Multimarkdown sub- and superscripts (#5512) (#7188)

Added an extension `short_subsuperscripts` which modifies the behavior
of `subscript` and `superscript`, allowing subscripts or superscripts containing only
alphanumerics to end with a space character (eg. `x^2 = 4` or `H~2 is
combustible`).  This improves support for multimarkdown. Closes #5512.

Add `Ext_short_subsuperscripts` constructor to `Extension` [API change].
This is enabled by default for `markdown_mmd`.

2 files changed, 20 insertions, 15 deletions

diff --git a/src/Text/Pandoc/Extensions.hs b/src/Text/Pandoc/Extensions.hs
index ce04ce641..2ef8f64e9 100644
--- a/src/Text/Pandoc/Extensions.hs
+++ b/src/Text/Pandoc/Extensions.hs
@@ -124,6 +124,7 @@ data Extension =
     | Ext_mmd_header_identifiers -- ^ Multimarkdown style header identifiers [myid]
     | Ext_mmd_link_attributes     -- ^ MMD style reference link attributes
     | Ext_mmd_title_block     -- ^ Multimarkdown metadata block
+    | Ext_short_subsuperscripts -- ^ sub-&superscripts w/o closing char (v~i)
     | Ext_multiline_tables    -- ^ Pandoc-style multiline tables
     | Ext_native_divs             -- ^ Use Div blocks for contents of <div> tags
     | Ext_native_spans            -- ^ Use Span inlines for contents of <span>
@@ -286,14 +287,9 @@ multimarkdownExtensions = extensionsFromList
   , Ext_auto_identifiers
   , Ext_mmd_header_identifiers
   , Ext_implicit_figures
-  -- Note: MMD's syntax for superscripts and subscripts
-  -- is a bit more permissive than pandoc's, allowing
-  -- e^2 and a~1 instead of e^2^ and a~1~, so even with
-  -- these options we don't have full support for MMD
-  -- superscripts and subscripts, but there's no reason
-  -- not to include these:
-  , Ext_superscript
+  , Ext_short_subsuperscripts
   , Ext_subscript
+  , Ext_superscript
   , Ext_backtick_code_blocks
   , Ext_spaced_reference_links
   -- So far only in dev version of mmd:
@@ -464,6 +460,7 @@ getAllExtensions f = universalExtensions <> getAll f
        , Ext_gutenberg
        , Ext_smart
        , Ext_literate_haskell
+       , Ext_short_subsuperscripts
        , Ext_rebase_relative_paths
        ]
   getAll "markdown_strict"   = allMarkdownExtensions
diff --git a/src/Text/Pandoc/Readers/Markdown.hs b/src/Text/Pandoc/Readers/Markdown.hs
index 2dc7ddf52..536e502cf 100644
--- a/src/Text/Pandoc/Readers/Markdown.hs
+++ b/src/Text/Pandoc/Readers/Markdown.hs
@@ -1692,21 +1692,29 @@ strikeout = fmap B.strikeout <$>
 
 superscript :: PandocMonad m => MarkdownParser m (F Inlines)
 superscript = do
-  guardEnabled Ext_superscript
   fmap B.superscript <$> try (do
     char '^'
-    mconcat <$> many1Till (do notFollowedBy spaceChar
-                              notFollowedBy newline
-                              inline) (char '^'))
+    mconcat <$> (try regularSuperscript <|> try mmdShortSuperscript))
+      where regularSuperscript = many1Till (do guardEnabled Ext_superscript
+                                               notFollowedBy spaceChar
+                                               notFollowedBy newline
+                                               inline) (char '^')
+            mmdShortSuperscript = do guardEnabled Ext_short_subsuperscripts
+                                     result <- take1WhileP isAlphaNum
+                                     return $ return $ return $ B.str result
 
 subscript :: PandocMonad m => MarkdownParser m (F Inlines)
 subscript = do
-  guardEnabled Ext_subscript
   fmap B.subscript <$> try (do
     char '~'
-    mconcat <$> many1Till (do notFollowedBy spaceChar
-                              notFollowedBy newline
-                              inline) (char '~'))
+    mconcat <$> (try regularSubscript <|> mmdShortSubscript))
+      where regularSubscript = many1Till (do guardEnabled Ext_subscript
+                                             notFollowedBy spaceChar
+                                             notFollowedBy newline
+                                             inline) (char '~')
+            mmdShortSubscript = do guardEnabled Ext_short_subsuperscripts
+                                   result <- take1WhileP isAlphaNum
+                                   return $ return $ return $ B.str result
 
 whitespace :: PandocMonad m => MarkdownParser m (F Inlines)
 whitespace = spaceChar >> return <$> (lb <|> regsp) <?> "whitespace"