icuSources/data/brkitr/rules/line_loose_fi.txt

   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_loose_fi.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/
  12 #         tailored as noted in 3rd paragraph below.
  13 #
  14 #         TODO:  Rule LB 8 remains as it was in Unicode 5.2
  15 #         This is only because of a limitation of ICU break engine implementation,
  16 #         not because the older behavior is desirable.
  17 #
  18 #         This tailors the line break behavior both for Finnish and to correpond to CSS
  19 #         line-break=loose (BCP47 -u-lb-loose) as defined for languages other than
  20 #         Chinese & Japanese.
  21 #         It sets characters of class CJ to behave like ID.
  22 #         In addition, it allows breaks before 3005, 303B, 309D, 309E, 30FD, 30FE (all NS).
  23 #
  24 #  Character Classes defined by TR 14.
  25 #
  26
  27 !!chain;
  28 !!quoted_literals_only;
  29
  30 $AI = [:LineBreak =  Ambiguous:];
  31 $AL = [:LineBreak =  Alphabetic:];
  32 $BA = [:LineBreak =  Break_After:];
  33 $HH = [\u2010];     # \u2010 is HYPHEN, default line break is BA.
  34 $BB = [:LineBreak =  Break_Before:];
  35 $BK = [:LineBreak =  Mandatory_Break:];
  36 $B2 = [:LineBreak =  Break_Both:];
  37 $CB = [:LineBreak =  Contingent_Break:];
  38 $CJ = [:LineBreak =  Conditional_Japanese_Starter:];
  39 $CL = [:LineBreak =  Close_Punctuation:];
  40 # $CM = [:LineBreak =  Combining_Mark:];
  41 $CP = [:LineBreak =  Close_Parenthesis:];
  42 $CR = [:LineBreak =  Carriage_Return:];
  43 $EB = [[:LineBreak =  EB:] \U0001F46A-\U0001F46D\U0001F46F\U0001F91D\U0001F93C];
  44 $EM = [:LineBreak =  EM:];
  45 $EX = [:LineBreak =  Exclamation:];
  46 $GL = [:LineBreak =  Glue:];
  47 $HL = [:LineBreak =  Hebrew_Letter:];
  48 $HY = [:LineBreak =  Hyphen:];
  49 $H2 = [:LineBreak =  H2:];
  50 $H3 = [:LineBreak =  H3:];
  51 # CSS Loose tailoring: CJ resolves to ID
  52 $ID = [[:LineBreak =  Ideographic:] $CJ];
  53 $IN = [:LineBreak =  Inseperable:];
  54 $IS = [:LineBreak =  Infix_Numeric:];
  55 $JL = [:LineBreak =  JL:];
  56 $JV = [:LineBreak =  JV:];
  57 $JT = [:LineBreak =  JT:];
  58 $LF = [:LineBreak =  Line_Feed:];
  59 $NL = [:LineBreak =  Next_Line:];
  60 $NSX = [\u3005 \u303B \u309D \u309E \u30FD \u30FE];
  61 $NS = [[:LineBreak =  Nonstarter:] - $NSX];
  62 $NU = [:LineBreak =  Numeric:];
  63 $OP = [:LineBreak =  Open_Punctuation:];
  64 $PO = [:LineBreak =  Postfix_Numeric:];
  65 $PR = [:LineBreak =  Prefix_Numeric:];
  66 $QU = [:LineBreak =  Quotation:];
  67 $RI = [:LineBreak =  Regional_Indicator:];
  68 $SA = [:LineBreak =  Complex_Context:];
  69 $SG = [:LineBreak =  Surrogate:];
  70 $SP = [:LineBreak =  Space:];
  71 $SY = [:LineBreak =  Break_Symbols:];
  72 $WJ = [:LineBreak =  Word_Joiner:];
  73 $XX = [:LineBreak =  Unknown:];
  74 $ZW = [:LineBreak =  ZWSpace:];
  75 $ZWJ = [:LineBreak = ZWJ:];
  76
  77 # By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
  78 #         list it in the numerous rules that use CM.
  79 # By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
  80
  81 $CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
  82
  83 #   Dictionary character set, for triggering language-based break engines. Currently
  84 #   limited to LineBreak=Complex_Context (SA).
  85
  86 $dictionary = [$SA];
  87
  88 #
  89 #  Rule LB1.  By default, treat AI  (characters with ambiguous east Asian width),
  90 #                               SA  (Dictionary chars, excluding Mn and Mc)
  91 #                               SG  (Unpaired Surrogates)
  92 #                               XX  (Unknown, unassigned)
  93 #                         as $AL  (Alphabetic)
  94 #
  95 $ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]];
  96
  97
  98 ## -------------------------------------------------
  99
 100 #
 101 # CAN_CM  is the set of characters that may combine with CM combining chars.
 102 #         Note that Linebreak UAX 14's concept of a combining char and the rules
 103 #         for what they can combine with are _very_ different from the rest of Unicode.
 104 #
 105 #         Note that $CM itself is left out of this set.  If CM is needed as a base
 106 #         it must be listed separately in the rule.
