HTML Reader: be more forgiving about figcaption

fixes jgm#4183

src/Text/Pandoc/Readers/HTML.hs

@@ -588,17 +588,23 @@ pFigure = try $ do
   skipMany pBlank
   let pImg  = (\x -> (Just x, Nothing)) <$>
                (pOptInTag "p" pImage <* skipMany pBlank)
-      pCapt = (\x -> (Nothing, Just x)) <$>
-               (pInTags "figcaption" inline <* skipMany pBlank)
+      pCapt = (\x -> (Nothing, Just x)) <$> do
+                skipMany pBlank
+                bs <- pInTags "figcaption" block
+                skipMany pBlank
+                let getInlines (Plain xs) = xs
+                    getInlines (Para xs)  = xs
+                    getInlines _          = mempty
+                return $ query getInlines bs
       pSkip = (Nothing, Nothing) <$ pSatisfy (not . matchTagClose "figure")
   res <- many (pImg <|> pCapt <|> pSkip)
   let mbimg = msum $ map fst res
   let mbcap = msum $ map snd res
   TagClose _ <- pSatisfy (matchTagClose "figure")
-  let caption = fromMaybe mempty mbcap
   case B.toList <$> mbimg of
-       Just [Image attr _ (url, tit)] ->
-         return $ B.para $ B.imageWith attr url ("fig:" ++ tit) caption
+       Just [Image attr alt (url, tit)] ->
+         let caption = fromMaybe alt mbcap
+         in  return $ B.para $ B.imageWith attr url ("fig:" ++ tit) $ B.fromList caption
        _ -> mzero
 
 pCodeBlock :: PandocMonad m => TagParser m Blocks

test/command/4183.md

@@ -0,0 +1,32 @@
+```
+% pandoc -f html -t native
+<figure>
+  <img src="foo" alt="bar">
+</figure>
+^D
+[Para [Image ("",[],[]) [Str "bar"] ("foo","fig:")]]
+```
+
+```
+% pandoc -f html -t native
+<figure>
+  <img src="foo" alt="bar">
+  <figcaption>
+    <div>
+      baz
+    </div>
+  </figcaption>
+</figure>
+^D
+[Para [Image ("",[],[]) [Str "baz"] ("foo","fig:")]]
+```
+
+```
+% pandoc -f html -t native
+<figure>
+  <img src="foo">
+  <figcaption><p><em>baz</em></p></figcaption>
+</figure>
+^D
+[Para [Image ("",[],[]) [Emph [Str "baz"]] ("foo","fig:")]]
+```