1 | <?php |
---|
2 | /* vim: set expandtab tabstop=4 shiftwidth=4 softtabstop=4: */ |
---|
3 | // +-----------------------------------------------------------------------+ |
---|
4 | // | Copyright (c) 2002-2003 Richard Heyes | |
---|
5 | // | Copyright (c) 2003-2005 The PHP Group | |
---|
6 | // | All rights reserved. | |
---|
7 | // | | |
---|
8 | // | Redistribution and use in source and binary forms, with or without | |
---|
9 | // | modification, are permitted provided that the following conditions | |
---|
10 | // | are met: | |
---|
11 | // | | |
---|
12 | // | o Redistributions of source code must retain the above copyright | |
---|
13 | // | notice, this list of conditions and the following disclaimer. | |
---|
14 | // | o Redistributions in binary form must reproduce the above copyright | |
---|
15 | // | notice, this list of conditions and the following disclaimer in the | |
---|
16 | // | documentation and/or other materials provided with the distribution.| |
---|
17 | // | o The names of the authors may not be used to endorse or promote | |
---|
18 | // | products derived from this software without specific prior written | |
---|
19 | // | permission. | |
---|
20 | // | | |
---|
21 | // | THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS | |
---|
22 | // | "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT | |
---|
23 | // | LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR | |
---|
24 | // | A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT | |
---|
25 | // | OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, | |
---|
26 | // | SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT | |
---|
27 | // | LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, | |
---|
28 | // | DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY | |
---|
29 | // | THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT | |
---|
30 | // | (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE | |
---|
31 | // | OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. | |
---|
32 | // | | |
---|
33 | // +-----------------------------------------------------------------------+ |
---|
34 | // | Author: Richard Heyes <richard@phpguru.org> | |
---|
35 | // +-----------------------------------------------------------------------+ |
---|
36 | |
---|
37 | require_once dirname(__FILE__) . '/../PEAR.php'; |
---|
38 | |
---|
39 | /** |
---|
40 | * +----------------------------- IMPORTANT ------------------------------+ |
---|
41 | * | Usage of this class compared to native php extensions such as | |
---|
42 | * | mailparse or imap, is slow and may be feature deficient. If available| |
---|
43 | * | you are STRONGLY recommended to use the php extensions. | |
---|
44 | * +----------------------------------------------------------------------+ |
---|
45 | * |
---|
46 | * Mime Decoding class |
---|
47 | * |
---|
48 | * This class will parse a raw mime email and return |
---|
49 | * the structure. Returned structure is similar to |
---|
50 | * that returned by imap_fetchstructure(). |
---|
51 | * |
---|
52 | * USAGE: (assume $input is your raw email) |
---|
53 | * |
---|
54 | * $decode = new Mail_mimeDecode($input, "\r\n"); |
---|
55 | * $structure = $decode->decode(); |
---|
56 | * print_r($structure); |
---|
57 | * |
---|
58 | * Or statically: |
---|
59 | * |
---|
60 | * $params['input'] = $input; |
---|
61 | * $structure = Mail_mimeDecode::decode($params); |
---|
62 | * print_r($structure); |
---|
63 | * |
---|
64 | * TODO: |
---|
65 | * o Implement multipart/appledouble |
---|
66 | * o UTF8: ??? |
---|
67 | |
---|
68 | > 4. We have also found a solution for decoding the UTF-8 |
---|
69 | > headers. Therefore I made the following function: |
---|
70 | > |
---|
71 | > function decode_utf8($txt) { |
---|
72 | > $trans=array("?#8216;"=>"探","撤"=>"短","?"=>"?#8226;","徹" |
---|
73 | =>"?#8250;"); |
---|
74 | > $txt=strtr($txt,$trans); |
---|
75 | > return(utf8_decode($txt)); |
---|
76 | > } |
---|
77 | > |
---|
78 | > And I have inserted the following line to the class: |
---|
79 | > |
---|
80 | > if (strtolower($charset)=="utf-8") $text=decode_utf8($text); |
---|
81 | > |
---|
82 | > ... before the following one in the "_decodeHeader" function: |
---|
