1// Copyright (c) 2011 The Chromium Authors. All rights reserved.
2// Use of this source code is governed by a BSD-style license that can be
3// found in the LICENSE file.
4
5#ifndef NET_BASE_DATA_URL_H_
6#define NET_BASE_DATA_URL_H_
7
8#include <string>
9
10#include "net/base/net_export.h"
11
12class GURL;
13
14namespace net {
15
16// See RFC 2397 for a complete description of the 'data' URL scheme.
17//
18// Briefly, a 'data' URL has the form:
19//
20//   data:[<mediatype>][;base64],<data>
21//
22// The <mediatype> is an Internet media type specification (with optional
23// parameters.)  The appearance of ";base64" means that the data is encoded as
24// base64.  Without ";base64", the data (as a sequence of octets) is represented
25// using ASCII encoding for octets inside the range of safe URL characters and
26// using the standard %xx hex encoding of URLs for octets outside that range.
27// If <mediatype> is omitted, it defaults to text/plain;charset=US-ASCII.  As a
28// shorthand, "text/plain" can be omitted but the charset parameter supplied.
29//
30class NET_EXPORT DataURL {
31 public:
32  // This method can be used to parse a 'data' URL into its component pieces.
33  //
34  // The resulting mime_type is normalized to lowercase.  The data is the
35  // decoded data (e.g.., if the data URL specifies base64 encoding, then the
36  // returned data is base64 decoded, and any %-escaped bytes are unescaped).
37  //
38  // If the media type value doesn't match the media-type production defined in
39  // RFC 7231, mime_type will be set to the default value "text/plain". We
40  // don't simply fail for this grammar violation since Chromium had been
41  // accepting such invalid values. For example, <img> element with the src
42  // attribute set to a data URL with an invalid media type "image" (without a
43  // slash and subtype) had been displayed. However, the value this method will
44  // store in mime_type argument can be used for generating other headers, etc.
45  // This could lead to security vulnerability. We don't want to accept
46  // arbitrary value and ask each caller to validate the return value.
47  //
48  // If the charset parameter is specified but its value doesn't match the
49  // token production defined in RFC 7230, this method simply fails and returns
50  // false.
51  //
52  // If there's any other grammar violation in the URL, then this method will
53  // return false. Output variables may be changed and contain invalid data. On
54  // success, true is returned.
55  //
56  // OPTIONAL: If |data| is NULL, then the <data> section will not be parsed
57  //           or validated.
58  //
59  static bool Parse(const GURL& url,
60                    std::string* mime_type,
61                    std::string* charset,
62                    std::string* data);
63};
64
65}  // namespace net
66
67#endif  // NET_BASE_DATA_URL_H_
68