Safe Haskell	None
Language	Haskell2010

Data.Warc.Header

Contents

Parsing
Encoding
WARC Version
Types
Header field types
- Standard fields
Lenses

Synopsis

header :: Parser RecordHeader
encodeHeader :: RecordHeader -> Builder
data Version = Version {
- versionMajor, versionMinor :: !Int
}
warc0_16 :: Version
data RecordHeader = RecordHeader {
- _recWarcVersion :: Version
- _recHeaders :: HashMap FieldName ByteString
}
data WarcType
- = WarcInfo
- | Response
- | Resource
- | Request
- | Metadata
- | Revisit
- | Conversion
- | Continuation
- | FutureType !Text
newtype RecordId = RecordId Uri
data TruncationReason
- = TruncLength
- | TruncTime
- | TruncDisconnect
- | TruncUnspecified
- | TruncOther !Text
data Digest = Digest {
- digestAlgorithm, digestHash :: !ByteString
}
newtype Uri = Uri ByteString
data Field a = Field {
- fieldName :: FieldName
- encode :: a -> Builder
- decode :: Parser a
}
newtype FieldName = FieldName {
- getFieldName :: Text
}
field :: Field a -> Traversal' RecordHeader a
lookupField :: RecordHeader -> Field a -> Maybe (Either String a)
addField :: Field a -> a -> RecordHeader -> RecordHeader
mapField :: (a -> b) -> (b -> a) -> Field a -> Field b
rawField :: FieldName -> Field ByteString
warcRecordId :: Field RecordId
contentLength :: Field Integer
warcDate :: Field UTCTime
warcType :: Field WarcType
contentType :: Field ByteString
warcConcurrentTo :: Field RecordId
warcBlockDigest :: Field Digest
warcPayloadDigest :: Field Digest
warcIpAddress :: Field ByteString
warcRefersTo :: Field Uri
warcTargetUri :: Field Uri
warcTruncated :: Field TruncationReason
warcWarcinfoID :: Field RecordId
warcFilename :: Field Text
warcProfile :: Field Uri
warcSegmentNumber :: Field Integer
warcSegmentTotalLength :: Field Integer
recWarcVersion :: Lens' RecordHeader Version
recHeaders :: Lens' RecordHeader (HashMap FieldName ByteString)

Parsing

header :: Parser RecordHeader Source #

A WARC header

Encoding

encodeHeader :: RecordHeader -> Builder Source #

WARC Version

data Version Source #

Constructors

Version
Fields versionMajor, versionMinor :: !Int

Instances

Eq Version Source #
Instance details Defined in Data.Warc.Header Methods (==) :: Version -> Version -> Bool # (/=) :: Version -> Version -> Bool #
Ord Version Source #
Instance details Defined in Data.Warc.Header Methods compare :: Version -> Version -> Ordering # (<) :: Version -> Version -> Bool # (<=) :: Version -> Version -> Bool # (>) :: Version -> Version -> Bool # (>=) :: Version -> Version -> Bool # max :: Version -> Version -> Version # min :: Version -> Version -> Version #
Read Version Source #
Instance details Defined in Data.Warc.Header Methods readsPrec :: Int -> ReadS Version # readList :: ReadS [Version] # readPrec :: ReadPrec Version # readListPrec :: ReadPrec [Version] #
Show Version Source #
Instance details Defined in Data.Warc.Header Methods showsPrec :: Int -> Version -> ShowS # show :: Version -> String # showList :: [Version] -> ShowS #

warc0_16 :: Version Source #

Types

data RecordHeader Source #

Constructors

RecordHeader
Fields _recWarcVersion :: Version _recHeaders :: HashMap FieldName ByteString

Instances

Show RecordHeader Source #
Instance details Defined in Data.Warc.Header Methods showsPrec :: Int -> RecordHeader -> ShowS # show :: RecordHeader -> String # showList :: [RecordHeader] -> ShowS #

data WarcType Source #

Constructors

WarcInfo
Response
Resource
Request
Metadata
Revisit
Conversion
Continuation
FutureType !Text

