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`.

1 files changed, 16 insertions, 8 deletions

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"