ICU-59117.0.1.tar.gz

[apple/icu.git] / icuSources / data / brkitr / rules / word_fi_sv.txt

diff --git a/icuSources/data/brkitr/rules/word_fi_sv.txt b/icuSources/data/brkitr/rules/word_fi_sv.txt
index 114100aff4be155260f3b37a74a03bbbd3744827..e4fb26a3446ad6b52448c8ec8f2d4fbb050df326 100644 (file)
--- a/icuSources/data/brkitr/rules/word_fi_sv.txt
+++ b/icuSources/data/brkitr/rules/word_fi_sv.txt
@@ -1,13 +1,15 @@
-#
-# Copyright (C) 2002-2016, International Business Machines Corporation
+#
+# 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_fi_sv.txt
 #
 # ICU Word Break Rules, fi/sv locales (these are actually the standard UAX #29 rules)
 #      See Unicode Standard Annex #29.
-#      These rules are based on UAX #29 Revision 27 for Unicode Version 8.0
-#      with additions from L2/16-011R3 for Emoji sequences.
+#      These rules are based on UAX #29 Revision 29 for Unicode Version 9.0
+#      with additions for Emoji Sequences from https://goo.gl/cluFCn
 #
 # Note:  Updates to word.txt will usually need to be merged into
 #        word_POSIX.txt also.
@@ -25,20 +27,13 @@
 #  Character Class Definitions.
 #
 
