str.c revision 1.58
1 /* $NetBSD: str.c,v 1.58 2020/08/10 19:30:30 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 1.58 2020/08/10 19:30:30 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 1.58 2020/08/10 19:30:30 rillig Exp $"); 80 #endif 81 #endif /* not lint */ 82 #endif 83 84 #include "make.h" 85 86 /*- 87 * str_concat -- 88 * concatenate the two strings, inserting a space or slash between them. 89 * 90 * returns -- 91 * the resulting string in allocated space. 92 */ 93 char * 94 str_concat(const char *s1, const char *s2, StrConcatMode mode) 95 { 96 size_t len1 = strlen(s1); 97 size_t len2 = strlen(s2); 98 char *result = bmake_malloc(len1 + 1 + len2 + 1); 99 100 /* copy first string into place */ 101 memcpy(result, s1, len1); 102 103 /* add separator character */ 104 if (mode == STR_ADDSPACE) { 105 result[len1] = ' '; 106 ++len1; 107 } else if (mode == STR_ADDSLASH) { 108 result[len1] = '/'; 109 ++len1; 110 } 111 112 /* copy second string plus EOS into place */ 113 memcpy(result + len1, s2, len2 + 1); 114 115 return result; 116 } 117 118 /*- 119 * brk_string -- 120 * Fracture a string into an array of words (as delineated by tabs or 121 * spaces) taking quotation marks into account. Leading tabs/spaces 122 * are ignored. 123 * 124 * If expand is TRUE, quotes are removed and escape sequences 125 * such as \r, \t, etc... are expanded. In this case, the return value 126 * is NULL on parse errors. 127 * 128 * returns -- 129 * Pointer to the array of pointers to the words. 130 * Memory containing the actual words in *out_words_buf. 131 * Both of these must be free'd by the caller. 132 * Number of words in *out_words_len. 133 */ 134 char ** 135 brk_string(const char *str, int *out_words_len, Boolean expand, 136 char **out_words_buf) 137 { 138 size_t str_len; 139 char *words_buf; 140 int words_cap; 141 char **words; 142 int words_len; 143 char inquote; 144 char *word_start; 145 char *word_end; 146 const char *str_p; 147 148 /* skip leading space chars. */ 149 for (; *str == ' ' || *str == '\t'; ++str) 150 continue; 151 152 /* words_buf holds the words, separated by '\0'. */ 153 str_len = strlen(str); 154 words_buf = bmake_malloc(strlen(str) + 1); 155 156 words_cap = MAX((str_len / 5), 50); 157 words = bmake_malloc((words_cap + 1) * sizeof(char *)); 158 159 /* 160 * copy the string; at the same time, parse backslashes, 161 * quotes and build the word list. 162 */ 163 words_len = 0; 164 inquote = '\0'; 165 word_start = words_buf; 166 word_end = words_buf; 167 for (str_p = str;; ++str_p) { 168 char ch = *str_p; 169 switch (ch) { 170 case '"': 171 case '\'': 172 if (inquote) { 173 if (inquote == ch) 174 inquote = '\0'; 175 else 176 break; 177 } else { 178 inquote = (char)ch; 179 /* Don't miss "" or '' */ 180 if (word_start == NULL && str_p[1] == inquote) { 181 if (!expand) { 182 word_start = word_end; 183 *word_end++ = ch; 184 } else 185 word_start = word_end + 1; 186 str_p++; 187 inquote = '\0'; 188 break; 189 } 190 } 191 if (!expand) { 192 if (word_start == NULL) 193 word_start = word_end; 194 *word_end++ = ch; 195 } 196 continue; 197 case ' ': 198 case '\t': 199 case '\n': 200 if (inquote) 201 break; 202 if (word_start == NULL) 203 continue; 204 /* FALLTHROUGH */ 205 case '\0': 206 /* 207 * end of a token -- make sure there's enough words 208 * space and save off a pointer. 209 */ 210 if (word_start == NULL) 211 goto done; 212 213 *word_end++ = '\0'; 214 if (words_len == words_cap) { 215 size_t new_size; 216 words_cap *= 2; /* ramp up fast */ 217 new_size = (words_cap + 1) * sizeof(char *); 218 words = bmake_realloc(words, new_size); 219 } 220 words[words_len++] = word_start; 221 word_start = NULL; 222 if (ch == '\n' || ch == '\0') { 223 if (expand && inquote) { 224 free(words); 225 free(words_buf); 226 *out_words_buf = NULL; 227 return NULL; 228 } 229 goto done; 230 } 231 continue; 232 case '\\': 233 if (!expand) { 234 if (word_start == NULL) 235 word_start = word_end; 236 *word_end++ = '\\'; 237 /* catch '\' at end of line */ 238 if (str_p[1] == '\0') 239 continue; 240 ch = *++str_p; 