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

# 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_loose_cj.txt
#
#         Line Breaking Rules
#         Implement default line breaking as defined by
#         Unicode Standard Annex #14 Revision 42 for Unicode 12.0
#         http://www.unicode.org/reports/tr14/, 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 tailors the line break behavior to correspond to CSS
#         line-break=loose (BCP47 -u-lb-loose) as defined for Chinese & Japanese.
#         It sets characters of class CJ to behave like ID.
#         In addition, it allows breaks:
#         * before hyphens 2010 & 2013 (both BA) and 301C, 30A0 (both NS)
#         * before iteration marks 3005, 303B, 309D, 309E, 30FD, 30FE (all NS)
#         * between characters of LineBreak class IN such as 2026
#         * before some centered punct 203C, 2047, 2048, 2049, 30FB, FF1A, FF1B,
#           FF65 (all NS) and FF01, FF1F (both EX).
#         * before suffix characters with LineBreak class PO and EastAsianWidth A,F,W;
#           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.


#
#  Character Classes defined by TR 14.
#

!!chain;
!!quoted_literals_only;

$AI = [:LineBreak =  Ambiguous:];
$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:] \u201d];
# $CM = [:LineBreak =  Combining_Mark:];
$CP = [:LineBreak =  Close_Parenthesis:];
$CR = [:LineBreak =  Carriage_Return:];
$EB = [:LineBreak =  EB:];
$EM = [:LineBreak =  EM:];
$EXX = [\uFF01 \uFF1F];
$EX = [[:LineBreak =  Exclamation:] - $EXX];
$GL = [:LineBreak =  Glue:];
$HL = [:LineBreak =  Hebrew_Letter:];
$HY = [:LineBreak =  Hyphen:];
$H2 = [:LineBreak =  H2:];
$H3 = [:LineBreak =  H3:];
# CSS Loose 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:];
$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:] \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:] - [\u201c\u201d]];
$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:]]]];
$CMX = [[$CM] - [$ZWJ]];

#   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:]]]];


## -------------------------------------------------

#
# 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 $HY $NS $IN $NU $PR $PO $POX $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
#              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
#                                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 $BAX $HY]] $CM* $GL;
^$CM+ $GL;


# LB 13   Don't break before ']' or '!' or or '/', even after spaces.
#
# Do not include $EXX here
$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 $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;

# LB 16
# Do not break between closing punctuation and $NS, even with intervening spaces
# But DO allow a break between closing punctuation and $NSX, don't include it here
($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    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
$BB $CM* $LB20NonBreaks;

# LB 21a Don't break after Hebrew + Hyphen
#   HL (HY | BA) x
#
$HL $CM* ($HY | $BA | $BAX) $CM* [^$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;  # delete this rule for CSS loose
$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
# Do not include $POX here
#
$PR $CM* ($ID | $EB | $EM);
($ID | $EB | $EM) $CM*  $PO;


#
# LB 24
#
# Do not include $PRX here
($PR | $PO | $POX) $CM* ($ALPlus | $HL);
($ALPlus | $HL) $CM* ($PR | $PO | $POX);     # TODO: should this be ($PR | $PRX | $PO)
^$CM+ ($PR | $PO | $POX);       # Rule 10, any otherwise unattached CM behaves as AL

#
# LB 25   Numbers.
#
# Here do not include $PRX at the beginning or $POX at the end
(($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
#
$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)
# Do not include $POX or $PRX here
($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 .   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}];
# 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.

