icuSources/data/brkitr/rules/line_loose.txt

   1 # Copyright (C) 2016 and later: Unicode, Inc. and others.
   2 # License & terms of use: http://www.unicode.org/copyright.html
   3 #
   4 # Copyright (c) 2002-2016  International Business Machines Corporation and
   5 # others. All Rights Reserved.
   6 #
   7 #  file:  line_loose.txt
   8 #
   9 #         Line Breaking Rules
  10 #         Implement default line breaking as defined by
  11 #         Unicode Standard Annex #14 Revision 44 for Unicode 13.0
  12 #         http://www.unicode.org/reports/tr14/, with the following modification:
  13 #
  14 #         Boundaries between hyphens and following letters are suppressed when
  15 #         there is a boundary preceding the hyphen. See rule 20.9
  16 #
  17 #         This tailors the line break behavior to correspond to CSS
  18 #         line-break=loose (BCP47 -u-lb-loose) as defined for languages other than
  19 #         Chinese & Japanese.
  20 #         It sets characters of class CJ to behave like ID.
  21 #         In addition, it allows breaks:
  22 #         * before iteration marks 3005, 303B, 309D, 309E, 30FD, 30FE (all NS)
  23 #         * between characters of LineBreak class IN
  24
  25 #
  26 #  Character Classes defined by TR 14.
  27 #
  28
  29 !!chain;
  30 !!quoted_literals_only;
  31
  32 $AI = [:LineBreak =  Ambiguous:];
  33 $AL = [:LineBreak =  Alphabetic:];
  34 $BA = [:LineBreak =  Break_After:];
  35 $HH = [\u2010];     # \u2010 is HYPHEN, default line break is BA.
  36 $BB = [:LineBreak =  Break_Before:];
  37 $BK = [:LineBreak =  Mandatory_Break:];
  38 $B2 = [:LineBreak =  Break_Both:];
  39 $CB = [:LineBreak =  Contingent_Break:];
  40 $CJ = [:LineBreak =  Conditional_Japanese_Starter:];
  41 $CL = [:LineBreak =  Close_Punctuation:];
  42 # $CM = [:LineBreak =  Combining_Mark:];
  43 $CP = [:LineBreak =  Close_Parenthesis:];
  44 $CR = [:LineBreak =  Carriage_Return:];
  45 $EB = [:LineBreak =  EB:];
  46 $EM = [:LineBreak =  EM:];
  47 $EX = [:LineBreak =  Exclamation:];
  48 $GL = [:LineBreak =  Glue:];
  49 $HL = [:LineBreak =  Hebrew_Letter:];
  50 $HY = [:LineBreak =  Hyphen:];
  51 $H2 = [:LineBreak =  H2:];
  52 $H3 = [:LineBreak =  H3:];
  53 # CSS Loose tailoring: CJ resolves to ID
  54 $ID = [[:LineBreak =  Ideographic:] $CJ];
  55 $IN = [:LineBreak =  Inseperable:];
  56 $IS = [:LineBreak =  Infix_Numeric:];
  57 $JL = [:LineBreak =  JL:];
  58 $JV = [:LineBreak =  JV:];
  59 $JT = [:LineBreak =  JT:];
  60 $LF = [:LineBreak =  Line_Feed:];
  61 $NL = [:LineBreak =  Next_Line:];
  62 $NSX = [\u3005 \u303B \u309D \u309E \u30FD \u30FE];
  63 $NS = [[:LineBreak =  Nonstarter:] - $NSX];
  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 # OP30 and CP30 are variants of OP and CP that appear in-line in rule LB30 from UAX 14,
  80 # without a formal name. Because ICU rules require multiple uses of the expressions,
  81 # give them a single definition with a name
  82
  83 $OP30 = [$OP - [\p{ea=F}\p{ea=W}\p{ea=H}]];
  84 $CP30 = [$CP - [\p{ea=F}\p{ea=W}\p{ea=H}]];
  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 $CMX = [[$CM] - [$ZWJ]];
  92
  93 #   Dictionary character set, for triggering language-based break engines. Currently
  94 #   limited to LineBreak=Complex_Context (SA).
  95
  96 $dictionary = [$SA];
  97
  98 #
  99 #  Rule LB1.  By default, treat AI  (characters with ambiguous east Asian width),
 100 #                               SA  (Dictionary chars, excluding Mn and Mc)
 101 #                               SG  (Unpaired Surrogates)
 102 #                               XX  (Unknown, unassigned)
 103 #                         as $AL  (Alphabetic)
 104 #
 105 $ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]];
 106
 107
 108 ## -------------------------------------------------
 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 $OP30 $QU $BA $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 #              ZW SP* ÷
 151 #
 152 $LB8Breaks    = [$LB4Breaks $ZW];
 153 $LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
 154 $ZW $SP* / [^$SP $ZW $LB4Breaks];
 155
 156 # LB 8a        ZWJ x            Do not break Emoji ZWJ sequences.
