| # |
| # 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.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_POSIX.txt also. |
| |
| ############################################################################## |
| # |
| # Character class definitions from TR 29 |
| # |
| ############################################################################## |
| |
| !!chain; |
| !!quoted_literals_only; |
| |
| |
| # |
| # Character Class Definitions. |
| # |
| |
| $CR = [\p{Word_Break = CR}]; |
| $LF = [\p{Word_Break = LF}]; |
| $Newline = [\p{Word_Break = Newline} ]; |
| $Extend = [\p{Word_Break = Extend}]; |
| $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}]; |
| # Remove two full stop characters from $MidNumLet and add them to $MidNum |
| # to break a hostname into its components at the cost of breaking |
| # 'e.g.' and 'i.e.' as well. |
| # $MidNumLet is used in rules 6/7 (rules of our interest) and rules 11/12. |
| # Because it's OR'd with $MidNum in rules 11/12, rules 11/12 are not affected |
| # while rules 6/7 are reverted to the old behavior we want. |
| $MidNumLet = [[\p{Word_Break = MidNumLet}] - [\u002E \uFF0E]]; |
| $MidLetter = [\p{Word_Break = MidLetter}]; |
| $MidNum = [\p{Word_Break = MidNum}[\u002E \uFF0E]]; |
| $Numeric = [[\p{Word_Break = Numeric}] [\uFF10-\uff19]]; # Patch for ICU-12079 |
| $ExtendNumLet = [\p{Word_Break = ExtendNumLet}]; |
| $WSegSpace = [\p{Word_Break = WSegSpace}]; |
| $Extended_Pict = [:ExtPict:]; |
| |
| $Han = [:Han:]; |
| $Hiragana = [:Hiragana:]; |
| |
| |
| # 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]; |
| |
| # leave CJK scripts out of ALetterPlus |
| $ALetterPlus = [$ALetter-$dictionaryCJK [$ComplexContext-$Extend-$Control]]; |
| |
| |
| # |
| # Rules 4 Ignore Format and Extend characters, |
| # except when they appear at the beginning of a region of text. |
| # |
| # TODO: check if handling of katakana in dictionary makes rules incorrect/void |
| $KatakanaEx = $Katakana ($Extend | $Format | $ZWJ)*; |
| $Hebrew_LetterEx = $Hebrew_Letter ($Extend | $Format | $ZWJ)*; |
| $ALetterEx = $ALetterPlus ($Extend | $Format | $ZWJ)*; |
| $Single_QuoteEx = $Single_Quote ($Extend | $Format | $ZWJ)*; |
| $Double_QuoteEx = $Double_Quote ($Extend | $Format | $ZWJ)*; |
| $MidNumLetEx = $MidNumLet ($Extend | $Format | $ZWJ)*; |
| $MidLetterEx = $MidLetter ($Extend | $Format | $ZWJ)*; |
| $MidNumEx = $MidNum ($Extend | $Format | $ZWJ)*; |
| $NumericEx = $Numeric ($Extend | $Format | $ZWJ)*; |
| $ExtendNumLetEx = $ExtendNumLet ($Extend | $Format | $ZWJ)*; |
| $Regional_IndicatorEx = $Regional_Indicator ($Extend | $Format | $ZWJ)*; |
| |
| $Ideographic = [\p{Ideographic}]; |
| $HiraganaEx = $Hiragana ($Extend | $Format | $ZWJ)*; |
| $IdeographicEx = $Ideographic ($Extend | $Format | $ZWJ)*; |
| |
| ## ------------------------------------------------- |
| |
| # Rule 3 - CR x LF |
| # |
| $CR $LF; |
| |
| # Rule 3c ZWJ x (Extended_Pict | EmojiNRK). Precedes WB4, so no intervening Extend chars allowed. |
| # |
| $ZWJ $Extended_Pict; |
| |
| # Rule 3d - Keep horizontal whitespace together. |
| # |
| $WSegSpace $WSegSpace; |
| |
| # Rule 4 - ignore Format and Extend characters, except when they appear at the beginning |
| # of a region of Text. The rule here comes into play when the start of text |
| # begins with a group of Format chars, or with a "word" consisting of a single |
| # char that is not in any of the listed word break categories followed by |
| # format char(s), or is not a CJK dictionary character. |
| [^$CR $LF $Newline]? ($Extend | $Format | $ZWJ)+; |
| |
| $NumericEx {100}; |
| $ALetterEx {200}; |
| $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}; # |
| |
| $Extended_Pict ($Extend | $Format | $ZWJ)*; |
| |
| # |
| # rule 5 |
| # Do not break between most letters. |
| # |
| ($ALetterEx | $Hebrew_LetterEx) ($ALetterEx | $Hebrew_LetterEx) {200}; |
| |
| # rule 6 and 7 |
| ($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 |
| |
| $NumericEx $NumericEx {100}; |
| |
| # rule 9 |
| |
| ($ALetterEx | $Hebrew_LetterEx) $NumericEx {200}; |
| |
| # rule 10 |
| |
| $NumericEx ($ALetterEx | $Hebrew_LetterEx) {200}; |
| |
| # rule 11 and 12 |
| |
| $NumericEx ($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx {100}; |
| |
| # rule 13 |
| # 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) |
| $Hebrew_LetterEx $ExtendNumLetEx {200}; # (13a) |
| $NumericEx $ExtendNumLetEx {100}; # (13a) |
| $KatakanaEx $ExtendNumLetEx {400}; # (13a) |
| $ExtendNumLetEx $ExtendNumLetEx {200}; # (13a) |
| |
| $ExtendNumLetEx $ALetterEx {200}; # (13b) |
| $ExtendNumLetEx $Hebrew_Letter {200}; # (13b) |
| $ExtendNumLetEx $NumericEx {100}; # (13b) |
| $ExtendNumLetEx $KatakanaEx {400}; # (13b) |
| |
| # rules 15 - 17 |
| # Pairs of Regional Indicators stay together. |
| # With rule chaining disabled by ^, this rule will match exactly two of them. |
| # No other rule begins with a Regional_Indicator, so chaining cannot extend the match. |
| # |
| ^$Regional_IndicatorEx $Regional_IndicatorEx; |
| |
| # 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. |
| .; |