github/sqoop
5
0
Fork 0
mirror of https://github.com/apache/sqoop.git synced 2025-05-02 20:39:58 +08:00
Code Issues Projects Releases Wiki Activity

Add shim classes to allow compilation against different Hadoop distributions

Browse Source 
Version-incompatible code now moved to HadoopShim subclasses.
HadoopShim singleton instance dynamically loaded based on VersionInfo.
Separate MRUnit builds from Apache and CDH placed in /lib subdirs.
Modified 'ant package' target to properly include all shims.

From: Aaron Kimball <aaron@cloudera.com>

git-svn-id: https://svn.apache.org/repos/asf/incubator/sqoop/trunk@1149880 13f79535-47bb-0310-9956-ffa450edef68
This commit is contained in:
Andrew Bayer 2011-07-22 20:03:41 +00:00
parent 22190b9ba3
commit b55cb598da
19 changed files with 750 additions and 63 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

42
build.xml
View File

@ -32,6 +32,7 @@
<!-- locations in the source tree -->
<property name="src.dir" location="${basedir}/src/java" />
<property name="test.dir" location="${basedir}/src/test" />
<property name="shim.src.dir" location="${basedir}/src/shims" />
<property name="lib.dir" location="${basedir}/lib" />
<property name="docs.src.dir" location="${basedir}/src/docs" />
@ -101,7 +102,8 @@
-->
<path id="lib.path">
<fileset dir="${lib.dir}">
<include name="**/*.jar" />
<include name="*.jar" />
<include name="${hadoop.dist}/*.jar" />
</fileset>
</path>
@ -131,9 +133,35 @@
<!-- "init" target reserved for future setup purposes. -->
<target name="init" />
<!-- Compile a shim class so Sqoop can run with the specified hadoop.dist -->
<target name="compile-one-shim"
depends="init, ivy-retrieve-common, ivy-retrieve-hadoop">
<mkdir dir="${build.classes}" />
<javac
encoding="${build.encoding}"
destdir="${build.classes}"
debug="${javac.debug}"
deprecation="${javac.deprecation}">
<classpath refid="compile.classpath"/>
<src path="${shim.src.dir}/${hadoop.dist}" />
<src path="${shim.src.dir}/common" />
<include name="**/*.java" />
</javac>
</target>
<!-- Compile all shim classes (for a distribution jar) -->
<target name="compile-all-shims" depends="init">
<antcall target="compile-one-shim" inheritAll="false">
<param name="hadoop.dist" value="apache" />
</antcall>
<antcall target="compile-one-shim" inheritAll="false">
<param name="hadoop.dist" value="cloudera" />
</antcall>
</target>
<!-- Compile core classes for the project -->
<target name="compile"
depends="init, ivy-retrieve-common, ivy-retrieve-hadoop"
depends="init, ivy-retrieve-common, ivy-retrieve-hadoop, compile-one-shim"
description="Compile core classes for the project">
<!-- don't use an out-of-date instrumented build. -->
<delete dir="${cobertura.class.dir}" />
@ -171,12 +199,15 @@
</target>
<!-- Ensure that all source code can be built -->
<target name="compile-all" depends="compile,compile-test"
<target name="compile-all" depends="compile,compile-test,compile-all-shims"
description="Compile all sources"/>
<target name="package" depends="jar,compile-all,docs,ivy-retrieve-redist"
description="Create a redistributable package">
<!-- rebuild the jar to include all shims. -->
<jar jarfile="${build.dir}/${dest.jar}" basedir="${build.classes}" />
<mkdir dir="${dist.dir}"/>
<!-- copy in the build artifact -->
@ -194,6 +225,9 @@
<exclude name="build/**" />
<exclude name="lib/**" />
<exclude name=".git/**" />
<exclude name="tags" />
<exclude name=".project" />
<exclude name=".classpath" />
</fileset>
</copy>
@ -205,7 +239,7 @@
</fileset>
</copy>
<copy todir="${dist.dir}/lib" includeEmptyDirs="false" flatten="true">
<copy todir="${dist.dir}/lib" includeEmptyDirs="false">
<fileset dir="${lib.dir}">
<include name="**/*" />
<exclude name="ivy*" />