83 | > |
---|
84 | > $input = str_replace($encoded, $text, $input); |
---|
85 | > |
---|
86 | > This way from now on it can easily decode the UTF-8 headers too. |
---|
87 | |
---|
88 | * |
---|
89 | * @author Richard Heyes <richard@phpguru.org> |
---|
90 | * @version $Revision: 1.46 $ |
---|
91 | * @package Mail |
---|
92 | */ |
---|
93 | class Mail_mimeDecode extends PEAR |
---|
94 | { |
---|
95 | /** |
---|
96 | * The raw email to decode |
---|
97 | * @var string |
---|
98 | */ |
---|
99 | var $_input; |
---|
100 | |
---|
101 | /** |
---|
102 | * The header part of the input |
---|
103 | * @var string |
---|
104 | */ |
---|
105 | var $_header; |
---|
106 | |
---|
107 | /** |
---|
108 | * The body part of the input |
---|
109 | * @var string |
---|
110 | */ |
---|
111 | var $_body; |
---|
112 | |
---|
113 | /** |
---|
114 | * If an error occurs, this is used to store the message |
---|
115 | * @var string |
---|
116 | */ |
---|
117 | var $_error; |
---|
118 | |
---|
119 | /** |
---|
120 | * Flag to determine whether to include bodies in the |
---|
121 | * returned object. |
---|
122 | * @var boolean |
---|
123 | */ |
---|
124 | var $_include_bodies; |
---|
125 | |
---|
126 | /** |
---|
127 | * Flag to determine whether to decode bodies |
---|
128 | * @var boolean |
---|
129 | */ |
---|
130 | var $_decode_bodies; |
---|
131 | |
---|
132 | /** |
---|
133 | * Flag to determine whether to decode headers |
---|
134 | * @var boolean |
---|
135 | */ |
---|
136 | var $_decode_headers; |
---|
137 | |
---|
138 | /** |
---|
139 | * Constructor. |
---|
140 | * |
---|
141 | * Sets up the object, initialise the variables, and splits and |
---|
142 | * stores the header and body of the input. |
---|
143 | * |
---|
144 | * @param string The input to decode |
---|
145 | * @access public |
---|
146 | */ |
---|
147 | function Mail_mimeDecode($input) |
---|
148 | { |
---|
149 | list($header, $body) = $this->_splitBodyHeader($input); |
---|
150 | |
---|
151 | $this->_input = $input; |
---|
152 | $this->_header = $header; |
---|
153 | $this->_body = $body; |
---|
154 | $this->_decode_bodies = false; |
---|
155 | $this->_include_bodies = true; |
---|
156 | } |
---|
157 | |
---|
158 | /** |
---|
159 | * Begins the decoding process. If called statically |
---|
160 | * it will create an object and call the decode() method |
---|
161 | * of it. |
---|
162 | * |
---|
163 | * @param array An array of various parameters that determine |
---|
164 | * various things: |
---|
165 | * include_bodies - Whether to include the body in the returned |
---|
166 | * object. |
---|
167 | * decode_bodies - Whether to decode the bodies |
---|
168 | * of the parts. (Transfer encoding) |
---|
169 | * decode_headers - Whether to decode headers |
---|
170 | * input - If called statically, this will be treated |
---|
171 | * as the input |
---|
172 | * @return object Decoded results |
---|
173 | * @access public |
---|
174 | */ |
---|
175 | function decode($params = null) |
---|
176 | { |
---|
177 | // determine if this method has been called statically |
---|
178 | $isStatic = !(isset($this) && get_class($this) == __CLASS__); |
---|
179 | |
---|
180 | // Have we been called statically? |
---|
181 | // If so, create an object and pass details to that. |
---|
182 | if ($isStatic AND isset($params['input'])) { |
---|
183 | |
---|
184 | $obj = new Mail_mimeDecode($params['input']); |
---|
185 | $structure = $obj->decode($params); |
---|
186 | |
---|
187 | // Called statically but no input |
---|
188 | } elseif ($isStatic) { |
---|
189 | return PEAR::raiseError('Called statically and no input given'); |
---|
190 | |
---|
191 | // Called via an object |
---|
192 | } else { |
---|
193 | $this->_include_bodies = isset($params['include_bodies']) ? |
---|
194 | $params['include_bodies'] : false; |
---|
195 | $this->_decode_bodies = isset($params['decode_bodies']) ? |
---|
196 | $params['decode_bodies'] : false; |
---|
197 | $this->_decode_headers = isset($params['decode_headers']) ? |
---|
198 | $params['decode_headers'] : false; |
---|
199 | |
---|
200 | $structure = $this->_decode($this->_header, $this->_body); |
---|
201 | if ($structure === false) { |
---|
202 | $structure = $this->raiseError($this->_error); |
---|