 157 #
 158 $ZWJ [^$CM];
 159
 160 # LB 9     Combining marks.      X   $CM needs to behave like X, where X is not $SP, $BK $CR $LF $NL
 161 #                                $CM not covered by the above needs to behave like $AL
 162 #                                See definition of $CAN_CM.
 163
 164 $CAN_CM $CM+;                   #  Stick together any combining sequences that don't match other rules.
 165 ^$CM+;
 166
 167 #
 168 # LB 11  Do not break before or after WORD JOINER & related characters.
 169 #
 170 $CAN_CM $CM*  $WJ;
 171 $LB8NonBreaks $WJ;
 172 ^$CM+         $WJ;
 173
 174 $WJ $CM* .;
 175
 176 #
 177 # LB 12  Do not break after NBSP and related characters.
 178 #         GL  x
 179 #
 180 $GL $CM* .;
 181
 182 #
 183 # LB 12a  Do not break before NBSP and related characters ...
 184 #            [^SP BA HY] x GL
 185 #
 186 [[$LB8NonBreaks] - [$SP $BA $HY]] $CM* $GL;
 187 ^$CM+ $GL;
 188
 189
 190
 191
 192 # LB 13   Don't break before ']' or '!' or or '/', even after spaces.
 193 #
 194 $LB8NonBreaks $CL;
 195 $CAN_CM $CM*  $CL;
 196 ^$CM+         $CL;              # by rule 10, stand-alone CM behaves as AL
 197
 198 $LB8NonBreaks $CP;
 199 $CAN_CM $CM*  $CP;
 200 ^$CM+         $CP;              # by rule 10, stand-alone CM behaves as AL
 201
 202 $LB8NonBreaks $EX;
 203 $CAN_CM $CM*  $EX;
 204 ^$CM+         $EX;              # by rule 10, stand-alone CM behaves as AL
 205
 206 $LB8NonBreaks $SY;
 207 $CAN_CM $CM*  $SY;
 208 ^$CM+         $SY;              # by rule 10, stand-alone CM behaves as AL
 209
 210
 211 #
 212 # LB 14  Do not break after OP, even after spaces
 213 #        Note subtle interaction with "SP IS /" rules in LB14a.
 214 #        This rule consumes the SP, chaining happens on the IS, effectivley overriding the  SP IS rules,
 215 #        which is the desired behavior.
 216 #
 217 $OP $CM* $SP* .;
 218
 219 $OP $CM* $SP+ $CM+ $AL_FOLLOW?;    # by rule 10, stand-alone CM behaves as AL
 220                                    # by rule 8, CM following a SP is stand-alone.
 221
 222
 223 # LB 14a Force a break before start of a number with a leading decimal pt, e.g. " .23"
 224 #        Note: would be simpler to express as "$SP / $IS $CM* $NU;", but ICU rules have limitations.
 225 #        See issue ICU-20303
 226
 227
 228 $CanFollowIS = [$BK $CR $LF $NL $SP $ZW $WJ $GL $CL $CP $EX $IS $SY $QU $BA $HY $NS $ALPlus $HL $IN];
 229 $SP $IS           / [^ $CanFollowIS $NU $CM];
 230 $SP $IS $CM* $CMX / [^ $CanFollowIS $NU $CM];
 231
 232 #
 233 # LB 14b Do not break before numeric separators (IS), even after spaces.
 234
 235 [$LB8NonBreaks - $SP] $IS;
 236 $SP $IS $CM* [$CanFollowIS {eof}];
 237 $SP $IS $CM* $ZWJ [^$CM $NU];
 238
 239 $CAN_CM $CM*  $IS;
 240 ^$CM+         $IS;              # by rule 10, stand-alone CM behaves as AL
 241
 242
 243 # LB 15
 244 $QU $CM* $SP* $OP;
 245
 246 # LB 16
 247 # Do not break between closing punctuation and $NS, even with intervening spaces
 248 # But DO allow a break between closing punctuation and $NSX, don't include it here
 249 ($CL | $CP) $CM* $SP* $NS;
 250
 251 # LB 17
 252 $B2 $CM* $SP* $B2;
 253
 254 #
 255 # LB 18  Break after spaces.
 256 #
 257 $LB18NonBreaks = [$LB8NonBreaks - [$SP]];
 258 $LB18Breaks    = [$LB8Breaks $SP];
 259
 260
 261 # LB 19
 262 #         x QU
 263 $LB18NonBreaks $CM* $QU;
 264 ^$CM+               $QU;
 265
 266 #         QU  x
 267 $QU $CM* .;
 268
 269 # LB 20
 270 #        <break>  $CB
 271 #        $CB   <break>
 272 #
 273 $LB20NonBreaks = [$LB18NonBreaks - $CB];
 274
 275 # LB 20.09    Don't break between Hyphens and Letters when there is a break preceding the hyphen.
