[apple/icu.git] / icuSources / test / testdata / word_urbTokTest.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:  word_urbTokTest.txt
#
# ICU Word Break Rules
#      See Unicode Standard Annex #29.
#      These rules are based on UAX #29 Revision 29 for Unicode Version 9.0
#      with additions for Emoji Sequences from https://goo.gl/cluFCn
#      Also modified with additions for testing urbtok_ functions.
#

##############################################################################
#
#  Character class definitions from TR 29
#
##############################################################################

!!chain;

# Smart Tokenizer customization

$Space				= [\u0020];
$Fullstop       	= [\u002E\uFE52\uFF0E];
$Dash          		= [\u002D\uFE63\uFF0D];

$Terminators    	= [\u0021\u00A1\u00A1\u01C3\u01C3\u01C3\u203C\u2048\uFE15\uFF01\u003F];
$Parenthesis    	= [\u0028\u005B\u007B\u0029\u005D\u007D];
$Punctuation    	= [\u007E\u003D\u002A\u003C\u003E];
$OtherSingle    	= [\u0060\u0300\u030F];

$Hash           	= [\u0023 \uFE5F \uFF03];
$At             	= [\u0040 \uFE6B \uFF20];
$Dollar         	= [\u0024];

$Semicolon      	= [\u003B];
$Colon         		= [\u003A];

#
#  Character Class Definitions.
#

$CR                 = [\p{Word_Break = CR}];
$LF                 = [\p{Word_Break = LF}];
$Newline            = [\p{Word_Break = Newline}];
$Extend             = [\p{Word_Break = Extend}];
$ZWJ                = [\p{Word_Break = ZWJ}];
$Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
$Format             = [\p{Word_Break = Format}];
$Katakana           = [\p{Word_Break = Katakana}];
$Hebrew_Letter      = [\p{Word_Break = Hebrew_Letter}];
$ALetter            = [\p{Word_Break = ALetter}];
$Single_Quote       = [\p{Word_Break = Single_Quote}\u2018\u2019];
$Double_Quote       = [\p{Word_Break = Double_Quote}];
$MidNumLet          = [\p{Word_Break = MidNumLet}-[$Fullstop $Single_Quote]];
$MidLetter          = [\p{Word_Break = MidLetter}-[$Single_Quote]];
$MidNum             = [\p{Word_Break = MidNum}];
$Numeric            = [\p{Word_Break = Numeric}];
$ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
$E_Base             = [\p{Word_Break = EB}\U0001F3C2\U0001F3C7\U0001F3CC\U0001F46A-\U0001F46D\U0001F46F\U0001F574\U0001F6CC];
$E_Modifier         = [\p{Word_Break = EM}];

# Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r12773
$Extended_Pict      = [\U0001F774-\U0001F77F\u2700-\u2701\u2703-\u2704\u270E\u2710-\u2711\u2765-\u2767\U0001F030-\U0001F093\U0001F094-\U0001F09F\U0001F10D-\U0001F10F\U0001F12F\U0001F16C-\U0001F16F\U0001F1AD-\U0001F1E5\U0001F203-\U0001F20F\U0001F23C-\U0001F23F\U0001F249-\U0001F24F\U0001F252-\U0001F2FF\U0001F7D5-\U0001F7FF\U0001F000-\U0001F003\U0001F005-\U0001F02B\U0001F02C-\U0001F02F\U0001F322-\U0001F323\U0001F394-\U0001F395\U0001F398\U0001F39C-\U0001F39D\U0001F3F1-\U0001F3F2\U0001F3F6\U0001F4FE\U0001F53E-\U0001F548\U0001F54F\U0001F568-\U0001F56E\U0001F571-\U0001F572\U0001F57B-\U0001F586\U0001F588-\U0001F589\U0001F58E-\U0001F58F\U0001F591-\U0001F594\U0001F597-\U0001F5A3\U0001F5A6-\U0001F5A7\U0001F5A9-\U0001F5B0\U0001F5B3-\U0001F5BB\U0001F5BD-\U0001F5C1\U0001F5C5-\U0001F5D0\U0001F5D4-\U0001F5DB\U0001F5DF-\U0001F5E0\U0001F5E2\U0001F5E4-\U0001F5E7\U0001F5E9-\U0001F5EE\U0001F5F0-\U0001F5F2\U0001F5F4-\U0001F5F9\u2605\u2607-\u260D\u260F-\u2610\u2612\u2616-\u2617\u2619-\u261C\u261E-\u261F\u2621\u2624-\u2625\u2627-\u2629\u262B-\u262D\u2630-\u2637\u263B-\u2647\u2654-\u265F\u2661-\u2662\u2664\u2667\u2669-\u267A\u267C-\u267E\u2680-\u2691\u2695\u2698\u269A\u269D-\u269F\u26A2-\u26A9\u26AC-\u26AF\u26B2-\u26BC\u26BF-\u26C3\u26C6-\u26C7\u26C9-\u26CD\u26D0\u26D2\u26D5-\u26E8\u26EB-\u26EF\u26F6\u26FB-\u26FC\u26FE-\u26FF\u2388\U0001FA00-\U0001FFFD\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F0AF-\U0001F0B0\U0001F0C0\U0001F0D0\U0001F0F6-\U0001F0FF\U0001F80C-\U0001F80F\U0001F848-\U0001F84F\U0001F85A-\U0001F85F\U0001F888-\U0001F88F\U0001F8AE-\U0001F8FF\U0001F900-\U0001F90F\U0001F91F\U0001F928-\U0001F92F\U0001F931-\U0001F932\U0001F93F\U0001F94C-\U0001F94F\U0001F95F-\U0001F97F\U0001F992-\U0001F9BF\U0001F9C1-\U0001F9FF\U0001F6C6-\U0001F6CA\U0001F6E6-\U0001F6E8\U0001F6EA\U0001F6F1-\U0001F6F2\U0001F6D3-\U0001F6DF\U0001F6ED-\U0001F6EF\U0001F6F7-\U0001F6FF];
$EBG                = [\p{Word_Break = EBG}];
$EmojiNRK           = [[\p{Emoji}] - [\p{Word_Break = Regional_Indicator}\u002a\u00230-9©®™〰〽]];

