#
-# Copyright (C) 2002-2003, International Business Machines Corporation and others.
-# All Rights Reserved.
+# Copyright (C) 2002-2015, International Business Machines Corporation
+# and others. All Rights Reserved.
#
-# file: word.txt
+# file: word.txt
#
-# ICU Word Break Rules
+# ICU Word Break Rules
# See Unicode Standard Annex #29.
-# These rules are based on Version 4.0.0, dated 2003-04-17
+# These rules are based on UAX #29 Revision 22 for Unicode Version 6.3
#
+# Note: Updates to word.txt will usually need to be merged into
+# word_POSIX.txt also.
-
-
-####################################################################################
+##############################################################################
#
# Character class definitions from TR 29
#
-####################################################################################
-$Katakana = [[:Script = KATAKANA:] [:name = KATAKANA-HIRAGANA PROLONGED SOUND MARK:]
- [:name = HALFWIDTH KATAKANA-HIRAGANA PROLONGED SOUND MARK:]
- [:name = HALFWIDTH KATAKANA VOICED SOUND MARK:]
- [:name = HALFWIDTH KATAKANA SEMI-VOICED SOUND MARK:]];
-
+##############################################################################
-$ALetter = [[:Alphabetic:] [:name= HEBREW PUNCTUATION GERESH:]
- - [:Ideographic:]
- - $Katakana
- - [:Script = Thai:]
- - [:Script = Lao:]
- - [:Script = Hiragana:]];
-
-$MidLetter = [[:name = APOSTROPHE:] [:name = MIDDLE DOT:] [:name = HEBREW PUNCTUATION GERSHAYIM:]
- [:name = RIGHT SINGLE QUOTATION MARK:] [:name = HYPHENATION POINT:]];
-
-$MidNumLet = [[:name = FULL STOP:] [:name = COLON:]];
-
-$MidNum = [[:LineBreak = Infix_Numeric:] - $MidNumLet];
-$Numeric = [:LineBreak = Numeric:];
+!!chain;
#
# Character Class Definitions.
-# The names are those from TR29.
#
-$CR = \u000d;
-$LF = \u000a;
-$Control = [[:Zl:] [:Zp:] [:Cc:] [:Cf:]];
-$Extend = [[:Grapheme_Extend = TRUE:]];
+$CR = [\p{Word_Break = CR}];
+$LF = [\p{Word_Break = LF}];
+$Newline = [\p{Word_Break = Newline}];
+$Extend = [\p{Word_Break = Extend}];
+$Format = [\p{Word_Break = Format}];
+$Katakana = [\p{Word_Break = Katakana}];
+$Hebrew_Letter = [\p{Word_Break = Hebrew_Letter}];
+$ALetter = [\p{Word_Break = ALetter}];
+$Single_Quote = [\p{Word_Break = Single_Quote}];
+$Double_Quote = [\p{Word_Break = Double_Quote}];
+$MidNumLet = [\p{Word_Break = MidNumLet}];
+$MidLetter = [\p{Word_Break = MidLetter}];
+$MidNum = [\p{Word_Break = MidNum}];
+$Numeric = [\p{Word_Break = Numeric}];
+$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
+$Han = [:Han:];
+$Hiragana = [:Hiragana:];
+$RI_A = \U0001F1E6; # Trail ETU
+$RI_B = \U0001F1E7; # Trail ER
+$RI_C = \U0001F1E8; # Trail AHLNO
+$RI_D = \U0001F1E9; # Trail EK
+$RI_E = \U0001F1EA; # Trail S
+$RI_F = \U0001F1EB; # Trail IR
+$RI_G = \U0001F1EC; # Trail B
+$RI_H = \U0001F1ED; # Trail K
+$RI_I = \U0001F1EE; # Trail DELNT
+$RI_J = \U0001F1EF; # Trail OP
+$RI_K = \U0001F1F0; # Trail R
+$RI_M = \U0001F1F2; # Trail OXY
+$RI_N = \U0001F1F3; # Trail LOZ
+$RI_P = \U0001F1F5; # Trail HLRT
+$RI_R = \U0001F1F7; # Trail U
+$RI_S = \U0001F1F8; # Trail AEG
+$RI_T = \U0001F1F9; # Trail R
+$RI_U = \U0001F1FA; # Trail S
+$RI_V = \U0001F1FB; # Trail N
+$RI_Z = \U0001F1FF; # Trail A
-####################################################################################
-#
-# Word Break Rules. Definitions and Rules specific to word break begin Here.
