| # Copyright (c) 2002-2016 International Business Machines Corporation and |
| # others. All Rights Reserved. |
| # |
| # file: line_normal_fi.txt |
| # |
| # Line Breaking Rules |
| # Implement default line breaking as defined by |
| # Unicode Standard Annex #14 Revision 35 for Unicode 8.0 |
| # http://www.unicode.org/reports/tr14/ |
| # tailored as noted in 2nd paragraph below. |
| # |
| # Includes the Emoji breaking proposals from Unicode L2/16-011R3. |
| # http://www.unicode.org/L2/L2016/16011r3-break-prop-emoji.pdf |
| # |
| # 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, |
| # not because the older behavior is desirable. |
| # |
| # This tailors the line break behavior for Finnish, and to correspond to CSS |
| # line-break=normal (BCP47 -u-lb-normal) as defined for languages other than |
| # Chinese & Japanese. |
| # It sets characters of class CJ to behave like ID. |
| |
| # |
| # Character Classes defined by TR 14. |
| # |
| |
| !!chain; |
| |
| $AI = [:LineBreak = Ambiguous:]; |
| $AL = [:LineBreak = Alphabetic:]; |
| $BA = [:LineBreak = Break_After:]; |
| $HH = [\u2010]; # \u2010 is HYPHEN, default line break is BA. |
| $BB = [:LineBreak = Break_Before:]; |
| $BK = [:LineBreak = Mandatory_Break:]; |
| $B2 = [:LineBreak = Break_Both:]; |
| $CB = [:LineBreak = Contingent_Break:]; |
| $CJ = [:LineBreak = Conditional_Japanese_Starter:]; |
| $CL = [:LineBreak = Close_Punctuation:]; |
| # $CM = [:LineBreak = Combining_Mark:]; |
| $CP = [:LineBreak = Close_Parenthesis:]; |
| $CR = [:LineBreak = Carriage_Return:]; |
| $EB = [:LineBreak = EB:]; |
| $EM = [:LineBreak = EM:]; |
| $EX = [:LineBreak = Exclamation:]; |
| $GL = [:LineBreak = Glue:]; |
| $HL = [:LineBreak = Hebrew_Letter:]; |
| $HY = [:LineBreak = Hyphen:]; |
| $H2 = [:LineBreak = H2:]; |
| $H3 = [:LineBreak = H3:]; |
| # CSS Normal tailoring: CJ resolves to ID |
| $ID = [[:LineBreak = Ideographic:] $CJ]; |
| $IN = [:LineBreak = Inseperable:]; |
| $IS = [:LineBreak = Infix_Numeric:]; |
| $JL = [:LineBreak = JL:]; |
| $JV = [:LineBreak = JV:]; |
| $JT = [:LineBreak = JT:]; |
| $LF = [:LineBreak = Line_Feed:]; |
| $NL = [:LineBreak = Next_Line:]; |
| $NS = [:LineBreak = Nonstarter:]; |
| $NU = [:LineBreak = Numeric:]; |
| $OP = [:LineBreak = Open_Punctuation:]; |
| $PO = [:LineBreak = Postfix_Numeric:]; |
| $PR = [:LineBreak = Prefix_Numeric:]; |
| $QU = [:LineBreak = Quotation:]; |
| $RI = [:LineBreak = Regional_Indicator:]; |
| $SA = [:LineBreak = Complex_Context:]; |
| $SG = [:LineBreak = Surrogate:]; |
| $SP = [:LineBreak = Space:]; |
| $SY = [:LineBreak = Break_Symbols:]; |
| $WJ = [:LineBreak = Word_Joiner:]; |
| $XX = [:LineBreak = Unknown:]; |
| $ZW = [:LineBreak = ZWSpace:]; |
| $ZWJ = [:LineBreak = ZWJ:]; |
| |
| # 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 (SA). |
| |
| $dictionary = [$SA]; |
| |
| # |
| # Rule LB1. By default, treat AI (characters with ambiguous east Asian width), |
| # SA (Dictionary chars, excluding Mn and Mc) |
| # SG (Unpaired Surrogates) |
| # XX (Unknown, unassigned) |
| # as $AL (Alphabetic) |
| # |
| $ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]]; |
| |
| |
| ## ------------------------------------------------- |
| |
| !!forward; |
| |
