summaryrefslogtreecommitdiff
path: root/i18npool/source/breakiterator/data/line.txt
diff options
context:
space:
mode:
Diffstat (limited to 'i18npool/source/breakiterator/data/line.txt')
-rw-r--r--i18npool/source/breakiterator/data/line.txt680
1 files changed, 218 insertions, 462 deletions
diff --git a/i18npool/source/breakiterator/data/line.txt b/i18npool/source/breakiterator/data/line.txt
index ff3f3eafc42e..46a618c63cae 100644
--- a/i18npool/source/breakiterator/data/line.txt
+++ b/i18npool/source/breakiterator/data/line.txt
@@ -1,176 +1,116 @@
-# Copyright (c) 2002-2006 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.txt
#
# Line Breaking Rules
-# Implement default line breaking as defined by Unicode Standard Annex #14 version 5.0.0
-# http://www.unicode.org/reports/tr14/
-
-
+# Implement default line breaking as defined by
+# Unicode Standard Annex #14 (https://www.unicode.org/reports/tr14/)
+# for Unicode 14.0, with the following modification:
+#
+# 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.
#
# Character Classes defined by TR 14.
#
-!!chain;
-!!LBCMNoChain;
+### BEGIN CUSTOMIZATION
+### This file contains LibreOffice-specific rule customizations.
+###
+### To aid future maintainability:
+### - The change location should be bracketed by comments of this form.
+### - The original rule should be commented out, and the modified rule placed alongside.
+### - By doing this, maintainers can more easily compare to an upstream baseline.
+###
+### END CUSTOMIZATION
-
-!!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 the incredibly annoying 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.
-#
+!!chain;
+!!quoted_literals_only;
$AI = [:LineBreak = Ambiguous:];
-$DG = \u00B0;
-$AL = [[:LineBreak = Alphabetic:] $DG];
+$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:] [:LineBreak = Close_Parenthesis:]]; # tdf#31271
-$CM = [:LineBreak = Combining_Mark:];
+$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:];
$H3 = [:LineBreak = H3:];
-$ID = [[:LineBreak = Ideographic:] - [\ufe30]];
-$IN = [:LineBreak = Inseparable:];
-$IS = [[:LineBreak = Infix_Numeric:] [\ufe30]];
+$ID = [:LineBreak = Ideographic:];
+$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 includes CJ for CSS strict line breaking.
$NS = [[:LineBreak = Nonstarter:] $CJ];
$NU = [:LineBreak = Numeric:];
-$OP = [[:LineBreak = Open_Punctuation:] - $DG];
+$OP = [:LineBreak = Open_Punctuation:];
$PO = [:LineBreak = Postfix_Numeric:];
-$BS = \u005C;
-$PR = [[:LineBreak = Prefix_Numeric:] - $BS];
+$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:] $BS];
+$SY = [:LineBreak = Break_Symbols:];
$WJ = [:LineBreak = Word_Joiner:];
$XX = [:LineBreak = Unknown:];
$ZW = [:LineBreak = ZWSpace:];
+$ZWJ = [:LineBreak = ZWJ:];
+
+# 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}]];
+
+$ExtPictUnassigned = [\p{Extended_Pictographic} & \p{Cn}];
+
+# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
+# list it in the numerous rules that use CM.
+# By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
+
+$CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
+$CMX = [[$CM] - [$ZWJ]];
# Dictionary character set, for triggering language-based break engines. Currently
-# limited to LineBreak=Complex_Context. Note that this set only works in Unicode
-# 5.0 or later as the definition of Complex_Context was corrected to include all
-# characters requiring dictionary break.
+# limited to LineBreak=Complex_Context (SA).
