5
0
mirror of https://github.com/apache/sqoop.git synced 2025-05-05 06:29:49 +08:00

SQOOP-735 Introduce output format option to Sqoop import

(Jarek Jarcec Cecho)
This commit is contained in:
Bilung Lee 2012-12-03 18:03:31 -08:00
parent 8a5cd6728a
commit cf3d71049d
5 changed files with 57 additions and 1 deletions

View File

@ -28,5 +28,7 @@ public class OutputForm {
@Input public StorageType storageType; @Input public StorageType storageType;
@Input public OutputFormat outputFormat;
@Input(size = 25) public String outputDirectory; @Input(size = 25) public String outputDirectory;
} }

View File

@ -0,0 +1,33 @@
/**
* Licensed to the Apache Software Foundation (ASF) under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. The ASF licenses this file
* to you 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 org.apache.sqoop.framework.configuration;
/**
* Various supported formats on disk
*/
public enum OutputFormat {
/**
* Comma separated text file
*/
TEXT_FILE,
/**
* Sequence file
*/
SEQUENCE_FILE,
}

View File

@ -35,6 +35,9 @@ output.help = You must supply the information requested in order to \
output.storageType.label = Storage type output.storageType.label = Storage type
output.storageType.help = Target on Hadoop ecosystem where to store data output.storageType.help = Target on Hadoop ecosystem where to store data
output.outputFormat.label = Output format
output.outputFormat.help = Format in which data should be serialized
output.outputDirectory.label = Output directory output.outputDirectory.label = Output directory
output.outputDirectory.help = Output directory for final data output.outputDirectory.help = Output directory for final data

View File

@ -19,9 +19,14 @@
import org.apache.hadoop.io.NullWritable; import org.apache.hadoop.io.NullWritable;
import org.apache.sqoop.common.MutableMapContext; import org.apache.sqoop.common.MutableMapContext;
import org.apache.sqoop.common.SqoopException;
import org.apache.sqoop.framework.ExecutionEngine; import org.apache.sqoop.framework.ExecutionEngine;
import org.apache.sqoop.framework.SubmissionRequest; import org.apache.sqoop.framework.SubmissionRequest;
import org.apache.sqoop.framework.configuration.ImportJobConfiguration;
import org.apache.sqoop.framework.configuration.OutputFormat;
import org.apache.sqoop.job.JobConstants; import org.apache.sqoop.job.JobConstants;
import org.apache.sqoop.job.MapreduceExecutionError;
import org.apache.sqoop.job.etl.HdfsSequenceImportLoader;
import org.apache.sqoop.job.etl.HdfsTextImportLoader; import org.apache.sqoop.job.etl.HdfsTextImportLoader;
import org.apache.sqoop.job.etl.Importer; import org.apache.sqoop.job.etl.Importer;
import org.apache.sqoop.job.io.Data; import org.apache.sqoop.job.io.Data;
@ -42,6 +47,7 @@ public SubmissionRequest createSubmissionRequest() {
@Override @Override
public void prepareImportSubmission(SubmissionRequest gRequest) { public void prepareImportSubmission(SubmissionRequest gRequest) {
MRSubmissionRequest request = (MRSubmissionRequest) gRequest; MRSubmissionRequest request = (MRSubmissionRequest) gRequest;
ImportJobConfiguration jobConf = (ImportJobConfiguration) request.getConfigFrameworkJob();
// Configure map-reduce classes for import // Configure map-reduce classes for import
request.setInputFormatClass(SqoopInputFormat.class); request.setInputFormatClass(SqoopInputFormat.class);
@ -61,6 +67,15 @@ public void prepareImportSubmission(SubmissionRequest gRequest) {
context.setString(JobConstants.JOB_ETL_PARTITIONER, importer.getPartitioner().getName()); context.setString(JobConstants.JOB_ETL_PARTITIONER, importer.getPartitioner().getName());
context.setString(JobConstants.JOB_ETL_EXTRACTOR, importer.getExtractor().getName()); context.setString(JobConstants.JOB_ETL_EXTRACTOR, importer.getExtractor().getName());
context.setString(JobConstants.JOB_ETL_DESTROYER, importer.getDestroyer().getName()); context.setString(JobConstants.JOB_ETL_DESTROYER, importer.getDestroyer().getName());
context.setString(JobConstants.JOB_ETL_LOADER, HdfsTextImportLoader.class.getName());
// TODO: This settings should be abstracted to core module at some point
if(jobConf.output.outputFormat == OutputFormat.TEXT_FILE) {
context.setString(JobConstants.JOB_ETL_LOADER, HdfsTextImportLoader.class.getName());
} else if(jobConf.output.outputFormat == OutputFormat.SEQUENCE_FILE) {
context.setString(JobConstants.JOB_ETL_LOADER, HdfsSequenceImportLoader.class.getName());
} else {
throw new SqoopException(MapreduceExecutionError.MAPRED_EXEC_0024,
"Format: " + jobConf.output.outputFormat);
}
} }
} }

View File

@ -73,6 +73,9 @@ public enum MapreduceExecutionError implements ErrorCode {
/** Unknown job type */ /** Unknown job type */
MAPRED_EXEC_0023("Unknown job type"), MAPRED_EXEC_0023("Unknown job type"),
/** Unsupported output format type found **/
MAPRED_EXEC_0024("Unknown output format type"),
; ;
private final String message; private final String message;