Org reader: put header tags into empty spans

Org mode allows headers to be tagged:

``` org-mode
* Headline         :TAG1:TAG2:
```

Instead of being interpreted as part of the headline, the tags are now
put into the attributes of empty spans.  Spans without textual content
won't be visible by default, but they are detectable by filters.  They
can also be styled using CSS when written as HTML.

This fixes #2160.

1 files changed, 19 insertions, 2 deletions

diff --git a/src/Text/Pandoc/Readers/Org.hs b/src/Text/Pandoc/Readers/Org.hs
index 83fb48764..dd8da30c2 100644
--- a/src/Text/Pandoc/Readers/Org.hs
+++ b/src/Text/Pandoc/Readers/Org.hs
@@ -652,8 +652,25 @@ parseFormat = try $ do
 header :: OrgParser (F Blocks)
 header = try $ do
   level <- headerStart
-  title <- inlinesTillNewline
-  return $ B.header level <$> title
+  title <- manyTill inline (lookAhead headerEnd)
+  tags <- headerEnd
+  let inlns = trimInlinesF . mconcat $ title <> map tagToInlineF tags
+  return $ B.header level <$> inlns
+ where
+   tagToInlineF :: String -> F Inlines
+   tagToInlineF t = return $ B.spanWith ("", ["tag"], [("data-tag-name", t)]) mempty
+
+headerEnd :: OrgParser [String]
+headerEnd = option [] headerTags <* newline
+
+headerTags :: OrgParser [String]
+headerTags = try $
+  skipSpaces
+  *> char ':'
+  *> many1 tag
+  <* skipSpaces
+ where tag = many1 (alphaNum <|> oneOf "@%#_")
+             <* char ':'
 
 headerStart :: OrgParser Int
 headerStart = try $