-$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 $CM*;
-$BBcm = $BB $CM*;
-$B2cm = $B2 $CM*;
-$CLcm = $CL $CM*;
-$EXcm = $EX $CM*;
-$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 $CM*;
-$NUcm = $NU $CM*;
-$OPcm = $OP $CM*;
-$POcm = $PO $CM*;
-$PRcm = $PR $CM*;
-$QUcm = $QU $CM*;
-$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 $CM+;
-$BB $CM+;
-$B2 $CM+;
-$CL $CM+;
-$EX $CM+;
-$GL $CM+;
-$HL $CM+;
-$HY $CM+;
-$H2 $CM+;
-$H3 $CM+;
-$ID $CM+;
-$IN $CM+;
-$IS $CM+;
-$JL $CM+;
-$JV $CM+;
-$JT $CM+;
-$NS $CM+;
-$NU $CM+;
-$OP $CM+;
-$PO $CM+;
-$PR $CM+;
-$QU $CM+;
-$SY $CM+;
-$WJ $CM+;
+## -------------------------------------------------
#
# CAN_CM is the set of characters that may combine with CM combining chars.
@@ -186,19 +126,15 @@ $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 $EX $HL $IS $SY $WJ $GL $QU $BA $HY $NS $IN $NU $ALPlus $OP];
-$AL_FOLLOW = [$AL_FOLLOW_NOCM $AL_FOLLOW_CM];
+$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];
#
# 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};
#
@@ -206,91 +142,124 @@ $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
+# ZW SP* ÷
#
$LB8Breaks = [$LB4Breaks $ZW];
$LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
+$ZW $SP* / [^$SP $ZW $LB4Breaks];
+# LB 8a ZWJ x Do not break Emoji ZWJ sequences.
+#
+$ZWJ [^$CM];
-# 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 [^$CAN_CM];
-$WJcm $CAN_CM $CM*;
+$WJ $CM* .;
#
-# LB 12 Do not break before or after NBSP and related characters.
+# LB 12 Do not break after NBSP and related characters.
+# GL x
#
-# (!SP) x GL
-[$LB8NonBreaks-$SP] $CM* $GLcm;
-$CM+ $GLcm;
+$GL $CM* .;
-# GL x
-$GLcm ($LB8Breaks | $SP);
-$GLcm [$LB8NonBreaks-$SP] $CM*; # Don't let a combining mark go onto $CR, $BK, etc.
- # TODO: I don't think we need this rule.
- # All but $CM will chain off of preceding rule.
- # $GLcm will pick up the CM case by itself.
+#
+# LB 12a Do not break before NBSP and related characters ...
+# [^SP BA HY] x GL
+#
+[[$LB8NonBreaks] - [$SP $BA $HY]] $CM* $GL;
+^$CM+ $GL;
-#
-# LB 13 Don't break before ']' or '!' or ';' or '/', even after spaces.
+# LB 13 Don't break before ']' or '!' or '/', even after spaces.
#
$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
$LB8NonBreaks $EX;
$CAN_CM $CM* $EX;
-$CM+ $EX; # by rule 10, stand-alone CM behaves as AL
-
-$LB8NonBreaks $IS;
-$CAN_CM $CM* $IS;
-$CM+ $IS; # by rule 10, stand-alone CM behaves as AL
+^$CM+ $EX; # 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+ $SY; # by rule 10, stand-alone CM behaves as AL
#
-# LB 14 Do not break after OP, even after spaced
+# LB 14 Do not break after OP, even after spaces
+# Note subtle interaction with "SP IS /" rules in LB14a.
+# This rule consumes the SP, chaining happens on the IS, effectivley overriding the SP IS rules,
+# which is the desired behavior.
+#
+$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 $IN];
+$SP $IS / [^ $CanFollowIS $NU $CM];
+$SP $IS $CM* $CMX / [^ $CanFollowIS $NU $CM];
+
#
-$OPcm $SP* $CAN_CM $CM*;
-$OPcm $SP* $CANT_CM;
+# LB 14b Do not break before numeric separators (IS), even after spaces.
+
+[$LB8NonBreaks - $SP] $IS;
+$SP $IS $CM* [$CanFollowIS {eof}];
+$SP $IS $CM* $ZWJ [^$CM $NU];
+
+$CAN_CM $CM* $IS;
+^$CM+ $IS; # by rule 10, stand-alone CM behaves as AL
-$OPcm $SP+ $CM+ $AL_FOLLOW?; # by rule 10, stand-alone CM behaves as AL
# LB 15
-# $QUcm $SP* $OPcm;
+
+### BEGIN CUSTOMIZATION
+### i#83649: Allow line break between quote and opening punctuation.
+### This customization simply disables rule LB 15.
