Xomw: Start converting XomwLinkHolderArray

400_xowa/src/gplx/core/lists/hashs/Hash_adp__int.java

@@ -18,7 +18,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 package gplx.core.lists.hashs; import gplx.*; import gplx.core.*; import gplx.core.lists.*;
 import gplx.core.primitives.*;
 public class Hash_adp__int {
-	private final    Ordered_hash hash = Ordered_hash_.New();
+	private final    Hash_adp hash = Hash_adp_.New();
 	private final    Int_obj_ref tmp_key = Int_obj_ref.New_neg1();
 	public void Clear()								{hash.Clear();}
 	public int Len()								{return hash.Count();}

gplx.xowa.mediawiki/src/gplx/core/lists/HashByInt.java

@@ -0,0 +1,65 @@
+/*
+XOWA: the XOWA Offline Wiki Application
+Copyright (C) 2012 gnosygnu@gmail.com
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU Affero General Public License as
+published by the Free Software Foundation, either version 3 of the
+License, or (at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU Affero General Public License for more details.
+
+You should have received a copy of the GNU Affero General Public License
+along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/
+package gplx.core.lists; import gplx.*; import gplx.core.*;
+import gplx.core.primitives.*;
+public class HashByInt {
+	private final    Ordered_hash hash = Ordered_hash_.New();
+	private final    Int_obj_ref tmp_key = Int_obj_ref.New_neg1();
+	public void Clear() {
+		hash.Clear();
+	}
+	public int Len() {
+		return hash.Len();
+	}
+	public Object Get_by_or_fail(int key) {
+		synchronized (tmp_key) {
+			HashByIntItem item = (HashByIntItem)hash.Get_by_or_fail(tmp_key.Val_(key));
+			return item.val;
+		}
+	}
+	public Object Get_by_or_null(int key) {
+		synchronized (tmp_key) {
+			HashByIntItem item = (HashByIntItem)hash.Get_by(tmp_key.Val_(key));
+			return item == null ? null : item.val;
+		}
+	}
+	public HashByInt Add_as_bry(int key, String val) {return Add(key, Bry_.new_u8(val));}
+	public HashByInt Add(int key, Object val) {
+		HashByIntItem item = new HashByIntItem(key, val);
+		hash.Add(Int_obj_ref.New(key), item);
+		return this;
+	}
+	public HashByInt Clone() {
+		HashByInt rv = new HashByInt();
+
+		int len = hash.Len();
+		for (int i = 0; i < len; i++) {
+			HashByIntItem item = (HashByIntItem)hash.Get_at(i);
+			rv.Add(item.key, item);
+		}
+		return rv;
+	}
+}
+class HashByIntItem {
+	public final    int key;
+	public final    Object val;
+	public HashByIntItem(int key, Object val) {
+		this.key = key;
+		this.val = val;
+	}
+}

gplx.xowa.mediawiki/src/gplx/xowa/mediawiki/includes/XomwNamespace.java

@@ -16,9 +16,8 @@ You should have received a copy of the GNU Affero General Public License
 along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */
 package gplx.xowa.mediawiki.includes; import gplx.*; import gplx.xowa.*; import gplx.xowa.mediawiki.*;
-import gplx.core.lists.hashs.*;
+import gplx.core.lists.*;
 public class XomwNamespace {
-//
 //		/**
 //		* These namespaces should always be first-letter capitalized, now and
 //		* forevermore. Historically, they could've probably been lowercased too,
@@ -192,12 +191,12 @@ public class XomwNamespace {
 	* @return array
 	* @since 1.17
 	*/
-	private static Hash_adp__int namespaces = null;
+	private static HashByInt namespaces = null;
-	public static Hash_adp__int getCanonicalNamespaces() {return getCanonicalNamespaces(false);}
+	public static HashByInt getCanonicalNamespaces() {return getCanonicalNamespaces(false);}
-	public static Hash_adp__int getCanonicalNamespaces(boolean rebuild) {
+	public static HashByInt getCanonicalNamespaces(boolean rebuild) {
 		if (namespaces == null || rebuild) {
 //				global $wgExtraNamespaces, $wgCanonicalNamespaceNames;
-			namespaces = XomwSetup.wgCanonicalNamespaceNames;
+			namespaces = XomwSetup.wgCanonicalNamespaceNames.Clone();
 			namespaces.Add_as_bry(XomwDefines.NS_MAIN, "");
 
 //				// Add extension namespaces

gplx.xowa.mediawiki/src/gplx/xowa/mediawiki/includes/XomwSetup.java

@@ -16,7 +16,7 @@ You should have received a copy of the GNU Affero General Public License
 along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */
 package gplx.xowa.mediawiki.includes; import gplx.*; import gplx.xowa.*; import gplx.xowa.mediawiki.*;
-import gplx.core.lists.hashs.*;
+import gplx.core.lists.*;
 /**
 * Include most things that are needed to make MediaWiki work.
 *
@@ -395,7 +395,7 @@ public class XomwSetup {
 	* Definitions of the NS_ constants are in Defines.php
 	* @private
 	*/
-	public static Hash_adp__int wgCanonicalNamespaceNames = new Hash_adp__int()
+	public static HashByInt wgCanonicalNamespaceNames = new HashByInt()
 		.Add_as_bry(XomwDefines.NS_MEDIA            ,  "Media")
 		.Add_as_bry(XomwDefines.NS_SPECIAL          ,  "Special")
 		.Add_as_bry(XomwDefines.NS_TALK             ,  "Talk")

gplx.xowa.mediawiki/src/gplx/xowa/mediawiki/includes/XomwTitle.java

@@ -204,7 +204,7 @@ public class XomwTitle {
 //			try {
 //				t.secureAndSplit();
 //				return t;
-//			} catch (MalformedTitleException $ex) {
+//			} catch (XomwMalformedTitleException $ex) {
 //				return null;
 //			}
 //		}
@@ -266,14 +266,14 @@ public class XomwTitle {
 
 		try {
 			return XomwTitle.newFromTextThrow(text, defaultNamespace);
-		} catch (MalformedTitleException ex) {
+		} catch (XomwMalformedTitleException ex) {
 			Err_.Noop(ex);
 			return null;
 		}
 	}
 