$Han                = [:Han:];
$Hiragana           = [:Hiragana:];


#   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.

$Control        = [\p{Grapheme_Cluster_Break = Control}]; 
$HangulSyllable = [\uac00-\ud7a3];
$ComplexContext = [:LineBreak = Complex_Context:];
$KanaKanji      = [$Han $Hiragana $Katakana];
$dictionaryCJK  = [$KanaKanji $HangulSyllable];
$dictionary     = [$ComplexContext $dictionaryCJK];

# leave CJK scripts out of ALetterPlus
$ALetterPlus  = [$ALetter-$dictionaryCJK [$ComplexContext-$Extend-$Control]];


#
#  Rules 4    Ignore Format and Extend characters,
#             except when they appear at the beginning of a region of text.
#
# TODO: check if handling of katakana in dictionary makes rules incorrect/void
$KatakanaEx           = $Katakana           ($Extend |  $Format | $ZWJ)*;
$Hebrew_LetterEx      = $Hebrew_Letter      ($Extend |  $Format | $ZWJ)*;
$ALetterEx            = $ALetterPlus        ($Extend |  $Format | $ZWJ)*;
$Single_QuoteEx       = $Single_Quote       ($Extend |  $Format | $ZWJ)*;
$Double_QuoteEx       = $Double_Quote       ($Extend |  $Format | $ZWJ)*;
$MidNumLetEx          = $MidNumLet          ($Extend |  $Format | $ZWJ)*;
$MidLetterEx          = $MidLetter          ($Extend |  $Format | $ZWJ)*;
$MidNumEx             = $MidNum             ($Extend |  $Format | $ZWJ)*;
$NumericEx            = $Numeric            ($Extend |  $Format | $ZWJ)*;
$ExtendNumLetEx       = $ExtendNumLet       ($Extend |  $Format | $ZWJ)*;
$Regional_IndicatorEx = $Regional_Indicator ($Extend |  $Format | $ZWJ)*;

$Ideographic    = [\p{Ideographic}];
$HiraganaEx     = $Hiragana     ($Extend |  $Format | $ZWJ)*;
$IdeographicEx  = $Ideographic  ($Extend |  $Format | $ZWJ)*;

$Letter = [A-Za-z];

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

!!forward;

# Rule 3 - CR x LF
#
$CR $LF;

# Rule 3c   ZWJ x (Extended_Pict | EmojiNRK).  Precedes WB4, so no intervening Extend chars allowed.
#
$ZWJ ($Extended_Pict | $EmojiNRK);


# Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
#          of a region of Text.   The rule here comes into play when the start of text
#          begins with a group of Format chars, or with a "word" consisting of a single
#          char that is not in any of the listed word break categories followed by
#          format char(s), or is not a CJK dictionary character.
[^$CR $LF $Newline]? ($Extend |  $Format | $ZWJ)+;

$NumericEx {100};
$ALetterEx {200};
$HangulSyllable {200};
$Hebrew_LetterEx{200};
$KatakanaEx {400};       # note:  these status values override those from rule 5
$HiraganaEx {400};       #        by virtue of being numerically larger.
$IdeographicEx {400};    #

$E_Base ($Extend | $Format | $ZWJ)*;
$E_Modifier ($Extend | $Format | $ZWJ)*;
$Extended_Pict ($Extend | $Format | $ZWJ)*;

#
# rule 5
#    Do not break between most letters.
#
($ALetterEx | $Hebrew_LetterEx)  ($ALetterEx | $Hebrew_LetterEx) {200};

# rule 6 and 7
($ALetterEx | $Hebrew_LetterEx) ($MidLetterEx | $MidNumLetEx ) ($ALetterEx | $Hebrew_LetterEx) {200};

# rule 7a
$Hebrew_LetterEx $Single_QuoteEx {200};

# rule 7b and 7c
$Hebrew_LetterEx $Double_QuoteEx $Hebrew_LetterEx {200};

# rule 8

$NumericEx $NumericEx {100};

# rule 9

($ALetterEx | $Hebrew_LetterEx) $NumericEx {200};

