[ooo-build-commit] Branch 'ooo/master' - 2 commits - i18npool/inc i18npool/source svtools/source
Jan Holesovsky
kendy at kemper.freedesktop.org
Thu Aug 6 18:29:27 PDT 2009
i18npool/inc/breakiterator_ctl.hxx | 1
i18npool/inc/breakiterator_unicode.hxx | 6
i18npool/inc/xdictionary.hxx | 4
i18npool/source/breakiterator/breakiterator_cjk.cxx | 4
i18npool/source/breakiterator/breakiterator_ctl.cxx | 7
i18npool/source/breakiterator/breakiterator_unicode.cxx | 29 +-
i18npool/source/breakiterator/data/dict_word.txt | 3
i18npool/source/breakiterator/data/dict_word_dash.txt | 148 ----------
i18npool/source/breakiterator/data/dict_word_nodash.txt | 147 ++++++++++
i18npool/source/breakiterator/data/dict_word_prepostdash.txt | 157 +++++++++++
i18npool/source/breakiterator/makefile.mk | 2
i18npool/source/breakiterator/xdictionary.cxx | 30 ++
i18npool/source/localedata/data/de_DE.xml | 9
i18npool/source/localedata/data/nl_NL.xml | 35 +-
i18npool/source/localedata/data/pl_PL.xml | 7
i18npool/source/localedata/data/sv_SE.xml | 7
svtools/source/config/useroptions.cxx | 107 +++++--
17 files changed, 478 insertions(+), 225 deletions(-)
New commits:
commit f7144b16bc066c6fbff3a5a883f0c76cf977f9f6
Author: Release Engineers <releng at openoffice.org>
Date: Thu Aug 6 18:13:57 2009 +0000
CWS-TOOLING: integrate CWS tl73
2009-07-31 15:29:33 +0200 tl r274535 : #i64400# dash/hyphen should not break words
diff --git a/i18npool/inc/breakiterator_ctl.hxx b/i18npool/inc/breakiterator_ctl.hxx
index 089cbaa..161c1a5 100644
--- a/i18npool/inc/breakiterator_ctl.hxx
+++ b/i18npool/inc/breakiterator_ctl.hxx
@@ -58,6 +58,7 @@ protected:
sal_Int32* nextCellIndex;
sal_Int32* previousCellIndex;
sal_Int32 cellIndexSize;
+
virtual void SAL_CALL makeIndex(const rtl::OUString& text, sal_Int32 pos) throw(com::sun::star::uno::RuntimeException);
};
diff --git a/i18npool/inc/breakiterator_unicode.hxx b/i18npool/inc/breakiterator_unicode.hxx
index b0414ef..4708d09 100644
--- a/i18npool/inc/breakiterator_unicode.hxx
+++ b/i18npool/inc/breakiterator_unicode.hxx
@@ -86,12 +86,16 @@ protected:
const sal_Char *cBreakIterator, *wordRule, *lineRule;
Boundary result; // for word break iterator
- struct {
+ struct BI_Data {
UnicodeString aICUText;
icu::BreakIterator *aBreakIterator;
+
+ BI_Data() : aICUText(), aBreakIterator(NULL) {}
} character, word, sentence, line, *icuBI;
+
com::sun::star::lang::Locale aLocale;
sal_Int16 aBreakType, aWordType;
+
void SAL_CALL loadICUBreakIterator(const com::sun::star::lang::Locale& rLocale,
sal_Int16 rBreakType, sal_Int16 rWordType, const sal_Char* name, const rtl::OUString& rText) throw(com::sun::star::uno::RuntimeException);
};
diff --git a/i18npool/inc/xdictionary.hxx b/i18npool/inc/xdictionary.hxx
index 1e18e17..a338973 100644
--- a/i18npool/inc/xdictionary.hxx
+++ b/i18npool/inc/xdictionary.hxx
@@ -45,11 +45,13 @@ namespace com { namespace sun { namespace star { namespace i18n {
// cache structure.
struct WordBreakCache {
- sal_Bool equals(const sal_Unicode *str, Boundary& boundary); // checking cached string
sal_Int32 length; // contents length saved here.
sal_Unicode *contents; // seperated segment contents.
sal_Int32* wordboundary; // word boundaries in segments.
sal_Int32 size; // size of wordboundary
+
+ WordBreakCache();
+ sal_Bool equals(const sal_Unicode *str, Boundary& boundary); // checking cached string
};
class xdictionary
diff --git a/i18npool/source/breakiterator/breakiterator_cjk.cxx b/i18npool/source/breakiterator/breakiterator_cjk.cxx
index 554b68b..78c3e25 100644
--- a/i18npool/source/breakiterator/breakiterator_cjk.cxx
+++ b/i18npool/source/breakiterator/breakiterator_cjk.cxx
@@ -46,7 +46,9 @@ namespace com { namespace sun { namespace star { namespace i18n {
// class BreakIterator_CJK
// ----------------------------------------------------;
-BreakIterator_CJK::BreakIterator_CJK() : dict(NULL)
+BreakIterator_CJK::BreakIterator_CJK() :
+ dict( NULL ),
+ hangingCharacters()
{
cBreakIterator = "com.sun.star.i18n.BreakIterator_CJK";
}
diff --git a/i18npool/source/breakiterator/breakiterator_ctl.cxx b/i18npool/source/breakiterator/breakiterator_ctl.cxx
index 551781e..16743cd 100644
--- a/i18npool/source/breakiterator/breakiterator_ctl.cxx
+++ b/i18npool/source/breakiterator/breakiterator_ctl.cxx
@@ -45,11 +45,14 @@ namespace com { namespace sun { namespace star { namespace i18n {
/**
* Constructor.
*/
-BreakIterator_CTL::BreakIterator_CTL()
+BreakIterator_CTL::BreakIterator_CTL() :
+ cachedText(),
+ nextCellIndex( NULL ),
+ previousCellIndex( NULL ),
+ cellIndexSize( 512 )
{
cBreakIterator = "com.sun.star.i18n.BreakIterator_CTL";
// to improve performance, alloc big enough memory in construct.
