Author: cutting
Date: Wed Sep 5 16:10:42 2007
New Revision: 573095
URL: http://svn.apache.org/viewvc?rev=573095&view=rev
Log:
HADOOP-1425. Replace uses ToolBase with the Tool interface. Contributed by
Enis.
Modified:
lucene/hadoop/trunk/CHANGES.txt
lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/Grep.java
lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/PiEstimator.java
lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/RandomWriter.java
lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/Sort.java
lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/WordCount.java
lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/dancing/DistributedPentomino.java
lucene/hadoop/trunk/src/java/org/apache/hadoop/dfs/DFSAdmin.java
lucene/hadoop/trunk/src/java/org/apache/hadoop/dfs/DFSck.java
lucene/hadoop/trunk/src/java/org/apache/hadoop/fs/FsShell.java
lucene/hadoop/trunk/src/java/org/apache/hadoop/fs/s3/MigrationTool.java
lucene/hadoop/trunk/src/java/org/apache/hadoop/mapred/JobClient.java
lucene/hadoop/trunk/src/java/org/apache/hadoop/mapred/lib/aggregate/ValueAggregatorJob.java
lucene/hadoop/trunk/src/java/org/apache/hadoop/util/CopyFiles.java
lucene/hadoop/trunk/src/java/org/apache/hadoop/util/GenericOptionsParser.java
lucene/hadoop/trunk/src/java/org/apache/hadoop/util/ToolRunner.java
lucene/hadoop/trunk/src/test/org/apache/hadoop/mapred/BigMapOutput.java
Modified: lucene/hadoop/trunk/CHANGES.txt
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/CHANGES.txt?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
--- lucene/hadoop/trunk/CHANGES.txt (original)
+++ lucene/hadoop/trunk/CHANGES.txt Wed Sep 5 16:10:42 2007
@@ -160,6 +160,9 @@
HADOOP-1825. Create $HADOOP_PID_DIR when it does not exist.
(Michael Bieniosek via cutting)
+ HADOOP-1425. Replace uses of ToolBase with the Tool interface.
+ (Enis Soztutar via cutting)
+
Release 0.14.1 - 2007-09-04
Modified: lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/Grep.java
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/Grep.java?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
--- lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/Grep.java
(original)
+++ lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/Grep.java Wed
Sep 5 16:10:42 2007
@@ -17,73 +17,81 @@
*/
package org.apache.hadoop.examples;
-import org.apache.hadoop.mapred.JobConf;
-import org.apache.hadoop.mapred.JobClient;
-import org.apache.hadoop.mapred.SequenceFileOutputFormat;
-import org.apache.hadoop.mapred.SequenceFileInputFormat;
-
-import org.apache.hadoop.mapred.lib.RegexMapper;
-import org.apache.hadoop.mapred.lib.InverseMapper;
-import org.apache.hadoop.mapred.lib.LongSumReducer;
-
-import org.apache.hadoop.io.LongWritable;
-import org.apache.hadoop.io.Text;
+import java.util.Random;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
-
-import java.util.Random;
+import org.apache.hadoop.io.LongWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.mapred.*;
+import org.apache.hadoop.mapred.lib.*;
+import org.apache.hadoop.util.Tool;
+import org.apache.hadoop.util.ToolRunner;
/* Extracts matching regexs from input files and counts them. */
-public class Grep {
+public class Grep extends Configured implements Tool {
private Grep() {} // singleton
- public static void main(String[] args) throws Exception {
+ public int run(String[] args) throws Exception {
if (args.length < 3) {
System.out.println("Grep <inDir> <outDir> <regex> [<group>]");
- System.exit(-1);
+ ToolRunner.printGenericCommandUsage(System.out);
+ return -1;
}
Path tempDir =
new Path("grep-temp-"+
- Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));
+ Integer.toString(new Random().nextInt(Integer.MAX_VALUE)));
+
+ JobConf grepJob = new JobConf(getConf(), Grep.class);
+
+ try {
+
+ grepJob.setJobName("grep-search");
- JobConf grepJob = new JobConf(Grep.class);
- grepJob.setJobName("grep-search");
+ grepJob.setInputPath(new Path(args[0]));
- grepJob.setInputPath(new Path(args[0]));
+ grepJob.setMapperClass(RegexMapper.class);
+ grepJob.set("mapred.mapper.regex", args[2]);
+ if (args.length == 4)
+ grepJob.set("mapred.mapper.regex.group", args[3]);
- grepJob.setMapperClass(RegexMapper.class);
- grepJob.set("mapred.mapper.regex", args[2]);
- if (args.length == 4)
- grepJob.set("mapred.mapper.regex.group", args[3]);
-
- grepJob.setCombinerClass(LongSumReducer.class);
- grepJob.setReducerClass(LongSumReducer.class);
+ grepJob.setCombinerClass(LongSumReducer.class);
+ grepJob.setReducerClass(LongSumReducer.class);
- grepJob.setOutputPath(tempDir);
- grepJob.setOutputFormat(SequenceFileOutputFormat.class);
- grepJob.setOutputKeyClass(Text.class);
- grepJob.setOutputValueClass(LongWritable.class);