203 | } |
---|
204 | } |
---|
205 | |
---|
206 | return $structure; |
---|
207 | } |
---|
208 | |
---|
209 | /** |
---|
210 | * Performs the decoding. Decodes the body string passed to it |
---|
211 | * If it finds certain content-types it will call itself in a |
---|
212 | * recursive fashion |
---|
213 | * |
---|
214 | * @param string Header section |
---|
215 | * @param string Body section |
---|
216 | * @return object Results of decoding process |
---|
217 | * @access private |
---|
218 | */ |
---|
219 | function _decode($headers, $body, $default_ctype = 'text/plain') |
---|
220 | { |
---|
221 | $return = new stdClass; |
---|
222 | $return->headers = array(); |
---|
223 | $headers = $this->_parseHeaders($headers); |
---|
224 | |
---|
225 | foreach ($headers as $value) { |
---|
226 | if (isset($return->headers[strtolower($value['name'])]) AND !is_array($return->headers[strtolower($value['name'])])) { |
---|
227 | $return->headers[strtolower($value['name'])] = array($return->headers[strtolower($value['name'])]); |
---|
228 | $return->headers[strtolower($value['name'])][] = $value['value']; |
---|
229 | |
---|
230 | } elseif (isset($return->headers[strtolower($value['name'])])) { |
---|
231 | $return->headers[strtolower($value['name'])][] = $value['value']; |
---|
232 | |
---|
233 | } else { |
---|
234 | $return->headers[strtolower($value['name'])] = $value['value']; |
---|
235 | } |
---|
236 | } |
---|
237 | |
---|
238 | reset($headers); |
---|
239 | while (list($key, $value) = each($headers)) { |
---|
240 | $headers[$key]['name'] = strtolower($headers[$key]['name']); |
---|
241 | switch ($headers[$key]['name']) { |
---|
242 | |
---|
243 | case 'content-type': |
---|
244 | $content_type = $this->_parseHeaderValue($headers[$key]['value']); |
---|
245 | |
---|
246 | if (preg_match('/([0-9a-z+.-]+)\/([0-9a-z+.-]+)/i', $content_type['value'], $regs)) { |
---|
247 | $return->ctype_primary = $regs[1]; |
---|
248 | $return->ctype_secondary = $regs[2]; |
---|
249 | } |
---|
250 | |
---|
251 | if (isset($content_type['other'])) { |
---|
252 | while (list($p_name, $p_value) = each($content_type['other'])) { |
---|
253 | $return->ctype_parameters[$p_name] = $p_value; |
---|
254 | } |
---|
255 | } |
---|
256 | break; |
---|
257 | |
---|
258 | case 'content-disposition': |
---|
259 | $content_disposition = $this->_parseHeaderValue($headers[$key]['value']); |
---|
260 | $return->disposition = $content_disposition['value']; |
---|
261 | if (isset($content_disposition['other'])) { |
---|
262 | while (list($p_name, $p_value) = each($content_disposition['other'])) { |
---|
263 | $return->d_parameters[$p_name] = $p_value; |
---|
264 | } |
---|
265 | } |
---|
266 | break; |
---|
267 | |
---|
268 | case 'content-transfer-encoding': |
---|
269 | $content_transfer_encoding = $this->_parseHeaderValue($headers[$key]['value']); |
---|
270 | break; |
---|
271 | } |
---|
272 | } |
---|
273 | |
---|
274 | if (isset($content_type)) { |
---|
275 | switch (strtolower($content_type['value'])) { |
---|
276 | case 'text/plain': |
---|
277 | $encoding = isset($content_transfer_encoding) ? $content_transfer_encoding['value'] : '7bit'; |
---|
278 | $this->_include_bodies ? $return->body = ($this->_decode_bodies ? $this->_decodeBody($body, $encoding) : $body) : null; |
---|
279 | break; |
---|
280 | |
---|
281 | case 'text/html': |
---|
282 | $encoding = isset($content_transfer_encoding) ? $content_transfer_encoding['value'] : '7bit'; |
---|
283 | $this->_include_bodies ? $return->body = ($this->_decode_bodies ? $this->_decodeBody($body, $encoding) : $body) : null; |
---|
284 | break; |
---|
285 | |
---|
286 | case 'multipart/parallel': |
---|
287 | case 'multipart/report': // RFC1892 |
---|
288 | case 'multipart/signed': // PGP |
---|
289 | case 'multipart/digest': |
---|
290 | case 'multipart/alternative': |
---|
291 | case 'multipart/related': |
---|
292 | case 'multipart/mixed': |
---|
293 | if(!isset($content_type['other']['boundary'])){ |
---|
294 | $this->_error = 'No boundary found for ' . $content_type['value'] . ' part'; |
---|
295 | return false; |
---|
296 | } |
---|
297 | |
---|
298 | $default_ctype = (strtolower($content_type['value']) === 'multipart/digest') ? 'message/rfc822' : 'text/plain'; |
