|
1
|
|
|
<?php |
|
2
|
|
|
// +-----------------------------------------------------------------------+ |
|
3
|
|
|
// | Copyright (c) 2002 Richard Heyes | |
|
4
|
|
|
// | All rights reserved. | |
|
5
|
|
|
// | | |
|
6
|
|
|
// | Redistribution and use in source and binary forms, with or without | |
|
7
|
|
|
// | modification, are permitted provided that the following conditions | |
|
8
|
|
|
// | are met: | |
|
9
|
|
|
// | | |
|
10
|
|
|
// | o Redistributions of source code must retain the above copyright | |
|
11
|
|
|
// | notice, this list of conditions and the following disclaimer. | |
|
12
|
|
|
// | o Redistributions in binary form must reproduce the above copyright | |
|
13
|
|
|
// | notice, this list of conditions and the following disclaimer in the | |
|
14
|
|
|
// | documentation and/or other materials provided with the distribution.| |
|
15
|
|
|
// | o The names of the authors may not be used to endorse or promote | |
|
16
|
|
|
// | products derived from this software without specific prior written | |
|
17
|
|
|
// | permission. | |
|
18
|
|
|
// | | |
|
19
|
|
|
// | THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS | |
|
20
|
|
|
// | "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT | |
|
21
|
|
|
// | LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR | |
|
22
|
|
|
// | A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT | |
|
23
|
|
|
// | OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, | |
|
24
|
|
|
// | SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT | |
|
25
|
|
|
// | LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, | |
|
26
|
|
|
// | DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY | |
|
27
|
|
|
// | THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT | |
|
28
|
|
|
// | (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE | |
|
29
|
|
|
// | OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. | |
|
30
|
|
|
// | | |
|
31
|
|
|
// +-----------------------------------------------------------------------+ |
|
32
|
|
|
// | Author: Richard Heyes <[email protected]> | |
|
33
|
|
|
// +-----------------------------------------------------------------------+ |
|
34
|
|
|
|
|
35
|
|
|
require_once XHELP_PEAR_PATH . '/PEAR.php'; |
|
36
|
|
|
|
|
37
|
|
|
/** |
|
38
|
|
|
* +----------------------------- IMPORTANT ------------------------------+ |
|
39
|
|
|
* | Usage of this class compared to native php extensions such as | |
|
40
|
|
|
* | mailparse or imap, is slow and may be feature deficient. If available| |
|
41
|
|
|
* | you are STRONGLY recommended to use the php extensions. | |
|
42
|
|
|
* +----------------------------------------------------------------------+ |
|
43
|
|
|
* |
|
44
|
|
|
* Mime Decoding class |
|
45
|
|
|
* |
|
46
|
|
|
* This class will parse a raw mime email and return |
|
47
|
|
|
* the structure. Returned structure is similar to |
|
48
|
|
|
* that returned by imap_fetchstructure(). |
|
49
|
|
|
* |
|
50
|
|
|
* USAGE: (assume $input is your raw email) |
|
51
|
|
|
* |
|
52
|
|
|
* $decode = new Mail_mimeDecode($input, "\r\n"); |
|
53
|
|
|
* $structure = $decode->decode(); |
|
54
|
|
|
* print_r($structure); |
|
55
|
|
|
* |
|
56
|
|
|
* Or statically: |
|
57
|
|
|
* |
|
58
|
|
|
* $params['input'] = $input; |
|
59
|
|
|
* $structure = Mail_mimeDecode::decode($params); |
|
60
|
|
|
* print_r($structure); |
|
61
|
|
|
* |
|
62
|
|
|
* TODO: |
|
63
|
|
|
* - Implement further content types, eg. multipart/parallel, |
|
64
|
|
|
* perhaps even message/partial. |
|
65
|
|
|
* |
|
66
|
|
|
* @author Richard Heyes <[email protected]> |
|
67
|
|
|
* @version $Revision: 1.2 $ |
|
68
|
|
|
*/ |
|
69
|
|
|
class Mail_mimeDecode extends PEAR |
|
70
|
|
|
{ |
|
71
|
|
|
/** |
|
72
|
|
|
* The raw email to decode |
|
73
|
|
|
* @var string |
|
74
|
|
|
*/ |
|
75
|
|
|
public $_input; |
|
76
|
|
|
/** |
|
77
|
|
|
* The header part of the input |
|
78
|
|
|
* @var string |
|
79
|
|
|
*/ |
|
80
|
|
|
public $_header; |
|
81
|
|
