i18npool/source/characterclassification/cclass_unicode_parser.cxx | 18
++++++++--
offapi/com/sun/star/i18n/KParseTokens.idl | 7 +++
sc/source/core/tool/compiler.cxx | 6 +--
sw/source/core/bastyp/calc.cxx | 2 -
4 files changed, 26 insertions(+), 7 deletions(-)
New commits:
commit 0644deaa8a441e2ad9c41ad4b4a528b1579e9cd9
Author: Michael Stahl <michael.st...@allotropia.de>
AuthorDate: Wed Jan 29 19:54:14 2025 +0100
Commit: Xisco Fauli <xiscofa...@libreoffice.org>
CommitDate: Tue Feb 4 16:43:42 2025 +0100
tdf#158867 offapi,i18npool,starmath: fix "," in Math again
This is essentially the same bug that was fixed in commit
2caa9d7ddcff3f6e380c306b737e9b5e9cdaf4c2 "Resolves: tdf#127873 accept
',' comma group separator in number entities again".
The problem is that sw wants to recognize group separators only if there
are 3 digits following so it really looks like a number (see bug
tdf#42518), but starmath really wants to recognize either comma or dot
as a decimal separator and uses the GROUP_SEPARATOR_IN_NUMBER as a hack
to get this behaviour, so the same parser can work in any locale.
Introduce new constant GROUP_SEPARATOR_IN_NUMBER_3 so that sw and
starmath can request different parsing.
sc/source/core/tool/compiler.cxx also uses GROUP_SEPARATOR_IN_NUMBER and
it's unclear to me what is desired there, but there are no known
regression reports so leave the behaviour there unchanged.
(regression from commit 1bd9a51b826015746069fcc0d02a30a2ddc7e7f5)
Change-Id: Icb7662f26d89677cf84ccad07a2ea4c380587ab4
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/180920
Tested-by: Jenkins
Reviewed-by: Michael Stahl <michael.st...@allotropia.de>
(cherry picked from commit ff16c4e3f27efc0fc9ed734b19ae778482566cdb)
Reviewed-on: https://gerrit.libreoffice.org/c/core/+/181118
Reviewed-by: Thorsten Behrens <thorsten.behr...@allotropia.de>
diff --git a/i18npool/source/characterclassification/cclass_unicode_parser.cxx
b/i18npool/source/characterclassification/cclass_unicode_parser.cxx
index 9ed95e2f907a..97fae9518adc 100644
--- a/i18npool/source/characterclassification/cclass_unicode_parser.cxx
+++ b/i18npool/source/characterclassification/cclass_unicode_parser.cxx
@@ -23,6 +23,7 @@
#include <rtl/character.hxx>
#include <rtl/math.hxx>
#include <rtl/ustring.hxx>
+#include <sal/log.hxx>
#include <com/sun/star/i18n/KParseTokens.hpp>
#include <com/sun/star/i18n/KParseType.hpp>
#include <com/sun/star/i18n/LocaleData2.hpp>
@@ -441,7 +442,11 @@ void cclass_Unicode::initParserTable( const Locale&
rLocale, sal_Int32 startChar
cDecimalSepAlt = aItem.decimalSeparatorAlternative.toChar();
}
- if (nContTypes & KParseTokens::GROUP_SEPARATOR_IN_NUMBER)
+ SAL_WARN_IF((nContTypes & KParseTokens::GROUP_SEPARATOR_IN_NUMBER)
+ && (nContTypes & KParseTokens::GROUP_SEPARATOR_IN_NUMBER_3),
+ "i18npool", "only one GROUP_SEPARATOR_IN_NUMBER* should be used");
+ if (nContTypes & KParseTokens::GROUP_SEPARATOR_IN_NUMBER
+ || nContTypes & KParseTokens::GROUP_SEPARATOR_IN_NUMBER_3)
{
if ( cGroupSep < nDefCnt )
pTable[cGroupSep] |= ParserFlags::VALUE;
@@ -827,13 +832,20 @@ void cclass_Unicode::parseText( ParseResult& r, const
OUString& rText, sal_Int32
{
if (current == cGroupSep)
{
- // accept only if it is followed by 3 digits
+ // depending or requested nContTypes, accept only if
+ // it is followed by 3 digits
sal_Int32 tempIndex(index);
sal_uInt32 const nextChar2((tempIndex <
rText.getLength()) ? rText.iterateCodePoints(&tempIndex) : 0);
