| Index: source/data/brkitr/rules/line_loose_cj.txt
|
| diff --git a/source/data/brkitr/line_loose_cj.txt b/source/data/brkitr/rules/line_loose_cj.txt
|
| similarity index 51%
|
| rename from source/data/brkitr/line_loose_cj.txt
|
| rename to source/data/brkitr/rules/line_loose_cj.txt
|
| index 9934fe3aa1d077407f538b8d3ba6a649fdf7622d..9b781f875a6dedad5e3e3e8f9b0c282b6f68372f 100644
|
| --- a/source/data/brkitr/line_loose_cj.txt
|
| +++ b/source/data/brkitr/rules/line_loose_cj.txt
|
| @@ -1,13 +1,19 @@
|
| -# Copyright (c) 2002-2015 International Business Machines Corporation and
|
| +# Copyright (C) 2016 and later: Unicode, Inc. and others.
|
| +# License & terms of use: http://www.unicode.org/copyright.html
|
| +# Copyright (c) 2002-2016 International Business Machines Corporation and
|
| # others. All Rights Reserved.
|
| #
|
| # file: line_loose_cj.txt
|
| #
|
| # Line Breaking Rules
|
| -# Implement default line breaking as defined by
|
| -# Unicode Standard Annex #14 Revision 34 for Unicode 8.0
|
| +# Implement default line breaking as defined by
|
| +# Unicode Standard Annex #14 Revision 37 for Unicode 9.0
|
| # http://www.unicode.org/reports/tr14/
|
| -# tailored as noted in 2nd paragraph below..
|
| +#
|
| +# Includes extensions to the handling of emoji ZWJ sequences from
|
| +# https://goo.gl/cluFCn
|
| +#
|
| +# tailored as noted in 2nd paragraph below.
|
| #
|
| # TODO: Rule LB 8 remains as it was in Unicode 5.2
|
| # This is only because of a limitation of ICU break engine implementation,
|
| @@ -33,44 +39,6 @@
|
| #
|
|
|
| !!chain;
|
| -!!LBCMNoChain;
|
| -
|
| -
|
| -!!lookAheadHardBreak;
|
| -#
|
| -# !!lookAheadHardBreak Described here because it is (as yet) undocumented elsewhere
|
| -# and only used for the line break rules.
|
| -#
|
| -# It is used in the implementation of rule LB 10
|
| -# which says to treat any combining mark that is not attached to a base
|
| -# character as if it were of class AL (alphabetic).
|
| -#
|
| -# The problem occurs in the reverse rules.
|
| -#
|
| -# Consider a sequence like, with correct breaks as shown
|
| -# LF ID CM AL AL
|
| -# ^ ^ ^
|
| -# Then consider the sequence without the initial ID (ideographic)
|
| -# LF CM AL AL
|
| -# ^ ^
|
| -# Our CM, which in the first example was attached to the ideograph,
|
| -# is now unattached, becomes an alpha, and joins in with the other
|
| -# alphas.
|
| -#
|
| -# When iterating forwards, these sequences do not present any problems
|
| -# When iterating backwards, we need to look ahead when encountering
|
| -# a CM to see whether it attaches to something further on or not.
|
| -# (Look-ahead in a reverse rule is looking towards the start)
|
| -#
|
| -# If the CM is unattached, we need to force a break.
|
| -#
|
| -# !!lookAheadHardBreak forces the run time state machine to
|
| -# stop immediately when a look ahead rule ( '/' operator) matches,
|
| -# and set the match position to that of the look-ahead operator,
|
| -# no matter what other rules may be in play at the time.
|
| -#
|
| -# See rule LB 19 for an example.
|
| -#
|
|
|
| $AI = [:LineBreak = Ambiguous:];
|
| $AL = [:LineBreak = Alphabetic:];
|
| @@ -82,9 +50,11 @@ $B2 = [:LineBreak = Break_Both:];
|
| $CB = [:LineBreak = Contingent_Break:];
|
| $CJ = [:LineBreak = Conditional_Japanese_Starter:];
|
| $CL = [:LineBreak = Close_Punctuation:];
|
| -$CM = [:LineBreak = Combining_Mark:];
|
| +# $CM = [:LineBreak = Combining_Mark:];
|
| $CP = [:LineBreak = Close_Parenthesis:];
|
| $CR = [:LineBreak = Carriage_Return:];
|
| +$EB = [[:LineBreak = EB:]\U0001F3C2\U0001F3C7\U0001F3CC\U0001F46A-\U0001F46D\U0001F46F\U0001F574\U0001F6CC];
|
| +$EM = [:LineBreak = EM:];
|
| $EXX = [\uFF01 \uFF1F];
|
| $EX = [[:LineBreak = Exclamation:] - $EXX];
|
| $GL = [:LineBreak = Glue:];
|
| @@ -92,6 +62,7 @@ $HL = [:LineBreak = Hebrew_Letter:];
|
| $HY = [:LineBreak = Hyphen:];
|
| $H2 = [:LineBreak = H2:];
|
| $H3 = [:LineBreak = H3:];
|
| +# CSS Loose tailoring: CJ resolves to ID
|
| $ID = [[:LineBreak = Ideographic:] $CJ];
|
| $IN = [:LineBreak = Inseperable:];
|
| $IS = [:LineBreak = Infix_Numeric:];
|