 	/**
-	* Like Title::newFromText(), but throws MalformedTitleException when the title is invalid,
+	* Like Title::newFromText(), but throws XomwMalformedTitleException when the title is invalid,
 	* rather than returning null.
 	*
 	* The exception subclasses encode detailed information about why the title is invalid.
@@ -283,7 +283,7 @@ public class XomwTitle {
 	* @since 1.25
 	* @param String $text Title text to check
 	* @param int $defaultNamespace
-	* @throws MalformedTitleException If the title is invalid
+	* @throws XomwMalformedTitleException If the title is invalid
 	* @return Title
 	*/
 	public static XomwTitle newFromTextThrow(byte[] text, int defaultNamespace) {
@@ -351,7 +351,7 @@ public class XomwTitle {
 //			try {
 //				t.secureAndSplit();
 //				return t;
-//			} catch (MalformedTitleException $ex) {
+//			} catch (XomwMalformedTitleException $ex) {
 //				return null;
 //			}
 //		}
@@ -543,7 +543,7 @@ public class XomwTitle {
 //			try {
 //				t.secureAndSplit();
 //				return t;
-//			} catch (MalformedTitleException $ex) {
+//			} catch (XomwMalformedTitleException $ex) {
 //				return null;
 //			}
 //		}
@@ -988,7 +988,7 @@ public class XomwTitle {
 		}
 
 //			try {
-			XomwMediaWikiTitleCodec formatter = getTitleFormatter();
+			XomwTitleFormatter formatter = getTitleFormatter();
 			return formatter.getNamespaceName(this.mNamespace, this.mDbkeyform);
 //			} catch (InvalidArgumentException $ex) {
 //				wfDebug(__METHOD__ . ': ' . $ex.getMessage() . "\n");
@@ -3351,7 +3351,7 @@ public class XomwTitle {
 	* namespace prefixes, sets the other forms, and canonicalizes
 	* everything.
 	*
-	* @throws MalformedTitleException On invalid titles
+	* @throws XomwMalformedTitleException On invalid titles
 	* @return boolean True on success
 	*/
 	private boolean secureAndSplit() {
@@ -3368,7 +3368,7 @@ public class XomwTitle {
 		// @note: getTitleParser() returns a TitleParser implementation which does not have a
 		//        splitTitleString method, but the only implementation (MediaWikiTitleCodec) does
 		XomwMediaWikiTitleCodec titleCodec = XomwMediaWikiServices.getInstance().getTitleParser();
-		// MalformedTitleException can be thrown here
+		// XomwMalformedTitleException can be thrown here
 		XomwMediaWikiTitleCodecParts parts = titleCodec.splitTitleString(dbkey, this.getDefaultNamespace());
 
 		// Fill fields

gplx.xowa.mediawiki/src/gplx/xowa/mediawiki/includes/parsers/XomwLinkHolderArray.java