+ grepJob.setOutputPath(tempDir);
+ grepJob.setOutputFormat(SequenceFileOutputFormat.class);
+ grepJob.setOutputKeyClass(Text.class);
+ grepJob.setOutputValueClass(LongWritable.class);
- JobClient.runJob(grepJob);
+ JobClient.runJob(grepJob);
- JobConf sortJob = new JobConf(Grep.class);
- sortJob.setJobName("grep-sort");
+ JobConf sortJob = new JobConf(Grep.class);
+ sortJob.setJobName("grep-sort");
- sortJob.setInputPath(tempDir);
- sortJob.setInputFormat(SequenceFileInputFormat.class);
+ sortJob.setInputPath(tempDir);
+ sortJob.setInputFormat(SequenceFileInputFormat.class);
- sortJob.setMapperClass(InverseMapper.class);
+ sortJob.setMapperClass(InverseMapper.class);
- sortJob.setNumReduceTasks(1); // write a single file
- sortJob.setOutputPath(new Path(args[1]));
- sortJob.setOutputKeyComparatorClass // sort by decreasing freq
+ sortJob.setNumReduceTasks(1); // write a single file
+ sortJob.setOutputPath(new Path(args[1]));
+ sortJob.setOutputKeyComparatorClass // sort by decreasing freq
(LongWritable.DecreasingComparator.class);
- JobClient.runJob(sortJob);
+ JobClient.runJob(sortJob);
+ }
+ finally {
+ FileSystem.get(grepJob).delete(tempDir);
+ }
+ return 0;
+ }
- FileSystem.get(grepJob).delete(tempDir);
+ public static void main(String[] args) throws Exception {
+ int res = ToolRunner.run(new Configuration(), new Grep(), args);
+ System.exit(res);
}
}
Modified:
lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/PiEstimator.java
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/PiEstimator.java?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
---
lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/PiEstimator.java
(original)
+++
lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/PiEstimator.java
Wed Sep 5 16:10:42 2007
@@ -21,7 +21,9 @@
import java.io.IOException;
import java.util.Iterator;
import java.util.Random;
+
import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.LongWritable;
@@ -29,13 +31,23 @@
import org.apache.hadoop.io.Writable;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.io.SequenceFile.CompressionType;
-import org.apache.hadoop.mapred.*;
+import org.apache.hadoop.mapred.JobClient;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.MapReduceBase;
+import org.apache.hadoop.mapred.Mapper;
+import org.apache.hadoop.mapred.OutputCollector;
+import org.apache.hadoop.mapred.Reducer;
+import org.apache.hadoop.mapred.Reporter;
+import org.apache.hadoop.mapred.SequenceFileInputFormat;
+import org.apache.hadoop.mapred.SequenceFileOutputFormat;
+import org.apache.hadoop.util.Tool;
+import org.apache.hadoop.util.ToolRunner;
/**
* A Map-reduce program to estimaate the valu eof Pi using monte-carlo
* method.
*/
-public class PiEstimator {
+public class PiEstimator extends Configured implements Tool {
/**
* Mappper class for Pi estimation.
@@ -47,6 +59,7 @@
/** Mapper configuration.
*
*/
+ @Override
public void configure(JobConf job) {
}
@@ -83,6 +96,7 @@
out.collect(new LongWritable(1), new LongWritable(numInside));
}
+ @Override
public void close() {
// nothing
}
@@ -98,6 +112,7 @@
/** Reducer configuration.
*
*/
+ @Override
public void configure(JobConf job) {
conf = job;
}
@@ -124,6 +139,7 @@
}
}
+ @Override
public void close() throws IOException {
Path tmpDir = new Path("test-mini-mr");
Path outDir = new Path(tmpDir, "out");
@@ -141,11 +157,10 @@
* This is the main driver for computing the value of Pi using
* monte-carlo method.
*/
- static double launch(int numMaps, long numPoints, String jt, String dfs)
+ double launch(int numMaps, long numPoints, String jt, String dfs)
throws IOException {
- Configuration conf = new Configuration();
- JobConf jobConf = new JobConf(conf, PiEstimator.class);
+ JobConf jobConf = new JobConf(getConf(), PiEstimator.class);
if (jt != null) { jobConf.set("mapred.job.tracker", jt); }
if (dfs != null) { jobConf.set("fs.default.name", dfs); }
jobConf.setJobName("test-mini-mr");
@@ -194,7 +209,7 @@
long startTime = System.currentTimeMillis();
JobClient.runJob(jobConf);
System.out.println("Job Finished in "+
- (double)(System.currentTimeMillis() -
startTime)/1000.0 + " seconds");
+ (System.currentTimeMillis() - startTime)/1000.0 + "
seconds");
Path inFile = new Path(outDir, "reduce-out");
SequenceFile.Reader reader = new SequenceFile.Reader(fileSys, inFile,
jobConf);
@@ -202,7 +217,7 @@
LongWritable numOutside = new LongWritable();
reader.next(numInside, numOutside);
reader.close();
- estimate = (double) (numInside.get()*4.0)/(numMaps*numPoints);
+ estimate = (numInside.get()*4.0)/(numMaps*numPoints);
} finally {
fileSys.delete(tmpDir);
}
@@ -213,18 +228,27 @@
/**
* Launches all the tasks in order.
