• 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_fi.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#         tailored as noted in 2nd paragraph below.
13#
14#         Includes extensions to the handling of emoji ZWJ sequences from
15#         https://goo.gl/cluFCn
16#
17#         TODO:  Rule LB 8 remains as it was in Unicode 5.2
18#         This is only because of a limitation of ICU break engine implementation,
19#         not because the older behavior is desirable.
20#
21#         This tailors the line break behavior for Finnish, while otherwise behaving
22#         per UAX 14 which corresponds to CSS line-break=strict (BCP47 -u-lb-strict).
23#         It sets characters of class CJ to behave like NS.
24#
25#         This corresponds to CSS line-break=strict (BCP47 -u-lb-strict).
26#         It sets characters of class CJ to behave like 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$BA = [:LineBreak =  Break_After:];
38$HH = [\u2010];     # \u2010 is HYPHEN, default line break is BA.
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$H3 = [:LineBreak =  H3:];
56$ID = [:LineBreak =  Ideographic:];
57$IN = [:LineBreak =  Inseperable:];
58$IS = [:LineBreak =  Infix_Numeric:];
59$JL = [:LineBreak =  JL:];
60$JV = [:LineBreak =  JV:];
61$JT = [:LineBreak =  JT:];
62$LF = [:LineBreak =  Line_Feed:];
63$NL = [:LineBreak =  Next_Line:];
64# NS includes CJ for CSS strict line breaking.
65$NS = [[:LineBreak =  Nonstarter:] $CJ];
66$NU = [:LineBreak =  Numeric:];
67$OP = [:LineBreak =  Open_Punctuation:];
68$PO = [:LineBreak =  Postfix_Numeric:];
69$PR = [:LineBreak =  Prefix_Numeric:];
70$QU = [:LineBreak =  Quotation:];
71$RI = [:LineBreak =  Regional_Indicator:];
72$SA = [:LineBreak =  Complex_Context:];
73$SG = [:LineBreak =  Surrogate:];
74$SP = [:LineBreak =  Space:];
75$SY = [:LineBreak =  Break_Symbols:];
76$WJ = [:LineBreak =  Word_Joiner:];
77$XX = [:LineBreak =  Unknown:];
78$ZW = [:LineBreak =  ZWSpace:];
79$ZWJ = [:LineBreak = ZWJ:];
80
81$EmojiNRK = [[\p{Emoji}] - [$RI \u002a\u00230-9©®™〰〽]];
82# Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r13267
83$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];
84
85# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
86#         list it in the numerous rules that use CM.
87# By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
88
89$CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
90
91#   Dictionary character set, for triggering language-based break engines. Currently
92#   limited to LineBreak=Complex_Context (SA).
93
94$dictionary = [$SA];
95
96#
97#  Rule LB1.  By default, treat AI  (characters with ambiguous east Asian width),
98#                               SA  (Dictionary chars, excluding Mn and Mc)
99#                               SG  (Unpaired Surrogates)
100#                               XX  (Unknown, unassigned)
101#                         as $AL  (Alphabetic)
102#
103$ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]];
104
105
106## -------------------------------------------------
107
108!!forward;
109
110#
111# CAN_CM  is the set of characters that may combine with CM combining chars.
112#         Note that Linebreak UAX 14's concept of a combining char and the rules
113#         for what they can combine with are _very_ different from the rest of Unicode.
114#
115#         Note that $CM itself is left out of this set.  If CM is needed as a base
116#         it must be listed separately in the rule.
117#
118$CAN_CM  = [^$SP $BK $CR $LF $NL $ZW $CM];       # Bases that can   take CMs
119$CANT_CM = [ $SP $BK $CR $LF $NL $ZW $CM];       # Bases that can't take CMs
120
121#
122# AL_FOLLOW  set of chars that can unconditionally follow an AL
123#            Needed in rules where stand-alone $CM s are treated as AL.
124#
125$AL_FOLLOW      = [$BK $CR $LF $NL $ZW $SP $CL $CP $EX $HL $IS $SY $WJ $GL $OP $QU $BA $HH $HY $NS $IN $NU $PR $PO $ALPlus];
126
127
128#
129#  Rule LB 4, 5    Mandatory (Hard) breaks.
130#
131$LB4Breaks    = [$BK $CR $LF $NL];
132$LB4NonBreaks = [^$BK $CR $LF $NL $CM];
133$CR $LF {100};
134
135#
136#  LB 6    Do not break before hard line breaks.
