Home | History | Annotate | Download | only in rules 
      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_cj.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 #         tailored as noted in 2nd paragraph below.
     17 #
     18 #         TODO:  Rule LB 8 remains as it was in Unicode 5.2
     19 #         This is only because of a limitation of ICU break engine implementation,
     20 #         not because the older behavior is desirable.
     21 #
     22 #         This tailors the line break behavior to correspond to CSS
     23 #         line-break=loose (BCP47 -u-lb-loose) as defined for Chinese & Japanese.
     24 #         It sets characters of class CJ to behave like ID.
     25 #         In addition, it allows breaks:
     26 #         * before hyphens 2010 & 2013 (both BA) and 301C, 30A0 (both NS)
     27 #         * before iteration marks 3005, 303B, 309D, 309E, 30FD, 30FE (all NS)
     28 #         * between characters of LineBreak class IN such as 2026
     29 #         * before some centered punct 203C, 2047, 2048, 2049, 30FB, FF1A, FF1B,
     30 #           FF65 (all NS) and FF01, FF1F (both EX).
     31 #         * before suffix characters with LineBreak class PO and EastAsianWidth A,F,W;
     32 #           this includes: 00B0 2030 2032 2033 2035 2103 2109 FE6A FF05 FFE0
     33 #         * after prefix characters with LineBreak class PR and EastAsianWidth A,F,W;
     34 #           this includes: 00A4 00B1 20AC 2116 FE69 FF04 FFE1 FFE5 FFE6
     35 
     36 
     37 #
     38 #  Character Classes defined by TR 14.
     39 #
     40 
     41 !!chain;
     42 !!quoted_literals_only;
     43 
     44 $AI = [:LineBreak =  Ambiguous:];
     45 $AL = [:LineBreak =  Alphabetic:];
     46 $BAX = [\u2010 \u2013];
     47 $BA = [[:LineBreak =  Break_After:] - $BAX];
     48 $BB = [:LineBreak =  Break_Before:];
     49 $BK = [:LineBreak =  Mandatory_Break:];
     50 $B2 = [:LineBreak =  Break_Both:];
     51 $CB = [:LineBreak =  Contingent_Break:];
     52 $CJ = [:LineBreak =  Conditional_Japanese_Starter:];
     53 $CL = [:LineBreak =  Close_Punctuation:];
     54 # $CM = [:LineBreak =  Combining_Mark:];
     55 $CP = [:LineBreak =  Close_Parenthesis:];
     56 $CR = [:LineBreak =  Carriage_Return:];
     57 $EB = [:LineBreak =  EB:];
     58 $EM = [:LineBreak =  EM:];
     59 $EXX = [\uFF01 \uFF1F];
     60 $EX = [[:LineBreak =  Exclamation:] - $EXX];
     61 $GL = [:LineBreak =  Glue:];
     62 $HL = [:LineBreak =  Hebrew_Letter:];
     63 $HY = [:LineBreak =  Hyphen:];
     64 $H2 = [:LineBreak =  H2:];
     65 $H3 = [:LineBreak =  H3:];
     66 # CSS Loose tailoring: CJ resolves to ID
     67 $ID = [[:LineBreak =  Ideographic:] $CJ];
     68 $IN = [:LineBreak =  Inseperable:];
     69 $IS = [:LineBreak =  Infix_Numeric:];
     70 $JL = [:LineBreak =  JL:];
     71 $JV = [:LineBreak =  JV:];
     72 $JT = [:LineBreak =  JT:];
     73 $LF = [:LineBreak =  Line_Feed:];
     74 $NL = [:LineBreak =  Next_Line:];
     75 $NSX = [\u301C \u30A0 \u3005 \u303B \u309D \u309E \u30FD \u30FE \u203C \u2047 \u2048 \u2049 \u30FB \uFF1A \uFF1B \uFF65];
     76 $NS = [[:LineBreak =  Nonstarter:] - $NSX];
     77 $NU = [:LineBreak =  Numeric:];
     78 $OP = [:LineBreak =  Open_Punctuation:];
     79 $POX = [\u00B0 \u2030 \u2032 \u2033 \u2035 \u2103 \u2109 \uFE6A \uFF05 \uFFE0];
     80 $PO = [[:LineBreak =  Postfix_Numeric:] - $POX];
     81 $PRX = [\u00A4 \u00B1 \u20AC \u2116 \uFE69 \uFF04 \uFFE1 \uFFE5 \uFFE6];
     82 $PR = [[:LineBreak =  Prefix_Numeric:] - $PRX];
     83 $QU = [:LineBreak =  Quotation:];
     84 $RI = [:LineBreak =  Regional_Indicator:];
     85 $SA = [:LineBreak =  Complex_Context:];
     86 $SG = [:LineBreak =  Surrogate:];
     87 $SP = [:LineBreak =  Space:];
     88 $SY = [:LineBreak =  Break_Symbols:];
     89 $WJ = [:LineBreak =  Word_Joiner:];
     90 $XX = [:LineBreak =  Unknown:];
     91 $ZW = [:LineBreak =  ZWSpace:];
     92 $ZWJ = [:LineBreak = ZWJ:];
     93 
     94 $EmojiNRK = [[\p{Emoji}] - [$RI \u002a\u00230-9]];
     95 # Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r13267
     96 $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];
     97 
     98 # By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
     99 #         list it in the numerous rules that use CM.
