Data.XML.Parser.High

High-level XML parsers, built on top of Data.XML.Parser.Mid:

• entity references are expanded
• CDATAs are abstracted away
• comments are ignored
• whitespace between tokens is ignored
• duplicate attributes are ignored

All documentation examples assume the following setup:

:set -XOverloadedStrings
import Data.Attoparsec.ByteString

Documentation

module Data.XML.Parser.High.AttrParser

module Data.XML.Parser.High.NameParser

data Prolog

XML document prolog.

Constructors

Prolog

Fields

• prologXmlDeclaration :: Maybe XMLDeclaration
• prologInstructions :: [Instruction]
• prologDoctype :: Maybe Doctype

Instances

Eq Prolog

Defined in Data.XML.Parser.High

Methods

(==) :: Prolog -> Prolog -> Bool

(/=) :: Prolog -> Prolog -> Bool

Ord Prolog

Defined in Data.XML.Parser.High

Methods

compare :: Prolog -> Prolog -> Ordering

(<) :: Prolog -> Prolog -> Bool

(<=) :: Prolog -> Prolog -> Bool

(>) :: Prolog -> Prolog -> Bool

(>=) :: Prolog -> Prolog -> Bool

max :: Prolog -> Prolog -> Prolog

min :: Prolog -> Prolog -> Prolog

Read Prolog

Defined in Data.XML.Parser.High

Methods

readsPrec :: Int -> ReadS Prolog

readList :: ReadS [Prolog]

readPrec :: ReadPrec Prolog

readListPrec :: ReadPrec [Prolog]

Show Prolog

Defined in Data.XML.Parser.High

Methods

showsPrec :: Int -> Prolog -> ShowS

show :: Prolog -> String

showList :: [Prolog] -> ShowS

data Token

Constructors

TokenProlog Prolog

TokenInstruction Instruction

TokenTag QName (Map QName Text) [Token]

TokenTextContent Text

Instances

Eq Token

Defined in Data.XML.Parser.High

Methods

(==) :: Token -> Token -> Bool

(/=) :: Token -> Token -> Bool

Ord Token

Defined in Data.XML.Parser.High

Methods

compare :: Token -> Token -> Ordering

(<) :: Token -> Token -> Bool

(<=) :: Token -> Token -> Bool

(>) :: Token -> Token -> Bool

(>=) :: Token -> Token -> Bool

max :: Token -> Token -> Token

min :: Token -> Token -> Token

Read Token

Defined in Data.XML.Parser.High

Methods

readsPrec :: Int -> ReadS Token

readList :: ReadS [Token]

readPrec :: ReadPrec Token

readListPrec :: ReadPrec [Token]

Show Token

Defined in Data.XML.Parser.High

Methods

showsPrec :: Int -> Token -> ShowS

show :: Token -> String

showList :: [Token] -> ShowS

data TokenParser m a

A parser that consumes whole Tokens.

Instances

Monad m => Monad (TokenParser m)

Defined in Data.XML.Parser.High

Methods

(>>=) :: TokenParser m a -> (a -> TokenParser m b) -> TokenParser m b

(>>) :: TokenParser m a -> TokenParser m b -> TokenParser m b

return :: a -> TokenParser m a

fail :: String -> TokenParser m a

Functor m => Functor (TokenParser m)

Defined in Data.XML.Parser.High

Methods

fmap :: (a -> b) -> TokenParser m a -> TokenParser m b

(<$) :: a -> TokenParser m b -> TokenParser m a

(Parsing m, Monad m) => MonadFail (TokenParser m)

Defined in Data.XML.Parser.High

Methods

fail :: String -> TokenParser m a

Applicative m => Applicative (TokenParser m)

Defined in Data.XML.Parser.High

Methods

pure :: a -> TokenParser m a

(<*>) :: TokenParser m (a -> b) -> TokenParser m a -> TokenParser m b

liftA2 :: (a -> b -> c) -> TokenParser m a -> TokenParser m b -> TokenParser m c

(*>) :: TokenParser m a -> TokenParser m b -> TokenParser m b

(<*) :: TokenParser m a -> TokenParser m b -> TokenParser m a

Alternative m => Alternative (TokenParser m)

Defined in Data.XML.Parser.High

Methods

empty :: TokenParser m a

(<|>) :: TokenParser m a -> TokenParser m a -> TokenParser m a

some :: TokenParser m a -> TokenParser m [a]

many :: TokenParser m a -> TokenParser m [a]

data ContentParser m a

How to parse tag content.

Instances

Functor m => Functor (ContentParser m)

Defined in Data.XML.Parser.High

Methods

fmap :: (a -> b) -> ContentParser m a -> ContentParser m b

(<$) :: a -> ContentParser m b -> ContentParser m a

noContent :: Applicative m => ContentParser m ()

Assert that content is empty.

