Home | History | Annotate | Download | only in rules
      1 #
      2 # Copyright (C) 2016 and later: Unicode, Inc. and others.
      3 # License & terms of use: http://www.unicode.org/copyright.html
      4 # Copyright (C) 2002-2016, International Business Machines Corporation 
      5 # and others. All Rights Reserved.
      6 #
      7 # file:  word_POSIX.txt
      8 #
      9 # ICU Word Break Rules, POSIX locale.
     10 #      See Unicode Standard Annex #29.
     11 #      These rules are based on UAX #29 Revision 29 for Unicode Version 9.0
     12 #      with additions for Emoji Sequences from https://goo.gl/cluFCn
     13 #
     14 # Note:  Updates to word.txt will usually need to be merged into
     15 #        word_POSIX.txt also.
     16 
     17 ##############################################################################
     18 #
     19 #  Character class definitions from TR 29
     20 #
     21 ##############################################################################
     22 
     23 !!chain;
     24 
     25 
     26 #
     27 #  Character Class Definitions.
     28 #
     29 
     30 $CR                 = [\p{Word_Break = CR}];
     31 $LF                 = [\p{Word_Break = LF}];
     32 $Newline            = [\p{Word_Break = Newline} ];
     33 $Extend             = [\p{Word_Break = Extend}];
     34 $ZWJ                = [\p{Word_Break = ZWJ}];
     35 $Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
     36 $Format             = [\p{Word_Break = Format}];
     37 $Katakana           = [\p{Word_Break = Katakana}];
     38 $Hebrew_Letter      = [\p{Word_Break = Hebrew_Letter}];
     39 $ALetter            = [\p{Word_Break = ALetter}];
     40 $Single_Quote       = [\p{Word_Break = Single_Quote}];
     41 $Double_Quote       = [\p{Word_Break = Double_Quote}];
     42 $MidNumLet          = [\p{Word_Break = MidNumLet} - [.]];
     43 $MidLetter          = [\p{Word_Break = MidLetter} - [\:]];
     44 $MidNum             = [\p{Word_Break = MidNum} [.]];
     45 $Numeric            = [\p{Word_Break = Numeric}];
     46 $ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
     47 $E_Base             = [\p{Word_Break = EB}\U0001F3C2\U0001F3C7\U0001F3CC\U0001F46A-\U0001F46D\U0001F46F\U0001F574\U0001F6CC];
     48 $E_Modifier         = [\p{Word_Break = EM}];
     49 
     50 # Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r12773
     51 $Extended_Pict      = [\U0001F774-\U0001F77F\u2700-\u2701\u2703-\u2704\u270E\u2710-\u2711\u2765-\u2767\U0001F030-\U0001F093\U0001F094-\U0001F09F\U0001F10D-\U0001F10F\U0001F12F\U0001F16C-\U0001F16F\U0001F1AD-\U0001F1E5\U0001F203-\U0001F20F\U0001F23C-\U0001F23F\U0001F249-\U0001F24F\U0001F252-\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\u2605\u2607-\u260D\u260F-\u2610\u2612\u2616-\u2617\u2619-\u261C\u261E-\u261F\u2621\u2624-\u2625\u2627-\u2629\u262B-\u262D\u2630-\u2637\u263B-\u2647\u2654-\u265F\u2661-\u2662\u2664\u2667\u2669-\u267A\u267C-\u267E\u2680-\u2691\u2695\u2698\u269A\u269D-\u269F\u26A2-\u26A9\u26AC-\u26AF\u26B2-\u26BC\u26BF-\u26C3\u26C6-\u26C7\u26C9-\u26CD\u26D0\u26D2\u26D5-\u26E8\u26EB-\u26EF\u26F6\u26FB-\u26FC\u26FE-\u26FF\u2388\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-\U0001F90F\U0001F91F\U0001F928-\U0001F92F\U0001F931-\U0001F932\U0001F93F\U0001F94C-\U0001F94F\U0001F95F-\U0001F97F\U0001F992-\U0001F9BF\U0001F9C1-\U0001F9FF\U0001F6C6-\U0001F6CA\U0001F6E6-\U0001F6E8\U0001F6EA\U0001F6F1-\U0001F6F2\U0001F6D3-\U0001F6DF\U0001F6ED-\U0001F6EF\U0001F6F7-\U0001F6FF];
     52 $EBG                = [\p{Word_Break = EBG}];
     53 $EmojiNRK           = [[\p{Emoji}] - [\p{Word_Break = Regional_Indicator}\u002a\u00230-9]];
     54 
     55 $Han                = [:Han:];
     56 $Hiragana           = [:Hiragana:];
     57 
     58 
     59 #   Dictionary character set, for triggering language-based break engines. Currently
     60 #   limited to LineBreak=Complex_Context. Note that this set only works in Unicode
     61 #   5.0 or later as the definition of Complex_Context was corrected to include all
     62 #   characters requiring dictionary break.
