Github user chinmaykolhatkar commented on a diff in the pull request:
https://github.com/apache/incubator-apex-malhar/pull/207#discussion_r55640050
--- Diff:
library/src/main/java/com/datatorrent/lib/io/fs/HDFSInputModule.java ---
@@ -0,0 +1,236 @@
+/**
+ * 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 com.datatorrent.lib.io.fs;
+
+import javax.validation.constraints.Min;
+import javax.validation.constraints.NotNull;
+import javax.validation.constraints.Size;
+
+import org.apache.commons.lang.mutable.MutableLong;
+import org.apache.hadoop.conf.Configuration;
+
+import com.datatorrent.api.Context;
+import com.datatorrent.api.DAG;
+import com.datatorrent.api.Module;
+import com.datatorrent.common.metric.MetricsAggregator;
+import com.datatorrent.common.metric.SingleMetricAggregator;
+import com.datatorrent.common.metric.sum.LongSumAggregator;
+import com.datatorrent.common.partitioner.StatelessPartitioner;
+import com.datatorrent.lib.counters.BasicCounters;
+import com.datatorrent.lib.io.block.AbstractBlockReader.ReaderRecord;
+import com.datatorrent.lib.io.block.BlockMetadata.FileBlockMetadata;
+import com.datatorrent.lib.io.block.HDFSBlockReader;
+import com.datatorrent.lib.io.fs.AbstractFileSplitter.FileMetadata;
+import com.datatorrent.lib.io.fs.HDFSFileSplitter.HDFSScanner;
+import com.datatorrent.netlet.util.Slice;
+
+/**
+ * HDFSInputModule is used to read files from HDFS. <br/>
+ * Module emits FileMetadata, BlockMetadata and the block bytes.
+ */
+public class HDFSInputModule implements Module
+{
+
+ @NotNull
+ @Size(min = 1)
+ private String files;
+ private String filePatternRegularExp;
+ @Min(0)
+ private long scanIntervalMillis;
+ private boolean recursive = true;
+ private long blockSize;
+ private boolean sequencialFileRead = false;
+ private int readersCount;
+
+ public final transient ProxyOutputPort<FileMetadata> filesMetadataOutput
= new ProxyOutputPort();
+ public final transient ProxyOutputPort<FileBlockMetadata>
blocksMetadataOutput = new ProxyOutputPort();
+ public final transient ProxyOutputPort<ReaderRecord<Slice>> messages =
new ProxyOutputPort();
+
+ @Override
+ public void populateDAG(DAG dag, Configuration conf)
+ {
+ HDFSFileSplitter fileSplitter = dag.addOperator("FileSplitter", new
HDFSFileSplitter());
+ HDFSBlockReader blockReader = dag.addOperator("BlockReader", new
HDFSBlockReader());
+
+ dag.addStream("BlockMetadata", fileSplitter.blocksMetadataOutput,
blockReader.blocksMetadataInput);
+
+ filesMetadataOutput.set(fileSplitter.filesMetadataOutput);
+ blocksMetadataOutput.set(blockReader.blocksMetadataOutput);
+ messages.set(blockReader.messages);
+
+ fileSplitter.setSequencialFileRead(sequencialFileRead);
+ if (blockSize != 0) {
+ fileSplitter.setBlockSize(blockSize);
+ }
+
+ HDFSScanner fileScanner = (HDFSScanner)fileSplitter.getScanner();
+ fileScanner.setFiles(files);
+ if (scanIntervalMillis != 0) {
+ fileScanner.setScanIntervalMillis(scanIntervalMillis);
+ }
+ fileScanner.setRecursive(recursive);
+ if (filePatternRegularExp != null) {
+
fileSplitter.getScanner().setFilePatternRegularExp(filePatternRegularExp);
+ }
+
+ blockReader.setUri(files);
+ if (readersCount != 0) {
+ dag.setAttribute(blockReader, Context.OperatorContext.PARTITIONER,
new StatelessPartitioner<HDFSBlockReader>(readersCount));
+ }
+
+ MetricsAggregator blockReaderMetrics = new MetricsAggregator();
+ blockReaderMetrics.addAggregators("bytesReadPerSec", new
SingleMetricAggregator[] {new LongSumAggregator()});
+ dag.setAttribute(blockReader,
Context.OperatorContext.METRICS_AGGREGATOR, blockReaderMetrics);
+ dag.setAttribute(blockReader,
Context.OperatorContext.COUNTERS_AGGREGATOR, new
BasicCounters.LongAggregator<MutableLong>());
+ }
+
+ /**
+ * A comma separated list of directories to scan. If the path is not
fully qualified the default file system is used.
+ * A fully qualified path can be provided to scan directories in other
filesystems.
+ *
+ * @param files
+ * files
--- End diff --
Can we please have javadoc comments in proper format?
---
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 [email protected] or file a JIRA ticket
with INFRA.
---
