summaryrefslogtreecommitdiffstats
path: root/libkmime/kmime_parsers.cpp
blob: 202ce4bf48627037701e586dd2230ab9a0d1ad27 (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
/*
    kmime_parsers.cpp

    KMime, the KDE internet mail/usenet news message library.
    Copyright (c) 2001 the KMime authors.
    See file AUTHORS for details

    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.
    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, US
*/
#include "kmime_parsers.h"

#include <tqregexp.h>

using namespace KMime::Parser;

namespace KMime {
namespace Parser {


MultiPart::MultiPart(const TQCString &src, const TQCString &boundary)
{
  s_rc=src;
  b_oundary=boundary;
}


bool MultiPart::parse()
{
  TQCString b="--"+b_oundary, part;
  int pos1=0, pos2=0, blen=b.length();

  p_arts.clear();

  //find the first valid boundary
  while(1) {
    if( (pos1=s_rc.find(b.data(), pos1))==-1 || pos1==0 || s_rc[pos1-1]=='\n' ) //valid boundary found or no boundary at all
      break;
    pos1+=blen; //boundary found but not valid => skip it;
  }

  if(pos1>-1) {
    pos1+=blen;
    if(s_rc[pos1]=='-' && s_rc[pos1+1]=='-') // the only valid boundary is the end-boundary - this message is *really* broken
      pos1=-1; //we give up
    else if( (pos1-blen)>1 ) //preamble present
      p_reamble=s_rc.left(pos1-blen);
  }


  while(pos1>-1 && pos2>-1) {

    //skip the rest of the line for the first boundary - the message-part starts here
    if( (pos1=s_rc.find('\n', pos1))>-1 ) { //now search the next linebreak
      //now find the next valid boundary
      pos2=++pos1; //pos1 and pos2 point now to the beginning of the next line after the boundary
      while(1) {
        if( (pos2=s_rc.find(b.data(), pos2))==-1 || s_rc[pos2-1]=='\n' ) //valid boundary or no more boundaries found
          break;
        pos2+=blen; //boundary is invalid => skip it;
      }

      if(pos2==-1) { // no more boundaries found
        part=s_rc.mid(pos1, s_rc.length()-pos1); //take the rest of the string
        p_arts.append(part);
        pos1=-1;
        pos2=-1; //break;
      }
      else {
        part=s_rc.mid(pos1, pos2-pos1 - 1 ); // pos2 - 1 (\n) is part of the boundary (see RFC 2046, section 5.1.1)
        p_arts.append(part);
        pos2+=blen; //pos2 points now to the first charakter after the boundary
        if(s_rc[pos2]=='-' && s_rc[pos2+1]=='-') { //end-boundary
          pos1=pos2+2; //pos1 points now to the character directly after the end-boundary
          if( (pos1=s_rc.find('\n', pos1))>-1 ) //skipt the rest of this line
            e_pilouge=s_rc.mid(pos1+1, s_rc.length()-pos1-1); //everything after the end-boundary is considered as the epilouge
          pos1=-1;
          pos2=-1; //break
        }
        else {
          pos1=pos2; //the search continues ...
        }
      }
    }
  }

  return (!p_arts.isEmpty());
}

//============================================================================================


NonMimeParser::NonMimeParser(const TQCString &src) :
  s_rc(src), p_artNr(-1), t_otalNr(-1)
{}

/**
 * try to guess the mimetype from the file-extension
 */
TQCString NonMimeParser::guessMimeType(const TQCString& fileName)
{
  TQCString tmp, mimeType;
  int pos;

  if(!fileName.isEmpty()) {
    pos=fileName.findRev('.');
    if(pos++ != -1) {
      tmp=fileName.mid(pos, fileName.length()-pos).upper();
      if(tmp=="JPG" || tmp=="JPEG")       mimeType="image/jpeg";
      else if(tmp=="GIF")                 mimeType="image/gif";
      else if(tmp=="PNG")                 mimeType="image/png";
      else if(tmp=="TIFF" || tmp=="TIF")  mimeType="image/tiff";
      else if(tmp=="XPM")                 mimeType="image/x-xpm";
      else if(tmp=="XBM")                 mimeType="image/x-xbm";
      else if(tmp=="BMP")                 mimeType="image/x-bmp";
      else if(tmp=="TXT" ||
              tmp=="ASC" ||
              tmp=="H" ||
              tmp=="C" ||
              tmp=="CC" ||
              tmp=="CPP")                 mimeType="text/plain";
      else if(tmp=="HTML" || tmp=="HTM")  mimeType="text/html";
      else                                mimeType="application/octet-stream";
    }
    else mimeType="application/octet-stream";
  }
  else mimeType="application/octet-stream";

  return mimeType;
}

//============================================================================================


