1 /* $NetBSD: str.c,v 1.65 2020/09/13 15:15:51 rillig Exp $ */ 2 3 /*- 4 * Copyright (c) 1988, 1989, 1990, 1993 5 * The Regents of the University of California. All rights reserved. 6 * 7 * This code is derived from software contributed to Berkeley by 8 * Adam de Boor. 9 * 10 * Redistribution and use in source and binary forms, with or without 11 * modification, are permitted provided that the following conditions 12 * are met: 13 * 1. Redistributions of source code must retain the above copyright 14 * notice, this list of conditions and the following disclaimer. 15 * 2. Redistributions in binary form must reproduce the above copyright 16 * notice, this list of conditions and the following disclaimer in the 17 * documentation and/or other materials provided with the distribution. 18 * 3. Neither the name of the University nor the names of its contributors 19 * may be used to endorse or promote products derived from this software 20 * without specific prior written permission. 21 * 22 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 23 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 24 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 25 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 26 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 27 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 28 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 29 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 30 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 31 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 32 * SUCH DAMAGE. 33 */ 34 35 /*- 36 * Copyright (c) 1989 by Berkeley Softworks 37 * All rights reserved. 38 * 39 * This code is derived from software contributed to Berkeley by 40 * Adam de Boor. 41 * 42 * Redistribution and use in source and binary forms, with or without 43 * modification, are permitted provided that the following conditions 44 * are met: 45 * 1. Redistributions of source code must retain the above copyright 46 * notice, this list of conditions and the following disclaimer. 47 * 2. Redistributions in binary form must reproduce the above copyright 48 * notice, this list of conditions and the following disclaimer in the 49 * documentation and/or other materials provided with the distribution. 50 * 3. All advertising materials mentioning features or use of this software 51 * must display the following acknowledgement: 52 * This product includes software developed by the University of 53 * California, Berkeley and its contributors. 54 * 4. Neither the name of the University nor the names of its contributors 55 * may be used to endorse or promote products derived from this software 56 * without specific prior written permission. 57 * 58 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND 59 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE 60 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE 61 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE 62 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL 63 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS 64 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) 65 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT 66 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY 67 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF 68 * SUCH DAMAGE. 