Add sourcepos extension for commonmarke

* Add `Ext_sourcepos` constructor for `Extension`.
* Add `sourcepos` extension (only for commonmark).
* Bump to 2.11.3

With the `sourcepos` extension set set, `data-pos` attributes are added
to the AST by the commonmark reader. No other readers are affected.  The
`data-pos` attributes are put on elements that accept attributes; for
other elements, an enlosing Div or Span is added to hold the attributes.

Closes #4565.

5 files changed, 20 insertions, 6 deletions

diff --git a/MANUAL.txt b/MANUAL.txt
index 0a1300947..461ebf54d 100644
--- a/MANUAL.txt
+++ b/MANUAL.txt
@@ -5127,6 +5127,13 @@ for regular emphasis, add extra blank space around headings.
 
   [Project Gutenberg]: https://www.gutenberg.org
 
+#### Extension: `sourcepos` ####
+
+Include source position attributes when parsing `commonmark`.
+For elements that accept attributes, a `data-pos` attribute
+is added; other elements are placed in a surrounding
+Div or Span elemnet with a `data-pos` attribute.
+
 ## Markdown variants
 
 In addition to pandoc's extended Markdown, the following Markdown
diff --git a/pandoc.cabal b/pandoc.cabal
index c02dfeb38..5829856da 100644
--- a/pandoc.cabal
+++ b/pandoc.cabal
@@ -1,6 +1,6 @@
 cabal-version:   2.2
 name:            pandoc
-version:         2.11.2
+version:         2.11.3
 build-type:      Simple
 license:         GPL-2.0-or-later
 license-file:    COPYING.md
diff --git a/src/Text/Pandoc/Extensions.hs b/src/Text/Pandoc/Extensions.hs
index a94e24e2c..9865f897b 100644
--- a/src/Text/Pandoc/Extensions.hs
+++ b/src/Text/Pandoc/Extensions.hs
@@ -154,6 +154,7 @@ data Extension =
     | Ext_yaml_metadata_block -- ^ YAML metadata block
     | Ext_gutenberg           -- ^ Use Project Gutenberg conventions for plain
     | Ext_attributes          -- ^ Generic attribute syntax
+    | Ext_sourcepos           -- ^ Include source position attributes
     deriving (Show, Read, Enum, Eq, Ord, Bounded, Data, Typeable, Generic)
 
 -- | Extensions to be used with pandoc-flavored markdown.
@@ -503,6 +504,7 @@ getAllExtensions f = universalExtensions <> getAll f
     , Ext_implicit_header_references
     , Ext_attributes
     , Ext_fenced_code_attributes
+    , Ext_sourcepos
     ]
   getAll "commonmark_x"    = getAll "commonmark"
   getAll "org"             = autoIdExtensions <>
diff --git a/src/Text/Pandoc/Options.hs b/src/Text/Pandoc/Options.hs
index c7f1a56fa..ecd65a54d 100644
--- a/src/Text/Pandoc/Options.hs
+++ b/src/Text/Pandoc/Options.hs
@@ -65,6 +65,7 @@ data ReaderOptions = ReaderOptions{
        , readerDefaultImageExtension :: Text -- ^ Default extension for images
        , readerTrackChanges          :: TrackChanges -- ^ Track changes setting for docx
        , readerStripComments         :: Bool -- ^ Strip HTML comments instead of parsing as raw HTML
+                                             -- (only implemented in commonmark)
 } deriving (Show, Read, Data, Typeable, Generic)
 
 instance HasSyntaxExtensions ReaderOptions where
diff --git a/src/Text/Pandoc/Readers/CommonMark.hs b/src/Text/Pandoc/Readers/CommonMark.hs
index d32a38342..9eef498e1 100644
--- a/src/Text/Pandoc/Readers/CommonMark.hs
+++ b/src/Text/Pandoc/Readers/CommonMark.hs
@@ -32,11 +32,15 @@ import Data.Typeable
 
 -- | Parse a CommonMark formatted string into a 'Pandoc' structure.
 readCommonMark :: PandocMonad m => ReaderOptions -> Text -> m Pandoc
-readCommonMark opts s = do
-  let res = runIdentity $ commonmarkWith (specFor opts) "" s
-  case res of
-    Left err -> throwError $ PandocParsecError s err
-    Right (Cm bls :: Cm () Blocks) -> return $ B.doc bls
+readCommonMark opts s
+  | isEnabled Ext_sourcepos opts =
+    case runIdentity (commonmarkWith (specFor opts) "" s) of
+      Left err -> throwError $ PandocParsecError s err
+      Right (Cm bls :: Cm SourceRange Blocks) -> return $ B.doc bls
+  | otherwise =
+    case runIdentity (commonmarkWith (specFor opts) "" s) of
+      Left err -> throwError $ PandocParsecError s err
+      Right (Cm bls :: Cm () Blocks) -> return $ B.doc bls
 
 specFor :: (Monad m, Typeable m, Typeable a,
             Rangeable (Cm a Inlines), Rangeable (Cm a Blocks))