ICU-59131.0.1.tar.gz

[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;