#
-# Copyright (C) 2002-2006, International Business Machines Corporation
+# Copyright (C) 2002-2015, International Business Machines Corporation
# and others. All Rights Reserved.
#
-# file: word.txt
+# file: word_POSIX.txt
#
# ICU Word Break Rules, POSIX locale.
# See Unicode Standard Annex #29.
-# These rules are based on Unicode Version 5.0 0
-# Includes post Unicode 5.0 change to treat Japanese half width voicing marks
-# as Extend
+# These rules are based on UAX #29 Revision 22 for Unicode Version 6.3
#
# Note: Updates to word.txt will usually need to be merged into
-# word_POSIX.txt and word_ja.txt also.
+# word_POSIX.txt also.
##############################################################################
#
##############################################################################
!!chain;
+!!RINoChain;
#
# Character Class Definitions.
#
-$VoiceMarks = [\uff9e\uff9f];
-$Format = [\p{Word_Break = Format}];
-$Katakana = [\p{Word_Break = Katakana}-$VoiceMarks];
-$ALetter = [\p{Word_Break = ALetter}];
-$MidLetter = [\p{Word_Break = MidLetter} - [ \:]];
-$MidNum = [\p{Word_Break = MidNum}];
-$Numeric = [\p{Word_Break = Numeric}];
-$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
-
-
-$CR = \u000d;
-$LF = \u000a;
-$Extend = [\p{Grapheme_Cluster_Break = Extend}$VoiceMarks];
-$Control = [\p{Grapheme_Cluster_Break = Control}];
+$CR = [\p{Word_Break = CR}];
+$LF = [\p{Word_Break = LF}];
+$Newline = [\p{Word_Break = Newline}];
+$Extend = [\p{Word_Break = Extend}];
+$RI = [\p{Word_Break = Regional_Indicator}];
+$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}];
+
+$Han = [:Han:];
+$Hiragana = [:Hiragana:];
+
+# Special character classes for people & body part emoji:
+# Subsets of $Extend:
+$ZWJ = \u200D;
+$EmojiVar = \uFE0F;
+# The following are subsets of \p{Word_Break = Other}
+$EmojiForSeqs = [\u2764 \U0001F441 \U0001F466-\U0001F469 \U0001F48B \U0001F5E8];
+$EmojiForMods = [\u261D \u26F9 \u270A-\u270D \U0001F385 \U0001F3C3-\U0001F3C4 \U0001F3CA-\U0001F3CB \U0001F442-\U0001F443 \U0001F446-\U0001F450 \U0001F466-\U0001F469 \U0001F46E-\U0001F478 \U0001F47C \U0001F481-\U0001F483 \U0001F485-\U0001F487 \U0001F4AA \U0001F575 \U0001F590 \U0001F595 \U0001F596 \U0001F645-\U0001F647 \U0001F64B-\U0001F64F \U0001F6A3 \U0001F6B4-\U0001F6B6 \U0001F6C0 \U0001F918];
+$EmojiMods = [\U0001F3FB-\U0001F3FF];
# 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.
-$dictionary = [:LineBreak = Complex_Context:];
-$ALetterPlus = [$ALetter [$dictionary-$Extend-$Control]];
+$Control = [\p{Grapheme_Cluster_Break = Control}];
+$HangulSyllable = [\uac00-\ud7a3];
+$ComplexContext = [:LineBreak = Complex_Context:];
+$KanaKanji = [$Han $Hiragana $Katakana];
+$dictionaryCJK = [$KanaKanji $HangulSyllable];
+$dictionary = [$ComplexContext $dictionaryCJK];
+
+# leave CJK scripts out of ALetterPlus
+$ALetterPlus = [$ALetter-$dictionaryCJK [$ComplexContext-$Extend-$Control]];
#
-# Rules 3 Grapheme Clusters behave like their first char.
-# Rule 4 Ignore trailing Format characters (Also see note in TR 29)
+# Rules 4 Ignore Format and Extend characters,
+# except when they appear at the beginning of a region of text.
#
-$KatakanaEx = $Katakana ($Extend | $Format)*;
-$ALetterEx = $ALetterPlus ($Extend | $Format)*;
-$MidLetterEx = $MidLetter ($Extend | $Format)*;
-$MidNumEx = $MidNum ($Extend | $Format)*;
-$NumericEx = $Numeric ($Extend | $Format)*;
-$ExtendNumLetEx = $ExtendNumLet ($Extend | $Format)*;
-
-$Hiragana = [:Hiragana:];
-$Ideographic = [:IDEOGRAPHIC:];
+# TODO: check if handling of katakana in dictionary makes rules incorrect/void
+$KatakanaEx = $Katakana ($Extend | $Format)*;
+$Hebrew_LetterEx = $Hebrew_Letter ($Extend | $Format)*;
+$ALetterEx = $ALetterPlus ($Extend | $Format)*;
+$Single_QuoteEx = $Single_Quote ($Extend | $Format)*;
+$Double_QuoteEx = $Double_Quote ($Extend | $Format)*;
+$MidNumLetEx = $MidNumLet ($Extend | $Format)*;
+$MidLetterEx = $MidLetter ($Extend | $Format)*;
+$MidNumEx = $MidNum ($Extend | $Format)*;
+$NumericEx = $Numeric ($Extend | $Format)*;
+$ExtendNumLetEx = $ExtendNumLet ($Extend | $Format)*;
+
+$Ideographic = [\p{Ideographic}];
$HiraganaEx = $Hiragana ($Extend | $Format)*;
$IdeographicEx = $Ideographic ($Extend | $Format)*;
# Rule 3 - CR x LF
-# see character breaks.