69 */ 70 71 #include "make.h" 72 73 /* "@(#)str.c 5.8 (Berkeley) 6/1/90" */ 74 MAKE_RCSID("$NetBSD: str.c,v 1.65 2020/09/13 15:15:51 rillig Exp $"); 75 76 /* Return the concatenation of s1 and s2, freshly allocated. */ 77 char * 78 str_concat2(const char *s1, const char *s2) 79 { 80 size_t len1 = strlen(s1); 81 size_t len2 = strlen(s2); 82 char *result = bmake_malloc(len1 + len2 + 1); 83 memcpy(result, s1, len1); 84 memcpy(result + len1, s2, len2 + 1); 85 return result; 86 } 87 88 /* Return the concatenation of s1, s2 and s3, freshly allocated. */ 89 char * 90 str_concat3(const char *s1, const char *s2, const char *s3) 91 { 92 size_t len1 = strlen(s1); 93 size_t len2 = strlen(s2); 94 size_t len3 = strlen(s3); 95 char *result = bmake_malloc(len1 + len2 + len3 + 1); 96 memcpy(result, s1, len1); 97 memcpy(result + len1, s2, len2); 98 memcpy(result + len1 + len2, s3, len3 + 1); 99 return result; 100 } 101 102 /* Return the concatenation of s1, s2, s3 and s4, freshly allocated. */ 103 char * 104 str_concat4(const char *s1, const char *s2, const char *s3, const char *s4) 105 { 106 size_t len1 = strlen(s1); 107 size_t len2 = strlen(s2); 108 size_t len3 = strlen(s3); 109 size_t len4 = strlen(s4); 110 char *result = bmake_malloc(len1 + len2 + len3 + len4 + 1); 111 memcpy(result, s1, len1); 112 memcpy(result + len1, s2, len2); 113 memcpy(result + len1 + len2, s3, len3); 114 memcpy(result + len1 + len2 + len3, s4, len4 + 1); 115 return result; 116 } 117 118 /* Fracture a string into an array of words (as delineated by tabs or spaces) 119 * taking quotation marks into account. Leading tabs/spaces are ignored. 120 * 121 * If expand is TRUE, quotes are removed and escape sequences such as \r, \t, 122 * etc... are expanded. In this case, the return value is NULL on parse 123 * errors. 124 * 125 * Returns the fractured words, which must be freed later using Words_Free. 126 * If expand was TRUE and there was a parse error, words is NULL, and in that 127 * case, nothing needs to be freed. 128 */ 129 Words 130 Str_Words(const char *str, Boolean expand) 131 { 132 size_t str_len; 133 char *words_buf; 134 size_t words_cap; 135 char **words; 136 size_t words_len; 137 char inquote; 138 char *word_start; 139 char *word_end; 140 const char *str_p; 141 142 /* skip leading space chars. */ 143 for (; *str == ' ' || *str == '\t'; ++str) 144 continue; 145 146 /* words_buf holds the words, separated by '\0'. */ 147 str_len = strlen(str); 148 words_buf = bmake_malloc(strlen(str) + 1); 149 150 words_cap = MAX((str_len / 5), 50); 151 words = bmake_malloc((words_cap + 1) * sizeof(char *)); 152 153 /* 154 * copy the string; at the same time, parse backslashes, 155 * quotes and build the word list. 156 */ 157 words_len = 0; 158 inquote = '\0'; 159 word_start = words_buf; 160 word_end = words_buf; 161 for (str_p = str;; ++str_p) { 162 char ch = *str_p; 163 switch (ch) { 164 case '"': 165 case '\'': 166 if (inquote) { 167 if (inquote == ch) 168 inquote = '\0'; 169 else 170 break; 171 } else { 172 inquote = (char)ch; 173 /* Don't miss "" or '' */ 174 if (word_start == NULL && str_p[1] == inquote) { 175 if (!expand) { 176 word_start = word_end; 177 *word_end++ = ch; 178 } else 179 word_start = word_end + 1; 180 str_p++; 181 inquote = '\0'; 182 break; 183 } 184 } 185 if (!expand) { 186 if (word_start == NULL) 187 word_start = word_end; 188 *word_end++ = ch; 189 } 190 continue; 191 case ' ': 192 case '\t': 193 case '\n': 194 if (inquote) 195 break; 196 if (word_start == NULL) 197 continue; 198 /* FALLTHROUGH */ 199 case '\0': 200 /* 201 * end of a token -- make sure there's enough words 202 * space and save off a pointer. 203 */ 204 if (word_start == NULL) 205 goto done; 206 207 *word_end++ = '\0'; 208 if (words_len == words_cap) { 209 size_t new_size; 210 words_cap *= 2; /* ramp up fast */ 211 new_size = (words_cap + 1) * sizeof(char *); 212 words = bmake_realloc(words, new_size); 213 } 214 words[words_len++] = word_start; 215 word_start = NULL; 216 if (ch == '\n' || ch == '\0') { 217 if (expand && inquote) { 218 free(words); 219 free(words_buf); 220 return (Words){ NULL, 0, NULL }; 221 } 222 goto done; 223 } 224 continue; 225 case '\\': 226 if (!expand) { 227 if (word_start == NULL) 228 word_start = word_end; 229 *word_end++ = '\\'; 230 /* catch '\' at end of line */ 231 if (str_p[1] == '\0') 232 continue; 233 ch = *++str_p; 234 break; 235 } 236 237 switch (ch = *++str_p) { 238 case '\0': 239 case '\n': 240 /* hmmm; fix it up as best we can */ 241 ch = '\\'; 242 --str_p; 243 break; 244 case 'b': 245 ch = '\b'; 246 break; 247 case 'f': 248 ch = '\f'; 249 break; 250 case 'n': 251 ch = '\n'; 252 break; 253 case 'r': 254 ch = '\r'; 255 break; 256 case 't': 257 ch = '\t'; 258 break; 259 } 260 break; 261 } 262 if (word_start == NULL) 263 word_start = word_end; 264 *word_end++ = ch; 265 } 266 done: 267 words[words_len] = NULL; 268 return (Words){ words, words_len, words_buf }; 269 } 270 271 /* 272 * Str_FindSubstring -- See if a string contains a particular substring. 