From 99fe8594d94573b8ba8ec1d1e47b57444de4e4cb Mon Sep 17 00:00:00 2001
From: John MacFarlane <jgm@berkeley.edu>
Date: Fri, 10 Jul 2015 10:28:39 -0700
Subject: Avoid parsing partial URLs as HTML tags.

Closes #2277.
---
 src/Text/Pandoc/Readers/HTML.hs | 9 ++++++++-
 tests/Tests/Readers/Markdown.hs | 3 +++
 2 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/src/Text/Pandoc/Readers/HTML.hs b/src/Text/Pandoc/Readers/HTML.hs
index f2f97dbc4..361d64361 100644
--- a/src/Text/Pandoc/Readers/HTML.hs
+++ b/src/Text/Pandoc/Readers/HTML.hs
@@ -911,8 +911,15 @@ htmlTag :: Monad m
 htmlTag f = try $ do
   lookAhead (char '<')
   inp <- getInput
-  let (next : _) = canonicalizeTags $ parseTags inp
+  let hasTagWarning (TagWarning _:_) = True
+      hasTagWarning _ = False
+  let (next : rest) = canonicalizeTags $ parseTagsOptions
+                       parseOptions{ optTagWarning = True } inp
   guard $ f next
+  -- we get a TagWarning on things like
+  -- <www.boe.es/buscar/act.php?id=BOE-A-1996-8930#a66>
+  -- which should NOT be parsed as an HTML tag, see #2277
+  guard $ not $ hasTagWarning rest
   case next of
        TagComment s
          | "<!--" `isPrefixOf` inp -> do
diff --git a/tests/Tests/Readers/Markdown.hs b/tests/Tests/Readers/Markdown.hs
index ed79f9e3d..e08ac1607 100644
--- a/tests/Tests/Readers/Markdown.hs
+++ b/tests/Tests/Readers/Markdown.hs
@@ -195,6 +195,9 @@ tests = [ testGroup "inline code"
           [ "with unicode dash following" =:
             "<http://foo.bar>\8212" =?> para (autolink "http://foo.bar" <>
                                          str "\8212")
+          , "a partial URL (#2277)" =:
+            "<www.boe.es/buscar/act.php?id=BOE-A-1996-8930#a66>" =?>
+            para (text "<www.boe.es/buscar/act.php?id=BOE-A-1996-8930#a66>")
           ]
         , testGroup "Headers"
           [ "blank line before header" =:
-- 
cgit v1.2.3