trunk/doc/pcredemo.3

.\" Start example.
.de EX
.  nr mE \\n(.f
.  nf
.  nh
.  ft CW
..
.
.
.\" End example.
.de EE
.  ft \\n(mE
.  fi
.  hy \\n(HY
..
.
.EX
/*************************************************
*           PCRE DEMONSTRATION PROGRAM           *
*************************************************/

/* This is a demonstration program to illustrate the most straightforward ways
of calling the PCRE regular expression library from a C program. See the
pcresample documentation for a short discussion ("man pcresample" if you have
the PCRE man pages installed).

In Unix-like environments, compile this program thuswise:

  gcc -Wall pcredemo.c -I/usr/local/include -L/usr/local/lib \e
    -R/usr/local/lib -lpcre

Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and
library files for PCRE are installed on your system. You don't need -I and -L
if PCRE is installed in the standard system libraries. Only some operating
systems (e.g. Solaris) use the -R option.

Building under Windows:

If you want to statically link this program against a non-dll .a file, you must
define PCRE_STATIC before including pcre.h, otherwise the pcre_malloc() and
pcre_free() exported functions will be declared __declspec(dllimport), with
unwanted results. So in this environment, uncomment the following line. */

/* #define PCRE_STATIC */

#include <stdio.h>
#include <string.h>
#include <pcre.h>

#define OVECCOUNT 30    /* should be a multiple of 3 */


int main(int argc, char **argv)
{
pcre *re;
const char *error;
char *pattern;
char *subject;
unsigned char *name_table;
int erroffset;
int find_all;
int namecount;
int name_entry_size;
int ovector[OVECCOUNT];
int subject_length;
int rc, i;


/**************************************************************************
* First, sort out the command line. There is only one possible option at  *
* the moment, "-g" to request repeated matching to find all occurrences,  *
* like Perl's /g option. We set the variable find_all to a non-zero value *
* if the -g option is present. Apart from that, there must be exactly two *
* arguments.                                                              *
**************************************************************************/

find_all = 0;
for (i = 1; i < argc; i++)
  {
  if (strcmp(argv[i], "-g") == 0) find_all = 1;
    else break;
  }

/* After the options, we require exactly two arguments, which are the pattern,
and the subject string. */

if (argc - i != 2)
  {
  printf("Two arguments required: a regex and a subject string\en");
  return 1;
  }

pattern = argv[i];
subject = argv[i+1];
subject_length = (int)strlen(subject);


/*************************************************************************
* Now we are going to compile the regular expression pattern, and handle *
* and errors that are detected.                                          *
*************************************************************************/

re = pcre_compile(
  pattern,              /* the pattern */
  0,                    /* default options */
  &error,               /* for error message */
  &erroffset,           /* for error offset */
  NULL);                /* use default character tables */

/* Compilation failed: print the error message and exit */

if (re == NULL)
  {
  printf("PCRE compilation failed at offset %d: %s\en", erroffset, error);
  return 1;
  }


/*************************************************************************
* If the compilation succeeded, we call PCRE again, in order to do a     *
* pattern match against the subject string. This does just ONE match. If *
* further matching is needed, it will be done below.                     *
*************************************************************************/

rc = pcre_exec(
  re,                   /* the compiled pattern */
  NULL,                 /* no extra data - we didn't study the pattern */
  subject,              /* the subject string */
  subject_length,       /* the length of the subject */
  0,                    /* start at offset 0 in the subject */
  0,                    /* default options */
  ovector,              /* output vector for substring information */
  OVECCOUNT);           /* number of elements in the output vector */

/* Matching failed: handle error cases */

if (rc < 0)
  {
  switch(rc)
    {
    case PCRE_ERROR_NOMATCH: printf("No match\en"); break;
    /*
    Handle other special cases if you like
    */
    default: printf("Matching error %d\en", rc); break;
    }
  pcre_free(re);     /* Release memory used for the compiled pattern */
  return 1;
  }

/* Match succeded */

printf("\enMatch succeeded at offset %d\en", ovector[0]);


/*************************************************************************
* We have found the first match within the subject string. If the output *
* vector wasn't big enough, say so. Then output any substrings that were *
* captured.                                                              *
*************************************************************************/

/* The output vector wasn't big enough */

if (rc == 0)
  {
  rc = OVECCOUNT/3;
  printf("ovector only has room for %d captured substrings\en", rc - 1);
  }

