1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
|
<?xml version="1.0" encoding="UTF-8" ?>
<!DOCTYPE ldml SYSTEM "../../common/dtd/ldml.dtd">
<!--
Copyright © 1991-2013 Unicode, Inc.
CLDR data files are interpreted according to the LDML specification (http://unicode.org/reports/tr35/)
For terms of use, see http://www.unicode.org/copyright.html
-->
<ldml>
<identity>
<version number="$Revision: 8242 $"/>
<generation date="$Date: 2013-02-24 21:06:02 -0600 (Sun, 24 Feb 2013) $"/>
<language type="root"/>
</identity>
<segmentations>
<segmentation type="GraphemeClusterBreak">
<variables>
<variable id="$CR">\p{Grapheme_Cluster_Break=CR}</variable>
<variable id="$LF">\p{Grapheme_Cluster_Break=LF}</variable>
<variable id="$Control">\p{Grapheme_Cluster_Break=Control}</variable>
<variable id="$Extend">\p{Grapheme_Cluster_Break=Extend}</variable>
<!-- <variable id="$Prepend">\p{Grapheme_Cluster_Break=Prepend}</variable> # TODO: Restore if the Prepend set becomes non-empty again -->
<variable id="$SpacingMark">\p{Grapheme_Cluster_Break=SpacingMark}</variable>
<variable id="$L">\p{Grapheme_Cluster_Break=L}</variable>
<variable id="$V">\p{Grapheme_Cluster_Break=V}</variable>
<variable id="$T">\p{Grapheme_Cluster_Break=T}</variable>
<variable id="$LV">\p{Grapheme_Cluster_Break=LV}</variable>
<variable id="$LVT">\p{Grapheme_Cluster_Break=LVT}</variable>
<variable id="$Regional_Indicator">\p{Grapheme_Cluster_Break=Regional_Indicator}</variable>
</variables>
<segmentRules>
<rule id="3"> $CR × $LF </rule>
<rule id="4"> ( $Control | $CR | $LF ) ÷ </rule>
<rule id="5"> ÷ ( $Control | $CR | $LF ) </rule>
<rule id="6"> $L × ( $L | $V | $LV | $LVT ) </rule>
<rule id="7"> ( $LV | $V ) × ( $V | $T ) </rule>
<rule id="8"> ( $LVT | $T) × $T </rule>
<rule id="8.1"> $Regional_Indicator × $Regional_Indicator </rule>
<rule id="9"> × $Extend </rule>
<rule id="9.1"> × $SpacingMark </rule>
<!-- <rule id="9.2"> $Prepend × </rule> # TODO: Restore if the Prepend set becomes non-empty again -->
</segmentRules>
</segmentation>
<segmentation type="LineBreak">
<variables>
<!-- Variables -->
<variable id="$AI">\p{Line_Break=Ambiguous}</variable>
<variable id="$AL">\p{Line_Break=Alphabetic}</variable>
<variable id="$B2">\p{Line_Break=Break_Both}</variable>
<variable id="$BA">\p{Line_Break=Break_After}</variable>
<variable id="$BB">\p{Line_Break=Break_Before}</variable>
<variable id="$BK">\p{Line_Break=Mandatory_Break}</variable>
<variable id="$CB">\p{Line_Break=Contingent_Break}</variable>
<variable id="$CL">\p{Line_Break=Close_Punctuation}</variable>
<variable id="$CP">\p{Line_Break=CP}</variable>
<variable id="$CM">\p{Line_Break=Combining_Mark}</variable>
<variable id="$CR">\p{Line_Break=Carriage_Return}</variable>
<variable id="$EX">\p{Line_Break=Exclamation}</variable>
<variable id="$GL">\p{Line_Break=Glue}</variable>
<variable id="$H2">\p{Line_Break=H2}</variable>
<variable id="$H3">\p{Line_Break=H3}</variable>
<variable id="$HL">\p{Line_Break=HL}</variable>
<variable id="$HY">\p{Line_Break=Hyphen}</variable>
