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 40 for Unicode 11.0
11#         http://www.unicode.org/reports/tr14/, with the following modification:
12#
13#         Boundaries between hyphens and following letters are suppressed when
14#         there is a boundary preceding the hyphen. See rule 20.9
15#
16#         This tailors the line break behavior to correspond to CSS
17#         line-break=normal (BCP47 -u-lb-normal) as defined for languages other than
18#         Chinese & Japanese.
19#         It sets characters of class CJ to behave like ID.
20
21#
22#  Character Classes defined by TR 14.
23#
24
25!!chain;
26!!quoted_literals_only;
27
28$AI = [:LineBreak =  Ambiguous:];
29$AL = [:LineBreak =  Alphabetic:];
30$BA = [:LineBreak =  Break_After:];
31$HH = [\u2010];     # \u2010 is HYPHEN, default line break is BA.
32$BB = [:LineBreak =  Break_Before:];
33$BK = [:LineBreak =  Mandatory_Break:];
34$B2 = [:LineBreak =  Break_Both:];
35$CB = [:LineBreak =  Contingent_Break:];
36$CJ = [:LineBreak =  Conditional_Japanese_Starter:];
37$CL = [:LineBreak =  Close_Punctuation:];
38# $CM = [:LineBreak =  Combining_Mark:];
39$CP = [:LineBreak =  Close_Parenthesis:];
40$CR = [:LineBreak =  Carriage_Return:];
41$EB = [:LineBreak =  EB:];
42$EM = [:LineBreak =  EM:];
43$EX = [:LineBreak =  Exclamation:];
44$GL = [:LineBreak =  Glue:];
45$HL = [:LineBreak =  Hebrew_Letter:];
46$HY = [:LineBreak =  Hyphen:];
47$H2 = [:LineBreak =  H2:];
48$H3 = [:LineBreak =  H3:];
49# CSS Normal tailoring: CJ resolves to ID
50$ID = [[:LineBreak =  Ideographic:] $CJ];
51$IN = [:LineBreak =  Inseperable:];
52$IS = [:LineBreak =  Infix_Numeric:];
53$JL = [:LineBreak =  JL:];
54$JV = [:LineBreak =  JV:];
55$JT = [:LineBreak =  JT:];
56$LF = [:LineBreak =  Line_Feed:];
57$NL = [:LineBreak =  Next_Line:];
58$NS = [:LineBreak =  Nonstarter:];
59$NU = [:LineBreak =  Numeric:];
60$OP = [:LineBreak =  Open_Punctuation:];
61$PO = [:LineBreak =  Postfix_Numeric:];
62$PR = [:LineBreak =  Prefix_Numeric:];
63$QU = [:LineBreak =  Quotation:];
64$RI = [:LineBreak =  Regional_Indicator:];
65$SA = [:LineBreak =  Complex_Context:];
66$SG = [:LineBreak =  Surrogate:];
67$SP = [:LineBreak =  Space:];
68$SY = [:LineBreak =  Break_Symbols:];
69$WJ = [:LineBreak =  Word_Joiner:];
70$XX = [:LineBreak =  Unknown:];
71$ZW = [:LineBreak =  ZWSpace:];
72$ZWJ = [:LineBreak = ZWJ:];
73
74# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
75#         list it in the numerous rules that use CM.
76# By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
77
78$CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
79
80#   Dictionary character set, for triggering language-based break engines. Currently
81#   limited to LineBreak=Complex_Context (SA).
82
83$dictionary = [$SA];
84
85#
86#  Rule LB1.  By default, treat AI  (characters with ambiguous east Asian width),
87#                               SA  (Dictionary chars, excluding Mn and Mc)
88#                               SG  (Unpaired Surrogates)
89#                               XX  (Unknown, unassigned)
90#                         as $AL  (Alphabetic)
91#
92$ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]];
93
94
95## -------------------------------------------------
96
97#
98# CAN_CM  is the set of characters that may combine with CM combining chars.
99#         Note that Linebreak UAX 14's concept of a combining char and the rules
100#         for what they can combine with are _very_ different from the rest of Unicode.
101#
102#         Note that $CM itself is left out of this set.  If CM is needed as a base
103#         it must be listed separately in the rule.