+###
+# $QU $CM* $SP* $OP;
+###
+### END CUSTOMIZATION
# LB 16
-$CLcm $SP* $NScm;
+($CL | $CP) $CM* $SP* $NS;
# LB 17
-$B2cm $SP* $B2cm;
+$B2 $CM* $SP* $B2;
#
# LB 18 Break after spaces.
@@ -301,347 +270,134 @@ $LB18Breaks = [$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
# <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 $CM* ($BAcm | $HYcm | $NScm);
+$LB20NonBreaks $CM* ($BA | $HY | $NS);
-$BBcm [^$CB]; # $BB x
-$BBcm $LB20NonBreaks $CM*;
-# LB 21a Don't break after Hebrew + Hyphen
-# HL (HY | BA) x
-#
-$HLcm ($HYcm | $BAcm) [^$CB]?;
+^$CM+ ($BA | $HY | $NS);
-# LB 22
-($ALcm | $HLcm) $INcm;
-$CM+ $INcm; # by rule 10, any otherwise unattached CM behaves as AL
-$IDcm $INcm;
-$INcm $INcm;
-$NUcm $INcm;
+$BB $CM* [^$CB]; # $BB x
+$BB $CM* $LB20NonBreaks;
-
-# $LB 23
-$IDcm $POcm;
-$ALcm $NUcm; # includes $LB19
-$HLcm $NUcm;
-$CM+ $NUcm; # Rule 10, any otherwise unattached CM behaves as AL
-$NUcm $ALcm;
-$NUcm $HLcm;
-
-#
-# LB 24
-#
-$PRcm $IDcm;
-$ALcm $PRcm;
-$PRcm ($ALcm | $HLcm);
-$POcm ($ALcm | $HLcm);
-
-#
-# LB 25 Numbers.
-#
-($PRcm | $POcm)? ($OPcm)? $NUcm ($NUcm | $SYcm | $IScm)* $CLcm? ($PRcm | $POcm)?;
-
-# LB 26 Do not break a Korean syllable
+# LB 21a Don't break after Hebrew + Hyphen
+# HL (HY | BA) x
#
-$JLcm ($JLcm | $JVcm | $H2cm | $H3cm);
-($JVcm | $H2cm) ($JVcm | $JTcm);
-($JTcm | $H3cm) $JTcm;
-
-# LB 27 Treat korean Syllable Block the same as ID (don't break it)
-($JLcm | $JVcm | $JTcm | $H2cm | $H3cm) $INcm;
-($JLcm | $JVcm | $JTcm | $H2cm | $H3cm) $POcm;
-$PRcm ($JLcm | $JVcm | $JTcm | $H2cm | $H3cm);
+$HL $CM* ($HY | $BA) $CM* [^$CB]?;
+# LB 21b (forward) Don't break between SY and HL
+# (break between HL and SY already disallowed by LB 13 above)
+$SY $CM* $HL;
-# LB 28 Do not break between alphabetics
+# LB 22 Do not break before ellipses
#
-($ALcm | $HLcm) ($ALcm | $HLcm);
-$CM+ ($ALcm | $HLcm); # The $CM+ is from rule 10, an unattached CM is treated as AL
+$LB20NonBreaks $CM* $IN;
+^$CM+ $IN;
-# LB 29
-$IScm ($ALcm | $NUcm);
+# LB 23
#
-# Rule 30 Do not break between letters, numbers or ordinary symbols
-# and opening or closing punctuation
-#
-($ALcm | $HLcm | $NUcm) $OPcm;
-$CM+ $OPcm;
-$CLcm ($ALcm | $HLcm | $NUcm);
+($ALPlus | $HL) $CM* $NU;
+^$CM+ $NU; # Rule 10, any otherwise unattached CM behaves as AL
+$NU $CM* ($ALPlus | $HL);
+# LB 23a
#
-# Reverse Rules.
-#
-## -------------------------------------------------
+$PR $CM* ($ID | $EB | $EM);
+($ID | $EB | $EM) $CM* $PO;
-!!reverse;
-
-$CM+ $ALPlus;
-$CM+ $BA;
-$CM+ $BB;
-$CM+ $B2;
-$CM+ $CL;
-$CM+ $EX;
-$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+ $NU;
-$CM+ $OP;
-$CM+ $PO;
-$CM+ $PR;
-$CM+ $QU;
-$CM+ $SY;
-$CM+ $WJ;
-$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 suppress 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.