<variable id="$ID">\p{Line_Break=Ideographic}</variable>
<variable id="$IN">\p{Line_Break=Inseparable}</variable>
<variable id="$IS">\p{Line_Break=Infix_Numeric}</variable>
<variable id="$JL">\p{Line_Break=JL}</variable>
<variable id="$JT">\p{Line_Break=JT}</variable>
<variable id="$JV">\p{Line_Break=JV}</variable>
<variable id="$LF">\p{Line_Break=Line_Feed}</variable>
<variable id="$NL">\p{Line_Break=Next_Line}</variable>
<variable id="$NS">\p{Line_Break=Nonstarter}</variable>
<variable id="$NU">\p{Line_Break=Numeric}</variable>
<variable id="$OP">\p{Line_Break=Open_Punctuation}</variable>
<variable id="$PO">\p{Line_Break=Postfix_Numeric}</variable>
<variable id="$PR">\p{Line_Break=Prefix_Numeric}</variable>
<variable id="$QU">\p{Line_Break=Quotation}</variable>
<variable id="$SA">\p{Line_Break=Complex_Context}</variable>
<variable id="$SG">\p{Line_Break=Surrogate}</variable>
<variable id="$SP">\p{Line_Break=Space}</variable>
<variable id="$SY">\p{Line_Break=Break_Symbols}</variable>
<variable id="$WJ">\p{Line_Break=Word_Joiner}</variable>
<variable id="$XX">\p{Line_Break=Unknown}</variable>
<variable id="$ZW">\p{Line_Break=ZWSpace}</variable>
<variable id="$CJ">\p{Line_Break=Conditional_Japanese_Starter}</variable>
<variable id="$RI">\p{Line_Break=Regional_Indicator}</variable>
<!-- LB 1 Assign a line breaking class to each code point of the input. -->
<!-- Resolve AI, CB, SA, SG, and XX into other line breaking classes depending on criteria outside the scope of this algorithm. -->
<!-- NOTE: CB is ok to fall through, but must handle others here. -->
<variable id="$AL">[$AI $AL $XX $SA $SG]</variable>
<variable id="$NS">[$NS $CJ]</variable>
<!-- WARNING: Fixes for Rule 9 -->
<!-- Treat X CM* as if it were X. -->
<!-- Where X is any line break class except SP, BK, CR, LF, NL or ZW. -->
<variable id="$X">$CM*</variable>
<variable id="$Spec1_">[$SP $BK $CR $LF $NL $ZW]</variable>
<variable id="$Spec2_">[^ $SP $BK $CR $LF $NL $ZW]</variable>
<variable id="$Spec3a_">[^ $SP $BA $HY $CM]</variable>
<variable id="$Spec3b_">[^ $BA $HY $CM]</variable>
<variable id="$Spec4_">[^ $NU $CM]</variable>
<variable id="$AI">($AI $X)</variable>
<variable id="$AL">($AL $X)</variable>
<variable id="$B2">($B2 $X)</variable>
<variable id="$BA">($BA $X)</variable>
<variable id="$BB">($BB $X)</variable>
<variable id="$CB">($CB $X)</variable>
<variable id="$CL">($CL $X)</variable>
<variable id="$CP">($CP $X)</variable>
<variable id="$CM">($CM $X)</variable>
<variable id="$CM">($CM $X)</variable>
<variable id="$GL">($GL $X)</variable>
<variable id="$H2">($H2 $X)</variable>
<variable id="$H3">($H3 $X)</variable>
<variable id="$HL">($HL $X)</variable>
<variable id="$HY">($HY $X)</variable>
<variable id="$ID">($ID $X)</variable>
<variable id="$IN">($IN $X)</variable>
<variable id="$IS">($IS $X)</variable>
<variable id="$JL">($JL $X)</variable>
<variable id="$JT">($JT $X)</variable>
<variable id="$JV">($JV $X)</variable>
<variable id="$NS">($NS $X)</variable>
