LUCENE-2978: Upgrade benchmark's commons-compress from 1.0 to 1.1.

git-svn-id: https://svn.apache.org/repos/asf/lucene/dev/trunk@1084210 13f79535-47bb-0310-9956-ffa450edef68

dev-tools/eclipse/dot.classpath

@@ -90,7 +90,7 @@
 	<classpathentry kind="lib" path="modules/analysis/phonetic/lib/commons-codec-1.4.jar"/>
 	<classpathentry kind="lib" path="modules/benchmark/lib/commons-beanutils-1.7.0.jar"/>
 	<classpathentry kind="lib" path="modules/benchmark/lib/commons-collections-3.1.jar"/>
-	<classpathentry kind="lib" path="modules/benchmark/lib/commons-compress-1.0.jar"/>
+	<classpathentry kind="lib" path="modules/benchmark/lib/commons-compress-1.1.jar"/>
 	<classpathentry kind="lib" path="modules/benchmark/lib/commons-digester-1.7.jar"/>
 	<classpathentry kind="lib" path="modules/benchmark/lib/commons-logging-1.0.4.jar"/>
 	<classpathentry kind="lib" path="modules/benchmark/lib/xercesImpl-2.9.1-patched-XERCESJ-1257.jar"/>

modules/benchmark/CHANGES.txt

@@ -2,6 +2,12 @@ Lucene Benchmark Contrib Change Log
 
 The Benchmark contrib package contains code for benchmarking Lucene in a variety of ways.
 
+03/22/2011
+  LUCENE-2978: Upgrade benchmark's commons-compress from 1.0 to 1.1 as 
+  the move of gzip decompression in LUCENE-1540 from Java's GZipInputStream
+  to commons-compress 1.0 made it 15 times slower. In 1.1 no such slow-down
+  is observed. (Doron Cohen)   
+  
 03/21/2011
   LUCENE-2958: WriteLineDocTask improvements - allow to emit line docs also for empty
   docs, and be flexible about which fields are added to the line file. For this, a header

modules/benchmark/lib/commons-compress-1.0.jar

@@ -1,2 +0,0 @@
-AnyObjectId[78d832c11c42023d4bc12077a1d9b7b5025217bc] was removed in git history.
-Apache SVN contains full history.

modules/benchmark/lib/commons-compress-1.1.jar

@@ -0,0 +1,2 @@
+AnyObjectId[51baf91a2df10184a8cca5cb43f11418576743a1] was removed in git history.
+Apache SVN contains full history.

modules/benchmark/lib/commons-compress-NOTICE.txt

@@ -1,15 +1,5 @@
 Apache Commons Compress
-Copyright 2002-2009 The Apache Software Foundation
+Copyright 2002-2010 The Apache Software Foundation
 
 This product includes software developed by
 The Apache Software Foundation (http://www.apache.org/).
-
-Original BZip2 classes contributed by Keiron Liddle
-<keiron@aftexsw.com>, Aftex Software to the Apache Ant project
-
-Original Tar classes from contributors of the Apache Ant project
-
-Original Zip classes from contributors of the Apache Ant project
-
-Original CPIO classes contributed by Markus Kuss and the jRPM project
-(jrpm.sourceforge.net)

modules/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ContentSource.java

@@ -55,15 +55,13 @@ import org.apache.lucene.benchmark.byTask.utils.Config;
  */
 public abstract class ContentSource {
   
-  private static final int BZIP = 0;
+  private static final Map<String,String> extensionToType = new HashMap<String,String>();
-  private static final int GZIP = 1;
-  private static final int OTHER = 2;
-  private static final Map<String,Integer> extensionToType = new HashMap<String,Integer>();
   static {
-    extensionToType.put(".bz2", Integer.valueOf(BZIP));
+  	// these in are lower case, we will lower case at the test as well
-    extensionToType.put(".bzip", Integer.valueOf(BZIP));
+    extensionToType.put(".bz2", CompressorStreamFactory.BZIP2);
-    extensionToType.put(".gz", Integer.valueOf(GZIP));
+    extensionToType.put(".bzip", CompressorStreamFactory.BZIP2);
-    extensionToType.put(".gzip", Integer.valueOf(GZIP));
+    extensionToType.put(".gz", CompressorStreamFactory.GZIP);
+    extensionToType.put(".gzip", CompressorStreamFactory.GZIP);
   }
   
   protected static final int BUFFER_SIZE = 1 << 16; // 64K
@@ -128,27 +126,14 @@ public abstract class ContentSource {
     
     String fileName = file.getName();
     int idx = fileName.lastIndexOf('.');
-    int type = OTHER;
+    String type = null;
     if (idx != -1) {
-      Integer typeInt = extensionToType.get(fileName.substring(idx));
+      type = extensionToType.get(fileName.substring(idx));
-      if (typeInt != null) {
-        type = typeInt.intValue();
-      }
     }
     
     try {
-      switch (type) {
+      if (type!=null) { // bzip or gzip
-        case BZIP:
+        return csFactory.createCompressorInputStream(type, is);
-          // According to BZip2CompressorInputStream's code, it reads the first 
-          // two file header chars ('B' and 'Z'). It is important to wrap the
-          // underlying input stream with a buffered one since
-          // Bzip2CompressorInputStream uses the read() method exclusively.
-          is = csFactory.createCompressorInputStream("bzip2", is);
-          break;
-        case GZIP:
-          is = csFactory.createCompressorInputStream("gz", is);
-          break;
-        default: // Do nothing, stay with FileInputStream
       } 
     } catch (CompressorException e) {
       IOException ioe = new IOException(e.getMessage());