4 |
|
|
5 |
/* This is a demonstration program to illustrate the most straightforward ways |
/* This is a demonstration program to illustrate the most straightforward ways |
6 |
of calling the PCRE regular expression library from a C program. See the |
of calling the PCRE regular expression library from a C program. See the |
7 |
pcresample documentation for a short discussion. |
pcresample documentation for a short discussion ("man pcresample" if you have |
8 |
|
the PCRE man pages installed). |
9 |
|
|
10 |
Compile thuswise: |
In Unix-like environments, if PCRE is installed in your standard system |
11 |
gcc -Wall pcredemo.c -I/usr/local/include -L/usr/local/lib \ |
libraries, you should be able to compile this program using this command: |
12 |
-R/usr/local/lib -lpcre |
|
13 |
|
gcc -Wall pcredemo.c -lpcre -o pcredemo |
14 |
|
|
15 |
|
If PCRE is not installed in a standard place, it is likely to be installed with |
16 |
|
support for the pkg-config mechanism. If you have pkg-config, you can compile |
17 |
|
this program using this command: |
18 |
|
|
19 |
|
gcc -Wall pcredemo.c `pkg-config --cflags --libs libpcre` -o pcredemo |
20 |
|
|
21 |
|
If you do not have pkg-config, you may have to use this: |
22 |
|
|
23 |
|
gcc -Wall pcredemo.c -I/usr/local/include -L/usr/local/lib \ |
24 |
|
-R/usr/local/lib -lpcre -o pcredemo |
25 |
|
|
26 |
Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and |
Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and |
27 |
library files for PCRE are installed on your system. Only some operating |
library files for PCRE are installed on your system. Only some operating |
28 |
systems (e.g. Solaris) use the -R option. |
systems (e.g. Solaris) use the -R option. |
|
*/ |
|
29 |
|
|
30 |
|
Building under Windows: |
31 |
|
|
32 |
|
If you want to statically link this program against a non-dll .a file, you must |
33 |
|
define PCRE_STATIC before including pcre.h, otherwise the pcre_malloc() and |
34 |
|
pcre_free() exported functions will be declared __declspec(dllimport), with |
35 |
|
unwanted results. So in this environment, uncomment the following line. */ |
36 |
|
|
37 |
|
/* #define PCRE_STATIC */ |
38 |
|
|
39 |
#include <stdio.h> |
#include <stdio.h> |
40 |
#include <string.h> |
#include <string.h> |
50 |
char *pattern; |
char *pattern; |
51 |
char *subject; |
char *subject; |
52 |
unsigned char *name_table; |
unsigned char *name_table; |
53 |
|
unsigned int option_bits; |
54 |
int erroffset; |
int erroffset; |
55 |
int find_all; |
int find_all; |
56 |
|
int crlf_is_newline; |
57 |
int namecount; |
int namecount; |
58 |
int name_entry_size; |
int name_entry_size; |
59 |
int ovector[OVECCOUNT]; |
int ovector[OVECCOUNT]; |
60 |
int subject_length; |
int subject_length; |
61 |
int rc, i; |
int rc, i; |
62 |
|
int utf8; |
63 |
|
|
64 |
|
|
65 |
/************************************************************************** |
/************************************************************************** |
151 |
|
|
152 |
/************************************************************************* |
/************************************************************************* |
153 |
* We have found the first match within the subject string. If the output * |
* We have found the first match within the subject string. If the output * |
154 |
* vector wasn't big enough, set its size to the maximum. Then output any * |
* vector wasn't big enough, say so. Then output any substrings that were * |
155 |
* substrings that were captured. * |
* captured. * |
156 |
*************************************************************************/ |
*************************************************************************/ |
157 |
|
|
158 |