/* Show substrings stored in the output vector by number. Obviously, in a real
application you might want to do things other than print them. */

for (i = 0; i < rc; i++)
  {
  char *substring_start = subject + ovector[2*i];
  int substring_length = ovector[2*i+1] - ovector[2*i];
  printf("%2d: %.*s\en", i, substring_length, substring_start);
  }


/**************************************************************************
* That concludes the basic part of this demonstration program. We have    *
* compiled a pattern, and performed a single match. The code that follows *
* shows first how to access named substrings, and then how to code for    *
* repeated matches on the same subject.                                   *
**************************************************************************/

/* See if there are any named substrings, and if so, show them by name. First
we have to extract the count of named parentheses from the pattern. */

(void)pcre_fullinfo(
  re,                   /* the compiled pattern */
  NULL,                 /* no extra data - we didn't study the pattern */
  PCRE_INFO_NAMECOUNT,  /* number of named substrings */
  &namecount);          /* where to put the answer */

if (namecount <= 0) printf("No named substrings\en"); else
  {
  unsigned char *tabptr;
  printf("Named substrings\en");

  /* Before we can access the substrings, we must extract the table for
  translating names to numbers, and the size of each entry in the table. */

  (void)pcre_fullinfo(
    re,                       /* the compiled pattern */
    NULL,                     /* no extra data - we didn't study the pattern */
    PCRE_INFO_NAMETABLE,      /* address of the table */
    &name_table);             /* where to put the answer */

  (void)pcre_fullinfo(
    re,                       /* the compiled pattern */
    NULL,                     /* no extra data - we didn't study the pattern */
    PCRE_INFO_NAMEENTRYSIZE,  /* size of each entry in the table */
    &name_entry_size);        /* where to put the answer */

  /* Now we can scan the table and, for each entry, print the number, the name,
  and the substring itself. */

  tabptr = name_table;
  for (i = 0; i < namecount; i++)
    {
    int n = (tabptr[0] << 8) | tabptr[1];
    printf("(%d) %*s: %.*s\en", n, name_entry_size - 3, tabptr + 2,
      ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]);
    tabptr += name_entry_size;
    }
  }


/*************************************************************************
* If the "-g" option was given on the command line, we want to continue  *
* to search for additional matches in the subject string, in a similar   *
* way to the /g option in Perl. This turns out to be trickier than you   *
* might think because of the possibility of matching an empty string.    *
* What happens is as follows:                                            *
*                                                                        *
* If the previous match was NOT for an empty string, we can just start   *
* the next match at the end of the previous one.                         *
*                                                                        *
* If the previous match WAS for an empty string, we can't do that, as it *
* would lead to an infinite loop. Instead, a special call of pcre_exec() *
* is made with the PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED flags set.    *
* The first of these tells PCRE that an empty string at the start of the *
* subject is not a valid match; other possibilities must be tried. The   *
* second flag restricts PCRE to one match attempt at the initial string  *
* position. If this match succeeds, an alternative to the empty string   *
* match has been found, and we can proceed round the loop.               *
*************************************************************************/

if (!find_all)
  {
  pcre_free(re);   /* Release the memory used for the compiled pattern */
  return 0;        /* Finish unless -g was given */
  }

/* Loop for second and subsequent matches */

for (;;)
  {
  int options = 0;                 /* Normally no options */
  int start_offset = ovector[1];   /* Start at end of previous match */

  /* If the previous match was for an empty string, we are finished if we are
  at the end of the subject. Otherwise, arrange to run another match at the
  same point to see if a non-empty match can be found. */

  if (ovector[0] == ovector[1])
    {
    if (ovector[0] == subject_length) break;
    options = PCRE_NOTEMPTY_ATSTART | PCRE_ANCHORED;
    }

  /* Run the next matching operation */

  rc = pcre_exec(
    re,                   /* the compiled pattern */
    NULL,                 /* no extra data - we didn't study the pattern */
    subject,              /* the subject string */
    subject_length,       /* the length of the subject */
    start_offset,         /* starting offset in the subject */
    options,              /* options */
    ovector,              /* output vector for substring information */
    OVECCOUNT);           /* number of elements in the output vector */

  /* This time, a result of NOMATCH isn't an error. If the value in "options"
  is zero, it just means we have found all possible matches, so the loop ends.
  Otherwise, it means we have failed to find a non-empty-string match at a
  point where there was a previous empty-string match. In this case, we do what
  Perl does: advance the matching position by one, and continue. We do this by
  setting the "end of previous match" offset, because that is picked up at the
  top of the loop as the point at which to start again. */

  if (rc == PCRE_ERROR_NOMATCH)
    {
    if (options == 0) break;
    ovector[1] = start_offset + 1;
    continue;    /* Go round the loop again */
    }

