html: handle equals sign before attribute

Apply the correct normalization when an equals sign appears before an
attribute name (e.g. '<tag =>' -> '<tag =="">'), per WHATWG 13.2.5.32.

Change-Id: Id21b428bd86117dd073c502767386bc718a3fb7b
Reviewed-on: https://go-review.googlesource.com/c/net/+/488695
Auto-Submit: Roland Shoemaker <roland@golang.org>
TryBot-Result: Gopher Robot <gobot@golang.org>
Reviewed-by: Nigel Tao <nigeltao@golang.org>
Run-TryBot: Roland Shoemaker <roland@golang.org>
Reviewed-by: Nigel Tao (INACTIVE; USE @golang.org INSTEAD) <nigeltao@google.com>

html/token.go

@@ -913,7 +913,14 @@ func (z *Tokenizer) readTagAttrKey() {
 		case ' ', '\n', '\r', '\t', '\f', '/':
 			z.pendingAttr[0].end = z.raw.end - 1
 			return
-		case '=', '>':
+		case '=':
+			if z.pendingAttr[0].start+1 == z.raw.end {
+				// WHATWG 13.2.5.32, if we see an equals sign before the attribute name
+				// begins, we treat it as a character in the attribute name and continue.
+				continue
+			}
+			fallthrough
+		case '>':
 			z.raw.end--
 			z.pendingAttr[0].end = z.raw.end
 			return

html/token_test.go

@@ -590,6 +590,17 @@ var tokenTests = []tokenTest{
 		`<p id=can't><p id=won't>`,
 		`<p id="can&#39;t">$<p id="won&#39;t">`,
 	},
+	// WHATWG 13.2.5.32 equals sign before attribute name state
+	{
+		"equals sign before attribute name",
+		`<p  =>`,
+		`<p =="">`,
+	},
+	{
+		"equals sign before attribute name, extra cruft",
+		`<p  =asd>`,
+		`<p =asd="">`,
+	},
 }
 
 func TestTokenizer(t *testing.T) {