split out reader and writer

This commit is contained in:
Shane Kumpf 2015-03-05 06:29:44 -07:00
parent ae8a7ff587
commit fe8d4458d0
3 changed files with 67 additions and 31 deletions

10
pom.xml
View File

@ -17,16 +17,6 @@
</properties>
<repositories>
<repository>
<releases>
<enabled>true</enabled>
</releases>
<snapshots>
<enabled>false</enabled>
</snapshots>
<id>clojars.org</id>
<url>http://clojars.org/repo</url>
</repository>
<repository>
<releases>
<enabled>true</enabled>

View File

@ -0,0 +1,58 @@
/*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
package com.github.sakserv.sequencefile;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.io.IntWritable;
import org.apache.hadoop.io.SequenceFile;
import org.apache.hadoop.io.Text;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import java.io.IOException;
public class SequenceFileReader {
// Logger
private static final Logger LOG = LoggerFactory.getLogger(SequenceFileReader.class);
public static void main(String[] args) {
String inputFile = args[0];
Configuration conf = new Configuration();
try {
Path seqFilePath = new Path(inputFile);
SequenceFile.Reader reader = new SequenceFile.Reader(conf,
SequenceFile.Reader.file(seqFilePath));
Text key = new Text();
IntWritable val = new IntWritable();
while (reader.next(key, val)) {
LOG.info("Sequence File Data: Key: " + key + "\tValue: " + val);
}
reader.close();
} catch(IOException e) {
LOG.error("ERROR: Could not load hadoop configuration");
e.printStackTrace();
}
}
}

View File

@ -24,21 +24,21 @@ import org.slf4j.LoggerFactory;
import java.io.IOException;
public class Main {
public class SequenceFileWriter {
// Logger
private static final Logger LOG = LoggerFactory.getLogger(Main.class);
private static final Logger LOG = LoggerFactory.getLogger(SequenceFileWriter.class);
public static void main(String[] args) {
String outputFile = args[0];
Configuration conf = new Configuration();
try {
FileSystem fs = FileSystem.get(conf);
Path seqFileDir = new Path("/tmp/seq_file_test");
fs.mkdirs(seqFileDir);
Path seqFilePath = new Path(seqFileDir + "/file.seq");
Path seqFilePath = new Path(outputFile);
fs.mkdirs(seqFilePath.getParent());
SequenceFile.Writer writer = SequenceFile.createWriter(conf,
SequenceFile.Writer.file(seqFilePath), SequenceFile.Writer.keyClass(Text.class),
@ -48,20 +48,8 @@ public class Main {
writer.append(new Text("key2"), new IntWritable(2));
writer.close();
SequenceFile.Reader reader = new SequenceFile.Reader(conf,
SequenceFile.Reader.file(seqFilePath));
Text key = new Text();
IntWritable val = new IntWritable();
while (reader.next(key, val)) {
System.out.println("SEQFILE KEY: " + key + "\t" + val);
}
fs.mkdirs(new Path("/tmp/seq_file_test"));
reader.close();
LOG.info("SUCCESS: Successfully wrote " + seqFilePath + " to HDFS.");
} catch(IOException e) {
LOG.error("ERROR: Could not load hadoop configuration");
e.printStackTrace();