-# Apple $EmojiForMods becomes $E_Base here
-$E_Base      = [\u261D\u26F9\u270A-\u270D\U0001F385\U0001F3C2-\U0001F3C4\U0001F3C7\U0001F3CA-\U0001F3CC\U0001F442-\U0001F443\U0001F446-\U0001F450\U0001F466-\U0001F478\U0001F47C\U0001F481-\U0001F483\U0001F485-\U0001F487\U0001F4AA\U0001F574-\U0001F575\U0001F57A\U0001F590\U0001F595-\U0001F596\U0001F645-\U0001F647\U0001F64B-\U0001F64F\U0001F6A3\U0001F6B4-\U0001F6B6\U0001F6C0\U0001F6CC\U0001F918-\U0001F91E\U0001F926\U0001F930\U0001F933-\U0001F939\U0001F93C-\U0001F93E];
-# Apple $EmojiMods becomes $E_Modifier here, same chars
-$E_Modifier  = [\U0001F3FB-\U0001F3FF];
-$ZWJ = [\u200D];
-# Apple $EmojiForSeqs becomes $GAZ here (only emoji that follow a ZWJ)
-$GAZ         = [\u2640\u2642\u2764\u2695-\u2696\u2708\U0001F308\U0001F33E\U0001F373\U0001F393\U0001F3A4\U0001F3A8\U0001F3EB\U0001F3ED\U0001F466-\U0001F469\U0001F48B\U0001F4BB-\U0001F4BC\U0001F527\U0001F52C\U0001F5E8\U0001F680\U0001F692];
-
 $CR                 = [\p{Word_Break = CR}];
 $LF                 = [\p{Word_Break = LF}];
 $Newline            = [\p{Word_Break = Newline} ];
-$Extend             = [[\p{Word_Break = Extend}][:Block=Tags:]];
+$Extend             = [\p{Word_Break = Extend}];
+$ZWJ                = [\p{Word_Break = ZWJ}];
 $Regional_Indicator = [\p{Word_Break = Regional_Indicator}];
-$Format             = [[\p{Word_Break = Format}] - [:Block=Tags:]];
+$Format             = [\p{Word_Break = Format}];
 $Katakana           = [\p{Word_Break = Katakana}];
 $Hebrew_Letter      = [\p{Word_Break = Hebrew_Letter}];
 $ALetter            = [\p{Word_Break = ALetter}];
@@ -49,6 +44,13 @@ $MidLetter          = [\p{Word_Break = MidLetter}];
 $MidNum             = [\p{Word_Break = MidNum}];
 $Numeric            = [\p{Word_Break = Numeric}];
 $ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
+$E_Base             = [[\p{Word_Break = EB}] \U0001F46A-\U0001F46D\U0001F46F\U0001F91D\U0001F93C];
+$E_Modifier         = [\p{Word_Break = EM}];
+
+# Data for Extended Pictographic scraped from CLDR common/properties/ExtendedPictographic.txt, r13267
+$Extended_Pict = [\U0001F774-\U0001F77F\U00002700-\U00002701\U00002703-\U00002704\U0000270E\U00002710-\U00002711\U00002765-\U00002767\U0001F030-\U0001F093\U0001F094-\U0001F09F\U0001F10D-\U0001F10F\U0001F12F\U0001F16C-\U0001F16F\U0001F1AD-\U0001F1E5\U0001F260-\U0001F265\U0001F203-\U0001F20F\U0001F23C-\U0001F23F\U0001F249-\U0001F24F\U0001F252-\U0001F25F\U0001F266-\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\U00002605\U00002607-\U0000260D\U0000260F-\U00002610\U00002612\U00002616-\U00002617\U00002619-\U0000261C\U0000261E-\U0000261F\U00002621\U00002624-\U00002625\U00002627-\U00002629\U0000262B-\U0000262D\U00002630-\U00002637\U0000263B-\U00002647\U00002654-\U0000265F\U00002661-\U00002662\U00002664\U00002667\U00002669-\U0000267A\U0000267C-\U0000267E\U00002680-\U00002691\U00002695\U00002698\U0000269A\U0000269D-\U0000269F\U000026A2-\U000026A9\U000026AC-\U000026AF\U000026B2-\U000026BC\U000026BF-\U000026C3\U000026C6-\U000026C7\U000026C9-\U000026CD\U000026D0\U000026D2\U000026D5-\U000026E8\U000026EB-\U000026EF\U000026F6\U000026FB-\U000026FC\U000026FE-\U000026FF\U00002388\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-\U0001F90B\U0001F91F\U0001F928-\U0001F92F\U0001F931-\U0001F932\U0001F94C\U0001F95F-\U0001F96B\U0001F992-\U0001F997\U0001F9D0-\U0001F9E6\U0001F90C-\U0001F90F\U0001F93F\U0001F94D-\U0001F94F\U0001F96C-\U0001F97F\U0001F998-\U0001F9BF\U0001F9C1-\U0001F9CF\U0001F9E7-\U0001F9FF\U0001F6C6-\U0001F6CA\U0001F6D3-\U0001F6D4\U0001F6E6-\U0001F6E8\U0001F6EA\U0001F6F1-\U0001F6F2\U0001F6F7-\U0001F6F8\U0001F6D5-\U0001F6DF\U0001F6ED-\U0001F6EF\U0001F6F9-\U0001F6FF];
+$EBG                = [\p{Word_Break = EBG}];
+$EmojiNRK           = [[\p{Emoji}] - [\p{Word_Break = Regional_Indicator}\u002a\u00230-9©®™〰〽]];
 
 $Han                = [:Han:];
 $Hiragana           = [:Hiragana:];
@@ -59,7 +61,7 @@ $Hiragana           = [:Hiragana:];
 #   5.0 or later as the definition of Complex_Context was corrected to include all
 #   characters requiring dictionary break.
 
-$Control        = [\p{Grapheme_Cluster_Break = Control}];
+$Control        = [\p{Grapheme_Cluster_Break = Control}]; 
 $HangulSyllable = [\uac00-\ud7a3];
 $ComplexContext = [:LineBreak = Complex_Context:];
 $KanaKanji      = [$Han $Hiragana $Katakana];
@@ -71,7 +73,7 @@ $ALetterPlus  = [$ALetter-$dictionaryCJK [$ComplexContext-$Extend-$Control]];
 
 
 #
-#  Rules 4    Ignore Format and Extend characters,
+#  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
@@ -100,9 +102,9 @@ $IdeographicEx  = $Ideographic  ($Extend |  $Format | $ZWJ)*;
 #
 $CR $LF;
 
