#
-# Copyright (C) 2002-2006, International Business Machines Corporation
+# Copyright (C) 2002-2010, International Business Machines Corporation
# and others. All Rights Reserved.
#
# file: word_ja.txt
#
# ICU Word Break Rules
# See Unicode Standard Annex #29.
-# These rules are based on Unicode Version 5.0 0
-# Includes post Unicode 5.0 change to treat Japanese half width voicing marks
-# as Extend
+# These rules are based on UAX-29 Revision 16 for Unicode 6.0
#
# Note: Updates to word.txt will usually need to be merged into
# word_POSIX.txt and word_ja.txt also.
# Character Class Definitions.
#
-$VoiceMarks = [\uff9e\uff9f];
+$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}-$VoiceMarks];
+$Katakana = [\p{Word_Break = Katakana}];
$ALetter = [\p{Word_Break = ALetter}];
+$MidNumLet = [\p{Word_Break = MidNumLet}];
$MidLetter = [\p{Word_Break = MidLetter}];
$MidNum = [\p{Word_Break = MidNum}];
$Numeric = [\p{Word_Break = Numeric}];
$ExtendNumLet = [\p{Word_Break = ExtendNumLet}];
-$CR = \u000d;
-$LF = \u000a;
-$Extend = [\p{Grapheme_Cluster_Break = Extend}$VoiceMarks];
-$Control = [\p{Grapheme_Cluster_Break = Control}];
-
# 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.
$dictionary = [:LineBreak = Complex_Context:];
-$ALetterPlus = [$ALetter [$dictionary-$Extend-$Control]];
-
+$Control = [\p{Grapheme_Cluster_Break = Control}];
+$ALetterPlus = [$ALetter [$dictionary-$Extend-$Control]]; # Note: default ALetter does not
+ # include the dictionary characters.
#
-# Rules 3 Grapheme Clusters behave like their first char.
-# Rule 4 Ignore trailing Format characters (Also see note in TR 29)
+# Rules 4 Ignore Format and Extend characters,
+# except when they appear at the beginning of a region of text.
#
$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 | $Format)*;
-$Hiragana = [:Hiragana:];
-$Ideographic = [:IDEOGRAPHIC:];
+$Hiragana = [\p{script=Hiragana}];
+$Ideographic = [\p{Ideographic} [\u3005 \u3007 \u303B]];
$HiraganaEx = $Hiragana ($Extend | $Format)*;
$IdeographicEx = $Ideographic ($Extend | $Format)*;
# Rule 3 - CR x LF
-# see character breaks.
-
-$CR $LF ($Extend | $Format)*;
+#
+$CR $LF;
# Rule 4 - ignore Format and Extend characters, except when they appear at the beginning
# of a region of Text. The rule here comes into play when the start of text
# begins with a group of Format chars, or with a "word" consisting of a single
# char that is not in any of the listed word break categories followed by
# format char(s).
-.? ($Extend | $Format)+;
-
+[^$CR $LF $Newline]? ($Extend | $Format)+;
$NumericEx {100};
$ALetterEx {200};
-$KatakanaEx {300};
-$HiraganaEx {300};
-$IdeographicEx {400};
+$KatakanaEx {300}; # note: these status values override those from rule 5
+$HiraganaEx {300}; # by virtual of being numerically larger.
+$IdeographicEx {400}; #
+#
# rule 5
-
+# Do not break between most letters.
+#
$ALetterEx $ALetterEx {200};
# rule 6 and 7
-$ALetterEx $MidLetterEx $ALetterEx {200};
+$ALetterEx ($MidLetterEx | $MidNumLetEx) $ALetterEx {200};
# rule 8
# rule 9
-$ALetterEx $Format* $NumericEx {200};
+$ALetterEx $NumericEx {200};
# rule 10
# rule 11 and 12
-$NumericEx $MidNumEx $NumericEx {100};
+$NumericEx ($MidNumEx | $MidNumLetEx) $NumericEx {100};
# rule 13
$HiraganaEx $HiraganaEx {300};
$IdeographicEx $IdeographicEx {400};
+
# rule 13a/b
$ALetterEx $ExtendNumLetEx {200}; # (13a)
$NumericEx $ExtendNumLetEx {100}; # (13a)
$KatakanaEx $ExtendNumLetEx {300}; # (13a)
-$ExtendNumLetEx $ExtendNumLetEx{200}; # (13a)
+$ExtendNumLetEx $ExtendNumLetEx {200}; # (13a)
$ExtendNumLetEx $ALetterEx {200}; # (13b)
$ExtendNumLetEx $NumericEx {100}; # (13b)
!!reverse;
$BackALetterEx = ($Format | $Extend)* $ALetterPlus;
+$BackMidNumLetEx = ($Format | $Extend)* $MidNumLet;
$BackNumericEx = ($Format | $Extend)* $Numeric;
$BackMidNumEx = ($Format | $Extend)* $MidNum;
$BackMidLetterEx = ($Format | $Extend)* $MidLetter;
$BackExtendNumLetEx= ($Format | $Extend)* $ExtendNumLet;
# rule 3
-($Format | $Extend)* $LF $CR;
+$LF $CR;
# rule 4
-($Format | $Extend)* .?;
+($Format | $Extend)* [^$CR $LF $Newline]?;
# rule 5
# rule 6 and 7
-$BackALetterEx $BackMidLetterEx $BackALetterEx;
+$BackALetterEx ($BackMidLetterEx | $BackMidNumLetEx) $BackALetterEx;
# rule 8
# rule 11 and 12
-$BackNumericEx $BackMidNumEx $BackNumericEx;
+$BackNumericEx ($BackMidNumEx | $BackMidNumLetEx) $BackNumericEx;
# rule 13
$BackHiraganaEx $BackHiraganaEx;
$BackIdeographicEx $BackIdeographicEx;
+
+
# rules 13 a/b
#
-($BackALetterEx | $BackNumericEx | $BackKatakanaEx | $BackExtendNumLetEx) $BackExtendNumLetEx;
-$BackExtendNumLetEx ($BackALetterEx | $BackNumericEx | $BackKatakanaEx);
+$BackExtendNumLetEx ($BackALetterEx | $BackNumericEx | $BackKatakanaEx | $BackExtendNumLetEx);
+($BackALetterEx | $BackNumericEx | $BackKatakanaEx) $BackExtendNumLetEx;
## -------------------------------------------------
($Extend | $Format)+ .?;
# rule 6
-$MidLetter $BackALetterEx;
+($MidLetter | $MidNumLet) $BackALetterEx;
# rule 11
-$MidNum $BackNumericEx;
+($MidNum | $MidNumLet) $BackNumericEx;
# For dictionary-based break
$dictionary $dictionary;
($Extend | $Format)+ .?;
# rule 6
-$MidLetterEx $ALetterEx;
+($MidLetterEx | $MidNumLetEx) $ALetterEx;
# rule 11
-$MidNumEx $NumericEx;
+($MidNumEx | $MidNumLetEx) $NumericEx;
# For dictionary-based break
$dictionary $dictionary;
projects / apple / icu.git / blobdiff