@@ -0,0 +1,638 @@
+/*
+XOWA: the XOWA Offline Wiki Application
+Copyright (C) 2012 gnosygnu@gmail.com
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU Affero General Public License as
+published by the Free Software Foundation, either version 3 of the
+License, or (at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU Affero General Public License for more details.
+
+You should have received a copy of the GNU Affero General Public License
+along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/
+package gplx.xowa.mediawiki.includes.parsers; import gplx.*; import gplx.xowa.*; import gplx.xowa.mediawiki.*; import gplx.xowa.mediawiki.includes.*;
+import gplx.langs.htmls.*;
+/**
+* Holder of replacement pairs for wiki links
+*/
+public class XomwLinkHolderArray {
+	private final    Bry_bfr tmp = Bry_bfr_.New();
+	private final    Xomw_link_holder_list internals = new Xomw_link_holder_list();
+//		public $interwikis = [];
+//		public $size = 0;
+//
+	/**
+	* @var Parser
+	*/
+	private final    Xomw_parser parent;
+//		protected $tempIdOffset;
+
+	/**
+	* @param Parser $parent
+	*/
+	public XomwLinkHolderArray(Xomw_parser parent) {
+		this.parent = parent;
+	}
+
+//		/**
+//		* Reduce memory usage to reduce the impact of circular references
+//		*/
+//		public function __destruct() {
+//			foreach ( $this as $name => $value ) {
+//				unset( $this->$name );
+//			}
+//		}
+//
+//		/**
+//		* Don't serialize the parent Object, it is big, and not needed when it is
+//		* a parameter to mergeForeign(), which is the only application of
+//		* serializing at present.
+//		*
+//		* Compact the titles, only serialize the text form.
+//		* @return array
+//		*/
+//		public function __sleep() {
+//			foreach ( $this->internals as &$nsLinks ) {
+//				foreach ( $nsLinks as &$entry ) {
+//					unset( $entry['title'] );
+//				}
+//			}
+//			unset( $nsLinks );
+//			unset( $entry );
+//
+//			foreach ( $this->interwikis as &$entry ) {
+//				unset( $entry['title'] );
+//			}
+//			unset( $entry );
+//
+//			return [ 'internals', 'interwikis', 'size' ];
+//		}
+//
+//		/**
+//		* Recreate the Title objects
+//		*/
+//		public function __wakeup() {
+//			foreach ( $this->internals as &$nsLinks ) {
+//				foreach ( $nsLinks as &$entry ) {
+//					$entry['title'] = Title::newFromText( $entry['pdbk'] );
+//				}
+//			}
+//			unset( $nsLinks );
+//			unset( $entry );
+//
+//			foreach ( $this->interwikis as &$entry ) {
+//				$entry['title'] = Title::newFromText( $entry['pdbk'] );
+//			}
+//			unset( $entry );
+//		}
+//
+//		/**
+//		* Merge another LinkHolderArray into this one
+//		* @param LinkHolderArray $other
+//		*/
+//		public function merge( $other ) {
+//			foreach ( $other->internals as $ns => $entries ) {
+//				$this->size += count( $entries );
+//				if ( !isset( $this->internals[$ns] ) ) {
+//					$this->internals[$ns] = $entries;
+//				} else {
+//					$this->internals[$ns] += $entries;
+//				}
+//			}
+//			$this->interwikis += $other->interwikis;
+//		}
+//
+//		/**
+//		* Merge a LinkHolderArray from another parser instance into this one. The
+//		* keys will not be preserved. Any text which went with the old
+//		* LinkHolderArray and needs to work with the new one should be passed in
+//		* the $texts array. The strings in this array will have their link holders
+//		* converted for use in the destination link holder. The resulting array of
+//		* strings will be returned.
+//		*
+//		* @param LinkHolderArray $other
+//		* @param array $texts Array of strings
+//		* @return array
+//		*/
+//		public function mergeForeign( $other, $texts ) {
+//			$this->tempIdOffset = $idOffset = $this->parent->nextLinkID();
+//			$maxId = 0;
+//
+//			# Renumber @gplx.Internal protected links
+//			foreach ( $other->internals as $ns => $nsLinks ) {
+//				foreach ( $nsLinks as $key => $entry ) {
+//					$newKey = $idOffset + $key;
+//					$this->internals[$ns][$newKey] = $entry;
+//					$maxId = $newKey > $maxId ? $newKey : $maxId;
+//				}
+//			}
+//			$texts = preg_replace_callback( '/(<!--LINK \d+:)(\d+)(-->)/',
+//				[ $this, 'mergeForeignCallback' ], $texts );
+//
+//			# Renumber interwiki links
+//			foreach ( $other->interwikis as $key => $entry ) {
+//				$newKey = $idOffset + $key;
+//				$this->interwikis[$newKey] = $entry;
+//				$maxId = $newKey > $maxId ? $newKey : $maxId;
+//			}
+//			$texts = preg_replace_callback( '/(<!--IWLINK )(\d+)(-->)/',
+//				[ $this, 'mergeForeignCallback' ], $texts );
+//
+//			# Set the parent link ID to be beyond the highest used ID
+//			$this->parent->setLinkID( $maxId + 1 );
+//			$this->tempIdOffset = null;
+//			return $texts;
+//		}
+//
+//		/**
+//		* @param array $m
+//		* @return String
+//		*/
+//		protected function mergeForeignCallback( $m ) {
+//			return $m[1] . ( $m[2] + $this->tempIdOffset ) . $m[3];
+//		}
+//
+//		/**
+//		* Get a subset of the current LinkHolderArray which is sufficient to
+//		* interpret the given text.
+//		* @param String $text
+//		* @return LinkHolderArray
+//		*/
+//		public function getSubArray( $text ) {
+//			$sub = new LinkHolderArray( $this->parent );
+//
+//			# Internal links
+//			$pos = 0;
+//			while ( $pos < strlen( $text ) ) {
+//				if ( !preg_match( '/<!--LINK (\d+):(\d+)-->/',
+//					$text, $m, PREG_OFFSET_CAPTURE, $pos )
+//				) {
+//					break;
+//				}
+//				$ns = $m[1][0];
+//				$key = $m[2][0];
+//				$sub->internals[$ns][$key] = $this->internals[$ns][$key];
+//				$pos = $m[0][1] + strlen( $m[0][0] );
+//			}
+//
+//			# Interwiki links
+//			$pos = 0;
+//			while ( $pos < strlen( $text ) ) {
+//				if ( !preg_match( '/<!--IWLINK (\d+)-->/', $text, $m, PREG_OFFSET_CAPTURE, $pos ) ) {
+//					break;
+//				}
+//				$key = $m[1][0];
+//				$sub->interwikis[$key] = $this->interwikis[$key];
+//				$pos = $m[0][1] + strlen( $m[0][0] );
+//			}
+//			return $sub;
+//		}
+//
+//		/**
+//		* Returns true if the memory requirements of this Object are getting large
+//		* @return boolean
+//		*/
+//		public function isBig() {
+//			global $wgLinkHolderBatchSize;
+//			return $this->size > $wgLinkHolderBatchSize;
+//		}
+//
+//		/**
+//		* Clear all stored link holders.
+//		* Make sure you don't have any text left using these link holders, before you call this
+//		*/
+//		public function clear() {
+//			$this->internals = [];
+//			$this->interwikis = [];
+//			$this->size = 0;
+//		}
+
+	/**
+	* Make a link placeholder. The text returned can be later resolved to a real link with
+	* replaceLinkHolders(). This is done for two reasons: firstly to avoid further
+	* parsing of interwiki links, and secondly to allow all existence checks and
+	* article length checks (for stub links) to be bundled into a single query.
+	*
+	* @param Title $nt
+	* @param String $text
+	* @param array $query [optional]
+	* @param String $trail [optional]