|
/** |
|
82
|
|
|
* The body part of the input |
|
83
|
|
|
* @var string |
|
84
|
|
|
*/ |
|
85
|
|
|
public $_body; |
|
86
|
|
|
/** |
|
87
|
|
|
* If an error occurs, this is used to store the message |
|
88
|
|
|
* @var string |
|
89
|
|
|
*/ |
|
90
|
|
|
public $_error; |
|
91
|
|
|
/** |
|
92
|
|
|
* Flag to determine whether to include bodies in the |
|
93
|
|
|
* returned object. |
|
94
|
|
|
* @var bool |
|
95
|
|
|
*/ |
|
96
|
|
|
public $_include_bodies; |
|
97
|
|
|
/** |
|
98
|
|
|
* Flag to determine whether to decode bodies |
|
99
|
|
|
* @var bool |
|
100
|
|
|
*/ |
|
101
|
|
|
public $_decode_bodies; |
|
102
|
|
|
/** |
|
103
|
|
|
* Flag to determine whether to decode headers |
|
104
|
|
|
* @var bool |
|
105
|
|
|
*/ |
|
106
|
|
|
public $_decode_headers; |
|
107
|
|
|
/** |
|
108
|
|
|
* If invoked from a class, $this will be set. This has problematic |
|
109
|
|
|
* connotations for calling decode() statically. Hence this variable |
|
110
|
|
|
* is used to determine if we are indeed being called statically or |
|
111
|
|
|
* via an object. |
|
112
|
|
|
*/ |
|
113
|
|
|
public $mailMimeDecode; |
|
114
|
|
|
|
|
115
|
|
|
/** |
|
116
|
|
|
* Constructor. |
|
117
|
|
|
* |
|
118
|
|
|
* Sets up the object, initialise the variables, and splits and |
|
119
|
|
|
* stores the header and body of the input. |
|
120
|
|
|
* |
|
121
|
|
|
* @param mixed $input |
|
122
|
|
|
*/ |
|
123
|
|
|
public function __construct($input) |
|
124
|
|
|
{ |
|
125
|
|
|
[$header, $body] = $this->_splitBodyHeader($input); |
|
126
|
|
|
|
|
127
|
|
|
$this->_input = $input; |
|
128
|
|
|
$this->_header = $header; |
|
129
|
|
|
$this->_body = $body; |
|
130
|
|
|
$this->_decode_bodies = false; |
|
131
|
|
|
$this->_include_bodies = true; |
|
132
|
|
|
|
|
133
|
|
|
$this->mailMimeDecode = true; |
|
134
|
|
|
} |
|
135
|
|
|
|
|
136
|
|
|
/** |
|
137
|
|
|
* Begins the decoding process. If called statically |
|
138
|
|
|
* it will create an object and call the decode() method |
|
139
|
|
|
* of it. |
|
140
|
|
|
* |
|
141
|
|
|
* @param null|mixed $params |
|
142
|
|
|
* @return object Decoded results |
|
143
|
|
|
*/ |
|
144
|
|
|
public function decode($params = null) |
|
145
|
|
|
{ |
|
146
|
|
|
// Have we been called statically? If so, create an object and pass details to that. |
|
147
|
|
|
if (!isset($this->mailMimeDecode) && isset($params['input'])) { |
|
148
|
|
|
$obj = new self($params['input']); |
|
149
|
|
|
$structure = $obj->decode($params); |
|
150
|
|
|
// Called statically but no input |
|
151
|
|
|
} elseif (isset($this->mailMimeDecode)) { |
|
152
|
|
|
$this->_include_bodies = $params['include_bodies'] ?? false; |
|
153
|
|
|
$this->_decode_bodies = $params['decode_bodies'] ?? false; |
|
154
|
|
|
$this->_decode_headers = $params['decode_headers'] ?? false; |
|
155
|
|
|
|
|
156
|
|
|
$structure = $this->_decode($this->_header, $this->_body); |
|
|
|
|
|
|
157
|
|
|
if (false === $structure) { |
|
158
|
|
|
$structure = $this->raiseError($this->_error); |
|
159
|
|
|
} |
|
160
|
|
|
} else { |
|
161
|
|
|
return PEAR::raiseError('Called statically and no input given'); |
|
162
|
|
|
// Called via an object |
|
163
|
|
|
} |
|
164
|
|
|
|
|
165
|
|
|
return $structure; |
|
166
|
|
|
} |
|
167
|
|
|
|
|
168
|
|
|
/** |
|
169
|
|
|
* Performs the decoding. Decodes the body string passed to it |
|
170
|
|
|
* If it finds certain content-types it will call itself in a |
|
171
|
|
|
* recursive fashion |
|
172
|
|
|
* |
|
173
|
|
|
* @param array $headers |
|
174
|
|
|
* @param string $body |
|
175
|
|
|
* @param string $default_ctype |
|
176
|
|
|
* @return object|false Results of decoding process |
|
177
|
|
|
*/ |
|
178
|
|
|
public function _decode(array $headers, string $body, string $default_ctype = 'text/plain') |
|
179
|
|
|
{ |
|
180
|
|
|
$return = new stdClass(); |
|
181
|
|
|
$headers = $this->_parseHeaders($headers); |
|
182
|
|
|
|
|
183
|
|
|
foreach ($headers as $value) { |
|
184
|
|
|