<variable id="$NU">($NU $X)</variable>
<variable id="$OP">($OP $X)</variable>
<variable id="$PO">($PO $X)</variable>
<variable id="$PR">($PR $X)</variable>
<variable id="$QU">($QU $X)</variable>
<variable id="$SA">($SA $X)</variable>
<variable id="$SG">($SG $X)</variable>
<variable id="$SY">($SY $X)</variable>
<variable id="$WJ">($WJ $X)</variable>
<variable id="$XX">($XX $X)</variable>
<variable id="$RI">($RI $X)</variable>
<!-- OUT OF ORDER ON PURPOSE -->
<!-- LB 10 Treat any remaining combining mark as AL. -->
<variable id="$AL">($AL | ^ $CM | (?<=$Spec1_) $CM)</variable>
</variables>
<segmentRules>
<!-- LB 4 Always break after hard line breaks (but never between CR and LF). -->
<rule id="4"> $BK ÷ </rule>
<!-- LB 5 Treat CR followed by LF, as well as CR, LF and NL as hard line breaks. -->
<rule id="5.01"> $CR × $LF </rule>
<rule id="5.02"> $CR ÷ </rule>
<rule id="5.03"> $LF ÷ </rule>
<rule id="5.04"> $NL ÷ </rule>
<!-- LB 6 Do not break before hard line breaks. -->
<rule id="6"> × ( $BK | $CR | $LF | $NL ) </rule>
<!-- LB 7 Do not break before spaces or zero-width space. -->
<rule id="7.01"> × $SP </rule>
<rule id="7.02"> × $ZW </rule>
<!-- LB 8 Break before any character following a zero-width space, even if one or more spaces intervene. -->
<rule id="8"> $ZW $SP* ÷ </rule>
<!-- LB 9 Do not break a combining character sequence; treat it as if it has the LB class of the base character -->
<!-- in all of the following rules. (Where X is any line break class except SP, BK, CR, LF, NL or ZW.) -->
<rule id="9"> $Spec2_ × $CM </rule>
<!-- WARNING: this is done by modifying the variable values for all but SP.... That is, $AL is really ($AI $CM*)! -->
<!-- LB 11 Do not break before or after WORD JOINER and related characters. -->
<rule id="11.01"> × $WJ </rule>
<rule id="11.02"> $WJ × </rule>
<!-- LB 12 Do not break after NBSP and related characters. -->
<rule id="12"> $GL × </rule>
<rule id="12.1"> $Spec3a_ × $GL </rule>
<rule id="12.2"> $Spec3b_ $CM+ × $GL </rule>
<rule id="12.3"> ^ $CM+ × $GL </rule>
<!-- LB 13 Do not break before ‘]’ or ‘!’ or ‘;’ or ‘/’, even after spaces. -->
<!-- Using customization 7. -->
<rule id="13.01"> × $EX </rule>
<rule id="13.02"> $Spec4_ × ($CL | $CP | $IS | $SY) </rule>
<rule id="13.03"> $Spec4_ $CM+ × ($CL | $CP | $IS | $SY) </rule>
<rule id="13.04"> ^ $CM+ × ($CL | $CP | $IS | $SY) </rule>
<!-- LB 14 Do not break after ‘[’, even after spaces. -->
<rule id="14"> $OP $SP* × </rule>
<!-- LB 15 Do not break within ‘"[’, even with intervening spaces. -->
<rule id="15"> $QU $SP* × $OP </rule>
<!-- LB 16 Do not break between closing punctuation and a nonstarter (lb=NS), even with intervening spaces. -->
<rule id="16"> ($CL | $CP) $SP* × $NS </rule>
<!-- LB 17 Do not break within ‘——’, even with intervening spaces. -->
<rule id="17"> $B2 $SP* × $B2 </rule>
<!-- LB 18 Break after spaces. -->
<rule id="18"> $SP ÷ </rule>
<!-- LB 19 Do not break before or after ‘"’. -->
<rule id="19.01"> × $QU </rule>
<rule id="19.02"> $QU × </rule>
