Fixed bug in the markdown reader: HTML preceding a code block

could cause it to be parsed as a paragraph.  (The problem is that
the HTML parser used to eat all blank space after an HTML block,
including the indentation of the code block.)  Resolves Issue #39.
+ In Text.Pandoc.Readers.HTML, removed parsing of following space
  from rawHtmlBlock.
+ In Text.Pandoc.Readers.Markdown, modified rawHtmlBlocks so that
  indentation is eaten *only* on the first line after the HTML
  block.  This means that in
  <div>
       foo
  <div>
  the foo won't be treated as a code block, but in
  <div>

      foo

  </div>
  it will.  This seems the right approach for least suprise.


git-svn-id: https://pandoc.googlecode.com/svn/trunk@1164 788f1e2b-df1e-0410-8736-df70ead52e1b

Text/Pandoc/Readers/HTML.hs

@@ -207,9 +207,8 @@ htmlBlockElement = choice [ htmlScript, htmlStyle, htmlComment, xmlDec, definiti
 
 rawHtmlBlock = try $ do
   body <- htmlBlockElement <|> anyHtmlTag <|> anyHtmlEndTag
-  sp <- many space
   state <- getState
-  if stateParseRaw state then return (RawHtml (body ++ sp)) else return Null
+  if stateParseRaw state then return (RawHtml body) else return Null
 
 -- We don't want to parse </body> or </html> as raw HTML, since these
 -- are handled in parseHtml.

Text/Pandoc/Readers/Markdown.hs

@@ -507,11 +507,18 @@ strictHtmlBlock = try $ do
              return $ tag ++ concat contents ++ end
 
 rawHtmlBlocks = do
-  htmlBlocks <- many1 rawHtmlBlock    
-  let combined = concatMap (\(RawHtml str) -> str) htmlBlocks
-  let combined' = if not (null combined) && last combined == '\n'
-                     then init combined  -- strip extra newline 
-                     else combined 
+  htmlBlocks <- many1 $ do (RawHtml blk) <- rawHtmlBlock
+                           sps <- do sp1 <- many spaceChar
+                                     sp2 <- option "" (blankline >> return "\n")
+                                     sp3 <- many spaceChar
+                                     sp4 <- option "" blanklines
+                                     return $ sp1 ++ sp2 ++ sp3 ++ sp4
+                           -- note: we want raw html to be able to
+                           -- precede a code block, when separated
+                           -- by a blank line
+                           return $ blk ++ sps
+  let combined = concat htmlBlocks
+  let combined' = if last combined == '\n' then init combined else combined
   return $ RawHtml combined'
 
 --