>>> parseOnly (runTokenParser $ tag' anyName anyAttr noContent) "<tag key='value'>body</tag>"
Left ...
>>> parseOnly (runTokenParser $ tag' anyName anyAttr noContent) "<tag key='value'></tag>"
Right ()
>>> parseOnly (runTokenParser $ tag' anyName anyAttr noContent) "<tag key='value'/>"
Right ()

withContent :: TokenParser m a -> ContentParser m a

Assert that content is not empty, and parse it using given token parser.

>>> parseOnly (runTokenParser $ tag' anyName anyAttr (withContent textContent')) "<tag key='value'>body</tag>"
Right "body"
>>> parseOnly (runTokenParser $ tag' anyName anyAttr (withContent textContent')) "<tag key='value'></tag>"
Left ...
>>> parseOnly (runTokenParser $ tag' anyName anyAttr (withContent textContent')) "<tag key='value'/>"
Left ...
>>> parseOnly (runTokenParser $ tag' anyName anyAttr (withContent $ pure ())) "<tag key='value'/>"
Left ...

anyContent :: CharParsing m => Monad m => ContentParser m ()

Accept any content, including empty content.

>>> parseOnly (runTokenParser $ tag' anyName anyAttr anyContent) "<tag key='value'>body</tag>"
Right ()
>>> parseOnly (runTokenParser $ tag' anyName anyAttr anyContent) "<tag key='value'></tag>"
Right ()
>>> parseOnly (runTokenParser $ tag' anyName anyAttr anyContent) "<tag key='value'/>"
Right ()

runTokenParser :: TokenParser m a -> m a

prolog :: CharParsing m => Monad m => TokenParser m Prolog

https://www.w3.org/TR/REC-xml/#NT-prolog

>>> parseOnly (runTokenParser prolog) "<?xml version='1.0'?><!DOCTYPE greeting>"
Right (Prolog {prologXmlDeclaration = Just (XMLDeclaration "1.0" ...), prologInstructions = [], prologDoctype = Just (Doctype "greeting" ...)})
>>> parseOnly (runTokenParser prolog) "<?xml version='1.0'?>  <!-- comments and whitespace are ignored --><!DOCTYPE greeting>"
Right (Prolog {prologXmlDeclaration = Just (XMLDeclaration "1.0" ...), prologInstructions = [], prologDoctype = Just (Doctype "greeting" ...)})

instruction :: CharParsing m => Monad m => TokenParser m Instruction

Parse a processing instruction.

https://www.w3.org/TR/REC-xml/#dt-pi

>>> parseOnly (runTokenParser instruction) "<?php echo 'Hello World!'; ?>"
Right (Instruction "php" "echo 'Hello World!'; ")
>>> parseOnly (runTokenParser instruction) "<!-- comments and whitespace are ignored -->  <?php echo 'Hello World!'; ?>"
Right (Instruction "php" "echo 'Hello World!'; ")

textContent :: CharParsing m => Monad m => EntityDecoder -> TokenParser m Text

Parse textual content of a tag, including CDATA.

textContent' :: CharParsing m => Monad m => TokenParser m Text

Same as textContent (decodePredefinedEntities <> decodeHtmlEntities), provided for convenience.

>>> parseOnly (runTokenParser $ tag' anyName anyAttr (withContent textContent')) "<tag>body<!-- Ignored comment --><![CDATA[<innertag>innerbody</innertag>]]></tag>"
Right "body<innertag>innerbody</innertag>"

tag

Arguments

:: CharParsing m

=> Monad m

=> EntityDecoder

How to expand entity references

-> NameParser a

How to parse tag name

-> (a -> AttrParser b)

How to parse tag attributes

-> (b -> ContentParser m c)

How to parse tag content

-> TokenParser m c

Generic tag parser.

tag'

Arguments

:: CharParsing m

=> Monad m

=> NameParser a

How to parse tag name

-> AttrParser b

How to parse tag attributes

-> ContentParser m c

How to parse tag content

-> TokenParser m c

Simplified version of tag:

• no state forwarding between name, attributes and content parsers
• uses decodePredefinedEntities <> decodeHtmlEntities to expand entity references

anyTag :: CharParsing m => Monad m => TokenParser m ()

Parse a tag with any name, any attributes and any content.

>>> parseOnly (runTokenParser anyTag) "<tag key='value'>body</tag>"
Right ()
>>> parseOnly (runTokenParser anyTag) "<tag key='value'/>"
Right ()
>>> parseOnly (runTokenParser anyTag) "<!-- ignored comment --><tag key='value'/>"
Right ()
>>> parseOnly (runTokenParser anyTag) "<tag key='value'>body<!-- ignored comment --></tag>"
Right ()

anyToken :: CharParsing m => Monad m => EntityDecoder -> TokenParser m Token

Parse any Token.

anyToken' :: CharParsing m => Monad m => TokenParser m Token

Same as anyToken (decodePredefinedEntities <> decodeHtmlEntities), provided for convenience.