# LB 30b Do not break between an Emoji Base and an Emoji Modifier
$EB $CM* $EM;

# LB 31 Break everywhere else.
#       Match a single code point if no other rule applies.
.;
Commit	Line	Data
0f5d89e8	1	# Copyright (C) 2016 and later: Unicode, Inc. and others.
f3c0d7a5	2	# License & terms of use: http://www.unicode.org/copyright.html
2ca993e8	3	# Copyright (c) 2002-2016 International Business Machines Corporation and
08b89b0a A	4	# others. All Rights Reserved.
	5	#
	6	# file: line_loose_cj.txt
	7	#
	8	# Line Breaking Rules
2ca993e8	9	# Implement default line breaking as defined by
3d1f044b A	10	# Unicode Standard Annex #14 Revision 42 for Unicode 12.0
3d1f044b A	11	# http://www.unicode.org/reports/tr14/, with the following modification:
2ca993e8	12	#
3d1f044b A	13	# Boundaries between hyphens and following letters are suppressed when
3d1f044b A	14	# there is a boundary preceding the hyphen. See rule 20.9
08b89b0a A	15	#
	16	# This tailors the line break behavior to correspond to CSS
	17	# line-break=loose (BCP47 -u-lb-loose) as defined for Chinese & Japanese.
	18	# It sets characters of class CJ to behave like ID.
	19	# In addition, it allows breaks:
	20	# * before hyphens 2010 & 2013 (both BA) and 301C, 30A0 (both NS)
	21	# * before iteration marks 3005, 303B, 309D, 309E, 30FD, 30FE (all NS)
	22	# * between characters of LineBreak class IN such as 2026
	23	# * before some centered punct 203C, 2047, 2048, 2049, 30FB, FF1A, FF1B,
	24	# FF65 (all NS) and FF01, FF1F (both EX).
	25	# * before suffix characters with LineBreak class PO and EastAsianWidth A,F,W;
	26	# this includes: 00B0 2030 2032 2033 2035 2103 2109 FE6A FF05 FFE0
	27	# * after prefix characters with LineBreak class PR and EastAsianWidth A,F,W;
	28	# this includes: 00A4 00B1 20AC 2116 FE69 FF04 FFE1 FFE5 FFE6
3d1f044b	29	# It allows breaking before 201C and after 201D, for zh_Hans, zh_Hant, and ja.
08b89b0a A	30
	31
	32	#
	33	# Character Classes defined by TR 14.
	34	#
	35
	36	!!chain;
0f5d89e8	37	!!quoted_literals_only;
08b89b0a	38
f3c0d7a5 A	39	$AI = [:LineBreak = Ambiguous:];
f3c0d7a5 A	40	$AL = [:LineBreak = Alphabetic:];
08b89b0a A	41	$BAX = [\u2010 \u2013];
08b89b0a A	42	$BA = [[:LineBreak = Break_After:] - $BAX];
3d1f044b	43	$HH = [\u2010]; # \u2010 is HYPHEN, default line break is BA.
08b89b0a A	44	$BB = [:LineBreak = Break_Before:];
	45	$BK = [:LineBreak = Mandatory_Break:];
	46	$B2 = [:LineBreak = Break_Both:];
	47	$CB = [:LineBreak = Contingent_Break:];
	48	$CJ = [:LineBreak = Conditional_Japanese_Starter:];
3d1f044b	49	$CL = [[:LineBreak = Close_Punctuation:] \u201d];
f3c0d7a5	50	# $CM = [:LineBreak = Combining_Mark:];
08b89b0a A	51	$CP = [:LineBreak = Close_Parenthesis:];
08b89b0a A	52	$CR = [:LineBreak = Carriage_Return:];
3d1f044b	53	$EB = [:LineBreak = EB:];
f3c0d7a5	54	$EM = [:LineBreak = EM:];
08b89b0a A	55	$EXX = [\uFF01 \uFF1F];
	56	$EX = [[:LineBreak = Exclamation:] - $EXX];
	57	$GL = [:LineBreak = Glue:];
	58	$HL = [:LineBreak = Hebrew_Letter:];
	59	$HY = [:LineBreak = Hyphen:];