*/
- public static void main(String[] argv) throws Exception {
- if (argv.length < 2) {
+ public int run(String[] args) throws Exception {
+ if (args.length < 2) {
System.err.println("Usage: TestMiniMR <nMaps> <nSamples>");
- return;
+ ToolRunner.printGenericCommandUsage(System.err);
+ return -1;
}
-
- int nMaps = Integer.parseInt(argv[0]);
- long nSamples = Long.parseLong(argv[1]);
+
+ int nMaps = Integer.parseInt(args[0]);
+ long nSamples = Long.parseLong(args[1]);
System.out.println("Number of Maps = "+nMaps+" Samples per Map =
"+nSamples);
System.out.println("Estimated value of PI is "+
launch(nMaps, nSamples, null, null));
+
+ return 0;
}
+
+ public static void main(String[] argv) throws Exception {
+ int res = ToolRunner.run(new Configuration(), new PiEstimator(), argv);
+ System.exit(res);
+ }
+
}
Modified:
lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/RandomWriter.java
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/RandomWriter.java?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
---
lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/RandomWriter.java
(original)
+++
lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/RandomWriter.java
Wed Sep 5 16:10:42 2007
@@ -23,11 +23,28 @@
import java.util.Random;
import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
-import org.apache.hadoop.io.*;
-import org.apache.hadoop.mapred.*;
+import org.apache.hadoop.io.BytesWritable;
+import org.apache.hadoop.io.Text;
+import org.apache.hadoop.io.Writable;
+import org.apache.hadoop.io.WritableComparable;
+import org.apache.hadoop.mapred.ClusterStatus;
+import org.apache.hadoop.mapred.FileSplit;
+import org.apache.hadoop.mapred.InputFormat;
+import org.apache.hadoop.mapred.InputSplit;
+import org.apache.hadoop.mapred.JobClient;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.MapReduceBase;
+import org.apache.hadoop.mapred.Mapper;
+import org.apache.hadoop.mapred.OutputCollector;
+import org.apache.hadoop.mapred.RecordReader;
+import org.apache.hadoop.mapred.Reporter;
+import org.apache.hadoop.mapred.SequenceFileOutputFormat;
import org.apache.hadoop.mapred.lib.IdentityReducer;
+import org.apache.hadoop.util.Tool;
import org.apache.hadoop.util.ToolBase;
+import org.apache.hadoop.util.ToolRunner;
/**
* This program uses map/reduce to just run a distributed job where there is
@@ -64,7 +81,7 @@
* Equivalently, [EMAIL PROTECTED] RandomWriter} also supports all the above
options
* and ones supported by [EMAIL PROTECTED] ToolBase} via the command-line.
*/
-public class RandomWriter extends ToolBase {
+public class RandomWriter extends Configured implements Tool {
/**
* User counters
@@ -186,6 +203,7 @@
* Save the values out of the configuaration that we need to write
* the data.
*/
+ @Override
public void configure(JobConf job) {
numBytesToWrite = job.getLong("test.randomwrite.bytes_per_map",
1*1024*1024*1024);
@@ -208,12 +226,13 @@
*/
public int run(String[] args) throws Exception {
if (args.length == 0) {
- System.out.println("Usage: writer <out-dir> [<config>]");
+ System.out.println("Usage: writer <out-dir>");
+ ToolRunner.printGenericCommandUsage(System.out);
return -1;
}
Path outDir = new Path(args[0]);
- JobConf job = new JobConf(conf);
+ JobConf job = new JobConf(getConf());
job.setJarByClass(RandomWriter.class);
job.setJobName("random-writer");
@@ -263,7 +282,7 @@
}
public static void main(String[] args) throws Exception {
- int res = new RandomWriter().doMain(new Configuration(), args);
+ int res = ToolRunner.run(new Configuration(), new RandomWriter(), args);
System.exit(res);
}
Modified: lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/Sort.java
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/Sort.java?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
--- lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/Sort.java
(original)
+++ lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/Sort.java Wed
Sep 5 16:10:42 2007
@@ -18,14 +18,18 @@
package org.apache.hadoop.examples;
-import java.io.*;
+import java.io.IOException;
import java.util.*;
import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.conf.Configured;
+import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.mapred.*;
-import org.apache.hadoop.mapred.lib.*;
-import org.apache.hadoop.fs.*;
+import org.apache.hadoop.mapred.lib.IdentityMapper;
+import org.apache.hadoop.mapred.lib.IdentityReducer;
+import org.apache.hadoop.util.Tool;
+import org.apache.hadoop.util.ToolRunner;
/**
* This is the trivial map/reduce program that does absolutely nothing
@@ -34,40 +38,40 @@
* To run: bin/hadoop jar build/hadoop-examples.jar sort
* [-m <i>maps</i>] [-r <i>reduces</i>] <i>in-dir</i>
<i>out-dir</i>
*/
-public class Sort {
-
- static void printUsage() {
+public class Sort extends Configured implements Tool {
+
+ static int printUsage() {
System.out.println("sort [-m <maps>] [-r <reduces>] <input> <output>");
- System.exit(1);
+ ToolRunner.printGenericCommandUsage(System.out);
+ return -1;
}
-
+
/**
* The main driver for sort program.