+	* @param String $prefix [optional]
+	* @return String
+	*/
+	public void makeHolder(Bry_bfr bfr, XomwTitle nt, byte[] text, byte[][] query, byte[] trail, byte[] prefix) {
+		if (nt == null) {
+			// Fail gracefully
+			bfr.Add_str_a7("<!-- ERROR -->").Add(prefix).Add(text).Add(trail);
+		}
+		else {
+			// Separate the link trail from the rest of the link
+//				list( $inside, $trail ) = Linker::splitTrail( $trail );
+			byte[] inside = Bry_.Empty;
+
+			Xomw_link_holder_item entry = new Xomw_link_holder_item
+				( nt
+				, tmp.Add_bry_many(prefix, text, inside).To_bry_and_clear()
+				, query);
+
+			if (nt.isExternal()) {
+				// Use a globally unique ID to keep the objects mergable
+//					$key = $this->parent->nextLinkID();
+//					$this->interwikis[$key] = $entry;
+//					$retVal = "<!--IWLINK $key-->{$trail}";
+			}
+			else {
+				int key = this.parent.nextLinkID();
+				this.internals.Add(key, entry);
+				bfr.Add(Bry__link__bgn).Add_int_variable(key).Add(Gfh_tag_.Comm_end).Add(trail);	// "<!--LINK $ns:$key-->{$trail}";
+			}
+		}
+	}
+//
+//		/**
+//		* Replace <!--LINK--> link placeholders with actual links, in the buffer
+//		*
+//		* @param String $text
+//		*/
+//		public function replace( &$text ) {
+//			$this->replaceInternal( $text );
+//			$this->replaceInterwiki( $text );
+//		}
+//
+//		/**
+//		* Replace @gplx.Internal protected links
+//		* @param String $text
+//		*/
+//		protected function replaceInternal( &$text ) {
+//			if ( !$this->internals ) {
+//				return;
+//			}
+//
+//			global $wgContLang;
+//
+//			$colours = [];
+//			$linkCache = LinkCache::singleton();
+//			$output = $this->parent->getOutput();
+//			$linkRenderer = $this->parent->getLinkRenderer();
+//
+//			$dbr = wfGetDB( DB_REPLICA );
+//
+//			# Sort by namespace
+//			ksort( $this->internals );
+//
+//			$linkcolour_ids = [];
+//
+//			# Generate query
+//			$lb = new LinkBatch();
+//			$lb->setCaller( __METHOD__ );
+//
+//			foreach ( $this->internals as $ns => $entries ) {
+//				foreach ( $entries as $entry ) {
+//					/** @var Title $title */
+//					$title = $entry['title'];
+//					$pdbk = $entry['pdbk'];
+//
+//					# Skip invalid entries.
+//					# Result will be ugly, but prevents crash.
+//					if ( is_null( $title ) ) {
+//						continue;
+//					}
+//
+//					# Check if it's a static known link, e.g. interwiki
+//					if ( $title->isAlwaysKnown() ) {
+//						$colours[$pdbk] = '';
+//					} elseif ( $ns == NS_SPECIAL ) {
+//						$colours[$pdbk] = 'new';
+//					} else {
+//						$id = $linkCache->getGoodLinkID( $pdbk );
+//						if ( $id != 0 ) {
+//							$colours[$pdbk] = $linkRenderer->getLinkClasses( $title );
+//							$output->addLink( $title, $id );
+//							$linkcolour_ids[$id] = $pdbk;
+//						} elseif ( $linkCache->isBadLink( $pdbk ) ) {
+//							$colours[$pdbk] = 'new';
+//						} else {
+//							# Not in the link cache, add it to the query
+//							$lb->addObj( $title );
+//						}
+//					}
+//				}
+//			}
+//			if ( !$lb->isEmpty() ) {
+//				$fields = array_merge(
+//					LinkCache::getSelectFields(),
+//					[ 'page_namespace', 'page_title' ]
+//				);
+//
+//				$res = $dbr->select(
+//					'page',
+//					$fields,
+//					$lb->constructSet( 'page', $dbr ),
+//					__METHOD__
+//				);
+//
+//				# Fetch data and form into an associative array
+//				# non-existent = broken
+//				foreach ( $res as $s ) {
+//					$title = Title::makeTitle( $s->page_namespace, $s->page_title );
+//					$pdbk = $title->getPrefixedDBkey();
+//					$linkCache->addGoodLinkObjFromRow( $title, $s );
+//					$output->addLink( $title, $s->page_id );
+//					$colours[$pdbk] = $linkRenderer->getLinkClasses( $title );
+//					// add id to the extension todolist
+//					$linkcolour_ids[$s->page_id] = $pdbk;
+//				}
+//				unset( $res );
+//			}
+//			if ( count( $linkcolour_ids ) ) {
+//				// pass an array of page_ids to an extension
+//				Hooks::run( 'GetLinkColours', [ $linkcolour_ids, &$colours ] );
+//			}
+//
+//			# Do a second query for different language variants of links and categories
+//			if ( $wgContLang->hasVariants() ) {
+//				$this->doVariants( $colours );
+//			}
+//
+//			# Construct search and replace arrays
+//			$replacePairs = [];
+//			foreach ( $this->internals as $ns => $entries ) {
+//				foreach ( $entries as $index => $entry ) {
+//					$pdbk = $entry['pdbk'];
+//					$title = $entry['title'];
+//					$query = isset( $entry['query'] ) ? $entry['query'] : [];
+//					$key = "$ns:$index";
+//					$searchkey = "<!--LINK $key-->";
+//					$displayText = $entry['text'];
+//					if ( isset( $entry['selflink'] ) ) {
+//						$replacePairs[$searchkey] = Linker::makeSelfLinkObj( $title, $displayText, $query );
+//						continue;
+//					}
+//					if ( $displayText === '' ) {
+//						$displayText = null;
+//					} else {
+//						$displayText = new HtmlArmor( $displayText );
+//					}
+//					if ( !isset( $colours[$pdbk] ) ) {
+//						$colours[$pdbk] = 'new';
+//					}
+//					$attribs = [];
+//					if ( $colours[$pdbk] == 'new' ) {
+//						$linkCache->addBadLinkObj( $title );
+//						$output->addLink( $title, 0 );
+//						$link = $linkRenderer->makeBrokenLink(
+//							$title, $displayText, $attribs, $query
+//						);
+//					} else {
+//						$link = $linkRenderer->makePreloadedLink(
+//							$title, $displayText, $colours[$pdbk], $attribs, $query
+//						);
+//					}
+//
+//					$replacePairs[$searchkey] = $link;
+//				}
+//			}
+//			$replacer = new HashtableReplacer( $replacePairs, 1 );
+//
+//			# Do the thing
+//			$text = preg_replace_callback(
+//				'/(<!--LINK .*?-->)/',
+//				$replacer->cb(),
+//				$text
+//			);
+//		}
+//
+//		/**
+//		* Replace interwiki links
+//		* @param String $text
+//		*/
+//		protected function replaceInterwiki( &$text ) {
+//			if ( empty( $this->interwikis ) ) {
+//				return;
+//			}
+//
+//			# Make interwiki link HTML
+//			$output = $this->parent->getOutput();
+//			$replacePairs = [];
+//			$linkRenderer = $this->parent->getLinkRenderer();
+//			foreach ( $this->interwikis as $key => $link ) {
+//				$replacePairs[$key] = $linkRenderer->makeLink(
+//					$link['title'],
+//					new HtmlArmor( $link['text'] )
+//				);
+//				$output->addInterwikiLink( $link['title'] );
+//			}
+//			$replacer = new HashtableReplacer( $replacePairs, 1 );
+//
+//			$text = preg_replace_callback(
+//				'/<!--IWLINK (.*?)-->/',
+//				$replacer->cb(),
+//				$text );
+//		}
+//
+//		/**
+//		* Modify $this->internals and $colours according to language variant linking rules
+//		* @param array $colours
+//		*/
+//		protected function doVariants( &$colours ) {
+//			global $wgContLang;
+//			$linkBatch = new LinkBatch();
+//			$variantMap = []; // maps $pdbkey_Variant => $keys (of link holders)
+//			$output = $this->parent->getOutput();
