• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
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#      Plus additional characters introduces with Emoji 5, http://www.unicode.org/reports/tr51/proposed.html
14#
15# Note:  Updates to word.txt will usually need to be merged into
16#        word_POSIX.txt also.
17
18##############################################################################
19#
20#  Character class definitions from TR 29
21#
22##############################################################################
23
24!!chain;
25!!quoted_literals_only;
26
27
28#
29#  Character Class Definitions.
30#
31
32$CR                 = [\p{Word_Break = CR}];
33$LF                 = [\p{Word_Break = LF}];
34$Newline            = [\p{Word_Break = Newline} ];
35$Extend             = [\p{Word_Break = Extend}];
36$ZWJ                = [\p{Word_Break = ZWJ}];
37$Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
38$Format             = [\p{Word_Break = Format}];
39$Katakana           = [\p{Word_Break = Katakana}];
40$Hebrew_Letter      = [\p{Word_Break = Hebrew_Letter}];
41$ALetter            = [\p{Word_Break = ALetter}];
42$Single_Quote       = [\p{Word_Break = Single_Quote}];
43$Double_Quote       = [\p{Word_Break = Double_Quote}];
44$MidNumLet          = [\p{Word_Break = MidNumLet} - [.]];
45$MidLetter          = [\p{Word_Break = MidLetter} - [\:]];
46$MidNum             = [\p{Word_Break = MidNum} [.]];
47$Numeric            = [\p{Word_Break = Numeric}];
48$ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
49$E_Base             = [\p{Word_Break = EB}];
50$E_Modifier         = [\p{Word_Break = EM}];
51
52# Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r13267
53$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];
54$EBG                = [\p{Word_Break = EBG}];
55$EmojiNRK           = [[\p{Emoji}] - [\p{Word_Break = Regional_Indicator}\u002a\u00230-9©®™〰〽]];
56
57$Han                = [:Han:];
58$Hiragana           = [:Hiragana:];
59
60
61#   Dictionary character set, for triggering language-based break engines. Currently
62#   limited to LineBreak=Complex_Context. Note that this set only works in Unicode
63#   5.0 or later as the definition of Complex_Context was corrected to include all
64#   characters requiring dictionary break.
65
66$Control        = [\p{Grapheme_Cluster_Break = Control}];
67$HangulSyllable = [\uac00-\ud7a3];
68$ComplexContext = [:LineBreak = Complex_Context:];
69$KanaKanji      = [$Han $Hiragana $Katakana];
70$dictionaryCJK  = [$KanaKanji $HangulSyllable];
71$dictionary     = [$ComplexContext $dictionaryCJK];
72
73# leave CJK scripts out of ALetterPlus
74$ALetterPlus  = [$ALetter-$dictionaryCJK [$ComplexContext-$Extend-$Control]];
75
76
77#
78#  Rules 4    Ignore Format and Extend characters,
79#             except when they appear at the beginning of a region of text.
80#
81# TODO: check if handling of katakana in dictionary makes rules incorrect/void
82$KatakanaEx           = $Katakana           ($Extend |  $Format | $ZWJ)*;
83$Hebrew_LetterEx      = $Hebrew_Letter      ($Extend |  $Format | $ZWJ)*;
84$ALetterEx            = $ALetterPlus        ($Extend |  $Format | $ZWJ)*;
85$Single_QuoteEx       = $Single_Quote       ($Extend |  $Format | $ZWJ)*;
86$Double_QuoteEx       = $Double_Quote       ($Extend |  $Format | $ZWJ)*;
87$MidNumLetEx          = $MidNumLet          ($Extend |  $Format | $ZWJ)*;
88$MidLetterEx          = $MidLetter          ($Extend |  $Format | $ZWJ)*;
89$MidNumEx             = $MidNum             ($Extend |  $Format | $ZWJ)*;
90$NumericEx            = $Numeric            ($Extend |  $Format | $ZWJ)*;
91$ExtendNumLetEx       = $ExtendNumLet       ($Extend |  $Format | $ZWJ)*;
92$Regional_IndicatorEx = $Regional_Indicator ($Extend |  $Format | $ZWJ)*;
93
94$Ideographic    = [\p{Ideographic}];
95$HiraganaEx     = $Hiragana     ($Extend |  $Format | $ZWJ)*;
96$IdeographicEx  = $Ideographic  ($Extend |  $Format | $ZWJ)*;
97
98## -------------------------------------------------
99
100!!forward;
101
102
103# Rule 3 - CR x LF
104#
105$CR $LF;
106
107# Rule 3c   ZWJ x (Extended_Pict | EmojiNRK).  Precedes WB4, so no intervening Extend chars allowed.
