• Home
  • Line#
  • Scopes#
  • Navigate#
  • Raw
  • Download
1# Copyright (C) 2016 and later: Unicode, Inc. and others.
2# License & terms of use: http://www.unicode.org/copyright.html
3# Copyright (c) 2002-2016  International Business Machines Corporation and
4# others. All Rights Reserved.
5#
6#  file:  line_normal_cj.txt
7#
8#         Line Breaking Rules
9#         Implement default line breaking as defined by
10#         Unicode Standard Annex #14 Revision 37 for Unicode 9.0
11#         http://www.unicode.org/reports/tr14/
12#
13#         Includes extensions to the handling of emoji ZWJ sequences from
14#         https://goo.gl/cluFCn
15#
16#         tailored as noted in 2nd paragraph below.
17#
18#         TODO:  Rule LB 8 remains as it was in Unicode 5.2
19#         This is only because of a limitation of ICU break engine implementation,
20#         not because the older behavior is desirable.
21#
22#         This tailors the line break behavior to correspond to CSS
23#         line-break=normal (BCP47 -u-lb-normal) as defined for Chinese & Japanese.
24#         It sets characters of class CJ to behave like ID.
25#         In addition, it allows breaks:
26#         * before hyphens 2010 & 2013 (both BA) and 301C, 30A0 (both NS)
27
28#
29#  Character Classes defined by TR 14.
30#
31
32!!chain;
33!!quoted_literals_only;
34
35$AI = [:LineBreak =  Ambiguous:];
36$AL = [:LineBreak =  Alphabetic:];
37$BAX = [\u2010 \u2013];
38$BA = [[:LineBreak =  Break_After:] - $BAX];
39$BB = [:LineBreak =  Break_Before:];
40$BK = [:LineBreak =  Mandatory_Break:];
41$B2 = [:LineBreak =  Break_Both:];
42$CB = [:LineBreak =  Contingent_Break:];
43$CJ = [:LineBreak =  Conditional_Japanese_Starter:];
44$CL = [:LineBreak =  Close_Punctuation:];
45# $CM = [:LineBreak =  Combining_Mark:];
46$CP = [:LineBreak =  Close_Parenthesis:];
47$CR = [:LineBreak =  Carriage_Return:];
48$EB = [:LineBreak =  EB:];
49$EM = [:LineBreak =  EM:];
50$EX = [:LineBreak =  Exclamation:];
51$GL = [:LineBreak =  Glue:];
52$HL = [:LineBreak =  Hebrew_Letter:];
53$HY = [:LineBreak =  Hyphen:];
54$H2 = [:LineBreak =  H2:];
55$H3 = [:LineBreak =  H3:];
56# CSS Normal tailoring: CJ resolves to ID
57$ID = [[:LineBreak =  Ideographic:] $CJ];
58$IN = [:LineBreak =  Inseperable:];
59$IS = [:LineBreak =  Infix_Numeric:];
60$JL = [:LineBreak =  JL:];
61$JV = [:LineBreak =  JV:];
62$JT = [:LineBreak =  JT:];
63$LF = [:LineBreak =  Line_Feed:];
64$NL = [:LineBreak =  Next_Line:];
65$NSX = [\u301C \u30A0];
66$NS = [[:LineBreak =  Nonstarter:] - $NSX];
67$NU = [:LineBreak =  Numeric:];
68$OP = [:LineBreak =  Open_Punctuation:];
69$PO = [:LineBreak =  Postfix_Numeric:];
70$PR = [:LineBreak =  Prefix_Numeric:];
71$QU = [:LineBreak =  Quotation:];
72$RI = [:LineBreak =  Regional_Indicator:];
73$SA = [:LineBreak =  Complex_Context:];
74$SG = [:LineBreak =  Surrogate:];
75$SP = [:LineBreak =  Space:];
76$SY = [:LineBreak =  Break_Symbols:];
77$WJ = [:LineBreak =  Word_Joiner:];
78$XX = [:LineBreak =  Unknown:];
79$ZW = [:LineBreak =  ZWSpace:];
80$ZWJ = [:LineBreak = ZWJ:];
81
82$EmojiNRK = [[\p{Emoji}] - [$RI \u002a\u00230-9©®™〰〽]];
83# Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r13267
84$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];
85
86# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
87#         list it in the numerous rules that use CM.
88# By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
89
90$CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
91
92#   Dictionary character set, for triggering language-based break engines. Currently
93#   limited to LineBreak=Complex_Context (SA).
94
95$dictionary = [$SA];
96
97#
98#  Rule LB1.  By default, treat AI  (characters with ambiguous east Asian width),
99#                               SA  (Dictionary chars, excluding Mn and Mc)
100#                               SG  (Unpaired Surrogates)
101#                               XX  (Unknown, unassigned)
102#                         as $AL  (Alphabetic)
103#
104$ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]];
105
106
107## -------------------------------------------------
108
109!!forward;
110
111#
112# CAN_CM  is the set of characters that may combine with CM combining chars.
