https://docs.neurobin.org/jpcre2/
https://github.com/jpcre2/jpcre2
现成的别人封装好的库
https://github.com/kiyolee/pcre2-win-build
https://sourceforge.net/projects/pcre/files/pcre2/10.33/
首先下载https://sourceforge.net/projects/pcre/
解压到 D:\ABNF\pcre2-10.33,参考 D:\ABNF\pcre2-10.33\NON-AUTOTOOLS-BUILD 中的cmake
如下图所示:
出现如下图:
打开 D:\ABNF\pcre2-10.33\build\PCRE2.sln,出现如下图所示
注意:会发生一个编译错误,解决办法如下:
pcre2-8工程配置如下图所示: WIN32;_WINDOWS;PCRE2_STATIC;PCRE2_CODE_UNIT_WIDTH=8;HAVE_CONFIG_H;_CRT_SECURE_NO_DEPRECATE;_CRT_SECURE_NO_WARNINGS;CMAKE_INTDIR="Debug";%(PreprocessorDefinitions)
生成D:\ABNF\pcre2-10.33\build\x64\Debug\pcre2-8d.lib。下面进行调用:用ConsoleApplication1来进行调用,其中ConsoleApplication1的工程设置如下-DEBUG-64位:宏定义:WIN32;_DEBUG;_CONSOLE;_LIB;%(PreprocessorDefinitions);PCRE2_STATIC;PCRE2_CODE_UNIT_WIDTH=8;HAVE_CONFIG_H;,附加包含目录:D:\ABNF\pcre2-10.33\build,引用库目录:D:\ABNF\pcre2-10.33\build\x64\Debug, 引用库:pcre2-8d.lib;,然后运行,用测试 程序如下:测试程序参考 D:\ABNF\pcre2-10.33\src\pcre2test.c。ConsoleApplication1代码如下:
VS2015的宏定义:_DEBUG;_CONSOLE;%(PreprocessorDefinitions);HAVE_CONFIG_H;PCRE2_STATIC;PCRE2_CODE_UNIT_WIDTH=8;_CRT_SECURE_NO_DEPRECATE;_CRT_SECURE_NO_WARNINGS;
// ConsoleApplication1.cpp : 定义控制台应用程序的入口点。
//
#include <iostream>
#include "pcre2.h"
using namespace std;
#if 0
int main(int argc, char* argv[])
{
cout << "hello world" << endl;
getchar();
return 0;
}
#endif
#if 1
int main(int argc, char* argv[])
{
///(\d+)\.(\d+)\.(\d+)\.(\d+)/ 192.168.2.2
string s0 = argv[0];
string s1 = argv[1];
string s2 = argv[2];
//string s3 = argv[3];
cout << "hello world" << endl;
//(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 (in this case, 8 bits). */
PCRE2_SPTR name_table = NULL;
int crlf_is_newline;
int errornumber;
int find_all;
int i;
int rc;
int utf8;
uint32_t option_bits;
uint32_t namecount;
uint32_t name_entry_size;
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. *
**************************************************************************/
find_all = 0;
for (i = 1; i < argc; i++)
{
if (strcmp(argv[i], "-g") == 0) find_all = 1;
else if (argv[i][0] == '-')
{
printf("Unrecognised option %s\n", argv[i]);
getchar();
return 1;
}
else break;
}
/* After the options, we require exactly two arguments, which are the pattern,
and the subject string. */
if (argc - i != 2)
{
printf("Exactly two arguments required: a regex and a subject string\n");
getchar();
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];// "/(\d+)\.(\d+)\.(\d+)\.(\d+)/"
//pattern = (PCRE2_SPTR)("(\d+)\.(\d+)\.(\d+)\.(\d+)");// "/(\d+)\.(\d+)\.(\d+)\.(\d+)/"
//subject = (PCRE2_SPTR)argv[i + 1];// "192.168.2.2"
//pattern = (PCRE2_SPTR)("\\w+");
pattern = (PCRE2_SPTR)("(\\d+)\.(\\d+)\.(\\d+)\.(\\d+)"); //(?'fenzu0'\\d+)) (?'Word'\w+))
//pattern = (PCRE2_SPTR)("(\?\'fenzu0\'\\d+))\.(\\d+)\.(\\d+)\.(\\d+)");
subject = (PCRE2_SPTR)("192.168.2.2");// "192.168.2.2"
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(
pattern, /* the pattern */
PCRE2_ZERO_TERMINATED, /* indicates pattern is zero-terminated */
0, /* default options */
&errornumber, /* for error number */
&erroroffset, /* for error offset */
NULL); /* use default compile context */
/* Compilation failed: print the error message and exit. */
if (re == NULL)
{
PCRE2_UCHAR buffer[256];
pcre2_get_error_message(errornumber, buffer, sizeof(buffer));
printf("PCRE2 compilation failed at offset %d: %s\n", (int)erroroffset,
buffer);
getchar();
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 < 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. */
getchar();
return 1;
}
/* Match succeded. Get a pointer to the output vector, where string offsets are
stored. */
ovector = pcre2_get_ovector_pointer(match_data);
printf("Match 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. *
*************************************************************************/
/* The output vector wasn't big enough. This should not happen, because we used
pcre2_match_data_create_from_pattern() above. */
if (rc == 0)
printf("ovector was not big enough for all the captured substrings\n");
/* We must guard against patterns such as /(?=.\K)/ that use \K in an assertion
to set the start of a match later than its end. In this demonstration program,
we just detect this case and give up. */
if (ovector[0] > ovector[1])
{
printf("\\K was used in an assertion to set the match start after its end.\n"
"From end to start the match was: %.*s\n", (int)(ovector[0] - ovector[1]),
(char *)(subject + ovector[1]));
printf("Run abandoned\n");
pcre2_match_data_free(match_data);
