[388] | 1 | // Copyright (c) Microsoft. All rights reserved.
|
---|
| 2 | // Licensed under the MIT license. See LICENSE file in the project root for full license information.
|
---|
| 3 |
|
---|
| 4 | #include <stdlib.h>
|
---|
| 5 | #include <stddef.h>
|
---|
| 6 | #include <string.h>
|
---|
| 7 | #include "azure_c_shared_utility/gballoc.h"
|
---|
| 8 | #include "azure_c_shared_utility/urlencode.h"
|
---|
| 9 | #include "azure_c_shared_utility/xlogging.h"
|
---|
| 10 | #include "azure_c_shared_utility/strings.h"
|
---|
| 11 | #include "azure_c_shared_utility/crt_abstractions.h"
|
---|
| 12 |
|
---|
| 13 | #define NIBBLE_TO_STRING(c) (char)((c) < 10 ? (c) + '0' : (c) - 10 + 'a')
|
---|
| 14 | #define NIBBLE_FROM_STRING(c) (char)(ISDIGIT(c) ? (c) - '0' : TOUPPER(c) + 10 - 'A')
|
---|
| 15 | #define IS_HEXDIGIT(c) ( \
|
---|
| 16 | ((c >= '0') && (c <= '9')) || \
|
---|
| 17 | ((c >= 'A') && (c <= 'F')) || \
|
---|
| 18 | ((c >= 'a') && (c <= 'f')) \
|
---|
| 19 | )
|
---|
| 20 | #define IS_PRINTABLE(c) ( \
|
---|
| 21 | (c == 0) || \
|
---|
| 22 | (c == '!') || \
|
---|
| 23 | (c == '(') || (c == ')') || (c == '*') || \
|
---|
| 24 | (c == '-') || (c == '.') || \
|
---|
| 25 | ((c >= '0') && (c <= '9')) || \
|
---|
| 26 | ((c >= 'A') && (c <= 'Z')) || \
|
---|
| 27 | (c == '_') || \
|
---|
| 28 | ((c >= 'a') && (c <= 'z')) \
|
---|
| 29 | )
|
---|
| 30 |
|
---|
| 31 | /*The below macros are to be called on the big nibble of a hex value*/
|
---|
| 32 | #define IS_IN_ASCII_RANGE(c) ( \
|
---|
| 33 | (c >= '0') && (c <= '7') \
|
---|
| 34 | )
|
---|
| 35 | #define IS_IN_EXTENDED_ASCII_RANGE(c) ( \
|
---|
| 36 | ((c >= '8') && (c <= '9')) || \
|
---|
| 37 | ((c >= 'A') && (c <= 'F')) || \
|
---|
| 38 | ((c >= 'a') && (c <= 'f')) \
|
---|
| 39 | )
|
---|
| 40 | #define IS_IN_CONTINUATION_BYTE_RANGE(c) ( \
|
---|
| 41 | (c == '8') || (c == '9') || \
|
---|
| 42 | (c == 'A') || (c == 'B') || \
|
---|
| 43 | (c == 'a') || (c == 'b') \
|
---|
| 44 | )
|
---|
| 45 | #define IS_IN_LEADING_BYTE_RANGE(c) ( \
|
---|
| 46 | ((c >= 'C') && (c <= 'F')) || \
|
---|
| 47 | ((c >= 'c') && (c <= 'f')) \
|
---|
| 48 | )
|
---|
| 49 | #define IS_IN_UNSUPPORTED_LEADING_BYTE_RANGE(c) ( \
|
---|
| 50 | ((c >= 'D') && (c <= 'F')) || \
|
---|
| 51 | ((c >= 'd') && (c <= 'f')) \
|
---|
| 52 | )
|
---|
| 53 |
|
---|
| 54 | static size_t URL_PrintableChar(unsigned char charVal, char* buffer)
|
---|
| 55 | {
|
---|
| 56 | size_t size;
|
---|
| 57 | if (IS_PRINTABLE(charVal))
|
---|
| 58 | {
|
---|
| 59 | buffer[0] = (char)charVal;
|
---|
| 60 | size = 1;
|
---|
| 61 | }
|
---|
| 62 | else
|
---|
| 63 | {
|
---|
| 64 | char bigNibbleStr;
|
---|
| 65 | char littleNibbleStr;
|
---|
| 66 | unsigned char bigNibbleVal = charVal >> 4;
|
---|
| 67 | unsigned char littleNibbleVal = charVal & 0x0F;
|
---|
| 68 |
|
---|
| 69 | if (bigNibbleVal >= 0x0C)
|
---|
| 70 | {
|
---|
| 71 | bigNibbleVal -= 0x04;
|
---|
| 72 | }
|
---|
| 73 |
|
---|
| 74 | bigNibbleStr = NIBBLE_TO_STRING(bigNibbleVal);
|
---|
| 75 | littleNibbleStr = NIBBLE_TO_STRING(littleNibbleVal);