if (isset($return->headers[mb_strtolower($value['name'])]) && !is_array($return->headers[mb_strtolower($value['name'])])) { |
|
185
|
|
|
$return->headers[mb_strtolower($value['name'])] = [$return->headers[mb_strtolower($value['name'])]]; |
|
186
|
|
|
$return->headers[mb_strtolower($value['name'])][] = $value['value']; |
|
187
|
|
|
} elseif (isset($return->headers[mb_strtolower($value['name'])])) { |
|
188
|
|
|
$return->headers[mb_strtolower($value['name'])][] = $value['value']; |
|
189
|
|
|
} else { |
|
190
|
|
|
$return->headers[mb_strtolower($value['name'])] = $value['value']; |
|
191
|
|
|
} |
|
192
|
|
|
} |
|
193
|
|
|
|
|
194
|
|
|
reset($headers); |
|
195
|
|
|
// while (list($key, $value) = each($headers)) { |
|
196
|
|
|
foreach ($headers as $key => $value) { |
|
197
|
|
|
$headers[$key]['name'] = \mb_strtolower($value['name']); |
|
198
|
|
|
switch ($headers[$key]['name']) { |
|
199
|
|
|
case 'content-type': |
|
200
|
|
|
$content_type = $this->_parseHeaderValue($headers[$key]['value']); |
|
201
|
|
|
|
|
202
|
|
|
if (preg_match('/([0-9a-z+.-]+)\/([0-9a-z+.-]+)/i', $content_type['value'], $regs)) { |
|
203
|
|
|
$return->ctype_primary = $regs[1]; |
|
204
|
|
|
$return->ctype_secondary = $regs[2]; |
|
205
|
|
|
} |
|
206
|
|
|
|
|
207
|
|
|
if (isset($content_type['other'])) { |
|
208
|
|
|
foreach ($content_type['other'] as $p_name => $p_value) { |
|
209
|
|
|
$return->ctype_parameters[$p_name] = $p_value; |
|
210
|
|
|
} |
|
211
|
|
|
} |
|
212
|
|
|
break; |
|
213
|
|
|
case 'content-disposition': |
|
214
|
|
|
$content_disposition = $this->_parseHeaderValue($headers[$key]['value']); |
|
215
|
|
|
$return->disposition = $content_disposition['value']; |
|
216
|
|
|
if (isset($content_disposition['other'])) { |
|
217
|
|
|
foreach ($content_disposition['other'] as $p_name => $p_value) { |
|
218
|
|
|
$return->d_parameters[$p_name] = $p_value; |
|
219
|
|
|
} |
|
220
|
|
|
} |
|
221
|
|
|
break; |
|
222
|
|
|
case 'content-transfer-encoding': |
|
223
|
|
|
$content_transfer_encoding = $this->_parseHeaderValue($headers[$key]['value']); |
|
224
|
|
|
break; |
|
225
|
|
|
} |
|
226
|
|
|
} |
|
227
|
|
|
|
|
228
|
|
|
if (isset($content_type)) { |
|
229
|
|
|
switch (mb_strtolower($content_type['value'])) { |
|
230
|
|
|
case 'text/plain': |
|
231
|
|
|
$encoding = isset($content_transfer_encoding) ? $content_transfer_encoding['value'] : '7bit'; |
|
232
|
|
|
$this->_include_bodies ? $return->body = ($this->_decode_bodies ? $this->_decodeBody($body, $encoding) : $body) : null; |
|
233
|
|
|
break; |
|
234
|
|
|
case 'text/html': |
|
235
|
|
|
$encoding = isset($content_transfer_encoding) ? $content_transfer_encoding['value'] : '7bit'; |
|
236
|
|
|
$this->_include_bodies ? $return->body = ($this->_decode_bodies ? $this->_decodeBody($body, $encoding) : $body) : null; |
|
237
|
|
|
break; |
|
238
|
|
|
case 'multipart/parallel': |
|
239
|
|
|
case 'multipart/report': // RFC1892 |
|
240
|
|
|
case 'multipart/signed': // PGP |
|
241
|
|
|
case 'multipart/digest': |
|
242
|
|
|
case 'multipart/alternative': |
|
243
|
|
|
case 'multipart/related': |
|
244
|
|
|
case 'multipart/mixed': |
|
245
|
|
|
if (!isset($content_type['other']['boundary'])) { |
|
246
|
|
|
$this->_error = 'No boundary found for ' . $content_type['value'] . ' part'; |
|
247
|
|
|
|
|
248
|
|
|
return false; |
|
249
|
|
|
} |
|
250
|
|
|
|
|
251
|
|
|
$default_ctype = ('multipart/digest' === \mb_strtolower($content_type['value'])) ? 'message/rfc822' : 'text/plain'; |
|
252
|
|
|
|
|
253
|
|
|
$parts = $this->_boundarySplit($body, $content_type['other']['boundary']); |
|
254
|
|
|
foreach ($parts as $iValue) { |
|
255
|
|
|
[$part_header, $part_body] = $this->_splitBodyHeader($iValue); |
|
256
|
|
|
$part = $this->_decode($part_header, $part_body, $default_ctype); |
|
257
|
|
|
if (false == $part) { |
|
258
|
|
|
$part = $this->raiseError($this->_error); |
|
259
|
|
|
} |
|
260
|
|
|
$return->parts[] = $part; |
|
261
|
|
|
} |
|
262
|
|
|
break; |
|
263
|
|
|
case 'message/rfc822': |
|
