/src/curl/lib/curl_fnmatch.c
Line | Count | Source (jump to first uncovered line) |
1 | | /*************************************************************************** |
2 | | * _ _ ____ _ |
3 | | * Project ___| | | | _ \| | |
4 | | * / __| | | | |_) | | |
5 | | * | (__| |_| | _ <| |___ |
6 | | * \___|\___/|_| \_\_____| |
7 | | * |
8 | | * Copyright (C) Daniel Stenberg, <daniel@haxx.se>, et al. |
9 | | * |
10 | | * This software is licensed as described in the file COPYING, which |
11 | | * you should have received as part of this distribution. The terms |
12 | | * are also available at https://curl.se/docs/copyright.html. |
13 | | * |
14 | | * You may opt to use, copy, modify, merge, publish, distribute and/or sell |
15 | | * copies of the Software, and permit persons to whom the Software is |
16 | | * furnished to do so, under the terms of the COPYING file. |
17 | | * |
18 | | * This software is distributed on an "AS IS" basis, WITHOUT WARRANTY OF ANY |
19 | | * KIND, either express or implied. |
20 | | * |
21 | | * SPDX-License-Identifier: curl |
22 | | * |
23 | | ***************************************************************************/ |
24 | | |
25 | | #include "curl_setup.h" |
26 | | #ifndef CURL_DISABLE_FTP |
27 | | #include <curl/curl.h> |
28 | | |
29 | | #include "curl_fnmatch.h" |
30 | | #include "curl_memory.h" |
31 | | |
32 | | /* The last #include file should be: */ |
33 | | #include "memdebug.h" |
34 | | |
35 | | #ifndef HAVE_FNMATCH |
36 | | |
37 | | #define CURLFNM_CHARSET_LEN (sizeof(char) * 256) |
38 | | #define CURLFNM_CHSET_SIZE (CURLFNM_CHARSET_LEN + 15) |
39 | | |
40 | | #define CURLFNM_NEGATE CURLFNM_CHARSET_LEN |
41 | | |
42 | | #define CURLFNM_ALNUM (CURLFNM_CHARSET_LEN + 1) |
43 | | #define CURLFNM_DIGIT (CURLFNM_CHARSET_LEN + 2) |
44 | | #define CURLFNM_XDIGIT (CURLFNM_CHARSET_LEN + 3) |
45 | | #define CURLFNM_ALPHA (CURLFNM_CHARSET_LEN + 4) |
46 | | #define CURLFNM_PRINT (CURLFNM_CHARSET_LEN + 5) |
47 | | #define CURLFNM_BLANK (CURLFNM_CHARSET_LEN + 6) |
48 | | #define CURLFNM_LOWER (CURLFNM_CHARSET_LEN + 7) |
49 | | #define CURLFNM_GRAPH (CURLFNM_CHARSET_LEN + 8) |
50 | | #define CURLFNM_SPACE (CURLFNM_CHARSET_LEN + 9) |
51 | | #define CURLFNM_UPPER (CURLFNM_CHARSET_LEN + 10) |
52 | | |
53 | | typedef enum { |
54 | | CURLFNM_SCHS_DEFAULT = 0, |
55 | | CURLFNM_SCHS_RIGHTBR, |
56 | | CURLFNM_SCHS_RIGHTBRLEFTBR |
57 | | } setcharset_state; |
58 | | |
59 | | typedef enum { |
60 | | CURLFNM_PKW_INIT = 0, |
61 | | CURLFNM_PKW_DDOT |
62 | | } parsekey_state; |
63 | | |
64 | | typedef enum { |
65 | | CCLASS_OTHER = 0, |
66 | | CCLASS_DIGIT, |
67 | | CCLASS_UPPER, |
68 | | CCLASS_LOWER |
69 | | } char_class; |
70 | | |
71 | | #define SETCHARSET_OK 1 |
72 | | #define SETCHARSET_FAIL 0 |
73 | | |
74 | | static int parsekeyword(unsigned char **pattern, unsigned char *charset) |
75 | | { |
76 | | parsekey_state state = CURLFNM_PKW_INIT; |
77 | | #define KEYLEN 10 |
78 | | char keyword[KEYLEN] = { 0 }; |
79 | | int i; |
80 | | unsigned char *p = *pattern; |
81 | | bool found = FALSE; |
82 | | for(i = 0; !found; i++) { |
