commit 4109fccea424c486ca00a51bbe2ac2940e66075b
author Andrew Balholm <andybalholm@gmail.com> Mon May 12 16:42:14 2014 +1000
committer Nigel Tao <nigeltao@golang.org> Mon May 12 16:42:14 2014 +1000
tree de5d62dedc196a592032a666ce3e66249f01c308
parent c286e198d6a796666801bd26651d4623aa9750a2

html: handle '<' before a tag

As pointed out at
https://groups.google.com/forum/#!topic/golang-nuts/LJozHIXAAJY,
`<<p>html</p>` was parsed as `&lt;&lt;p&gt;html</p>`.
There was no test case for this. Chrome parses it as `&lt<p>html</p>`,
and that seems to be correct. We were missing the
"Reconcume the current input character" step at
http://www.whatwg.org/specs/web-apps/current-work/multipage/tokenization.html#tag-open-state

LGTM=nigeltao
R=golang-codereviews, gobot, nigeltao
CC=golang-codereviews, nigeltao
https://golang.org/cl/96060044

html/token.go

diff --git a/html/token.go b/html/token.go
index 3c17c7e..a226099 100644
--- a/html/token.go
+++ b/html/token.go
@@ -1002,6 +1002,8 @@
 			// "<!DOCTYPE declarations>" and "<?xml processing instructions?>".
 			tokenType = CommentToken
 		default:
+			// Reconsume the current character.
+			z.raw.end--
 			continue
 		}
 

html/token_test.go

diff --git a/html/token_test.go b/html/token_test.go
index 38d80d7..f6988a8 100644
--- a/html/token_test.go
+++ b/html/token_test.go
@@ -105,6 +105,11 @@
 		"if x<0 and y < 0 then x*y>0",
 		"if x&lt;0 and y &lt; 0 then x*y&gt;0",
 	},
+	{
+		"not a tag #11",
+		"<<p>",
+		"&lt;$<p>",
+	},
 	// EOF in a tag name.
 	{
 		"tag name eof #0",