epub: Add EPUB3 subject metadata (authority/term)

This adds the ability to specify EPUB 3 `authority` and `term` specific
refinements to the `subject` tag. Specifying a plain `subject` tag in
metadata will function as before.

MANUAL.txt

@@ -2189,7 +2189,7 @@ Currently the following pipes are predefined:
     and AsciiDoc metadata; repeat as for `author`, above
 
 `subject`
-:   document subject, included in ODT, PDF, docx and pptx metadata
+:   document subject, included in ODT, PDF, docx, EPUB, and pptx metadata
 
 `description`
 :   document description, included in ODT, docx and pptx metadata. Some
@@ -6189,7 +6189,12 @@ The following fields are recognized:
     language if nothing is specified.
 
 `subject`
-  ~ A string value or a list of such values.
+  ~ Either a string value, or an object with fields `text`, `authority`,
+    and `term`, or a list of such objects. Valid values for `authority`
+    are either a [reserved authority value] (currently `AAT`, `BIC`,
+    `BISAC`, `CLC`, `DDC`, `CLIL`, `EuroVoc`, `MEDTOP`, `LCSH`, `NDC`,
+    `Thema`, `UDC`, and `WGS`) or an absolute IRI identifying a custom
+    scheme. Valid values for `term` are defined by the scheme.
 
 `description`
   ~ A string value.
@@ -6239,6 +6244,7 @@ The following fields are recognized:
     - `scroll-axis`: `vertical`|`horizontal`|`default`
 
 [MARC relators]: https://loc.gov/marc/relators/relaterm.html
+[reserved authority value]: https://idpf.github.io/epub-registries/authorities/
 [`spine` element]: http://idpf.org/epub/301/spec/epub-publications.html#sec-spine-elem
 
 ## The `epub:type` attribute

src/Text/Pandoc/Writers/EPUB.hs

@@ -79,7 +79,7 @@ data EPUBMetadata = EPUBMetadata{
   , epubLanguage            :: Text
   , epubCreator             :: [Creator]
   , epubContributor         :: [Creator]
-  , epubSubject             :: [Text]
+  , epubSubject             :: [Subject]
   , epubDescription         :: Maybe Text
   , epubType                :: Maybe Text
   , epubFormat              :: Maybe Text
@@ -121,6 +121,12 @@ data Title = Title{
 
 data ProgressionDirection = LTR | RTL deriving Show
 
+data Subject = Subject{
+    subjectText      :: Text
+  , subjectAuthority :: Maybe Text
+  , subjectTerm      :: Maybe Text
+  } deriving Show
+
 dcName :: Text -> QName
 dcName n = QName n Nothing (Just "dc")
 
@@ -232,7 +238,11 @@ addMetadataFromXML e@(Element (QName name _ (Just "dc")) attrs _ _) md
                        , creatorRole = getAttr "role"
                        , creatorFileAs = getAttr "file-as"
                        } : epubContributor md }
-  | name == "subject" = md{ epubSubject = strContent e : epubSubject md }
+  | name == "subject" = md{ epubSubject =
+              Subject  { subjectText = strContent e
+                       , subjectAuthority = getAttr "authority"
+                       , subjectTerm = getAttr "term"
+                       } : epubSubject md }
   | name == "description" = md { epubDescription = Just $ strContent e }
   | name == "type" = md { epubType = Just $ strContent e }
   | name == "format" = md { epubFormat = Just $ strContent e }
@@ -313,12 +323,13 @@ getDate s meta = getList s meta handleMetaValue
         handleMetaValue mv = Date { dateText = fromMaybe "" $ normalizeDate' $ metaValueToString mv
                                   , dateEvent = Nothing }
 
-simpleList :: T.Text -> Meta -> [Text]
+getSubject :: T.Text -> Meta -> [Subject]
-simpleList s meta =
+getSubject s meta = getList s meta handleMetaValue
-  case lookupMeta s meta of
+  where handleMetaValue (MetaMap m) =
-       Just (MetaList xs) -> map metaValueToString xs
+           Subject{ subjectText = maybe "" metaValueToString $ M.lookup "text" m
-       Just x             -> [metaValueToString x]
+                  , subjectAuthority = metaValueToString <$> M.lookup "authority" m
-       Nothing            -> []
+                  , subjectTerm = metaValueToString <$> M.lookup "term" m }
+        handleMetaValue mv = Subject (metaValueToString mv) Nothing Nothing
 
 metadataFromMeta :: WriterOptions -> Meta -> EPUBMetadata
 metadataFromMeta opts meta = EPUBMetadata{
@@ -352,7 +363,7 @@ metadataFromMeta opts meta = EPUBMetadata{
            lookupMeta "language" meta `mplus` lookupMeta "lang" meta
         creators = getCreator "creator" meta
         contributors = getCreator "contributor" meta
-        subjects = simpleList "subject" meta
+        subjects = getSubject "subject" meta
         description = metaValueToString <$> lookupMeta "description" meta
         epubtype = metaValueToString <$> lookupMeta "type" meta
         format = metaValueToString <$> lookupMeta "format" meta
@@ -974,7 +985,7 @@ metadataElement version md currentTime =
                        epubCreator md
         contributorNodes = withIds "epub-contributor"
                            (toCreatorNode "contributor") $ epubContributor md
-        subjectNodes = map (dcTag "subject") $ epubSubject md
+        subjectNodes = withIds "subject" toSubjectNode $ epubSubject md
         descriptionNodes = maybe [] (dcTag' "description") $ epubDescription md
         typeNodes = maybe [] (dcTag' "type") $ epubType md
         formatNodes = maybe [] (dcTag' "format") $ epubFormat md
@@ -1046,6 +1057,16 @@ metadataElement version md currentTime =
              (("id",id') :
                 maybe [] (\x -> [("opf:event",x)]) (dateEvent date)) $
                  dateText date]
+        toSubjectNode id' subject
+          | version == EPUB2 = [dcNode "subject" !
+            [("id",id')] $ subjectText subject]
+          | otherwise = (dcNode "subject" ! [("id",id')] $ subjectText subject)
+            : maybe [] (\x -> (unode "meta" !
+                    [("refines", "#" <> id'),("property","authority")] $ x) :
+                    maybe [] (\y -> [unode "meta" !
+                         [("refines", "#" <> id'),("property","term")] $ y])
+                         (subjectTerm subject))
+                    (subjectAuthority subject)
         schemeToOnix :: Text -> Text
         schemeToOnix "ISBN-10"              = "02"
         schemeToOnix "GTIN-13"              = "03"