summaryrefslogtreecommitdiffstats
path: root/kioslaves/imap4/rfcdecoder.cc
blob: 4eeb207d5bc71a35a397868dbeca73e223bbc1c7 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
/**********************************************************************
 *
 *   rfcdecoder.cc  - handler for various rfc/mime encodings
 *   Copyright (C) 2000 s.carstens@gmx.de
 *
 *   This program is free software; you can redistribute it and/or modify
 *   it under the terms of the GNU General Public License as published by
 *   the Free Software Foundation; either version 2 of the License, or
 *   (at your option) any later version.
 *
 *   This program is distributed in the hope that it will be useful,
 *   but WITHOUT ANY WARRANTY; without even the implied warranty of
 *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 *   GNU General Public License for more details.
 *
 *   You should have received a copy of the GNU General Public License
 *   along with this program; if not, write to the Free Software
 *   Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.
 *
 *   Send comments and bug fixes to s.carstens@gmx.de
 *
 *********************************************************************/
#include "rfcdecoder.h"

#include <ctype.h>
#include <sys/types.h>

#include <stdio.h>
#include <stdlib.h>

#include <tqtextcodec.h>
#include <tqbuffer.h>
#include <tqregexp.h>
#include <kmdcodec.h>

// This part taken from rfc 2192 IMAP URL Scheme. C. Newman. September 1997.
// adapted to QT-Toolkit by Sven Carstens <s.carstens@gmx.de> 2000

static unsigned char base64chars[] =
  "ABCDEFGHIJKLMNOPTQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
#define UNDEFINED 64
#define MAXLINE  76

/* UTF16 definitions */
#define UTF16MASK       0x03FFUL
#define UTF16SHIFT      10
#define UTF16BASE       0x10000UL
#define UTF16HIGHSTART  0xD800UL
#define UTF16HIGHEND    0xDBFFUL
#define UTF16LOSTART    0xDC00UL
#define UTF16LOEND      0xDFFFUL

/* Convert an IMAP mailbox to a Unicode path
 */
TQString rfcDecoder::fromIMAP (const TQString & inSrc)
{
  unsigned char c, i, bitcount;
  unsigned long ucs4, utf16, bitbuf;
  unsigned char base64[256], utf8[6];
  unsigned long srcPtr = 0;
  TQCString dst;
  TQCString src = inSrc.ascii ();
  uint srcLen = inSrc.length();

  /* initialize modified base64 decoding table */
  memset (base64, UNDEFINED, sizeof (base64));
  for (i = 0; i < sizeof (base64chars); ++i)
  {
    base64[(int)base64chars[i]] = i;
  }

  /* loop until end of string */
  while (srcPtr < srcLen)
  {
    c = src[srcPtr++];
    /* deal with literal characters and &- */
    if (c != '&' || src[srcPtr] == '-')
    {
      /* encode literally */
      dst += c;
      /* skip over the '-' if this is an &- sequence */
      if (c == '&')
        srcPtr++;
    }
    else
    {
      /* convert modified UTF-7 -> UTF-16 -> UCS-4 -> UTF-8 -> HEX */
      bitbuf = 0;
      bitcount = 0;
      ucs4 = 0;
      while ((c = base64[(unsigned char) src[srcPtr]]) != UNDEFINED)
      {
        ++srcPtr;
        bitbuf = (bitbuf << 6) | c;
        bitcount += 6;
        /* enough bits for a UTF-16 character? */
        if (bitcount >= 16)
        {
          bitcount -= 16;
          utf16 = (bitcount ? bitbuf >> bitcount : bitbuf) & 0xffff;
          /* convert UTF16 to UCS4 */
          if (utf16 >= UTF16HIGHSTART && utf16 <= UTF16HIGHEND)
          {
            ucs4 = (utf16 - UTF16HIGHSTART) << UTF16SHIFT;
            continue;
          }
          else if (utf16 >= UTF16LOSTART && utf16 <= UTF16LOEND)
          {
            ucs4 += utf16 - UTF16LOSTART + UTF16BASE;
          }
          else
          {
            ucs4 = utf16;
          }
          /* convert UTF-16 range of UCS4 to UTF-8 */
          if (ucs4 <= 0x7fUL)
          {
            utf8[0] = ucs4;
            i = 1;
          }
          else if (ucs4 <= 0x7ffUL)
          {
            utf8[0] = 0xc0 | (ucs4 >> 6);
            utf8[1] = 0x80 | (ucs4 & 0x3f);
            i = 2;
          }
          else if (ucs4 <= 0xffffUL)
          {
            utf8[0] = 0xe0 | (ucs4 >> 12);
            utf8[1] = 0x80 | ((ucs4 >> 6) & 0x3f);
            utf8[2] = 0x80 | (ucs4 & 0x3f);
            i = 3;
          }
          else
          {
            utf8[0] = 0xf0 | (ucs4 >> 18);
            utf8[1] = 0x80 | ((ucs4 >> 12) & 0x3f);
            utf8[2] = 0x80 | ((ucs4 >> 6) & 0x3f);
            utf8[3] = 0x80 | (ucs4 & 0x3f);
            i = 4;
          }
          /* copy it */
          for (c = 0; c < i; ++c)
          {
            dst += utf8[c];
          }
        }
      }
      /* skip over trailing '-' in modified UTF-7 encoding */
      if (src[srcPtr] == '-')
        ++srcPtr;
    }
  }
  return TQString::fromUtf8 (dst.data ());
}

