Parent: [094e46] (diff)

Child: [02475f] (diff)

Download this file

mh_mail.cpp    487 lines (444 with data), 15.1 kB

  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
#ifndef lint
static char rcsid[] = "@(#$Id: mh_mail.cpp,v 1.29 2007-01-17 13:53:40 dockes Exp $ (C) 2005 J.F.Dockes";
#endif
/*
* 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.,
* 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
*/
#include <stdio.h>
#include <fcntl.h>
#include <errno.h>
#include <unistd.h>
#include <time.h>
#include <map>
#include <sstream>
#include "mimehandler.h"
#include "readfile.h"
#include "transcode.h"
#include "mimeparse.h"
#include "mh_mail.h"
#include "debuglog.h"
#include "smallut.h"
#include "mh_html.h"
// binc imap mime definitions
#include "mime.h"
using namespace std;
static const int maxdepth = 20;
MimeHandlerMail::~MimeHandlerMail()
{
delete m_bincdoc;
if (m_fd >= 0)
close(m_fd);
delete m_stream;
for (vector<MHMailAttach*>::iterator it = m_attachments.begin();
it != m_attachments.end(); it++) {
delete *it;
}
}
bool MimeHandlerMail::set_document_file(const string &fn)
{
LOGDEB(("MimeHandlerMail::set_document_file(%s)\n", fn.c_str()));
if (m_fd >= 0) {
close(m_fd);
m_fd = -1;
}
m_fd = open(fn.c_str(), 0);
if (m_fd < 0) {
LOGERR(("MimeHandlerMail::set_document_file: open(%s) errno %d\n",
fn.c_str(), errno));
return false;
}
delete m_bincdoc;
m_bincdoc = new Binc::MimeDocument;
m_bincdoc->parseFull(m_fd);
if (!m_bincdoc->isHeaderParsed() && !m_bincdoc->isAllParsed()) {
LOGERR(("MimeHandlerMail::mkDoc: mime parse error for %s\n",
fn.c_str()));
return false;
}
m_havedoc = true;
return true;
}
bool MimeHandlerMail::set_document_string(const string &msgtxt)
{
LOGDEB1(("MimeHandlerMail::set_document_string\n"));
LOGDEB2(("Message text: [%s]\n", msgtxt.c_str()));
delete m_stream;
m_stream = new stringstream(msgtxt);
delete m_bincdoc;
m_bincdoc = new Binc::MimeDocument;
m_bincdoc->parseFull(*m_stream);
if (!m_bincdoc->isHeaderParsed() && !m_bincdoc->isAllParsed()) {
LOGERR(("MimeHandlerMail::set_document_string: mime parse error\n"));
return false;
}
m_havedoc = true;
return true;
}
bool MimeHandlerMail::skip_to_document(const string& ipath)
{
LOGDEB(("MimeHandlerMail::skip_to_document(%s)\n", ipath.c_str()));
if (m_idx == -1) {
// No decoding done yet. If ipath is null need do nothing
if (ipath == "" || ipath == "-1")
return true;
// ipath points to attachment: need to decode message
if (!next_document()) {
LOGERR(("MimeHandlerMail::skip_to_doc: next_document failed\n"));
return false;
}
}
m_idx = atoi(ipath.c_str());
return true;
}
bool MimeHandlerMail::next_document()
{
LOGDEB(("MimeHandlerMail::next_document m_idx %d m_havedoc %d\n",
m_idx, m_havedoc));
if (!m_havedoc)
return false;
bool res = false;
if (m_idx == -1) {
m_metaData["mimetype"] = "text/plain";
res = processMsg(m_bincdoc, 0);
LOGDEB1(("MimeHandlerMail::next_document: mimetype %s\n",
m_metaData["mimetype"].c_str()));
} else {
res = processAttach();
}
m_idx++;
m_havedoc = m_idx < (int)m_attachments.size();
return res;
}
// Decode according to content transfer encoding
static bool decodeBody(const string& cte, const string& body, string& decoded,
const string** respp)
{
// By default, there is no encoding (7bit,8bit,raw). Also in case of
// decoding error
*respp = &body;