| @@ -117,100 +88,38 @@ $SY = [:LineBreak = Break_Symbols:];
|
| $WJ = [:LineBreak = Word_Joiner:];
|
| $XX = [:LineBreak = Unknown:];
|
| $ZW = [:LineBreak = ZWSpace:];
|
| +$ZWJ = [:LineBreak = ZWJ:];
|
| +
|
| +$EmojiNRK = [[\p{Emoji}] - [$RI \u002a\u00230-9©®™〰〽]];
|
| +# Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r12773
|
| +$Extended_Pict = [\U0001F774-\U0001F77F\u2700-\u2701\u2703-\u2704\u270E\u2710-\u2711\u2765-\u2767\U0001F030-\U0001F093\U0001F094-\U0001F09F\U0001F10D-\U0001F10F\U0001F12F\U0001F16C-\U0001F16F\U0001F1AD-\U0001F1E5\U0001F203-\U0001F20F\U0001F23C-\U0001F23F\U0001F249-\U0001F24F\U0001F252-\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\u2605\u2607-\u260D\u260F-\u2610\u2612\u2616-\u2617\u2619-\u261C\u261E-\u261F\u2621\u2624-\u2625\u2627-\u2629\u262B-\u262D\u2630-\u2637\u263B-\u2647\u2654-\u265F\u2661-\u2662\u2664\u2667\u2669-\u267A\u267C-\u267E\u2680-\u2691\u2695\u2698\u269A\u269D-\u269F\u26A2-\u26A9\u26AC-\u26AF\u26B2-\u26BC\u26BF-\u26C3\u26C6-\u26C7\u26C9-\u26CD\u26D0\u26D2\u26D5-\u26E8\u26EB-\u26EF\u26F6\u26FB-\u26FC\u26FE-\u26FF\u2388\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-\U0001F90F\U0001F91F\U0001F928-\U0001F92F\U0001F931-\U0001F932\U0001F93F\U0001F94C-\U0001F94F\U0001F95F-\U0001F97F\U0001F992-\U0001F9BF\U0001F9C1-\U0001F9FF\U0001F6C6-\U0001F6CA\U0001F6E6-\U0001F6E8\U0001F6EA\U0001F6F1-\U0001F6F2\U0001F6D3-\U0001F6DF\U0001F6ED-\U0001F6EF\U0001F6F7-\U0001F6FF];
|
| +
|
| +# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
|
| +# list it in the numerous rules that use CM.
|
| +# By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
|
| +
|
| +$CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
|
|
|
| # Dictionary character set, for triggering language-based break engines. Currently
|
| -# limited to LineBreak=Complex_Context. Note that this set only works in Unicode
|
| -# 5.0 or later as the definition of Complex_Context was corrected to include all
|
| -# characters requiring dictionary break.
|
| +# limited to LineBreak=Complex_Context (SA).
|
|
|
| -$dictionary = [:LineBreak = Complex_Context:];
|
| +$dictionary = [$SA];
|
|
|
| #
|
| # Rule LB1. By default, treat AI (characters with ambiguous east Asian width),
|
| -# SA (South East Asian: Thai, Lao, Khmer)
|
| +# SA (Dictionary chars, excluding Mn and Mc)
|
| # SG (Unpaired Surrogates)
|
| # XX (Unknown, unassigned)
|
| # as $AL (Alphabetic)
|
| #
|
| -$ALPlus = [$AL $AI $SA $SG $XX];
|
| -
|
| -#
|
| -# Combining Marks. X $CM* behaves as if it were X. Rule LB6.
|
| -#
|
| -$ALcm = $ALPlus $CM*;
|
| -$BAcm = $BA $CM*;
|
| -$BAXcm = $BAX $CM*;
|
| -$BBcm = $BB $CM*;
|
| -$B2cm = $B2 $CM*;
|
| -$CLcm = $CL $CM*;
|
| -$CPcm = $CP $CM*;
|
| -$EXcm = $EX $CM*;
|
| -$EXXcm = $EXX $CM*;
|
| -$GLcm = $GL $CM*;
|
| -$HLcm = $HL $CM*;
|
| -$HYcm = $HY $CM*;
|
| -$H2cm = $H2 $CM*;
|
| -$H3cm = $H3 $CM*;
|
| -$IDcm = $ID $CM*;
|
| -$INcm = $IN $CM*;
|
| -$IScm = $IS $CM*;
|
| -$JLcm = $JL $CM*;
|
| -$JVcm = $JV $CM*;
|
| -$JTcm = $JT $CM*;
|
| -$NScm = $NS $CM*;
|
| -$NSXcm = $NSX $CM*;
|
| -$NUcm = $NU $CM*;
|
| -$OPcm = $OP $CM*;
|
| -$POcm = $PO $CM*;
|
| -$POXcm = $POX $CM*;
|
| -$PRcm = $PR $CM*;
|
| -$PRXcm = $PRX $CM*;
|
| -$QUcm = $QU $CM*;
|
| -$RIcm = $RI $CM*;
|
| -$SYcm = $SY $CM*;
|
| -$WJcm = $WJ $CM*;
|
| +$ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]];
|
| +
|
|
|
| ## -------------------------------------------------
|
|
|
| !!forward;
|
|
|
| #
|
| -# Each class of character can stand by itself as an unbroken token, with trailing combining stuff
|
| -#
|
| -$ALPlus $CM+;
|
| -$BA $CM+;
|
| -$BAX $CM+;
|
| -$BB $CM+;
|
| -$B2 $CM+;
|
| -$CL $CM+;
|
| -$CP $CM+;
|
| -$EX $CM+;
|
| -$EXX $CM+;
|
| -$GL $CM+;
|
| -$HL $CM+;
|
| -$HY $CM+;
|
| -$H2 $CM+;
|
| -$H3 $CM+;
|
| -$ID $CM+;
|
| -$IN $CM+;
|
| -$IS $CM+;
|
| -$JL $CM+;
|
| -$JV $CM+;
|
| -$JT $CM+;
|
| -$NS $CM+;
|
| -$NSX $CM+;
|
| -$NU $CM+;
|
| -$OP $CM+;
|
| -$PO $CM+;
|
| -$POX $CM+;
|
| -$PR $CM+;
|
| -$PRX $CM+;
|
| -$QU $CM+;
|
| -$RI $CM+;
|
| -$SY $CM+;
|
| -$WJ $CM+;
|
| -
|
| -#
|
| # CAN_CM is the set of characters that may combine with CM combining chars.
