html/template: check "type" attribute in <script>

Currently any script tag is treated as a javascript container, although
<script type="text/template"> must not be. Check "type" attribute of
"script" tag. If it is present and it is not a JS MIME type, do not
transition to elementScript state.

Fixes #12149, where // inside text template was treated as regexp.
Fixes #6701

Change-Id: I8fc9e504f7280bdd800f40383c061853665ac8a2
Reviewed-on: https://go-review.googlesource.com/14336
Run-TryBot: Russ Cox <rsc@golang.org>
TryBot-Result: Gobot Gobot <gobot@golang.org>
Reviewed-by: Russ Cox <rsc@golang.org>

src/html/template/content_test.go

@@ -161,6 +161,47 @@ func TestTypedContent(t *testing.T) {
 				`greeting=H%69\x26addressee=(World)`,
 			},
 		},
+		{
+			`<script type="text/javascript">alert("{{.}}")</script>`,
+			[]string{
+				`\x3cb\x3e \x22foo%\x22 O\x27Reilly \x26bar;`,
+				`a[href =~ \x22\/\/example.com\x22]#foo`,
+				`Hello, \x3cb\x3eWorld\x3c\/b\x3e \x26amp;tc!`,
+				` dir=\x22ltr\x22`,
+				`c \x26\x26 alert(\x22Hello, World!\x22);`,
+				// Escape sequence not over-escaped.
+				`Hello, World \x26 O\x27Reilly\x21`,
+				`greeting=H%69\x26addressee=(World)`,
+			},
+		},
+		{
+			`<script type="text/javascript">alert({{.}})</script>`,
+			[]string{
+				`"\u003cb\u003e \"foo%\" O'Reilly \u0026bar;"`,
+				`"a[href =~ \"//example.com\"]#foo"`,
+				`"Hello, \u003cb\u003eWorld\u003c/b\u003e \u0026amp;tc!"`,
+				`" dir=\"ltr\""`,
+				// Not escaped.
+				`c && alert("Hello, World!");`,
+				// Escape sequence not over-escaped.
+				`"Hello, World & O'Reilly\x21"`,
+				`"greeting=H%69\u0026addressee=(World)"`,
+			},
+		},
+		{
+			// Not treated as JS. The output is same as for <div>{{.}}</div>
+			`<script type="text/template">{{.}}</script>`,
+			[]string{
+				`&lt;b&gt; &#34;foo%&#34; O&#39;Reilly &amp;bar;`,
+				`a[href =~ &#34;//example.com&#34;]#foo`,
+				// Not escaped.
+				`Hello, <b>World</b> &amp;tc!`,
+				` dir=&#34;ltr&#34;`,
+				`c &amp;&amp; alert(&#34;Hello, World!&#34;);`,
+				`Hello, World &amp; O&#39;Reilly\x21`,
+				`greeting=H%69&amp;addressee=(World)`,
+			},
+		},
 		{
 			`<button onclick='alert("{{.}}")'>`,
 			[]string{

src/html/template/context.go

@@ -285,7 +285,8 @@ type element uint8
 const (
 	// elementNone occurs outside a special tag or special element body.
 	elementNone element = iota
-	// elementScript corresponds to the raw text <script> element.
+	// elementScript corresponds to the raw text <script> element
+	// with JS MIME type or no type attribute.
 	elementScript
 	// elementStyle corresponds to the raw text <style> element.
 	elementStyle
@@ -319,6 +320,8 @@ const (
 	attrNone attr = iota
 	// attrScript corresponds to an event handler attribute.
 	attrScript
+	// attrScriptType corresponds to the type attribute in script HTML element
+	attrScriptType
 	// attrStyle corresponds to the style attribute whose value is CSS.
 	attrStyle
 	// attrURL corresponds to an attribute whose value is a URL.
@@ -328,6 +331,7 @@ const (
 var attrNames = [...]string{
 	attrNone:       "attrNone",
 	attrScript:     "attrScript",
+	attrScriptType: "attrScriptType",
 	attrStyle:      "attrStyle",
 	attrURL:        "attrURL",
 }

src/html/template/escape.go

@@ -673,6 +673,8 @@ func contextAfterText(c context, s []byte) (context, int) {
 		return transitionFunc[c.state](c, s[:i])
 	}
 
+	// We are at the beginning of an attribute value.
+
 	i := bytes.IndexAny(s, delimEnds[c.delim])
 	if i == -1 {
 		i = len(s)
@@ -703,13 +705,21 @@ func contextAfterText(c context, s []byte) (context, int) {
 		}
 		return c, len(s)
 	}
+
+	element := c.element
+
+	// If this is a non-JS "type" attribute inside "script" tag, do not treat the contents as JS.
+	if c.state == stateAttr && c.element == elementScript && c.attr == attrScriptType && !isJSType(string(s[:i])) {
+		element = elementNone
+	}
+
 	if c.delim != delimSpaceOrTagEnd {
 		// Consume any quote.
 		i++
 	}
 	// On exiting an attribute, we discard all state information
 	// except the state and element.
-	return context{state: stateTag, element: c.element}, i
+	return context{state: stateTag, element: element}, i
 }
 
