walkero
/
pcre2
1
0
Fork 0
Code Issues Pull Requests Projects Releases 1 Wiki Activity
pcre2/doc/html/pcre2demo.html

444 lines
17 KiB
HTML
Raw Normal View History

Documentation scripts
2014-09-23 13:35:51 +02:00
<html>
<head>
<title>pcre2demo specification</title>
</head>
<body bgcolor="#FFFFFF" text="#00005A" link="#0066FF" alink="#3399FF" vlink="#2222BB">
<h1>pcre2demo man page</h1>
<p>
Return to the <a href="index.html">PCRE2 index page</a>.
</p>
<p>
This page is part of the PCRE2 HTML documentation. It was generated
automatically from the original man page. If there is any nonsense in it,
please consult the man page, in case the conversion went wrong.
<br>
<ul>
</ul>
<PRE>
/*************************************************
* PCRE2 DEMONSTRATION PROGRAM *
*************************************************/
/* This is a demonstration program to illustrate a straightforward way of
calling the PCRE2 regular expression library from a C program. See the
pcre2sample documentation for a short discussion ("man pcre2sample" if you have
the PCRE2 man pages installed). PCRE2 is a revised API for the library, and is
incompatible with the original PCRE API.
Tidy a lot of files (remove trailing spaces)
2014-10-20 19:28:49 +02:00
There are actually three libraries, each supporting a different code unit
Documentation scripts
2014-09-23 13:35:51 +02:00
width. This demonstration program uses the 8-bit library.
In Unix-like environments, if PCRE2 is installed in your standard system
libraries, you should be able to compile this program using this command:
gcc -Wall pcre2demo.c -lpcre2-8 -o pcre2demo
If PCRE2 is not installed in a standard place, it is likely to be installed
with support for the pkg-config mechanism. If you have pkg-config, you can
compile this program using this command:
gcc -Wall pcre2demo.c `pkg-config --cflags --libs libpcre2-8` -o pcre2demo
If you do not have pkg-config, you may have to use this:
gcc -Wall pcre2demo.c -I/usr/local/include -L/usr/local/lib \
-R/usr/local/lib -lpcre2-8 -o pcre2demo
Replace "/usr/local/include" and "/usr/local/lib" with wherever the include and
library files for PCRE2 are installed on your system. Only some operating
systems (Solaris is one) use the -R option.
Building under Windows:
If you want to statically link this program against a non-dll .a file, you must
define PCRE2_STATIC before including pcre2.h, so in this environment, uncomment
the following line. */
/* #define PCRE2_STATIC */
Tidy a lot of files (remove trailing spaces)
2014-10-20 19:28:49 +02:00
/* This macro must be defined before including pcre2.h. For a program that uses
only one code unit width, it makes it possible to use generic function names
Documentation scripts
2014-09-23 13:35:51 +02:00
such as pcre2_compile(). */
#define PCRE2_CODE_UNIT_WIDTH 8
#include &lt;stdio.h&gt;
#include &lt;string.h&gt;
#include &lt;pcre2.h&gt;
/**************************************************************************
* Here is the program. The API includes the concept of "contexts" for *
* setting up unusual interface requirements for compiling and matching, *
* such as custom memory managers and non-standard newline definitions. *
* This program does not do any of this, so it makes no use of contexts, *
* always passing NULL where a context could be given. *
**************************************************************************/
int main(int argc, char **argv)
{
pcre2_code *re;
PCRE2_SPTR pattern; /* PCRE2_SPTR is a pointer to unsigned code units of */
PCRE2_SPTR subject; /* the appropriate width (8, 16, or 32 bits). */
PCRE2_SPTR name_table;
int crlf_is_newline;
int errornumber;
int find_all;
int i;
int namecount;
int name_entry_size;
int rc;
int utf8;
uint32_t option_bits;
uint32_t newline;
PCRE2_SIZE erroroffset;
PCRE2_SIZE *ovector;
size_t subject_length;
pcre2_match_data *match_data;
/**************************************************************************
* 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 &lt; 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\n");
return 1;
}
/* As pattern and subject are char arguments, they can be straightforwardly
cast to PCRE2_SPTR as we are working in 8-bit code units. */
pattern = (PCRE2_SPTR)argv[i];
subject = (PCRE2_SPTR)argv[i+1];
subject_length = strlen((char *)subject);
/*************************************************************************
* Now we are going to compile the regular expression pattern, and handle *
* any errors that are detected. *
*************************************************************************/
re = pcre2_compile(
More documentation.