  /* Other matching errors are not recoverable. */

  if (rc < 0)
    {
    printf("Matching error %d\en", rc);
    pcre_free(re);    /* Release memory used for the compiled pattern */
    return 1;
    }

  /* Match succeded */

  printf("\enMatch succeeded again at offset %d\en", ovector[0]);

  /* The match succeeded, but the output vector wasn't big enough. */

  if (rc == 0)
    {
    rc = OVECCOUNT/3;
    printf("ovector only has room for %d captured substrings\en", rc - 1);
    }

  /* As before, show substrings stored in the output vector by number, and then
  also any named substrings. */

  for (i = 0; i < rc; i++)
    {
    char *substring_start = subject + ovector[2*i];
    int substring_length = ovector[2*i+1] - ovector[2*i];
    printf("%2d: %.*s\en", i, substring_length, substring_start);
    }

  if (namecount <= 0) printf("No named substrings\en"); else
    {
    unsigned char *tabptr = name_table;
    printf("Named substrings\en");
    for (i = 0; i < namecount; i++)
      {
      int n = (tabptr[0] << 8) | tabptr[1];
      printf("(%d) %*s: %.*s\en", n, name_entry_size - 3, tabptr + 2,
        ovector[2*n+1] - ovector[2*n], subject + ovector[2*n]);
      tabptr += name_entry_size;
      }
    }
  }      /* End of loop to find second and subsequent matches */

printf("\en");
pcre_free(re);       /* Release memory used for the compiled pattern */
return 0;
}