	60	$H2 = [:LineBreak = H2:];
	61	$H3 = [:LineBreak = H3:];
f3c0d7a5 A	62	# CSS Loose tailoring: CJ resolves to ID
f3c0d7a5 A	63	$ID = [[:LineBreak = Ideographic:] $CJ];
08b89b0a A	64	$IN = [:LineBreak = Inseperable:];
	65	$IS = [:LineBreak = Infix_Numeric:];
	66	$JL = [:LineBreak = JL:];
	67	$JV = [:LineBreak = JV:];
	68	$JT = [:LineBreak = JT:];
	69	$LF = [:LineBreak = Line_Feed:];
	70	$NL = [:LineBreak = Next_Line:];
	71	$NSX = [\u301C \u30A0 \u3005 \u303B \u309D \u309E \u30FD \u30FE \u203C \u2047 \u2048 \u2049 \u30FB \uFF1A \uFF1B \uFF65];
	72	$NS = [[:LineBreak = Nonstarter:] - $NSX];
	73	$NU = [:LineBreak = Numeric:];
3d1f044b	74	$OP = [[:LineBreak = Open_Punctuation:] \u201c];
08b89b0a A	75	$POX = [\u00B0 \u2030 \u2032 \u2033 \u2035 \u2103 \u2109 \uFE6A \uFF05 \uFFE0];
	76	$PO = [[:LineBreak = Postfix_Numeric:] - $POX];
	77	$PRX = [\u00A4 \u00B1 \u20AC \u2116 \uFE69 \uFF04 \uFFE1 \uFFE5 \uFFE6];
	78	$PR = [[:LineBreak = Prefix_Numeric:] - $PRX];
3d1f044b	79	$QU = [[:LineBreak = Quotation:] - [\u201c\u201d]];
08b89b0a A	80	$RI = [:LineBreak = Regional_Indicator:];
	81	$SA = [:LineBreak = Complex_Context:];
	82	$SG = [:LineBreak = Surrogate:];
	83	$SP = [:LineBreak = Space:];
	84	$SY = [:LineBreak = Break_Symbols:];
	85	$WJ = [:LineBreak = Word_Joiner:];
	86	$XX = [:LineBreak = Unknown:];
	87	$ZW = [:LineBreak = ZWSpace:];
f3c0d7a5 A	88	$ZWJ = [:LineBreak = ZWJ:];
f3c0d7a5 A	89
f3c0d7a5 A	90	# By LB9, a ZWJ also behaves as a CM. Including it in the definition of CM avoids having to explicitly
	91	# list it in the numerous rules that use CM.
	92	# By LB1, SA characters with general categor of Mn or Mc also resolve to CM.
	93
	94	$CM = [[:LineBreak = Combining_Mark:] $ZWJ [$SA & [[:Mn:][:Mc:]]]];
3d1f044b	95	$CMX = [[$CM] - [$ZWJ]];
08b89b0a A	96
08b89b0a A	97	# Dictionary character set, for triggering language-based break engines. Currently
f3c0d7a5	98	# limited to LineBreak=Complex_Context (SA).
08b89b0a	99
f3c0d7a5	100	$dictionary = [$SA];
08b89b0a A	101
	102	#
	103	# Rule LB1. By default, treat AI (characters with ambiguous east Asian width),
f3c0d7a5	104	# SA (Dictionary chars, excluding Mn and Mc)
08b89b0a A	105	# SG (Unpaired Surrogates)
	106	# XX (Unknown, unassigned)
	107	# as $AL (Alphabetic)
	108	#
f3c0d7a5 A	109	$ALPlus = [$AL $AI $SG $XX [$SA-[[:Mn:][:Mc:]]]];
f3c0d7a5 A	110
08b89b0a A	111
	112	## -------------------------------------------------
	113
08b89b0a A	114	#
	115	# CAN_CM is the set of characters that may combine with CM combining chars.
	116	# Note that Linebreak UAX 14's concept of a combining char and the rules
	117	# for what they can combine with are _very_ different from the rest of Unicode.
	118	#
	119	# Note that $CM itself is left out of this set. If CM is needed as a base
	120	# it must be listed separately in the rule.
	121	#
	122	$CAN_CM = [^$SP $BK $CR $LF $NL $ZW $CM]; # Bases that can take CMs
	123	$CANT_CM = [ $SP $BK $CR $LF $NL $ZW $CM]; # Bases that can't take CMs
	124
	125	#
	126	# AL_FOLLOW set of chars that can unconditionally follow an AL
