1 /* $NetBSD: str.c,v 1.64 2020/08/30 19:56:02 rillig Exp $ */
4 * Copyright (c) 1988, 1989, 1990, 1993
5 * The Regents of the University of California. All rights reserved.
7 * This code is derived from software contributed to Berkeley by
10 * Redistribution and use in source and binary forms, with or without
11 * modification, are permitted provided that the following conditions
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.
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
36 * Copyright (c) 1989 by Berkeley Softworks
37 * All rights reserved.
39 * This code is derived from software contributed to Berkeley by
42 * Redistribution and use in source and binary forms, with or without
43 * modification, are permitted provided that the following conditions
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.
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
72 static char rcsid[] = "$NetBSD: str.c,v 1.64 2020/08/30 19:56:02 rillig Exp $";
74 #include <sys/cdefs.h>
77 static char sccsid[] = "@(#)str.c 5.8 (Berkeley) 6/1/90";
79 __RCSID("$NetBSD: str.c,v 1.64 2020/08/30 19:56:02 rillig Exp $");
86 /* Return the concatenation of s1 and s2, freshly allocated. */
88 str_concat2(const char *s1, const char *s2)
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);
98 /* Return the concatenation of s1, s2 and s3, freshly allocated. */
100 str_concat3(const char *s1, const char *s2, const char *s3)
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);
112 /* Return the concatenation of s1, s2, s3 and s4, freshly allocated. */
114 str_concat4(const char *s1, const char *s2, const char *s3, const char *s4)
116 size_t len1 = strlen(s1);
117 size_t len2 = strlen(s2);
118 size_t len3 = strlen(s3);
119 size_t len4 = strlen(s4);
120 char *result = bmake_malloc(len1 + len2 + len3 + len4 + 1);
121 memcpy(result, s1, len1);
122 memcpy(result + len1, s2, len2);
123 memcpy(result + len1 + len2, s3, len3);
124 memcpy(result + len1 + len2 + len3, s4, len4 + 1);
128 /* Fracture a string into an array of words (as delineated by tabs or spaces)
129 * taking quotation marks into account. Leading tabs/spaces are ignored.
131 * If expand is TRUE, quotes are removed and escape sequences such as \r, \t,
132 * etc... are expanded. In this case, the return value is NULL on parse
135 * Returns the fractured words, which must be freed later using Words_Free.
136 * If expand was TRUE and there was a parse error, words is NULL, and in that
137 * case, nothing needs to be freed.
140 Str_Words(const char *str, Boolean expand)
152 /* skip leading space chars. */
153 for (; *str == ' ' || *str == '\t'; ++str)
156 /* words_buf holds the words, separated by '\0'. */
157 str_len = strlen(str);
158 words_buf = bmake_malloc(strlen(str) + 1);
160 words_cap = MAX((str_len / 5), 50);
161 words = bmake_malloc((words_cap + 1) * sizeof(char *));
164 * copy the string; at the same time, parse backslashes,
165 * quotes and build the word list.
169 word_start = words_buf;
170 word_end = words_buf;
171 for (str_p = str;; ++str_p) {
183 /* Don't miss "" or '' */
184 if (word_start == NULL && str_p[1] == inquote) {
186 word_start = word_end;
189 word_start = word_end + 1;
196 if (word_start == NULL)
197 word_start = word_end;
206 if (word_start == NULL)
211 * end of a token -- make sure there's enough words
212 * space and save off a pointer.
214 if (word_start == NULL)
218 if (words_len == words_cap) {
220 words_cap *= 2; /* ramp up fast */
221 new_size = (words_cap + 1) * sizeof(char *);
222 words = bmake_realloc(words, new_size);
224 words[words_len++] = word_start;
226 if (ch == '\n' || ch == '\0') {
227 if (expand && inquote) {
230 return (Words){ NULL, 0, NULL };
237 if (word_start == NULL)
238 word_start = word_end;
240 /* catch '\' at end of line */
241 if (str_p[1] == '\0')
247 switch (ch = *++str_p) {
250 /* hmmm; fix it up as best we can */
272 if (word_start == NULL)
273 word_start = word_end;
277 words[words_len] = NULL;
278 return (Words){ words, words_len, words_buf };
282 * Str_FindSubstring -- See if a string contains a particular substring.
285 * string String to search.
286 * substring Substring to find in string.
288 * Results: If string contains substring, the return value is the location of
289 * the first matching instance of substring in string. If string doesn't
290 * contain substring, the return value is NULL. Matching is done on an exact
291 * character-for-character basis with no wildcards or special characters.
293 * Side effects: None.
296 Str_FindSubstring(const char *string, const char *substring)
301 * First scan quickly through the two strings looking for a single-
302 * character match. When it's found, then compare the rest of the
306 for (b = substring; *string != 0; string++) {
312 return UNCONST(string);
322 * Str_Match -- Test if a string matches a pattern like "*.[ch]".
324 * XXX this function does not detect or report malformed patterns.
327 * Non-zero is returned if string matches the pattern, 0 otherwise. The
328 * matching operation permits the following special characters in the
329 * pattern: *?\[] (as in fnmatch(3)).
331 * Side effects: None.
334 Str_Match(const char *str, const char *pat)
338 * See if we're at the end of both the pattern and the
339 * string. If, we succeeded. If we're at the end of the
340 * pattern but not at the end of the string, we failed.
344 if (*str == 0 && *pat != '*')
348 * A '*' in the pattern matches any substring. We handle this
349 * by calling ourselves for each suffix of the string.
358 if (Str_Match(str, pat))
365 /* A '?' in the pattern matches any single character. */
370 * A '[' in the pattern matches a character from a list.
371 * The '[' is followed by the list of acceptable characters,
372 * or by ranges (two characters separated by '-'). In these
373 * character lists, the backslash is an ordinary character.
376 Boolean neg = pat[1] == '^';
380 if (*pat == ']' || *pat == 0) {
390 if (*pat <= *str && pat[2] >= *str)
392 if (*pat >= *str && pat[2] <= *str)
398 if (neg && *pat != ']' && *pat != 0)
400 while (*pat != ']' && *pat != 0)
408 * A backslash in the pattern matches the character following