1 /*****************************************************************************
3 *****************************************************************************
4 * Copyright (C) 2007-2011 VLC authors and VideoLAN
6 * This program is free software; you can redistribute it and/or modify it
7 * under the terms of the GNU Lesser General Public License as published by
8 * the Free Software Foundation; either version 2.1 of the License, or
9 * (at your option) any later version.
11 * This program is distributed in the hope that it will be useful,
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
14 * GNU Lesser General Public License for more details.
16 * You should have received a copy of the GNU Lesser General Public License
17 * along with this program; if not, write to the Free Software Foundation,
18 * Inc., 51 Franklin Street, Fifth Floor, Boston MA 02110-1301, USA.
19 *****************************************************************************/
22 * Converts a DVB SI text item to UTF-8.
23 * Refer to EN 800 486 annex A.
24 * @return a heap-allocation nul-terminated UTF-8 string or NULL on error.
26 static char *vlc_from_EIT (const void *buf, size_t length)
28 if (unlikely(length == 0))
32 const char *encoding = encbuf;
36 unsigned char c = *in;
41 encoding = "ISO_6937";
43 else if ((1 << c) & 0x0EFE) /* 1-7, 9-11 -> ISO 8859-(c+4) */
45 snprintf (encbuf, sizeof (encbuf), "ISO_8859-%hhu", 4 + c);
49 case 0x10: /* two more bytes */
51 if (length < 3 || in[1] != 0x00)
55 if ((1 << c) & 0xEFFE) /* 1-11, 13-15 -> ISO 8859-(c) */
56 snprintf (encbuf, sizeof (encbuf), "ISO_8859-%hhu", c);
60 case 0x11: /* the BMP */
61 case 0x14: /* Big5 subset of the BMP */
65 /* DVB has no clue about Korean. KS X 1001 (a.k.a. KS C 5601) is a
66 * character set, not a character encoding... So we assume EUC-KR.
67 * It is an encoding of KS X 1001. In practice, I guess nobody uses
68 * this in any real DVB system. */
71 case 0x13: /* GB-2312-1980 */
78 case 0x1F: /* operator-specific(?) */
88 char *out = FromCharset (encoding, in, length);
91 out = strndup (in, length);
92 if (unlikely(out == NULL))
97 /* Convert control codes */
98 for (char *p = strchr (out, '\xC2'); p; p = strchr (p + 1, '\xC2'))
100 /* We have valid UTF-8, to 0xC2 is followed by a continuation byte. */
101 /* 0x80-0x85,0x88-0x89 are reserved.
102 * 0x86-0x87 are identical to Unicode and Latin-1.
104 * 0x8B-0x9F are unspecified. */
106 memcpy (p, "\r\n", 2);
109 /* Private use area */
110 for (char *p = strchr (out, '\xEE'); p; p = strchr (p + 1, '\xEE'))
112 /* Within UTF-8, 0xEE is followed by a two continuation bytes. */
116 memcpy (p, "\r\r\n", 3); /* we need three bytes, so to CRs ;) */