|
| # Note that Linebreak UAX 14's concept of a combining char and the rules
|
| # for what they can combine with are _very_ different from the rest of Unicode.
|
| @@ -224,19 +133,15 @@ $CANT_CM = [ $SP $BK $CR $LF $NL $ZW $CM]; # Bases that can't take CMs
|
| #
|
| # AL_FOLLOW set of chars that can unconditionally follow an AL
|
| # Needed in rules where stand-alone $CM s are treated as AL.
|
| -# Chaining is disabled with CM because it causes other failures,
|
| -# so for this one case we need to manually list out longer sequences.
|
| #
|
| -$AL_FOLLOW_NOCM = [$BK $CR $LF $NL $ZW $SP];
|
| -$AL_FOLLOW_CM = [$CL $CP $EX $HL $IS $SY $WJ $GL $OP $QU $BA $HY $NS $IN $NU $ALPlus];
|
| -$AL_FOLLOW = [$AL_FOLLOW_NOCM $AL_FOLLOW_CM];
|
| +$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];
|
|
|
|
|
| #
|
| # Rule LB 4, 5 Mandatory (Hard) breaks.
|
| #
|
| $LB4Breaks = [$BK $CR $LF $NL];
|
| -$LB4NonBreaks = [^$BK $CR $LF $NL];
|
| +$LB4NonBreaks = [^$BK $CR $LF $NL $CM];
|
| $CR $LF {100};
|
|
|
| #
|
| @@ -244,13 +149,13 @@ $CR $LF {100};
|
| #
|
| $LB4NonBreaks? $LB4Breaks {100}; # LB 5 do not break before hard breaks.
|
| $CAN_CM $CM* $LB4Breaks {100};
|
| -$CM+ $LB4Breaks {100};
|
| +^$CM+ $LB4Breaks {100};
|
|
|
| # LB 7 x SP
|
| # x ZW
|
| $LB4NonBreaks [$SP $ZW];
|
| $CAN_CM $CM* [$SP $ZW];
|
| -$CM+ [$SP $ZW];
|
| +^$CM+ [$SP $ZW];
|
|
|
| #
|
| # LB 8 Break after zero width space
|
| @@ -261,38 +166,38 @@ $CM+ [$SP $ZW];
|
| $LB8Breaks = [$LB4Breaks $ZW];
|
| $LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
|
|
|
| +# LB 8a ZWJ x (ID | Extended_Pict | EmojiNRK) Emoji ZWJ sequences.
|
| +#
|
| +$ZWJ ($ID | $Extended_Pict | $EmojiNRK);
|
|
|
| -# LB 9 Combining marks. X $CM needs to behave like X, where X is not $SP, $BK $CR $LF $NL
|
| -# $CM not covered by the above needs to behave like $AL
|
| +# LB 9 Combining marks. X $CM needs to behave like X, where X is not $SP, $BK $CR $LF $NL
|
| +# $CM not covered by the above needs to behave like $AL
|
| # See definition of $CAN_CM.
|
|
|
| $CAN_CM $CM+; # Stick together any combining sequences that don't match other rules.
|
| -$CM+;
|
| +^$CM+;
|
|
|
| #
|
| # LB 11 Do not break before or after WORD JOINER & related characters.
|
| #
|
| -$CAN_CM $CM* $WJcm;
|
| -$LB8NonBreaks $WJcm;
|
| -$CM+ $WJcm;
|
| +$CAN_CM $CM* $WJ;
|
| +$LB8NonBreaks $WJ;
|
| +^$CM+ $WJ;
|
|
|
| -$WJcm $CANT_CM;
|
| -$WJcm $CAN_CM $CM*;
|
| +$WJ $CM* .;
|
|
|
| #
|
| # LB 12 Do not break after NBSP and related characters.
|
| # GL x
|
| #
|
| -$GLcm $CAN_CM $CM*;
|
| -$GLcm $CANT_CM;
|
| -
|
| +$GL $CM* .;
|
| +
|
| #
|
| # LB 12a Do not break before NBSP and related characters ...