- cellIndexSize = 512;
nextCellIndex = (sal_Int32*) calloc(cellIndexSize, sizeof(sal_Int32));
previousCellIndex = (sal_Int32*) calloc(cellIndexSize, sizeof(sal_Int32));
memset(nextCellIndex, 0, cellIndexSize * sizeof(sal_Int32));
diff --git a/i18npool/source/breakiterator/breakiterator_unicode.cxx b/i18npool/source/breakiterator/breakiterator_unicode.cxx
index ad1ef28..5a6e1ab 100644
--- a/i18npool/source/breakiterator/breakiterator_unicode.cxx
+++ b/i18npool/source/breakiterator/breakiterator_unicode.cxx
@@ -51,20 +51,23 @@ namespace com { namespace sun { namespace star { namespace i18n {
#define ERROR ::com::sun::star::uno::RuntimeException()
-#define ImplementName "com.sun.star.i18n.BreakIterator_Unicode";
-
-
-BreakIterator_Unicode::BreakIterator_Unicode()
+//#define ImplementName "com.sun.star.i18n.BreakIterator_Unicode";
+
+
+BreakIterator_Unicode::BreakIterator_Unicode() :
+ cBreakIterator( "com.sun.star.i18n.BreakIterator_Unicode" ), // implementation name
+ wordRule( "word" ),
+ lineRule( "line" ),
+ result(),
+ character(),
+ word(),
+ sentence(),
+ line(),
+ icuBI( NULL ),
+ aLocale(),
+ aBreakType(),
+ aWordType()
{
- wordRule="word";
- lineRule="line";
- character.aBreakIterator=word.aBreakIterator=sentence.aBreakIterator=line.aBreakIterator=NULL;
- character.aICUText=UnicodeString();
- word.aICUText=UnicodeString();
- sentence.aICUText=UnicodeString();
- line.aICUText=UnicodeString();
- cBreakIterator = ImplementName;
- icuBI=NULL;
}
diff --git a/i18npool/source/breakiterator/data/dict_word.txt b/i18npool/source/breakiterator/data/dict_word.txt
index 4c5c808..367a82d 100644
--- a/i18npool/source/breakiterator/data/dict_word.txt
+++ b/i18npool/source/breakiterator/data/dict_word.txt
@@ -34,7 +34,8 @@ $ALetter = [\u0002 [:Alphabetic:] [:name= COMMERCIAL AT:] [:name= HEBREW PUNCT
$MidLetter = [[:name = APOSTROPHE:] [:name = GRAVE ACCENT:] \u0084 [:name = SOFT HYPHEN:] [:name = MIDDLE DOT:] [:name = GREEK TONOS:] [:name= FULL STOP:]
[:name = HEBREW PUNCTUATION GERSHAYIM:] [:name = DOUBLE VERTICAL LINE:] [:name = LEFT SINGLE QUOTATION MARK:]
- [:name = RIGHT SINGLE QUOTATION MARK:] [:name = HYPHENATION POINT:] [:name = PRIME:] ];
+ [:name = RIGHT SINGLE QUOTATION MARK:] [:name = HYPHENATION POINT:] [:name = PRIME:]
+ [:name = HYPHEN-MINUS:] [:name = EN DASH:] [:name = EM DASH:] ];
$SufixLetter = [:name= FULL STOP:];
diff --git a/i18npool/source/breakiterator/data/dict_word_dash.txt b/i18npool/source/breakiterator/data/dict_word_dash.txt
deleted file mode 100644
index 7f861c7..0000000
--- a/i18npool/source/breakiterator/data/dict_word_dash.txt
+++ /dev/null
@@ -1,148 +0,0 @@
-#
-# Copyright (C) 2002-2003, International Business Machines Corporation and others.
-# All Rights Reserved.
-#
-# file: dict_word.txt
-#
-# ICU Word Break Rules
-# See Unicode Standard Annex #29.
-# These rules are based on Version 4.0.0, dated 2003-04-17
-#
-
-
-
-####################################################################################
-#
-# Character class definitions from TR 29
-#
-####################################################################################
-$Katakana = [[:Script = KATAKANA:] [:name = KATAKANA-HIRAGANA PROLONGED SOUND MARK:]
- [:name = HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK:]
- [:name = HALFWIDTH KATAKANA VOICED SOUND MARK:]
- [:name = HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK:]];
-
-$Ideographic = [:Ideographic:];
-$Hangul = [:Script = HANGUL:];
-
-$ALetter = [\u0002 [:Alphabetic:] [:name= COMMERCIAL AT:] [:name= HEBREW PUNCTUATION GERESH:]
- - $Ideographic
- - $Katakana
- - $Hangul
- - [:Script = Thai:]
- - [:Script = Lao:]
- - [:Script = Hiragana:]];
-
-$MidLetter = [[:name = APOSTROPHE:] [:name = GRAVE ACCENT:] \u0084 [:name = SOFT HYPHEN:] [:name = MIDDLE DOT:] [:name = GREEK TONOS:] [:name= FULL STOP:]
- [:name = HEBREW PUNCTUATION GERSHAYIM:] [:name = DOUBLE VERTICAL LINE:] [:name = LEFT SINGLE QUOTATION MARK:]
- [:name = RIGHT SINGLE QUOTATION MARK:] [:name = HYPHENATION POINT:] [:name = PRIME:]
- [:name = HYPHEN-MINUS:] [:name = EN DASH:] ];
-
-$SufixLetter = [:name= FULL STOP:];
-
-
-$MidNum = [[:LineBreak = Infix_Numeric:] [:name= COMMERCIAL AT:] \u0084 [:name = GREEK TONOS:] [:name = ARABIC DECIMAL SEPARATOR:]
- [:name = LEFT SINGLE QUOTATION MARK:] [:name = RIGHT SINGLE QUOTATION MARK:] [:name = SINGLE HIGH-REVERSED-9 QUOTATION MARK:]
- [:name = PRIME:]];
-$Numeric = [:LineBreak = Numeric:];
-
-
-$TheZWSP = \u200b;
-
-#
-# Character Class Definitions.