 276 #             Originally added as a Finnish tailoring, now promoted to default ICU behavior.
 277 #             Note: this is not default UAX-14 behaviour. See issue ICU-8151.
 278 #
 279 ^($HY | $HH) $CM* $ALPlus;
 280
 281 # LB 21        x   (BA | HY | NS)
 282 #           BB x
 283 #
 284 # DO allow breaks here before NSX, so don't include it
 285 $LB20NonBreaks $CM* ($BA | $HY | $NS);
 286
 287
 288 ^$CM+ ($BA | $HY | $NS);
 289
 290 $BB $CM* [^$CB];                                  #  $BB  x
 291 $BB $CM* $LB20NonBreaks;
 292
 293 # LB 21a Don't break after Hebrew + Hyphen
 294 #   HL (HY | BA) x
 295 #
 296 $HL $CM* ($HY | $BA) $CM* [^$CB]?;
 297
 298 # LB 21b (forward) Don't break between SY and HL
 299 # (break between HL and SY already disallowed by LB 13 above)
 300 $SY $CM* $HL;
 301
 302
 303 # LB 22  Do not break before ellipses
 304 #
 305 [$LB20NonBreaks - $IN] $CM*    $IN;    # line_loose tailoring
 306 ^$CM+ $IN;
 307
 308
 309 # LB 23
 310 #
 311 ($ALPlus | $HL) $CM* $NU;
 312 ^$CM+  $NU;       # Rule 10, any otherwise unattached CM behaves as AL
 313 $NU $CM* ($ALPlus | $HL);
 314
 315 # LB 23a
 316 #
 317 $PR $CM* ($ID | $EB | $EM);
 318 ($ID | $EB | $EM) $CM*  $PO;
 319
 320
 321 #
 322 # LB 24
 323 #
 324 ($PR | $PO) $CM* ($ALPlus | $HL);
 325 ($ALPlus | $HL) $CM* ($PR | $PO);
 326 ^$CM+ ($PR | $PO);       # Rule 10, any otherwise unattached CM behaves as AL
 327
 328 #
 329 # LB 25   Numbers.
 330 #
 331 (($PR | $PO) $CM*)? (($OP | $HY) $CM*)? ($IS $CM*)? $NU ($CM* ($NU | $SY | $IS))*
 332     ($CM* ($CL | $CP))? ($CM* ($PR | $PO))?;
 333
 334 # LB 26  Do not break a Korean syllable
 335 #
 336 $JL $CM* ($JL | $JV | $H2 | $H3);
 337 ($JV | $H2) $CM* ($JV | $JT);
 338 ($JT | $H3) $CM* $JT;
 339
 340 # LB 27  Treat korean Syllable Block the same as ID  (don't break it)
 341 ($JL | $JV | $JT | $H2 | $H3) $CM* $IN;
 342 ($JL | $JV | $JT | $H2 | $H3) $CM* $PO;
 343 $PR $CM* ($JL | $JV | $JT | $H2 | $H3);
 344
 345
 346 # LB 28   Do not break between alphabetics
 347 #
 348 ($ALPlus | $HL) $CM* ($ALPlus | $HL);
 349 ^$CM+ ($ALPlus | $HL);      # The $CM+ is from rule 10, an unattached CM is treated as AL
 350
 351 # LB 29
 352 $IS $CM* ($ALPlus | $HL);
 353
 354 # LB 30
 355 ($ALPlus | $HL | $NU) $CM* $OP30;
 356 ^$CM+ $OP30;         # The $CM+ is from rule 10, an unattached CM is treated as AL.
 357 $CP30 $CM* ($ALPlus | $HL | $NU);
 358
 359 # LB 30a  Do not break between regional indicators. Break after pairs of them.
 360 #         Tricky interaction with LB8a: ZWJ x .   together with ZWJ acting like a CM.
 361 $RI $CM* $RI                 / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $IN $CM]];
 362 $RI $CM* $RI $CM* [$CM-$ZWJ] / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $IN $CM]];
 363 $RI $CM* $RI $CM* [$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $IN $ZWJ {eof}];
 364 # note: the preceding rule includes {eof} rather than having the last [set] term qualified with '?'
 365 #       because of the chain-out behavior difference. The rule must chain out only from the [set characters],
 366 #       not from the preceding $RI or $CM, which it would be able to do if the set were optional.
 367
 368 # LB 30b Do not break between an Emoji Base and an Emoji Modifier
 369 $EB $CM* $EM;
 370
 371 # LB 31 Break everywhere else.
 372 #       Match a single code point if no other rule applies.
 373 .;