264
|
|
|
$obj = new self($body); |
|
265
|
|
|
$return->parts[] = $obj->decode(['include_bodies' => $this->_include_bodies]); |
|
266
|
|
|
unset($obj); |
|
267
|
|
|
break; |
|
268
|
|
|
default: |
|
269
|
|
|
if (!isset($content_transfer_encoding['value'])) { |
|
270
|
|
|
$content_transfer_encoding['value'] = '7bit'; |
|
271
|
|
|
} |
|
272
|
|
|
$this->_include_bodies ? $return->body = ($this->_decode_bodies ? $this->_decodeBody($body, $content_transfer_encoding['value']) : $body) : null; |
|
273
|
|
|
break; |
|
274
|
|
|
} |
|
275
|
|
|
} else { |
|
276
|
|
|
$ctype = explode('/', $default_ctype); |
|
277
|
|
|
$return->ctype_primary = $ctype[0]; |
|
278
|
|
|
$return->ctype_secondary = $ctype[1]; |
|
279
|
|
|
$this->_include_bodies ? $return->body = ($this->_decode_bodies ? $this->_decodeBody($body) : $body) : null; |
|
280
|
|
|
} |
|
281
|
|
|
|
|
282
|
|
|
return $return; |
|
283
|
|
|
} |
|
284
|
|
|
|
|
285
|
|
|
/** |
|
286
|
|
|
* Given the output of the above function, this will return an |
|
287
|
|
|
* array of references to the parts, indexed by mime number. |
|
288
|
|
|
* |
|
289
|
|
|
* @param object $structure The structure to go through |
|
290
|
|
|
* @param bool $no_refs |
|
291
|
|
|
* @param string $mime_number Internal use only. |
|
292
|
|
|
* @param string $prepend |
|
293
|
|
|
* @return array Mime numbers |
|
294
|
|
|
*/ |
|
295
|
|
|
public function &getMimeNumbers(object $structure, bool $no_refs, string $mime_number = '', string $prepend = ''): array |
|
296
|
|
|
{ |
|
297
|
|
|
$return = []; |
|
298
|
|
|
if (!empty($structure->parts)) { |
|
299
|
|
|
if ('' != $mime_number) { |
|
300
|
|
|
$structure->mime_id = $prepend . $mime_number; |
|
301
|
|
|
$return[$prepend . $mime_number] = &$structure; |
|
302
|
|
|
} |
|
303
|
|
|
foreach ($structure->parts as $i => $iValue) { |
|
304
|
|
|
if (!empty($structure->headers['content-type']) && 0 === mb_strpos(mb_strtolower($structure->headers['content-type']), 'message/')) { |
|
305
|
|
|
$prepend .= $mime_number . '.'; |
|
306
|
|
|
$_mime_number = ''; |
|
307
|
|
|
} else { |
|
308
|
|
|
$_mime_number = ('' == $mime_number ? $i + 1 : sprintf('%s.%s', $mime_number, $i + 1)); |
|
309
|
|
|
} |
|
310
|
|
|
|
|
311
|
|
|
$arr = &self::getMimeNumbers($structure->parts[$i], $no_refs, $_mime_number, $prepend); |
|
|
|
|
|
|
312
|
|
|
foreach ($arr as $key => $val) { |
|
313
|
|
|
$no_refs ? $return[$key] = '' : $return[$key] = &$val; |
|
314
|
|
|
} |
|
315
|
|
|
} |
|
316
|
|
|
} else { |
|
317
|
|
|
if ('' === $mime_number) { |
|
318
|
|
|
$mime_number = '1'; |
|
319
|
|
|
} |
|
320
|
|
|
$structure->mime_id = $prepend . $mime_number; |
|
321
|
|
|
$no_refs ? $return[$prepend . $mime_number] = '' : $return[$prepend . $mime_number] = &$structure; |
|
322
|
|
|
} |
|
323
|
|
|
|
|
324
|
|
|
return $return; |
|
325
|
|
|
} |
|
326
|
|
|
|
|
327
|
|
|
/** |
|
328
|
|
|
* Given a string containing a header and body |
|
329
|
|
|
* section, this function will split them (at the first |
|
330
|
|
|
* blank line) and return them. |
|
331
|
|
|
* |
|
332
|
|
|
* @param mixed $input |
|
333
|
|
|
* @return array|false Contains header and body section |
|
334
|
|
|
*/ |
|
335
|
|
|
public function _splitBodyHeader($input) |
|
336
|
|
|
{ |
|
337
|
|
|
if (preg_match("/^(.*?)\r?\n\r?\n(.*)/s", $input, $match)) { |
|
338
|
|
|
return [$match[1], $match[2]]; |
|
339
|
|
|
} |
|
340
|
|
|
$this->_error = 'Could not split header and body'; |
|
341
|
|
|
|
|
342
|
|
|
return false; |
|
343
|
|
|
} |
|
344
|
|
|
|
|
345
|
|
|
/** |
|
346
|
|
|
* Parse headers given in $input and return |
|
347
|
|
|
* as assoc array. |
|
348
|
|
|
* |
|
349
|
|
|
* @param mixed $input |
|
350
|
|
|
* @return array Contains parsed headers |
|
351
|
|
|
*/ |
|
352
|
|
|
public function _parseHeaders($input): array |
|
353
|
|
|
{ |
|
354
|
|
|
if ('' !== $input) { |
|
355
|
|
|
// Unfold the input |
|
356
|
|
|
$input = preg_replace("/\r?\n/", "\r\n", $input); |
|
357
|
|
|