-#
-####################################################################################
+$RI_A_End = [\U0001F1EA \U0001F1F9 \U0001F1FA]; # ETU
+$RI_B_End = [\U0001F1EA \U0001F1F7]; # ER
+$RI_C_End = [\U0001F1E6 \U0001F1ED \U0001F1F1 \U0001F1F3 \U0001F1F4]; # AHLNO
+$RI_D_End = [\U0001F1EA \U0001F1F0]; # EK
+$RI_E_End = \U0001F1F8; # S
+$RI_F_End = [\U0001F1EE \U0001F1F7]; # IR
+$RI_G_End = \U0001F1E7; # B
+$RI_H_End = \U0001F1F0; # K
+$RI_I_End = [\U0001F1E9 \U0001F1EA \U0001F1F1 \U0001F1F3 \U0001F1F9]; # DELNT
+$RI_J_End = [\U0001F1F5 \U0001F1F4]; # OP
+$RI_K_End = \U0001F1F7; # R
+$RI_M_End = [\U0001F1F4 \U0001F1FD \U0001F1FE]; # OXY
+$RI_N_End = [\U0001F1F1 \U0001F1F4 \U0001F1FF]; # LOZ
+$RI_P_End = [\U0001F1ED \U0001F1F1 \U0001F1F7 \U0001F1F9]; # HLRT
+$RI_R_End = \U0001F1FA; # U
+$RI_S_End = [\U0001F1E6 \U0001F1EA \U0001F1EC]; # AEG
+$RI_T_End = \U0001F1F7; # R
+$RI_U_End = \U0001F1F8; # S
+$RI_V_End = \U0001F1F3; # N
+$RI_Z_End = \U0001F1E6; # A
-$Format = [[:Cf:]];
+# Special character classes for people & body part emoji:
+# Subsets of $Extend:
+$ZWJ = \u200D;
+$EmojiVar = \uFE0F;
+# The following are subsets of \p{Word_Break = Other}
+$EmojiForSeqs = [\u2764 \U0001F466-\U0001F469 \U0001F48B];
+$EmojiForMods = [\u261D \u270A-\u270C \U0001F385 \U0001F3C3-\U0001F3C4 \U0001F3C7 \U0001F3CA \U0001F442-\U0001F443 \U0001F446-\U0001F450 \U0001F466-\U0001F469 \U0001F46E-\U0001F478 \U0001F47C \U0001F481-\U0001F483 \U0001F485-\U0001F487 \U0001F4AA \U0001F596 \U0001F645-\U0001F647 \U0001F64B-\U0001F64F \U0001F6A3 \U0001F6B4-\U0001F6B6 \U0001F6C0];
+$EmojiMods = [\U0001F3FB-\U0001F3FF];
+# 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 $dictionaryCJK];
-# Rule 3: Treat a grapheme cluster as if it were a single character.
-# Hangul Syllables are easier to deal with here than they are in Grapheme Clusters
-# because we don't need to find the boundaries between adjacent syllables -
-# they won't be word boundaries.
-#
+# leave CJK scripts out of ALetterPlus
+$ALetterPlus = [$ALetter-$dictionaryCJK [$ComplexContext-$Extend-$Control]];
#
-# "Extended" definitions. Grapheme Cluster + Format Chars, treated like the base char.
+# Rules 4 Ignore Format and Extend characters,
+# except when they appear at the beginning of a region of text.