-
-$CR $LF ($Extend | $Format)*;
+#
+$CR $LF;
# Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
# of a region of Text. The rule here comes into play when the start of text
# begins with a group of Format chars, or with a "word" consisting of a single
# char that is not in any of the listed word break categories followed by
-# format char(s).
-.? ($Extend | $Format)+;
-
+# format char(s), or is not a CJK dictionary character.
+[^$CR $LF $Newline]? ($Extend | $Format)+;
$NumericEx {100};
$ALetterEx {200};
-$KatakanaEx {300};
-$HiraganaEx {300};
-$IdeographicEx {400};
+$HangulSyllable {200};
+$Hebrew_LetterEx{200};
+$KatakanaEx {400}; # note: these status values override those from rule 5
+$HiraganaEx {400}; # by virtue of being numerically larger.
+$IdeographicEx {400}; #
+#
# rule 5
-
-$ALetterEx $ALetterEx {200};
+# Do not break between most letters.
+#
+($ALetterEx | $Hebrew_LetterEx) ($ALetterEx | $Hebrew_LetterEx) {200};
# rule 6 and 7
-$ALetterEx $MidLetterEx $ALetterEx {200};
+($ALetterEx | $Hebrew_LetterEx) ($MidLetterEx | $MidNumLetEx | $Single_QuoteEx) ($ALetterEx | $Hebrew_LetterEx) {200};
+
+# rule 7a
+$Hebrew_LetterEx $Single_QuoteEx {200};
+
+# rule 7b and 7c
+$Hebrew_LetterEx $Double_QuoteEx $Hebrew_LetterEx {200};
# rule 8
# rule 9
-$ALetterEx $Format* $NumericEx {200};
+($ALetterEx | $Hebrew_LetterEx) $NumericEx {200};
# rule 10
-$NumericEx $ALetterEx {200};
+$NumericEx ($ALetterEx | $Hebrew_LetterEx) {200};
# rule 11 and 12
-$NumericEx $MidNumEx $NumericEx {100};
+$NumericEx ($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx {100};
# rule 13
-
-$KatakanaEx $KatakanaEx {300};
+# to be consistent with $KanaKanji $KanaKanhi, changed
+# from 300 to 400.
+# See also TestRuleStatus in intltest/rbbiapts.cpp
+$KatakanaEx $KatakanaEx {400};
# rule 13a/b
-$ALetterEx $ExtendNumLetEx {200}; # (13a)
-$NumericEx $ExtendNumLetEx {100}; # (13a)
-$KatakanaEx $ExtendNumLetEx {300}; # (13a)
-$ExtendNumLetEx $ExtendNumLetEx{200}; # (13a)
+$ALetterEx $ExtendNumLetEx {200}; # (13a)
+$Hebrew_LetterEx $ExtendNumLetEx {200}; # (13a)
+$NumericEx $ExtendNumLetEx {100}; # (13a)
+$KatakanaEx $ExtendNumLetEx {400}; # (13a)
+$ExtendNumLetEx $ExtendNumLetEx {200}; # (13a)
-$ExtendNumLetEx $ALetterEx {200}; # (13b)
-$ExtendNumLetEx $NumericEx {100}; # (13b)
-$ExtendNumLetEx $KatakanaEx {300}; # (13b)
-
+$ExtendNumLetEx $ALetterEx {200}; # (13b)
+$ExtendNumLetEx $Hebrew_Letter {200}; # (13b)
+$ExtendNumLetEx $NumericEx {100}; # (13b)
+$ExtendNumLetEx $KatakanaEx {400}; # (13b)
+
+# rule 13c
+
+$RI $RI $Extend* / $RI;
+$RI $RI $Extend*;
+
+# Special forward rules for people & body part emoji:
+# don't break $ZWJ from subsequent $EmojiForSeqs; don't break between relevant emoji and $EmojiMods
+$ZWJ $EmojiForSeqs;
+$EmojiForMods $EmojiVar? $EmojiMods;
+
+# special handling for CJK characters: chain for later dictionary segmentation
+$HangulSyllable $HangulSyllable {200};
+$KanaKanji $KanaKanji {400}; # different rule status if both kana and kanji found
## -------------------------------------------------
!!reverse;
-$BackALetterEx = ($Format | $Extend)* $ALetterPlus;
-$BackNumericEx = ($Format | $Extend)* $Numeric;
-$BackMidNumEx = ($Format | $Extend)* $MidNum;
-$BackMidLetterEx = ($Format | $Extend)* $MidLetter;
