str.c revision 1.16 1 /* $NetBSD: str.c,v 1.16 1998/03/26 19:20:37 christos Exp $ */
2
3 /*-
4 * Copyright (c) 1988, 1989, 1990, 1993
5 * The Regents of the University of California. All rights reserved.
6 * Copyright (c) 1989 by Berkeley Softworks
7 * All rights reserved.
8 *
9 * This code is derived from software contributed to Berkeley by
10 * Adam de Boor.
11 *
12 * Redistribution and use in source and binary forms, with or without
13 * modification, are permitted provided that the following conditions
14 * are met:
15 * 1. Redistributions of source code must retain the above copyright
16 * notice, this list of conditions and the following disclaimer.
17 * 2. Redistributions in binary form must reproduce the above copyright
18 * notice, this list of conditions and the following disclaimer in the
19 * documentation and/or other materials provided with the distribution.
20 * 3. All advertising materials mentioning features or use of this software
21 * must display the following acknowledgement:
22 * This product includes software developed by the University of
23 * California, Berkeley and its contributors.
24 * 4. Neither the name of the University nor the names of its contributors
25 * may be used to endorse or promote products derived from this software
26 * without specific prior written permission.
27 *
28 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
29 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
30 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
31 * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
32 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
33 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
34 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
35 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
36 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
37 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
38 * SUCH DAMAGE.
39 */
40
41 #ifdef MAKE_BOOTSTRAP
42 static char rcsid[] = "$NetBSD: str.c,v 1.16 1998/03/26 19:20:37 christos Exp $";
43 #else
44 #include <sys/cdefs.h>
45 #ifndef lint
46 #if 0
47 static char sccsid[] = "@(#)str.c 5.8 (Berkeley) 6/1/90";
48 #else
49 __RCSID("$NetBSD: str.c,v 1.16 1998/03/26 19:20:37 christos Exp $");
50 #endif
51 #endif /* not lint */
52 #endif
53
54 #include "make.h"
55
56 /*-
57 * str_concat --
58 * concatenate the two strings, inserting a space or slash between them,
59 * freeing them if requested.
60 *
61 * returns --
62 * the resulting string in allocated space.
63 */
64 char *
65 str_concat(s1, s2, flags)
66 char *s1, *s2;
67 int flags;
68 {
69 register int len1, len2;
70 register char *result;
71
72 /* get the length of both strings */
73 len1 = strlen(s1);
74 len2 = strlen(s2);
75
76 /* allocate length plus separator plus EOS */
77 result = emalloc((u_int)(len1 + len2 + 2));
78
79 /* copy first string into place */
80 memcpy(result, s1, len1);
81
82 /* add separator character */
83 if (flags & STR_ADDSPACE) {
84 result[len1] = ' ';
85 ++len1;
86 } else if (flags & STR_ADDSLASH) {
87 result[len1] = '/';
88 ++len1;
89 }
90
91 /* copy second string plus EOS into place */
92 memcpy(result + len1, s2, len2 + 1);
93
94 /* free original strings */
95 if (flags & STR_DOFREE) {
96 (void)free(s1);
97 (void)free(s2);
98 }
99 return(result);
100 }
101
102 /*-
103 * brk_string --
104 * Fracture a string into an array of words (as delineated by tabs or
105 * spaces) taking quotation marks into account. Leading tabs/spaces
106 * are ignored.
107 *
108 * returns --
109 * Pointer to the array of pointers to the words. To make life easier,
110 * the first word is always the value of the .MAKE variable.
111 */
112 char **
113 brk_string(str, store_argc, expand, buffer)
114 register char *str;
115 int *store_argc;
116 Boolean expand;
117 char **buffer;
118 {
119 register int argc, ch;
120 register char inquote, *p, *start, *t;
121 int len;
122 int argmax = 50, curlen = 0;
123 char **argv = (char **)emalloc((argmax + 1) * sizeof(char *));
124
125 /* skip leading space chars. */
126 for (; *str == ' ' || *str == '\t'; ++str)
127 continue;
128
129 /* allocate room for a copy of the string */
130 if ((len = strlen(str) + 1) > curlen)
131 *buffer = emalloc(curlen = len);
132
133 /*
134 * copy the string; at the same time, parse backslashes,
135 * quotes and build the argument list.