|
| # [^SP BA HY] x GL
|
| #
|
| -[[$LB8NonBreaks] - [$SP $BA $BAX $HY]] $CM* $GLcm;
|
| -$CM+ GLcm;
|
| -
|
| +[[$LB8NonBreaks] - [$SP $BA $BAX $HY]] $CM* $GL;
|
| +^$CM+ $GL;
|
|
|
|
|
| #
|
| @@ -301,43 +206,43 @@ $CM+ GLcm;
|
| # Do not include $EXX here
|
| $LB8NonBreaks $CL;
|
| $CAN_CM $CM* $CL;
|
| -$CM+ $CL; # by rule 10, stand-alone CM behaves as AL
|
| +^$CM+ $CL; # by rule 10, stand-alone CM behaves as AL
|
|
|
| $LB8NonBreaks $CP;
|
| $CAN_CM $CM* $CP;
|
| -$CM+ $CP; # by rule 10, stand-alone CM behaves as AL
|
| +^$CM+ $CP; # by rule 10, stand-alone CM behaves as AL
|
|
|
| $LB8NonBreaks $EX;
|
| $CAN_CM $CM* $EX;
|
| -$CM+ $EX; # by rule 10, stand-alone CM behaves as AL
|
| +^$CM+ $EX; # by rule 10, stand-alone CM behaves as AL
|
|
|
| $LB8NonBreaks $IS;
|
| $CAN_CM $CM* $IS;
|
| -$CM+ $IS; # by rule 10, stand-alone CM behaves as AL
|
| +^$CM+ $IS; # by rule 10, stand-alone CM behaves as AL
|
|
|
| $LB8NonBreaks $SY;
|
| $CAN_CM $CM* $SY;
|
| -$CM+ $SY; # by rule 10, stand-alone CM behaves as AL
|
| +^$CM+ $SY; # by rule 10, stand-alone CM behaves as AL
|
|
|
|
|
| #
|
| # LB 14 Do not break after OP, even after spaces
|
| #
|
| -$OPcm $SP* $CAN_CM $CM*;
|
| -$OPcm $SP* $CANT_CM;
|
| +$OP $CM* $SP* .;
|
|
|
| -$OPcm $SP+ $CM+ $AL_FOLLOW?; # by rule 10, stand-alone CM behaves as AL
|
| +$OP $CM* $SP+ $CM+ $AL_FOLLOW?; # by rule 10, stand-alone CM behaves as AL
|
| + # by rule 8, CM following a SP is stand-alone.
|
|
|
| # LB 15
|
| -$QUcm $SP* $OPcm;
|
| +$QU $CM* $SP* $OP;
|
|
|
| # LB 16
|
| # Do not break between closing punctuation and $NS, even with intervening spaces
|
| # But DO allow a break between closing punctuation and $NSX, don't include it here
|
| -($CLcm | $CPcm) $SP* $NScm;
|
| +($CL | $CP) $CM* $SP* $NS;
|
|
|
| # LB 17
|
| -$B2cm $SP* $B2cm;
|
| +$B2 $CM* $SP* $B2;
|
|
|
| #
|
| # LB 18 Break after spaces.
|
| @@ -348,13 +253,11 @@ $LB18Breaks = [$LB8Breaks $SP];
|
|
|
| # LB 19
|
| # x QU
|
| -$LB18NonBreaks $CM* $QUcm;
|
| -$CM+ $QUcm;
|
| +$LB18NonBreaks $CM* $QU;
|
| +^$CM+ $QU;
|
|
|
| # QU x
|
| -$QUcm .?;
|
| -$QUcm $LB18NonBreaks $CM*; # Don't let a combining mark go onto $CR, $BK, etc.
|
| - # TODO: I don't think this rule is needed.
|
| +$QU $CM* .;
|
|
|
|
|
| # LB 20
|
| @@ -366,81 +269,96 @@ $LB20NonBreaks = [$LB18NonBreaks - $CB];
|
| # LB 21 x (BA | HY | NS)
|
| # BB x
|
| #
|
| -# DO allow breaks here before $BAXcm and $NSXcm, so don't include them
|
| -$LB20NonBreaks $CM* ($BAcm | $HYcm | $NScm);
|
| +# DO allow breaks here before $BAX and $NSX, so don't include them
|
| +$LB20NonBreaks $CM* ($BA | $HY | $NS);
|
| +^$CM+ ($BA | $HY | $NS);
|
|
|
| -$BBcm [^$CB]; # $BB x
|
| -$BBcm $LB20NonBreaks $CM*;
|
| +$BB $CM* [^$CB]; # $BB x
|
| +$BB $CM* $LB20NonBreaks;
|
|
|
| # LB 21a Don't break after Hebrew + Hyphen
|
| # HL (HY | BA) x
|
| -#
|
| -$HLcm ($HYcm | $BAcm | $BAXcm) [^$CB]?;
|
| +#
|
| +$HL $CM* ($HY | $BA | $BAX) $CM* [^$CB]?;
|
|
|
| # LB 21b (forward) Don't break between SY and HL
|
| # (break between HL and SY already disallowed by LB 13 above)
|
| -$SYcm $HLcm;
|
| +$SY $CM* $HL;
|
|
|
| # LB 22
|
| -($ALcm | $HLcm) $INcm;
|
| -$CM+ $INcm; # by rule 10, any otherwise unattached CM behaves as AL
|
| -$EXcm $INcm;
|
| -$IDcm $INcm;
|
| -# $INcm $INcm; # delete this rule for CSS loose
|
| -$NUcm $INcm;
|
| +($ALPlus | $HL) $CM* $IN;
|
