henrike@webrtc.org | 0e118e7 | 2013-07-10 00:45:36 +0000 | [diff] [blame] | 1 | /* |
| 2 | * libjingle |
| 3 | * Copyright 2008, Google Inc. |
| 4 | * |
| 5 | * Redistribution and use in source and binary forms, with or without |
| 6 | * modification, are permitted provided that the following conditions are met: |
| 7 | * |
| 8 | * 1. Redistributions of source code must retain the above copyright notice, |
| 9 | * this list of conditions and the following disclaimer. |
| 10 | * 2. Redistributions in binary form must reproduce the above copyright notice, |
| 11 | * this list of conditions and the following disclaimer in the documentation |
| 12 | * and/or other materials provided with the distribution. |
| 13 | * 3. The name of the author may not be used to endorse or promote products |
| 14 | * derived from this software without specific prior written permission. |
| 15 | * |
| 16 | * THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED |
| 17 | * WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF |
| 18 | * MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO |
| 19 | * EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, |
| 20 | * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, |
| 21 | * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; |
| 22 | * OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, |
| 23 | * WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR |
| 24 | * OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF |
| 25 | * ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. |
| 26 | */ |
| 27 | |
| 28 | #include "talk/base/urlencode.h" |
| 29 | |
| 30 | #include "talk/base/common.h" |
| 31 | #include "talk/base/stringutils.h" |
| 32 | |
| 33 | static int HexPairValue(const char * code) { |
| 34 | int value = 0; |
| 35 | const char * pch = code; |
| 36 | for (;;) { |
| 37 | int digit = *pch++; |
| 38 | if (digit >= '0' && digit <= '9') { |
| 39 | value += digit - '0'; |
| 40 | } |
| 41 | else if (digit >= 'A' && digit <= 'F') { |
| 42 | value += digit - 'A' + 10; |
| 43 | } |
| 44 | else if (digit >= 'a' && digit <= 'f') { |
| 45 | value += digit - 'a' + 10; |
| 46 | } |
| 47 | else { |
| 48 | return -1; |
| 49 | } |
| 50 | if (pch == code + 2) |
| 51 | return value; |
| 52 | value <<= 4; |
| 53 | } |
| 54 | } |
| 55 | |
| 56 | int InternalUrlDecode(const char *source, char *dest, |
| 57 | bool encode_space_as_plus) { |
| 58 | char * start = dest; |
| 59 | |
| 60 | while (*source) { |
| 61 | switch (*source) { |
| 62 | case '+': |
| 63 | if (encode_space_as_plus) { |
| 64 | *(dest++) = ' '; |
| 65 | } else { |
| 66 | *dest++ = *source; |
| 67 | } |
| 68 | break; |
| 69 | case '%': |
| 70 | if (source[1] && source[2]) { |
| 71 | int value = HexPairValue(source + 1); |
| 72 | if (value >= 0) { |
| 73 | *(dest++) = value; |
| 74 | source += 2; |
| 75 | } |
| 76 | else { |
| 77 | *dest++ = '?'; |
| 78 | } |
| 79 | } |
| 80 | else { |
| 81 | *dest++ = '?'; |
| 82 | } |
| 83 | break; |
| 84 | default: |
| 85 | *dest++ = *source; |
| 86 | } |
| 87 | source++; |
| 88 | } |
| 89 | |
| 90 | *dest = 0; |
| 91 | return static_cast<int>(dest - start); |
| 92 | } |
| 93 | |
| 94 | int UrlDecode(const char *source, char *dest) { |
| 95 | return InternalUrlDecode(source, dest, true); |
| 96 | } |
| 97 | |
| 98 | int UrlDecodeWithoutEncodingSpaceAsPlus(const char *source, char *dest) { |
| 99 | return InternalUrlDecode(source, dest, false); |
| 100 | } |
| 101 | |