|
---|
| 76 |
|
---|
| 77 | buffer[0] = '%';
|
---|
| 78 |
|
---|
| 79 | if (charVal < 0x80)
|
---|
| 80 | {
|
---|
| 81 | buffer[1] = bigNibbleStr;
|
---|
| 82 | buffer[2] = littleNibbleStr;
|
---|
| 83 | size = 3;
|
---|
| 84 | }
|
---|
| 85 | else
|
---|
| 86 | {
|
---|
| 87 | buffer[1] = 'c';
|
---|
| 88 | buffer[3] = '%';
|
---|
| 89 | buffer[4] = bigNibbleStr;
|
---|
| 90 | buffer[5] = littleNibbleStr;
|
---|
| 91 | if (charVal < 0xC0)
|
---|
| 92 | {
|
---|
| 93 | buffer[2] = '2';
|
---|
| 94 | }
|
---|
| 95 | else
|
---|
| 96 | {
|
---|
| 97 | buffer[2] = '3';
|
---|
| 98 | }
|
---|
| 99 | size = 6;
|
---|
| 100 | }
|
---|
| 101 | }
|
---|
| 102 |
|
---|
| 103 | return size;
|
---|
| 104 | }
|
---|
| 105 |
|
---|
| 106 | static size_t calculateDecodedStringSize(const char* encodedString, size_t len)
|
---|
| 107 | {
|
---|
| 108 | size_t decodedSize = 0;
|
---|
| 109 |
|
---|
| 110 | if (encodedString == NULL)
|
---|
| 111 | {
|
---|
| 112 | LogError("Null encoded string");
|
---|
| 113 | }
|
---|
| 114 | else if (len == 0)
|
---|
| 115 | {
|
---|
| 116 | decodedSize = 1; //for null terminator
|
---|
| 117 | }
|
---|
| 118 | else
|
---|
| 119 | {
|
---|
| 120 | size_t remaining_len = len;
|
---|
| 121 | size_t next_step = 0;
|
---|
| 122 | size_t i = 0;
|
---|
| 123 | while (i < len)
|
---|
| 124 | {
|
---|
| 125 | //percent encoded character
|
---|
| 126 | if (encodedString[i] == '%')
|
---|
| 127 | {
|
---|
| 128 | if (remaining_len < 3 || !IS_HEXDIGIT(encodedString[i+1]) || !IS_HEXDIGIT(encodedString[i+2]))
|
---|
| 129 | {
|
---|
| 130 | LogError("Incomplete or invalid percent encoding");
|
---|
| 131 | break;
|
---|
| 132 | }
|
---|
| 133 | else if (!IS_IN_ASCII_RANGE(encodedString[i+1]))
|
---|
| 134 | {
|
---|
| 135 | LogError("Out of range of characters accepted by this decoder");
|
---|
| 136 | break;
|
---|
| 137 | }
|
---|
| 138 | else
|
---|
| 139 | {
|
---|
| 140 | decodedSize++;
|
---|
| 141 | next_step = 3;
|
---|
| 142 | }
|
---|
| 143 | }
|
---|
| 144 | else if (!IS_PRINTABLE(encodedString[i]))
|
---|
| 145 | {
|
---|
| 146 | LogError("Unprintable value in encoded string");
|
---|
| 147 | break;
|
---|
| 148 | }
|
---|
| 149 | //safe character
|
---|
| 150 | else
|
---|
| 151 | {
|
---|
| 152 | decodedSize++;
|
---|
| 153 | next_step = 1;
|
---|
| 154 | }
|
---|
| 155 |
|
---|
| 156 | i += next_step;
|
---|
| 157 | remaining_len -= next_step;
|
---|
| 158 | }
|
---|
| 159 |
|
---|
| 160 | if (encodedString[i] != '\0') //i.e. broke out of above loop due to error
|
---|
| 161 | {
|
---|
| 162 | decodedSize = 0;
|
---|
| 163 | }
|
---|
| 164 | else
|
---|
| 165 | {
|
---|
| 166 | decodedSize++; //add space for the null terminator
|
---|
| 167 | }
|
---|
| 168 | }
|
---|
| 169 | return decodedSize;
|
---|
| 170 | }
|
---|
| 171 |
|
---|
| 172 | static unsigned char charFromNibbles(char bigNibbleStr, char littleNibbleStr)
|
---|
| 173 | {
|
---|
| 174 | unsigned char bigNibbleVal = NIBBLE_FROM_STRING(bigNibbleStr);
|
---|
| 175 | unsigned char littleNibbleVal = NIBBLE_FROM_STRING(littleNibbleStr);