137#
138$LB4NonBreaks?  $LB4Breaks {100};    # LB 5  do not break before hard breaks.
139$CAN_CM $CM*    $LB4Breaks {100};
140^$CM+           $LB4Breaks {100};
141
142# LB 7         x SP
143#              x ZW
144$LB4NonBreaks [$SP $ZW];
145$CAN_CM $CM*  [$SP $ZW];
146^$CM+         [$SP $ZW];
147
148#
149# LB 8         Break after zero width space
150#              TODO:  ZW SP* <break>
151#              An engine change is required to write the reverse rule for this.
152#              For now, leave the Unicode 5.2 rule, ZW <break>
153#
154$LB8Breaks    = [$LB4Breaks $ZW];
155$LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
156
157# LB 8a        ZWJ x (ID | Extended_Pict | EmojiNRK)   Emoji ZWJ sequences.
158#
159$ZWJ ($ID | $Extended_Pict | $EmojiNRK);
160
161# LB 9     Combining marks.      X   $CM needs to behave like X, where X is not $SP, $BK $CR $LF $NL
162#                                $CM not covered by the above needs to behave like $AL
163#                                See definition of $CAN_CM.
164
165$CAN_CM $CM+;                   #  Stick together any combining sequences that don't match other rules.
166^$CM+;
167
168#
169# LB 11  Do not break before or after WORD JOINER & related characters.
170#
171$CAN_CM $CM*  $WJ;
172$LB8NonBreaks $WJ;
173^$CM+         $WJ;
174
175$WJ $CM* .;
176
177#
178# LB 12  Do not break after NBSP and related characters.
179#         GL  x
180#
181$GL $CM* .;
182
183#
184# LB 12a  Do not break before NBSP and related characters ...
185#            [^SP BA HY] x GL
186#
187[[$LB8NonBreaks] - [$SP $BA $HH $HY]] $CM* $GL;
188^$CM+ $GL;
189
190
191
192#
193# LB 13   Don't break before ']' or '!' or ';' or '/', even after spaces.
194#
195$LB8NonBreaks $CL;
196$CAN_CM $CM*  $CL;
197^$CM+         $CL;              # by rule 10, stand-alone CM behaves as AL
198
199$LB8NonBreaks $CP;
200$CAN_CM $CM*  $CP;
201^$CM+         $CP;              # by rule 10, stand-alone CM behaves as AL
202
203$LB8NonBreaks $EX;
204$CAN_CM $CM*  $EX;
205^$CM+         $EX;              # by rule 10, stand-alone CM behaves as AL
206
207$LB8NonBreaks $IS;
208$CAN_CM $CM*  $IS;
209^$CM+         $IS;              # by rule 10, stand-alone CM behaves as AL
210
211$LB8NonBreaks $SY;
212$CAN_CM $CM*  $SY;
213^$CM+         $SY;              # by rule 10, stand-alone CM behaves as AL
214
215
216#
217# LB 14  Do not break after OP, even after spaces
218#
219$OP $CM* $SP* .;
220
221$OP $CM* $SP+ $CM+ $AL_FOLLOW?;    # by rule 10, stand-alone CM behaves as AL
222                                   # by rule 8, CM following a SP is stand-alone.
223
224# LB 15
225$QU $CM* $SP* $OP;
226
227# LB 16
228($CL | $CP) $CM* $SP* $NS;
229
230# LB 17
231$B2 $CM* $SP* $B2;
232
233#
234# LB 18  Break after spaces.
