diff --git a/HaXml.cabal b/HaXml.cabal --- a/HaXml.cabal +++ b/HaXml.cabal @@ -1,5 +1,5 @@ name: HaXml -version: 1.19.3 +version: 1.19.4 license: LGPL license-file: COPYRIGHT author: Malcolm Wallace @@ -41,6 +41,7 @@ Text.XML.HaXml.ShowXmlLazy, Text.XML.HaXml.Types, Text.XML.HaXml.TypeMapping, + Text.XML.HaXml.Util, Text.XML.HaXml.Validate, Text.XML.HaXml.Verbatim, Text.XML.HaXml.Wrappers, @@ -59,7 +60,7 @@ else build-depends: base < 2 || >= 3, bytestring extensions: CPP, ExistentialQuantification - cpp-options: -DVERSION=1.19.3 + cpp-options: -DVERSION=1.19.4 nhc98-options: -K10M Executable Canonicalise diff --git a/Makefile b/Makefile --- a/Makefile +++ b/Makefile @@ -1,5 +1,5 @@ SOFTWARE = HaXml -VERSION = 1.19.3 +VERSION = 1.19.4 #CPP = cpp -traditional CPP = cpphs --text --noline # useful e.g. on MacOS X @@ -20,6 +20,7 @@ src/Text/XML/HaXml/TypeMapping.hs src/Text/XML/HaXml/XmlContent.hs \ src/Text/XML/HaXml/SAX.hs \ src/Text/XML/HaXml/ShowXmlLazy.hs \ + src/Text/XML/HaXml/Util.hs \ src/Text/XML/HaXml/Html/Generate.hs src/Text/XML/HaXml/Html/Parse.hs \ src/Text/XML/HaXml/Html/Pretty.hs \ src/Text/XML/HaXml/Html/ParseLazy.hs \ diff --git a/configure b/configure --- a/configure +++ b/configure @@ -2,7 +2,7 @@ # configure -- prepare to compile/install the HaXml package # author: Malcolm.Wallace@cs.york.ac.uk, August 2002 -VERSION="1.19.3" +VERSION="1.19.4" if [ -f obj/prefix ] then INSTALLDIR=`cat obj/prefix` diff --git a/docs/HaXml/Text-XML-HaXml-Util.html b/docs/HaXml/Text-XML-HaXml-Util.html new file mode 100644 --- /dev/null +++ b/docs/HaXml/Text-XML-HaXml-Util.html @@ -0,0 +1,261 @@ + + +Text.XML.HaXml.Util
HaXmlSource codeContentsIndex
Text.XML.HaXml.Util
Contents
utility functions to access XML content +
Description
  • Only a shmall module containing some helper functions to extract xml content + - I would have added this to Types but I've put it into an additional module + - to avoid circular references (Verbatim - Types) +
Synopsis
docContent :: i -> Document i -> Content i
contentElem :: Content i -> Element i
attrs :: Element i -> [Attribute]
utility functions to access XML content +
docContent :: i -> Document i -> Content iSource
contentElem :: Content i -> Element iSource
attrs :: Element i -> [Attribute]Source
Produced by Haddock version 0.8
diff --git a/docs/HaXml/doc-index-A.html b/docs/HaXml/doc-index-A.html --- a/docs/HaXml/doc-index-A.html +++ b/docs/HaXml/doc-index-A.html @@ -393,6 +393,14 @@ >attrsText.XML.HaXml.UtilattrvalcontentElemText.XML.HaXml.UtilcpdocContentText.XML.HaXml.UtildoctypedecltagTextContentText.XML.HaXml.UtiltagWithText.XML.HaXml.UtilText.XML.HaXml.Validate + +
{- |
+ - Only a shmall module containing some helper functions to extract xml content
+ - I would have added this to Types but I've put it into an additional module
+ - to avoid circular references (Verbatim <-> Types)
+-}
+
+module Text.XML.HaXml.Util
+  (
+  -- ** utility functions to access XML content
+    docContent
+  , contentElem
+  , attrs
+  , tagTextContent
+  ) where
+
+import Text.XML.HaXml.Posn
+import Text.XML.HaXml.Types
+import Text.XML.HaXml.Verbatim
+
+-- get the main element of the document so that you can apply CFilters directly
+-- i is typically (posInNewCxt "filename" Nothing) 
+docContent :: i -> Document i -> Content i
+docContent i (Document _ _ e _) = CElem e i
+
+-- if you know that your CFilter returns a tag your can use this function to get the tag Element 
+contentElem ::  Content i -> Element i
+contentElem (CElem e _) = e
+contentElem _ = error "content is not a CElem"
+attrs :: Element i -> [Attribute]
+attrs ( Elem _ attrs _ ) = attrs
+tagTextContent ((CElem (Elem _ _ cs) _)) = concatMap verbatim cs 
+
+{-
+  now you can extract an attribute quite easily:
+    let doc = "<xml><a><b a=\"x\">content</b></a></xml>"
+    let b = head $ xtract id "a/b" $ docContent (posInNewCxt filename Nothing) $ xmlParse filename doc
+    putStrLn $ "attr a of tag b" ++ (show $ lookup "a" $  attrs $ contentElem b)
+    putStrLn $ "text content of b :" ++ tagTextContent b
+  still (too) much code IMHO
+-}
+
+
+ diff --git a/docs/changelog.html b/docs/changelog.html --- a/docs/changelog.html +++ b/docs/changelog.html @@ -20,7 +20,7 @@ in the XtractLazy tool.
  • Version 1.19.2 updates the Cabal file to enable HaXml to build with both ghc-6.6.x and ghc-6.8.x. -
  • Version 1.19.3 fixes an incompatibility with some versions of the +
  • Version 1.19.4 fixes an incompatibility with some versions of the Bytestring package. Also has a bugfix in the DTD validator, and adds some new utility functions in Text.XML.HaXml.Util. diff --git a/docs/index.html b/docs/index.html --- a/docs/index.html +++ b/docs/index.html @@ -132,11 +132,11 @@