| +^$CM+ $IN; # by rule 10, any otherwise unattached CM behaves as AL
|
| +$EX $CM* $IN;
|
| +($ID | $EB | $EM) $CM* $IN;
|
| +# $IN $CM* $IN; # delete this rule for CSS loose
|
| +$NU $CM* $IN;
|
|
|
|
|
| -# LB 23
|
| +# $LB 23
|
| +#
|
| +($ALPlus | $HL) $CM* $NU;
|
| +^$CM+ $NU; # Rule 10, any otherwise unattached CM behaves as AL
|
| +$NU $CM* ($ALPlus | $HL);
|
| +
|
| +# LB 23a
|
| # Do not include $POX here
|
| -$IDcm $POcm;
|
| -$ALcm $NUcm; # includes $LB19
|
| -$HLcm $NUcm;
|
| -$CM+ $NUcm; # Rule 10, any otherwise unattached CM behaves as AL
|
| -$NUcm $ALcm;
|
| -$NUcm $HLcm;
|
| +#
|
| +$PR $CM* ($ID | $EB | $EM);
|
| +($ID | $EB | $EM) $CM* $PO;
|
| +
|
|
|
| #
|
| # LB 24
|
| #
|
| # Do not include $PRX here
|
| -$PRcm $IDcm;
|
| -$PRcm ($ALcm | $HLcm);
|
| -($POcm | $POXcm) ($ALcm | $HLcm);
|
| +($PR | $PO | $POX) $CM* ($ALPlus | $HL);
|
| +($ALPlus | $HL) $CM* ($PR | $PO | $POX); # TODO: should this be ($PR | $PRX | $PO)
|
| +^$CM+ ($PR | $PO | $POX); # Rule 10, any otherwise unattached CM behaves as AL
|
|
|
| #
|
| # LB 25 Numbers.
|
| #
|
| # Here do not include $PRX at the beginning or $POX at the end
|
| -($PRcm | $POcm | $POXcm)? ($OPcm | $HYcm)? $NUcm ($NUcm | $SYcm | $IScm)* ($CLcm | $CPcm)? ($PRcm | $PRXcm | $POcm)?;
|
| +(($PR | $PO | $POX) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
|
| + ($CM* ($CL | $CP))? ($CM* ($PR | $PRX | $PO))?;
|
|
|
| # LB 26 Do not break a Korean syllable
|
| #
|
| -$JLcm ($JLcm | $JVcm | $H2cm | $H3cm);
|
| -($JVcm | $H2cm) ($JVcm | $JTcm);
|
| -($JTcm | $H3cm) $JTcm;
|
| +$JL $CM* ($JL | $JV | $H2 | $H3);
|
| +($JV | $H2) $CM* ($JV | $JT);
|
| +($JT | $H3) $CM* $JT;
|
|
|
| # LB 27 Treat korean Syllable Block the same as ID (don't break it)
|
| # Do not include $POX or $PRX here
|
| -($JLcm | $JVcm | $JTcm | $H2cm | $H3cm) $INcm;
|
| -($JLcm | $JVcm | $JTcm | $H2cm | $H3cm) $POcm;
|
| -$PRcm ($JLcm | $JVcm | $JTcm | $H2cm | $H3cm);
|
| +($JL | $JV | $JT | $H2 | $H3) $CM* $IN;
|
| +($JL | $JV | $JT | $H2 | $H3) $CM* $PO;
|
| +$PR $CM* ($JL | $JV | $JT | $H2 | $H3);
|
|
|
|
|
| # LB 28 Do not break between alphabetics
|
| #
|
| -($ALcm | $HLcm) ($ALcm | $HLcm);
|
| -$CM+ ($ALcm | $HLcm); # The $CM+ is from rule 10, an unattached CM is treated as AL
|
| +($ALPlus | $HL) $CM* ($ALPlus | $HL);
|
| +^$CM+ ($ALPlus | $HL); # The $CM+ is from rule 10, an unattached CM is treated as AL
|
|
|
| # LB 29
|
| -$IScm ($ALcm | $HLcm);
|
| +$IS $CM* ($ALPlus | $HL);
|
|
|
| # LB 30
|
| -($ALcm | $HLcm | $NUcm) $OPcm;
|
| -$CM+ $OPcm; # The $CM+ is from rule 10, an unattached CM is treated as AL.
|
| -$CPcm ($ALcm | $HLcm | $NUcm);
|
| +($ALPlus | $HL | $NU) $CM* $OP;
|
| +^$CM+ $OP; # The $CM+ is from rule 10, an unattached CM is treated as AL.
|
| +$CP $CM* ($ALPlus | $HL | $NU);
|
| +
|
| +# LB 30a Do not break between regional indicators. Break after pairs of them.
|
| +# Tricky interaction with LB8a: ZWJ x ID
|
| +$RI $CM* $RI / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM] {eof}];
|
| +$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 $EmojiNRK] {eof}];
|
| +$RI $CM* $RI $CM* [$CM-$ZWJ] / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM] {eof}];
|
| +
|
| +$RI $CM* $RI $CM* [$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS {eof}];
|
| +$RI $CM* $RI $CM* $ZWJ ($ID | $Extended_Pict | $EmojiNRK);
|
|
|
| -# LB 30a Do not break between regional indicators.