---|
299 | |
---|
300 | $parts = $this->_boundarySplit($body, $content_type['other']['boundary']); |
---|
301 | for ($i = 0; $i < count($parts); $i++) { |
---|
302 | list($part_header, $part_body) = $this->_splitBodyHeader($parts[$i]); |
---|
303 | $part = $this->_decode($part_header, $part_body, $default_ctype); |
---|
304 | if($part === false) |
---|
305 | $part = $this->raiseError($this->_error); |
---|
306 | $return->parts[] = $part; |
---|
307 | } |
---|
308 | break; |
---|
309 | |
---|
310 | case 'message/rfc822': |
---|
311 | $obj = &new Mail_mimeDecode($body); |
---|
312 | $return->parts[] = $obj->decode(array('include_bodies' => $this->_include_bodies, |
---|
313 | 'decode_bodies' => $this->_decode_bodies, |
---|
314 | 'decode_headers' => $this->_decode_headers)); |
---|
315 | unset($obj); |
---|
316 | break; |
---|
317 | |
---|
318 | default: |
---|
319 | if(!isset($content_transfer_encoding['value'])) |
---|
320 | $content_transfer_encoding['value'] = '7bit'; |
---|
321 | $this->_include_bodies ? $return->body = ($this->_decode_bodies ? $this->_decodeBody($body, $content_transfer_encoding['value']) : $body) : null; |
---|
322 | break; |
---|
323 | } |
---|
324 | |
---|
325 | } else { |
---|
326 | $ctype = explode('/', $default_ctype); |
---|
327 | $return->ctype_primary = $ctype[0]; |
---|
328 | $return->ctype_secondary = $ctype[1]; |
---|
329 | $this->_include_bodies ? $return->body = ($this->_decode_bodies ? $this->_decodeBody($body) : $body) : null; |
---|
330 | } |
---|
331 | |
---|
332 | return $return; |
---|
333 | } |
---|
334 | |
---|
335 | /** |
---|
336 | * Given the output of the above function, this will return an |
---|
337 | * array of references to the parts, indexed by mime number. |
---|
338 | * |
---|
339 | * @param object $structure The structure to go through |
---|
340 | * @param string $mime_number Internal use only. |
---|
341 | * @return array Mime numbers |
---|
342 | */ |
---|
343 | function &getMimeNumbers(&$structure, $no_refs = false, $mime_number = '', $prepend = '') |
---|
344 | { |
---|
345 | $return = array(); |
---|
346 | if (!empty($structure->parts)) { |
---|
347 | if ($mime_number != '') { |
---|
348 | $structure->mime_id = $prepend . $mime_number; |
---|
349 | $return[$prepend . $mime_number] = &$structure; |
---|
350 | } |
---|
351 | for ($i = 0; $i < count($structure->parts); $i++) { |
---|
352 | |
---|
353 | |
---|
354 | if (!empty($structure->headers['content-type']) AND substr(strtolower($structure->headers['content-type']), 0, 8) == 'message/') { |
---|
355 | $prepend = $prepend . $mime_number . '.'; |
---|
356 | $_mime_number = ''; |
---|
357 | } else { |
---|
358 | $_mime_number = ($mime_number == '' ? $i + 1 : sprintf('%s.%s', $mime_number, $i + 1)); |
---|
359 | } |
---|
360 | |
---|
361 | $arr = &Mail_mimeDecode::getMimeNumbers($structure->parts[$i], $no_refs, $_mime_number, $prepend); |
---|
362 | foreach ($arr as $key => $val) { |
---|
363 | $no_refs ? $return[$key] = '' : $return[$key] = &$arr[$key]; |
---|
364 | } |
---|
365 | } |
---|
366 | } else { |
---|
367 | if ($mime_number == '') { |
---|
368 | $mime_number = '1'; |
---|
369 | } |
---|
370 | $structure->mime_id = $prepend . $mime_number; |
---|
371 | $no_refs ? $return[$prepend . $mime_number] = '' : $return[$prepend . $mime_number] = &$structure; |
---|
372 | } |
---|
373 | |
---|
374 | return $return; |
---|
375 | } |
---|
376 | |
---|
377 | /** |
---|
378 | * Given a string containing a header and body |
---|
379 | * section, this function will split them (at the first |
---|
380 | * blank line) and return them. |
---|
381 | * |
---|
382 | * @param string Input to split apart |
---|
383 | * @return array Contains header and body section |
---|
384 | * @access private |
---|
385 | */ |
---|
386 | function _splitBodyHeader($input) |
---|
387 | { |
---|
388 | if (preg_match("/^(.*?)\r?\n\r?\n(.*)/s", $input, $match)) { |
---|
389 | return array($match[1], $match[2]); |
---|
390 | } |
---|
391 | $this->_error = 'Could not split header and body'; |
---|
392 | return false; |
---|
393 | } |
---|
394 | |
---|
395 | /** |
---|
396 | * Parse headers given in $input and return |
---|
397 | * as assoc array. |
---|
398 | * |
---|