235#
236$LB18NonBreaks = [$LB8NonBreaks - [$SP]];
237$LB18Breaks    = [$LB8Breaks $SP];
238
239
240# LB 19
241#         x QU
242$LB18NonBreaks $CM* $QU;
243^$CM+               $QU;
244
245#         QU  x
246$QU $CM* .;
247
248
249# LB 20
250#        <break>  $CB
251#        $CB   <break>
252
253$LB20NonBreaks = [$LB18NonBreaks - $CB];
254
255# LB 20.09 added rule for Finnish tailoring
256# LB 21        x   (BA | HY | NS)
257#           BB x
258#
259$LB20NonBreaks $CM* ($BA | $HH | $HY | $NS) $CM* / $AL;
260$LB20NonBreaks $CM* ($BA | $HH | $HY | $NS);
261($HY | $HH) $AL;
262^$CM+ ($BA | $HY | $HH | $NS);
263
264$BB $CM* [^$CB];                                  #  $BB  x
265$BB $CM* $LB20NonBreaks;
266
267# LB 21a Don't break after Hebrew + Hyphen
268#   HL (HY | BA) x
269#
270$HL $CM* ($HY | $BA | $HH) $CM* [^$CB]?;
271
272# LB 21b (forward) Don't break between SY and HL
273# (break between HL and SY already disallowed by LB 13 above)
274$SY $CM* $HL;
275
276# LB 22
277($ALPlus | $HL) $CM* $IN;
278^$CM+    $IN;     #  by rule 10, any otherwise unattached CM behaves as AL
279$EX $CM*    $IN;
280($ID | $EB | $EM) $CM*  $IN;
281$IN $CM*    $IN;
282$NU $CM*    $IN;
283
284
285# $LB 23
286#
287($ALPlus | $HL) $CM* $NU;
288^$CM+  $NU;       # Rule 10, any otherwise unattached CM behaves as AL
289$NU $CM* ($ALPlus | $HL);
290
291# LB 23a
292#
293$PR $CM* ($ID | $EB | $EM);
294($ID | $EB | $EM) $CM*  $PO;
295
296
297#
298# LB 24
299#
300($PR | $PO) $CM* ($ALPlus | $HL);
301($ALPlus | $HL) $CM* ($PR | $PO);
302^$CM+ ($PR | $PO);       # Rule 10, any otherwise unattached CM behaves as AL
303
304#
305# LB 25   Numbers.
306#
307(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
308    ($CM* ($CL | $CP))? ($CM* ($PR | $PO))?;
309
310# LB 26  Do not break a Korean syllable
311#
312$JL $CM* ($JL | $JV | $H2 | $H3);
313($JV | $H2) $CM* ($JV | $JT);
314($JT | $H3) $CM* $JT;
315
316# LB 27  Treat korean Syllable Block the same as ID  (don't break it)
317($JL | $JV | $JT | $H2 | $H3) $CM* $IN;
318($JL | $JV | $JT | $H2 | $H3) $CM* $PO;
319$PR $CM* ($JL | $JV | $JT | $H2 | $H3);
320
321
322# LB 28   Do not break between alphabetics
323#
324($ALPlus | $HL) $CM* ($ALPlus | $HL);
325^$CM+ ($ALPlus | $HL);      # The $CM+ is from rule 10, an unattached CM is treated as AL
326
327# LB 29
328$IS $CM* ($ALPlus | $HL);
329
330# LB 30
331($ALPlus | $HL | $NU) $CM* $OP;
332^$CM+ $OP;         # The $CM+ is from rule 10, an unattached CM is treated as AL.
333$CP $CM* ($ALPlus | $HL | $NU);
334
335# LB 30a  Do not break between regional indicators. Break after pairs of them.
336#         Tricky interaction with LB8a: ZWJ x ID
337$RI $CM* $RI                / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM] {eof}];
338$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 $EmojiNRK] {eof}];
339$RI $CM* $RI $CM* [$CM-$ZWJ] / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM] {eof}];
340
341$RI $CM* $RI $CM* [$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS {eof}];
342$RI $CM* $RI $CM* $ZWJ ($ID | $Extended_Pict | $EmojiNRK);
343
344# LB 30b Do not break between an Emoji Base and an Emoji Modifier
345$EB $CM* $EM;
346
347# LB 31 Break everywhere else.
348#       Match a single code point if no other rule applies.
349.;
350
351## -------------------------------------------------
352
353!!safe_reverse;
354
355# LB 9
356^$CM+ [^$CM $BK $CR $LF $NL $ZW $SP];
357
358# LB 14
359$SP+ $CM* $OP;
360
361# LB 15
362$SP+ $CM* $QU;
363
364# LB 16
365$SP+ $CM* ($CL | $CP);
366
367# LB 17
368$SP+ $CM* $B2;
369
370# LB 21
371$CM* ($HY | $BA | $HH) $CM* $HL;
372
373# LB 25
374($CM* ($IS | $SY))+ $CM* $NU;
375($CL | $CP) $CM* ($NU | $IS | $SY);
376
377#  LB 30
378($CM* $RI)+;
379
380# For dictionary-based break
381$dictionary $dictionary;
382