Data.XML.Parser.Low

Low-level XML parsers:

• parsed tokens are small and may overlap; it is not possible to tokenize XML document in a stateless way
• parsers are reversible: all formatting details are retained (e.g. whitespacing)

All documentation examples assume the following setup:

:set -XOverloadedStrings
import Data.Attoparsec.ByteString

Documentation

module Data.XML.Parser.Low.Entity

module Data.XML.Parser.Low.Name

data Reference

Entity reference, or character reference.

Constructors

EntityRef Text

CharRef Char

Instances

Eq Reference

Defined in Data.XML.Parser.Low

Methods

(==) :: Reference -> Reference -> Bool

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

Ord Reference

Defined in Data.XML.Parser.Low

Methods

compare :: Reference -> Reference -> Ordering

(<) :: Reference -> Reference -> Bool

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

(>) :: Reference -> Reference -> Bool

(>=) :: Reference -> Reference -> Bool

max :: Reference -> Reference -> Reference

min :: Reference -> Reference -> Reference

Read Reference

Defined in Data.XML.Parser.Low

Methods

readsPrec :: Int -> ReadS Reference

readList :: ReadS [Reference]

readPrec :: ReadPrec Reference

readListPrec :: ReadPrec [Reference]

Show Reference

Defined in Data.XML.Parser.Low

Methods

showsPrec :: Int -> Reference -> ShowS

show :: Reference -> String

showList :: [Reference] -> ShowS

data Content

Raw text or reference.

Constructors

ContentText Text

ContentReference Reference

Instances

Eq Content

Defined in Data.XML.Parser.Low

Methods

(==) :: Content -> Content -> Bool

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

Ord Content

Defined in Data.XML.Parser.Low

Methods

compare :: Content -> Content -> Ordering

(<) :: Content -> Content -> Bool

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

(>) :: Content -> Content -> Bool

(>=) :: Content -> Content -> Bool

max :: Content -> Content -> Content

min :: Content -> Content -> Content

Read Content

Defined in Data.XML.Parser.Low

Methods

readsPrec :: Int -> ReadS Content

readList :: ReadS [Content]

readPrec :: ReadPrec Content

readListPrec :: ReadPrec [Content]

Show Content

Defined in Data.XML.Parser.Low

Methods

showsPrec :: Int -> Content -> ShowS

show :: Content -> String

showList :: [Content] -> ShowS

expandContent :: Alternative m => EntityDecoder -> Content -> m Text

Expand content reference, if any.

expandContents :: Alternative m => Monad m => EntityDecoder -> [Content] -> m Text

Same as expandContent, but on a list. Provided for convenience.

expandReference :: Alternative m => EntityDecoder -> Reference -> m Text

Resolve reference into raw text.

expandReference' :: Reference -> Maybe Text

Same as expandReference decodePredefinedEntities, provided for convenience.

tokenSingleQuote :: CharParsing m => m Char

'

tokenDoubleQuote :: CharParsing m => m Char

"

tokenQuote :: CharParsing m => m Char

Single or double quote.

tokenWhitespace :: CharParsing m => m String

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

tokenEqual :: CharParsing m => Monad m => m ()

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

tokenReference :: CharParsing m => Monad m => m Reference

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

>>> parseOnly tokenReference "<"
Right (CharRef '<')
>>> parseOnly tokenReference "&docdate;"
Right (EntityRef "docdate")

tokenContent :: CharParsing m => Monad m => String -> m Content

tokenEntityDeclarationOpen :: CharParsing m => m ()

<!ENTITY

tokenInstructionOpen :: CharParsing m => Monad m => m Text

Return processing instruction name.

>>> parseOnly tokenInstructionOpen "<?php"
Right "php"

tokenInstructionClose :: CharParsing m => m ()

?>

tokenCdataOpen :: CharParsing m => m ()

<![CDATA[

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

tokenCdataClose :: CharParsing m => m ()

]]>

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

tokenCommentOpen :: CharParsing m => m ()

<!--

tokenCommentClose :: CharParsing m => m ()

-->

tokenDoctypeOpen :: CharParsing m => m ()

<!DOCTYPE

tokenXmlDeclarationOpen :: CharParsing m => m ()

<?xml

tokenXmlDeclarationClose :: CharParsing m => m ()

?>

tokenEmptyElementTagClose :: CharParsing m => m ()

/>

tokenStartTagOpen :: CharParsing m => Monad m => m QName

Return tag name.

>>> parseOnly tokenStartTagOpen "<foo"
Right (QName {namePrefix = "", nameLocal = "foo"})

tokenEndTagOpen :: CharParsing m => Monad m => m QName

Return tag name.

>>> parseOnly tokenEndTagOpen "</foo"
Right (QName {namePrefix = "", nameLocal = "foo"})

tokenElementClose :: CharParsing m => m ()

>