henrike@webrtc.org | f7795df | 2014-05-13 18:00:26 +0000 | [diff] [blame^] | 1 | /* |
| 2 | * Copyright 2008 The WebRTC Project Authors. All rights reserved. |
| 3 | * |
| 4 | * Use of this source code is governed by a BSD-style license |
| 5 | * that can be found in the LICENSE file in the root of the source |
| 6 | * tree. An additional intellectual property rights grant can be found |
| 7 | * in the file PATENTS. All contributing project authors may |
| 8 | * be found in the AUTHORS file in the root of the source tree. |
| 9 | */ |
| 10 | |
| 11 | #include "webrtc/base/urlencode.h" |
| 12 | |
| 13 | #include "webrtc/base/common.h" |
| 14 | #include "webrtc/base/stringutils.h" |
| 15 | |
| 16 | static int HexPairValue(const char * code) { |
| 17 | int value = 0; |
| 18 | const char * pch = code; |
| 19 | for (;;) { |
| 20 | int digit = *pch++; |
| 21 | if (digit >= '0' && digit <= '9') { |
| 22 | value += digit - '0'; |
| 23 | } |
| 24 | else if (digit >= 'A' && digit <= 'F') { |
| 25 | value += digit - 'A' + 10; |
| 26 | } |
| 27 | else if (digit >= 'a' && digit <= 'f') { |
| 28 | value += digit - 'a' + 10; |
| 29 | } |
| 30 | else { |
| 31 | return -1; |
| 32 | } |
| 33 | if (pch == code + 2) |
| 34 | return value; |
| 35 | value <<= 4; |
| 36 | } |
| 37 | } |
| 38 | |
| 39 | int InternalUrlDecode(const char *source, char *dest, |
| 40 | bool encode_space_as_plus) { |
| 41 | char * start = dest; |
| 42 | |
| 43 | while (*source) { |
| 44 | switch (*source) { |
| 45 | case '+': |
| 46 | if (encode_space_as_plus) { |
| 47 | *(dest++) = ' '; |
| 48 | } else { |
| 49 | *dest++ = *source; |
| 50 | } |
| 51 | break; |
| 52 | case '%': |
| 53 | if (source[1] && source[2]) { |
| 54 | int value = HexPairValue(source + 1); |
| 55 | if (value >= 0) { |
| 56 | *(dest++) = value; |
| 57 | source += 2; |
| 58 | } |
| 59 | else { |
| 60 | *dest++ = '?'; |
| 61 | } |
| 62 | } |
| 63 | else { |
| 64 | *dest++ = '?'; |
| 65 | } |
| 66 | break; |
| 67 | default: |
| 68 | *dest++ = *source; |
| 69 | } |
| 70 | source++; |
| 71 | } |
| 72 | |
| 73 | *dest = 0; |
| 74 | return static_cast<int>(dest - start); |
| 75 | } |
| 76 | |
| 77 | int UrlDecode(const char *source, char *dest) { |
| 78 | return InternalUrlDecode(source, dest, true); |
| 79 | } |
| 80 | |
| 81 | int UrlDecodeWithoutEncodingSpaceAsPlus(const char *source, char *dest) { |
| 82 | return InternalUrlDecode(source, dest, false); |
| 83 | } |
| 84 | |
| 85 | bool IsValidUrlChar(char ch, bool unsafe_only) { |
| 86 | if (unsafe_only) { |
| 87 | return !(ch <= ' ' || strchr("\\\"^&`<>[]{}", ch)); |
| 88 | } else { |
| 89 | return isalnum(ch) || strchr("-_.!~*'()", ch); |
| 90 | } |
| 91 | } |
| 92 | |
| 93 | int InternalUrlEncode(const char *source, char *dest, unsigned int max, |
| 94 | bool encode_space_as_plus, bool unsafe_only) { |
| 95 | static const char *digits = "0123456789ABCDEF"; |
| 96 | if (max == 0) { |
| 97 | return 0; |
| 98 | } |
| 99 | |
| 100 | char *start = dest; |
