r94118 MediaWiki - Code Review archive

Repository:	MediaWiki
Revision:	< r94117‎ \| r94118 \| r94119 >
Date:	16:13, 9 August 2011
Author:	kbrown
Status:	ok (Comments)
Tags:
Comment:	*add function for update.php schema updates
Modified paths:	/trunk/extensions/ArchiveLinks/ArchiveLinks.class.php (modified) (history) /trunk/extensions/ArchiveLinks/ArchiveLinks.php (modified) (history) /trunk/extensions/ArchiveLinks/setuptables.sql (modified) (history)

Diff [purge]

Index: trunk/extensions/ArchiveLinks/ArchiveLinks.php
—	—	@@ -19,14 +19,18 @@
20	20
21	21	$wgHooks['ArticleSaveComplete'][] = 'ArchiveLinks::queueExternalLinks';
22	22	$wgHooks['LinkerMakeExternalLink'][] = 'ArchiveLinks::rewriteLinks';
	23	+$wgHooks['LoadExtensionSchemaUpdates'][] = 'ArchiveLinks::schemaUpdates';
23	24
24	25	$wgSpecialPages['ModifyArchiveBlacklist'] = 'SpecialModifyArchiveBlacklist';
25	26	$wgSpecialPages['ViewArchive'] = 'SpecialViewArchive';
26	27
	28	+$wgAutoloadClasses['ApiQueryArchiveFeed'] = "$path/ApiQueryArchiveFeed.php";
	29	+$wgAPIListModules['archivefeed'] = 'ApiQueryArchiveFeed';
	30	+
27	31	$wgArchiveLinksConfig = array(
28		~~- 'archive_service' => 'wikiwix',~~
	32	+ 'archive_service' => 'internet_archive',
29	33	'use_multiple_archives' => false,
30	34	'run_spider_in_loop' => false,
31	35	'in_progress_ignore_delay' => 7200,
32		~~- 'generate_feed' => true,~~
	36	+ 'generate_feed' => false,
33	37	);
\ No newline at end of file
Index: trunk/extensions/ArchiveLinks/setuptables.sql
—	—	@@ -1,22 +1,22 @@
2		~~-CREATE TABLE IF NOT EXISTS `el_archive_blacklist` (~~
	2	+CREATE TABLE IF NOT EXISTS /$wgDBprefix/`el_archive_blacklist` (
3	3	`bl_id` int(11) unsigned NOT NULL AUTO_INCREMENT,
4	4	`bl_type` tinyint(4) NOT NULL,
5	5	`bl_url` varchar(10000) NOT NULL,
6	6	`bl_expiry` int(11) unsigned NOT NULL,
7	7	`bl_reason` varchar(255) NOT NULL,
8	8	PRIMARY KEY (`bl_id`)
9		~~-) ENGINE=InnoDB DEFAULT CHARSET=utf8 AUTO_INCREMENT=2 ;~~
	9	+) /$wgDBTableOptions/;
10	10
11		~~-CREATE TABLE IF NOT EXISTS `el_archive_log` (~~
	11	+CREATE TABLE IF NOT EXISTS /$wgDBprefix/`el_archive_log` (
12	12	`log_id` int(11) unsigned NOT NULL AUTO_INCREMENT,
13	13	`log_result` tinyint(4) NOT NULL,
14	14	`log_url` varchar(10000) NOT NULL,
15	15	`log_time` int(11) unsigned NOT NULL,
16	16	`log_http_code` varchar(255) NOT NULL,
17	17	PRIMARY KEY (`log_id`)
18		~~-) ENGINE=InnoDB DEFAULT CHARSET=utf8 AUTO_INCREMENT=1 ;~~
	18	+) /$wgDBTableOptions/;
19	19
20		~~-CREATE TABLE IF NOT EXISTS `el_archive_queue` (~~
	20	+CREATE TABLE IF NOT EXISTS /$wgDBprefix/`el_archive_queue` (
21	21	`queue_id` int(11) unsigned NOT NULL AUTO_INCREMENT,
22	22	`page_id` int(11) unsigned NOT NULL,
23	23	`url` varchar(10000) NOT NULL,
—	—	@@ -24,12 +24,20 @@
25	25	`insertion_time` int(11) unsigned NOT NULL,
26	26	`in_progress` varchar(50) NOT NULL,
27	27	PRIMARY KEY (`queue_id`)
28		~~-) ENGINE=InnoDB DEFAULT CHARSET=utf8 AUTO_INCREMENT=105 ;~~
	28	+) /$wgDBTableOptions/;
29	29
30		~~-CREATE TABLE IF NOT EXISTS `el_archive_link_history` (~~
	30	+CREATE TABLE IF NOT EXISTS /$wgDBprefix/`el_archive_link_history` (
31	31	`hist_id` int(11) unsigned NOT NULL,
32	32	`hist_page_id` int(11) unsigned NOT NULL,
33	33	`hist_url` varchar(10000) NOT NULL,
34	34	`hist_insertion_time` int(11) unsigned NOT NULL,
35	35	PRIMARY KEY (`hist_id`)
36		~~-) ENGINE=InnoDB DEFAULT CHARSET=utf8;~~
\ No newline at end of file
	36	+) /$wgDBTableOptions/;
	37	+
	38	+CREATE TABLE IF NOT EXISTS /$wgDBprefix/`el_archive_resource` (
	39	+ `resource_id` int(11) NOT NULL,
	40	+ `el_id` int(11) NOT NULL,
	41	+ `resource_url` varchar(10000) NOT NULL,
	42	+ `resource_location` varchar(10000) NOT NULL,
	43	+ PRIMARY KEY (`resource_id`)
	44	+) /$wgDBTableOptions/;
Index: trunk/extensions/ArchiveLinks/ArchiveLinks.class.php
—	—	@@ -42,6 +42,8 @@
43	43	$old_id = $article->getTitle();
44	44	$old_id = $old_id->getPreviousRevisionID( $page_id );
45	45
	46	+ die('firing');
	47	+
46	48	$db_result['links_on_page'] = $db_master->select( 'el_archive_link_history', '*', array( 'hist_page_id' => $page_id ), __METHOD__ );
47	49