| # |
| # 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. |
| # |
| # Note that $CM itself is left out of this set. If CM is needed as a base |
| # it must be listed separately in the rule. |
| # |
| $CAN_CM = [^$SP $BK $CR $LF $NL $ZW $CM]; # Bases that can take CMs |
| $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. |
| # |
| $AL_FOLLOW = [$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]; |
| |
| |
| # |
| # Rule LB 4, 5 Mandatory (Hard) breaks. |
| # |
| $LB4Breaks = [$BK $CR $LF $NL]; |
| $LB4NonBreaks = [^$BK $CR $LF $NL $CM]; |
| $CR $LF {100}; |
| |
| # |
| # LB 6 Do not break before hard line breaks. |
| # |
| $LB4NonBreaks? $LB4Breaks {100}; # LB 5 do not break before hard breaks. |
| $CAN_CM $CM* $LB4Breaks {100}; |
| ^$CM+ $LB4Breaks {100}; |
| |
| # LB 7 x SP |
| # x ZW |
| $LB4NonBreaks [$SP $ZW]; |
| $CAN_CM $CM* [$SP $ZW]; |
| ^$CM+ [$SP $ZW]; |
| |
| # |
| # LB 8 Break after zero width space |
| # TODO: ZW SP* <break> |
| # An engine change is required to write the reverse rule for this. |
| # For now, leave the Unicode 5.2 rule, ZW <break> |
| # |
| $LB8Breaks = [$LB4Breaks $ZW]; |
| $LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]]; |
| |
| # LB 8a ZWJ x (ID | EB | EM) Emoji ZWJ sequences. |
| # |
| $ZWJ ($ID | $EB | $EM); |
| |
| # 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+; |
| |
| # |
| # LB 11 Do not break before or after WORD JOINER & related characters. |
| # |
| $CAN_CM $CM* $WJ; |
| $LB8NonBreaks $WJ; |
| ^$CM+ $WJ; |
| |
| $WJ $CM* .; |
| |
| # |
| # LB 12 Do not break after NBSP and related characters. |
| # GL x |
| # |
| $GL $CM* .; |
| |
| # |
| # LB 12a Do not break before NBSP and related characters ... |
| # [^SP BA HY] x GL |
| # |
| [[$LB8NonBreaks] - [$SP $BA $HH $HY]] $CM* $GL; |
| ^$CM+ $GL; |
| |
| |
| |
| # |
| # LB 13 Don't break before ']' or '!' or ';' or '/', even after spaces. |
| # |
| $LB8NonBreaks $CL; |
| $CAN_CM $CM* $CL; |
| ^$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 |
| |
| $LB8NonBreaks $EX; |
| $CAN_CM $CM* $EX; |
| ^$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 |
| |
| $LB8NonBreaks $SY; |
| $CAN_CM $CM* $SY; |
| ^$CM+ $SY; # by rule 10, stand-alone CM behaves as AL |
| |
| |
| # |
| # LB 14 Do not break after OP, even after spaces |
| # |
| $OP $CM* $SP* .; |
| |
| $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 |
| $QU $CM* $SP* $OP; |
| |
| # LB 16 |
| ($CL | $CP) $CM* $SP* $NS; |
| |
| # LB 17 |
| $B2 $CM* $SP* $B2; |
| |
| # |
| # LB 18 Break after spaces. |
| # |
| $LB18NonBreaks = [$LB8NonBreaks - [$SP]]; |
| $LB18Breaks = [$LB8Breaks $SP]; |
| |
| |
| # LB 19 |
| # x QU |
| $LB18NonBreaks $CM* $QU; |
| ^$CM+ $QU; |
| |
| # QU x |
| $QU $CM* .; |
| |
| |
| # LB 20 |
| # <break> $CB |
| # $CB <break> |
| |
| $LB20NonBreaks = [$LB18NonBreaks - $CB]; |
| |
| # LB 20.09 added rule for Finnish tailoring |
| # LB 21 x (BA | HY | NS) |
| # BB x |
| # |
| $LB20NonBreaks $CM* ($BA | $HH | $HY | $NS) $CM* / $AL; |
| $LB20NonBreaks $CM* ($BA | $HH | $HY | $NS); |
| ($HY | $HH) $AL; |
| ^$CM+ ($BA | $HY | $HH | $NS); |
| |
| $BB $CM* [^$CB]; # $BB x |
| $BB $CM* $LB20NonBreaks; |
| |
| # LB 21a Don't break after Hebrew + Hyphen |
