Markdown reader: revised definition list syntax (closes #1429).

* This change brings pandoc's definition list syntax into alignment
  with that used in PHP markdown extra and multimarkdown (with the
  exception that pandoc is more flexible about the definition markers,
  allowing tildes as well as colons).

* Lazily wrapped definitions are now allowed; blank space is required
  between list items; and the space before definition is used to
  determine whether it is a paragraph or a "plain" element.

* For backwards compatibility, a new extension,
  `compact_definition_lists`, has been added that restores the behavior
  of pandoc 1.12.x, allowing tight definition lists with no blank space
  between items, and disallowing lazy wrapping.

2 files changed, 40 insertions, 23 deletions

diff --git a/src/Text/Pandoc/Options.hs b/src/Text/Pandoc/Options.hs
index 8580a6914..ac791ac74 100644
--- a/src/Text/Pandoc/Options.hs
+++ b/src/Text/Pandoc/Options.hs
@@ -84,6 +84,8 @@ data Extension =
     | Ext_lists_without_preceding_blankline -- ^ Allow lists without preceding blank
     | Ext_startnum            -- ^ Make start number of ordered list significant
     | Ext_definition_lists    -- ^ Definition lists as in pandoc, mmd, php
+    | Ext_compact_definition_lists  -- ^ Definition lists without
+                               -- space between items, and disallow laziness
     | Ext_example_lists       -- ^ Markdown-style numbered examples
     | Ext_all_symbols_escapable  -- ^ Make all non-alphanumerics escapable
     | Ext_intraword_underscores  -- ^ Treat underscore inside word as literal
diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs
index 1e8a03ae8..01db5a13c 100644
--- a/src/Text/Pandoc/Readers/Markdown.hs
+++ b/src/Text/Pandoc/Readers/Markdown.hs
@@ -846,38 +846,53 @@ defListMarker = do
      else mzero
   return ()
 
-definitionListItem :: MarkdownParser (F (Inlines, [Blocks]))
-definitionListItem = try $ do
-  -- first, see if this has any chance of being a definition list:
-  lookAhead (anyLine >> optional blankline >> defListMarker)
-  term <- trimInlinesF . mconcat <$> manyTill inline newline
-  optional blankline
-  raw <- many1 defRawBlock
-  state <- getState
-  let oldContext = stateParserContext state
-  -- parse the extracted block, which may contain various block elements:
+definitionListItem :: Bool -> MarkdownParser (F (Inlines, [Blocks]))
+definitionListItem compact = try $ do
+  rawLine' <- anyLine
+  raw <- many1 $ defRawBlock compact
+  term <- parseFromString (trimInlinesF . mconcat <$> many inline) rawLine'
   contents <- mapM (parseFromString parseBlocks) raw
-  updateState (\st -> st {stateParserContext = oldContext})
+  optional blanklines
   return $ liftM2 (,) term (sequence contents)
 
-defRawBlock :: MarkdownParser String
-defRawBlock = try $ do
+defRawBlock :: Bool -> MarkdownParser String
+defRawBlock compact = try $ do
+  hasBlank <- option False $ blankline >> return True
   defListMarker
   firstline <- anyLine
-  rawlines <- many (notFollowedBy blankline >> indentSpaces >> anyLine)
-  trailing <- option "" blanklines
-  cont <- liftM concat $ many $ do
-            lns <- many1 $ notFollowedBy blankline >> indentSpaces >> anyLine
-            trl <- option "" blanklines
-            return $ unlines lns ++ trl
-  return $ firstline ++ "\n" ++ unlines rawlines ++ trailing ++ cont
+  let dline = try
+               ( do notFollowedBy blankline
+                    if compact -- laziness not compatible with compact
+                       then () <$ indentSpaces
+                       else (() <$ indentSpaces)
+                             <|> notFollowedBy defListMarker
+                    anyLine )
+  rawlines <- many dline
+  cont <- liftM concat $ many $ try $ do
+            trailing <- option "" blanklines
+            ln <- indentSpaces >> notFollowedBy blankline >> anyLine
+            lns <- many dline
+            return $ trailing ++ unlines (ln:lns)
+  return $ trimr (firstline ++ "\n" ++ unlines rawlines ++ cont) ++
+            if hasBlank || not (null cont) then "\n\n" else ""
 
 definitionList :: MarkdownParser (F Blocks)
-definitionList = do
-  guardEnabled Ext_definition_lists
-  items <- fmap sequence $ many1 definitionListItem
+definitionList = try $ do
+  lookAhead (anyLine >> optional blankline >> defListMarker)
+  compactDefinitionList <|> normalDefinitionList
+
+compactDefinitionList :: MarkdownParser (F Blocks)
+compactDefinitionList = do
+  guardEnabled Ext_compact_definition_lists
+  items <- fmap sequence $ many1 $ definitionListItem True
   return $ B.definitionList <$> fmap compactify'DL items
 
+normalDefinitionList :: MarkdownParser (F Blocks)
+normalDefinitionList = do
+  guardEnabled Ext_definition_lists
+  items <- fmap sequence $ many1 $ definitionListItem False
+  return $ B.definitionList <$> items
+
 --
 -- paragraph block
 --