Handle pipes in code spans in table cells correctly

CHANGELOG.md

@@ -3,6 +3,9 @@
 * The parser can now recover from block-level parse errors in tables and
   continue parsing.
 
+* Pipes in code spans in table cells are not considered as table cell
+  delimiters anymore.
+
 ## MMark 0.0.5.0
 
 * Documentation improvements.

Text/MMark/Parser.hs

@@ -462,6 +462,7 @@ pTable = do
       startPos <- getPosition
       txt      <- fmap (T.stripEnd . T.pack) . foldMany' . choice $
         [ (++) . T.unpack <$> hidden (string "\\|")
+        , (++) . T.unpack <$> pCodeSpanB
         , (:) <$> label "inline content" (satisfy cellChar) ]
       return (IspSpan startPos txt)
     cellChar x = x /= '|' && notNewline x
@@ -538,6 +539,23 @@ pParagraph = do
   (if allowNaked then toBlock else Paragraph)
     (IspSpan startPos (assembleParagraph (l:ls []))) <$ sc
 
+----------------------------------------------------------------------------
+-- Auxiliary block-level parsers
+
+-- | 'match' a code span, this is a specialised and adjusted version of
+-- 'pCodeSpan'.
+
+pCodeSpanB :: BParser Text
+pCodeSpanB = fmap fst . match . hidden $ do
+  n <- try (length <$> some (char '`'))
+  let finalizer = try $ do
+        void $ count n (char '`')
+        notFollowedBy (char '`')
+  skipManyTill
+    (takeWhile1P Nothing (== '`') <|>
+     takeWhile1P Nothing (\x -> x /= '`' && notNewline x))
+    finalizer
+
 ----------------------------------------------------------------------------
 -- Inline parser
 
@@ -590,6 +608,8 @@ pInlines = do
             else pPlain
 
 -- | Parse a code span.
+--
+-- See also: 'pCodeSpanB'.
 
 pCodeSpan :: IParser Inline
 pCodeSpan = do

tests/Text/MMarkSpec.hs

@@ -1837,6 +1837,21 @@ spec = parallel $ do
       it "escaped pipes do not fool position tracking" $
         let s = "Foo | Bar\n--- | ---\n\\| *fo | bar"
         in s ~-> err (posN 26 s) (ueib <> etok '*' <> elabel "inline content")
+      it "pipes in code spans in headers do not fool the parser" $
+        "`|Foo|` | `|Bar|`\n--- | ---\nfoo | bar" ==->
+          "<table>\n<thead>\n<tr><th><code>|Foo|</code></th><th><code>|Bar|</code></th></tr>\n</thead>\n<tbody>\n<tr><td>foo</td><td>bar</td></tr>\n</tbody>\n</table>\n"
+      it "pipes in code spans in cells do not fool the parser" $
+        "Foo | Bar\n--- | ---\n`|foo|` | `|bar|`" ==->
+          "<table>\n<thead>\n<tr><th>Foo</th><th>Bar</th></tr>\n</thead>\n<tbody>\n<tr><td><code>|foo|</code></td><td><code>|bar|</code></td></tr>\n</tbody>\n</table>\n"
+      it "multi-line code spans are disallowed in table headers" $
+        "`Foo\nBar` | Bar\n--- | ---\nfoo | bar" ==->
+          "<p><code>Foo Bar</code> | Bar\n--- | ---\nfoo | bar</p>\n"
+      it "multi-line code spans are disallowed in table cells" $
+        let s = "Foo | Bar\n--- | ---\n`foo\nbar` | bar"
+        in s ~~->
+           [ err (posN 24 s) (utok '\n' <> etok '`')
+           , err (posN 35 s) (ueib <> etok '`' <> elabel "code span content")
+           ]
       it "parses tables with just header row" $
         "Foo | Bar\n--- | ---" ==->
           "<table>\n<thead>\n<tr><th>Foo</th><th>Bar</th></tr>\n</thead>\n<tbody>\n</tbody>\n</table>\n"