if (!stringlowercmp("quoted-printable", cte)) {
if (!qp_decode(body, decoded)) {
LOGERR(("decodeBody: quoted-printable decoding failed !\n"));
return false;
}
*respp = &decoded;
} else if (!stringlowercmp("base64", cte)) {
if (!base64_decode(body, decoded)) {
LOGERR(("decodeBody: base64 decoding failed !. body [%s]\n",
body.c_str()));
return false;
}
*respp = &decoded;
}
return true;
}
bool MimeHandlerMail::processAttach()
{
LOGDEB(("MimeHandlerMail::processAttach() m_idx %d\n", m_idx));
if (!m_havedoc)
return false;
if (m_idx >= (int)m_attachments.size()) {
m_havedoc = false;
return false;
}
MHMailAttach *att = m_attachments[m_idx];
LOGDEB1(("processAttach:content-type: %s\n", att->m_contentType.c_str()));
m_metaData["mimetype"] = att->m_contentType;
m_metaData["charset"] = att->m_charset;
m_metaData["filename"] = att->m_filename;
m_metaData["content"] = "";
string& body = m_metaData["content"];
att->m_part->getBody(body, 0, att->m_part->bodylength);
string decoded;
const string *bdp;
if (!decodeBody(att->m_contentTransferEncoding, body, decoded, &bdp)) {
return false;
}
if (bdp != &body)
body = decoded;
char nbuf[10];
sprintf(nbuf, "%d", m_idx);
m_metaData["ipath"] = nbuf;
return true;
}
// Transform a single message into a document. The subject becomes the
// title, and any simple body part with a content-type of text or html
// and content-disposition inline gets concatenated as text.
//
// If depth is not zero, we're called recursively for an
// message/rfc822 part and we must not touch the doc fields except the
// text
bool MimeHandlerMail::processMsg(Binc::MimePart *doc, int depth)
{
LOGDEB2(("MimeHandlerMail::processMsg: depth %d\n", depth));
if (depth++ >= maxdepth) {
// Have to stop somewhere
LOGINFO(("MimeHandlerMail::processMsg: maxdepth %d exceeded\n",
maxdepth));
// Return true anyway, better to index partially than not at all
return true;
}
// Handle some headers.
string& text = m_metaData["content"];
Binc::HeaderItem hi;
string transcoded;
if (doc->h.getFirstHeader("From", hi)) {
rfc2047_decode(hi.getValue(), transcoded);
text += string("From: ") + transcoded + string("\n");
if (depth == 1) {
m_metaData["author"] = transcoded;
}
}
if (doc->h.getFirstHeader("To", hi)) {
rfc2047_decode(hi.getValue(), transcoded);
text += string("To: ") + transcoded + string("\n");
}
if (doc->h.getFirstHeader("Date", hi)) {
rfc2047_decode(hi.getValue(), transcoded);
if (depth == 1) {
time_t t = rfc2822DateToUxTime(transcoded);
if (t != (time_t)-1) {
char ascuxtime[100];
sprintf(ascuxtime, "%ld", (long)t);
m_metaData["modificationdate"] = ascuxtime;
} else {
// Leave mtime field alone, ftime will be used instead.
LOGDEB(("rfc2822Date...: failed: [%s]\n", transcoded.c_str()));
}
}
text += string("Date: ") + transcoded + string("\n");
}
if (doc->h.getFirstHeader("Subject", hi)) {
rfc2047_decode(hi.getValue(), transcoded);
if (depth == 1)
m_metaData["title"] = transcoded;
text += string("Subject: ") + transcoded + string("\n");
}
text += '\n';
LOGDEB2(("MimeHandlerMail::processMsg:ismultipart %d mime subtype '%s'\n",
doc->isMultipart(), doc->getSubType().c_str()));
walkmime(doc, depth);
LOGDEB2(("MimeHandlerMail::processMsg:text:[%s]\n",
m_metaData["content"].c_str()));
return true;
}
// Recursively walk the message mime parts and concatenate all the
// inline html or text that we find anywhere.