+//			$linkCache = LinkCache::singleton();
+//			$titlesToBeConverted = '';
+//			$titlesAttrs = [];
+//
+//			// Concatenate titles to a single String, thus we only need auto convert the
+//			// single String to all variants. This would improve parser's performance
+//			// significantly.
+//			foreach ( $this->internals as $ns => $entries ) {
+//				if ( $ns == NS_SPECIAL ) {
+//					continue;
+//				}
+//				foreach ( $entries as $index => $entry ) {
+//					$pdbk = $entry['pdbk'];
+//					// we only deal with new links (in its first query)
+//					if ( !isset( $colours[$pdbk] ) || $colours[$pdbk] === 'new' ) {
+//						$titlesAttrs[] = [ $index, $entry['title'] ];
+//						// separate titles with \0 because it would never appears
+//						// in a valid title
+//						$titlesToBeConverted .= $entry['title']->getText() . "\0";
+//					}
+//				}
+//			}
+//
+//			// Now do the conversion and explode String to text of titles
+//			$titlesAllVariants = $wgContLang->autoConvertToAllVariants( rtrim( $titlesToBeConverted, "\0" ) );
+//			$allVariantsName = array_keys( $titlesAllVariants );
+//			foreach ( $titlesAllVariants as &$titlesVariant ) {
+//				$titlesVariant = explode( "\0", $titlesVariant );
+//			}
+//
+//			// Then add variants of links to link batch
+//			$parentTitle = $this->parent->getTitle();
+//			foreach ( $titlesAttrs as $i => $attrs ) {
+//				/** @var Title $title */
+//				list( $index, $title ) = $attrs;
+//				$ns = $title->getNamespace();
+//				$text = $title->getText();
+//
+//				foreach ( $allVariantsName as $variantName ) {
+//					$textVariant = $titlesAllVariants[$variantName][$i];
+//					if ( $textVariant === $text ) {
+//						continue;
+//					}
+//
+//					$variantTitle = Title::makeTitle( $ns, $textVariant );
+//
+//					// Self-link checking for mixed/different variant titles. At this point, we
+//					// already know the exact title does not exist, so the link cannot be to a
+//					// variant of the current title that exists as a separate page.
+//					if ( $variantTitle->equals( $parentTitle ) && !$title->hasFragment() ) {
+//						$this->internals[$ns][$index]['selflink'] = true;
+//						continue 2;
+//					}
+//
+//					$linkBatch->addObj( $variantTitle );
+//					$variantMap[$variantTitle->getPrefixedDBkey()][] = "$ns:$index";
+//				}
+//			}
+//
+//			// process categories, check if a category exists in some variant
+//			$categoryMap = []; // maps $category_variant => $category (dbkeys)
+//			$varCategories = []; // category replacements oldDBkey => newDBkey
+//			foreach ( $output->getCategoryLinks() as $category ) {
+//				$categoryTitle = Title::makeTitleSafe( NS_CATEGORY, $category );
+//				$linkBatch->addObj( $categoryTitle );
+//				$variants = $wgContLang->autoConvertToAllVariants( $category );
+//				foreach ( $variants as $variant ) {
+//					if ( $variant !== $category ) {
+//						$variantTitle = Title::makeTitleSafe( NS_CATEGORY, $variant );
+//						if ( is_null( $variantTitle ) ) {
+//							continue;
+//						}
+//						$linkBatch->addObj( $variantTitle );
+//						$categoryMap[$variant] = [ $category, $categoryTitle ];
+//					}
+//				}
+//			}
+//
+//			if ( !$linkBatch->isEmpty() ) {
+//				// construct query
+//				$dbr = wfGetDB( DB_REPLICA );
+//				$fields = array_merge(
+//					LinkCache::getSelectFields(),
+//					[ 'page_namespace', 'page_title' ]
+//				);
+//
+//				$varRes = $dbr->select( 'page',
+//					$fields,
+//					$linkBatch->constructSet( 'page', $dbr ),
+//					__METHOD__
+//				);
+//
+//				$linkcolour_ids = [];
+//				$linkRenderer = $this->parent->getLinkRenderer();
+//
+//				// for each found variants, figure out link holders and replace
+//				foreach ( $varRes as $s ) {
+//					$variantTitle = Title::makeTitle( $s->page_namespace, $s->page_title );
+//					$varPdbk = $variantTitle->getPrefixedDBkey();
+//					$vardbk = $variantTitle->getDBkey();
+//
+//					$holderKeys = [];
+//					if ( isset( $variantMap[$varPdbk] ) ) {
+//						$holderKeys = $variantMap[$varPdbk];
+//						$linkCache->addGoodLinkObjFromRow( $variantTitle, $s );
+//						$output->addLink( $variantTitle, $s->page_id );
+//					}
+//
+//					// loop over link holders
+//					foreach ( $holderKeys as $key ) {
+//						list( $ns, $index ) = explode( ':', $key, 2 );
+//						$entry =& $this->internals[$ns][$index];
+//						$pdbk = $entry['pdbk'];
+//
+//						if ( !isset( $colours[$pdbk] ) || $colours[$pdbk] === 'new' ) {
+//							// found link in some of the variants, replace the link holder data
+//							$entry['title'] = $variantTitle;
+//							$entry['pdbk'] = $varPdbk;
+//
+//							// set pdbk and colour
+//							$colours[$varPdbk] = $linkRenderer->getLinkClasses( $variantTitle );
+//							$linkcolour_ids[$s->page_id] = $pdbk;
+//						}
+//					}
+//
+//					// check if the Object is a variant of a category
+//					if ( isset( $categoryMap[$vardbk] ) ) {
+//						list( $oldkey, $oldtitle ) = $categoryMap[$vardbk];
+//						if ( !isset( $varCategories[$oldkey] ) && !$oldtitle->exists() ) {
+//							$varCategories[$oldkey] = $vardbk;
+//						}
+//					}
+//				}
+//				Hooks::run( 'GetLinkColours', [ $linkcolour_ids, &$colours ] );
+//
+//				// rebuild the categories in original order (if there are replacements)
+//				if ( count( $varCategories ) > 0 ) {
+//					$newCats = [];
+//					$originalCats = $output->getCategories();
+//					foreach ( $originalCats as $cat => $sortkey ) {
+//						// make the replacement
+//						if ( array_key_exists( $cat, $varCategories ) ) {
+//							$newCats[$varCategories[$cat]] = $sortkey;
+//						} else {
+//							$newCats[$cat] = $sortkey;
+//						}
+//					}
+//					$output->setCategoryLinks( $newCats );
+//				}
+//			}
+//		}
+//
+//		/**
+//		* Replace <!--LINK--> link placeholders with plain text of links
+//		* (not HTML-formatted).
+//		*
+//		* @param String $text
+//		* @return String
+//		*/
+//		public function replaceText( $text ) {
+//			$text = preg_replace_callback(
+//				'/<!--(LINK|IWLINK) (.*?)-->/',
+//				[ &$this, 'replaceTextCallback' ],
+//				$text );
+//
+//			return $text;
+//		}
+//
+//		/**
+//		* Callback for replaceText()
+//		*
+//		* @param array $matches
+//		* @return String
+//		* @private
+//		*/
+//		public function replaceTextCallback( $matches ) {
+//			$type = $matches[1];
+//			$key = $matches[2];
+//			if ( $type == 'LINK' ) {
+//				list( $ns, $index ) = explode( ':', $key, 2 );
+//				if ( isset( $this->internals[$ns][$index]['text'] ) ) {
+//					return $this->internals[$ns][$index]['text'];
+//				}
+//			} elseif ( $type == 'IWLINK' ) {
+//				if ( isset( $this->interwikis[$key]['text'] ) ) {
+//					return $this->interwikis[$key]['text'];
+//				}
+//			}
+//			return $matches[0];
+//		}
+	private static final    byte[] Bry__link__bgn = Bry_.new_a7("<!--LINK ");
+}

