| 1 | /* Copyright (C) 2010-2020 The RetroArch team |
| 2 | * |
| 3 | * --------------------------------------------------------------------------------------- |
| 4 | * The following license statement only applies to this file (stdstring.c). |
| 5 | * --------------------------------------------------------------------------------------- |
| 6 | * |
| 7 | * Permission is hereby granted, free of charge, |
| 8 | * to any person obtaining a copy of this software and associated documentation files (the "Software"), |
| 9 | * to deal in the Software without restriction, including without limitation the rights to |
| 10 | * use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, |
| 11 | * and to permit persons to whom the Software is furnished to do so, subject to the following conditions: |
| 12 | * |
| 13 | * The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software. |
| 14 | * |
| 15 | * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, |
| 16 | * INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, |
| 17 | * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. |
| 18 | * IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, |
| 19 | * WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, |
| 20 | * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE. |
| 21 | */ |
| 22 | |
| 23 | #include <stdint.h> |
| 24 | #include <ctype.h> |
| 25 | |
| 26 | #include <string/stdstring.h> |
| 27 | #include <encodings/utf.h> |
| 28 | |
| 29 | const uint8_t lr_char_props[256] = { |
| 30 | /*x0 x1 x2 x3 x4 x5 x6 x7 x8 x9 xA xB xC xD xE xF */ |
| 31 | 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80,0x80,0x00,0x00,0x80,0x00,0x00, /* 0x */ |
| 32 | 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 1x */ |
| 33 | 0x80,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 2x !"#$%&'()*+,-./ */ |
| 34 | 0x41,0x41,0x41,0x41,0x41,0x41,0x41,0x41,0x41,0x41,0x00,0x00,0x00,0x00,0x00,0x00, /* 3x 0123456789:;<=>? */ |
| 35 | 0x00,0x23,0x23,0x23,0x23,0x23,0x23,0x22,0x22,0x22,0x22,0x22,0x22,0x22,0x22,0x22, /* 4x @ABCDEFGHIJKLMNO */ |
| 36 | 0x22,0x22,0x22,0x22,0x22,0x22,0x22,0x22,0x22,0x22,0x22,0x00,0x00,0x00,0x00,0x08, /* 5x PQRSTUVWXYZ[\]^_ */ |
| 37 | 0x00,0x25,0x25,0x25,0x25,0x25,0x25,0x24,0x24,0x24,0x24,0x24,0x24,0x24,0x24,0x24, /* 6x `abcdefghijklmno */ |
| 38 | 0x24,0x24,0x24,0x24,0x24,0x24,0x24,0x24,0x24,0x24,0x24,0x00,0x00,0x00,0x00,0x00, /* 7x pqrstuvwxyz{|}~ */ |
| 39 | 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 8x */ |
| 40 | 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* 9x */ |
| 41 | 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Ax */ |
| 42 | 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Bx */ |
| 43 | 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Cx */ |
| 44 | 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Dx */ |
| 45 | 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Ex */ |
| 46 | 0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00, /* Fx */ |
| 47 | }; |
| 48 | |
| 49 | char *string_init(const char *src) |
| 50 | { |
| 51 | return src ? strdup(src) : NULL; |
| 52 | } |
| 53 | |
| 54 | void string_set(char **string, const char *src) |
| 55 | { |
| 56 | free(*string); |
| 57 | *string = string_init(src); |
| 58 | } |
| 59 | |
| 60 | |
| 61 | char *string_to_upper(char *s) |
