Function parse_commit_date

commit.c:128–194

}

static timestamp_t parse_commit_date(const char *buf, const char *tail)
{
	const char *dateptr;
	const char *eol;

	if (buf + 6 >= tail)
		return 0;
	if (memcmp(buf, "author", 6))
		return 0;
	while (buf < tail && *buf++ != '\n')
		/* nada */;
	if (buf + 9 >= tail)
		return 0;
	if (memcmp(buf, "committer", 9))
		return 0;

	/*
	 * Jump to end-of-line so that we can walk backwards to find the
	 * end-of-email ">". This is more forgiving of malformed cases
	 * because unexpected characters tend to be in the name and email
	 * fields.
	 */
	eol = memchr(buf, '\n', tail - buf);
	if (!eol)
		return 0;
	dateptr = eol;
	while (dateptr > buf && dateptr[-1] != '>')
		dateptr--;
	if (dateptr == buf)
		return 0;

	/*
	 * Trim leading whitespace, but make sure we have at least one
	 * non-whitespace character, as parse_timestamp() will otherwise walk
	 * right past the newline we found in "eol" when skipping whitespace
	 * itself.
	 *
	 * In theory it would be sufficient to allow any character not matched
	 * by isspace(), but there's a catch: our isspace() does not
	 * necessarily match the behavior of parse_timestamp(), as the latter
	 * is implemented by system routines which match more exotic control
	 * codes, or even locale-dependent sequences.
	 *
	 * Since we expect the timestamp to be a number, we can check for that.
	 * Anything else (e.g., a non-numeric token like "foo") would just
	 * cause parse_timestamp() to return 0 anyway.
	 */
	while (dateptr < eol && isspace(*dateptr))
		dateptr++;
	if (!isdigit(*dateptr) && *dateptr != '-')
		return 0;

	/*
	 * We know there is at least one digit (or dash), so we'll begin
	 * parsing there and stop at worst case at eol.
	 *
	 * Note that we may feed parse_timestamp() extra characters here if the
	 * commit is malformed, and it will parse as far as it can. For