     63 
     64 $Control        = [\p{Grapheme_Cluster_Break = Control}]; 
     65 $HangulSyllable = [\uac00-\ud7a3];
     66 $ComplexContext = [:LineBreak = Complex_Context:];
     67 $KanaKanji      = [$Han $Hiragana $Katakana];
     68 $dictionaryCJK  = [$KanaKanji $HangulSyllable];
     69 $dictionary     = [$ComplexContext $dictionaryCJK];
     70 
     71 # leave CJK scripts out of ALetterPlus
     72 $ALetterPlus  = [$ALetter-$dictionaryCJK [$ComplexContext-$Extend-$Control]];
     73 
     74 
     75 #
     76 #  Rules 4    Ignore Format and Extend characters, 
     77 #             except when they appear at the beginning of a region of text.
     78 #
     79 # TODO: check if handling of katakana in dictionary makes rules incorrect/void
     80 $KatakanaEx           = $Katakana           ($Extend |  $Format | $ZWJ)*;
     81 $Hebrew_LetterEx      = $Hebrew_Letter      ($Extend |  $Format | $ZWJ)*;
     82 $ALetterEx            = $ALetterPlus        ($Extend |  $Format | $ZWJ)*;
     83 $Single_QuoteEx       = $Single_Quote       ($Extend |  $Format | $ZWJ)*;
     84 $Double_QuoteEx       = $Double_Quote       ($Extend |  $Format | $ZWJ)*;
     85 $MidNumLetEx          = $MidNumLet          ($Extend |  $Format | $ZWJ)*;
     86 $MidLetterEx          = $MidLetter          ($Extend |  $Format | $ZWJ)*;
     87 $MidNumEx             = $MidNum             ($Extend |  $Format | $ZWJ)*;
     88 $NumericEx            = $Numeric            ($Extend |  $Format | $ZWJ)*;
     89 $ExtendNumLetEx       = $ExtendNumLet       ($Extend |  $Format | $ZWJ)*;
     90 $Regional_IndicatorEx = $Regional_Indicator ($Extend |  $Format | $ZWJ)*;
     91 
     92 $Ideographic    = [\p{Ideographic}];
     93 $HiraganaEx     = $Hiragana     ($Extend |  $Format | $ZWJ)*;
     94 $IdeographicEx  = $Ideographic  ($Extend |  $Format | $ZWJ)*;
     95 
     96 ## -------------------------------------------------
     97 
     98 !!forward;
     99 
    100 
    101 # Rule 3 - CR x LF
    102 #
    103 $CR $LF;
    104 
    105 # Rule 3c   ZWJ x (Extended_Pict | EmojiNRK).  Precedes WB4, so no intervening Extend chars allowed.
    106 #
    107 $ZWJ ($Extended_Pict | $EmojiNRK);
    108 
    109 
    110 # Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
    111 #          of a region of Text.   The rule here comes into play when the start of text
    112 #          begins with a group of Format chars, or with a "word" consisting of a single
    113 #          char that is not in any of the listed word break categories followed by
    114 #          format char(s), or is not a CJK dictionary character.
    115 [^$CR $LF $Newline]? ($Extend |  $Format | $ZWJ)+;
    116 
    117 $NumericEx {100};
    118 $ALetterEx {200};
    119 $HangulSyllable {200};
    120 $Hebrew_LetterEx{200};
    121 $KatakanaEx {400};       # note:  these status values override those from rule 5
    122 $HiraganaEx {400};       #        by virtue of being numerically larger.
    123 $IdeographicEx {400};    #
    124 
    125 $E_Base ($Extend | $Format | $ZWJ)*;
    126 $E_Modifier ($Extend | $Format | $ZWJ)*;
    127 $Extended_Pict ($Extend | $Format | $ZWJ)*;
    128 
    129 #
    130 # rule 5
    131 #    Do not break between most letters.