# rule 10

$NumericEx ($ALetterEx | $Hebrew_LetterEx) {200};

# rule 11 and 12

$NumericEx ($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx {100};

# rule 13
# to be consistent with $KanaKanji $KanaKanhi, changed
# from 300 to 400.
# See also TestRuleStatus in intltest/rbbiapts.cpp
$KatakanaEx  $KatakanaEx {400};

# rule 13a/b

$ALetterEx       $ExtendNumLetEx {200};    #  (13a)
$Hebrew_LetterEx $ExtendNumLetEx {200};    #  (13a)
$NumericEx       $ExtendNumLetEx {100};    #  (13a)
$KatakanaEx      $ExtendNumLetEx {400};    #  (13a)
$ExtendNumLetEx  $ExtendNumLetEx {200};    #  (13a)

$ExtendNumLetEx  $ALetterEx      {200};    #  (13b)
$ExtendNumLetEx  $Hebrew_Letter  {200};    #  (13b)
$ExtendNumLetEx  $NumericEx      {100};    #  (13b)
$ExtendNumLetEx  $KatakanaEx     {400};    #  (13b)

# rule 14
#    Do not break within emoji modifier sequences

($E_Base | $EBG) ($Format | $Extend | $ZWJ)* $E_Modifier;

# rules 15 - 17
#    Pairs of Regional Indicators stay together.
#    With rule chaining disabled by ^, this rule will match exactly two of them.
#    No other rule begins with a Regional_Indicator, so chaining cannot extend the match.
#
^$Regional_IndicatorEx $Regional_IndicatorEx;

# special handling for CJK characters: chain for later dictionary segmentation
$HangulSyllable $HangulSyllable {200};
$KanaKanji $KanaKanji {400}; # different rule status if both kana and kanji found 

$Space* {1};
$Newline* {2};

$Fullstop {20};
$Dash {21};
$Single_Quote {22};

$Contraction = (N | n) $Single_Quote (T | t);
$Contraction2 = (N | n) $Single_Quote (T | t) $Single_Quote (V | v) (E | e);
$Contraction3 = (Y | y) $Single_Quote (A | a) (L | l) (L | l);

$Time = (0 | 1 | 2)? $Numeric $Colon (0 | 1 | 2 | 3 | 4 | 5) $Numeric;
$IPAddress = $Numeric? $Numeric? $Numeric $Fullstop $Numeric? $Numeric? $Numeric;

(N | n) $Single_Quote (T | t) {202};
(Y | y) $Single_Quote (A | a) (L | l)* {202};

$Fullstop $Fullstop ($Fullstop*) {40};
$Dash $Dash ($Dash*) {40};
$Terminators $Terminators ($Terminators*) {40};
$Punctuation $Punctuation ($Punctuation*) {40};
$OtherSingle $OtherSingle ($OtherSingle*) {40};

$Single_Quote $Single_Quote {40};
$Single_Quote $Single_Quote $Single_Quote* {40};

$Hash ($ALetter | $Numeric)* {30};
$At ($ALetter | $Numeric)* {31};
$Dollar $ALetter ($ALetter | $Numeric)* {31};

$Time {50};
$IPAddress {51};

$ALetter / $IPAddress;
$ALetter / $Time;

($Colon | $Semicolon) $Parenthesis {32};

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

!!reverse;

$BackHebrew_LetterEx      = ($Format | $Extend | $ZWJ)* $Hebrew_Letter;
$BackALetterEx            = ($Format | $Extend | $ZWJ)* $ALetterPlus;
$BackSingle_QuoteEx       = ($Format | $Extend | $ZWJ)* $Single_Quote;
$BackDouble_QuoteEx       = ($Format | $Extend | $ZWJ)* $Double_Quote;
$BackMidNumLetEx          = ($Format | $Extend | $ZWJ)* $MidNumLet;
$BackNumericEx            = ($Format | $Extend | $ZWJ)* $Numeric;
$BackMidNumEx             = ($Format | $Extend | $ZWJ)* $MidNum;
$BackMidLetterEx          = ($Format | $Extend | $ZWJ)* $MidLetter;
$BackKatakanaEx           = ($Format | $Extend | $ZWJ)* $Katakana;
$BackHiraganaEx           = ($Format | $Extend | $ZWJ)* $Hiragana;
$BackExtendNumLetEx       = ($Format | $Extend | $ZWJ)* $ExtendNumLet;
$BackRegional_IndicatorEx = ($Format | $Extend | $ZWJ)* $Regional_Indicator;

# rule 3
$LF $CR;

# Rule 3c   ZWJ x (Extended_Pict | EmojiNRK).  Precedes WB4, so no intervening Extend chars allowed.
#
($Extended_Pict | $EmojiNRK) $ZWJ;

# rule 4
($Format | $Extend | $ZWJ)*  [^$CR $LF $Newline]?;

# rule 5

($BackALetterEx | $BackHebrew_LetterEx) ($BackALetterEx | $BackHebrew_LetterEx);

# rule 6 and 7

($BackALetterEx | $BackHebrew_LetterEx) ($BackMidLetterEx | $BackMidNumLetEx ) ($BackALetterEx | $BackHebrew_LetterEx);