|
---|
| 176 |
|
---|
| 177 | return bigNibbleVal << 4 | littleNibbleVal;
|
---|
| 178 | }
|
---|
| 179 |
|
---|
| 180 | static void createDecodedString(const char* input, size_t input_size, char* output)
|
---|
| 181 | {
|
---|
| 182 | /* Note that there is no danger of reckless indexing here, as calculateDecodedStringSize()
|
---|
| 183 | has already checked lengths of strings to ensure the formatting is always correct*/
|
---|
| 184 | size_t i = 0;
|
---|
| 185 | while (i <= input_size) //the <= instead of < ensures the '\0' will be copied
|
---|
| 186 | {
|
---|
| 187 | if (input[i] != '%')
|
---|
| 188 | {
|
---|
| 189 | *output++ = input[i];
|
---|
| 190 | i++;
|
---|
| 191 | }
|
---|
| 192 | else
|
---|
| 193 | {
|
---|
| 194 | *output++ = charFromNibbles(input[i+1], input[i+2]);
|
---|
| 195 | i += 3;
|
---|
| 196 | }
|
---|
| 197 | }
|
---|
| 198 | }
|
---|
| 199 |
|
---|
| 200 | static size_t URL_PrintableCharSize(unsigned char charVal)
|
---|
| 201 | {
|
---|
| 202 | size_t size;
|
---|
| 203 | if (IS_PRINTABLE(charVal))
|
---|
| 204 | {
|
---|
| 205 | size = 1;
|
---|
| 206 | }
|
---|
| 207 | else
|
---|
| 208 | {
|
---|
| 209 | if (charVal < 0x80)
|
---|
| 210 | {
|
---|
| 211 | size = 3;
|
---|
| 212 | }
|
---|
| 213 | else
|
---|
| 214 | {
|
---|
| 215 | size = 6;
|
---|
| 216 | }
|
---|
| 217 | }
|
---|
| 218 | return size;
|
---|
| 219 | }
|
---|
| 220 |
|
---|
| 221 | static STRING_HANDLE encode_url_data(const char* text)
|
---|
| 222 | {
|
---|
| 223 | STRING_HANDLE result;
|
---|
| 224 | size_t lengthOfResult = 0;
|
---|
| 225 | char* encodedURL;
|
---|
| 226 | unsigned char currentUnsignedChar;
|
---|
| 227 | const char* iterator = text;
|
---|
| 228 |
|
---|
| 229 | /*Codes_SRS_URL_ENCODE_06_003: [If input is a zero length string then URL_Encode will return a zero length string.]*/
|
---|
| 230 | do
|
---|
| 231 | {
|
---|
| 232 | currentUnsignedChar = (unsigned char)(*iterator++);
|
---|
| 233 | lengthOfResult += URL_PrintableCharSize(currentUnsignedChar);
|
---|
| 234 | } while (currentUnsignedChar != 0);
|
---|
| 235 |
|
---|
| 236 | if ((encodedURL = (char*)malloc(lengthOfResult)) == NULL)
|
---|
| 237 | {
|
---|
| 238 | /*Codes_SRS_URL_ENCODE_06_002: [If an error occurs during the encoding of input then URL_Encode will return NULL.]*/
|
---|
| 239 | result = NULL;
|
---|
| 240 | LogError("URL_Encode:: MALLOC failure on encode.");
|
---|
| 241 | }
|
---|
| 242 | else
|
---|
| 243 | {
|
---|
| 244 | size_t currentEncodePosition = 0;
|
---|
| 245 | iterator = text;;
|
---|
| 246 | do
|
---|
| 247 | {
|
---|
| 248 | currentUnsignedChar = (unsigned char)(*iterator++);
|
---|
| 249 | currentEncodePosition += URL_PrintableChar(currentUnsignedChar, &encodedURL[currentEncodePosition]);
|
---|
| 250 | } while (currentUnsignedChar != 0);
|
---|
| 251 |
|
---|
| 252 | result = STRING_new_with_memory(encodedURL);
|
---|
| 253 | if (result == NULL)
|
---|
| 254 | {
|
---|
| 255 | LogError("URL_Encode:: MALLOC failure on encode.");
|
---|
| 256 | free(encodedURL);
|
