]> git.saurik.com Git - apple/icu.git/blob - icuSources/data/brkitr/word_POSIX.txt
ICU-8.11.tar.gz
[apple/icu.git] / icuSources / data / brkitr / word_POSIX.txt
1 #
2 # Copyright (C) 2002-2006, International Business Machines Corporation
3 # and others. All Rights Reserved.
4 #
5 # file: word.txt
6 #
7 # ICU Word Break Rules, POSIX locale.
8 # See Unicode Standard Annex #29.
9 # These rules are based on Unicode Version 5.0 0
10 # Includes post Unicode 5.0 change to treat Japanese half width voicing marks
11 # as Extend
12 #
13 # Note: Updates to word.txt will usually need to be merged into
14 # word_POSIX.txt and word_ja.txt also.
15
16 ##############################################################################
17 #
18 # Character class definitions from TR 29
19 #
20 ##############################################################################
21
22 !!chain;
23
24
25 #
26 # Character Class Definitions.
27 #
28
29 $VoiceMarks = [\uff9e\uff9f];
30 $Format = [\p{Word_Break = Format}];
31 $Katakana = [\p{Word_Break = Katakana}-$VoiceMarks];
32 $ALetter = [\p{Word_Break = ALetter}];
33 $MidLetter = [\p{Word_Break = MidLetter} - [ \:]];
34 $MidNum = [\p{Word_Break = MidNum}];
35 $Numeric = [\p{Word_Break = Numeric}];
36 $ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
37
38
39 $CR = \u000d;
40 $LF = \u000a;
41 $Extend = [\p{Grapheme_Cluster_Break = Extend}$VoiceMarks];
42 $Control = [\p{Grapheme_Cluster_Break = Control}];
43
44 # Dictionary character set, for triggering language-based break engines. Currently
45 # limited to LineBreak=Complex_Context. Note that this set only works in Unicode
46 # 5.0 or later as the definition of Complex_Context was corrected to include all
47 # characters requiring dictionary break.
48
49 $dictionary = [:LineBreak = Complex_Context:];
50 $ALetterPlus = [$ALetter [$dictionary-$Extend-$Control]];
51
52
53 #
54 # Rules 3 Grapheme Clusters behave like their first char.
55 # Rule 4 Ignore trailing Format characters (Also see note in TR 29)
56 #
57 $KatakanaEx = $Katakana ($Extend | $Format)*;
58 $ALetterEx = $ALetterPlus ($Extend | $Format)*;
59 $MidLetterEx = $MidLetter ($Extend | $Format)*;
60 $MidNumEx = $MidNum ($Extend | $Format)*;
61 $NumericEx = $Numeric ($Extend | $Format)*;
62 $ExtendNumLetEx = $ExtendNumLet ($Extend | $Format)*;
63
64 $Hiragana = [:Hiragana:];
65 $Ideographic = [:IDEOGRAPHIC:];
66 $HiraganaEx = $Hiragana ($Extend | $Format)*;
67 $IdeographicEx = $Ideographic ($Extend | $Format)*;
68
69 ## -------------------------------------------------
70
71 !!forward;
72
73
74 # Rule 3 - CR x LF
75 # see character breaks.
76
77 $CR $LF ($Extend | $Format)*;
78
79 # Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
80 # of a region of Text. The rule here comes into play when the start of text
81 # begins with a group of Format chars, or with a "word" consisting of a single
82 # char that is not in any of the listed word break categories followed by
83 # format char(s).
84 .? ($Extend | $Format)+;
85
86
87 $NumericEx {100};
88 $ALetterEx {200};
89 $KatakanaEx {300};
90 $HiraganaEx {300};
91 $IdeographicEx {400};
92
93 # rule 5
94
95 $ALetterEx $ALetterEx {200};
96
97 # rule 6 and 7
98 $ALetterEx $MidLetterEx $ALetterEx {200};
99
100 # rule 8
101
102 $NumericEx $NumericEx {100};
103
104 # rule 9
105
106 $ALetterEx $Format* $NumericEx {200};
107
108 # rule 10
109
110 $NumericEx $ALetterEx {200};
111
112 # rule 11 and 12
113
114 $NumericEx $MidNumEx $NumericEx {100};
115
116 # rule 13
117
118 $KatakanaEx $KatakanaEx {300};
119
120 # rule 13a/b
121
122 $ALetterEx $ExtendNumLetEx {200}; # (13a)
123 $NumericEx $ExtendNumLetEx {100}; # (13a)
124 $KatakanaEx $ExtendNumLetEx {300}; # (13a)
125 $ExtendNumLetEx $ExtendNumLetEx{200}; # (13a)
126
127 $ExtendNumLetEx $ALetterEx {200}; # (13b)
128 $ExtendNumLetEx $NumericEx {100}; # (13b)
129 $ExtendNumLetEx $KatakanaEx {300}; # (13b)
130
131
132
133 ## -------------------------------------------------
134
135 !!reverse;
136
137 $BackALetterEx = ($Format | $Extend)* $ALetterPlus;
138 $BackNumericEx = ($Format | $Extend)* $Numeric;
139 $BackMidNumEx = ($Format | $Extend)* $MidNum;
140 $BackMidLetterEx = ($Format | $Extend)* $MidLetter;
141 $BackKatakanaEx = ($Format | $Extend)* $Katakana;
142 $BackExtendNumLetEx= ($Format | $Extend)* $ExtendNumLet;
143
144 # rule 3
145 ($Format | $Extend)* $LF $CR;
146
147 # rule 4
148 ($Format | $Extend)* .?;
149
150 # rule 5
151
152 $BackALetterEx $BackALetterEx;
153
154 # rule 6 and 7
155
156 $BackALetterEx $BackMidLetterEx $BackALetterEx;
157
158
159 # rule 8
160
161 $BackNumericEx $BackNumericEx;
162
163 # rule 9
164
165 $BackNumericEx $BackALetterEx;
166
167 # rule 10
168
169 $BackALetterEx $BackNumericEx;
170
171 # rule 11 and 12
172
173 $BackNumericEx $BackMidNumEx $BackNumericEx;
174
175 # rule 13
176
177 $BackKatakanaEx $BackKatakanaEx;
178
179 # rules 13 a/b
180 #
181 ($BackALetterEx | $BackNumericEx | $BackKatakanaEx | $BackExtendNumLetEx) $BackExtendNumLetEx;
182 $BackExtendNumLetEx ($BackALetterEx | $BackNumericEx | $BackKatakanaEx);
183
184 ## -------------------------------------------------
185
186 !!safe_reverse;
187
188 # rule 3
189 ($Extend | $Format)+ .?;
190
191 # rule 6
192 $MidLetter $BackALetterEx;
193
194 # rule 11
195 $MidNum $BackNumericEx;
196
197 # For dictionary-based break
198 $dictionary $dictionary;
199
200 ## -------------------------------------------------
201
202 !!safe_forward;
203
204 # rule 4
205 ($Extend | $Format)+ .?;
206
207 # rule 6
208 $MidLetterEx $ALetterEx;
209
210 # rule 11
211 $MidNumEx $NumericEx;
212
213 # For dictionary-based break
214 $dictionary $dictionary;