blob: bc2881bdc34ee026bcb8a8c46dde5b865edbf6ae [file] [log] [blame]
diff --git a/source/data/brkitr/word.txt b/source/data/brkitr/word.txt
index c74da4c..c5d6df7 100644
--- a/source/data/brkitr/word.txt
+++ b/source/data/brkitr/word.txt
@@ -60,11 +60,9 @@ $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]];
#
@@ -166,11 +164,6 @@ $ExtendNumLetEx $KatakanaEx {400}; # (13b)
$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;
@@ -237,10 +230,6 @@ $BackExtendNumLetEx ($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $B
$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;
diff --git a/source/data/brkitr/brklocal.mk b/source/data/brkitr/brklocal.mk
index c41c85a..5e0641b 100644
--- a/source/data/brkitr/brklocal.mk
+++ b/source/data/brkitr/brklocal.mk
@@ -34,17 +34,17 @@ BRK_RES_ALIAS_SOURCE = $(BRK_RES_SYNTHETIC_ALIAS)
# List of dictionary files (dict).
-BRK_DICT_SOURCE = burmesedict.txt cjdict.txt khmerdict.txt laodict.txt\
+BRK_DICT_SOURCE = burmesedict.txt khmerdict.txt laodict.txt\
thaidict.txt
# List of break iterator files (brk).
BRK_SOURCE = char.txt line.txt line_fi.txt\
- sent.txt sent_el.txt title.txt word.txt
+ sent.txt sent_el.txt title.txt word.txt word_ja.txt
# Ordinary resources
BRK_RES_SOURCE = de.txt el.txt en.txt en_US.txt\
es.txt fi.txt fr.txt it.txt\
- pt.txt ru.txt
+ pt.txt ru.txt ja.txt
diff --git a/source/data/brkitr/root.txt b/source/data/brkitr/root.txt
index 2dd1fdc..1d066be 100644
--- a/source/data/brkitr/root.txt
+++ b/source/data/brkitr/root.txt
@@ -16,9 +16,6 @@ root{
word:process(dependency){"word.brk"}
}
dictionaries{
- Hani:process(dependency){"cjdict.dict"}
- Hira:process(dependency){"cjdict.dict"}
- Kata:process(dependency){"cjdict.dict"}
Khmr:process(dependency){"khmerdict.dict"}
Laoo:process(dependency){"laodict.dict"}
Mymr:process(dependency){"burmesedict.dict"}
diff --git a/source/data/brkitr/ja.txt b/source/data/brkitr/ja.txt
index 3eb81d0..ffdbc6d 100644
--- a/source/data/brkitr/ja.txt
+++ b/source/data/brkitr/ja.txt
@@ -9,6 +9,6 @@
ja{
Version{"2.0.82.42"}
boundaries{
- line:process(dependency){"line_ja.brk"}
+ word:process(dependency){"word_ja.brk"}
}
}