Issue 235 - Error getting reference to Jonah

CHANGELOG.md

@@ -7,6 +7,12 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [0.15.5] - 2026-01-24
+
+### Fixed
+
+- [Issue #235](https://github.com/avendesora/pythonbible/issues/235) - Error getting reference to Jonah
+
 ## [0.15.4] - 2026-01-01
 
 ### Changed
@@ -234,7 +240,8 @@ The goal of this release was to address [Issue #90], and to make things related
 
 ## [0.0.1] - 2020-10-08
 
-[unreleased]: https://github.com/avendesora/pythonbible/compare/v0.15.4...HEAD
+[unreleased]: https://github.com/avendesora/pythonbible/compare/v0.15.5...HEAD
+[0.15.5]: https://github.com/avendesora/pythonbible/compare/v0.15.4...v0.15.5
 [0.15.4]: https://github.com/avendesora/pythonbible/compare/v0.15.3...v0.15.4
 [0.15.3]: https://github.com/avendesora/pythonbible/compare/v0.15.2...v0.15.3
 [0.15.2]: https://github.com/avendesora/pythonbible/compare/v0.15.1...v0.15.2

docs/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "pythonbible-docs"
-version = "0.15.4"
+version = "0.15.5"
 description-file = "README.md"
 requires-python = ">=3.13"
 authors = [

docs/source/conf.py

@@ -23,7 +23,7 @@
 author = "Nathan Patton"
 
 # The full version, including alpha/beta/rc tags
-release = "0.15.4"
+release = "0.15.5"
 
 
 # -- General configuration ---------------------------------------------------

pythonbible/pyproject.toml

@@ -11,7 +11,7 @@ module-name = "pythonbible"
 
 [project]
 name = "pythonbible"
-version = "0.15.4"
+version = "0.15.5"
 description-file = "README.md"
 requires-python = ">=3.10"
 authors = [
@@ -172,7 +172,7 @@ ignore = [
 
 [tool.ruff.lint.per-file-ignores]
 "pythonbible/bible/bible.py" = ["PLR0913", "FBT001", "FBT002"]
-"pythonbible/books.py" = ["ARG004", "PYI034"]
+"pythonbible/books/__init__.py" = ["ARG004", "PYI034"]
 "pythonbible/book_groups.py" = ["ARG004", "PYI034"]
 "pythonbible/formatter.py" = ["ANN401", "FBT001", "FBT002", "PLR0911"]
 "pythonbible/parser.py" = ["PLR2004"]

pythonbible/pythonbible/__init__.py

@@ -8,7 +8,7 @@
 
 from __future__ import annotations
 
-__version__ = "0.15.4"
+__version__ = "0.15.5"
 
 from .bible import add_bible
 from .bible import get_bible

pythonbible/pythonbible/books.py → pythonbible/pythonbible/books/__init__.py

@@ -4,6 +4,13 @@
 from typing import Any
 from typing import Type
 
+from pythonbible.books.common_constants import FIRST
+from pythonbible.books.common_constants import FIRST_BOOK
+from pythonbible.books.common_constants import SECOND
+from pythonbible.books.common_constants import SECOND_BOOK
+from pythonbible.books.common_constants import THIRD
+from pythonbible.books.john import JOHN_REGULAR_EXPRESSION
+
 
 def _build_book_regular_expression(
     book: str,
@@ -24,30 +31,22 @@ def _add_suffix(regex: str, suffix: str | None = None) -> str:
 _SAMUEL_REGULAR_EXPRESSION = r"(Samuel|Sam\.*|Sa\.*|Sm\.*)"
 _KINGS_REGULAR_EXPRESSION = r"(Kings|Kgs\.*|Kin\.*|Ki\.*)"
 _CHRONICLES_REGULAR_EXPRESSION = r"(Chronicles|Chron\.*|Chro\.*|Chr\.*|Ch\.*)"
-_JOHN_REGULAR_EXPRESSION = r"(John|Joh\.*|Jhn\.*|Jo\.*(?!shua|b|nah|el)|Jn\.*)"
 _CORINTHIANS_REGULAR_EXPRESSION = r"Co\.*(?:r\.*(?:inthians)?)?"
 _THESSALONIANS_REGULAR_EXPRESSION = r"Th\.*(?:(s|(es(?:s)?))\.*(?:alonians)?)?"
 _TIMOTHY_REGULAR_EXPRESSION = r"Ti\.*(?:m\.*(?:othy)?)?"
 _PETER_REGULAR_EXPRESSION = r"(Pe\.*(?:t\.*(?:er)?)?|Pt\.*)"
 