| 101 | while (static_cast<unsigned>(dest - start) < max && *source) { |
| 102 | unsigned char ch = static_cast<unsigned char>(*source); |
| 103 | if (*source == ' ' && encode_space_as_plus && !unsafe_only) { |
| 104 | *dest++ = '+'; |
| 105 | } else if (IsValidUrlChar(ch, unsafe_only)) { |
| 106 | *dest++ = *source; |
| 107 | } else { |
| 108 | if (static_cast<unsigned>(dest - start) + 4 > max) { |
| 109 | break; |
| 110 | } |
| 111 | *dest++ = '%'; |
| 112 | *dest++ = digits[(ch >> 4) & 0x0F]; |
| 113 | *dest++ = digits[ ch & 0x0F]; |
| 114 | } |
| 115 | source++; |
| 116 | } |
| 117 | ASSERT(static_cast<unsigned int>(dest - start) < max); |
| 118 | *dest = 0; |
| 119 | |
| 120 | return static_cast<int>(dest - start); |
| 121 | } |
| 122 | |
| 123 | int UrlEncode(const char *source, char *dest, unsigned max) { |
| 124 | return InternalUrlEncode(source, dest, max, true, false); |
| 125 | } |
| 126 | |
| 127 | int UrlEncodeWithoutEncodingSpaceAsPlus(const char *source, char *dest, |
| 128 | unsigned max) { |
| 129 | return InternalUrlEncode(source, dest, max, false, false); |
| 130 | } |
| 131 | |
| 132 | int UrlEncodeOnlyUnsafeChars(const char *source, char *dest, unsigned max) { |
| 133 | return InternalUrlEncode(source, dest, max, false, true); |
| 134 | } |
| 135 | |
| 136 | std::string |
| 137 | InternalUrlDecodeString(const std::string & encoded, |
| 138 | bool encode_space_as_plus) { |
| 139 | size_t needed_length = encoded.length() + 1; |
| 140 | char* buf = STACK_ARRAY(char, needed_length); |
| 141 | InternalUrlDecode(encoded.c_str(), buf, encode_space_as_plus); |
| 142 | return buf; |
| 143 | } |
| 144 | |
| 145 | std::string |
| 146 | UrlDecodeString(const std::string & encoded) { |
| 147 | return InternalUrlDecodeString(encoded, true); |
| 148 | } |
| 149 | |
| 150 | std::string |
| 151 | UrlDecodeStringWithoutEncodingSpaceAsPlus(const std::string & encoded) { |
| 152 | return InternalUrlDecodeString(encoded, false); |
| 153 | } |
| 154 | |
| 155 | std::string |
| 156 | InternalUrlEncodeString(const std::string & decoded, |
| 157 | bool encode_space_as_plus, |
| 158 | bool unsafe_only) { |
| 159 | int needed_length = static_cast<int>(decoded.length()) * 3 + 1; |
| 160 | char* buf = STACK_ARRAY(char, needed_length); |
| 161 | InternalUrlEncode(decoded.c_str(), buf, needed_length, |
| 162 | encode_space_as_plus, unsafe_only); |
| 163 | return buf; |
| 164 | } |
| 165 | |
| 166 | std::string |
| 167 | UrlEncodeString(const std::string & decoded) { |
| 168 | return InternalUrlEncodeString(decoded, true, false); |
| 169 | } |
| 170 | |
| 171 | std::string |
| 172 | UrlEncodeStringWithoutEncodingSpaceAsPlus(const std::string & decoded) { |
| 173 | return InternalUrlEncodeString(decoded, false, false); |
| 174 | } |
| 175 | |
| 176 | std::string |
| 177 | UrlEncodeStringForOnlyUnsafeChars(const std::string & decoded) { |
| 178 | return InternalUrlEncodeString(decoded, false, true); |
| 179 | } |