104#
105$CAN_CM  = [^$SP $BK $CR $LF $NL $ZW $CM];       # Bases that can   take CMs
106$CANT_CM = [ $SP $BK $CR $LF $NL $ZW $CM];       # Bases that can't take CMs
107
108#
109# AL_FOLLOW  set of chars that can unconditionally follow an AL
110#            Needed in rules where stand-alone $CM s are treated as AL.
111#
112$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 $ALPlus];
113
114
115#
116#  Rule LB 4, 5    Mandatory (Hard) breaks.
117#
118$LB4Breaks    = [$BK $CR $LF $NL];
119$LB4NonBreaks = [^$BK $CR $LF $NL $CM];
120$CR $LF {100};
121
122#
123#  LB 6    Do not break before hard line breaks.
124#
125$LB4NonBreaks?  $LB4Breaks {100};    # LB 5  do not break before hard breaks.
126$CAN_CM $CM*    $LB4Breaks {100};
127^$CM+           $LB4Breaks {100};
128
129# LB 7         x SP
130#              x ZW
131$LB4NonBreaks [$SP $ZW];
132$CAN_CM $CM*  [$SP $ZW];
133^$CM+         [$SP $ZW];
134
135#
136# LB 8         Break after zero width space
137#              ZW SP* ÷
138#
139$LB8Breaks    = [$LB4Breaks $ZW];
140$LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
141$ZW $SP* / [^$SP $ZW $LB4Breaks];
142
143# LB 8a        ZWJ x            Do not break Emoji ZWJ sequences.
144#
145$ZWJ [^$CM];
146
147# LB 9     Combining marks.      X   $CM needs to behave like X, where X is not $SP, $BK $CR $LF $NL
148#                                $CM not covered by the above needs to behave like $AL
149#                                See definition of $CAN_CM.
150
151$CAN_CM $CM+;                   #  Stick together any combining sequences that don't match other rules.
152^$CM+;
153
154#
155# LB 11  Do not break before or after WORD JOINER & related characters.
156#
157$CAN_CM $CM*  $WJ;
158$LB8NonBreaks $WJ;
159^$CM+         $WJ;
160
161$WJ $CM* .;
162
163#
164# LB 12  Do not break after NBSP and related characters.
165#         GL  x
166#
167$GL $CM* .;
168
169#
170# LB 12a  Do not break before NBSP and related characters ...
171#            [^SP BA HY] x GL
172#
173[[$LB8NonBreaks] - [$SP $BA $HY]] $CM* $GL;
174^$CM+ $GL;
175
176
177
178#
179# LB 13   Don't break before ']' or '!' or ';' or '/', even after spaces.
180#
181$LB8NonBreaks $CL;
182$CAN_CM $CM*  $CL;
183^$CM+         $CL;              # by rule 10, stand-alone CM behaves as AL
184
185$LB8NonBreaks $CP;
186$CAN_CM $CM*  $CP;
187^$CM+         $CP;              # by rule 10, stand-alone CM behaves as AL
188
189$LB8NonBreaks $EX;
190$CAN_CM $CM*  $EX;
191^$CM+         $EX;              # by rule 10, stand-alone CM behaves as AL
192
193$LB8NonBreaks $IS;
194$CAN_CM $CM*  $IS;
195^$CM+         $IS;              # by rule 10, stand-alone CM behaves as AL
196
197$LB8NonBreaks $SY;
198$CAN_CM $CM*  $SY;
199^$CM+         $SY;              # by rule 10, stand-alone CM behaves as AL
200
201
202#
203# LB 14  Do not break after OP, even after spaces
204#
205$OP $CM* $SP* .;
206
207$OP $CM* $SP+ $CM+ $AL_FOLLOW?;    # by rule 10, stand-alone CM behaves as AL
208                                   # by rule 8, CM following a SP is stand-alone.
209
210# LB 15
211$QU $CM* $SP* $OP;
212
213# LB 16
214($CL | $CP) $CM* $SP* $NS;
215
216# LB 17
217$B2 $CM* $SP* $B2;
218
219#
220# LB 18  Break after spaces.
221#
222$LB18NonBreaks = [$LB8NonBreaks - [$SP]];
223$LB18Breaks    = [$LB8Breaks $SP];
224
225
226# LB 19
227#         x QU
228$LB18NonBreaks $CM* $QU;
229^$CM+               $QU;
230
231#         QU  x
232$QU $CM* .;
233
234# LB 20
235#        <break>  $CB
236#        $CB   <break>
237#
238$LB20NonBreaks = [$LB18NonBreaks - $CB];
239
240# LB 20.09    Don't break between Hyphens and Letters when there is a break preceding the hyphen.