2
ivy.xml
View File

@ -76,7 +76,7 @@
<!-- Dependencies for Cloudera's Distribution for Hadoop -->
<dependency org="org.apache.hadoop" name="hadoop-core"
rev="${hadoop-core.cloudera.version}" conf="cloudera->default"/>
<dependency org="org.apache.hadoop" name="hadoop-core-test"
<dependency org="org.apache.hadoop" name="hadoop-test"
rev="${hadoop-core.cloudera.version}" conf="clouderatest->default"/>
<!-- Common dependencies for Sqoop -->

2
ivy/ivysettings.xml
View File

@ -47,7 +47,7 @@
<ibiblio name="apache-snapshot" root="${snapshot.apache.org}"
m2compatible="true" checkmodified="true" changingPattern=".*SNAPSHOT"/>
<filesystem name="fs" m2compatible="true" force="true">
<filesystem name="fs" m2compatible="true">
<artifact pattern="${repo.dir}/org/apache/hadoop/[module]/[revision]/[module]-[revision].[ext]"/>
<ivy pattern="${repo.dir}/org/apache/hadoop/[module]/[revision]/[module]-[revision].pom"/>
</filesystem>

0
lib/LICENSE-hadoop-0.22-SNAPSHOT-mrunit.txt → lib/apache/LICENSE-hadoop-0.22-SNAPSHOT-mrunit.txt
View File

0
lib/hadoop-0.22-SNAPSHOT-mrunit.jar → lib/apache/hadoop-0.22-SNAPSHOT-mrunit.jar
View File

244
lib/cloudera/LICENSE-hadoop-mrunit-0.20.2-CDH3b2-SNAPSHOT.txt Normal file
View File

@ -0,0 +1,244 @@
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
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.
APACHE HADOOP SUBCOMPONENTS:
The Apache Hadoop project contains subcomponents with separate copyright
notices and license terms. Your use of the source code for the these
subcomponents is subject to the terms and conditions of the following
licenses.
For the org.apache.hadoop.util.bloom.* classes:
/**
*
* Copyright (c) 2005, European Commission project OneLab under contract
* 034819 (http://www.one-lab.org)
* All rights reserved.
* Redistribution and use in source and binary forms, with or
* without modification, are permitted provided that the following
* conditions are met:
* - Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* - Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the distribution.
* - Neither the name of the University Catholique de Louvain - UCL
* nor the names of its contributors may be used to endorse or
* promote products derived from this software without specific prior
* written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS
* FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE
* COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT,
* INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING,
* BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
* CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN
* ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
* POSSIBILITY OF SUCH DAMAGE.
*/

BIN
lib/cloudera/hadoop-mrunit-0.20.2-CDH3b2-SNAPSHOT.jar Normal file
View File

Binary file not shown.

4
src/java/org/apache/hadoop/sqoop/lib/LargeObjectLoader.java
View File

@ -42,6 +42,7 @@
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.TaskInputOutputContext;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.sqoop.shims.HadoopShim;
/**
* Contains a set of methods which can read db columns from a ResultSet into
@ -81,7 +82,8 @@ public LargeObjectLoader(TaskInputOutputContext context)
*/
private String getNextLobFileName() {
String file = "_lob/obj_" + context.getConfiguration().get(
JobContext.TASK_ID, "unknown_task_id") + nextLobFileId;
HadoopShim.get().getTaskIdProperty(), "unknown_task_id")
+ nextLobFileId;
nextLobFileId++;
return file;

4
src/java/org/apache/hadoop/sqoop/manager/MySQLUtils.java
View File

@ -36,6 +36,7 @@
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.lib.db.DBConfiguration;
import org.apache.hadoop.sqoop.shims.HadoopShim;
import org.apache.hadoop.sqoop.util.DirectImportUtils;
/**
@ -97,7 +98,8 @@ public static boolean outputDelimsAreMySQL(Configuration conf) {
public static String writePasswordFile(Configuration conf)
throws IOException {
// Create the temp file to hold the user's password.
String tmpDir = conf.get(JobContext.JOB_LOCAL_DIR, "/tmp/");
String tmpDir = conf.get(
HadoopShim.get().getJobLocalDirProperty(), "/tmp/");
File tempFile = File.createTempFile("mysql-cnf",".cnf", new File(tmpDir));
// Make the password file only private readable.

