--- /dev/null
+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
+// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
+fi{
+ boundaries{
+ word:process(dependency){"word_fi_sv.brk"}
+ }
+}
# These rules are based on UAX #29 Revision 34 for Unicode Version 12.0
#
# Note: Updates to word.txt will usually need to be merged into
-# word_POSIX.txt also.
+# word_POSIX.txt and word_fi_sv.txt also.
##############################################################################
#
$Format = [\p{Word_Break = Format}];
$Katakana = [\p{Word_Break = Katakana}];
$Hebrew_Letter = [\p{Word_Break = Hebrew_Letter}];
-$ALetter = [\p{Word_Break = ALetter}];
+$ALetter = [\p{Word_Break = ALetter} @];
$Single_Quote = [\p{Word_Break = Single_Quote}];
$Double_Quote = [\p{Word_Break = Double_Quote}];
$MidNumLet = [\p{Word_Break = MidNumLet}];
-$MidLetter = [\p{Word_Break = MidLetter}];
+$MidLetter = [\p{Word_Break = MidLetter} - [\: \uFE55 \uFF1A]];
$MidNum = [\p{Word_Break = MidNum}];
$Numeric = [\p{Word_Break = Numeric}];
$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
$Format = [\p{Word_Break = Format}];
$Katakana = [\p{Word_Break = Katakana}];
$Hebrew_Letter = [\p{Word_Break = Hebrew_Letter}];
-$ALetter = [\p{Word_Break = ALetter}];
+$ALetter = [\p{Word_Break = ALetter} @];
$Single_Quote = [\p{Word_Break = Single_Quote}];
$Double_Quote = [\p{Word_Break = Double_Quote}];
$MidNumLet = [\p{Word_Break = MidNumLet} - [.]];
-$MidLetter = [\p{Word_Break = MidLetter} - [\:]];
+$MidLetter = [\p{Word_Break = MidLetter} - [\: \uFE55 \uFF1A]];
$MidNum = [\p{Word_Break = MidNum} [.]];
$Numeric = [\p{Word_Break = Numeric}];
$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
--- /dev/null
+#
+# Copyright (C) 2016 and later: Unicode, Inc. and others.
+# License & terms of use: http://www.unicode.org/copyright.html
+# Copyright (C) 2002-2016, International Business Machines Corporation
+# and others. All Rights Reserved.
+#
+# file: word_fi_sv.txt
+#
+# ICU Word Break Rules
+# See Unicode Standard Annex #29.
+# These rules are based on UAX #29 Revision 34 for Unicode Version 12.0
+#
+# Note: Updates to word.txt will usually need to be merged into
+# word_fi_sv.txt also.
+
+##############################################################################
+#
+# Character class definitions from TR 29
+#
+##############################################################################
+
+!!chain;
+!!quoted_literals_only;
+
+
+#
+# Character Class Definitions.
+#
+
+$Han = [:Han:];
+
+$CR = [\p{Word_Break = CR}];
+$LF = [\p{Word_Break = LF}];
+$Newline = [\p{Word_Break = Newline}];
+$Extend = [\p{Word_Break = Extend}-$Han];
+$ZWJ = [\p{Word_Break = ZWJ}];
+$Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
+$Format = [\p{Word_Break = Format}];
+$Katakana = [\p{Word_Break = Katakana}];
+$Hebrew_Letter = [\p{Word_Break = Hebrew_Letter}];
+$ALetter = [\p{Word_Break = ALetter} @];
+$Single_Quote = [\p{Word_Break = Single_Quote}];
+$Double_Quote = [\p{Word_Break = Double_Quote}];
+$MidNumLet = [\p{Word_Break = MidNumLet}];
+$MidLetter = [\p{Word_Break = MidLetter}];
+$MidNum = [\p{Word_Break = MidNum}];
+$Numeric = [\p{Word_Break = Numeric}];
+$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
+$WSegSpace = [\p{Word_Break = WSegSpace}];
+$Extended_Pict = [\p{Extended_Pictographic}];
+
+$Hiragana = [:Hiragana:];
+$Ideographic = [\p{Ideographic}];
+
+
+# Dictionary character set, for triggering language-based break engines. Currently
+# limited to LineBreak=Complex_Context. Note that this set only works in Unicode
+# 5.0 or later as the definition of Complex_Context was corrected to include all
+# characters requiring dictionary break.
