| Index: android/brkitr.patch
|
| diff --git a/android/brkitr.patch b/android/brkitr.patch
|
| index 0d27775d5054b5ade1d8e5c654118bebb379e08c..713b39e6ca0299033126b9272fe40f8f522adf2e 100644
|
| --- a/android/brkitr.patch
|
| +++ b/android/brkitr.patch
|
| @@ -1,8 +1,8 @@
|
| diff --git a/source/data/brkitr/brklocal.mk b/source/data/brkitr/brklocal.mk
|
| -index cb5226a..39202f1 100644
|
| +index b5eca75..2a75a9e 100644
|
| --- a/source/data/brkitr/brklocal.mk
|
| +++ b/source/data/brkitr/brklocal.mk
|
| -@@ -34,14 +34,14 @@ BRK_RES_ALIAS_SOURCE = $(BRK_RES_SYNTHETIC_ALIAS)
|
| +@@ -34,7 +34,7 @@ BRK_RES_ALIAS_SOURCE = $(BRK_RES_SYNTHETIC_ALIAS)
|
|
|
|
|
| # List of dictionary files (dict).
|
| @@ -11,30 +11,31 @@ index cb5226a..39202f1 100644
|
| thaidict.txt
|
|
|
|
|
| - # List of break iterator files (brk).
|
| +@@ -42,7 +42,7 @@ BRK_DICT_SOURCE = burmesedict.txt cjdict.txt khmerdict.txt laodict.txt\
|
| BRK_SOURCE = char.txt line.txt\
|
| line_normal.txt line_normal_cj.txt line_normal_fi.txt\
|
| + line_loose_cj.txt\
|
| - sent.txt sent_el.txt title.txt word.txt
|
| + sent.txt sent_el.txt title.txt word.txt word_ja.txt
|
|
|
|
|
| # Ordinary resources
|
| diff --git a/source/data/brkitr/ja.txt b/source/data/brkitr/ja.txt
|
| -index f9f986e..cd07526 100644
|
| +index 2e9a1c8..cb732a7 100644
|
| --- a/source/data/brkitr/ja.txt
|
| +++ b/source/data/brkitr/ja.txt
|
| -@@ -13,5 +13,6 @@ ja{
|
| - line_loose:process(dependency){"line_normal_cj.brk"}
|
| +@@ -7,5 +7,6 @@ ja{
|
| + line_loose:process(dependency){"line_loose_cj.brk"}
|
| line_normal:process(dependency){"line_normal_cj.brk"}
|
| line_strict:process(dependency){"line.brk"}
|
| + word:process(dependency){"word_ja.brk"}
|
| }
|
| }
|
| diff --git a/source/data/brkitr/root.txt b/source/data/brkitr/root.txt
|
| -index 77ddd14..2e275a1 100644
|
| +index 1a1ad8a..c790282 100644
|
| --- a/source/data/brkitr/root.txt
|
| +++ b/source/data/brkitr/root.txt
|
| -@@ -19,9 +19,6 @@ root{
|
| +@@ -13,9 +13,6 @@ root{
|
| word:process(dependency){"word.brk"}
|
| }
|
| dictionaries{
|
| @@ -44,11 +45,11 @@ index 77ddd14..2e275a1 100644
|
| Khmr:process(dependency){"khmerdict.dict"}
|
| Laoo:process(dependency){"laodict.dict"}
|
| Mymr:process(dependency){"burmesedict.dict"}
|
| -diff --git a/source/data/brkitr/word.txt b/source/data/brkitr/word.txt
|
| -index f89a2fe..9603957 100644
|
| ---- a/source/data/brkitr/word.txt
|
| -+++ b/source/data/brkitr/word.txt
|
| -@@ -54,11 +54,9 @@ $Control = [\p{Grapheme_Cluster_Break = Control}];
|
| +diff --git a/source/data/brkitr/rules/word.txt b/source/data/brkitr/rules/word.txt
|
| +index 9c93dd5..eb150ea 100644
|
| +--- a/source/data/brkitr/rules/word.txt
|
| ++++ b/source/data/brkitr/rules/word.txt
|
| +@@ -71,11 +71,9 @@ $Control = [\p{Grapheme_Cluster_Break = Control}];
|
| $HangulSyllable = [\uac00-\ud7a3];
|
| $ComplexContext = [:LineBreak = Complex_Context:];
|
| $KanaKanji = [$Han $Hiragana $Katakana];
|
| @@ -62,9 +63,9 @@ index f89a2fe..9603957 100644
|
|
|
|
|
| #
|
| -@@ -160,11 +158,6 @@ $ExtendNumLetEx $KatakanaEx {400}; # (13b)
|
| -
|
| - $Regional_IndicatorEx $Regional_IndicatorEx;
|
| +@@ -194,11 +192,6 @@ $ExtendNumLetEx $KatakanaEx {400}; # (13b)
|
| + #
|
| + ^$Regional_IndicatorEx $Regional_IndicatorEx;
|
|
|
| -# special handling for CJK characters: chain for later dictionary segmentation
|
| -$HangulSyllable $HangulSyllable {200};
|
| @@ -74,14 +75,14 @@ index f89a2fe..9603957 100644
|
| ## -------------------------------------------------
|
|
|
| !!reverse;
|
| -@@ -231,10 +224,6 @@ $BackExtendNumLetEx ($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $B
|
| -
|
| - $BackRegional_IndicatorEx $BackRegional_IndicatorEx;
|
| +@@ -265,10 +258,6 @@ $BackKatakanaEx $BackKatakanaEx;
|
| + $BackExtendNumLetEx ($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx | $BackExtendNumLetEx);
|
| + ($BackALetterEx | $BackHebrew_LetterEx | $BackNumericEx | $BackKatakanaEx) $BackExtendNumLetEx;
|
|
|
| -# special handling for CJK characters: chain for later dictionary segmentation
|
| -$HangulSyllable $HangulSyllable;
|
| -$KanaKanji $KanaKanji; #different rule status if both kanji and kana found
|
| -
|
| - ## -------------------------------------------------
|
| + # rule 14
|
|
|
| - !!safe_reverse;
|
| + $E_Modifier ($Format | $Extend | $ZWJ)* ($E_Base | $EBG);
|
|
|