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