399 | * @param string Headers to parse |
---|
400 | * @return array Contains parsed headers |
---|
401 | * @access private |
---|
402 | */ |
---|
403 | function _parseHeaders($input) |
---|
404 | { |
---|
405 | |
---|
406 | if ($input !== '') { |
---|
407 | // Unfold the input |
---|
408 | $input = preg_replace("/\r?\n/", "\r\n", $input); |
---|
409 | $input = preg_replace("/\r\n(\t| )+/", ' ', $input); |
---|
410 | $headers = explode("\r\n", trim($input)); |
---|
411 | |
---|
412 | foreach ($headers as $value) { |
---|
413 | $hdr_name = substr($value, 0, $pos = strpos($value, ':')); |
---|
414 | $hdr_value = substr($value, $pos+1); |
---|
415 | if($hdr_value[0] == ' ') |
---|
416 | $hdr_value = substr($hdr_value, 1); |
---|
417 | |
---|
418 | $return[] = array( |
---|
419 | 'name' => $hdr_name, |
---|
420 | 'value' => $this->_decode_headers ? $this->_decodeHeader($hdr_value) : $hdr_value |
---|
421 | ); |
---|
422 | } |
---|
423 | } else { |
---|
424 | $return = array(); |
---|
425 | } |
---|
426 | |
---|
427 | return $return; |
---|
428 | } |
---|
429 | |
---|
430 | /** |
---|
431 | * Function to parse a header value, |
---|
432 | * extract first part, and any secondary |
---|
433 | * parts (after ;) This function is not as |
---|
434 | * robust as it could be. Eg. header comments |
---|
435 | * in the wrong place will probably break it. |
---|
436 | * |
---|
437 | * @param string Header value to parse |
---|
438 | * @return array Contains parsed result |
---|
439 | * @access private |
---|
440 | */ |
---|
441 | function _parseHeaderValue($input) |
---|
442 | { |
---|
443 | |
---|
444 | if (($pos = strpos($input, ';')) !== false) { |
---|
445 | |
---|
446 | $return['value'] = trim(substr($input, 0, $pos)); |
---|
447 | $input = trim(substr($input, $pos+1)); |
---|
448 | |
---|
449 | if (strlen($input) > 0) { |
---|
450 | |
---|
451 | // This splits on a semi-colon, if there's no preceeding backslash |
---|
452 | // Now works with quoted values; had to glue the \; breaks in PHP |
---|
453 | // the regex is already bordering on incomprehensible |
---|
454 | $splitRegex = '/([^;\'"]*[\'"]([^\'"]*([^\'"]*)*)[\'"][^;\'"]*|([^;]+))(;|$)/'; |
---|
455 | preg_match_all($splitRegex, $input, $matches); |
---|
456 | $parameters = array(); |
---|
457 | for ($i=0; $i<count($matches[0]); $i++) { |
---|
458 | $param = $matches[0][$i]; |
---|
459 | while (substr($param, -2) == '\;') { |
---|
460 | $param .= $matches[0][++$i]; |
---|
461 | } |
---|
462 | $parameters[] = $param; |
---|
463 | } |
---|
464 | |
---|
465 | for ($i = 0; $i < count($parameters); $i++) { |
---|
466 | $param_name = trim(substr($parameters[$i], 0, $pos = strpos($parameters[$i], '=')), "'\";\t\\ "); |
---|
467 | $param_value = trim(str_replace('\;', ';', substr($parameters[$i], $pos + 1)), "'\";\t\\ "); |
---|
468 | if ($param_value[0] == '"') { |
---|
469 | $param_value = substr($param_value, 1, -1); |
---|
470 | } |
---|
471 | $return['other'][$param_name] = $param_value; |
---|
472 | $return['other'][strtolower($param_name)] = $param_value; |
---|
473 | } |
---|
474 | } |
---|
475 | } else { |
---|
476 | $return['value'] = trim($input); |
---|
477 | } |
---|
478 | |
---|
479 | return $return; |
---|
480 | } |
---|
481 | |
---|
482 | /** |
---|
483 | * This function splits the input based |
---|
484 | * on the given boundary |
---|
485 | * |
---|
486 | * @param string Input to parse |
---|
487 | * @return array Contains array of resulting mime parts |
---|
488 | * @access private |
---|
489 | */ |
---|
490 | function _boundarySplit($input, $boundary) |
---|
491 | { |
---|
492 | $parts = array(); |
---|
493 | |
---|
494 | $bs_possible = substr($boundary, 2, -2); |
---|
495 | $bs_check = '\"' . $bs_possible . '\"'; |
---|
496 | |
---|
497 | if ($boundary == $bs_check) { |
---|
498 | $boundary = $bs_possible; |
---|
499 | } |
---|
500 | |
---|
501 | $tmp = explode('--' . $boundary, $input); |
---|
502 | |
---|
503 | for ($i = 1; $i < count($tmp) - 1; $i++) { |
---|
504 | $parts[] = $tmp[$i]; |
---|
505 | } |
---|
506 | |
---|
507 | return $parts; |
---|
508 | } |
---|
509 | |
---|
510 | /** |
---|
511 | * Given a header, this function will decode it |
---|
512 | * according to RFC2047. Probably not *exactly* |
---|