<!-- LB 20 Break before and after unresolved CB. -->
<rule id="20.01"> ÷ $CB </rule>
<rule id="20.02"> $CB ÷ </rule>
<!-- LB 21 Do not break before hyphen-minus, other hyphens, fixed-width spaces, small kana and other non-starters, or after acute accents. -->
<rule id="21.01"> × $BA </rule>
<rule id="21.02"> × $HY </rule>
<rule id="21.03"> × $NS </rule>
<rule id="21.04"> $BB × </rule>
<!-- LB 21 Do not break before hyphen-minus, other hyphens, fixed-width spaces, small kana and other non-starters, or after acute accents. -->
<rule id="21.1"> $HL ($HY | $BA) × </rule>
<!-- LB 22 Do not break between two ellipses, or between letters or numbers and ellipsis. -->
<rule id="22.01"> ($AL | $HL) × $IN </rule>
<rule id="22.02"> $ID × $IN </rule>
<rule id="22.03"> $IN × $IN </rule>
<rule id="22.04"> $NU × $IN </rule>
<!-- LB 23 Do not break within ‘a9’, ‘3a’, or ‘H%’. -->
<rule id="23.01"> $ID × $PO </rule>
<rule id="23.02"> ($AL | $HL) × $NU </rule>
<rule id="23.03"> $NU × ($AL | $HL) </rule>
<!-- LB 24 Do not break between prefix and letters or ideographs. -->
<rule id="24.01"> $PR × $ID </rule>
<rule id="24.02"> $PR × ($AL | $HL) </rule>
<rule id="24.03"> $PO × ($AL | $HL) </rule>
<!-- Using customization 7 -->
<!-- LB 18 Do not break between the following pairs of classes. -->
<!-- LB 18-alternative: $PR? ( $OP | $HY )? $NU ($NU | $SY | $IS)* ($CL | $CP)? $PO? -->
<!-- Insert × every place it could go. However, make sure that at least one thing is concrete, otherwise would cause $NU to not break before or after -->
<rule id="25.01"> ($PR | $PO) × ( $OP | $HY )? $NU </rule>
<rule id="25.02"> ( $OP | $HY ) × $NU </rule>
<rule id="25.03"> $NU × ($NU | $SY | $IS) </rule>
<rule id="25.04"> $NU ($NU | $SY | $IS)* × ($NU | $SY | $IS | $CL | $CP) </rule>
<rule id="25.05"> $NU ($NU | $SY | $IS)* ($CL | $CP)? × ($PO | $PR) </rule>
<!-- LB 26 Do not break a Korean syllable. -->
<rule id="26.01"> $JL × $JL | $JV | $H2 | $H3 </rule>
<rule id="26.02"> $JV | $H2 × $JV | $JT </rule>
<rule id="26.03"> $JT | $H3 × $JT </rule>
<!-- LB 27 Treat a Korean Syllable Block the same as ID. -->
<rule id="27.01"> $JL | $JV | $JT | $H2 | $H3 × $IN </rule>
<rule id="27.02"> $JL | $JV | $JT | $H2 | $H3 × $PO </rule>
<rule id="27.03"> $PR × $JL | $JV | $JT | $H2 | $H3 </rule>
<!-- LB 28 Do not break between alphabetics ("at"). -->
<rule id="28"> ($AL | $HL) × ($AL | $HL) </rule>
<!-- LB 29 Do not break between numeric punctuation and alphabetics ("e.g."). -->
<rule id="29"> $IS × ($AL | $HL) </rule>
<!-- LB 30 Do not break between letters, numbers or ordinary symbols and opening or closing punctuation. -->
<rule id="30.01"> ($AL | $HL | $NU) × $OP </rule>
<rule id="30.02"> $CP × ($AL | $HL | $NU) </rule>
<!-- LB 30a Do not break between Regional Indicators. -->
<rule id="30.11"> $RI × $RI </rule>
</segmentRules>
</segmentation>
<segmentation type="SentenceBreak">
<variables>
<variable id="$CR">\p{Sentence_Break=CR}</variable>
<variable id="$LF">\p{Sentence_Break=LF}</variable>
