icuSources/test/testdata/wordNLLTu9.txt

   1 ## wordNLLTu9.txt
   2 ## The following corresponds to a draft(?) source file from CoreLP of 2017
   3 ##############################################################################
   4 #
   5 # Copyright (C) 2016 and later: Unicode, Inc. and others.
   6 # License & terms of use: http://www.unicode.org/copyright.html
   7 # Copyright (C) 2002-2016, International Business Machines Corporation
   8 # and others. All Rights Reserved.
   9 #
  10 # file:  word_urbTokTest.txt
  11 #
  12 # ICU Word Break Rules
  13 #      See Unicode Standard Annex #29.
  14 #      These rules are based on UAX #29 Revision 29 for Unicode Version 9.0
  15 #      with additions for Emoji Sequences from https://goo.gl/cluFCn
  16 #      Also modified with additions for testing urbtok_ functions.
  17 #
  18
  19 ##############################################################################
  20 #
  21 #  Character class definitions from TR 29
  22 #
  23 ##############################################################################
  24
  25 !!chain;
  26
  27 # Smart Tokenizer customization
  28
  29 $Space                          = [\u0020];
  30 $Fullstop               = [\u002E\uFE52\uFF0E];
  31 $Dash                   = [\u002D\uFE63\uFF0D];
  32
  33 $Terminators            = [\u0021\u00A1\u00A1\u01C3\u01C3\u01C3\u203C\u2048\uFE15\uFF01\u003F];
  34 $Parenthesis            = [\u0028\u005B\u007B\u0029\u005D\u007D];
  35 $Punctuation            = [\u007E\u003D\u002A\u003C\u003E];
  36 $OtherSingle            = [\u0060\u0300\u030F];
  37
  38 $Hash                   = [\u0023 \uFE5F \uFF03];
  39 $At                     = [\u0040 \uFE6B \uFF20];
  40 $Dollar                 = [\u0024];
  41
  42 $Semicolon              = [\u003B];
  43 $Colon                  = [\u003A];
  44
  45 #
  46 #  Character Class Definitions.
  47 #
  48
  49 $CR                 = [\p{Word_Break = CR}];
  50 $LF                 = [\p{Word_Break = LF}];
  51 $Newline            = [\p{Word_Break = Newline}];
  52 $Extend             = [\p{Word_Break = Extend}];
  53 $ZWJ                = [\p{Word_Break = ZWJ}];
  54 $Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
  55 $Format             = [\p{Word_Break = Format}];
  56 $Katakana           = [\p{Word_Break = Katakana}];
  57 $Hebrew_Letter      = [\p{Word_Break = Hebrew_Letter}];
  58 $ALetter            = [\p{Word_Break = ALetter}];
  59 $Single_Quote       = [\p{Word_Break = Single_Quote}\u2018\u2019];
  60 $Double_Quote       = [\p{Word_Break = Double_Quote}];
  61 $MidNumLet          = [\p{Word_Break = MidNumLet}-[$Fullstop $Single_Quote]];
  62 $MidLetter          = [\p{Word_Break = MidLetter}-[$Single_Quote]];
  63 $MidNum             = [\p{Word_Break = MidNum}];
  64 $Numeric            = [\p{Word_Break = Numeric}];
  65 $ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
  66 $E_Base             = [\p{Word_Break = EB}\U0001F3C2\U0001F3C7\U0001F3CC\U0001F46A-\U0001F46D\U0001F46F\U0001F574\U0001F6CC];
  67 $E_Modifier         = [\p{Word_Break = EM}];
  68
  69 # Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r12773
  70 $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];
  71 $EBG                = [\p{Word_Break = EBG}];
  72 $EmojiNRK           = [[\p{Emoji}] - [\p{Word_Break = Regional_Indicator}\u002a\u00230-9©®™〰〽]];
  73
  74 $Han                = [:Han:];
  75 $Hiragana           = [:Hiragana:];
  76
  77
  78 #   Dictionary character set, for triggering language-based break engines. Currently
  79 #   limited to LineBreak=Complex_Context. Note that this set only works in Unicode
  80 #   5.0 or later as the definition of Complex_Context was corrected to include all
  81 #   characters requiring dictionary break.
  82
  83 $Control        = [\p{Grapheme_Cluster_Break = Control}];
  84 $HangulSyllable = [\uac00-\ud7a3];
  85 $ComplexContext = [:LineBreak = Complex_Context:];
  86 $KanaKanji      = [$Han $Hiragana $Katakana];
  87 $dictionaryCJK  = [$KanaKanji $HangulSyllable];
  88 $dictionary     = [$ComplexContext $dictionaryCJK];
  89
  90 # leave CJK scripts out of ALetterPlus
  91 $ALetterPlus  = [$ALetter-$dictionaryCJK [$ComplexContext-$Extend-$Control]];
  92
  93
  94 #
  95 #  Rules 4    Ignore Format and Extend characters,
  96 #             except when they appear at the beginning of a region of text.