7
src/java/org/apache/hadoop/sqoop/mapreduce/ExportJobBase.java
View File

@ -36,7 +36,6 @@
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.OutputFormat;
import org.apache.hadoop.mapreduce.TaskCounter;
import org.apache.hadoop.mapreduce.lib.db.DBConfiguration;
import org.apache.hadoop.mapreduce.lib.db.DBOutputFormat;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
@ -49,6 +48,7 @@
import org.apache.hadoop.sqoop.manager.ConnManager;
import org.apache.hadoop.sqoop.manager.ExportJobContext;
import org.apache.hadoop.sqoop.orm.TableClassName;
import org.apache.hadoop.sqoop.shims.HadoopShim;
import org.apache.hadoop.sqoop.util.ClassLoaderStack;
import org.apache.hadoop.sqoop.util.ExportException;
import org.apache.hadoop.sqoop.util.PerfCounters;
@ -113,7 +113,7 @@ protected void configureMapper(Job job, String tableName,
job.setMapperClass(getMapperClass());
// Concurrent writes of the same records would be problematic.
job.setMapSpeculativeExecution(false);
HadoopShim.get().setJobMapSpeculativeExecution(job, false);
job.setMapOutputKeyClass(SqoopRecord.class);
job.setMapOutputValueClass(NullWritable.class);
@ -138,8 +138,7 @@ protected boolean runJob(Job job) throws ClassNotFoundException, IOException,
counters.addBytes(job.getCounters().getGroup("FileSystemCounters")
.findCounter("HDFS_BYTES_READ").getValue());
LOG.info("Transferred " + counters.toString());
long numRecords = job.getCounters()
.findCounter(TaskCounter.MAP_INPUT_RECORDS).getValue();
long numRecords = HadoopShim.get().getNumMapInputRecords(job);
LOG.info("Exported " + numRecords + " records.");
return success;

5
src/java/org/apache/hadoop/sqoop/mapreduce/ImportJobBase.java
View File

@ -36,7 +36,6 @@
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.OutputFormat;
import org.apache.hadoop.mapreduce.TaskCounter;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat;
import org.apache.hadoop.mapreduce.lib.db.DBConfiguration;
@ -47,6 +46,7 @@
import org.apache.hadoop.sqoop.SqoopOptions;
import org.apache.hadoop.sqoop.manager.ConnManager;
import org.apache.hadoop.sqoop.orm.TableClassName;
import org.apache.hadoop.sqoop.shims.HadoopShim;
import org.apache.hadoop.sqoop.util.ClassLoaderStack;
import org.apache.hadoop.sqoop.util.ImportException;
import org.apache.hadoop.sqoop.util.PerfCounters;
@ -122,8 +122,7 @@ protected boolean runJob(Job job) throws ClassNotFoundException, IOException,
counters.addBytes(job.getCounters().getGroup("FileSystemCounters")
.findCounter("HDFS_BYTES_WRITTEN").getValue());
LOG.info("Transferred " + counters.toString());
long numRecords = job.getCounters()
.findCounter(TaskCounter.MAP_OUTPUT_RECORDS).getValue();
long numRecords = HadoopShim.get().getNumMapOutputRecords(job);
LOG.info("Retrieved " + numRecords + " records.");
return success;
}

4
src/java/org/apache/hadoop/sqoop/mapreduce/JobBase.java
View File

@ -31,6 +31,7 @@
import org.apache.hadoop.mapreduce.OutputFormat;
import org.apache.hadoop.sqoop.SqoopOptions;
import org.apache.hadoop.sqoop.shims.HadoopShim;
import org.apache.hadoop.sqoop.util.ClassLoaderStack;
/**
@ -175,7 +176,8 @@ protected int configureNumTasks(Job job) throws IOException {
numMapTasks = SqoopOptions.DEFAULT_NUM_MAPPERS;
LOG.warn("Invalid mapper count; using " + numMapTasks + " mappers.");
}
job.getConfiguration().setInt(JobContext.NUM_MAPS, numMapTasks);
HadoopShim.get().setJobNumMaps(job, numMapTasks);
job.setNumReduceTasks(0);
return numMapTasks;
}

