str.c revision 1.59
1 /* $NetBSD: str.c,v 1.59 2020/08/10 19:53:19 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 #ifndef MAKE_NATIVE 72 static char rcsid[] = "$NetBSD: str.c,v 1.59 2020/08/10 19:53:19 rillig Exp $"; 73 #else 74 #include <sys/cdefs.h> 75 #ifndef lint 76 #if 0 77 static char sccsid[] = "@(#)str.c 5.8 (Berkeley) 6/1/90"; 78 #else 79 __RCSID("$NetBSD: str.c,v 1.59 2020/08/10 19:53:19 rillig Exp $"); 80 #endif 81 #endif /* not lint */ 82 #endif 83 84 #include "make.h" 85 86 /* Return the concatenation of s1 and s2, freshly allocated. */ 87 char * 88 str_concat2(const char *s1, const char *s2) 89 { 90 size_t len1 = strlen(s1); 91 size_t len2 = strlen(s2); 92 char *result = bmake_malloc(len1 + len2 + 1); 93 memcpy(result, s1, len1); 94 memcpy(result + len1, s2, len2 + 1); 95 return result; 96 } 97 98 /* Return the concatenation of s1, s2 and s3, freshly allocated. */ 99 char * 100 str_concat3(const char *s1, const char *s2, const char *s3) 101 { 102 size_t len1 = strlen(s1); 103 size_t len2 = strlen(s2); 104 size_t len3 = strlen(s3); 105 char *result = bmake_malloc(len1 + len2 + len3 + 1); 106 memcpy(result, s1, len1); 107 memcpy(result + len1, s2, len2); 108 memcpy(result + len1 + len2, s3, len3 + 1); 109 return result; 110 } 111 112 /*- 113 * brk_string -- 114 * Fracture a string into an array of words (as delineated by tabs or 115 * spaces) taking quotation marks into account. Leading tabs/spaces 116 * are ignored. 117 * 118 * If expand is TRUE, quotes are removed and escape sequences 119 * such as \r, \t, etc... are expanded. In this case, the return value 120 * is NULL on parse errors. 121 * 122 * returns -- 123 * Pointer to the array of pointers to the words. 124 * Memory containing the actual words in *out_words_buf. 125 * Both of these must be free'd by the caller. 126 * Number of words in *out_words_len. 127 */ 128 char ** 129 brk_string(const char *str, int *out_words_len, Boolean expand, 130 char **out_words_buf) 131 { 132 size_t str_len; 133 char *words_buf; 134 int words_cap; 135 char **words; 136 int 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 *out_words_buf = NULL; 221 return NULL; 222 } 223 goto done; 224 } 225 continue; 226 case '\\': 227 if (!expand) { 228 if (word_start == NULL) 229 word_start = word_end; 230 *word_end++ = '\\'; 231 /* catch '\' at end of line */ 232 if (str_p[1] == '\0') 233 continue; 234 ch = *++str_p; 235 break; 236 } 237 238 switch (ch = *++str_p) { 239 case '\0': 240 case '\n': 241 /* hmmm; fix it up as best we can */ 242 ch = '\\'; 243 --str_p; 244 break; 245 case 'b': 246 ch = '\b'; 247 break; 248 case 'f': 249 ch = '\f'; 250 break; 251 case 'n': 252 ch = '\n'; 253 break; 254 case 'r': 255 ch = '\r'; 256 break; 257 case 't': 258 ch = '\t'; 259 break; 260 } 261 break; 262 } 263 if (word_start == NULL) 264 word_start = word_end; 265 *word_end++ = ch; 266 } 267 done: 268 words[words_len] = NULL; 269 *out_words_len = words_len; 270 *out_words_buf = words_buf; 271 return words; 272 } 273 274 /* 275 * Str_FindSubstring -- See if a string contains a particular substring. 276 * 277 * Input: 278 * string String to search. 279 * substring Substring to find in string. 280 * 281 * Results: If string contains substring, the return value is the location of 282 * the first matching instance of substring in string. If string doesn't 283 * contain substring, the return value is NULL. Matching is done on an exact 284 * character-for-character basis with no wildcards or special characters. 285 * 286 * Side effects: None. 287 */ 288 char * 289 Str_FindSubstring(const char *string, const char *substring) 290 { 291 const char *a, *b; 292 293 /* 294 * First scan quickly through the two strings looking for a single- 295 * character match. When it's found, then compare the rest of the 296 * substring. 297 */ 298 299 for (b = substring; *string != 0; string++) { 300 if (*string != *b) 301 continue; 302 a = string; 303 for (;;) { 304 if (*b == 0) 305 return UNCONST(string); 306 if (*a++ != *b++) 307 break; 308 } 309 b = substring; 310 } 311 return NULL; 312 } 313 314 /* 315 * Str_Match -- Test if a string matches a pattern like "*.[ch]". 316 * 317 * XXX this function does not detect or report malformed patterns. 318 * 319 * Results: 320 * Non-zero is returned if string matches the pattern, 0 otherwise. The 321 * matching operation permits the following special characters in the 322 * pattern: *?\[] (as in fnmatch(3)). 323 * 324 * Side effects: None. 325 */ 326 Boolean 327 Str_Match(const char *str, const char *pat) 328 { 329 for (;;) { 330 /* 331 * See if we're at the end of both the pattern and the 332 * string. If, we succeeded. If we're at the end of the 333 * pattern but not at the end of the string, we failed. 334 */ 335 if (*pat == 0) 336 return *str == 0; 337 if (*str == 0 && *pat != '*') 338 return FALSE; 339 340 /* 341 * A '*' in the pattern matches any substring. We handle this 342 * by calling ourselves for each suffix of the string. 343 */ 344 if (*pat == '*') { 345 pat++; 346 while (*pat == '*') 347 pat++; 348 if (*pat == 0) 349 return TRUE; 350 while (*str != 0) { 351 if (Str_Match(str, pat)) 352 return TRUE; 353 str++; 354 } 355 return FALSE; 356 } 357 358 /* A '?' in the pattern matches any single character. */ 359 if (*pat == '?') 360 goto thisCharOK; 361 362 /* 363 * A '[' in the pattern matches a character from a list. 364 * The '[' is followed by the list of acceptable characters, 365 * or by ranges (two characters separated by '-'). In these 366 * character lists, the backslash is an ordinary character. 367 */ 368 if (*pat == '[') { 369 Boolean neg = pat[1] == '^'; 370 pat += 1 + neg; 371 372 for (;;) { 373 if (*pat == ']' || *pat == 0) { 374 if (neg) 375 break; 376 return FALSE; 377 } 378 if (*pat == *str) 379 break; 380 if (pat[1] == '-') { 381 if (pat[2] == 0) 382 return neg; 383 if (*pat <= *str && pat[2] >= *str) 384 break; 385 if (*pat >= *str && pat[2] <= *str) 386 break; 387 pat += 2; 388 } 389 pat++; 390 } 391 if (neg && *pat != ']' && *pat != 0) 392 return FALSE; 393 while (*pat != ']' && *pat != 0) 394 pat++; 395 if (*pat == 0) 396 pat--; 397 goto thisCharOK; 398 } 399 400 /* 401 * A backslash in the pattern matches the character following 402 * it exactly. 403 */ 404 if (*pat == '\\') { 405 pat++; 406 if (*pat == 0) 407 return FALSE; 408 } 409 410 if (*pat != *str) 411 return FALSE; 412 413 thisCharOK: 414 pat++; 415 str++; 416 } 417 } 418
Indexes created Tue Sep 23 14:10:03 GMT 2025