+
+$Control = [\p{Grapheme_Cluster_Break = Control}];
+$HangulSyllable = [\uac00-\ud7a3];
+$ComplexContext = [:LineBreak = Complex_Context:];
+$KanaKanji = [$Han $Hiragana $Katakana];
+$dictionaryCJK = [$KanaKanji $HangulSyllable];
+$dictionary = [$ComplexContext $dictionaryCJK];
+
+# TODO: check if handling of katakana in dictionary makes rules incorrect/void
+
+# leave CJK scripts out of ALetterPlus
+$ALetterPlus = [$ALetter-$dictionaryCJK [$ComplexContext-$Extend-$Control]];
+
+
+## -------------------------------------------------
+
+# Rule 3 - CR x LF
+#
+$CR $LF;
+
+# Rule 3c Do not break within emoji zwj sequences.
+# ZWJ × \p{Extended_Pictographic}. Precedes WB4, so no intervening Extend chars allowed.
+#
+$ZWJ $Extended_Pict;
+
+# Rule 3d - Keep horizontal whitespace together.
+#
+$WSegSpace $WSegSpace;
+
+# Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
+# of a region of Text.
+
+$ExFm = [$Extend $Format $ZWJ];
+
+^$ExFm+; # This rule fires only when there are format or extend characters at the
+ # start of text, or immediately following another boundary. It groups them, in
+ # the event there are more than one.
+
+[^$CR $LF $Newline $ExFm] $ExFm*; # This rule rule attaches trailing format/extends to words,
+ # with no special rule status value.
+
+$Numeric $ExFm* {100}; # This group of rules also attach trailing format/extends, but
+$ALetterPlus $ExFm* {200}; # with rule status set based on the word's final base character.
+$HangulSyllable {200};
+$Hebrew_Letter $ExFm* {200};
+$Katakana $ExFm* {400}; # note: these status values override those from rule 5
+$Hiragana $ExFm* {400}; # by virtue of being numerically larger.
+$Ideographic $ExFm* {400}; #
+
+#
+# rule 5
+# Do not break between most letters.
+#
+($ALetterPlus | $Hebrew_Letter) $ExFm* ($ALetterPlus | $Hebrew_Letter);
+
+# rule 6 and 7
+($ALetterPlus | $Hebrew_Letter) $ExFm* ($MidLetter | $MidNumLet | $Single_Quote) $ExFm* ($ALetterPlus | $Hebrew_Letter) {200};
+
+# rule 7a
+$Hebrew_Letter $ExFm* $Single_Quote {200};
+
+# rule 7b and 7c
+$Hebrew_Letter $ExFm* $Double_Quote $ExFm* $Hebrew_Letter;
+
+# rule 8
+
+$Numeric $ExFm* $Numeric;
+
+# rule 9
+
+($ALetterPlus | $Hebrew_Letter) $ExFm* $Numeric;
+
+# rule 10
+
+$Numeric $ExFm* ($ALetterPlus | $Hebrew_Letter);
+
+# rule 11 and 12
+
+$Numeric $ExFm* ($MidNum | $MidNumLet | $Single_Quote) $ExFm* $Numeric;
+
+# rule 13
+# to be consistent with $KanaKanji $KanaKanhi, changed
+# from 300 to 400.
+# See also TestRuleStatus in intltest/rbbiapts.cpp
+$Katakana $ExFm* $Katakana {400};
+
+# rule 13a/b
+
+$ALetterPlus $ExFm* $ExtendNumLet {200}; # (13a)
+$Hebrew_Letter $ExFm* $ExtendNumLet {200}; # (13a)
+$Numeric $ExFm* $ExtendNumLet {100}; # (13a)
+$Katakana $ExFm* $ExtendNumLet {400}; # (13a)
+$ExtendNumLet $ExFm* $ExtendNumLet {200}; # (13a)
+
+$ExtendNumLet $ExFm* $ALetterPlus {200}; # (13b)
+$ExtendNumLet $ExFm* $Hebrew_Letter {200}; # (13b)
+$ExtendNumLet $ExFm* $Numeric {100}; # (13b)
+$ExtendNumLet $ExFm* $Katakana {400}; # (13b)
+
+# rules 15 - 17
+# Pairs of Regional Indicators stay together.