4
src/java/org/apache/hadoop/sqoop/mapreduce/MySQLExportMapper.java
View File

@ -34,6 +34,7 @@
import org.apache.hadoop.mapreduce.Mapper;
import org.apache.hadoop.mapreduce.lib.db.DBConfiguration;
import org.apache.hadoop.sqoop.manager.MySQLUtils;
import org.apache.hadoop.sqoop.shims.HadoopShim;
import org.apache.hadoop.sqoop.util.AsyncSink;
import org.apache.hadoop.sqoop.util.JdbcUrl;
import org.apache.hadoop.sqoop.util.LoggingAsyncSink;
@ -97,7 +98,8 @@ public class MySQLExportMapper<KEYIN, VALIN>
* A File object representing the FIFO is in 'fifoFile'.
*/
private void initMySQLImportProcess() throws IOException {
String tmpDir = conf.get(JobContext.JOB_LOCAL_DIR, "/tmp/");
String tmpDir = conf.get(HadoopShim.get().getJobLocalDirProperty(),
"/tmp/");
this.fifoFile = new File(tmpDir,
conf.get(MySQLUtils.TABLE_NAME_KEY, "UNKNOWN_TABLE") + ".txt");
String filename = fifoFile.toString();

119
src/shims/apache/org/apache/hadoop/sqoop/shims/Apache22HadoopShim.java Normal file
View File

@ -0,0 +1,119 @@
/**
* Licensed to Cloudera, Inc. under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. Cloudera, Inc. 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.hadoop.sqoop.shims;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapreduce.Counters;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.JobContext;
import org.apache.hadoop.mapreduce.MapContext;
import org.apache.hadoop.mapreduce.OutputCommitter;
import org.apache.hadoop.mapreduce.TaskAttemptID;
import org.apache.hadoop.mapreduce.TaskCounter;
import org.apache.hadoop.mapreduce.TaskType;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter;
import org.apache.hadoop.mapreduce.server.jobtracker.JTConfig;
import org.apache.hadoop.mapreduce.task.MapContextImpl;
import org.apache.hadoop.mrunit.mapreduce.mock.MockReporter;
/**
* Hadoop Shim for Apache 0.22.
*/
public class Apache22HadoopShim extends HadoopShim {
@Override
public long getNumMapOutputRecords(Job job)
throws IOException, InterruptedException {
return job.getCounters().findCounter(
TaskCounter.MAP_OUTPUT_RECORDS).getValue();
}
@Override
public long getNumMapInputRecords(Job job)
throws IOException, InterruptedException {
return job.getCounters().findCounter(
TaskCounter.MAP_INPUT_RECORDS).getValue();
}
@Override
public String getTaskIdProperty() {
return JobContext.TASK_ID;
}
@Override
public String getJobLocalDirProperty() {
return JobContext.JOB_LOCAL_DIR;
}
@Override
public void setJobNumMaps(Job job, int numMapTasks) {
job.getConfiguration().setInt(JobContext.NUM_MAPS, numMapTasks);
}
@Override
public void setJobMapSpeculativeExecution(Job job, boolean isEnabled) {
job.setMapSpeculativeExecution(isEnabled);
}
@Override
public void setJobtrackerAddr(Configuration conf, String addr) {
conf.set(JTConfig.JT_IPC_ADDRESS, "local");
}
private class MockMapContextWithCommitter
extends MapContextImpl<Object, Object, Object, Object> {
private Configuration conf;
private Path path;
public MockMapContextWithCommitter(Configuration c, Path p) {
super(c, new TaskAttemptID("jt", 0, TaskType.MAP, 0, 0),
null, null, null, new MockReporter(new Counters()), null);
this.conf = c;
this.path = p;
}
@Override
public InputSplit getInputSplit() {
return new FileSplit(new Path(path, "inputFile"), 0, 0, new String[0]);
}
@Override
public Configuration getConfiguration() {
return conf;
}
@Override
public OutputCommitter getOutputCommitter() {
try {
return new FileOutputCommitter(path, this);
} catch (IOException ioe) {
return null;
}
}
}
@Override
public MapContext getMapContextForIOPath(Configuration conf, Path p) {
return new MockMapContextWithCommitter(conf, p);
}
}

