file/src/encoding.c

65  * ubuf, and the number of characters converted in ulen.
68 file_encoding(struct magic_set *ms, const unsigned char *buf, size_t nbytes, unichar **ubuf, size_t *ulen, const char **code, const char **code_mime, const char **type)
75 	*ulen = 0;
90 	if (looks_ascii(buf, nbytes, *ubuf, ulen)) {
91 		DPRINTF(("ascii %" SIZE_T_FORMAT "u\n", *ulen));
94 	} else if (looks_utf8_with_BOM(buf, nbytes, *ubuf, ulen) > 0) {
95 		DPRINTF(("utf8/bom %" SIZE_T_FORMAT "u\n", *ulen));
98 	} else if (file_looks_utf8(buf, nbytes, *ubuf, ulen) > 1) {
99 		DPRINTF(("utf8 %" SIZE_T_FORMAT "u\n", *ulen));
102 	} else if ((ucs_type = looks_ucs16(buf, nbytes, *ubuf, ulen)) != 0) {
110 		DPRINTF(("ucs16 %" SIZE_T_FORMAT "u\n", *ulen));
111 	} else if (looks_latin1(buf, nbytes, *ubuf, ulen)) {
112 		DPRINTF(("latin1 %" SIZE_T_FORMAT "u\n", *ulen));
115 	} else if (looks_extended(buf, nbytes, *ubuf, ulen)) {
116 		DPRINTF(("extended %" SIZE_T_FORMAT "u\n", *ulen));
122 		if (looks_ascii(nbuf, nbytes, *ubuf, ulen)) {
123 			DPRINTF(("ebcdic %" SIZE_T_FORMAT "u\n", *ulen));
126 		} else if (looks_latin1(nbuf, nbytes, *ubuf, ulen)) {
128 			    *ulen));
225     size_t *ulen)
229 	*ulen = 0;
237 		ubuf[(*ulen)++] = buf[i];
244 looks_latin1(const unsigned char *buf, size_t nbytes, unichar *ubuf, size_t *ulen)
248 	*ulen = 0;
256 		ubuf[(*ulen)++] = buf[i];
264     size_t *ulen)
268 	*ulen = 0;
276 		ubuf[(*ulen)++] = buf[i];
290  * If ubuf is non-NULL on entry, text is decoded into ubuf, *ulen;
294 file_looks_utf8(const unsigned char *buf, size_t nbytes, unichar *ubuf, size_t *ulen)
302 		*ulen = 0;
315 				ubuf[(*ulen)++] = buf[i];
351 				ubuf[(*ulen)++] = c;
366     size_t *ulen)
369 		return file_looks_utf8(buf + 3, nbytes - 3, ubuf, ulen);
376     size_t *ulen)
391 	*ulen = 0;
397 			ubuf[(*ulen)++] = buf[i + 1] + 256 * buf[i];
399 			ubuf[(*ulen)++] = buf[i] + 256 * buf[i + 1];
401 		if (ubuf[*ulen - 1] == 0xfffe)
403 		if (ubuf[*ulen - 1] < 128 &&
404 		    text_chars[(size_t)ubuf[*ulen - 1]] != T)