module Data.Csv.Types
    (
    -- * Core CSV types
      Csv
    , Record
    , Header
    , Name
    , NamedRecord
    , Field
    , toNamedRecord

    -- * Header handling
    , HasHeader(..)
    ) where

import qualified Data.ByteString as S
import qualified Data.HashMap.Strict as HM
import Data.Vector (Vector)
import qualified Data.Vector as V

-- | CSV data represented as a Haskell vector of vector of
-- bytestrings.
type Csv = Vector Record

-- | A record corresponds to a single line in a CSV file.
type Record = Vector Field

-- | The header corresponds to the first line a CSV file. Not all CSV
-- files have a header.
type Header = Vector Name

-- | A header has one or more names, describing the data in the column
-- following the name.
type Name = S.ByteString

-- | A record corresponds to a single line in a CSV file, indexed by
-- the column name rather than the column index.
type NamedRecord = HM.HashMap S.ByteString S.ByteString

-- | A single field within a record.
type Field = S.ByteString

-- | Convert a 'Record' to a 'NamedRecord' by attaching column names.
-- The 'Header' and 'Record' must be of the same length.
toNamedRecord :: Header -> Record -> NamedRecord
toNamedRecord :: Header -> Header -> NamedRecord
toNamedRecord Header
hdr Header
v = [(Name, Name)] -> NamedRecord
forall k v. (Eq k, Hashable k) => [(k, v)] -> HashMap k v
HM.fromList ([(Name, Name)] -> NamedRecord)
-> (Vector (Name, Name) -> [(Name, Name)])
-> Vector (Name, Name)
-> NamedRecord
forall b c a. (b -> c) -> (a -> b) -> a -> c
. Vector (Name, Name) -> [(Name, Name)]
forall a. Vector a -> [a]
V.toList (Vector (Name, Name) -> NamedRecord)
-> Vector (Name, Name) -> NamedRecord
forall a b. (a -> b) -> a -> b
$ Header -> Header -> Vector (Name, Name)
forall a b. Vector a -> Vector b -> Vector (a, b)
V.zip Header
hdr Header
v

-- | Is the CSV data preceded by a header?
data HasHeader = HasHeader  -- ^ The CSV data is preceded by a header
               | NoHeader   -- ^ The CSV data is not preceded by a header