pcre2_code_free(re);
getchar();
return 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++)
{
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 */
&namecount); /* where to put the answer */
if (namecount == 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 */
&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 */
&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. In the 8-bit library the number is held in two
bytes, most significant first. */
tabptr = name_table;
for (i = 0; i < namecount; i++)
{
int n = (tabptr[0] << 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 0
if (!find_all) /* Check for -g */
{
pcre2_match_data_free(match_data); /* Release the memory that was used */
pcre2_code_free(re); /* for the match data and the pattern. */
getchar();
return 0; /* Exit the program. */
}
#endif
/* 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, &option_bits);
utf8 = (option_bits & 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, &newline);
crlf_is_newline = newline == PCRE2_NEWLINE_ANY ||
newline == PCRE2_NEWLINE_CRLF ||
newline == PCRE2_NEWLINE_ANYCRLF;
/* 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;
}
/* If the previous match was not an empty string, there is one tricky case to
consider. If a pattern contains \K within a lookbehind assertion at the
start, the end of the matched string can be at the offset where the match
started. Without special action, this leads to a loop that keeps on matching
the same substring. We must detect this case and arrange to move the start on
by one character. The pcre2_get_startchar() function returns the starting
offset that was passed to pcre2_match(). */
else
{
PCRE2_SIZE startchar = pcre2_get_startchar(match_data);
if (start_offset <= startchar)
{
if (startchar >= subject_length) break; /* Reached end of subject. */
start_offset = startchar + 1; /* Advance by one character. */
if (utf8) /* If UTF-8, it may be more */
{ /* than one code unit. */
for (; start_offset < subject_length; start_offset++)
if ((subject[start_offset] & 0xc0) != 0x80) break;
}
}
}
/* 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 && /* If CRLF is a newline & */
start_offset < subject_length - 1 && /* we are at CRLF, */
subject[start_offset] == '\r' &&
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] < subject_length) /* character. */
{
if ((subject[ovector[1]] & 0xc0) != 0x80) break;
ovector[1] += 1;
}
}
continue; /* Go round the loop again */
}
/* Other matching errors are not recoverable. */
if (rc < 0)
{
printf("Matching error %d\n", rc);
pcre2_match_data_free(match_data);
pcre2_code_free(re);
getchar();
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");
/* We must guard against patterns such as /(?=.\K)/ that use \K in an
assertion to set the start of a match later than its end. In this
demonstration program, we just detect this case and give up. */
if (ovector[0] > ovector[1])
{
printf("\\K was used in an assertion to set the match start after its end.\n"
"From end to start the match was: %.*s\n", (int)(ovector[0] - ovector[1]),
(char *)(subject + ovector[1]));
printf("Run abandoned\n");
pcre2_match_data_free(match_data);
pcre2_code_free(re);
getchar();
return 1;
}
/* As before, show substrings stored in the output vector by number, and then
also any named substrings. */
for (i = 0; i < 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 == 0) printf("No named substrings\n"); else
{
PCRE2_SPTR tabptr = name_table;
printf("Named substrings\n");
for (i = 0; i < namecount; i++)
{
int n = (tabptr[0] << 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);
getchar();
return 0;
getchar();
return 0;
}
#endif
其中:调试信息如下 :/(\d+)\.(\d+)\.(\d+)\.(\d+)/ 192.168.2.2 。字符集也选空,如下图所示:
-g (\d+)\.(\d+)\.(\d+)\.(\d+) 192.168.2.9.292.268.22.29
OK,
release 64版本:
LIB : PCRE2_STATIC;NDEBUG;_WINDOWS;PCRE2_CODE_UNIT_WIDTH=8;HAVE_CONFIG_H;_CRT_SECURE_NO_DEPRECATE;_CRT_SECURE_NO_WARNINGS;CMAKE_INTDIR="Release";%(PreprocessorDefinitions)
ConsoleApplication1 附加包含目录:D:\ABNF\pcre2-10.33\build 链接器输入:pcre2-8.lib; 链接器目录:D:\ABNF\pcre2-10.33\build\x64\Release\ ,链接器的所有选项:目标计算机:MachineX64 (/MACHINE:X64)
其它的release 32 debug32 版本类似,重点是要有 PCRE2_STATIC;PCRE2_CODE_UNIT_WIDTH=8;HAVE_CONFIG_H; 宏,就OK。
测试的话,对照pcre2demo.c中的代码。
上面证明了代码是正确 的,下面来把所要用到的库给提取出来自己编译一下。
事实证明,自己添加源码的话,需要的图如下所示:
其中最后一副图的应该是不用管的,所有用到的H+CPP都是直接通过CMAKE来编译后的,注意这些源CPP和图中的CPP一样,不能加多哦,不然会报错误的。
然后添加宏:PCRE2_STATIC;PCRE2_CODE_UNIT_WIDTH=8;HAVE_CONFIG_H;_CRT_SECURE_NO_DEPRECATE;_CRT_SECURE_NO_WARNINGS;,然后编译并运行成功,成功图和第一种方法一样。