-$BackKatakanaEx = ($Format | $Extend)* $Katakana;
-$BackExtendNumLetEx= ($Format | $Extend)* $ExtendNumLet;
+$BackHebrew_LetterEx = ($Format | $Extend)* $Hebrew_Letter;
+$BackALetterEx = ($Format | $Extend)* $ALetterPlus;
+$BackSingle_QuoteEx = ($Format | $Extend)* $Single_Quote;
+$BackDouble_QuoteEx = ($Format | $Extend)* $Double_Quote;
+$BackMidNumLetEx = ($Format | $Extend)* $MidNumLet;
+$BackNumericEx = ($Format | $Extend)* $Numeric;
+$BackMidNumEx = ($Format | $Extend)* $MidNum;
+$BackMidLetterEx = ($Format | $Extend)* $MidLetter;
+$BackKatakanaEx = ($Format | $Extend)* $Katakana;
+$BackHiraganaEx = ($Format | $Extend)* $Hiragana;
+$BackExtendNumLetEx = ($Format | $Extend)* $ExtendNumLet;
# rule 3
-($Format | $Extend)* $LF $CR;
+$LF $CR;
# rule 4
-($Format | $Extend)* .?;
+($Format | $Extend)* [^$CR $LF $Newline]?;
# rule 5
-$BackALetterEx $BackALetterEx;
+($BackALetterEx | $BackHebrew_LetterEx) ($BackALetterEx | $BackHebrew_LetterEx);
# rule 6 and 7
-$BackALetterEx $BackMidLetterEx $BackALetterEx;
+($BackALetterEx | $BackHebrew_LetterEx) ($BackMidLetterEx | $BackMidNumLetEx | $BackSingle_QuoteEx) ($BackALetterEx | $BackHebrew_LetterEx);
+
+# rule 7a
+$BackSingle_QuoteEx $BackHebrew_LetterEx;
+# Rule 7b and 7c
+$BackHebrew_LetterEx $BackDouble_QuoteEx $BackHebrew_LetterEx;
# rule 8
# rule 9
-$BackNumericEx $BackALetterEx;
+$BackNumericEx ($BackALetterEx | $BackHebrew_LetterEx);
# rule 10
-$BackALetterEx $BackNumericEx;
+($BackALetterEx | $BackHebrew_LetterEx) $BackNumericEx;
# rule 11 and 12
-$BackNumericEx $BackMidNumEx $BackNumericEx;
+$BackNumericEx ($BackMidNumEx | $BackMidNumLetEx | $BackSingle_QuoteEx) $BackNumericEx;
# rule 13
# rules 13 a/b
#
-($BackALetterEx | $BackNumericEx | $BackKatakanaEx | $BackExtendNumLetEx) $BackExtendNumLetEx;
-$BackExtendNumLetEx ($BackALetterEx | $BackNumericEx | $BackKatakanaEx);
+$BackExtendNumLetEx ($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx | $BackExtendNumLetEx);
+($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx) $BackExtendNumLetEx;
+
+# rule 13c
+
+$Extend* $RI $RI / $Extend* $RI $RI;
+$Extend* $RI $RI;
+
+# Special reverse rules for people & body part emoji:
+# don't break $ZWJ from subsequent $EmojiForSeqs; don't break between relevant emoji and $EmojiMods
+$EmojiForSeqs $ZWJ;
+$EmojiMods $EmojiVar? $EmojiForMods;
+
+# special handling for CJK characters: chain for later dictionary segmentation
+$HangulSyllable $HangulSyllable;
+$KanaKanji $KanaKanji; #different rule status if both kanji and kana found
## -------------------------------------------------
($Extend | $Format)+ .?;
# rule 6
-$MidLetter $BackALetterEx;
+($MidLetter | $MidNumLet | $Single_Quote) ($BackALetterEx | $BackHebrew_LetterEx);
+
+# rule 7b
+$Double_Quote $BackHebrew_LetterEx;
+
# rule 11
-$MidNum $BackNumericEx;
+($MidNum | $MidNumLet | $Single_Quote) $BackNumericEx;
+$RI $RI+;
# For dictionary-based break
$dictionary $dictionary;
($Extend | $Format)+ .?;
# rule 6
-$MidLetterEx $ALetterEx;
+($MidLetterEx | $MidNumLetEx | $Single_QuoteEx) ($ALetterEx | $Hebrew_LetterEx);
+
+# rule 7b
+$Double_QuoteEx $Hebrew_LetterEx;
# rule 11
-$MidNumEx $NumericEx;
+($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx;
+$RI $RI+;
# For dictionary-based break
$dictionary $dictionary;
projects / apple / icu.git / blobdiff