/* replace " with \" and \ with \\ " and \ characters */
TQString rfcDecoder::quoteIMAP(const TQString &src)
{
  uint len = src.length();
  TQString result;
  result.reserve(2 * len);
  for (unsigned int i = 0; i < len; i++)
  {
    if (src[i] == '"' || src[i] == '\\')
      result += '\\';
    result += src[i];
  }
  //result.squeeze(); - unnecessary and slow
  return result;
}

/* Convert Unicode path to modified UTF-7 IMAP mailbox
 */
TQString rfcDecoder::toIMAP (const TQString & inSrc)
{
  unsigned int utf8pos, utf8total, c, utf7mode, bitstogo, utf16flag;
  unsigned long ucs4, bitbuf;
  TQCString src = inSrc.utf8 ();
  TQString dst;

  ulong srcPtr = 0;
  utf7mode = 0;
  utf8total = 0;
  bitstogo = 0;
  utf8pos = 0;
  bitbuf = 0;
  ucs4 = 0;
  while (srcPtr < src.length ())
  {
    c = (unsigned char) src[srcPtr++];
    /* normal character? */
    if (c >= ' ' && c <= '~')
    {
      /* switch out of UTF-7 mode */
      if (utf7mode)
      {
        if (bitstogo)
        {
          dst += base64chars[(bitbuf << (6 - bitstogo)) & 0x3F];
          bitstogo = 0;
        }
        dst += '-';
        utf7mode = 0;
      }
      dst += c;
      /* encode '&' as '&-' */
      if (c == '&')
      {
        dst += '-';
      }
      continue;
    }
    /* switch to UTF-7 mode */
    if (!utf7mode)
    {
      dst += '&';
      utf7mode = 1;
    }
    /* Encode US-ASCII characters as themselves */
    if (c < 0x80)
    {
      ucs4 = c;
      utf8total = 1;
    }
    else if (utf8total)
    {
      /* save UTF8 bits into UCS4 */
      ucs4 = (ucs4 << 6) | (c & 0x3FUL);
      if (++utf8pos < utf8total)
      {
        continue;
      }
    }
    else
    {
      utf8pos = 1;
      if (c < 0xE0)
      {
        utf8total = 2;
        ucs4 = c & 0x1F;
      }
      else if (c < 0xF0)
      {
        utf8total = 3;
        ucs4 = c & 0x0F;
      }
      else
      {
        /* NOTE: can't convert UTF8 sequences longer than 4 */
        utf8total = 4;
        ucs4 = c & 0x03;
      }
      continue;
    }
    /* loop to split ucs4 into two utf16 chars if necessary */
    utf8total = 0;
    do
    {
      if (ucs4 >= UTF16BASE)
      {
        ucs4 -= UTF16BASE;
        bitbuf = (bitbuf << 16) | ((ucs4 >> UTF16SHIFT) + UTF16HIGHSTART);
        ucs4 = (ucs4 & UTF16MASK) + UTF16LOSTART;
        utf16flag = 1;
      }
      else
      {
        bitbuf = (bitbuf << 16) | ucs4;
        utf16flag = 0;
      }
      bitstogo += 16;
      /* spew out base64 */
      while (bitstogo >= 6)
      {
        bitstogo -= 6;
        dst += base64chars[(bitstogo ? (bitbuf >> bitstogo) : bitbuf) & 0x3F];
      }
    }
    while (utf16flag);
  }
  /* if in UTF-7 mode, finish in ASCII */
  if (utf7mode)
  {
    if (bitstogo)
    {
      dst += base64chars[(bitbuf << (6 - bitstogo)) & 0x3F];
    }
    dst += '-';
  }
  return quoteIMAP(dst);
}

//-----------------------------------------------------------------------------
TQString rfcDecoder::decodeQuoting(const TQString &aStr)
{
  TQString result;
  unsigned int strLength(aStr.length());
  for (unsigned int i = 0; i < strLength ; i++)
  {
    if (aStr[i] == "\\") i++;
    result += aStr[i];
  }
  return result;
}

