net/base/escape.h

   1 // Copyright (c) 2012 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_ESCAPE_H_
   6 #define NET_BASE_ESCAPE_H_
   7
   8 #include <string>
   9 #include <vector>
  10
  11 #include "base/basictypes.h"
  12 #include "base/strings/string16.h"
  13 #include "base/strings/utf_offset_string_conversions.h"
  14 #include "net/base/net_export.h"
  15
  16 namespace net {
  17
  18 // Escaping --------------------------------------------------------------------
  19
  20 // Escapes characters in text suitable for use as a query parameter value.
  21 // We %XX everything except alphanumerics and -_.!~*'()
  22 // Spaces change to "+" unless you pass usePlus=false.
  23 // This is basically the same as encodeURIComponent in javascript.
  24 NET_EXPORT std::string EscapeQueryParamValue(const std::string& text,
  25                                              bool use_plus);
  26
  27 // Escapes a partial or complete file/pathname.  This includes:
  28 // non-printable, non-7bit, and (including space)  "#%:<>?[\]^`{|}
  29 // For the base::string16 version, we attempt a conversion to |codepage| before
  30 // encoding the string.  If this conversion fails, we return false.
  31 NET_EXPORT std::string EscapePath(const std::string& path);
  32
  33 #if defined(OS_MACOSX)
  34 // Escapes characters as per expectations of NSURL. This includes:
  35 // non-printable, non-7bit, and (including space)  "#%<>[\]^`{|}
  36 NET_EXPORT std::string EscapeNSURLPrecursor(const std::string& precursor);
  37 #endif  // defined(OS_MACOSX)
  38
  39 // Escapes application/x-www-form-urlencoded content.  This includes:
  40 // non-printable, non-7bit, and (including space)  ?>=<;+'&%$#"![\]^`{|}
  41 // Space is escaped as + (if use_plus is true) and other special characters
  42 // as %XX (hex).
  43 NET_EXPORT std::string EscapeUrlEncodedData(const std::string& path,
  44                                             bool use_plus);
  45
  46 // Escapes all non-ASCII input.
  47 NET_EXPORT std::string EscapeNonASCII(const std::string& input);
  48
  49 // Escapes characters in text suitable for use as an external protocol handler
  50 // command.
  51 // We %XX everything except alphanumerics and -_.!~*'() and the restricted
  52 // chracters (;/?:@&=+$,#[]) and a valid percent escape sequence (%XX).
  53 NET_EXPORT std::string EscapeExternalHandlerValue(const std::string& text);
  54
  55 // Appends the given character to the output string, escaping the character if
  56 // the character would be interpretted as an HTML delimiter.
  57 NET_EXPORT void AppendEscapedCharForHTML(char c, std::string* output);
  58
  59 // Escapes chars that might cause this text to be interpretted as HTML tags.
  60 NET_EXPORT std::string EscapeForHTML(const std::string& text);
  61 NET_EXPORT base::string16 EscapeForHTML(const base::string16& text);
  62
  63 // Unescaping ------------------------------------------------------------------
  64
  65 class UnescapeRule {
  66  public:
  67   // A combination of the following flags that is passed to the unescaping
  68   // functions.
  69   typedef uint32 Type;
  70
  71   enum {
  72     // Don't unescape anything at all.
  73     NONE = 0,
  74
  75     // Don't unescape anything special, but all normal unescaping will happen.
  76     // This is a placeholder and can't be combined with other flags (since it's
  77     // just the absence of them). All other unescape rules imply "normal" in
  78     // addition to their special meaning. Things like escaped letters, digits,
  79     // and most symbols will get unescaped with this mode.
  80     NORMAL = 1,
  81
  82     // Convert %20 to spaces. In some places where we're showing URLs, we may
  83     // want this. In places where the URL may be copied and pasted out, then
  84     // you wouldn't want this since it might not be interpreted in one piece
  85     // by other applications.
  86     SPACES = 2,
  87
  88     // Unescapes various characters that will change the meaning of URLs,
  89     // including '%', '+', '&', '/', '#'. If we unescaped these characters, the
  90     // resulting URL won't be the same as the source one. This flag is used when
  91     // generating final output like filenames for URLs where we won't be
  92     // interpreting as a URL and want to do as much unescaping as possible.
  93     URL_SPECIAL_CHARS = 4,
  94
  95     // Unescapes control characters such as %01. This INCLUDES NULLs. This is
  96     // used for rare cases such as data: URL decoding where the result is binary
  97     // data. This flag also unescapes BiDi control characters.
  98     //
  99     // DO NOT use CONTROL_CHARS if the URL is going to be displayed in the UI
 100     // for security reasons.
 101     CONTROL_CHARS = 8,
 102
 103     // URL queries use "+" for space. This flag controls that replacement.
 104     REPLACE_PLUS_WITH_SPACE = 16,
 105   };
 106 };
 107
 108 // Unescapes |escaped_text| and returns the result.
 109 // Unescaping consists of looking for the exact pattern "%XX", where each X is
 110 // a hex digit, and converting to the character with the numerical value of
 111 // those digits. Thus "i%20=%203%3b" unescapes to "i = 3;".
 112 //
 113 // Watch out: this doesn't necessarily result in the correct final result,
 114 // because the encoding may be unknown. For example, the input might be ASCII,
 115 // which, after unescaping, is supposed to be interpreted as UTF-8, and then
 116 // converted into full UTF-16 chars. This function won't tell you if any
 117 // conversions need to take place, it only unescapes.
 118 NET_EXPORT std::string UnescapeURLComponent(const std::string& escaped_text,
 119                                             UnescapeRule::Type rules);
 120 NET_EXPORT base::string16 UnescapeURLComponent(
 121     const base::string16& escaped_text,
 122     UnescapeRule::Type rules);
 123
 124 // Unescapes the given substring as a URL, and then tries to interpret the
 125 // result as being encoded as UTF-8. If the result is convertable into UTF-8, it
 126 // will be returned as converted. If it is not, the original escaped string will
 127 // be converted into a base::string16 and returned.  |adjustments| provides
 128 // information on how the original string was adjusted to get the string
 129 // returned.
 130 NET_EXPORT base::string16 UnescapeAndDecodeUTF8URLComponent(
 131     const std::string& text,
 132     UnescapeRule::Type rules);
 133 NET_EXPORT base::string16 UnescapeAndDecodeUTF8URLComponentWithAdjustments(
 134     const std::string& text,
 135     UnescapeRule::Type rules,
 136     base::OffsetAdjuster::Adjustments* adjustments);
 137
 138 // Unescapes the following ampersand character codes from |text|:
 139 // &lt; &gt; &amp; &quot; &#39;
 140 NET_EXPORT base::string16 UnescapeForHTML(const base::string16& text);
 141
 142 }  // namespace net
 143
 144 #endif  // NET_BASE_ESCAPE_H_