|
| -$RIcm $RIcm;
|
| +# LB 30b Do not break between an Emoji Base and an Emoji Modifier
|
| +$EB $CM* $EM;
|
|
|
| #
|
| # Reverse Rules.
|
| @@ -449,40 +367,10 @@ $RIcm $RIcm;
|
|
|
| !!reverse;
|
|
|
| -$CM+ $ALPlus;
|
| -$CM+ $BA;
|
| -$CM+ $BAX;
|
| -$CM+ $BB;
|
| -$CM+ $B2;
|
| -$CM+ $CL;
|
| -$CM+ $CP;
|
| -$CM+ $EX;
|
| -$CM+ $EXX;
|
| -$CM+ $GL;
|
| -$CM+ $HL;
|
| -$CM+ $HY;
|
| -$CM+ $H2;
|
| -$CM+ $H3;
|
| -$CM+ $ID;
|
| -$CM+ $IN;
|
| -$CM+ $IS;
|
| -$CM+ $JL;
|
| -$CM+ $JV;
|
| -$CM+ $JT;
|
| -$CM+ $NS;
|
| -$CM+ $NSX;
|
| -$CM+ $NU;
|
| -$CM+ $OP;
|
| -$CM+ $PO;
|
| -$CM+ $POX;
|
| -$CM+ $PR;
|
| -$CM+ $PRX;
|
| -$CM+ $QU;
|
| -$CM+ $RI;
|
| -$CM+ $SY;
|
| -$CM+ $WJ;
|
| -$CM+;
|
| +# LB 9 Combining Marks.
|
| +# Stick together any combining sequences that don't match other rules.
|
|
|
| +^$CM+ $CAN_CM?;
|
|
|
| #
|
| # Sequences of the form (shown forwards)
|
| @@ -493,26 +381,16 @@ $AL_FOLLOW $CM+ / (
|
| [$BK $CR $LF $NL $ZW {eof}] |
|
| $SP+ $CM+ $SP |
|
| $SP+ $CM* ([^$OP $CM $SP] | [$AL {eof}])); # if LB 14 will match, need to surpress this break.
|
| - # LB14 says OP SP* x .
|
| + # LB14 says OP SP* x .
|
| # becomes OP SP* x AL
|
| # becomes OP SP* x CM+ AL_FOLLOW
|
| #
|
| # Further note: the $AL in [$AL {eof}] is only to work around
|
| # a rule compiler bug which complains about
|
| # empty sets otherwise.
|
| -
|
| -#
|
| -# Sequences of the form (shown forwards)
|
| -# [CANT_CM] <break> [CM] <break> [PR]
|
| -# The CM needs to behave as an AL
|
| -# This rule is concerned about getting the second of the two <breaks> in place.
|
| -#
|
| -
|
| -[$PR $PRX ] / $CM+ [$BK $CR $LF $NL $ZW $SP {eof}];
|
| -
|
|
|
|
|
| -# LB 4, 5, 5
|
| +# LB 4, 5, 6
|
|
|
| $LB4Breaks [$LB4NonBreaks-$CM];
|
| $LB4Breaks $CM+ $CAN_CM;
|
| @@ -529,30 +407,36 @@ $LF $CR;
|
| # Requires an engine enhancement.
|
| # / $SP* $ZW
|
|
|
| +# LB 8a ZWJ x (ID | Extended_Pict | EmojiNRK)
|
| +#
|
| +($ID | $Extended_Pict | $EmojiNRK) $ZWJ $CM* $CAN_CM?;
|
| +
|
| +
|
| # LB 9,10 Combining marks.
|
| # X $CM needs to behave like X, where X is not $SP or controls.
|
| # $CM not covered by the above needs to behave like $AL
|
| # Stick together any combining sequences that don't match other rules.
|
| -$CM+ $CAN_CM;
|
| +^$CM+ $CAN_CM;
|
|
|
|
|
| # LB 11
|
| -$CM* $WJ $CM* $CAN_CM;
|
| -$CM* $WJ [$LB8NonBreaks-$CM];
|
| +#
|
| +$WJ $CM* $CAN_CM;
|
| +$WJ [$LB8NonBreaks-$CM];
|
|
|
| $CANT_CM $CM* $WJ;
|
| -$CM* $CAN_CM $CM* $WJ;
|
| +$CAN_CM $CM* $WJ;
|
|
|
| # LB 12a
|
| # [^SP BA HY] x GL
|
| #
|
| -$CM* $GL $CM* [$LB8NonBreaks-[$CM $SP $BA $BAX $HY]];
|
| +$GL $CM* [$LB8NonBreaks-[$CM $SP $BA $BAX $HY]];
|
|
|
| # LB 12
|
| # GL x
|
| #
|
| $CANT_CM $CM* $GL;
|
| -$CM* $CAN_CM $CM* $GL;
|
| +$CAN_CM $CM* $GL;
|
|
|
|
|
| # LB 13
|
| @@ -569,34 +453,22 @@ $EX [$LB8NonBreaks-$CM];
|
| $IS [$LB8NonBreaks-$CM];
|
| $SY [$LB8NonBreaks-$CM];
|
|
|
| -# Rule 13 & 14 taken together for an edge case.
|
| -# Match this, shown forward
|
| -# OP SP+ ($CM+ behaving as $AL) (CL | CP | EX | IS | IY)
|
| -# This really wants to chain at the $CM+ (which is acting as an $AL)
|
| -# except for $CM chaining being disabled.
