#
# Line Breaking Rules
# Implement default line breaking as defined by
-# Unicode Standard Annex #14 Revision 40 for Unicode 11.0
-# http://www.unicode.org/reports/tr14/
+# Unicode Standard Annex #14 Revision 42 for Unicode 12.0
+# http://www.unicode.org/reports/tr14/, with the following modification:
#
-# 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.
+# Boundaries between hyphens and following letters are suppressed when
+# there is a boundary preceding the hyphen. See rule 20.9
#
# This tailors the line break behavior to correspond to CSS
# line-break=loose (BCP47 -u-lb-loose) as defined for Chinese & Japanese.
# this includes: 00B0 2030 2032 2033 2035 2103 2109 FE6A FF05 FFE0
# * after prefix characters with LineBreak class PR and EastAsianWidth A,F,W;
# this includes: 00A4 00B1 20AC 2116 FE69 FF04 FFE1 FFE5 FFE6
+# It allows breaking before 201C and after 201D, for zh_Hans, zh_Hant, and ja.
#
$AL = [:LineBreak = Alphabetic:];
$BAX = [\u2010 \u2013];
$BA = [[:LineBreak = Break_After:] - $BAX];
+$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:];
+$CL = [[:LineBreak = Close_Punctuation:] \u201d];
# $CM = [:LineBreak = Combining_Mark:];
$CP = [:LineBreak = Close_Parenthesis:];
$CR = [:LineBreak = Carriage_Return:];
-$EB = [[:LineBreak = EB:] \U0001F46A-\U0001F46D\U0001F46F\U0001F91D\U0001F93C];
+$EB = [:LineBreak = EB:];
$EM = [:LineBreak = EM:];
$EXX = [\uFF01 \uFF1F];
$EX = [[:LineBreak = Exclamation:] - $EXX];
$NSX = [\u301C \u30A0 \u3005 \u303B \u309D \u309E \u30FD \u30FE \u203C \u2047 \u2048 \u2049 \u30FB \uFF1A \uFF1B \uFF65];
$NS = [[:LineBreak = Nonstarter:] - $NSX];
$NU = [:LineBreak = Numeric:];
-$OP = [:LineBreak = Open_Punctuation:];
+$OP = [[:LineBreak = Open_Punctuation:] \u201c];
$POX = [\u00B0 \u2030 \u2032 \u2033 \u2035 \u2103 \u2109 \uFE6A \uFF05 \uFFE0];
$PO = [[:LineBreak = Postfix_Numeric:] - $POX];
$PRX = [\u00A4 \u00B1 \u20AC \u2116 \uFE69 \uFF04 \uFFE1 \uFFE5 \uFFE6];
$PR = [[:LineBreak = Prefix_Numeric:] - $PRX];
-$QU = [:LineBreak = Quotation:];
+$QU = [[:LineBreak = Quotation:] - [\u201c\u201d]];
$RI = [:LineBreak = Regional_Indicator:];
$SA = [:LineBreak = Complex_Context:];
$SG = [:LineBreak = Surrogate:];
# By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
$CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
+$CMX = [[$CM] - [$ZWJ]];
# Dictionary character set, for triggering language-based break engines. Currently
# limited to LineBreak=Complex_Context (SA).
#
# 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>
+# ZW SP* รท
#
$LB8Breaks = [$LB4Breaks $ZW];
$LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
+$ZW $SP* / [^$SP $ZW $LB4Breaks];
# LB 8a ZWJ x Do not break Emoji ZWJ sequences.
#
^$CM+ $GL;
-#
-# LB 13 Don't break before ']' or '!' or ';' or '/', even after spaces.
+
+# LB 13 Don't break before ']' or '!' or or '/', even after spaces.
#
# Do not include $EXX here
$LB8NonBreaks $CL;
$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
+# Note subtle interaction with "SP IS /" rules in LB14a.
+# This rule consumes the SP, chaining happens on the IS, effectivley overriding the SP IS rules,
+# which is the desired behavior.
#
$OP $CM* $SP* .;
$OP $CM* $SP+ $CM+ $AL_FOLLOW?; # by rule 10, stand-alone CM behaves as AL
# by rule 8, CM following a SP is stand-alone.
+
+# LB 14a Force a break before start of a number with a leading decimal pt, e.g. " .23"
+# Note: would be simpler to express as "$SP / $IS $CM* $NU;", but ICU rules have limitations.
+# See issue ICU-20303
+
+
+$CanFollowIS = [$BK $CR $LF $NL $SP $ZW $WJ $GL $CL $CP $EX $IS $SY $QU $BA $HY $NS $ALPlus $HL];
+$SP $IS / [^ $CanFollowIS $NU $CM];
+$SP $IS $CM* $CMX / [^ $CanFollowIS $NU $CM];
+
+#
+# LB 14b Do not break before numeric separators (IS), even after spaces.
+
+[$LB8NonBreaks - $SP] $IS;
+$SP $IS $CM* [$CanFollowIS {eof}];
+$SP $IS $CM* $ZWJ [^$CM $NU];
+
+$CAN_CM $CM* $IS;
+^$CM+ $IS; # by rule 10, stand-alone CM behaves as AL
+
+
# LB 15
$QU $CM* $SP* $OP;
# QU x
$QU $CM* .;
-
# LB 20
# <break> $CB
# $CB <break>
-
+#
$LB20NonBreaks = [$LB18NonBreaks - $CB];
+# LB 20.09 Don't break between Hyphens and Letters when there is a break preceding the hyphen.
+# Originally added as a Finnish tailoring, now promoted to default ICU behavior.
+# Note: this is not default UAX-14 behaviour. See issue ICU-8151.
+#
+^($HY | $HH) $CM* $ALPlus;
+
# LB 21 x (BA | HY | NS)
# BB x
#
# DO allow breaks here before $BAX and $NSX, so don't include them
$LB20NonBreaks $CM* ($BA | $HY | $NS);
+
+
^$CM+ ($BA | $HY | $NS);
$BB $CM* [^$CB]; # $BB x
# LB 25 Numbers.
#
# Here do not include $PRX at the beginning or $POX at the end
-(($PR | $PO | $POX) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
+(($PR | $PO | $POX) $CM*)? (($OP | $HY) $CM*)? ($IS $CM*)? $NU ($CM* ($NU | $SY | $IS))*
($CM* ($CL | $CP))? ($CM* ($PR | $PRX | $PO))?;
# LB 26 Do not break a Korean syllable
projects / apple / icu.git / blobdiff