM LLLA..SYRIAC LETTER MALAYALAM SSA +0870..0882 ; R # Lo [19] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC LETTER ALEF WITH ATTACHED LEFT HAMZA +088E ; R # Lo ARABIC VERTICAL TAIL +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH +08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW +08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE +08B9 ; R # Lo ARABIC LETTER REH WITH SMALL NOON ABOVE +10AC5 ; R # Lo MANICHAEAN LETTER DALETH +10AC7 ; R # Lo MANICHAEAN LETTER WAW +10AC9..10ACA ; R # Lo [2] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER ZHAYIN +10ACE..10AD2 ; R # Lo [5] MANICHAEAN LETTER TETH..MANICHAEAN LETTER KHAPH +10ADD ; R # Lo MANICHAEAN LETTER SADHE +10AE1 ; R # Lo MANICHAEAN LETTER RESH +10AE4 ; R # Lo MANICHAEAN LETTER TAW +10AEF ; R # No MANICHAEAN NUMBER ONE HUNDRED +10B81 ; R # Lo PSALTER PAHLAVI LETTER BETH +10B83..10B85 ; R # Lo [3] PSALTER PAHLAVI LETTER DALETH..PSALTER PAHLAVI LETTER WAW-AYIN-RESH +10B89 ; R # Lo PSALTER PAHLAVI LETTER KAPH +10B8C ; R # Lo PSALTER PAHLAVI LETTER NUN +10B8E..10B8F ; R # Lo [2] PSALTER PAHLAVI LETTER PE..PSALTER PAHLAVI LETTER SADHE +10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW +10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR +10D22 ; R # Lo HANIFI ROHINGYA MARK SAKIN +10EC2 ; R # Lo ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW +10F33 ; R # Lo SOGDIAN LETTER HE +10F54 ; R # No SOGDIAN NUMBER ONE HUNDRED +10F74..10F75 ; R # Lo [2] OLD UYGHUR LETTER ZAYIN..OLD UYGHUR LETTER FINAL HETH +10FB4..10FB6 ; R # Lo [3] CHORASMIAN LETTER DALETH..CHORASMIAN LETTER WAW +10FB9..10FBA ; R # Lo [2] CHORASMIAN LETTER HETH..CHORASMIAN LETTER YODH +10FBD ; R # Lo CHORASMIAN LETTER MEM +10FC2..10FC3 ; R # Lo [2] CHORASMIAN LETTER RESH..CHORASMIAN LETTER SHIN +10FC9 ; R # No CHORASMIAN NUMBER TEN + +# Total code points: 153 + +# ================================================ + +# Joining_Type=Left_Joining + +A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA +10ACD ; L # Lo MANICHAEAN LETTER HETH +10AD7 ; L # Lo MANICHAEAN LETTER NUN +10D00 ; L # Lo HANIFI ROHINGYA LETTER A +10FCB ; L # No CHORASMIAN NUMBER ONE HUNDRED + +# Total code points: 5 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; T # Cf ARABIC LETTER MARK +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +07FD ; T # Mn NKO DANTAYALAN +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +0897..089F ; T # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; T # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA +08E3..0902 ; T # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09FE ; T # Mn BENGALI SANDHI MARK +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; T # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B55..0B56 ; T # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C00 ; T # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C04 ; T # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; T # Mn TELUGU SIGN NUKTA +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C81 ; T # Mn KANNADA SIGN CANDRABINDU +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D00..0D01 ; T # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; T # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0D81 ; T # Mn SINHALA SIGN CANDRABINDU +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EBC ; T # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO +0EC8..0ECE ; T # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1733 ; T # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; T # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR +1885..1886 ; T # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; T # Mn BUGINESE VOWEL SIGN AE +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; T # Me COMBINING PARENTHESES OVERLAY +1ABF..1ACE ; T # Mn [16] COMBINING LATIN SMALL LETTER W BELOW..COMBINING LATIN SMALL LETTER INSULAR T +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB..1BAD ; T # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1DC0..1DFF ; T # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69E..A69F ; T # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A82C ; T # Mn SYLOTI NAGRI SIGN ALTERNATE HASANTA +A8C4..A8C5 ; T # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A8FF ; T # Mn DEVANAGARI VOWEL SIGN AY +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC..A9BD ; T # Mn [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET +A9E5 ; T # Mn MYANMAR SIGN SHAN SAW +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AA7C ; T # Mn MYANMAR SIGN TAI LAING TONE-2 +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE2F ; T # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +102E0 ; T # Mn COPTIC EPACT THOUSANDS MARK +10376..1037A ; T # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +10AE5..10AE6 ; T # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +10D24..10D27 ; T # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D69..10D6D ; T # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK +10EAB..10EAC ; T # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK +10EFC..10EFF ; T # Mn [4] ARABIC COMBINING ALEF OVERLAY..ARABIC SMALL LOW WORD MADDA +10F46..10F50 ; T # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; T # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; T # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; T # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +1107F..11081 ; T # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; T # Mn KAITHI VOWEL SIGN VOCALIC R +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11173 ; T # Mn MAHAJANI SIGN NUKTA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +111C9..111CC ; T # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK +111CF ; T # Mn SHARADA SIGN INVERTED CANDRABINDU +1122F..11231 ; T # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11234 ; T # Mn KHOJKI SIGN ANUSVARA +11236..11237 ; T # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; T # Mn KHOJKI SIGN SUKUN +11241 ; T # Mn KHOJKI VOWEL SIGN VOCALIC R +112DF ; T # Mn KHUDAWADI SIGN ANUSVARA +112E3..112EA ; T # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +11300..11301 ; T # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU +1133B..1133C ; T # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA +11340 ; T # Mn GRANTHA VOWEL SIGN II +11366..1136C ; T # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; T # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113BB..113C0 ; T # Mn [6] TULU-TIGALARI VOWEL SIGN U..TULU-TIGALARI VOWEL SIGN VOCALIC LL +113CE ; T # Mn TULU-TIGALARI SIGN VIRAMA +113D0 ; T # Mn TULU-TIGALARI CONJOINER +113D2 ; T # Mn TULU-TIGALARI GEMINATION MARK +113E1..113E2 ; T # Mn [2] TULU-TIGALARI VEDIC TONE SVARITA..TULU-TIGALARI VEDIC TONE ANUDATTA +11438..1143F ; T # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; T # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; T # Mn NEWA SIGN NUKTA +1145E ; T # Mn NEWA SANDHI MARK +114B3..114B8 ; T # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114BA ; T # Mn TIRHUTA VOWEL SIGN SHORT E +114BF..114C0 ; T # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C2..114C3 ; T # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +115B2..115B5 ; T # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115BC..115BD ; T # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BF..115C0 ; T # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +115DC..115DD ; T # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU +11633..1163A ; T # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163D ; T # Mn MODI SIGN ANUSVARA +1163F..11640 ; T # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +1171D ; T # Mn AHOM CONSONANT SIGN MEDIAL LA +1171F ; T # Mn AHOM CONSONANT SIGN MEDIAL LIGATING RA +11722..11725 ; T # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU +11727..1172B ; T # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +1182F..11837 ; T # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA +11839..1183A ; T # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA +1193B..1193C ; T # Mn [2] DIVES AKURU SIGN ANUSVARA..DIVES AKURU SIGN CANDRABINDU +1193E ; T # Mn DIVES AKURU VIRAMA +11943 ; T # Mn DIVES AKURU SIGN NUKTA +119D4..119D7 ; T # Mn [4] NANDINAGARI VOWEL SIGN U..NANDINAGARI VOWEL SIGN VOCALIC RR +119DA..119DB ; T # Mn [2] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN AI +119E0 ; T # Mn NANDINAGARI SIGN VIRAMA +11A01..11A0A ; T # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; T # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; T # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; T # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; T # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; T # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; T # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; T # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11C30..11C36 ; T # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; T # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; T # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; T # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; T # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; T # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; T # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; T # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; T # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; T # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; T # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; T # Mn MASARAM GONDI RA-KARA +11D90..11D91 ; T # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D95 ; T # Mn GUNJALA GONDI SIGN ANUSVARA +11D97 ; T # Mn GUNJALA GONDI VIRAMA +11EF3..11EF4 ; T # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U +11F00..11F01 ; T # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA +11F36..11F3A ; T # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R +11F40 ; T # Mn KAWI VOWEL SIGN EU +11F42 ; T # Mn KAWI CONJOINER +11F5A ; T # Mn KAWI SIGN NUKTA +13430..1343F ; T # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE +13440 ; T # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY +13447..13455 ; T # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED +1611E..16129 ; T # Mn [12] GURUNG KHEMA VOWEL SIGN AA..GURUNG KHEMA VOWEL LENGTH MARK +1612D..1612F ; T # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA +16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16F4F ; T # Mn MIAO SIGN CONSONANT MODIFIER BAR +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +16FE4 ; T # Mn KHITAN SMALL SCRIPT FILLER +1BC9D..1BC9E ; T # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1BCA0..1BCA3 ; T # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CF00..1CF2D ; T # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; T # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1DA00..1DA36 ; T # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN +1DA3B..1DA6C ; T # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT +1DA75 ; T # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS +1DA84 ; T # Mn SIGNWRITING LOCATION HEAD NECK +1DA9B..1DA9F ; T # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 +1DAA1..1DAAF ; T # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; T # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; T # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; T # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; T # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; T # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E08F ; T # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +1E130..1E136 ; T # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; T # Mn TOTO SIGN RISING TONE +1E2EC..1E2EF ; T # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI +1E4EC..1E4EF ; T # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E5EE..1E5EF ; T # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR +1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; T # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1E94B ; T # Lm ADLAM NASALIZATION MARK +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 2185 + +# EOF diff --git a/data/17.0.0-derived-joining-type.txt b/data/17.0.0-derived-joining-type.txt new file mode 100644 index 0000000..9e6aa70 --- /dev/null +++ b/data/17.0.0-derived-joining-type.txt @@ -0,0 +1,596 @@ +# DerivedJoiningType-17.0.0.txt +# Date: 2025-06-30, 06:20:20 GMT +# © 2025 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use and license, see https://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see https://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +0883..0885 ; C # Lo [3] ARABIC TATWEEL WITH OVERSTRUCK HAMZA..ARABIC TATWEEL WITH TWO DOTS BELOW +180A ; C # Po MONGOLIAN NIRUGU +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 7 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0848 ; D # Lo MANDAIC LETTER ATT +084A..0853 ; D # Lo [10] MANDAIC LETTER AK..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +0860 ; D # Lo SYRIAC LETTER MALAYALAM NGA +0862..0865 ; D # Lo [4] SYRIAC LETTER MALAYALAM NYA..SYRIAC LETTER MALAYALAM NNNA +0868 ; D # Lo SYRIAC LETTER MALAYALAM LLA +0886 ; D # Lo ARABIC LETTER THIN YEH +0889..088D ; D # Lo [5] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER KEHEH WITH TWO DOTS VERTICALLY BELOW +088F ; D # Lo ARABIC LETTER NOON WITH RING ABOVE +08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE +08B3..08B8 ; D # Lo [6] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER TEH WITH SMALL TEH ABOVE +08BA..08C8 ; D # Lo [15] ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE..ARABIC LETTER GRAF +1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER +1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1878 ; D # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS +1887..18A8 ; D # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; D # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA +10AC0..10AC4 ; D # Lo [5] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER GHIMEL +10AD3..10AD6 ; D # Lo [4] MANICHAEAN LETTER LAMEDH..MANICHAEAN LETTER MEM +10AD8..10ADC ; D # Lo [5] MANICHAEAN LETTER SAMEKH..MANICHAEAN LETTER FE +10ADE..10AE0 ; D # Lo [3] MANICHAEAN LETTER QOPH..MANICHAEAN LETTER QHOPH +10AEB..10AEE ; D # No [4] MANICHAEAN NUMBER ONE..MANICHAEAN NUMBER TWENTY +10B80 ; D # Lo PSALTER PAHLAVI LETTER ALEPH +10B82 ; D # Lo PSALTER PAHLAVI LETTER GIMEL +10B86..10B88 ; D # Lo [3] PSALTER PAHLAVI LETTER ZAYIN..PSALTER PAHLAVI LETTER YODH +10B8A..10B8B ; D # Lo [2] PSALTER PAHLAVI LETTER LAMEDH..PSALTER PAHLAVI LETTER MEM-QOPH +10B8D ; D # Lo PSALTER PAHLAVI LETTER SAMEKH +10B90 ; D # Lo PSALTER PAHLAVI LETTER SHIN +10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY +10D01..10D21 ; D # Lo [33] HANIFI ROHINGYA LETTER BA..HANIFI ROHINGYA VOWEL O +10D23 ; D # Lo HANIFI ROHINGYA MARK NA KHONNA +10EC3..10EC4 ; D # Lo [2] ARABIC LETTER TAH WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC6..10EC7 ; D # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW +10F30..10F32 ; D # Lo [3] SOGDIAN LETTER ALEPH..SOGDIAN LETTER GIMEL +10F34..10F44 ; D # Lo [17] SOGDIAN LETTER WAW..SOGDIAN LETTER LESH +10F51..10F53 ; D # No [3] SOGDIAN NUMBER ONE..SOGDIAN NUMBER TWENTY +10F70..10F73 ; D # Lo [4] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER WAW +10F76..10F81 ; D # Lo [12] OLD UYGHUR LETTER YODH..OLD UYGHUR LETTER LESH +10FB0 ; D # Lo CHORASMIAN LETTER ALEPH +10FB2..10FB3 ; D # Lo [2] CHORASMIAN LETTER BETH..CHORASMIAN LETTER GIMEL +10FB8 ; D # Lo CHORASMIAN LETTER ZAYIN +10FBB..10FBC ; D # Lo [2] CHORASMIAN LETTER KAPH..CHORASMIAN LETTER LAMEDH +10FBE..10FBF ; D # Lo [2] CHORASMIAN LETTER NUN..CHORASMIAN LETTER SAMEKH +10FC1 ; D # Lo CHORASMIAN LETTER PE +10FC4 ; D # Lo CHORASMIAN LETTER TAW +10FCA ; D # No CHORASMIAN NUMBER TWENTY +1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA + +# Total code points: 615 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846..0847 ; R # Lo [2] MANDAIC LETTER AZ..MANDAIC LETTER IT +0849 ; R # Lo MANDAIC LETTER AKSA +0854 ; R # Lo MANDAIC LETTER ASH +0856..0858 ; R # Lo [3] MANDAIC LETTER DUSHENNA..MANDAIC LETTER AIN +0867 ; R # Lo SYRIAC LETTER MALAYALAM RA +0869..086A ; R # Lo [2] SYRIAC LETTER MALAYALAM LLLA..SYRIAC LETTER MALAYALAM SSA +0870..0882 ; R # Lo [19] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC LETTER ALEF WITH ATTACHED LEFT HAMZA +088E ; R # Lo ARABIC VERTICAL TAIL +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH +08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW +08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE +08B9 ; R # Lo ARABIC LETTER REH WITH SMALL NOON ABOVE +10AC5 ; R # Lo MANICHAEAN LETTER DALETH +10AC7 ; R # Lo MANICHAEAN LETTER WAW +10AC9..10ACA ; R # Lo [2] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER ZHAYIN +10ACE..10AD2 ; R # Lo [5] MANICHAEAN LETTER TETH..MANICHAEAN LETTER KHAPH +10ADD ; R # Lo MANICHAEAN LETTER SADHE +10AE1 ; R # Lo MANICHAEAN LETTER RESH +10AE4 ; R # Lo MANICHAEAN LETTER TAW +10AEF ; R # No MANICHAEAN NUMBER ONE HUNDRED +10B81 ; R # Lo PSALTER PAHLAVI LETTER BETH +10B83..10B85 ; R # Lo [3] PSALTER PAHLAVI LETTER DALETH..PSALTER PAHLAVI LETTER WAW-AYIN-RESH +10B89 ; R # Lo PSALTER PAHLAVI LETTER KAPH +10B8C ; R # Lo PSALTER PAHLAVI LETTER NUN +10B8E..10B8F ; R # Lo [2] PSALTER PAHLAVI LETTER PE..PSALTER PAHLAVI LETTER SADHE +10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW +10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR +10D22 ; R # Lo HANIFI ROHINGYA MARK SAKIN +10EC2 ; R # Lo ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW +10F33 ; R # Lo SOGDIAN LETTER HE +10F54 ; R # No SOGDIAN NUMBER ONE HUNDRED +10F74..10F75 ; R # Lo [2] OLD UYGHUR LETTER ZAYIN..OLD UYGHUR LETTER FINAL HETH +10FB4..10FB6 ; R # Lo [3] CHORASMIAN LETTER DALETH..CHORASMIAN LETTER WAW +10FB9..10FBA ; R # Lo [2] CHORASMIAN LETTER HETH..CHORASMIAN LETTER YODH +10FBD ; R # Lo CHORASMIAN LETTER MEM +10FC2..10FC3 ; R # Lo [2] CHORASMIAN LETTER RESH..CHORASMIAN LETTER SHIN +10FC9 ; R # No CHORASMIAN NUMBER TEN + +# Total code points: 153 + +# ================================================ + +# Joining_Type=Left_Joining + +A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA +10ACD ; L # Lo MANICHAEAN LETTER HETH +10AD7 ; L # Lo MANICHAEAN LETTER NUN +10D00 ; L # Lo HANIFI ROHINGYA LETTER A +10FCB ; L # No CHORASMIAN NUMBER ONE HUNDRED + +# Total code points: 5 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; T # Cf ARABIC LETTER MARK +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +07FD ; T # Mn NKO DANTAYALAN +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +0897..089F ; T # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; T # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA +08E3..0902 ; T # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09FE ; T # Mn BENGALI SANDHI MARK +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; T # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B55..0B56 ; T # Mn [2] ORIYA SIGN OVERLINE..ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C00 ; T # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C04 ; T # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; T # Mn TELUGU SIGN NUKTA +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C81 ; T # Mn KANNADA SIGN CANDRABINDU +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D00..0D01 ; T # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; T # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0D81 ; T # Mn SINHALA SIGN CANDRABINDU +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EBC ; T # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO +0EC8..0ECE ; T # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1733 ; T # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; T # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR +1885..1886 ; T # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; T # Mn BUGINESE VOWEL SIGN AE +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; T # Me COMBINING PARENTHESES OVERLAY +1ABF..1ADD ; T # Mn [31] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOT-AND-RING BELOW +1AE0..1AEB ; T # Mn [12] COMBINING LEFT TACK ABOVE..COMBINING DOUBLE RIGHTWARDS ARROW ABOVE +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB..1BAD ; T # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1DC0..1DFF ; T # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69E..A69F ; T # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A82C ; T # Mn SYLOTI NAGRI SIGN ALTERNATE HASANTA +A8C4..A8C5 ; T # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A8FF ; T # Mn DEVANAGARI VOWEL SIGN AY +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC..A9BD ; T # Mn [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET +A9E5 ; T # Mn MYANMAR SIGN SHAN SAW +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AA7C ; T # Mn MYANMAR SIGN TAI LAING TONE-2 +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE2F ; T # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +102E0 ; T # Mn COPTIC EPACT THOUSANDS MARK +10376..1037A ; T # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +10AE5..10AE6 ; T # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +10D24..10D27 ; T # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D69..10D6D ; T # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK +10EAB..10EAC ; T # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK +10EFA..10EFF ; T # Mn [6] ARABIC DOUBLE VERTICAL BAR BELOW..ARABIC SMALL LOW WORD MADDA +10F46..10F50 ; T # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; T # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; T # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; T # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +1107F..11081 ; T # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; T # Mn KAITHI VOWEL SIGN VOCALIC R +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11173 ; T # Mn MAHAJANI SIGN NUKTA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +111C9..111CC ; T # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK +111CF ; T # Mn SHARADA SIGN INVERTED CANDRABINDU +1122F..11231 ; T # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11234 ; T # Mn KHOJKI SIGN ANUSVARA +11236..11237 ; T # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; T # Mn KHOJKI SIGN SUKUN +11241 ; T # Mn KHOJKI VOWEL SIGN VOCALIC R +112DF ; T # Mn KHUDAWADI SIGN ANUSVARA +112E3..112EA ; T # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +11300..11301 ; T # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU +1133B..1133C ; T # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA +11340 ; T # Mn GRANTHA VOWEL SIGN II +11366..1136C ; T # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; T # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113BB..113C0 ; T # Mn [6] TULU-TIGALARI VOWEL SIGN U..TULU-TIGALARI VOWEL SIGN VOCALIC LL +113CE ; T # Mn TULU-TIGALARI SIGN VIRAMA +113D0 ; T # Mn TULU-TIGALARI CONJOINER +113D2 ; T # Mn TULU-TIGALARI GEMINATION MARK +113E1..113E2 ; T # Mn [2] TULU-TIGALARI VEDIC TONE SVARITA..TULU-TIGALARI VEDIC TONE ANUDATTA +11438..1143F ; T # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; T # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; T # Mn NEWA SIGN NUKTA +1145E ; T # Mn NEWA SANDHI MARK +114B3..114B8 ; T # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114BA ; T # Mn TIRHUTA VOWEL SIGN SHORT E +114BF..114C0 ; T # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C2..114C3 ; T # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +115B2..115B5 ; T # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115BC..115BD ; T # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BF..115C0 ; T # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +115DC..115DD ; T # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU +11633..1163A ; T # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163D ; T # Mn MODI SIGN ANUSVARA +1163F..11640 ; T # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +1171D ; T # Mn AHOM CONSONANT SIGN MEDIAL LA +1171F ; T # Mn AHOM CONSONANT SIGN MEDIAL LIGATING RA +11722..11725 ; T # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU +11727..1172B ; T # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +1182F..11837 ; T # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA +11839..1183A ; T # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA +1193B..1193C ; T # Mn [2] DIVES AKURU SIGN ANUSVARA..DIVES AKURU SIGN CANDRABINDU +1193E ; T # Mn DIVES AKURU VIRAMA +11943 ; T # Mn DIVES AKURU SIGN NUKTA +119D4..119D7 ; T # Mn [4] NANDINAGARI VOWEL SIGN U..NANDINAGARI VOWEL SIGN VOCALIC RR +119DA..119DB ; T # Mn [2] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN AI +119E0 ; T # Mn NANDINAGARI SIGN VIRAMA +11A01..11A0A ; T # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; T # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; T # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; T # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; T # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; T # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; T # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; T # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11B60 ; T # Mn SHARADA VOWEL SIGN OE +11B62..11B64 ; T # Mn [3] SHARADA VOWEL SIGN UE..SHARADA VOWEL SIGN SHORT E +11B66 ; T # Mn SHARADA VOWEL SIGN CANDRA E +11C30..11C36 ; T # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; T # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; T # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; T # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; T # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; T # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; T # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; T # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; T # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; T # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; T # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; T # Mn MASARAM GONDI RA-KARA +11D90..11D91 ; T # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D95 ; T # Mn GUNJALA GONDI SIGN ANUSVARA +11D97 ; T # Mn GUNJALA GONDI VIRAMA +11EF3..11EF4 ; T # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U +11F00..11F01 ; T # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA +11F36..11F3A ; T # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R +11F40 ; T # Mn KAWI VOWEL SIGN EU +11F42 ; T # Mn KAWI CONJOINER +11F5A ; T # Mn KAWI SIGN NUKTA +13430..1343F ; T # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE +13440 ; T # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY +13447..13455 ; T # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED +1611E..16129 ; T # Mn [12] GURUNG KHEMA VOWEL SIGN AA..GURUNG KHEMA VOWEL LENGTH MARK +1612D..1612F ; T # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA +16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16F4F ; T # Mn MIAO SIGN CONSONANT MODIFIER BAR +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +16FE4 ; T # Mn KHITAN SMALL SCRIPT FILLER +1BC9D..1BC9E ; T # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1BCA0..1BCA3 ; T # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CF00..1CF2D ; T # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; T # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1DA00..1DA36 ; T # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN +1DA3B..1DA6C ; T # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT +1DA75 ; T # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS +1DA84 ; T # Mn SIGNWRITING LOCATION HEAD NECK +1DA9B..1DA9F ; T # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 +1DAA1..1DAAF ; T # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; T # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; T # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; T # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; T # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; T # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E08F ; T # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +1E130..1E136 ; T # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; T # Mn TOTO SIGN RISING TONE +1E2EC..1E2EF ; T # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI +1E4EC..1E4EF ; T # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E5EE..1E5EF ; T # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR +1E6E3 ; T # Mn TAI YO SIGN UE +1E6E6 ; T # Mn TAI YO SIGN AU +1E6EE..1E6EF ; T # Mn [2] TAI YO SIGN AY..TAI YO SIGN ANG +1E6F5 ; T # Mn TAI YO SIGN OM +1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; T # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1E94B ; T # Lm ADLAM NASALIZATION MARK +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 2224 + +# EOF diff --git a/data/18.0.0-derived-joining-type.txt b/data/18.0.0-derived-joining-type.txt new file mode 100644 index 0000000..0fc7029 --- /dev/null +++ b/data/18.0.0-derived-joining-type.txt @@ -0,0 +1,600 @@ +# DerivedJoiningType-18.0.0.txt +# Date: 2026-06-29, 15:25:03 GMT +# © 2026 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use and license, see https://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see https://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +0883..0885 ; C # Lo [3] ARABIC TATWEEL WITH OVERSTRUCK HAMZA..ARABIC TATWEEL WITH TWO DOTS BELOW +180A ; C # Po MONGOLIAN NIRUGU +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 7 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0848 ; D # Lo MANDAIC LETTER ATT +084A..0853 ; D # Lo [10] MANDAIC LETTER AK..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +0860 ; D # Lo SYRIAC LETTER MALAYALAM NGA +0862..0865 ; D # Lo [4] SYRIAC LETTER MALAYALAM NYA..SYRIAC LETTER MALAYALAM NNNA +0868 ; D # Lo SYRIAC LETTER MALAYALAM LLA +0886 ; D # Lo ARABIC LETTER THIN YEH +0889..088D ; D # Lo [5] ARABIC LETTER NOON WITH INVERTED SMALL V..ARABIC LETTER KEHEH WITH TWO DOTS VERTICALLY BELOW +088F ; D # Lo ARABIC LETTER NOON WITH RING ABOVE +08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE +08B3..08B8 ; D # Lo [6] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER TEH WITH SMALL TEH ABOVE +08BA..08C8 ; D # Lo [15] ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE..ARABIC LETTER GRAF +1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER +1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1878 ; D # Lo [53] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER CHA WITH TWO DOTS +1887..18A8 ; D # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; D # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA +10AC0..10AC4 ; D # Lo [5] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER GHIMEL +10AD3..10AD6 ; D # Lo [4] MANICHAEAN LETTER LAMEDH..MANICHAEAN LETTER MEM +10AD8..10ADC ; D # Lo [5] MANICHAEAN LETTER SAMEKH..MANICHAEAN LETTER FE +10ADE..10AE0 ; D # Lo [3] MANICHAEAN LETTER QOPH..MANICHAEAN LETTER QHOPH +10AEB..10AEE ; D # No [4] MANICHAEAN NUMBER ONE..MANICHAEAN NUMBER TWENTY +10B80 ; D # Lo PSALTER PAHLAVI LETTER ALEPH +10B82 ; D # Lo PSALTER PAHLAVI LETTER GIMEL +10B86..10B88 ; D # Lo [3] PSALTER PAHLAVI LETTER ZAYIN..PSALTER PAHLAVI LETTER YODH +10B8A..10B8B ; D # Lo [2] PSALTER PAHLAVI LETTER LAMEDH..PSALTER PAHLAVI LETTER MEM-QOPH +10B8D ; D # Lo PSALTER PAHLAVI LETTER SAMEKH +10B90 ; D # Lo PSALTER PAHLAVI LETTER SHIN +10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY +10D01..10D21 ; D # Lo [33] HANIFI ROHINGYA LETTER BA..HANIFI ROHINGYA VOWEL O +10D23 ; D # Lo HANIFI ROHINGYA MARK NA KHONNA +10EC3..10EC4 ; D # Lo [2] ARABIC LETTER TAH WITH TWO DOTS VERTICALLY BELOW..ARABIC LETTER KAF WITH TWO DOTS VERTICALLY BELOW +10EC6..10EC7 ; D # Lo [2] ARABIC LETTER THIN NOON..ARABIC LETTER YEH WITH FOUR DOTS BELOW +10F30..10F32 ; D # Lo [3] SOGDIAN LETTER ALEPH..SOGDIAN LETTER GIMEL +10F34..10F44 ; D # Lo [17] SOGDIAN LETTER WAW..SOGDIAN LETTER LESH +10F51..10F53 ; D # No [3] SOGDIAN NUMBER ONE..SOGDIAN NUMBER TWENTY +10F70..10F73 ; D # Lo [4] OLD UYGHUR LETTER ALEPH..OLD UYGHUR LETTER WAW +10F76..10F81 ; D # Lo [12] OLD UYGHUR LETTER YODH..OLD UYGHUR LETTER LESH +10FB0 ; D # Lo CHORASMIAN LETTER ALEPH +10FB2..10FB3 ; D # Lo [2] CHORASMIAN LETTER BETH..CHORASMIAN LETTER GIMEL +10FB8 ; D # Lo CHORASMIAN LETTER ZAYIN +10FBB..10FBC ; D # Lo [2] CHORASMIAN LETTER KAPH..CHORASMIAN LETTER LAMEDH +10FBE..10FBF ; D # Lo [2] CHORASMIAN LETTER NUN..CHORASMIAN LETTER SAMEKH +10FC1 ; D # Lo CHORASMIAN LETTER PE +10FC4 ; D # Lo CHORASMIAN LETTER TAW +10FCA ; D # No CHORASMIAN NUMBER TWENTY +1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA + +# Total code points: 615 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846..0847 ; R # Lo [2] MANDAIC LETTER AZ..MANDAIC LETTER IT +0849 ; R # Lo MANDAIC LETTER AKSA +0854 ; R # Lo MANDAIC LETTER ASH +0856..0858 ; R # Lo [3] MANDAIC LETTER DUSHENNA..MANDAIC LETTER AIN +0867 ; R # Lo SYRIAC LETTER MALAYALAM RA +0869..086A ; R # Lo [2] SYRIAC LETTER MALAYALAM LLLA..SYRIAC LETTER MALAYALAM SSA +0870..0882 ; R # Lo [19] ARABIC LETTER ALEF WITH ATTACHED FATHA..ARABIC LETTER ALEF WITH ATTACHED LEFT HAMZA +088E ; R # Lo ARABIC VERTICAL TAIL +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH +08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW +08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE +08B9 ; R # Lo ARABIC LETTER REH WITH SMALL NOON ABOVE +10AC5 ; R # Lo MANICHAEAN LETTER DALETH +10AC7 ; R # Lo MANICHAEAN LETTER WAW +10AC9..10ACA ; R # Lo [2] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER ZHAYIN +10ACE..10AD2 ; R # Lo [5] MANICHAEAN LETTER TETH..MANICHAEAN LETTER KHAPH +10ADD ; R # Lo MANICHAEAN LETTER SADHE +10AE1 ; R # Lo MANICHAEAN LETTER RESH +10AE4 ; R # Lo MANICHAEAN LETTER TAW +10AEF ; R # No MANICHAEAN NUMBER ONE HUNDRED +10B81 ; R # Lo PSALTER PAHLAVI LETTER BETH +10B83..10B85 ; R # Lo [3] PSALTER PAHLAVI LETTER DALETH..PSALTER PAHLAVI LETTER WAW-AYIN-RESH +10B89 ; R # Lo PSALTER PAHLAVI LETTER KAPH +10B8C ; R # Lo PSALTER PAHLAVI LETTER NUN +10B8E..10B8F ; R # Lo [2] PSALTER PAHLAVI LETTER PE..PSALTER PAHLAVI LETTER SADHE +10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW +10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR +10D22 ; R # Lo HANIFI ROHINGYA MARK SAKIN +10EC2 ; R # Lo ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW +10F33 ; R # Lo SOGDIAN LETTER HE +10F54 ; R # No SOGDIAN NUMBER ONE HUNDRED +10F74..10F75 ; R # Lo [2] OLD UYGHUR LETTER ZAYIN..OLD UYGHUR LETTER FINAL HETH +10FB4..10FB6 ; R # Lo [3] CHORASMIAN LETTER DALETH..CHORASMIAN LETTER WAW +10FB9..10FBA ; R # Lo [2] CHORASMIAN LETTER HETH..CHORASMIAN LETTER YODH +10FBD ; R # Lo CHORASMIAN LETTER MEM +10FC2..10FC3 ; R # Lo [2] CHORASMIAN LETTER RESH..CHORASMIAN LETTER SHIN +10FC9 ; R # No CHORASMIAN NUMBER TEN + +# Total code points: 153 + +# ================================================ + +# Joining_Type=Left_Joining + +A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA +10ACD ; L # Lo MANICHAEAN LETTER HETH +10AD7 ; L # Lo MANICHAEAN LETTER NUN +10D00 ; L # Lo HANIFI ROHINGYA LETTER A +10ED9..10EEE ; L # Lo [22] ARABIC CROWN LETTER BEH..ARABIC CROWN LETTER YEH +10FCB ; L # No CHORASMIAN NUMBER ONE HUNDRED + +# Total code points: 27 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7..05C9 ; T # Mn [3] HEBREW POINT QAMATS QATAN..HEBREW POINT DAGESH HAZAQ MUDGASH +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; T # Cf ARABIC LETTER MARK +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +07FD ; T # Mn NKO DANTAYALAN +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +0897..089F ; T # Mn [9] ARABIC PEPET..ARABIC HALF MADDA OVER MADDA +08CA..08E1 ; T # Mn [24] ARABIC SMALL HIGH FARSI YEH..ARABIC SMALL HIGH SIGN SAFHA +08E3..0902 ; T # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +09FE ; T # Mn BENGALI SANDHI MARK +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0AFA..0AFF ; T # Mn [6] GUJARATI SIGN SUKUN..GUJARATI SIGN TWO-CIRCLE NUKTA ABOVE +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B53..0B56 ; T # Mn [4] ORIYA SIGN DOT ABOVE..ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C00 ; T # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C04 ; T # Mn TELUGU SIGN COMBINING ANUSVARA ABOVE +0C3C ; T # Mn TELUGU SIGN NUKTA +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C81 ; T # Mn KANNADA SIGN CANDRABINDU +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D00..0D01 ; T # Mn [2] MALAYALAM SIGN COMBINING ANUSVARA ABOVE..MALAYALAM SIGN CANDRABINDU +0D3B..0D3C ; T # Mn [2] MALAYALAM SIGN VERTICAL BAR VIRAMA..MALAYALAM SIGN CIRCULAR VIRAMA +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0D81 ; T # Mn SINHALA SIGN CANDRABINDU +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EBC ; T # Mn [9] LAO VOWEL SIGN I..LAO SEMIVOWEL SIGN LO +0EC8..0ECE ; T # Mn [7] LAO TONE MAI EK..LAO YAMAKKAN +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1733 ; T # Mn [2] HANUNOO VOWEL SIGN I..HANUNOO VOWEL SIGN U +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +180F ; T # Mn MONGOLIAN FREE VARIATION SELECTOR FOUR +1885..1886 ; T # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; T # Mn BUGINESE VOWEL SIGN AE +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; T # Me COMBINING PARENTHESES OVERLAY +1ABF..1AF0 ; T # Mn [50] COMBINING LATIN SMALL LETTER W BELOW..COMBINING DOUBLE COMMA ABOVE +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB..1BAD ; T # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1DC0..1DFF ; T # Mn [64] COMBINING DOTTED GRAVE ACCENT..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69E..A69F ; T # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A82C ; T # Mn SYLOTI NAGRI SIGN ALTERNATE HASANTA +A8C4..A8C5 ; T # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A8FF ; T # Mn DEVANAGARI VOWEL SIGN AY +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC..A9BD ; T # Mn [2] JAVANESE VOWEL SIGN PEPET..JAVANESE CONSONANT SIGN KERET +A9E5 ; T # Mn MYANMAR SIGN SHAN SAW +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AA7C ; T # Mn MYANMAR SIGN TAI LAING TONE-2 +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE2F ; T # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +102E0 ; T # Mn COPTIC EPACT THOUSANDS MARK +10376..1037A ; T # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +10AE5..10AE6 ; T # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +10D24..10D27 ; T # Mn [4] HANIFI ROHINGYA SIGN HARBAHAY..HANIFI ROHINGYA SIGN TASSI +10D69..10D6D ; T # Mn [5] GARAY VOWEL SIGN E..GARAY CONSONANT NASALIZATION MARK +10EAB..10EAC ; T # Mn [2] YEZIDI COMBINING HAMZA MARK..YEZIDI COMBINING MADDA MARK +10ECB..10ECF ; T # Mn [5] ARABIC NORTHEAST POINTING ARROWHEAD ABOVE..ARABIC LARGE CIRCLE ABOVE +10EF0..10EFF ; T # Mn [16] ARABIC SMALL LOW UPRIGHT RECTANGULAR ZERO..ARABIC SMALL LOW WORD MADDA +10F46..10F50 ; T # Mn [11] SOGDIAN COMBINING DOT BELOW..SOGDIAN COMBINING STROKE BELOW +10F82..10F85 ; T # Mn [4] OLD UYGHUR COMBINING DOT ABOVE..OLD UYGHUR COMBINING TWO DOTS BELOW +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11070 ; T # Mn BRAHMI SIGN OLD TAMIL VIRAMA +11073..11074 ; T # Mn [2] BRAHMI VOWEL SIGN OLD TAMIL SHORT E..BRAHMI VOWEL SIGN OLD TAMIL SHORT O +1107F..11081 ; T # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110C2 ; T # Mn KAITHI VOWEL SIGN VOCALIC R +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11173 ; T # Mn MAHAJANI SIGN NUKTA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +111C9..111CC ; T # Mn [4] SHARADA SANDHI MARK..SHARADA EXTRA SHORT VOWEL MARK +111CF ; T # Mn SHARADA SIGN INVERTED CANDRABINDU +1122F..11231 ; T # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11234 ; T # Mn KHOJKI SIGN ANUSVARA +11236..11237 ; T # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; T # Mn KHOJKI SIGN SUKUN +11241 ; T # Mn KHOJKI VOWEL SIGN VOCALIC R +112DF ; T # Mn KHUDAWADI SIGN ANUSVARA +112E3..112EA ; T # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +11300..11301 ; T # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU +1133B..1133C ; T # Mn [2] COMBINING BINDU BELOW..GRANTHA SIGN NUKTA +11340 ; T # Mn GRANTHA VOWEL SIGN II +11366..1136C ; T # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; T # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +113BB..113C0 ; T # Mn [6] TULU-TIGALARI VOWEL SIGN U..TULU-TIGALARI VOWEL SIGN VOCALIC LL +113CE ; T # Mn TULU-TIGALARI SIGN VIRAMA +113D0 ; T # Mn TULU-TIGALARI CONJOINER +113D2 ; T # Mn TULU-TIGALARI GEMINATION MARK +113E1..113E2 ; T # Mn [2] TULU-TIGALARI VEDIC TONE SVARITA..TULU-TIGALARI VEDIC TONE ANUDATTA +11438..1143F ; T # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; T # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; T # Mn NEWA SIGN NUKTA +1145E ; T # Mn NEWA SANDHI MARK +114B3..114B8 ; T # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114BA ; T # Mn TIRHUTA VOWEL SIGN SHORT E +114BF..114C0 ; T # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C2..114C3 ; T # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +115B2..115B5 ; T # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115BC..115BD ; T # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BF..115C0 ; T # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +115DC..115DD ; T # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU +11633..1163A ; T # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163D ; T # Mn MODI SIGN ANUSVARA +1163F..11640 ; T # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +1171D ; T # Mn AHOM CONSONANT SIGN MEDIAL LA +1171F ; T # Mn AHOM CONSONANT SIGN MEDIAL LIGATING RA +11722..11725 ; T # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU +11727..1172B ; T # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +1182F..11837 ; T # Mn [9] DOGRA VOWEL SIGN U..DOGRA SIGN ANUSVARA +11839..1183A ; T # Mn [2] DOGRA SIGN VIRAMA..DOGRA SIGN NUKTA +1193B..1193C ; T # Mn [2] DIVES AKURU SIGN ANUSVARA..DIVES AKURU SIGN CANDRABINDU +1193E ; T # Mn DIVES AKURU VIRAMA +11943 ; T # Mn DIVES AKURU SIGN NUKTA +119D4..119D7 ; T # Mn [4] NANDINAGARI VOWEL SIGN U..NANDINAGARI VOWEL SIGN VOCALIC RR +119DA..119DB ; T # Mn [2] NANDINAGARI VOWEL SIGN E..NANDINAGARI VOWEL SIGN AI +119E0 ; T # Mn NANDINAGARI SIGN VIRAMA +11A01..11A0A ; T # Mn [10] ZANABAZAR SQUARE VOWEL SIGN I..ZANABAZAR SQUARE VOWEL LENGTH MARK +11A33..11A38 ; T # Mn [6] ZANABAZAR SQUARE FINAL CONSONANT MARK..ZANABAZAR SQUARE SIGN ANUSVARA +11A3B..11A3E ; T # Mn [4] ZANABAZAR SQUARE CLUSTER-FINAL LETTER YA..ZANABAZAR SQUARE CLUSTER-FINAL LETTER VA +11A47 ; T # Mn ZANABAZAR SQUARE SUBJOINER +11A51..11A56 ; T # Mn [6] SOYOMBO VOWEL SIGN I..SOYOMBO VOWEL SIGN OE +11A59..11A5B ; T # Mn [3] SOYOMBO VOWEL SIGN VOCALIC R..SOYOMBO VOWEL LENGTH MARK +11A8A..11A96 ; T # Mn [13] SOYOMBO FINAL CONSONANT SIGN G..SOYOMBO SIGN ANUSVARA +11A98..11A99 ; T # Mn [2] SOYOMBO GEMINATION MARK..SOYOMBO SUBJOINER +11B60 ; T # Mn SHARADA VOWEL SIGN OE +11B62..11B64 ; T # Mn [3] SHARADA VOWEL SIGN UE..SHARADA VOWEL SIGN SHORT E +11B66 ; T # Mn SHARADA VOWEL SIGN CANDRA E +11C30..11C36 ; T # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; T # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; T # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; T # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; T # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; T # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; T # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +11D31..11D36 ; T # Mn [6] MASARAM GONDI VOWEL SIGN AA..MASARAM GONDI VOWEL SIGN VOCALIC R +11D3A ; T # Mn MASARAM GONDI VOWEL SIGN E +11D3C..11D3D ; T # Mn [2] MASARAM GONDI VOWEL SIGN AI..MASARAM GONDI VOWEL SIGN O +11D3F..11D45 ; T # Mn [7] MASARAM GONDI VOWEL SIGN AU..MASARAM GONDI VIRAMA +11D47 ; T # Mn MASARAM GONDI RA-KARA +11D90..11D91 ; T # Mn [2] GUNJALA GONDI VOWEL SIGN EE..GUNJALA GONDI VOWEL SIGN AI +11D95 ; T # Mn GUNJALA GONDI SIGN ANUSVARA +11D97 ; T # Mn GUNJALA GONDI VIRAMA +11DF0 ; T # Mn BENGALI SIGN COMBINING ANUSVARA ABOVE +11EF3..11EF4 ; T # Mn [2] MAKASAR VOWEL SIGN I..MAKASAR VOWEL SIGN U +11F00..11F01 ; T # Mn [2] KAWI SIGN CANDRABINDU..KAWI SIGN ANUSVARA +11F36..11F3A ; T # Mn [5] KAWI VOWEL SIGN I..KAWI VOWEL SIGN VOCALIC R +11F40 ; T # Mn KAWI VOWEL SIGN EU +11F42 ; T # Mn KAWI CONJOINER +11F5A ; T # Mn KAWI SIGN NUKTA +13430..1343F ; T # Cf [16] EGYPTIAN HIEROGLYPH VERTICAL JOINER..EGYPTIAN HIEROGLYPH END WALLED ENCLOSURE +13440 ; T # Mn EGYPTIAN HIEROGLYPH MIRROR HORIZONTALLY +13447..13455 ; T # Mn [15] EGYPTIAN HIEROGLYPH MODIFIER DAMAGED AT TOP START..EGYPTIAN HIEROGLYPH MODIFIER DAMAGED +1611E..16129 ; T # Mn [12] GURUNG KHEMA VOWEL SIGN AA..GURUNG KHEMA VOWEL LENGTH MARK +1612D..1612F ; T # Mn [3] GURUNG KHEMA SIGN ANUSVARA..GURUNG KHEMA SIGN THOLHOMA +16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16F4F ; T # Mn MIAO SIGN CONSONANT MODIFIER BAR +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +16FE4 ; T # Mn KHITAN SMALL SCRIPT FILLER +1BC9D..1BC9E ; T # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1BCA0..1BCA3 ; T # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1CF00..1CF2D ; T # Mn [46] ZNAMENNY COMBINING MARK GORAZDO NIZKO S KRYZHEM ON LEFT..ZNAMENNY COMBINING MARK KRYZH ON LEFT +1CF30..1CF46 ; T # Mn [23] ZNAMENNY COMBINING TONAL RANGE MARK MRACHNO..ZNAMENNY PRIZNAK MODIFIER ROG +1D127..1D128 ; T # Mn [2] MUSICAL SYMBOL COMBINING STRESS..MUSICAL SYMBOL COMBINING UNSTRESS +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1D25B..1D25C ; T # Mn [2] MUSICAL SYMBOL COMBINING TREMOLO-4..MUSICAL SYMBOL COMBINING TREMOLO-5 +1DA00..1DA36 ; T # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN +1DA3B..1DA6C ; T # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT +1DA75 ; T # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS +1DA84 ; T # Mn SIGNWRITING LOCATION HEAD NECK +1DA9B..1DA9F ; T # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 +1DAA1..1DAAF ; T # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; T # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; T # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; T # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; T # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; T # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E08F ; T # Mn COMBINING CYRILLIC SMALL LETTER BYELORUSSIAN-UKRAINIAN I +1E130..1E136 ; T # Mn [7] NYIAKENG PUACHUE HMONG TONE-B..NYIAKENG PUACHUE HMONG TONE-D +1E2AE ; T # Mn TOTO SIGN RISING TONE +1E2EC..1E2EF ; T # Mn [4] WANCHO TONE TUP..WANCHO TONE KOINI +1E4EC..1E4EF ; T # Mn [4] NAG MUNDARI SIGN MUHOR..NAG MUNDARI SIGN SUTUH +1E5EE..1E5EF ; T # Mn [2] OL ONAL SIGN MU..OL ONAL SIGN IKIR +1E6E3 ; T # Mn TAI YO SIGN UE +1E6E6 ; T # Mn TAI YO SIGN AU +1E6EE..1E6EF ; T # Mn [2] TAI YO SIGN AY..TAI YO SIGN ANG +1E6F5 ; T # Mn TAI YO SIGN OM +1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; T # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +1E94B ; T # Lm ADLAM NASALIZATION MARK +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 2255 + +# EOF diff --git a/data/4.1.0-derived-joining-type.txt b/data/4.1.0-derived-joining-type.txt new file mode 100644 index 0000000..b57fa51 --- /dev/null +++ b/data/4.1.0-derived-joining-type.txt @@ -0,0 +1,234 @@ +# DerivedJoiningType-4.1.0.txt +# Date: 2005-02-26, 02:36:56 GMT [MD] +# +# Unicode Character Database +# Copyright (c) 1991-2005 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# For documentation, see UCD.html + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 2 + +# ================================================ + +# Joining_Type=Dual_Joining + +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063A ; D # Lo [8] ARABIC LETTER SEEN..ARABIC LETTER GHAIN +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D ; D # Lo ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE + +# Total code points: 137 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE + +# Total code points: 69 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0486 ; T # Mn [4] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC PSILI PNEUMATA +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05B9 ; T # Mn [41] HEBREW ACCENT ETNAHTA..HEBREW POINT HOLAM +05BB..05BD ; T # Mn [3] HEBREW POINT QUBUTS..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..0615 ; T # Mn [6] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL HIGH TAH +064B..065E ; T # Mn [20] ARABIC FATHATAN..ARABIC FATHA WITH TWO DOTS +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DE ; T # Me ARABIC START OF RUB EL HIZB +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +0901..0902 ; T # Mn [2] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN ANUSVARA +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0954 ; T # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B43 ; T # Mn [3] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC R +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B56 ; T # Mn ORIYA AI LENGTH MARK +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0D41..0D43 ; T # Mn [3] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC R +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EB9 ; T # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; T # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F90..0F97 ; T # Mn [8] TIBETAN SUBJOINED LETTER KA..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032 ; T # Mn MYANMAR VOWEL SIGN AI +1036..1037 ; T # Mn [2] MYANMAR SIGN ANUSVARA..MYANMAR SIGN DOT BELOW +1039 ; T # Mn MYANMAR SIGN VIRAMA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +135F ; T # Mn ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Cf [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1DC0..1DC3 ; T # Mn [4] COMBINING DOTTED GRAVE ACCENT..COMBINING SUSPENSION MARK +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2063 ; T # Cf [4] WORD JOINER..INVISIBLE SEPARATOR +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20EB ; T # Mn [7] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING LONG DOUBLE SOLIDUS OVERLAY +302A..302F ; T # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE23 ; T # Mn [4] COMBINING LIGATURE LEFT HALF..COMBINING DOUBLE TILDE RIGHT HALF +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 975 diff --git a/data/5.0.0-derived-joining-type.txt b/data/5.0.0-derived-joining-type.txt new file mode 100644 index 0000000..232c470 --- /dev/null +++ b/data/5.0.0-derived-joining-type.txt @@ -0,0 +1,248 @@ +# DerivedJoiningType-5.0.0.txt +# Date: 2006-03-09, 23:13:52 GMT [MD] +# +# Unicode Character Database +# Copyright (c) 1991-2006 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# For documentation, see UCD.html + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 3 + +# ================================================ + +# Joining_Type=Dual_Joining + +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063A ; D # Lo [8] ARABIC LETTER SEEN..ARABIC LETTER GHAIN +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D ; D # Lo ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA + +# Total code points: 170 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE + +# Total code points: 69 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0486 ; T # Mn [4] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC PSILI PNEUMATA +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..0615 ; T # Mn [6] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL HIGH TAH +064B..065E ; T # Mn [20] ARABIC FATHATAN..ARABIC FATHA WITH TWO DOTS +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DE ; T # Me ARABIC START OF RUB EL HIZB +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +0901..0902 ; T # Mn [2] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN ANUSVARA +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0954 ; T # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B43 ; T # Mn [3] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC R +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B56 ; T # Mn ORIYA AI LENGTH MARK +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D41..0D43 ; T # Mn [3] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC R +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EB9 ; T # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; T # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F90..0F97 ; T # Mn [8] TIBETAN SUBJOINED LETTER KA..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032 ; T # Mn MYANMAR VOWEL SIGN AI +1036..1037 ; T # Mn [2] MYANMAR SIGN ANUSVARA..MYANMAR SIGN DOT BELOW +1039 ; T # Mn MYANMAR SIGN VIRAMA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +135F ; T # Mn ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Cf [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1DC0..1DCA ; T # Mn [11] COMBINING DOTTED GRAVE ACCENT..COMBINING LATIN SMALL LETTER R BELOW +1DFE..1DFF ; T # Mn [2] COMBINING LEFT ARROWHEAD ABOVE..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2063 ; T # Cf [4] WORD JOINER..INVISIBLE SEPARATOR +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20EF ; T # Mn [11] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING RIGHT ARROW BELOW +302A..302F ; T # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE23 ; T # Mn [4] COMBINING LIGATURE LEFT HALF..COMBINING DOUBLE TILDE RIGHT HALF +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 1021 + +# EOF diff --git a/data/5.1.0-derived-joining-type.txt b/data/5.1.0-derived-joining-type.txt new file mode 100644 index 0000000..fefa936 --- /dev/null +++ b/data/5.1.0-derived-joining-type.txt @@ -0,0 +1,283 @@ +# DerivedJoiningType-5.1.0.txt +# Date: 2008-03-03, 21:57:37 GMT [MD] +# +# Unicode Character Database +# Copyright (c) 1991-2008 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# For documentation, see UCD.html + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 3 + +# ================================================ + +# Joining_Type=Dual_Joining + +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA + +# Total code points: 188 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE + +# Total code points: 74 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +064B..065E ; T # Mn [20] ARABIC FATHATAN..ARABIC FATHA WITH TWO DOTS +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DE ; T # Me ARABIC START OF RUB EL HIZB +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +0901..0902 ; T # Mn [2] DEVANAGARI SIGN CANDRABINDU..DEVANAGARI SIGN ANUSVARA +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0954 ; T # Mn [4] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI ACUTE ACCENT +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B56 ; T # Mn ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EB9 ; T # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; T # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F90..0F97 ; T # Mn [8] TIBETAN SUBJOINED LETTER KA..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +135F ; T # Mn ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Cf [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1DC0..1DE6 ; T # Mn [39] COMBINING DOTTED GRAVE ACCENT..COMBINING LATIN SMALL LETTER Z +1DFE..1DFF ; T # Mn [2] COMBINING LEFT ARROWHEAD ABOVE..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302F ; T # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A67C..A67D ; T # Mn [2] COMBINING CYRILLIC KAVYKA..COMBINING CYRILLIC PAYEROK +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A8C4 ; T # Mn SAURASHTRA SIGN VIRAMA +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE26 ; T # Mn [7] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 1177 + +# EOF diff --git a/data/5.2.0-derived-joining-type.txt b/data/5.2.0-derived-joining-type.txt new file mode 100644 index 0000000..d4dcc85 --- /dev/null +++ b/data/5.2.0-derived-joining-type.txt @@ -0,0 +1,318 @@ +# DerivedJoiningType-5.2.0.txt +# Date: 2009-05-28, 20:37:39 GMT [MD] +# +# Unicode Character Database +# Copyright (c) 1991-2009 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# For documentation, see http://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 3 + +# ================================================ + +# Joining_Type=Dual_Joining + +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA + +# Total code points: 188 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE + +# Total code points: 74 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +064B..065E ; T # Mn [20] ARABIC FATHATAN..ARABIC FATHA WITH TWO DOTS +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DE ; T # Me ARABIC START OF RUB EL HIZB +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0900..0902 ; T # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0955 ; T # Mn [5] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN CANDRA LONG E +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B56 ; T # Mn ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EB9 ; T # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; T # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F90..0F97 ; T # Mn [8] TIBETAN SUBJOINED LETTER KA..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135F ; T # Mn ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Cf [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1DC0..1DE6 ; T # Mn [39] COMBINING DOTTED GRAVE ACCENT..COMBINING LATIN SMALL LETTER Z +1DFD..1DFF ; T # Mn [3] COMBINING ALMOST EQUAL TO BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302F ; T # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A67C..A67D ; T # Mn [2] COMBINING CYRILLIC KAVYKA..COMBINING CYRILLIC PAYEROK +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A8C4 ; T # Mn SAURASHTRA SIGN VIRAMA +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC ; T # Mn JAVANESE VOWEL SIGN PEPET +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE26 ; T # Mn [7] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +11080..11081 ; T # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110BD ; T # Cf KAITHI NUMBER SIGN +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 1308 + +# EOF diff --git a/data/6.0.0-derived-joining-type.txt b/data/6.0.0-derived-joining-type.txt new file mode 100644 index 0000000..32272c7 --- /dev/null +++ b/data/6.0.0-derived-joining-type.txt @@ -0,0 +1,327 @@ +# DerivedJoiningType-6.0.0.txt +# Date: 2010-08-19, 00:48:10 GMT [MD] +# +# Unicode Character Database +# Copyright (c) 1991-2010 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# For documentation, see http://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 3 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA + +# Total code points: 189 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE + +# Total code points: 74 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +0900..0902 ; T # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B56 ; T # Mn ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EB9 ; T # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; T # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Cf [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1DC0..1DE6 ; T # Mn [39] COMBINING DOTTED GRAVE ACCENT..COMBINING LATIN SMALL LETTER Z +1DFC..1DFF ; T # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302F ; T # Mn [6] IDEOGRAPHIC LEVEL TONE MARK..HANGUL DOUBLE DOT TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A67C..A67D ; T # Mn [2] COMBINING CYRILLIC KAVYKA..COMBINING CYRILLIC PAYEROK +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A8C4 ; T # Mn SAURASHTRA SIGN VIRAMA +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC ; T # Mn JAVANESE VOWEL SIGN PEPET +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE26 ; T # Mn [7] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11080..11081 ; T # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110BD ; T # Cf KAITHI NUMBER SIGN +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 1344 + +# EOF diff --git a/data/6.1.0-derived-joining-type.txt b/data/6.1.0-derived-joining-type.txt new file mode 100644 index 0000000..f9d7c7a --- /dev/null +++ b/data/6.1.0-derived-joining-type.txt @@ -0,0 +1,356 @@ +# DerivedJoiningType-6.1.0.txt +# Date: 2011-11-27, 05:10:23 GMT [MD] +# +# Unicode Character Database +# Copyright (c) 1991-2011 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# For documentation, see http://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 3 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0847..0848 ; D # Lo [2] MANDAIC LETTER IT..MANDAIC LETTER ATT +084A..084E ; D # Lo [5] MANDAIC LETTER AK..MANDAIC LETTER AS +0850..0853 ; D # Lo [4] MANDAIC LETTER AP..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +08A0 ; D # Lo ARABIC LETTER BEH WITH SMALL V BELOW +08A2..08A9 ; D # Lo [8] ARABIC LETTER JEEM WITH TWO DOTS ABOVE..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE + +# Total code points: 215 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846 ; R # Lo MANDAIC LETTER AZ +0849 ; R # Lo MANDAIC LETTER AKSA +084F ; R # Lo MANDAIC LETTER IN +0854 ; R # Lo MANDAIC LETTER ASH +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH + +# Total code points: 82 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08E4..08FE ; T # Mn [27] ARABIC CURLY FATHA..ARABIC DAMMA WITH DOT +0900..0902 ; T # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B56 ; T # Mn ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EB9 ; T # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; T # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB ; T # Mn SUNDANESE SIGN VIRAMA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1DC0..1DE6 ; T # Mn [39] COMBINING DOTTED GRAVE ACCENT..COMBINING LATIN SMALL LETTER Z +1DFC..1DFF ; T # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69F ; T # Mn COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A8C4 ; T # Mn SAURASHTRA SIGN VIRAMA +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC ; T # Mn JAVANESE VOWEL SIGN PEPET +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE26 ; T # Mn [7] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11080..11081 ; T # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110BD ; T # Cf KAITHI NUMBER SIGN +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 1423 + +# EOF diff --git a/data/6.2.0-derived-joining-type.txt b/data/6.2.0-derived-joining-type.txt new file mode 100644 index 0000000..f8cfd1d --- /dev/null +++ b/data/6.2.0-derived-joining-type.txt @@ -0,0 +1,356 @@ +# DerivedJoiningType-6.2.0.txt +# Date: 2012-05-23, 20:34:48 GMT [MD] +# +# Unicode Character Database +# Copyright (c) 1991-2012 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# For documentation, see http://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 3 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0847..0848 ; D # Lo [2] MANDAIC LETTER IT..MANDAIC LETTER ATT +084A..084E ; D # Lo [5] MANDAIC LETTER AK..MANDAIC LETTER AS +0850..0853 ; D # Lo [4] MANDAIC LETTER AP..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +08A0 ; D # Lo ARABIC LETTER BEH WITH SMALL V BELOW +08A2..08A9 ; D # Lo [8] ARABIC LETTER JEEM WITH TWO DOTS ABOVE..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE + +# Total code points: 215 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846 ; R # Lo MANDAIC LETTER AZ +0849 ; R # Lo MANDAIC LETTER AKSA +084F ; R # Lo MANDAIC LETTER IN +0854 ; R # Lo MANDAIC LETTER ASH +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH + +# Total code points: 82 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08E4..08FE ; T # Mn [27] ARABIC CURLY FATHA..ARABIC DAMMA WITH DOT +0900..0902 ; T # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B56 ; T # Mn ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EB9 ; T # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; T # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB ; T # Mn SUNDANESE SIGN VIRAMA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1DC0..1DE6 ; T # Mn [39] COMBINING DOTTED GRAVE ACCENT..COMBINING LATIN SMALL LETTER Z +1DFC..1DFF ; T # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69F ; T # Mn COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A8C4 ; T # Mn SAURASHTRA SIGN VIRAMA +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC ; T # Mn JAVANESE VOWEL SIGN PEPET +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE26 ; T # Mn [7] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11080..11081 ; T # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110BD ; T # Cf KAITHI NUMBER SIGN +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 1423 + +# EOF diff --git a/data/6.3.0-derived-joining-type.txt b/data/6.3.0-derived-joining-type.txt new file mode 100644 index 0000000..5cc2818 --- /dev/null +++ b/data/6.3.0-derived-joining-type.txt @@ -0,0 +1,374 @@ +# DerivedJoiningType-6.3.0.txt +# Date: 2013-03-02, 16:07:37 GMT [MD] +# +# Unicode Character Database +# Copyright (c) 1991-2013 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# For documentation, see http://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +180A ; C # Po MONGOLIAN NIRUGU +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 4 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0847..0848 ; D # Lo [2] MANDAIC LETTER IT..MANDAIC LETTER ATT +084A..084E ; D # Lo [5] MANDAIC LETTER AK..MANDAIC LETTER AS +0850..0853 ; D # Lo [4] MANDAIC LETTER AP..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +08A0 ; D # Lo ARABIC LETTER BEH WITH SMALL V BELOW +08A2..08A9 ; D # Lo [8] ARABIC LETTER JEEM WITH TWO DOTS ABOVE..