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.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 # TODO: Rule LB 8 remains as it was in Unicode 5.2 17 # This is only because of a limitation of ICU break engine implementation, 18 # not because the older behavior is desirable. 19 # 20 # This corresponds to CSS line-break=strict (BCP47 -u-lb-strict). 21 # It sets characters of class CJ to behave like NS. 22 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 $BB = [:LineBreak = Break_Before:]; 34 $BK = [:LineBreak = Mandatory_Break:]; 35 $B2 = [:LineBreak = Break_Both:]; 36 $CB = [:LineBreak = Contingent_Break:]; 37 $CJ = [:LineBreak = Conditional_Japanese_Starter:]; 38 $CL = [:LineBreak = Close_Punctuation:]; 39 # $CM = [:LineBreak = Combining_Mark:]; 40 $CP = [:LineBreak = Close_Parenthesis:]; 41 $CR = [:LineBreak = Carriage_Return:]; 42 $EB = [:LineBreak = EB:]; 43 $EM = [:LineBreak = EM:]; 44 $EX = [:LineBreak = Exclamation:]; 45 $GL = [:LineBreak = Glue:]; 46 $HL = [:LineBreak = Hebrew_Letter:]; 47 $HY = [:LineBreak = Hyphen:]; 48 $H2 = [:LineBreak = H2:]; 49 $H3 = [:LineBreak = H3:]; 50 $ID = [:LineBreak = Ideographic:]; 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 includes CJ for CSS strict line breaking. 59 $NS = [[:LineBreak = Nonstarter:] $CJ]; 60 $NU = [:LineBreak = Numeric:]; 61 $OP = [:LineBreak = Open_Punctuation:]; 62 $PO = [:LineBreak = Postfix_Numeric:]; 63 $PR = [:LineBreak = Prefix_Numeric:]; 64 $QU = [:LineBreak = Quotation:]; 65 $RI = [:LineBreak = Regional_Indicator:]; 66 $SA = [:LineBreak = Complex_Context:]; 67 $SG = [:LineBreak = Surrogate:]; 68 $SP = [:LineBreak = Space:]; 69 $SY = [:LineBreak = Break_Symbols:]; 70 $WJ = [:LineBreak = Word_Joiner:]; 71 $XX = [:LineBreak = Unknown:]; 72 $ZW = [:LineBreak = ZWSpace:]; 73 $ZWJ = [:LineBreak = ZWJ:]; 74 75 $EmojiNRK = [[\p{Emoji}] - [$RI \u002a\u00230-9]]; 76 # Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r13267 77 $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]; 78 79 # By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly 80 # list it in the numerous rules that use CM. 81 # By LB1, SA characters with general categor of Mn or Mc also resolve to CM. 82 83 $CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]]; 84 85 # Dictionary character set, for triggering language-based break engines. Currently 86 # limited to LineBreak=Complex_Context (SA). 87 88 $dictionary = [$SA]; 89 90 # 91 # Rule LB1. By default, treat AI (characters with ambiguous east Asian width), 92 # SA (Dictionary chars, excluding Mn and Mc) 93 # SG (Unpaired Surrogates) 94 # XX (Unknown, unassigned) 95 # as $AL (Alphabetic) 96 # 97 $ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]]; 98 99 100 ## ------------------------------------------------- 101 102 !!forward; 103 104 # 105 # CAN_CM is the set of characters that may combine with CM combining chars. 106 # Note that Linebreak UAX 14's concept of a combining char and the rules 107 # for what they can combine with are _very_ different from the rest of Unicode. 