| # |
| # 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 29 for Unicode Version 9.0 |
| # with additions for Emoji Sequences from https://goo.gl/cluFCn |
| # Plus additional characters introduces with Emoji 5, http://www.unicode.org/reports/tr51/proposed.html |
| # |
| # 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]]; #includes fullwidth digits |
| $ExtendNumLet = [\p{Word_Break = ExtendNumLet}]; |
| $E_Base = [\p{Word_Break = EB}]; |
| $E_Modifier = [\p{Word_Break = EM}]; |
| |
| # Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r13267 |
| $Extended_Pict = [\U0001F774-\U0001F77F\U00002700-\U00002701\U00002703-\U00002704\U0000270E\U00002710-\U00002711\U00002765-\U00002767\U0001F030-\U0001F093\U0001F094-\U0001F09F\U0001F10D-\U0001F10F\U0001F12F\U0001F16C-\U0001F16F\U0001F1AD-\U0001F1E5\U0001F260-\U0001F265\U0001F203-\U0001F20F\U0001F23C-\U0001F23F\U0001F249-\U0001F24F\U0001F252-\U0001F25F\U0001F266-\U0001F2FF\U0001F7D5-\U0001F7FF\U0001F000-\U0001F003\U0001F005-\U0001F02B\U0001F02C-\U0001F02F\U0001F322-\U0001F323\U0001F394-\U0001F395\U0001F398\U0001F39C-\U0001F39D\U0001F3F1-\U0001F3F2\U0001F3F6\U0001F4FE\U0001F53E-\U0001F548\U0001F54F\U0001F568-\U0001F56E\U0001F571-\U0001F572\U0001F57B-\U0001F586\U0001F588-\U0001F589\U0001F58E-\U0001F58F\U0001F591-\U0001F594\U0001F597-\U0001F5A3\U0001F5A6-\U0001F5A7\U0001F5A9-\U0001F5B0\U0001F5B3-\U0001F5BB\U0001F5BD-\U0001F5C1\U0001F5C5-\U0001F5D0\U0001F5D4-\U0001F5DB\U0001F5DF-\U0001F5E0\U0001F5E2\U0001F5E4-\U0001F5E7\U0001F5E9-\U0001F5EE\U0001F5F0-\U0001F5F2\U0001F5F4-\U0001F5F9\U00002605\U00002607-\U0000260D\U0000260F-\U00002610\U00002612\U00002616-\U00002617\U00002619-\U0000261C\U0000261E-\U0000261F\U00002621\U00002624-\U00002625\U00002627-\U00002629\U0000262B-\U0000262D\U00002630-\U00002637\U0000263B-\U00002647\U00002654-\U0000265F\U00002661-\U00002662\U00002664\U00002667\U00002669-\U0000267A\U0000267C-\U0000267E\U00002680-\U00002691\U00002695\U00002698\U0000269A\U0000269D-\U0000269F\U000026A2-\U000026A9\U000026AC-\U000026AF\U000026B2-\U000026BC\U000026BF-\U000026C3\U000026C6-\U000026C7\U000026C9-\U000026CD\U000026D0\U000026D2\U000026D5-\U000026E8\U000026EB-\U000026EF\U000026F6\U000026FB-\U000026FC\U000026FE-\U000026FF\U00002388\U0001FA00-\U0001FFFD\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F0AF-\U0001F0B0\U0001F0C0\U0001F0D0\U0001F0F6-\U0001F0FF\U0001F80C-\U0001F80F\U0001F848-\U0001F84F\U0001F85A-\U0001F85F\U0001F888-\U0001F88F\U0001F8AE-\U0001F8FF\U0001F900-\U0001F90B\U0001F91F\U0001F928-\U0001F92F\U0001F931-\U0001F932\U0001F94C\U0001F95F-\U0001F96B\U0001F992-\U0001F997\U0001F9D0-\U0001F9E6\U0001F90C-\U0001F90F\U0001F93F\U0001F94D-\U0001F94F\U0001F96C-\U0001F97F\U0001F998-\U0001F9BF\U0001F9C1-\U0001F9CF\U0001F9E7-\U0001F9FF\U0001F6C6-\U0001F6CA\U0001F6D3-\U0001F6D4\U0001F6E6-\U0001F6E8\U0001F6EA\U0001F6F1-\U0001F6F2\U0001F6F7-\U0001F6F8\U0001F6D5-\U0001F6DF\U0001F6ED-\U0001F6EF\U0001F6F9-\U0001F6FF]; |
| $EBG = [\p{Word_Break = EBG}]; |
| $EmojiNRK = [[\p{Emoji}] - [\p{Word_Break = Regional_Indicator}\u002a\u00230-9©®™〰〽]]; |
| |
| $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)*; |
| |
| ## ------------------------------------------------- |
| |
| !!forward; |
| |
| |
| # 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 | $EmojiNRK); |
| |
| |
| # Rule 4 - ignore Format and Extend characters, except when they appear at the beginning |
| # of a region of Text. The rule here comes into play when the start of text |
| # begins with a group of Format chars, or with a "word" consisting of a single |
| # char that is not in any of the listed word break categories followed by |
| # format char(s), or is not a CJK dictionary character. |
| [^$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}; # |
| |
| $E_Base ($Extend | $Format | $ZWJ)*; |
| $E_Modifier ($Extend | $Format | $ZWJ)*; |
| $Extended_Pict ($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 $KatakanaEx {400}; # (13b) |
| |
| # rule 14 |
| # Do not break within emoji modifier sequences |
| |
| ($E_Base | $EBG) ($Format | $Extend | $ZWJ)* $E_Modifier; |
| |
| # rules 15 - 17 |
| # Pairs of Regional Indicators stay together. |
| # With rule chaining disabled by ^, this rule will match exactly two of them. |
| # No other rule begins with a Regional_Indicator, so chaining cannot extend the match. |
| # |
| ^$Regional_IndicatorEx $Regional_IndicatorEx; |
| |
| # special handling for CJK characters: chain for later dictionary segmentation |
| $HangulSyllable $HangulSyllable {200}; |
| $KanaKanji $KanaKanji {400}; # different rule status if both kana and kanji found |
| |
| # Rule 999 |
| # Match a single code point if no other rule applies. |
| .; |
| |
| |
| ## ------------------------------------------------- |
| |
| !!safe_reverse; |
| |
| # rule 3 |
| ($Extend | $Format | $ZWJ)+ .?; |
| |
| # rule 6 |
| ($MidLetter | $MidNumLet | $Single_Quote) ($Format | $Extend | $ZWJ)* ($Hebrew_Letter | $ALetterPlus); |
| |
| # rule 7b |
| $Double_Quote ($Format | $Extend | $ZWJ)* $Hebrew_Letter; |
| |
| |
| # rule 11 |
| ($MidNum | $MidNumLet | $Single_Quote) ($Format | $Extend | $ZWJ)* $Numeric; |
| |
| # rule 13c |
| $Regional_Indicator ($Format | $Extend | $ZWJ)* $Regional_Indicator; |
| |
| # For dictionary-based break |
| $dictionary $dictionary; |
| |
| # Skip over potentially very long words or numbers. |
| # Not necessary to reach a safe point, but avoids potential performance problems. |
| ($ALetter | $Numeric) ($ALetter | $Numeric); |