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER +1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1877 ; D # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA +1887..18A8 ; D # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; D # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA + +# Total code points: 389 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846 ; R # Lo MANDAIC LETTER AZ +0849 ; R # Lo MANDAIC LETTER AKSA +084F ; R # Lo MANDAIC LETTER IN +0854 ; R # Lo MANDAIC LETTER ASH +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH + +# Total code points: 82 + +# ================================================ + +# Joining_Type=Left_Joining + +A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA + +# Total code points: 1 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; T # Cf ARABIC LETTER MARK +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08E4..08FE ; T # Mn [27] ARABIC CURLY FATHA..ARABIC DAMMA WITH DOT +0900..0902 ; T # Mn [3] DEVANAGARI SIGN INVERTED CANDRABINDU..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B56 ; T # Mn ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EB9 ; T # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; T # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; T # Mn BUGINESE VOWEL SIGN AE +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB ; T # Mn SUNDANESE SIGN VIRAMA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1DC0..1DE6 ; T # Mn [39] COMBINING DOTTED GRAVE ACCENT..COMBINING LATIN SMALL LETTER Z +1DFC..1DFF ; T # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69F ; T # Mn COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A8C4 ; T # Mn SAURASHTRA SIGN VIRAMA +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC ; T # Mn JAVANESE VOWEL SIGN PEPET +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE26 ; T # Mn [7] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +11080..11081 ; T # Mn [2] KAITHI SIGN CANDRABINDU..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110BD ; T # Cf KAITHI NUMBER SIGN +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 1425 + +# EOF diff --git a/data/7.0.0-derived-joining-type.txt b/data/7.0.0-derived-joining-type.txt new file mode 100644 index 0000000..9381eb9 --- /dev/null +++ b/data/7.0.0-derived-joining-type.txt @@ -0,0 +1,441 @@ +# DerivedJoiningType-7.0.0.txt +# Date: 2014-02-07, 18:42:13 GMT [MD] +# +# Unicode Character Database +# Copyright (c) 1991-2014 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# For documentation, see http://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +180A ; C # Po MONGOLIAN NIRUGU +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 4 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0847..0848 ; D # Lo [2] MANDAIC LETTER IT..MANDAIC LETTER ATT +084A..084E ; D # Lo [5] MANDAIC LETTER AK..MANDAIC LETTER AS +0850..0853 ; D # Lo [4] MANDAIC LETTER AP..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE +1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER +1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1877 ; D # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA +1887..18A8 ; D # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; D # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA +10AC0..10AC4 ; D # Lo [5] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER GHIMEL +10AD3..10AD6 ; D # Lo [4] MANICHAEAN LETTER LAMEDH..MANICHAEAN LETTER MEM +10AD8..10ADC ; D # Lo [5] MANICHAEAN LETTER SAMEKH..MANICHAEAN LETTER FE +10ADE..10AE0 ; D # Lo [3] MANICHAEAN LETTER QOPH..MANICHAEAN LETTER QHOPH +10AEB..10AEE ; D # No [4] MANICHAEAN NUMBER ONE..MANICHAEAN NUMBER TWENTY +10B80 ; D # Lo PSALTER PAHLAVI LETTER ALEPH +10B82 ; D # Lo PSALTER PAHLAVI LETTER GIMEL +10B86..10B88 ; D # Lo [3] PSALTER PAHLAVI LETTER ZAYIN..PSALTER PAHLAVI LETTER YODH +10B8A..10B8B ; D # Lo [2] PSALTER PAHLAVI LETTER LAMEDH..PSALTER PAHLAVI LETTER MEM-QOPH +10B8D ; D # Lo PSALTER PAHLAVI LETTER SAMEKH +10B90 ; D # Lo PSALTER PAHLAVI LETTER SHIN +10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY + +# Total code points: 424 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846 ; R # Lo MANDAIC LETTER AZ +0849 ; R # Lo MANDAIC LETTER AKSA +084F ; R # Lo MANDAIC LETTER IN +0854 ; R # Lo MANDAIC LETTER ASH +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH +08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW +08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE +10AC5 ; R # Lo MANICHAEAN LETTER DALETH +10AC7 ; R # Lo MANICHAEAN LETTER WAW +10AC9..10ACA ; R # Lo [2] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER ZHAYIN +10ACE..10AD2 ; R # Lo [5] MANICHAEAN LETTER TETH..MANICHAEAN LETTER KHAPH +10ADD ; R # Lo MANICHAEAN LETTER SADHE +10AE1 ; R # Lo MANICHAEAN LETTER RESH +10AE4 ; R # Lo MANICHAEAN LETTER TAW +10AEF ; R # No MANICHAEAN NUMBER ONE HUNDRED +10B81 ; R # Lo PSALTER PAHLAVI LETTER BETH +10B83..10B85 ; R # Lo [3] PSALTER PAHLAVI LETTER DALETH..PSALTER PAHLAVI LETTER WAW-AYIN-RESH +10B89 ; R # Lo PSALTER PAHLAVI LETTER KAPH +10B8C ; R # Lo PSALTER PAHLAVI LETTER NUN +10B8E..10B8F ; R # Lo [2] PSALTER PAHLAVI LETTER PE..PSALTER PAHLAVI LETTER SADHE +10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW +10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR + +# Total code points: 111 + +# ================================================ + +# Joining_Type=Left_Joining + +A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA +10ACD ; L # Lo MANICHAEAN LETTER HETH +10AD7 ; L # Lo MANICHAEAN LETTER NUN + +# Total code points: 3 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; T # Cf ARABIC LETTER MARK +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08E4..0902 ; T # Mn [31] ARABIC CURLY FATHA..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B56 ; T # Mn ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C00 ; T # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C81 ; T # Mn KANNADA SIGN CANDRABINDU +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D01 ; T # Mn MALAYALAM SIGN CANDRABINDU +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EB9 ; T # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; T # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; T # Mn BUGINESE VOWEL SIGN AE +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; T # Me COMBINING PARENTHESES OVERLAY +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB..1BAD ; T # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1DC0..1DF5 ; T # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DFC..1DFF ; T # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69F ; T # Mn COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A8C4 ; T # Mn SAURASHTRA SIGN VIRAMA +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC ; T # Mn JAVANESE VOWEL SIGN PEPET +A9E5 ; T # Mn MYANMAR SIGN SHAN SAW +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AA7C ; T # Mn MYANMAR SIGN TAI LAING TONE-2 +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE2D ; T # Mn [14] COMBINING LIGATURE LEFT HALF..COMBINING CONJOINING MACRON BELOW +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +102E0 ; T # Mn COPTIC EPACT THOUSANDS MARK +10376..1037A ; T # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +10AE5..10AE6 ; T # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +1107F..11081 ; T # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110BD ; T # Cf KAITHI NUMBER SIGN +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11173 ; T # Mn MAHAJANI SIGN NUKTA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +1122F..11231 ; T # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11234 ; T # Mn KHOJKI SIGN ANUSVARA +11236..11237 ; T # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +112DF ; T # Mn KHUDAWADI SIGN ANUSVARA +112E3..112EA ; T # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +11301 ; T # Mn GRANTHA SIGN CANDRABINDU +1133C ; T # Mn GRANTHA SIGN NUKTA +11340 ; T # Mn GRANTHA VOWEL SIGN II +11366..1136C ; T # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; T # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +114B3..114B8 ; T # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114BA ; T # Mn TIRHUTA VOWEL SIGN SHORT E +114BF..114C0 ; T # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C2..114C3 ; T # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +115B2..115B5 ; T # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115BC..115BD ; T # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BF..115C0 ; T # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +11633..1163A ; T # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163D ; T # Mn MODI SIGN ANUSVARA +1163F..11640 ; T # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +1BC9D..1BC9E ; T # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1BCA0..1BCA3 ; T # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 1567 + +# EOF diff --git a/data/8.0.0-derived-joining-type.txt b/data/8.0.0-derived-joining-type.txt new file mode 100644 index 0000000..3261fe0 --- /dev/null +++ b/data/8.0.0-derived-joining-type.txt @@ -0,0 +1,451 @@ +# DerivedJoiningType-8.0.0.txt +# Date: 2015-02-13, 13:47:12 GMT [MD] +# +# Unicode Character Database +# Copyright (c) 1991-2015 Unicode, Inc. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# For documentation, see http://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +180A ; C # Po MONGOLIAN NIRUGU +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 4 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0848 ; D # Lo MANDAIC LETTER ATT +084A..0853 ; D # Lo [10] MANDAIC LETTER AK..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE +08B3..08B4 ; D # Lo [2] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER KAF WITH DOT BELOW +1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER +1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1877 ; D # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA +1887..18A8 ; D # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; D # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA +10AC0..10AC4 ; D # Lo [5] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER GHIMEL +10AD3..10AD6 ; D # Lo [4] MANICHAEAN LETTER LAMEDH..MANICHAEAN LETTER MEM +10AD8..10ADC ; D # Lo [5] MANICHAEAN LETTER SAMEKH..MANICHAEAN LETTER FE +10ADE..10AE0 ; D # Lo [3] MANICHAEAN LETTER QOPH..MANICHAEAN LETTER QHOPH +10AEB..10AEE ; D # No [4] MANICHAEAN NUMBER ONE..MANICHAEAN NUMBER TWENTY +10B80 ; D # Lo PSALTER PAHLAVI LETTER ALEPH +10B82 ; D # Lo PSALTER PAHLAVI LETTER GIMEL +10B86..10B88 ; D # Lo [3] PSALTER PAHLAVI LETTER ZAYIN..PSALTER PAHLAVI LETTER YODH +10B8A..10B8B ; D # Lo [2] PSALTER PAHLAVI LETTER LAMEDH..PSALTER PAHLAVI LETTER MEM-QOPH +10B8D ; D # Lo PSALTER PAHLAVI LETTER SAMEKH +10B90 ; D # Lo PSALTER PAHLAVI LETTER SHIN +10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY + +# Total code points: 426 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846..0847 ; R # Lo [2] MANDAIC LETTER AZ..MANDAIC LETTER IT +0849 ; R # Lo MANDAIC LETTER AKSA +0854 ; R # Lo MANDAIC LETTER ASH +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH +08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW +08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE +10AC5 ; R # Lo MANICHAEAN LETTER DALETH +10AC7 ; R # Lo MANICHAEAN LETTER WAW +10AC9..10ACA ; R # Lo [2] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER ZHAYIN +10ACE..10AD2 ; R # Lo [5] MANICHAEAN LETTER TETH..MANICHAEAN LETTER KHAPH +10ADD ; R # Lo MANICHAEAN LETTER SADHE +10AE1 ; R # Lo MANICHAEAN LETTER RESH +10AE4 ; R # Lo MANICHAEAN LETTER TAW +10AEF ; R # No MANICHAEAN NUMBER ONE HUNDRED +10B81 ; R # Lo PSALTER PAHLAVI LETTER BETH +10B83..10B85 ; R # Lo [3] PSALTER PAHLAVI LETTER DALETH..PSALTER PAHLAVI LETTER WAW-AYIN-RESH +10B89 ; R # Lo PSALTER PAHLAVI LETTER KAPH +10B8C ; R # Lo PSALTER PAHLAVI LETTER NUN +10B8E..10B8F ; R # Lo [2] PSALTER PAHLAVI LETTER PE..PSALTER PAHLAVI LETTER SADHE +10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW +10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR + +# Total code points: 111 + +# ================================================ + +# Joining_Type=Left_Joining + +A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA +10ACD ; L # Lo MANICHAEAN LETTER HETH +10AD7 ; L # Lo MANICHAEAN LETTER NUN + +# Total code points: 3 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; T # Cf ARABIC LETTER MARK +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08E3..0902 ; T # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B56 ; T # Mn ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C00 ; T # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C81 ; T # Mn KANNADA SIGN CANDRABINDU +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D01 ; T # Mn MALAYALAM SIGN CANDRABINDU +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EB9 ; T # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; T # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; T # Mn BUGINESE VOWEL SIGN AE +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; T # Me COMBINING PARENTHESES OVERLAY +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB..1BAD ; T # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1DC0..1DF5 ; T # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DFC..1DFF ; T # Mn [4] COMBINING DOUBLE INVERTED BREVE BELOW..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69E..A69F ; T # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A8C4 ; T # Mn SAURASHTRA SIGN VIRAMA +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC ; T # Mn JAVANESE VOWEL SIGN PEPET +A9E5 ; T # Mn MYANMAR SIGN SHAN SAW +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AA7C ; T # Mn MYANMAR SIGN TAI LAING TONE-2 +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE2F ; T # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +102E0 ; T # Mn COPTIC EPACT THOUSANDS MARK +10376..1037A ; T # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +10AE5..10AE6 ; T # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +1107F..11081 ; T # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110BD ; T # Cf KAITHI NUMBER SIGN +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11173 ; T # Mn MAHAJANI SIGN NUKTA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +111CA..111CC ; T # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK +1122F..11231 ; T # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11234 ; T # Mn KHOJKI SIGN ANUSVARA +11236..11237 ; T # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +112DF ; T # Mn KHUDAWADI SIGN ANUSVARA +112E3..112EA ; T # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +11300..11301 ; T # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU +1133C ; T # Mn GRANTHA SIGN NUKTA +11340 ; T # Mn GRANTHA VOWEL SIGN II +11366..1136C ; T # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; T # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +114B3..114B8 ; T # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114BA ; T # Mn TIRHUTA VOWEL SIGN SHORT E +114BF..114C0 ; T # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C2..114C3 ; T # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +115B2..115B5 ; T # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115BC..115BD ; T # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BF..115C0 ; T # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +115DC..115DD ; T # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU +11633..1163A ; T # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163D ; T # Mn MODI SIGN ANUSVARA +1163F..11640 ; T # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +1171D..1171F ; T # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA +11722..11725 ; T # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU +11727..1172B ; T # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +1BC9D..1BC9E ; T # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1BCA0..1BCA3 ; T # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1DA00..1DA36 ; T # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN +1DA3B..1DA6C ; T # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT +1DA75 ; T # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS +1DA84 ; T # Mn SIGNWRITING LOCATION HEAD NECK +1DA9B..1DA9F ; T # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 +1DAA1..1DAAF ; T # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 1716 + +# EOF diff --git a/data/9.0.0-derived-joining-type.txt b/data/9.0.0-derived-joining-type.txt new file mode 100644 index 0000000..0fb5439 --- /dev/null +++ b/data/9.0.0-derived-joining-type.txt @@ -0,0 +1,475 @@ +# DerivedJoiningType-9.0.0.txt +# Date: 2016-06-01, 10:34:26 GMT +# © 2016 Unicode®, Inc. +# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries. +# For terms of use, see http://www.unicode.org/terms_of_use.html +# +# Unicode Character Database +# For documentation, see http://www.unicode.org/reports/tr44/ + +# ================================================ + +# Type T is derived, as described in ArabicShaping.txt + +# All code points not explicitly listed for Joining_Type +# have the value Non_Joining (U). + +# @missing: 0000..10FFFF; Non_Joining + +# ================================================ + +# Joining_Type=Join_Causing + +0640 ; C # Lm ARABIC TATWEEL +07FA ; C # Lm NKO LAJANYALAN +180A ; C # Po MONGOLIAN NIRUGU +200D ; C # Cf ZERO WIDTH JOINER + +# Total code points: 4 + +# ================================================ + +# Joining_Type=Dual_Joining + +0620 ; D # Lo ARABIC LETTER KASHMIRI YEH +0626 ; D # Lo ARABIC LETTER YEH WITH HAMZA ABOVE +0628 ; D # Lo ARABIC LETTER BEH +062A..062E ; D # Lo [5] ARABIC LETTER TEH..ARABIC LETTER KHAH +0633..063F ; D # Lo [13] ARABIC LETTER SEEN..ARABIC LETTER FARSI YEH WITH THREE DOTS ABOVE +0641..0647 ; D # Lo [7] ARABIC LETTER FEH..ARABIC LETTER HEH +0649..064A ; D # Lo [2] ARABIC LETTER ALEF MAKSURA..ARABIC LETTER YEH +066E..066F ; D # Lo [2] ARABIC LETTER DOTLESS BEH..ARABIC LETTER DOTLESS QAF +0678..0687 ; D # Lo [16] ARABIC LETTER HIGH HAMZA YEH..ARABIC LETTER TCHEHEH +069A..06BF ; D # Lo [38] ARABIC LETTER SEEN WITH DOT BELOW AND DOT ABOVE..ARABIC LETTER TCHEH WITH DOT ABOVE +06C1..06C2 ; D # Lo [2] ARABIC LETTER HEH GOAL..ARABIC LETTER HEH GOAL WITH HAMZA ABOVE +06CC ; D # Lo ARABIC LETTER FARSI YEH +06CE ; D # Lo ARABIC LETTER YEH WITH SMALL V +06D0..06D1 ; D # Lo [2] ARABIC LETTER E..ARABIC LETTER YEH WITH THREE DOTS BELOW +06FA..06FC ; D # Lo [3] ARABIC LETTER SHEEN WITH DOT BELOW..ARABIC LETTER GHAIN WITH DOT BELOW +06FF ; D # Lo ARABIC LETTER HEH WITH INVERTED V +0712..0714 ; D # Lo [3] SYRIAC LETTER BETH..SYRIAC LETTER GAMAL GARSHUNI +071A..071D ; D # Lo [4] SYRIAC LETTER HETH..SYRIAC LETTER YUDH +071F..0727 ; D # Lo [9] SYRIAC LETTER KAPH..SYRIAC LETTER REVERSED PE +0729 ; D # Lo SYRIAC LETTER QAPH +072B ; D # Lo SYRIAC LETTER SHIN +072D..072E ; D # Lo [2] SYRIAC LETTER PERSIAN BHETH..SYRIAC LETTER PERSIAN GHAMAL +074E..0758 ; D # Lo [11] SYRIAC LETTER SOGDIAN KHAPH..ARABIC LETTER HAH WITH THREE DOTS POINTING UPWARDS BELOW +075C..076A ; D # Lo [15] ARABIC LETTER SEEN WITH FOUR DOTS ABOVE..ARABIC LETTER LAM WITH BAR +076D..0770 ; D # Lo [4] ARABIC LETTER SEEN WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER SEEN WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0772 ; D # Lo ARABIC LETTER HAH WITH SMALL ARABIC LETTER TAH ABOVE +0775..0777 ; D # Lo [3] ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER FARSI YEH WITH EXTENDED ARABIC-INDIC DIGIT FOUR BELOW +077A..077F ; D # Lo [6] ARABIC LETTER YEH BARREE WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER KAF WITH TWO DOTS ABOVE +07CA..07EA ; D # Lo [33] NKO LETTER A..NKO LETTER JONA RA +0841..0845 ; D # Lo [5] MANDAIC LETTER AB..MANDAIC LETTER USHENNA +0848 ; D # Lo MANDAIC LETTER ATT +084A..0853 ; D # Lo [10] MANDAIC LETTER AK..MANDAIC LETTER AR +0855 ; D # Lo MANDAIC LETTER AT +08A0..08A9 ; D # Lo [10] ARABIC LETTER BEH WITH SMALL V BELOW..ARABIC LETTER YEH WITH TWO DOTS BELOW AND DOT ABOVE +08AF..08B0 ; D # Lo [2] ARABIC LETTER SAD WITH THREE DOTS BELOW..ARABIC LETTER GAF WITH INVERTED STROKE +08B3..08B4 ; D # Lo [2] ARABIC LETTER AIN WITH THREE DOTS BELOW..ARABIC LETTER KAF WITH DOT BELOW +08B6..08B8 ; D # Lo [3] ARABIC LETTER BEH WITH SMALL MEEM ABOVE..ARABIC LETTER TEH WITH SMALL TEH ABOVE +08BA..08BD ; D # Lo [4] ARABIC LETTER YEH WITH TWO DOTS BELOW AND SMALL NOON ABOVE..ARABIC LETTER AFRICAN NOON +1807 ; D # Po MONGOLIAN SIBE SYLLABLE BOUNDARY MARKER +1820..1842 ; D # Lo [35] MONGOLIAN LETTER A..MONGOLIAN LETTER CHI +1843 ; D # Lm MONGOLIAN LETTER TODO LONG VOWEL SIGN +1844..1877 ; D # Lo [52] MONGOLIAN LETTER TODO E..MONGOLIAN LETTER MANCHU ZHA +1887..18A8 ; D # Lo [34] MONGOLIAN LETTER ALI GALI A..MONGOLIAN LETTER MANCHU ALI GALI BHA +18AA ; D # Lo MONGOLIAN LETTER MANCHU ALI GALI LHA +A840..A871 ; D # Lo [50] PHAGS-PA LETTER KA..PHAGS-PA SUBJOINED LETTER RA +10AC0..10AC4 ; D # Lo [5] MANICHAEAN LETTER ALEPH..MANICHAEAN LETTER GHIMEL +10AD3..10AD6 ; D # Lo [4] MANICHAEAN LETTER LAMEDH..MANICHAEAN LETTER MEM +10AD8..10ADC ; D # Lo [5] MANICHAEAN LETTER SAMEKH..MANICHAEAN LETTER FE +10ADE..10AE0 ; D # Lo [3] MANICHAEAN LETTER QOPH..MANICHAEAN LETTER QHOPH +10AEB..10AEE ; D # No [4] MANICHAEAN NUMBER ONE..MANICHAEAN NUMBER TWENTY +10B80 ; D # Lo PSALTER PAHLAVI LETTER ALEPH +10B82 ; D # Lo PSALTER PAHLAVI LETTER GIMEL +10B86..10B88 ; D # Lo [3] PSALTER PAHLAVI LETTER ZAYIN..PSALTER PAHLAVI LETTER YODH +10B8A..10B8B ; D # Lo [2] PSALTER PAHLAVI LETTER LAMEDH..PSALTER PAHLAVI LETTER MEM-QOPH +10B8D ; D # Lo PSALTER PAHLAVI LETTER SAMEKH +10B90 ; D # Lo PSALTER PAHLAVI LETTER SHIN +10BAD..10BAE ; D # No [2] PSALTER PAHLAVI NUMBER TEN..PSALTER PAHLAVI NUMBER TWENTY +1E900..1E943 ; D # L& [68] ADLAM CAPITAL LETTER ALIF..ADLAM SMALL LETTER SHA + +# Total code points: 501 + +# ================================================ + +# Joining_Type=Right_Joining + +0622..0625 ; R # Lo [4] ARABIC LETTER ALEF WITH MADDA ABOVE..ARABIC LETTER ALEF WITH HAMZA BELOW +0627 ; R # Lo ARABIC LETTER ALEF +0629 ; R # Lo ARABIC LETTER TEH MARBUTA +062F..0632 ; R # Lo [4] ARABIC LETTER DAL..ARABIC LETTER ZAIN +0648 ; R # Lo ARABIC LETTER WAW +0671..0673 ; R # Lo [3] ARABIC LETTER ALEF WASLA..ARABIC LETTER ALEF WITH WAVY HAMZA BELOW +0675..0677 ; R # Lo [3] ARABIC LETTER HIGH HAMZA ALEF..ARABIC LETTER U WITH HAMZA ABOVE +0688..0699 ; R # Lo [18] ARABIC LETTER DDAL..ARABIC LETTER REH WITH FOUR DOTS ABOVE +06C0 ; R # Lo ARABIC LETTER HEH WITH YEH ABOVE +06C3..06CB ; R # Lo [9] ARABIC LETTER TEH MARBUTA GOAL..ARABIC LETTER VE +06CD ; R # Lo ARABIC LETTER YEH WITH TAIL +06CF ; R # Lo ARABIC LETTER WAW WITH DOT ABOVE +06D2..06D3 ; R # Lo [2] ARABIC LETTER YEH BARREE..ARABIC LETTER YEH BARREE WITH HAMZA ABOVE +06D5 ; R # Lo ARABIC LETTER AE +06EE..06EF ; R # Lo [2] ARABIC LETTER DAL WITH INVERTED V..ARABIC LETTER REH WITH INVERTED V +0710 ; R # Lo SYRIAC LETTER ALAPH +0715..0719 ; R # Lo [5] SYRIAC LETTER DALATH..SYRIAC LETTER ZAIN +071E ; R # Lo SYRIAC LETTER YUDH HE +0728 ; R # Lo SYRIAC LETTER SADHE +072A ; R # Lo SYRIAC LETTER RISH +072C ; R # Lo SYRIAC LETTER TAW +072F ; R # Lo SYRIAC LETTER PERSIAN DHALATH +074D ; R # Lo SYRIAC LETTER SOGDIAN ZHAIN +0759..075B ; R # Lo [3] ARABIC LETTER DAL WITH TWO DOTS VERTICALLY BELOW AND SMALL TAH..ARABIC LETTER REH WITH STROKE +076B..076C ; R # Lo [2] ARABIC LETTER REH WITH TWO DOTS VERTICALLY ABOVE..ARABIC LETTER REH WITH HAMZA ABOVE +0771 ; R # Lo ARABIC LETTER REH WITH SMALL ARABIC LETTER TAH AND TWO DOTS +0773..0774 ; R # Lo [2] ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER ALEF WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0778..0779 ; R # Lo [2] ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT TWO ABOVE..ARABIC LETTER WAW WITH EXTENDED ARABIC-INDIC DIGIT THREE ABOVE +0840 ; R # Lo MANDAIC LETTER HALQA +0846..0847 ; R # Lo [2] MANDAIC LETTER AZ..MANDAIC LETTER IT +0849 ; R # Lo MANDAIC LETTER AKSA +0854 ; R # Lo MANDAIC LETTER ASH +08AA..08AC ; R # Lo [3] ARABIC LETTER REH WITH LOOP..ARABIC LETTER ROHINGYA YEH +08AE ; R # Lo ARABIC LETTER DAL WITH THREE DOTS BELOW +08B1..08B2 ; R # Lo [2] ARABIC LETTER STRAIGHT WAW..ARABIC LETTER ZAIN WITH INVERTED V ABOVE +08B9 ; R # Lo ARABIC LETTER REH WITH SMALL NOON ABOVE +10AC5 ; R # Lo MANICHAEAN LETTER DALETH +10AC7 ; R # Lo MANICHAEAN LETTER WAW +10AC9..10ACA ; R # Lo [2] MANICHAEAN LETTER ZAYIN..MANICHAEAN LETTER ZHAYIN +10ACE..10AD2 ; R # Lo [5] MANICHAEAN LETTER TETH..MANICHAEAN LETTER KHAPH +10ADD ; R # Lo MANICHAEAN LETTER SADHE +10AE1 ; R # Lo MANICHAEAN LETTER RESH +10AE4 ; R # Lo MANICHAEAN LETTER TAW +10AEF ; R # No MANICHAEAN NUMBER ONE HUNDRED +10B81 ; R # Lo PSALTER PAHLAVI LETTER BETH +10B83..10B85 ; R # Lo [3] PSALTER PAHLAVI LETTER DALETH..PSALTER PAHLAVI LETTER WAW-AYIN-RESH +10B89 ; R # Lo PSALTER PAHLAVI LETTER KAPH +10B8C ; R # Lo PSALTER PAHLAVI LETTER NUN +10B8E..10B8F ; R # Lo [2] PSALTER PAHLAVI LETTER PE..PSALTER PAHLAVI LETTER SADHE +10B91 ; R # Lo PSALTER PAHLAVI LETTER TAW +10BA9..10BAC ; R # No [4] PSALTER PAHLAVI NUMBER ONE..PSALTER PAHLAVI NUMBER FOUR + +# Total code points: 112 + +# ================================================ + +# Joining_Type=Left_Joining + +A872 ; L # Lo PHAGS-PA SUPERFIXED LETTER RA +10ACD ; L # Lo MANICHAEAN LETTER HETH +10AD7 ; L # Lo MANICHAEAN LETTER NUN + +# Total code points: 3 + +# ================================================ + +# Joining_Type=Transparent + +00AD ; T # Cf SOFT HYPHEN +0300..036F ; T # Mn [112] COMBINING GRAVE ACCENT..COMBINING LATIN SMALL LETTER X +0483..0487 ; T # Mn [5] COMBINING CYRILLIC TITLO..COMBINING CYRILLIC POKRYTIE +0488..0489 ; T # Me [2] COMBINING CYRILLIC HUNDRED THOUSANDS SIGN..COMBINING CYRILLIC MILLIONS SIGN +0591..05BD ; T # Mn [45] HEBREW ACCENT ETNAHTA..HEBREW POINT METEG +05BF ; T # Mn HEBREW POINT RAFE +05C1..05C2 ; T # Mn [2] HEBREW POINT SHIN DOT..HEBREW POINT SIN DOT +05C4..05C5 ; T # Mn [2] HEBREW MARK UPPER DOT..HEBREW MARK LOWER DOT +05C7 ; T # Mn HEBREW POINT QAMATS QATAN +0610..061A ; T # Mn [11] ARABIC SIGN SALLALLAHOU ALAYHE WASSALLAM..ARABIC SMALL KASRA +061C ; T # Cf ARABIC LETTER MARK +064B..065F ; T # Mn [21] ARABIC FATHATAN..ARABIC WAVY HAMZA BELOW +0670 ; T # Mn ARABIC LETTER SUPERSCRIPT ALEF +06D6..06DC ; T # Mn [7] ARABIC SMALL HIGH LIGATURE SAD WITH LAM WITH ALEF MAKSURA..ARABIC SMALL HIGH SEEN +06DF..06E4 ; T # Mn [6] ARABIC SMALL HIGH ROUNDED ZERO..ARABIC SMALL HIGH MADDA +06E7..06E8 ; T # Mn [2] ARABIC SMALL HIGH YEH..ARABIC SMALL HIGH NOON +06EA..06ED ; T # Mn [4] ARABIC EMPTY CENTRE LOW STOP..ARABIC SMALL LOW MEEM +070F ; T # Cf SYRIAC ABBREVIATION MARK +0711 ; T # Mn SYRIAC LETTER SUPERSCRIPT ALAPH +0730..074A ; T # Mn [27] SYRIAC PTHAHA ABOVE..SYRIAC BARREKH +07A6..07B0 ; T # Mn [11] THAANA ABAFILI..THAANA SUKUN +07EB..07F3 ; T # Mn [9] NKO COMBINING SHORT HIGH TONE..NKO COMBINING DOUBLE DOT ABOVE +0816..0819 ; T # Mn [4] SAMARITAN MARK IN..SAMARITAN MARK DAGESH +081B..0823 ; T # Mn [9] SAMARITAN MARK EPENTHETIC YUT..SAMARITAN VOWEL SIGN A +0825..0827 ; T # Mn [3] SAMARITAN VOWEL SIGN SHORT A..SAMARITAN VOWEL SIGN U +0829..082D ; T # Mn [5] SAMARITAN VOWEL SIGN LONG I..SAMARITAN MARK NEQUDAA +0859..085B ; T # Mn [3] MANDAIC AFFRICATION MARK..MANDAIC GEMINATION MARK +08D4..08E1 ; T # Mn [14] ARABIC SMALL HIGH WORD AR-RUB..ARABIC SMALL HIGH SIGN SAFHA +08E3..0902 ; T # Mn [32] ARABIC TURNED DAMMA BELOW..DEVANAGARI SIGN ANUSVARA +093A ; T # Mn DEVANAGARI VOWEL SIGN OE +093C ; T # Mn DEVANAGARI SIGN NUKTA +0941..0948 ; T # Mn [8] DEVANAGARI VOWEL SIGN U..DEVANAGARI VOWEL SIGN AI +094D ; T # Mn DEVANAGARI SIGN VIRAMA +0951..0957 ; T # Mn [7] DEVANAGARI STRESS SIGN UDATTA..DEVANAGARI VOWEL SIGN UUE +0962..0963 ; T # Mn [2] DEVANAGARI VOWEL SIGN VOCALIC L..DEVANAGARI VOWEL SIGN VOCALIC LL +0981 ; T # Mn BENGALI SIGN CANDRABINDU +09BC ; T # Mn BENGALI SIGN NUKTA +09C1..09C4 ; T # Mn [4] BENGALI VOWEL SIGN U..BENGALI VOWEL SIGN VOCALIC RR +09CD ; T # Mn BENGALI SIGN VIRAMA +09E2..09E3 ; T # Mn [2] BENGALI VOWEL SIGN VOCALIC L..BENGALI VOWEL SIGN VOCALIC LL +0A01..0A02 ; T # Mn [2] GURMUKHI SIGN ADAK BINDI..GURMUKHI SIGN BINDI +0A3C ; T # Mn GURMUKHI SIGN NUKTA +0A41..0A42 ; T # Mn [2] GURMUKHI VOWEL SIGN U..GURMUKHI VOWEL SIGN UU +0A47..0A48 ; T # Mn [2] GURMUKHI VOWEL SIGN EE..GURMUKHI VOWEL SIGN AI +0A4B..0A4D ; T # Mn [3] GURMUKHI VOWEL SIGN OO..GURMUKHI SIGN VIRAMA +0A51 ; T # Mn GURMUKHI SIGN UDAAT +0A70..0A71 ; T # Mn [2] GURMUKHI TIPPI..GURMUKHI ADDAK +0A75 ; T # Mn GURMUKHI SIGN YAKASH +0A81..0A82 ; T # Mn [2] GUJARATI SIGN CANDRABINDU..GUJARATI SIGN ANUSVARA +0ABC ; T # Mn GUJARATI SIGN NUKTA +0AC1..0AC5 ; T # Mn [5] GUJARATI VOWEL SIGN U..GUJARATI VOWEL SIGN CANDRA E +0AC7..0AC8 ; T # Mn [2] GUJARATI VOWEL SIGN E..GUJARATI VOWEL SIGN AI +0ACD ; T # Mn GUJARATI SIGN VIRAMA +0AE2..0AE3 ; T # Mn [2] GUJARATI VOWEL SIGN VOCALIC L..GUJARATI VOWEL SIGN VOCALIC LL +0B01 ; T # Mn ORIYA SIGN CANDRABINDU +0B3C ; T # Mn ORIYA SIGN NUKTA +0B3F ; T # Mn ORIYA VOWEL SIGN I +0B41..0B44 ; T # Mn [4] ORIYA VOWEL SIGN U..ORIYA VOWEL SIGN VOCALIC RR +0B4D ; T # Mn ORIYA SIGN VIRAMA +0B56 ; T # Mn ORIYA AI LENGTH MARK +0B62..0B63 ; T # Mn [2] ORIYA VOWEL SIGN VOCALIC L..ORIYA VOWEL SIGN VOCALIC LL +0B82 ; T # Mn TAMIL SIGN ANUSVARA +0BC0 ; T # Mn TAMIL VOWEL SIGN II +0BCD ; T # Mn TAMIL SIGN VIRAMA +0C00 ; T # Mn TELUGU SIGN COMBINING CANDRABINDU ABOVE +0C3E..0C40 ; T # Mn [3] TELUGU VOWEL SIGN AA..TELUGU VOWEL SIGN II +0C46..0C48 ; T # Mn [3] TELUGU VOWEL SIGN E..TELUGU VOWEL SIGN AI +0C4A..0C4D ; T # Mn [4] TELUGU VOWEL SIGN O..TELUGU SIGN VIRAMA +0C55..0C56 ; T # Mn [2] TELUGU LENGTH MARK..TELUGU AI LENGTH MARK +0C62..0C63 ; T # Mn [2] TELUGU VOWEL SIGN VOCALIC L..TELUGU VOWEL SIGN VOCALIC LL +0C81 ; T # Mn KANNADA SIGN CANDRABINDU +0CBC ; T # Mn KANNADA SIGN NUKTA +0CBF ; T # Mn KANNADA VOWEL SIGN I +0CC6 ; T # Mn KANNADA VOWEL SIGN E +0CCC..0CCD ; T # Mn [2] KANNADA VOWEL SIGN AU..KANNADA SIGN VIRAMA +0CE2..0CE3 ; T # Mn [2] KANNADA VOWEL SIGN VOCALIC L..KANNADA VOWEL SIGN VOCALIC LL +0D01 ; T # Mn MALAYALAM SIGN CANDRABINDU +0D41..0D44 ; T # Mn [4] MALAYALAM VOWEL SIGN U..MALAYALAM VOWEL SIGN VOCALIC RR +0D4D ; T # Mn MALAYALAM SIGN VIRAMA +0D62..0D63 ; T # Mn [2] MALAYALAM VOWEL SIGN VOCALIC L..MALAYALAM VOWEL SIGN VOCALIC LL +0DCA ; T # Mn SINHALA SIGN AL-LAKUNA +0DD2..0DD4 ; T # Mn [3] SINHALA VOWEL SIGN KETTI IS-PILLA..SINHALA VOWEL SIGN KETTI PAA-PILLA +0DD6 ; T # Mn SINHALA VOWEL SIGN DIGA PAA-PILLA +0E31 ; T # Mn THAI CHARACTER MAI HAN-AKAT +0E34..0E3A ; T # Mn [7] THAI CHARACTER SARA I..THAI CHARACTER PHINTHU +0E47..0E4E ; T # Mn [8] THAI CHARACTER MAITAIKHU..THAI CHARACTER YAMAKKAN +0EB1 ; T # Mn LAO VOWEL SIGN MAI KAN +0EB4..0EB9 ; T # Mn [6] LAO VOWEL SIGN I..LAO VOWEL SIGN UU +0EBB..0EBC ; T # Mn [2] LAO VOWEL SIGN MAI KON..LAO SEMIVOWEL SIGN LO +0EC8..0ECD ; T # Mn [6] LAO TONE MAI EK..LAO NIGGAHITA +0F18..0F19 ; T # Mn [2] TIBETAN ASTROLOGICAL SIGN -KHYUD PA..TIBETAN ASTROLOGICAL SIGN SDONG TSHUGS +0F35 ; T # Mn TIBETAN MARK NGAS BZUNG NYI ZLA +0F37 ; T # Mn TIBETAN MARK NGAS BZUNG SGOR RTAGS +0F39 ; T # Mn TIBETAN MARK TSA -PHRU +0F71..0F7E ; T # Mn [14] TIBETAN VOWEL SIGN AA..TIBETAN SIGN RJES SU NGA RO +0F80..0F84 ; T # Mn [5] TIBETAN VOWEL SIGN REVERSED I..TIBETAN MARK HALANTA +0F86..0F87 ; T # Mn [2] TIBETAN SIGN LCI RTAGS..TIBETAN SIGN YANG RTAGS +0F8D..0F97 ; T # Mn [11] TIBETAN SUBJOINED SIGN LCE TSA CAN..TIBETAN SUBJOINED LETTER JA +0F99..0FBC ; T # Mn [36] TIBETAN SUBJOINED LETTER NYA..TIBETAN SUBJOINED LETTER FIXED-FORM RA +0FC6 ; T # Mn TIBETAN SYMBOL PADMA GDAN +102D..1030 ; T # Mn [4] MYANMAR VOWEL SIGN I..MYANMAR VOWEL SIGN UU +1032..1037 ; T # Mn [6] MYANMAR VOWEL SIGN AI..MYANMAR SIGN DOT BELOW +1039..103A ; T # Mn [2] MYANMAR SIGN VIRAMA..MYANMAR SIGN ASAT +103D..103E ; T # Mn [2] MYANMAR CONSONANT SIGN MEDIAL WA..MYANMAR CONSONANT SIGN MEDIAL HA +1058..1059 ; T # Mn [2] MYANMAR VOWEL SIGN VOCALIC L..MYANMAR VOWEL SIGN VOCALIC LL +105E..1060 ; T # Mn [3] MYANMAR CONSONANT SIGN MON MEDIAL NA..MYANMAR CONSONANT SIGN MON MEDIAL LA +1071..1074 ; T # Mn [4] MYANMAR VOWEL SIGN GEBA KAREN I..MYANMAR VOWEL SIGN KAYAH EE +1082 ; T # Mn MYANMAR CONSONANT SIGN SHAN MEDIAL WA +1085..1086 ; T # Mn [2] MYANMAR VOWEL SIGN SHAN E ABOVE..MYANMAR VOWEL SIGN SHAN FINAL Y +108D ; T # Mn MYANMAR SIGN SHAN COUNCIL EMPHATIC TONE +109D ; T # Mn MYANMAR VOWEL SIGN AITON AI +135D..135F ; T # Mn [3] ETHIOPIC COMBINING GEMINATION AND VOWEL LENGTH MARK..ETHIOPIC COMBINING GEMINATION MARK +1712..1714 ; T # Mn [3] TAGALOG VOWEL SIGN I..TAGALOG SIGN VIRAMA +1732..1734 ; T # Mn [3] HANUNOO VOWEL SIGN I..HANUNOO SIGN PAMUDPOD +1752..1753 ; T # Mn [2] BUHID VOWEL SIGN I..BUHID VOWEL SIGN U +1772..1773 ; T # Mn [2] TAGBANWA VOWEL SIGN I..TAGBANWA VOWEL SIGN U +17B4..17B5 ; T # Mn [2] KHMER VOWEL INHERENT AQ..KHMER VOWEL INHERENT AA +17B7..17BD ; T # Mn [7] KHMER VOWEL SIGN I..KHMER VOWEL SIGN UA +17C6 ; T # Mn KHMER SIGN NIKAHIT +17C9..17D3 ; T # Mn [11] KHMER SIGN MUUSIKATOAN..KHMER SIGN BATHAMASAT +17DD ; T # Mn KHMER SIGN ATTHACAN +180B..180D ; T # Mn [3] MONGOLIAN FREE VARIATION SELECTOR ONE..MONGOLIAN FREE VARIATION SELECTOR THREE +1885..1886 ; T # Mn [2] MONGOLIAN LETTER ALI GALI BALUDA..MONGOLIAN LETTER ALI GALI THREE BALUDA +18A9 ; T # Mn MONGOLIAN LETTER ALI GALI DAGALGA +1920..1922 ; T # Mn [3] LIMBU VOWEL SIGN A..LIMBU VOWEL SIGN U +1927..1928 ; T # Mn [2] LIMBU VOWEL SIGN E..LIMBU VOWEL SIGN O +1932 ; T # Mn LIMBU SMALL LETTER ANUSVARA +1939..193B ; T # Mn [3] LIMBU SIGN MUKPHRENG..LIMBU SIGN SA-I +1A17..1A18 ; T # Mn [2] BUGINESE VOWEL SIGN I..BUGINESE VOWEL SIGN U +1A1B ; T # Mn BUGINESE VOWEL SIGN AE +1A56 ; T # Mn TAI THAM CONSONANT SIGN MEDIAL LA +1A58..1A5E ; T # Mn [7] TAI THAM SIGN MAI KANG LAI..TAI THAM CONSONANT SIGN SA +1A60 ; T # Mn TAI THAM SIGN SAKOT +1A62 ; T # Mn TAI THAM VOWEL SIGN MAI SAT +1A65..1A6C ; T # Mn [8] TAI THAM VOWEL SIGN I..TAI THAM VOWEL SIGN OA BELOW +1A73..1A7C ; T # Mn [10] TAI THAM VOWEL SIGN OA ABOVE..TAI THAM SIGN KHUEN-LUE KARAN +1A7F ; T # Mn TAI THAM COMBINING CRYPTOGRAMMIC DOT +1AB0..1ABD ; T # Mn [14] COMBINING DOUBLED CIRCUMFLEX ACCENT..COMBINING PARENTHESES BELOW +1ABE ; T # Me COMBINING PARENTHESES OVERLAY +1B00..1B03 ; T # Mn [4] BALINESE SIGN ULU RICEM..BALINESE SIGN SURANG +1B34 ; T # Mn BALINESE SIGN REREKAN +1B36..1B3A ; T # Mn [5] BALINESE VOWEL SIGN ULU..BALINESE VOWEL SIGN RA REPA +1B3C ; T # Mn BALINESE VOWEL SIGN LA LENGA +1B42 ; T # Mn BALINESE VOWEL SIGN PEPET +1B6B..1B73 ; T # Mn [9] BALINESE MUSICAL SYMBOL COMBINING TEGEH..BALINESE MUSICAL SYMBOL COMBINING GONG +1B80..1B81 ; T # Mn [2] SUNDANESE SIGN PANYECEK..SUNDANESE SIGN PANGLAYAR +1BA2..1BA5 ; T # Mn [4] SUNDANESE CONSONANT SIGN PANYAKRA..SUNDANESE VOWEL SIGN PANYUKU +1BA8..1BA9 ; T # Mn [2] SUNDANESE VOWEL SIGN PAMEPET..SUNDANESE VOWEL SIGN PANEULEUNG +1BAB..1BAD ; T # Mn [3] SUNDANESE SIGN VIRAMA..SUNDANESE CONSONANT SIGN PASANGAN WA +1BE6 ; T # Mn BATAK SIGN TOMPI +1BE8..1BE9 ; T # Mn [2] BATAK VOWEL SIGN PAKPAK E..BATAK VOWEL SIGN EE +1BED ; T # Mn BATAK VOWEL SIGN KARO O +1BEF..1BF1 ; T # Mn [3] BATAK VOWEL SIGN U FOR SIMALUNGUN SA..BATAK CONSONANT SIGN H +1C2C..1C33 ; T # Mn [8] LEPCHA VOWEL SIGN E..LEPCHA CONSONANT SIGN T +1C36..1C37 ; T # Mn [2] LEPCHA SIGN RAN..LEPCHA SIGN NUKTA +1CD0..1CD2 ; T # Mn [3] VEDIC TONE KARSHANA..VEDIC TONE PRENKHA +1CD4..1CE0 ; T # Mn [13] VEDIC SIGN YAJURVEDIC MIDLINE SVARITA..VEDIC TONE RIGVEDIC KASHMIRI INDEPENDENT SVARITA +1CE2..1CE8 ; T # Mn [7] VEDIC SIGN VISARGA SVARITA..VEDIC SIGN VISARGA ANUDATTA WITH TAIL +1CED ; T # Mn VEDIC SIGN TIRYAK +1CF4 ; T # Mn VEDIC TONE CANDRA ABOVE +1CF8..1CF9 ; T # Mn [2] VEDIC TONE RING ABOVE..VEDIC TONE DOUBLE RING ABOVE +1DC0..1DF5 ; T # Mn [54] COMBINING DOTTED GRAVE ACCENT..COMBINING UP TACK ABOVE +1DFB..1DFF ; T # Mn [5] COMBINING DELETION MARK..COMBINING RIGHT ARROWHEAD AND DOWN ARROWHEAD BELOW +200B ; T # Cf ZERO WIDTH SPACE +200E..200F ; T # Cf [2] LEFT-TO-RIGHT MARK..RIGHT-TO-LEFT MARK +202A..202E ; T # Cf [5] LEFT-TO-RIGHT EMBEDDING..RIGHT-TO-LEFT OVERRIDE +2060..2064 ; T # Cf [5] WORD JOINER..INVISIBLE PLUS +206A..206F ; T # Cf [6] INHIBIT SYMMETRIC SWAPPING..NOMINAL DIGIT SHAPES +20D0..20DC ; T # Mn [13] COMBINING LEFT HARPOON ABOVE..COMBINING FOUR DOTS ABOVE +20DD..20E0 ; T # Me [4] COMBINING ENCLOSING CIRCLE..COMBINING ENCLOSING CIRCLE BACKSLASH +20E1 ; T # Mn COMBINING LEFT RIGHT ARROW ABOVE +20E2..20E4 ; T # Me [3] COMBINING ENCLOSING SCREEN..COMBINING ENCLOSING UPWARD POINTING TRIANGLE +20E5..20F0 ; T # Mn [12] COMBINING REVERSE SOLIDUS OVERLAY..COMBINING ASTERISK ABOVE +2CEF..2CF1 ; T # Mn [3] COPTIC COMBINING NI ABOVE..COPTIC COMBINING SPIRITUS LENIS +2D7F ; T # Mn TIFINAGH CONSONANT JOINER +2DE0..2DFF ; T # Mn [32] COMBINING CYRILLIC LETTER BE..COMBINING CYRILLIC LETTER IOTIFIED BIG YUS +302A..302D ; T # Mn [4] IDEOGRAPHIC LEVEL TONE MARK..IDEOGRAPHIC ENTERING TONE MARK +3099..309A ; T # Mn [2] COMBINING KATAKANA-HIRAGANA VOICED SOUND MARK..COMBINING KATAKANA-HIRAGANA SEMI-VOICED SOUND MARK +A66F ; T # Mn COMBINING CYRILLIC VZMET +A670..A672 ; T # Me [3] COMBINING CYRILLIC TEN MILLIONS SIGN..COMBINING CYRILLIC THOUSAND MILLIONS SIGN +A674..A67D ; T # Mn [10] COMBINING CYRILLIC LETTER UKRAINIAN IE..COMBINING CYRILLIC PAYEROK +A69E..A69F ; T # Mn [2] COMBINING CYRILLIC LETTER EF..COMBINING CYRILLIC LETTER IOTIFIED E +A6F0..A6F1 ; T # Mn [2] BAMUM COMBINING MARK KOQNDON..BAMUM COMBINING MARK TUKWENTIS +A802 ; T # Mn SYLOTI NAGRI SIGN DVISVARA +A806 ; T # Mn SYLOTI NAGRI SIGN HASANTA +A80B ; T # Mn SYLOTI NAGRI SIGN ANUSVARA +A825..A826 ; T # Mn [2] SYLOTI NAGRI VOWEL SIGN U..SYLOTI NAGRI VOWEL SIGN E +A8C4..A8C5 ; T # Mn [2] SAURASHTRA SIGN VIRAMA..SAURASHTRA SIGN CANDRABINDU +A8E0..A8F1 ; T # Mn [18] COMBINING DEVANAGARI DIGIT ZERO..COMBINING DEVANAGARI SIGN AVAGRAHA +A926..A92D ; T # Mn [8] KAYAH LI VOWEL UE..KAYAH LI TONE CALYA PLOPHU +A947..A951 ; T # Mn [11] REJANG VOWEL SIGN I..REJANG CONSONANT SIGN R +A980..A982 ; T # Mn [3] JAVANESE SIGN PANYANGGA..JAVANESE SIGN LAYAR +A9B3 ; T # Mn JAVANESE SIGN CECAK TELU +A9B6..A9B9 ; T # Mn [4] JAVANESE VOWEL SIGN WULU..JAVANESE VOWEL SIGN SUKU MENDUT +A9BC ; T # Mn JAVANESE VOWEL SIGN PEPET +A9E5 ; T # Mn MYANMAR SIGN SHAN SAW +AA29..AA2E ; T # Mn [6] CHAM VOWEL SIGN AA..CHAM VOWEL SIGN OE +AA31..AA32 ; T # Mn [2] CHAM VOWEL SIGN AU..CHAM VOWEL SIGN UE +AA35..AA36 ; T # Mn [2] CHAM CONSONANT SIGN LA..CHAM CONSONANT SIGN WA +AA43 ; T # Mn CHAM CONSONANT SIGN FINAL NG +AA4C ; T # Mn CHAM CONSONANT SIGN FINAL M +AA7C ; T # Mn MYANMAR SIGN TAI LAING TONE-2 +AAB0 ; T # Mn TAI VIET MAI KANG +AAB2..AAB4 ; T # Mn [3] TAI VIET VOWEL I..TAI VIET VOWEL U +AAB7..AAB8 ; T # Mn [2] TAI VIET MAI KHIT..TAI VIET VOWEL IA +AABE..AABF ; T # Mn [2] TAI VIET VOWEL AM..TAI VIET TONE MAI EK +AAC1 ; T # Mn TAI VIET TONE MAI THO +AAEC..AAED ; T # Mn [2] MEETEI MAYEK VOWEL SIGN UU..MEETEI MAYEK VOWEL SIGN AAI +AAF6 ; T # Mn MEETEI MAYEK VIRAMA +ABE5 ; T # Mn MEETEI MAYEK VOWEL SIGN ANAP +ABE8 ; T # Mn MEETEI MAYEK VOWEL SIGN UNAP +ABED ; T # Mn MEETEI MAYEK APUN IYEK +FB1E ; T # Mn HEBREW POINT JUDEO-SPANISH VARIKA +FE00..FE0F ; T # Mn [16] VARIATION SELECTOR-1..VARIATION SELECTOR-16 +FE20..FE2F ; T # Mn [16] COMBINING LIGATURE LEFT HALF..COMBINING CYRILLIC TITLO RIGHT HALF +FEFF ; T # Cf ZERO WIDTH NO-BREAK SPACE +FFF9..FFFB ; T # Cf [3] INTERLINEAR ANNOTATION ANCHOR..INTERLINEAR ANNOTATION TERMINATOR +101FD ; T # Mn PHAISTOS DISC SIGN COMBINING OBLIQUE STROKE +102E0 ; T # Mn COPTIC EPACT THOUSANDS MARK +10376..1037A ; T # Mn [5] COMBINING OLD PERMIC LETTER AN..COMBINING OLD PERMIC LETTER SII +10A01..10A03 ; T # Mn [3] KHAROSHTHI VOWEL SIGN I..KHAROSHTHI VOWEL SIGN VOCALIC R +10A05..10A06 ; T # Mn [2] KHAROSHTHI VOWEL SIGN E..KHAROSHTHI VOWEL SIGN O +10A0C..10A0F ; T # Mn [4] KHAROSHTHI VOWEL LENGTH MARK..KHAROSHTHI SIGN VISARGA +10A38..10A3A ; T # Mn [3] KHAROSHTHI SIGN BAR ABOVE..KHAROSHTHI SIGN DOT BELOW +10A3F ; T # Mn KHAROSHTHI VIRAMA +10AE5..10AE6 ; T # Mn [2] MANICHAEAN ABBREVIATION MARK ABOVE..MANICHAEAN ABBREVIATION MARK BELOW +11001 ; T # Mn BRAHMI SIGN ANUSVARA +11038..11046 ; T # Mn [15] BRAHMI VOWEL SIGN AA..BRAHMI VIRAMA +1107F..11081 ; T # Mn [3] BRAHMI NUMBER JOINER..KAITHI SIGN ANUSVARA +110B3..110B6 ; T # Mn [4] KAITHI VOWEL SIGN U..KAITHI VOWEL SIGN AI +110B9..110BA ; T # Mn [2] KAITHI SIGN VIRAMA..KAITHI SIGN NUKTA +110BD ; T # Cf KAITHI NUMBER SIGN +11100..11102 ; T # Mn [3] CHAKMA SIGN CANDRABINDU..CHAKMA SIGN VISARGA +11127..1112B ; T # Mn [5] CHAKMA VOWEL SIGN A..CHAKMA VOWEL SIGN UU +1112D..11134 ; T # Mn [8] CHAKMA VOWEL SIGN AI..CHAKMA MAAYYAA +11173 ; T # Mn MAHAJANI SIGN NUKTA +11180..11181 ; T # Mn [2] SHARADA SIGN CANDRABINDU..SHARADA SIGN ANUSVARA +111B6..111BE ; T # Mn [9] SHARADA VOWEL SIGN U..SHARADA VOWEL SIGN O +111CA..111CC ; T # Mn [3] SHARADA SIGN NUKTA..SHARADA EXTRA SHORT VOWEL MARK +1122F..11231 ; T # Mn [3] KHOJKI VOWEL SIGN U..KHOJKI VOWEL SIGN AI +11234 ; T # Mn KHOJKI SIGN ANUSVARA +11236..11237 ; T # Mn [2] KHOJKI SIGN NUKTA..KHOJKI SIGN SHADDA +1123E ; T # Mn KHOJKI SIGN SUKUN +112DF ; T # Mn KHUDAWADI SIGN ANUSVARA +112E3..112EA ; T # Mn [8] KHUDAWADI VOWEL SIGN U..KHUDAWADI SIGN VIRAMA +11300..11301 ; T # Mn [2] GRANTHA SIGN COMBINING ANUSVARA ABOVE..GRANTHA SIGN CANDRABINDU +1133C ; T # Mn GRANTHA SIGN NUKTA +11340 ; T # Mn GRANTHA VOWEL SIGN II +11366..1136C ; T # Mn [7] COMBINING GRANTHA DIGIT ZERO..COMBINING GRANTHA DIGIT SIX +11370..11374 ; T # Mn [5] COMBINING GRANTHA LETTER A..COMBINING GRANTHA LETTER PA +11438..1143F ; T # Mn [8] NEWA VOWEL SIGN U..NEWA VOWEL SIGN AI +11442..11444 ; T # Mn [3] NEWA SIGN VIRAMA..NEWA SIGN ANUSVARA +11446 ; T # Mn NEWA SIGN NUKTA +114B3..114B8 ; T # Mn [6] TIRHUTA VOWEL SIGN U..TIRHUTA VOWEL SIGN VOCALIC LL +114BA ; T # Mn TIRHUTA VOWEL SIGN SHORT E +114BF..114C0 ; T # Mn [2] TIRHUTA SIGN CANDRABINDU..TIRHUTA SIGN ANUSVARA +114C2..114C3 ; T # Mn [2] TIRHUTA SIGN VIRAMA..TIRHUTA SIGN NUKTA +115B2..115B5 ; T # Mn [4] SIDDHAM VOWEL SIGN U..SIDDHAM VOWEL SIGN VOCALIC RR +115BC..115BD ; T # Mn [2] SIDDHAM SIGN CANDRABINDU..SIDDHAM SIGN ANUSVARA +115BF..115C0 ; T # Mn [2] SIDDHAM SIGN VIRAMA..SIDDHAM SIGN NUKTA +115DC..115DD ; T # Mn [2] SIDDHAM VOWEL SIGN ALTERNATE U..SIDDHAM VOWEL SIGN ALTERNATE UU +11633..1163A ; T # Mn [8] MODI VOWEL SIGN U..MODI VOWEL SIGN AI +1163D ; T # Mn MODI SIGN ANUSVARA +1163F..11640 ; T # Mn [2] MODI SIGN VIRAMA..MODI SIGN ARDHACANDRA +116AB ; T # Mn TAKRI SIGN ANUSVARA +116AD ; T # Mn TAKRI VOWEL SIGN AA +116B0..116B5 ; T # Mn [6] TAKRI VOWEL SIGN U..TAKRI VOWEL SIGN AU +116B7 ; T # Mn TAKRI SIGN NUKTA +1171D..1171F ; T # Mn [3] AHOM CONSONANT SIGN MEDIAL LA..AHOM CONSONANT SIGN MEDIAL LIGATING RA +11722..11725 ; T # Mn [4] AHOM VOWEL SIGN I..AHOM VOWEL SIGN UU +11727..1172B ; T # Mn [5] AHOM VOWEL SIGN AW..AHOM SIGN KILLER +11C30..11C36 ; T # Mn [7] BHAIKSUKI VOWEL SIGN I..BHAIKSUKI VOWEL SIGN VOCALIC L +11C38..11C3D ; T # Mn [6] BHAIKSUKI VOWEL SIGN E..BHAIKSUKI SIGN ANUSVARA +11C3F ; T # Mn BHAIKSUKI SIGN VIRAMA +11C92..11CA7 ; T # Mn [22] MARCHEN SUBJOINED LETTER KA..MARCHEN SUBJOINED LETTER ZA +11CAA..11CB0 ; T # Mn [7] MARCHEN SUBJOINED LETTER RA..MARCHEN VOWEL SIGN AA +11CB2..11CB3 ; T # Mn [2] MARCHEN VOWEL SIGN U..MARCHEN VOWEL SIGN E +11CB5..11CB6 ; T # Mn [2] MARCHEN SIGN ANUSVARA..MARCHEN SIGN CANDRABINDU +16AF0..16AF4 ; T # Mn [5] BASSA VAH COMBINING HIGH TONE..BASSA VAH COMBINING HIGH-LOW TONE +16B30..16B36 ; T # Mn [7] PAHAWH HMONG MARK CIM TUB..PAHAWH HMONG MARK CIM TAUM +16F8F..16F92 ; T # Mn [4] MIAO TONE RIGHT..MIAO TONE BELOW +1BC9D..1BC9E ; T # Mn [2] DUPLOYAN THICK LETTER SELECTOR..DUPLOYAN DOUBLE MARK +1BCA0..1BCA3 ; T # Cf [4] SHORTHAND FORMAT LETTER OVERLAP..SHORTHAND FORMAT UP STEP +1D167..1D169 ; T # Mn [3] MUSICAL SYMBOL COMBINING TREMOLO-1..MUSICAL SYMBOL COMBINING TREMOLO-3 +1D173..1D17A ; T # Cf [8] MUSICAL SYMBOL BEGIN BEAM..MUSICAL SYMBOL END PHRASE +1D17B..1D182 ; T # Mn [8] MUSICAL SYMBOL COMBINING ACCENT..MUSICAL SYMBOL COMBINING LOURE +1D185..1D18B ; T # Mn [7] MUSICAL SYMBOL COMBINING DOIT..MUSICAL SYMBOL COMBINING TRIPLE TONGUE +1D1AA..1D1AD ; T # Mn [4] MUSICAL SYMBOL COMBINING DOWN BOW..MUSICAL SYMBOL COMBINING SNAP PIZZICATO +1D242..1D244 ; T # Mn [3] COMBINING GREEK MUSICAL TRISEME..COMBINING GREEK MUSICAL PENTASEME +1DA00..1DA36 ; T # Mn [55] SIGNWRITING HEAD RIM..SIGNWRITING AIR SUCKING IN +1DA3B..1DA6C ; T # Mn [50] SIGNWRITING MOUTH CLOSED NEUTRAL..SIGNWRITING EXCITEMENT +1DA75 ; T # Mn SIGNWRITING UPPER BODY TILTING FROM HIP JOINTS +1DA84 ; T # Mn SIGNWRITING LOCATION HEAD NECK +1DA9B..1DA9F ; T # Mn [5] SIGNWRITING FILL MODIFIER-2..SIGNWRITING FILL MODIFIER-6 +1DAA1..1DAAF ; T # Mn [15] SIGNWRITING ROTATION MODIFIER-2..SIGNWRITING ROTATION MODIFIER-16 +1E000..1E006 ; T # Mn [7] COMBINING GLAGOLITIC LETTER AZU..COMBINING GLAGOLITIC LETTER ZHIVETE +1E008..1E018 ; T # Mn [17] COMBINING GLAGOLITIC LETTER ZEMLJA..COMBINING GLAGOLITIC LETTER HERU +1E01B..1E021 ; T # Mn [7] COMBINING GLAGOLITIC LETTER SHTA..COMBINING GLAGOLITIC LETTER YATI +1E023..1E024 ; T # Mn [2] COMBINING GLAGOLITIC LETTER YU..COMBINING GLAGOLITIC LETTER SMALL YUS +1E026..1E02A ; T # Mn [5] COMBINING GLAGOLITIC LETTER YO..COMBINING GLAGOLITIC LETTER FITA +1E8D0..1E8D6 ; T # Mn [7] MENDE KIKAKUI COMBINING NUMBER TEENS..MENDE KIKAKUI COMBINING NUMBER MILLIONS +1E944..1E94A ; T # Mn [7] ADLAM ALIF LENGTHENER..ADLAM NUKTA +E0001 ; T # Cf LANGUAGE TAG +E0020..E007F ; T # Cf [96] TAG SPACE..CANCEL TAG +E0100..E01EF ; T # Mn [240] VARIATION SELECTOR-17..VARIATION SELECTOR-256 + +# Total code points: 1839 + +# EOF diff --git a/data/resources.mjs b/data/resources.mjs index 25e40b5..63bb478 100644 --- a/data/resources.mjs +++ b/data/resources.mjs @@ -184,6 +184,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/4.1.