136 */
137 argc = 0;
138 inquote = '\0';
139 for (p = str, start = t = *buffer;; ++p) {
140 switch(ch = *p) {
141 case '"':
142 case '\'':
143 if (inquote)
144 if (inquote == ch)
145 inquote = '\0';
146 else
147 break;
148 else {
149 inquote = (char) ch;
150 /* Don't miss "" or '' */
151 if (start == NULL && p[1] == inquote) {
152 start = t + 1;
153 break;
154 }
155 }
156 if (!expand) {
157 if (!start)
158 start = t;
159 *t++ = ch;
160 }
161 continue;
162 case ' ':
163 case '\t':
164 case '\n':
165 if (inquote)
166 break;
167 if (!start)
168 continue;
169 /* FALLTHROUGH */
170 case '\0':
171 /*
172 * end of a token -- make sure there's enough argv
173 * space and save off a pointer.
174 */
175 if (!start)
176 goto done;
177
178 *t++ = '\0';
179 if (argc == argmax) {
180 argmax *= 2; /* ramp up fast */
181 argv = (char **)erealloc(argv,
182 (argmax + 1) * sizeof(char *));
183 }
184 argv[argc++] = start;
185 start = (char *)NULL;
186 if (ch == '\n' || ch == '\0')
187 goto done;
188 continue;
189 case '\\':
190 if (!expand) {
191 if (!start)
192 start = t;
193 *t++ = '\\';
194 ch = *++p;
195 break;
196 }
197
198 switch (ch = *++p) {
199 case '\0':
200 case '\n':
201 /* hmmm; fix it up as best we can */
202 ch = '\\';
203 --p;
204 break;
205 case 'b':
206 ch = '\b';
207 break;
208 case 'f':
209 ch = '\f';
210 break;
211 case 'n':
212 ch = '\n';
213 break;
214 case 'r':
215 ch = '\r';
216 break;
217 case 't':
218 ch = '\t';
219 break;
220 }
221 break;
222 }
223 if (!start)
224 start = t;
225 *t++ = (char) ch;
226 }
227 done: argv[argc] = (char *)NULL;
228 *store_argc = argc;
229 return(argv);
230 }
231
232 /*
233 * Str_FindSubstring -- See if a string contains a particular substring.
234 *
235 * Results: If string contains substring, the return value is the location of
236 * the first matching instance of substring in string. If string doesn't
237 * contain substring, the return value is NULL. Matching is done on an exact
238 * character-for-character basis with no wildcards or special characters.
239 *
240 * Side effects: None.
241 */
242 char *
243 Str_FindSubstring(string, substring)
244 register char *string; /* String to search. */
245 char *substring; /* Substring to find in string */
246 {
247 register char *a, *b;
248
249 /*
250 * First scan quickly through the two strings looking for a single-
251 * character match. When it's found, then compare the rest of the
252 * substring.
253 */
254
255 for (b = substring; *string != 0; string += 1) {
256 if (*string != *b)
257 continue;
258 a = string;
259 for (;;) {
260 if (*b == 0)
261 return(string);
262 if (*a++ != *b++)
263 break;
264 }
265 b = substring;
266 }
267 return((char *) NULL);
268 }
269
270 /*
271 * Str_Match --
272 *
273 * See if a particular string matches a particular pattern.
274 *
275 * Results: Non-zero is returned if string matches pattern, 0 otherwise. The
276 * matching operation permits the following special characters in the
277 * pattern: *?\[] (see the man page for details on what these mean).
278 *
279 * Side effects: None.
280 */
281 int
282 Str_Match(string, pattern)
283 register char *string; /* String */
284 register char *pattern; /* Pattern */
285 {
286 char c2;
287
288 for (;;) {
289 /*
290 * See if we're at the end of both the pattern and the
291 * string. If, we succeeded. If we're at the end of the
292 * pattern but not at the end of the string, we failed.
293 */
294 if (*pattern == 0)
295 return(!*string);
296 if (*string == 0 && *pattern != '*')
297 return(0);
298 /*
299 * Check for a "*" as the next pattern character. It matches
300 * any substring. We handle this by calling ourselves
301 * recursively for each postfix of string, until either we
302 * match or we reach the end of the string.