513 | * conformant, but it does pass all the given |
---|
514 | * examples (in RFC2047). |
---|
515 | * |
---|
516 | * @param string Input header value to decode |
---|
517 | * @return string Decoded header value |
---|
518 | * @access private |
---|
519 | */ |
---|
520 | function _decodeHeader($input) |
---|
521 | { |
---|
522 | // Remove white space between encoded-words |
---|
523 | $input = preg_replace('/(=\?[^?]+\?(q|b)\?[^?]*\?=)(\s)+=\?/i', '\1=?', $input); |
---|
524 | |
---|
525 | // For each encoded-word... |
---|
526 | while (preg_match('/(=\?([^?]+)\?(q|b)\?([^?]*)\?=)/i', $input, $matches)) { |
---|
527 | |
---|
528 | $encoded = $matches[1]; |
---|
529 | $charset = $matches[2]; |
---|
530 | $encoding = $matches[3]; |
---|
531 | $text = $matches[4]; |
---|
532 | |
---|
533 | switch (strtolower($encoding)) { |
---|
534 | case 'b': |
---|
535 | $text = base64_decode($text); |
---|
536 | break; |
---|
537 | |
---|
538 | case 'q': |
---|
539 | $text = str_replace('_', ' ', $text); |
---|
540 | preg_match_all('/=([a-f0-9]{2})/i', $text, $matches); |
---|
541 | foreach($matches[1] as $value) |
---|
542 | $text = str_replace('='.$value, chr(hexdec($value)), $text); |
---|
543 | break; |
---|
544 | } |
---|
545 | |
---|
546 | $input = str_replace($encoded, $text, $input); |
---|
547 | } |
---|
548 | |
---|
549 | return $input; |
---|
550 | } |
---|
551 | |
---|
552 | /** |
---|
553 | * Given a body string and an encoding type, |
---|
554 | * this function will decode and return it. |
---|
555 | * |
---|
556 | * @param string Input body to decode |
---|
557 | * @param string Encoding type to use. |
---|
558 | * @return string Decoded body |
---|
559 | * @access private |
---|
560 | */ |
---|
561 | function _decodeBody($input, $encoding = '7bit') |
---|
562 | { |
---|
563 | switch (strtolower($encoding)) { |
---|
564 | case '7bit': |
---|
565 | return $input; |
---|
566 | break; |
---|
567 | |
---|
568 | case 'quoted-printable': |
---|
569 | return $this->_quotedPrintableDecode($input); |
---|
570 | break; |
---|
571 | |
---|
572 | case 'base64': |
---|
573 | return base64_decode($input); |
---|
574 | break; |
---|
575 | |
---|
576 | default: |
---|
577 | return $input; |
---|
578 | } |
---|
579 | } |
---|
580 | |
---|
581 | /** |
---|
582 | * Given a quoted-printable string, this |
---|
583 | * function will decode and return it. |
---|
584 | * |
---|
585 | * @param string Input body to decode |
---|
586 | * @return string Decoded body |
---|
587 | * @access private |
---|
588 | */ |
---|
589 | function _quotedPrintableDecode($input) |
---|
590 | { |
---|
591 | // Remove soft line breaks |
---|
592 | $input = preg_replace("/=\r?\n/", '', $input); |
---|
593 | |
---|
594 | // Replace encoded characters |
---|
595 | $input = preg_replace('/=([a-f0-9]{2})/ie', "chr(hexdec('\\1'))", $input); |
---|
596 | |
---|
597 | return $input; |
---|
598 | } |
---|
599 | |
---|
600 | /** |
---|
601 | * Checks the input for uuencoded files and returns |
---|
602 | * an array of them. Can be called statically, eg: |
---|
603 | * |
---|
604 | * $files =& Mail_mimeDecode::uudecode($some_text); |
---|
605 | * |
---|
606 | * It will check for the begin 666 ... end syntax |
---|
607 | * however and won't just blindly decode whatever you |
---|
608 | * pass it. |
---|
609 | * |
---|
610 | * @param string Input body to look for attahcments in |
---|
611 | * @return array Decoded bodies, filenames and permissions |
---|
612 | * @access public |
---|
613 | * @author Unknown |
---|
614 | */ |
---|
615 | function &uudecode($input) |
---|
616 | { |
---|
617 | // Find all uuencoded sections |
---|
618 | preg_match_all("/begin ([0-7]{3}) (.+)\r?\n(.+)\r?\nend/Us", $input, $matches); |
---|
619 | |
---|
620 | for ($j = 0; $j < count($matches[3]); $j++) { |
---|
621 | |
---|
622 | $str = $matches[3][$j]; |
---|
623 | $filename = $matches[2][$j]; |
---|
624 | $fileperm = $matches[1][$j]; |
---|
625 | |
---|
626 | $file = ''; |
---|
627 | $str = preg_split("/\r?\n/", trim($str)); |
---|
628 | $strlen = count($str); |
---|
629 | |
---|
630 | for ($i = 0; $i < $strlen; $i++) { |
---|
631 | $pos = 1; |
---|
632 | $d = 0; |
---|
633 | $len=(int)(((ord(substr($str[$i],0,1)) -32) - ' ') & 077); |
---|
634 | |
