Data.Chinese.CCDict

Simplified Chinese - English dictionary with pinyin phonetics.

Documentation

type CCDict = IntMap CCTrieEntry

data Entry

Dictionary entry

Constructors

Entry

Fields

entrySimplified :: !Text

entryTraditional :: !Text

entryPinyin :: [Text]

entryDefinition :: [[Text]]

Instances

Eq Entry

Ord Entry

Read Entry

Show Entry

load :: FilePath -> IO CCDict

Load dictionary from file.

parse :: Text -> CCDict

Load dictionary from unicode text.

lookup :: Text -> CCDict -> Maybe Entry

O(n). Lookup dictionary entry for a string of simplified chinese.

ccDict :: CCDict

Embedded dictionary.

data Token

Constructors

KnownWord Entry

UnknownWord Text

Instances

Eq Token

Ord Token

Read Token

Show Token

tokenizer :: CCDict -> Text -> [Token]

Break a string of simplified chinese down to a list of tokens.