4 * A custom strpbrk implementation.
6 #ifndef PRISM_STRPBRK_H
7 #define PRISM_STRPBRK_H
9 #include "prism/defines.h"
10 #include "prism/diagnostic.h"
11 #include "prism/parser.h"
17 * Here we have rolled our own version of strpbrk. The standard library strpbrk
18 * has undefined behavior when the source string is not null-terminated. We want
19 * to support strings that are not null-terminated because pm_parse does not
20 * have the contract that the string is null-terminated. (This is desirable
21 * because it means the extension can call pm_parse with the result of a call to
24 * The standard library strpbrk also does not support passing a maximum length
25 * to search. We want to support this for the reason mentioned above, but we
26 * also don't want it to stop on null bytes. Ruby actually allows null bytes
27 * within strings, comments, regular expressions, etc. So we need to be able to
30 * Finally, we want to support encodings wherein the charset could contain
31 * characters that are trailing bytes of multi-byte characters. For example, in
32 * Shift-JIS, the backslash character can be a trailing byte. In that case we
33 * need to take a slower path and iterate one multi-byte character at a time.
35 * @param parser The parser.
36 * @param source The source to search.
37 * @param charset The charset to search for.
38 * @param length The maximum number of bytes to search.
39 * @param validate Whether to validate that the source string is valid in the
40 * current encoding of the parser.
41 * @return A pointer to the first character in the source string that is in the
42 * charset, or NULL if no such character exists.
44 const uint8_t * pm_strpbrk(pm_parser_t
*parser
, const uint8_t *source
, const uint8_t *charset
, ptrdiff_t length
, bool validate
);