  97 #
  98 # TODO: check if handling of katakana in dictionary makes rules incorrect/void
  99 $KatakanaEx           = $Katakana           ($Extend |  $Format | $ZWJ)*;
 100 $Hebrew_LetterEx      = $Hebrew_Letter      ($Extend |  $Format | $ZWJ)*;
 101 $ALetterEx            = $ALetterPlus        ($Extend |  $Format | $ZWJ)*;
 102 $Single_QuoteEx       = $Single_Quote       ($Extend |  $Format | $ZWJ)*;
 103 $Double_QuoteEx       = $Double_Quote       ($Extend |  $Format | $ZWJ)*;
 104 $MidNumLetEx          = $MidNumLet          ($Extend |  $Format | $ZWJ)*;
 105 $MidLetterEx          = $MidLetter          ($Extend |  $Format | $ZWJ)*;
 106 $MidNumEx             = $MidNum             ($Extend |  $Format | $ZWJ)*;
 107 $NumericEx            = $Numeric            ($Extend |  $Format | $ZWJ)*;
 108 $ExtendNumLetEx       = $ExtendNumLet       ($Extend |  $Format | $ZWJ)*;
 109 $Regional_IndicatorEx = $Regional_Indicator ($Extend |  $Format | $ZWJ)*;
 110
 111 $Ideographic    = [\p{Ideographic}];
 112 $HiraganaEx     = $Hiragana     ($Extend |  $Format | $ZWJ)*;
 113 $IdeographicEx  = $Ideographic  ($Extend |  $Format | $ZWJ)*;
 114
 115 $Letter = [A-Za-z];
 116
 117 ## -------------------------------------------------
 118
 119 !!forward;
 120
 121 # Rule 3 - CR x LF
 122 #
 123 $CR $LF;
 124
 125 # Rule 3c   ZWJ x (Extended_Pict | EmojiNRK).  Precedes WB4, so no intervening Extend chars allowed.
 126 #
 127 $ZWJ ($Extended_Pict | $EmojiNRK);
 128
 129
 130 # Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
 131 #          of a region of Text.   The rule here comes into play when the start of text
 132 #          begins with a group of Format chars, or with a "word" consisting of a single
 133 #          char that is not in any of the listed word break categories followed by
 134 #          format char(s), or is not a CJK dictionary character.
 135 [^$CR $LF $Newline]? ($Extend |  $Format | $ZWJ)+;
 136
 137 $NumericEx {100};
 138 $ALetterEx {200};
 139 $HangulSyllable {200};
 140 $Hebrew_LetterEx{200};
 141 $KatakanaEx {400};       # note:  these status values override those from rule 5
 142 $HiraganaEx {400};       #        by virtue of being numerically larger.
 143 $IdeographicEx {400};    #
 144
 145 $E_Base ($Extend | $Format | $ZWJ)*;
 146 $E_Modifier ($Extend | $Format | $ZWJ)*;
 147 $Extended_Pict ($Extend | $Format | $ZWJ)*;
 148
 149 #
 150 # rule 5
 151 #    Do not break between most letters.
 152 #
 153 ($ALetterEx | $Hebrew_LetterEx)  ($ALetterEx | $Hebrew_LetterEx) {200};
 154
 155 # rule 6 and 7
 156 ($ALetterEx | $Hebrew_LetterEx) ($MidLetterEx | $MidNumLetEx ) ($ALetterEx | $Hebrew_LetterEx) {200};
 157
 158 # rule 7a
 159 $Hebrew_LetterEx $Single_QuoteEx {200};
 160
 161 # rule 7b and 7c
 162 $Hebrew_LetterEx $Double_QuoteEx $Hebrew_LetterEx {200};
 163
 164 # rule 8
 165
 166 $NumericEx $NumericEx {100};
 167
 168 # rule 9
 169
 170 ($ALetterEx | $Hebrew_LetterEx) $NumericEx {200};
 171
 172 # rule 10
 173
 174 $NumericEx ($ALetterEx | $Hebrew_LetterEx) {200};
 175
 176 # rule 11 and 12
 177
 178 $NumericEx ($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx {100};
 179
 180 # rule 13
 181 # to be consistent with $KanaKanji $KanaKanhi, changed
 182 # from 300 to 400.
 183 # See also TestRuleStatus in intltest/rbbiapts.cpp
 184 $KatakanaEx  $KatakanaEx {400};
 185
 186 # rule 13a/b
 187
 188 $ALetterEx       $ExtendNumLetEx {200};    #  (13a)
 189 $Hebrew_LetterEx $ExtendNumLetEx {200};    #  (13a)
 190 $NumericEx       $ExtendNumLetEx {100};    #  (13a)
 191 $KatakanaEx      $ExtendNumLetEx {400};    #  (13a)
 192 $ExtendNumLetEx  $ExtendNumLetEx {200};    #  (13a)
 193
 194 $ExtendNumLetEx  $ALetterEx      {200};    #  (13b)
 195 $ExtendNumLetEx  $Hebrew_Letter  {200};    #  (13b)
 196 $ExtendNumLetEx  $NumericEx      {100};    #  (13b)
 197 $ExtendNumLetEx  $KatakanaEx     {400};    #  (13b)
 198
 199 # rule 14
 200 #    Do not break within emoji modifier sequences
 201
 202 ($E_Base | $EBG) ($Format | $Extend | $ZWJ)* $E_Modifier;
 203
 204 # rules 15 - 17
 205 #    Pairs of Regional Indicators stay together.
