libpurple/protocols/oscar/encoding.h

Tue, 27 Jul 2010 21:17:01 +0000

author
Ivan Komarov <ivan.komarov@pidgin.im>
date
Tue, 27 Jul 2010 21:17:01 +0000
branch
soc.2010.icq-tlc
changeset 30660
cd134a2014f2
parent 30659
c663d8b84d1f
child 30661
b33b4612a753
permissions
-rw-r--r--

Stop using custom encodings (and LATIN-1, for that matter) for sending
OSCAR messages (ICBM, chat, Direct IM). Now, we use ASCII if a message
contains ASCII characters only, and UTF-16 in all other cases.

That fixes #10833 (offline messages now will be sent as UTF-16)
and also a whole bunch of potential problems we can get
with charset 0x3. Different clients tend to interpret this
charset differently; for instance, the official client
always interprets it as LATIN-1, while alternative
clients may decode it as some other user-specified
8-bit encoding. On the other hand, ASCII messages
(charset 0x0) and UTF-16 messages (charset 0x2) are understood
uniformly by all clients.

I also cleaned-up the code a little (got rid of code paths that were
never executed, flags that were always set, unused struct members, etc.)

30659
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
1 /*
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
2 * Purple's oscar protocol plugin
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
3 * This file is the legal property of its developers.
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
4 * Please see the AUTHORS file distributed alongside this file.
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
5 *
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
6 * This library is free software; you can redistribute it and/or
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
7 * modify it under the terms of the GNU Lesser General Public
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
8 * License as published by the Free Software Foundation; either
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
9 * version 2 of the License, or (at your option) any later version.
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
10 *
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
11 * This library is distributed in the hope that it will be useful,
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
14 * Lesser General Public License for more details.
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
15 *
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
16 * You should have received a copy of the GNU Lesser General Public
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
17 * License along with this library; if not, write to the Free Software
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
18 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02111-1301 USA
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
19 */
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
20
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
21 #ifndef _ENCODING_H_
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
22 #define _ENCODING_H_
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
23
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
24 #include "oscar.h"
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
25 #include "oscarcommon.h"
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
26
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
27 /**
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
28 * Determine the simplest encoding we can send this message in.
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
29 */
30660
cd134a2014f2 Stop using custom encodings (and LATIN-1, for that matter) for sending
Ivan Komarov <ivan.komarov@pidgin.im>
parents: 30659
diff changeset
30 guint16 oscar_charset_check(const char *utf8);
30659
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
31
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
32 /**
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
33 * Take a string of the form charset="bleh" where bleh is
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
34 * one of us-ascii, utf-8, iso-8859-1, or unicode-2-0, and
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
35 * return a newly allocated string containing bleh.
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
36 */
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
37 gchar * oscar_encoding_extract(const char *encoding);
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
38
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
39 gchar * oscar_encoding_to_utf8(PurpleAccount *account, const char *encoding, const char *text, int textlen);
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
40 gchar * oscar_utf8_try_convert(PurpleAccount *account, OscarData *od, const gchar *msg);
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
41
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
42 /**
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
43 * This attemps to decode an incoming IM into a UTF8 string.
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
44 *
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
45 * We try decoding using two different character sets. The charset
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
46 * specified in the IM determines the order in which we attempt to
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
47 * decode. We do this because there are lots of broken ICQ clients
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
48 * that don't correctly send non-ASCII messages. And if Purple isn't
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
49 * able to deal with that crap, then people complain like banshees.
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
50 */
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
51 gchar * oscar_decode_im_part(PurpleAccount *account,
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
52 const char *sourcebn,
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
53 guint16 charset, guint16 charsubset,
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
54 const gchar *data, gsize datalen);
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
55
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
56 /**
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
57 * Figure out what encoding to use when sending a given outgoing message.
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
58 */
30660
cd134a2014f2 Stop using custom encodings (and LATIN-1, for that matter) for sending
Ivan Komarov <ivan.komarov@pidgin.im>
parents: 30659
diff changeset
59 gchar * oscar_convert_to_best_encoding(const gchar *msg, gsize *result_len, guint16 *charset, gchar **charsetstr);
30659
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
60
c663d8b84d1f Damn it.
Ivan Komarov <ivan.komarov@pidgin.im>
parents:
diff changeset
61 #endif

mercurial