Instances

Eq WarcType Source #
Instance details Defined in Data.Warc.Header Methods (==) :: WarcType -> WarcType -> Bool # (/=) :: WarcType -> WarcType -> Bool #
Ord WarcType Source #
Instance details Defined in Data.Warc.Header Methods compare :: WarcType -> WarcType -> Ordering # (<) :: WarcType -> WarcType -> Bool # (<=) :: WarcType -> WarcType -> Bool # (>) :: WarcType -> WarcType -> Bool # (>=) :: WarcType -> WarcType -> Bool # max :: WarcType -> WarcType -> WarcType # min :: WarcType -> WarcType -> WarcType #
Read WarcType Source #
Instance details Defined in Data.Warc.Header Methods readsPrec :: Int -> ReadS WarcType # readList :: ReadS [WarcType] # readPrec :: ReadPrec WarcType # readListPrec :: ReadPrec [WarcType] #
Show WarcType Source #
Instance details Defined in Data.Warc.Header Methods showsPrec :: Int -> WarcType -> ShowS # show :: WarcType -> String # showList :: [WarcType] -> ShowS #

newtype RecordId Source #

Constructors

RecordId Uri

Instances

Eq RecordId Source #
Instance details Defined in Data.Warc.Header Methods (==) :: RecordId -> RecordId -> Bool # (/=) :: RecordId -> RecordId -> Bool #
Ord RecordId Source #
Instance details Defined in Data.Warc.Header Methods compare :: RecordId -> RecordId -> Ordering # (<) :: RecordId -> RecordId -> Bool # (<=) :: RecordId -> RecordId -> Bool # (>) :: RecordId -> RecordId -> Bool # (>=) :: RecordId -> RecordId -> Bool # max :: RecordId -> RecordId -> RecordId # min :: RecordId -> RecordId -> RecordId #
Read RecordId Source #
Instance details Defined in Data.Warc.Header Methods readsPrec :: Int -> ReadS RecordId # readList :: ReadS [RecordId] # readPrec :: ReadPrec RecordId # readListPrec :: ReadPrec [RecordId] #
Show RecordId Source #
Instance details Defined in Data.Warc.Header Methods showsPrec :: Int -> RecordId -> ShowS # show :: RecordId -> String # showList :: [RecordId] -> ShowS #

data TruncationReason Source #

Constructors

TruncLength
TruncTime
TruncDisconnect
TruncUnspecified
TruncOther !Text

Instances

Eq TruncationReason Source #
Instance details Defined in Data.Warc.Header Methods (==) :: TruncationReason -> TruncationReason -> Bool # (/=) :: TruncationReason -> TruncationReason -> Bool #
Ord TruncationReason Source #
Instance details Defined in Data.Warc.Header Methods compare :: TruncationReason -> TruncationReason -> Ordering # (<) :: TruncationReason -> TruncationReason -> Bool # (<=) :: TruncationReason -> TruncationReason -> Bool # (>) :: TruncationReason -> TruncationReason -> Bool # (>=) :: TruncationReason -> TruncationReason -> Bool # max :: TruncationReason -> TruncationReason -> TruncationReason # min :: TruncationReason -> TruncationReason -> TruncationReason #
Read TruncationReason Source #
Instance details Defined in Data.Warc.Header Methods readsPrec :: Int -> ReadS TruncationReason # readList :: ReadS [TruncationReason] # readPrec :: ReadPrec TruncationReason # readListPrec :: ReadPrec [TruncationReason] #
Show TruncationReason Source #
Instance details Defined in Data.Warc.Header Methods showsPrec :: Int -> TruncationReason -> ShowS # show :: TruncationReason -> String # showList :: [TruncationReason] -> ShowS #