<variable id="$Extend">\p{Sentence_Break=Extend}</variable>
<variable id="$Format">\p{Sentence_Break=Format}</variable>
<variable id="$Sep">\p{Sentence_Break=Sep}</variable>
<variable id="$Sp">\p{Sentence_Break=Sp}</variable>
<variable id="$Lower">\p{Sentence_Break=Lower}</variable>
<variable id="$Upper">\p{Sentence_Break=Upper}</variable>
<variable id="$OLetter">\p{Sentence_Break=OLetter}</variable>
<variable id="$Numeric">\p{Sentence_Break=Numeric}</variable>
<variable id="$ATerm">\p{Sentence_Break=ATerm}</variable>
<variable id="$STerm">\p{Sentence_Break=STerm}</variable>
<variable id="$Close">\p{Sentence_Break=Close}</variable>
<variable id="$SContinue">\p{Sentence_Break=SContinue}</variable>
<variable id="$Any">.</variable>
<!-- Expresses the negation in rule 8; can't do this with normal regex, but works with UnicodeSet, which is all we need. -->
<!-- WARNING: For Rule 5, now add format and extend to everything but Sep -->
<variable id="$FE">[$Format $Extend]</variable>
<variable id="$NotPreLower_">[^ $OLetter $Upper $Lower $Sep $CR $LF $STerm $ATerm]</variable>
<variable id="$Sp">($Sp $FE*)</variable>
<variable id="$Lower">($Lower $FE*)</variable>
<variable id="$Upper">($Upper $FE*)</variable>
<variable id="$OLetter">($OLetter $FE*)</variable>
<variable id="$Numeric">($Numeric $FE*)</variable>
<variable id="$ATerm">($ATerm $FE*)</variable>
<variable id="$STerm">($STerm $FE*)</variable>
<variable id="$Close">($Close $FE*)</variable>
<variable id="$SContinue">($SContinue $FE*)</variable>
</variables>
<segmentRules>
<!-- Do not break within CRLF -->
<rule id="3"> $CR × $LF </rule>
<!-- Break after paragraph separators. -->
<rule id="4"> ($Sep | $CR | $LF) ÷ </rule>
<!-- Ignore Format and Extend characters, except when they appear at the beginning of a region of text. -->
<!-- (See Section 6.2 Grapheme Cluster and Format Rules.) -->
<!-- WARNING: Implemented as don't break before format (except after linebreaks), -->
<!-- AND add format and extend in all variables definitions that appear after this point! -->
<rule id="5"> × [$Format $Extend] </rule>
<!-- Do not break after ambiguous terminators like period, if immediately followed by a number or lowercase letter, -->
<!-- is between uppercase letters, or if the first following letter (optionally after certain punctuation) is lowercase. -->
<!-- For example, a period may be an abbreviation or numeric period, and not mark the end of a sentence. -->
<rule id="6"> $ATerm × $Numeric </rule>
<rule id="7"> $Upper $ATerm × $Upper </rule>
<rule id="8"> $ATerm $Close* $Sp* × $NotPreLower_* $Lower </rule>
<rule id="8.1"> ($STerm | $ATerm) $Close* $Sp* × ($SContinue | $STerm | $ATerm) </rule>
<!-- Break after sentence terminators, but include closing punctuation, trailing spaces, and (optionally) a paragraph separator. -->
<rule id="9"> ( $STerm | $ATerm ) $Close* × ( $Close | $Sp | $Sep | $CR | $LF ) </rule>
<!-- Note the fix to $Sp*, $Sep? -->
<rule id="10"> ( $STerm | $ATerm ) $Close* $Sp* × ( $Sp | $Sep | $CR | $LF ) </rule>
