cndict 0.8.0 → 0.8.1

raw patch · 3 files changed

+10/−2 lines, 3 files

Files

cndict.cabal +1/−1
data/dict.sorted too large to diff
src/Data/Chinese/Segmentation.hs +9/−1

cndict.cabal view

@@ -2,7 +2,7 @@ -- documentation, see http://haskell.org/cabal/users-guide/  name:                cndict-version:             0.8.0+version:             0.8.1 synopsis:            Chinese/Mandarin <-> English dictionary, Chinese lexer. -- description: license:             PublicDomain

data/dict.sorted view

file too large to diff

src/Data/Chinese/Segmentation.hs view

@@ -82,7 +82,11 @@       ,["合上", "书"]       ,["第二", "天性"]       ,["都", "会"]-      ,["上", "都"]]+      ,["上", "都"]+      ,["把", "手举"]+      ,["天", "下雨"]+      ,["四十", "分"]+      ,["写","作文"]]  greedyGroups :: [[[Token]]] -> [[[Token]]] greedyGroups = map worker@@ -230,6 +234,10 @@         , ("上帝什么都会", "上帝 什么 都 会")         -- , ("他比我高一个头", "他 比 我 高 一 个 头") -- What's the right way to tokenize here?         , ("每张桌子上都有菜单", "每 张 桌子 上 都 有 菜单")+        , ("把手举起来","把 手举 起来")+        , ("若天下雨","若 天 下雨")+        , ("现在是五点四十分","现在 是 五 点 四十 分")+        , ("她在写作文","她 在 写 作文")         ]