* Invoke this method to submit the map/reduce job.
* @throws IOException When there is communication problems with the
* job tracker.
*/
- public static void main(String[] args) throws IOException {
- Configuration defaults = new Configuration();
-
- JobConf jobConf = new JobConf(defaults, Sort.class);
+ public int run(String[] args) throws Exception {
+
+ JobConf jobConf = new JobConf(getConf(), Sort.class);
jobConf.setJobName("sorter");
-
+
jobConf.setInputFormat(SequenceFileInputFormat.class);
jobConf.setOutputFormat(SequenceFileOutputFormat.class);
-
+
jobConf.setOutputKeyClass(BytesWritable.class);
jobConf.setOutputValueClass(BytesWritable.class);
-
+
jobConf.setMapperClass(IdentityMapper.class);
jobConf.setReducerClass(IdentityReducer.class);
-
+
JobClient client = new JobClient(jobConf);
ClusterStatus cluster = client.getClusterStatus();
int num_maps = cluster.getTaskTrackers() *
- jobConf.getInt("test.sort.maps_per_host", 10);
+ jobConf.getInt("test.sort.maps_per_host", 10);
int num_reduces = cluster.getTaskTrackers() *
- jobConf.getInt("test.sort.reduces_per_host", cluster.getMaxTasks());
+ jobConf.getInt("test.sort.reduces_per_host", cluster.getMaxTasks());
List<String> otherArgs = new ArrayList<String>();
for(int i=0; i < args.length; ++i) {
try {
@@ -80,41 +84,46 @@
}
} catch (NumberFormatException except) {
System.out.println("ERROR: Integer expected instead of " + args[i]);
- printUsage();
+ return printUsage();
} catch (ArrayIndexOutOfBoundsException except) {
System.out.println("ERROR: Required parameter missing from " +
- args[i-1]);
- printUsage(); // exits
+ args[i-1]);
+ return printUsage(); // exits
}
}
-
+
jobConf.setNumMapTasks(num_maps);
jobConf.setNumReduceTasks(num_reduces);
-
+
// Make sure there are exactly 2 parameters left.
if (otherArgs.size() != 2) {
System.out.println("ERROR: Wrong number of parameters: " +
- otherArgs.size() + " instead of 2.");
- printUsage();
+ otherArgs.size() + " instead of 2.");
+ return printUsage();
}
- jobConf.setInputPath(new Path((String) otherArgs.get(0)));
- jobConf.setOutputPath(new Path((String) otherArgs.get(1)));
-
- // Uncomment to run locally in a single process
- //job_conf.set("mapred.job.tracker", "local");
-
+ jobConf.setInputPath(new Path(otherArgs.get(0)));
+ jobConf.setOutputPath(new Path(otherArgs.get(1)));
+
System.out.println("Running on " +
- cluster.getTaskTrackers() +
- " nodes to sort from " +
- jobConf.getInputPaths()[0] + " into " +
- jobConf.getOutputPath() + " with " + num_reduces + "
reduces.");
+ cluster.getTaskTrackers() +
+ " nodes to sort from " +
+ jobConf.getInputPaths()[0] + " into " +
+ jobConf.getOutputPath() + " with " + num_reduces + " reduces.");
Date startTime = new Date();
System.out.println("Job started: " + startTime);
JobClient.runJob(jobConf);
Date end_time = new Date();
System.out.println("Job ended: " + end_time);
System.out.println("The job took " +
- (end_time.getTime() - startTime.getTime()) /1000 + "
seconds.");
+ (end_time.getTime() - startTime.getTime()) /1000 + " seconds.");
+ return 0;
}
-
+
+
+
+ public static void main(String[] args) throws Exception {
+ int res = ToolRunner.run(new Configuration(), new Sort(), args);
+ System.exit(res);
+ }
+
}
Modified:
lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/WordCount.java
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/WordCount.java?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
--- lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/WordCount.java
(original)
+++ lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/WordCount.java
Wed Sep 5 16:10:42 2007
@@ -18,20 +18,27 @@
package org.apache.hadoop.examples;
-import java.io.*;
-import java.util.*;
+import java.io.IOException;
+import java.util.ArrayList;
+import java.util.Iterator;
+import java.util.List;
+import java.util.StringTokenizer;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.MapReduceBase;
import org.apache.hadoop.mapred.Mapper;
import org.apache.hadoop.mapred.OutputCollector;
import org.apache.hadoop.mapred.Reducer;
import org.apache.hadoop.mapred.Reporter;
-import org.apache.hadoop.mapred.MapReduceBase;
+import org.apache.hadoop.util.Tool;
+import org.apache.hadoop.util.ToolRunner;
/**
* This is an example Hadoop Map/Reduce application.
