diocloid/LinkTitles
1
0
Fork 0
mirror of https://github.com/diocloid/LinkTitles.git synced 2025-07-13 17:59:29 +02:00
Code Issues Packages Projects Releases Wiki Activity

* Fixed linking in Namespace pages

Browse Source 
* added paramters to cli interface
  --page={pagename}   only process that page
  --log : show some output about the process
  --debug : show debug output in cli
* changed pagecount on SpecialPage to use COUNT instead of selecting all rows
This commit is contained in:
c0nnex
2015-10-02 02:35:47 +02:00
parent 70c679f757
commit 124e92aafd
3 changed files with 95 additions and 36 deletions
Download Patch File Download Diff File Expand all files Collapse all files

68
LinkTitles.body.php
View File

@ -35,6 +35,9 @@
/// A Title object for the target page currently being examined.
private static $targetTitle;
// The TiltleValue object of the target page
private static $targetTitleValue;
/// The content object for the currently processed target page.
/// This variable is necessary to be able to prevent loading the target
/// content twice.
@ -52,6 +55,9 @@
private static $wordStartDelim;
private static $wordEndDelim;
public static $ltConsoleOutput;
public static $ltConsoleOutputDebug;
/// Setup function, hooks the extension's functions to MediaWiki events.
public static function setup() {
global $wgLinkTitlesParseOnEdit;
@ -91,6 +97,24 @@
return true;
}
/// Local Debugging output function which can send output to console as well
public static function ltDebugLog($text) {
if (LinkTitles::$ltConsoleOutputDebug)
{
print $text . "\n";
}
wfDebugLog('LinkTitles', $text , 'private');
}
/// Local Logging output function which can send output to console as well
public static function ltLog($text) {
if (LinkTitles::$ltConsoleOutput)
{
print $text . "\n";
}
wfDebugLog('LinkTitles', $text , 'private');
}
/// Core function of the extension, performs the actual parsing of the content.
/// @param Title $title Title of the page being parsed
/// @param $text String that holds the article content
@ -116,6 +140,8 @@
LinkTitles::$currentTitle = $title;
$newText = $text;
// Build a blacklist of pages that are not supposed to be link
// targets. This includes the current page.
$blackList = str_replace( '_', ' ',
@ -123,13 +149,11 @@
LinkTitles::$currentTitle->getDbKey() . '")' );
$currentNamespace[] = $title->getNamespace();
wfDebugLog("LinkTitles",'$wgLinkTitlesNamespaces = '. print_r($wgLinkTitlesNamespaces,true),'private');
wfDebugLog("LinkTitles",'$currentNamespace = '. print_r($currentNamespace,true),'private');
// Build our weight list. Make sure current namespace is first element
$namespaces = array_diff($wgLinkTitlesNamespaces, $currentNamespace);
array_unshift($namespaces, $currentNamespace[0] );
wfDebugLog("LinkTitles",'$namespaces = '. print_r($namespaces,true),'private');
// No need for sanitiy check. we are sure that we have at least one element in the array
$weightSelect = "CASE page_namespace ";
@ -186,9 +210,11 @@
// Escape certain special characters in the page title to prevent
// regexp compilation errors
LinkTitles::$targetTitleText = LinkTitles::$targetTitle->getPrefixedText(); // containes Namespace !
$quotedTitle = preg_quote( LinkTitles::$targetTitle->getTitleValue()->getText(), '/');
wfDebugLog("LinkTitles",'TargetTitle='. LinkTitles::$targetTitleText,"private");
wfDebugLog("LinkTitles",'TargetTitleQuoted='. $quotedTitle,"private");
$quotedTitle = preg_quote( LinkTitles::$targetTitleValue->getText(), '/');
LinkTitles::ltDebugLog('TargetTitle='. LinkTitles::$targetTitleText,"private");
LinkTitles::ltDebugLog('TargetTitleQuoted='. $quotedTitle,"private");
// Depending on the global configuration setting $wgCapitalLinks,
// the title has to be searched for either in a strictly case-sensitive
// way, or in a 'fuzzy' way where the first letter of the title may
@ -242,7 +268,9 @@
/// to obtain such an object.
/// @returns undefined
public static function processPage(Title $title, RequestContext $context) {
// TODO: make this namespace-aware
LinkTitles::ltLog('Processing '. $title->getPrefixedText());
$page = WikiPage::factory($title);
$content = $page->getContent();
$text = $content->getContentHandler()->serializeContent($content);
@ -270,7 +298,9 @@
// Build an anonymous callback function to be used in simple mode.
private static function simpleModeCallback( array $matches ) {
if ( LinkTitles::checkTargetPage() ) {
LinkTitles::ltLog("Linking '$matches[0]' to '" . LinkTitles::$targetTitle . "'");
return '[[' . LinkTitles::$targetTitle . "|" . $matches[0] . ']]';
}
else
@ -295,13 +325,8 @@
// we need to ignore the first letter of the page titles, as
// it does not matter for linking.
if ( LinkTitles::checkTargetPage() ) {
if ( strcmp(substr(LinkTitles::$targetTitleText, 1), substr($matches[0], 1)) == 0 ) {
// Case-sensitive match: no need to bulid piped link.
LinkTitles::ltLog("Linking (smart) '$matches[0]' to '" . LinkTitles::$targetTitle . "'");
return '[[' . LinkTitles::$targetTitle . "|" . $matches[0] . ']]';
} else {
// Case-insensitive match: build piped link.
return '[[' . LinkTitles::$targetTitleText . '|' . $matches[0] . ']]';
}
}
else
{
@ -311,13 +336,8 @@
// If $wgCapitalLinks is false, we can use the simple variant
// of the callback function.
if ( LinkTitles::checkTargetPage() ) {
if ( strcmp(LinkTitles::$targetTitleText, $matches[0]) == 0 ) {
// Case-sensitive match: no need to bulid piped link.
return '[[' . $matches[0] . ']]';
} else {
// Case-insensitive match: build piped link.
return '[[' . LinkTitles::$targetTitleText . '|' . $matches[0] . ']]';
}
LinkTitles::ltLog("Linking (smart) '$matches[0]' to '" . LinkTitles::$targetTitle . "'");
return '[[' . LinkTitles::$targetTitle . '|' . $matches[0] . ']]';
}
else
{
@ -329,10 +349,10 @@
/// Sets member variables for the current target page.
private static function newTarget($ns, $title ) {
// @todo Make this wiki namespace aware.
LinkTitles::$targetTitle = Title::newFromText( $title , $ns );
wfDebugLog("LinkTitles",'newtarget='. print_r( LinkTitles::$targetTitle, true ) ,"private");
wfDebugLog("LinkTitles",'altTarget='. print_r( LinkTitles::$targetTitle->getTitleValue(), true ) ,"private");
LinkTitles::$targetTitle = Title::makeTitleSafe($ns,$title);
LinkTitles::ltDebugLog('newtarget='. LinkTitles::$targetTitle->getText() ,"private");
LinkTitles::$targetTitleValue = LinkTitles::$targetTitle->getTitleValue();
LinkTitles::ltDebugLog('altTarget='. LinkTitles::$targetTitleValue->getText() ,"private");
LinkTitles::$targetContent = null;
}