/* The output vector wasn't big enough */ |
/* The output vector wasn't big enough */ |
177 |
/************************************************************************** |
/************************************************************************** |
178 |
* That concludes the basic part of this demonstration program. We have * |
* That concludes the basic part of this demonstration program. We have * |
179 |
* compiled a pattern, and performed a single match. The code that follows * |
* compiled a pattern, and performed a single match. The code that follows * |
180 |
* first shows how to access named substrings, and then how to code for * |
* shows first how to access named substrings, and then how to code for * |
181 |
* repeated matches on the same subject. * |
* repeated matches on the same subject. * |
182 |
**************************************************************************/ |
**************************************************************************/ |
183 |
|
|
236 |
* * |
* * |
237 |
* If the previous match WAS for an empty string, we can't do that, as it * |
* If the previous match WAS for an empty string, we can't do that, as it * |
238 |
* would lead to an infinite loop. Instead, a special call of pcre_exec() * |
* would lead to an infinite loop. Instead, a special call of pcre_exec() * |
239 |
* is made with the PCRE_NOTEMPTY and PCRE_ANCHORED flags set. The first * |
* is made with the PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED flags set. * |
240 |
* of these tells PCRE that an empty string is not a valid match; other * |
* The first of these tells PCRE that an empty string at the start of the * |
241 |
* possibilities must be tried. The second flag restricts PCRE to one * |
* subject is not a valid match; other possibilities must be tried. The * |
242 |
* match attempt at the initial string position. If this match succeeds, * |
* second flag restricts PCRE to one match attempt at the initial string * |
243 |
* an alternative to the empty string match has been found, and we can * |
* position. If this match succeeds, an alternative to the empty string * |
244 |
* proceed round the loop. * |
* match has been found, and we can print it and proceed round the loop, * |
245 |
|
* advancing by the length of whatever was found. If this match does not * |
246 |
|
* succeed, we still stay in the loop, advancing by just one character. * |
247 |
|
* In UTF-8 mode, which can be set by (*UTF8) in the pattern, this may be * |
248 |
|
* more than one byte. * |
249 |
|
* * |
250 |
|
* However, there is a complication concerned with newlines. When the * |
251 |
|
* newline convention is such that CRLF is a valid newline, we want must * |
252 |
|
* advance by two characters rather than one. The newline convention can * |
253 |
|
* be set in the regex by (*CR), etc.; if not, we must find the default. * |
254 |
*************************************************************************/ |
*************************************************************************/ |
255 |
|
|
256 |
if (!find_all) |
if (!find_all) /* Check for -g */ |
257 |
{ |
{ |
258 |
pcre_free(re); /* Release the memory used for the compiled pattern */ |
pcre_free(re); /* Release the memory used for the compiled pattern */ |
259 |
return 0; /* Finish unless -g was given */ |
return 0; /* Finish unless -g was given */ |
260 |
} |
} |
261 |
|
|
262 |
|
/* Before running the loop, check for UTF-8 and whether CRLF is a valid newline |
263 |
|
sequence. First, find the options with which the regex was compiled; extract |
264 |
|
the UTF-8 state, and mask off all but the newline options. */ |
265 |
|
|
266 |
|
(void)pcre_fullinfo(re, NULL, PCRE_INFO_OPTIONS, &option_bits); |
267 |
|