	127	# Needed in rules where stand-alone $CM s are treated as AL.
08b89b0a	128	#
f3c0d7a5	129	$AL_FOLLOW = [$BK $CR $LF $NL $ZW $SP $CL $CP $EX $HL $IS $SY $WJ $GL $OP $QU $BA $HY $NS $IN $NU $PR $PO $POX $ALPlus];
08b89b0a A	130
	131
	132	#
	133	# Rule LB 4, 5 Mandatory (Hard) breaks.
	134	#
	135	$LB4Breaks = [$BK $CR $LF $NL];
2ca993e8	136	$LB4NonBreaks = [^$BK $CR $LF $NL $CM];
08b89b0a A	137	$CR $LF {100};
	138
	139	#
	140	# LB 6 Do not break before hard line breaks.
	141	#
	142	$LB4NonBreaks? $LB4Breaks {100}; # LB 5 do not break before hard breaks.
	143	$CAN_CM $CM* $LB4Breaks {100};
2ca993e8	144	^$CM+ $LB4Breaks {100};
08b89b0a A	145
	146	# LB 7 x SP
	147	# x ZW
	148	$LB4NonBreaks [$SP $ZW];
	149	$CAN_CM $CM* [$SP $ZW];
2ca993e8	150	^$CM+ [$SP $ZW];
08b89b0a A	151
	152	#
	153	# LB 8 Break after zero width space
3d1f044b	154	# ZW SP* ÷
08b89b0a A	155	#
	156	$LB8Breaks = [$LB4Breaks $ZW];
	157	$LB8NonBreaks = [[$LB4NonBreaks] - [$ZW]];
3d1f044b	158	$ZW $SP* / [^$SP $ZW $LB4Breaks];
08b89b0a	159
0f5d89e8	160	# LB 8a ZWJ x Do not break Emoji ZWJ sequences.
2ca993e8	161	#
0f5d89e8	162	$ZWJ [^$CM];
08b89b0a	163
2ca993e8 A	164	# LB 9 Combining marks. X $CM needs to behave like X, where X is not $SP, $BK $CR $LF $NL
2ca993e8 A	165	# $CM not covered by the above needs to behave like $AL
08b89b0a A	166	# See definition of $CAN_CM.
	167
	168	$CAN_CM $CM+; # Stick together any combining sequences that don't match other rules.
2ca993e8	169	^$CM+;
08b89b0a A	170
	171	#
	172	# LB 11 Do not break before or after WORD JOINER & related characters.
	173	#
f3c0d7a5 A	174	$CAN_CM $CM* $WJ;
	175	$LB8NonBreaks $WJ;
	176	^$CM+ $WJ;
08b89b0a	177
f3c0d7a5	178	$WJ $CM* .;
08b89b0a A	179
	180	#
	181	# LB 12 Do not break after NBSP and related characters.
	182	# GL x
	183	#
f3c0d7a5	184	$GL $CM* .;
2ca993e8	185
08b89b0a A	186	#
	187	# LB 12a Do not break before NBSP and related characters ...
	188	# [^SP BA HY] x GL
	189	#
f3c0d7a5 A	190	[[$LB8NonBreaks] - [$SP $BA $BAX $HY]] $CM* $GL;
f3c0d7a5 A	191	^$CM+ $GL;
08b89b0a A	192
08b89b0a A	193
3d1f044b A	194
3d1f044b A	195	# LB 13 Don't break before ']' or '!' or or '/', even after spaces.
08b89b0a A	196	#
	197	# Do not include $EXX here
	198	$LB8NonBreaks $CL;
	199	$CAN_CM $CM* $CL;
2ca993e8	200	^$CM+ $CL; # by rule 10, stand-alone CM behaves as AL
08b89b0a A	201
	202	$LB8NonBreaks $CP;
	203	$CAN_CM $CM* $CP;
2ca993e8	204	^$CM+ $CP; # by rule 10, stand-alone CM behaves as AL
08b89b0a A	205
	206	$LB8NonBreaks $EX;
	207	$CAN_CM $CM* $EX;
2ca993e8	208	^$CM+ $EX; # by rule 10, stand-alone CM behaves as AL
08b89b0a	209
08b89b0a A	210	$LB8NonBreaks $SY;
08b89b0a A	211	$CAN_CM $CM* $SY;
2ca993e8	212	^$CM+ $SY; # by rule 10, stand-alone CM behaves as AL
08b89b0a A	213
	214
	215	#
	216	# LB 14 Do not break after OP, even after spaces
3d1f044b A	217	# Note subtle interaction with "SP IS /" rules in LB14a.
	218	# This rule consumes the SP, chaining happens on the IS, effectivley overriding the SP IS rules,
	219	# which is the desired behavior.