    100 # By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
    101 
    102 $CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
    103 
    104 #   Dictionary character set, for triggering language-based break engines. Currently
    105 #   limited to LineBreak=Complex_Context (SA).
    106 
    107 $dictionary = [$SA];
    108 
    109 #
    110 #  Rule LB1.  By default, treat AI  (characters with ambiguous east Asian width),
    111 #                               SA  (Dictionary chars, excluding Mn and Mc)
    112 #                               SG  (Unpaired Surrogates)
    113 #                               XX  (Unknown, unassigned)
    114 #                         as $AL  (Alphabetic)
    115 #
    116 $ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]];
    117 
    118 
    119 ## -------------------------------------------------
    120 
    121 !!forward;
    122 
    123 #
    124 # CAN_CM  is the set of characters that may combine with CM combining chars.
    125 #         Note that Linebreak UAX 14's concept of a combining char and the rules
    126 #         for what they can combine with are _very_ different from the rest of Unicode.
    127 #
    128 #         Note that $CM itself is left out of this set.  If CM is needed as a base
    129 #         it must be listed separately in the rule.
    130 #
    131 $CAN_CM  = [^$SP $BK $CR $LF $NL $ZW $CM];       # Bases that can   take CMs
    132 $CANT_CM = [ $SP $BK $CR $LF $NL $ZW $CM];       # Bases that can't take CMs
    133 
    134 #
    135 # AL_FOLLOW  set of chars that can unconditionally follow an AL
    136 #            Needed in rules where stand-alone $CM s are treated as AL.
    137 #
    138 $AL_FOLLOW      = [$BK $CR $LF $NL $ZW $SP $CL $CP $EX $HL $IS $SY $WJ $GL $OP $QU $BA $HY $NS $IN $NU $PR $PO $POX $ALPlus];
    139 
    140 
    141 #
    142 #  Rule LB 4, 5    Mandatory (Hard) breaks.
    143 #
    144 $LB4Breaks    = [$BK $CR $LF $NL];
    145 $LB4NonBreaks = [^$BK $CR $LF $NL $CM];
    146 $CR $LF {100};
    147 
    148 #
    149 #  LB 6    Do not break before hard line breaks.
    150 #
    151 $LB4NonBreaks?  $LB4Breaks {100};    # LB 5  do not break before hard breaks.
    152 $CAN_CM $CM*    $LB4Breaks {100};
    153 ^$CM+           $LB4Breaks {100};
    154 
    155 # LB 7         x SP
    156 #              x ZW
    157 $LB4NonBreaks [$SP $ZW];
    158 $CAN_CM $CM*  [$SP $ZW];
    159 ^$CM+         [$SP $ZW];
    160 
    161 #
    162 # LB 8         Break after zero width space
    163 #              TODO:  ZW SP* <break>
    164 #              An engine change is required to write the reverse rule for this.
    165 #              For now, leave the Unicode 5.2 rule, ZW <break>
    166 #
    167 $LB8Breaks    = [$LB4Breaks $ZW];
    168 $LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
    169 
    170 # LB 8a        ZWJ x (ID | Extended_Pict | EmojiNRK)   Emoji ZWJ sequences.
    171 #
    172 $ZWJ ($ID | $Extended_Pict | $EmojiNRK);
    173 
    174 # LB 9     Combining marks.      X   $CM needs to behave like X, where X is not $SP, $BK $CR $LF $NL
    175 #                                $CM not covered by the above needs to behave like $AL
    176 #                                See definition of $CAN_CM.