//
// RFC2046 reminder:
// Top level media types:
// Simple: text, image, audio, video, application,
// Composite: multipart, message.
//
// multipart can be mixed, signed, alternative, parallel, digest.
// message/rfc822 may also be of interest.
void MimeHandlerMail::walkmime(Binc::MimePart* doc, int depth)
{
LOGDEB2(("MimeHandlerMail::walkmime: depth %d\n", depth));
if (depth++ >= maxdepth) {
LOGINFO(("walkmime: max depth (%d) exceeded\n", maxdepth));
return;
}
string& out = m_metaData["content"];
if (doc->isMultipart()) {
LOGDEB2(("walkmime: ismultipart %d subtype '%s'\n",
doc->isMultipart(), doc->getSubType().c_str()));
// We only handle alternative, related and mixed (no digests).
std::vector<Binc::MimePart>::iterator it;
if (!stringicmp("mixed", doc->getSubType()) ||
!stringicmp("signed", doc->getSubType()) ||
!stringicmp("related", doc->getSubType())) {
// Multipart mixed and related: process each part.
for (it = doc->members.begin(); it != doc->members.end();it++) {
walkmime(&(*it), depth);
}
} else if (!stringicmp("alternative", doc->getSubType())) {
// Multipart/alternative: look for a text/plain part, then html.
// Process if found
std::vector<Binc::MimePart>::iterator ittxt, ithtml;
ittxt = ithtml = doc->members.end();
int i = 1;
for (it = doc->members.begin();
it != doc->members.end(); it++, i++) {
// Get and parse content-type header
Binc::HeaderItem hi;
if (!it->h.getFirstHeader("Content-Type", hi)) {
LOGDEB(("walkmime:no ctent-type header for part %d\n", i));
continue;
}
MimeHeaderValue content_type;
parseMimeHeaderValue(hi.getValue(), content_type);
LOGDEB2(("walkmime: C-type: %s\n",content_type.value.c_str()));
if (!stringlowercmp("text/plain", content_type.value))
ittxt = it;
else if (!stringlowercmp("text/html", content_type.value))
ithtml = it;
}
if (ittxt != doc->members.end()) {
LOGDEB2(("walkmime: alternative: chose text/plain part\n"))
walkmime(&(*ittxt), depth);
} else if (ithtml != doc->members.end()) {
LOGDEB2(("walkmime: alternative: chose text/html part\n"))
walkmime(&(*ithtml), depth);
}
}
return;
}
// Part is not multipart: it must be either simple or message. Take
// a look at interesting headers and a possible filename parameter
// Get and parse content-type header.
Binc::HeaderItem hi;
string ctt = "text/plain";
if (doc->h.getFirstHeader("Content-Type", hi)) {
ctt = hi.getValue();
}
LOGDEB2(("walkmime:content-type: %s\n", ctt.c_str()));
MimeHeaderValue content_type;
parseMimeHeaderValue(ctt, content_type);
// Get and parse Content-Disposition header
string ctd = "inline";
if (doc->h.getFirstHeader("Content-Disposition", hi)) {
ctd = hi.getValue();
}
MimeHeaderValue content_disposition;
parseMimeHeaderValue(ctd, content_disposition);
LOGDEB2(("Content_disposition:[%s]\n", content_disposition.value.c_str()));
string dispindic;
if (stringlowercmp("inline", content_disposition.value))
dispindic = "Attachment";
else
dispindic = "Inline";
// See if we have a filename.
string filename;
map<string,string>::const_iterator it;
it = content_disposition.params.find(string("filename"));
if (it != content_disposition.params.end())
filename = it->second;
if (doc->isMessageRFC822()) {
LOGDEB2(("walkmime: message/RFC822 part\n"));
// The first part is the already parsed message. Call
// processMsg instead of walkmime so that mail headers get
// printed. The depth will tell it what to do
if (doc->members.empty()) {
//??
return;
}
out += "\n";
if (m_forPreview)
out += "[" + dispindic + " " + content_type.value + ": ";
out += filename;
if (m_forPreview)
out += "]";
out += "\n\n";
processMsg(&doc->members[0], depth);
return;
}
// "Simple" part.
