tagsoup 0.12 → 0.12.1

raw patch · 3 files changed

+43/−12 lines, 3 files

Files

• Text/HTML/TagSoup/Options.hs +40/−9
• Text/HTML/TagSoup/Parser.hs +1/−1
• tagsoup.cabal +2/−2

@@ -8,9 +8,31 @@ import Text.StringLike  --- | These options control how 'parseTags' works.+-- | These options control how 'parseTags' works. The 'ParseOptions' type is usually generated by one of+--   'parseOptions', 'parseOptionsFast' or 'parseOptionsEntities', then selected fields may be overriden.+--+--   The options 'optTagPosition' and 'optTagWarning' specify whether to generate+--   'TagPosition' or 'TagWarning' elements respectively. Usually these options should be set to @False@+--   to simplify future stages, unless you rely on position information or want to give malformed HTML+--   messages to the end user.+--+--   The options 'optEntityData' and 'optEntityAttrib' control how entities, for example @ @ are handled.+--   Both take a string, and a boolean, where @True@ indicates that the entity ended with a semi-colon @;@.+--   Inside normal text 'optEntityData' will be called, and the results will be inserted in the tag stream.+--   Inside a tag attribute 'optEntityAttrib' will be called, and the first component of the result will be used+--   in the attribute, and the second component will be appended after the 'TagOpen' value (usually the second+--   component is @[]@). As an example, to not decode any entities, pass:+--+-- > parseOptions+-- >     {optEntityData=\(str,b) -> [TagText $ "&" ++ str ++ [';' | b]]+-- >     ,optEntityAttrib\(str,b) -> ("&" ++ str ++ [';' | b], [])++--   The 'optTagTextMerge' value specifies if you always want adjacent 'TagText' values to be merged.+--   Merging adjacent pieces of text has a small performance penalty, but will usually make subsequent analysis+--   simpler. Contiguous runs of characters without entities or tags will also be generated as single 'TagText'+--   values. data ParseOptions str = ParseOptions-    {optTagPosition :: Bool -- ^ Should 'TagPosition' values be given before some items (default=False,fast=False)+    {optTagPosition :: Bool -- ^ Should 'TagPosition' values be given before some items (default=False,fast=False).     ,optTagWarning :: Bool  -- ^ Should 'TagWarning' values be given (default=False,fast=False)     ,optEntityData :: (str,Bool) -> [Tag str] -- ^ How to lookup an entity (Bool = has ending @';'@)     ,optEntityAttrib :: (str,Bool) -> (str,[Tag str]) -- ^ How to lookup an entity in an attribute (Bool = has ending @';'@?)@@ -19,17 +41,26 @@     deriving Typeable  --- | The default parse options value, described in 'ParseOptions'.-parseOptions :: StringLike str => ParseOptions str-parseOptions = ParseOptions False False entityData entityAttrib True+-- | A 'ParseOptions' structure using a custom function to lookup attributes. Any attribute+--   that is not found will be left intact, and a 'TagWarning' given (if 'optTagWarning' is set).+--+--   If you do not want to resolve any entities, simpliy pass @const Nothing@ for the lookup function.+parseOptionsEntities :: StringLike str => (str -> Maybe str) -> ParseOptions str+parseOptionsEntities lookupEntity = ParseOptions False False entityData entityAttrib True     where         entityData x = TagText a : b             where (a,b) = entityAttrib x -        entityAttrib ~(x,b) = case lookupEntity y of-            Just y -> (fromChar y, [])-            Nothing -> (fromString $ "&" ++ y ++ [';'|b], [TagWarning $ fromString $ "Unknown entity: " ++ y])-            where y = toString x+        entityAttrib ~(x,b) = case lookupEntity x of+            Just y -> (y, [])+            Nothing -> (fromChar '&' `append` x `append` fromString [';'|b]+                       ,[TagWarning $ fromString "Unknown entity: " `append` x])+++-- | The default parse options value, described in 'ParseOptions'. Equivalent to+--   @'parseOptionsEntities' 'lookupEntity'@.+parseOptions :: StringLike str => ParseOptions str+parseOptions = parseOptionsEntities $ fmap fromChar . lookupEntity . toString   -- | A 'ParseOptions' structure optimised for speed, following the fast options.

@@ -1,7 +1,7 @@  module Text.HTML.TagSoup.Parser(     parseTags, parseTagsOptions,-    ParseOptions(..), parseOptions, parseOptionsFast+    ParseOptions(..), parseOptions, parseOptionsFast, parseOptionsEntities     ) where  import Text.HTML.TagSoup.Type

@@ -1,7 +1,7 @@ cabal-version:  >= 1.6 name:           tagsoup-version:        0.12-copyright:      Neil Mitchell 2006-2010+version:        0.12.1+copyright:      Neil Mitchell 2006-2011 author:         Neil Mitchell <ndmitchell@gmail.com> maintainer:     Neil Mitchell <ndmitchell@gmail.com> homepage:       http://community.haskell.org/~ndm/tagsoup/