48	50	$old_external_links = array();
—	—	@@ -55,7 +57,7 @@
56	58	$new_external_links = array_diff( $external_links, $old_external_links );
57	59	unset( $old_external_links );
58	60
59		~~- die( var_dump( $old_external_links ) );~~
	61	+ //die( var_dump( $old_external_links ) );
60	62	} elseif ( count( $external_links ) > 0 ) {
61	63	$new_external_links = $external_links;
62	64	}
—	—	@@ -67,27 +69,13 @@
68	70	if ( count( $new_external_links ) <= $wgArchiveLinksConfig['link_insert_max'] ) {
69	71	//insert the links into the queue now
70	72	foreach( $new_external_links as $link ) {
71		~~- /$db_result['blacklist'] = $db_slave->select( 'el_archive_blacklist', '', array( 'bl_url' => $link ), __METHOD__, array( 'LIMIT' => '1', ) );~~
	73	+ $this->feed_insert_links( $link );
	74	+
	75	+ /*
72	76
73	77
74	78	/*
75		~~- if ( $db_result['blacklist-numrows'] === 0 && $db_result['queue-numrows'] === 0 ) {~~
76		~~- //this link is new to the wiki~~
77		~~- $db_master->insert( 'el_archive_queue', array(~~
78		~~- 'page_id' => $page_id,~~
79		~~- 'url' => $link,~~
80		~~- 'delay_time' => '0',~~
81		~~- 'insertion_time' => $time,~~
82		~~- 'in_progress' => '0',~~
83		~~- ));~~
84		-
85		~~- $db_master->insert( 'el_archive_link_history', array(~~
86		~~- 'page_id' => $page_id,~~
87		~~- 'url' => $link,~~
88		~~- 'delay_time' => '0',~~
89		~~- 'insertion_time' => $time,~~
90		~~- 'in_progress' => '0',~~
91		~~- ));~~
	79	+
92	80	} elseif ( $db_result['history-row']['hist_insertion_time'] >= $time - $wgArchiveLinksConfig['global_rearchive_time'] ) {
93	81	$db_result['history_page'] = $db_slave->select( 'el_archive_link_history', '*', array( 'hist_url' => $link, 'page_id' => $page_id ), __METHOD__, array( 'LIMIT' => '1', 'ORDER BY' => 'hist_id DESC' ) );
94	82
—	—	@@ -224,11 +212,64 @@
225	213	$url = $this->strencode( $url );
226	214	}
227	215
228		~~- $db_result['queue'] = $db_slave->select( 'el_archive_queue', '*', array( 'url' => $link ), __METHOD__, array( 'LIMIT' => '1', ) );~~
229		-
230		~~- $db_result['queue-numrows'] = $db_result['queue']->numRows();~~
231		~~- $db_result['blacklist-numrows'] = $db_result['blacklist']->numRows();~~
	216	+ $db_result['queue'] = $db_slave->select( 'el_archive_queue', '*', array( 'url' => $link ), __METHOD__, array( 'LIMIT' => '1', ) );
	217	+ $db_result['blacklist'] = $db_slave->select( 'el_archive_blacklist', '*', array( 'bl_url' => $link ), __METHOD__, array( 'LIMIT' => '1', ) );
	218	+
	219	+ $db_result['queue-numrows'] = $db_result['queue']->numRows();
	220	+ $db_result['blacklist-numrows'] = $db_result['blacklist']->numRows();
	221	+
	222	+ if ( $db_result['blacklist-numrows'] === 0 && $db_result['queue-numrows'] === 0 ) {
	223	+ $db_master->insert( 'el_archive_queue', array(
	224	+ 'page_id' => $page_id,
	225	+ 'url' => $link,
	226	+ 'delay_time' => '0',
	227	+ 'insertion_time' => $time,
	228	+ 'in_progress' => '0',
	229	+ ));
	230	+
	231	+ $db_master->insert( 'el_archive_link_history', array(
	232	+ 'page_id' => $page_id,
	233	+ 'url' => $link,
	234	+ 'delay_time' => '0',
	235	+ 'insertion_time' => $time,
	236	+ 'in_progress' => '0',
	237	+ ));
	238	+ }
232	239	}
	240	+
	241	+ public static function schemaUpdate ( $updater = null ) {
	242	+ $path = dirname( __FILE__ );
	243	+ $updater->addExtesionUpdate( array(
	244	+ 'addTable',
	245	+ 'el_archive_link_history',
	246	+ $path . '/setuptables.sql',
	247	+ true
	248	+ ));
	249	+ $updater->addExtesionUpdate( array(
	250	+ 'addTable',
	251	+ 'el_archive_queue',
	252	+ $path . '/setuptables.sql',
	253	+ true
	254	+ ));
	255	+ $updater->addExtesionUpdate( array(
	256	+ 'addTable',
	257	+ 'el_archive_log',
	258	+ $path . '/setuptables.sql',
	259	+ true
	260	+ ));
	261	+ $updater->addExtesionUpdate( array(
	262	+ 'addTable',
	263	+ 'el_archive_resource',
	264	+ $path . '/setuptables.sql',
	265	+ true
	266	+ ));
	267	+ $updater->addExtesionUpdate( array(
	268	+ 'addTable',
	269	+ 'el_archive_link_blacklist',
	270	+ $path . '/setuptables.sql',
	271	+ true
	272	+ ));
	273	+ }
233	274	}
234	275
235	276	class InsertURLsIntoQueue extends Job {