UUEncoded::UUEncoded(const TQCString &src, const TQCString &subject) :
  NonMimeParser(src), s_ubject(subject)
{}


bool UUEncoded::parse()
{
  int currentPos=0;
  bool success=true, firstIteration=true;

  while (success) {
    int beginPos=currentPos, uuStart=currentPos, endPos=0, lineCount=0, MCount=0, pos=0, len=0;
    bool containsBegin=false, containsEnd=false;
    TQCString tmp,fileName;

    if( (beginPos=s_rc.find(TQRegExp("begin [0-9][0-9][0-9]"),currentPos))>-1 && (beginPos==0 || s_rc.at(beginPos-1)=='\n') ) {
      containsBegin=true;
      uuStart=s_rc.find('\n', beginPos);
      if(uuStart==-1) {//no more line breaks found, we give up
        success = false;
        break;
      } else
        uuStart++; //points now at the beginning of the next line
    }
      else beginPos=currentPos;

    if ( (endPos=s_rc.find("\nend",(uuStart>0)? uuStart-1:0))==-1 )
      endPos=s_rc.length(); //no end found
    else
      containsEnd=true;

    if ((containsBegin && containsEnd) || firstIteration) {

      //printf("beginPos=%d , uuStart=%d , endPos=%d\n", beginPos, uuStart, endPos);
      //all lines in a uuencoded text start with 'M'
      for(int idx=uuStart; idx<endPos; idx++)
        if(s_rc[idx]=='\n') {
          lineCount++;
          if(idx+1<endPos && s_rc[idx+1]=='M') {
            idx++;
            MCount++;
          }
        }

      //printf("lineCount=%d , MCount=%d\n", lineCount, MCount);
      if( MCount==0 || (lineCount-MCount)>10 ||
          ((!containsBegin || !containsEnd) && (MCount<15)) ) {  // harder check for splitted-articles
        success = false;
        break; //too many "non-M-Lines" found, we give up
      }

      if( (!containsBegin || !containsEnd) && !s_ubject.isNull()) {  // message may be split up => parse subject
	TQRegExp rx("[0-9]+/[0-9]+");
	pos=rx.search(TQString(s_ubject), 0);
	len=rx.matchedLength();
        if(pos!=-1) {
          tmp=s_ubject.mid(pos, len);
          pos=tmp.find('/');
          p_artNr=tmp.left(pos).toInt();
          t_otalNr=tmp.right(tmp.length()-pos-1).toInt();
        } else {
          success = false;
          break; //no "part-numbers" found in the subject, we give up
        }
      }

      //everything before "begin" is text
      if(beginPos>0)
        t_ext.append(s_rc.mid(currentPos,beginPos-currentPos));

      if(containsBegin)
        fileName = s_rc.mid(beginPos+10, uuStart-beginPos-11); //everything between "begin ### " and the next LF is considered as the filename
      else
        fileName = "";
      f_ilenames.append(fileName);
      b_ins.append(s_rc.mid(uuStart, endPos-uuStart+1)); //everything beetween "begin" and "end" is uuencoded     
      m_imeTypes.append(guessMimeType(fileName));
      firstIteration=false;

      int next = s_rc.find('\n', endPos+1);
      if(next==-1) { //no more line breaks found, we give up
        success = false;
        break;
      } else
        next++; //points now at the beginning of the next line
      currentPos = next;

    } else {
      success = false;
    }
  }

  // append trailing text part of the article
  t_ext.append(s_rc.right(s_rc.length()-currentPos));

  return ((b_ins.count()>0) || isPartial());
}


//============================================================================================


YENCEncoded::YENCEncoded(const TQCString &src) :
  NonMimeParser(src)
{}


bool YENCEncoded::yencMeta(TQCString& src, const TQCString& name, int* value)
{
  bool found = false;
  TQCString sought=name + "=";

  int iPos=src.find( sought.data() );
  if (iPos>-1) {
    int pos1=src.find(' ', iPos);
    int pos2=src.find('\r', iPos);
    int pos3=src.find('\t', iPos);
    int pos4=src.find('\n', iPos);
    if (pos2>=0 && (pos1<0 || pos1>pos2))
      pos1=pos2;
    if (pos3>=0 && (pos1<0 || pos1>pos3))
      pos1=pos3;
    if (pos4>=0 && (pos1<0 || pos1>pos4))
      pos1=pos4;
    iPos=src.findRev( '=', pos1)+1;
    if (iPos<pos1) {
      char c=src.at( iPos);
      if ( c>='0' && c<='9') {
        found=true;
        *value=src.mid( iPos, pos1-iPos).toInt();
      }
    }
  }
  return found;
}


