| OLD | NEW |
| 1 diff --git a/source/data/brkitr/word.txt b/source/data/brkitr/word.txt | 1 diff --git a/source/data/brkitr/word.txt b/source/data/brkitr/word.txt |
| 2 index c74da4c..c5d6df7 100644 | 2 index c74da4c..c5d6df7 100644 |
| 3 --- a/source/data/brkitr/word.txt | 3 --- a/source/data/brkitr/word.txt |
| 4 +++ b/source/data/brkitr/word.txt | 4 +++ b/source/data/brkitr/word.txt |
| 5 @@ -60,11 +60,9 @@ $Control = [\p{Grapheme_Cluster_Break = Control}]; | 5 @@ -60,11 +60,9 @@ $Control = [\p{Grapheme_Cluster_Break = Control}]; |
| 6 $HangulSyllable = [\uac00-\ud7a3]; | 6 $HangulSyllable = [\uac00-\ud7a3]; |
| 7 $ComplexContext = [:LineBreak = Complex_Context:]; | 7 $ComplexContext = [:LineBreak = Complex_Context:]; |
| 8 $KanaKanji = [$Han $Hiragana $Katakana]; | 8 $KanaKanji = [$Han $Hiragana $Katakana]; |
| 9 -$dictionaryCJK = [$KanaKanji $HangulSyllable]; | 9 -$dictionaryCJK = [$KanaKanji $HangulSyllable]; |
| 10 -$dictionary = [$ComplexContext $dictionaryCJK]; | 10 -$dictionary = [$ComplexContext $dictionaryCJK]; |
| (...skipping 22 matching lines...) Expand all Loading... |
| 33 $BackRegional_IndicatorEx $BackRegional_IndicatorEx; | 33 $BackRegional_IndicatorEx $BackRegional_IndicatorEx; |
| 34 | 34 |
| 35 -# special handling for CJK characters: chain for later dictionary segmentation | 35 -# special handling for CJK characters: chain for later dictionary segmentation |
| 36 -$HangulSyllable $HangulSyllable; | 36 -$HangulSyllable $HangulSyllable; |
| 37 -$KanaKanji $KanaKanji; #different rule status if both kanji and kana found | 37 -$KanaKanji $KanaKanji; #different rule status if both kanji and kana found |
| 38 - | 38 - |
| 39 ## ------------------------------------------------- | 39 ## ------------------------------------------------- |
| 40 | 40 |
| 41 !!safe_reverse; | 41 !!safe_reverse; |
| 42 diff --git a/source/data/brkitr/brklocal.mk b/source/data/brkitr/brklocal.mk | 42 diff --git a/source/data/brkitr/brklocal.mk b/source/data/brkitr/brklocal.mk |
| 43 index ad36492..1d69c1e 100644 | 43 index c41c85a..5e0641b 100644 |
| 44 --- a/source/data/brkitr/brklocal.mk | 44 --- a/source/data/brkitr/brklocal.mk |
| 45 +++ b/source/data/brkitr/brklocal.mk | 45 +++ b/source/data/brkitr/brklocal.mk |
| 46 @@ -34,17 +34,17 @@ BRK_RES_ALIAS_SOURCE = $(BRK_RES_SYNTHETIC_ALIAS) | 46 @@ -34,17 +34,17 @@ BRK_RES_ALIAS_SOURCE = $(BRK_RES_SYNTHETIC_ALIAS) |
| 47 | 47 |
| 48 | 48 |
| 49 # List of dictionary files (dict). | 49 # List of dictionary files (dict). |
| 50 -BRK_DICT_SOURCE = burmesedict.txt cjdict.txt khmerdict.txt laodict.txt\ | 50 -BRK_DICT_SOURCE = burmesedict.txt cjdict.txt khmerdict.txt laodict.txt\ |
| 51 +BRK_DICT_SOURCE = burmesedict.txt khmerdict.txt laodict.txt\ | 51 +BRK_DICT_SOURCE = burmesedict.txt khmerdict.txt laodict.txt\ |
