ICU update to 54.1 - step 5

source/data/brkitr/word_ja.txt

 #
 # Copyright (C) 2002-2013, International Business Machines Corporation 
 # and others. All Rights Reserved.
 #
-# file:  word.txt
+# file:  word_ja.txt
 #
 # ICU Word Break Rules
 #      See Unicode Standard Annex #29.
 #      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.
 
 ##############################################################################
 #
@@ skipping 12 matching lines @@
 $LF                 = [\p{Word_Break = LF}];
 $Newline            = [\p{Word_Break = Newline}];
 $Extend             = [\p{Word_Break = Extend}];
 $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}];
 $Double_Quote       = [\p{Word_Break = Double_Quote}];
-$MidNumLet          = [\p{Word_Break = MidNumLet}];
+# Remove two full stop characters from $MidNumLet and add them to $MidNum
+# to break a hostname into its components at the cost of breaking
+# 'e.g.' and 'i.e.' as well.
+# $MidNumLet is used in rules 6/7 (rules of our interest) and rules 11/12.
+# Because it's OR'd with $MidNum in rules 11/12, rules 11/12 are not affected
+# while rules 6/7 are reverted to the old behavior we want.
+$MidNumLet    = [[\p{Word_Break = MidNumLet}] - [\u002E \uFF0E]];
 $MidLetter          = [\p{Word_Break = MidLetter}];
-$MidNum             = [\p{Word_Break = MidNum}];
-$Numeric            = [\p{Word_Break = Numeric}];
+$MidNum       = [\p{Word_Break = MidNum}[\u002E \uFF0E]];
+$Numeric      = [\p{Word_Break = Numeric}[\uff10-\uff19]]; #includes fullwidth digits
 $ExtendNumLet       = [\p{Word_Break = ExtendNumLet}];
 
 $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.
 
-$Control        = [\p{Grapheme_Cluster_Break = Control}]; 
+$Control        = [\p{Grapheme_Cluster_Break = Control}];
 $HangulSyllable = [\uac00-\ud7a3];
 $ComplexContext = [:LineBreak = Complex_Context:];
 $KanaKanji      = [$Han $Hiragana $Katakana];
-$dictionaryCJK  = [$KanaKanji $HangulSyllable];
-$dictionary     = [$ComplexContext $dictionaryCJK];
+$dictionary     = [$ComplexContext];
 
-# leave CJK scripts out of ALetterPlus
-$ALetterPlus  = [$ALetter-$dictionaryCJK [$ComplexContext-$Extend-$Control]];
+$ALetterPlus  = [$ALetter [$ComplexContext-$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)*;
 $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)*;
 $Regional_IndicatorEx = $Regional_Indicator ($Extend |  $Format)*;
 
-$Ideographic    = [\p{Ideographic}];
+$Ideographic    = [\p{Ideographic} [\u3005 \u3007 \u303B]];
 $HiraganaEx     = $Hiragana     ($Extend |  $Format)*;
 $IdeographicEx  = $Ideographic  ($Extend |  $Format)*;
 
 ## -------------------------------------------------
 
 !!forward;
 
 
 # Rule 3 - CR x LF
 #
@@ skipping 43 matching lines @@
 
 # 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  $KatakanaEx {400};
+$HiraganaEx  $HiraganaEx {400};
+$IdeographicEx  $IdeographicEx {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
 
 $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 
-
-
 ## -------------------------------------------------
 
 !!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)* $Hiragana;
+$BackIdeographicEx        = ($Format | $Extend)* $Ideographic;
 $BackExtendNumLetEx       = ($Format | $Extend)* $ExtendNumLet;
 $BackRegional_IndicatorEx = ($Format | $Extend)* $Regional_Indicator;
 
 # rule 3
 $LF $CR;
 
 # rule 4
 ($Format | $Extend)*  [^$CR $LF $Newline]?;
 
 # rule 5
@@ skipping 22 matching lines @@
 
 ($BackALetterEx | $BackHebrew_LetterEx) $BackNumericEx;
 
 # rule 11 and 12
 
 $BackNumericEx ($BackMidNumEx | $BackMidNumLetEx | $BackSingle_QuoteEx) $BackNumericEx;
 
 # rule 13
 
 $BackKatakanaEx $BackKatakanaEx;
+$BackHiraganaEx $BackHiraganaEx;
+$BackIdeographicEx $BackIdeographicEx;
 
 # rules 13 a/b
 #
 $BackExtendNumLetEx ($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx | $BackExtendNumLetEx);
 ($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx) $BackExtendNumLetEx; 
 
 # rule 13c
 
 $BackRegional_IndicatorEx $BackRegional_IndicatorEx;
 
-# 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);
 
@@ skipping 18 matching lines @@
 ($MidLetterEx | $MidNumLetEx | $Single_QuoteEx) ($ALetterEx | $Hebrew_LetterEx);
 
 # rule 7b
 $Double_QuoteEx $Hebrew_LetterEx;
 
 # rule 11
 ($MidNumEx | $MidNumLetEx | $Single_QuoteEx) $NumericEx;
 
 # For dictionary-based break
 $dictionary $dictionary;