118
src/shims/cloudera/org/apache/hadoop/sqoop/shims/CDH3Shim.java Normal file
View File

@ -0,0 +1,118 @@
/**
* Licensed to Cloudera, Inc. under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. Cloudera, Inc. 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.hadoop.sqoop.shims;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapreduce.Counters;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.MapContext;
import org.apache.hadoop.mapreduce.OutputCommitter;
import org.apache.hadoop.mapreduce.TaskAttemptID;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter;
import org.apache.hadoop.mrunit.mapreduce.mock.MockReporter;
/**
* Hadoop Shim for CDH3 (based on 0.20.2)
*/
public class CDH3Shim extends HadoopShim {
@Override
public long getNumMapOutputRecords(Job job)
throws IOException, InterruptedException {
return job.getCounters().findCounter(
"org.apache.hadoop.mapred.Task$Counter",
"MAP_OUTPUT_RECORDS").getValue();
}
@Override
public long getNumMapInputRecords(Job job)
throws IOException, InterruptedException {
return job.getCounters().findCounter(
"org.apache.hadoop.mapred.Task$Counter",
"MAP_INPUT_RECORDS").getValue();
}
@Override
public String getTaskIdProperty() {
return "mapred.task.id";
}
@Override
public String getJobLocalDirProperty() {
return "job.local.dir";
}
@Override
public void setJobNumMaps(Job job, int numMapTasks) {
job.getConfiguration().setInt("mapred.map.tasks", numMapTasks);
}
@Override
public void setJobMapSpeculativeExecution(Job job, boolean isEnabled) {
job.getConfiguration().setBoolean(
"mapred.map.tasks.speculative.execution", isEnabled);
}
@Override
public void setJobtrackerAddr(Configuration conf, String addr) {
conf.set("mapred.job.tracker", addr);
}
private class MockMapContextWithCommitter
extends MapContext<Object, Object, Object, Object> {
private Path path;
private Configuration conf;
public MockMapContextWithCommitter(Configuration c, Path p) {
super(c, new TaskAttemptID("jt", 0, true, 0, 0),
null, null, null, new MockReporter(new Counters()), null);
this.path = p;
this.conf = c;
}
@Override
public OutputCommitter getOutputCommitter() {
try {
return new FileOutputCommitter(path, this);
} catch (IOException ioe) {
return null;
}
}
@Override
public InputSplit getInputSplit() {
return new FileSplit(new Path(path, "inputFile"), 0, 0, new String[0]);
}
@Override
public Configuration getConfiguration() {
return conf;
}
}
@Override
public MapContext getMapContextForIOPath(Configuration conf, Path p) {
return new MockMapContextWithCommitter(conf, p);
}
}

88
src/shims/common/org/apache/hadoop/sqoop/shims/HadoopShim.java Normal file
View File