241#             Originally added as a Finnish tailoring, now promoted to default ICU behavior.
242#             Note: this is not default UAX-14 behaviour. See issue ICU-8151.
243#
244^($HY | $HH) $CM* $ALPlus;
245
246# LB 21        x   (BA | HY | NS)
247#           BB x
248#
249$LB20NonBreaks $CM* ($BA | $HY | $NS);
250
251
252^$CM+ ($BA | $HY | $NS);
253
254$BB $CM* [^$CB];                                  #  $BB  x
255$BB $CM* $LB20NonBreaks;
256
257# LB 21a Don't break after Hebrew + Hyphen
258#   HL (HY | BA) x
259#
260$HL $CM* ($HY | $BA) $CM* [^$CB]?;
261
262# LB 21b (forward) Don't break between SY and HL
263# (break between HL and SY already disallowed by LB 13 above)
264$SY $CM* $HL;
265
266# LB 22
267($ALPlus | $HL) $CM* $IN;
268^$CM+    $IN;     #  by rule 10, any otherwise unattached CM behaves as AL
269$EX $CM*    $IN;
270($ID | $EB | $EM) $CM*  $IN;
271$IN $CM*    $IN;
272$NU $CM*    $IN;
273
274
275# $LB 23
276#
277($ALPlus | $HL) $CM* $NU;
278^$CM+  $NU;       # Rule 10, any otherwise unattached CM behaves as AL
279$NU $CM* ($ALPlus | $HL);
280
281# LB 23a
282#
283$PR $CM* ($ID | $EB | $EM);
284($ID | $EB | $EM) $CM*  $PO;
285
286
287#
288# LB 24
289#
290($PR | $PO) $CM* ($ALPlus | $HL);
291($ALPlus | $HL) $CM* ($PR | $PO);
292^$CM+ ($PR | $PO);       # Rule 10, any otherwise unattached CM behaves as AL
293
294#
295# LB 25   Numbers.
296#
297(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
298    ($CM* ($CL | $CP))? ($CM* ($PR | $PO))?;
299
300# LB 26  Do not break a Korean syllable
301#
302$JL $CM* ($JL | $JV | $H2 | $H3);
303($JV | $H2) $CM* ($JV | $JT);
304($JT | $H3) $CM* $JT;
305
306# LB 27  Treat korean Syllable Block the same as ID  (don't break it)
307($JL | $JV | $JT | $H2 | $H3) $CM* $IN;
308($JL | $JV | $JT | $H2 | $H3) $CM* $PO;
309$PR $CM* ($JL | $JV | $JT | $H2 | $H3);
310
311
312# LB 28   Do not break between alphabetics
313#
314($ALPlus | $HL) $CM* ($ALPlus | $HL);
315^$CM+ ($ALPlus | $HL);      # The $CM+ is from rule 10, an unattached CM is treated as AL
316
317# LB 29
318$IS $CM* ($ALPlus | $HL);
319
320# LB 30
321($ALPlus | $HL | $NU) $CM* $OP;
322^$CM+ $OP;         # The $CM+ is from rule 10, an unattached CM is treated as AL.
323$CP $CM* ($ALPlus | $HL | $NU);
324
325# LB 30a  Do not break between regional indicators. Break after pairs of them.
326#         Tricky interaction with LB8a: ZWJ x .   together with ZWJ acting like a CM.
327$RI $CM* $RI                 / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM]];
328$RI $CM* $RI $CM* [$CM-$ZWJ] / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM]];
329$RI $CM* $RI $CM* [$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $ZWJ {eof}];
330# note: the preceding rule includes {eof} rather than having the last [set] term qualified with '?'
331#       because of the chain-out behavior difference. The rule must chain out only from the [set characters],
332#       not from the preceding $RI or $CM, which it would be able to do if the set were optional.
333
334# LB 30b Do not break between an Emoji Base and an Emoji Modifier
335$EB $CM* $EM;
336
337# LB 31 Break everywhere else.
338#       Match a single code point if no other rule applies.
339.;
340