#
-# Copyright (C) 2002-2013, International Business Machines Corporation
+# Copyright (C) 2002-2015, International Business Machines Corporation
# and others. All Rights Reserved.
#
# file: word_POSIX.txt
#
# ICU Word Break Rules, POSIX locale.
# See Unicode Standard Annex #29.
-# These rules are based on UAX #29 Revision 20 for Unicode Version 6.2
+# 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.
##############################################################################
!!chain;
+!!RINoChain;
#
# Character Class Definitions.
#
-$CR = [\p{Word_Break = CR}];
-$LF = [\p{Word_Break = LF}];
-$Newline = [\p{Word_Break = Newline}];
-$Extend = [\p{Word_Break = Extend}];
-$Format = [\p{Word_Break = Format}];
-$Hiragana = [:Hiragana:];
-$Katakana = [\p{Word_Break = Katakana}];
-$Han = [:Han:];
-$ALetter = [\p{Word_Break = ALetter}];
-$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}];
-
-$RI_A = \U0001F1E6; # Trail ERTU
-$RI_B = \U0001F1E7; # Trail EGR
-$RI_C = \U0001F1E8; # Trail AHLNZ
-$RI_D = \U0001F1E9; # Trail EK
-$RI_E = \U0001F1EA; # Trail GS
-$RI_F = \U0001F1EB; # Trail IR
-$RI_G = \U0001F1EC; # Trail BR
-$RI_H = \U0001F1ED; # Trail KU
-$RI_I = \U0001F1EE; # Trail DLNT
-$RI_J = \U0001F1EF; # Trail OP
-$RI_K = \U0001F1F0; # Trail R
-$RI_L = \U0001F1F1; # Trail B
-$RI_M = \U0001F1F2; # Trail OXY
-$RI_N = \U0001F1F3; # Trail LO
-$RI_P = \U0001F1F5; # Trail LT
-$RI_R = \U0001F1F7; # Trail OU
-$RI_S = \U0001F1F8; # Trail AEGK
-$RI_T = \U0001F1F9; # Trail HRW
-$RI_U = \U0001F1FA; # Trail AS
-$RI_V = \U0001F1FB; # Trail N
-
-$RI_A_End = [\U0001F1EA \U0001F1F7 \U0001F1F9 \U0001F1FA]; # ERTU
-$RI_B_End = [\U0001F1EA \U0001F1EC \U0001F1F7]; # EGR
-$RI_C_End = [\U0001F1E6 \U0001F1ED \U0001F1F1 \U0001F1F3 \U0001F1FF]; # AHLNZ
-$RI_D_End = [\U0001F1EA \U0001F1F0]; # EK
-$RI_E_End = [\U0001F1EC \U0001F1F8]; # GS
-$RI_F_End = [\U0001F1EE \U0001F1F7]; # IR
-$RI_G_End = [\U0001F1E7 \U0001F1F7]; # BR
-$RI_H_End = [\U0001F1F0 \U0001F1FA]; # KU
-$RI_I_End = [\U0001F1E9 \U0001F1F1 \U0001F1F3 \U0001F1F9]; # DLNT
-$RI_J_End = [\U0001F1F4 \U0001F1F5]; # OP
-$RI_K_End = \U0001F1F7; # R
-$RI_L_End = \U0001F1E7; # B
-$RI_M_End = [\U0001F1F4 \U0001F1FD \U0001F1FE]; # OXY
-$RI_N_End = [\U0001F1F1 \U0001F1F4]; # LO
-$RI_P_End = [\U0001F1F1 \U0001F1F9]; # LT
-$RI_R_End = [\U0001F1F4 \U0001F1FA]; # OU
-$RI_S_End = [\U0001F1E6 \U0001F1EA \U0001F1EC \U0001F1F0]; # AEGK
-$RI_T_End = [\U0001F1ED \U0001F1F7 \U0001F1FC]; # HRW
-$RI_U_End = [\U0001F1E6 \U0001F1F8]; # AS
-$RI_V_End = \U0001F1F3; # N
-
+$CR = [\p{Word_Break = CR}];
+$LF = [\p{Word_Break = LF}];
+$Newline = [\p{Word_Break = Newline}];
+$Extend = [\p{Word_Break = Extend}];
+$RI = [\p{Word_Break = Regional_Indicator}];
+$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}];
+$Double_Quote = [\p{Word_Break = Double_Quote}];
+$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:];
+
+# 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 \U0001F441 \U0001F466-\U0001F469 \U0001F48B \U0001F5E8];
+$EmojiForMods = [\u261D \u26F9 \u270A-\u270D \U0001F385 \U0001F3C3-\U0001F3C4 \U0001F3CA-\U0001F3CB \U0001F442-\U0001F443 \U0001F446-\U0001F450 \U0001F466-\U0001F469 \U0001F46E-\U0001F478 \U0001F47C \U0001F481-\U0001F483 \U0001F485-\U0001F487 \U0001F4AA \U0001F575 \U0001F590 \U0001F595 \U0001F596 \U0001F645-\U0001F647 \U0001F64B-\U0001F64F \U0001F6A3 \U0001F6B4-\U0001F6B6 \U0001F6C0 \U0001F918];
+$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
# 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 | $Format)*;
-$ALetterEx = $ALetterPlus ($Extend | $Format)*;
-$MidNumLetEx = $MidNumLet ($Extend | $Format)*;
-$MidLetterEx = $MidLetter ($Extend | $Format)*;
-$MidNumEx = $MidNum ($Extend | $Format)*;
-$NumericEx = $Numeric ($Extend | $Format)*;
-$ExtendNumLetEx = $ExtendNumLet ($Extend | $Format)*;
+$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)*;
$Ideographic = [\p{Ideographic}];
$HiraganaEx = $Hiragana ($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.
