annotate fetchnews.php @ 7:01dc7eeaf5df

Added some more checks to article data, added some commands, added 'dot stuffing' for block transfers
author Ivo Smits <Ivo@UCIS.nl>
date Tue, 12 Apr 2011 14:10:41 +0200
parents 0dcdb73cbcbf
children 005339a1b2ce
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
3
0dcdb73cbcbf Increased article body length to 16MB in database scheme, cleaned up the code, added a script to forcefully reload an individual article
Ivo Smits <Ivo@UCIS.nl>
parents: 2
diff changeset
1 #!/usr/bin/php
0
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
2 <?php
2
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
3 chdir(__DIR__);
3
0dcdb73cbcbf Increased article body length to 16MB in database scheme, cleaned up the code, added a script to forcefully reload an individual article
Ivo Smits <Ivo@UCIS.nl>
parents: 2
diff changeset
4 require_once './common.php';
0
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
5
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
6 foreach ($db->evalAllAssoc('SELECT * FROM `peers`') as $peer) {
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
7 $socket = stream_socket_client($peer['address']);
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
8 if ($socket === FALSE) die("Could not connect to peer $peer[address]\n");
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
9 $line = nntp_readline($socket);
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
10 $code = strtok($line, " \t");
2
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
11 if ($code == 200) {
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
12 } else if ($code == 201) {
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
13 $peer['post'] = 0;
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
14 } else die("Error code $code from $peer[address]\n");
0
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
15 foreach ($db->evalAllAssoc('SELECT * FROM `peergroups` WHERE `peer` = ?', $peer['id']) as $peergroup) {
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
16 $group = $db->evalRowAssoc('SELECT * FROM `groups` WHERE `id` = ?', $peergroup['group']);
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
17 nntp_writeline($socket, 'GROUP '.$group['name']);
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
18 $line = nntp_readline($socket);
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
19 $code = strtok($line, " \t");
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
20 if ($code != 211) die("Error code $code from $peer[address]\n");
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
21 strtok(" \t"); //number of articles
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
22 $low = strtok(" \t");
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
23 $high = strtok(" \t");
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
24 strtok(" \t"); //group name
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
25 if ($low != $peergroup['low'] || $high != $peergroup['high'] || $peergroup['low'] === NULL || $peergroup['high'] === NULL) {
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
26 for ($i = $low; $i <= $high; $i++) {
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
27 if ($i >= $peergroup['low'] && $i <= $peergroup['high'] && $peergroup['low'] !== NULL && $peergroup['high'] !== NULL) continue;
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
28 nntp_writeline($socket, 'STAT '.$i);
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
29 $line = nntp_readline($socket);
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
30 $code = strtok($line, " \t");
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
31 if ($code == 423) {
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
32 print("Gap in article numbering at $i\n");
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
33 continue;
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
34 }
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
35 if ($code != 223) die("Error code $code from $peer[address]\n");
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
36 strtok(" \t"); //article number
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
37 $messageid = strtok(" \t");
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
38 if ($messageid[0] != '<' || $messageid[strlen($messageid)-1] != '>') die("Malformed message ID $messageid\n");
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
39 $messageid = substr($messageid, 1, -1);
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
40 $message = $db->evalRowAssoc('SELECT * FROM `messages` WHERE `messageid` = ?', $messageid);
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
41 if ($message) {
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
42 $groupmessage = $db->evalRowAssoc('SELECT * FROM `groupmessages` WHERE `group` = ? AND `message` = ?', array($group['id'], $message['id']));
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
43 if (!$groupmessage) {
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
44 $db->insert('INSERT INTO `groupmessages` (`group`, `message`) VALUES (?, ?)', array($group['id'], $message['id']));
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
45 }
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
46 } else {
3
0dcdb73cbcbf Increased article body length to 16MB in database scheme, cleaned up the code, added a script to forcefully reload an individual article
Ivo Smits <Ivo@UCIS.nl>
parents: 2
diff changeset
47 nntp_writeline($socket, 'ARTICLE '.$i);
0
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
48 $line = nntp_readline($socket);
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
49 $code = strtok($line, " \t");
3
0dcdb73cbcbf Increased article body length to 16MB in database scheme, cleaned up the code, added a script to forcefully reload an individual article
Ivo Smits <Ivo@UCIS.nl>
parents: 2
diff changeset
50 if ($code != 220) die("Error code $code from $peer[address]\n");
0
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
51 strtok(" \t"); //article number
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
52 $lines = nntp_readlines($socket);
3
0dcdb73cbcbf Increased article body length to 16MB in database scheme, cleaned up the code, added a script to forcefully reload an individual article
Ivo Smits <Ivo@UCIS.nl>
parents: 2
diff changeset
53 try {
0dcdb73cbcbf Increased article body length to 16MB in database scheme, cleaned up the code, added a script to forcefully reload an individual article