| 62 | { |
| 63 | char *cs = (char *)s; |
| 64 | for ( ; *cs != '\0'; cs++) |
| 65 | *cs = toupper((unsigned char)*cs); |
| 66 | return s; |
| 67 | } |
| 68 | |
| 69 | char *string_to_lower(char *s) |
| 70 | { |
| 71 | char *cs = (char *)s; |
| 72 | for ( ; *cs != '\0'; cs++) |
| 73 | *cs = tolower((unsigned char)*cs); |
| 74 | return s; |
| 75 | } |
| 76 | |
| 77 | char *string_ucwords(char *s) |
| 78 | { |
| 79 | char *cs = (char *)s; |
| 80 | for ( ; *cs != '\0'; cs++) |
| 81 | { |
| 82 | if (*cs == ' ') |
| 83 | *(cs+1) = toupper((unsigned char)*(cs+1)); |
| 84 | } |
| 85 | |
| 86 | s[0] = toupper((unsigned char)s[0]); |
| 87 | return s; |
| 88 | } |
| 89 | |
| 90 | char *string_replace_substring(const char *in, |
| 91 | const char *pattern, const char *replacement) |
| 92 | { |
| 93 | size_t numhits, pattern_len, replacement_len, outlen; |
| 94 | const char *inat = NULL; |
| 95 | const char *inprev = NULL; |
| 96 | char *out = NULL; |
| 97 | char *outat = NULL; |
| 98 | |
| 99 | /* if either pattern or replacement is NULL, |
| 100 | * duplicate in and let caller handle it. */ |
| 101 | if (!pattern || !replacement) |
| 102 | return strdup(in); |
| 103 | |
| 104 | pattern_len = strlen(pattern); |
| 105 | replacement_len = strlen(replacement); |
| 106 | numhits = 0; |
| 107 | inat = in; |
| 108 | |
| 109 | while ((inat = strstr(inat, pattern))) |
| 110 | { |
| 111 | inat += pattern_len; |
| 112 | numhits++; |
| 113 | } |
| 114 | |
| 115 | outlen = strlen(in) - pattern_len*numhits + replacement_len*numhits; |
| 116 | out = (char *)malloc(outlen+1); |
| 117 | |
| 118 | if (!out) |
| 119 | return NULL; |
| 120 | |
| 121 | outat = out; |
| 122 | inat = in; |
| 123 | inprev = in; |
| 124 | |
| 125 | while ((inat = strstr(inat, pattern))) |
| 126 | { |
| 127 | memcpy(outat, inprev, inat-inprev); |
| 128 | outat += inat-inprev; |
| 129 | memcpy(outat, replacement, replacement_len); |
| 130 | outat += replacement_len; |
| 131 | inat += pattern_len; |
| 132 | inprev = inat; |
| 133 | } |
| 134 | strcpy(outat, inprev); |
| 135 | |
| 136 | return out; |
| 137 | } |
| 138 | |
| 139 | /* Remove leading whitespaces */ |
| 140 | char *string_trim_whitespace_left(char *const s) |
| 141 | { |
| 142 | if (s && *s) |
| 143 | { |
| 144 | size_t len = strlen(s); |
| 145 | char *current = s; |
| 146 | |
| 147 | while (*current && ISSPACE((unsigned char)*current)) |
| 148 | { |
| 149 | ++current; |
| 150 | --len; |
| 151 | } |
| 152 | |
| 153 | if (s != current) |
| 154 | memmove(s, current, len + 1); |
| 155 | } |
| 156 | |
| 157 | return s; |
| 158 | } |
| 159 | |
| 160 | /* Remove trailing whitespaces */ |
| 161 | char *string_trim_whitespace_right(char *const s) |
| 162 | { |
| 163 | if (s && *s) |
| 164 | { |
| 165 | size_t len = strlen(s); |
| 166 | char *current = s + len - 1; |
| 167 | |
| 168 | while (current != s && ISSPACE((unsigned char)*current)) |
| 169 | { |
| 170 | --current; |
| 171 | --len; |
| 172 | } |
| 173 | |
| 174 | current[ISSPACE((unsigned char)*current) ? 0 : 1] = '\0'; |
| 175 | } |
| 176 | |
| 177 | return s; |
| 178 | } |
| 179 | |
| 180 | /* Remove leading and trailing whitespaces */ |
| 181 | char *string_trim_whitespace(char *const s) |
| 182 | { |
| 183 | string_trim_whitespace_right(s); /* order matters */ |
| 184 | string_trim_whitespace_left(s); |