# rule 7a
$BackSingle_QuoteEx $BackHebrew_LetterEx;

# Rule 7b and 7c
$BackHebrew_LetterEx $BackDouble_QuoteEx $BackHebrew_LetterEx;

# rule 8

$BackNumericEx $BackNumericEx;

# rule 9

$BackNumericEx ($BackALetterEx | $BackHebrew_LetterEx);

# rule 10

($BackALetterEx | $BackHebrew_LetterEx) $BackNumericEx;

# rule 11 and 12

$BackNumericEx ($BackMidNumEx | $BackMidNumLetEx | $BackSingle_QuoteEx) $BackNumericEx;

# rule 13

$BackKatakanaEx $BackKatakanaEx;

# rules 13 a/b
#
$BackExtendNumLetEx ($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx | $BackExtendNumLetEx);
($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx) $BackExtendNumLetEx; 

# special handling for CJK characters: chain for later dictionary segmentation
$HangulSyllable $HangulSyllable;
$KanaKanji $KanaKanji; #different rule status if both kanji and kana found

# rule 14

$E_Modifier ($Format | $Extend | $ZWJ)* ($E_Base | $EBG);

# rule 15 - 17
#    Pairs of Regional Indicators stay together.

^$BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)* 
        ($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
^$BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)* 
        ($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];

($Extended_Pict | $EmojiNRK) $ZWJ $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)* 
        ($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
($Extended_Pict | $EmojiNRK) $ZWJ $BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)* 
        ($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];

$Space* {1};
$Newline* {2};

$Fullstop {20};
$Dash {21};
$Single_Quote {22};

(N | n) $Single_Quote (T | t) {202};
(Y | y) $Single_Quote (A | a) (L | l)* {202};

$Fullstop $Fullstop ($Fullstop*) {40};
$Dash $Dash ($Dash*) {40};
$Terminators $Terminators ($Terminators*) {40};
$Punctuation $Punctuation ($Punctuation*) {40};
$OtherSingle $OtherSingle ($OtherSingle*) {40};

$Single_Quote $Single_Quote {40};
$Single_Quote $Single_Quote $Single_Quote* {40};

$Hash ($ALetter | $Numeric)* {30};
$At ($ALetter | $Numeric)* {31};
$Dollar $ALetter ($ALetter | $Numeric)* {31};

$Time {50};
$IPAddress {51};

$ALetter / $IPAddress;
$ALetter / $Time;

($Colon | $Semicolon) $Parenthesis {32};

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

!!safe_reverse;

# rule 3
($Extend | $Format | $ZWJ)+ .?;

# rule 6
($MidLetter | $MidNumLet | $Single_Quote) ($BackALetterEx | $BackHebrew_LetterEx);

# rule 7b
$Double_Quote $BackHebrew_LetterEx;


# rule 11
($MidNum | $MidNumLet | $Single_Quote) $BackNumericEx;

# rule 13c
$BackRegional_IndicatorEx*;

# For dictionary-based break
$dictionary $dictionary;

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

!!safe_forward;