83 | | char c = *p++; |
84 | | if(i >= KEYLEN) |
85 | | return SETCHARSET_FAIL; |
86 | | switch(state) { |
87 | | case CURLFNM_PKW_INIT: |
88 | | if(ISLOWER(c)) |
89 | | keyword[i] = c; |
90 | | else if(c == ':') |
91 | | state = CURLFNM_PKW_DDOT; |
92 | | else |
93 | | return SETCHARSET_FAIL; |
94 | | break; |
95 | | case CURLFNM_PKW_DDOT: |
96 | | if(c == ']') |
97 | | found = TRUE; |
98 | | else |
99 | | return SETCHARSET_FAIL; |
100 | | } |
101 | | } |
102 | | #undef KEYLEN |
103 | | |
104 | | *pattern = p; /* move caller's pattern pointer */ |
105 | | if(strcmp(keyword, "digit") == 0) |
106 | | charset[CURLFNM_DIGIT] = 1; |
107 | | else if(strcmp(keyword, "alnum") == 0) |
108 | | charset[CURLFNM_ALNUM] = 1; |
109 | | else if(strcmp(keyword, "alpha") == 0) |
110 | | charset[CURLFNM_ALPHA] = 1; |
111 | | else if(strcmp(keyword, "xdigit") == 0) |
112 | | charset[CURLFNM_XDIGIT] = 1; |
113 | | else if(strcmp(keyword, "print") == 0) |
114 | | charset[CURLFNM_PRINT] = 1; |
115 | | else if(strcmp(keyword, "graph") == 0) |
116 | | charset[CURLFNM_GRAPH] = 1; |
117 | | else if(strcmp(keyword, "space") == 0) |
118 | | charset[CURLFNM_SPACE] = 1; |
119 | | else if(strcmp(keyword, "blank") == 0) |
120 | | charset[CURLFNM_BLANK] = 1; |
121 | | else if(strcmp(keyword, "upper") == 0) |
122 | | charset[CURLFNM_UPPER] = 1; |
123 | | else if(strcmp(keyword, "lower") == 0) |
124 | | charset[CURLFNM_LOWER] = 1; |
125 | | else |
126 | | return SETCHARSET_FAIL; |
127 | | return SETCHARSET_OK; |
128 | | } |
129 | | |
130 | | /* Return the character class. */ |
131 | | static char_class charclass(unsigned char c) |
132 | | { |
133 | | if(ISUPPER(c)) |
134 | | return CCLASS_UPPER; |
135 | | if(ISLOWER(c)) |
136 | | return CCLASS_LOWER; |
137 | | if(ISDIGIT(c)) |
138 | | return CCLASS_DIGIT; |
139 | | return CCLASS_OTHER; |
140 | | } |
141 | | |
142 | | /* Include a character or a range in set. */ |
143 | | static void setcharorrange(unsigned char **pp, unsigned char *charset) |
144 | | { |
145 | | unsigned char *p = (*pp)++; |
146 | | unsigned char c = *p++; |
147 | | |
148 | | charset[c] = 1; |
149 | | if(ISALNUM(c) && *p++ == '-') { |
150 | | char_class cc = charclass(c); |
151 | | unsigned char endrange = *p++; |
152 | | |
153 | | if(endrange == '\\') |
154 | | endrange = *p++; |
155 | | if(endrange >= c && charclass(endrange) == cc) { |
156 | | while(c++ != endrange) |
157 | | if(charclass(c) == cc) /* Chars in class may be not consecutive. */ |
158 | | charset[c] = 1; |
159 | | *pp = p; |
160 | | } |
161 | | } |
162 | | } |
163 | | |
164 | | /* returns 1 (true) if pattern is OK, 0 if is bad ("p" is pattern pointer) */ |
165 | | static int setcharset(unsigned char **p, unsigned char *charset) |
166 | | { |
167 | | setcharset_state state = CURLFNM_SCHS_DEFAULT; |
168 | | bool something_found = FALSE; |
169 | | unsigned char c; |
170 | | |
171 | | memset(charset, 0, CURLFNM_CHSET_SIZE); |
172 | | for(;;) { |
173 | | c = **p; |
174 | | if(!c) |
175 | | return SETCHARSET_FAIL; |
176 | | |
177 | | switch(state) { |
178 | | case CURLFNM_SCHS_DEFAULT: |
179 | | if(c == ']') { |