$IdeographicEx {400}; #
# rule 5
# Do not break between most letters.
#
-$ALetterEx $ALetterEx {200};
+($ALetterEx | $Hebrew_LetterEx) ($ALetterEx | $Hebrew_LetterEx) {200};
# rule 6 and 7
-$ALetterEx ($MidLetterEx | $MidNumLetEx) $ALetterEx {200};
+($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 $Hebrew_LetterEx {200};
# rule 8
# rule 9
-$ALetterEx $NumericEx {200};
+($ALetterEx | $Hebrew_LetterEx) $NumericEx {200};
# rule 10
-$NumericEx $ALetterEx {200};
+$NumericEx ($ALetterEx | $Hebrew_LetterEx) {200};
# rule 11 and 12
-$NumericEx ($MidNumEx | $MidNumLetEx) $NumericEx {100};
+$NumericEx ($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx {100};
# rule 13
# to be consistent with $KanaKanji $KanaKanhi, changed
# rule 13a/b
-$ALetterEx $ExtendNumLetEx {200}; # (13a)
-$NumericEx $ExtendNumLetEx {100}; # (13a)
-$KatakanaEx $ExtendNumLetEx {400}; # (13a)
-$ExtendNumLetEx $ExtendNumLetEx {200}; # (13a)
+$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 $NumericEx {100}; # (13b)
-$ExtendNumLetEx $KatakanaEx {400}; # (13b)
+$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_L ($Extend|$Format)* $RI_L_End ($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 $RI $Extend* / $RI;
+$RI $RI $Extend*;
+
+# 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 $HangulSyllable {200};
!!reverse;
+$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)* $MidNum;
# rule 5
-$BackALetterEx $BackALetterEx;
+($BackALetterEx | $BackHebrew_LetterEx) ($BackALetterEx | $BackHebrew_LetterEx);
# rule 6 and 7
-$BackALetterEx ($BackMidLetterEx | $BackMidNumLetEx) $BackALetterEx;
+($BackALetterEx | $BackHebrew_LetterEx) ($BackMidLetterEx | $BackMidNumLetEx | $BackSingle_QuoteEx) ($BackALetterEx | $BackHebrew_LetterEx);
+
+# rule 7a
+$BackSingle_QuoteEx $BackHebrew_LetterEx;
+# Rule 7b and 7c
+$BackHebrew_LetterEx $BackDouble_QuoteEx $BackHebrew_LetterEx;
# rule 8
# rule 9
-$BackNumericEx $BackALetterEx;
+$BackNumericEx ($BackALetterEx | $BackHebrew_LetterEx);
# rule 10
-$BackALetterEx $BackNumericEx;
+($BackALetterEx | $BackHebrew_LetterEx) $BackNumericEx;
# rule 11 and 12
-$BackNumericEx ($BackMidNumEx | $BackMidNumLetEx) $BackNumericEx;
+$BackNumericEx ($BackMidNumEx | $BackMidNumLetEx | $BackSingle_QuoteEx) $BackNumericEx;
# rule 13
# rules 13 a/b
#
-$BackExtendNumLetEx ($BackALetterEx | $BackNumericEx | $BackKatakanaEx | $BackExtendNumLetEx);
-($BackALetterEx | $BackNumericEx | $BackKatakanaEx) $BackExtendNumLetEx;
+$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)* $RI_L_End ($Format|$Extend)* $RI_L;
-($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)* $RI_V;
+$Extend* $RI $RI / $Extend* $RI $RI;
+$Extend* $RI $RI;
+
+# 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 $HangulSyllable;
($Extend | $Format)+ .?;
# rule 6
-($MidLetter | $MidNumLet) $BackALetterEx;
+($MidLetter | $MidNumLet | $Single_Quote) ($BackALetterEx | $BackHebrew_LetterEx);
+
+# rule 7b
+$Double_Quote $BackHebrew_LetterEx;
+
# rule 11
-($MidNum | $MidNumLet) $BackNumericEx;
+($MidNum | $MidNumLet | $Single_Quote) $BackNumericEx;
+$RI $RI+;
# For dictionary-based break
$dictionary $dictionary;
($Extend | $Format)+ .?;
# rule 6
-($MidLetterEx | $MidNumLetEx) $ALetterEx;
+($MidLetterEx | $MidNumLetEx | $Single_QuoteEx) ($ALetterEx | $Hebrew_LetterEx);
+
+# rule 7b
+$Double_QuoteEx $Hebrew_LetterEx;
# rule 11
-($MidNumEx | $MidNumLetEx) $NumericEx;
+($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx;
+$RI $RI+;
# For dictionary-based break
$dictionary $dictionary;
projects / apple / icu.git / blobdiff