I'm compiling a pcre pattern with utf8 flag enabled and am trying to match a utf8 char* string against it, but it is not matching and pcre_exec returns negative. I'm passing the subject length as 65 to pcre_exec which is the number of characters in the string. Please help/
(If I try without the flag PCRE_UTF8 however, it matches but the offset vector[1] is 30 which is index of the character just before a unicode character in my input string)
#include "stdafx.h"
#include "pcre.h"
#include <pcre.h> /* PCRE lib NONE */
#include <stdio.h> /* I/O lib C89 */
#include <stdlib.h> /* Standard Lib C89 */
#include <string.h> /* Strings C89 */
#include <iostream>
int main(int argc, char *argv[])
{
pcre *reCompiled;
int pcreExecRet;
int subStrVec[30];
const char *pcreErrorStr;
int pcreErrorOffset;
char* aStrRegex = "(\\?\\w+\\?\\s*=)?\\s*(call|exec|execute)\\s+(?<spName>\\w+)("
// params can be an empty pair of paranthesis or have parameters inside them as well.
"\\(\\s*(?<params>[?\\w,]+)\\s*\\)"
// paramList along with its paranthesis is optional below so a SP call can be just "exec sp_name" for a stored proc call without any parameters.
")?";
reCompiled = pcre_compile(aStrRegex, 0, &pcreErrorStr, &pcreErrorOffset, NULL);
if(reCompiled == NULL) {
printf("ERROR: Could not compile '%s': %s\n", aStrRegex, pcreErrorStr);
exit(1);
}
char* line = "?rt?=call SqlTxFunctionTesting(?înFîéld?,?outField?,?inOutField?)";
pcreExecRet = pcre_exec(reCompiled,
NULL,
line,
65, // length of string
0, // Start looking at this point
0, // OPTIONS
subStrVec,
30); // Length of subStrVec
printf("\nret=%d",pcreExecRet);
}
Thanks,
Kannan