You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@lucene.apache.org by do...@apache.org on 2011/03/22 16:08:30 UTC
svn commit: r1084210 - in /lucene/dev/trunk: dev-tools/eclipse/
modules/benchmark/ modules/benchmark/lib/
modules/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/
Author: doronc
Date: Tue Mar 22 15:08:29 2011
New Revision: 1084210
URL: http://svn.apache.org/viewvc?rev=1084210&view=rev
Log:
LUCENE-2978: Upgrade benchmark's commons-compress from 1.0 to 1.1.
Added:
lucene/dev/trunk/modules/benchmark/lib/commons-compress-1.1.jar (with props)
Removed:
lucene/dev/trunk/modules/benchmark/lib/commons-compress-1.0.jar
Modified:
lucene/dev/trunk/dev-tools/eclipse/dot.classpath
lucene/dev/trunk/modules/benchmark/CHANGES.txt
lucene/dev/trunk/modules/benchmark/lib/commons-compress-NOTICE.txt
lucene/dev/trunk/modules/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ContentSource.java
Modified: lucene/dev/trunk/dev-tools/eclipse/dot.classpath
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/dev-tools/eclipse/dot.classpath?rev=1084210&r1=1084209&r2=1084210&view=diff
==============================================================================
--- lucene/dev/trunk/dev-tools/eclipse/dot.classpath (original)
+++ lucene/dev/trunk/dev-tools/eclipse/dot.classpath Tue Mar 22 15:08:29 2011
@@ -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"/>
Modified: lucene/dev/trunk/modules/benchmark/CHANGES.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/benchmark/CHANGES.txt?rev=1084210&r1=1084209&r2=1084210&view=diff
==============================================================================
--- lucene/dev/trunk/modules/benchmark/CHANGES.txt (original)
+++ lucene/dev/trunk/modules/benchmark/CHANGES.txt Tue Mar 22 15:08:29 2011
@@ -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
Added: lucene/dev/trunk/modules/benchmark/lib/commons-compress-1.1.jar
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/benchmark/lib/commons-compress-1.1.jar?rev=1084210&view=auto
==============================================================================
Binary file - no diff available.
Modified: lucene/dev/trunk/modules/benchmark/lib/commons-compress-NOTICE.txt
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/benchmark/lib/commons-compress-NOTICE.txt?rev=1084210&r1=1084209&r2=1084210&view=diff
==============================================================================
--- lucene/dev/trunk/modules/benchmark/lib/commons-compress-NOTICE.txt (original)
+++ lucene/dev/trunk/modules/benchmark/lib/commons-compress-NOTICE.txt Tue Mar 22 15:08:29 2011
@@ -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
-<ke...@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)
Modified: lucene/dev/trunk/modules/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ContentSource.java
URL: http://svn.apache.org/viewvc/lucene/dev/trunk/modules/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ContentSource.java?rev=1084210&r1=1084209&r2=1084210&view=diff
==============================================================================
--- lucene/dev/trunk/modules/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ContentSource.java (original)
+++ lucene/dev/trunk/modules/benchmark/src/java/org/apache/lucene/benchmark/byTask/feeds/ContentSource.java Tue Mar 22 15:08:29 2011
@@ -55,15 +55,13 @@ import org.apache.lucene.benchmark.byTas
*/
public abstract class ContentSource {
- private static final int BZIP = 0;
- private static final int GZIP = 1;
- private static final int OTHER = 2;
- private static final Map<String,Integer> extensionToType = new HashMap<String,Integer>();
+ private static final Map<String,String> extensionToType = new HashMap<String,String>();
static {
- extensionToType.put(".bz2", Integer.valueOf(BZIP));
- extensionToType.put(".bzip", Integer.valueOf(BZIP));
- extensionToType.put(".gz", Integer.valueOf(GZIP));
- extensionToType.put(".gzip", Integer.valueOf(GZIP));
+ // these in are lower case, we will lower case at the test as well
+ extensionToType.put(".bz2", CompressorStreamFactory.BZIP2);
+ extensionToType.put(".bzip", CompressorStreamFactory.BZIP2);
+ extensionToType.put(".gz", CompressorStreamFactory.GZIP);
+ extensionToType.put(".gzip", CompressorStreamFactory.GZIP);
}
protected static final int BUFFER_SIZE = 1 << 16; // 64K
@@ -128,28 +126,15 @@ 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));
- if (typeInt != null) {
- type = typeInt.intValue();
- }
+ type = extensionToType.get(fileName.substring(idx));
}
try {
- switch (type) {
- case BZIP:
- // 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
- }
+ if (type!=null) { // bzip or gzip
+ return csFactory.createCompressorInputStream(type, is);
+ }
} catch (CompressorException e) {
IOException ioe = new IOException(e.getMessage());
ioe.initCause(e);