2014-09-29 18:45:37 +02:00
pattern, /* the pattern */
Tidy a lot of files (remove trailing spaces)
2014-10-20 19:28:49 +02:00
PCRE2_ZERO_TERMINATED, /* indicates pattern is zero-terminated */
More documentation.
2014-09-29 18:45:37 +02:00
0, /* default options */
&amp;errornumber, /* for error number */
&amp;erroroffset, /* for error offset */
NULL); /* use default compile context */
Documentation scripts
2014-09-23 13:35:51 +02:00
/* Compilation failed: print the error message and exit. */
if (re == NULL)
{
Tidy a lot of files (remove trailing spaces)
2014-10-20 19:28:49 +02:00
PCRE2_UCHAR buffer[256];
Documentation scripts
2014-09-23 13:35:51 +02:00
pcre2_get_error_message(errornumber, buffer, sizeof(buffer));
Tidy a lot of files (remove trailing spaces)
2014-10-20 19:28:49 +02:00
printf("PCRE2 compilation failed at offset %d: %s\n", (int)erroroffset,
Documentation scripts
2014-09-23 13:35:51 +02:00
buffer);
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. Before running the *
* match we must set up a match_data block for holding the result. *
*************************************************************************/
/* Using this function ensures that the block is exactly the right size for
the number of capturing parentheses in the pattern. */
match_data = pcre2_match_data_create_from_pattern(re, NULL);
rc = pcre2_match(
re, /* the compiled pattern */
subject, /* the subject string */
subject_length, /* the length of the subject */
0, /* start at offset 0 in the subject */
0, /* default options */
match_data, /* block for storing the result */
NULL); /* use default match context */
/* Matching failed: handle error cases */
if (rc &lt; 0)
{
switch(rc)
{
case PCRE2_ERROR_NOMATCH: printf("No match\n"); break;
/*
Handle other special cases if you like
*/
default: printf("Matching error %d\n", rc); break;
}
pcre2_match_data_free(match_data); /* Release memory used for the match */
pcre2_code_free(re); /* data and the compiled pattern. */
return 1;
}
Tidy a lot of files (remove trailing spaces)
2014-10-20 19:28:49 +02:00
/* Match succeded. Get a pointer to the output vector, where string offsets are
Documentation scripts
2014-09-23 13:35:51 +02:00
stored. */
ovector = pcre2_get_ovector_pointer(match_data);
printf("\nMatch succeeded at offset %d\n", (int)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. *
*************************************************************************/
Tidy a lot of files (remove trailing spaces)
2014-10-20 19:28:49 +02:00
/* The output vector wasn't big enough. This should not happen, because we used
Documentation scripts
2014-09-23 13:35:51 +02:00
pcre2_match_data_create_from_pattern() above. */
if (rc == 0)
printf("ovector was not big enough for all the captured substrings\n");
/* 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 &lt; rc; i++)
{
PCRE2_SPTR substring_start = subject + ovector[2*i];
size_t substring_length = ovector[2*i+1] - ovector[2*i];
printf("%2d: %.*s\n", i, (int)substring_length, (char *)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)pcre2_pattern_info(
re, /* the compiled pattern */
PCRE2_INFO_NAMECOUNT, /* get the number of named substrings */
&amp;namecount); /* where to put the answer */
if (namecount &lt;= 0) printf("No named substrings\n"); else
{
PCRE2_SPTR tabptr;
printf("Named substrings\n");
/* 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)pcre2_pattern_info(
re, /* the compiled pattern */
PCRE2_INFO_NAMETABLE, /* address of the table */
&amp;name_table); /* where to put the answer */
(void)pcre2_pattern_info(
re, /* the compiled pattern */
PCRE2_INFO_NAMEENTRYSIZE, /* size of each entry in the table */
&amp;name_entry_size); /* where to put the answer */
/* Now we can scan the table and, for each entry, print the number, the name,
Tidy a lot of files (remove trailing spaces)
2014-10-20 19:28:49 +02:00
and the substring itself. In the 8-bit library the number is held in two
Documentation scripts
2014-09-23 13:35:51 +02:00
bytes, most significant first. */
tabptr = name_table;
for (i = 0; i &lt; namecount; i++)
{
int n = (tabptr[0] &lt;&lt; 8) | tabptr[1];
printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2,
(int)(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 call of pcre2_match() is *
* made with the PCRE2_NOTEMPTY_ATSTART and PCRE2_ANCHORED flags set. The *
* first of these tells PCRE2 that an empty string at the start of the *
* subject is not a valid match; other possibilities must be tried. The *
