| Copyright | Copyright (C) 2010 Uwe Schmidt |
|---|---|
| License | MIT |
| Maintainer | Uwe Schmidt (uwe@fh-wedel.de) |
| Stability | stable |
| Portability | portable |
| Safe Haskell | None |
| Language | Haskell2010 |
Text.XML.HXT.Arrow.XmlState.SystemConfig
Description
system configuration and common options options
Synopsis
- withTrace :: Int -> SysConfig
- withSysAttr :: String -> String -> SysConfig
- withAcceptedMimeTypes :: [String] -> SysConfig
- withMimeTypeHandler :: String -> IOSArrow XmlTree XmlTree -> SysConfig
- withMimeTypeFile :: String -> SysConfig
- withFileMimeType :: String -> SysConfig
- withWarnings :: Bool -> SysConfig
- withErrors :: Bool -> SysConfig
- withRemoveWS :: Bool -> SysConfig
- withPreserveComment :: Bool -> SysConfig
- withParseByMimeType :: Bool -> SysConfig
- withParseHTML :: Bool -> SysConfig
- withValidate :: Bool -> SysConfig
- withSubstDTDEntities :: Bool -> SysConfig
- withSubstHTMLEntities :: Bool -> SysConfig
- withCheckNamespaces :: Bool -> SysConfig
- withCanonicalize :: Bool -> SysConfig
- withIgnoreNoneXmlContents :: Bool -> SysConfig
- withStrictInput :: Bool -> SysConfig
- withEncodingErrors :: Bool -> SysConfig
- withInputEncoding :: String -> SysConfig
- withDefaultBaseURI :: String -> SysConfig
- withInputOption :: String -> String -> SysConfig
- withInputOptions :: Attributes -> SysConfig
- withRedirect :: Bool -> SysConfig
- withProxy :: String -> SysConfig
- withIndent :: Bool -> SysConfig
- withOutputEncoding :: String -> SysConfig
- withOutputXML :: SysConfig
- withOutputHTML :: SysConfig
- withOutputXHTML :: SysConfig
- withOutputPLAIN :: SysConfig
- withXmlPi :: Bool -> SysConfig
- withNoEmptyElemFor :: [String] -> SysConfig
- withAddDefaultDTD :: Bool -> SysConfig
- withTextMode :: Bool -> SysConfig
- withShowTree :: Bool -> SysConfig
- withShowHaskell :: Bool -> SysConfig
- withCompression :: (CompressionFct, DeCompressionFct) -> SysConfig
- withStrictDeserialize :: Bool -> SysConfig
- yes :: Bool
- no :: Bool
Documentation
withSysAttr :: String -> String -> SysConfig #
withSysAttr key value : store an arbitrary key value pair in system state
withAcceptedMimeTypes :: [String] -> SysConfig #
Specify the set of accepted mime types.
All contents of documents for which the mime type is not found in this list are discarded.
withMimeTypeHandler :: String -> IOSArrow XmlTree XmlTree -> SysConfig #
Specify a content handler for documents of a given mime type
withMimeTypeFile :: String -> SysConfig #
withMimeTypeFile filename : input option,
set the mime type table for file: documents by given file.
The format of this config file must be in the syntax of a debian linux "mime.types" config file
withFileMimeType :: String -> SysConfig #
Force a given mime type for all file contents.
The mime type for file access will then not be computed by looking into a mime.types file
withWarnings :: Bool -> SysConfig #
withWarnings yes/no : system option, issue warnings during reading, HTML parsing and processing,
default is yes
withErrors :: Bool -> SysConfig #
withErrors yes/no : system option for suppressing error messages, default is no
withRemoveWS :: Bool -> SysConfig #
withRemoveWS yes/no : read and write option, remove all whitespace, used for document indentation, default is no
withPreserveComment :: Bool -> SysConfig #
withPreserveComment yes/no : read option, preserve comments during canonicalization, default is no
withParseByMimeType :: Bool -> SysConfig #
withParseByMimeType yes/no : read option, select the parser by the mime type of the document
(pulled out of the HTTP header).