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/4.1.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/4.1.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/4.1.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -213,6 +215,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/5.0.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/5.0.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/5.0.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/5.0.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -242,6 +246,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/5.1.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/5.1.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/5.1.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/5.1.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -271,6 +277,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/5.2.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/5.2.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/5.2.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/5.2.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -306,6 +314,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/6.0.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/6.0.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/6.0.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/6.0.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -342,6 +352,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/6.1.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/6.1.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/6.1.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/6.1.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -378,6 +390,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/6.2.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/6.2.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/6.2.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/6.2.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -415,6 +429,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/6.3.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/6.3.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/6.3.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/6.3.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -452,6 +468,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/7.0.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/7.0.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/7.0.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/7.0.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -489,6 +507,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/8.0.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/8.0.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/8.0.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/8.0.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -526,6 +546,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/9.0.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/9.0.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/9.0.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/9.0.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -563,6 +585,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/10.0.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/10.0.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/10.0.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/10.0.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -602,6 +626,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/11.0.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/11.0.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/11.0.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/11.0.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -651,6 +677,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/12.0.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/12.0.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/12.0.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/12.0.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -700,6 +728,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/12.1.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/12.1.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/12.1.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/12.1.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -749,6 +779,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/13.0.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/13.0.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/13.0.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/13.0.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -798,6 +830,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/14.0.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/14.0.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/14.0.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/14.0.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -847,6 +881,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/15.0.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/15.0.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/15.0.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/15.0.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -896,6 +932,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/15.1.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/15.1.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/15.1.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/15.1.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -945,6 +983,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/16.0.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/16.0.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/16.0.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/16.0.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -994,6 +1034,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/17.0.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/17.0.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/17.0.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/17.0.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': @@ -1043,6 +1085,8 @@ const resources = [ 'line-break': 'https://unicode.org/Public/18.0.0/ucd/LineBreak.txt', 'arabic-shaping': 'https://unicode.org/Public/18.0.0/ucd/ArabicShaping.txt', + 'derived-joining-type': + 'https://unicode.org/Public/18.0.0/ucd/extracted/DerivedJoiningType.txt', 'grapheme-cluster-break': 'https://unicode.org/Public/18.0.0/ucd/auxiliary/GraphemeBreakProperty.txt', 'word-break': diff --git a/index.mjs b/index.mjs index 8c3886d..577483e 100644 --- a/index.mjs +++ b/index.mjs @@ -17,7 +17,8 @@ import parseSpecialCasing from './scripts/parse-special-casing.mjs'; import parseSimpleCaseMapping from './scripts/parse-simple-case-mapping.mjs'; import parseGraphemeWordSentenceBreak from './scripts/parse-grapheme-word-sentence-break.mjs'; import parseVerticalOrientation from './scripts/parse-vertical-orientation.mjs'; -import parseArabicShaping from './scripts/parse-arabic-shaping.mjs'; +import parseJoiningType from './scripts/parse-joining-type.mjs'; +import parseDecompositionMapping from './scripts/parse-decomposition-mapping.mjs'; import parseEmoji from './scripts/parse-emoji.mjs'; import parseEmojiSequences from './scripts/parse-emoji-sequences.mjs'; import parseNames from './scripts/parse-names.mjs'; @@ -173,7 +174,7 @@ const generateData = async (version) => { console.log('Parsing Unicode v%s `Joining_Type`…', version); utils.extend(dirMap, utils.writeFiles({ 'version': version, - 'map': await parseArabicShaping(version), + 'map': await parseJoiningType(version), 'type': 'Joining_Type', })); console.log('Parsing Unicode v%s binary emoji properties…', version); @@ -213,6 +214,12 @@ const generateData = async (version) => { 'map': await parseSpecialCasing(version), 'type': 'Special_Casing', })); + console.log('Parsing Unicode v%s `Decomposition_Mapping`…', version); + utils.extend(dirMap, utils.writeFiles({ + 'version': version, + 'map': await parseDecompositionMapping(version), + 'type': 'Decomposition_Mapping', + })); // Sort array values. for (const property of Object.keys(dirMap)) { if (Array.isArray(dirMap[property])) { diff --git a/scripts/download.mjs b/scripts/download.mjs index 65e4307..366af5d 100644 --- a/scripts/download.mjs +++ b/scripts/download.mjs @@ -65,6 +65,7 @@ const TYPES = [ 'sentence-break', 'vertical-orientation', 'arabic-shaping', + 'derived-joining-type', 'emoji', 'emoji-sequences', 'emoji-test', diff --git a/scripts/parse-arabic-shaping.mjs b/scripts/parse-arabic-shaping.mjs deleted file mode 100644 index 3ecfa2d..0000000 --- a/scripts/parse-arabic-shaping.mjs +++ /dev/null @@ -1,39 +0,0 @@ -import utils from './utils.mjs'; -import valueAliases from 'unicode-property-value-aliases'; -import regenerate from 'regenerate'; - -const aliases = valueAliases.get('Joining_Type'); - -const findCanonicalName = (shortName) => { - const canonicalName = aliases.get(shortName); - if (!canonicalName) { - throw new Error(`Failed to find canonical name for Joining_Type=${shortName}. Update \`unicode-property-value-aliases\`.`); - } - return canonicalName; -}; - -const parseArabicShaping = async (version) => { - const source = utils.readDataFile(version, 'arabic-shaping'); - if (!source) { - return; - } - const map = {}; - const lines = source.split('\n'); - for (const line of lines) { - const trimmed = line.trim(); - if (!trimmed || trimmed.startsWith('#')) { - continue; - } - // Format: `0600; ARABIC NUMBER SIGN; U; No_Joining_Group`. - // Field 1 (schematic name) is a comment; field 2 is the - // Joining_Type value; field 3 (Joining_Group) is out of scope. - const data = trimmed.split(';'); - const codePoint = parseInt(data[0].trim(), 16); - const joiningType = findCanonicalName(data[2].trim()); - map[joiningType] ??= regenerate(); - map[joiningType].add(codePoint); - } - return map; -}; - -export default parseArabicShaping; diff --git a/scripts/parse-decomposition-mapping.mjs b/scripts/parse-decomposition-mapping.mjs new file mode 100644 index 0000000..15305d0 --- /dev/null +++ b/scripts/parse-decomposition-mapping.mjs @@ -0,0 +1,61 @@ +import utils from './utils.mjs'; +import valueAliases from 'unicode-property-value-aliases'; + +// The tags in UnicodeData.txt are the long Decomposition_Type names (e.g. +// ``), not the short aliases the map is keyed by. +const canonicalNames = new Map( + [...valueAliases.get('Decomposition_Type').values()] + .map((name) => [name.toLowerCase(), name]) +); + +const findCanonicalName = (tag) => { + const canonicalName = canonicalNames.get(tag.toLowerCase()); + if (!canonicalName) { + throw new Error(`Failed to find canonical name for Decomposition_Type=${tag}. Update \`unicode-property-value-aliases\`.`); + } + return canonicalName; +}; + +// The column index of Decomposition_Mapping in UnicodeData.txt: +// https://www.unicode.org/reports/tr44/#UnicodeData.txt +const columnIndexOfDecompositionMapping = 5; + +const parseDecompositionMapping = async (version) => { + if (parseInt(version.split('.')[0], 10) < 2) { + // Unicode v1.1.5 uses a pre-standard format, e.g. `<+circled> 0031 + // <-circled>`, with no Decomposition_Type to map the tags onto. + return; + } + const source = utils.readDataFile(version, 'database'); + if (!source) { + return; + } + const map = {}; + const lines = source.split('\n'); + for (const line of lines) { + const trimmed = line.trim(); + if (!trimmed || trimmed.startsWith('#')) { + continue; + } + const data = trimmed.split(';'); + const decomposition = data[columnIndexOfDecompositionMapping].trim(); + if (decomposition === '') { + continue; + } + // Format: ` 0640 064B`, or `0627 0653` for a canonical + // decomposition, which carries no tag. + const match = /^<(\w+)>\s*(.*)$/.exec(decomposition); + const decompositionType = match ? findCanonicalName(match[1]) : 'Canonical'; + const from = parseInt(data[0], 16); + const to = (match ? match[2] : decomposition).split(/\s+/) + .map((codePoint) => parseInt(codePoint, 16)); + if (to.some(Number.isNaN)) { + throw new Error('Cannot parse the unicode data: ' + line); + } + map[decompositionType] ??= new Map(); + map[decompositionType].set(from, to); + } + return map; +}; + +export default parseDecompositionMapping; diff --git a/scripts/parse-joining-type.mjs b/scripts/parse-joining-type.mjs new file mode 100644 index 0000000..c558cdd --- /dev/null +++ b/scripts/parse-joining-type.mjs @@ -0,0 +1,74 @@ +import utils from './utils.mjs'; +import valueAliases from 'unicode-property-value-aliases'; +import regenerate from 'regenerate'; + +const aliases = valueAliases.get('Joining_Type'); + +const findCanonicalName = (shortName) => { + const canonicalName = aliases.get(shortName); + if (!canonicalName) { + throw new Error(`Failed to find canonical name for Joining_Type=${shortName}. Update \`unicode-property-value-aliases\`.`); + } + return canonicalName; +}; + +const parseDerivedJoiningType = (source) => { + const map = {}; + const lines = source.split('\n'); + for (const line of lines) { + const trimmed = line.trim(); + if (!trimmed || trimmed.startsWith('#')) { + continue; + } + // Format: `064B..0655; T # Mn [11] ARABIC FATHATAN..ARABIC HAMZA BELOW`. + const data = trimmed.split(';'); + const [first, last] = data[0].trim().split('..') + .map((codePoint) => parseInt(codePoint, 16)); + const joiningType = findCanonicalName(data[1].split('#')[0].trim()); + map[joiningType] ??= regenerate(); + map[joiningType].addRange(first, last ?? first); + } + // Code points that aren’t listed have the default value `Non_Joining`. + const nonJoining = regenerate().addRange(0, 0x10FFFF); + for (const codePoints of Object.values(map)) { + nonJoining.remove(codePoints); + } + map.Non_Joining = nonJoining; + return map; +}; + +const parseArabicShaping = (source) => { + const map = {}; + const lines = source.split('\n'); + for (const line of lines) { + const trimmed = line.trim(); + if (!trimmed || trimmed.startsWith('#')) { + continue; + } + // Format: `0600; ARABIC NUMBER SIGN; U; No_Joining_Group`. + // Field 1 (schematic name) is a comment; field 2 is the + // Joining_Type value; field 3 (Joining_Group) is out of scope. + const data = trimmed.split(';'); + const codePoint = parseInt(data[0].trim(), 16); + const joiningType = findCanonicalName(data[2].trim()); + map[joiningType] ??= regenerate(); + map[joiningType].add(codePoint); + } + return map; +}; + +const parseJoiningType = async (version) => { + // `DerivedJoiningType.txt` lists the `Transparent` code points that + // `ArabicShaping.txt` leaves implicit, so prefer it where it’s available. + const derivedSource = utils.readDataFile(version, 'derived-joining-type'); + if (derivedSource) { + return parseDerivedJoiningType(derivedSource); + } + const source = utils.readDataFile(version, 'arabic-shaping'); + if (!source) { + return; + } + return parseArabicShaping(source); +}; + +export default parseJoiningType; diff --git a/scripts/utils.mjs b/scripts/utils.mjs index 721c5c6..098b56b 100644 --- a/scripts/utils.mjs +++ b/scripts/utils.mjs @@ -104,7 +104,7 @@ const writeFiles = (options) => { const type = typeof options.type === 'function' ? options.type(item) : options.type; - const isCaseFoldingOrMapping = type === 'Case_Folding' || type === 'Simple_Case_Mapping' || type === 'Special_Casing'; + const isCodePointMapping = type === 'Case_Folding' || type === 'Simple_Case_Mapping' || type === 'Special_Casing' || type === 'Decomposition_Mapping'; const isNamesCanon = type === 'Names' && !subType; const isNameAliases = type === 'Names' && subType === 'name-aliases'; const subdir = isNameAliases ? item.charAt(0).toUpperCase() + item.slice(1) : item; @@ -165,7 +165,7 @@ const writeFiles = (options) => { let symbolsFileContent = `import ranges from './ranges.mjs';\n\nexport default ranges.flatMap((r) => Array.from(r.values()));\n`; let codePointsType = 'number[]'; let symbolsType = 'string[]'; - if (!isCaseFoldingOrMapping) { + if (!isCodePointMapping) { const encodedRanges = codePoints instanceof regenerate ? encodeRegenerate(codePoints) : encodeRanges(codePoints); fs.writeFileSync( path.resolve(dir, 'ranges.mjs'), @@ -206,7 +206,7 @@ const writeFiles = (options) => { codePointsFileContent = `import { gunzipSync } from 'node:zlib';\n\nexport default ${ gzipInline(codePoints) };\n`; symbolsFileContent = `import { gunzipSync } from 'node:zlib';\n\nexport default ${ gzipInline(symbols) };\n`; } - if ((type === 'Case_Folding' && item === 'F') || type === 'Special_Casing') { + if ((type === 'Case_Folding' && item === 'F') || type === 'Special_Casing' || type === 'Decomposition_Mapping') { codePointsType = 'Map'; } else { codePointsType = 'Map'; diff --git a/templates/README.md b/templates/README.md index 8e34fb4..12baa3f 100644 --- a/templates/README.md +++ b/templates/README.md @@ -81,7 +81,7 @@ import <%= id %> from '@unicode/unicode-<%= version %>/<%= type %>/index.mjs'; / } dirs[type].forEach(function(dir) { const id = dir.replaceAll(/[^a-zA-Z0-9_$]/g, '_').replace(/^([0-9])/, '_$1'); - if ('Case_Folding' == type || 'Simple_Case_Mapping' == type || 'Special_Casing' == type) { + if ('Case_Folding' == type || 'Simple_Case_Mapping' == type || 'Special_Casing' == type || 'Decomposition_Mapping' == type) { %> import <%= id %>CodePoints from '@unicode/unicode-<%= version %>/<%= type %>/<%= dir %>/code-points.mjs'; // Lookup map from code point to code point or array of code points. import <%= id %>Symbols from '@unicode/unicode-<%= version %>/<%= type %>/<%= dir %>/symbols.mjs'; // Lookup map from symbol to symbol(s). diff --git a/tests/tests.mjs b/tests/tests.mjs index 303a07e..aa75080 100644 --- a/tests/tests.mjs +++ b/tests/tests.mjs @@ -70,5 +70,15 @@ suite(`The generated latest Unicode js`, () => { const { default: data } = await import(`../output/unicode-${newest}/Joining_Type/Dual_Joining/ranges.mjs`); t.assert.snapshot(data); }); + test('Joining_Type/Transparent should match the snapshot', async (t) => { + const { default: data } = await import(`../output/unicode-${newest}/Joining_Type/Transparent/ranges.mjs`); + t.assert.snapshot(data); + }); + test('Decomposition_Mapping/Isolated should match the snapshot', async (t) => { + const { default: map } = await import(`../output/unicode-${newest}/Decomposition_Mapping/Isolated/code-points.mjs`); + t.assert.snapshot( + [...map.entries()] + ); + }); }); diff --git a/tests/tests.mjs.snapshot b/tests/tests.mjs.snapshot index 6ff0b7b..d6a2bfc 100644 --- a/tests/tests.mjs.snapshot +++ b/tests/tests.mjs.snapshot @@ -2978,807 +2978,4344 @@ exports[`The generated latest Unicode js > Case_Folding/S should match the snaps ] `; -exports[`The generated latest Unicode js > General_Category/Modifier_Letter should match the snapshot 1`] = ` +exports[`The generated latest Unicode js > Decomposition_Mapping/Isolated should match the snapshot 1`] = ` [ + [ + 64336, + [ + 1649 + ] + ], + [ + 64338, + [ + 1659 + ] + ], + [ + 64342, + [ + 1662 + ] + ], + [ + 64346, + [ + 1664 + ] + ], + [ + 64350, + [ + 1658 + ] + ], + [ + 64354, + [ + 1663 + ] + ], + [ + 64358, + [ + 1657 + ] + ], + [ + 64362, + [ + 1700 + ] + ], + [ + 64366, + [ + 1702 + ] + ], + [ + 64370, + [ + 1668 + ] + ], + [ + 64374, + [ + 1667 + ] + ], + [ + 64378, + [ + 1670 + ] + ], + [ + 64382, + [ + 1671 + ] + ], + [ + 64386, + [ + 1677 + ] + ], + [ + 64388, + [ + 1676 + ] + ], + [ + 64390, + [ + 1678 + ] + ], + [ + 64392, + [ + 1672 + ] + ], + [ + 64394, + [ + 1688 + ] + ], + [ + 64396, + [ + 1681 + ] + ], + [ + 64398, + [ + 1705 + ] + ], + [ + 64402, + [ + 1711 + ] + ], + [ + 64406, + [ + 1715 + ] + ], + [ + 64410, + [ + 1713 + ] + ], + [ + 64414, + [ + 1722 + ] + ], + [ + 64416, + [ + 1723 + ] + ], + [ + 64420, + [ + 1728 + ] + ], + [ + 64422, + [ + 1729 + ] + ], + [ + 64426, + [ + 1726 + ] + ], + [ + 64430, + [ + 1746 + ] + ], + [ + 64432, + [ + 1747 + ] + ], + [ + 64467, + [ + 1709 + ] + ], + [ + 64471, + [ + 1735 + ] + ], + [ + 64473, + [ + 1734 + ] + ], + [ + 64475, + [ + 1736 + ] + ], + [ + 64477, + [ + 1655 + ] + ], + [ + 64478, + [ + 1739 + ] + ], + [ + 64480, + [ + 1733 + ] + ], + [ + 64482, + [ + 1737 + ] + ], + [ + 64484, + [ + 1744 + ] + ], + [ + 64490, + [ + 1574, + 1575 + ] + ], + [ + 64492, + [ + 1574, + 1749 + ] + ], + [ + 64494, + [ + 1574, + 1608 + ] + ], + [ + 64496, + [ + 1574, + 1735 + ] + ], + [ + 64498, + [ + 1574, + 1734 + ] + ], + [ + 64500, + [ + 1574, + 1736 + ] + ], + [ + 64502, + [ + 1574, + 1744 + ] + ], + [ + 64505, + [ + 1574, + 1609 + ] + ], + [ + 64508, + [ + 1740 + ] + ], + [ + 64512, + [ + 1574, + 1580 + ] + ], + [ + 64513, + [ + 1574, + 1581 + ] + ], + [ + 64514, + [ + 1574, + 1605 + ] + ], + [ + 64515, + [ + 1574, + 1609 + ] + ], + [ + 64516, + [ + 1574, + 1610 + ] + ], + [ + 64517, + [ + 1576, + 1580 + ] + ], + [ + 64518, + [ + 1576, + 1581 + ] + ], + [ + 64519, + [ + 1576, + 1582 + ] + ], + [ + 64520, + [ + 1576, + 1605 + ] + ], + [ + 64521, + [ + 1576, + 1609 + ] + ], + [ + 64522, + [ + 1576, + 1610 + ] + ], + [ + 64523, + [ + 1578, + 1580 + ] + ], + [ + 64524, + [ + 1578, + 1581 + ] + ], + [ + 64525, + [ + 1578, + 1582 + ] + ], + [ + 64526, + [ + 1578, + 1605 + ] + ], + [ + 64527, + [ + 1578, + 1609 + ] + ], + [ + 64528, + [ + 1578, + 1610 + ] + ], + [ + 64529, + [ + 1579, + 1580 + ] + ], + [ + 64530, + [ + 1579, + 1605 + ] + ], + [ + 64531, + [ + 1579, + 1609 + ] + ], + [ + 64532, + [ + 1579, + 1610 + ] + ], + [ + 64533, + [ + 1580, + 1581 + ] + ], + [ + 64534, + [ + 1580, + 1605 + ] + ], + [ + 64535, + [ + 1581, + 1580 + ] + ], + [ + 64536, + [ + 1581, + 1605 + ] + ], + [ + 64537, + [ + 1582, + 1580 + ] + ], + [ + 64538, + [ + 1582, + 1581 + ] + ], + [ + 64539, + [ + 1582, + 1605 + ] + ], + [ + 64540, + [ + 1587, + 1580 + ] + ], + [ + 64541, + [ + 1587, + 1581 + ] + ], + [ + 64542, + [ + 1587, + 1582 + ] + ], + [ + 64543, + [ + 1587, + 1605 + ] + ], + [ + 64544, + [ + 1589, + 1581 + ] + ], + [ + 64545, + [ + 1589, + 1605 + ] + ], + [ + 64546, + [ + 1590, + 1580 + ] + ], + [ + 64547, + [ + 1590, + 1581 + ] + ], + [ + 64548, + [ + 1590, + 1582 + ] + ], + [ + 64549, + [ + 1590, + 1605 + ] + ], + [ + 64550, + [ + 1591, + 1581 + ] + ], + [ + 64551, + [ + 1591, + 1605 + ] + ], + [ + 64552, + [ + 1592, + 1605 + ] + ], + [ + 64553, + [ + 1593, + 1580 + ] + ], + [ + 64554, + [ + 1593, + 1605 + ] + ], + [ + 64555, + [ + 1594, + 1580 + ] + ], + [ + 64556, + [ + 1594, + 1605 + ] + ], + [ + 64557, + [ + 1601, + 1580 + ] + ], + [ + 64558, + [ + 1601, + 1581 + ] + ], + [ + 64559, + [ + 1601, + 1582 + ] + ], + [ + 64560, + [ + 1601, + 1605 + ] + ], + [ + 64561, + [ + 1601, + 1609 + ] + ], + [ + 64562, + [ + 1601, + 1610 + ] + ], + [ + 64563, + [ + 1602, + 1581 + ] + ], + [ + 64564, + [ + 1602, + 1605 + ] + ], + [ + 64565, + [ + 1602, + 1609 + ] + ], + [ + 64566, + [ + 1602, + 1610 + ] + ], + [ + 64567, + [ + 1603, + 1575 + ] + ], + [ + 64568, + [ + 1603, + 1580 + ] + ], + [ + 64569, + [ + 1603, + 1581 + ] + ], + [ + 64570, + [ + 1603, + 1582 + ] + ], + [ + 64571, + [ + 1603, + 1604 + ] + ], + [ + 64572, + [ + 1603, + 1605 + ] + ], + [ + 64573, + [ + 1603, + 1609 + ] + ], + [ + 64574, + [ + 1603, + 1610 + ] + ], + [ + 64575, + [ + 1604, + 1580 + ] + ], + [ + 64576, + [ + 1604, + 1581 + ] + ], + [ + 64577, + [ + 1604, + 1582 + ] + ], + [ + 64578, + [ + 1604, + 1605 + ] + ], + [ + 64579, + [ + 1604, + 1609 + ] + ], + [ + 64580, + [ + 1604, + 1610 + ] + ], + [ + 64581, + [ + 1605, + 1580 + ] + ], + [ + 64582, + [ + 1605, + 1581 + ] + ], + [ + 64583, + [ + 1605, + 1582 + ] + ], + [ + 64584, + [ + 1605, + 1605 + ] + ], + [ + 64585, + [ + 1605, + 1609 + ] + ], + [ + 64586, + [ + 1605, + 1610 + ] + ], + [ + 64587, + [ + 1606, + 1580 + ] + ], + [ + 64588, + [ + 1606, + 1581 + ] + ], + [ + 64589, + [ + 1606, + 1582 + ] + ], + [ + 64590, + [ + 1606, + 1605 + ] + ], + [ + 64591, + [ + 1606, + 1609 + ] + ], + [ + 64592, + [ + 1606, + 1610 + ] + ], + [ + 64593, + [ + 1607, + 1580 + ] + ], + [ + 64594, + [ + 1607, + 1605 + ] + ], + [ + 64595, + [ + 1607, + 1609 + ] + ], + [ + 64596, + [ + 1607, + 1610 + ] + ], + [ + 64597, + [ + 1610, + 1580 + ] + ], + [ + 64598, + [ + 1610, + 1581 + ] + ], + [ + 64599, + [ + 1610, + 1582 + ] + ], + [ + 64600, + [ + 1610, + 1605 + ] + ], + [ + 64601, + [ + 1610, + 1609 + ] + ], + [ + 64602, + [ + 1610, + 1610 + ] + ], + [ + 64603, + [ + 1584, + 1648 + ] + ], + [ + 64604, + [ + 1585, + 1648 + ] + ], + [ + 64605, + [ + 1609, + 1648 + ] + ], + [ + 64606, + [ + 32, + 1612, + 1617 + ] + ], + [ + 64607, + [ + 32, + 1613, + 1617 + ] + ], + [ + 64608, + [ + 32, + 1614, + 1617 + ] + ], + [ + 64609, + [ + 32, + 1615, + 1617 + ] + ], + [ + 64610, + [ + 32, + 1616, + 1617 + ] + ], + [ + 64611, + [ + 32, + 1617, + 1648 + ] + ], + [ + 64757, + [ + 1591, + 1609 + ] + ], + [ + 64758, + [ + 1591, + 1610 + ] + ], + [ + 64759, + [ + 1593, + 1609 + ] + ], + [ + 64760, + [ + 1593, + 1610 + ] + ], + [ + 64761, + [ + 1594, + 1609 + ] + ], + [ + 64762, + [ + 1594, + 1610 + ] + ], + [ + 64763, + [ + 1587, + 1609 + ] + ], + [ + 64764, + [ + 1587, + 1610 + ] + ], + [ + 64765, + [ + 1588, + 1609 + ] + ], + [ + 64766, + [ + 1588, + 1610 + ] + ], + [ + 64767, + [ + 1581, + 1609 + ] + ], + [ + 64768, + [ + 1581, + 1610 + ] + ], + [ + 64769, + [ + 1580, + 1609 + ] + ], + [ + 64770, + [ + 1580, + 1610 + ] + ], + [ + 64771, + [ + 1582, + 1609 + ] + ], + [ + 64772, + [ + 1582, + 1610 + ] + ], + [ + 64773, + [ + 1589, + 1609 + ] + ], + [ + 64774, + [ + 1589, + 1610 + ] + ], + [ + 64775, + [ + 1590, + 1609 + ] + ], + [ + 64776, + [ + 1590, + 1610 + ] + ], + [ + 64777, + [ + 1588, + 1580 + ] + ], + [ + 64778, + [ + 1588, + 1581 + ] + ], + [ + 64779, + [ + 1588, + 1582 + ] + ], + [ + 64780, + [ + 1588, + 1605 + ] + ], + [ + 64781, + [ + 1588, + 1585 + ] + ], + [ + 64782, + [ + 1587, + 1585 + ] + ], + [ + 64783, + [ + 1589, + 1585 + ] + ], + [ + 64784, + [ + 1590, + 1585 + ] + ], + [ + 64829, + [ + 1575, + 1611 + ] + ], + [ + 65008, + [ + 1589, + 1604, + 1746 + ] + ], + [ + 65009, + [ + 1602, + 1604, + 1746 + ] + ], + [ + 65010, + [ + 1575, + 1604, + 1604, + 1607 + ] + ], + [ + 65011, + [ + 1575, + 1603, + 1576, + 1585 + ] + ], + [ + 65012, + [ + 1605, + 1581, + 1605, + 1583 + ] + ], + [ + 65013, + [ + 1589, + 1604, + 1593, + 1605 + ] + ], + [ + 65014, + [ + 1585, + 1587, + 1608, + 1604 + ] + ], + [ + 65015, + [ + 1593, + 1604, + 1610, + 1607 + ] + ], + [ + 65016, + [ + 1608, + 1587, + 1604, + 1605 + ] + ], + [ + 65017, + [ + 1589, + 1604, + 1609 + ] + ], + [ + 65018, + [ + 1589, + 1604, + 1609, + 32, + 1575, + 1604, + 1604, + 1607, + 32, + 1593, + 1604, + 1610, + 1607, + 32, + 1608, + 1587, + 1604, + 1605 + ] + ], + [ + 65019, + [ + 1580, + 1604, + 32, + 1580, + 1604, + 1575, + 1604, + 1607 + ] + ], + [ + 65020, + [ + 1585, + 1740, + 1575, + 1604 + ] + ], + [ + 65136, + [ + 32, + 1611 + ] + ], + [ + 65138, + [ + 32, + 1612 + ] + ], + [ + 65140, + [ + 32, + 1613 + ] + ], + [ + 65142, + [ + 32, + 1614 + ] + ], + [ + 65144, + [ + 32, + 1615 + ] + ], + [ + 65146, + [ + 32, + 1616 + ] + ], + [ + 65148, + [ + 32, + 1617 + ] + ], + [ + 65150, + [ + 32, + 1618 + ] + ], + [ + 65152, + [ + 1569 + ] + ], + [ + 65153, + [ + 1570 + ] + ], + [ + 65155, + [ + 1571 + ] + ], + [ + 65157, + [ + 1572 + ] + ], + [ + 65159, + [ + 1573 + ] + ], + [ + 65161, + [ + 1574 + ] + ], + [ + 65165, + [ + 1575 + ] + ], + [ + 65167, + [ + 1576 + ] + ], + [ + 65171, + [ + 1577 + ] + ], + [ + 65173, + [ + 1578 + ] + ], + [ + 65177, + [ + 1579 + ] + ], + [ + 65181, + [ + 1580 + ] + ], + [ + 65185, + [ + 1581 + ] + ], + [ + 65189, + [ + 1582 + ] + ], + [ + 65193, + [ + 1583 + ] + ], + [ + 65195, + [ + 1584 + ] + ], + [ + 65197, + [ + 1585 + ] + ], + [ + 65199, + [ + 1586 + ] + ], + [ + 65201, + [ + 1587 + ] + ], + [ + 65205, + [ + 1588 + ] + ], + [ + 65209, + [ + 1589 + ] + ], + [ + 65213, + [ + 1590 + ] + ], + [ + 65217, + [ + 1591 + ] + ], + [ + 65221, + [ + 1592 + ] + ], + [ + 65225, + [ + 1593 + ] + ], + [ + 65229, + [ + 1594 + ] + ], + [ + 65233, + [ + 1601 + ] + ], + [ + 65237, + [ + 1602 + ] + ], + [ + 65241, + [ + 1603 + ] + ], + [ + 65245, + [ + 1604 + ] + ], + [ + 65249, + [ + 1605 + ] + ], + [ + 65253, + [ + 1606 + ] + ], + [ + 65257, + [ + 1607 + ] + ], + [ + 65261, + [ + 1608 + ] + ], + [ + 65263, + [ + 1609 + ] + ], + [ + 65265, + [ + 1610 + ] + ], + [ + 65269, + [ + 1604, + 1570 + ] + ], + [ + 65271, + [ + 1604, + 1571 + ] + ], + [ + 65273, + [ + 1604, + 1573 + ] + ], + [ + 65275, + [ + 1604, + 1575 + ] + ] +] +`; + +exports[`The generated latest Unicode js > General_Category/Modifier_Letter should match the snapshot 1`] = ` +[ + { + "begin": 688, + "end": 706, + "length": 18 + }, + { + "begin": 710, + "end": 722, + "length": 12 + }, + { + "begin": 736, + "end": 741, + "length": 5 + }, + { + "begin": 748, + "end": 749, + "length": 1 + }, + { + "begin": 750, + "end": 751, + "length": 1 + }, + { + "begin": 884, + "end": 885, + "length": 1 + }, + { + "begin": 890, + "end": 891, + "length": 1 + }, + { + "begin": 1368, + "end": 1370, + "length": 2 + }, + { + "begin": 1419, + "end": 1421, + "length": 2 + }, + { + "begin": 1600, + "end": 1601, + "length": 1 + }, + { + "begin": 1765, + "end": 1767, + "length": 2 + }, + { + "begin": 2036, + "end": 2038, + "length": 2 + }, + { + "begin": 2042, + "end": 2043, + "length": 1 + }, + { + "begin": 2074, + "end": 2075, + "length": 1 + }, + { + "begin": 2084, + "end": 2085, + "length": 1 + }, + { + "begin": 2088, + "end": 2089, + "length": 1 + }, + { + "begin": 2249, + "end": 2250, + "length": 1 + }, + { + "begin": 2417, + "end": 2418, + "length": 1 + }, + { + "begin": 3654, + "end": 3655, + "length": 1 + }, + { + "begin": 3782, + "end": 3783, + "length": 1 + }, + { + "begin": 4348, + "end": 4349, + "length": 1 + }, + { + "begin": 6103, + "end": 6104, + "length": 1 + }, + { + "begin": 6211, + "end": 6212, + "length": 1 + }, + { + "begin": 6823, + "end": 6824, + "length": 1 + }, + { + "begin": 7288, + "end": 7294, + "length": 6 + }, + { + "begin": 7468, + "end": 7531, + "length": 63 + }, + { + "begin": 7544, + "end": 7545, + "length": 1 + }, + { + "begin": 7579, + "end": 7616, + "length": 37 + }, + { + "begin": 8305, + "end": 8306, + "length": 1 + }, + { + "begin": 8319, + "end": 8320, + "length": 1 + }, + { + "begin": 8335, + "end": 8352, + "length": 17 + }, + { + "begin": 11388, + "end": 11390, + "length": 2 + }, + { + "begin": 11631, + "end": 11632, + "length": 1 + }, + { + "begin": 11823, + "end": 11824, + "length": 1 + }, + { + "begin": 12293, + "end": 12294, + "length": 1 + }, + { + "begin": 12337, + "end": 12342, + "length": 5 + }, + { + "begin": 12347, + "end": 12348, + "length": 1 + }, + { + "begin": 12445, + "end": 12447, + "length": 2 + }, + { + "begin": 12540, + "end": 12543, + "length": 3 + }, + { + "begin": 40981, + "end": 40982, + "length": 1 + }, + { + "begin": 42232, + "end": 42238, + "length": 6 + }, + { + "begin": 42508, + "end": 42509, + "length": 1 + }, + { + "begin": 42623, + "end": 42624, + "length": 1 + }, + { + "begin": 42652, + "end": 42654, + "length": 2 + }, + { + "begin": 42775, + "end": 42784, + "length": 9 + }, + { + "begin": 42864, + "end": 42865, + "length": 1 + }, + { + "begin": 42888, + "end": 42889, + "length": 1 + }, + { + "begin": 42993, + "end": 42997, + "length": 4 + }, + { + "begin": 43000, + "end": 43002, + "length": 2 + }, + { + "begin": 43471, + "end": 43472, + "length": 1 + }, + { + "begin": 43494, + "end": 43495, + "length": 1 + }, + { + "begin": 43632, + "end": 43633, + "length": 1 + }, + { + "begin": 43741, + "end": 43742, + "length": 1 + }, + { + "begin": 43763, + "end": 43765, + "length": 2 + }, + { + "begin": 43868, + "end": 43872, + "length": 4 + }, + { + "begin": 43881, + "end": 43882, + "length": 1 + }, + { + "begin": 65392, + "end": 65393, + "length": 1 + }, + { + "begin": 65438, + "end": 65440, + "length": 2 + }, + { + "begin": 67456, + "end": 67462, + "length": 6 + }, + { + "begin": 67463, + "end": 67505, + "length": 42 + }, + { + "begin": 67506, + "end": 67520, + "length": 14 + }, + { + "begin": 68942, + "end": 68943, + "length": 1 + }, + { + "begin": 68975, + "end": 68976, + "length": 1 + }, + { + "begin": 69317, + "end": 69318, + "length": 1 + }, + { + "begin": 73177, + "end": 73178, + "length": 1 + }, + { + "begin": 92992, + "end": 92996, + "length": 4 + }, + { + "begin": 93504, + "end": 93507, + "length": 3 + }, + { + "begin": 93547, + "end": 93549, + "length": 2 + }, + { + "begin": 94099, + "end": 94112, + "length": 13 + }, + { + "begin": 94176, + "end": 94178, + "length": 2 + }, + { + "begin": 94179, + "end": 94180, + "length": 1 + }, + { + "begin": 94194, + "end": 94196, + "length": 2 + }, + { + "begin": 110576, + "end": 110580, + "length": 4 + }, + { + "begin": 110581, + "end": 110588, + "length": 7 + }, + { + "begin": 110589, + "end": 110591, + "length": 2 + }, + { + "begin": 122829, + "end": 122880, + "length": 51 + }, + { + "begin": 122928, + "end": 122990, + "length": 62 + }, + { + "begin": 123191, + "end": 123198, + "length": 7 + }, + { + "begin": 124139, + "end": 124140, + "length": 1 + }, + { + "begin": 124671, + "end": 124672, + "length": 1 + }, + { + "begin": 125259, + "end": 125260, + "length": 1 + } +] +`; + +exports[`The generated latest Unicode js > Joining_Type/Dual_Joining should match the snapshot 1`] = ` +[ + { + "begin": 1568, + "end": 1569, + "length": 1 + }, + { + "begin": 1574, + "end": 1575, + "length": 1 + }, + { + "begin": 1576, + "end": 1577, + "length": 1 + }, + { + "begin": 1578, + "end": 1583, + "length": 5 + }, + { + "begin": 1587, + "end": 1600, + "length": 13 + }, + { + "begin": 1601, + "end": 1608, + "length": 7 + }, + { + "begin": 1609, + "end": 1611, + "length": 2 + }, + { + "begin": 1646, + "end": 1648, + "length": 2 + }, + { + "begin": 1656, + "end": 1672, + "length": 16 + }, + { + "begin": 1690, + "end": 1728, + "length": 38 + }, + { + "begin": 1729, + "end": 1731, + "length": 2 + }, + { + "begin": 1740, + "end": 1741, + "length": 1 + }, + { + "begin": 1742, + "end": 1743, + "length": 1 + }, + { + "begin": 1744, + "end": 1746, + "length": 2 + }, + { + "begin": 1786, + "end": 1789, + "length": 3 + }, + { + "begin": 1791, + "end": 1792, + "length": 1 + }, + { + "begin": 1810, + "end": 1813, + "length": 3 + }, + { + "begin": 1818, + "end": 1822, + "length": 4 + }, + { + "begin": 1823, + "end": 1832, + "length": 9 + }, + { + "begin": 1833, + "end": 1834, + "length": 1 + }, + { + "begin": 1835, + "end": 1836, + "length": 1 + }, + { + "begin": 1837, + "end": 1839, + "length": 2 + }, + { + "begin": 1870, + "end": 1881, + "length": 11 + }, + { + "begin": 1884, + "end": 1899, + "length": 15 + }, + { + "begin": 1901, + "end": 1905, + "length": 4 + }, + { + "begin": 1906, + "end": 1907, + "length": 1 + }, + { + "begin": 1909, + "end": 1912, + "length": 3 + }, + { + "begin": 1914, + "end": 1920, + "length": 6 + }, + { + "begin": 1994, + "end": 2027, + "length": 33 + }, + { + "begin": 2113, + "end": 2118, + "length": 5 + }, + { + "begin": 2120, + "end": 2121, + "length": 1 + }, + { + "begin": 2122, + "end": 2132, + "length": 10 + }, + { + "begin": 2133, + "end": 2134, + "length": 1 + }, + { + "begin": 2144, + "end": 2145, + "length": 1 + }, + { + "begin": 2146, + "end": 2150, + "length": 4 + }, + { + "begin": 2152, + "end": 2153, + "length": 1 + }, + { + "begin": 2182, + "end": 2183, + "length": 1 + }, + { + "begin": 2185, + "end": 2190, + "length": 5 + }, + { + "begin": 2191, + "end": 2192, + "length": 1 + }, + { + "begin": 2208, + "end": 2218, + "length": 10 + }, + { + "begin": 2223, + "end": 2225, + "length": 2 + }, + { + "begin": 2227, + "end": 2233, + "length": 6 + }, + { + "begin": 2234, + "end": 2249, + "length": 15 + }, + { + "begin": 6151, + "end": 6152, + "length": 1 + }, + { + "begin": 6176, + "end": 6265, + "length": 89 + }, + { + "begin": 6279, + "end": 6313, + "length": 34 + }, + { + "begin": 6314, + "end": 6315, + "length": 1 + }, + { + "begin": 43072, + "end": 43122, + "length": 50 + }, + { + "begin": 68288, + "end": 68293, + "length": 5 + }, + { + "begin": 68307, + "end": 68311, + "length": 4 + }, + { + "begin": 68312, + "end": 68317, + "length": 5 + }, + { + "begin": 68318, + "end": 68321, + "length": 3 + }, + { + "begin": 68331, + "end": 68335, + "length": 4 + }, + { + "begin": 68480, + "end": 68481, + "length": 1 + }, + { + "begin": 68482, + "end": 68483, + "length": 1 + }, + { + "begin": 68486, + "end": 68489, + "length": 3 + }, + { + "begin": 68490, + "end": 68492, + "length": 2 + }, + { + "begin": 68493, + "end": 68494, + "length": 1 + }, + { + "begin": 68496, + "end": 68497, + "length": 1 + }, + { + "begin": 68525, + "end": 68527, + "length": 2 + }, + { + "begin": 68865, + "end": 68898, + "length": 33 + }, + { + "begin": 68899, + "end": 68900, + "length": 1 + }, + { + "begin": 69315, + "end": 69317, + "length": 2 + }, + { + "begin": 69318, + "end": 69320, + "length": 2 + }, + { + "begin": 69424, + "end": 69427, + "length": 3 + }, + { + "begin": 69428, + "end": 69445, + "length": 17 + }, + { + "begin": 69457, + "end": 69460, + "length": 3 + }, + { + "begin": 69488, + "end": 69492, + "length": 4 + }, + { + "begin": 69494, + "end": 69506, + "length": 12 + }, + { + "begin": 69552, + "end": 69553, + "length": 1 + }, + { + "begin": 69554, + "end": 69556, + "length": 2 + }, + { + "begin": 69560, + "end": 69561, + "length": 1 + }, + { + "begin": 69563, + "end": 69565, + "length": 2 + }, + { + "begin": 69566, + "end": 69568, + "length": 2 + }, + { + "begin": 69569, + "end": 69570, + "length": 1 + }, + { + "begin": 69572, + "end": 69573, + "length": 1 + }, + { + "begin": 69578, + "end": 69579, + "length": 1 + }, + { + "begin": 125184, + "end": 125252, + "length": 68 + } +] +`; + +exports[`The generated latest Unicode js > Joining_Type/Transparent should match the snapshot 1`] = ` +[ + { + "begin": 173, + "end": 174, + "length": 1 + }, + { + "begin": 768, + "end": 880, + "length": 112 + }, + { + "begin": 1155, + "end": 1162, + "length": 7 + }, + { + "begin": 1425, + "end": 1470, + "length": 45 + }, + { + "begin": 1471, + "end": 1472, + "length": 1 + }, + { + "begin": 1473, + "end": 1475, + "length": 2 + }, + { + "begin": 1476, + "end": 1478, + "length": 2 + }, + { + "begin": 1479, + "end": 1482, + "length": 3 + }, + { + "begin": 1552, + "end": 1563, + "length": 11 + }, + { + "begin": 1564, + "end": 1565, + "length": 1 + }, + { + "begin": 1611, + "end": 1632, + "length": 21 + }, + { + "begin": 1648, + "end": 1649, + "length": 1 + }, + { + "begin": 1750, + "end": 1757, + "length": 7 + }, + { + "begin": 1759, + "end": 1765, + "length": 6 + }, + { + "begin": 1767, + "end": 1769, + "length": 2 + }, + { + "begin": 1770, + "end": 1774, + "length": 4 + }, + { + "begin": 1807, + "end": 1808, + "length": 1 + }, + { + "begin": 1809, + "end": 1810, + "length": 1 + }, + { + "begin": 1840, + "end": 1867, + "length": 27 + }, + { + "begin": 1958, + "end": 1969, + "length": 11 + }, + { + "begin": 2027, + "end": 2036, + "length": 9 + }, + { + "begin": 2045, + "end": 2046, + "length": 1 + }, + { + "begin": 2070, + "end": 2074, + "length": 4 + }, + { + "begin": 2075, + "end": 2084, + "length": 9 + }, + { + "begin": 2085, + "end": 2088, + "length": 3 + }, + { + "begin": 2089, + "end": 2094, + "length": 5 + }, + { + "begin": 2137, + "end": 2140, + "length": 3 + }, + { + "begin": 2199, + "end": 2208, + "length": 9 + }, + { + "begin": 2250, + "end": 2274, + "length": 24 + }, + { + "begin": 2275, + "end": 2307, + "length": 32 + }, + { + "begin": 2362, + "end": 2363, + "length": 1 + }, + { + "begin": 2364, + "end": 2365, + "length": 1 + }, + { + "begin": 2369, + "end": 2377, + "length": 8 + }, + { + "begin": 2381, + "end": 2382, + "length": 1 + }, + { + "begin": 2385, + "end": 2392, + "length": 7 + }, + { + "begin": 2402, + "end": 2404, + "length": 2 + }, + { + "begin": 2433, + "end": 2434, + "length": 1 + }, + { + "begin": 2492, + "end": 2493, + "length": 1 + }, + { + "begin": 2497, + "end": 2501, + "length": 4 + }, + { + "begin": 2509, + "end": 2510, + "length": 1 + }, + { + "begin": 2530, + "end": 2532, + "length": 2 + }, + { + "begin": 2558, + "end": 2559, + "length": 1 + }, + { + "begin": 2561, + "end": 2563, + "length": 2 + }, + { + "begin": 2620, + "end": 2621, + "length": 1 + }, + { + "begin": 2625, + "end": 2627, + "length": 2 + }, + { + "begin": 2631, + "end": 2633, + "length": 2 + }, + { + "begin": 2635, + "end": 2638, + "length": 3 + }, + { + "begin": 2641, + "end": 2642, + "length": 1 + }, + { + "begin": 2672, + "end": 2674, + "length": 2 + }, + { + "begin": 2677, + "end": 2678, + "length": 1 + }, + { + "begin": 2689, + "end": 2691, + "length": 2 + }, + { + "begin": 2748, + "end": 2749, + "length": 1 + }, + { + "begin": 2753, + "end": 2758, + "length": 5 + }, + { + "begin": 2759, + "end": 2761, + "length": 2 + }, + { + "begin": 2765, + "end": 2766, + "length": 1 + }, + { + "begin": 2786, + "end": 2788, + "length": 2 + }, + { + "begin": 2810, + "end": 2816, + "length": 6 + }, + { + "begin": 2817, + "end": 2818, + "length": 1 + }, + { + "begin": 2876, + "end": 2877, + "length": 1 + }, + { + "begin": 2879, + "end": 2880, + "length": 1 + }, + { + "begin": 2881, + "end": 2885, + "length": 4 + }, + { + "begin": 2893, + "end": 2894, + "length": 1 + }, + { + "begin": 2899, + "end": 2903, + "length": 4 + }, + { + "begin": 2914, + "end": 2916, + "length": 2 + }, + { + "begin": 2946, + "end": 2947, + "length": 1 + }, + { + "begin": 3008, + "end": 3009, + "length": 1 + }, + { + "begin": 3021, + "end": 3022, + "length": 1 + }, + { + "begin": 3072, + "end": 3073, + "length": 1 + }, + { + "begin": 3076, + "end": 3077, + "length": 1 + }, + { + "begin": 3132, + "end": 3133, + "length": 1 + }, + { + "begin": 3134, + "end": 3137, + "length": 3 + }, + { + "begin": 3142, + "end": 3145, + "length": 3 + }, + { + "begin": 3146, + "end": 3150, + "length": 4 + }, + { + "begin": 3157, + "end": 3159, + "length": 2 + }, + { + "begin": 3170, + "end": 3172, + "length": 2 + }, + { + "begin": 3201, + "end": 3202, + "length": 1 + }, + { + "begin": 3260, + "end": 3261, + "length": 1 + }, + { + "begin": 3263, + "end": 3264, + "length": 1 + }, + { + "begin": 3270, + "end": 3271, + "length": 1 + }, + { + "begin": 3276, + "end": 3278, + "length": 2 + }, + { + "begin": 3298, + "end": 3300, + "length": 2 + }, + { + "begin": 3328, + "end": 3330, + "length": 2 + }, + { + "begin": 3387, + "end": 3389, + "length": 2 + }, + { + "begin": 3393, + "end": 3397, + "length": 4 + }, + { + "begin": 3405, + "end": 3406, + "length": 1 + }, + { + "begin": 3426, + "end": 3428, + "length": 2 + }, + { + "begin": 3457, + "end": 3458, + "length": 1 + }, + { + "begin": 3530, + "end": 3531, + "length": 1 + }, + { + "begin": 3538, + "end": 3541, + "length": 3 + }, + { + "begin": 3542, + "end": 3543, + "length": 1 + }, + { + "begin": 3633, + "end": 3634, + "length": 1 + }, + { + "begin": 3636, + "end": 3643, + "length": 