i18nutil/source/utility/unicode.cxx | 4 ++--
sw/qa/extras/uiwriter/uiwriter7.cxx | 13 +++++++++++++
2 files changed, 15 insertions(+), 2 deletions(-)
New commits:
commit 6d78861299331fdfa51a070ced1ce498ceff342f
Author: Mike Kaganski <mike.kagan...@collabora.com>
AuthorDate: Sun Feb 2 14:37:34 2025 +0500
Commit: Mike Kaganski <mike.kagan...@collabora.com>
CommitDate: Sun Feb 2 12:01:13 2025 +0100
tdf#164989: Disallow combining characters when a hex already appeared
We either expect a single (maybe combined) character to convert into "U+"
notation, or a sequence of hexadecimal numbers (possibly with U+) for
conversion to characters. If we already saw a hexadecimal ASCII character,
it can't be preceded by a character combining with it, so stop as soon as
such an unexpected character appears.
Change-Id: Ic480fe8f173240eb263d5a77286b149c933049a6
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/181007
Tested-by: Jenkins
Reviewed-by: Mike Kaganski <mike.kagan...@collabora.com>
diff --git a/i18nutil/source/utility/unicode.cxx
b/i18nutil/source/utility/unicode.cxx
index d2d54e53623c..c9bfbeeb0a80 100644
--- a/i18nutil/source/utility/unicode.cxx
+++ b/i18nutil/source/utility/unicode.cxx
@@ -1065,7 +1065,7 @@ bool ToggleUnicodeCodepoint::AllowMoreInput(sal_uInt32
uChar)
switch ( unicode::getUnicodeType(uChar) )
{
case css::i18n::UnicodeType::SURROGATE:
- if( bPreventNonHex )
+ if (bPreventNonHex || mbIsHexString)
{
mbAllowMoreChars = false;
return false;
@@ -1096,7 +1096,7 @@ bool ToggleUnicodeCodepoint::AllowMoreInput(sal_uInt32
uChar)
case css::i18n::UnicodeType::NON_SPACING_MARK:
case css::i18n::UnicodeType::COMBINING_SPACING_MARK:
- if( bPreventNonHex )
+ if (bPreventNonHex || mbIsHexString)
{
mbAllowMoreChars = false;
return false;
diff --git a/sw/qa/extras/uiwriter/uiwriter7.cxx
b/sw/qa/extras/uiwriter/uiwriter7.cxx
index 909d31d70249..abb115312b0b 100644
--- a/sw/qa/extras/uiwriter/uiwriter7.cxx
+++ b/sw/qa/extras/uiwriter/uiwriter7.cxx
@@ -2411,6 +2411,19 @@ CPPUNIT_TEST_FIXTURE(SwUiWriterTest7,
testUnicodeNotationToggle)
// - Actual : xyz侮U+e0101
// i.e., one codepoint to the left of the combining codepoint was not
converted
CPPUNIT_ASSERT_EQUAL(sWithCombiningSMPName, sDocString);
+
+ pWrtShell->SplitNode();
+ // Given a combined character "è", consisting of U+0065 and U+0300,
followed by a HEX
+ // without a U+ for the conversion into the next character "n"
+ pWrtShell->Insert2(u"è006E"_ustr);
+ dispatchCommand(mxComponent, u".uno:UnicodeNotationToggle"_ustr,
aPropertyValues);
+ sDocString =
pWrtShell->GetCursor()->GetPointNode().GetTextNode()->GetText();
+ // Before tdf#164989 fix, this failed with
+ // - Expected: èn
+ // - Actual : è006U+0300
+ // i.e., it converted the last combined character *before* the HEX code
*to HEX*, replacing
+ // the last character of the HEX; not the expected conversion of the code
itself *from HEX*.
+ CPPUNIT_ASSERT_EQUAL(u"\u0065\u0300n"_ustr, sDocString);
}
CPPUNIT_TEST_FIXTURE(SwUiWriterTest7, testTdf34957)