108#
109$ZWJ ($Extended_Pict | $EmojiNRK);
110
111
112# Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
113#          of a region of Text.   The rule here comes into play when the start of text
114#          begins with a group of Format chars, or with a "word" consisting of a single
115#          char that is not in any of the listed word break categories followed by
116#          format char(s), or is not a CJK dictionary character.
117[^$CR $LF $Newline]? ($Extend |  $Format | $ZWJ)+;
118
119$NumericEx {100};
120$ALetterEx {200};
121$HangulSyllable {200};
122$Hebrew_LetterEx{200};
123$KatakanaEx {400};       # note:  these status values override those from rule 5
124$HiraganaEx {400};       #        by virtue of being numerically larger.
125$IdeographicEx {400};    #
126
127$E_Base ($Extend | $Format | $ZWJ)*;
128$E_Modifier ($Extend | $Format | $ZWJ)*;
129$Extended_Pict ($Extend | $Format | $ZWJ)*;
130
131#
132# rule 5
133#    Do not break between most letters.
134#
135($ALetterEx | $Hebrew_LetterEx)  ($ALetterEx | $Hebrew_LetterEx) {200};
136
137# rule 6 and 7
138($ALetterEx | $Hebrew_LetterEx) ($MidLetterEx | $MidNumLetEx | $Single_QuoteEx) ($ALetterEx | $Hebrew_LetterEx) {200};
139
140# rule 7a
141$Hebrew_LetterEx $Single_QuoteEx {200};
142
143# rule 7b and 7c
144$Hebrew_LetterEx $Double_QuoteEx $Hebrew_LetterEx {200};
145
146# rule 8
147
148$NumericEx $NumericEx {100};
149
150# rule 9
151
152($ALetterEx | $Hebrew_LetterEx) $NumericEx {200};
153
154# rule 10
155
156$NumericEx ($ALetterEx | $Hebrew_LetterEx) {200};
157
158# rule 11 and 12
159
160$NumericEx ($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx {100};
161
162# rule 13
163# to be consistent with $KanaKanji $KanaKanhi, changed
164# from 300 to 400.
165# See also TestRuleStatus in intltest/rbbiapts.cpp
166$KatakanaEx  $KatakanaEx {400};
167
168# rule 13a/b
169
170$ALetterEx       $ExtendNumLetEx {200};    #  (13a)
171$Hebrew_LetterEx $ExtendNumLetEx {200};    #  (13a)
172$NumericEx       $ExtendNumLetEx {100};    #  (13a)
173$KatakanaEx      $ExtendNumLetEx {400};    #  (13a)
174$ExtendNumLetEx  $ExtendNumLetEx {200};    #  (13a)
175
176$ExtendNumLetEx  $ALetterEx      {200};    #  (13b)
177$ExtendNumLetEx  $Hebrew_Letter  {200};    #  (13b)
178$ExtendNumLetEx  $NumericEx      {100};    #  (13b)
179$ExtendNumLetEx  $KatakanaEx     {400};    #  (13b)
180
181# rule 14
182#    Do not break within emoji modifier sequences
183
184($E_Base | $EBG) ($Format | $Extend | $ZWJ)* $E_Modifier;
185
186# rules 15 - 17
187#    Pairs of Regional Indicators stay together.
188#    With rule chaining disabled by ^, this rule will match exactly two of them.
189#    No other rule begins with a Regional_Indicator, so chaining cannot extend the match.
190#
191^$Regional_IndicatorEx $Regional_IndicatorEx;
192
193# special handling for CJK characters: chain for later dictionary segmentation
194$HangulSyllable $HangulSyllable {200};
195$KanaKanji $KanaKanji {400}; # different rule status if both kana and kanji found
196
197# Rule 999
198#     Match a single code point if no other rule applies.
199.;
200
201
202## -------------------------------------------------
203
204!!safe_reverse;
205
206# rule 3
207($Extend | $Format | $ZWJ)+ .?;
208
209# rule 6
210($MidLetter | $MidNumLet | $Single_Quote) ($Format | $Extend | $ZWJ)* ($Hebrew_Letter | $ALetterPlus);
211
212# rule 7b
213$Double_Quote ($Format | $Extend | $ZWJ)* $Hebrew_Letter;
214
215
216# rule 11
217($MidNum | $MidNumLet | $Single_Quote) ($Format | $Extend | $ZWJ)* $Numeric;
218
219# rule 13c
220$Regional_Indicator ($Format | $Extend | $ZWJ)* $Regional_Indicator;
221
222# For dictionary-based break
223$dictionary $dictionary;
224