ICU-64260.0.1.tar.gz

[apple/icu.git] / icuSources / data / brkitr / rules / line.txt

diff --git a/icuSources/data/brkitr/rules/line.txt b/icuSources/data/brkitr/rules/line.txt
index 993a2fa035e81a334d15364a4d9f2af0ef87f219..059ace966d3676ffa524254166b72d189c29024e 100644 (file)
--- a/icuSources/data/brkitr/rules/line.txt
+++ b/icuSources/data/brkitr/rules/line.txt
@@ -7,12 +7,11 @@
 #
 #         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:
 #
-#         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 corresponds to CSS line-break=strict (BCP47 -u-lb-strict).
 #         It sets characters of class CJ to behave like NS.
@@ -27,6 +26,7 @@
 $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:];
@@ -36,7 +36,7 @@ $CL = [:LineBreak =  Close_Punctuation:];
 # $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:];
 $EX = [:LineBreak =  Exclamation:];
 $GL = [:LineBreak =  Glue:];
@@ -79,6 +79,7 @@ $ZWJ = [:LineBreak = ZWJ:];
 # 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).
@@ -137,12 +138,11 @@ $CAN_CM $CM*  [$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>
+#              ZW SP* ÷
 #
 $LB8Breaks    = [$LB4Breaks $ZW];
 $LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
+$ZW $SP* / [^$SP $ZW $LB4Breaks];
 
 # LB 8a        ZWJ x            Do not break Emoji ZWJ sequences.
 #
@@ -179,8 +179,8 @@ $GL $CM* .;
 
 
 
-#
-# LB 13   Don't break before ']' or '!' or ';' or '/', even after spaces.
+
+# LB 13   Don't break before ']' or '!' or or '/', even after spaces.
 #
 $LB8NonBreaks $CL;
 $CAN_CM $CM*  $CL;
@@ -194,10 +194,6 @@ $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
@@ -205,12 +201,36 @@ $CAN_CM $CM*  $SY;
 
 #
 # 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;
 
@@ -235,17 +255,24 @@ $LB18NonBreaks $CM* $QU;
 #         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
 #
 $LB20NonBreaks $CM* ($BA | $HY | $NS);
+
+
 ^$CM+ ($BA | $HY | $NS);
 
 $BB $CM* [^$CB];                                  #  $BB  x
@@ -291,7 +318,7 @@ $PR $CM* ($ID | $EB | $EM);
 #
 # LB 25   Numbers.
 #
-(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? $NU ($CM* ($NU | $SY | $IS))*
+(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? ($IS $CM*)? $NU ($CM* ($NU | $SY | $IS))*
     ($CM* ($CL | $CP))? ($CM* ($PR | $PO))?;
 
 # LB 26  Do not break a Korean syllable