08b89b0a	220	#
f3c0d7a5	221	$OP $CM* $SP* .;
08b89b0a	222
f3c0d7a5 A	223	$OP $CM* $SP+ $CM+ $AL_FOLLOW?; # by rule 10, stand-alone CM behaves as AL
f3c0d7a5 A	224	# by rule 8, CM following a SP is stand-alone.
08b89b0a	225
3d1f044b A	226
	227	# LB 14a Force a break before start of a number with a leading decimal pt, e.g. " .23"
	228	# Note: would be simpler to express as "$SP / $IS $CM* $NU;", but ICU rules have limitations.
	229	# See issue ICU-20303
	230
	231
	232	$CanFollowIS = [$BK $CR $LF $NL $SP $ZW $WJ $GL $CL $CP $EX $IS $SY $QU $BA $HY $NS $ALPlus $HL];
	233	$SP $IS / [^ $CanFollowIS $NU $CM];
	234	$SP $IS $CM* $CMX / [^ $CanFollowIS $NU $CM];
	235
	236	#
	237	# LB 14b Do not break before numeric separators (IS), even after spaces.
	238
	239	[$LB8NonBreaks - $SP] $IS;
	240	$SP $IS $CM* [$CanFollowIS {eof}];
	241	$SP $IS $CM* $ZWJ [^$CM $NU];
	242
	243	$CAN_CM $CM* $IS;
	244	^$CM+ $IS; # by rule 10, stand-alone CM behaves as AL
	245
	246
08b89b0a	247	# LB 15
f3c0d7a5	248	$QU $CM* $SP* $OP;
08b89b0a A	249
	250	# LB 16
	251	# Do not break between closing punctuation and $NS, even with intervening spaces
	252	# But DO allow a break between closing punctuation and $NSX, don't include it here
f3c0d7a5	253	($CL \| $CP) $CM* $SP* $NS;
08b89b0a A	254
08b89b0a A	255	# LB 17
f3c0d7a5	256	$B2 $CM* $SP* $B2;
08b89b0a A	257
	258	#
	259	# LB 18 Break after spaces.
	260	#
	261	$LB18NonBreaks = [$LB8NonBreaks - [$SP]];
	262	$LB18Breaks = [$LB8Breaks $SP];
	263
	264
	265	# LB 19
	266	# x QU
f3c0d7a5 A	267	$LB18NonBreaks $CM* $QU;
f3c0d7a5 A	268	^$CM+ $QU;
08b89b0a A	269
08b89b0a A	270	# QU x
f3c0d7a5	271	$QU $CM* .;
08b89b0a	272
08b89b0a A	273	# LB 20
	274	# <break> $CB
	275	# $CB <break>
3d1f044b	276	#
08b89b0a A	277	$LB20NonBreaks = [$LB18NonBreaks - $CB];
08b89b0a A	278
3d1f044b A	279	# LB 20.09 Don't break between Hyphens and Letters when there is a break preceding the hyphen.
	280	# Originally added as a Finnish tailoring, now promoted to default ICU behavior.
	281	# Note: this is not default UAX-14 behaviour. See issue ICU-8151.
	282	#
	283	^($HY \| $HH) $CM* $ALPlus;
	284
08b89b0a A	285	# LB 21 x (BA \| HY \| NS)
	286	# BB x
	287	#
f3c0d7a5 A	288	# DO allow breaks here before $BAX and $NSX, so don't include them
f3c0d7a5 A	289	$LB20NonBreaks $CM* ($BA \| $HY \| $NS);
3d1f044b A	290
3d1f044b A	291
f3c0d7a5	292	^$CM+ ($BA \| $HY \| $NS);
08b89b0a	293
f3c0d7a5 A	294	$BB $CM* [^$CB]; # $BB x
f3c0d7a5 A	295	$BB $CM* $LB20NonBreaks;
08b89b0a A	296
	297	# LB 21a Don't break after Hebrew + Hyphen
	298	# HL (HY \| BA) x
2ca993e8	299	#
f3c0d7a5	300	$HL $CM* ($HY \| $BA \| $BAX) $CM* [^$CB]?;
08b89b0a A	301
	302	# LB 21b (forward) Don't break between SY and HL
	303	# (break between HL and SY already disallowed by LB 13 above)
f3c0d7a5	304	$SY $CM* $HL;
08b89b0a A	305
08b89b0a A	306	# LB 22
f3c0d7a5 A	307	($ALPlus \| $HL) $CM* $IN;
	308	^$CM+ $IN; # by rule 10, any otherwise unattached CM behaves as AL
	309	$EX $CM* $IN;
	310	($ID \| $EB \| $EM) $CM* $IN;
