Bug 460787 - Do not use deprecated Lucene 3.5 methods/classes

Moves from deprecated methods/classes to newer ones by simply redoing
what the deprecated methods were doing in Lucene 3.5 itself using the
newer APIs.
This is preliminalry work for updating to Lucene 4.x/5.x where these
deprecated ones are actually removed.


Change-Id: I96937e00a251630a6927130efb88cc1652080cb9
Signed-off-by: Alexander Kurtakov <akurtako@redhat.com>

4 files changed, 34 insertions, 18 deletions

diff --git a/org.eclipse.help.base/src/org/eclipse/help/internal/search/Analyzer_en.java b/org.eclipse.help.base/src/org/eclipse/help/internal/search/Analyzer_en.java
index 13157cf9f..a066aa4e3 100644
--- a/org.eclipse.help.base/src/org/eclipse/help/internal/search/Analyzer_en.java
+++ b/org.eclipse.help.base/src/org/eclipse/help/internal/search/Analyzer_en.java
@@ -1,5 +1,5 @@
 /*******************************************************************************
- * Copyright (c) 2000, 2012 IBM Corporation and others.
+ * Copyright (c) 2000, 2015 IBM Corporation and others.
  * All rights reserved. This program and the accompanying materials
  * are made available under the terms of the Eclipse Public License v1.0
  * which accompanies this distribution, and is available at
@@ -7,6 +7,7 @@
  *
  * Contributors:
  *     IBM Corporation - initial API and implementation
+ *     Alexander Kurtakov - Bug 460787
  *******************************************************************************/
 package org.eclipse.help.internal.search;
 import java.io.*;
@@ -14,6 +15,7 @@ import java.util.HashSet;
 import java.util.Set;
 
 import org.apache.lucene.analysis.*;
+import org.apache.lucene.util.Version;
 /**
  * Lucene Analyzer for English. LowerCaseTokenizer->StopFilter->PorterStemFilter
  */
@@ -29,7 +31,7 @@ public final class Analyzer_en extends Analyzer {
 	 * Reader.
 	 */
 	public final TokenStream tokenStream(String fieldName, Reader reader) {
-		return new PorterStemFilter(new StopFilter(false, new LowerCaseAndDigitsTokenizer(reader), getStopWords(), false));
+		return new PorterStemFilter(new StopFilter(Version.LUCENE_30, new LowerCaseAndDigitsTokenizer(reader), getStopWords(), false));
 	}
 
 	private Set<String> stopWords;
diff --git a/org.eclipse.help.base/src/org/eclipse/help/internal/search/DefaultAnalyzer.java b/org.eclipse.help.base/src/org/eclipse/help/internal/search/DefaultAnalyzer.java
index b176e9de3..4109474ab 100644
--- a/org.eclipse.help.base/src/org/eclipse/help/internal/search/DefaultAnalyzer.java
+++ b/org.eclipse.help.base/src/org/eclipse/help/internal/search/DefaultAnalyzer.java
@@ -1,10 +1,12 @@
 /*******************************************************************************
- * Copyright (c) 2000, 2012 IBM Corporation and others. All rights reserved. This program and the
+ * Copyright (c) 2000, 2015 IBM Corporation and others. All rights reserved. This program and the
  * accompanying materials are made available under the terms of the Eclipse Public License v1.0
  * which accompanies this distribution, and is available at
  * http://www.eclipse.org/legal/epl-v10.html
  *
- * Contributors: IBM Corporation - initial API and implementation
+ * Contributors:
+ *     IBM Corporation - initial API and implementation
+ *     Alexander Kurtakov - Bug 460787
  *******************************************************************************/
 package org.eclipse.help.internal.search;
 
@@ -17,7 +19,7 @@ import com.ibm.icu.text.BreakIterator;
 import org.apache.lucene.analysis.Analyzer;
 import org.apache.lucene.analysis.LowerCaseFilter;
 import org.apache.lucene.analysis.TokenStream;
-
+import org.apache.lucene.util.Version;
 import org.eclipse.help.internal.base.HelpBasePlugin;
 
 import org.eclipse.core.runtime.Platform;
@@ -86,7 +88,7 @@ public final class DefaultAnalyzer extends Analyzer {
 	 * Reader.
 	 */
 	public final TokenStream tokenStream(String fieldName, Reader reader) {
-		return new LowerCaseFilter(new WordTokenStream(fieldName, reader, locale));
+		return new LowerCaseFilter(Version.LUCENE_30, new WordTokenStream(fieldName, reader, locale));
 	}
 
 	/**
diff --git a/org.eclipse.help.base/src/org/eclipse/help/internal/search/LowerCaseAndDigitsTokenizer.java b/org.eclipse.help.base/src/org/eclipse/help/internal/search/LowerCaseAndDigitsTokenizer.java
index 0dd3943e6..a475688d1 100644
--- a/org.eclipse.help.base/src/org/eclipse/help/internal/search/LowerCaseAndDigitsTokenizer.java
+++ b/org.eclipse.help.base/src/org/eclipse/help/internal/search/LowerCaseAndDigitsTokenizer.java
@@ -1,5 +1,5 @@
 /*******************************************************************************
- * Copyright (c) 2000, 2007 IBM Corporation and others.
+ * Copyright (c) 2000, 2015 IBM Corporation and others.
  * All rights reserved. This program and the accompanying materials
  * are made available under the terms of the Eclipse Public License v1.0
  * which accompanies this distribution, and is available at
@@ -7,12 +7,14 @@
  *
  * Contributors:
  *     IBM Corporation - initial API and implementation
+ *     Alexander Kurtakov - Bug 460787
  *******************************************************************************/
 package org.eclipse.help.internal.search;
 
 import java.io.*;
 
 import org.apache.lucene.analysis.*;
+import org.apache.lucene.util.Version;
 