gplx.xowa.mediawiki/src/gplx/xowa/mediawiki/includes/parsers/Xomw_parser.java

@@ -52,6 +52,17 @@ public class Xomw_parser {
 	public Xomw_quote_wkr          Quote_wkr()       {return quote_wkr;}      private final    Xomw_quote_wkr quote_wkr;
 	public Xomw_lnki_wkr           Lnki_wkr()        {return lnki_wkr;}       private final    Xomw_lnki_wkr lnki_wkr;
 	public boolean                 Output_type__wiki() {return output_type__wiki;} private final    boolean output_type__wiki = false;
+
+
+	private int mLinkID;
+	/**
+	* @return int
+	*/
+	public int nextLinkID() {
+		return this.mLinkID++;
+	}
+
+
 	public Xomw_parser() {
 		if (regex_space == null) {
 			synchronized (Type_adp_.ClassOf_obj(this)) {

gplx.xowa.mediawiki/src/gplx/xowa/mediawiki/includes/parsers/lnkis/Xomw_lnki_wkr.java

@@ -675,16 +675,17 @@ public class Xomw_lnki_wkr {// THREAD.UNSAFE: caching for repeated calls
 //				$handler->parserTransformHook($this, $file);
 //			}
 	}
-//		protected function stripAltText( $caption, $holders ) {
+//		private byte[] stripAltText(byte[] caption, Xomw_link_holders holders) {
 //			// Strip bad stuff out of the title (tooltip).  We can't just use
 //			// replaceLinkHoldersText() here, because if this function is called
 //			// from replaceInternalLinks2(), mLinkHolders won't be up-to-date.
-//			if ( $holders ) {
+//			byte[] tooltip;
-//				$tooltip = $holders->replaceText( $caption );
+//			if (holders != null) {
+//				tooltip = holders.Replace(caption);
 //			} else {
-//				$tooltip = $this->replaceLinkHoldersText( $caption );
+//				tooltip = this.Replace_link_holders(caption);
 //			}
-//
+
 //			// make sure there are no placeholders in thumbnail attributes
 //			// that are later expanded to html- so expand them now and
 //			// remove the tags

gplx.xowa.mediawiki/src/gplx/xowa/mediawiki/includes/title/XomwMalformedTitleException.java

@@ -16,5 +16,5 @@ You should have received a copy of the GNU Affero General Public License
 along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */
 package gplx.xowa.mediawiki.includes.title; import gplx.*; import gplx.xowa.*; import gplx.xowa.mediawiki.*; import gplx.xowa.mediawiki.includes.*;
-public class MalformedTitleException extends Err { 	public MalformedTitleException(String name, byte[] text) {super(false, "", name, name);}
+public class XomwMalformedTitleException extends Err { 	public XomwMalformedTitleException(String name, byte[] text) {super(false, "", name, name);}
 }

gplx.xowa.mediawiki/src/gplx/xowa/mediawiki/includes/title/XomwMediaWikiTitleCodec.java

