From d84a6041e12547331f3a252ea4e8b4d229ba1159 Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Sat, 13 Feb 2021 13:06:22 -0800
Subject: HTML reader: fix bad handling of empty src attribute in iframe.
- If src is empty, we simply skip the iframe.
- If src is invalid or cannot be fetched, we issue a warning
and skip instead of failing with an error.
- Closes #7099.
---
src/Text/Pandoc/Readers/HTML.hs | 18 ++++++++++++------
1 file changed, 12 insertions(+), 6 deletions(-)
(limited to 'src/Text/Pandoc/Readers/HTML.hs')
diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs
index afc7a3e25..cc60b5501 100644
--- a/src/Text/Pandoc/Readers/HTML.hs
+++ b/src/Text/Pandoc/Readers/HTML.hs
@@ -26,7 +26,7 @@ module Text.Pandoc.Readers.HTML ( readHtml
import Control.Applicative ((<|>))
import Control.Monad (guard, msum, mzero, unless, void)
-import Control.Monad.Except (throwError)
+import Control.Monad.Except (throwError, catchError)
import Control.Monad.Reader (ask, asks, lift, local, runReaderT)
import Data.ByteString.Base64 (encode)
import Data.Char (isAlphaNum, isLetter)
@@ -393,11 +393,17 @@ pIframe = try $ do
tag <- pSatisfy (tagOpen (=="iframe") (isJust . lookup "src"))
pCloses "iframe" <|> eof
url <- canonicalizeUrl $ fromAttrib "src" tag
- (bs, _) <- openURL url
- let inp = UTF8.toText bs
- opts <- readerOpts <$> getState
- Pandoc _ contents <- readHtml opts inp
- return $ B.divWith ("",["iframe"],[]) $ B.fromList contents
+ if T.null url
+ then ignore $ renderTags' [tag, TagClose "iframe"]
+ else catchError
+ (do (bs, _) <- openURL url
+ let inp = UTF8.toText bs
+ opts <- readerOpts <$> getState
+ Pandoc _ contents <- readHtml opts inp
+ return $ B.divWith ("",["iframe"],[]) $ B.fromList contents)
+ (\e -> do
+ logMessage $ CouldNotFetchResource url (renderError e)
+ ignore $ renderTags' [tag, TagClose "iframe"])
pRawHtmlBlock :: PandocMonad m => TagParser m Blocks
pRawHtmlBlock = do
--
cgit v1.2.3