$wgTitleInterwikiCache = array();
define ( 'GAID_FOR_UPDATE', 1 );
+# Title::newFromTitle maintains a cache to avoid
+# expensive re-normalization of commonly used titles.
+# On a batch operation this can become a memory leak
+# if not bounded. After hitting this many titles,
+# reset the cache.
+define( 'MW_TITLECACHE_MAX', 1000 );
+
/**
* Title class
* - Represents a title, which may contain an interwiki designation or namespace
$this->mInterwiki = $this->mUrlform =
$this->mTextform = $this->mDbkeyform = '';
$this->mArticleID = -1;
- $this->mNamespace = 0;
+ $this->mNamespace = NS_MAIN;
$this->mRestrictionsLoaded = false;
$this->mRestrictions = array();
- $this->mDefaultNamespace = 0;
+ # Dont change the following, NS_MAIN is hardcoded in several place
+ # See bug #696
+ $this->mDefaultNamespace = NS_MAIN;
}
/**
* @static
* @access public
*/
- /* static */ function &newFromText( $text, $defaultNamespace = 0 ) {
+ function &newFromText( $text, $defaultNamespace = NS_MAIN ) {
$fname = 'Title::newFromText';
wfProfileIn( $fname );
+ if( is_object( $text ) ) {
+ wfDebugDieBacktrace( 'Title::newFromText given an object' );
+ }
+
/**
* Wiki pages often contain multiple links to the same page.
* Title normalization and parsing can become expensive on
* In theory these are value objects and won't get changed...
*/
static $titleCache = array();
- if( $defaultNamespace == 0 && isset( $titleCache[$text] ) ) {
+ if( $defaultNamespace == NS_MAIN && isset( $titleCache[$text] ) ) {
wfProfileOut( $fname );
return $titleCache[$text];
}
$t->mDefaultNamespace = $defaultNamespace;
if( $t->secureAndSplit() ) {
- if( $defaultNamespace == 0 ) {
+ if( $defaultNamespace == NS_MAIN ) {
+ if( count( $titleCache ) >= MW_TITLECACHE_MAX ) {
+ # Avoid memory leaks on mass operations...
+ $titleCache = array();
+ }
$titleCache[$text] =& $t;
}
wfProfileOut( $fname );
if ( $query == '' ) {
$url = str_replace( '$1', $dbkey, $wgArticlePath );
} else {
+ if( preg_match( '/^(.*&|)action=([^&]*)(&(.*)|)$/', $query, $matches ) ) {
+ global $wgActionPaths;
+ $action = urldecode( $matches[2] );
+ if( isset( $wgActionPaths[$action] ) ) {
+ $query = $matches[1];
+ if( isset( $matches[4] ) ) $query .= $matches[4];
+ $url = str_replace( '$1', $dbkey, $wgActionPaths[$action] );
+ if( $query != '' ) $url .= '?' . $query;
+ return $url;
+ }
+ }
if ( $query == '-' ) {
$query = '';
}
}
return false;
}
+
+ /**
+ * Is this a talk page of some sort?
+ * @return bool
+ * @access public
+ */
+ function isTalkPage() {
+ return Namespace::isTalk( $this->getNamespace() );
+ }
/**
* Is this a .css or .js subpage of a user page?
# Clean up whitespace
#
- $t = preg_replace( '/[\\s_]+/', '_', $this->mDbkeyform );
+ $t = preg_replace( '/[ _]+/', '_', $this->mDbkeyform );
$t = trim( $t, '_' );
if ( '' == $t ) {
# We shouldn't need to query the DB for the size.
#$maxSize = $dbr->textFieldSize( 'page', 'page_title' );
if ( strlen( $r ) > 255 ) {
+ wfProfileOut( $fname );
return false;
}
$t = $r;
}
+ /**
+ * Can't make a link to a namespace alone...
+ * "empty" local links can only be self-links
+ * with a fragment identifier.
+ */
+ if( $t == '' &&
+ $this->mInterwiki == '' &&
+ $this->mNamespace != NS_MAIN ) {
+ wfProfileOut( $fname );
+ return false;
+ }
+
+ if( $wgUseLatin1 && $this->mInterwiki != '' ) {
+ # On a Latin-1 wiki, numbered character entities may have
+ # left us with a mix of 8-bit and UTF-8 characters, and
+ # some of those might be Windows-1252 special chars.
+ # Normalize interwikis to pure UTF-8.