@ -0,0 +1,88 @@
/**
* Licensed to Cloudera, Inc. under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. Cloudera, Inc. 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.hadoop.sqoop.shims;
import java.io.IOException;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.MapContext;
/**
* In order to be compatible with multiple versions of Hadoop, all parts
* of the Hadoop interface that are not cross-version compatible are
* encapsulated in an implementation of this class. Users should use
* the ShimLoader class as a factory to obtain an implementation of
* HadoopShims corresponding to the version of Hadoop currently on the
* classpath.
*/
public abstract class HadoopShim {
protected HadoopShim() {
}
/**
* @return the number of mapper output records from a job using its counters.
*/
public abstract long getNumMapOutputRecords(Job job)
throws IOException, InterruptedException;
/**
* @return the number of mapper input records from a job using its counters.
*/
public abstract long getNumMapInputRecords(Job job)
throws IOException, InterruptedException;
/**
* @return the Configuration property identifying the current task id.
*/
public abstract String getTaskIdProperty();
/**
* @return the Configuration property identifying the job's local dir.
*/
public abstract String getJobLocalDirProperty();
/**
* Set the (hinted) number of map tasks for a job.
*/
public abstract void setJobNumMaps(Job job, int numMapTasks);
/**
* Set the mapper speculative execution property for a job.
*/
public abstract void setJobMapSpeculativeExecution(Job job, boolean isEnabled);
/**
* Sets the Jobtracker address to use for a job.
*/
public abstract void setJobtrackerAddr(Configuration conf, String addr);
/**
* Returns a mock MapContext that has both an OutputCommitter and an
* InputSplit wired to the specified path.
* Used for testing LargeObjectLoader.
*/
public abstract MapContext getMapContextForIOPath(
Configuration conf, Path p);
public final static synchronized HadoopShim get() {
return ShimLoader.getHadoopShim();
}
}

112
src/shims/common/org/apache/hadoop/sqoop/shims/ShimLoader.java Normal file
View File

@ -0,0 +1,112 @@
/**
* Licensed to Cloudera, Inc. under one
* or more contributor license agreements. See the NOTICE file
* distributed with this work for additional information
* regarding copyright ownership. Cloudera, Inc. 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.hadoop.sqoop.shims;
import java.util.ArrayList;
import java.util.List;
import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.util.VersionInfo;
/**
* Provides a service locator for the appropriate shim, dynamically chosen
* based on the Hadoop version in the classpath.
*/
public abstract class ShimLoader {
private static HadoopShim hadoopShim;
public static final Log LOG = LogFactory.getLog(ShimLoader.class.getName());
/**
* The names of the classes for shimming Hadoop.
* This list must be maintained in the same order as HADOOP_SHIM_MATCHES
*/
private static final List<String> HADOOP_SHIM_CLASSES =
new ArrayList<String>();
/**
* The regular expressions compared against the Hadoop version string
* when determining which shim class to load.
*/
private static final List<String> HADOOP_SHIM_MATCHES =
new ArrayList<String>();
static {
// These regular expressions will be evaluated in order until one matches.
// Check
HADOOP_SHIM_MATCHES.add("0.20.2-[cC][dD][hH]3.*");
HADOOP_SHIM_CLASSES.add("org.apache.hadoop.sqoop.shims.CDH3Shim");
// Apache 0.22 trunk
HADOOP_SHIM_MATCHES.add("0.22-.*");
HADOOP_SHIM_CLASSES.add("org.apache.hadoop.sqoop.shims.Apache22HadoopShim");
// Apache 0.22 trunk snapshots often compile with "Unknown" version,
// so we default to guessing Apache in this case.
HADOOP_SHIM_MATCHES.add("Unknown");
HADOOP_SHIM_CLASSES.add("org.apache.hadoop.sqoop.shims.Apache22HadoopShim");
}
/**
* Factory method to get an instance of HadoopShim based on the
* version of Hadoop on the classpath.
*/
public static synchronized HadoopShim getHadoopShim() {
if (hadoopShim == null) {
hadoopShim = loadShim(HADOOP_SHIM_MATCHES, HADOOP_SHIM_CLASSES,
HadoopShim.class);
}
return hadoopShim;
}
@SuppressWarnings("unchecked")
private static <T> T loadShim(List<String> matchExprs,
List<String> classNames, Class<T> xface) {
String version = VersionInfo.getVersion();
LOG.debug("Loading shims for class : " + xface.getName());
LOG.debug("Hadoop version: " + version);
for (int i = 0; i < matchExprs.size(); i++) {
if (version.matches(matchExprs.get(i))) {
String className = classNames.get(i);
if (LOG.isDebugEnabled()) {
LOG.debug("Version matched regular expression: " + matchExprs.get(i));
LOG.debug("Trying to load class: " + className);
}
try {
Class clazz = Class.forName(className);
return xface.cast(clazz.newInstance());
} catch (Exception e) {
throw new RuntimeException("Could not load shim in class " +
className, e);
}
}
}
throw new RuntimeException("Could not find appropriate Hadoop shim for "
+ version);
}
private ShimLoader() {
// prevent instantiation
}
}