108 # 109 # Note that $CM itself is left out of this set. If CM is needed as a base 110 # it must be listed separately in the rule. 111 # 112 $CAN_CM = [^$SP $BK $CR $LF $NL $ZW $CM]; # Bases that can take CMs 113 $CANT_CM = [ $SP $BK $CR $LF $NL $ZW $CM]; # Bases that can't take CMs 114 115 # 116 # AL_FOLLOW set of chars that can unconditionally follow an AL 117 # Needed in rules where stand-alone $CM s are treated as AL. 118 # 119 $AL_FOLLOW = [$BK $CR $LF $NL $ZW $SP $CL $CP $EX $HL $IS $SY $WJ $GL $OP $QU $BA $HY $NS $IN $NU $PR $PO $ALPlus]; 120 121 122 # 123 # Rule LB 4, 5 Mandatory (Hard) breaks. 124 # 125 $LB4Breaks = [$BK $CR $LF $NL]; 126 $LB4NonBreaks = [^$BK $CR $LF $NL $CM]; 127 $CR $LF {100}; 128 129 # 130 # LB 6 Do not break before hard line breaks. 131 # 132 $LB4NonBreaks? $LB4Breaks {100}; # LB 5 do not break before hard breaks. 133 $CAN_CM $CM* $LB4Breaks {100}; 134 ^$CM+ $LB4Breaks {100}; 135 136 # LB 7 x SP 137 # x ZW 138 $LB4NonBreaks [$SP $ZW]; 139 $CAN_CM $CM* [$SP $ZW]; 140 ^$CM+ [$SP $ZW]; 141 142 # 143 # LB 8 Break after zero width space 144 # TODO: ZW SP* <break> 145 # An engine change is required to write the reverse rule for this. 146 # For now, leave the Unicode 5.2 rule, ZW <break> 147 # 148 $LB8Breaks = [$LB4Breaks $ZW]; 149 $LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]]; 150 151 # LB 8a ZWJ x (ID | Extended_Pict | EmojiNRK) Emoji ZWJ sequences. 152 # 153 $ZWJ ($ID | $Extended_Pict | $EmojiNRK); 154 155 # LB 9 Combining marks. X $CM needs to behave like X, where X is not $SP, $BK $CR $LF $NL 156 # $CM not covered by the above needs to behave like $AL 157 # See definition of $CAN_CM. 158 159 $CAN_CM $CM+; # Stick together any combining sequences that don't match other rules. 160 ^$CM+; 161 162 # 163 # LB 11 Do not break before or after WORD JOINER & related characters. 164 # 165 $CAN_CM $CM* $WJ; 166 $LB8NonBreaks $WJ; 167 ^$CM+ $WJ; 168 169 $WJ $CM* .; 170 171 # 172 # LB 12 Do not break after NBSP and related characters. 173 # GL x 174 # 175 $GL $CM* .; 176 177 # 178 # LB 12a Do not break before NBSP and related characters ... 179 # [^SP BA HY] x GL 180 # 181 [[$LB8NonBreaks] - [$SP $BA $HY]] $CM* $GL; 182 ^$CM+ $GL; 183 184 185 186 # 187 # LB 13 Don't break before ']' or '!' or ';' or '/', even after spaces. 188 # 189 $LB8NonBreaks $CL; 190 $CAN_CM $CM* $CL; 191 ^$CM+ $CL; # by rule 10, stand-alone CM behaves as AL 192 193 $LB8NonBreaks $CP; 194 $CAN_CM $CM* $CP; 195 ^$CM+ $CP; # by rule 10, stand-alone CM behaves as AL 196 197 $LB8NonBreaks $EX; 198 $CAN_CM $CM* $EX; 199 ^$CM+ $EX; # by rule 10, stand-alone CM behaves as AL 200 201 $LB8NonBreaks $IS; 202 $CAN_CM $CM* $IS; 203 ^$CM+ $IS; # by rule 10, stand-alone CM behaves as AL 204 205 $LB8NonBreaks $SY; 206 $CAN_CM $CM* $SY; 207 ^$CM+ $SY; # by rule 10, stand-alone CM behaves as AL 208 209 210 # 211 # LB 14 Do not break after OP, even after spaces 212 # 213 $OP $CM* $SP* .; 214 215 $OP $CM* $SP+ $CM+ $AL_FOLLOW?; # by rule 10, stand-alone CM behaves as AL 216 # by rule 8, CM following a SP is stand-alone. 217 218 # LB 15 219 $QU $CM* $SP* $OP; 220 221 # LB 16 222 ($CL | $CP) $CM* $SP* $NS; 223 224 # LB 17 225 $B2 $CM* $SP* $B2; 226 227 # 228 # LB 18 Break after spaces. 