@@ -18,7 +18,7 @@ along with this program.  If not, see <http://www.gnu.org/licenses/>.
 package gplx.xowa.mediawiki.includes.title; import gplx.*; import gplx.xowa.*; import gplx.xowa.mediawiki.*; import gplx.xowa.mediawiki.includes.*;
 import gplx.xowa.mediawiki.languages.*;
 import gplx.xowa.mediawiki.includes.utls.*;
-public class XomwMediaWikiTitleCodec {
+public class XomwMediaWikiTitleCodec implements XomwTitleFormatter {
 	/**
 	* @var Language
 	*/
@@ -120,7 +120,7 @@ public class XomwMediaWikiTitleCodec {
 //		* @param String $text The text to parse
 //		* @param int $defaultNamespace Namespace to assume per default (usually NS_MAIN)
 //		*
-//		* @throws MalformedTitleException
+//		* @throws XomwMalformedTitleException
 //		* @return TitleValue
 //		*/
 //		public function parseTitle($text, $defaultNamespace) {
@@ -131,7 +131,7 @@ public class XomwMediaWikiTitleCodec {
 //
 //			// Relative fragment links are not supported by TitleValue
 //			if ($parts['dbkey'] === '') {
-//				throw new MalformedTitleException('title-invalid-empty', $text);
+//				throw new XomwMalformedTitleException('title-invalid-empty', $text);
 //			}
 //
 //			return new TitleValue(
@@ -232,7 +232,7 @@ public class XomwMediaWikiTitleCodec {
 	* @param String $text
 	* @param int $defaultNamespace
 	*
-	* @throws MalformedTitleException If $text is not a valid title String.
+	* @throws XomwMalformedTitleException If $text is not a valid title String.
 	* @return array A map with the fields 'interwiki', 'fragment', 'namespace',
 	*         'user_case_dbkey', and 'dbkey'.
 	*/
@@ -260,7 +260,7 @@ public class XomwMediaWikiTitleCodec {
 
 //			if (strpos(dbkey, UtfNormal\Constants::UTF8_REPLACEMENT) !== false) {
 //				// Contained illegal UTF-8 sequences or forbidden Unicode chars.
-//				throw new MalformedTitleException('title-invalid-utf8', text);
+//				throw new XomwMalformedTitleException('title-invalid-utf8', text);
 //			}
 
 		parts.dbkey = dbkey;
@@ -274,7 +274,7 @@ public class XomwMediaWikiTitleCodec {
 //			}
 
 		if (dbkey == Bry_.Empty) {
-			throw new MalformedTitleException("title-invalid-empty", text);
+			throw new XomwMalformedTitleException("title-invalid-empty", text);
 		}
 
 		// Namespace or interwiki prefix
@@ -296,11 +296,11 @@ public class XomwMediaWikiTitleCodec {
 //						if ($ns == NS_TALK && preg_match($prefixRegexp, dbkey, $x)) {
 //							if ($this->language->getNsIndex($x[1])) {
 //								// Disallow Talk:File:x type titles...
-//								throw new MalformedTitleException('title-invalid-talk-namespace', text);
+//								throw new XomwMalformedTitleException('title-invalid-talk-namespace', text);
 //							} elseif (Interwiki::isValidInterwiki($x[1])) {
 //								// TODO: get rid of global state!
 //								// Disallow Talk:Interwiki:x type titles...
-//								throw new MalformedTitleException('title-invalid-talk-namespace', text);
+//								throw new XomwMalformedTitleException('title-invalid-talk-namespace', text);
 //							}
 //						}
 //					} elseif (Interwiki::isValidInterwiki($p)) {
@@ -359,7 +359,7 @@ public class XomwMediaWikiTitleCodec {
 //			$rxTc = self::getTitleInvalidRegex();
 //			$matches = [];
 //			if (preg_match($rxTc, dbkey, $matches)) {
-//				throw new MalformedTitleException('title-invalid-characters', text, [ $matches[0] ]);
+//				throw new XomwMalformedTitleException('title-invalid-characters', text, [ $matches[0] ]);
 //			}
 
 		// Pages with "/./" or "/../" appearing in the URLs will often be un-
@@ -377,12 +377,12 @@ public class XomwMediaWikiTitleCodec {
 //					substr(dbkey, -3) == '/..'
 //				)
 //			) {
-//				throw new MalformedTitleException('title-invalid-relative', text);
+//				throw new XomwMalformedTitleException('title-invalid-relative', text);
 //			}
 
 		// Magic tilde sequences? Nu-uh!
 //			if (strpos(dbkey, '~~~') !== false) {
-//				throw new MalformedTitleException('title-invalid-magic-tilde', text);
+//				throw new XomwMalformedTitleException('title-invalid-magic-tilde', text);
 //			}
 
 		// Limit the size of titles to 255 bytes. This is typically the size of the
@@ -391,7 +391,7 @@ public class XomwMediaWikiTitleCodec {
 		// to subpage syntax for long titles, e.g. [[Special:Block/Long name]]
 //			$maxLength = (parts['namespace'] != NS_SPECIAL) ? 255 : 512;
 //			if (strlen(dbkey) > $maxLength) {
-//				throw new MalformedTitleException('title-invalid-too-long', text,
+//				throw new XomwMalformedTitleException('title-invalid-too-long', text,
 //					[ Message::numParam($maxLength) ]);
 //			}
 
@@ -407,7 +407,7 @@ public class XomwMediaWikiTitleCodec {
 		// self-links with a fragment identifier.
 //			if (dbkey == '' && parts['interwiki'] === '') {
 //				if (parts['namespace'] != NS_MAIN) {
-//					throw new MalformedTitleException('title-invalid-empty', text);
+//					throw new XomwMalformedTitleException('title-invalid-empty', text);
 //				}
 //			}
 
@@ -423,7 +423,7 @@ public class XomwMediaWikiTitleCodec {
 
 		// Any remaining initial :s are illegal.
 		if (dbkey != Bry_.Empty && Byte_ascii.Colon == dbkey[0]) {
-			throw new MalformedTitleException("title-invalid-leading-colon", text);
+			throw new XomwMalformedTitleException("title-invalid-leading-colon", text);
 		}
 
 		// Fill fields

gplx.xowa.mediawiki/src/gplx/xowa/mediawiki/includes/title/XomwTitleFormatter.java