 107 #
 108 $CAN_CM  = [^$SP $BK $CR $LF $NL $ZW $CM];       # Bases that can   take CMs
 109 $CANT_CM = [ $SP $BK $CR $LF $NL $ZW $CM];       # Bases that can't take CMs
 110
 111 #
 112 # AL_FOLLOW  set of chars that can unconditionally follow an AL
 113 #            Needed in rules where stand-alone $CM s are treated as AL.
 114 #
 115 $AL_FOLLOW      = [$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];
 116
 117
 118 #
 119 #  Rule LB 4, 5    Mandatory (Hard) breaks.
 120 #
 121 $LB4Breaks    = [$BK $CR $LF $NL];
 122 $LB4NonBreaks = [^$BK $CR $LF $NL $CM];
 123 $CR $LF {100};
 124
 125 #
 126 #  LB 6    Do not break before hard line breaks.
 127 #
 128 $LB4NonBreaks?  $LB4Breaks {100};    # LB 5  do not break before hard breaks.
 129 $CAN_CM $CM*    $LB4Breaks {100};
 130 ^$CM+           $LB4Breaks {100};
 131
 132 # LB 7         x SP
 133 #              x ZW
 134 $LB4NonBreaks [$SP $ZW];
 135 $CAN_CM $CM*  [$SP $ZW];
 136 ^$CM+         [$SP $ZW];
 137
 138 #
 139 # LB 8         Break after zero width space
 140 #              TODO:  ZW SP* <break>
 141 #              An engine change is required to write the reverse rule for this.
 142 #              For now, leave the Unicode 5.2 rule, ZW <break>
 143 #
 144 $LB8Breaks    = [$LB4Breaks $ZW];
 145 $LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
 146
 147 # LB 8a        ZWJ x            Do not break Emoji ZWJ sequences.
 148 #
 149 $ZWJ [^$CM];
 150
 151 # LB 9     Combining marks.      X   $CM needs to behave like X, where X is not $SP, $BK $CR $LF $NL
 152 #                                $CM not covered by the above needs to behave like $AL
 153 #                                See definition of $CAN_CM.
 154
 155 $CAN_CM $CM+;                   #  Stick together any combining sequences that don't match other rules.
 156 ^$CM+;
 157
 158 #
 159 # LB 11  Do not break before or after WORD JOINER & related characters.
 160 #
 161 $CAN_CM $CM*  $WJ;
 162 $LB8NonBreaks $WJ;
 163 ^$CM+         $WJ;
 164
 165 $WJ $CM* .;
 166
 167 #
 168 # LB 12  Do not break after NBSP and related characters.
 169 #         GL  x
 170 #
 171 $GL $CM* .;
 172
 173 #
 174 # LB 12a  Do not break before NBSP and related characters ...
 175 #            [^SP BA HY] x GL
 176 #
 177 [[$LB8NonBreaks] - [$SP $BA $HH $HY]] $CM* $GL;
 178 ^$CM+ $GL;
 179
 180
 181
 182 #
 183 # LB 13   Don't break before ']' or '!' or ';' or '/', even after spaces.
 184 #
 185 $LB8NonBreaks $CL;
 186 $CAN_CM $CM*  $CL;
 187 ^$CM+         $CL;              # by rule 10, stand-alone CM behaves as AL
 188
 189 $LB8NonBreaks $CP;
 190 $CAN_CM $CM*  $CP;
 191 ^$CM+         $CP;              # by rule 10, stand-alone CM behaves as AL
 192
 193 $LB8NonBreaks $EX;
 194 $CAN_CM $CM*  $EX;
 195 ^$CM+         $EX;              # by rule 10, stand-alone CM behaves as AL
 196
 197 $LB8NonBreaks $IS;
 198 $CAN_CM $CM*  $IS;
 199 ^$CM+         $IS;              # by rule 10, stand-alone CM behaves as AL
 200
 201 $LB8NonBreaks $SY;
 202 $CAN_CM $CM*  $SY;
 203 ^$CM+         $SY;              # by rule 10, stand-alone CM behaves as AL
 204
 205
 206 #
 207 # LB 14  Do not break after OP, even after spaces
 208 #
 209 $OP $CM* $SP* .;
 210
 211 $OP $CM* $SP+ $CM+ $AL_FOLLOW?;    # by rule 10, stand-alone CM behaves as AL
 212                                    # by rule 8, CM following a SP is stand-alone.
 213
 214 # LB 15
 215 $QU $CM* $SP* $OP;
 216
 217 # LB 16
 218 # Do not break between closing punctuation and $NS, even with intervening spaces
 219 # But DO allow a break between closing punctuation and $NSX, don't include it here
 220 ($CL | $CP) $CM* $SP* $NS;
 221
 222 # LB 17
 223 $B2 $CM* $SP* $B2;
 224
 225 #
 226 # LB 18  Break after spaces.
