Documentation

data OrthoFreq Source

data PunktData Source

data Entity a Source

data Token Source

type Punkt = Reader PunktData Source

norm :: Text -> Text Source

is_initial :: Token -> Bool Source

is_word :: Token -> Bool Source

strunk_log :: Double -> Double -> Double -> Double -> Double Source

dunning_log :: Double -> Double -> Double -> Double -> Double Source

ask_type_count :: ReaderT PunktData Identity (HashMap Text Int) Source

ask_total_toks :: ReaderT PunktData Identity Double Source

ask_total_enders :: ReaderT PunktData Identity Double Source

ask_ortho :: Text -> Punkt OrthoFreq Source

ask_colloc :: Text -> Text -> Punkt Double Source

freq :: Text -> Punkt Double Source

freq_snoc_dot :: Text -> Punkt Double Source

freq_type :: Text -> Punkt Double Source

dlen :: Text -> Double Source

prob_abbr :: Text -> Punkt Double Source

decide_ortho :: Text -> Punkt (Maybe Bool) Source

decide_initial_ortho :: Text -> Punkt (Maybe Bool) Source

prob_starter :: Text -> Punkt Double Source

prob_colloc :: Text -> Text -> Punkt Double Source

build_type_count :: [Token] -> HashMap Text Int Source

build_ortho_count :: [Token] -> HashMap Text OrthoFreq Source

build_collocs :: [Token] -> HashMap (Text, Text) Int Source

to_tokens :: Text -> [Token] Source

build_punkt_data :: [Token] -> PunktData Source

classify_by_type :: Token -> Punkt Token Source

classify_by_next :: Token -> Token -> Punkt Token Source

classify_punkt :: Text -> [Token] Source

find_breaks :: Text -> [(Int, Int)] Source

substring :: Text -> Int -> Int -> Text Source

match_spaces :: Text -> Maybe (Int, Int) Source

split_sentences :: Text -> [Text] Source

runPunkt :: PunktData -> Punkt a -> a Source