//-----------------------------------------------------------------------------
TQTextCodec *
rfcDecoder::codecForName (const TQString & _str)
{
  if (_str.isEmpty ())
    return NULL;
  return TQTextCodec::codecForName (_str.lower ().
                                   replace ("windows", "cp").latin1 ());
}

//-----------------------------------------------------------------------------
const TQString
rfcDecoder::decodeRFC2047String (const TQString & _str)
{
  TQString throw_away;

  return decodeRFC2047String (_str, throw_away);
}

//-----------------------------------------------------------------------------
const TQString
rfcDecoder::decodeRFC2047String (const TQString & _str, TQString & charset)
{
  TQString throw_away;

  return decodeRFC2047String (_str, charset, throw_away);
}

//-----------------------------------------------------------------------------
const TQString
rfcDecoder::decodeRFC2047String (const TQString & _str, TQString & charset,
                                 TQString & language)
{
  //do we have a rfc string
  if (_str.find("=?") < 0)
    return _str;

  TQCString aStr = _str.ascii ();  // TQString.length() means Unicode chars
  TQCString result;
  char *pos, *beg, *end, *mid = NULL;
  TQCString str;
  char encoding = 0, ch;
  bool valid;
  const int maxLen = 200;
  int i;

//  result.truncate(aStr.length());
  for (pos = aStr.data (); *pos; pos++)
  {
    if (pos[0] != '=' || pos[1] != '?')
    {
      result += *pos;
      continue;
    }
    beg = pos + 2;
    end = beg;
    valid = TRUE;
    // parse charset name
    for (i = 2, pos += 2;
         i < maxLen && (*pos != '?' && (ispunct (*pos) || isalnum (*pos)));
         i++)
      pos++;
    if (*pos != '?' || i < 4 || i >= maxLen)
      valid = FALSE;
    else
    {
      charset = TQCString (beg, i - 1);  // -2 + 1 for the zero
      int pt = charset.findRev('*');
      if (pt != -1)
      {
        // save language for later usage
        language = charset.right (charset.length () - pt - 1);

        // tie off language as defined in rfc2047
        charset.truncate(pt);
      }
      // get encoding and check delimiting question marks
      encoding = toupper (pos[1]);
      if (pos[2] != '?'
          || (encoding != 'Q' && encoding != 'B' && encoding != 'q'
              && encoding != 'b'))
        valid = FALSE;
      pos += 3;
      i += 3;
//    kdDebug(7116) << "rfcDecoder::decodeRFC2047String - charset " << charset << " - language " << language << " - '" << pos << "'" << endl;
    }
    if (valid)
    {
      mid = pos;
      // search for end of encoded part
      while (i < maxLen && *pos && !(*pos == '?' && *(pos + 1) == '='))
      {
        i++;
        pos++;
      }
      end = pos + 2;            //end now points to the first char after the encoded string
      if (i >= maxLen || !*pos)
        valid = FALSE;
    }
    if (valid)
    {
      ch = *pos;
      *pos = '\0';
      str = TQCString (mid).left ((int) (mid - pos - 1));
      if (encoding == 'Q')
      {
        // decode quoted printable text
        for (i = str.length () - 1; i >= 0; i--)
          if (str[i] == '_')
            str[i] = ' ';
//    kdDebug(7116) << "rfcDecoder::decodeRFC2047String - before QP '" << str << "'" << endl;

        str = KCodecs::quotedPrintableDecode(str);
//    kdDebug(7116) << "rfcDecoder::decodeRFC2047String - after QP '" << str << "'" << endl;
      }
      else
      {
        // decode base64 text
        str = KCodecs::base64Decode(str);
      }
      *pos = ch;
      int len = str.length();
      for (i = 0; i < len; i++)
        result += (char) (TQChar) str[i];

      pos = end - 1;
    }
    else
    {
//    kdDebug(7116) << "rfcDecoder::decodeRFC2047String - invalid" << endl;
      //result += "=?";
      //pos = beg -1; // because pos gets increased shortly afterwards
      pos = beg - 2;
      result += *pos++;
      result += *pos;
    }
  }
  if (!charset.isEmpty ())
  {
    TQTextCodec *aCodec = codecForName (charset.ascii ());
    if (aCodec)
    {
//    kdDebug(7116) << "Codec is " << aCodec->name() << endl;
      return aCodec->toUnicode (result);
    }
  }
  return result;
}


