blob: c9ea6c945ee8a2bb0f9c9efc664f875b72bf857f (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
|
#ifndef PRISM_STRPBRK_H
#define PRISM_STRPBRK_H
#include "prism/defines.h"
#include "prism/parser.h"
#include <stddef.h>
#include <string.h>
// Here we have rolled our own version of strpbrk. The standard library strpbrk
// has undefined behavior when the source string is not null-terminated. We want
// to support strings that are not null-terminated because pm_parse does not
// have the contract that the string is null-terminated. (This is desirable
// because it means the extension can call pm_parse with the result of a call to
// mmap).
//
// The standard library strpbrk also does not support passing a maximum length
// to search. We want to support this for the reason mentioned above, but we
// also don't want it to stop on null bytes. Ruby actually allows null bytes
// within strings, comments, regular expressions, etc. So we need to be able to
// skip past them.
//
// Finally, we want to support encodings wherein the charset could contain
// characters that are trailing bytes of multi-byte characters. For example, in
// Shift-JIS, the backslash character can be a trailing byte. In that case we
// need to take a slower path and iterate one multi-byte character at a time.
const uint8_t * pm_strpbrk(pm_parser_t *parser, const uint8_t *source, const uint8_t *charset, ptrdiff_t length);
#endif
|