utf8 = option_bits & PCRE_UTF8; |
268 |
|
option_bits &= PCRE_NEWLINE_CR|PCRE_NEWLINE_LF|PCRE_NEWLINE_CRLF| |
269 |
|
PCRE_NEWLINE_ANY|PCRE_NEWLINE_ANYCRLF; |
270 |
|
|
271 |
|
/* If no newline options were set, find the default newline convention from the |
272 |
|
build configuration. */ |
273 |
|
|
274 |
|
if (option_bits == 0) |
275 |
|
{ |
276 |
|
int d; |
277 |
|
(void)pcre_config(PCRE_CONFIG_NEWLINE, &d); |
278 |
|
/* Note that these values are always the ASCII ones, even in |
279 |
|
EBCDIC environments. CR = 13, NL = 10. */ |
280 |
|
option_bits = (d == 13)? PCRE_NEWLINE_CR : |
281 |
|
(d == 10)? PCRE_NEWLINE_LF : |
282 |
|
(d == (13<<8 | 10))? PCRE_NEWLINE_CRLF : |
283 |
|
(d == -2)? PCRE_NEWLINE_ANYCRLF : |
284 |
|
(d == -1)? PCRE_NEWLINE_ANY : 0; |
285 |
|
} |
286 |
|
|
287 |
|
/* See if CRLF is a valid newline sequence. */ |
288 |
|
|
289 |
|
crlf_is_newline = |
290 |
|
option_bits == PCRE_NEWLINE_ANY || |
291 |
|
option_bits == PCRE_NEWLINE_CRLF || |
292 |
|
option_bits == PCRE_NEWLINE_ANYCRLF; |
293 |
|
|
294 |
/* Loop for second and subsequent matches */ |
/* Loop for second and subsequent matches */ |
295 |
|
|
296 |
for (;;) |
for (;;) |
305 |
if (ovector[0] == ovector[1]) |
if (ovector[0] == ovector[1]) |
306 |
{ |
{ |
307 |
if (ovector[0] == subject_length) break; |
if (ovector[0] == subject_length) break; |
308 |
options = PCRE_NOTEMPTY | PCRE_ANCHORED; |
options = PCRE_NOTEMPTY_ATSTART | PCRE_ANCHORED; |
309 |
} |
} |
310 |
|
|
311 |
/* Run the next matching operation */ |
/* Run the next matching operation */ |
324 |
is zero, it just means we have found all possible matches, so the loop ends. |
is zero, it just means we have found all possible matches, so the loop ends. |
325 |
Otherwise, it means we have failed to find a non-empty-string match at a |
Otherwise, it means we have failed to find a non-empty-string match at a |
326 |
point where there was a previous empty-string match. In this case, we do what |
point where there was a previous empty-string match. In this case, we do what |
327 |
Perl does: advance the matching position by one, and continue. We do this by |
Perl does: advance the matching position by one character, and continue. We |
328 |
setting the "end of previous match" offset, because that is picked up at the |
do this by setting the "end of previous match" offset, because that is picked |
329 |
top of the loop as the point at which to start again. */ |
up at the top of the loop as the point at which to start again. |
330 |
|
|
331 |
|
There are two complications: (a) When CRLF is a valid newline sequence, and |
332 |
|
the current position is just before it, advance by an extra byte. (b) |
333 |
|
Otherwise we must ensure that we skip an entire UTF-8 character if we are in |
334 |
|
UTF-8 mode. */ |
335 |
|
|
336 |
if (rc == PCRE_ERROR_NOMATCH) |
if (rc == PCRE_ERROR_NOMATCH) |
337 |
{ |
{ |
338 |
if (options == 0) break; |
if (options == 0) break; /* All matches found */ |
339 |
ovector[1] = start_offset + 1; |
ovector[1] = start_offset + 1; /* Advance one byte */ |
340 |
|
if (crlf_is_newline && /* If CRLF is newline & */ |
341 |
|
start_offset < subject_length - 1 && /* we are at CRLF, */ |
342 |
|
subject[start_offset] == '\r' && |
343 |
|
subject[start_offset + 1] == '\n') |
344 |
|
ovector[1] += 1; /* Advance by one more. */ |
345 |
|
else if (utf8) /* Otherwise, ensure we */ |
346 |
|
{ /* advance a whole UTF-8 */ |
347 |
|
while (ovector[1] < subject_length) /* character. */ |
348 |
|
{ |
349 |
|
if ((subject[ovector[1]] & 0xc0) != 0x80) break; |
350 |
|
ovector[1] += 1; |
351 |
|
} |
352 |
|
} |
353 |
continue; /* Go round the loop again */ |
continue; /* Go round the loop again */ |
354 |
} |
} |
355 |
|
|