src/unmime.c

   1 /*
   2  * Sylpheed -- a GTK+ based, lightweight, and fast e-mail client
   3  * Copyright (C) 1999-2009 Hiroyuki Yamamoto and the Claws Mail team
   4  *
   5  * This program is free software; you can redistribute it and/or modify
   6  * it under the terms of the GNU General Public License as published by
   7  * the Free Software Foundation; either version 3 of the License, or
   8  * (at your option) any later version.
   9  *
  10  * This program is distributed in the hope that it will be useful,
  11  * but WITHOUT ANY WARRANTY; without even the implied warranty of
  12  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  13  * GNU General Public License for more details.
  14  *
  15  * You should have received a copy of the GNU General Public License
  16  * along with this program. If not, see <http://www.gnu.org/licenses/>.
  17  *
  18  */
  19
  20 #ifdef HAVE_CONFIG_H
  21 #  include "config.h"
  22 #endif
  23
  24 #include <glib.h>
  25 #include <string.h>
  26 #include <ctype.h>
  27
  28 #include "codeconv.h"
  29 #include "base64.h"
  30 #include "quoted-printable.h"
  31
  32 #define ENCODED_WORD_BEGIN      "=?"
  33 #define ENCODED_WORD_END        "?="
  34
  35 /* Decodes headers based on RFC2045 and RFC2047. */
  36
  37 gchar *unmime_header(const gchar *encoded_str)
  38 {
  39         const gchar *p = encoded_str;
  40         const gchar *eword_begin_p, *encoding_begin_p, *text_begin_p,
  41                     *eword_end_p;
  42         gchar charset[32];
  43         gchar encoding;
  44         gchar *conv_str;
  45         GString *outbuf;
  46         gchar *out_str;
  47         gsize out_len;
  48
  49         outbuf = g_string_sized_new(strlen(encoded_str) * 2);
  50
  51         while (*p != '\0') {
  52                 gchar *decoded_text = NULL;
  53                 gint len;
  54
  55                 eword_begin_p = strstr(p, ENCODED_WORD_BEGIN);
  56                 if (!eword_begin_p) {
  57                         g_string_append(outbuf, p);
  58                         break;
  59                 }
  60                 encoding_begin_p = strchr(eword_begin_p + 2, '?');
  61                 if (!encoding_begin_p) {
  62                         g_string_append(outbuf, p);
  63                         break;
  64                 }
  65                 text_begin_p = strchr(encoding_begin_p + 1, '?');
  66                 if (!text_begin_p) {
  67                         g_string_append(outbuf, p);
  68                         break;
  69                 }
  70                 eword_end_p = strstr(text_begin_p + 1, ENCODED_WORD_END);
  71                 if (!eword_end_p) {
  72                         g_string_append(outbuf, p);
  73                         break;
  74                 }
  75
  76                 if (p == encoded_str) {
  77                         g_string_append_len(outbuf, p, eword_begin_p - p);
  78                         p = eword_begin_p;
  79                 } else {
  80                         /* ignore spaces between encoded words */
  81                         const gchar *sp;
  82
  83                         for (sp = p; sp < eword_begin_p; sp++) {
  84                                 if (!g_ascii_isspace(*sp)) {
  85                                         g_string_append_len
  86                                                 (outbuf, p, eword_begin_p - p);
  87                                         p = eword_begin_p;
  88                                         break;
  89                                 }
  90                         }
  91                 }
  92
  93                 len = MIN(sizeof(charset) - 1,
  94                           encoding_begin_p - (eword_begin_p + 2));
  95                 memcpy(charset, eword_begin_p + 2, len);
  96                 charset[len] = '\0';
  97                 encoding = g_ascii_toupper(*(encoding_begin_p + 1));
  98
  99                 if (encoding == 'B') {
 100                         decoded_text = g_malloc
 101                                 (eword_end_p - (text_begin_p + 1) + 1);
 102                         len = base64_decode(decoded_text, text_begin_p + 1,
 103                                             eword_end_p - (text_begin_p + 1));
 104                         decoded_text[len] = '\0';
 105                 } else if (encoding == 'Q') {
 106                         decoded_text = g_malloc
 107                                 (eword_end_p - (text_begin_p + 1) + 1);
 108                         len = qp_decode_q_encoding
 109                                 (decoded_text, text_begin_p + 1,
 110                                  eword_end_p - (text_begin_p + 1));
 111                 } else {
 112                         g_string_append_len(outbuf, p, eword_end_p + 2 - p);
 113                         p = eword_end_p + 2;
 114                         continue;
 115                 }
 116
 117                 /* convert to UTF-8 */
 118                 conv_str = conv_codeset_strdup(decoded_text, charset, NULL);
 119                 if (!conv_str || !g_utf8_validate(conv_str, -1, NULL)) {
 120                         g_free(conv_str);
 121                         conv_str = g_malloc(len + 1);
 122                         conv_utf8todisp(conv_str, len + 1, decoded_text);
 123                 }
 124                 g_string_append(outbuf, conv_str);
 125                 g_free(conv_str);
 126
 127                 g_free(decoded_text);
 128
 129                 p = eword_end_p + 2;
 130         }
 131
 132         out_str = outbuf->str;
 133         out_len = outbuf->len;
 134         g_string_free(outbuf, FALSE);
 135
 136         return g_realloc(out_str, out_len + 1);
 137 }