---|
| 257 | }
|
---|
| 258 | }
|
---|
| 259 | return result;
|
---|
| 260 | }
|
---|
| 261 |
|
---|
| 262 | STRING_HANDLE URL_EncodeString(const char* textEncode)
|
---|
| 263 | {
|
---|
| 264 | STRING_HANDLE result;
|
---|
| 265 | if (textEncode == NULL)
|
---|
| 266 | {
|
---|
| 267 | result = NULL;
|
---|
| 268 | }
|
---|
| 269 | else
|
---|
| 270 | {
|
---|
| 271 | result = encode_url_data(textEncode);
|
---|
| 272 | }
|
---|
| 273 | return result;
|
---|
| 274 | }
|
---|
| 275 |
|
---|
| 276 | STRING_HANDLE URL_Encode(STRING_HANDLE input)
|
---|
| 277 | {
|
---|
| 278 | STRING_HANDLE result;
|
---|
| 279 | if (input == NULL)
|
---|
| 280 | {
|
---|
| 281 | /*Codes_SRS_URL_ENCODE_06_001: [If input is NULL then URL_Encode will return NULL.]*/
|
---|
| 282 | result = NULL;
|
---|
| 283 | LogError("URL_Encode:: NULL input");
|
---|
| 284 | }
|
---|
| 285 | else
|
---|
| 286 | {
|
---|
| 287 | result = encode_url_data(STRING_c_str(input));
|
---|
| 288 | }
|
---|
| 289 | return result;
|
---|
| 290 | }
|
---|
| 291 |
|
---|
| 292 | STRING_HANDLE URL_DecodeString(const char* textDecode)
|
---|
| 293 | {
|
---|
| 294 | STRING_HANDLE result;
|
---|
| 295 | if (textDecode == NULL)
|
---|
| 296 | {
|
---|
| 297 | result = NULL;
|
---|
| 298 | }
|
---|
| 299 | else
|
---|
| 300 | {
|
---|
| 301 | STRING_HANDLE tempString = STRING_construct(textDecode);
|
---|
| 302 | if (tempString == NULL)
|
---|
| 303 | {
|
---|
| 304 | result = NULL;
|
---|
| 305 | }
|
---|
| 306 | else
|
---|
| 307 | {
|
---|
| 308 | result = URL_Decode(tempString);
|
---|
| 309 | STRING_delete(tempString);
|
---|
| 310 | }
|
---|
| 311 | }
|
---|
| 312 | return result;
|
---|
| 313 | }
|
---|
| 314 |
|
---|
| 315 | STRING_HANDLE URL_Decode(STRING_HANDLE input)
|
---|
| 316 | {
|
---|
| 317 | STRING_HANDLE result;
|
---|
| 318 | if (input == NULL)
|
---|
| 319 | {
|
---|
| 320 | LogError("URL_Decode:: NULL input");
|
---|
| 321 | result = NULL;
|
---|
| 322 | }
|
---|
| 323 | else
|
---|
| 324 | {
|
---|
| 325 | size_t decodedStringSize;
|
---|
| 326 | char* decodedString;
|
---|
| 327 | const char* inputString = STRING_c_str(input);
|
---|
| 328 | size_t inputLen = strlen(inputString);
|
---|
| 329 | if ((decodedStringSize = calculateDecodedStringSize(inputString, inputLen)) == 0)
|
---|
| 330 | {
|
---|
| 331 | LogError("URL_Decode:: Invalid input string");
|
---|
| 332 | result = NULL;
|
---|
| 333 | }
|
---|
| 334 | else if ((decodedString = (char*)malloc(decodedStringSize)) == NULL)
|
---|
| 335 | {
|
---|
| 336 | LogError("URL_Decode:: MALLOC failure on decode.");
|
---|
| 337 | result = NULL;
|
---|
| 338 | }
|
---|
| 339 | else
|
---|
| 340 | {
|
---|
| 341 | createDecodedString(inputString, inputLen, decodedString);
|
---|
| 342 | result = STRING_new_with_memory(decodedString);
|
---|
| 343 | if (result == NULL)
|
---|
| 344 | {
|
---|
| 345 | LogError("URL_Decode:: MALLOC failure on decode");
|
---|
| 346 | free(decodedString);
|
---|
| 347 | }
|
---|
| 348 | }
|
---|
| 349 | }
|
---|
| 350 | return result;
|
---|
| 351 | }
|
---|