-# The names are those from TR29.
-#
-$CR = \u000d;
-$LF = \u000a;
-$Control = [[[:Zl:] [:Zp:] [:Cc:] [:Cf:]] - $TheZWSP];
-$Extend = [[:Grapheme_Extend = TRUE:]];
-
-
-
-
-####################################################################################
-#
-# Word Break Rules. Definitions and Rules specific to word break begin Here.
-#
-####################################################################################
-
-$Format = [[:Cf:] - $TheZWSP];
-
-
-
-# Rule 3: Treat a grapheme cluster as if it were a single character.
-# Hangul Syllables are easier to deal with here than they are in Grapheme Clusters
-# because we don't need to find the boundaries between adjacent syllables -
-# they won't be word boundaries.
-#
-
-
-#
-# "Extended" definitions. Grapheme Cluster + Format Chars, treated like the base char.
-#
-$ALetterEx = $ALetter $Extend*;
-$NumericEx = $Numeric $Extend*;
-$MidNumEx = $MidNum $Extend*;
-$MidLetterEx = $MidLetter $Extend*;
-$SufixLetterEx= $SufixLetter $Extend*;
-$KatakanaEx = $Katakana $Extend*;
-$IdeographicEx= $Ideographic $Extend*;
-$HangulEx = $Hangul $Extend*;
-$FormatEx = $Format $Extend*;
-
-
-#
-# Numbers. Rules 8, 11, 12 form the TR.
-#
-$NumberSequence = $NumericEx ($FormatEx* $MidNumEx? $FormatEx* $NumericEx)*;
-$NumberSequence {100};
-
-#
-# Words. Alpha-numerics. Rule 5, 6, 7, 9, 10
-# - must include at least one letter.
-# - may include both letters and numbers.
-# - may include MideLetter, MidNumber punctuation.
-#
-$LetterSequence = $ALetterEx ($FormatEx* $MidLetterEx? $FormatEx* $ALetterEx)*; # rules #6, #7
-($NumberSequence $FormatEx*)? $LetterSequence ($FormatEx* ($NumberSequence | $LetterSequence))* $SufixLetterEx? {200};
-
-[[:P:][:S:]]*;
-
-#
-# Do not break between Katakana. Rule #13.
-#
-$KatakanaEx ($FormatEx* $KatakanaEx)* {300};
-[:Hiragana:] $Extend* {300};
-
-#
-# Ideographic Characters. Stand by themselves as words.
-# Separated from the "Everything Else" rule, below, only so that they
-# can be tagged with a return value. TODO: is this what we want?
-#
-$IdeographicEx ($FormatEx* $IdeographicEx)* {400};
-$HangulEx ($FormatEx* $HangulEx)* {400};
-
-#
-# Everything Else, with no tag.
-# Non-Control chars combine with $Extend (combining) chars.
-# Controls are do not.
-#
-[^$Control [:Ideographic:]] $Extend*;
-$CR $LF;
-
-#
-# Reverse Rules. Back up over any of the chars that can group together.
-# (Reverse rules do not need to be exact; they can back up too far,
-# but must back up at least enough, and must stop on a boundary.)
-#
-
-# NonStarters are the set of all characters that can appear at the 2nd - nth position of
-# a word. (They may also be the first.) The reverse rule skips over these, until it
-# reaches something that can only be the start (and probably only) char in a "word".
-# A space or punctuation meets the test.
-#
-$NonStarters = [$Numeric $ALetter $Katakana $Ideographic $Hangul [:P:] [:S:] $MidLetter $MidNum $SufixLetter $Extend $Format];
-
-#!.*;
-! ($NonStarters* | \n \r) .;
-
diff --git a/i18npool/source/breakiterator/data/dict_word_nodash.txt b/i18npool/source/breakiterator/data/dict_word_nodash.txt
new file mode 100644
index 0000000..4c5c808
--- /dev/null
+++ b/i18npool/source/breakiterator/data/dict_word_nodash.txt
@@ -0,0 +1,147 @@
+#
+# Copyright (C) 2002-2003, International Business Machines Corporation and others.
+# All Rights Reserved.
+#
+# file: dict_word.txt
+#
+# ICU Word Break Rules
+# See Unicode Standard Annex #29.
+# These rules are based on Version 4.0.0, dated 2003-04-17
+#
+
+
+
+####################################################################################
+#
+# Character class definitions from TR 29
+#
+####################################################################################
+$Katakana = [[:Script = KATAKANA:] [:name = KATAKANA-HIRAGANA PROLONGED SOUND MARK:]
+ [:name = HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK:]
+ [:name = HALFWIDTH KATAKANA VOICED SOUND MARK:]
+ [:name = HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK:]];
+
+$Ideographic = [:Ideographic:];
+$Hangul = [:Script = HANGUL:];
+
+$ALetter = [\u0002 [:Alphabetic:] [:name= COMMERCIAL AT:] [:name= HEBREW PUNCTUATION GERESH:]
+ - $Ideographic
+ - $Katakana
+ - $Hangul
+ - [:Script = Thai:]
+ - [:Script = Lao:]
+ - [:Script = Hiragana:]];
+
+$MidLetter = [[:name = APOSTROPHE:] [:name = GRAVE ACCENT:] \u0084 [:name = SOFT HYPHEN:] [:name = MIDDLE DOT:] [:name = GREEK TONOS:] [:name= FULL STOP:]
+ [:name = HEBREW PUNCTUATION GERSHAYIM:] [:name = DOUBLE VERTICAL LINE:] [:name = LEFT SINGLE QUOTATION MARK:]
+ [:name = RIGHT SINGLE QUOTATION MARK:] [:name = HYPHENATION POINT:] [:name = PRIME:] ];
+
+$SufixLetter = [:name= FULL STOP:];
+
+
+$MidNum = [[:LineBreak = Infix_Numeric:] [:name= COMMERCIAL AT:] \u0084 [:name = GREEK TONOS:] [:name = ARABIC DECIMAL SEPARATOR:]
+ [:name = LEFT SINGLE QUOTATION MARK:] [:name = RIGHT SINGLE QUOTATION MARK:] [:name = SINGLE HIGH-REVERSED-9 QUOTATION MARK:]
+ [:name = PRIME:]];
+$Numeric = [:LineBreak = Numeric:];
+
+
+$TheZWSP = \u200b;
+
+#
+# Character Class Definitions.