---|
635 | while (($d + 3 <= $len) AND ($pos + 4 <= strlen($str[$i]))) { |
---|
636 | $c0 = (ord(substr($str[$i],$pos,1)) ^ 0x20); |
---|
637 | $c1 = (ord(substr($str[$i],$pos+1,1)) ^ 0x20); |
---|
638 | $c2 = (ord(substr($str[$i],$pos+2,1)) ^ 0x20); |
---|
639 | $c3 = (ord(substr($str[$i],$pos+3,1)) ^ 0x20); |
---|
640 | $file .= chr(((($c0 - ' ') & 077) << 2) | ((($c1 - ' ') & 077) >> 4)); |
---|
641 | |
---|
642 | $file .= chr(((($c1 - ' ') & 077) << 4) | ((($c2 - ' ') & 077) >> 2)); |
---|
643 | |
---|
644 | $file .= chr(((($c2 - ' ') & 077) << 6) | (($c3 - ' ') & 077)); |
---|
645 | |
---|
646 | $pos += 4; |
---|
647 | $d += 3; |
---|
648 | } |
---|
649 | |
---|
650 | if (($d + 2 <= $len) && ($pos + 3 <= strlen($str[$i]))) { |
---|
651 | $c0 = (ord(substr($str[$i],$pos,1)) ^ 0x20); |
---|
652 | $c1 = (ord(substr($str[$i],$pos+1,1)) ^ 0x20); |
---|
653 | $c2 = (ord(substr($str[$i],$pos+2,1)) ^ 0x20); |
---|
654 | $file .= chr(((($c0 - ' ') & 077) << 2) | ((($c1 - ' ') & 077) >> 4)); |
---|
655 | |
---|
656 | $file .= chr(((($c1 - ' ') & 077) << 4) | ((($c2 - ' ') & 077) >> 2)); |
---|
657 | |
---|
658 | $pos += 3; |
---|
659 | $d += 2; |
---|
660 | } |
---|
661 | |
---|
662 | if (($d + 1 <= $len) && ($pos + 2 <= strlen($str[$i]))) { |
---|
663 | $c0 = (ord(substr($str[$i],$pos,1)) ^ 0x20); |
---|
664 | $c1 = (ord(substr($str[$i],$pos+1,1)) ^ 0x20); |
---|
665 | $file .= chr(((($c0 - ' ') & 077) << 2) | ((($c1 - ' ') & 077) >> 4)); |
---|
666 | |
---|
667 | } |
---|
668 | } |
---|
669 | $files[] = array('filename' => $filename, 'fileperm' => $fileperm, 'filedata' => $file); |
---|
670 | } |
---|
671 | |
---|
672 | return $files; |
---|
673 | } |
---|
674 | |
---|
675 | /** |
---|
676 | * getSendArray() returns the arguments required for Mail::send() |
---|
677 | * used to build the arguments for a mail::send() call |
---|
678 | * |
---|
679 | * Usage: |
---|
680 | * $mailtext = Full email (for example generated by a template) |
---|
681 | * $decoder = new Mail_mimeDecode($mailtext); |
---|
682 | * $parts = $decoder->getSendArray(); |
---|
683 | * if (!PEAR::isError($parts) { |
---|
684 | * list($recipents,$headers,$body) = $parts; |
---|
685 | * $mail = Mail::factory('smtp'); |
---|
686 | * $mail->send($recipents,$headers,$body); |
---|
687 | * } else { |
---|
688 | * echo $parts->message; |
---|
689 | * } |
---|
690 | * @return mixed array of recipeint, headers,body or Pear_Error |
---|
691 | * @access public |
---|
692 | * @author Alan Knowles <alan@akbkhome.com> |
---|
693 | */ |
---|
694 | function getSendArray() |
---|
695 | { |
---|
696 | // prevent warning if this is not set |
---|
697 | $this->_decode_headers = FALSE; |
---|
698 | $headerlist =$this->_parseHeaders($this->_header); |
---|
699 | $to = ""; |
---|
700 | if (!$headerlist) { |
---|
701 | return $this->raiseError("Message did not contain headers"); |
---|
702 | } |
---|
703 | foreach($headerlist as $item) { |
---|
704 | $header[$item['name']] = $item['value']; |
---|
705 | switch (strtolower($item['name'])) { |
---|
706 | case "to": |
---|
707 | case "cc": |
---|
708 | case "bcc": |
---|
709 | $to = ",".$item['value']; |
---|
710 | default: |
---|
711 | break; |
---|
712 | } |
---|
713 | } |
---|
714 | if ($to == "") { |
---|
715 | return $this->raiseError("Message did not contain any recipents"); |
---|
716 | } |
---|
717 | $to = substr($to,1); |
---|
718 | return array($to,$header,$this->_body); |
---|
719 | } |
---|
720 | |
---|
721 | /** |
---|
722 | * Returns a xml copy of the output of |
---|
723 | * Mail_mimeDecode::decode. Pass the output in as the |
---|
724 | * argument. This function can be called statically. Eg: |
---|
725 | * |
---|
726 | * $output = $obj->decode(); |
---|
727 | * $xml = Mail_mimeDecode::getXML($output); |
---|
728 | * |
---|
729 | * The DTD used for this should have been in the package. Or |
---|
730 | * alternatively you can get it from cvs, or here: |
---|
731 | * http://www.phpguru.org/xmail/xmail.dtd. |
---|
732 | * |
---|
733 | * @param object Input to convert to xml. This should be the |
---|
734 | * output of the Mail_mimeDecode::decode function |
---|
735 | * @return string XML version of input |
---|
736 | * @access public |
---|
737 | */ |
---|