@@ -0,0 +1,98 @@
+/*
+XOWA: the XOWA Offline Wiki Application
+Copyright (C) 2012 gnosygnu@gmail.com
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU Affero General Public License as
+published by the Free Software Foundation, either version 3 of the
+License, or (at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU Affero General Public License for more details.
+
+You should have received a copy of the GNU Affero General Public License
+along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/
+package gplx.xowa.mediawiki.includes.title; import gplx.*; import gplx.xowa.*; import gplx.xowa.mediawiki.*; import gplx.xowa.mediawiki.includes.*;
+/**
+* A title formatter service for MediaWiki.
+*
+* This is designed to encapsulate knowledge about conventions for the title
+* forms to be used in the database, in urls, in wikitext, etc.
+*
+* @see https://www.mediawiki.org/wiki/Requests_for_comment/TitleValue
+* @since 1.23
+*/
+public interface XomwTitleFormatter {
+//		/**
+//		* Returns the title formatted for display.
+//		* Per default, this includes the namespace but not the fragment.
+//		*
+//		* @note Normalization is applied if $title is not in TitleValue::TITLE_FORM.
+//		*
+//		* @param int|boolean $namespace The namespace ID (or false, if the namespace should be ignored)
+//		* @param String $text The page title
+//		* @param String $fragment The fragment name (may be empty).
+//		* @param String $interwiki The interwiki prefix (may be empty).
+//		*
+//		* @return String
+//		*/
+//		public function formatTitle($namespace, $text, $fragment = '', $interwiki = '');
+//
+//		/**
+//		* Returns the title text formatted for display, without namespace of fragment.
+//		*
+//		* @note Only minimal normalization is applied. Consider using TitleValue::getText() directly.
+//		*
+//		* @param LinkTarget $title The title to format
+//		*
+//		* @return String
+//		*/
+//		public function getText(LinkTarget $title);
+//
+//		/**
+//		* Returns the title formatted for display, including the namespace name.
+//		*
+//		* @param LinkTarget $title The title to format
+//		*
+//		* @return String
+//		*/
+//		public function getPrefixedText(LinkTarget $title);
+//
+//		/**
+//		* Return the title in prefixed database key form, with interwiki
+//		* and namespace.
+//		*
+//		* @since 1.27
+//		*
+//		* @param LinkTarget $target
+//		*
+//		* @return String
+//		*/
+//		public function getPrefixedDBkey(LinkTarget $target);
+//
+//		/**
+//		* Returns the title formatted for display, with namespace and fragment.
+//		*
+//		* @param LinkTarget $title The title to format
+//		*
+//		* @return String
+//		*/
+//		public function getFullText(LinkTarget $title);
+
+	/**
+	* Returns the name of the namespace for the given title.
+	*
+	* @note This must take into account gender sensitive namespace names.
+	* @todo Move this to a separate interface
+	*
+	* @param int $namespace
+	* @param String $text
+	*
+	* @throws InvalidArgumentException
+	* @return String
+	*/
+	byte[] getNamespaceName(int ns, byte[] text);
+}

gplx.xowa.mediawiki/src/gplx/xowa/mediawiki/includes/title/XomwTitleParser.java

@@ -0,0 +1,42 @@
+/*
+XOWA: the XOWA Offline Wiki Application
+Copyright (C) 2012 gnosygnu@gmail.com
+
+This program is free software: you can redistribute it and/or modify
+it under the terms of the GNU Affero General Public License as
+published by the Free Software Foundation, either version 3 of the
+License, or (at your option) any later version.
+
+This program is distributed in the hope that it will be useful,
+but WITHOUT ANY WARRANTY; without even the implied warranty of
+MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+GNU Affero General Public License for more details.
+
+You should have received a copy of the GNU Affero General Public License
+along with this program.  If not, see <http://www.gnu.org/licenses/>.
+*/
+package gplx.xowa.mediawiki.includes.title; import gplx.*; import gplx.xowa.*; import gplx.xowa.mediawiki.*; import gplx.xowa.mediawiki.includes.*;
+/**
+* A title parser service for %MediaWiki.
+*
+* This is designed to encapsulate knowledge about conventions for the title
+* forms to be used in the database, in urls, in wikitext, etc.
+*
+* @see https://www.mediawiki.org/wiki/Requests_for_comment/TitleValue
+* @since 1.23
+*/
+public interface XomwTitleParser {
+	/**
+	* Parses the given text and constructs a TitleValue. Normalization
+	* is applied according to the rules appropriate for the form specified by $form.
+	*
+	* @note this only parses local page links, interwiki-prefixes etc. are not considered!
+	*
+	* @param String $text The text to parse
+	* @param int $defaultNamespace Namespace to assume per default (usually NS_MAIN)
+	*
+	* @throws MalformedTitleException If the text is not a valid representation of a page title.
+	* @return TitleValue
+	*/
+	XomwTitle parseTitle(byte[] text, int defaultNamespace);
+}

gplx.xowa.mediawiki/src/gplx/xowa/mediawiki/languages/XomwLanguage.java

@@ -16,7 +16,7 @@ You should have received a copy of the GNU Affero General Public License
 along with this program.  If not, see <http://www.gnu.org/licenses/>.
 */
 package gplx.xowa.mediawiki.languages; import gplx.*; import gplx.xowa.*; import gplx.xowa.mediawiki.*;
-import gplx.core.lists.hashs.*;
+import gplx.core.lists.*;
 import gplx.xowa.mediawiki.includes.*;
 public class XomwLanguage {
 //		/**
@@ -32,7 +32,7 @@ public class XomwLanguage {
 //		public $mExtendedSpecialPageAliases;
 //
 //		/** @var array|null */
-	private Hash_adp__int namespaceNames;
+	private HashByInt namespaceNames;
 //		protected $mNamespaceIds, $namespaceAliases;
 //
 //		/**
@@ -482,11 +482,11 @@ public class XomwLanguage {
 	*
 	* @return array
 	*/
-	public Hash_adp__int getNamespaces() {
+	public HashByInt getNamespaces() {
 		if (this.namespaceNames == null) {
 //				global $wgMetaNamespace, $wgMetaNamespaceTalk, $wgExtraNamespaces;
 //
-			Hash_adp__int validNamespaces = XomwNamespace.getCanonicalNamespaces();
+			HashByInt validNamespaces = XomwNamespace.getCanonicalNamespaces();
 //
 //				this.namespaceNames = $wgExtraNamespaces +
 //					self::$dataCache->getItem(this.mCode, 'namespaceNames');
@@ -563,9 +563,8 @@ public class XomwLanguage {
 	* @return String|boolean String if the namespace value exists, otherwise false
 	*/
 	public byte[] getNsText(int index) {
-		Hash_adp__int ns = this.getNamespaces();
+		HashByInt ns = this.getNamespaces();
 		return (byte[])ns.Get_by_or_null(index);
-//			return isset($ns[$index]) ? $ns[$index] : false;
 	}
 
 //		/**