241 break; 242 } 243 244 switch (ch = *++str_p) { 245 case '\0': 246 case '\n': 247 /* hmmm; fix it up as best we can */ 248 ch = '\\'; 249 --str_p; 250 break; 251 case 'b': 252 ch = '\b'; 253 break; 254 case 'f': 255 ch = '\f'; 256 break; 257 case 'n': 258 ch = '\n'; 259 break; 260 case 'r': 261 ch = '\r'; 262 break; 263 case 't': 264 ch = '\t'; 265 break; 266 } 267 break; 268 } 269 if (word_start == NULL) 270 word_start = word_end; 271 *word_end++ = ch; 272 } 273 done: 274 words[words_len] = NULL; 275 *out_words_len = words_len; 276 *out_words_buf = words_buf; 277 return words; 278 } 279 280 /* 281 * Str_FindSubstring -- See if a string contains a particular substring. 282 * 283 * Input: 284 * string String to search. 285 * substring Substring to find in string. 286 * 287 * Results: If string contains substring, the return value is the location of 288 * the first matching instance of substring in string. If string doesn't 289 * contain substring, the return value is NULL. Matching is done on an exact 290 * character-for-character basis with no wildcards or special characters. 291 * 292 * Side effects: None. 293 */ 294 char * 295 Str_FindSubstring(const char *string, const char *substring) 296 { 297 const char *a, *b; 298 299 /* 300 * First scan quickly through the two strings looking for a single- 301 * character match. When it's found, then compare the rest of the 302 * substring. 303 */ 304 305 for (b = substring; *string != 0; string++) { 306 if (*string != *b) 307 continue; 308 a = string; 309 for (;;) { 310 if (*b == 0) 311 return UNCONST(string); 312 if (*a++ != *b++) 313 break; 314 } 315 b = substring; 316 } 317 return NULL; 318 } 319 320 /* 321 * Str_Match -- Test if a string matches a pattern like "*.[ch]". 322 * 323 * XXX this function does not detect or report malformed patterns. 324 * 325 * Results: 326 * Non-zero is returned if string matches the pattern, 0 otherwise. The 327 * matching operation permits the following special characters in the 328 * pattern: *?\[] (as in fnmatch(3)). 329 * 330 * Side effects: None. 331 */ 332 Boolean 333 Str_Match(const char *str, const char *pat) 334 { 335 for (;;) { 336 /* 337 * See if we're at the end of both the pattern and the 338 * string. If, we succeeded. If we're at the end of the 339 * pattern but not at the end of the string, we failed. 340 */ 341 if (*pat == 0) 342 return *str == 0; 343 if (*str == 0 && *pat != '*') 344 return FALSE; 345 346 /* 347 * A '*' in the pattern matches any substring. We handle this 348 * by calling ourselves for each suffix of the string. 349 */ 350 if (*pat == '*') { 351 pat++; 352 while (*pat == '*') 353 pat++; 354 if (*pat == 0) 355 return TRUE; 356 while (*str != 0) { 357 if (Str_Match(str, pat)) 358 return TRUE; 359 str++; 360 } 361 return FALSE; 362 } 363 364 /* A '?' in the pattern matches any single character. */ 365 if (*pat == '?') 366 goto thisCharOK; 367 368 /* 369 * A '[' in the pattern matches a character from a list. 370 * The '[' is followed by the list of acceptable characters, 371 * or by ranges (two characters separated by '-'). In these 372 * character lists, the backslash is an ordinary character. 373 */ 374 if (*pat == '[') { 375 Boolean neg = pat[1] == '^'; 376 pat += 1 + neg; 377 378 for (;;) { 379 if (*pat == ']' || *pat == 0) { 380 if (neg) 381 break; 382 return FALSE; 383 } 384 if (*pat == *str) 385 break; 386 if (pat[1] == '-') { 387 if (pat[2] == 0) 388 return neg; 389 if (*pat <= *str && pat[2] >= *str) 390 break; 391 if (*pat >= *str && pat[2] <= *str) 392 break; 393 pat += 2; 394 } 395 pat++; 396 } 397 if (neg && *pat != ']' && *pat != 0) 398 return FALSE; 399 while (*pat != ']' && *pat != 0) 400 pat++; 401 if (*pat == 0) 402 pat--; 403 goto thisCharOK; 404 } 405 406 /* 407 * A backslash in the pattern matches the character following 408 * it exactly. 409 */ 410 if (*pat == '\\') { 411 pat++; 412 if (*pat == 0) 413 return FALSE; 414 } 415 416 if (*pat != *str) 417 return FALSE; 418 419 thisCharOK: 420 pat++; 421 str++; 422 } 423 } 424
Indexes created Sat Oct 18 08:10:09 GMT 2025