Skip to content

Unicode Specials block bug #2510

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
michalvasko merged 3 commits into from
Apr 14, 2026
Merged

Unicode Specials block bug #2510

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
e7a4e3a
Correction of unicode block range bug
manoe Apr 10, 2026
798683a
Unicode Specials block bug correction
manoe Apr 13, 2026
2b41eda
Use original char array with strlen to map unicode block to unicode r…
manoe Apr 13, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 15 additions & 14 deletions src/ly_common.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -724,7 +724,6 @@ ly_pat_compile_posix(const char *pattern, void **pat_comp, struct ly_err_item **
static LY_ERR
ly_pat_compile_xmlschema_chblocks_xmlschema2perl(const char *pattern, char **regex, struct ly_err_item **err)
{
#define URANGE_LEN 19
char *ublock2urange[][2] = {
{"BasicLatin", "[\\x{0000}-\\x{007F}]"},
{"Latin-1Supplement", "[\\x{0080}-\\x{00FF}]"},
Expand Down Expand Up @@ -829,15 +828,6 @@ ly_pat_compile_xmlschema_chblocks_xmlschema2perl(const char *pattern, char **reg
}
end = (ptr - perl_regex) + 1;

/* need more space */
if (end - start < URANGE_LEN) {
perl_regex = ly_realloc(perl_regex, strlen(perl_regex) + (URANGE_LEN - (end - start)) + 1);
*regex = perl_regex;
if (!perl_regex) {
return ly_err_new(err, LY_EMEM, 0, NULL, NULL, LY_EMEM_MSG);
}
}

/* find our range */
for (idx = 0; ublock2urange[idx][0]; ++idx) {
if (!strncmp(perl_regex + start + ly_strlen_const("\\p{Is"),
Expand All @@ -851,6 +841,17 @@ ly_pat_compile_xmlschema_chblocks_xmlschema2perl(const char *pattern, char **reg
}
ublock = idx;

/* need more space */
size_t urange_len = strlen(ublock2urange[ublock][1]);

if (end - start < urange_len) {
perl_regex = ly_realloc(perl_regex, strlen(perl_regex) + (urange_len - (end - start)) + 1);
*regex = perl_regex;
if (!perl_regex) {
return ly_err_new(err, LY_EMEM, 0, NULL, NULL, LY_EMEM_MSG);
}
}

/* make the space in the string and replace the block (but we cannot include brackets if it was already enclosed in them) */
for (idx2 = 0, idx = 0; idx2 < start; ++idx2) {
if ((perl_regex[idx2] == '[') && (!idx2 || (perl_regex[idx2 - 1] != '\\'))) {
Expand All @@ -863,11 +864,11 @@ ly_pat_compile_xmlschema_chblocks_xmlschema2perl(const char *pattern, char **reg
}
if (idx) {
/* skip brackets */
memmove(perl_regex + start + (URANGE_LEN - 2), perl_regex + end, strlen(perl_regex + end) + 1);
memcpy(perl_regex + start, ublock2urange[ublock][1] + 1, URANGE_LEN - 2);
memmove(perl_regex + start + (urange_len - 2), perl_regex + end, strlen(perl_regex + end) + 1);
memcpy(perl_regex + start, ublock2urange[ublock][1] + 1, urange_len - 2);
} else {
memmove(perl_regex + start + URANGE_LEN, perl_regex + end, strlen(perl_regex + end) + 1);
memcpy(perl_regex + start, ublock2urange[ublock][1], URANGE_LEN);
memmove(perl_regex + start + urange_len, perl_regex + end, strlen(perl_regex + end) + 1);
memcpy(perl_regex + start, ublock2urange[ublock][1], urange_len);
}
}

Expand Down
16 changes: 16 additions & 0 deletions tests/utests/types/string.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -863,6 +863,22 @@ test_data_xml(void **state)
UTEST_INVALID_MODULE(schema, LYS_IN_YANG, NULL, LY_EVALID);
CHECK_LOG_CTX("Regular expression \"[\\p{IsBasicLatin}\\p{IsUnknownUnicodeBlock}]+\" "
"is not valid (\"UnknownUnicodeBlock}]+\": unknown block name).", "/T_UB_8:port", 0);

schema = MODULE_CREATE_YANG("T_UB_9", "leaf port {type string { pattern "
"'[\\p{IsSpecials}]+';}}");
UTEST_ADD_MODULE(schema, LYS_IN_YANG, NULL, NULL);
TEST_SUCCESS_XML("T_UB_9", "&#xFFFA;&#xFFFD;", STRING, "\xef\xbf\xba\xef\xbf\xbd");

schema = MODULE_CREATE_YANG("T_UB_10", "leaf port {type string { pattern "
"'[\\p{IsSpecials}]+';}}");
UTEST_ADD_MODULE(schema, LYS_IN_YANG, NULL, NULL);
TEST_ERROR_XML("T_UB_10", "&#xFFDF;&#xFFFD;");
CHECK_LOG_CTX("Unsatisfied pattern - \"\xef\xbf\x9f\xef\xbf\xbd\" does not match \"[\\p{IsSpecials}]+\".", "/T_UB_10:port", 1);

schema = MODULE_CREATE_YANG("T_UB_11", "leaf port {type string { pattern "
"'[\\p{IsSpecials}]+';}}");
UTEST_ADD_MODULE(schema, LYS_IN_YANG, NULL, NULL);
TEST_SUCCESS_XML("T_UB_11", "&#xFEFF;&#xFFFD;", STRING, "\xef\xbb\xbf\xef\xbf\xbd");
}

static void
Expand Down
Loading