| 185 | |
| 186 | return s; |
| 187 | } |
| 188 | |
| 189 | char *word_wrap(char* buffer, const char *string, int line_width, bool unicode, unsigned max_lines) |
| 190 | { |
| 191 | unsigned i = 0; |
| 192 | unsigned len = (unsigned)strlen(string); |
| 193 | unsigned lines = 1; |
| 194 | |
| 195 | while (i < len) |
| 196 | { |
| 197 | unsigned counter; |
| 198 | int pos = (int)(&buffer[i] - buffer); |
| 199 | |
| 200 | /* copy string until the end of the line is reached */ |
| 201 | for (counter = 1; counter <= (unsigned)line_width; counter++) |
| 202 | { |
| 203 | const char *character; |
| 204 | unsigned char_len; |
| 205 | unsigned j = i; |
| 206 | |
| 207 | /* check if end of string reached */ |
| 208 | if (i == len) |
| 209 | { |
| 210 | buffer[i] = 0; |
| 211 | return buffer; |
| 212 | } |
| 213 | |
| 214 | character = utf8skip(&string[i], 1); |
| 215 | char_len = (unsigned)(character - &string[i]); |
| 216 | |
| 217 | if (!unicode) |
| 218 | counter += char_len - 1; |
| 219 | |
| 220 | do |
| 221 | { |
| 222 | buffer[i] = string[i]; |
| 223 | char_len--; |
| 224 | i++; |
| 225 | } while (char_len); |
| 226 | |
| 227 | /* check for newlines embedded in the original input |
| 228 | * and reset the index */ |
| 229 | if (buffer[j] == '\n') |
| 230 | { |
| 231 | lines++; |
| 232 | counter = 1; |
| 233 | } |
| 234 | } |
| 235 | |
| 236 | /* check for whitespace */ |
| 237 | if (string[i] == ' ') |
| 238 | { |
| 239 | if ((max_lines == 0 || lines < max_lines)) |
| 240 | { |
| 241 | buffer[i] = '\n'; |
| 242 | i++; |
| 243 | lines++; |
| 244 | } |
| 245 | } |
| 246 | else |
| 247 | { |
| 248 | int k; |
| 249 | |
| 250 | /* check for nearest whitespace back in string */ |
| 251 | for (k = i; k > 0; k--) |
| 252 | { |
| 253 | if (string[k] != ' ' || (max_lines != 0 && lines >= max_lines)) |
| 254 | continue; |
| 255 | |
| 256 | buffer[k] = '\n'; |
| 257 | /* set string index back to character after this one */ |
| 258 | i = k + 1; |
| 259 | lines++; |
| 260 | break; |
| 261 | } |
| 262 | |
| 263 | if (&buffer[i] - buffer == pos) |
| 264 | return buffer; |
| 265 | } |
| 266 | } |
| 267 | |
| 268 | buffer[i] = 0; |
| 269 | |
| 270 | return buffer; |
| 271 | } |
| 272 | |
| 273 | /* Splits string into tokens seperated by 'delim' |
| 274 | * > Returned token string must be free()'d |
| 275 | * > Returns NULL if token is not found |
| 276 | * > After each call, 'str' is set to the position after the |
| 277 | * last found token |
| 278 | * > Tokens *include* empty strings |
| 279 | * Usage example: |
| 280 | * char *str = "1,2,3,4,5,6,7,,,10,"; |
| 281 | * char **str_ptr = &str; |
| 282 | * char *token = NULL; |
| 283 | * while ((token = string_tokenize(str_ptr, ","))) |
| 284 | * { |
| 285 | * printf("%s\n", token); |
| 286 | * free(token); |
| 287 | * token = NULL; |
| 288 | * } |
| 289 | */ |
| 290 | char* string_tokenize(char **str, const char *delim) |
| 291 | { |
| 292 | /* Taken from https://codereview.stackexchange.com/questions/216956/strtok-function-thread-safe-supports-empty-tokens-doesnt-change-string# */ |
| 293 | char *str_ptr = NULL; |
| 294 | char *delim_ptr = NULL; |
| 295 | char *token = NULL; |
| 296 | size_t token_len = 0; |
| 297 | |
| 298 | /* Sanity checks */ |
| 299 | if (!str || string_is_empty(delim)) |