54
src/test/org/apache/hadoop/sqoop/lib/TestLargeObjectLoader.java
View File

@ -35,8 +35,7 @@
import org.apache.hadoop.mapreduce.OutputCommitter;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.output.FileOutputCommitter;
import org.apache.hadoop.mrunit.mapreduce.mock.MockMapContext;
import org.apache.hadoop.mrunit.types.Pair;
import org.apache.hadoop.sqoop.shims.HadoopShim;
import org.apache.hadoop.sqoop.testutil.MockResultSet;
/**
@ -44,47 +43,6 @@
*/
public class TestLargeObjectLoader extends TestCase {
/**
* A mock MapContext that uses FileOutputCommitter.
* This MapContext is actually serving two roles here; when writing the
* CLOB files, its OutputCommitter is used to determine where to write
* the CLOB data, as these are placed in the task output work directory.
* When reading the CLOB data back for verification, we use the
* getInputSplit() to determine where to read our source data from--the same
* directory. We are repurposing the same context for both output and input.
*/
private static class MockMapContextWithCommitter<K1, V1, K2, V2>
extends MockMapContext<K1, V1, K2, V2> {
private Path outputDir;
private Configuration conf;
public MockMapContextWithCommitter(Configuration conf, Path outDir) {
super(new ArrayList<Pair<K1, V1>>(), new Counters());
this.outputDir = outDir;
this.conf = conf;
}
@Override
public OutputCommitter getOutputCommitter() {
try {
return new FileOutputCommitter(outputDir, this);
} catch (IOException ioe) {
return null;
}
}
@Override
public InputSplit getInputSplit() {
return new FileSplit(new Path(outputDir, "inputFile"), 0, 0, new String[0]);
}
@Override
public Configuration getConfiguration() {
return conf;
}
}
protected Configuration conf;
protected MapContext mapContext;
protected LargeObjectLoader loader;
@ -100,7 +58,15 @@ public void setUp() throws IOException {
}
fs.mkdirs(outDir);
mapContext = new MockMapContextWithCommitter(conf, outDir);
/* A mock MapContext that uses FileOutputCommitter.
* This MapContext is actually serving two roles here; when writing the
* CLOB files, its OutputCommitter is used to determine where to write
* the CLOB data, as these are placed in the task output work directory.
* When reading the CLOB data back for verification, we use the
* getInputSplit() to determine where to read our source data from--the same
* directory. We are repurposing the same context for both output and input.
*/
mapContext = HadoopShim.get().getMapContextForIOPath(conf, outDir);
loader = new LargeObjectLoader(mapContext);
}

4
src/test/org/apache/hadoop/sqoop/orm/TestParseMethods.java
View File

@ -31,12 +31,12 @@
import org.apache.hadoop.mapred.FileOutputFormat;
import org.apache.hadoop.mapred.JobClient;
import org.apache.hadoop.mapred.JobConf;
import org.apache.hadoop.mapreduce.server.jobtracker.JTConfig;
import org.apache.hadoop.util.ReflectionUtils;
import org.apache.hadoop.sqoop.SqoopOptions;
import org.apache.hadoop.sqoop.SqoopOptions.InvalidOptionsException;
import org.apache.hadoop.sqoop.orm.CompilationManager;
import org.apache.hadoop.sqoop.shims.HadoopShim;
import org.apache.hadoop.sqoop.testutil.CommonArgs;
import org.apache.hadoop.sqoop.testutil.HsqldbTestServer;
import org.apache.hadoop.sqoop.testutil.ImportJobTestCase;
@ -118,7 +118,7 @@ public void runParseTest(String fieldTerminator, String lineTerminator, String e
job.set(ReparseMapper.USER_TYPE_NAME_KEY, tableClassName);
// use local mode in the same JVM.
job.set(JTConfig.JT_IPC_ADDRESS, "local");
HadoopShim.get().setJobtrackerAddr(job, "local");
job.set("fs.default.name", "file:///");
String warehouseDir = getWarehouseDir();