| # HL (HY | BA) x |
| # |
| $HL $CM* ($HY | $BA | $HH) $CM* [^$CB]?; |
| |
| # LB 21b (forward) Don't break between SY and HL |
| # (break between HL and SY already disallowed by LB 13 above) |
| $SY $CM* $HL; |
| |
| # LB 22 |
| ($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; |
| $NU $CM* $IN; |
| |
| |
| # $LB 23 |
| # |
| ($ALPlus | $HL) $CM* $NU; |
| ^$CM+ $NU; # Rule 10, any otherwise unattached CM behaves as AL |
| $NU $CM* ($ALPlus | $HL); |
| |
| # LB 23a |
| # |
| $PR $CM* ($ID | $EB | $EM); |
| ($ID | $EB | $EM) $CM* $PO; |
| |
| |
| # |
| # LB 24 |
| # |
| ($PR | $PO) $CM* ($ALPlus | $HL); |
| ($ALPlus | $HL) $CM* ($PR | $PO); |
| ^$CM+ ($PR | $PO); # Rule 10, any otherwise unattached CM behaves as AL |
| |
| # |
| # LB 25 Numbers. |
| # |
| (($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))* |
| ($CM* ($CL | $CP))? ($CM* ($PR | $PO))?; |
| |
| # LB 26 Do not break a Korean syllable |
| # |
| $JL $CM* ($JL | $JV | $H2 | $H3); |
| ($JV | $H2) $CM* ($JV | $JT); |
| ($JT | $H3) $CM* $JT; |
| |
| # LB 27 Treat korean Syllable Block the same as ID (don't break it) |
| ($JL | $JV | $JT | $H2 | $H3) $CM* $IN; |
| ($JL | $JV | $JT | $H2 | $H3) $CM* $PO; |
| $PR $CM* ($JL | $JV | $JT | $H2 | $H3); |
| |
| |
| # LB 28 Do not break between alphabetics |
| # |
| ($ALPlus | $HL) $CM* ($ALPlus | $HL); |
| ^$CM+ ($ALPlus | $HL); # The $CM+ is from rule 10, an unattached CM is treated as AL |
| |
| # LB 29 |
| $IS $CM* ($ALPlus | $HL); |
| |
| # LB 30 |
| ($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 $EB $EM] {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 | $EB | $EM); |
| |
| # LB 30b Do not break between an Emoji Base and an Emoji Modifier |
| $EB $CM* $EM; |
| |
| # |
| # Reverse Rules. |
| # |
| ## ------------------------------------------------- |
| |
| !!reverse; |
| |
| # LB 9 Combining Marks. |
| # Stick together any combining sequences that don't match other rules. |
| |
| ^$CM+ $CAN_CM?; |
| |
| # |
| # Sequences of the form (shown forwards) |
| # [CANT_CM] <break> [CM] [whatever] |
| # The CM needs to behave as an AL |
| # |
| $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 . |
| # 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. |
| |
| |
| # LB 4, 5, 6 |
| |
| $LB4Breaks [$LB4NonBreaks-$CM]; |
| $LB4Breaks $CM+ $CAN_CM; |
| $LF $CR; |
| |
| |
| # LB 7 x SP |
| # x ZW |
| [$SP $ZW] [$LB4NonBreaks-$CM]; |
| [$SP $ZW] $CM+ $CAN_CM; |
| |
| # LB 8 ZW SP* <break> |
| # TODO: to implement this, we need more than one look-ahead hard break in play at a time. |
| # Requires an engine enhancement. |
| # / $SP* $ZW |
| |
| # LB 8a ZWJ x ID Unicode Emoji proposal L2/16-011R3 |
| # The ZWJ will look like a CM to whatever precedes it. |
| # |
| ($ID | $EB | $EM) $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; |
| |
| |
| # LB 11 |
| # |
| $WJ $CM* $CAN_CM; |
| $WJ [$LB8NonBreaks-$CM]; |
| |
| $CANT_CM $CM* $WJ; |
| $CAN_CM $CM* $WJ; |
| |
| # LB 12a |
| # [^SP BA HY] x GL |
| # |
| $GL $CM* [$LB8NonBreaks-[$CM $SP $BA $HH $HY]]; |
| |
| # LB 12 |
| # GL x |
| # |
| $CANT_CM $CM* $GL; |
| $CAN_CM $CM* $GL; |
| |
| |
| # LB 13 |
| $CL $CM+ $CAN_CM; |
| $CP $CM+ $CAN_CM; |
| $EX $CM+ $CAN_CM; |
| $IS $CM+ $CAN_CM; |