@@ -42,7 +49,7 @@
* To run: bin/hadoop jar build/hadoop-examples.jar wordcount
* [-m <i>maps</i>] [-r <i>reduces</i>] <i>in-dir</i>
<i>out-dir</i>
*/
-public class WordCount {
+public class WordCount extends Configured implements Tool {
/**
* Counts the words in each line.
@@ -84,9 +91,10 @@
}
}
- static void printUsage() {
+ static int printUsage() {
System.out.println("wordcount [-m <maps>] [-r <reduces>] <input>
<output>");
- System.exit(1);
+ ToolRunner.printGenericCommandUsage(System.out);
+ return -1;
}
/**
@@ -95,8 +103,8 @@
* @throws IOException When there is communication problems with the
* job tracker.
*/
- public static void main(String[] args) throws IOException {
- JobConf conf = new JobConf(WordCount.class);
+ public int run(String[] args) throws Exception {
+ JobConf conf = new JobConf(getConf(), WordCount.class);
conf.setJobName("wordcount");
// the keys are words (strings)
@@ -120,26 +128,30 @@
}
} catch (NumberFormatException except) {
System.out.println("ERROR: Integer expected instead of " + args[i]);
- printUsage();
+ return printUsage();
} catch (ArrayIndexOutOfBoundsException except) {
System.out.println("ERROR: Required parameter missing from " +
args[i-1]);
- printUsage(); // exits
+ return printUsage();
}
}
// Make sure there are exactly 2 parameters left.
if (other_args.size() != 2) {
System.out.println("ERROR: Wrong number of parameters: " +
other_args.size() + " instead of 2.");
- printUsage();
+ return printUsage();
}
- conf.setInputPath(new Path((String) other_args.get(0)));
- conf.setOutputPath(new Path((String) other_args.get(1)));
-
- // Uncomment to run locally in a single process
- // conf.set("mapred.job.tracker", "local");
-
+ conf.setInputPath(new Path(other_args.get(0)));
+ conf.setOutputPath(new Path(other_args.get(1)));
+
JobClient.runJob(conf);
+ return 0;
}
+
+ public static void main(String[] args) throws Exception {
+ int res = ToolRunner.run(new Configuration(), new WordCount(), args);
+ System.exit(res);
+ }
+
}
Modified:
lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/dancing/DistributedPentomino.java
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/dancing/DistributedPentomino.java?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
---
lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/dancing/DistributedPentomino.java
(original)
+++
lucene/hadoop/trunk/src/examples/org/apache/hadoop/examples/dancing/DistributedPentomino.java
Wed Sep 5 16:10:42 2007
@@ -19,10 +19,13 @@
package org.apache.hadoop.examples.dancing;
import java.io.*;
-import java.util.*;
+import java.util.List;
+import java.util.StringTokenizer;
-import org.apache.hadoop.fs.Path;
+import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.conf.Configured;
import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.WritableComparable;
import org.apache.hadoop.mapred.*;
@@ -38,7 +41,7 @@
* the previous choice. That file is given as the input to
* map/reduce. The output key/value are the move prefix/solution as Text/Text.
*/
-public class DistributedPentomino {
+public class DistributedPentomino extends Configured implements Tool {
/**
* Each map takes a line, which represents a prefix move and finds all of
@@ -98,6 +101,7 @@
pent.solve(prefix);
}
+ @Override
public void configure(JobConf conf) {
depth = conf.getInt("pent.depth", -1);
width = conf.getInt("pent.width", -1);
@@ -146,56 +150,58 @@
* This takes about 2.5 hours on 20 nodes with 2 cpus/node.
* Splits the job into 2000 maps and 1 reduce.