 _MACCABEES_REGULAR_EXPRESSION = r"(Maccabees|Macc\.*|Mac\.*|Ma\.*|M\.*)"
 
-_FIRST = r"1|I\s+|1st\s+|First\s+"
-_SECOND = r"2|II|2nd\s+|Second\s+"
-_THIRD = r"3|III|3rd\s+|Third\s+"
-
-_FIRST_BOOK = rf"{_FIRST}|(First\s+Book\s+of(?:\s+the)?)"
-_SECOND_BOOK = rf"{_SECOND}|(Second\s+Book\s+of(?:\s+the)?)"
-
 _EPISTLE_OF_PAUL_TO = r"Epistle\s+of\s+Paul\s+(?:the\s+Apostle\s+)?to(?:\s+the)?"
 _GENERAL_EPISTLE_OF = r"(?:General\s+)?Epistle\s+(?:General\s+)?of"
 
-_FIRST_PAUL_EPISTLE = rf"{_FIRST}|(First\s+{_EPISTLE_OF_PAUL_TO})"
-_SECOND_PAUL_EPISTLE = rf"{_SECOND}|(Second\s+{_EPISTLE_OF_PAUL_TO})"
+_FIRST_PAUL_EPISTLE = rf"{FIRST}|(First\s+{_EPISTLE_OF_PAUL_TO})"
+_SECOND_PAUL_EPISTLE = rf"{SECOND}|(Second\s+{_EPISTLE_OF_PAUL_TO})"
 
-_FIRST_GENERAL_EPISTLE = rf"{_FIRST}|(First\s+{_GENERAL_EPISTLE_OF})"
-_SECOND_GENERAL_EPISTLE = rf"{_SECOND}|(Second\s+{_GENERAL_EPISTLE_OF})"
-_THIRD_GENERAL_EPISTLE = rf"{_THIRD}|(Third\s+{_GENERAL_EPISTLE_OF})"
+_FIRST_GENERAL_EPISTLE = rf"{FIRST}|(First\s+{_GENERAL_EPISTLE_OF})"
+_SECOND_GENERAL_EPISTLE = rf"{SECOND}|(Second\s+{_GENERAL_EPISTLE_OF})"
+_THIRD_GENERAL_EPISTLE = rf"{THIRD}|(Third\s+{_GENERAL_EPISTLE_OF})"
 