+ $t = Title::mergeLatin1Utf8( $t );
+ }
+
# Fill fields
$this->mDbkeyform = $t;
$this->mUrlform = wfUrlencode( $t );
* @access public
*/
function moveTo( &$nt, $auth = true ) {
+ global $wgUser;
if( !$this or !$nt ) {
return 'badtitletext';
}
$u = new SearchUpdate( $newid, $this->getPrefixedDBkey(), '' );
$u->doUpdate();
+ wfRunHooks( 'TitleMoveComplete', $this, $nt, $wgUser, $oldid, $newid );
return true;
}
/* private */ function moveOverExistingRedirect( &$nt ) {
global $wgUser, $wgLinkCache, $wgUseSquid, $wgMwRedir;
$fname = 'Title::moveOverExistingRedirect';
- $comment = wfMsg( '1movedto2', $this->getPrefixedText(), $nt->getPrefixedText() );
+ $comment = wfMsgForContent( '1movedto2', $this->getPrefixedText(), $nt->getPrefixedText() );
$now = wfTimestampNow();
- $won = wfInvertTimestamp( $now );
$rand = wfRandom();
$newid = $nt->getArticleID();
$oldid = $this->getArticleID();
'rev_comment' => $comment,
'rev_user' => $wgUser->getID(),
'rev_user_text' => $wgUser->getName(),
- 'rev_timestamp' => $now,
- 'inverse_timestamp' => $won ), $fname
+ 'rev_timestamp' => $now
+ ), $fname
);
$revid = $dbw->insertId();
$dbw->insert( 'text', array(
);
$newid = $dbw->insertId();
$wgLinkCache->clearLink( $this->getPrefixedDBkey() );
-
- RecentChange::notifyMoveOverRedirect( $now, $this, $nt, $wgUser, $comment );
+ # Record in RC
+ // Replaced by a log entry
+ // RecentChange::notifyMoveOverRedirect( $now, $this, $nt, $wgUser, $comment );
+
+ # Log the move
+ $log = new LogPage( 'move' );
+ $log->addEntry( 'move_redir', $this, '', array(1 => $nt->getText()) );
+
# Swap links
# Load titles and IDs
global $wgUser, $wgLinkCache, $wgUseSquid;
global $wgMwRedir;
$fname = 'MovePageForm::moveToNewTitle';
- $comment = wfMsg( '1movedto2', $this->getPrefixedText(), $nt->getPrefixedText() );
+ $comment = wfMsgForContent( '1movedto2', $this->getPrefixedText(), $nt->getPrefixedText() );
$newid = $nt->getArticleID();
$oldid = $this->getArticleID();
$dbw =& wfGetDB( DB_MASTER );
$now = $dbw->timestamp();
- $won = wfInvertTimestamp( wfTimestamp(TS_MW,$now) );
wfSeedRandom();
$rand = wfRandom();
'rev_comment' => $comment,
'rev_user' => $wgUser->getID(),
'rev_user_text' => $wgUser->getName(),
- 'rev_timestamp' => $now,
- 'inverse_timestamp' => $won ), $fname
+ 'rev_timestamp' => $now
+ ), $fname
);
$revid = $dbw->insertId();
$dbw->insert( 'text', array(
$newid = $dbw->insertId();
$wgLinkCache->clearLink( $this->getPrefixedDBkey() );
+ // attach revision to the new page
+ $dbw->update( 'revision', array('rev_page' => $newid), array('rev_id' => $revid), $fname);
+
# Record in RC
- RecentChange::notifyMoveToNew( $now, $this, $nt, $wgUser, $comment );
+ // Replaced by a log entry
+ // RecentChange::notifyMoveToNew( $now, $this, $nt, $wgUser, $comment );
+
+ # Log the move
+ $log = new LogPage( 'move' );
+ $log->addEntry( 'move', $this, '', array(1 => $nt->getText()) );
# Purge squid and linkscc as per article creation
Article::onArticleCreate( $nt );
$fname = 'Title::createRedirect';
$dbw =& wfGetDB( DB_MASTER );
$now = wfTimestampNow();
- $won = wfInvertTimestamp( $now );
$seqVal = $dbw->nextSequenceValue( 'page_page_id_seq' );
$dbw->insert( 'page', array(
'rev_user' => $wgUser->getID(),
'rev_user_text' => $wgUser->getName(),
'rev_timestamp' => $now,
- 'inverse_timestamp' => $won,
), $fname );
$dbw->update( 'page',
'rev_page=' . IntVal( $this->getArticleId() ) .
' AND rev_id>' . IntVal( $revision ) . ' ORDER BY rev_id' );
}
+
+ /**
+ * Compare with another title.
