081e6815 |
1 | /* -*-c-*- |
2 | * |
6075c3ad |
3 | * $Id: str.c,v 1.5 2000/10/08 09:50:11 mdw Exp $ |
081e6815 |
4 | * |
5 | * Functions for hacking with strings |
6 | * |
7 | * (c) 1999 Straylight/Edgeware |
8 | */ |
9 | |
10 | /*----- Licensing notice --------------------------------------------------* |
11 | * |
12 | * This file is part of the mLib utilities library. |
13 | * |
14 | * mLib is free software; you can redistribute it and/or modify |
15 | * it under the terms of the GNU Library General Public License as |
16 | * published by the Free Software Foundation; either version 2 of the |
17 | * License, or (at your option) any later version. |
18 | * |
19 | * mLib is distributed in the hope that it will be useful, |
20 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
21 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
22 | * GNU Library General Public License for more details. |
23 | * |
24 | * You should have received a copy of the GNU Library General Public |
25 | * License along with mLib; if not, write to the Free |
26 | * Software Foundation, Inc., 59 Temple Place - Suite 330, Boston, |
27 | * MA 02111-1307, USA. |
28 | */ |
29 | |
30 | /*----- Revision history --------------------------------------------------* |
31 | * |
32 | * $Log: str.c,v $ |
6075c3ad |
33 | * Revision 1.5 2000/10/08 09:50:11 mdw |
34 | * (str_qword): Remove redundant definition of @STRF_QUOTE@. |
35 | * |
efae42a6 |
36 | * Revision 1.4 2000/10/08 09:43:34 mdw |
37 | * New quoted string handling and simple pattern matching. |
38 | * |
48d198f1 |
39 | * Revision 1.3 1999/12/22 15:41:14 mdw |
40 | * Skip past trailing whitespace in str_getword. |
41 | * |
f3a542e8 |
42 | * Revision 1.2 1999/05/26 20:52:57 mdw |
43 | * Add new `rest' argument for `str_split'. |
44 | * |
081e6815 |
45 | * Revision 1.1 1999/05/17 20:37:01 mdw |
46 | * Some trivial string hacks. |
47 | * |
48 | */ |
49 | |
50 | /*----- Header files ------------------------------------------------------*/ |
51 | |
52 | #include <ctype.h> |
53 | #include <stdio.h> |
54 | #include <stdlib.h> |
55 | #include <string.h> |
56 | |
57 | #include "str.h" |
58 | |
59 | /*----- Main code ---------------------------------------------------------*/ |
60 | |
efae42a6 |
61 | /* --- @str_qword@ --- * |
081e6815 |
62 | * |
63 | * Arguments: @char **pp@ = address of pointer into string |
efae42a6 |
64 | * @unsigned f@ = various flags |
081e6815 |
65 | * |
efae42a6 |
66 | * Returns: Pointer to the next space-separated possibly-quoted word from |
67 | * the string, or null. |
081e6815 |
68 | * |
efae42a6 |
69 | * Use: Fetches the next word from a string. If the flag |
70 | * @STRF_QUOTE@ is set, the `\' character acts as an escape, and |
71 | * single and double quotes protect whitespace. |
081e6815 |
72 | */ |
73 | |
efae42a6 |
74 | char *str_qword(char **pp, unsigned f) |
081e6815 |
75 | { |
efae42a6 |
76 | char *p = *pp, *q, *qq; |
77 | int st = 0, pst = 0; |
78 | |
79 | /* --- Preliminaries --- */ |
081e6815 |
80 | |
81 | if (!p) |
82 | return (0); |
081e6815 |
83 | while (isspace((unsigned char)*p)) |
84 | p++; |
efae42a6 |
85 | if (!*p) { |
86 | *pp = 0; |
87 | return (0); |
88 | } |
89 | |
90 | /* --- Main work --- */ |
081e6815 |
91 | |
efae42a6 |
92 | for (q = qq = p; *q; q++) { |