Follow-up revisions

Revision	Commit summary	Author	Date
r94157	fix typos from r94118	kbrown	15:22, 10 August 2011
r94164	fix partial excaping problem on setuptables.sql, follow up to r94118	kbrown	16:20, 10 August 2011
r94165	gah, fix sql statement, forgot to remove other backtick... r94118...	kbrown	16:37, 10 August 2011

Comments

#Comment by NeilK (talk | contribs) 16:02, 10 August 2011

I think you left a debug die() on line 45 of ArchiveLinks.class.php. Otherwise looks okay

#Comment by NeilK (talk | contribs) 16:10, 10 August 2011

In general I'm finding it hard to follow queueExternalLinks -- please break it up into a couple of functions & remove the commented code. Getting close to the end of GSoC!

#Comment by NeilK (talk | contribs) 15:55, 16 August 2011

marking ok as debugging statements removed, dead code removed, in folowups.

Status & tagging log

16:08, 16 August 2011 😂 (talk | contribs) changed the tags for r94118 [removed: nodeploy]
15:55, 16 August 2011 NeilK (talk | contribs) changed the status of r94118 [removed: fixme added: ok]
20:46, 15 August 2011 MarkAHershberger (talk | contribs) changed the tags for r94118 [added: nodeploy]
16:02, 10 August 2011 NeilK (talk | contribs) changed the status of r94118 [removed: new added: fixme]