+# The names are those from TR29.
+#
+$CR = \u000d;
+$LF = \u000a;
+$Control = [[[:Zl:] [:Zp:] [:Cc:] [:Cf:]] - $TheZWSP];
+$Extend = [[:Grapheme_Extend = TRUE:]];
+
+
+
+
+####################################################################################
+#
+# Word Break Rules. Definitions and Rules specific to word break begin Here.
+#
+####################################################################################
+
+$Format = [[:Cf:] - $TheZWSP];
+
+
+
+# Rule 3: Treat a grapheme cluster as if it were a single character.
+# Hangul Syllables are easier to deal with here than they are in Grapheme Clusters
+# because we don't need to find the boundaries between adjacent syllables -
+# they won't be word boundaries.
+#
+
+
+#
+# "Extended" definitions. Grapheme Cluster + Format Chars, treated like the base char.
+#
+$ALetterEx = $ALetter $Extend*;
+$NumericEx = $Numeric $Extend*;
+$MidNumEx = $MidNum $Extend*;
+$MidLetterEx = $MidLetter $Extend*;
+$SufixLetterEx= $SufixLetter $Extend*;
+$KatakanaEx = $Katakana $Extend*;
+$IdeographicEx= $Ideographic $Extend*;
+$HangulEx = $Hangul $Extend*;
+$FormatEx = $Format $Extend*;
+
+
+#
+# Numbers. Rules 8, 11, 12 form the TR.
+#
+$NumberSequence = $NumericEx ($FormatEx* $MidNumEx? $FormatEx* $NumericEx)*;
+$NumberSequence {100};
+
+#
+# Words. Alpha-numerics. Rule 5, 6, 7, 9, 10
+# - must include at least one letter.
+# - may include both letters and numbers.
+# - may include MideLetter, MidNumber punctuation.
+#
+$LetterSequence = $ALetterEx ($FormatEx* $MidLetterEx? $FormatEx* $ALetterEx)*; # rules #6, #7
+($NumberSequence $FormatEx*)? $LetterSequence ($FormatEx* ($NumberSequence | $LetterSequence))* $SufixLetterEx? {200};
+
+[[:P:][:S:]]*;
+
+#
+# Do not break between Katakana. Rule #13.
+#
+$KatakanaEx ($FormatEx* $KatakanaEx)* {300};
+[:Hiragana:] $Extend* {300};
+
+#
+# Ideographic Characters. Stand by themselves as words.
+# Separated from the "Everything Else" rule, below, only so that they
+# can be tagged with a return value. TODO: is this what we want?
+#
+$IdeographicEx ($FormatEx* $IdeographicEx)* {400};
+$HangulEx ($FormatEx* $HangulEx)* {400};
+
+#
+# Everything Else, with no tag.
+# Non-Control chars combine with $Extend (combining) chars.
+# Controls are do not.
+#
+[^$Control [:Ideographic:]] $Extend*;
+$CR $LF;
+
+#
+# Reverse Rules. Back up over any of the chars that can group together.
+# (Reverse rules do not need to be exact; they can back up too far,
+# but must back up at least enough, and must stop on a boundary.)
+#
+
+# NonStarters are the set of all characters that can appear at the 2nd - nth position of
+# a word. (They may also be the first.) The reverse rule skips over these, until it
+# reaches something that can only be the start (and probably only) char in a "word".
+# A space or punctuation meets the test.
+#
+$NonStarters = [$Numeric $ALetter $Katakana $Ideographic $Hangul [:P:] [:S:] $MidLetter $MidNum $SufixLetter $Extend $Format];
+
+#!.*;
+! ($NonStarters* | \n \r) .;
+
diff --git a/i18npool/source/breakiterator/data/dict_word_prepostdash.txt b/i18npool/source/breakiterator/data/dict_word_prepostdash.txt
new file mode 100644
index 0000000..1bf9445
--- /dev/null
+++ b/i18npool/source/breakiterator/data/dict_word_prepostdash.txt
@@ -0,0 +1,157 @@
+#
+# Copyright (C) 2002-2003, International Business Machines Corporation and others.
+# All Rights Reserved.
+#
+# file: dict_word.txt
+#
+# ICU Word Break Rules
+# See Unicode Standard Annex #29.
+# These rules are based on Version 4.0.0, dated 2003-04-17
+#
+
+
+
+####################################################################################
+#
+# Character class definitions from TR 29
+#
+####################################################################################
+$Katakana = [[:Script = KATAKANA:] [:name = KATAKANA-HIRAGANA PROLONGED SOUND MARK:]
+ [:name = HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK:]
+ [:name = HALFWIDTH KATAKANA VOICED SOUND MARK:]
+ [:name = HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK:]];
+
+$Ideographic = [:Ideographic:];
+$Hangul = [:Script = HANGUL:];
+
+# list of dashes or hyphens that should be accepted as part of the word if a single one of these
+# pre- or postfixes a word. E.g. in German: "Arbeits-" or "-nehmer" where that hyphen needs to
+# be part of the word in order to have it properly spell checked etc.