-
-#
-# 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 ] / $CM+ [$BK $CR $LF $NL $ZW $SP {eof}];
-
-
-
-# LB 4, 5, 5
-
-$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 Break after zero width space
-
-
-# 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+ $CAN_CM;
-
-
-# LB 11
-$CM* $WJ $CM* $CAN_CM;
-$CM* $WJ [$LB8NonBreaks-$CM];
-
- $CANT_CM $CM* $WJ;
-$CM* $CAN_CM $CM* $WJ;
-
-# LB 12
-# x GL
#
-$CM* $GL $CM* [$LB8NonBreaks-$CM-$SP];
+# LB 24
+#
+($PR | $PO) $CM* ($ALPlus | $HL);
+($ALPlus | $HL) $CM* ($PR | $PO);
+^$CM+ ($PR | $PO); # Rule 10, any otherwise unattached CM behaves as AL
#
-# GL x
+# LB 25 Numbers.
#
-$CANT_CM $CM* $GL;
-$CM* $CAN_CM $CM* $GL;
+(($PR | $PO) $CM*)? (($OP | $HY) $CM*)? ($IS $CM*)? $NU ($CM* ($NU | $SY | $IS))*
+ ($CM* ($CL | $CP))? ($CM* ($PR | $PO))?;
+### BEGIN CUSTOMIZATION
+### i#83229: Allow line break after hyphen in number range context.
+### The default ICU rules treat number ranges (e.g. 100-199) as a single token. This change forces
+### a break opportunity after the embedded '-', but only if followed by another numeral.
+###
+### This customization does not replace any existing rule.
+### Maintainers: note that this rule should consist of two instances of the LB 25 numbers rule,
+### separated by a hyphen and an explicit break.
-# LB 13
-$CL $CM+ $CAN_CM;
-$EX $CM+ $CAN_CM;
-$IS $CM+ $CAN_CM;
-$SY $CM+ $CAN_CM;
+((($PR | $PO) $CM*)? (($OP | $HY) $CM*)? ($IS $CM*)? $NU ($CM* ($NU | $SY | $IS))*
+ ($CM* ($CL | $CP))? ($CM* ($PR | $PO))?)
+ ($HY $CM*) /
+((($PR | $PO) $CM*)? (($OP | $HY) $CM*)? ($IS $CM*)? $NU ($CM* ($NU | $SY | $IS))*
+ ($CM* ($CL | $CP))? ($CM* ($PR | $PO))?);
-$CL [$LB8NonBreaks-$CM];
-$EX [$LB8NonBreaks-$CM];
-$IS [$LB8NonBreaks-$CM];
-$SY [$LB8NonBreaks-$CM];
+### END CUSTOMIZATION
-# Rule 13 & 14 taken together for an edge case.
-# Match this, shown forward
-# OP SP+ ($CM+ behaving as $AL) (CL | EX | IS | IY)
-# This really wants to chain at the $CM+ (which is acting as an $AL)
-# except for $CM chaining being disabled.
-[$CL $EX $IS $SY] $CM+ $SP+ $CM* $OP;
+### TODO
+### ((PrefixNumeric | PostfixNumeric) CombMark*) ? ((OpenPunc | Hyphen) CombMark*)?
+### (InfixNumeric CombMark*)? Numeric (CombMark* (Numeric | BreakSym | InfixNumeric))*
+### (CombMark* (ClosePunc | CloseParen))? (CombMark* (PrefixNumeric | PostfixNumeric))?
-# LB 14 OP SP* x
+# LB 26 Do not break a Korean syllable
#
-$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.
-
-
-
-# LB 15
-# $CM* $OP $SP* $CM* $QU;
-
-# LB 16
-$CM* $NS $SP* $CM* $CL;
+$JL $CM* ($JL | $JV | $H2 | $H3);
+($JV | $H2) $CM* ($JV | $JT);
+($JT | $H3) $CM* $JT;
-# LB 17
-$CM* $B2 $SP* $CM* $B2;
-
-# LB 18 break after spaces
-# Nothing explicit needed here.
-
-
-#
-# LB 19
-#
-$CM* $QU $CM* $CAN_CM; # . x QU
-$CM* $QU $LB18NonBreaks;
+# LB 27 Treat korean Syllable Block the same as ID (don't break it)
+($JL | $JV | $JT | $H2 | $H3) $CM* $PO;
+$PR $CM* ($JL | $JV | $JT | $H2 | $H3);
-$CM* $CAN_CM $CM* $QU; # QU x .
