0f6458c · typeable/pandoc

git.iko.soy/typeable/pandoc

Don't double extract images from docx.

This fixes a regression that was introduced when `--extract-media` was generalized to work with any input format. We were getting two versions of each image extracted from a docx, one with a hash, one with the original filename, though only the hash one was used. This patch restores the original behavior (using the original filename). Pointed out in comments on #3674. Thanks to @laperouse.

commit0f6458c0c13380969ccac82d54a0e68a3ec76200 authorJohn MacFarlane <jgm@berkeley.edu> dateThu 18 May 2017, 13:38 (9 years ago) parent818d5c2

1 file changed+14−9

compare with master

unifiedsplit

src/Text/Pandoc/Class.hs+14−9

src/Text/Pandoc/Class.hs+14−9

@@ -345,19 +345,24 @@ withPaths (p:ps) action fp =

345345 catchError (action (p </> fp))

346346 (\_ -> withPaths ps action fp)

347347

348−-- | Traverse tree, filling media bag.

348+-- | Traverse tree, filling media bag for any images that

349+-- aren't already in the media bag.

349350fillMediaBag :: PandocMonad m => Maybe String -> Pandoc -> m Pandoc

350351fillMediaBag sourceURL d = walkM handleImage d

351352 where handleImage :: PandocMonad m => Inline -> m Inline

352353 handleImage (Image attr lab (src, tit)) = catchError

353− (do (bs, mt) <- fetchItem sourceURL src

354− let ext = fromMaybe (takeExtension src)

355− (mt >>= extensionFromMimeType)

356− let bs' = BL.fromChunks [bs]

357− let basename = showDigest $ sha1 bs'

358− let fname = basename <.> ext

359− insertMedia fname mt bs'

360− return $ Image attr lab (fname, tit))

354+ (do mediabag <- getMediaBag

355+ case lookupMedia src mediabag of

356+ Just (_, _) -> return $ Image attr lab (src, tit)

357+ Nothing -> do

358+ (bs, mt) <- downloadOrRead sourceURL src

359+ let ext = fromMaybe (takeExtension src)

360+ (mt >>= extensionFromMimeType)

361+ let bs' = BL.fromChunks [bs]

362+ let basename = showDigest $ sha1 bs'

363+ let fname = basename <.> ext

364+ insertMedia fname mt bs'

365+ return $ Image attr lab (fname, tit))

361366 (\e -> do

362367 case e of

363368 PandocResourceNotFound _ -> do