| 102 | bool IsValidUrlChar(char ch, bool unsafe_only) { |
| 103 | if (unsafe_only) { |
| 104 | return !(ch <= ' ' || strchr("\\\"^&`<>[]{}", ch)); |
| 105 | } else { |
| 106 | return isalnum(ch) || strchr("-_.!~*'()", ch); |
| 107 | } |
| 108 | } |
| 109 | |
| 110 | int InternalUrlEncode(const char *source, char *dest, unsigned int max, |
| 111 | bool encode_space_as_plus, bool unsafe_only) { |
| 112 | static const char *digits = "0123456789ABCDEF"; |
| 113 | if (max == 0) { |
| 114 | return 0; |
| 115 | } |
| 116 | |
| 117 | char *start = dest; |
| 118 | while (static_cast<unsigned>(dest - start) < max && *source) { |
| 119 | unsigned char ch = static_cast<unsigned char>(*source); |
| 120 | if (*source == ' ' && encode_space_as_plus && !unsafe_only) { |
| 121 | *dest++ = '+'; |
| 122 | } else if (IsValidUrlChar(ch, unsafe_only)) { |
| 123 | *dest++ = *source; |
| 124 | } else { |
| 125 | if (static_cast<unsigned>(dest - start) + 4 > max) { |
| 126 | break; |
| 127 | } |
| 128 | *dest++ = '%'; |
| 129 | *dest++ = digits[(ch >> 4) & 0x0F]; |
| 130 | *dest++ = digits[ ch & 0x0F]; |
| 131 | } |
| 132 | source++; |
| 133 | } |
| 134 | ASSERT(static_cast<unsigned int>(dest - start) < max); |
| 135 | *dest = 0; |
| 136 | |
| 137 | return static_cast<int>(dest - start); |
| 138 | } |
| 139 | |
| 140 | int UrlEncode(const char *source, char *dest, unsigned max) { |
| 141 | return InternalUrlEncode(source, dest, max, true, false); |
| 142 | } |
| 143 | |
| 144 | int UrlEncodeWithoutEncodingSpaceAsPlus(const char *source, char *dest, |
| 145 | unsigned max) { |
| 146 | return InternalUrlEncode(source, dest, max, false, false); |
| 147 | } |
| 148 | |
| 149 | int UrlEncodeOnlyUnsafeChars(const char *source, char *dest, unsigned max) { |
| 150 | return InternalUrlEncode(source, dest, max, false, true); |
| 151 | } |
| 152 | |
| 153 | std::string |
| 154 | InternalUrlDecodeString(const std::string & encoded, |
| 155 | bool encode_space_as_plus) { |
| 156 | size_t needed_length = encoded.length() + 1; |
| 157 | char* buf = STACK_ARRAY(char, needed_length); |
| 158 | InternalUrlDecode(encoded.c_str(), buf, encode_space_as_plus); |
| 159 | return buf; |
| 160 | } |
| 161 | |
| 162 | std::string |
| 163 | UrlDecodeString(const std::string & encoded) { |
| 164 | return InternalUrlDecodeString(encoded, true); |
| 165 | } |
| 166 | |
| 167 | std::string |
| 168 | UrlDecodeStringWithoutEncodingSpaceAsPlus(const std::string & encoded) { |
| 169 | return InternalUrlDecodeString(encoded, false); |
| 170 | } |
| 171 | |
| 172 | std::string |
| 173 | InternalUrlEncodeString(const std::string & decoded, |
| 174 | bool encode_space_as_plus, |
| 175 | bool unsafe_only) { |
| 176 | int needed_length = static_cast<int>(decoded.length()) * 3 + 1; |
| 177 | char* buf = STACK_ARRAY(char, needed_length); |
| 178 | InternalUrlEncode(decoded.c_str(), buf, needed_length, |
| 179 | encode_space_as_plus, unsafe_only); |
| 180 | return buf; |
| 181 | } |
| 182 | |
| 183 | std::string |
| 184 | UrlEncodeString(const std::string & decoded) { |
| 185 | return InternalUrlEncodeString(decoded, true, false); |
| 186 | } |
| 187 | |
| 188 | std::string |
| 189 | UrlEncodeStringWithoutEncodingSpaceAsPlus(const std::string & decoded) { |
| 190 | return InternalUrlEncodeString(decoded, false, false); |
| 191 | } |
| 192 | |
| 193 | std::string |
| 194 | UrlEncodeStringForOnlyUnsafeChars(const std::string & decoded) { |
| 195 | return InternalUrlEncodeString(decoded, false, true); |
| 196 | } |