 // editActionNode records a change to an action pipeline for later commit.

src/html/template/escape_test.go

@@ -1364,6 +1364,10 @@ func TestEscapeText(t *testing.T) {
 			`<script type=text/javascript `,
 			context{state: stateTag, element: elementScript},
 		},
+		{
+			`<script>`,
+			context{state: stateJS, jsCtx: jsCtxRegexp, element: elementScript},
+		},
 		{
 			`<script>foo`,
 			context{state: stateJS, jsCtx: jsCtxDivOp, element: elementScript},
@@ -1388,6 +1392,14 @@ func TestEscapeText(t *testing.T) {
 			`<script>document.write("<script>alert(1)</script>");`,
 			context{state: stateText},
 		},
+		{
+			`<script type="text/template">`,
+			context{state: stateText},
+		},
+		{
+			`<script type="notjs">`,
+			context{state: stateText},
+		},
 		{
 			`<Script>`,
 			context{state: stateJS, element: elementScript},

src/html/template/js.go

@@ -362,3 +362,41 @@ func isJSIdentPart(r rune) bool {
 	}
 	return false
 }
+
+// isJSType returns true if the given MIME type should be considered JavaScript.
+//
+// It is used to determine whether a script tag with a type attribute is a javascript container.
+func isJSType(mimeType string) bool {
+	// per
+	//   http://www.w3.org/TR/html5/scripting-1.html#attr-script-type
+	//   https://tools.ietf.org/html/rfc7231#section-3.1.1
+	//   http://tools.ietf.org/html/rfc4329#section-3
+
+	// discard parameters
+	if i := strings.Index(mimeType, ";"); i >= 0 {
+		mimeType = mimeType[:i]
+	}
+	mimeType = strings.TrimSpace(mimeType)
+	switch mimeType {
+	case
+		"application/ecmascript",
+		"application/javascript",
+		"application/x-ecmascript",
+		"application/x-javascript",
+		"text/ecmascript",
+		"text/javascript",
+		"text/javascript1.0",
+		"text/javascript1.1",
+		"text/javascript1.2",
+		"text/javascript1.3",
+		"text/javascript1.4",
+		"text/javascript1.5",
+		"text/jscript",
+		"text/livescript",
+		"text/x-ecmascript",
+		"text/x-javascript":
+		return true
+	default:
+		return false
+	}
+}

src/html/template/js_test.go

@@ -332,6 +332,24 @@ func TestEscapersOnLower7AndSelectHighCodepoints(t *testing.T) {
 	}
 }
 
+func TestIsJsMimeType(t *testing.T) {
+	tests := []struct {
+		in  string
+		out bool
+	}{
+		{"application/javascript;version=1.8", true},
+		{"application/javascript;version=1.8;foo=bar", true},
+		{"application/javascript/version=1.8", false},
+		{"text/javascript", true},
+	}
+
+	for _, test := range tests {
+		if isJSType(test.in) != test.out {
+			t.Errorf("isJSType(%q) = %v, want %v", test.in, !test.out, test.out)
+		}
+	}
+}
+
 func BenchmarkJSValEscaperWithNum(b *testing.B) {
 	for i := 0; i < b.N; i++ {
 		jsValEscaper(3.141592654)

src/html/template/transition.go

@@ -105,7 +105,12 @@ func tTag(c context, s []byte) (context, int) {
 			err:   errorf(ErrBadHTML, nil, 0, "expected space, attr name, or end of tag, but got %q", s[i:]),
 		}, len(s)
 	}
-	switch attrType(string(s[i:j])) {
+
+	attrName := string(s[i:j])
+	if c.element == elementScript && attrName == "type" {
+		attr = attrScriptType
+	} else {
+		switch attrType(attrName) {
 		case contentTypeURL:
 			attr = attrURL
 		case contentTypeCSS:
@@ -113,6 +118,8 @@ func tTag(c context, s []byte) (context, int) {
 		case contentTypeJS:
 			attr = attrScript
 		}
+	}
+
 	if j == len(s) {
 		state = stateAttrName
 	} else {
@@ -151,6 +158,7 @@ func tAfterName(c context, s []byte) (context, int) {
 var attrStartStates = [...]state{
 	attrNone:       stateAttr,
 	attrScript:     stateJS,
+	attrScriptType: stateAttr,
 	attrStyle:      stateCSS,
 	attrURL:        stateURL,
 }