Changes in entity handling:

+ Entities are parsed (and unicode characters returned) in both
  Markdown and HTML readers.
+ Parsers characterEntity, namedEntity, decimalEntity, hexEntity added
  to Entities.hs; these parse a string and return a unicode character.
+ Changed 'entity' parser in HTML reader to use the 'characterEntity'
  parser from Entities.hs.  
+ Added new 'entity' parser to Markdown reader, and added '&' as a 
  special character.  Adjusted test suite accordingly since now we 
  get 'Str "AT",Str "&",Str "T"' instead of 'Str "AT&T"..
+ stringToSGML moved to Entities.hs.  escapeSGML removed as redundant,
  given encodeEntities.
+ stringToSGML, encodeEntities, and specialCharToEntity are given a
  boolean parameter that causes only numerical entities to be used.
  This is used in the docbook writer.  The HTML writer uses named
  entities where possible, but not all docbook-consumers know about
  the named entities without special instructions, so it seems safer
  to use numerical entities there.
+ decodeEntities is rewritten in a way that avoids Text.Regex, using
  the new parsers.
+ charToEntity and charToNumericalEntity added to Entities.hs.
+ Moved specialCharToEntity from Shared.hs to Entities.hs.
+ Removed unneeded 'decodeEntities' from 'str' parser in HTML and
  Markdown readers.
+ Removed sgmlHexEntity, sgmlDecimalEntity, sgmlNamedEntity, and
  sgmlCharacterEntity from Shared.hs.
+ Modified Docbook writer so that it doesn't rely on Text.Regex for
  detecting "mailto" links.



git-svn-id: https://pandoc.googlecode.com/svn/trunk@515 788f1e2b-df1e-0410-8736-df70ead52e1b

1 files changed, 9 insertions, 4 deletions

diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs
index 3aa0a6f12..9b3f047e9 100644
--- a/src/Text/Pandoc/Readers/Markdown.hs
+++ b/src/Text/Pandoc/Readers/Markdown.hs
@@ -42,7 +42,7 @@ import Text.Pandoc.Readers.HTML ( rawHtmlBlock,
                                   anyHtmlTag, anyHtmlEndTag,
                                   htmlEndTag, extractTagType,
                                   htmlBlockElement )
-import Text.Pandoc.Entities ( decodeEntities )
+import Text.Pandoc.Entities ( characterEntity )
 import Text.ParserCombinators.Parsec
 
 -- | Read markdown from an input string and return a Pandoc document.
@@ -88,12 +88,13 @@ blockQuoteChar = '>'
 hyphenChar = '-'
 ellipsesChar = '.'
 listColSepChar = '|'
+entityStart = '&'
 
 -- treat these as potentially non-text when parsing inline:
 specialChars = [escapeChar, labelStart, labelEnd, emphStart, emphEnd,
                 emphStartAlt, emphEndAlt, codeStart, codeEnd, autoLinkEnd,
                 autoLinkStart, mathStart, mathEnd, imageStart, noteStart,
-                hyphenChar, ellipsesChar] ++ quoteChars
+                hyphenChar, ellipsesChar, entityStart] ++ quoteChars
 
 --
 -- auxiliary functions
@@ -674,7 +675,7 @@ text = choice [ escapedChar, math, strong, emph, smartPunctuation,
                 code, ltSign, symbol,
                 str, linebreak, tabchar, whitespace, endline ] <?> "text"
 
-inline = choice [ rawLaTeXInline', escapedChar, special, text ] <?> "inline"
+inline = choice [ rawLaTeXInline', escapedChar, entity, special, text ] <?> "inline"
 
 special = choice [ noteRef, inlineNote, link, referenceLink, rawHtmlInline', 
                    autoLink, image ] <?> "link, inline html, note, or image"
@@ -827,9 +828,13 @@ linebreak = try (do
 
 nonEndline = noneOf endLineChars
 
+entity = do
+  ent <- characterEntity
+  return $ Str [ent]
+
 str = do 
   result <- many1 ((noneOf (specialChars ++ spaceChars ++ endLineChars))) 
-  return (Str (decodeEntities result))
+  return (Str result)
 
 -- an endline character that can be treated as a space, not a structural break
 endline = try (do