diff --git a/hxt.cabal b/hxt.cabal --- a/hxt.cabal +++ b/hxt.cabal @@ -1,6 +1,6 @@ -- arch-tag: Haskell XML Toolbox main description file Name: hxt -Version: 9.3.1.1 +Version: 9.3.1.2 Synopsis: A collection of tools for processing XML with Haskell. Description: The Haskell XML Toolbox bases on the ideas of HaXml and HXML, but introduces a more general approach for processing XML with Haskell. @@ -15,6 +15,8 @@ hxt-curl, hxt-tagsoup, hxt-relaxng, hxt-xpath, hxt-xslt, hxt-regex-xmlschema contain the extensions. hxt-unicode contains encoding and decoding functions, hxt-charproperties char properties for unicode and XML. + . + Changes from 9.3.1.1: new parser xreadDoc . Changes from 9.3.1.0: in readString all input decoding switched off . diff --git a/src/Text/XML/HXT/Arrow/ParserInterface.hs b/src/Text/XML/HXT/Arrow/ParserInterface.hs --- a/src/Text/XML/HXT/Arrow/ParserInterface.hs +++ b/src/Text/XML/HXT/Arrow/ParserInterface.hs @@ -35,9 +35,12 @@ parseXmlDTDPart :: ArrowXml a => a (String, XmlTree) XmlTree parseXmlDTDPart = arr2L XP.parseXmlDTDPart -parseXmlContent :: ArrowXml a => a String XmlTree -parseXmlContent = arrL XP.xread +xreadCont :: ArrowXml a => a String XmlTree +xreadCont = arrL XP.xread +xreadDoc :: ArrowXml a => a String XmlTree +xreadDoc = arrL XP.xreadDoc + parseXmlEntityEncodingSpec , parseXmlDocEncodingSpec , removeEncodingSpec :: ArrowXml a => a XmlTree XmlTree @@ -67,7 +70,10 @@ parseHtmlDoc :: ArrowList a => a (String, String) XmlTree parseHtmlDoc = arr2L HP.parseHtmlDocument -parseHtmlContent :: ArrowList a => a String XmlTree -parseHtmlContent = arrL HP.parseHtmlContent +hread :: ArrowList a => a String XmlTree +hread = arrL HP.parseHtmlContent + +hreadDoc :: ArrowList a => a String XmlTree +hreadDoc = arrL $ HP.parseHtmlDocument "string" -- ------------------------------------------------------------ diff --git a/src/Text/XML/HXT/Arrow/ReadDocument.hs b/src/Text/XML/HXT/Arrow/ReadDocument.hs --- a/src/Text/XML/HXT/Arrow/ReadDocument.hs +++ b/src/Text/XML/HXT/Arrow/ReadDocument.hs @@ -2,7 +2,7 @@ {- | Module : Text.XML.HXT.Arrow.ReadDocument - Copyright : Copyright (C) 2005 Uwe Schmidt + Copyright : Copyright (C) 2005-2013 Uwe Schmidt License : MIT Maintainer : Uwe Schmidt (uwe@fh-wedel.de) @@ -21,7 +21,9 @@ , readString , readFromString , hread + , hreadDoc , xread + , xreadDoc ) where @@ -39,7 +41,7 @@ , rememberDTDAttrl , removeDocWhiteSpace ) -import Text.XML.HXT.Arrow.ParserInterface +import qualified Text.XML.HXT.Arrow.ParserInterface as PI import Text.XML.HXT.Arrow.ProcessDocument ( getDocumentContents , parseXmlDocument , parseXmlDocumentWithExpat @@ -479,24 +481,38 @@ hread :: ArrowXml a => a String XmlTree hread = fromLA $ - parseHtmlContent -- substHtmlEntityRefs is done in parser + PI.hread -- substHtmlEntityRefs is done in parser >>> -- as well as subst HTML char refs editNTreeA [isError :-> none] -- ignores all errors -{- no longer neccesary, text nodes are merged in parser - >>> - canonicalizeContents --- -} +-- | like hread, but accepts a whole document, not a HTML content +hreadDoc :: ArrowXml a => a String XmlTree +hreadDoc + = fromLA $ + PI.hreadDoc -- substHtmlEntityRefs is done in parser + >>> -- as well as subst HTML char refs + editNTreeA [isError :-> none] -- ignores all errors + -- ------------------------------------------------------------ -- | --- parse a string as XML content, substitute all predefined XML entity refs and canonicalize tree +-- parse a string as XML CONTENT, (no xml decl or doctype decls are allowed), +-- substitute all predefined XML entity refs and canonicalize tree -- This xread arrow delegates all work to the xread parser function in module XmlParsec xread :: ArrowXml a => a String XmlTree -xread - = parseXmlContent +xread = PI.xreadCont + +-- | +-- a more general version of xread which +-- parses a whole document including a prolog +-- (xml decl, doctype decl) and processing +-- instructions. Doctype decls remain uninterpreted, +-- but are in the list of results trees. + +xreadDoc :: ArrowXml a => a String XmlTree +xreadDoc = PI.xreadDoc {- -- the old version, where the parser does not subst char refs and cdata xread = root [] [parseXmlContent] -- substXmlEntityRefs is done in parser diff --git a/src/Text/XML/HXT/Parser/HtmlParsec.hs b/src/Text/XML/HXT/Parser/HtmlParsec.hs --- a/src/Text/XML/HXT/Parser/HtmlParsec.hs +++ b/src/Text/XML/HXT/Parser/HtmlParsec.hs @@ -119,7 +119,7 @@ parseHtmlDocument = parseHtmlFromString htmlDocument parseHtmlContent :: String -> XmlTrees -parseHtmlContent = parseHtmlFromString htmlContent "text" +parseHtmlContent = parseHtmlFromString htmlContent "string" -- ------------------------------------------------------------ diff --git a/src/Text/XML/HXT/Parser/XmlParsec.hs b/src/Text/XML/HXT/Parser/XmlParsec.hs --- a/src/Text/XML/HXT/Parser/XmlParsec.hs +++ b/src/Text/XML/HXT/Parser/XmlParsec.hs @@ -37,6 +37,7 @@ , textDecl , encodingDecl , xread + , xreadDoc , parseXmlContent , parseXmlDocEncodingSpec @@ -618,13 +619,19 @@ -- see also: 'parseXmlContent' xread :: String -> XmlTrees -xread str +xread = xread' content -- take the content parser for parsing the string + +xreadDoc :: String -> XmlTrees +xreadDoc = xread' document' -- take the document' parser for parsing the string + +xread' :: XParser () XmlTrees -> String -> XmlTrees +xread' content' str = parseXmlFromString parser (withNormNewline ()) loc str where loc = "string: " ++ show (if length str > 40 then take 40 str ++ "..." else str) parser = do - res <- content -- take the content parser for parsing the string - eof -- and test on everything consumed + res <- content' + eof -- test on everything consumed return res -- |