Resolves: tdf#123575 treat Katakana middle dots as midletter
Treat U+30FB KATAKANA MIDDLE DOT U+FF65 HALFWIDTH KATAKANA MIDDLE DOT like U+00B7 MIDDLE DOT and other U_WB_MIDLETTER. Change-Id: Iea18e7582f29edf5d8c5bad047f97ed4088edf7c Reviewed-on: https://gerrit.libreoffice.org/68032 Reviewed-by: Eike Rathke <erack@redhat.com> Tested-by: Jenkins
This commit is contained in:
@@ -654,8 +654,12 @@ ParserFlags cclass_Unicode::getFlagsExtended(sal_uInt32 const c)
|
|||||||
case U_OTHER_PUNCTUATION:
|
case U_OTHER_PUNCTUATION:
|
||||||
// fdo#61754 Lets see (if we not at the start) if this is midletter
|
// fdo#61754 Lets see (if we not at the start) if this is midletter
|
||||||
// punctuation and allow it in a word if it is similarly to
|
// punctuation and allow it in a word if it is similarly to
|
||||||
// U_NON_SPACING_MARK
|
// U_NON_SPACING_MARK, for example U+00B7 MIDDLE DOT.
|
||||||
if (bStart || U_WB_MIDLETTER != u_getIntPropertyValue(c, UCHAR_WORD_BREAK))
|
// tdf#123575 for U+30FB KATAKANA MIDDLE DOT property is not
|
||||||
|
// U_WB_MIDLETTER but U_WB_KATAKANA instead, explicitly test that
|
||||||
|
// and U+FF65 HALFWIDTH KATAKANA MIDDLE DOT.
|
||||||
|
if (bStart || (U_WB_MIDLETTER != u_getIntPropertyValue(c, UCHAR_WORD_BREAK)
|
||||||
|
&& c != 0x30FB && c != 0xFF65))
|
||||||
return ParserFlags::ILLEGAL;
|
return ParserFlags::ILLEGAL;
|
||||||
else
|
else
|
||||||
{
|
{
|
||||||
|
Reference in New Issue
Block a user