*/
- public static void main(String[] args) throws IOException {
+ public static void main(String[] args) throws Exception {
+ int res = ToolRunner.run(new Configuration(), new DistributedPentomino(),
args);
+ System.exit(res);
+ }
+
+ public int run(String[] args) throws Exception {
JobConf conf;
int depth = 5;
int width = 9;
int height = 10;
Class pentClass;
if (args.length == 0) {
- System.out.println("pentomino <output> [conf]");
- return;
- }
- if (args.length == 1) {
- conf = new JobConf();
- conf.setInt("pent.width", width);
- conf.setInt("pent.height", height);
- conf.setInt("pent.depth", depth);
- pentClass = OneSidedPentomino.class;
- } else {
- conf = new JobConf(args[0]);
- width = conf.getInt("pent.width", width);
- height = conf.getInt("pent.height", height);
- depth = conf.getInt("pent.depth", depth);
- pentClass = conf.getClass("pent.class", OneSidedPentomino.class);
+ System.out.println("pentomino <output>");
+ ToolRunner.printGenericCommandUsage(System.out);
+ return -1;
}
+
+ conf = new JobConf(getConf());
+ width = conf.getInt("pent.width", width);
+ height = conf.getInt("pent.height", height);
+ depth = conf.getInt("pent.depth", depth);
+ pentClass = conf.getClass("pent.class", OneSidedPentomino.class);
+
Path output = new Path(args[0]);
Path input = new Path(output + "_input");
- conf.setInputPath(input);
- conf.setOutputPath(output);
- conf.setJarByClass(PentMap.class);
FileSystem fileSys = FileSystem.get(conf);
- conf.setJobName("dancingElephant");
- Pentomino pent = (Pentomino) ReflectionUtils.newInstance(pentClass, conf);
- pent.initialize(width, height);
- createInputDirectory(fileSys, input, pent, depth);
-
- // the keys are the prefix strings
- conf.setOutputKeyClass(Text.class);
- // the values are puzzle solutions
- conf.setOutputValueClass(Text.class);
-
- conf.setMapperClass(PentMap.class);
- conf.setReducerClass(IdentityReducer.class);
-
- conf.setNumMapTasks(2000);
- conf.setNumReduceTasks(1);
-
- // Uncomment to run locally in a single process
- //conf.set("mapred.job.tracker", "local");
-
- JobClient.runJob(conf);
- fileSys.delete(input);
+ try {
+ conf.setInputPath(input);
+ conf.setOutputPath(output);
+ conf.setJarByClass(PentMap.class);
+
+ conf.setJobName("dancingElephant");
+ Pentomino pent = (Pentomino) ReflectionUtils.newInstance(pentClass,
conf);
+ pent.initialize(width, height);
+ createInputDirectory(fileSys, input, pent, depth);
+
+ // the keys are the prefix strings
+ conf.setOutputKeyClass(Text.class);
+ // the values are puzzle solutions
+ conf.setOutputValueClass(Text.class);
+
+ conf.setMapperClass(PentMap.class);
+ conf.setReducerClass(IdentityReducer.class);
+
+ conf.setNumMapTasks(2000);
+ conf.setNumReduceTasks(1);
+
+ JobClient.runJob(conf);
+ } finally {
+ fileSys.delete(input);
+ }
+ return 0;
}
}
Modified: lucene/hadoop/trunk/src/java/org/apache/hadoop/dfs/DFSAdmin.java
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/src/java/org/apache/hadoop/dfs/DFSAdmin.java?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
--- lucene/hadoop/trunk/src/java/org/apache/hadoop/dfs/DFSAdmin.java (original)
+++ lucene/hadoop/trunk/src/java/org/apache/hadoop/dfs/DFSAdmin.java Wed Sep 5
16:10:42 2007
@@ -213,6 +213,8 @@
System.out.println(refreshNodes);
System.out.println(upgradeProgress);
System.out.println(help);
+ System.out.println();
+ ToolRunner.printGenericCommandUsage(System.out);
}
}
@@ -325,6 +327,8 @@
System.err.println(" [-upgradeProgress status | details |
force]");
System.err.println(" [-metasave filename]");
System.err.println(" [-help [cmd]]");
+ System.err.println();
+ ToolRunner.printGenericCommandUsage(System.err);
}
}
Modified: lucene/hadoop/trunk/src/java/org/apache/hadoop/dfs/DFSck.java
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/src/java/org/apache/hadoop/dfs/DFSck.java?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
--- lucene/hadoop/trunk/src/java/org/apache/hadoop/dfs/DFSck.java (original)
+++ lucene/hadoop/trunk/src/java/org/apache/hadoop/dfs/DFSck.java Wed Sep 5
16:10:42 2007
@@ -89,6 +89,7 @@
System.err.println("\t-files\tprint out files being checked");
System.err.println("\t-blocks\tprint out block report");
System.err.println("\t-locations\tprint out locations for every block");
+ ToolRunner.printGenericCommandUsage(System.err);
return -1;
}
StringBuffer url = new StringBuffer("http://"+fsName+"/fsck?path=";);
Modified: lucene/hadoop/trunk/src/java/org/apache/hadoop/fs/FsShell.java
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/src/java/org/apache/hadoop/fs/FsShell.java?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
--- lucene/hadoop/trunk/src/java/org/apache/hadoop/fs/FsShell.java (original)
+++ lucene/hadoop/trunk/src/java/org/apache/hadoop/fs/FsShell.java Wed Sep 5
16:10:42 2007
@@ -1216,9 +1216,6 @@
" [-stat [format] <path>]");
} else {
System.err.println("Usage: java FsShell");