113#         Note that Linebreak UAX 14's concept of a combining char and the rules
114#         for what they can combine with are _very_ different from the rest of Unicode.
115#
116#         Note that $CM itself is left out of this set.  If CM is needed as a base
117#         it must be listed separately in the rule.
118#
119$CAN_CM  = [^$SP $BK $CR $LF $NL $ZW $CM];       # Bases that can   take CMs
120$CANT_CM = [ $SP $BK $CR $LF $NL $ZW $CM];       # Bases that can't take CMs
121
122#
123# AL_FOLLOW  set of chars that can unconditionally follow an AL
124#            Needed in rules where stand-alone $CM s are treated as AL.
125#
126$AL_FOLLOW      = [$BK $CR $LF $NL $ZW $SP $CL $CP $EX $HL $IS $SY $WJ $GL $OP $QU $BA $HY $NS $IN $NU $PR $PO $ALPlus];
127
128
129#
130#  Rule LB 4, 5    Mandatory (Hard) breaks.
131#
132$LB4Breaks    = [$BK $CR $LF $NL];
133$LB4NonBreaks = [^$BK $CR $LF $NL $CM];
134$CR $LF {100};
135
136#
137#  LB 6    Do not break before hard line breaks.
138#
139$LB4NonBreaks?  $LB4Breaks {100};    # LB 5  do not break before hard breaks.
140$CAN_CM $CM*    $LB4Breaks {100};
141^$CM+           $LB4Breaks {100};
142
143# LB 7         x SP
144#              x ZW
145$LB4NonBreaks [$SP $ZW];
146$CAN_CM $CM*  [$SP $ZW];
147^$CM+         [$SP $ZW];
148
149#
150# LB 8         Break after zero width space
151#              TODO:  ZW SP* <break>
152#              An engine change is required to write the reverse rule for this.
153#              For now, leave the Unicode 5.2 rule, ZW <break>
154#
155$LB8Breaks    = [$LB4Breaks $ZW];
156$LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
157
158# LB 8a        ZWJ x (ID | Extended_Pict | EmojiNRK)   Emoji ZWJ sequences.
159#
160$ZWJ ($ID | $Extended_Pict | $EmojiNRK);
161
162# LB 9     Combining marks.      X   $CM needs to behave like X, where X is not $SP, $BK $CR $LF $NL
163#                                $CM not covered by the above needs to behave like $AL
164#                                See definition of $CAN_CM.
165
166$CAN_CM $CM+;                   #  Stick together any combining sequences that don't match other rules.
167^$CM+;
168
169#
170# LB 11  Do not break before or after WORD JOINER & related characters.
171#
172$CAN_CM $CM*  $WJ;
173$LB8NonBreaks $WJ;
174^$CM+         $WJ;
175
176$WJ $CM* .;
177
178#
179# LB 12  Do not break after NBSP and related characters.
180#         GL  x
181#
182$GL $CM* .;
183
184#
185# LB 12a  Do not break before NBSP and related characters ...
186#            [^SP BA HY] x GL
187#
188[[$LB8NonBreaks] - [$SP $BA $BAX $HY]] $CM* $GL;
189^$CM+ $GL;
190
191
192
193#
194# LB 13   Don't break before ']' or '!' or ';' or '/', even after spaces.
195#
196$LB8NonBreaks $CL;
197$CAN_CM $CM*  $CL;
198^$CM+         $CL;              # by rule 10, stand-alone CM behaves as AL
199
200$LB8NonBreaks $CP;
201$CAN_CM $CM*  $CP;
202^$CM+         $CP;              # by rule 10, stand-alone CM behaves as AL
203
204$LB8NonBreaks $EX;
205$CAN_CM $CM*  $EX;
206^$CM+         $EX;              # by rule 10, stand-alone CM behaves as AL
207
208$LB8NonBreaks $IS;
209$CAN_CM $CM*  $IS;
210^$CM+         $IS;              # by rule 10, stand-alone CM behaves as AL
211
212$LB8NonBreaks $SY;
213$CAN_CM $CM*  $SY;
214^$CM+         $SY;              # by rule 10, stand-alone CM behaves as AL
215
216
217#
218# LB 14  Do not break after OP, even after spaces
219#
220$OP $CM* $SP* .;
221
222$OP $CM* $SP+ $CM+ $AL_FOLLOW?;    # by rule 10, stand-alone CM behaves as AL
223                                   # by rule 8, CM following a SP is stand-alone.
224
225# LB 15
226$QU $CM* $SP* $OP;
227
228# LB 16
229# Do not break between closing punctuation and $NS, even with intervening spaces
230# But DO allow a break between closing punctuation and $NSX, don't include it here
231($CL | $CP) $CM* $SP* $NS;
232
233# LB 17
234$B2 $CM* $SP* $B2;
235
236#
237# LB 18  Break after spaces.