- $CANT_CM $CM* $QU;
-
-#
-# LB 20 Break before and after CB.
-# nothing needed here.
+# LB 28 Do not break between alphabetics
#
-
-# LB 21
-$CM* ($BA | $HY | $NS) $CM* [$LB20NonBreaks-$CM]; # . x (BA | HY | NS)
-
-$CM* [$LB20NonBreaks-$CM] $CM* $BB; # BB x .
-[^$CB] $CM* $BB; #
-
-# LB21a
-[^$CB] $CM* ($HY | $BA) $CM* $HL;
-
-# LB 22
-$CM* $IN $CM* ($ALPlus | $HL);
-$CM* $IN $CM* $ID;
-$CM* $IN $CM* $IN;
-$CM* $IN $CM* $NU;
-
-# LB 23
-$CM* $PO $CM* $ID;
-$CM* $NU $CM* ($ALPlus | $HL);
-$CM* ($ALPlus | $HL) $CM* $NU;
-
-# LB 24
-$CM* $ID $CM* $PR;
-$CM* $PR $CM* $ALPlus;
-$CM* ($ALPlus | $HL) $CM* $PR;
-$CM* ($ALPlus | $HL) $CM* $PO;
-
-$CM* $ALPlus $CM* ($IS | $SY | $HY)+ / $SP;
-$CM* $NU+ $CM* $HY+ / $SP;
-
-# LB 25
-($CM* ($PR | $PO))? ($CM* $CL)? ($CM* ($NU | $IS | $SY))* $CM* $NU ($CM* ($OP))? ($CM* ($PR | $PO))?;
-
-# LB 26
-$CM* ($H3 | $H2 | $JV | $JL) $CM* $JL;
-$CM* ($JT | $JV) $CM* ($H2 | $JV);
-$CM* $JT $CM* ($H3 | $JT);
-
-# LB 27
-$CM* $IN $CM* ($H3 | $H2 | $JT | $JV | $JL);
-$CM* $PO $CM* ($H3 | $H2 | $JT | $JV | $JL);
-$CM* ($H3 | $H2 | $JT | $JV | $JL) $CM* $PR;
-
-# LB 28
-$CM* ($ALPlus | $HL) $CM* ($ALPlus | $HL);
+($ALPlus | $HL) $CM* ($ALPlus | $HL);
+^$CM+ ($ALPlus | $HL); # The $CM+ is from rule 10, an unattached CM is treated as AL
# LB 29
-$CM* ($NU | $ALPlus) $CM* $IS+ [^$SP];
+$IS $CM* ($ALPlus | $HL);
# LB 30
-$CM* $OP $CM* ($ALPlus | $HL | $NU);
-$CM* ($ALPlus | $HL | $NU) $CM* ($CL | $SY)+ [^$SP];
-
-
-## -------------------------------------------------
-
-!!safe_reverse;
-
-# LB 7
-$CM+ [^$CM $BK $CR $LF $NL $ZW $SP];
-$CM+ $SP / .;
-
-# LB 9
-$SP+ $CM* $OP;
-
-# LB 10
-$SP+ $CM* $QU;
-
-# LB 11
-$SP+ $CM* $CL;
-$SP+ $CM* $B2;
-
-# LB 21
-$CM* ($HY | $BA) $CM* $HL;
-
-# LB 18
-($CM* ($IS | $SY))+ $CM* $NU;
-$CL $CM* ($NU | $IS | $SY);
-
-# For dictionary-based break
-$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 $B2 $PR $HY $BA $SP $dictionary]+ [^$CM $OP $QU $CL $B2 $PR $HY $BA $dictionary];
-$dictionary $dictionary;
-
+($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 $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 $CM, which it would be able to do if the set were optional.
+
+# LB30b Do not break between an emoji base (or potential emoji) and an emoji modifier.
+$EB $CM* $EM;
+$ExtPictUnassigned $CM* $EM;
+
+# LB 31 Break everywhere else.
+# Match a single code point if no other rule applies.
+.;
generated by cgit (git 2.34.1) at 2024-06-25 20:15:46 +0000