+# With incoming rule chaining disabled by ^, this rule will match exactly two of them.
+# No other rule begins with a Regional_Indicator, so chaining cannot extend the match.
+#
+^$Regional_Indicator $ExFm* $Regional_Indicator;
+
+# special handling for CJK characters: chain for later dictionary segmentation
+$HangulSyllable $HangulSyllable {200};
+$KanaKanji $KanaKanji {400}; # different rule status if both kana and kanji found
+
+# Rule 999
+# Match a single code point if no other rule applies.
+.;
--- /dev/null
+// © 2016 and later: Unicode, Inc. and others.
+// License & terms of use: http://www.unicode.org/copyright.html
+// Generated using tools/cldr/cldr-to-icu/build-icu-data.xml
+sv{
+ boundaries{
+ word:process(dependency){"word_fi_sv.brk"}
+ }
+}
--- /dev/null
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Copyright (C) 2016 and later: Unicode, Inc. and others.
+ License & terms of use: http://www.unicode.org/copyright.html
+ Copyright (c) 2010-2015 International Business Machines Corporation and others. All rights reserved.
+-->
+<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
+[
+ <!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
+ %icu;
+]
+>
+<ldml>
+ <identity>
+ <version number="$Revision$"/>
+ <language type="fi"/>
+ </identity>
+ <special xmlns:icu="http://www.icu-project.org/">
+ <icu:breakIteratorData>
+ <icu:boundaries>
+ <icu:word icu:dependency="word_fi_sv.brk"/>
+ </icu:boundaries>
+ </icu:breakIteratorData>
+ </special>
+</ldml>
+
--- /dev/null
+<?xml version="1.0" encoding="UTF-8" ?>
+<!--
+ Copyright (C) 2016 and later: Unicode, Inc. and others.
+ License & terms of use: http://www.unicode.org/copyright.html
+ Copyright (c) 2010-2015 International Business Machines Corporation and others. All rights reserved.
+-->
+<!DOCTYPE ldml SYSTEM "../../dtd/cldr/common/dtd/ldml.dtd"
+[
+ <!ENTITY % icu SYSTEM "../../dtd/cldr/common/dtd/ldmlICU.dtd">
+ %icu;
+]
+>
+<ldml>
+ <identity>
+ <version number="$Revision$"/>
+ <language type="sv"/>
+ </identity>
+ <special xmlns:icu="http://www.icu-project.org/">
+ <icu:breakIteratorData>
+ <icu:boundaries>
+ <icu:word icu:dependency="word_fi_sv.brk"/>
+ </icu:boundaries>
+ </icu:breakIteratorData>
+ </special>
+</ldml>
+
{"21097", "LineBreakTest.txt", u"\uBD10\uC694\u002E\u0020\u0041\u002E\u0033\u0020\uBABB"},
{"21097", "LineBreakTest.txt", u"\uC694\u002E\u0020\u0041\u002E\u0034\u0020\uBABB"},
{"21097", "LineBreakTest.txt", u"a.2\u3000\u300C"},
+
+ // ICU-22127 until UAX #29 wordbreak is update for the colon changes in ICU-22112,
+ // need to skip some tests in WordBreakTest.txt
+ {"22127", "WordBreakTest.txt", u"a:"},
+ {"22127", "WordBreakTest.txt", u"A:"},
};
for (int n=0; n<UPRV_LENGTHOF(badTestCases); n++) {
const TestCase &badCase = badTestCases[n];
if (!strcmp(fileName, badCase.fFileName) &&
- testCase == UnicodeString(badCase.fString)) {
+ testCase.startsWith(UnicodeString(badCase.fString))) {
return logKnownIssue(badCase.fTicketNum);
}
}
fKatakanaSet = new UnicodeSet(u"[\\p{Word_Break = Katakana}]", status);
fRegionalIndicatorSet = new UnicodeSet(u"[\\p{Word_Break = Regional_Indicator}]", status);