229 # 230 $LB18NonBreaks = [$LB8NonBreaks - [$SP]]; 231 $LB18Breaks = [$LB8Breaks $SP]; 232 233 234 # LB 19 235 # x QU 236 $LB18NonBreaks $CM* $QU; 237 ^$CM+ $QU; 238 239 # QU x 240 $QU $CM* .; 241 242 243 # LB 20 244 # <break> $CB 245 # $CB <break> 246 247 $LB20NonBreaks = [$LB18NonBreaks - $CB]; 248 249 # LB 21 x (BA | HY | NS) 250 # BB x 251 # 252 $LB20NonBreaks $CM* ($BA | $HY | $NS); 253 ^$CM+ ($BA | $HY | $NS); 254 255 $BB $CM* [^$CB]; # $BB x 256 $BB $CM* $LB20NonBreaks; 257 258 # LB 21a Don't break after Hebrew + Hyphen 259 # HL (HY | BA) x 260 # 261 $HL $CM* ($HY | $BA) $CM* [^$CB]?; 262 263 # LB 21b (forward) Don't break between SY and HL 264 # (break between HL and SY already disallowed by LB 13 above) 265 $SY $CM* $HL; 266 267 # LB 22 268 ($ALPlus | $HL) $CM* $IN; 269 ^$CM+ $IN; # by rule 10, any otherwise unattached CM behaves as AL 270 $EX $CM* $IN; 271 ($ID | $EB | $EM) $CM* $IN; 272 $IN $CM* $IN; 273 $NU $CM* $IN; 274 275 276 # $LB 23 277 # 278 ($ALPlus | $HL) $CM* $NU; 279 ^$CM+ $NU; # Rule 10, any otherwise unattached CM behaves as AL 280 $NU $CM* ($ALPlus | $HL); 281 282 # LB 23a 283 # 284 $PR $CM* ($ID | $EB | $EM); 285 ($ID | $EB | $EM) $CM* $PO; 286 287 288 # 289 # LB 24 290 # 291 ($PR | $PO) $CM* ($ALPlus | $HL); 292 ($ALPlus | $HL) $CM* ($PR | $PO); 293 ^$CM+ ($PR | $PO); # Rule 10, any otherwise unattached CM behaves as AL 294 295 # 296 # LB 25 Numbers. 297 # 298 (($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))* 299 ($CM* ($CL | $CP))? ($CM* ($PR | $PO))?; 300 301 # LB 26 Do not break a Korean syllable 302 # 303 $JL $CM* ($JL | $JV | $H2 | $H3); 304 ($JV | $H2) $CM* ($JV | $JT); 305 ($JT | $H3) $CM* $JT; 306 307 # LB 27 Treat korean Syllable Block the same as ID (don't break it) 308 ($JL | $JV | $JT | $H2 | $H3) $CM* $IN; 309 ($JL | $JV | $JT | $H2 | $H3) $CM* $PO; 310 $PR $CM* ($JL | $JV | $JT | $H2 | $H3); 311 312 313 # LB 28 Do not break between alphabetics 314 # 315 ($ALPlus | $HL) $CM* ($ALPlus | $HL); 316 ^$CM+ ($ALPlus | $HL); # The $CM+ is from rule 10, an unattached CM is treated as AL 317 318 # LB 29 319 $IS $CM* ($ALPlus | $HL); 320 321 # LB 30 322 ($ALPlus | $HL | $NU) $CM* $OP; 323 ^$CM+ $OP; # The $CM+ is from rule 10, an unattached CM is treated as AL. 324 $CP $CM* ($ALPlus | $HL | $NU); 325 326 # LB 30a Do not break between regional indicators. Break after pairs of them. 327 # Tricky interaction with LB8a: ZWJ x ID 328 $RI $CM* $RI / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM] {eof}]; 329 $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}]; 330 $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}]; 331 332 $RI $CM* $RI $CM* [$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS {eof}]; 333 $RI $CM* $RI $CM* $ZWJ ($ID | $Extended_Pict | $EmojiNRK); 334 335 # LB 30b Do not break between an Emoji Base and an Emoji Modifier 336 $EB $CM* $EM; 337 338 # LB 31 Break everywhere else. 339 # Match a single code point if no other rule applies. 340 .; 341 342 ## ------------------------------------------------- 343 344 !!safe_reverse; 345 346 # LB 9 347 ^$CM+ [^$CM $BK $CR $LF $NL $ZW $SP]; 348 349 # LB 14 350 $SP+ $CM* $OP; 351 352 # LB 15 353 $SP+ $CM* $QU; 354 355 # LB 16 356 $SP+ $CM* ($CL | $CP); 357 358 # LB 17 359 $SP+ $CM* $B2; 360 361 # LB 21 362 $CM* ($HY | $BA) $CM* $HL; 363 364 # LB 25 365 ($CM* ($IS | $SY))+ $CM* $NU; 366 ($CL | $CP) $CM* ($NU | $IS | $SY); 367 368 # LB 30 369 ($CM* $RI)+; 370 371 # For dictionary-based break 372 $dictionary $dictionary; 373 374