/* End of pcredemo.c */
.EE
1	ph10	429	.\" Start example.
2			.de EX
3			. nr mE \\n(.f
4			. nf
5			. nh
6			. ft CW
7			..
8			.
9			.
10			.\" End example.
11			.de EE
12			. ft \\n(mE
13			. fi
14			. hy \\n(HY
15			..
16			.
17			.EX
18			/*************************************************
19			* PCRE DEMONSTRATION PROGRAM *
20			*************************************************/
21
22			/* This is a demonstration program to illustrate the most straightforward ways
23			of calling the PCRE regular expression library from a C program. See the
24			pcresample documentation for a short discussion ("man pcresample" if you have
25			the PCRE man pages installed).
26
27			In Unix-like environments, compile this program thuswise:
28
29			gcc -Wall pcredemo.c -I/usr/local/include -L/usr/local/lib \e
30			-R/usr/local/lib -lpcre
31
32			Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and
33			library files for PCRE are installed on your system. You don't need -I and -L
34			if PCRE is installed in the standard system libraries. Only some operating
35			systems (e.g. Solaris) use the -R option.
36
37			Building under Windows:
38
39			If you want to statically link this program against a non-dll .a file, you must
40			define PCRE_STATIC before including pcre.h, otherwise the pcre_malloc() and
41			pcre_free() exported functions will be declared __declspec(dllimport), with
42			unwanted results. So in this environment, uncomment the following line. */
43
44			/* #define PCRE_STATIC */
45
46			#include <stdio.h>
47			#include <string.h>
48			#include <pcre.h>
49
50			#define OVECCOUNT 30 /* should be a multiple of 3 */
51
52
53			int main(int argc, char **argv)
54			{
55			pcre *re;
56			const char *error;
57			char *pattern;
58			char *subject;
59			unsigned char *name_table;
60			int erroffset;
61			int find_all;
62			int namecount;
63			int name_entry_size;
64			int ovector[OVECCOUNT];
65			int subject_length;
66			int rc, i;
67
68
69			/**************************************************************************
70			* First, sort out the command line. There is only one possible option at *
71			* the moment, "-g" to request repeated matching to find all occurrences, *
72			* like Perl's /g option. We set the variable find_all to a non-zero value *
73			* if the -g option is present. Apart from that, there must be exactly two *
74			* arguments. *
75			**************************************************************************/
76
77			find_all = 0;
78			for (i = 1; i < argc; i++)
79			{
80			if (strcmp(argv[i], "-g") == 0) find_all = 1;
81			else break;
82			}
83
84			/* After the options, we require exactly two arguments, which are the pattern,
85			and the subject string. */
86
87			if (argc - i != 2)
88			{
89			printf("Two arguments required: a regex and a subject string\en");
90			return 1;
91			}
92
93			pattern = argv[i];
94			subject = argv[i+1];
95			subject_length = (int)strlen(subject);
96
97
98			/*************************************************************************
99			* Now we are going to compile the regular expression pattern, and handle *
100			* and errors that are detected. *
101			*************************************************************************/
102
103			re = pcre_compile(
104			pattern, /* the pattern */
105			0, /* default options */
106			&error, /* for error message */
107			&erroffset, /* for error offset */
108			NULL); /* use default character tables */
109
110			/* Compilation failed: print the error message and exit */
111
112			if (re == NULL)
113			{
114			printf("PCRE compilation failed at offset %d: %s\en", erroffset, error);
115			return 1;
116			}
117
118
119			/*************************************************************************
120			* If the compilation succeeded, we call PCRE again, in order to do a *
121			* pattern match against the subject string. This does just ONE match. If *
122			* further matching is needed, it will be done below. *
123			*************************************************************************/
124
125			rc = pcre_exec(
126			re, /* the compiled pattern */
127			NULL, /* no extra data - we didn't study the pattern */
128			subject, /* the subject string */
129			subject_length, /* the length of the subject */
130			0, /* start at offset 0 in the subject */
131			0, /* default options */
132			ovector, /* output vector for substring information */
133			OVECCOUNT); /* number of elements in the output vector */
134
135			/* Matching failed: handle error cases */
136
137			if (rc < 0)
138			{
139			switch(rc)
140			{
141			case PCRE_ERROR_NOMATCH: printf("No match\en"); break;
142			/*
143			Handle other special cases if you like
144			*/
145			default: printf("Matching error %d\en", rc); break;
146			}
147			pcre_free(re); /* Release memory used for the compiled pattern */
148			return 1;
149			}
150
151			/* Match succeded */
152
153			printf("\enMatch succeeded at offset %d\en", ovector[0]);
154
155
156			/*************************************************************************
157			* We have found the first match within the subject string. If the output *
158			* vector wasn't big enough, say so. Then output any substrings that were *
159			* captured. *
160			*************************************************************************/
161
162			/* The output vector wasn't big enough */
163
164			if (rc == 0)
165			{
166			rc = OVECCOUNT/3;
167			printf("ovector only has room for %d captured substrings\en", rc - 1);
168			}
169
170			/* Show substrings stored in the output vector by number. Obviously, in a real
171			application you might want to do things other than print them. */
172
173			for (i = 0; i < rc; i++)
174			{
175			char substring_start = subject + ovector[2i];
176			int substring_length = ovector[2i+1] - ovector[2i];
177			printf("%2d: %.*s\en", i, substring_length, substring_start);
178			}
179
180
181			/**************************************************************************
182			* That concludes the basic part of this demonstration program. We have *
183			* compiled a pattern, and performed a single match. The code that follows *
184			* shows first how to access named substrings, and then how to code for *
185			* repeated matches on the same subject. *
186			**************************************************************************/
187
188			/* See if there are any named substrings, and if so, show them by name. First
