]> git.saurik.com Git - apple/icu.git/blobdiff - icuSources/data/brkitr/word.txt
ICU-531.48.tar.gz
[apple/icu.git] / icuSources / data / brkitr / word.txt
index 06c07df450a5072f5f809b97f618055ec6328f35..8d37f031281131a791761feea325f6bd78536472 100644 (file)
@@ -1,5 +1,5 @@
 #
-# Copyright (C) 2002-2013, International Business Machines Corporation 
+# Copyright (C) 2002-2015, International Business Machines Corporation 
 # and others. All Rights Reserved.
 #
 # file:  word.txt
@@ -43,48 +43,56 @@ $ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
 $Han                = [:Han:];
 $Hiragana           = [:Hiragana:];
 
-$RI_A        = \U0001F1E6;  # Trail ERTU
-$RI_B        = \U0001F1E7;  # Trail EGR
-$RI_C        = \U0001F1E8;  # Trail AHLNZ
+$RI_A        = \U0001F1E6;  # Trail ETU
+$RI_B        = \U0001F1E7;  # Trail ER
+$RI_C        = \U0001F1E8;  # Trail AHLNO
 $RI_D        = \U0001F1E9;  # Trail EK
-$RI_E        = \U0001F1EA;  # Trail GS
+$RI_E        = \U0001F1EA;  # Trail S
 $RI_F        = \U0001F1EB;  # Trail IR
-$RI_G        = \U0001F1EC;  # Trail BR
-$RI_H        = \U0001F1ED;  # Trail KU
-$RI_I        = \U0001F1EE;  # Trail DLNT
+$RI_G        = \U0001F1EC;  # Trail B
+$RI_H        = \U0001F1ED;  # Trail K
+$RI_I        = \U0001F1EE;  # Trail DELNT
 $RI_J        = \U0001F1EF;  # Trail OP
 $RI_K        = \U0001F1F0;  # Trail R
-$RI_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_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
 
-$RI_A_End    = [\U0001F1EA \U0001F1F7 \U0001F1F9 \U0001F1FA];          # ERTU
-$RI_B_End    = [\U0001F1EA \U0001F1EC \U0001F1F7];              # EGR
-$RI_C_End    = [\U0001F1E6 \U0001F1ED \U0001F1F1 \U0001F1F3 \U0001F1FF]; # AHLNZ
+$RI_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    = [\U0001F1EC \U0001F1F8];                         # GS
+$RI_E_End    = \U0001F1F8;                                      # S
 $RI_F_End    = [\U0001F1EE \U0001F1F7];                         # IR
-$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_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_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_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
 
+# 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
@@ -209,7 +217,6 @@ $RI_H ($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)*;
@@ -218,6 +225,12 @@ $RI_S ($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};
@@ -298,7 +311,6 @@ $BackExtendNumLetEx ($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $B
 ($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;
@@ -307,6 +319,12 @@ $BackExtendNumLetEx ($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $B
 ($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;