+$PrePostDashHyphen = [ [:name = HYPHEN-MINUS:] [:name = EN DASH:] [:name = EM DASH:] ];
+
+
+$ALetter = [\u0002 [:Alphabetic:] [:name= COMMERCIAL AT:] [:name= HEBREW PUNCTUATION GERESH:]
+ - $Ideographic
+ - $Katakana
+ - $Hangul
+ - [:Script = Thai:]
+ - [:Script = Lao:]
+ - [:Script = Hiragana:]];
+
+$MidLetter = [[:name = APOSTROPHE:] [:name = GRAVE ACCENT:] \u0084 [:name = SOFT HYPHEN:] [:name = MIDDLE DOT:] [:name = GREEK TONOS:] [:name= FULL STOP:]
+ [:name = HEBREW PUNCTUATION GERSHAYIM:] [:name = DOUBLE VERTICAL LINE:] [:name = LEFT SINGLE QUOTATION MARK:]
+ [:name = RIGHT SINGLE QUOTATION MARK:] [:name = HYPHENATION POINT:] [:name = PRIME:]
+ [:name = HYPHEN-MINUS:] [:name = EN DASH:] [:name = EM DASH:] ];
+
+$SufixLetter = [:name= FULL STOP:];
+
+
+$MidNum = [[:LineBreak = Infix_Numeric:] [:name= COMMERCIAL AT:] \u0084 [:name = GREEK TONOS:] [:name = ARABIC DECIMAL SEPARATOR:]
+ [:name = LEFT SINGLE QUOTATION MARK:] [:name = RIGHT SINGLE QUOTATION MARK:] [:name = SINGLE HIGH-REVERSED-9 QUOTATION MARK:]
+ [:name = PRIME:]];
+$Numeric = [:LineBreak = Numeric:];
+
+
+$TheZWSP = \u200b;
+
+#
+# Character Class Definitions.
+# The names are those from TR29.
+#
+$CR = \u000d;
+$LF = \u000a;
+$Control = [[[:Zl:] [:Zp:] [:Cc:] [:Cf:]] - $TheZWSP];
+$Extend = [[:Grapheme_Extend = TRUE:]];
+
+
+
+
+####################################################################################
+#
+# Word Break Rules. Definitions and Rules specific to word break begin Here.
+#
+####################################################################################
+
+$Format = [[:Cf:] - $TheZWSP];
+
+
+
+# Rule 3: Treat a grapheme cluster as if it were a single character.
+# Hangul Syllables are easier to deal with here than they are in Grapheme Clusters
+# because we don't need to find the boundaries between adjacent syllables -
+# they won't be word boundaries.
+#
+
+
+#
+# "Extended" definitions. Grapheme Cluster + Format Chars, treated like the base char.
+#
+$ALetterEx = $ALetter $Extend*;
+$NumericEx = $Numeric $Extend*;
+$MidNumEx = $MidNum $Extend*;
+$MidLetterEx = $MidLetter $Extend*;
+$SufixLetterEx= $SufixLetter $Extend*;
+$KatakanaEx = $Katakana $Extend*;
+$IdeographicEx= $Ideographic $Extend*;
+$HangulEx = $Hangul $Extend*;
+$FormatEx = $Format $Extend*;
+
+
+#
+# Numbers. Rules 8, 11, 12 form the TR.
+#
+$NumberSequence = $NumericEx ($FormatEx* $MidNumEx? $FormatEx* $NumericEx)*;
+$NumberSequence {100};
+
+#
+# Words. Alpha-numerics. Rule 5, 6, 7, 9, 10
+# - must include at least one letter.
+# - may include both letters and numbers.
+# - may include MideLetter, MidNumber punctuation.
+#
+# At most one leading or trailing dash/hyphen should be accepted as well.
+# E.g. in German: "Arbeits-" or "-nehmer" where that hyphen needs to
+# be part of the word in order to have it properly spell checked etc.
+$LetterSequence = $PrePostDashHyphen? $ALetterEx ($FormatEx* $MidLetterEx? $FormatEx* $ALetterEx)* $PrePostDashHyphen?; # rules #6, #7
+($NumberSequence $FormatEx*)? $LetterSequence ($FormatEx* ($NumberSequence | $LetterSequence))* $SufixLetterEx? {200};
+
+[[:P:][:S:]]*;
+
+#
+# Do not break between Katakana. Rule #13.
+#
+$KatakanaEx ($FormatEx* $KatakanaEx)* {300};
+[:Hiragana:] $Extend* {300};
+
+#
+# Ideographic Characters. Stand by themselves as words.
+# Separated from the "Everything Else" rule, below, only so that they
+# can be tagged with a return value. TODO: is this what we want?
+#
+$IdeographicEx ($FormatEx* $IdeographicEx)* {400};
+$HangulEx ($FormatEx* $HangulEx)* {400};
+
+#
+# Everything Else, with no tag.
+# Non-Control chars combine with $Extend (combining) chars.
+# Controls are do not.
+#
+[^$Control [:Ideographic:]] $Extend*;
+$CR $LF;
+
+#
+# Reverse Rules. Back up over any of the chars that can group together.
+# (Reverse rules do not need to be exact; they can back up too far,
+# but must back up at least enough, and must stop on a boundary.)
+#
+
+# NonStarters are the set of all characters that can appear at the 2nd - nth position of
+# a word. (They may also be the first.) The reverse rule skips over these, until it
+# reaches something that can only be the start (and probably only) char in a "word".
+# A space or punctuation meets the test.