180 | | if(something_found) |
181 | | return SETCHARSET_OK; |
182 | | something_found = TRUE; |
183 | | state = CURLFNM_SCHS_RIGHTBR; |
184 | | charset[c] = 1; |
185 | | (*p)++; |
186 | | } |
187 | | else if(c == '[') { |
188 | | unsigned char *pp = *p + 1; |
189 | | |
190 | | if(*pp++ == ':' && parsekeyword(&pp, charset)) |
191 | | *p = pp; |
192 | | else { |
193 | | charset[c] = 1; |
194 | | (*p)++; |
195 | | } |
196 | | something_found = TRUE; |
197 | | } |
198 | | else if(c == '^' || c == '!') { |
199 | | if(!something_found) { |
200 | | if(charset[CURLFNM_NEGATE]) { |
201 | | charset[c] = 1; |
202 | | something_found = TRUE; |
203 | | } |
204 | | else |
205 | | charset[CURLFNM_NEGATE] = 1; /* negate charset */ |
206 | | } |
207 | | else |
208 | | charset[c] = 1; |
209 | | (*p)++; |
210 | | } |
211 | | else if(c == '\\') { |
212 | | c = *(++(*p)); |
213 | | if(c) |
214 | | setcharorrange(p, charset); |
215 | | else |
216 | | charset['\\'] = 1; |
217 | | something_found = TRUE; |
218 | | } |
219 | | else { |
220 | | setcharorrange(p, charset); |
221 | | something_found = TRUE; |
222 | | } |
223 | | break; |
224 | | case CURLFNM_SCHS_RIGHTBR: |
225 | | if(c == '[') { |
226 | | state = CURLFNM_SCHS_RIGHTBRLEFTBR; |
227 | | charset[c] = 1; |
228 | | (*p)++; |
229 | | } |
230 | | else if(c == ']') { |
231 | | return SETCHARSET_OK; |
232 | | } |
233 | | else if(ISPRINT(c)) { |
234 | | charset[c] = 1; |
235 | | (*p)++; |
236 | | state = CURLFNM_SCHS_DEFAULT; |
237 | | } |
238 | | else |
239 | | /* used 'goto fail' instead of 'return SETCHARSET_FAIL' to avoid a |
240 | | * nonsense warning 'statement not reached' at end of the fnc when |
241 | | * compiling on Solaris */ |
242 | | goto fail; |
243 | | break; |
244 | | case CURLFNM_SCHS_RIGHTBRLEFTBR: |
245 | | if(c == ']') |
246 | | return SETCHARSET_OK; |
247 | | state = CURLFNM_SCHS_DEFAULT; |
248 | | charset[c] = 1; |
249 | | (*p)++; |
250 | | break; |
251 | | } |
252 | | } |
253 | | fail: |
254 | | return SETCHARSET_FAIL; |
255 | | } |
256 | | |
257 | | static int loop(const unsigned char *pattern, const unsigned char *string, |
258 | | int maxstars) |
259 | | { |
260 | | unsigned char *p = (unsigned char *)pattern; |
261 | | unsigned char *s = (unsigned char *)string; |
262 | | unsigned char charset[CURLFNM_CHSET_SIZE] = { 0 }; |
263 | | |
264 | | for(;;) { |
265 | | unsigned char *pp; |
266 | | |
267 | | switch(*p) { |
268 | | case '*': |
269 | | if(!maxstars) |
270 | | return CURL_FNMATCH_NOMATCH; |
271 | | /* Regroup consecutive stars and question marks. This can be done because |
272 | | '*?*?*' can be expressed as '??*'. */ |
273 | | for(;;) { |
274 | | if(*++p == '\0') |
275 | | return CURL_FNMATCH_MATCH; |
276 | | if(*p == '?') { |
277 | | if(!*s++) |
278 | | return CURL_FNMATCH_NOMATCH; |
279 | | } |
280 | | else if(*p != '*') |
281 | | break; |
282 | | } |
283 | | /* Skip string characters until we find a match with pattern suffix. */ |
284 | | for(maxstars--; *s; s++) { |
285 | | if(loop(p, s, maxstars) == CURL_FNMATCH_MATCH) |
286 | | return CURL_FNMATCH_MATCH; |
287 | | } |