7 + }, + { + "begin": 3655, + "end": 3663, + "length": 8 + }, + { + "begin": 3761, + "end": 3762, + "length": 1 + }, + { + "begin": 3764, + "end": 3773, + "length": 9 + }, + { + "begin": 3784, + "end": 3791, + "length": 7 + }, + { + "begin": 3864, + "end": 3866, + "length": 2 + }, + { + "begin": 3893, + "end": 3894, + "length": 1 + }, + { + "begin": 3895, + "end": 3896, + "length": 1 + }, + { + "begin": 3897, + "end": 3898, + "length": 1 + }, + { + "begin": 3953, + "end": 3967, + "length": 14 + }, + { + "begin": 3968, + "end": 3973, + "length": 5 + }, + { + "begin": 3974, + "end": 3976, + "length": 2 + }, + { + "begin": 3981, + "end": 3992, + "length": 11 + }, + { + "begin": 3993, + "end": 4029, + "length": 36 + }, + { + "begin": 4038, + "end": 4039, + "length": 1 + }, + { + "begin": 4141, + "end": 4145, + "length": 4 + }, + { + "begin": 4146, + "end": 4152, + "length": 6 + }, + { + "begin": 4153, + "end": 4155, + "length": 2 + }, + { + "begin": 4157, + "end": 4159, + "length": 2 + }, + { + "begin": 4184, + "end": 4186, + "length": 2 + }, + { + "begin": 4190, + "end": 4193, + "length": 3 + }, + { + "begin": 4209, + "end": 4213, + "length": 4 + }, + { + "begin": 4226, + "end": 4227, + "length": 1 + }, + { + "begin": 4229, + "end": 4231, + "length": 2 + }, + { + "begin": 4237, + "end": 4238, + "length": 1 + }, + { + "begin": 4253, + "end": 4254, + "length": 1 + }, + { + "begin": 4957, + "end": 4960, + "length": 3 + }, + { + "begin": 5906, + "end": 5909, + "length": 3 + }, + { + "begin": 5938, + "end": 5940, + "length": 2 + }, + { + "begin": 5970, + "end": 5972, + "length": 2 + }, + { + "begin": 6002, + "end": 6004, + "length": 2 + }, + { + "begin": 6068, + "end": 6070, + "length": 2 + }, + { + "begin": 6071, + "end": 6078, + "length": 7 + }, + { + "begin": 6086, + "end": 6087, + "length": 1 + }, { - "begin": 688, - "end": 706, - "length": 18 + "begin": 6089, + "end": 6100, + "length": 11 }, { - "begin": 710, - "end": 722, - "length": 12 + "begin": 6109, + "end": 6110, + "length": 1 }, { - "begin": 736, - "end": 741, + "begin": 6155, + "end": 6158, + "length": 3 + }, + { + "begin": 6159, + "end": 6160, + "length": 1 + }, + { + "begin": 6277, + "end": 6279, + "length": 2 + }, + { + "begin": 6313, + "end": 6314, + "length": 1 + }, + { + "begin": 6432, + "end": 6435, + "length": 3 + }, + { + "begin": 6439, + "end": 6441, + "length": 2 + }, + { + "begin": 6450, + "end": 6451, + "length": 1 + }, + { + "begin": 6457, + "end": 6460, + "length": 3 + }, + { + "begin": 6679, + "end": 6681, + "length": 2 + }, + { + "begin": 6683, + "end": 6684, + "length": 1 + }, + { + "begin": 6742, + "end": 6743, + "length": 1 + }, + { + "begin": 6744, + "end": 6751, + "length": 7 + }, + { + "begin": 6752, + "end": 6753, + "length": 1 + }, + { + "begin": 6754, + "end": 6755, + "length": 1 + }, + { + "begin": 6757, + "end": 6765, + "length": 8 + }, + { + "begin": 6771, + "end": 6781, + "length": 10 + }, + { + "begin": 6783, + "end": 6784, + "length": 1 + }, + { + "begin": 6832, + "end": 6897, + "length": 65 + }, + { + "begin": 6912, + "end": 6916, + "length": 4 + }, + { + "begin": 6964, + "end": 6965, + "length": 1 + }, + { + "begin": 6966, + "end": 6971, "length": 5 }, { - "begin": 748, - "end": 749, + "begin": 6972, + "end": 6973, "length": 1 }, { - "begin": 750, - "end": 751, + "begin": 6978, + "end": 6979, "length": 1 }, { - "begin": 884, - "end": 885, + "begin": 7019, + "end": 7028, + "length": 9 + }, + { + "begin": 7040, + "end": 7042, + "length": 2 + }, + { + "begin": 7074, + "end": 7078, + "length": 4 + }, + { + "begin": 7080, + "end": 7082, + "length": 2 + }, + { + "begin": 7083, + "end": 7086, + "length": 3 + }, + { + "begin": 7142, + "end": 7143, "length": 1 }, { - "begin": 890, - "end": 891, + "begin": 7144, + "end": 7146, + "length": 2 + }, + { + "begin": 7149, + "end": 7150, "length": 1 }, { - "begin": 1368, - "end": 1370, + "begin": 7151, + "end": 7154, + "length": 3 + }, + { + "begin": 7212, + "end": 7220, + "length": 8 + }, + { + "begin": 7222, + "end": 7224, "length": 2 }, { - "begin": 1419, - "end": 1421, + "begin": 7376, + "end": 7379, + "length": 3 + }, + { + "begin": 7380, + "end": 7393, + "length": 13 + }, + { + "begin": 7394, + "end": 7401, + "length": 7 + }, + { + "begin": 7405, + "end": 7406, + "length": 1 + }, + { + "begin": 7412, + "end": 7413, + "length": 1 + }, + { + "begin": 7416, + "end": 7418, "length": 2 }, { - "begin": 1600, - "end": 1601, + "begin": 7616, + "end": 7680, + "length": 64 + }, + { + "begin": 8203, + "end": 8204, "length": 1 }, { - "begin": 1765, - "end": 1767, + "begin": 8206, + "end": 8208, "length": 2 }, { - "begin": 2036, - "end": 2038, + "begin": 8234, + "end": 8239, + "length": 5 + }, + { + "begin": 8288, + "end": 8293, + "length": 5 + }, + { + "begin": 8298, + "end": 8304, + "length": 6 + }, + { + "begin": 8400, + "end": 8433, + "length": 33 + }, + { + "begin": 11503, + "end": 11506, + "length": 3 + }, + { + "begin": 11647, + "end": 11648, + "length": 1 + }, + { + "begin": 11744, + "end": 11776, + "length": 32 + }, + { + "begin": 12330, + "end": 12334, + "length": 4 + }, + { + "begin": 12441, + "end": 12443, "length": 2 }, { - "begin": 2042, - "end": 2043, + "begin": 42607, + "end": 42611, + "length": 4 + }, + { + "begin": 42612, + "end": 42622, + "length": 10 + }, + { + "begin": 42654, + "end": 42656, + "length": 2 + }, + { + "begin": 42736, + "end": 42738, + "length": 2 + }, + { + "begin": 43010, + "end": 43011, "length": 1 }, { - "begin": 2074, - "end": 2075, + "begin": 43014, + "end": 43015, "length": 1 }, { - "begin": 2084, - "end": 2085, + "begin": 43019, + "end": 43020, "length": 1 }, { - "begin": 2088, - "end": 2089, + "begin": 43045, + "end": 43047, + "length": 2 + }, + { + "begin": 43052, + "end": 43053, "length": 1 }, { - "begin": 2249, - "end": 2250, + "begin": 43204, + "end": 43206, + "length": 2 + }, + { + "begin": 43232, + "end": 43250, + "length": 18 + }, + { + "begin": 43263, + "end": 43264, + "length": 1 + }, + { + "begin": 43302, + "end": 43310, + "length": 8 + }, + { + "begin": 43335, + "end": 43346, + "length": 11 + }, + { + "begin": 43392, + "end": 43395, + "length": 3 + }, + { + "begin": 43443, + "end": 43444, + "length": 1 + }, + { + "begin": 43446, + "end": 43450, + "length": 4 + }, + { + "begin": 43452, + "end": 43454, + "length": 2 + }, + { + "begin": 43493, + "end": 43494, + "length": 1 + }, + { + "begin": 43561, + "end": 43567, + "length": 6 + }, + { + "begin": 43569, + "end": 43571, + "length": 2 + }, + { + "begin": 43573, + "end": 43575, + "length": 2 + }, + { + "begin": 43587, + "end": 43588, + "length": 1 + }, + { + "begin": 43596, + "end": 43597, + "length": 1 + }, + { + "begin": 43644, + "end": 43645, + "length": 1 + }, + { + "begin": 43696, + "end": 43697, + "length": 1 + }, + { + "begin": 43698, + "end": 43701, + "length": 3 + }, + { + "begin": 43703, + "end": 43705, + "length": 2 + }, + { + "begin": 43710, + "end": 43712, + "length": 2 + }, + { + "begin": 43713, + "end": 43714, + "length": 1 + }, + { + "begin": 43756, + "end": 43758, + "length": 2 + }, + { + "begin": 43766, + "end": 43767, + "length": 1 + }, + { + "begin": 44005, + "end": 44006, + "length": 1 + }, + { + "begin": 44008, + "end": 44009, + "length": 1 + }, + { + "begin": 44013, + "end": 44014, + "length": 1 + }, + { + "begin": 64286, + "end": 64287, "length": 1 }, { - "begin": 2417, - "end": 2418, - "length": 1 + "begin": 65024, + "end": 65040, + "length": 16 }, { - "begin": 3654, - "end": 3655, - "length": 1 + "begin": 65056, + "end": 65072, + "length": 16 }, { - "begin": 3782, - "end": 3783, + "begin": 65279, + "end": 65280, "length": 1 }, { - "begin": 4348, - "end": 4349, - "length": 1 + "begin": 65529, + "end": 65532, + "length": 3 }, { - "begin": 6103, - "end": 6104, + "begin": 66045, + "end": 66046, "length": 1 }, { - "begin": 6211, - "end": 6212, + "begin": 66272, + "end": 66273, "length": 1 }, { - "begin": 6823, - "end": 6824, - "length": 1 + "begin": 66422, + "end": 66427, + "length": 5 }, { - "begin": 7288, - "end": 7294, - "length": 6 + "begin": 68097, + "end": 68100, + "length": 3 }, { - "begin": 7468, - "end": 7531, - "length": 63 + "begin": 68101, + "end": 68103, + "length": 2 }, { - "begin": 7544, - "end": 7545, - "length": 1 + "begin": 68108, + "end": 68112, + "length": 4 }, { - "begin": 7579, - "end": 7616, - "length": 37 + "begin": 68152, + "end": 68155, + "length": 3 }, { - "begin": 8305, - "end": 8306, + "begin": 68159, + "end": 68160, "length": 1 }, { - "begin": 8319, - "end": 8320, - "length": 1 + "begin": 68325, + "end": 68327, + "length": 2 }, { - "begin": 8335, - "end": 8352, - "length": 17 + "begin": 68900, + "end": 68904, + "length": 4 }, { - "begin": 11388, - "end": 11390, + "begin": 68969, + "end": 68974, + "length": 5 + }, + { + "begin": 69291, + "end": 69293, "length": 2 }, { - "begin": 11631, - "end": 11632, - "length": 1 + "begin": 69323, + "end": 69328, + "length": 5 }, { - "begin": 11823, - "end": 11824, - "length": 1 + "begin": 69360, + "end": 69376, + "length": 16 }, { - "begin": 12293, - "end": 12294, + "begin": 69446, + "end": 69457, + "length": 11 + }, + { + "begin": 69506, + "end": 69510, + "length": 4 + }, + { + "begin": 69633, + "end": 69634, "length": 1 }, { - "begin": 12337, - "end": 12342, - "length": 5 + "begin": 69688, + "end": 69703, + "length": 15 }, { - "begin": 12347, - "end": 12348, + "begin": 69744, + "end": 69745, "length": 1 }, { - "begin": 12445, - "end": 12447, + "begin": 69747, + "end": 69749, "length": 2 }, { - "begin": 12540, - "end": 12543, + "begin": 69759, + "end": 69762, "length": 3 }, { - "begin": 40981, - "end": 40982, - "length": 1 + "begin": 69811, + "end": 69815, + "length": 4 }, { - "begin": 42232, - "end": 42238, - "length": 6 + "begin": 69817, + "end": 69819, + "length": 2 }, { - "begin": 42508, - "end": 42509, + "begin": 69826, + "end": 69827, "length": 1 }, { - "begin": 42623, - "end": 42624, + "begin": 69888, + "end": 69891, + "length": 3 + }, + { + "begin": 69927, + "end": 69932, + "length": 5 + }, + { + "begin": 69933, + "end": 69941, + "length": 8 + }, + { + "begin": 70003, + "end": 70004, "length": 1 }, { - "begin": 42652, - "end": 42654, + "begin": 70016, + "end": 70018, "length": 2 }, { - "begin": 42775, - "end": 42784, + "begin": 70070, + "end": 70079, "length": 9 }, { - "begin": 42864, - "end": 42865, - "length": 1 + "begin": 70089, + "end": 70093, + "length": 4 }, { - "begin": 42888, - "end": 42889, + "begin": 70095, + "end": 70096, "length": 1 }, { - "begin": 42993, - "end": 42997, - "length": 4 + "begin": 70191, + "end": 70194, + "length": 3 }, { - "begin": 43000, - "end": 43002, + "begin": 70196, + "end": 70197, + "length": 1 + }, + { + "begin": 70198, + "end": 70200, "length": 2 }, { - "begin": 43471, - "end": 43472, + "begin": 70206, + "end": 70207, "length": 1 }, { - "begin": 43494, - "end": 43495, + "begin": 70209, + "end": 70210, "length": 1 }, { - "begin": 43632, - "end": 43633, + "begin": 70367, + "end": 70368, "length": 1 }, { - "begin": 43741, - "end": 43742, - "length": 1 + "begin": 70371, + "end": 70379, + "length": 8 }, { - "begin": 43763, - "end": 43765, + "begin": 70400, + "end": 70402, "length": 2 }, { - "begin": 43868, - "end": 43872, - "length": 4 + "begin": 70459, + "end": 70461, + "length": 2 }, { - "begin": 43881, - "end": 43882, + "begin": 70464, + "end": 70465, "length": 1 }, { - "begin": 65392, - "end": 65393, - "length": 1 + "begin": 70502, + "end": 70509, + "length": 7 }, { - "begin": 65438, - "end": 65440, - "length": 2 + "begin": 70512, + "end": 70517, + "length": 5 }, { - "begin": 67456, - "end": 67462, + "begin": 70587, + "end": 70593, "length": 6 }, { - "begin": 67463, - "end": 67505, - "length": 42 - }, - { - "begin": 67506, - "end": 67520, - "length": 14 - }, - { - "begin": 68942, - "end": 68943, + "begin": 70606, + "end": 70607, "length": 1 }, { - "begin": 68975, - "end": 68976, + "begin": 70608, + "end": 70609, "length": 1 }, { - "begin": 69317, - "end": 69318, + "begin": 70610, + "end": 70611, "length": 1 }, { - "begin": 73177, - "end": 73178, - "length": 1 + "begin": 70625, + "end": 70627, + "length": 2 }, { - "begin": 92992, - "end": 92996, - "length": 4 + "begin": 70712, + "end": 70720, + "length": 8 }, { - "begin": 93504, - "end": 93507, + "begin": 70722, + "end": 70725, "length": 3 }, { - "begin": 93547, - "end": 93549, - "length": 2 + "begin": 70726, + "end": 70727, + "length": 1 }, { - "begin": 94099, - "end": 94112, - "length": 13 + "begin": 70750, + "end": 70751, + "length": 1 }, { - "begin": 94176, - "end": 94178, - "length": 2 + "begin": 70835, + "end": 70841, + "length": 6 }, { - "begin": 94179, - "end": 94180, + "begin": 70842, + "end": 70843, "length": 1 }, { - "begin": 94194, - "end": 94196, + "begin": 70847, + "end": 70849, "length": 2 }, { - "begin": 110576, - "end": 110580, - "length": 4 + "begin": 70850, + "end": 70852, + "length": 2 }, { - "begin": 110581, - "end": 110588, - "length": 7 + "begin": 71090, + "end": 71094, + "length": 4 }, { - "begin": 110589, - "end": 110591, + "begin": 71100, + "end": 71102, "length": 2 }, { - "begin": 122829, - "end": 122880, - "length": 51 + "begin": 71103, + "end": 71105, + "length": 2 }, { - "begin": 122928, - "end": 122990, - "length": 62 + "begin": 71132, + "end": 71134, + "length": 2 }, { - "begin": 123191, - "end": 123198, - "length": 7 + "begin": 71219, + "end": 71227, + "length": 8 }, { - "begin": 124139, - "end": 124140, + "begin": 71229, + "end": 71230, "length": 1 }, { - "begin": 124671, - "end": 124672, + "begin": 71231, + "end": 71233, + "length": 2 + }, + { + "begin": 71339, + "end": 71340, "length": 1 }, { - "begin": 125259, - "end": 125260, + "begin": 71341, + "end": 71342, "length": 1 - } -] -`; - -exports[`The generated latest Unicode js > Joining_Type/Dual_Joining should match the snapshot 1`] = ` -[ + }, { - "begin": 1568, - "end": 1569, + "begin": 71344, + "end": 71350, + "length": 6 + }, + { + "begin": 71351, + "end": 71352, "length": 1 }, { - "begin": 1574, - "end": 1575, + "begin": 71453, + "end": 71454, "length": 1 }, { - "begin": 1576, - "end": 1577, + "begin": 71455, + "end": 71456, "length": 1 }, { - "begin": 1578, - "end": 1583, - "length": 5 + "begin": 71458, + "end": 71462, + "length": 4 }, { - "begin": 1587, - "end": 1600, - "length": 13 + "begin": 71463, + "end": 71468, + "length": 5 }, { - "begin": 1601, - "end": 1608, - "length": 7 + "begin": 71727, + "end": 71736, + "length": 9 }, { - "begin": 1609, - "end": 1611, + "begin": 71737, + "end": 71739, "length": 2 }, { - "begin": 1646, - "end": 1648, + "begin": 71995, + "end": 71997, "length": 2 }, { - "begin": 1656, - "end": 1672, - "length": 16 + "begin": 71998, + "end": 71999, + "length": 1 }, { - "begin": 1690, - "end": 1728, - "length": 38 + "begin": 72003, + "end": 72004, + "length": 1 }, { - "begin": 1729, - "end": 1731, + "begin": 72148, + "end": 72152, + "length": 4 + }, + { + "begin": 72154, + "end": 72156, "length": 2 }, { - "begin": 1740, - "end": 1741, + "begin": 72160, + "end": 72161, "length": 1 }, { - "begin": 1742, - "end": 1743, - "length": 1 + "begin": 72193, + "end": 72203, + "length": 10 }, { - "begin": 1744, - "end": 1746, - "length": 2 + "begin": 72243, + "end": 72249, + "length": 6 }, { - "begin": 1786, - "end": 1789, - "length": 3 + "begin": 72251, + "end": 72255, + "length": 4 }, { - "begin": 1791, - "end": 1792, + "begin": 72263, + "end": 72264, "length": 1 }, { - "begin": 1810, - "end": 1813, + "begin": 72273, + "end": 72279, + "length": 6 + }, + { + "begin": 72281, + "end": 72284, "length": 3 }, { - "begin": 1818, - "end": 1822, - "length": 4 + "begin": 72330, + "end": 72343, + "length": 13 }, { - "begin": 1823, - "end": 1832, - "length": 9 + "begin": 72344, + "end": 72346, + "length": 2 }, { - "begin": 1833, - "end": 1834, + "begin": 72544, + "end": 72545, "length": 1 }, { - "begin": 1835, - "end": 1836, + "begin": 72546, + "end": 72549, + "length": 3 + }, + { + "begin": 72550, + "end": 72551, "length": 1 }, { - "begin": 1837, - "end": 1839, - "length": 2 + "begin": 72752, + "end": 72759, + "length": 7 }, { - "begin": 1870, - "end": 1881, - "length": 11 + "begin": 72760, + "end": 72766, + "length": 6 }, { - "begin": 1884, - "end": 1899, - "length": 15 + "begin": 72767, + "end": 72768, + "length": 1 }, { - "begin": 1901, - "end": 1905, - "length": 4 + "begin": 72850, + "end": 72872, + "length": 22 }, { - "begin": 1906, - "end": 1907, - "length": 1 + "begin": 72874, + "end": 72881, + "length": 7 }, { - "begin": 1909, - "end": 1912, - "length": 3 + "begin": 72882, + "end": 72884, + "length": 2 }, { - "begin": 1914, - "end": 1920, + "begin": 72885, + "end": 72887, + "length": 2 + }, + { + "begin": 73009, + "end": 73015, "length": 6 }, { - "begin": 1994, - "end": 2027, - "length": 33 + "begin": 73018, + "end": 73019, + "length": 1 }, { - "begin": 2113, - "end": 2118, - "length": 5 + "begin": 73020, + "end": 73022, + "length": 2 }, { - "begin": 2120, - "end": 2121, + "begin": 73023, + "end": 73030, + "length": 7 + }, + { + "begin": 73031, + "end": 73032, "length": 1 }, { - "begin": 2122, - "end": 2132, - "length": 10 + "begin": 73104, + "end": 73106, + "length": 2 }, { - "begin": 2133, - "end": 2134, + "begin": 73109, + "end": 73110, "length": 1 }, { - "begin": 2144, - "end": 2145, + "begin": 73111, + "end": 73112, "length": 1 }, { - "begin": 2146, - "end": 2150, - "length": 4 + "begin": 73200, + "end": 73201, + "length": 1 }, { - "begin": 2152, - "end": 2153, - "length": 1 + "begin": 73459, + "end": 73461, + "length": 2 }, { - "begin": 2182, - "end": 2183, - "length": 1 + "begin": 73472, + "end": 73474, + "length": 2 }, { - "begin": 2185, - "end": 2190, + "begin": 73526, + "end": 73531, "length": 5 }, { - "begin": 2191, - "end": 2192, + "begin": 73536, + "end": 73537, "length": 1 }, { - "begin": 2208, - "end": 2218, - "length": 10 + "begin": 73538, + "end": 73539, + "length": 1 }, { - "begin": 2223, - "end": 2225, - "length": 2 + "begin": 73562, + "end": 73563, + "length": 1 }, { - "begin": 2227, - "end": 2233, - "length": 6 + "begin": 78896, + "end": 78913, + "length": 17 }, { - "begin": 2234, - "end": 2249, + "begin": 78919, + "end": 78934, "length": 15 }, { - "begin": 6151, - "end": 6152, - "length": 1 + "begin": 90398, + "end": 90410, + "length": 12 }, { - "begin": 6176, - "end": 6265, - "length": 89 + "begin": 90413, + "end": 90416, + "length": 3 }, { - "begin": 6279, - "end": 6313, - "length": 34 + "begin": 92912, + "end": 92917, + "length": 5 }, { - "begin": 6314, - "end": 6315, + "begin": 92976, + "end": 92983, + "length": 7 + }, + { + "begin": 94031, + "end": 94032, "length": 1 }, { - "begin": 43072, - "end": 43122, - "length": 50 + "begin": 94095, + "end": 94099, + "length": 4 }, { - "begin": 68288, - "end": 68293, - "length": 5 + "begin": 94180, + "end": 94181, + "length": 1 }, { - "begin": 68307, - "end": 68311, + "begin": 113821, + "end": 113823, + "length": 2 + }, + { + "begin": 113824, + "end": 113828, "length": 4 }, { - "begin": 68312, - "end": 68317, - "length": 5 + "begin": 118528, + "end": 118574, + "length": 46 }, { - "begin": 68318, - "end": 68321, + "begin": 118576, + "end": 118599, + "length": 23 + }, + { + "begin": 119079, + "end": 119081, + "length": 2 + }, + { + "begin": 119143, + "end": 119146, "length": 3 }, { - "begin": 68331, - "end": 68335, - "length": 4 + "begin": 119155, + "end": 119171, + "length": 16 }, { - "begin": 68480, - "end": 68481, - "length": 1 + "begin": 119173, + "end": 119180, + "length": 7 }, { - "begin": 68482, - "end": 68483, - "length": 1 + "begin": 119210, + "end": 119214, + "length": 4 }, { - "begin": 68486, - "end": 68489, + "begin": 119362, + "end": 119365, "length": 3 }, { - "begin": 68490, - "end": 68492, + "begin": 119387, + "end": 119389, "length": 2 }, { - "begin": 68493, - "end": 68494, + "begin": 121344, + "end": 121399, + "length": 55 + }, + { + "begin": 121403, + "end": 121453, + "length": 50 + }, + { + "begin": 121461, + "end": 121462, "length": 1 }, { - "begin": 68496, - "end": 68497, + "begin": 121476, + "end": 121477, "length": 1 }, { - "begin": 68525, - "end": 68527, - "length": 2 + "begin": 121499, + "end": 121504, + "length": 5 }, { - "begin": 68865, - "end": 68898, - "length": 33 + "begin": 121505, + "end": 121520, + "length": 15 }, { - "begin": 68899, - "end": 68900, - "length": 1 + "begin": 122880, + "end": 122887, + "length": 7 }, { - "begin": 69315, - "end": 69317, - "length": 2 + "begin": 122888, + "end": 122905, + "length": 17 }, { - "begin": 69318, - "end": 69320, + "begin": 122907, + "end": 122914, + "length": 7 + }, + { + "begin": 122915, + "end": 122917, "length": 2 }, { - "begin": 69424, - "end": 69427, - "length": 3 + "begin": 122918, + "end": 122923, + "length": 5 }, { - "begin": 69428, - "end": 69445, - "length": 17 + "begin": 123023, + "end": 123024, + "length": 1 }, { - "begin": 69457, - "end": 69460, - "length": 3 + "begin": 123184, + "end": 123191, + "length": 7 }, { - "begin": 69488, - "end": 69492, - "length": 4 + "begin": 123566, + "end": 123567, + "length": 1 }, { - "begin": 69494, - "end": 69506, - "length": 12 + "begin": 123628, + "end": 123632, + "length": 4 }, { - "begin": 69552, - "end": 69553, - "length": 1 + "begin": 124140, + "end": 124144, + "length": 4 }, { - "begin": 69554, - "end": 69556, + "begin": 124398, + "end": 124400, "length": 2 }, { - "begin": 69560, - "end": 69561, + "begin": 124643, + "end": 124644, "length": 1 }, { - "begin": 69563, - "end": 69565, - "length": 2 + "begin": 124646, + "end": 124647, + "length": 1 }, { - "begin": 69566, - "end": 69568, + "begin": 124654, + "end": 124656, "length": 2 }, { - "begin": 69569, - "end": 69570, + "begin": 124661, + "end": 124662, "length": 1 }, { - "begin": 69572, - "end": 69573, - "length": 1 + "begin": 125136, + "end": 125143, + "length": 7 }, { - "begin": 69578, - "end": 69579, + "begin": 125252, + "end": 125260, + "length": 8 + }, + { + "begin": 917505, + "end": 917506, "length": 1 }, { - "begin": 125184, - "end": 125252, - "length": 68 + "begin": 917536, + "end": 917632, + "length": 96 + }, + { + "begin": 917760, + "end": 918000, + "length": 240 } ] `;