| 52 thaidict.txt | 52 thaidict.txt |
| 53 | 53 |
| 54 | 54 |
| 55 # List of break iterator files (brk). | 55 # List of break iterator files (brk). |
| 56 BRK_SOURCE = char.txt line.txt line_fi.txt\ | 56 BRK_SOURCE = char.txt line.txt line_fi.txt\ |
| 57 - sent.txt sent_el.txt title.txt word.txt | 57 - sent.txt sent_el.txt title.txt word.txt |
| 58 + sent.txt sent_el.txt title.txt word.txt word_ja.txt | 58 + sent.txt sent_el.txt title.txt word.txt word_ja.txt |
| 59 | 59 |
| 60 | 60 |
| 61 # Ordinary resources | 61 # Ordinary resources |
| 62 BRK_RES_SOURCE = de.txt el.txt en.txt en_US.txt\ | 62 BRK_RES_SOURCE = de.txt el.txt en.txt en_US.txt\ |
| 63 en_US_POSIX.txt es.txt fi.txt fr.txt it.txt\ | 63 es.txt fi.txt fr.txt it.txt\ |
| 64 - pt.txt ru.txt | 64 - pt.txt ru.txt |
| 65 + pt.txt ru.txt ja.txt | 65 + pt.txt ru.txt ja.txt |
| 66 | 66 |
| 67 diff --git a/source/data/brkitr/root.txt b/source/data/brkitr/root.txt | 67 diff --git a/source/data/brkitr/root.txt b/source/data/brkitr/root.txt |
| 68 index 2dd1fdc..1d066be 100644 | 68 index 2dd1fdc..1d066be 100644 |
| 69 --- a/source/data/brkitr/root.txt | 69 --- a/source/data/brkitr/root.txt |
| 70 +++ b/source/data/brkitr/root.txt | 70 +++ b/source/data/brkitr/root.txt |
| 71 @@ -16,9 +16,6 @@ root{ | 71 @@ -16,9 +16,6 @@ root{ |
| 72 word:process(dependency){"word.brk"} | 72 word:process(dependency){"word.brk"} |
| 73 } | 73 } |
| 74 dictionaries{ | 74 dictionaries{ |
| 75 - Hani:process(dependency){"cjdict.dict"} | 75 - Hani:process(dependency){"cjdict.dict"} |
| 76 - Hira:process(dependency){"cjdict.dict"} | 76 - Hira:process(dependency){"cjdict.dict"} |
| 77 - Kata:process(dependency){"cjdict.dict"} | 77 - Kata:process(dependency){"cjdict.dict"} |
| 78 Khmr:process(dependency){"khmerdict.dict"} | 78 Khmr:process(dependency){"khmerdict.dict"} |
| 79 Laoo:process(dependency){"laodict.dict"} | 79 Laoo:process(dependency){"laodict.dict"} |
| 80 Mymr:process(dependency){"burmesedict.dict"} | 80 Mymr:process(dependency){"burmesedict.dict"} |
| 81 diff --git a/source/data/brkitr/ja.txt b/source/data/brkitr/ja.txt | 81 diff --git a/source/data/brkitr/ja.txt b/source/data/brkitr/ja.txt |
| 82 index 3eb81d0..ffdbc6d 100644 | 82 index 3eb81d0..ffdbc6d 100644 |
| 83 --- a/source/data/brkitr/ja.txt | 83 --- a/source/data/brkitr/ja.txt |
| 84 +++ b/source/data/brkitr/ja.txt | 84 +++ b/source/data/brkitr/ja.txt |
| 85 @@ -9,6 +9,6 @@ | 85 @@ -9,6 +9,6 @@ |
| 86 ja{ | 86 ja{ |
| 87 Version{"2.0.82.42"} | 87 Version{"2.0.82.42"} |
| 88 boundaries{ | 88 boundaries{ |
| 89 - line:process(dependency){"line_ja.brk"} | 89 - line:process(dependency){"line_ja.brk"} |
| 90 + word:process(dependency){"word_ja.brk"} | 90 + word:process(dependency){"word_ja.brk"} |
| 91 } | 91 } |
| 92 } | 92 } |
| OLD | NEW |