238#
239$LB18NonBreaks = [$LB8NonBreaks - [$SP]];
240$LB18Breaks    = [$LB8Breaks $SP];
241
242
243# LB 19
244#         x QU
245$LB18NonBreaks $CM* $QU;
246^$CM+               $QU;
247
248#         QU  x
249$QU $CM* .;
250
251
252# LB 20
253#        <break>  $CB
254#        $CB   <break>
255
256$LB20NonBreaks = [$LB18NonBreaks - $CB];
257
258# LB 21        x   (BA | HY | NS)
259#           BB x
260#
261# DO allow breaks here before $BAXcm and $NSXcm, so don't include them
262$LB20NonBreaks $CM* ($BA | $HY | $NS);
263^$CM+ ($BA | $HY | $NS);
264
265$BB $CM* [^$CB];                                  #  $BB  x
266$BB $CM* $LB20NonBreaks;
267
268# LB 21a Don't break after Hebrew + Hyphen
269#   HL (HY | BA) x
270#
271$HL $CM* ($HY | $BA | $BAX) $CM* [^$CB]?;
272
273# LB 21b (forward) Don't break between SY and HL
274# (break between HL and SY already disallowed by LB 13 above)
275$SY $CM* $HL;
276
277# LB 22
278($ALPlus | $HL) $CM* $IN;
279^$CM+    $IN;     #  by rule 10, any otherwise unattached CM behaves as AL
280$EX $CM*    $IN;
281($ID | $EB | $EM) $CM*  $IN;
282$IN $CM*    $IN;
283$NU $CM*    $IN;
284
285
286# $LB 23
287#
288($ALPlus | $HL) $CM* $NU;
289^$CM+  $NU;       # Rule 10, any otherwise unattached CM behaves as AL
290$NU $CM* ($ALPlus | $HL);
291
292# LB 23a
293#
294$PR $CM* ($ID | $EB | $EM);
295($ID | $EB | $EM) $CM*  $PO;
296
297
298#
299# LB 24
300#
301($PR | $PO) $CM* ($ALPlus | $HL);
302($ALPlus | $HL) $CM* ($PR | $PO);
303^$CM+ ($PR | $PO);       # Rule 10, any otherwise unattached CM behaves as AL
304
305#
306# LB 25   Numbers.
307#
308(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
309    ($CM* ($CL | $CP))? ($CM* ($PR | $PO))?;
310
311# LB 26  Do not break a Korean syllable
312#
313$JL $CM* ($JL | $JV | $H2 | $H3);
314($JV | $H2) $CM* ($JV | $JT);
315($JT | $H3) $CM* $JT;
316
317# LB 27  Treat korean Syllable Block the same as ID  (don't break it)
318($JL | $JV | $JT | $H2 | $H3) $CM* $IN;
319($JL | $JV | $JT | $H2 | $H3) $CM* $PO;
320$PR $CM* ($JL | $JV | $JT | $H2 | $H3);
321
322
323# LB 28   Do not break between alphabetics
324#
325($ALPlus | $HL) $CM* ($ALPlus | $HL);
326^$CM+ ($ALPlus | $HL);      # The $CM+ is from rule 10, an unattached CM is treated as AL
327
328# LB 29
329$IS $CM* ($ALPlus | $HL);
330
331# LB 30
332($ALPlus | $HL | $NU) $CM* $OP;
333^$CM+ $OP;         # The $CM+ is from rule 10, an unattached CM is treated as AL.
334$CP $CM* ($ALPlus | $HL | $NU);
335
336# LB 30a  Do not break between regional indicators. Break after pairs of them.
337#         Tricky interaction with LB8a: ZWJ x ID
338$RI $CM* $RI                / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM] {eof}];
339$RI $CM* $RI $CM*  $ZWJ     / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM $ID $Extended_Pict $EmojiNRK] {eof}];
340$RI $CM* $RI $CM* [$CM-$ZWJ] / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM] {eof}];
341
342$RI $CM* $RI $CM* [$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS {eof}];
343$RI $CM* $RI $CM* $ZWJ ($ID | $Extended_Pict | $EmojiNRK);
344
345# LB 30b Do not break between an Emoji Base and an Emoji Modifier
346$EB $CM* $EM;
347
348# LB 31 Break everywhere else.
349#       Match a single code point if no other rule applies.
350.;
351
352## -------------------------------------------------
353
354!!safe_reverse;
355
356# LB 9
357^$CM+ [^$CM $BK $CR $LF $NL $ZW $SP];
358
359# LB 14
360$SP+ $CM* $OP;
361
362# LB 15
363$SP+ $CM* $QU;
364
365# LB 16
366$SP+ $CM* ($CL | $CP);
367
368# LB 17
369$SP+ $CM* $B2;
370
371# LB 21
372$CM* ($HY | $BA | $BAX) $CM* $HL;
373
374# LB 25
375($CM* ($IS | $SY))+ $CM* $NU;
376($CL | $CP) $CM* ($NU | $IS | $SY);
377
378#  LB 30
379($CM* $RI)+;
380
381# For dictionary-based break
382$dictionary $dictionary;
383