    132 #
    133 ($ALetterEx | $Hebrew_LetterEx)  ($ALetterEx | $Hebrew_LetterEx) {200};
    134 
    135 # rule 6 and 7
    136 ($ALetterEx | $Hebrew_LetterEx) ($MidLetterEx | $MidNumLetEx | $Single_QuoteEx) ($ALetterEx | $Hebrew_LetterEx) {200};
    137 
    138 # rule 7a
    139 $Hebrew_LetterEx $Single_QuoteEx {200};
    140 
    141 # rule 7b and 7c
    142 $Hebrew_LetterEx $Double_QuoteEx $Hebrew_LetterEx {200};
    143 
    144 # rule 8
    145 
    146 $NumericEx $NumericEx {100};
    147 
    148 # rule 9
    149 
    150 ($ALetterEx | $Hebrew_LetterEx) $NumericEx {200};
    151 
    152 # rule 10
    153 
    154 $NumericEx ($ALetterEx | $Hebrew_LetterEx) {200};
    155 
    156 # rule 11 and 12 
    157 
    158 $NumericEx ($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx {100};
    159 
    160 # rule 13
    161 # to be consistent with $KanaKanji $KanaKanhi, changed
    162 # from 300 to 400.
    163 # See also TestRuleStatus in intltest/rbbiapts.cpp
    164 $KatakanaEx  $KatakanaEx {400};
    165 
    166 # rule 13a/b
    167 
    168 $ALetterEx       $ExtendNumLetEx {200};    #  (13a)
    169 $Hebrew_LetterEx $ExtendNumLetEx {200};    #  (13a)
    170 $NumericEx       $ExtendNumLetEx {100};    #  (13a)
    171 $KatakanaEx      $ExtendNumLetEx {400};    #  (13a)
    172 $ExtendNumLetEx  $ExtendNumLetEx {200};    #  (13a)
    173 
    174 $ExtendNumLetEx  $ALetterEx      {200};    #  (13b)
    175 $ExtendNumLetEx  $Hebrew_Letter  {200};    #  (13b)
    176 $ExtendNumLetEx  $NumericEx      {100};    #  (13b)
    177 $ExtendNumLetEx  $KatakanaEx     {400};    #  (13b)
    178 
    179 # rule 14
    180 #    Do not break within emoji modifier sequences
    181 
    182 ($E_Base | $EBG) ($Format | $Extend | $ZWJ)* $E_Modifier;
    183 
    184 # rules 15 - 17
    185 #    Pairs of Regional Indicators stay together.
    186 #    With rule chaining disabled by ^, this rule will match exactly two of them.
    187 #    No other rule begins with a Regional_Indicator, so chaining cannot extend the match.
    188 #
    189 ^$Regional_IndicatorEx $Regional_IndicatorEx;
    190 
    191 # special handling for CJK characters: chain for later dictionary segmentation
    192 $HangulSyllable $HangulSyllable {200};
    193 $KanaKanji $KanaKanji {400}; # different rule status if both kana and kanji found 
    194 
    195 
    196 ## -------------------------------------------------
    197 
    198 !!reverse;
    199 
    200 $BackHebrew_LetterEx      = ($Format | $Extend | $ZWJ)* $Hebrew_Letter;
    201 $BackALetterEx            = ($Format | $Extend | $ZWJ)* $ALetterPlus;
    202 $BackSingle_QuoteEx       = ($Format | $Extend | $ZWJ)* $Single_Quote;
    203 $BackDouble_QuoteEx       = ($Format | $Extend | $ZWJ)* $Double_Quote;
    204 $BackMidNumLetEx          = ($Format | $Extend | $ZWJ)* $MidNumLet;
    205 $BackNumericEx            = ($Format | $Extend | $ZWJ)* $Numeric;
    206 $BackMidNumEx             = ($Format | $Extend | $ZWJ)* $MidNum;
    207 $BackMidLetterEx          = ($Format | $Extend | $ZWJ)* $MidLetter;
    208 $BackKatakanaEx           = ($Format | $Extend | $ZWJ)* $Katakana;
    209 $BackHiraganaEx           = ($Format | $Extend | $ZWJ)* $Hiragana;
    210 $BackExtendNumLetEx       = ($Format | $Extend | $ZWJ)* $ExtendNumLet;
    211 $BackRegional_IndicatorEx = ($Format | $Extend | $ZWJ)* $Regional_Indicator;
    212 
    213 # rule 3
    214 $LF $CR;
    215 
    216 # Rule 3c   ZWJ x (Extended_Pict | EmojiNRK).  Precedes WB4, so no intervening Extend chars allowed.