189			we have to extract the count of named parentheses from the pattern. */
190
191			(void)pcre_fullinfo(
192			re, /* the compiled pattern */
193			NULL, /* no extra data - we didn't study the pattern */
194			PCRE_INFO_NAMECOUNT, /* number of named substrings */
195			&namecount); /* where to put the answer */
196
197			if (namecount <= 0) printf("No named substrings\en"); else
198			{
199			unsigned char *tabptr;
200			printf("Named substrings\en");
201
202			/* Before we can access the substrings, we must extract the table for
203			translating names to numbers, and the size of each entry in the table. */
204
205			(void)pcre_fullinfo(
206			re, /* the compiled pattern */
207			NULL, /* no extra data - we didn't study the pattern */
208			PCRE_INFO_NAMETABLE, /* address of the table */
209			&name_table); /* where to put the answer */
210
211			(void)pcre_fullinfo(
212			re, /* the compiled pattern */
213			NULL, /* no extra data - we didn't study the pattern */
214			PCRE_INFO_NAMEENTRYSIZE, /* size of each entry in the table */
215			&name_entry_size); /* where to put the answer */
216
217			/* Now we can scan the table and, for each entry, print the number, the name,
218			and the substring itself. */
219
220			tabptr = name_table;
221			for (i = 0; i < namecount; i++)
222			{
223			int n = (tabptr[0] << 8) \| tabptr[1];
224			printf("(%d) %s: %.s\en", n, name_entry_size - 3, tabptr + 2,
225			ovector[2n+1] - ovector[2n], subject + ovector[2*n]);
226			tabptr += name_entry_size;
227			}
228			}
229
230
231			/*************************************************************************
232			* If the "-g" option was given on the command line, we want to continue *
233			* to search for additional matches in the subject string, in a similar *
234			* way to the /g option in Perl. This turns out to be trickier than you *
235			* might think because of the possibility of matching an empty string. *
236			* What happens is as follows: *
237			* *
238			* If the previous match was NOT for an empty string, we can just start *
239			* the next match at the end of the previous one. *
240			* *
241			* If the previous match WAS for an empty string, we can't do that, as it *
242			* would lead to an infinite loop. Instead, a special call of pcre_exec() *
243	ph10	453	* is made with the PCRE_NOTEMPTY_ATSTART and PCRE_ANCHORED flags set. *
244			* The first of these tells PCRE that an empty string at the start of the *
245			* subject is not a valid match; other possibilities must be tried. The *
246			* second flag restricts PCRE to one match attempt at the initial string *
247			* position. If this match succeeds, an alternative to the empty string *
248			* match has been found, and we can proceed round the loop. *
249	ph10	429	*************************************************************************/
250
251			if (!find_all)
252			{
253			pcre_free(re); /* Release the memory used for the compiled pattern */
254			return 0; /* Finish unless -g was given */
255			}
256
257			/* Loop for second and subsequent matches */
258
259			for (;;)
260			{
261			int options = 0; /* Normally no options */
262			int start_offset = ovector[1]; /* Start at end of previous match */
263
264			/* If the previous match was for an empty string, we are finished if we are
265			at the end of the subject. Otherwise, arrange to run another match at the
266			same point to see if a non-empty match can be found. */
267
268			if (ovector[0] == ovector[1])
269			{
270			if (ovector[0] == subject_length) break;
271	ph10	453	options = PCRE_NOTEMPTY_ATSTART \| PCRE_ANCHORED;
272	ph10	429	}
273
274			/* Run the next matching operation */
275
276			rc = pcre_exec(
277			re, /* the compiled pattern */
278			NULL, /* no extra data - we didn't study the pattern */
279			subject, /* the subject string */
280			subject_length, /* the length of the subject */
281			start_offset, /* starting offset in the subject */
282			options, /* options */
283			ovector, /* output vector for substring information */
284			OVECCOUNT); /* number of elements in the output vector */
285
286			/* This time, a result of NOMATCH isn't an error. If the value in "options"
287			is zero, it just means we have found all possible matches, so the loop ends.
288			Otherwise, it means we have failed to find a non-empty-string match at a
289			point where there was a previous empty-string match. In this case, we do what
290			Perl does: advance the matching position by one, and continue. We do this by
291			setting the "end of previous match" offset, because that is picked up at the
292			top of the loop as the point at which to start again. */
293
294			if (rc == PCRE_ERROR_NOMATCH)
295			{
296			if (options == 0) break;
297			ovector[1] = start_offset + 1;
298			continue; /* Go round the loop again */
299			}
300
301			/* Other matching errors are not recoverable. */
302
303			if (rc < 0)
304			{
305			printf("Matching error %d\en", rc);
306			pcre_free(re); /* Release memory used for the compiled pattern */
307			return 1;
308			}
309
310			/* Match succeded */
311
312			printf("\enMatch succeeded again at offset %d\en", ovector[0]);
313
314			/* The match succeeded, but the output vector wasn't big enough. */
315
316			if (rc == 0)
317			{
318			rc = OVECCOUNT/3;
319			printf("ovector only has room for %d captured substrings\en", rc - 1);
320			}
321
322			/* As before, show substrings stored in the output vector by number, and then
323			also any named substrings. */
324
325			for (i = 0; i < rc; i++)
326			{
327			char substring_start = subject + ovector[2i];
328			int substring_length = ovector[2i+1] - ovector[2i];
329			printf("%2d: %.*s\en", i, substring_length, substring_start);
330			}
331
332			if (namecount <= 0) printf("No named substrings\en"); else
333			{
334			unsigned char *tabptr = name_table;
335			printf("Named substrings\en");
336			for (i = 0; i < namecount; i++)
337			{
338			int n = (tabptr[0] << 8) \| tabptr[1];
339			printf("(%d) %s: %.s\en", n, name_entry_size - 3, tabptr + 2,
340			ovector[2n+1] - ovector[2n], subject + ovector[2*n]);
341			tabptr += name_entry_size;
342			}
343			}
344			} /* End of loop to find second and subsequent matches */
345
346			printf("\en");
347			pcre_free(re); /* Release memory used for the compiled pattern */
348			return 0;
349			}
350
351			/* End of pcredemo.c */
352			.EE