hxt-9.1.0: A collection of tools for processing XML with Haskell.

Portabilityportable
Stabilitystable
MaintainerUwe Schmidt (uwe@fh-wedel.de)

Text.XML.HXT.Arrow.XmlState.SystemConfig

Description

system configuration and common options options

Synopsis

Documentation

withTrace :: Int -> SysConfigSource

withTace level : system option, set the trace level, (0..4)

withSysAttr :: String -> String -> SysConfigSource

withSysAttr key value : store an arbitarty key value pair in system state

withMimeTypeFile :: String -> SysConfigSource

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 -> SysConfigSource

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 -> SysConfigSource

withWarnings yes/no : system option, issue warnings during reading, HTML parsing and processing, default is yes

withErrors :: Bool -> SysConfigSource

withErrors yes/no : system option for suppressing error messages, default is no

withRemoveWS :: Bool -> SysConfigSource

withRemoveWS yes/no : read and write option, remove all whitespace, used for document indentation, default is no

withPreserveComment :: Bool -> SysConfigSource

withPreserveComment yes/no : read option, preserve comments during canonicalization, default is no

withParseByMimeType :: Bool -> SysConfigSource

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 -> SysConfigSource

withParseHTML yes/no: read option, use HTML parser, default is no (use XML parser)

withValidate :: Bool -> SysConfigSource

withValidate yes/no: read option, validate document againsd DTD, default is yes

withCheckNamespaces :: Bool -> SysConfigSource

withCheckNamespaces yes/no: read option, check namespaces, default is no

withCanonicalize :: Bool -> SysConfigSource

withCanonicalize yes/no : read option, canonicalize document, default is yes

withIgnoreNoneXmlContents :: Bool -> SysConfigSource

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 -> SysConfigSource

withStrictInput yes/no : input option, input of file and HTTP contents is read eagerly, default is no

withEncodingErrors :: Bool -> SysConfigSource

withEncodingErrors yes/no : input option, ignore all encoding errors, default is no

withInputEncoding :: String -> SysConfigSource

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 -> SysConfigSource

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

withRedirect :: Bool -> SysConfigSource

withRedirect yes/no : input option, automatically follow redirected URIs, default is yes

withProxy :: String -> SysConfigSource

withProxy "host:port" : input option, configure a proxy for HTTP access, e.g. www-cache:3128

withIndent :: Bool -> SysConfigSource

withIndent yes/no : output option, indent document before output, default is no

withOutputEncoding :: String -> SysConfigSource

withOutputEncoding encoding , output option, default is the default input encoding or utf8, if input encoding is not set

withOutputXML :: SysConfigSource

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

withOutputHTML :: SysConfigSource

Write XHTML: quote all special XML chars, use HTML entity refs or char refs for none ASCII chars

withOutputXHTML :: SysConfigSource

Write XML: quote only special XML chars, don't substitute chars by HTML entities, and don't generate empty elements for HTML elements, which may contain any contents, e.g. script src=.../script instead of script src=... /

withOutputPLAIN :: SysConfigSource

suppreses all char and entitiy substitution

withCompression :: (CompressionFct, DeCompressionFct) -> SysConfigSource

Configure compression and decompression for binary serialization/deserialization. First component is the compression function applied after serialization, second the decompression applied before deserialization.