fHebrew_LetterSet = new UnicodeSet(u"[\\p{Word_Break = Hebrew_Letter}]", status);
- fALetterSet = new UnicodeSet(u"[\\p{Word_Break = ALetter}]", status);
+ fALetterSet = new UnicodeSet(u"[\\p{Word_Break = ALetter} @]", status);
fSingle_QuoteSet = new UnicodeSet(u"[\\p{Word_Break = Single_Quote}]", status);
fDouble_QuoteSet = new UnicodeSet(u"[\\p{Word_Break = Double_Quote}]", status);
fMidNumLetSet = new UnicodeSet(u"[\\p{Word_Break = MidNumLet}]", status);
- fMidLetterSet = new UnicodeSet(u"[\\p{Word_Break = MidLetter}]", status);
+ fMidLetterSet = new UnicodeSet(u"[\\p{Word_Break = MidLetter} - [\\: \\uFE55 \\uFF1A]]", status);
fMidNumSet = new UnicodeSet(u"[\\p{Word_Break = MidNum}]", status);
fNumericSet = new UnicodeSet(u"[\\p{Word_Break = Numeric}]", status);
fFormatSet = new UnicodeSet(u"[\\p{Word_Break = Format}]", status);
Format = [\p{Word_Break = Format}];
Katakana = [\p{Word_Break = Katakana}];
Hebrew_Letter = [\p{Word_Break = Hebrew_Letter}];
-ALetter = [\p{Word_Break = ALetter}];
+ALetter = [\p{Word_Break = ALetter} @];
Single_Quote = [\p{Word_Break = Single_Quote}];
Double_Quote = [\p{Word_Break = Double_Quote}];
MidNumLet = [\p{Word_Break = MidNumLet}];
-MidLetter = [\p{Word_Break = MidLetter}];
+MidLetter = [\p{Word_Break = MidLetter} - [\: \uFE55 \uFF1A]];
MidNum = [\p{Word_Break = MidNum}];
Numeric = [\p{Word_Break = Numeric}];
ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
Single_Quote = [\p{Word_Break = Single_Quote}];
Double_Quote = [\p{Word_Break = Double_Quote}];
MidNumLet = [\p{Word_Break = MidNumLet} - [.]];
-MidLetter = [\p{Word_Break = MidLetter} - [\:]];
+MidLetter = [\p{Word_Break = MidLetter} - [\: \uFE55 \uFF1A]];
MidNum = [\p{Word_Break = MidNum} [.]];
Numeric = [\p{Word_Break = Numeric}];
ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
<locale en_US>
<word>
-<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx:yy<200> •or<200> •struct.field<200> \
+<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx<200>:•yy<200> •or<200> •struct.field<200> \
•for<200> •CS<200>-•types<200>.•</data>
<data>•\uFF92\uFF76\uFF9E<400> •</data>
+<data>•xx@yy<200>.•</data>
<locale en_US_POSIX>
<word>
•for<200> •CS<200>-•types<200>.•</data>
<data>•\u06c9<200>\uc799\ufffa•</data>
<data>•\uFF92\uFF76\uFF9E<400> •</data>
+<data>•xx@yy<200>.•</data>
+
+<locale fi>
+<word>
+<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx:yy<200> •or<200> •struct.field<200> \
+•for<200> •CS<200>-•types<200>.•</data>
+<data>•\uFF92\uFF76\uFF9E<400> •</data>
+<data>•xx@yy<200>.•</data>
+
+<locale sv>
+<word>
+<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx:yy<200> •or<200> •struct.field<200> \
+•for<200> •CS<200>-•types<200>.•</data>
+<data>•\uFF92\uFF76\uFF9E<400> •</data>
+<data>•xx@yy<200>.•</data>
# UBreakIteratorType UBRK_CHARACTER, Locale "th"
version https://git-lfs.github.com/spec/v1
-oid sha256:cf5ab1c8ba2dfa4638a00292e159e22710407f3827327310824d7295371eabbd
-size 14166397
+oid sha256:fe0a6ec1cedc0254064bf0b8ab9ea97ced6b7ecb036c968c9b7b1f5e15543493
+size 14171830
version https://git-lfs.github.com/spec/v1
-oid sha256:c8a507295001abd5ecaa5ac9e3cb377f21f4fe78610f05ce4bbac8d4b7475d37
-size 93664