93 | switch (st) { |
94 | case '\\': |
95 | *qq++ = *q; |
96 | st = pst; |
97 | break; |
98 | case '\'': |
99 | case '\"': |
100 | if (*q == st) |
101 | st = pst = 0; |
102 | else if (*q == '\\') |
103 | st = '\\'; |
104 | else |
105 | *qq++ = *q; |
106 | break; |
107 | default: |
108 | if (isspace((unsigned char)*q)) { |
109 | do q++; while (*q && isspace((unsigned char)*q)); |
110 | goto done; |
111 | } else if (!(f & STRF_QUOTE)) |
112 | goto stdchar; |
113 | switch (*q) { |
114 | case '\\': |
115 | st = '\\'; |
116 | break; |
117 | case '\'': |
118 | case '\"': |
119 | st = pst = *q; |
120 | break; |
121 | default: |
122 | stdchar: |
123 | *qq++ = *q; |
124 | break; |
125 | } |
081e6815 |
126 | } |
127 | } |
128 | |
efae42a6 |
129 | /* --- Finished --- */ |
130 | |
131 | done: |
132 | *pp = *q ? q : 0; |
133 | *qq++ = 0; |
081e6815 |
134 | return (p); |
135 | } |
136 | |
efae42a6 |
137 | /* --- @str_qsplit@ --- * |
081e6815 |
138 | * |
139 | * Arguments: @char *p@ = pointer to string |
140 | * @char *v[]@ = pointer to array to fill in |
141 | * @size_t c@ = count of strings to fill in |
f3a542e8 |
142 | * @char **rest@ = where to store the remainder of the string |
efae42a6 |
143 | * @unsigned f@ = flags for @str_qword@ |
081e6815 |
144 | * |
145 | * Returns: Number of strings filled in. |
146 | * |
147 | * Use: Fills an array with pointers to the individual words of a |
148 | * string. The string is modified in place to contain zero |
149 | * bytes at the word boundaries, and the words have leading |
150 | * and trailing space stripped off. No more than @c@ words |
151 | * are read; the actual number is returned as the value of the |
152 | * function. Unused slots in the array are populated with |
f3a542e8 |
153 | * null bytes. If there's any string left, the address of the |
154 | * remainder is stored in @rest@ (if it's non-null); otherwise |
155 | * @rest@ is set to a null pointer. |
081e6815 |
156 | */ |
157 | |
efae42a6 |
158 | size_t str_qsplit(char *p, char *v[], size_t c, char **rest, unsigned f) |
081e6815 |
159 | { |
160 | size_t n = 0; |
161 | char *q; |
162 | |
efae42a6 |
163 | while (c && (q = str_qword(&p, f)) != 0) { |
081e6815 |
164 | *v++ = q; |
165 | c--; |
166 | n++; |
167 | } |
081e6815 |
168 | while (c) { |
169 | *v++ = 0; |
170 | c--; |
171 | } |
48d198f1 |
172 | if (rest) |
173 | *rest = p; |
081e6815 |
174 | return (n); |
175 | } |
176 | |
efae42a6 |
177 | /* --- @str_getword@ --- * |
178 | * |
179 | * Arguments: @char **pp@ = address of pointer into string |
180 | * |
181 | * Returns: Pointer to the next space-separated word from the string, |
182 | * or null. |
183 | * |
184 | * Use: Parses off space-separated words from a string. This is a |
185 | * compatibility veneer over @str_qword@. |
186 | */ |
187 | |
188 | char *str_getword(char **pp) |
189 | { |
190 | return (str_qword(pp, 0)); |
191 | } |
192 | |
193 | /* --- @str_split@ --- * |
194 | * |
195 | * Arguments: @char *p@ = pointer to string |
196 | * @char *v[]@ = pointer to array to fill in |
197 | * @size_t c@ = count of strings to fill in |
198 | * @char **rest@ = where to store the remainder of the string |
199 | * |
200 | * Returns: Number of strings filled in. |
201 | * |
202 | * Use: Fills an array with pointers to the individual words of a |