#
-$ALetterEx = $ALetter $Extend*;
-$NumericEx = $Numeric $Extend*;
-$MidNumEx = $MidNum $Extend*;
-$MidNumLetEx = $MidNumLet $Extend*;
-$MidLetterEx = $MidLetter $Extend*;
-$KatakanaEx = $Katakana $Extend*;
-$FormatEx = $Format $Extend*;
-
+# TODO: check if handling of katakana in dictionary makes rules incorrect/void
+$KatakanaEx = $Katakana ($Extend | $Format)*;
+$Hebrew_LetterEx = $Hebrew_Letter ($Extend | $Format)*;
+$ALetterEx = $ALetterPlus ($Extend | $Format)*;
+$Single_QuoteEx = $Single_Quote ($Extend | $Format)*;
+$Double_QuoteEx = $Double_Quote ($Extend | $Format)*;
+$MidNumLetEx = $MidNumLet ($Extend | $Format)*;
+$MidLetterEx = $MidLetter ($Extend | $Format)*;
+$MidNumEx = $MidNum ($Extend | $Format)*;
+$NumericEx = $Numeric ($Extend | $Format)*;
+$ExtendNumLetEx = $ExtendNumLet ($Extend | $Format)*;
-#
-# Numbers. Rules 8, 11, 12 form the TR.
-#
-$NumberSequence = $NumericEx ($FormatEx* ($MidNumEx | $MidNumLetEx)? $FormatEx* $NumericEx)*;
-$NumberSequence {100};
+$Ideographic = [\p{Ideographic}];
+$HiraganaEx = $Hiragana ($Extend | $Format)*;
+$IdeographicEx = $Ideographic ($Extend | $Format)*;
-#
-# Words. Alpha-numerics. Rule 5, 6, 7, 9, 10
-# - must include at least one letter.
-# - may include both letters and numbers.
-# - may include MideLetter, MidNumber punctuation.
-#
-$LetterSequence = $ALetterEx ($FormatEx* ($MidLetterEx | $MidNumLetEx)? $FormatEx* $ALetterEx)*; # rules #6, #7
-($NumberSequence $FormatEx*)? $LetterSequence ($FormatEx* ($NumberSequence | $LetterSequence))* {200};
+## -------------------------------------------------
-#
-# Do not break between Katakana. Rule #13.
-#
-$KatakanaEx ($FormatEx* $KatakanaEx)* {300};
-[:Hiragana:] $Extend* {300};
+!!forward;
-#
-# Ideographic Characters. Stand by themselves as words.
-# Separated from the "Everything Else" rule, below, only so that they
-# can be tagged with a return value. TODO: is this what we want?
-#
-[:IDEOGRAPHIC:] $Extend* {400};
+# Rule 3 - CR x LF
#
-# Everything Else, with no tag.
-# Non-Control chars combine with $Extend (combining) chars.
-# Controls are do not.
-#
-[^$Control [:Ideographic:]] $Extend*;
$CR $LF;
+# Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
+# of a region of Text. The rule here comes into play when the start of text
+# begins with a group of Format chars, or with a "word" consisting of a single
+# char that is not in any of the listed word break categories followed by
+# format char(s), or is not a CJK dictionary character.
+[^$CR $LF $Newline]? ($Extend | $Format)+;
+
+$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}; #
+
#
-# Reverse Rules. Back up over any of the chars that can group together.
-# (Reverse rules do not need to be exact; they can back up too far,
-# but must back up at least enough, and must stop on a boundary.)
+# rule 5
+# Do not break between most letters.