* second flag restricts PCRE2 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 print it and proceed round the loop, *
* advancing by the length of whatever was found. If this match does not *
* succeed, we still stay in the loop, advancing by just one character. *
* In UTF-8 mode, which can be set by (*UTF) in the pattern, this may be *
* more than one byte. *
* *
* However, there is a complication concerned with newlines. When the *
* newline convention is such that CRLF is a valid newline, we must *
* advance by two characters rather than one. The newline convention can *
* be set in the regex by (*CR), etc.; if not, we must find the default. *
*************************************************************************/
if (!find_all) /* Check for -g */
{
Tidy a lot of files (remove trailing spaces)
2014-10-20 19:28:49 +02:00
pcre2_match_data_free(match_data); /* Release the memory that was used */
Documentation scripts
2014-09-23 13:35:51 +02:00
pcre2_code_free(re); /* for the match data and the pattern. */
return 0; /* Exit the program. */
}
/* Before running the loop, check for UTF-8 and whether CRLF is a valid newline
sequence. First, find the options with which the regex was compiled and extract
the UTF state. */
(void)pcre2_pattern_info(re, PCRE2_INFO_ALLOPTIONS, &amp;option_bits);
utf8 = (option_bits &amp; PCRE2_UTF) != 0;
/* Now find the newline convention and see whether CRLF is a valid newline
sequence. */
(void)pcre2_pattern_info(re, PCRE2_INFO_NEWLINE, &amp;newline);
crlf_is_newline = newline == PCRE2_NEWLINE_ANY ||
newline == PCRE2_NEWLINE_CRLF ||
Tidy a lot of files (remove trailing spaces)
2014-10-20 19:28:49 +02:00
newline == PCRE2_NEWLINE_ANYCRLF;
Documentation scripts
2014-09-23 13:35:51 +02:00
/* Loop for second and subsequent matches */
for (;;)
{
uint32_t options = 0; /* Normally no options */
PCRE2_SIZE 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 = PCRE2_NOTEMPTY_ATSTART | PCRE2_ANCHORED;
}
/* Run the next matching operation */
rc = pcre2_match(
re, /* the compiled pattern */
subject, /* the subject string */
subject_length, /* the length of the subject */
start_offset, /* starting offset in the subject */
options, /* options */
match_data, /* block for storing the result */
NULL); /* use default match context */
/* 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 character, 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.
There are two complications: (a) When CRLF is a valid newline sequence, and
the current position is just before it, advance by an extra byte. (b)
Otherwise we must ensure that we skip an entire UTF character if we are in
UTF mode. */
if (rc == PCRE2_ERROR_NOMATCH)
{
if (options == 0) break; /* All matches found */
ovector[1] = start_offset + 1; /* Advance one code unit */
if (crlf_is_newline &amp;&amp; /* If CRLF is newline &amp; */
start_offset &lt; subject_length - 1 &amp;&amp; /* we are at CRLF, */
subject[start_offset] == '\r' &amp;&amp;
subject[start_offset + 1] == '\n')
ovector[1] += 1; /* Advance by one more. */
else if (utf8) /* Otherwise, ensure we */
{ /* advance a whole UTF-8 */
while (ovector[1] &lt; subject_length) /* character. */
{
if ((subject[ovector[1]] &amp; 0xc0) != 0x80) break;
ovector[1] += 1;
}
}
continue; /* Go round the loop again */
}
/* Other matching errors are not recoverable. */
if (rc &lt; 0)
{
printf("Matching error %d\n", rc);
pcre2_match_data_free(match_data);
pcre2_code_free(re);
return 1;
}
/* Match succeded */
printf("\nMatch succeeded again at offset %d\n", (int)ovector[0]);
/* The match succeeded, but the output vector wasn't big enough. This
should not happen. */
if (rc == 0)
printf("ovector was not big enough for all the captured substrings\n");
/* As before, show substrings stored in the output vector by number, and then
also any named substrings. */
for (i = 0; i &lt; rc; i++)
{
PCRE2_SPTR substring_start = subject + ovector[2*i];
size_t substring_length = ovector[2*i+1] - ovector[2*i];
printf("%2d: %.*s\n", i, (int)substring_length, (char *)substring_start);
}
if (namecount &lt;= 0) printf("No named substrings\n"); else
{
PCRE2_SPTR tabptr = name_table;
printf("Named substrings\n");
for (i = 0; i &lt; namecount; i++)
{
int n = (tabptr[0] &lt;&lt; 8) | tabptr[1];
printf("(%d) %*s: %.*s\n", n, name_entry_size - 3, tabptr + 2,
(int)(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("\n");
pcre2_match_data_free(match_data);
pcre2_code_free(re);
return 0;
}
/* End of pcre2demo.c */
<p>
Return to the <a href="index.html">PCRE2 index page</a>.
</p>