288 | | return CURL_FNMATCH_NOMATCH; |
289 | | case '?': |
290 | | if(!*s) |
291 | | return CURL_FNMATCH_NOMATCH; |
292 | | s++; |
293 | | p++; |
294 | | break; |
295 | | case '\0': |
296 | | return *s? CURL_FNMATCH_NOMATCH: CURL_FNMATCH_MATCH; |
297 | | case '\\': |
298 | | if(p[1]) |
299 | | p++; |
300 | | if(*s++ != *p++) |
301 | | return CURL_FNMATCH_NOMATCH; |
302 | | break; |
303 | | case '[': |
304 | | pp = p + 1; /* Copy in case of syntax error in set. */ |
305 | | if(setcharset(&pp, charset)) { |
306 | | int found = FALSE; |
307 | | if(!*s) |
308 | | return CURL_FNMATCH_NOMATCH; |
309 | | if(charset[(unsigned int)*s]) |
310 | | found = TRUE; |
311 | | else if(charset[CURLFNM_ALNUM]) |
312 | | found = ISALNUM(*s); |
313 | | else if(charset[CURLFNM_ALPHA]) |
314 | | found = ISALPHA(*s); |
315 | | else if(charset[CURLFNM_DIGIT]) |
316 | | found = ISDIGIT(*s); |
317 | | else if(charset[CURLFNM_XDIGIT]) |
318 | | found = ISXDIGIT(*s); |
319 | | else if(charset[CURLFNM_PRINT]) |
320 | | found = ISPRINT(*s); |
321 | | else if(charset[CURLFNM_SPACE]) |
322 | | found = ISSPACE(*s); |
323 | | else if(charset[CURLFNM_UPPER]) |
324 | | found = ISUPPER(*s); |
325 | | else if(charset[CURLFNM_LOWER]) |
326 | | found = ISLOWER(*s); |
327 | | else if(charset[CURLFNM_BLANK]) |
328 | | found = ISBLANK(*s); |
329 | | else if(charset[CURLFNM_GRAPH]) |
330 | | found = ISGRAPH(*s); |
331 | | |
332 | | if(charset[CURLFNM_NEGATE]) |
333 | | found = !found; |
334 | | |
335 | | if(!found) |
336 | | return CURL_FNMATCH_NOMATCH; |
337 | | p = pp + 1; |
338 | | s++; |
339 | | break; |
340 | | } |
341 | | /* Syntax error in set; mismatch! */ |
342 | | return CURL_FNMATCH_NOMATCH; |
343 | | |
344 | | default: |
345 | | if(*p++ != *s++) |
346 | | return CURL_FNMATCH_NOMATCH; |
347 | | break; |
348 | | } |
349 | | } |
350 | | } |
351 | | |
352 | | /* |
353 | | * @unittest: 1307 |
354 | | */ |
355 | | int Curl_fnmatch(void *ptr, const char *pattern, const char *string) |
356 | | { |
357 | | (void)ptr; /* the argument is specified by the curl_fnmatch_callback |
358 | | prototype, but not used by Curl_fnmatch() */ |
359 | | if(!pattern || !string) { |
360 | | return CURL_FNMATCH_FAIL; |
361 | | } |
362 | | return loop((unsigned char *)pattern, (unsigned char *)string, 2); |
363 | | } |
364 | | #else |
365 | | #include <fnmatch.h> |
366 | | /* |
367 | | * @unittest: 1307 |
368 | | */ |
369 | | int Curl_fnmatch(void *ptr, const char *pattern, const char *string) |
370 | 0 | { |
371 | 0 | (void)ptr; /* the argument is specified by the curl_fnmatch_callback |
372 | | prototype, but not used by Curl_fnmatch() */ |
373 | 0 | if(!pattern || !string) { |
374 | 0 | return CURL_FNMATCH_FAIL; |
375 | 0 | } |
376 | | |
377 | 0 | switch(fnmatch(pattern, string, 0)) { |
378 | 0 | case 0: |
379 | 0 | return CURL_FNMATCH_MATCH; |
380 | 0 | case FNM_NOMATCH: |
381 | 0 | return CURL_FNMATCH_NOMATCH; |
382 | 0 | default: |
383 | 0 | return CURL_FNMATCH_FAIL; |
384 | 0 | } |
385 | | /* not reached */ |
386 | 0 | } |
387 | | |
388 | | #endif |
389 | | |
390 | | #endif /* if FTP is disabled */ |