-# Rule 3c   ZWJ x GAZ.  Preceeds WB4, so no intervening Extend chars allowed.
+# Rule 3c   ZWJ x (Extended_Pict | EmojiNRK).  Precedes WB4, so no intervening Extend chars allowed.
 #
-$ZWJ $GAZ;
+$ZWJ ($Extended_Pict | $EmojiNRK);
 
 
 # Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
@@ -122,7 +124,7 @@ $IdeographicEx {400};    #
 
 $E_Base ($Extend | $Format | $ZWJ)*;
 $E_Modifier ($Extend | $Format | $ZWJ)*;
-$GAZ ($Extend | $Format | $ZWJ)*;
+$Extended_Pict ($Extend | $Format | $ZWJ)*;
 
 #
 # rule 5
@@ -151,7 +153,7 @@ $NumericEx $NumericEx {100};
 
 $NumericEx ($ALetterEx | $Hebrew_LetterEx) {200};
 
-# rule 11 and 12
+# rule 11 and 12 
 
 $NumericEx ($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx {100};
 
@@ -174,7 +176,12 @@ $ExtendNumLetEx  $Hebrew_Letter  {200};    #  (13b)
 $ExtendNumLetEx  $NumericEx      {100};    #  (13b)
 $ExtendNumLetEx  $KatakanaEx     {400};    #  (13b)
 
-# rule 13c
+# 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.
@@ -183,12 +190,7 @@ $ExtendNumLetEx  $KatakanaEx     {400};    #  (13b)
 
 # special handling for CJK characters: chain for later dictionary segmentation
 $HangulSyllable $HangulSyllable {200};
-$KanaKanji $KanaKanji {400}; # different rule status if both kana and kanji found
-
-# rule 13d
-#    E_Base x E_Modifier
-#
-($E_Base | $GAZ) ($Format | $Extend | $ZWJ)* $E_Modifier;
+$KanaKanji $KanaKanji {400}; # different rule status if both kana and kanji found 
 
 
 ## -------------------------------------------------
@@ -211,9 +213,9 @@ $BackRegional_IndicatorEx = ($Format | $Extend | $ZWJ)* $Regional_Indicator;
 # rule 3
 $LF $CR;
 
-# Rule 3c   ZWJ x GAZ.  Preceeds WB4, so no intervening Extend chars allowed.
+# Rule 3c   ZWJ x (Extended_Pict | EmojiNRK).  Precedes WB4, so no intervening Extend chars allowed.
 #
-$GAZ $ZWJ;
+($Extended_Pict | $EmojiNRK) $ZWJ;
 
 # rule 4
 ($Format | $Extend | $ZWJ)*  [^$CR $LF $Newline]?;
@@ -255,28 +257,29 @@ $BackKatakanaEx $BackKatakanaEx;
 # rules 13 a/b
 #
 $BackExtendNumLetEx ($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx | $BackExtendNumLetEx);
-($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx) $BackExtendNumLetEx;
+($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx) $BackExtendNumLetEx; 
 
-# rule 13c
+# 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);
 
-^$BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
+# rule 15 - 17
+#    Pairs of Regional Indicators stay together.
+
+^$BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)* 
         ($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
-^$BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
+^$BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)* 
         ($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
 
-$GAZ $ZWJ $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
+($Extended_Pict | $EmojiNRK) $ZWJ $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)* 
         ($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
-$GAZ $ZWJ $BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)*
+($Extended_Pict | $EmojiNRK) $ZWJ $BackRegional_IndicatorEx $BackRegional_IndicatorEx / ($BackRegional_IndicatorEx $BackRegional_IndicatorEx)* 
         ($Format | $Extend | $ZWJ)* [[^$Regional_Indicator $Format $Extend $ZWJ] {eof}];
 
-# special handling for CJK characters: chain for later dictionary segmentation
-$HangulSyllable $HangulSyllable;
-$KanaKanji $KanaKanji; #different rule status if both kanji and kana found
-
-# rule 13d
-
-$E_Modifier ($Format | $Extend | $ZWJ)* ($E_Base | $GAZ);
-
 
 
 ## -------------------------------------------------