|
| -[$CL $CP $EX $IS $SY] $CM+ $SP+ $CM* $OP;
|
|
|
| # LB 14 OP SP* x
|
| #
|
| -$CM* $CAN_CM $SP* $CM* $OP;
|
| - $CANT_CM $SP* $CM* $OP;
|
| -$AL_FOLLOW? $CM+ $SP $SP* $CM* $OP; # by LB 10, behaves like $AL_FOLLOW? $AL $SP* $CM* $OP
|
| -
|
| - $AL_FOLLOW_NOCM $CM+ $SP+ $CM* $OP;
|
| -$CM* $AL_FOLLOW_CM $CM+ $SP+ $CM* $OP;
|
| -$SY $CM $SP+ $OP; # TODO: Experiment. Remove.
|
| -
|
| +. $SP* $CM* $OP;
|
| +$AL_FOLLOW? $CM+ $SP+ $CM* $OP; # by LB 10, behaves like $AL_FOLLOW? $AL $SP+ $CM* $OP
|
|
|
|
|
| # LB 15
|
| -$CM* $OP $SP* $CM* $QU;
|
| +$OP $SP* $CM* $QU;
|
|
|
| # LB 16
|
| # Don't include $NSX here
|
| -$CM* $NS $SP* $CM* ($CL | $CP);
|
| +$NS $SP* $CM* ($CL | $CP);
|
|
|
| # LB 17
|
| -$CM* $B2 $SP* $CM* $B2;
|
| +$B2 $SP* $CM* $B2;
|
|
|
| # LB 18 break after spaces
|
| # Nothing explicit needed here.
|
| @@ -605,13 +477,13 @@ $CM* $B2 $SP* $CM* $B2;
|
| #
|
| # LB 19
|
| #
|
| -$CM* $QU $CM* $CAN_CM; # . x QU
|
| -$CM* $QU $LB18NonBreaks;
|
| +$QU $CM* $CAN_CM; # . x QU
|
| +$QU $LB18NonBreaks;
|
|
|
|
|
| -$CM* $CAN_CM $CM* $QU; # QU x .
|
| +$CAN_CM $CM* $QU; # QU x .
|
| $CANT_CM $CM* $QU;
|
| -
|
| +
|
| #
|
| # LB 20 Break before and after CB.
|
| # nothing needed here.
|
| @@ -619,35 +491,38 @@ $CM* $CAN_CM $CM* $QU; # QU x .
|
|
|
| # LB 21
|
| # Don't include $BAX or $NSX here
|
| -$CM* ($BA | $HY | $NS) $CM* [$LB20NonBreaks-$CM]; # . x (BA | HY | NS)
|
| +($BA | $HY | $NS) $CM* [$LB20NonBreaks-$CM]; # . x (BA | HY | NS)
|
|
|
| -$CM* [$LB20NonBreaks-$CM] $CM* $BB; # BB x .
|
| -[^$CB] $CM* $BB; #
|
| +[$LB20NonBreaks-$CM] $CM* $BB; # BB x .
|
| +[^$CB] $CM* $BB; #
|
|
|
| # LB21a
|
| -[^$CB]? $CM* ($HY | $BA | $BAX) $CM* $HL;
|
| +[^$CM $CB]? $CM* ($HY | $BA | $BAX) $CM* $HL;
|
|
|
| # LB21b (reverse)
|
| -$CM* $HL $CM* $SY;
|
| +$HL $CM* $SY;
|
|
|
| # LB 22
|
| -$CM* $IN $CM* ($ALPlus | $HL);
|
| -$CM* $IN $CM* $EX;
|
| -$CM* $IN $CM* $ID;
|
| -# $CM* $IN $CM* $IN; # delete this rule for CSS loose
|
| -$CM* $IN $CM* $NU;
|
| +$IN $CM* ($ALPlus | $HL);
|
| +$IN $CM* $EX;
|
| +$IN $CM* ($ID | $EB | $EM);
|
| +# $IN $CM* $IN; # delete this rule for CSS loose
|
| +$IN $CM* $NU;
|
|
|
| # LB 23
|
| # Do not include $POX here
|
| -$CM* $PO $CM* $ID;
|
| -$CM* $NU $CM* ($ALPlus | $HL);
|
| -$CM* ($ALPlus | $HL) $CM* $NU;
|
| +$NU $CM* ($ALPlus | $HL);
|
| +($ALPlus | $HL) $CM* $NU;
|
| +
|
| +# LB23a
|
| +# Do not include $PRX here
|
| +($ID | $EB | $EM) $CM* $PR;
|
| +$PO $CM* ($ID | $EB | $EM);
|
|
|
| # LB 24
|
| # Do not include $PRX here
|
| -$CM* $ID $CM* $PR;
|
| -$CM* ($ALPlus | $HL) $CM* $PR;
|
| -$CM* ($ALPlus | $HL) $CM* ($PO | $POX);
|
| +($ALPlus | $HL) $CM* ($PR | $PO | $POX);
|
| +($PR | $PO | $POX) $CM* ($ALPlus | $HL);
|
|
|
|
|
| # LB 25
|
| @@ -655,37 +530,56 @@ $CM* ($ALPlus | $HL) $CM* ($PO | $POX);
|
| ($CM* ($PR | $PRX | $PO))? ($CM* ($CL | $CP))? ($CM* ($NU | $IS | $SY))* $CM* $NU ($CM* ($OP | $HY))? ($CM* ($PR | $PO | $POX))?;
|
|
|
| # LB 26
|
| -$CM* ($H3 | $H2 | $JV | $JL) $CM* $JL;