Ivo Smits <Ivo@UCIS.nl>
parents: 2
diff changeset
54 nntp_article_store($lines);
0dcdb73cbcbf Increased article body length to 16MB in database scheme, cleaned up the code, added a script to forcefully reload an individual article
Ivo Smits <Ivo@UCIS.nl>
parents: 2
diff changeset
55 } catch (Exception $ex) {
0dcdb73cbcbf Increased article body length to 16MB in database scheme, cleaned up the code, added a script to forcefully reload an individual article
Ivo Smits <Ivo@UCIS.nl>
parents: 2
diff changeset
56 writelog($ex->getMessage());
0dcdb73cbcbf Increased article body length to 16MB in database scheme, cleaned up the code, added a script to forcefully reload an individual article
Ivo Smits <Ivo@UCIS.nl>
parents: 2
diff changeset
57 }
0
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
58 }
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
59 }
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
60 $db->update('UPDATE `peergroups` SET `low` = ?, `high` = ? WHERE `peer` = ? AND `group` = ?', array($low, $high, $peergroup['peer'], $peergroup['group']));
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
61 }
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
62 }
2
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
63 while ($peer['post']) {
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
64 if ($peer['lastposted'] === NULL) {
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
65 $articles = $db->evalAllAssoc('SELECT * FROM `messages` LIMIT 10');
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
66 } else {
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
67 $articles = $db->evalAllAssoc('SELECT * FROM `messages` WHERE `id` > ? LIMIT 10', $peer['lastposted']);
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
68 }
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
69 if (!count($articles)) break;
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
70 foreach ($articles as $article) {
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
71 nntp_writeline($socket, 'POST');
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
72 $line = nntp_readline($socket);
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
73 $code = strtok($line, " \t");
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
74 if ($code != 340) die("Error code $code from $peer[address]\n");
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
75 foreach (explode("\r\n", $article['header']) as $line) {
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
76 $parts = explode(': ', $line, 2);
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
77 switch (strtoupper($parts[0])) {
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
78 case 'PATH': case 'FROM': case 'NEWSGROUPS': case 'SUBJECT': case 'DATE': case 'ORGANIZATION':
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
79 case 'LINES': case 'MESSAGE-ID': case 'MIME-VERSION': case 'CONTENT-TYPE': case 'CONTENT-TRANSFER-ENCODING':
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
80 case 'USER-AGENT': case 'REFERENCES': case 'REPLY-TO': case 'SENDER': case 'FOLLOWUP-TO':
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
81 case 'EXPIRES': case 'CONTROL': case 'DISTRIBUTION': case 'KEYWORDS': case 'SUMMARY':
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
82 case 'IN-REPLY-TO':
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
83 break;
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
84 case 'NNTP-POSTING-HOST': case 'X-TRACE': case 'XREF': case 'X-COMPLAINTS-TO':
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
85 case 'NNTP-POSTING-DATE':
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
86 $line = NULL;
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
87 break;
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
88 default:
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
89 print("Sending unknown header $parts[0]\n");
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
90 }
7
01dc7eeaf5df Added some more checks to article data, added some commands, added 'dot stuffing' for block transfers
Ivo Smits <Ivo@UCIS.nl>
parents: 3
diff changeset
91 if ($line !== NULL) nntp_writeline_data($socket, $line);
2
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
92 }
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
93 nntp_writeline($socket, '');
7
01dc7eeaf5df Added some more checks to article data, added some commands, added 'dot stuffing' for block transfers
Ivo Smits <Ivo@UCIS.nl>
parents: 3
diff changeset
94 foreach (explode("\r\n", $article['body']) as $line) nntp_writeline_data($socket, $line);
2
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
95 nntp_writeline($socket, '.');
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
96 $line = nntp_readline($socket);
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
97 $code = strtok($line, " \t");
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
98 if ($code != 240) print("Article $article[messageid] was not accepted ($code)\n");
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
99 if ($article['id'] > $peer['lastposted']) $peer['lastposted'] = $article['id'];
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
100 }
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
101 $db->update('UPDATE `peers` SET `lastposted` = ? WHERE `id` = ?', array($peer['lastposted'], $peer['id']));
40e545510a57 Added support for POSTing to the server, added readme and todo, added support for upstream synchronization using POST
Ivo Smits <Ivo@UCIS.nl>
parents: 1
diff changeset
102 }
0
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
103 nntp_writeline($socket, 'QUIT');
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
104 fclose($socket);
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
105 }
d7ab68b71c74 Initial commit
Ivo Smits <Ivo@UCIS.nl>
parents:
diff changeset
106
3
0dcdb73cbcbf Increased article body length to 16MB in database scheme, cleaned up the code, added a script to forcefully reload an individual article
Ivo Smits <Ivo@UCIS.nl>
parents: 2
diff changeset
107 function writelog($line) {
0dcdb73cbcbf Increased article body length to 16MB in database scheme, cleaned up the code, added a script to forcefully reload an individual article
Ivo Smits <Ivo@UCIS.nl>
parents: 2
diff changeset
108 print($line."\n");
1
61fac319ca3e Update Path and Xref header fields while fetching messages, added database schema export
Ivo Smits <Ivo@UCIS.nl>
parents: 0
diff changeset
109 }