Copyright	© 2018 bruno cuconato
License	LPGL-3
Maintainer	bruno cuconato <bcclaro+hackage@gmail.com>
Stability	experimental
Portability	non-portable
Safe Haskell	Safe-Inferred
Language	Haskell2010

Conllu.Type

Contents

type and data declarations

Description

defines types for handling CoNLL-U data.

Synopsis

type Doc = [Sent]
data Sent = Sent {
- _meta :: [Comment]
- _words :: [CW AW]
}
type Comment = StringPair
type StringPair = (String, String)
data CW a = CW {
- _id :: ID
- _form :: FORM
- _lemma :: LEMMA
- _upos :: UPOS
- _xpos :: XPOS
- _feats :: FEATS
- _rel :: Maybe Rel
- _deps :: DEPS
- _misc :: MISC
}
data AW
data SW
data MT
data EN
data ID
- = SID Index
- | MID Index Index
- | EID Index Index
type FORM = Maybe String
type LEMMA = Maybe String
type UPOS = Maybe POS
type XPOS = Maybe String
type FEATS = [Feat]
type HEAD = ID
type DEPS = [Rel]
type MISC = Maybe String
data Feat = Feat {
- _feat :: String
- _featValues :: [String]
- _featType :: Maybe String
}
data Rel = Rel {
- _head :: HEAD
- _deprel :: EP
- _subdep :: Maybe String
- _rest :: Maybe [String]
}
type Index = Int
type IxSep = Char
_dep :: CW SW -> Maybe EP
depIs :: EP -> CW SW -> Bool
mkDEP :: String -> EP
mkUPOS :: String -> POS
mkAW :: ID -> FORM -> LEMMA -> UPOS -> XPOS -> FEATS -> Maybe Rel -> DEPS -> MISC -> CW AW
mkSW :: CW AW -> CW SW

type and data declarations

Documents and Sentences

type Doc = [Sent] Source #

data Sent Source #

Constructors

Sent
Fields _meta :: [Comment] the sentence's comments. _words :: [CW AW] the sentence's words.

Instances

Instances details

Eq Sent Source #
Instance details Defined in Conllu.Type Methods (==) :: Sent -> Sent -> Bool # (/=) :: Sent -> Sent -> Bool #
Show Sent Source #
Instance details Defined in Conllu.Type Methods showsPrec :: Int -> Sent -> ShowS # show :: Sent -> String # showList :: [Sent] -> ShowS #

type Comment = StringPair Source #

most comments are (key, value) pairs.

type StringPair = (String, String) Source #

represents a word line in a CoNLL-U file. note that we have collapsed some fields together: HEAD and DEPREL have been combined as a relation type Rel accessible by the $sel:_rel:CW function; the DEPS field is merely a list of Rel.

a C(oNLL-U)W(ord) may be a simple word, a multi-word token, or an empty node. this is captured by the phantom type (the a in the declaration), which can be parametrized by one of the data types below in order to build functions that only operate on one of these word types (see mkSWord on how to do this). see the _dep function, which only operates on simple words, which are the ones that have a DEPREL field.

Constructors

CW
Fields _id :: ID ID field _form :: FORM FORM field _lemma :: LEMMA LEMMA field _upos :: UPOS UPOS field _xpos :: XPOS XPOS field _feats :: FEATS FEATS field _rel :: Maybe Rel combined HEAD and DEPREL fields _deps :: DEPS DEPS field _misc :: MISC MISC field

Instances

Instances details

Eq (CW a) Source #
Instance details Defined in Conllu.Type Methods (==) :: CW a -> CW a -> Bool # (/=) :: CW a -> CW a -> Bool #
Ord (CW a) Source #
Instance details Defined in Conllu.Type Methods compare :: CW a -> CW a -> Ordering # (<) :: CW a -> CW a -> Bool # (<=) :: CW a -> CW a -> Bool # (>) :: CW a -> CW a -> Bool # (>=) :: CW a -> CW a -> Bool # max :: CW a -> CW a -> CW a # min :: CW a -> CW a -> CW a #
Show (CW a) Source #
Instance details Defined in Conllu.Type Methods showsPrec :: Int -> CW a -> ShowS # show :: CW a -> String # showList :: [CW a] -> ShowS #

Word types

data AW Source #

phantom type for any kind of word.

data SW Source #

phantom type for a simple word.

data MT Source #

phantom type for multiword tokens. do note that in MWTs only the ID, FORM and MISC fields may be non-empty.

data EN Source #

phantom type for an empty node.

Word Fields

data ID Source #

Constructors

SID Index	word ID is an integer
MID Index Index	multi-word token ID is a range
EID Index Index	empty node ID is a decimal

Instances

Instances details

Eq ID Source #
Instance details Defined in Conllu.Type Methods (==) :: ID -> ID -> Bool # (/=) :: ID -> ID -> Bool #
Ord ID Source #
Instance details Defined in Conllu.Type Methods compare :: ID -> ID -> Ordering # (<) :: ID -> ID -> Bool # (<=) :: ID -> ID -> Bool # (>) :: ID -> ID -> Bool # (>=) :: ID -> ID -> Bool # max :: ID -> ID -> ID # min :: ID -> ID -> ID #
Show ID Source #
Instance details Defined in Conllu.Type Methods showsPrec :: Int -> ID -> ShowS # show :: ID -> String # showList :: [ID] -> ShowS #

type FORM = Maybe String Source #

type LEMMA = Maybe String Source #

type UPOS = Maybe POS Source #

type XPOS = Maybe String Source #

type FEATS = [Feat] Source #

type HEAD = ID Source #

type DEPS = [Rel] Source #

type MISC = Maybe String Source #

data Feat Source #

feature representation

Constructors

Feat
Fields _feat :: String feature name _featValues :: [String] feature values _featType :: Maybe String feature type (inside brackets).

Instances

Instances details

Eq Feat Source #
Instance details Defined in Conllu.Type Methods (==) :: Feat -> Feat -> Bool # (/=) :: Feat -> Feat -> Bool #
Show Feat Source #
Instance details Defined in Conllu.Type Methods showsPrec :: Int -> Feat -> ShowS # show :: Feat -> String # showList :: [Feat] -> ShowS #

data Rel Source #

dependency relation representation.

Constructors

Rel
Fields _head :: HEAD head `ID` _deprel :: EP dependency relation type _subdep :: Maybe String dependency relation subtype _rest :: Maybe [String] provisitonal, see issues 17

Instances

Instances details

Eq Rel Source #
Instance details Defined in Conllu.Type Methods (==) :: Rel -> Rel -> Bool # (/=) :: Rel -> Rel -> Bool #
Show Rel Source #
Instance details Defined in Conllu.Type Methods showsPrec :: Int -> Rel -> ShowS # show :: Rel -> String # showList :: [Rel] -> ShowS #