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-tp613p622.html
Github user rmetzger commented on a diff in the pull request:
https://github.com/apache/incubator-flink/pull/32#discussion_r14036963
--- Diff: stratosphere-addons/hadoop-compatibility/src/main/java/eu/stratosphere/hadoopcompatibility/mapred/HadoopInputFormat.java ---
@@ -0,0 +1,287 @@
+/***********************************************************************************************************************
+ * 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.mapred;
+
+import java.io.IOException;
+import java.io.ObjectInputStream;
+import java.io.ObjectOutputStream;
+import java.util.ArrayList;
+
+import org.apache.commons.logging.Log;
+import org.apache.commons.logging.LogFactory;
+import org.apache.hadoop.io.Writable;
+import org.apache.hadoop.mapred.FileInputFormat;
+import org.apache.hadoop.mapred.JobConf;
+import org.apache.hadoop.mapred.RecordReader;
+import org.apache.hadoop.util.ReflectionUtils;
+
+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.mapred.utils.HadoopUtils;
+import eu.stratosphere.hadoopcompatibility.mapred.wrapper.HadoopDummyReporter;
+import eu.stratosphere.hadoopcompatibility.mapred.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.mapred.InputFormat<K, V> mapredInputFormat;
+ private Class<K> keyClass;
+ private Class<V> valueClass;
+ private JobConf jobConf;
+
+ public transient K key;
+ public transient V value;
+
+ public RecordReader<K, V> recordReader;
+ private transient boolean fetched = false;
+ private transient boolean hasNext;
+
+ public HadoopInputFormat() {
+ super();
+ }
+
+ public HadoopInputFormat(org.apache.hadoop.mapred.InputFormat<K,V> mapredInputFormat, Class<K> key, Class<V> value, JobConf job) {
+ super();
+ this.mapredInputFormat = mapredInputFormat;
+ this.keyClass = key;
+ this.valueClass = value;
+ HadoopUtils.mergeHadoopConf(job);
+ this.jobConf = job;
+ }
+
+ public void setJobConf(JobConf job) {
+ this.jobConf = job;
+ }
+
+ public org.apache.hadoop.mapred.InputFormat<K,V> getHadoopInputFormat() {
+ return mapredInputFormat;
+ }
+
+ public void setHadoopInputFormat(org.apache.hadoop.mapred.InputFormat<K,V> mapredInputFormat) {
+ this.mapredInputFormat = mapredInputFormat;
+ }
+
+ public JobConf getJobConf() {
+ return jobConf;
+ }
+
+ // --------------------------------------------------------------------------------------------
+ // 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(!(mapredInputFormat instanceof FileInputFormat)) {
+ return null;
+ }
+
+ final FileBaseStatistics cachedFileStats = (cachedStats != null && cachedStats instanceof FileBaseStatistics) ?
+ (FileBaseStatistics) cachedStats : null;
+
+ try {
+ final org.apache.hadoop.fs.Path[] paths = FileInputFormat.getInputPaths(this.jobConf);
+
+ 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()) {
+ LOG.error("Unexpected problen while getting the file statistics: "
--- End diff --
typo "problen".
Also, the `catch` statement probably needs to move up to the closing bracket.
---
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.
---