 206 #    With rule chaining disabled by ^, this rule will match exactly two of them.
 207 #    No other rule begins with a Regional_Indicator, so chaining cannot extend the match.
 208 #
 209 ^$Regional_IndicatorEx $Regional_IndicatorEx;
 210
 211 # special handling for CJK characters: chain for later dictionary segmentation
 212 $HangulSyllable $HangulSyllable {200};
 213 $KanaKanji $KanaKanji {400}; # different rule status if both kana and kanji found
 214
 215 $Space* {1};
 216 $Newline* {2};
 217
 218 $Fullstop {20};
 219 $Dash {21};
 220 $Single_Quote {22};
 221
 222 $Contraction = (N | n) $Single_Quote (T | t);
 223 $Contraction2 = (N | n) $Single_Quote (T | t) $Single_Quote (V | v) (E | e);
 224 $Contraction3 = (Y | y) $Single_Quote (A | a) (L | l) (L | l);
 225
 226 $Time = (0 | 1 | 2)? $Numeric $Colon (0 | 1 | 2 | 3 | 4 | 5) $Numeric;
 227 $IPAddress = $Numeric? $Numeric? $Numeric $Fullstop $Numeric? $Numeric? $Numeric;
 228
 229 (N | n) $Single_Quote (T | t) {202};
 230 (Y | y) $Single_Quote (A | a) (L | l)* {202};
 231
 232 $Fullstop $Fullstop ($Fullstop*) {40};
 233 $Dash $Dash ($Dash*) {40};
 234 $Terminators $Terminators ($Terminators*) {40};
 235 $Punctuation $Punctuation ($Punctuation*) {40};
 236 $OtherSingle $OtherSingle ($OtherSingle*) {40};
 237
 238 $Single_Quote $Single_Quote {40};
 239 $Single_Quote $Single_Quote $Single_Quote* {40};
 240
 241 $Hash ($ALetter | $Numeric)* {30};
 242 $At ($ALetter | $Numeric)* {31};
 243 $Dollar $ALetter ($ALetter | $Numeric)* {31};
 244
 245 $Time {50};
 246 $IPAddress {51};
 247
 248 $ALetter / $IPAddress;
 249 $ALetter / $Time;
 250
 251 ($Colon | $Semicolon) $Parenthesis {32};
 252
 253 # Rule 999
 254 #     Match a single code point if no other rule applies.
 255 .;
 256
 257
 258 ## -------------------------------------------------
 259 # definitions for no-longer-used reverse rules, needed by safe_reverse
 260
 261 $BackHebrew_LetterEx      = ($Format | $Extend | $ZWJ)* $Hebrew_Letter;
 262 $BackALetterEx            = ($Format | $Extend | $ZWJ)* $ALetterPlus;
 263 $BackSingle_QuoteEx       = ($Format | $Extend | $ZWJ)* $Single_Quote;
 264 $BackDouble_QuoteEx       = ($Format | $Extend | $ZWJ)* $Double_Quote;
 265 $BackMidNumLetEx          = ($Format | $Extend | $ZWJ)* $MidNumLet;
 266 $BackNumericEx            = ($Format | $Extend | $ZWJ)* $Numeric;
 267 $BackMidNumEx             = ($Format | $Extend | $ZWJ)* $MidNum;
 268 $BackMidLetterEx          = ($Format | $Extend | $ZWJ)* $MidLetter;
 269 $BackKatakanaEx           = ($Format | $Extend | $ZWJ)* $Katakana;
 270 $BackHiraganaEx           = ($Format | $Extend | $ZWJ)* $Hiragana;
 271 $BackExtendNumLetEx       = ($Format | $Extend | $ZWJ)* $ExtendNumLet;
 272 $BackRegional_IndicatorEx = ($Format | $Extend | $ZWJ)* $Regional_Indicator;
 273
 274 ## -------------------------------------------------
 275
 276 !!safe_reverse;
 277
 278 # rule 3
 279 ($Extend | $Format | $ZWJ)+ .?;
 280
 281 # rule 6
 282 ($MidLetter | $MidNumLet | $Single_Quote) ($BackALetterEx | $BackHebrew_LetterEx);
 283
 284 # rule 7b
 285 $Double_Quote $BackHebrew_LetterEx;
 286
 287
 288 # rule 11
 289 ($MidNum | $MidNumLet | $Single_Quote) $BackNumericEx;
 290
 291 # rule 13c
 292 $BackRegional_IndicatorEx*;
 293
 294 # For dictionary-based break
 295 $dictionary $dictionary;