+ *
+ * @param Title $title
+ * @return bool
+ */
+ function equals( &$title ) {
+ return $this->getInterwiki() == $title->getInterwiki()
+ && $this->getNamespace() == $title->getNamespace()
+ && $this->getDbkey() == $title->getDbkey();
+ }
+
+ /**
+ * Convert Windows-1252 extended codepoints to their real Unicode points.
+ * @param int $codepoint
+ * @return int
+ * @access private
+ */
+ function cp1252toUnicode( $codepoint ) {
+ # Mappings from:
+ # http://www.unicode.org/Public/MAPPINGS/VENDORS/MICSFT/WINDOWS/CP1252.TXT
+ static $cp1252 = array(
+ 0x80 => 0x20AC, #EURO SIGN
+ 0x81 => UNICODE_REPLACEMENT,
+ 0x82 => 0x201A, #SINGLE LOW-9 QUOTATION MARK
+ 0x83 => 0x0192, #LATIN SMALL LETTER F WITH HOOK
+ 0x84 => 0x201E, #DOUBLE LOW-9 QUOTATION MARK
+ 0x85 => 0x2026, #HORIZONTAL ELLIPSIS
+ 0x86 => 0x2020, #DAGGER
+ 0x87 => 0x2021, #DOUBLE DAGGER
+ 0x88 => 0x02C6, #MODIFIER LETTER CIRCUMFLEX ACCENT
+ 0x89 => 0x2030, #PER MILLE SIGN
+ 0x8A => 0x0160, #LATIN CAPITAL LETTER S WITH CARON
+ 0x8B => 0x2039, #SINGLE LEFT-POINTING ANGLE QUOTATION MARK
+ 0x8C => 0x0152, #LATIN CAPITAL LIGATURE OE
+ 0x8D => UNICODE_REPLACEMENT,
+ 0x8E => 0x017D, #LATIN CAPITAL LETTER Z WITH CARON
+ 0x8F => UNICODE_REPLACEMENT,
+ 0x90 => UNICODE_REPLACEMENT,
+ 0x91 => 0x2018, #LEFT SINGLE QUOTATION MARK
+ 0x92 => 0x2019, #RIGHT SINGLE QUOTATION MARK
+ 0x93 => 0x201C, #LEFT DOUBLE QUOTATION MARK
+ 0x94 => 0x201D, #RIGHT DOUBLE QUOTATION MARK
+ 0x95 => 0x2022, #BULLET
+ 0x96 => 0x2013, #EN DASH
+ 0x97 => 0x2014, #EM DASH
+ 0x98 => 0x02DC, #SMALL TILDE
+ 0x99 => 0x2122, #TRADE MARK SIGN
+ 0x9A => 0x0161, #LATIN SMALL LETTER S WITH CARON
+ 0x9B => 0x203A, #SINGLE RIGHT-POINTING ANGLE QUOTATION MARK
+ 0x9C => 0x0153, #LATIN SMALL LIGATURE OE
+ 0x9D => UNICODE_REPLACEMENT,
+ 0x9E => 0x017E, #LATIN SMALL LETTER Z WITH CARON
+ 0x9F => 0x0178, #LATIN CAPITAL LETTER Y WITH DIAERESIS
+ );
+ return isset( $cp1252[$codepoint] )
+ ? $cp1252[$codepoint]
+ : $codepoint;
+ }
+
+ /**
+ * HACKHACKHACK
+ * Take a string containing a mix of CP1252 characters and UTF-8 and try
+ * to convert it completely to UTF-8.
+ *
+ * @param string $string
+ * @return string
+ * @access private
+ */
+ function mergeLatin1Utf8( $string ) {
+ return preg_replace_callback(
+ # Windows CP1252 extends ISO-8859-1 by putting extra characters
+ # into the high control chars area. We have to convert these
+ # to their proper Unicode counterparts.
+ '/([\x80-\x9f])/u',
+ create_function( '$matches',
+ 'return codepointToUtf8(
+ Title::cp1252toUnicode(
+ utf8ToCodepoint( $matches[1] ) ) );' ),
+ preg_replace_callback(
+ # Up-convert everything from 8-bit to UTF-8, then
+ # filter the valid-looking UTF-8 back from the
+ # double-converted form.
+ '/((?:[\xc0-\xdf][\x80-\xbf]
+ |[\xe0-\xef][\x80-\xbf]{2}
+ |[\xf0-\xf7][\x80-\xbf]{3})+)/ux',
+ create_function( '$matches',
+ 'return utf8_decode( $matches[1] );' ),
+ utf8_encode( $string ) ) );
+ }
}
?>