| $SY $CM+ $CAN_CM; |
| |
| $CL [$LB8NonBreaks-$CM]; |
| $CP [$LB8NonBreaks-$CM]; |
| $EX [$LB8NonBreaks-$CM]; |
| $IS [$LB8NonBreaks-$CM]; |
| $SY [$LB8NonBreaks-$CM]; |
| |
| |
| # LB 14 OP SP* x |
| # |
| . $SP* $CM* $OP; |
| $AL_FOLLOW? $CM+ $SP+ $CM* $OP; # by LB 10, behaves like $AL_FOLLOW? $AL $SP+ $CM* $OP |
| |
| |
| # LB 15 |
| $OP $SP* $CM* $QU; |
| |
| # LB 16 |
| $NS $SP* $CM* ($CL | $CP); |
| |
| # LB 17 |
| $B2 $SP* $CM* $B2; |
| |
| # LB 18 break after spaces |
| # Nothing explicit needed here. |
| |
| |
| # |
| # LB 19 |
| # |
| $QU $CM* $CAN_CM; # . x QU |
| $QU $LB18NonBreaks; |
| |
| |
| $CAN_CM $CM* $QU; # QU x . |
| $CANT_CM $CM* $QU; |
| |
| # |
| # LB 20 Break before and after CB. |
| # nothing needed here. |
| # |
| |
| # LB 20.09 added rule for Finnish tailoring |
| $AL ($HY | $HH) / $SP; |
| |
| # LB 21 |
| ($BA | $HH | $HY | $NS) $CM* [$LB20NonBreaks-$CM]; # . x (BA | HY | NS) |
| |
| [$LB20NonBreaks-$CM] $CM* $BB; # BB x . |
| [^$CB] $CM* $BB; # |
| |
| # LB21a |
| [^$CB] $CM* ($HY | $BA | $HH) $CM* $HL; |
| |
| # LB21b (reverse) |
| $HL $CM* $SY; |
| |
| # LB 22 |
| $IN $CM* ($ALPlus | $HL); |
| $IN $CM* $EX; |
| $IN $CM* ($ID | $EB | $EM); |
| $IN $CM* $IN; |
| $IN $CM* $NU; |
| |
| # LB 23 |
| $NU $CM* ($ALPlus | $HL); |
| ($ALPlus | $HL) $CM* $NU; |
| |
| # LB23a |
| ($ID | $EB | $EM) $CM* $PR; |
| $PO $CM* ($ID | $EB | $EM); |
| |
| # LB 24 |
| ($ALPlus | $HL) $CM* ($PR | $PO); |
| ($PR | $PO) $CM* ($ALPlus | $HL); |
| |
| |
| # LB 25 |
| ($CM* ($PR | $PO))? ($CM* ($CL | $CP))? ($CM* ($NU | $IS | $SY))* $CM* $NU ($CM* ($OP | $HY))? ($CM* ($PR | $PO))?; |
| |
| # LB 26 |
| ($H3 | $H2 | $JV | $JL) $CM* $JL; |
| ($JT | $JV) $CM* ($H2 | $JV); |
| $JT $CM* ($H3 | $JT); |
| |
| # LB 27 |
| $IN $CM* ($H3 | $H2 | $JT | $JV | $JL); |
| $PO $CM* ($H3 | $H2 | $JT | $JV | $JL); |
| ($H3 | $H2 | $JT | $JV | $JL) $CM* $PR; |
| |
| # LB 28 |
| ($ALPlus | $HL) $CM* ($ALPlus | $HL); |
| |
| |
| # LB 29 |
| ($ALPlus | $HL) $CM* $IS; |
| |
| # LB 30 |
| $OP $CM* ($ALPlus | $HL | $NU); |
| ($ALPlus | $HL | $NU) $CM* $CP; |
| |
| # LB 30a |
| # 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; |
| # |
| [{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 / .; |
| |
| # LB 14 |
| $SP+ $CM* $OP; |
| |
| # LB 15 |
| $SP+ $CM* $QU; |
| |
| # LB 16 |
| $SP+ $CM* ($CL | $CP); |
| |
| # LB 17 |
| $SP+ $CM* $B2; |
| |
| # LB 21 |
| $CM* ($HY | $BA | $HH) $CM* $HL; |
| |
| # LB 25 |
| ($CM* ($IS | $SY))+ $CM* $NU; |
| ($CL | $CP) $CM* ($NU | $IS | $SY); |
| |
| # LB 30 |
| ($CM* $RI)+; |
| |
| # For dictionary-based break |
| $dictionary $dictionary; |
| |
| ## ------------------------------------------------- |
| |
| !!safe_forward; |
| |
| # Skip forward over all character classes that are involved in |
| # rules containing patterns with possibly more than one char |
| # of context. |
| # |
| # It might be slightly more efficient to have specific rules |
| # instead of one generic one, but only if we could |
| # turn off rule chaining. We don't want to move more |
| # than necessary. |
| # |
| ^[$CM $OP $QU $CL $CP $B2 $PR $HY $BA $SP $RI $ZWJ $dictionary]+ [^$CM $OP $QU $CL $CP $B2 $PR $HY $BA $RI $ZWJ $dictionary]; |
| $dictionary $dictionary; |
| |