#
+($ALetterEx | $Hebrew_LetterEx) ($ALetterEx | $Hebrew_LetterEx) {200};
+
+# rule 6 and 7
+($ALetterEx | $Hebrew_LetterEx) ($MidLetterEx | $MidNumLetEx | $Single_QuoteEx) ($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 $KatakanaEx {400}; # (13b)
+
+# rule 13c
+
+$RI_A ($Extend|$Format)* $RI_A_End ($Extend|$Format)*;
+$RI_B ($Extend|$Format)* $RI_B_End ($Extend|$Format)*;
+$RI_C ($Extend|$Format)* $RI_C_End ($Extend|$Format)*;
+$RI_D ($Extend|$Format)* $RI_D_End ($Extend|$Format)*;
+$RI_E ($Extend|$Format)* $RI_E_End ($Extend|$Format)*;
+$RI_F ($Extend|$Format)* $RI_F_End ($Extend|$Format)*;
+$RI_G ($Extend|$Format)* $RI_G_End ($Extend|$Format)*;
+$RI_H ($Extend|$Format)* $RI_H_End ($Extend|$Format)*;
+$RI_I ($Extend|$Format)* $RI_I_End ($Extend|$Format)*;
+$RI_J ($Extend|$Format)* $RI_J_End ($Extend|$Format)*;
+$RI_K ($Extend|$Format)* $RI_K_End ($Extend|$Format)*;
+$RI_M ($Extend|$Format)* $RI_M_End ($Extend|$Format)*;
+$RI_N ($Extend|$Format)* $RI_N_End ($Extend|$Format)*;
+$RI_P ($Extend|$Format)* $RI_P_End ($Extend|$Format)*;
+$RI_R ($Extend|$Format)* $RI_R_End ($Extend|$Format)*;
+$RI_S ($Extend|$Format)* $RI_S_End ($Extend|$Format)*;
+$RI_T ($Extend|$Format)* $RI_T_End ($Extend|$Format)*;
+$RI_U ($Extend|$Format)* $RI_U_End ($Extend|$Format)*;
+$RI_V ($Extend|$Format)* $RI_V_End ($Extend|$Format)*;
+$RI_Z ($Extend|$Format)* $RI_Z_End ($Extend|$Format)*;
+
+# Special forward rules for people & body part emoji:
+# don't break $ZWJ from subsequent $EmojiForSeqs; don't break between relevant emoji and $EmojiMods
+$ZWJ $EmojiForSeqs;
+$EmojiForMods $EmojiVar? $EmojiMods;
+
+# special handling for CJK characters: chain for later dictionary segmentation
+$HangulSyllable $HangulSyllable {200};
+$KanaKanji $KanaKanji {400}; # different rule status if both kana and kanji found
+
-# NonStarters are the set of all characters that can appear at the 2nd - nth position of
-# a word. (They may also be the first.) The reverse rule skips over these, until it
-# reaches something that can only be the start (and probably only) char in a "word".
-# A space or punctuation meets the test.
+## -------------------------------------------------
+
+!!reverse;
+
+$BackHebrew_LetterEx = ($Format | $Extend)* $Hebrew_Letter;
+$BackALetterEx = ($Format | $Extend)* $ALetterPlus;
+$BackSingle_QuoteEx = ($Format | $Extend)* $Single_Quote;
+$BackDouble_QuoteEx = ($Format | $Extend)* $Double_Quote;
+$BackMidNumLetEx = ($Format | $Extend)* $MidNumLet;
+$BackNumericEx = ($Format | $Extend)* $Numeric;
+$BackMidNumEx = ($Format | $Extend)* $MidNum;
+$BackMidLetterEx = ($Format | $Extend)* $MidLetter;
+$BackKatakanaEx = ($Format | $Extend)* $Katakana;
+$BackHiraganaEx = ($Format | $Extend)* $Hiragana;
+$BackExtendNumLetEx = ($Format | $Extend)* $ExtendNumLet;
+
+# rule 3
+$LF $CR;
+
+# rule 4
+($Format | $Extend)* [^$CR $LF $Newline]?;
+
+# rule 5
+
+($BackALetterEx | $BackHebrew_LetterEx) ($BackALetterEx | $BackHebrew_LetterEx);