303 */
304 if (*pattern == '*') {
305 pattern += 1;
306 if (*pattern == 0)
307 return(1);
308 while (*string != 0) {
309 if (Str_Match(string, pattern))
310 return(1);
311 ++string;
312 }
313 return(0);
314 }
315 /*
316 * Check for a "?" as the next pattern character. It matches
317 * any single character.
318 */
319 if (*pattern == '?')
320 goto thisCharOK;
321 /*
322 * Check for a "[" as the next pattern character. It is
323 * followed by a list of characters that are acceptable, or
324 * by a range (two characters separated by "-").
325 */
326 if (*pattern == '[') {
327 ++pattern;
328 for (;;) {
329 if ((*pattern == ']') || (*pattern == 0))
330 return(0);
331 if (*pattern == *string)
332 break;
333 if (pattern[1] == '-') {
334 c2 = pattern[2];
335 if (c2 == 0)
336 return(0);
337 if ((*pattern <= *string) &&
338 (c2 >= *string))
339 break;
340 if ((*pattern >= *string) &&
341 (c2 <= *string))
342 break;
343 pattern += 2;
344 }
345 ++pattern;
346 }
347 while ((*pattern != ']') && (*pattern != 0))
348 ++pattern;
349 goto thisCharOK;
350 }
351 /*
352 * If the next pattern character is '/', just strip off the
353 * '/' so we do exact matching on the character that follows.
354 */
355 if (*pattern == '\\') {
356 ++pattern;
357 if (*pattern == 0)
358 return(0);
359 }
360 /*
361 * There's no special character. Just make sure that the
362 * next characters of each string match.
363 */
364 if (*pattern != *string)
365 return(0);
366 thisCharOK: ++pattern;
367 ++string;
368 }
369 }
370
371
372 /*-
373 *-----------------------------------------------------------------------
374 * Str_SYSVMatch --
375 * Check word against pattern for a match (% is wild),
376 *
377 * Results:
378 * Returns the beginning position of a match or null. The number
379 * of characters matched is returned in len.
380 *
381 * Side Effects:
382 * None
383 *
384 *-----------------------------------------------------------------------
385 */
386 char *
387 Str_SYSVMatch(word, pattern, len)
388 char *word; /* Word to examine */
389 char *pattern; /* Pattern to examine against */
390 int *len; /* Number of characters to substitute */
391 {
392 char *p = pattern;
393 char *w = word;
394 char *m;
395
396 if (*p == '\0') {
397 /* Null pattern is the whole string */
398 *len = strlen(w);
399 return w;
400 }
401
402 if ((m = strchr(p, '%')) != NULL) {
403 /* check that the prefix matches */
404 for (; p != m && *w && *w == *p; w++, p++)
405 continue;
406
407 if (p != m)
408 return NULL; /* No match */
409
410 if (*++p == '\0') {
411 /* No more pattern, return the rest of the string */
412 *len = strlen(w);
413 return w;
414 }
415 }
416
417 m = w;
418
419 /* Find a matching tail */
420 do
421 if (strcmp(p, w) == 0) {
422 *len = w - m;
423 return m;
424 }
425 while (*w++ != '\0');
426
427 return NULL;
428 }
429
430
431 /*-
432 *-----------------------------------------------------------------------
433 * Str_SYSVSubst --
434 * Substitute '%' on the pattern with len characters from src.
435 * If the pattern does not contain a '%' prepend len characters
436 * from src.
437 *
438 * Results:
439 * None
440 *
441 * Side Effects:
442 * Places result on buf
443 *
444 *-----------------------------------------------------------------------
445 */
446 void
447 Str_SYSVSubst(buf, pat, src, len)
448 Buffer buf;
449 char *pat;
450 char *src;
451 int len;
452 {
453 char *m;
454
455 if ((m = strchr(pat, '%')) != NULL) {
456 /* Copy the prefix */
457 Buf_AddBytes(buf, m - pat, (Byte *) pat);
458 /* skip the % */
459 pat = m + 1;
460 }
461
462 /* Copy the pattern */
463 Buf_AddBytes(buf, len, (Byte *) src);
464
465 /* append the rest */
466 Buf_AddBytes(buf, strlen(pat), (Byte *) pat);
467 }
468