738 | function getXML($input) |
---|
739 | { |
---|
740 | $crlf = "\r\n"; |
---|
741 | $output = '<?xml version=\'1.0\'?>' . $crlf . |
---|
742 | '<!DOCTYPE email SYSTEM "http://www.phpguru.org/xmail/xmail.dtd">' . $crlf . |
---|
743 | '<email>' . $crlf . |
---|
744 | Mail_mimeDecode::_getXML($input) . |
---|
745 | '</email>'; |
---|
746 | |
---|
747 | return $output; |
---|
748 | } |
---|
749 | |
---|
750 | /** |
---|
751 | * Function that does the actual conversion to xml. Does a single |
---|
752 | * mimepart at a time. |
---|
753 | * |
---|
754 | * @param object Input to convert to xml. This is a mimepart object. |
---|
755 | * It may or may not contain subparts. |
---|
756 | * @param integer Number of tabs to indent |
---|
757 | * @return string XML version of input |
---|
758 | * @access private |
---|
759 | */ |
---|
760 | function _getXML($input, $indent = 1) |
---|
761 | { |
---|
762 | $htab = "\t"; |
---|
763 | $crlf = "\r\n"; |
---|
764 | $output = ''; |
---|
765 | $headers = @(array)$input->headers; |
---|
766 | |
---|
767 | foreach ($headers as $hdr_name => $hdr_value) { |
---|
768 | |
---|
769 | // Multiple headers with this name |
---|
770 | if (is_array($headers[$hdr_name])) { |
---|
771 | for ($i = 0; $i < count($hdr_value); $i++) { |
---|
772 | $output .= Mail_mimeDecode::_getXML_helper($hdr_name, $hdr_value[$i], $indent); |
---|
773 | } |
---|
774 | |
---|
775 | // Only one header of this sort |
---|
776 | } else { |
---|
777 | $output .= Mail_mimeDecode::_getXML_helper($hdr_name, $hdr_value, $indent); |
---|
778 | } |
---|
779 | } |
---|
780 | |
---|
781 | if (!empty($input->parts)) { |
---|
782 | for ($i = 0; $i < count($input->parts); $i++) { |
---|
783 | $output .= $crlf . str_repeat($htab, $indent) . '<mimepart>' . $crlf . |
---|
784 | Mail_mimeDecode::_getXML($input->parts[$i], $indent+1) . |
---|
785 | str_repeat($htab, $indent) . '</mimepart>' . $crlf; |
---|
786 | } |
---|
787 | } elseif (isset($input->body)) { |
---|
788 | $output .= $crlf . str_repeat($htab, $indent) . '<body><![CDATA[' . |
---|
789 | $input->body . ']]></body>' . $crlf; |
---|
790 | } |
---|
791 | |
---|
792 | return $output; |
---|
793 | } |
---|
794 | |
---|
795 | /** |
---|
796 | * Helper function to _getXML(). Returns xml of a header. |
---|
797 | * |
---|
798 | * @param string Name of header |
---|
799 | * @param string Value of header |
---|
800 | * @param integer Number of tabs to indent |
---|
801 | * @return string XML version of input |
---|
802 | * @access private |
---|
803 | */ |
---|
804 | function _getXML_helper($hdr_name, $hdr_value, $indent) |
---|
805 | { |
---|
806 | $htab = "\t"; |
---|
807 | $crlf = "\r\n"; |
---|
808 | $return = ''; |
---|
809 | |
---|
810 | $new_hdr_value = ($hdr_name != 'received') ? Mail_mimeDecode::_parseHeaderValue($hdr_value) : array('value' => $hdr_value); |
---|
811 | $new_hdr_name = str_replace(' ', '-', ucwords(str_replace('-', ' ', $hdr_name))); |
---|
812 | |
---|
813 | // Sort out any parameters |
---|
814 | if (!empty($new_hdr_value['other'])) { |
---|
815 | foreach ($new_hdr_value['other'] as $paramname => $paramvalue) { |
---|
816 | $params[] = str_repeat($htab, $indent) . $htab . '<parameter>' . $crlf . |
---|
817 | str_repeat($htab, $indent) . $htab . $htab . '<paramname>' . htmlspecialchars($paramname) . '</paramname>' . $crlf . |
---|
818 | str_repeat($htab, $indent) . $htab . $htab . '<paramvalue>' . htmlspecialchars($paramvalue) . '</paramvalue>' . $crlf . |
---|
819 | str_repeat($htab, $indent) . $htab . '</parameter>' . $crlf; |
---|
820 | } |
---|
821 | |
---|
822 | $params = implode('', $params); |
---|
823 | } else { |
---|
824 | $params = ''; |
---|
825 | } |
---|
826 | |
---|
827 | $return = str_repeat($htab, $indent) . '<header>' . $crlf . |
---|
828 | str_repeat($htab, $indent) . $htab . '<headername>' . htmlspecialchars($new_hdr_name) . '</headername>' . $crlf . |
---|
829 | str_repeat($htab, $indent) . $htab . '<headervalue>' . htmlspecialchars($new_hdr_value['value']) . '</headervalue>' . $crlf . |
---|
830 | $params . |
---|
831 | str_repeat($htab, $indent) . '</header>' . $crlf; |
---|
832 | |
---|
833 | return $return; |
---|
834 | } |
---|
835 | |
---|
836 | } // End of class |
---|
837 | ?> |
---|