bool YENCEncoded::parse()
{
  int currentPos=0;
  bool success=true;

  while (success) {
    int beginPos=currentPos, yencStart=currentPos;
    bool containsPart=false;
    TQCString fileName,mimeType;

    if ((beginPos=s_rc.find("=ybegin ", currentPos))>-1 && ( beginPos==0 || s_rc.at( beginPos-1)=='\n') ) {
      yencStart=s_rc.find( '\n', beginPos);
      if (yencStart==-1) { // no more line breaks found, give up
        success = false;
        break;
      } else {
        yencStart++;
        if (s_rc.find("=ypart", yencStart)==yencStart) {
          containsPart=true;
          yencStart=s_rc.find( '\n', yencStart);
          if ( yencStart== -1) {
            success=false;
            break;
          }
          yencStart++;
        }
      }
      // Try to identify yenc meta data

      // Filenames can contain any embedded chars until end of line
      TQCString meta=s_rc.mid(beginPos, yencStart-beginPos);
      int namePos=meta.find("name=");
      if (namePos== -1) {
        success=false;
        break;
      }
      int eolPos=meta.find('\r', namePos);
      if (eolPos== -1)
      eolPos=meta.find('\n', namePos);    
      if (eolPos== -1) {
        success=false;
        break;
      }
      fileName=meta.mid(namePos+5, eolPos-(namePos+5));

      // Other metadata is integer
      int yencLine;
      if (!yencMeta(meta, "line", &yencLine)) {
        success=false;
        break;
      }
      int yencSize;
      if (!yencMeta( meta, "size", &yencSize)) {
        success=false;
        break;
      }

      int partBegin, partEnd;
      if (containsPart) {
        if (!yencMeta(meta, "part", &p_artNr)) {
          success=false;
          break;
        }
        if (!yencMeta(meta, "begin", &partBegin) || !
             yencMeta(meta, "end", &partEnd)) {
          success=false;
          break;
        }
        if (!yencMeta(meta, "total", &t_otalNr))
          t_otalNr=p_artNr+1;
        if (yencSize==partEnd-partBegin+1)
          t_otalNr=1; else
        yencSize=partEnd-partBegin+1;
      }

      // We have a valid yenc header; now we extract the binary data
      int totalSize=0;
      int pos=yencStart;
      int len=s_rc.length();
      bool lineStart=true;
      int lineLength=0;
      bool containsEnd=false;
      TQByteArray binary = TQByteArray(yencSize);
      while (pos<len) {
        int ch=s_rc.at(pos);
        if (ch<0)
          ch+=256;
        if (ch=='\r')
        {
          if (lineLength!=yencLine && totalSize!=yencSize)          
            break;          
          pos++;
        }
        else if (ch=='\n')
        {
          lineStart=true;
          lineLength=0;
          pos++;
        }
        else
        {
          if (ch=='=')
          {
            if (pos+1<len)
            {
              ch=s_rc.at( pos+1);
              if (lineStart && ch=='y')
              {
                containsEnd=true;
                break;
              }
              pos+=2;
              ch-=64+42;
              if (ch<0)
                ch+=256;
              if (totalSize>=yencSize)            
                break;            
              binary.at(totalSize++)=ch;
              lineLength++;
            }
            else            
              break;            
          }
          else
          {
            ch-=42;
            if (ch<0)
              ch+=256;
            if (totalSize>=yencSize)            
              break;
            binary.at(totalSize++)=ch;
            lineLength++;
            pos++;
          }
          lineStart=false;
        }
      }
      
      if (!containsEnd)
      {
        success=false;
        break;
      }
      if (totalSize!=yencSize)
      {        
        success=false;
        break;
      }

      // pos now points to =yend; get end data
      eolPos=s_rc.find('\n', pos);
      if (eolPos== -1)
      {
        success=false;
        break;
      }
      meta=s_rc.mid(pos, eolPos-pos);
      if (!yencMeta(meta, "size", &totalSize))
      {        
        success=false;
        break;
      }
      if (totalSize!=yencSize)
      {        
        success=false;
        break;
      }

      f_ilenames.append(fileName);
      m_imeTypes.append(guessMimeType( fileName));
      b_ins.append(binary);

      //everything before "begin" is text
      if(beginPos>0)
        t_ext.append(s_rc.mid(currentPos,beginPos-currentPos));
      currentPos = eolPos+1;

    } else {
      success = false;
    }
  }

  // append trailing text part of the article
  t_ext.append(s_rc.right(s_rc.length()-currentPos));

  return b_ins.count()>0;
}

} // namespace Parser
} // namespace KMime