 
 class Book(Enum):
@@ -111,7 +110,7 @@ def abbreviations(self: Book) -> tuple[str, ...]:
         "1 Samuel",
         _build_book_regular_expression(
             _SAMUEL_REGULAR_EXPRESSION,
-            prefix=_FIRST_BOOK,
+            prefix=FIRST_BOOK,
             suffix=r"Otherwise\s+Called\s+The\s+First\s+Book\s+of\s+the\s+Kings",
         ),
         ("Sa", "Sam", "Sm"),
@@ -121,7 +120,7 @@ def abbreviations(self: Book) -> tuple[str, ...]:
         "2 Samuel",
         _build_book_regular_expression(
             _SAMUEL_REGULAR_EXPRESSION,
-            prefix=_SECOND_BOOK,
+            prefix=SECOND_BOOK,
             suffix=r"Otherwise\s+Called\s+The\s+Second\s+Book\s+of\s+the\s+Kings",
         ),
         ("Sa", "Sam", "Sm"),
@@ -131,7 +130,7 @@ def abbreviations(self: Book) -> tuple[str, ...]:
         "1 Kings",
         _build_book_regular_expression(
             _KINGS_REGULAR_EXPRESSION,
-            prefix=_FIRST_BOOK,
+            prefix=FIRST_BOOK,
             suffix=r"\,\s+Commonly\s+Called\s+the\s+Third\s+Book\s+of\s+the\s+Kings",
         ),
         ("Kgs", "Ki", "Kin"),
@@ -141,7 +140,7 @@ def abbreviations(self: Book) -> tuple[str, ...]:
         "2 Kings",
         _build_book_regular_expression(
             _KINGS_REGULAR_EXPRESSION,
-            prefix=_SECOND_BOOK,
+            prefix=SECOND_BOOK,
             suffix=r"\,\s+Commonly\s+Called\s+the\s+Fourth\s+Book\s+of\s+the\s+Kings",
         ),
         ("Kgs", "Ki", "Kin"),
@@ -151,7 +150,7 @@ def abbreviations(self: Book) -> tuple[str, ...]:
         "1 Chronicles",
         _build_book_regular_expression(
             _CHRONICLES_REGULAR_EXPRESSION,
-            prefix=_FIRST_BOOK,
+            prefix=FIRST_BOOK,
         ),
         ("Ch", "Chr", "Chro", "Chron"),
     )
@@ -160,7 +159,7 @@ def abbreviations(self: Book) -> tuple[str, ...]:
         "2 Chronicles",
         _build_book_regular_expression(
             _CHRONICLES_REGULAR_EXPRESSION,
-            prefix=_SECOND_BOOK,
+            prefix=SECOND_BOOK,
         ),
         ("Ch", "Chr", "Chro", "Chron"),
     )
@@ -229,7 +228,7 @@ def abbreviations(self: Book) -> tuple[str, ...]:
     JOHN = (
         43,
         "John",
-        rf"(?<!(?:1|2|3|I)\s)(?<!(?:1|2|3|I)){_JOHN_REGULAR_EXPRESSION}",
+        rf"(?<!(?:1|2|3|I)\s)(?<!(?:1|2|3|I)){JOHN_REGULAR_EXPRESSION}",
         ("Jhn", "Jn", "Jo", "Joh"),
     )
     ACTS = (
@@ -336,7 +335,7 @@ def abbreviations(self: Book) -> tuple[str, ...]:
         62,
         "1 John",
         _build_book_regular_expression(
-            _JOHN_REGULAR_EXPRESSION,
+            JOHN_REGULAR_EXPRESSION,
             prefix=_FIRST_GENERAL_EPISTLE,
         ),
         ("Jhn", "Jn", "Jo", "Joh"),
@@ -345,7 +344,7 @@ def abbreviations(self: Book) -> tuple[str, ...]:
         63,
         "2 John",
         _build_book_regular_expression(
-            _JOHN_REGULAR_EXPRESSION,
+            JOHN_REGULAR_EXPRESSION,
             prefix=_SECOND_GENERAL_EPISTLE,
         ),
         ("Jhn", "Jn", "Jo", "Joh"),
@@ -354,7 +353,7 @@ def abbreviations(self: Book) -> tuple[str, ...]:
         64,
         "3 John",
         _build_book_regular_expression(
-            _JOHN_REGULAR_EXPRESSION,
+            JOHN_REGULAR_EXPRESSION,
             prefix=_THIRD_GENERAL_EPISTLE,
         ),
         ("Jhn", "Jn", "Jo", "Joh"),
@@ -374,7 +373,7 @@ def abbreviations(self: Book) -> tuple[str, ...]:
         "1 Esdras",
         _build_book_regular_expression(
             r"(Esdras|Esdr\.*|Esd\.*|Es\.*)",
-            _FIRST,
+            FIRST,
         ),
         ("Es", "Esd", "Esdr"),
     )
@@ -396,7 +395,7 @@ def abbreviations(self: Book) -> tuple[str, ...]:
         "1 Maccabees",
         _build_book_regular_expression(
             _MACCABEES_REGULAR_EXPRESSION,
-            _FIRST,
+            FIRST,
         ),
         ("M", "Ma", "Mac", "Macc"),
     )
@@ -405,7 +404,7 @@ def abbreviations(self: Book) -> tuple[str, ...]:
         "2 Maccabees",
         _build_book_regular_expression(
             _MACCABEES_REGULAR_EXPRESSION,
-            _SECOND,
+            SECOND,
         ),
         ("M", "Ma", "Mac", "Macc"),
     )