+
+# rule 6 and 7
+
+($BackALetterEx | $BackHebrew_LetterEx) ($BackMidLetterEx | $BackMidNumLetEx | $BackSingle_QuoteEx) ($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 $BackKatakanaEx;
+
+# rules 13 a/b
#
-$NonStarters = [$Numeric $ALetter $Katakana $MidLetter $MidNum $MidNumLet $Extend $Format];
+$BackExtendNumLetEx ($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx | $BackExtendNumLetEx);
+($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx) $BackExtendNumLetEx;
+
+# rule 13c
+
+($Format|$Extend)* $RI_A_End ($Format|$Extend)* $RI_A;
+($Format|$Extend)* $RI_B_End ($Format|$Extend)* $RI_B;
+($Format|$Extend)* $RI_C_End ($Format|$Extend)* $RI_C;
+($Format|$Extend)* $RI_D_End ($Format|$Extend)* $RI_D;
+($Format|$Extend)* $RI_E_End ($Format|$Extend)* $RI_E;
+($Format|$Extend)* $RI_F_End ($Format|$Extend)* $RI_F;
+($Format|$Extend)* $RI_G_End ($Format|$Extend)* $RI_G;
+($Format|$Extend)* $RI_H_End ($Format|$Extend)* $RI_H;
+($Format|$Extend)* $RI_I_End ($Format|$Extend)* $RI_I;
+($Format|$Extend)* $RI_J_End ($Format|$Extend)* $RI_J;
+($Format|$Extend)* $RI_K_End ($Format|$Extend)* $RI_K;
+($Format|$Extend)* $RI_M_End ($Format|$Extend)* $RI_M;
+($Format|$Extend)* $RI_N_End ($Format|$Extend)* $RI_N;
+($Format|$Extend)* $RI_P_End ($Format|$Extend)* $RI_P;
+($Format|$Extend)* $RI_R_End ($Format|$Extend)* $RI_R;
+($Format|$Extend)* $RI_S_End ($Format|$Extend)* $RI_S;
+($Format|$Extend)* $RI_T_End ($Format|$Extend)* $RI_T;
+($Format|$Extend)* $RI_U_End ($Format|$Extend)* $RI_U;
+($Format|$Extend)* $RI_V_End ($Format|$Extend)* $RI_V;
+($Format|$Extend)* $RI_Z_End ($Format|$Extend)* $RI_Z;
+
+# Special reverse rules for people & body part emoji:
+# don't break $ZWJ from subsequent $EmojiForSeqs; don't break between relevant emoji and $EmojiMods
+$EmojiForSeqs $ZWJ;
+$EmojiMods $EmojiVar? $EmojiForMods;
+
+# special handling for CJK characters: chain for later dictionary segmentation
+$HangulSyllable $HangulSyllable;
+$KanaKanji $KanaKanji; #different rule status if both kanji and kana found
+
+## -------------------------------------------------
+
+!!safe_reverse;
+
+# rule 3
+($Extend | $Format)+ .?;
+
+# rule 6
+($MidLetter | $MidNumLet | $Single_Quote) ($BackALetterEx | $BackHebrew_LetterEx);
+
+# rule 7b
+$Double_Quote $BackHebrew_LetterEx;
+
+
+# rule 11
+($MidNum | $MidNumLet | $Single_Quote) $BackNumericEx;
+
+# For dictionary-based break
+$dictionary $dictionary;
+
+## -------------------------------------------------
+
+!!safe_forward;
+
+# rule 4
+($Extend | $Format)+ .?;
+
+# rule 6
+($MidLetterEx | $MidNumLetEx | $Single_QuoteEx) ($ALetterEx | $Hebrew_LetterEx);
+
+# rule 7b
+$Double_QuoteEx $Hebrew_LetterEx;
+
+# rule 11
+($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx;
-#!.*;
-! ($NonStarters* | \n \r) .;
+# For dictionary-based break
+$dictionary $dictionary;
projects / apple / icu.git / blobdiff