    217 #
    218 ($Extended_Pict | $EmojiNRK) $ZWJ;
    219 
    220 # rule 4
    221 ($Format | $Extend | $ZWJ)*  [^$CR $LF $Newline]?;
    222 
    223 # rule 5
    224 
    225 ($BackALetterEx | $BackHebrew_LetterEx) ($BackALetterEx | $BackHebrew_LetterEx);
    226 
    227 # rule 6 and 7
    228 
    229 ($BackALetterEx | $BackHebrew_LetterEx) ($BackMidLetterEx | $BackMidNumLetEx | $BackSingle_QuoteEx) ($BackALetterEx | $BackHebrew_LetterEx);
    230 
    231 # rule 7a
    232 $BackSingle_QuoteEx $BackHebrew_LetterEx;
    233 
    234 # Rule 7b and 7c
    235 $BackHebrew_LetterEx $BackDouble_QuoteEx $BackHebrew_LetterEx;
    236 
    237 # rule 8
    238 
    239 $BackNumericEx $BackNumericEx;
    240 
    241 # rule 9
    242 
    243 $BackNumericEx ($BackALetterEx | $BackHebrew_LetterEx);
    244 
    245 # rule 10
    246 
    247 ($BackALetterEx | $BackHebrew_LetterEx) $BackNumericEx;
    248 
    249 # rule 11 and 12
    250 
    251 $BackNumericEx ($BackMidNumEx | $BackMidNumLetEx | $BackSingle_QuoteEx) $BackNumericEx;
    252 
    253 # rule 13
    254 
    255 $BackKatakanaEx $BackKatakanaEx;
    256 
    257 # rules 13 a/b
    258 #
    259 $BackExtendNumLetEx ($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx | $BackExtendNumLetEx);
    260 ($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx) $BackExtendNumLetEx; 
    261 
    262 # special handling for CJK characters: chain for later dictionary segmentation
    263 $HangulSyllable $HangulSyllable;
    264 $KanaKanji $KanaKanji; #different rule status if both kanji and kana found
    265 
    266 # rule 14
    267 
    268 $E_Modifier ($Format | $Extend | $ZWJ)* ($E_Base | $EBG);
    269 
    270 # rule 15 - 17
    271 #    Pairs of Regional Indicators stay together.
    272 
    273 ^$BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)* 
    274         ($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
    275 ^$BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)* 
    276         ($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
    277 
    278 ($Extended_Pict | $EmojiNRK) $ZWJ $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)* 
    279         ($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
    280 ($Extended_Pict | $EmojiNRK) $ZWJ $BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)* 
    281         ($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
    282 
    283 
    284 
    285 ## -------------------------------------------------
    286 
    287 !!safe_reverse;
    288 
    289 # rule 3
    290 ($Extend | $Format | $ZWJ)+ .?;
    291 
    292 # rule 6
    293 ($MidLetter | $MidNumLet | $Single_Quote) ($BackALetterEx | $BackHebrew_LetterEx);
    294 
    295 # rule 7b
    296 $Double_Quote $BackHebrew_LetterEx;
    297 
    298 
    299 # rule 11
    300 ($MidNum | $MidNumLet | $Single_Quote) $BackNumericEx;
    301 
    302 # rule 13c
    303 $BackRegional_IndicatorEx*;
    304 
    305 # For dictionary-based break
    306 $dictionary $dictionary;
    307 
    308 ## -------------------------------------------------
    309 
    310 !!safe_forward;
    311 
    312 # rule 4
    313 ($Extend | $Format | $ZWJ)+ .?;
    314 
    315 # rule 6
    316 ($MidLetterEx | $MidNumLetEx | $Single_QuoteEx) ($ALetterEx | $Hebrew_LetterEx);
    317 
    318 # rule 7b
    319 $Double_QuoteEx $Hebrew_LetterEx;
    320 
    321 # rule 11
    322 ($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx;
    323 
    324 # rule 13c
    325 $Regional_IndicatorEx*;
    326 
    327 # For dictionary-based break
    328 $dictionary $dictionary;
    329