|
| -$CM* ($JT | $JV) $CM* ($H2 | $JV);
|
| -$CM* $JT $CM* ($H3 | $JT);
|
| +($H3 | $H2 | $JV | $JL) $CM* $JL;
|
| +($JT | $JV) $CM* ($H2 | $JV);
|
| +$JT $CM* ($H3 | $JT);
|
|
|
| # LB 27
|
| # Do not include $POX or $PRX here
|
| -$CM* $IN $CM* ($H3 | $H2 | $JT | $JV | $JL);
|
| -$CM* $PO $CM* ($H3 | $H2 | $JT | $JV | $JL);
|
| -$CM* ($H3 | $H2 | $JT | $JV | $JL) $CM* $PR;
|
| +$IN $CM* ($H3 | $H2 | $JT | $JV | $JL);
|
| +$PO $CM* ($H3 | $H2 | $JT | $JV | $JL);
|
| + ($H3 | $H2 | $JT | $JV | $JL) $CM* $PR;
|
|
|
| # LB 28
|
| -$CM* ($ALPlus | $HL) $CM* ($ALPlus | $HL);
|
| +($ALPlus | $HL) $CM* ($ALPlus | $HL);
|
|
|
|
|
| # LB 29
|
| -$CM* ($ALPlus | $HL) $CM* $IS;
|
| +($ALPlus | $HL) $CM* $IS;
|
|
|
| # LB 30
|
| -$CM* $OP $CM* ($ALPlus | $HL | $NU);
|
| -$CM* ($ALPlus | $HL | $NU) $CM* $CP;
|
| +$OP $CM* ($ALPlus | $HL | $NU);
|
| +($ALPlus | $HL | $NU) $CM* $CP;
|
|
|
| # LB 30a
|
| -$CM* $RI $CM* $RI;
|
| +# Pairs of Regional Indicators.
|
| +# The following two rules are nearly identical. The first matches only sequences with an odd number of adjacent RIs,
|
| +# the second with an even number. Stripping away the cruft they look like
|
| +# [^RI] RI / (RI RI)+ ^RI;
|
| +# [^RI] RI RI / (RI RI)+ ^RI;
|
| +#
|
| +# Line Loose tailoring: Don't include NSX here.
|
| +[{bof} $NS $HY $BA $QU $CL $CP $EX $IS $SY $WJ $GL $ZW $SP $BK $CR $LF $NL $ZWJ] $CM* $RI / ($CM* $RI $CM* $RI)+ $CM* [{eof}[^$RI $CM]];
|
| +[{bof} $NS $HY $BA $QU $CL $CP $EX $IS $SY $WJ $GL $ZW $SP $BK $CR $LF $NL $ZWJ] $CM* $RI $CM* $RI / ($CM* $RI $CM* $RI)+ $CM* [{eof}[^$RI $CM]];
|
| +
|
| +# In general, adjacent RIs stay together. The hard-break rules, above, overide this, forcing in the boundaries between pairs.
|
| +$RI $CM* $RI;
|
| +
|
| +# WJ, GL, QU, etc. are classes with rules like "WJ x " which includes "WJ x RI".
|
| +$RI $CM* ([$WJ $GL $QU $BB] | (($HY | $BA)$CM* $HL));
|
| +
|
| +
|
| +# LB 30b Do not break between an Emoji Base and an Emoji Modifier
|
| +$EM $CM* $EB;
|
| +
|
|
|
| ## -------------------------------------------------
|
|
|
| !!safe_reverse;
|
|
|
| # LB 9
|
| -$CM+ [^$CM $BK $CR $LF $NL $ZW $SP];
|
| -$CM+ $SP / .;
|
| +^$CM+ [^$CM $BK $CR $LF $NL $ZW $SP];
|
| +^$CM+ $SP / .;
|
|
|
| # LB 14
|
| $SP+ $CM* $OP;
|
| @@ -706,6 +600,9 @@ $CM* ($HY | $BA | $BAX) $CM* $HL;
|
| ($CM* ($IS | $SY))+ $CM* $NU;
|
| ($CL | $CP) $CM* ($NU | $IS | $SY);
|
|
|
| +# LB 30
|
| +($CM* $RI)+;
|
| +
|
| # For dictionary-based break
|
| $dictionary $dictionary;
|
|
|
| @@ -722,6 +619,6 @@ $dictionary $dictionary;
|
| # turn off rule chaining. We don't want to move more
|
| # than necessary.
|
| #
|
| -[$CM $OP $QU $CL $CP $B2 $PR $PRX $HY $BA $BAX $SP $dictionary]+ [^$CM $OP $QU $CL $CP $B2 $PR $PRX $HY $BA $BAX $dictionary];
|
| +^[$CM $OP $QU $CL $CP $B2 $PR $PRX $HY $BA $BAX $SP $RI $ZWJ $dictionary]+ [^$CM $OP $QU $CL $CP $B2 $PR $PRX $HY $BA $BAX $RI $ZWJ $dictionary];
|
| $dictionary $dictionary;
|
|
|
|
|
Chromium Code Reviews