273 * 274 * Input: 275 * string String to search. 276 * substring Substring to find in string. 277 * 278 * Results: If string contains substring, the return value is the location of 279 * the first matching instance of substring in string. If string doesn't 280 * contain substring, the return value is NULL. Matching is done on an exact 281 * character-for-character basis with no wildcards or special characters. 282 * 283 * Side effects: None. 284 */ 285 char * 286 Str_FindSubstring(const char *string, const char *substring) 287 { 288 const char *a, *b; 289 290 /* 291 * First scan quickly through the two strings looking for a single- 292 * character match. When it's found, then compare the rest of the 293 * substring. 294 */ 295 296 for (b = substring; *string != 0; string++) { 297 if (*string != *b) 298 continue; 299 a = string; 300 for (;;) { 301 if (*b == 0) 302 return UNCONST(string); 303 if (*a++ != *b++) 304 break; 305 } 306 b = substring; 307 } 308 return NULL; 309 } 310 311 /* 312 * Str_Match -- Test if a string matches a pattern like "*.[ch]". 313 * 314 * XXX this function does not detect or report malformed patterns. 315 * 316 * Results: 317 * Non-zero is returned if string matches the pattern, 0 otherwise. The 318 * matching operation permits the following special characters in the 319 * pattern: *?\[] (as in fnmatch(3)). 320 * 321 * Side effects: None. 322 */ 323 Boolean 324 Str_Match(const char *str, const char *pat) 325 { 326 for (;;) { 327 /* 328 * See if we're at the end of both the pattern and the 329 * string. If, we succeeded. If we're at the end of the 330 * pattern but not at the end of the string, we failed. 331 */ 332 if (*pat == 0) 333 return *str == 0; 334 if (*str == 0 && *pat != '*') 335 return FALSE; 336 337 /* 338 * A '*' in the pattern matches any substring. We handle this 339 * by calling ourselves for each suffix of the string. 340 */ 341 if (*pat == '*') { 342 pat++; 343 while (*pat == '*') 344 pat++; 345 if (*pat == 0) 346 return TRUE; 347 while (*str != 0) { 348 if (Str_Match(str, pat)) 349 return TRUE; 350 str++; 351 } 352 return FALSE; 353 } 354 355 /* A '?' in the pattern matches any single character. */ 356 if (*pat == '?') 357 goto thisCharOK; 358 359 /* 360 * A '[' in the pattern matches a character from a list. 361 * The '[' is followed by the list of acceptable characters, 362 * or by ranges (two characters separated by '-'). In these 363 * character lists, the backslash is an ordinary character. 364 */ 365 if (*pat == '[') { 366 Boolean neg = pat[1] == '^'; 367 pat += neg ? 2 : 1; 368 369 for (;;) { 370 if (*pat == ']' || *pat == 0) { 371 if (neg) 372 break; 373 return FALSE; 374 } 375 if (*pat == *str) 376 break; 377 if (pat[1] == '-') { 378 if (pat[2] == 0) 379 return neg; 380 if (*pat <= *str && pat[2] >= *str) 381 break; 382 if (*pat >= *str && pat[2] <= *str) 383 break; 384 pat += 2; 385 } 386 pat++; 387 } 388 if (neg && *pat != ']' && *pat != 0) 389 return FALSE; 390 while (*pat != ']' && *pat != 0) 391 pat++; 392 if (*pat == 0) 393 pat--; 394 goto thisCharOK; 395 } 396 397 /* 398 * A backslash in the pattern matches the character following 399 * it exactly. 400 */ 401 if (*pat == '\\') { 402 pat++; 403 if (*pat == 0) 404 return FALSE; 405 } 406 407 if (*pat != *str) 408 return FALSE; 409 410 thisCharOK: 411 pat++; 412 str++; 413 } 414 } 415