LOGDEB2(("walkmime: simple part\n"));
// Normally the default charset is us-ascii. But it happens that
// 8 bit chars exist in a message that is stated as us-ascii. Ie the
// mailer used by yahoo support ('KANA') does this. We could convert
// to iso-8859 only if the transfer-encoding is 8 bit, or test for
// actual 8 bit chars, but what the heck, le'ts use 8859-1 as default
string charset = "iso-8859-1";
it = content_type.params.find(string("charset"));
if (it != content_type.params.end())
charset = it->second;
if (charset.empty() ||
!stringlowercmp("us-ascii", charset) ||
!stringlowercmp("default", charset) ||
!stringlowercmp("x-user-defined", charset) ||
!stringlowercmp("x-unknown", charset) ||
!stringlowercmp("unknown", charset) ) {
charset = "iso-8859-1";
}
// Content transfer encoding
string cte = "7bit";
if (doc->h.getFirstHeader("Content-Transfer-Encoding", hi)) {
cte = hi.getValue();
}
// If the Content-Disposition is not inline, we treat it as
// attachment, as per rfc2183. We don't process attachments
// for now, except for indexing/displaying the file name
// If it is inline but not text or html, same thing.
if (stringlowercmp("inline", content_disposition.value) ||
(stringlowercmp("text/plain", content_type.value) &&
stringlowercmp("text/html", content_type.value)) ) {
if (!filename.empty()) {
out += "\n";
if (m_forPreview)
out += "[" + dispindic + " " + content_type.value + ": ";
out += filename;
if (m_forPreview)
out += "]";
out += "\n\n";
}
LOGDEB(("walkmime: pushing attchmnt fn [%s]\n", filename.c_str()));
MHMailAttach *att = new MHMailAttach;
if (att == 0) {
LOGERR(("Out of memory\n"));
return;
}
att->m_contentType = content_type.value;
stringtolower(att->m_contentType);
att->m_filename = filename;
att->m_charset = charset;
att->m_contentTransferEncoding = cte;
att->m_part = doc;
m_attachments.push_back(att);
return;
}
// We are dealing with an inline part of text/plain or text/html type
LOGDEB2(("walkmime: final: body start offset %d, length %d\n",
doc->getBodyStartOffset(), doc->getBodyLength()));
string body;
doc->getBody(body, 0, doc->bodylength);
string decoded;
const string *bdp;
if (!decodeBody(cte, body, decoded, &bdp)) {
LOGERR(("MimeHandlerMail::walkmime: failed decoding body\n"));
}
if (bdp != &body)
body = decoded;
// Handle html stripping and transcoding to utf8
string utf8;
const string *putf8 = 0;
if (!stringlowercmp("text/html", content_type.value)) {
MimeHandlerHtml mh("text/html");
mh.set_property(Dijon::Filter::OPERATING_MODE,
m_forPreview ? "view" : "index");
mh.set_property(Dijon::Filter::DEFAULT_CHARSET, charset);
mh.set_document_string(body);
mh.next_document();
map<string, string>::const_iterator it =
mh.get_meta_data().find("content");
if (it != mh.get_meta_data().end())
out += it->second;
} else {
// Transcode to utf-8
LOGDEB1(("walkmime: transcoding from %s to UTF-8\n", charset.c_str()));
if (!transcode(body, utf8, charset, "UTF-8")) {
LOGERR(("walkmime: transcode failed from cs '%s' to UTF-8\n",
charset.c_str()));
out += body;
} else {
out += utf8;
}
}
if (out.length() && out[out.length()-1] != '\n')
out += '\n';
LOGDEB2(("walkmime: out now: [%s]\n", out.c_str()));
}