<rule id="11"> ( $STerm | $ATerm ) $Close* $Sp* ($Sep | $CR | $LF)? ÷ </rule>
<!-- Otherwise, do not break -->
<rule id="12"> × $Any </rule>
</segmentRules>
</segmentation>
<segmentation type="WordBreak">
<variables>
<variable id="$CR">\p{Word_Break=CR}</variable>
<variable id="$LF">\p{Word_Break=LF}</variable>
<variable id="$Newline">\p{Word_Break=Newline}</variable>
<variable id="$Extend">\p{Word_Break=Extend}</variable>
<!-- Now normal variables -->
<variable id="$Format">\p{Word_Break=Format}</variable>
<variable id="$Katakana">\p{Word_Break=Katakana}</variable>
<variable id="$ALetter">\p{Word_Break=ALetter}</variable>
<variable id="$MidLetter">\p{Word_Break=MidLetter}</variable>
<variable id="$MidNum">\p{Word_Break=MidNum}</variable>
<variable id="$MidNumLet">\p{Word_Break=MidNumLet}</variable>
<variable id="$Numeric">\p{Word_Break=Numeric}</variable>
<variable id="$ExtendNumLet">\p{Word_Break=ExtendNumLet}</variable>
<variable id="$Regional_Indicator">\p{Word_Break=Regional_Indicator}</variable>
<!-- WARNING: For Rule 4: Fixes for GC, Format -->
<!-- Add format and extend to everything -->
<variable id="$FE">[$Format $Extend]</variable>
<variable id="$NotBreak_">[^ $Newline $CR $LF ]</variable>
<variable id="$Katakana">($Katakana $FE*)</variable>
<variable id="$ALetter">($ALetter $FE*)</variable>
<variable id="$MidLetter">($MidLetter $FE*)</variable>
<variable id="$MidNum">($MidNum $FE*)</variable>
<variable id="$MidNumLet">($MidNumLet $FE*)</variable>
<variable id="$Numeric">($Numeric $FE*)</variable>
<variable id="$ExtendNumLet">($ExtendNumLet $FE*)</variable>
<variable id="$Regional_Indicator">($Regional_Indicator $FE*)</variable>
</variables>
<segmentRules>
<rule id="3"> $CR × $LF </rule>
<rule id="3.1"> ($Newline | $CR | $LF) ÷ </rule>
<rule id="3.2"> ÷ ($Newline | $CR | $LF) </rule>
<!-- Ignore Format and Extend characters, except when they appear at the beginning of a region of text. -->
<!-- (See Section 6.2 Grapheme Cluster and Format Rules.) -->
<!-- WARNING: Implemented as don't break before format (except after linebreaks), -->
<!-- AND add format and extend in all variables definitions that appear after this point! -->
<rule id="4"> $NotBreak_ × [$Format $Extend] </rule>
<!-- Vanilla rules -->
<rule id="5"> $ALetter × $ALetter </rule>
<rule id="6"> $ALetter × ($MidLetter | $MidNumLet) $ALetter </rule>
<rule id="7"> $ALetter ($MidLetter | $MidNumLet) × $ALetter </rule>
<rule id="8"> $Numeric × $Numeric </rule>
<rule id="9"> $ALetter × $Numeric </rule>
<rule id="10"> $Numeric × $ALetter </rule>
<rule id="11"> $Numeric ($MidNum | $MidNumLet) × $Numeric </rule>
<rule id="12"> $Numeric × ($MidNum | $MidNumLet) $Numeric </rule>
<rule id="13"> $Katakana × $Katakana </rule>
<rule id="13.1"> ($ALetter | $Numeric | $Katakana | $ExtendNumLet) × $ExtendNumLet </rule>
<rule id="13.2"> $ExtendNumLet × ($ALetter | $Numeric | $Katakana) </rule>
<rule id="13.3"> $Regional_Indicator × $Regional_Indicator </rule>
</segmentRules>
</segmentation>
</segmentations>
</ldml>
|