    177 
    178 $CAN_CM $CM+;                   #  Stick together any combining sequences that don't match other rules.
    179 ^$CM+;
    180 
    181 #
    182 # LB 11  Do not break before or after WORD JOINER & related characters.
    183 #
    184 $CAN_CM $CM*  $WJ;
    185 $LB8NonBreaks $WJ;
    186 ^$CM+         $WJ;
    187 
    188 $WJ $CM* .;
    189 
    190 #
    191 # LB 12  Do not break after NBSP and related characters.
    192 #         GL  x
    193 #
    194 $GL $CM* .;
    195 
    196 #
    197 # LB 12a  Do not break before NBSP and related characters ...
    198 #            [^SP BA HY] x GL
    199 #
    200 [[$LB8NonBreaks] - [$SP $BA $BAX $HY]] $CM* $GL;
    201 ^$CM+ $GL;
    202 
    203 
    204 #
    205 # LB 13   Don't break before ']' or '!' or ';' or '/', even after spaces.
    206 #
    207 # Do not include $EXX here
    208 $LB8NonBreaks $CL;
    209 $CAN_CM $CM*  $CL;
    210 ^$CM+         $CL;              # by rule 10, stand-alone CM behaves as AL
    211 
    212 $LB8NonBreaks $CP;
    213 $CAN_CM $CM*  $CP;
    214 ^$CM+         $CP;              # by rule 10, stand-alone CM behaves as AL
    215 
    216 $LB8NonBreaks $EX;
    217 $CAN_CM $CM*  $EX;
    218 ^$CM+         $EX;              # by rule 10, stand-alone CM behaves as AL
    219 
    220 $LB8NonBreaks $IS;
    221 $CAN_CM $CM*  $IS;
    222 ^$CM+         $IS;              # by rule 10, stand-alone CM behaves as AL
    223 
    224 $LB8NonBreaks $SY;
    225 $CAN_CM $CM*  $SY;
    226 ^$CM+         $SY;              # by rule 10, stand-alone CM behaves as AL
    227 
    228 
    229 #
    230 # LB 14  Do not break after OP, even after spaces
    231 #
    232 $OP $CM* $SP* .;
    233 
    234 $OP $CM* $SP+ $CM+ $AL_FOLLOW?;    # by rule 10, stand-alone CM behaves as AL
    235                                    # by rule 8, CM following a SP is stand-alone.
    236 
    237 # LB 15
    238 $QU $CM* $SP* $OP;
    239 
    240 # LB 16
    241 # Do not break between closing punctuation and $NS, even with intervening spaces
    242 # But DO allow a break between closing punctuation and $NSX, don't include it here
    243 ($CL | $CP) $CM* $SP* $NS;
    244 
    245 # LB 17
    246 $B2 $CM* $SP* $B2;
    247 
    248 #
    249 # LB 18  Break after spaces.
    250 #
    251 $LB18NonBreaks = [$LB8NonBreaks - [$SP]];
    252 $LB18Breaks    = [$LB8Breaks $SP];
    253 
    254 
    255 # LB 19
    256 #         x QU
    257 $LB18NonBreaks $CM* $QU;
    258 ^$CM+               $QU;
    259 
    260 #         QU  x
    261 $QU $CM* .;
    262 
    263 
    264 # LB 20
    265 #        <break>  $CB
    266 #        $CB   <break>
    267 
    268 $LB20NonBreaks = [$LB18NonBreaks - $CB];
    269 
    270 # LB 21        x   (BA | HY | NS)
    271 #           BB x
    272 #
    273 # DO allow breaks here before $BAX and $NSX, so don't include them
    274 $LB20NonBreaks $CM* ($BA | $HY | $NS);
    275 ^$CM+ ($BA | $HY | $NS);
    276 
    277 $BB $CM* [^$CB];                                  #  $BB  x
    278 $BB $CM* $LB20NonBreaks;
    279 
    280 # LB 21a Don't break after Hebrew + Hyphen
    281 #   HL (HY | BA) x
    282 #
    283 $HL $CM* ($HY | $BA | $BAX) $CM* [^$CB]?;
    284 
    285 # LB 21b (forward) Don't break between SY and HL
    286 # (break between HL and SY already disallowed by LB 13 above)
    287 $SY $CM* $HL;
    288 
    289 # LB 22
    290 ($ALPlus | $HL) $CM* $IN;
    291 ^$CM+    $IN;     #  by rule 10, any otherwise unattached CM behaves as AL
    292 $EX $CM*    $IN;
    293 ($ID | $EB | $EM) $CM*  $IN;
    294 # $IN $CM*    $IN;  # delete this rule for CSS loose
    295 $NU $CM*    $IN;
    296 
    297 
    298 # $LB 23
    299 #
    300 ($ALPlus | $HL) $CM* $NU;
    301 ^$CM+  $NU;       # Rule 10, any otherwise unattached CM behaves as AL
    302 $NU $CM* ($ALPlus | $HL);
    303 
    304 # LB 23a
    305 # Do not include $POX here
    306 #
    307 $PR $CM* ($ID | $EB | $EM);
    308 ($ID | $EB | $EM) $CM*  $PO;
    309 
    310 
    311 #
    312 # LB 24
    313 #
    314 # Do not include $PRX here
    315 ($PR | $PO | $POX) $CM* ($ALPlus | $HL);
    316 ($ALPlus | $HL) $CM* ($PR | $PO | $POX);     # TODO: should this be ($PR | $PRX | $PO)
    317 ^$CM+ ($PR | $PO | $POX);       # Rule 10, any otherwise unattached CM behaves as AL
    318 
    319 #
    320 # LB 25   Numbers.