+#
+$NonStarters = [$Numeric $ALetter $Katakana $Ideographic $Hangul [:P:] [:S:] $MidLetter $MidNum $SufixLetter $Extend $Format];
+
+#!.*;
+! ($NonStarters* | \n \r) .;
+
diff --git a/i18npool/source/breakiterator/makefile.mk b/i18npool/source/breakiterator/makefile.mk
index 7ba9cd3..50e437e 100644
--- a/i18npool/source/breakiterator/makefile.mk
+++ b/i18npool/source/breakiterator/makefile.mk
@@ -93,7 +93,7 @@ $(MISC)$/%_brk.c : $(MISC)$/%.brk
# The output of gencmn generates warnings under Windows. We want to minimize the patches to external tools,
# so the output (OpenOffice_icu_dat.c) is changed here to include a pragma to disable the warnings.
# Output of gencmn is redirected to OpenOffice_icu_tmp.c with the -t switch.
-$(MISC)$/OpenOffice_%.c :
+$(MISC)$/OpenOffice_%.c : $(MY_BRK_BRKFILES:s/.brk/_brk.c/)
$(WRAPCMD) $(GENCMN) -n OpenOffice -t tmp -S -d $(MISC) O $(mktmp $(subst,$(MISC)$/, $(MY_BRK_BRKFILES:t"\n")))
echo $(USQ)#ifdef _MSC_VER$(USQ) > $@
echo $(USQ)#pragma warning( disable : 4229 4668 )$(USQ) >> $@
diff --git a/i18npool/source/breakiterator/xdictionary.cxx b/i18npool/source/breakiterator/xdictionary.cxx
index 43fad2b..cd35372 100644
--- a/i18npool/source/breakiterator/xdictionary.cxx
+++ b/i18npool/source/breakiterator/xdictionary.cxx
@@ -54,7 +54,21 @@ namespace com { namespace sun { namespace star { namespace i18n {
extern "C" { static void SAL_CALL thisModule() {} }
-xdictionary::xdictionary(const sal_Char *lang)
+xdictionary::xdictionary(const sal_Char *lang) :
+ existMark( NULL ),
+ index1( NULL ),
+ index2( NULL ),
+ lenArray( NULL ),
+ dataArea( NULL ),
+ hModule( NULL ),
+ boundary(),
+ japaneseWordBreak( sal_False )
+#if USE_CELL_BOUNDARY_CODE
+ // For CTL breakiterator, where the word boundary should not be inside cell.
+ ,
+ useCellBoundary( sal_False ),
+ cellBoundary( NULL )
+#endif
{
index1 = 0;
#ifdef SAL_DLLPREFIX
@@ -92,6 +106,7 @@ xdictionary::xdictionary(const sal_Char *lang)
#if USE_CELL_BOUNDARY_CODE
useCellBoundary = sal_False;
+ cellBoundary = NULL;
#endif
japaneseWordBreak = sal_False;
}
@@ -149,6 +164,19 @@ sal_Int32 xdictionary::getLongestMatch(const sal_Unicode* str, sal_Int32 sLen) {
return 0;
}
+
+/*
+ * c-tor
+ */
+
+WordBreakCache::WordBreakCache() :
+ length( 0 ),
+ contents( NULL ),
+ wordboundary( NULL ),
+ size( 0 )
+{
+}
+
/*
* Compare two unicode string,
*/
diff --git a/i18npool/source/localedata/data/de_DE.xml b/i18npool/source/localedata/data/de_DE.xml
index 295b826..a83b3db 100644
--- a/i18npool/source/localedata/data/de_DE.xml
+++ b/i18npool/source/localedata/data/de_DE.xml
@@ -328,7 +328,14 @@
</LC_CURRENCY>
<LC_TRANSLITERATION ref="en_US"/>
<LC_MISC>
- <ReservedWords>
+ <BreakIteratorRules>
+ <EditMode/>
+ <DictionaryMode>dict_word_prepostdash</DictionaryMode>
+ <WordCountMode/>
+ <CharacterMode/>
+ <LineMode/>
+ </BreakIteratorRules>
+ <ReservedWords>
<trueWord>wahr</trueWord>
<falseWord>falsch</falseWord>
<quarter1Word>1. Quartal</quarter1Word>
diff --git a/i18npool/source/localedata/data/nl_NL.xml b/i18npool/source/localedata/data/nl_NL.xml
index eedfdc1..5a91c9c 100644
--- a/i18npool/source/localedata/data/nl_NL.xml
+++ b/i18npool/source/localedata/data/nl_NL.xml
@@ -360,20 +360,27 @@
</LC_CURRENCY>
<LC_TRANSLITERATION ref="en_US"/>
<LC_MISC>
-<ReservedWords>
-<trueWord>waar</trueWord>
-<falseWord>onwaar</falseWord>
-<quarter1Word>1ste kwartaal</quarter1Word>
-<quarter2Word>2de kwartaal</quarter2Word>
-<quarter3Word>3de kwartaal</quarter3Word>
-<quarter4Word>4de kwartaal</quarter4Word>
-<aboveWord>boven</aboveWord>
-<belowWord>onder</belowWord>
-<quarter1Abbreviation>K1</quarter1Abbreviation>
-<quarter2Abbreviation>K2</quarter2Abbreviation>
-<quarter3Abbreviation>K3</quarter3Abbreviation>
-<quarter4Abbreviation>K4</quarter4Abbreviation>
-</ReservedWords>
+ <BreakIteratorRules>
+ <EditMode/>
+ <DictionaryMode>dict_word_prepostdash</DictionaryMode>
+ <WordCountMode/>
+ <CharacterMode/>
+ <LineMode/>
+ </BreakIteratorRules>
+ <ReservedWords>
+ <trueWord>waar</trueWord>
+ <falseWord>onwaar</falseWord>
+ <quarter1Word>1ste kwartaal</quarter1Word>
+ <quarter2Word>2de kwartaal</quarter2Word>
+ <quarter3Word>3de kwartaal</quarter3Word>
+ <quarter4Word>4de kwartaal</quarter4Word>
+ <aboveWord>boven</aboveWord>
+ <belowWord>onder</belowWord>
+ <quarter1Abbreviation>K1</quarter1Abbreviation>
+ <quarter2Abbreviation>K2</quarter2Abbreviation>
+ <quarter3Abbreviation>K3</quarter3Abbreviation>
+ <quarter4Abbreviation>K4</quarter4Abbreviation>
+ </ReservedWords>
</LC_MISC>
<LC_NumberingLevel ref="en_US"/>
<LC_OutLineNumberingLevel ref="en_US"/>