 227 #
 228 $LB18NonBreaks = [$LB8NonBreaks - [$SP]];
 229 $LB18Breaks    = [$LB8Breaks $SP];
 230
 231
 232 # LB 19
 233 #         x QU
 234 $LB18NonBreaks $CM* $QU;
 235 ^$CM+               $QU;
 236
 237 #         QU  x
 238 $QU $CM* .;
 239
 240
 241 # LB 20
 242 #        <break>  $CB
 243 #        $CB   <break>
 244
 245 $LB20NonBreaks = [$LB18NonBreaks - $CB];
 246
 247 # LB 20.09 added rule for Finnish tailoring
 248 # LB 21        x   (BA | HY | NS)
 249 #           BB x
 250 #
 251 # DO allow breaks here before NSX, so don't include it
 252 $LB20NonBreaks $CM* ($BA | $HH | $HY | $NS) $CM* / $AL;
 253 $LB20NonBreaks $CM* ($BA | $HH | $HY | $NS);
 254 ($HY | $HH) $AL;
 255 ^$CM+ ($BA | $HY | $HH | $NS);
 256
 257 $BB $CM* [^$CB];                                  #  $BB  x
 258 $BB $CM* $LB20NonBreaks;
 259
 260 # LB 21a Don't break after Hebrew + Hyphen
 261 #   HL (HY | BA) x
 262 #
 263 $HL $CM* ($HY | $BA | $HH) $CM* [^$CB]?;
 264
 265 # LB 21b (forward) Don't break between SY and HL
 266 # (break between HL and SY already disallowed by LB 13 above)
 267 $SY $CM* $HL;
 268
 269 # LB 22
 270 ($ALPlus | $HL) $CM* $IN;
 271 ^$CM+    $IN;     #  by rule 10, any otherwise unattached CM behaves as AL
 272 $EX $CM*    $IN;
 273 ($ID | $EB | $EM) $CM*  $IN;
 274 # $IN $CM*    $IN;  # delete this rule for CSS loose
 275 $NU $CM*    $IN;
 276
 277
 278 # $LB 23
 279 #
 280 ($ALPlus | $HL) $CM* $NU;
 281 ^$CM+  $NU;       # Rule 10, any otherwise unattached CM behaves as AL
 282 $NU $CM* ($ALPlus | $HL);
 283
 284 # LB 23a
 285 #
 286 $PR $CM* ($ID | $EB | $EM);
 287 ($ID | $EB | $EM) $CM*  $PO;
 288
 289
 290 #
 291 # LB 24
 292 #
 293 ($PR | $PO) $CM* ($ALPlus | $HL);
 294 ($ALPlus | $HL) $CM* ($PR | $PO);
 295 ^$CM+ ($PR | $PO);       # Rule 10, any otherwise unattached CM behaves as AL
 296
 297 #
 298 # LB 25   Numbers.
 299 #
 300 (($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
 301     ($CM* ($CL | $CP))? ($CM* ($PR | $PO))?;
 302
 303 # LB 26  Do not break a Korean syllable
 304 #
 305 $JL $CM* ($JL | $JV | $H2 | $H3);
 306 ($JV | $H2) $CM* ($JV | $JT);
 307 ($JT | $H3) $CM* $JT;
 308
 309 # LB 27  Treat korean Syllable Block the same as ID  (don't break it)
 310 ($JL | $JV | $JT | $H2 | $H3) $CM* $IN;
 311 ($JL | $JV | $JT | $H2 | $H3) $CM* $PO;
 312 $PR $CM* ($JL | $JV | $JT | $H2 | $H3);
 313
 314
 315 # LB 28   Do not break between alphabetics
 316 #
 317 ($ALPlus | $HL) $CM* ($ALPlus | $HL);
 318 ^$CM+ ($ALPlus | $HL);      # The $CM+ is from rule 10, an unattached CM is treated as AL
 319
 320 # LB 29
 321 $IS $CM* ($ALPlus | $HL);
 322
 323 # LB 30
 324 ($ALPlus | $HL | $NU) $CM* $OP;
 325 ^$CM+ $OP;         # The $CM+ is from rule 10, an unattached CM is treated as AL.
 326 $CP $CM* ($ALPlus | $HL | $NU);
 327
 328 # LB 30a  Do not break between regional indicators. Break after pairs of them.
 329 #         Tricky interaction with LB8a: ZWJ x .   together with ZWJ acting like a CM.
 330 $RI $CM* $RI                 / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM]];
 331 $RI $CM* $RI $CM* [$CM-$ZWJ] / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM]];
 332 $RI $CM* $RI $CM* [$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $ZWJ {eof}];
 333 # note: the preceding rule includes {eof} rather than having the last [set] term qualified with '?'
 334 #       because of the chain-out behavior difference. The rule must chain out only from the [set characters],
 335 #       not from the preceding $RI or $CM, which it would be able to do if the set were optional.
 336
 337 # LB 30b Do not break between an Emoji Base and an Emoji Modifier
 338 $EB $CM* $EM;
 339
 340 # LB 31 Break everywhere else.
 341 #       Match a single code point if no other rule applies.
 342 .;