# rule 4
($Extend | $Format | $ZWJ)+ .?;

# rule 6
($MidLetterEx | $MidNumLetEx | $Single_QuoteEx) ($ALetterEx | $Hebrew_LetterEx);

# rule 7b
$Double_QuoteEx $Hebrew_LetterEx;

# rule 11
($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx;

# rule 13c
$Regional_IndicatorEx*;

# For dictionary-based break
$dictionary $dictionary;
Commit	Line	Data
f3c0d7a5 A	1	#
	2	# Copyright (C) 2016 and later: Unicode, Inc. and others.
	3	# License & terms of use: http://www.unicode.org/copyright.html
	4	# Copyright (C) 2002-2016, International Business Machines Corporation
	5	# and others. All Rights Reserved.
	6	#
	7	# file: word_urbTokTest.txt
	8	#
	9	# ICU Word Break Rules
	10	# See Unicode Standard Annex #29.
	11	# These rules are based on UAX #29 Revision 29 for Unicode Version 9.0
	12	# with additions for Emoji Sequences from https://goo.gl/cluFCn
	13	# Also modified with additions for testing urbtok_ functions.
	14	#
	15
	16	##############################################################################
	17	#
	18	# Character class definitions from TR 29
	19	#
	20	##############################################################################
	21
	22	!!chain;
	23
	24	# Smart Tokenizer customization
	25
	26	$Space = [\u0020];
	27	$Fullstop = [\u002E\uFE52\uFF0E];
	28	$Dash = [\u002D\uFE63\uFF0D];
	29
	30	$Terminators = [\u0021\u00A1\u00A1\u01C3\u01C3\u01C3\u203C\u2048\uFE15\uFF01\u003F];
	31	$Parenthesis = [\u0028\u005B\u007B\u0029\u005D\u007D];
	32	$Punctuation = [\u007E\u003D\u002A\u003C\u003E];
	33	$OtherSingle = [\u0060\u0300\u030F];
	34
	35	$Hash = [\u0023 \uFE5F \uFF03];
	36	$At = [\u0040 \uFE6B \uFF20];
	37	$Dollar = [\u0024];
	38
	39	$Semicolon = [\u003B];
	40	$Colon = [\u003A];
	41
	42	#
	43	# Character Class Definitions.
	44	#
	45
	46	$CR = [\p{Word_Break = CR}];
	47	$LF = [\p{Word_Break = LF}];
	48	$Newline = [\p{Word_Break = Newline}];
	49	$Extend = [\p{Word_Break = Extend}];
	50	$ZWJ = [\p{Word_Break = ZWJ}];
	51	$Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
	52	$Format = [\p{Word_Break = Format}];
	53	$Katakana = [\p{Word_Break = Katakana}];
	54	$Hebrew_Letter = [\p{Word_Break = Hebrew_Letter}];
	55	$ALetter = [\p{Word_Break = ALetter}];
	56	$Single_Quote = [\p{Word_Break = Single_Quote}\u2018\u2019];
	57	$Double_Quote = [\p{Word_Break = Double_Quote}];
	58	$MidNumLet = [\p{Word_Break = MidNumLet}-[$Fullstop $Single_Quote]];
	59	$MidLetter = [\p{Word_Break = MidLetter}-[$Single_Quote]];
	60	$MidNum = [\p{Word_Break = MidNum}];
	61	$Numeric = [\p{Word_Break = Numeric}];
	62	$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
	63	$E_Base = [\p{Word_Break = EB}\U0001F3C2\U0001F3C7\U0001F3CC\U0001F46A-\U0001F46D\U0001F46F\U0001F574\U0001F6CC];
	64	$E_Modifier = [\p{Word_Break = EM}];
65
66	# Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r12773
67	$Extended_Pict = [\U0001F774-\U0001F77F\u2700-\u2701\u2703-\u2704\u270E\u2710-\u2711\u2765-\u2767\U0001F030-\U0001F093\U0001F094-\U0001F09F\U0001F10D-\U0001F10F\U0001F12F\U0001F16C-\U0001F16F\U0001F1AD-\U0001F1E5\U0001F203-\U0001F20F\U0001F23C-\U0001F23F\U0001F249-\U0001F24F\U0001F252-\U0001F2FF\U0001F7D5-\U0001F7FF\U0001F000-\U0001F003\U0001F005-\U0001F02B\U0001F02C-\U0001F02F\U0001F322-\U0001F323\U0001F394-\U0001F395\U0001F398\U0001F39C-\U0001F39D\U0001F3F1-\U0001F3F2\U0001F3F6\U0001F4FE\U0001F53E-\U0001F548\U0001F54F\U0001F568-\U0001F56E\U0001F571-\U0001F572\U0001F57B-\U0001F586\U0001F588-\U0001F589\U0001F58E-\U0001F58F\U0001F591-\U0001F594\U0001F597-\U0001F5A3\U0001F5A6-\U0001F5A7\U0001F5A9-\U0001F5B0\U0001F5B3-\U0001F5BB\U0001F5BD-\U0001F5C1\U0001F5C5-\U0001F5D0\U0001F5D4-\U0001F5DB\U0001F5DF-\U0001F5E0\U0001F5E2\U0001F5E4-\U0001F5E7\U0001F5E9-\U0001F5EE\U0001F5F0-\U0001F5F2\U0001F5F4-\U0001F5F9\u2605\u2607-\u260D\u260F-\u2610\u2612\u2616-\u2617\u2619-\u261C\u261E-\u261F\u2621\u2624-\u2625\u2627-\u2629\u262B-\u262D\u2630-\u2637\u263B-\u2647\u2654-\u265F\u2661-\u2662\u2664\u2667\u2669-\u267A\u267C-\u267E\u2680-\u2691\u2695\u2698\u269A\u269D-\u269F\u26A2-\u26A9\u26AC-\u26AF\u26B2-\u26BC\u26BF-