Skip to content

Unicode block bug #2508

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 5 commits into from
Apr 7, 2026
+50 −3
Merged

Unicode block bug #2508

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
55bb81c
Libyang erroneously interprets patterns with multiple Unicode blocks:…
manoe Apr 2, 2026
94b7201
Update copyright
manoe Apr 7, 2026
c8b5970
Change indentation of multi-line strings‰
manoe Apr 7, 2026
0ec2d66
Correct typo
manoe Apr 7, 2026
7eab138
Fix indentation based on uncrustify results
manoe Apr 7, 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
7 changes: 4 additions & 3 deletions src/ly_common.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -813,7 +813,7 @@ ly_pat_compile_xmlschema_chblocks_xmlschema2perl(const char *pattern, char **reg
{NULL, NULL}
};

size_t idx, idx2, start, end;
size_t idx, idx2, start, end, ublock;
char *perl_regex, *ptr;

perl_regex = *regex;
Expand Down Expand Up @@ -849,6 +849,7 @@ ly_pat_compile_xmlschema_chblocks_xmlschema2perl(const char *pattern, char **reg
return ly_err_new(err, LY_EVALID, 0, NULL, NULL, "Regular expression \"%s\" is not valid (\"%s\": %s).",
pattern, perl_regex + start + 5, "unknown block name");
}
ublock = idx;

/* 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) {
Expand All @@ -863,10 +864,10 @@ 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[idx][1] + 1, URANGE_LEN - 2);
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[idx][1], URANGE_LEN);
memcpy(perl_regex + start, ublock2urange[ublock][1], URANGE_LEN);
}
}

Expand Down
46 changes: 46 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 @@ -817,6 +817,52 @@ test_data_xml(void **state)
CHECK_LOG_CTX("Unsatisfied pattern - \"abc\" does not match \"a.*b\".", "/T_ANCHOR:port", 1);
TEST_ERROR_XML("T_ANCHOR", "cab");
CHECK_LOG_CTX("Unsatisfied pattern - \"cab\" does not match \"a.*b\".", "/T_ANCHOR:port", 1);

/* Unicode block test 1 - Basic Latin */
schema = MODULE_CREATE_YANG("T_UB_1", "leaf port {type string { pattern '\\p{IsBasicLatin}+';} } ");
UTEST_ADD_MODULE(schema, LYS_IN_YANG, NULL, NULL);
TEST_SUCCESS_XML("T_UB_1", "B4s1cLatin!", STRING, "B4s1cLatin!");

/* Unicode block test 2 - Basic Latin within brackets */
schema = MODULE_CREATE_YANG("T_UB_2", "leaf port {type string { pattern '[\\p{IsBasicLatin}]+';} } ");
UTEST_ADD_MODULE(schema, LYS_IN_YANG, NULL, NULL);
TEST_SUCCESS_XML("T_UB_2", "B4s1cLatin!", STRING, "B4s1cLatin!");

/* Unicode block test 3 - Latin-1 Supplement */
schema = MODULE_CREATE_YANG("T_UB_3", "leaf port {type string { pattern '[\\p{IsLatin-1Supplement}]+';} } ");
UTEST_ADD_MODULE(schema, LYS_IN_YANG, NULL, NULL);
TEST_SUCCESS_XML("T_UB_3", "ÁÉÍÓÖÜ", STRING, "ÁÉÍÓÖÜ");

/* Unicode block test 4 - Latin-1 Supplement */
schema = MODULE_CREATE_YANG("T_UB_4", "leaf port {type string { pattern '[\\p{IsLatin-1Supplement}]+';} } ");
UTEST_ADD_MODULE(schema, LYS_IN_YANG, NULL, NULL);
TEST_SUCCESS_XML("T_UB_4", "ÁÉÍÓÖÜ", STRING, "ÁÉÍÓÖÜ");

/* Unicode block test 5 - Latin Extended-A */
schema = MODULE_CREATE_YANG("T_UB_5", "leaf port {type string { pattern '[\\p{IsLatinExtended-A}]+';} } ");
UTEST_ADD_MODULE(schema, LYS_IN_YANG, NULL, NULL);
TEST_SUCCESS_XML("T_UB_5", "ŐŰőű", STRING, "ŐŰőű");

/* Unicode block test 6 - Basic Latin, Latin-1 Supplement, and Latin Extended-A */
schema = MODULE_CREATE_YANG("T_UB_6", "leaf port {type string {"
" pattern '[\\p{IsBasicLatin}\\p{IsLatin-1Supplement}\\p{IsLatinExtended-A}]+';"
"}} ");
UTEST_ADD_MODULE(schema, LYS_IN_YANG, NULL, NULL);
TEST_SUCCESS_XML("T_UB_6", "Árvíztűrő tükörfúrógép!", STRING, "Árvíztűrő tükörfúrógép!");

/* Unicode block test 7 - Unknown Unicode block */
schema = MODULE_CREATE_YANG("T_UB_7", "leaf port {type string { pattern '\\p{IsUnknownUnicodeBlock}+';} } ");
UTEST_INVALID_MODULE(schema, LYS_IN_YANG, NULL, LY_EVALID);
CHECK_LOG_CTX("Regular expression \"\\p{IsUnknownUnicodeBlock}+\" "
"is not valid (\"UnknownUnicodeBlock}+\": unknown block name).", "/T_UB_7:port", 0);

/* Unicode block test 8 - Unknown Unicode block with Basic Latin */
schema = MODULE_CREATE_YANG("T_UB_8", "leaf port {type string { "
" pattern '[\\p{IsBasicLatin}\\p{IsUnknownUnicodeBlock}]+';"
"}} ");
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);
}

static void
Expand Down
Loading