//-----------------------------------------------------------------------------
const char especials[17] = "()<>@,;:\"/[]?.= ";

const TQString
rfcDecoder::encodeRFC2047String (const TQString & _str)
{
  if (_str.isEmpty ())
    return _str;
  const signed char *latin = reinterpret_cast<const signed char *>(_str.latin1()), *l, *start, *stop;
  char hexcode;
  int numQuotes, i;
  int rptr = 0;
  // My stats show this number results in 12 resize() out of 73,000
  int resultLen = 3 * _str.length() / 2;
  TQCString result(resultLen);
  
  while (*latin)
  {
    l = latin;
    start = latin;
    while (*l)
    {
      if (*l == 32)
        start = l + 1;
      if (*l < 0)
        break;
      l++;
    }
    if (*l)
    {
      numQuotes = 1;
      while (*l)
      {
        /* The encoded word must be limited to 75 character */
        for (i = 0; i < 16; i++)
          if (*l == especials[i])
            numQuotes++;
        if (*l < 0)
          numQuotes++;
        /* Stop after 58 = 75 - 17 characters or at "<user@host..." */
        if (l - start + 2 * numQuotes >= 58 || *l == 60)
          break;
        l++;
      }
      if (*l)
      {
        stop = l - 1;
        while (stop >= start && *stop != 32)
          stop--;
        if (stop <= start)
          stop = l;
      }
      else
        stop = l;
      if (resultLen - rptr - 1 <= start -  latin + 1 + 16 /* =?iso-88... */) {
        resultLen += (start - latin + 1) * 2 + 20; // more space
	result.resize(resultLen);
      }
      while (latin < start)
      {
        result[rptr++] = *latin;
        latin++;
      }
      strcpy(&result[rptr], "=?iso-8859-1?q?"); rptr += 15;
      if (resultLen - rptr - 1 <= 3*(stop - latin + 1)) {
        resultLen += (stop - latin + 1) * 4 + 20; // more space
	result.resize(resultLen);
      }
      while (latin < stop) // can add up to 3 chars/iteration
      {
        numQuotes = 0;
        for (i = 0; i < 16; i++)
          if (*latin == especials[i])
            numQuotes = 1;
        if (*latin < 0)
          numQuotes = 1;
        if (numQuotes)
        {
          result[rptr++] = '=';
          hexcode = ((*latin & 0xF0) >> 4) + 48;
          if (hexcode >= 58)
            hexcode += 7;
          result[rptr++] = hexcode;
          hexcode = (*latin & 0x0F) + 48;
          if (hexcode >= 58)
            hexcode += 7;
          result[rptr++] = hexcode;
        }
        else
        {
          result[rptr++] = *latin;
        }
        latin++;
      }
      result[rptr++] = '?';
      result[rptr++] = '=';
    }
    else
    {
      while (*latin)
      {
        if (rptr == resultLen - 1) {
          resultLen += 30;
          result.resize(resultLen);
        }
        result[rptr++] = *latin;
        latin++;
      }
    }
  }
  result[rptr] = 0;
  //free (latinStart);
  return result;
}


//-----------------------------------------------------------------------------
const TQString
rfcDecoder::encodeRFC2231String (const TQString & _str)
{
  if (_str.isEmpty ())
    return _str;
  signed char *latin = (signed char *) calloc (1, _str.length () + 1);
  char *latin_us = (char *) latin;
  strcpy (latin_us, _str.latin1 ());
  signed char *l = latin;
  char hexcode;
  int i;
  bool quote;
  while (*l)
  {
    if (*l < 0)
      break;
    l++;
  }
  if (!*l) {
    free(latin);
    return _str.ascii ();
  }
  TQCString result;
  l = latin;
  while (*l)
  {
    quote = *l < 0;
    for (i = 0; i < 16; i++)
      if (*l == especials[i])
        quote = true;
    if (quote)
    {
      result += "%";
      hexcode = ((*l & 0xF0) >> 4) + 48;
      if (hexcode >= 58)
        hexcode += 7;
      result += hexcode;
      hexcode = (*l & 0x0F) + 48;
      if (hexcode >= 58)
        hexcode += 7;
      result += hexcode;
    }
    else
    {
      result += *l;
    }
    l++;
  }
  free (latin);
  return result;
}


//-----------------------------------------------------------------------------
const TQString
rfcDecoder::decodeRFC2231String (const TQString & _str)
{
  int p = _str.find ('\'');

  //see if it is an rfc string
  if (p < 0)
    return _str;

  int l = _str.findRev ('\'');

  //second is language
  if (p >= l)
    return _str;

  //first is charset or empty
  TQString charset = _str.left (p);
  TQString st = _str.mid (l + 1);
  TQString language = _str.mid (p + 1, l - p - 1);

  //kdDebug(7116) << "Charset: " << charset << " Language: " << language << endl;

  char ch, ch2;
  p = 0;
  while (p < (int) st.length ())
  {
    if (st.at (p) == 37)
    {
      ch = st.tqat (p + 1).latin1 () - 48;
      if (ch > 16)
        ch -= 7;
      ch2 = st.tqat (p + 2).latin1 () - 48;
      if (ch2 > 16)
        ch2 -= 7;
      st.tqat (p) = ch * 16 + ch2;
      st.remove (p + 1, 2);
    }
    p++;
  }
  return st;
}