203 | * string. This is a compatibility veneer over @str_qsplit@. |
204 | */ |
205 | |
206 | size_t str_split(char *p, char *v[], size_t c, char **rest) |
207 | { |
208 | return (str_qsplit(p, v, c, rest, 0)); |
209 | } |
210 | |
211 | /* --- @str_match@ --- * |
212 | * |
213 | * Arguments: @const char *p@ = pointer to pattern string |
214 | * @const char *s@ = string to compare with |
215 | * |
216 | * Returns: Nonzero if the pattern matches the string. |
217 | * |
218 | * Use: Does simple wildcard matching. This is quite nasty and more |
219 | * than a little slow. Supports metacharacters `*', `?' and |
220 | * '['. |
221 | */ |
222 | |
223 | int str_match(const char *p, const char *s) |
224 | { |
225 | for (;;) { |
226 | char pch = *p++, pche, sch; |
227 | int sense; |
228 | |
229 | switch (pch) { |
230 | case '?': |
231 | if (!*s) |
232 | return (0); |
233 | s++; |
234 | break; |
235 | case '*': |
236 | if (!*p) |
237 | return (1); |
238 | while (*s) { |
239 | if (str_match(p, s)) |
240 | return (1); |
241 | s++; |
242 | } |
243 | return (0); |
244 | case '[': |
245 | if (!*s) |
246 | return (0); |
247 | sch = *s++; |
248 | pch = *p++; |
249 | sense = 1; |
250 | if (pch == '^' || pch == '!') { |
251 | sense = !sense; |
252 | pch = *p++; |
253 | } |
254 | if (pch == ']') { |
255 | if (*p == '-' && p[1] && p[1] != ']') { |
256 | pche = p[1]; |
257 | p += 2; |
258 | if (pch <= sch && sch <= pche) |
259 | goto class_match; |
260 | } else if (pch == sch) |
261 | goto class_match; |
262 | pch = *p++; |
263 | } |
264 | for (;; pch = *p++) { |
265 | if (!pch || pch == ']') |
266 | goto class_nomatch; |
267 | if (*p == '-' && p[1] && p[1] != ']') { |
268 | pche = p[1]; |
269 | p += 2; |
270 | if (pch <= sch && sch <= pche) |
271 | goto class_match; |
272 | } else if (pch == sch) |
273 | goto class_match; |
274 | } |
275 | class_match: |
276 | if (!sense) |
277 | return (0); |
278 | for (;;) { |
279 | pch = *p++; |
280 | if (!pch) |
281 | return (0); |
282 | if (pch == ']') |
283 | break; |
284 | if (*p == '-' && p[1] && p[1] != ']') |
285 | p += 2; |
286 | } |
287 | break; |
288 | class_nomatch: |
289 | if (sense) |
290 | return (0); |
291 | break; |
292 | case '\\': |
293 | pch = *p++; |
294 | default: |
295 | if (pch != *s) |
296 | return (0); |
297 | if (!pch) |
298 | return (1); |
299 | s++; |
300 | break; |
301 | } |
302 | } |
303 | } |
304 | |
081e6815 |
305 | /* --- @str_sanitize@ --- * |
306 | * |
307 | * Arguments: @char *d@ = destination buffer |
308 | * @const char *p@ = pointer to source string |
309 | * @size_t sz@ = size of destination buffer |
310 | * |
311 | * Returns: --- |
312 | * |
313 | * Use: Writes a string into a buffer, being careful not to overflow |
314 | * the buffer, to null terminate the result, and to prevent |
315 | * nasty nonprintable characters ending up in the buffer. |
316 | */ |
317 | |
318 | void str_sanitize(char *d, const char *p, size_t sz) |
319 | { |
320 | if (!sz) |
321 | return; |
322 | sz--; |
323 | while (*p && sz) { |
324 | int ch = *p++; |
325 | if (!isgraph((unsigned char)ch)) |
326 | ch = '_'; |
327 | *d++ = ch; |
328 | sz--; |
329 | } |
330 | *d++ = 0; |
331 | } |
332 | |
333 | /*----- That's all, folks -------------------------------------------------*/ |