Posted by
zentol on
URL: http://deprecated-apache-flink-mailing-list-archive.368.s1.nabble.com/GitHub-incubator-flink-pull-request-The-Hadoop-Compatibility-has-been-re-tp613p623.html
Github user rmetzger commented on a diff in the pull request:
https://github.com/apache/incubator-flink/pull/32#discussion_r14037351
--- Diff: stratosphere-addons/hadoop-compatibility/src/main/java/eu/stratosphere/hadoopcompatibility/mapreduce/HadoopInputFormat.java ---
@@ -0,0 +1,337 @@
+/***********************************************************************************************************************
+ * Copyright (C) 2010-2013 by the Stratosphere project (
http://stratosphere.eu)
+ *
+ * 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 eu.stratosphere.hadoopcompatibility.mapreduce;
+
+import java.io.IOException;
+import java.io.ObjectInputStream;
+import java.io.ObjectOutputStream;
+import java.util.ArrayList;
+import java.util.List;
+
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+import org.apache.hadoop.io.Writable;
+import org.apache.hadoop.mapreduce.Job;
+import org.apache.hadoop.mapreduce.JobContext;
+import org.apache.hadoop.mapreduce.JobID;
+import org.apache.hadoop.mapreduce.RecordReader;
+import org.apache.hadoop.mapreduce.TaskAttemptContext;
+import org.apache.hadoop.mapreduce.TaskAttemptID;
+import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
+
+import eu.stratosphere.api.common.io.FileInputFormat.FileBaseStatistics;
+import eu.stratosphere.api.common.io.InputFormat;
+import eu.stratosphere.api.common.io.statistics.BaseStatistics;
+import eu.stratosphere.api.java.tuple.Tuple2;
+import eu.stratosphere.api.java.typeutils.ResultTypeQueryable;
+import eu.stratosphere.api.java.typeutils.TupleTypeInfo;
+import eu.stratosphere.api.java.typeutils.WritableTypeInfo;
+import eu.stratosphere.configuration.Configuration;
+import eu.stratosphere.core.fs.FileStatus;
+import eu.stratosphere.core.fs.FileSystem;
+import eu.stratosphere.core.fs.Path;
+import eu.stratosphere.hadoopcompatibility.mapreduce.utils.HadoopUtils;
+import eu.stratosphere.hadoopcompatibility.mapreduce.wrapper.HadoopInputSplit;
+import eu.stratosphere.types.TypeInformation;
+
+public class HadoopInputFormat<K extends Writable, V extends Writable> implements InputFormat<Tuple2<K,V>, HadoopInputSplit>, ResultTypeQueryable<Tuple2<K,V>> {
+
+ private static final long serialVersionUID = 1L;
+
+ private static final Log LOG = LogFactory.getLog(HadoopInputFormat.class);
+
+ private org.apache.hadoop.mapreduce.InputFormat<K, V> mapreduceInputFormat;
+ private Class<K> keyClass;
+ private Class<V> valueClass;
+ private org.apache.hadoop.conf.Configuration configuration;
+
+ public transient RecordReader<K, V> recordReader;
+ private boolean fetched = false;
+ private boolean hasNext;
+
+ public HadoopInputFormat() {
+ super();
+ }
+
+ public HadoopInputFormat(org.apache.hadoop.mapreduce.InputFormat<K,V> mapreduceInputFormat, Class<K> key, Class<V> value, Job job) {
+ super();
+ this.mapreduceInputFormat = mapreduceInputFormat;
+ this.keyClass = key;
+ this.valueClass = value;
+ this.configuration = job.getConfiguration();
+ HadoopUtils.mergeHadoopConf(configuration);
+ }
+
+ public void setConfiguration(org.apache.hadoop.conf.Configuration configuration) {
+ this.configuration = configuration;
+ }
+
+ public org.apache.hadoop.mapreduce.InputFormat<K,V> getHadoopInputFormat() {
+ return this.mapreduceInputFormat;
+ }
+
+ public void setHadoopInputFormat(org.apache.hadoop.mapreduce.InputFormat<K,V> mapreduceInputFormat) {
+ this.mapreduceInputFormat = mapreduceInputFormat;
+ }
+
+ public org.apache.hadoop.conf.Configuration getConfiguration() {
+ return this.configuration;
+ }
+
+ // --------------------------------------------------------------------------------------------
+ // InputFormat
+ // --------------------------------------------------------------------------------------------
+
+ @Override
+ public void configure(Configuration parameters) {
+ // nothing to do
+ }
+
+ @Override
+ public BaseStatistics getStatistics(BaseStatistics cachedStats) throws IOException {
+ // only gather base statistics for FileInputFormats
+ if(!(mapreduceInputFormat instanceof FileInputFormat)) {
+ return null;
+ }
+
+ JobContext jobContext = null;
+ try {
+ jobContext = HadoopUtils.instantiateJobContext(configuration, null);
+ }
+ catch (Exception e) {
+ throw new RuntimeException(e);
+ }
+
+ final FileBaseStatistics cachedFileStats = (cachedStats != null && cachedStats instanceof FileBaseStatistics) ?
+ (FileBaseStatistics) cachedStats : null;
+
+ try {
+ final org.apache.hadoop.fs.Path[] paths = FileInputFormat.getInputPaths(jobContext);
+
+ return getFileStats(cachedFileStats, paths, new ArrayList<FileStatus>(1));
+ } catch (IOException ioex) {
+ if (LOG.isWarnEnabled()) {
+ LOG.warn("Could not determine statistics due to an io error: "
+ + ioex.getMessage());
+ }
+ }
+ catch (Throwable t) {
+ if (LOG.isErrorEnabled()) {
--- End diff --
copy pasted typo
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at
[hidden email] or file a JIRA ticket
with INFRA.
---