data Digest Source #

Constructors

Digest
Fields digestAlgorithm, digestHash :: !ByteString

Instances

Eq Digest Source #
Instance details Defined in Data.Warc.Header Methods (==) :: Digest -> Digest -> Bool # (/=) :: Digest -> Digest -> Bool #
Ord Digest Source #
Instance details Defined in Data.Warc.Header Methods compare :: Digest -> Digest -> Ordering # (<) :: Digest -> Digest -> Bool # (<=) :: Digest -> Digest -> Bool # (>) :: Digest -> Digest -> Bool # (>=) :: Digest -> Digest -> Bool # max :: Digest -> Digest -> Digest # min :: Digest -> Digest -> Digest #
Read Digest Source #
Instance details Defined in Data.Warc.Header Methods readsPrec :: Int -> ReadS Digest # readList :: ReadS [Digest] # readPrec :: ReadPrec Digest # readListPrec :: ReadPrec [Digest] #
Show Digest Source #
Instance details Defined in Data.Warc.Header Methods showsPrec :: Int -> Digest -> ShowS # show :: Digest -> String # showList :: [Digest] -> ShowS #

newtype Uri Source #

Constructors

Uri ByteString

Instances

Eq Uri Source #
Instance details Defined in Data.Warc.Header Methods (==) :: Uri -> Uri -> Bool # (/=) :: Uri -> Uri -> Bool #
Ord Uri Source #
Instance details Defined in Data.Warc.Header Methods compare :: Uri -> Uri -> Ordering # (<) :: Uri -> Uri -> Bool # (<=) :: Uri -> Uri -> Bool # (>) :: Uri -> Uri -> Bool # (>=) :: Uri -> Uri -> Bool # max :: Uri -> Uri -> Uri # min :: Uri -> Uri -> Uri #
Read Uri Source #
Instance details Defined in Data.Warc.Header Methods readsPrec :: Int -> ReadS Uri # readList :: ReadS [Uri] # readPrec :: ReadPrec Uri # readListPrec :: ReadPrec [Uri] #
Show Uri Source #
Instance details Defined in Data.Warc.Header Methods showsPrec :: Int -> Uri -> ShowS # show :: Uri -> String # showList :: [Uri] -> ShowS #

Header field types

data Field a Source #

Constructors

Field
Fields fieldName :: FieldName encode :: a -> Builder decode :: Parser a

newtype FieldName Source #

Constructors

FieldName
Fields getFieldName :: Text

Instances

Eq FieldName Source #
Instance details Defined in Data.Warc.Header Methods (==) :: FieldName -> FieldName -> Bool # (/=) :: FieldName -> FieldName -> Bool #
Ord FieldName Source #
Instance details Defined in Data.Warc.Header Methods compare :: FieldName -> FieldName -> Ordering # (<) :: FieldName -> FieldName -> Bool # (<=) :: FieldName -> FieldName -> Bool # (>) :: FieldName -> FieldName -> Bool # (>=) :: FieldName -> FieldName -> Bool # max :: FieldName -> FieldName -> FieldName # min :: FieldName -> FieldName -> FieldName #
Read FieldName Source #
Instance details Defined in Data.Warc.Header Methods readsPrec :: Int -> ReadS FieldName # readList :: ReadS [FieldName] # readPrec :: ReadPrec FieldName # readListPrec :: ReadPrec [FieldName] #
Show FieldName Source #
Instance details Defined in Data.Warc.Header Methods showsPrec :: Int -> FieldName -> ShowS # show :: FieldName -> String # showList :: [FieldName] -> ShowS #
IsString FieldName Source #
Instance details Defined in Data.Warc.Header Methods fromString :: String -> FieldName #
Hashable FieldName Source #
Instance details Defined in Data.Warc.Header Methods hashWithSalt :: Int -> FieldName -> Int # hash :: FieldName -> Int #

field :: Field a -> Traversal' RecordHeader a Source #

A lens-y means of querying Fields.

lookupField :: RecordHeader -> Field a -> Maybe (Either String a) Source #

Lookup the value of a field. Returns Nothing if the field is not present, Just (Left err) in the event of a parse error, and Just (Right v) on success.

addField :: Field a -> a -> RecordHeader -> RecordHeader Source #

mapField :: (a -> b) -> (b -> a) -> Field a -> Field b Source #

rawField :: FieldName -> Field ByteString Source #