    Downloads

    Development versions:
    -HaXml-1.19.3, release date 2008.06.17
    +HaXml-1.19.4, release date 2008.06.17
    From Hackage
    By HTTP: -.tar.gz, -.zip. +.tar.gz, +.zip.
    By FTP: @@ -203,7 +203,7 @@

    Recent news

    -Version 1.19.3 has some minor bugfixes to increase compatibility with the +Version 1.19.4 has some minor bugfixes to increase compatibility with the ByteString package.
    Version 1.19.2 updates the Cabal file to enable HaXml to build with both ghc-6.6.x and ghc-6.8.x.
    diff --git a/src/Makefile b/src/Makefile --- a/src/Makefile +++ b/src/Makefile @@ -1,5 +1,5 @@ SOFTWARE = HaXml -VERSION = 1.19.3 +VERSION = 1.19.4 LIBSRCS = \ Text/XML/HaXml.hs Text/XML/HaXml/Combinators.hs Text/XML/HaXml/Lex.hs \ diff --git a/src/Text/XML/HaXml/Util.hs b/src/Text/XML/HaXml/Util.hs new file mode 100644 --- /dev/null +++ b/src/Text/XML/HaXml/Util.hs @@ -0,0 +1,41 @@ +{- | + - Only a shmall module containing some helper functions to extract xml content + - I would have added this to Types but I've put it into an additional module + - to avoid circular references (Verbatim <-> Types) +-} + +module Text.XML.HaXml.Util + ( + -- ** utility functions to access XML content + docContent + , contentElem + , attrs + , tagTextContent + ) where + +import Text.XML.HaXml.Posn +import Text.XML.HaXml.Types +import Text.XML.HaXml.Verbatim + +-- get the main element of the document so that you can apply CFilters directly +-- i is typically (posInNewCxt "filename" Nothing) +docContent :: i -> Document i -> Content i +docContent i (Document _ _ e _) = CElem e i + +-- if you know that your CFilter returns a tag your can use this function to get the tag Element +contentElem :: Content i -> Element i +contentElem (CElem e _) = e +contentElem _ = error "content is not a CElem" +attrs :: Element i -> [Attribute] +attrs ( Elem _ attrs _ ) = attrs +tagTextContent ((CElem (Elem _ _ cs) _)) = concatMap verbatim cs + +{- + now you can extract an attribute quite easily: + let doc = "content" + let b = head $ xtract id "a/b" $ docContent (posInNewCxt filename Nothing) $ xmlParse filename doc + putStrLn $ "attr a of tag b" ++ (show $ lookup "a" $ attrs $ contentElem b) + putStrLn $ "text content of b :" ++ tagTextContent b + still (too) much code IMHO +-} +