 /**
  * Tokenizer breaking words around letters or digits.
@@ -20,7 +22,7 @@ import org.apache.lucene.analysis.*;
 public class LowerCaseAndDigitsTokenizer extends CharTokenizer {
 
     public LowerCaseAndDigitsTokenizer(Reader input) {
-        super(input);
+        super(Version.LUCENE_30, input);
     }
     protected char normalize(char c) {
         return Character.toLowerCase(c);
diff --git a/org.eclipse.help.base/src/org/eclipse/help/internal/search/SearchIndex.java b/org.eclipse.help.base/src/org/eclipse/help/internal/search/SearchIndex.java
index a66e73e48..33c9476b7 100644
--- a/org.eclipse.help.base/src/org/eclipse/help/internal/search/SearchIndex.java
+++ b/org.eclipse.help.base/src/org/eclipse/help/internal/search/SearchIndex.java
@@ -8,6 +8,7 @@
  * Contributors:
  *     IBM Corporation - initial API and implementation
  *     Holger Voormann - fix for bug 426785 (http://eclip.se/426785)
+ *     Alexander Kurtakov - Bug 460787
  *******************************************************************************/
 package org.eclipse.help.internal.search;
 
@@ -32,13 +33,17 @@ import java.util.Set;
 import java.util.zip.ZipEntry;
 import java.util.zip.ZipInputStream;
 
+import org.apache.lucene.analysis.LimitTokenCountAnalyzer;
 import org.apache.lucene.document.Document;
 import org.apache.lucene.document.Field;
 import org.apache.lucene.index.IndexReader;
 import org.apache.lucene.index.IndexWriter;
 import org.apache.lucene.index.Term;
 import org.apache.lucene.index.TermDocs;
-import org.apache.lucene.index.IndexWriter.MaxFieldLength;
+import org.apache.lucene.index.IndexWriterConfig.OpenMode;
+import org.apache.lucene.index.IndexWriterConfig;
+import org.apache.lucene.index.LogByteSizeMergePolicy;
+import org.apache.lucene.index.LogMergePolicy;
 import org.apache.lucene.search.BooleanQuery;
 import org.apache.lucene.search.IndexSearcher;
 import org.apache.lucene.search.Query;
@@ -277,9 +282,13 @@ public class SearchIndex implements IHelpSearchIndex {
 			indexedDocs = new HelpProperties(INDEXED_DOCS_FILE, indexDir);
 			indexedDocs.restore();
 			setInconsistent(true);
-			MaxFieldLength max = new MaxFieldLength(1000000);
-			iw = new IndexWriter(luceneDirectory, analyzerDescriptor.getAnalyzer(), create, max);
-			iw.setMergeFactor(20);
+			LimitTokenCountAnalyzer analyzer = new LimitTokenCountAnalyzer(analyzerDescriptor.getAnalyzer(), 1000000);
+			IndexWriterConfig writerConfig = new IndexWriterConfig(org.apache.lucene.util.Version.LUCENE_31, analyzer);
+			writerConfig.setOpenMode(create ? OpenMode.CREATE : OpenMode.APPEND);
+			LogMergePolicy mergePolicy = new LogByteSizeMergePolicy();
+			mergePolicy.setMergeFactor(20);
+			writerConfig.setMergePolicy(mergePolicy);
+			iw = new IndexWriter(luceneDirectory, writerConfig);
 			return true;
 		} catch (IOException e) {
 			HelpBasePlugin.logError("Exception occurred in search indexing at beginAddBatch.", e); //$NON-NLS-1$
@@ -351,7 +360,7 @@ public class SearchIndex implements IHelpSearchIndex {
 			if (iw == null)
 				return false;
 			if (optimize)
-				iw.optimize();
+				iw.forceMerge(1, true);
 			iw.close();
 			iw = null;
 			// save the update info:
@@ -506,8 +515,8 @@ public class SearchIndex implements IHelpSearchIndex {
 		}
 		Directory[] luceneDirs = dirList.toArray(new Directory[dirList.size()]);
 		try {
-			iw.addIndexesNoOptimize(luceneDirs);
-			iw.optimize();
+			iw.addIndexes(luceneDirs);
+			iw.forceMerge(1, true);
 		} catch (IOException ioe) {
 			HelpBasePlugin.logError("Merging search indexes failed.", ioe); //$NON-NLS-1$
 			return new HashMap<String, String[]>();
@@ -793,7 +802,7 @@ public class SearchIndex implements IHelpSearchIndex {
 	public void openSearcher() throws IOException {
 		synchronized (searcherCreateLock) {
 			if (searcher == null) {
-				searcher = new IndexSearcher(luceneDirectory, false);
+				searcher = new IndexSearcher(IndexReader.open(luceneDirectory, false));
 			}
 		}
 	}
@@ -892,9 +901,10 @@ public class SearchIndex implements IHelpSearchIndex {
 	 */
 	private void cleanOldIndex() {
 		IndexWriter cleaner = null;
-		MaxFieldLength max = new MaxFieldLength(10000);
+		LimitTokenCountAnalyzer analyzer = new LimitTokenCountAnalyzer(analyzerDescriptor.getAnalyzer(), 10000);
 		try {
-			cleaner = new IndexWriter(luceneDirectory, analyzerDescriptor.getAnalyzer(), true, max);
+			cleaner = new IndexWriter(luceneDirectory, new IndexWriterConfig(org.apache.lucene.util.Version.LUCENE_31, analyzer).setOpenMode(
+			        OpenMode.CREATE));
 		} catch (IOException ioe) {
 		} finally {
 			try {