diff --git a/i18npool/source/localedata/data/pl_PL.xml b/i18npool/source/localedata/data/pl_PL.xml
index 4119060..1956896 100644
--- a/i18npool/source/localedata/data/pl_PL.xml
+++ b/i18npool/source/localedata/data/pl_PL.xml
@@ -326,13 +326,6 @@
</LC_CURRENCY>
<LC_TRANSLITERATION ref="en_US"/>
<LC_MISC>
- <BreakIteratorRules>
- <EditMode/>
- <DictionaryMode>dict_word_dash</DictionaryMode>
- <WordCountMode/>
- <CharacterMode/>
- <LineMode/>
- </BreakIteratorRules>
<ReservedWords>
<trueWord>prawda</trueWord>
<falseWord>fałsz</falseWord>
diff --git a/i18npool/source/localedata/data/sv_SE.xml b/i18npool/source/localedata/data/sv_SE.xml
index 333690a..211f95c 100644
--- a/i18npool/source/localedata/data/sv_SE.xml
+++ b/i18npool/source/localedata/data/sv_SE.xml
@@ -315,6 +315,13 @@
</LC_CURRENCY>
<LC_TRANSLITERATION ref="en_US"/>
<LC_MISC>
+ <BreakIteratorRules>
+ <EditMode/>
+ <DictionaryMode>dict_word_prepostdash</DictionaryMode>
+ <WordCountMode/>
+ <CharacterMode/>
+ <LineMode/>
+ </BreakIteratorRules>
<ReservedWords>
<trueWord>sant</trueWord>
<falseWord>falskt</falseWord>
commit 065bb6217363a28638e7c31036abcc1dec4f7b1c
Author: Release Engineers <releng at openoffice.org>
Date: Thu Aug 6 12:44:16 2009 +0000
CWS-TOOLING: integrate CWS os132
2009-07-21 15:24:18 +0200 os r274201 : #i103696# SwXTextPortion/SwXParagraph excluded
2009-07-15 13:19:17 +0200 os r274007 : #i103564# typo
2009-07-15 13:09:30 +0200 os r274005 : #i103564# SwFrames::hasElements
2009-07-15 13:02:16 +0200 os r274003 : #i103564# SwXBookmark::getPropertySetInfo fixed
2009-06-26 10:11:00 +0200 os r273395 : CWS-TOOLING: rebase CWS os132 to trunk at 272827 (milestone: DEV300:m50)
2009-06-23 08:52:24 +0200 os r273256 : #i102764# patch: attribute ListBoxes correctly handled in ::Reset()
2009-06-23 08:51:31 +0200 os r273255 : #i102764# ResetColor() added to remove background color
2009-06-22 14:57:38 +0200 os r273233 : #i102619# prevent access to already destroyed shell
2009-06-18 13:26:51 +0200 os r273112 : #i99508# ::insertTextContent: re-route to ::attach()
2009-06-18 10:59:53 +0200 os r273107 : #i85405# patch to enable 'Print grid' CheckBox correctly
2009-06-18 10:54:02 +0200 os r273106 : #i85133# dispose connection in GetColumnFmt to prevent connection locking
2009-06-18 10:24:31 +0200 os r273104 : #99535# ExportGraphic changed
2009-06-18 10:24:03 +0200 os r273103 : #99535# ExportGraphic changed
2009-06-18 10:23:11 +0200 os r273102 : #i102841# redlining mode switches to insert mode (cmc)
2009-06-17 14:05:42 +0200 os r273070 : #i102111# do not save already saved HTML documents before switching to source veiw
2009-06-17 13:18:20 +0200 os r273063 : #i101825# set rembered start position at the real start not at the initial start
2009-06-17 08:24:10 +0200 os r273048 : #99535# no dierect access to the file picker interface
2009-06-16 15:00:12 +0200 os r273020 : #i99937# notification of user options changes re-introduced
2009-06-15 14:36:03 +0200 os r272987 : #i98032# unreplaced text in protected areas must not be attributed either
2009-06-15 14:20:26 +0200 os r272985 : #i98032# replace list has to be initialised
2009-06-04 13:29:02 +0200 os r272624 : #i97810# set focus into column page
2009-06-04 11:01:14 +0200 os r272617 : #i98164# dialog resize to ease localisation
2009-06-04 10:59:44 +0200 os r272616 : #i98164# dialog resize to ease localisation
2009-05-28 16:05:03 +0200 os r272413 : #i98172# ConvertFieldsToText: take care of tabs with attributes
2009-05-28 11:12:45 +0200 os r272385 : #i59361# dialog controls resized
2009-05-28 11:03:14 +0200 os r272383 : #i59174# dialog controls moved
diff --git a/svtools/source/config/useroptions.cxx b/svtools/source/config/useroptions.cxx
index 9f2f87d..64273c9 100644
--- a/svtools/source/config/useroptions.cxx
+++ b/svtools/source/config/useroptions.cxx
@@ -49,51 +49,45 @@
#include <rtl/logfile.hxx>
#include "itemholder2.hxx"
-#ifndef _COM_SUN_STAR_BEANS_PROPERTY_HPP_
#include <com/sun/star/beans/Property.hpp>
-#endif
-
-#ifndef _COM_SUN_STAR_BEANS_XPROPERTYSET_HPP_
#include <com/sun/star/beans/XPropertySet.hpp>
-#endif
-
-#ifndef _COM_SUN_STAR_BEANS_PROPERTYATTRIBUTE_HPP_
#include <com/sun/star/beans/PropertyAttribute.hpp>
-#endif
-
-#ifndef _COM_SUN_STAR_CONTAINER_XNAMEACCESS_HPP_
#include <com/sun/star/container/XNameAccess.hpp>
-#endif
-
-#ifndef _COM_SUN_STAR_CONTAINER_XNAMECONTAINER_HPP_
#include <com/sun/star/container/XNameContainer.hpp>
-#endif
-
-#ifndef _COM_SUN_STAR_LANG_XSINGLESERVICEFACTORY_HPP_
#include <com/sun/star/lang/XSingleServiceFactory.hpp>
-#endif
-
-#ifndef _COMPHELPER_CONFIGURATIONHELPER_HXX_
+#include <com/sun/star/util/XChangesListener.hpp>