$input = preg_replace("/\r\n(\t| )+/", ' ', $input); |
|
358
|
|
|
$headers = explode("\r\n", trim($input)); |
|
359
|
|
|
|
|
360
|
|
|
foreach ($headers as $value) { |
|
361
|
|
|
$hdr_name = mb_substr($value, 0, $pos = mb_strpos($value, ':')); |
|
362
|
|
|
$hdr_value = mb_substr($value, $pos + 1); |
|
363
|
|
|
if (' ' === $hdr_value[0]) { |
|
364
|
|
|
$hdr_value = mb_substr($hdr_value, 1); |
|
365
|
|
|
} |
|
366
|
|
|
|
|
367
|
|
|
$return[] = [ |
|
368
|
|
|
'name' => $hdr_name, |
|
369
|
|
|
'value' => $this->_decode_headers ? $this->_decodeHeader($hdr_value) : $hdr_value, |
|
370
|
|
|
]; |
|
371
|
|
|
} |
|
372
|
|
|
} else { |
|
373
|
|
|
$return = []; |
|
374
|
|
|
} |
|
375
|
|
|
|
|
376
|
|
|
return $return; |
|
|
|
|
|
|
377
|
|
|
} |
|
378
|
|
|
|
|
379
|
|
|
/** |
|
380
|
|
|
* Function to parse a header value, |
|
381
|
|
|
* extract first part, and any secondary |
|
382
|
|
|
* parts (after ;) This function is not as |
|
383
|
|
|
* robust as it could be. Eg. header comments |
|
384
|
|
|
* in the wrong place will probably break it. |
|
385
|
|
|
* |
|
386
|
|
|
* @param mixed $input |
|
387
|
|
|
* @return array Contains parsed result |
|
388
|
|
|
*/ |
|
389
|
|
|
public function _parseHeaderValue($input): array |
|
390
|
|
|
{ |
|
391
|
|
|
if (false !== ($pos = mb_strpos($input, ';'))) { |
|
392
|
|
|
$return['value'] = trim(mb_substr($input, 0, $pos)); |
|
|
|
|
|
|
393
|
|
|
$input = trim(mb_substr($input, $pos + 1)); |
|
394
|
|
|
|
|
395
|
|
|
if ('' !== $input) { |
|
396
|
|
|
// This splits on a semi-colon, if there's no preceeding backslash |
|
397
|
|
|
// Can't handle if it's in double quotes however. (Of course anyone |
|
398
|
|
|
// sending that needs a good slap). |
|
399
|
|
|
$parameters = preg_split('/\s*(?<!\\\\);\s*/i', $input); |
|
400
|
|
|
|
|
401
|
|
|
foreach ($parameters as $i => $iValue) { |
|
402
|
|
|
$param_name = mb_substr($iValue, 0, $pos = mb_strpos($iValue, '=')); |
|
403
|
|
|
$param_value = mb_substr($iValue, $pos + 1); |
|
404
|
|
|
if ('"' === $param_value[0]) { |
|
405
|
|
|
$param_value = mb_substr($param_value, 1, -1); |
|
406
|
|
|
} |
|
407
|
|
|
$return['other'][$param_name] = $param_value; |
|
408
|
|
|
$return['other'][mb_strtolower($param_name)] = $param_value; |
|
409
|
|
|
} |
|
410
|
|
|
} |
|
411
|
|
|
} else { |
|
412
|
|
|
$return['value'] = trim($input); |
|
413
|
|
|
} |
|
414
|
|
|
|
|
415
|
|
|
return $return; |
|
416
|
|
|
} |
|
417
|
|
|
|
|
418
|
|
|
/** |
|
419
|
|
|
* This function splits the input based |
|
420
|
|
|
* on the given boundary |
|
421
|
|
|
* |
|
422
|
|
|
* @param string $input |
|
423
|
|
|
* @param string $boundary |
|
424
|
|
|
* @return array Contains array of resulting mime parts |
|
425
|
|
|
*/ |
|
426
|
|
|
public function _boundarySplit(string $input, string $boundary): array |
|
427
|
|
|
{ |
|
428
|
|
|
$tmp = explode('--' . $boundary, $input); |
|
429
|
|
|
|
|
430
|
|
|
for ($i = 1; $i < count($tmp) - 1; ++$i) { |
|
431
|
|
|
$parts[] = $tmp[$i]; |
|
432
|
|
|
} |
|
433
|
|
|
|
|
434
|
|
|
return $parts; |
|
|
|
|
|
|
435
|
|
|
} |
|
436
|
|
|
|
|
437
|
|
|
/** |
|
438
|
|
|
* Given a header, this function will decode it |
|
439
|
|
|
* according to RFC2047. Probably not *exactly* |
|
440
|
|
|
* conformant, but it does pass all the given |
|
441
|
|
|
* examples (in RFC2047). |
|
442
|
|
|
* |
|
443
|
|
|
* @param mixed $input |
|
444
|
|
|
* @return string Decoded header value |
|
445
|
|
|
*/ |
|
446
|
|
|
public function _decodeHeader($input): string |
|
447
|
|
|
{ |
|
448
|
|
|
// Remove white space between encoded-words |
|
449
|
|
|
$input = preg_replace('/(=\?[^?]+\?(q|b)\?[^?]*\?=)(\s)+=\?/i', '\1=?', $input); |
|
450
|
|
|
|
|
451
|
|
|
// For each encoded-word... |
|
452
|
|
|
while (preg_match('/(=\?([^?]+)\?(q|b)\?([^?]*)\?=)/i', $input, $matches)) { |
|
453
|
|
|
$encoded = $matches[1]; |
|
454
|
|
|
$charset = $matches[2]; |
|
|
|
|
|
|
455
|
|
|
$encoding = $matches[3]; |
|
456
|
|
|
$text = $matches[4]; |
|
457
|
|
|
|
|
458
