Dirk Gouders <dirk@gouders.net> writes:

> Hi,
>
> I would like to ask for an explanation or hint to my error for my
> attempt to use regexec(3) to match null-characters ('\0').
>
> To illustrate it, I wrote the attached test-program and what I do not
> understand is why I get false match-positions when testing with a string
> that contains '\0' (I am not absolutely sure if '.' is supposed to match '\0').
>
> Here is some "normal" output:
>
> $ printf ".\nab\n" | ./test_regex
> Compiling regex "."
> Testing string "ab"...
> regexec match: pos 0 length 1
>         "ab"
> Testing string "b"...
> regexec match: pos 1 length 1
>         "b"
> Testing string ""...
>
> But when I insert a '\0' into that string, the result is confusing to
> me:
>
> $ printf ".\na\0b\n" | ./test_regex
> Compiling regex "."
> Testing string "a"...
> regexec match: pos 0 length 1
>         "a"
> Testing string ""...
> regexec match: pos 2 length 1
>         "b"
> Testing string "b"...
> regexec match: pos 2 length 1
>         "b"
> Testing string ""...
>
> My appologies in advance should this question be easy to answer myself
> if I had googled it correctly.
>
> Regards,
>
> Dirk
>
> #include <stdlib.h>
> #include <stdio.h>
> #include <regex.h>
>
> int main()
> {
>         int ret;
>
>         char *line = NULL;
>         char *reg_expr = NULL;
>         size_t line_len = 256;
> 	size_t l;
>
>         static regex_t preg;
>
>         regmatch_t pmatch[1];
>
>                 
> 	ret = getline(&reg_expr, &line_len, stdin);
>
> 	if (ret < 1)
> 		exit(1);
>
> 	reg_expr[ret - 1] = '\0'; /* remove newline */
>
> 	printf("Compiling regex \"%s\"\n", reg_expr);
>
> 	if (ret = regcomp(&preg, reg_expr, REG_EXTENDED | REG_NEWLINE) != 0) {
> 		fprintf(stderr, "regcomp() failed: %d\n", ret);
> 		exit(1);
> 	}
>
>
> 	while (1) {
> 		ret = getline(&line, &line_len, stdin);
>         
> 		line[ret - 1] = '\0'; /* remove newline */
> 		line_len = ret - 1;
>
> 		if (ret < 1)
> 			break;
>
> 		for (int i = 0; i < line_len; i += l ? l : 1) {
>
> 			pmatch[0].rm_so = 0;
> 			pmatch[0].rm_eo = line_len - i;
>
> 			printf("Testing string \"");
> 			for (int j = i; j < line_len; j++)
> 				printf("%c", line[j]);
> 			printf("\"...\n");
>
> 			ret = regexec(&preg, line + i, 1, pmatch, REG_NOTEOL | REG_STARTEND);
>
> 			if (ret != 0) {
> 				printf("No match.\n");
> 				break;
> 			} else
> 				printf("regexec match: pos %u length %u\n\t\"%s\"\n",
> 				       pmatch[0].rm_so + i,
> 				       pmatch[0].rm_eo - pmatch[0].rm_so,
> 				       line + i + pmatch[0].rm_so);
>
> 			l = pmatch[0].rm_eo - pmatch[0].rm_so;
> 		}
> 	}
> }