Org reader: Add partial support for `#+EXCLUDE_TAGS` option. (#4950)

Closes #4284.

Headers with the corresponding tags should not appear in the output.

If one or more of the specified tags contains a non-tag character
like `+`, Org-mode will not treat that as a valid tag, but will
nonetheless continue scanning for valid tags. That behavior is not
replicated in this patch; entering `cat+dog` as one of the entries in
`#+EXCLUDE_TAGS` and running the file through Pandoc will cause the
parser to fail and result in the only excluded tag being the default, `noexport`.

1 files changed, 11 insertions, 0 deletions

diff --git a/src/Text/Pandoc/Readers/Org/Meta.hs b/src/Text/Pandoc/Readers/Org/Meta.hs
index 965e33d94..921cd27e0 100644
--- a/src/Text/Pandoc/Readers/Org/Meta.hs
+++ b/src/Text/Pandoc/Readers/Org/Meta.hs
@@ -52,6 +52,7 @@ import Data.Char (toLower)
 import Data.List (intersperse)
 import Data.Maybe (fromMaybe)
 import qualified Data.Map as M
+import qualified Data.Set as Set
 import Network.HTTP (urlEncode)
 
 -- | Returns the current meta, respecting export options.
@@ -158,6 +159,7 @@ optionLine = try $ do
     "seq_todo" -> todoSequence >>= updateState . registerTodoSequence
     "typ_todo" -> todoSequence >>= updateState . registerTodoSequence
     "macro"    -> macroDefinition >>= updateState . registerMacro
+    "exclude_tags" -> excludedTagSet >>= updateState . setExcludedTags
     "pandoc-emphasis-pre" -> emphChars >>= updateState . setEmphasisPreChar
     "pandoc-emphasis-post" -> emphChars >>= updateState . setEmphasisPostChar
     _          -> mzero
@@ -190,6 +192,15 @@ parseFormat = try $ replacePlain <|> replaceUrl <|> justAppend
    rest            = manyTill anyChar         (eof <|> () <$ oneOf "\n\r")
    tillSpecifier c = manyTill (noneOf "\n\r") (try $ string ('%':c:""))
 
+excludedTagSet :: Monad m => OrgParser m (Set.Set Tag)
+excludedTagSet = do
+  skipSpaces
+  Set.fromList . map Tag <$>
+                      many (orgTagWord <* skipSpaces) <* newline
+
+setExcludedTags :: Set.Set Tag -> OrgParserState -> OrgParserState
+setExcludedTags tagSet st = st { orgStateExcludedTags = tagSet }
+
 setEmphasisPreChar :: Maybe [Char] -> OrgParserState -> OrgParserState
 setEmphasisPreChar csMb st =
   let preChars = fromMaybe (orgStateEmphasisPostChars defaultOrgParserState) csMb