    321 #
    322 # Here do not include $PRX at the beginning or $POX at the end
    323 (($PR | $PO | $POX) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
    324     ($CM* ($CL | $CP))? ($CM* ($PR | $PRX | $PO))?;
    325 
    326 # LB 26  Do not break a Korean syllable
    327 #
    328 $JL $CM* ($JL | $JV | $H2 | $H3);
    329 ($JV | $H2) $CM* ($JV | $JT);
    330 ($JT | $H3) $CM* $JT;
    331 
    332 # LB 27  Treat korean Syllable Block the same as ID  (don't break it)
    333 # Do not include $POX or $PRX here
    334 ($JL | $JV | $JT | $H2 | $H3) $CM* $IN;
    335 ($JL | $JV | $JT | $H2 | $H3) $CM* $PO;
    336 $PR $CM* ($JL | $JV | $JT | $H2 | $H3);
    337 
    338 
    339 # LB 28   Do not break between alphabetics
    340 #
    341 ($ALPlus | $HL) $CM* ($ALPlus | $HL);
    342 ^$CM+ ($ALPlus | $HL);      # The $CM+ is from rule 10, an unattached CM is treated as AL
    343 
    344 # LB 29
    345 $IS $CM* ($ALPlus | $HL);
    346 
    347 # LB 30
    348 ($ALPlus | $HL | $NU) $CM* $OP;
    349 ^$CM+ $OP;         # The $CM+ is from rule 10, an unattached CM is treated as AL.
    350 $CP $CM* ($ALPlus | $HL | $NU);
    351 
    352 # LB 30a  Do not break between regional indicators. Break after pairs of them.
    353 #         Tricky interaction with LB8a: ZWJ x ID
    354 $RI $CM* $RI                / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM] {eof}];
    355 $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}];
    356 $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}];
    357 
    358 $RI $CM* $RI $CM* [$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS {eof}];
    359 $RI $CM* $RI $CM* $ZWJ ($ID | $Extended_Pict | $EmojiNRK);
    360 
    361 # LB 30b Do not break between an Emoji Base and an Emoji Modifier
    362 $EB $CM* $EM;
    363 
    364 # LB 31 Break everywhere else.
    365 #       Match a single code point if no other rule applies.
    366 .;
    367 
    368 ## -------------------------------------------------
    369 
    370 !!safe_reverse;
    371 
    372 # LB 9
    373 ^$CM+ [^$CM $BK $CR $LF $NL $ZW $SP];
    374 
    375 # LB 14
    376 $SP+ $CM* $OP;
    377 
    378 # LB 15
    379 $SP+ $CM* $QU;
    380 
    381 # LB 16
    382 $SP+ $CM* ($CL | $CP);
    383 
    384 # LB 17
    385 $SP+ $CM* $B2;
    386 
    387 # LB 21
    388 $CM* ($HY | $BA | $BAX) $CM* $HL;
    389 
    390 # LB 25
    391 ($CM* ($IS | $SY))+ $CM* $NU;
    392 ($CL | $CP) $CM* ($NU | $IS | $SY);
    393 
    394 #  LB 30
    395 ($CM* $RI)+;
    396 
    397 # For dictionary-based break
    398 $dictionary $dictionary;
    399