- System.err.println(" [-fs <local | file system URI>]");
- System.err.println(" [-conf <configuration file>]");
- System.err.println(" [-D <[property=value>]");
System.err.println(" [-ls <path>]");
System.err.println(" [-lsr <path>]");
System.err.println(" [-du <path>]");
@@ -1242,6 +1239,8 @@
System.err.println(" [-test -[ezd] <path>]");
System.err.println(" [-stat [format] <path>]");
System.err.println(" [-help [cmd]]");
+ System.err.println();
+ ToolRunner.printGenericCommandUsage(System.err);
}
}
Modified:
lucene/hadoop/trunk/src/java/org/apache/hadoop/fs/s3/MigrationTool.java
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/src/java/org/apache/hadoop/fs/s3/MigrationTool.java?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
--- lucene/hadoop/trunk/src/java/org/apache/hadoop/fs/s3/MigrationTool.java
(original)
+++ lucene/hadoop/trunk/src/java/org/apache/hadoop/fs/s3/MigrationTool.java Wed
Sep 5 16:10:42 2007
@@ -62,6 +62,7 @@
if (args.length == 0) {
System.err.println("Usage: MigrationTool <S3 file system URI>");
System.err.println("\t<S3 file system URI>\tfilesystem to migrate");
+ ToolRunner.printGenericCommandUsage(System.err);
return -1;
}
Modified: lucene/hadoop/trunk/src/java/org/apache/hadoop/mapred/JobClient.java
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/src/java/org/apache/hadoop/mapred/JobClient.java?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
--- lucene/hadoop/trunk/src/java/org/apache/hadoop/mapred/JobClient.java
(original)
+++ lucene/hadoop/trunk/src/java/org/apache/hadoop/mapred/JobClient.java Wed
Sep 5 16:10:42 2007
@@ -768,6 +768,7 @@
System.out.printf("\t-kill\t<job-id>\n");
System.out.printf("\t-events\t<job-id> <from-event-#> <#-of-events>\n");
System.out.printf("\t-list\n\n");
+ ToolRunner.printGenericCommandUsage(System.out);
throw new RuntimeException("JobClient: bad command-line arguments");
}
Modified:
lucene/hadoop/trunk/src/java/org/apache/hadoop/mapred/lib/aggregate/ValueAggregatorJob.java
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/src/java/org/apache/hadoop/mapred/lib/aggregate/ValueAggregatorJob.java?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
---
lucene/hadoop/trunk/src/java/org/apache/hadoop/mapred/lib/aggregate/ValueAggregatorJob.java
(original)
+++
lucene/hadoop/trunk/src/java/org/apache/hadoop/mapred/lib/aggregate/ValueAggregatorJob.java
Wed Sep 5 16:10:42 2007
@@ -21,17 +21,18 @@
import java.io.IOException;
import java.util.ArrayList;
+import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.mapred.InputFormat;
+import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapred.SequenceFileInputFormat;
import org.apache.hadoop.mapred.TextInputFormat;
import org.apache.hadoop.mapred.TextOutputFormat;
import org.apache.hadoop.mapred.jobcontrol.Job;
import org.apache.hadoop.mapred.jobcontrol.JobControl;
-import org.apache.hadoop.mapred.JobClient;
-import org.apache.hadoop.mapred.RunningJob;
+import org.apache.hadoop.util.GenericOptionsParser;
/**
* This is the main class for creating a map/reduce job using Aggregate
@@ -90,17 +91,26 @@
/**
* Create an Aggregate based map/reduce job.
*
- * @param args the arguments used for job creation
+ * @param args the arguments used for job creation. Generic hadoop
+ * arguments are accepted.
* @return a JobConf object ready for submission.
*
* @throws IOException
+ * @see GenericOptionsParser
*/
public static JobConf createValueAggregatorJob(String args[])
throws IOException {
+ Configuration conf = new Configuration();
+
+ GenericOptionsParser genericParser
+ = new GenericOptionsParser(conf, args);
+ args = genericParser.getRemainingArgs();
+
if (args.length < 2) {
System.out.println("usage: inputDirs outDir "
+ "[numOfReducer [textinputformat|seq [specfile [jobName]]]]");
+ GenericOptionsParser.printGenericCommandUsage(System.out);
System.exit(1);
}
String inputDir = args[0];
@@ -131,7 +141,7 @@
jobName = args[5];
}
- JobConf theJob = new JobConf();
+ JobConf theJob = new JobConf(conf);
if (specFile != null) {
theJob.addDefaultResource(specFile);
}
Modified: lucene/hadoop/trunk/src/java/org/apache/hadoop/util/CopyFiles.java
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/src/java/org/apache/hadoop/util/CopyFiles.java?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
--- lucene/hadoop/trunk/src/java/org/apache/hadoop/util/CopyFiles.java
(original)
+++ lucene/hadoop/trunk/src/java/org/apache/hadoop/util/CopyFiles.java Wed Sep
5 16:10:42 2007
@@ -39,8 +39,8 @@
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FSDataOutputStream;
-import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.FileStatus;
+import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.FileUtil;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.SequenceFile;
@@ -828,6 +828,7 @@
logPath = new Path(toURI(args[++idx]).getPath());
} else {
System.out.println(usage);
+ ToolRunner.printGenericCommandUsage(System.out);