\u26C3\u26C6-\u26C7\u26C9-\u26CD\u26D0\u26D2\u26D5-\u26E8\u26EB-\u26EF\u26F6\u26FB-\u26FC\u26FE-\u26FF\u2388\U0001FA00-\U0001FFFD\U0001F0A0-\U0001F0AE\U0001F0B1-\U0001F0BF\U0001F0C1-\U0001F0CF\U0001F0D1-\U0001F0F5\U0001F0AF-\U0001F0B0\U0001F0C0\U0001F0D0\U0001F0F6-\U0001F0FF\U0001F80C-\U0001F80F\U0001F848-\U0001F84F\U0001F85A-\U0001F85F\U0001F888-\U0001F88F\U0001F8AE-\U0001F8FF\U0001F900-\U0001F90F\U0001F91F\U0001F928-\U0001F92F\U0001F931-\U0001F932\U0001F93F\U0001F94C-\U0001F94F\U0001F95F-\U0001F97F\U0001F992-\U0001F9BF\U0001F9C1-\U0001F9FF\U0001F6C6-\U0001F6CA\U0001F6E6-\U0001F6E8\U0001F6EA\U0001F6F1-\U0001F6F2\U0001F6D3-\U0001F6DF\U0001F6ED-\U0001F6EF\U0001F6F7-\U0001F6FF];
68	$EBG = [\p{Word_Break = EBG}];
69	$EmojiNRK = [[\p{Emoji}] - [\p{Word_Break = Regional_Indicator}\u002a\u00230-9©®™〰〽]];
70
71	$Han = [:Han:];
72	$Hiragana = [:Hiragana:];
73
74
75	# Dictionary character set, for triggering language-based break engines. Currently
76	# limited to LineBreak=Complex_Context. Note that this set only works in Unicode
77	# 5.0 or later as the definition of Complex_Context was corrected to include all
78	# characters requiring dictionary break.
79
80	$Control = [\p{Grapheme_Cluster_Break = Control}];
81	$HangulSyllable = [\uac00-\ud7a3];
82	$ComplexContext = [:LineBreak = Complex_Context:];
83	$KanaKanji = [$Han $Hiragana $Katakana];
84	$dictionaryCJK = [$KanaKanji $HangulSyllable];
85	$dictionary = [$ComplexContext $dictionaryCJK];
86
87	# leave CJK scripts out of ALetterPlus
88	$ALetterPlus = [$ALetter-$dictionaryCJK [$ComplexContext-$Extend-$Control]];
89
90
91	#
92	# Rules 4 Ignore Format and Extend characters,
93	# except when they appear at the beginning of a region of text.
94	#
95	# TODO: check if handling of katakana in dictionary makes rules incorrect/void
96	$KatakanaEx = $Katakana ($Extend \| $Format \| $ZWJ)*;
97	$Hebrew_LetterEx = $Hebrew_Letter ($Extend \| $Format \| $ZWJ)*;
98	$ALetterEx = $ALetterPlus ($Extend \| $Format \| $ZWJ)*;
99	$Single_QuoteEx = $Single_Quote ($Extend \| $Format \| $ZWJ)*;
100	$Double_QuoteEx = $Double_Quote ($Extend \| $Format \| $ZWJ)*;
101	$MidNumLetEx = $MidNumLet ($Extend \| $Format \| $ZWJ)*;
102	$MidLetterEx = $MidLetter ($Extend \| $Format \| $ZWJ)*;
103	$MidNumEx = $MidNum ($Extend \| $Format \| $ZWJ)*;
104	$NumericEx = $Numeric ($Extend \| $Format \| $ZWJ)*;
105	$ExtendNumLetEx = $ExtendNumLet ($Extend \| $Format \| $ZWJ)*;
106	$Regional_IndicatorEx = $Regional_Indicator ($Extend \| $Format \| $ZWJ)*;
107
108	$Ideographic = [\p{Ideographic}];
109	$HiraganaEx = $Hiragana ($Extend \| $Format \| $ZWJ)*;
110	$IdeographicEx = $Ideographic ($Extend \| $Format \| $ZWJ)*;
111
112	$Letter = [A-Za-z];
113
114	## -------------------------------------------------
115
116	!!forward;
117
118	# Rule 3 - CR x LF
119	#
120	$CR $LF;
121
122	# Rule 3c ZWJ x (Extended_Pict \| EmojiNRK). Precedes WB4, so no intervening Extend chars allowed.
123	#
124	$ZWJ ($Extended_Pict \| $EmojiNRK);
125
126
127	# Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
128	# of a region of Text. The rule here comes into play when the start of text
129	# begins with a group of Format chars, or with a "word" consisting of a single
130	# char that is not in any of the listed word break categories followed by
131	# format char(s), or is not a CJK dictionary character.
132	[^$CR $LF $Newline]? ($Extend \| $Format \| $ZWJ)+;
133
134	$NumericEx {100};
135	$ALetterEx {200};
136	$HangulSyllable {200};
137	$Hebrew_LetterEx{200};
138	$KatakanaEx {400}; # note: these status values override those from rule 5
139	$HiraganaEx {400}; # by virtue of being numerically larger.
140	$IdeographicEx {400}; #
141
142	$E_Base ($Extend \| $Format \| $ZWJ)*;
143	$E_Modifier ($Extend \| $Format \| $ZWJ)*;
144	$Extended_Pict ($Extend \| $Format \| $ZWJ)*;
145
146	#
147	# rule 5
148	# Do not break between most letters.
149	#
150	($ALetterEx \| $Hebrew_LetterEx) ($ALetterEx \| $Hebrew_LetterEx) {200};
151
152	# rule 6 and 7