	311	# $IN $CM* $IN; # delete this rule for CSS loose
	312	$NU $CM* $IN;
08b89b0a A	313
08b89b0a A	314
2ca993e8	315	# $LB 23
f3c0d7a5 A	316	#
	317	($ALPlus \| $HL) $CM* $NU;
	318	^$CM+ $NU; # Rule 10, any otherwise unattached CM behaves as AL
	319	$NU $CM* ($ALPlus \| $HL);
	320
	321	# LB 23a
08b89b0a	322	# Do not include $POX here
f3c0d7a5 A	323	#
	324	$PR $CM* ($ID \| $EB \| $EM);
	325	($ID \| $EB \| $EM) $CM* $PO;
	326
08b89b0a A	327
	328	#
	329	# LB 24
	330	#
	331	# Do not include $PRX here
f3c0d7a5 A	332	($PR \| $PO \| $POX) $CM* ($ALPlus \| $HL);
	333	($ALPlus \| $HL) $CM* ($PR \| $PO \| $POX); # TODO: should this be ($PR \| $PRX \| $PO)
	334	^$CM+ ($PR \| $PO \| $POX); # Rule 10, any otherwise unattached CM behaves as AL
08b89b0a A	335
	336	#
	337	# LB 25 Numbers.
	338	#
	339	# Here do not include $PRX at the beginning or $POX at the end
3d1f044b	340	(($PR \| $PO \| $POX) $CM)? (($OP \| $HY) $CM)? ($IS $CM)? $NU ($CM ($NU \| $SY \| $IS))*
f3c0d7a5	341	($CM* ($CL \| $CP))? ($CM* ($PR \| $PRX \| $PO))?;
08b89b0a A	342
	343	# LB 26 Do not break a Korean syllable
	344	#
f3c0d7a5 A	345	$JL $CM* ($JL \| $JV \| $H2 \| $H3);
	346	($JV \| $H2) $CM* ($JV \| $JT);
	347	($JT \| $H3) $CM* $JT;
08b89b0a A	348
	349	# LB 27 Treat korean Syllable Block the same as ID (don't break it)
	350	# Do not include $POX or $PRX here
f3c0d7a5 A	351	($JL \| $JV \| $JT \| $H2 \| $H3) $CM* $IN;
	352	($JL \| $JV \| $JT \| $H2 \| $H3) $CM* $PO;
	353	$PR $CM* ($JL \| $JV \| $JT \| $H2 \| $H3);
08b89b0a A	354
	355
	356	# LB 28 Do not break between alphabetics
	357	#
f3c0d7a5 A	358	($ALPlus \| $HL) $CM* ($ALPlus \| $HL);
f3c0d7a5 A	359	^$CM+ ($ALPlus \| $HL); # The $CM+ is from rule 10, an unattached CM is treated as AL
08b89b0a A	360
08b89b0a A	361	# LB 29
f3c0d7a5	362	$IS $CM* ($ALPlus \| $HL);
08b89b0a A	363
08b89b0a A	364	# LB 30
f3c0d7a5 A	365	($ALPlus \| $HL \| $NU) $CM* $OP;
	366	^$CM+ $OP; # The $CM+ is from rule 10, an unattached CM is treated as AL.
	367	$CP $CM* ($ALPlus \| $HL \| $NU);
08b89b0a	368
2ca993e8	369	# LB 30a Do not break between regional indicators. Break after pairs of them.
0f5d89e8 A	370	# Tricky interaction with LB8a: ZWJ x . together with ZWJ acting like a CM.
	371	$RI $CM* $RI / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM]];
	372	$RI $CM* $RI $CM* [$CM-$ZWJ] / [[^$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $CM]];
	373	$RI $CM* $RI $CM* [$BK $CR $LF $NL $SP $ZW $WJ $CL $CP $EX $IS $SY $GL $QU $BA $HY $NS $ZWJ {eof}];
	374	# note: the preceding rule includes {eof} rather than having the last [set] term qualified with '?'
	375	# because of the chain-out behavior difference. The rule must chain out only from the [set characters],
	376	# not from the preceding $RI or $CM, which it would be able to do if the set were optional.
08b89b0a	377
2ca993e8 A	378	# LB 30b Do not break between an Emoji Base and an Emoji Modifier
2ca993e8 A	379	$EB $CM* $EM;
08b89b0a	380
0f5d89e8 A	381	# LB 31 Break everywhere else.
	382	# Match a single code point if no other rule applies.
	383	.;