return -1;
}
}
@@ -835,6 +836,7 @@
// mandatory command-line parameters
if (srcPath == null || destPath == null) {
System.out.println(usage);
+ ToolRunner.printGenericCommandUsage(System.out);
return -1;
}
Modified:
lucene/hadoop/trunk/src/java/org/apache/hadoop/util/GenericOptionsParser.java
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/src/java/org/apache/hadoop/util/GenericOptionsParser.java?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
---
lucene/hadoop/trunk/src/java/org/apache/hadoop/util/GenericOptionsParser.java
(original)
+++
lucene/hadoop/trunk/src/java/org/apache/hadoop/util/GenericOptionsParser.java
Wed Sep 5 16:10:42 2007
@@ -17,6 +17,8 @@
*/
package org.apache.hadoop.util;
+import java.io.PrintStream;
+
import org.apache.commons.cli.CommandLine;
import org.apache.commons.cli.CommandLineParser;
import org.apache.commons.cli.GnuParser;
@@ -210,4 +212,14 @@
return args;
}
+ public static void printGenericCommandUsage(PrintStream out) {
+ out.println("Generic options supported are");
+ out.println("-conf <configuration file> specify an application
configuration file");
+ out.println("-D <property=value> use value for given property");
+ out.println("-fs <local|namenode:port> specify a namenod");
+ out.println("-jt <local|jobtracker:port> specify a job tracker\n");
+ out.println("The general command line syntax is");
+ out.println("bin/hadoop command [genericOptions] [commandOptions]\n");
+ }
+
}
Modified: lucene/hadoop/trunk/src/java/org/apache/hadoop/util/ToolRunner.java
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/src/java/org/apache/hadoop/util/ToolRunner.java?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
--- lucene/hadoop/trunk/src/java/org/apache/hadoop/util/ToolRunner.java
(original)
+++ lucene/hadoop/trunk/src/java/org/apache/hadoop/util/ToolRunner.java Wed Sep
5 16:10:42 2007
@@ -17,6 +17,8 @@
*/
package org.apache.hadoop.util;
+import java.io.PrintStream;
+
import org.apache.hadoop.conf.Configuration;
/**
@@ -63,6 +65,11 @@
public static int run(Tool tool, String[] args)
throws Exception{
return run(tool.getConf(), tool, args);
+ }
+
+ /** Delegates to GenericOptionsParser#printGenericCommandUsage() */
+ public static void printGenericCommandUsage(PrintStream out) {
+ GenericOptionsParser.printGenericCommandUsage(out);
}
}
Modified:
lucene/hadoop/trunk/src/test/org/apache/hadoop/mapred/BigMapOutput.java
URL:
http://svn.apache.org/viewvc/lucene/hadoop/trunk/src/test/org/apache/hadoop/mapred/BigMapOutput.java?rev=573095&r1=573094&r2=573095&view=diff
==============================================================================
--- lucene/hadoop/trunk/src/test/org/apache/hadoop/mapred/BigMapOutput.java
(original)
+++ lucene/hadoop/trunk/src/test/org/apache/hadoop/mapred/BigMapOutput.java Wed
Sep 5 16:10:42 2007
@@ -18,21 +18,26 @@
package org.apache.hadoop.mapred;
-import java.io.*;
-import java.util.*;
+import java.io.IOException;
+import java.util.Date;
+import java.util.Random;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
-import org.apache.hadoop.mapred.SortValidator.RecordStatsChecker.*;
import org.apache.hadoop.conf.Configuration;
+import org.apache.hadoop.conf.Configured;
+import org.apache.hadoop.fs.FileSystem;
+import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.BytesWritable;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.SequenceFile.CompressionType;
-import org.apache.hadoop.mapred.lib.*;
-import org.apache.hadoop.util.ToolBase;
-import org.apache.hadoop.fs.*;
+import
org.apache.hadoop.mapred.SortValidator.RecordStatsChecker.NonSplitableSequenceFileInputFormat;
+import org.apache.hadoop.mapred.lib.IdentityMapper;
+import org.apache.hadoop.mapred.lib.IdentityReducer;
+import org.apache.hadoop.util.Tool;
+import org.apache.hadoop.util.ToolRunner;
-public class BigMapOutput extends ToolBase {
+public class BigMapOutput extends Configured implements Tool {
public static final Log LOG =
LogFactory.getLog(BigMapOutput.class.getName());
private static Random random = new Random();
@@ -95,6 +100,7 @@
private static void usage() {
System.err.println("BigMapOutput -input <input-dir> -output <output-dir> "
+
"[-create <filesize in MB>]");
+ ToolRunner.printGenericCommandUsage(System.err);
System.exit(1);
}
public int run(String[] args) throws Exception {
@@ -118,8 +124,8 @@
}
}
- FileSystem fs = FileSystem.get(conf);
- JobConf jobConf = new JobConf(conf, BigMapOutput.class);
+ FileSystem fs = FileSystem.get(getConf());
+ JobConf jobConf = new JobConf(getConf(), BigMapOutput.class);
jobConf.setJobName("BigMapOutput");
jobConf.setInputFormat(NonSplitableSequenceFileInputFormat.class);
@@ -148,7 +154,7 @@
}
public static void main(String argv[]) throws Exception {
- int res = new BigMapOutput().doMain(new Configuration(), argv);
+ int res = ToolRunner.run(new Configuration(), new BigMapOutput(), argv);
System.exit(res);
}