153	($ALetterEx \| $Hebrew_LetterEx) ($MidLetterEx \| $MidNumLetEx ) ($ALetterEx \| $Hebrew_LetterEx) {200};
154
155	# rule 7a
156	$Hebrew_LetterEx $Single_QuoteEx {200};
157
158	# rule 7b and 7c
159	$Hebrew_LetterEx $Double_QuoteEx $Hebrew_LetterEx {200};
160
161	# rule 8
162
163	$NumericEx $NumericEx {100};
164
165	# rule 9
166
167	($ALetterEx \| $Hebrew_LetterEx) $NumericEx {200};
168
169	# rule 10
170
171	$NumericEx ($ALetterEx \| $Hebrew_LetterEx) {200};
172
173	# rule 11 and 12
174
175	$NumericEx ($MidNumEx \| $MidNumLetEx \| $Single_QuoteEx) $NumericEx {100};
176
177	# rule 13
178	# to be consistent with $KanaKanji $KanaKanhi, changed
179	# from 300 to 400.
180	# See also TestRuleStatus in intltest/rbbiapts.cpp
181	$KatakanaEx $KatakanaEx {400};
182
183	# rule 13a/b
184
185	$ALetterEx $ExtendNumLetEx {200}; # (13a)
186	$Hebrew_LetterEx $ExtendNumLetEx {200}; # (13a)
187	$NumericEx $ExtendNumLetEx {100}; # (13a)
188	$KatakanaEx $ExtendNumLetEx {400}; # (13a)
189	$ExtendNumLetEx $ExtendNumLetEx {200}; # (13a)
190
191	$ExtendNumLetEx $ALetterEx {200}; # (13b)
192	$ExtendNumLetEx $Hebrew_Letter {200}; # (13b)
193	$ExtendNumLetEx $NumericEx {100}; # (13b)
194	$ExtendNumLetEx $KatakanaEx {400}; # (13b)
195
196	# rule 14
197	# Do not break within emoji modifier sequences
198
199	($E_Base \| $EBG) ($Format \| $Extend \| $ZWJ)* $E_Modifier;
200
201	# rules 15 - 17
202	# Pairs of Regional Indicators stay together.
203	# With rule chaining disabled by ^, this rule will match exactly two of them.
204	# No other rule begins with a Regional_Indicator, so chaining cannot extend the match.
205	#
206	^$Regional_IndicatorEx $Regional_IndicatorEx;
207
208	# special handling for CJK characters: chain for later dictionary segmentation
209	$HangulSyllable $HangulSyllable {200};
210	$KanaKanji $KanaKanji {400}; # different rule status if both kana and kanji found
211
212	$Space* {1};
213	$Newline* {2};
214
215	$Fullstop {20};
216	$Dash {21};
217	$Single_Quote {22};
218
219	$Contraction = (N \| n) $Single_Quote (T \| t);
220	$Contraction2 = (N \| n) $Single_Quote (T \| t) $Single_Quote (V \| v) (E \| e);
221	$Contraction3 = (Y \| y) $Single_Quote (A \| a) (L \| l) (L \| l);
222
223	$Time = (0 \| 1 \| 2)? $Numeric $Colon (0 \| 1 \| 2 \| 3 \| 4 \| 5) $Numeric;
224	$IPAddress = $Numeric? $Numeric? $Numeric $Fullstop $Numeric? $Numeric? $Numeric;
225
226	(N \| n) $Single_Quote (T \| t) {202};
227	(Y \| y) $Single_Quote (A \| a) (L \| l)* {202};
228
229	$Fullstop $Fullstop ($Fullstop*) {40};
230	$Dash $Dash ($Dash*) {40};
231	$Terminators $Terminators ($Terminators*) {40};
232	$Punctuation $Punctuation ($Punctuation*) {40};
233	$OtherSingle $OtherSingle ($OtherSingle*) {40};
234
235	$Single_Quote $Single_Quote {40};
236	$Single_Quote $Single_Quote $Single_Quote* {40};
237
238	$Hash ($ALetter \| $Numeric)* {30};
239	$At ($ALetter \| $Numeric)* {31};
240	$Dollar $ALetter ($ALetter \| $Numeric)* {31};
241
242	$Time {50};
243	$IPAddress {51};
244
245	$ALetter / $IPAddress;
246	$ALetter / $Time;
247
248	($Colon \| $Semicolon) $Parenthesis {32};
249
250	## -------------------------------------------------
251
252	!!reverse;
253
254	$BackHebrew_LetterEx = ($Format \| $Extend \| $ZWJ)* $Hebrew_Letter;
255	$BackALetterEx = ($Format \| $Extend \| $ZWJ)* $ALetterPlus;
256	$BackSingle_QuoteEx = ($Format \| $Extend \| $ZWJ)* $Single_Quote;
257	$BackDouble_QuoteEx = ($Format \| $Extend \| $ZWJ)* $Double_Quote;
258	$BackMidNumLetEx = ($Format \| $Extend \| $ZWJ)* $MidNumLet;
259	$BackNumericEx = ($Format \| $Extend \| $ZWJ)* $Numeric;
260	$BackMidNumEx = ($Format \| $Extend \| $ZWJ)* $MidNum;
261	$BackMidLetterEx = ($Format \| $Extend \| $ZWJ)* $MidLetter;
262	$BackKatakanaEx = ($Format \| $Extend \| $ZWJ)* $Katakana;
263	$BackHiraganaEx = ($Format \| $Extend \| $ZWJ)* $Hiragana;
264	$BackExtendNumLetEx = ($Format \| $Extend \| $ZWJ)* $ExtendNumLet;
265	$BackRegional_IndicatorEx = ($Format \| $Extend \| $ZWJ)* $Regional_Indicator;
266
267	# rule 3
268	$LF $CR;
269
270	# Rule 3c ZWJ x (Extended_Pict \| EmojiNRK). Precedes WB4, so no intervening Extend chars allowed.