40
LinkTitles.cli.php
View File

@ -64,6 +64,26 @@ class LinkTitlesCli extends Maintenance {
true, // requires argument
"s"
);
$this->addOption(
"page",
"page to process",
false, // not required
true, // requires argument
"p"
);
$this->addOption(
"log",
"enables logging to console",
false, // not required
false, // requires no argument
"l"
);
$this->addOption(
"debug",
"enables debug logging to console",
false, // not required
false // requires no argument
);
}
/// Main function of the maintenance script.
@ -78,6 +98,24 @@ class LinkTitlesCli extends Maintenance {
$this->error('FATAL: Start index must be 0 or greater.', 1);
};
if ($this->hasOption('log'))
{
LinkTitles::$ltConsoleOutput = true;
}
if ($this->hasOption('debug'))
{
LinkTitles::$ltConsoleOutputDebug = true;
}
$pagename = strval($this->getOption('page'));
if ($pagename != null)
{
$curTitle = Title::newFromDBkey( $pagename );
LinkTitles::processPage($curTitle,RequestContext::getMain() );
$this->output("\nFinished parsing.\n");
return;
}
// get our Namespaces
$namespacesClause = str_replace( '_', ' ','(' . implode( ', ',$wgLinkTitlesNamespaces ) . ')' );
@ -104,7 +142,7 @@ class LinkTitlesCli extends Maintenance {
// Iterate through the pages; break if a time limit is exceeded.
foreach ( $res as $row ) {
$index += 1;
$curTitle = Title::makeTitle( $row->page_namespace, $row->page_title);
$curTitle = Title::makeTitleSafe( $row->page_namespace, $row->page_title);
$this->output(
sprintf("\rPage #%d (%02.0f%%)", $index, $index / $numPages * 100)
);

13
SpecialLinkTitles.php
View File

@ -105,7 +105,7 @@ class SpecialLinkTitles extends SpecialPage {
else
{
// No end index was given. Therefore, count pages now.
$end = $this->countPages($dbr);
$end = $this->countPages($dbr, $namespacesClause );
};
array_key_exists('r', $postValues) ?
@ -128,7 +128,7 @@ class SpecialLinkTitles extends SpecialPage {
// Iterate through the pages; break if a time limit is exceeded.
foreach ( $res as $row ) {
$curTitle = Title::makeTitle( $row->page_namespace, $row->page_title);
$curTitle = Title::makeTitleSafe( $row->page_namespace, $row->page_title);
LinkTitles::processPage($curTitle, $this->getContext());
$start += 1;
@ -279,16 +279,17 @@ EOF
/// Counts the number of pages in a read-access wiki database ($dbr).
/// @param $dbr Read-only `Database` object.
/// @returns Number of pages in the default namespace (0) of the wiki.
private function countPages(&$dbr) {
private function countPages(&$dbr, $namespacesClause) {
$res = $dbr->select(
'page',
'page_id',
array('pagecount' => "COUNT(page_id)"),
array(
'page_namespace = 0',
'page_namespace IN ' . $namespacesClause,
),
__METHOD__
);
return $res->numRows();
return $res->current()->pagecount;
}
}