i18npool/qa/cppunit/test_breakiterator.cxx | 21 +++++++++++++++++++++
1 file changed, 21 insertions(+)
New commits:
commit 8c063d4e293e76982d4310ddc162b565a9a3c16e
Author: Jonathan Clark <jonat...@libreoffice.org>
AuthorDate: Mon Jul 15 13:44:14 2024 -0600
Commit: Jonathan Clark <jonat...@libreoffice.org>
CommitDate: Tue Jul 16 04:43:26 2024 +0200
tdf#114160 Regression tests for non-breaking ZWJ
Per Unicode rules, ZWJ shouldn't be treated as a line break opportunity.
This change adds regression tests to verify lines do not break at ZWJ.
tdf#114160 was a regression introduced during a prior ICU upgrade. This
was fixed by commit 44699b3de37f07090ac6fee1cd97aa76036e9700, but no
tests were added for ZWJ at that time.
Change-Id: Ieca919daea11dc161ae35fb6ffe5bd366cf4a6f0
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/170534
Tested-by: Jenkins
Reviewed-by: Jonathan Clark <jonat...@libreoffice.org>
diff --git a/i18npool/qa/cppunit/test_breakiterator.cxx
b/i18npool/qa/cppunit/test_breakiterator.cxx
index baf1d47603c7..3b4ae3efea3d 100644
--- a/i18npool/qa/cppunit/test_breakiterator.cxx
+++ b/i18npool/qa/cppunit/test_breakiterator.cxx
@@ -477,6 +477,27 @@ void TestBreakIterator::testLineBreaking()
CPPUNIT_ASSERT_EQUAL(sal_Int32{ 5 }, res.breakIndex);
}
}
+
+ // tdf#114160: ZWJ shouldn't be treated as a breaking character
+ {
+ aLocale.Language = "mn";
+ aLocale.Country = "MN";
+
+ {
+ auto res =
m_xBreak->getLineBreak(u"\u1828\u1820\u200d\u00a0\u200d\u1873\u1873"_ustr, 6,
+ aLocale, 0, aHyphOptions,
aUserOptions);
+ CPPUNIT_ASSERT_EQUAL(sal_Int32(0), res.breakIndex);
+ }
+
+ aLocale.Language = "en";
+ aLocale.Country = "US";
+
+ {
+ auto res = m_xBreak->getLineBreak(u"AB\u200d\u00a0\u200dCD"_ustr,
6, aLocale, 0,
+ aHyphOptions, aUserOptions);
+ CPPUNIT_ASSERT_EQUAL(sal_Int32(0), res.breakIndex);
+ }
+ }
}
//See https://bugs.libreoffice.org/show_bug.cgi?id=49629