|
|
|
switch (mb_strtolower($encoding)) { |
|
459
|
|
|
case 'b': |
|
460
|
|
|
$text = base64_decode($text, true); |
|
461
|
|
|
break; |
|
462
|
|
|
case 'q': |
|
463
|
|
|
$text = str_replace('_', ' ', $text); |
|
464
|
|
|
preg_match_all('/=([a-f0-9]{2})/i', $text, $matches); |
|
465
|
|
|
foreach ($matches[1] as $value) { |
|
466
|
|
|
$text = str_replace('=' . $value, chr(hexdec($value)), $text); |
|
|
|
|
|
|
467
|
|
|
} |
|
468
|
|
|
break; |
|
469
|
|
|
} |
|
470
|
|
|
|
|
471
|
|
|
$input = str_replace($encoded, $text, $input); |
|
472
|
|
|
} |
|
473
|
|
|
|
|
474
|
|
|
return $input; |
|
475
|
|
|
} |
|
476
|
|
|
|
|
477
|
|
|
/** |
|
478
|
|
|
* Given a body string and an encoding type, |
|
479
|
|
|
* this function will decode and return it. |
|
480
|
|
|
* |
|
481
|
|
|
* @param mixed $input |
|
482
|
|
|
* @param mixed $encoding |
|
483
|
|
|
* @return string Decoded body |
|
484
|
|
|
*/ |
|
485
|
|
|
public function _decodeBody($input, $encoding = '7bit'): string |
|
486
|
|
|
{ |
|
487
|
|
|
switch ($encoding) { |
|
488
|
|
|
case '7bit': |
|
489
|
|
|
return $input; |
|
490
|
|
|
case 'quoted-printable': |
|
491
|
|
|
return $this->_quotedPrintableDecode($input); |
|
492
|
|
|
case 'base64': |
|
493
|
|
|
return base64_decode($input, true); |
|
494
|
|
|
default: |
|
495
|
|
|
return $input; |
|
496
|
|
|
} |
|
497
|
|
|
} |
|
498
|
|
|
|
|
499
|
|
|
/** |
|
500
|
|
|
* Given a quoted-printable string, this |
|
501
|
|
|
* function will decode and return it. |
|
502
|
|
|
* |
|
503
|
|
|
* @param mixed $input |
|
504
|
|
|
* @return string Decoded body |
|
505
|
|
|
*/ |
|
506
|
|
|
public function _quotedPrintableDecode($input): string |
|
507
|
|
|
{ |
|
508
|
|
|
// Remove soft line breaks |
|
509
|
|
|
$input = preg_replace("/=\r?\n/", '', $input); |
|
510
|
|
|
|
|
511
|
|
|
// Replace encoded characters |
|
512
|
|
|
$input = preg_replace('/=([a-f0-9]{2})/ie', "chr(hexdec('\\1'))", $input); |
|
513
|
|
|
|
|
514
|
|
|
return $input; |
|
515
|
|
|
} |
|
516
|
|
|
|
|
517
|
|
|
/** |
|
518
|
|
|
* Checks the input for uuencoded files and returns |
|
519
|
|
|
* an array of them. Can be called statically, eg: |
|
520
|
|
|
* |
|
521
|
|
|
* $files =& Mail_mimeDecode::uudecode($some_text); |
|
522
|
|
|
* |
|
523
|
|
|
* It will check for the begin 666 ... end syntax |
|
524
|
|
|
* however and won't just blindly decode whatever you |
|
525
|
|
|
* pass it. |
|
526
|
|
|
* |
|
527
|
|
|
* @param mixed $input |
|
528
|
|
|
* @return array Decoded bodies, filenames and permissions |
|
529
|
|
|
* @author Unknown |
|
530
|
|
|
*/ |
|
531
|
|
|
public function &uudecode($input): array |
|
532
|
|
|
{ |
|
533
|
|
|
// Find all uuencoded sections |
|
534
|
|
|
preg_match_all("/begin ([0-7]{3}) (.+)\r?\n(.+)\r?\nend/Us", $input, $matches); |
|
535
|
|
|
|
|
536
|
|
|
for ($j = 0, $jMax = count($matches[3]); $j < $jMax; $j++) { |
|
537
|
|
|
$str = $matches[3][$j]; |
|
538
|
|
|
$filename = $matches[2][$j]; |
|
539
|
|
|
$fileperm = $matches[1][$j]; |
|
540
|
|
|
|
|
541
|
|
|
$file = ''; |
|
542
|
|
|
$str = preg_split("/\r?\n/", trim($str)); |
|
543
|
|
|
|
|
544
|
|
|
foreach ($str as $i => $iValue) { |
|
545
|
|
|
$pos = 1; |
|
546
|
|
|
$d = 0; |
|
547
|
|
|
$len = (((ord(mb_substr($iValue, 0, 1)) - 32) - ' ') & 077); |
|
548
|
|
|
|
|
549
|
|
|
while (($d + 3 <= $len) and ($pos + 4 <= mb_strlen($iValue))) { |
|
550
|
|
|
$c0 = (ord(mb_substr($iValue, $pos, 1)) ^ 0x20); |
|
551
|
|
|
$c1 = (ord(mb_substr($iValue, $pos + 1, 1)) ^ 0x20); |
|
552
|
|
|
$c2 = (ord(mb_substr($iValue, $pos + 2, 1)) ^ 0x20); |
|
553
|
|
|
$c3 = (ord(mb_substr($iValue, $pos + 3, 1)) ^ 0x20); |
|
554
|
|
|
$file .= chr(((($c0 - ' ') & 077) << 2) | ((($c1 - ' ') & 077) >> 4)); |
|
555
|
|
|
|
|
556
|
|
|
$file .= chr(((($c1 - ' ') & 077) << 4) | ((($c2 - ' ') & 077) >> 2)); |
|
557
|
|
|
|
|
558
|
|
|
$file .= chr(((($c2 - ' ') & 077) << 6) | (($c3 - ' ') & 077)); |
|
559
|
|
|
|
|
560
|
|
|
$pos += 4; |
|
561
|
|
|
$d += 3; |
|
562
|
|
|
} |
