Org reader: preserve targets of spurious links

Links with (internal) targets that the reader doesn't know about are
converted into emphasized text. Information on the link target is now
preserved by wrapping the text in a Span of class `spurious-link`, with
an attribute `target` set to the link's original target. This allows to
recover and fix broken or unknown links with filters.

See: #6916

1 files changed, 4 insertions, 5 deletions

diff --git a/src/Text/Pandoc/Readers/Org/Inlines.hs b/src/Text/Pandoc/Readers/Org/Inlines.hs
index b234bee58..0330cf55f 100644
--- a/src/Text/Pandoc/Readers/Org/Inlines.hs
+++ b/src/Text/Pandoc/Readers/Org/Inlines.hs
@@ -477,17 +477,17 @@ linkToInlinesF linkStr =
 
 internalLink :: Text -> Inlines -> F Inlines
 internalLink link title = do
-  anchorB <- (link `elem`) <$> asksF orgStateAnchorIds
-  if anchorB
+  ids <- asksF orgStateAnchorIds
+  if link `elem` ids
     then return $ B.link ("#" <> link) "" title
-    else return $ B.emph title
+    else let attr' = ("", ["spurious-link"] , [("target", link)])
+         in return $ B.spanWith attr' (B.emph title)
 
 -- | Parse an anchor like @<<anchor-id>>@ and return an empty span with
 -- @anchor-id@ set as id.  Legal anchors in org-mode are defined through
 -- @org-target-regexp@, which is fairly liberal.  Since no link is created if
 -- @anchor-id@ contains spaces, we are more restrictive in what is accepted as
 -- an anchor.
-
 anchor :: PandocMonad m => OrgParser m (F Inlines)
 anchor =  try $ do
   anchorId <- parseAnchor
@@ -501,7 +501,6 @@ anchor =  try $ do
 
 -- | Replace every char but [a-zA-Z0-9_.-:] with a hyphen '-'.  This mirrors
 -- the org function @org-export-solidify-link-text@.
-
 solidify :: Text -> Text
 solidify = T.map replaceSpecialChar
  where replaceSpecialChar c