pythonbible/pythonbible/books/common_constants.py

@@ -0,0 +1,8 @@
+"""Common constants used in Book regular expressions."""
+
+FIRST = r"1|I\s+|1st\s+|First\s+"
+SECOND = r"2|II|2nd\s+|Second\s+"
+THIRD = r"3|III|3rd\s+|Third\s+"
+
+FIRST_BOOK = rf"{FIRST}|(First\s+Book\s+of(?:\s+the)?)"
+SECOND_BOOK = rf"{SECOND}|(Second\s+Book\s+of(?:\s+the)?)"

pythonbible/pythonbible/books/john.py

@@ -0,0 +1,23 @@
+"""John book regular expression definitions."""
+
+import re
+
+_JO_EXCLUDE_SUFFIXES: tuple[str, ...] = (
+    "shua",  # Joshua
+    "b",  # Job
+    "nah",  # Jonah
+    "n",  # Jonah (abbreviation)
+    "el",  # Joel
+)
+
+_JO_EXCLUDED_SUFFIXES_PATTERN = "|".join(map(re.escape, _JO_EXCLUDE_SUFFIXES))
+_JO_NEGATIVE_LOOKAHEAD = f"(?!{_JO_EXCLUDED_SUFFIXES_PATTERN})"
+
+_ABBREVIATIONS: tuple[str, ...] = (
+    r"Joh\.*",
+    r"Jhn\.*",
+    r"Jo\.*" + _JO_NEGATIVE_LOOKAHEAD,
+    r"Jn\.*",
+)
+
+JOHN_REGULAR_EXPRESSION = rf"(John|{'|'.join(_ABBREVIATIONS)})"

pythonbible/tests/parser/parser_test.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+import pytest
+
 import pythonbible as bible
 
 
@@ -334,3 +336,69 @@ def test_book_abbreviations() -> None:
 
             if book != book.SONG_OF_SONGS:
                 assert expected == actual_period
+
+
+@pytest.mark.parametrize(
+    ("input_reference", "expected_output"),
+    [
+        (
+            "micah-jon",
+            bible.NormalizedReference(
+                book=bible.Book.MICAH,
+                start_chapter=None,
+                start_verse=None,
+                end_chapter=None,
+                end_verse=None,
+                end_book=bible.Book.JONAH,
+            ),
+        ),
+        (
+            "jon-jon",
+            bible.NormalizedReference(
+                book=bible.Book.JONAH,
+                start_chapter=None,
+                start_verse=None,
+                end_chapter=None,
+                end_verse=None,
+                end_book=bible.Book.JONAH,
+            ),
+        ),
+        (
+            "obadiah-jon",
+            bible.NormalizedReference(
+                book=bible.Book.OBADIAH,
+                start_chapter=None,
+                start_verse=None,
+                end_chapter=None,
+                end_verse=None,
+                end_book=bible.Book.JONAH,
+            ),
+        ),
+        (
+            "jon-john",
+            bible.NormalizedReference(
+                book=bible.Book.JONAH,
+                start_chapter=None,
+                start_verse=None,
+                end_chapter=None,
+                end_verse=None,
+                end_book=bible.Book.JOHN,
+            ),
+        ),
+    ],
+)
+def test_issue_235_jonah_abbreviation(
+    input_reference: str,
+    expected_output: bible.NormalizedReference,
+) -> None:
+    """Test for Issue 235 "Error getting reference to Jonah".
+
+    :param input_reference: The input reference string to test.
+    :param expected_output: The expected normalized reference output.
+    """
+    # Given a text string with an abbreviation for the book of Jonah
+    # When we parse the references from that text
+    references: list[bible.NormalizedReference] = bible.get_references(input_reference)
+
+    # Then the parser returns the appropriate normalized reference
+    assert references == [expected_output]