Safe Haskell	None
Language	Haskell2010

Data.XML.Parser.Low

Description

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

Synopsis

module Data.XML.Parser.Low.Entity
module Data.XML.Parser.Low.Name
data Reference
- = EntityRef Text
- | CharRef Char
data Content
- = ContentText Text
- | ContentReference Reference
expandContent :: Alternative m => EntityDecoder -> Content -> m Text
expandContents :: Alternative m => Monad m => EntityDecoder -> [Content] -> m Text
expandReference :: Alternative m => EntityDecoder -> Reference -> m Text
expandReference' :: Reference -> Maybe Text
tokenSingleQuote :: CharParsing m => m Char
tokenDoubleQuote :: CharParsing m => m Char
tokenQuote :: CharParsing m => m Char
tokenWhitespace :: CharParsing m => m String
tokenEqual :: CharParsing m => Monad m => m ()
tokenReference :: CharParsing m => Monad m => m Reference
tokenContent :: CharParsing m => Monad m => String -> m Content
tokenEntityDeclarationOpen :: CharParsing m => m ()
tokenInstructionOpen :: CharParsing m => Monad m => m Text
tokenInstructionClose :: CharParsing m => m ()
tokenCdataOpen :: CharParsing m => m ()
tokenCdataClose :: CharParsing m => m ()
tokenCommentOpen :: CharParsing m => m ()
tokenCommentClose :: CharParsing m => m ()
tokenDoctypeOpen :: CharParsing m => m ()
tokenXmlDeclarationOpen :: CharParsing m => m ()
tokenXmlDeclarationClose :: CharParsing m => m ()
tokenEmptyElementTagClose :: CharParsing m => m ()
tokenStartTagOpen :: CharParsing m => Monad m => m QName
tokenEndTagOpen :: CharParsing m => Monad m => m QName
tokenElementClose :: CharParsing m => m ()

Documentation

module Data.XML.Parser.Low.Entity

module Data.XML.Parser.Low.Name

data Reference Source #

Entity reference, or character reference.

Constructors

EntityRef Text
CharRef Char

Instances

Eq Reference Source #
Instance details Defined in Data.XML.Parser.Low Methods (==) :: Reference -> Reference -> Bool # (/=) :: Reference -> Reference -> Bool #
Ord Reference Source #
Instance details 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 Source #
Instance details Defined in Data.XML.Parser.Low Methods readsPrec :: Int -> ReadS Reference # readList :: ReadS [Reference] # readPrec :: ReadPrec Reference # readListPrec :: ReadPrec [Reference] #
Show Reference Source #
Instance details Defined in Data.XML.Parser.Low Methods showsPrec :: Int -> Reference -> ShowS # show :: Reference -> String # showList :: [Reference] -> ShowS #

data Content Source #

Raw text or reference.

Constructors

ContentText Text
ContentReference Reference

Instances

Eq Content Source #
Instance details Defined in Data.XML.Parser.Low Methods (==) :: Content -> Content -> Bool # (/=) :: Content -> Content -> Bool #
Ord Content Source #
Instance details 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 Source #
Instance details Defined in Data.XML.Parser.Low Methods readsPrec :: Int -> ReadS Content # readList :: ReadS [Content] # readPrec :: ReadPrec Content # readListPrec :: ReadPrec [Content] #
Show Content Source #
Instance details Defined in Data.XML.Parser.Low Methods showsPrec :: Int -> Content -> ShowS # show :: Content -> String # showList :: [Content] -> ShowS #

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

Expand content reference, if any.

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

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

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

Resolve reference into raw text.

expandReference' :: Reference -> Maybe Text Source #

Same as expandReference decodePredefinedEntities, provided for convenience.

tokenSingleQuote :: CharParsing m => m Char Source #

tokenDoubleQuote :: CharParsing m => m Char Source #

tokenQuote :: CharParsing m => m Char Source #

Single or double quote.

tokenWhitespace :: CharParsing m => m String Source #

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

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

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

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

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

>>> parseOnly tokenReference "&#x3C;"
Right (CharRef '<')
>>> parseOnly tokenReference "&docdate;"
Right (EntityRef "docdate")

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

tokenEntityDeclarationOpen :: CharParsing m => m () Source #

<!ENTITY

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

Return processing instruction name.

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

tokenInstructionClose :: CharParsing m => m () Source #

?>

tokenCdataOpen :: CharParsing m => m () Source #

<![CDATA[

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

tokenCdataClose :: CharParsing m => m () Source #

]]>

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

tokenCommentOpen :: CharParsing m => m () Source #

<!--

tokenCommentClose :: CharParsing m => m () Source #

-->

tokenDoctypeOpen :: CharParsing m => m () Source #

<!DOCTYPE

tokenXmlDeclarationOpen :: CharParsing m => m () Source #

<?xml

tokenXmlDeclarationClose :: CharParsing m => m () Source #

?>

tokenEmptyElementTagClose :: CharParsing m => m () Source #

/>

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

Return tag name.

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

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

Return tag name.

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

tokenElementClose :: CharParsing m => m () Source #