|
563
|
|
|
|
|
564
|
|
|
if (($d + 2 <= $len) && ($pos + 3 <= mb_strlen($iValue))) { |
|
565
|
|
|
$c0 = (ord(mb_substr($iValue, $pos, 1)) ^ 0x20); |
|
566
|
|
|
$c1 = (ord(mb_substr($iValue, $pos + 1, 1)) ^ 0x20); |
|
567
|
|
|
$c2 = (ord(mb_substr($iValue, $pos + 2, 1)) ^ 0x20); |
|
568
|
|
|
$file .= chr(((($c0 - ' ') & 077) << 2) | ((($c1 - ' ') & 077) >> 4)); |
|
569
|
|
|
|
|
570
|
|
|
$file .= chr(((($c1 - ' ') & 077) << 4) | ((($c2 - ' ') & 077) >> 2)); |
|
571
|
|
|
|
|
572
|
|
|
$pos += 3; |
|
573
|
|
|
$d += 2; |
|
574
|
|
|
} |
|
575
|
|
|
|
|
576
|
|
|
if (($d + 1 <= $len) && ($pos + 2 <= mb_strlen($iValue))) { |
|
577
|
|
|
$c0 = (ord(mb_substr($iValue, $pos, 1)) ^ 0x20); |
|
578
|
|
|
$c1 = (ord(mb_substr($iValue, $pos + 1, 1)) ^ 0x20); |
|
579
|
|
|
$file .= chr(((($c0 - ' ') & 077) << 2) | ((($c1 - ' ') & 077) >> 4)); |
|
580
|
|
|
} |
|
581
|
|
|
} |
|
582
|
|
|
$files[] = ['filename' => $filename, 'fileperm' => $fileperm, 'filedata' => $file]; |
|
583
|
|
|
} |
|
584
|
|
|
|
|
585
|
|
|
return $files; |
|
|
|
|
|
|
586
|
|
|
} |
|
587
|
|
|
|
|
588
|
|
|
/** |
|
589
|
|
|
* getSendArray() returns the arguments required for Mail::send() |
|
590
|
|
|
* used to build the arguments for a mail::send() call |
|
591
|
|
|
* |
|
592
|
|
|
* Usage: |
|
593
|
|
|
* $mailtext = Full email (for example generated by a template) |
|
594
|
|
|
* $decoder = new Mail_mimeDecode($mailtext); |
|
595
|
|
|
* $parts = $decoder->getSendArray(); |
|
596
|
|
|
* if (!PEAR::isError($parts) { |
|
597
|
|
|
* list($recipents,$headers,$body) = $parts; |
|
598
|
|
|
* $mail = Mail::factory('smtp'); |
|
599
|
|
|
* $mail->send($recipents,$headers,$body); |
|
600
|
|
|
* } else { |
|
601
|
|
|
* echo $parts->message; |
|
602
|
|
|
* } |
|
603
|
|
|
* @return array|\PEAR_Error array of recipeint, headers,body or Pear_Error |
|
604
|
|
|
* @author Alan Knowles <[email protected]> |
|
605
|
|
|
*/ |
|
606
|
|
|
public function getSendArray() |
|
607
|
|
|
{ |
|
608
|
|
|
// prevent warning if this is not set |
|
609
|
|
|
$this->_decode_headers = false; |
|
610
|
|
|
$headerlist = $this->_parseHeaders($this->_header); |
|
611
|
|
|
$to = ''; |
|
612
|
|
|
if (!$headerlist) { |
|
|
|
|
|
|
613
|
|
|
return $this->raiseError('Message did not contain headers'); |
|
614
|
|
|
} |
|
615
|
|
|
foreach ($headerlist as $item) { |
|
616
|
|
|
$header[$item['name']] = $item['value']; |
|
617
|
|
|
switch (mb_strtolower($item['name'])) { |
|
618
|
|
|
case 'to': |
|
619
|
|
|
case 'cc': |
|
620
|
|
|
case 'bcc': |
|
621
|
|
|
$to = ',' . $item['value']; |
|
622
|
|
|
// no break |
|
623
|
|
|
default: |
|
624
|
|
|
break; |
|
625
|
|
|
} |
|
626
|
|
|
} |
|
627
|
|
|
if ('' === $to) { |
|
|
|
|
|
|
628
|
|
|
return $this->raiseError('Message did not contain any recipents'); |
|
629
|
|
|
} |
|
630
|
|
|
$to = mb_substr($to, 1); |
|
631
|
|
|
|
|
632
|
|
|
return [$to, $header, $this->_body]; |
|
|
|
|
|
|
633
|
|
|
} |
|
634
|
|
|
|
|
635
|
|
|
/** |
|
636
|
|
|
* Returns a xml copy of the output of |
|
637
|
|
|
* Mail_mimeDecode::decode. Pass the output in as the |
|
638
|
|
|
* argument. This function can be called statically. Eg: |
|
639
|
|
|
* |
|
640
|
|
|
* $output = $obj->decode(); |
|
641
|
|
|
* $xml = Mail_mimeDecode::getXML($output); |
|
642
|
|
|
* |
|
643
|
|
|
* The DTD used for this should have been in the package. Or |
|
644
|
|
|
* alternatively you can get it from cvs, or here: |
|
645
|
|
|
* https://www.phpguru.org/xmail/xmail.dtd. |
|
646
|
|
|
* |
|
647
|
|
|
* @param mixed $input |
|
648
|
|
|
* @return string XML version of input |
|
649
|
|
|
*/ |
|
650
|
|
|
public function getXML($input): string |
|
651
|
|
|
{ |
|
652
|
|
|
$crlf = "\r\n"; |
|
653
|
|
|
$output = '<?xml version=\'1.0\'?>' . $crlf . '<!DOCTYPE email SYSTEM "https://www.phpguru.org/xmail/xmail.dtd">' . $crlf . '<email>' . $crlf . self::_getXML($input) . '</email>'; |
|
|
|
|
|
|
654
|
|
|
|
|
655
|
|
|
return $output; |
|
656
|
|
|
} |
|
657
|
|
|
|
|
658
|
|
|