+oid sha256:6ec86a03cb8a27a270dc589a433af299c4303b171519c40bf515751d8f726cef
+size 93663
version https://git-lfs.github.com/spec/v1
-oid sha256:1ec26b963167ffeabcc86f873ecbee723b7aad80bc0c4593dddb5cef89978213
-size 828453
+oid sha256:d95cc6820315fa875b7ecc5b15e2b1bffa0419d2562efd4b252dc0de4ff165b9
+size 828452
fRegionalIndicatorSet = new UnicodeSet("[\\p{Word_Break = Regional_Indicator}]");
fKatakanaSet = new UnicodeSet("[\\p{Word_Break = Katakana}]");
fHebrew_LetterSet = new UnicodeSet("[\\p{Word_Break = Hebrew_Letter}]");
- fALetterSet = new UnicodeSet("[\\p{Word_Break = ALetter}]");
+ fALetterSet = new UnicodeSet("[\\p{Word_Break = ALetter} @]");
fSingle_QuoteSet = new UnicodeSet("[\\p{Word_Break = Single_Quote}]");
fDouble_QuoteSet = new UnicodeSet("[\\p{Word_Break = Double_Quote}]");
fMidNumLetSet = new UnicodeSet("[\\p{Word_Break = MidNumLet}]");
- fMidLetterSet = new UnicodeSet("[\\p{Word_Break = MidLetter}]");
+ fMidLetterSet = new UnicodeSet("[\\p{Word_Break = MidLetter} - [\\: \\uFE55 \\uFF1A]]");
fMidNumSet = new UnicodeSet("[\\p{Word_Break = MidNum}]");
fNumericSet = new UnicodeSet("[\\p{Word_Break = Numeric}]");
fFormatSet = new UnicodeSet("[\\p{Word_Break = Format}]");
Format = [\p{Word_Break = Format}];
Katakana = [\p{Word_Break = Katakana}];
Hebrew_Letter = [\p{Word_Break = Hebrew_Letter}];
-ALetter = [\p{Word_Break = ALetter}];
+ALetter = [\p{Word_Break = ALetter} @];
Single_Quote = [\p{Word_Break = Single_Quote}];
Double_Quote = [\p{Word_Break = Double_Quote}];
MidNumLet = [\p{Word_Break = MidNumLet}];
-MidLetter = [\p{Word_Break = MidLetter}];
+MidLetter = [\p{Word_Break = MidLetter} - [\: \uFE55 \uFF1A]];
MidNum = [\p{Word_Break = MidNum}];
Numeric = [\p{Word_Break = Numeric}];
ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
Single_Quote = [\p{Word_Break = Single_Quote}];
Double_Quote = [\p{Word_Break = Double_Quote}];
MidNumLet = [\p{Word_Break = MidNumLet} - [.]];
-MidLetter = [\p{Word_Break = MidLetter} - [\:]];
+MidLetter = [\p{Word_Break = MidLetter} - [\: \uFE55 \uFF1A]];
MidNum = [\p{Word_Break = MidNum} [.]];
Numeric = [\p{Word_Break = Numeric}];
ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
<locale en_US>
<word>
-<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx:yy<200> •or<200> •struct.field<200> \
+<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx<200>:•yy<200> •or<200> •struct.field<200> \
•for<200> •CS<200>-•types<200>.•</data>
<data>•\uFF92\uFF76\uFF9E<400> •</data>
+<data>•xx@yy<200>.•</data>
<locale en_US_POSIX>
<word>
•for<200> •CS<200>-•types<200>.•</data>
<data>•\u06c9<200>\uc799\ufffa•</data>
<data>•\uFF92\uFF76\uFF9E<400> •</data>
+<data>•xx@yy<200>.•</data>
+
+<locale fi>
+<word>
+<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx:yy<200> •or<200> •struct.field<200> \
+•for<200> •CS<200>-•types<200>.•</data>
+<data>•\uFF92\uFF76\uFF9E<400> •</data>
+<data>•xx@yy<200>.•</data>
+
+<locale sv>
+<word>
+<data>•Can't<200> •have<200> •breaks<200> •in<200> •xx:yy<200> •or<200> •struct.field<200> \
+•for<200> •CS<200>-•types<200>.•</data>
+<data>•\uFF92\uFF76\uFF9E<400> •</data>
+<data>•xx@yy<200>.•</data>
# UBreakIteratorType UBRK_CHARACTER, Locale "th"
projects / icu / commitdiff