+#include <com/sun/star/util/XChangesNotifier.hpp>
+#include <com/sun/star/util/ChangesEvent.hpp>
#include <comphelper/configurationhelper.hxx>
-#endif
-
-#ifndef _UNOTOOLS_PROCESSFACTORY_HXX_
#include <unotools/processfactory.hxx>
-#endif
-
-#ifndef _SVT_LOGHELPER_HXX
-#include "loghelper.hxx"
-#endif
+#include <loghelper.hxx>
using namespace utl;
using namespace rtl;
+using namespace com::sun::star;
using namespace com::sun::star::uno;
namespace css = ::com::sun::star;
// class SvtUserOptions_Impl ---------------------------------------------
+class SvtUserOptions_Impl;
+class SvtUserConfigChangeListener_Impl : public cppu::WeakImplHelper1
+<
+ com::sun::star::util::XChangesListener
+>
+{
+ SvtUserOptions_Impl& m_rParent;
+ public:
+ SvtUserConfigChangeListener_Impl(SvtUserOptions_Impl& rParent);
+ ~SvtUserConfigChangeListener_Impl();
+
+ //XChangesListener
+ virtual void SAL_CALL changesOccurred( const util::ChangesEvent& Event ) throw(RuntimeException);
+ //XEventListener
+ virtual void SAL_CALL disposing( const lang::EventObject& Source ) throw(RuntimeException);
+};
-class SvtUserOptions_Impl
+class SvtUserOptions_Impl : public SfxBroadcaster
{
public:
SvtUserOptions_Impl();
@@ -144,8 +138,10 @@ public:
sal_Bool IsTokenReadonly( USHORT nToken ) const;
::rtl::OUString GetToken(USHORT nToken) const;
+ void Notify();
private:
+ uno::Reference< util::XChangesListener > m_xChangeListener;
css::uno::Reference< css::container::XNameAccess > m_xCfg;
css::uno::Reference< css::beans::XPropertySet > m_xData;
::rtl::OUString m_aLocale;
@@ -158,18 +154,47 @@ static sal_Int32 nRefCount = 0;
#define READONLY_DEFAULT sal_False
-// functions -------------------------------------------------------------
+/*-- 16.06.2009 14:22:56---------------------------------------------------
+
+ -----------------------------------------------------------------------*/
+SvtUserConfigChangeListener_Impl::SvtUserConfigChangeListener_Impl(SvtUserOptions_Impl& rParent) :
+ m_rParent( rParent )
+{
+}
+/*-- 16.06.2009 14:22:56---------------------------------------------------
-namespace
+ -----------------------------------------------------------------------*/
+SvtUserConfigChangeListener_Impl::~SvtUserConfigChangeListener_Impl()
{
- struct PropertyNames
- : public rtl::Static< Sequence< rtl::OUString >, PropertyNames> {};
+}
+/*-- 16.06.2009 14:22:56---------------------------------------------------
+
+ -----------------------------------------------------------------------*/
+void SvtUserConfigChangeListener_Impl::changesOccurred( const util::ChangesEvent& rEvent ) throw(RuntimeException)
+{
+ if(rEvent.Changes.getLength())
+ m_rParent.Notify();
+}
+/*-- 16.06.2009 14:22:56---------------------------------------------------
+
+ -----------------------------------------------------------------------*/
+void SvtUserConfigChangeListener_Impl::disposing( const lang::EventObject& rSource ) throw(RuntimeException)
+{
+ try
+ {
+ uno::Reference< util::XChangesNotifier > xChgNot( rSource.Source, UNO_QUERY_THROW);
+ xChgNot->removeChangesListener(this);
+ }
+ catch(Exception& )
+ {
+ }
}
// class SvtUserOptions_Impl ---------------------------------------------
// -----------------------------------------------------------------------
-SvtUserOptions_Impl::SvtUserOptions_Impl()
+SvtUserOptions_Impl::SvtUserOptions_Impl() :
+ m_xChangeListener( new SvtUserConfigChangeListener_Impl(*this) )
{
try
{
@@ -181,6 +206,14 @@ SvtUserOptions_Impl::SvtUserOptions_Impl()
css::uno::UNO_QUERY );
m_xData = css::uno::Reference< css::beans::XPropertySet >(m_xCfg, css::uno::UNO_QUERY);
+ uno::Reference< util::XChangesNotifier > xChgNot( m_xCfg, UNO_QUERY);
+ try
+ {
+ xChgNot->addChangesListener( m_xChangeListener );
+ }
+ catch(RuntimeException& )
+ {
+ }
}
catch(const css::uno::Exception& ex)
{
@@ -743,6 +776,12 @@ void SvtUserOptions_Impl::SetApartment( const ::rtl::OUString& sApartment )
// -----------------------------------------------------------------------
+void SvtUserOptions_Impl::Notify()
+{
+ Broadcast( SfxSimpleHint( SFX_HINT_USER_OPTIONS_CHANGED ) );
+}
+// -----------------------------------------------------------------------
+
sal_Bool SvtUserOptions_Impl::IsTokenReadonly( USHORT nToken ) const
{
css::uno::Reference< css::beans::XPropertySet > xData(m_xCfg, css::uno::UNO_QUERY);
@@ -906,7 +945,7 @@ SvtUserOptions::SvtUserOptions()
}
++nRefCount;
pImp = pOptions;
- //StartListening( *pImp);
+ StartListening( *pImp);
}
// -----------------------------------------------------------------------
More information about the ooo-build-commit
mailing list