Text.NKJP.Morphosyntax

Parsing the NKJP morphosyntax layer.

Data types

data Para t

A paragraph.

Constructors

Para

Fields

paraID :: t

sentences :: [Sent t]

Instances

Functor Para

Show t => Show (Para t)

data Sent t

A sentence.

Constructors

Sent

Fields

sentID :: t

segments :: [Seg t]

Instances

Functor Sent

Show t => Show (Sent t)

data Seg t

A segment.

Constructors

Seg

Fields

segID :: t

orth :: t

nps :: Bool

lexs :: [Lex t]

choice :: (t, t)

Instances

Functor Seg

Show t => Show (Seg t)

data Lex t

A lexciacal entry, potential interpretation of the segment.

Constructors

Lex

Fields

lexID :: t

base :: t

ctag :: t

msds :: [(t, t)]

Instances

Functor Lex

Show t => Show (Lex t)

Parsing

parseMorph :: Text -> [Para Text]

Parse textual contents of the ann_morphosyntax.xml file.

readMorph :: FilePath -> IO [Para Text]

Parse the stand-alone ann_morphosyntax.xml file.

readCorpus :: FilePath -> IO [(FilePath, Maybe [Para Text])]

Parse all ann_morphosyntax.xml files from the NCP .tar.gz file.