When the mime type is set to "text/html" the configured HTML parser is taken, when it's set to "text/xml" or "text/xhtml" the configured XML parser is taken. If the mime type is something else, no further processing is performed, the contents is given back to the application in form of a single text node. If the default document encoding is set to isoLatin1, this even enables processing of arbitray binary data.
withParseHTML :: Bool -> SysConfig #
withParseHTML yes/no: read option, use HTML parser, default is no (use XML parser)
withValidate :: Bool -> SysConfig #
withValidate yes/no: read option, validate document against DTD, default is yes
withSubstDTDEntities :: Bool -> SysConfig #
withSubstDTDEntities yes/no: read option, substitute general entities defined in DTD, default is yes.
switching this option and the validate option off can lead to faster parsing, because then
there is no need to access the DTD
withSubstHTMLEntities :: Bool -> SysConfig #
withSubstHTMLEntities yes/no: read option, substitute general entities defined in HTML DTD, default is no.
switching this option on and the substDTDEntities and validate options off can lead to faster parsing
because there is no need to access a DTD, but still the HTML general entities are substituted
withCheckNamespaces :: Bool -> SysConfig #
withCheckNamespaces yes/no: read option, check namespaces, default is no
withCanonicalize :: Bool -> SysConfig #
withCanonicalize yes/no : read option, canonicalize document, default is yes
withIgnoreNoneXmlContents :: Bool -> SysConfig #
withIgnoreNoneXmlContents yes/no : input option, ignore document contents of none XML/HTML documents.
This option can be useful for implementing crawler like applications, e.g. an URL checker. In those cases net traffic can be reduced.
withStrictInput :: Bool -> SysConfig #
withStrictInput yes/no : input option, input of file and HTTP contents is read eagerly, default is no
withEncodingErrors :: Bool -> SysConfig #
withEncodingErrors yes/no : input option, ignore all encoding errors, default is no
withInputEncoding :: String -> SysConfig #
withInputEncoding encodingName : input option
Set default document encoding (utf8, isoLatin1, usAscii, iso8859_2, ... , iso8859_16, ...).
Only XML, HTML and text documents are decoded,
default decoding for XML/HTML is utf8, for text iso latin1 (no decoding).
withDefaultBaseURI :: String -> SysConfig #
withDefaultBaseURI URI , input option, set the default base URI
This option can be useful when parsing documents from stdin or contained in a string, and interpreting relative URIs within the document
withInputOption :: String -> String -> SysConfig #
withInputOptions :: Attributes -> SysConfig #
withRedirect :: Bool -> SysConfig #
withRedirect yes/no : input option, automatically follow redirected URIs, default is yes
withProxy :: String -> SysConfig #
withProxy "host:port" : input option, configure a proxy for HTTP access, e.g. www-cache:3128
withIndent :: Bool -> SysConfig #
withIndent yes/no : output option, indent document before output, default is no
withOutputEncoding :: String -> SysConfig #
withOutputEncoding encoding , output option,
default is the default input encoding or utf8, if input encoding is not set
withOutputXML : output option, default writing
Default is writing XML: quote special XML chars >,<,",',& where neccessary,
add XML processing instruction
and encode document with respect to withOutputEncoding
Write XHTML: quote all special XML chars, use HTML entity refs or char refs for none ASCII chars
withOutputPLAIN :: SysConfig #
suppreses all char and entitiy substitution
withNoEmptyElemFor :: [String] -> SysConfig #
withAddDefaultDTD :: Bool -> SysConfig #
withTextMode :: Bool -> SysConfig #
withShowTree :: Bool -> SysConfig #
withShowHaskell :: Bool -> SysConfig #
withCompression :: (CompressionFct, DeCompressionFct) -> SysConfig #
Configure compression and decompression for binary serialization/deserialization. First component is the compression function applied after serialization, second the decompression applied before deserialization.
withStrictDeserialize :: Bool -> SysConfig #
Strict input for deserialization of binary data