sal_uInt32 const nextChar3((tempIndex <
rText.getLength()) ? rText.iterateCodePoints(&tempIndex) : 0);
- if (getFlags(nextChar, eState) &
ParserFlags::VALUE_DIGIT
+ if ((nContTypes &
KParseTokens::GROUP_SEPARATOR_IN_NUMBER_3)
+ && getFlags(nextChar, eState) &
ParserFlags::VALUE_DIGIT
&& getFlags(nextChar2, eState) &
ParserFlags::VALUE_DIGIT
&& getFlags(nextChar3, eState) &
ParserFlags::VALUE_DIGIT)
+ {
+ nParseTokensType |=
KParseTokens::GROUP_SEPARATOR_IN_NUMBER_3;
+ }
+ else if ((nContTypes &
KParseTokens::GROUP_SEPARATOR_IN_NUMBER_3) == 0
+ && getFlags(nextChar, eState) &
ParserFlags::VALUE_DIGIT)
{
nParseTokensType |=
KParseTokens::GROUP_SEPARATOR_IN_NUMBER;
}
diff --git a/offapi/com/sun/star/i18n/KParseTokens.idl
b/offapi/com/sun/star/i18n/KParseTokens.idl
index f06b9861d6df..bb04c251d82c 100644
--- a/offapi/com/sun/star/i18n/KParseTokens.idl
+++ b/offapi/com/sun/star/i18n/KParseTokens.idl
@@ -93,6 +93,13 @@ published constants KParseTokens
/// Unicode (above 127) other number
const long UNI_OTHER_NUMBER = 0x00080000;
+ /** The same as GROUP_SEPARATOR_IN_NUMBER, but require <em>3</em>
+ digits following the group separator.
+
+ @since LibreOffice 25.2
+ */
+ const long GROUP_SEPARATOR_IN_NUMBER_3 = 0x04000000;
+
/** If this bit is set in <em>nContCharFlags</em> parameters, the
locale's group separator characters in numbers are accepted and
ignored/skipped. Else a group separator in a number ends the
diff --git a/sc/source/core/tool/compiler.cxx b/sc/source/core/tool/compiler.cxx
index 26684473bc44..6d7cd6fb6599 100644
--- a/sc/source/core/tool/compiler.cxx
+++ b/sc/source/core/tool/compiler.cxx
@@ -786,7 +786,7 @@ struct Convention_A1 : public ScCompiler::Convention
static constexpr OUString aAddAllowed(u"?#"_ustr);
return pCharClass->parseAnyToken( rFormula,
nSrcPos, nStartFlags, aAddAllowed,
- (bGroupSeparator ? nContFlags |
KParseTokens::GROUP_SEPARATOR_IN_NUMBER : nContFlags),
+ (bGroupSeparator ? nContFlags |
KParseTokens::GROUP_SEPARATOR_IN_NUMBER_3 : nContFlags),
aAddAllowed );
}
@@ -1411,7 +1411,7 @@ struct ConventionXL_A1 : public Convention_A1, public
ConventionXL
static constexpr OUString aAddAllowed(u"?!"_ustr);
return pCharClass->parseAnyToken( rFormula,
nSrcPos, nStartFlags, aAddAllowed,
- (bGroupSeparator ? nContFlags |
KParseTokens::GROUP_SEPARATOR_IN_NUMBER : nContFlags),
+ (bGroupSeparator ? nContFlags |
KParseTokens::GROUP_SEPARATOR_IN_NUMBER_3 : nContFlags),
aAddAllowed );
}
@@ -1762,7 +1762,7 @@ struct ConventionXL_R1C1 : public ScCompiler::Convention,
public ConventionXL
return pCharClass->parseAnyToken( rFormula,
nSrcPos, nStartFlags, aAddAllowed,
- (bGroupSeparator ? nContFlags |
KParseTokens::GROUP_SEPARATOR_IN_NUMBER : nContFlags),
+ (bGroupSeparator ? nContFlags |
KParseTokens::GROUP_SEPARATOR_IN_NUMBER_3 : nContFlags),
aAddAllowed );
}
diff --git a/sw/source/core/bastyp/calc.cxx b/sw/source/core/bastyp/calc.cxx
index fbfc4b701457..ebc24d4f6e0d 100644
--- a/sw/source/core/bastyp/calc.cxx
+++ b/sw/source/core/bastyp/calc.cxx
@@ -115,7 +115,7 @@ const sal_Int32 coStartFlags =
// Continuing characters may be any alphanumeric, underscore, or dot.
const sal_Int32 coContFlags =
- (coStartFlags | i18n::KParseTokens::ASC_DOT |
i18n::KParseTokens::GROUP_SEPARATOR_IN_NUMBER)
+ (coStartFlags | i18n::KParseTokens::ASC_DOT |
i18n::KParseTokens::GROUP_SEPARATOR_IN_NUMBER_3)
& ~i18n::KParseTokens::IGNORE_LEADING_WS;
extern "C" {