| 300 | return NULL; |
| 301 | |
| 302 | str_ptr = *str; |
| 303 | |
| 304 | /* Note: we don't check string_is_empty() here, |
| 305 | * empty strings are valid */ |
| 306 | if (!str_ptr) |
| 307 | return NULL; |
| 308 | |
| 309 | /* Search for delimiter */ |
| 310 | delim_ptr = strstr(str_ptr, delim); |
| 311 | |
| 312 | if (delim_ptr) |
| 313 | token_len = delim_ptr - str_ptr; |
| 314 | else |
| 315 | token_len = strlen(str_ptr); |
| 316 | |
| 317 | /* Allocate token string */ |
| 318 | token = (char *)malloc((token_len + 1) * sizeof(char)); |
| 319 | |
| 320 | if (!token) |
| 321 | return NULL; |
| 322 | |
| 323 | /* Copy token */ |
| 324 | strlcpy(token, str_ptr, (token_len + 1) * sizeof(char)); |
| 325 | token[token_len] = '\0'; |
| 326 | |
| 327 | /* Update input string pointer */ |
| 328 | *str = delim_ptr ? delim_ptr + strlen(delim) : NULL; |
| 329 | |
| 330 | return token; |
| 331 | } |
| 332 | |
| 333 | /* Removes every instance of character 'c' from 'str' */ |
| 334 | void string_remove_all_chars(char *str, char c) |
| 335 | { |
| 336 | char *read_ptr = NULL; |
| 337 | char *write_ptr = NULL; |
| 338 | |
| 339 | if (string_is_empty(str)) |
| 340 | return; |
| 341 | |
| 342 | read_ptr = str; |
| 343 | write_ptr = str; |
| 344 | |
| 345 | while (*read_ptr != '\0') |
| 346 | { |
| 347 | *write_ptr = *read_ptr++; |
| 348 | write_ptr += (*write_ptr != c) ? 1 : 0; |
| 349 | } |
| 350 | |
| 351 | *write_ptr = '\0'; |
| 352 | } |
| 353 | |
| 354 | /* Replaces every instance of character 'find' in 'str' |
| 355 | * with character 'replace' */ |
| 356 | void string_replace_all_chars(char *str, char find, char replace) |
| 357 | { |
| 358 | char *str_ptr = str; |
| 359 | |
| 360 | if (string_is_empty(str)) |
| 361 | return; |
| 362 | |
| 363 | while ((str_ptr = strchr(str_ptr, find))) |
| 364 | *str_ptr++ = replace; |
| 365 | } |
| 366 | |
| 367 | /* Converts string to unsigned integer. |
| 368 | * Returns 0 if string is invalid */ |
| 369 | unsigned string_to_unsigned(const char *str) |
| 370 | { |
| 371 | const char *ptr = NULL; |
| 372 | |
| 373 | if (string_is_empty(str)) |
| 374 | return 0; |
| 375 | |
| 376 | for (ptr = str; *ptr != '\0'; ptr++) |
| 377 | { |
| 378 | if (!ISDIGIT((unsigned char)*ptr)) |
| 379 | return 0; |
| 380 | } |
| 381 | |
| 382 | return (unsigned)strtoul(str, NULL, 10); |
| 383 | } |
| 384 | |
| 385 | /* Converts hexadecimal string to unsigned integer. |
| 386 | * Handles optional leading '0x'. |
| 387 | * Returns 0 if string is invalid */ |
| 388 | unsigned string_hex_to_unsigned(const char *str) |
| 389 | { |
| 390 | const char *hex_str = str; |
| 391 | const char *ptr = NULL; |
| 392 | size_t len; |
| 393 | |
| 394 | if (string_is_empty(str)) |
| 395 | return 0; |
| 396 | |
| 397 | /* Remove leading '0x', if required */ |
| 398 | len = strlen(str); |
| 399 | |
| 400 | if (len >= 2) |
| 401 | if ((str[0] == '0') && |
| 402 | ((str[1] == 'x') || (str[1] == 'X'))) |
| 403 | hex_str = str + 2; |
| 404 | |
| 405 | if (string_is_empty(hex_str)) |
| 406 | return 0; |
| 407 | |
| 408 | /* Check for valid characters */ |
| 409 | for (ptr = hex_str; *ptr != '\0'; ptr++) |
| 410 | { |
| 411 | if (!isxdigit((unsigned char)*ptr)) |
| 412 | return 0; |
| 413 | } |
| 414 | |
| 415 | return (unsigned)strtoul(hex_str, NULL, 16); |
| 416 | } |