ICU-66108.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 059ace966d3676ffa524254166b72d189c29024e..5b0db0b44f223532ec9f5402da00bd45b3918839 100644 (file)
--- a/icuSources/data/brkitr/rules/line.txt
+++ b/icuSources/data/brkitr/rules/line.txt
@@ -7,7 +7,7 @@
 #
 #         Line Breaking Rules
 #         Implement default line breaking as defined by
-#         Unicode Standard Annex #14 Revision 42 for Unicode 12.0
+#         Unicode Standard Annex #14 Revision 44 for Unicode 13.0
 #         http://www.unicode.org/reports/tr14/, with the following modification:
 #
 #         Boundaries between hyphens and following letters are suppressed when
@@ -74,6 +74,13 @@ $ZWJ = [:LineBreak = ZWJ:];
 #  $EmojiNRK = [[\p{Emoji}] - [$RI \u002a\u00230-9©®™〰〽]];
 #  $Extended_Pict = [:ExtPict:];
 
+# OP30 and CP30 are variants of OP and CP that appear in-line in rule LB30 from UAX 14,
+# without a formal name. Because ICU rules require multiple uses of the expressions,
+# give them a single definition with a name
+
+$OP30 = [$OP - [\p{ea=F}\p{ea=W}\p{ea=H}]];
+$CP30 = [$CP - [\p{ea=F}\p{ea=W}\p{ea=H}]];
+
 # 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.
@@ -113,7 +120,7 @@ $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 $HY $NS $IN $NU $PR $PO $ALPlus];
+$AL_FOLLOW      = [$BK $CR $LF $NL $ZW $SP $CL $CP $EX $HL $IS $SY $WJ $GL $OP30 $QU $BA $HY $NS $IN $NU $PR $PO $ALPlus];
 
 
 #
@@ -216,7 +223,7 @@ $OP $CM* $SP+ $CM+ $AL_FOLLOW?;    # by rule 10, stand-alone CM behaves as AL
 #        See issue ICU-20303
 
 
-$CanFollowIS = [$BK $CR $LF $NL $SP $ZW $WJ $GL $CL $CP $EX $IS $SY $QU $BA $HY $NS $ALPlus $HL];
+$CanFollowIS = [$BK $CR $LF $NL $SP $ZW $WJ $GL $CL $CP $EX $IS $SY $QU $BA $HY $NS $ALPlus $HL $IN];
 $SP $IS           / [^ $CanFollowIS $NU $CM];
 $SP $IS $CM* $CMX / [^ $CanFollowIS $NU $CM];
 
@@ -287,16 +294,13 @@ $HL $CM* ($HY | $BA) $CM* [^$CB]?;
 # (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*    $IN;
+# LB 22  Do not break before ellipses
+#
+$LB20NonBreaks $CM*    $IN;
+^$CM+ $IN;
 
 
-# $LB 23
+# LB 23
 #
 ($ALPlus | $HL) $CM* $NU;
 ^$CM+  $NU;       # Rule 10, any otherwise unattached CM behaves as AL
@@ -342,15 +346,15 @@ $PR $CM* ($JL | $JV | $JT | $H2 | $H3);
 $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 | $NU);
+($ALPlus | $HL | $NU) $CM* $OP30;
+^$CM+ $OP30;         # The $CM+ is from rule 10, an unattached CM is treated as AL.
+$CP30 $CM* ($ALPlus | $HL | $NU);
 
 # LB 30a  Do not break between regional indicators. Break after pairs of them.
 #         Tricky interaction with LB8a: ZWJ x .   together with ZWJ acting like a CM.
-$RI $CM* $RI                 / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM]];
-$RI $CM* $RI $CM* [$CM-$ZWJ] / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM]];
-$RI $CM* $RI $CM* [$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $ZWJ {eof}];
+$RI $CM* $RI                 / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $IN $CM]];
+$RI $CM* $RI $CM* [$CM-$ZWJ] / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $IN $CM]];
+$RI $CM* $RI $CM* [$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $IN $ZWJ {eof}];
 # note: the preceding rule includes {eof} rather than having the last [set] term qualified with '?'
 #       because of the chain-out behavior difference. The rule must chain out only from the [set characters],
 #       not from the preceding $RI or $CM, which it would be able to do if the set were optional.