271	#
272	($Extended_Pict \| $EmojiNRK) $ZWJ;
273
274	# rule 4
275	($Format \| $Extend \| $ZWJ)* [^$CR $LF $Newline]?;
276
277	# rule 5
278
279	($BackALetterEx \| $BackHebrew_LetterEx) ($BackALetterEx \| $BackHebrew_LetterEx);
280
281	# rule 6 and 7
282
283	($BackALetterEx \| $BackHebrew_LetterEx) ($BackMidLetterEx \| $BackMidNumLetEx ) ($BackALetterEx \| $BackHebrew_LetterEx);
284
285	# rule 7a
286	$BackSingle_QuoteEx $BackHebrew_LetterEx;
287
288	# Rule 7b and 7c
289	$BackHebrew_LetterEx $BackDouble_QuoteEx $BackHebrew_LetterEx;
290
291	# rule 8
292
293	$BackNumericEx $BackNumericEx;
294
295	# rule 9
296
297	$BackNumericEx ($BackALetterEx \| $BackHebrew_LetterEx);
298
299	# rule 10
300
301	($BackALetterEx \| $BackHebrew_LetterEx) $BackNumericEx;
302
303	# rule 11 and 12
304
305	$BackNumericEx ($BackMidNumEx \| $BackMidNumLetEx \| $BackSingle_QuoteEx) $BackNumericEx;
306
307	# rule 13
308
309	$BackKatakanaEx $BackKatakanaEx;
310
311	# rules 13 a/b
312	#
313	$BackExtendNumLetEx ($BackALetterEx \| $BackHebrew_LetterEx \| $BackNumericEx \| $BackKatakanaEx \| $BackExtendNumLetEx);
314	($BackALetterEx \| $BackHebrew_LetterEx \| $BackNumericEx \| $BackKatakanaEx) $BackExtendNumLetEx;
315
316	# special handling for CJK characters: chain for later dictionary segmentation
317	$HangulSyllable $HangulSyllable;
318	$KanaKanji $KanaKanji; #different rule status if both kanji and kana found
319
320	# rule 14
321
322	$E_Modifier ($Format \| $Extend \| $ZWJ)* ($E_Base \| $EBG);
323
324	# rule 15 - 17
325	# Pairs of Regional Indicators stay together.
326
327	^$BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
328	($Format \| $Extend \| $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
329	^$BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
330	($Format \| $Extend \| $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
331
332	($Extended_Pict \| $EmojiNRK) $ZWJ $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
333	($Format \| $Extend \| $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
334	($Extended_Pict \| $EmojiNRK) $ZWJ $BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
335	($Format \| $Extend \| $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
336
337	$Space* {1};
338	$Newline* {2};
339
340	$Fullstop {20};
341	$Dash {21};
342	$Single_Quote {22};
343
344	(N \| n) $Single_Quote (T \| t) {202};
345	(Y \| y) $Single_Quote (A \| a) (L \| l)* {202};
346
347	$Fullstop $Fullstop ($Fullstop*) {40};
348	$Dash $Dash ($Dash*) {40};
349	$Terminators $Terminators ($Terminators*) {40};
350	$Punctuation $Punctuation ($Punctuation*) {40};
351	$OtherSingle $OtherSingle ($OtherSingle*) {40};
352
353	$Single_Quote $Single_Quote {40};
354	$Single_Quote $Single_Quote $Single_Quote* {40};
355
356	$Hash ($ALetter \| $Numeric)* {30};
357	$At ($ALetter \| $Numeric)* {31};
358	$Dollar $ALetter ($ALetter \| $Numeric)* {31};
359
360	$Time {50};
361	$IPAddress {51};
362
363	$ALetter / $IPAddress;
364	$ALetter / $Time;
365
366	($Colon \| $Semicolon) $Parenthesis {32};
367
368	## -------------------------------------------------
369
370	!!safe_reverse;
371
372	# rule 3
373	($Extend \| $Format \| $ZWJ)+ .?;
374
375	# rule 6
376	($MidLetter \| $MidNumLet \| $Single_Quote) ($BackALetterEx \| $BackHebrew_LetterEx);
377
378	# rule 7b
379	$Double_Quote $BackHebrew_LetterEx;
380
381
382	# rule 11
383	($MidNum \| $MidNumLet \| $Single_Quote) $BackNumericEx;
384
385	# rule 13c
386	$BackRegional_IndicatorEx*;
387
388	# For dictionary-based break
389	$dictionary $dictionary;
390
391	## -------------------------------------------------
392
393	!!safe_forward;
394
395	# rule 4
396	($Extend \| $Format \| $ZWJ)+ .?;
397
398	# rule 6
399	($MidLetterEx \| $MidNumLetEx \| $Single_QuoteEx) ($ALetterEx \| $Hebrew_LetterEx);
400
401	# rule 7b
402	$Double_QuoteEx $Hebrew_LetterEx;
403
404	# rule 11
405	($MidNumEx \| $MidNumLetEx \| $Single_QuoteEx) $NumericEx;
406
407	# rule 13c
408	$Regional_IndicatorEx*;
409
410	# For dictionary-based break
411	$dictionary $dictionary;