/** |
|
659
|
|
|
* Function that does the actual conversion to xml. Does a single |
|
660
|
|
|
* mimepart at a time. |
|
661
|
|
|
* |
|
662
|
|
|
* @param mixed $input |
|
663
|
|
|
* @param mixed $indent |
|
664
|
|
|
* @return string XML version of input |
|
665
|
|
|
*/ |
|
666
|
|
|
public function _getXML($input, $indent = 1): string |
|
667
|
|
|
{ |
|
668
|
|
|
$htab = "\t"; |
|
669
|
|
|
$crlf = "\r\n"; |
|
670
|
|
|
$output = ''; |
|
671
|
|
|
$headers = @(array)$input->headers; |
|
672
|
|
|
|
|
673
|
|
|
foreach ($headers as $hdr_name => $hdr_value) { |
|
674
|
|
|
// Multiple headers with this name |
|
675
|
|
|
if (is_array($hdr_value)) { |
|
676
|
|
|
for ($i = 0, $iMax = count($hdr_value); $i < $iMax; ++$i) { |
|
677
|
|
|
$output .= self::_getXML_helper($hdr_name, $hdr_value[$i], $indent); |
|
|
|
|
|
|
678
|
|
|
} |
|
679
|
|
|
// Only one header of this sort |
|
680
|
|
|
} else { |
|
681
|
|
|
$output .= self::_getXML_helper($hdr_name, $hdr_value, $indent); |
|
682
|
|
|
} |
|
683
|
|
|
} |
|
684
|
|
|
|
|
685
|
|
|
if (!empty($input->parts)) { |
|
686
|
|
|
for ($i = 0, $iMax = count($input->parts); $i < $iMax; ++$i) { |
|
687
|
|
|
$output .= $crlf . str_repeat($htab, $indent) . '<mimepart>' . $crlf . self::_getXML($input->parts[$i], $indent + 1) . str_repeat($htab, $indent) . '</mimepart>' . $crlf; |
|
|
|
|
|
|
688
|
|
|
} |
|
689
|
|
|
} elseif (isset($input->body)) { |
|
690
|
|
|
$output .= $crlf . str_repeat($htab, $indent) . '<body><![CDATA[' . $input->body . ']]></body>' . $crlf; |
|
691
|
|
|
} |
|
692
|
|
|
|
|
693
|
|
|
return $output; |
|
694
|
|
|
} |
|
695
|
|
|
|
|
696
|
|
|
/** |
|
697
|
|
|
* Helper function to _getXML(). Returns xml of a header. |
|
698
|
|
|
* |
|
699
|
|
|
* @param mixed $hdr_name |
|
700
|
|
|
* @param mixed $hdr_value |
|
701
|
|
|
* @param mixed $indent |
|
702
|
|
|
* @return string XML version of input |
|
703
|
|
|
*/ |
|
704
|
|
|
public function _getXML_helper($hdr_name, $hdr_value, $indent): string |
|
705
|
|
|
{ |
|
706
|
|
|
$htab = "\t"; |
|
707
|
|
|
$crlf = "\r\n"; |
|
708
|
|
|
$return = ''; |
|
|
|
|
|
|
709
|
|
|
|
|
710
|
|
|
$new_hdr_value = ('received' !== $hdr_name) ? self::_parseHeaderValue($hdr_value) : ['value' => $hdr_value]; |
|
|
|
|
|
|
711
|
|
|
$new_hdr_name = str_replace(' ', '-', ucwords(str_replace('-', ' ', $hdr_name))); |
|
712
|
|
|
|
|
713
|
|
|
// Sort out any parameters |
|
714
|
|
|
if (!empty($new_hdr_value['other'])) { |
|
715
|
|
|
foreach ($new_hdr_value['other'] as $paramname => $paramvalue) { |
|
716
|
|
|
$params[] = str_repeat($htab, $indent) |
|
717
|
|
|
. $htab |
|
718
|
|
|
. '<parameter>' |
|
719
|
|
|
. $crlf |
|
720
|
|
|
. str_repeat($htab, $indent) |
|
721
|
|
|
. $htab |
|
722
|
|
|
. $htab |
|
723
|
|
|
. '<paramname>' |
|
724
|
|
|
. htmlspecialchars($paramname, ENT_QUOTES | ENT_HTML5) |
|
725
|
|
|
. '</paramname>' |
|
726
|
|
|
. $crlf |
|
727
|
|
|
. str_repeat($htab, $indent) |
|
728
|
|
|
. $htab |
|
729
|
|
|
. $htab |
|
730
|
|
|
. '<paramvalue>' |
|
731
|
|
|
. htmlspecialchars($paramvalue, ENT_QUOTES | ENT_HTML5) |
|
732
|
|
|
. '</paramvalue>' |
|
733
|
|
|
. $crlf |
|
734
|
|
|
. str_repeat($htab, $indent) |
|
735
|
|
|
. $htab |
|
736
|
|
|
. '</parameter>' |
|
737
|
|
|
. $crlf; |
|
738
|
|
|
} |
|
739
|
|
|
|
|
740
|
|
|
$params = implode('', $params); |
|
|
|
|
|
|
741
|
|
|
} else { |
|
742
|
|
|
$params = ''; |
|
743
|
|
|
} |
|
744
|
|
|
|
|
745
|
|
|
$return = str_repeat($htab, $indent) . '<header>' . $crlf . str_repeat($htab, $indent) . $htab . '<headername>' . htmlspecialchars($new_hdr_name, ENT_QUOTES | ENT_HTML5) . '</headername>' . $crlf . str_repeat($htab, $indent) . $htab . '<headervalue>' . htmlspecialchars( |
|
746
|
|
|
$new_hdr_value['value'], |
|
747
|
|
|
ENT_QUOTES | ENT_HTML5 |
|
748
|
|
|
) . '</headervalue>' . $crlf . $params . str_repeat($htab, $indent) . '</header>' . $crlf; |
|
749
|
|
|
|
|
750
|
|
|
return $return; |
|
751
|
|
|
} |
|
752
|
|
|
} // End of class |
|
753
|
|
|
|