apex-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From amberarrow <...@git.apache.org>
Subject [GitHub] apex-malhar pull request #326: APEXMALHAR-2116 Added FS record reader operat...
Date Tue, 21 Jun 2016 23:27:33 GMT
Github user amberarrow commented on a diff in the pull request:

    https://github.com/apache/apex-malhar/pull/326#discussion_r67971098
  
    --- Diff: library/src/main/java/org/apache/apex/malhar/lib/fs/FSRecordReaderModule.java
---
    @@ -0,0 +1,317 @@
    +/**
    + * 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.apex.malhar.lib.fs;
    +
    +import javax.validation.constraints.Min;
    +
    +import javax.validation.constraints.NotNull;
    +import javax.validation.constraints.Size;
    +
    +import org.apache.apex.malhar.lib.fs.FSRecordReader.RECORD_READER_MODE;
    +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.partitioner.StatelessPartitioner;
    +import com.datatorrent.lib.codec.KryoSerializableStreamCodec;
    +import com.datatorrent.lib.io.block.BlockMetadata;
    +import com.datatorrent.lib.io.block.FSSliceReader;
    +import com.datatorrent.lib.io.fs.FileSplitterInput;
    +
    +/**
    + * This module is used for reading records/tuples from FileSystem.
    + * Records can be read in parallel using multiple partitions of record reader operator.
    + * (Ordering is not guaranteed when records are read in parallel)
    + *
    + * Input directory is scanned at specified interval to poll for new data.
    + * 
    + * The module reads data in parallel, following parameters can be configured<br/>
    + * 1. files: list of file(s)/directories to read<br/>
    + * 2. filePatternRegularExp: Files names matching given regex will be read<br/>
    + * 3. scanIntervalMillis: interval between two scans to discover new files in input directory<br/>
    + * 4. recursive: if scan recursively input directories<br/>
    + * 5. blockSize: block size used to read input blocks of file<br/>
    + * 6. readersCount: count of readers to read input file<br/>
    + * 7. sequencialFileRead: If emit file blocks in sequence?<br/>
    + * 8. blocksThreshold: number of blocks emitted per window
    + */
    +@org.apache.hadoop.classification.InterfaceStability.Evolving
    +public class FSRecordReaderModule implements Module
    +{
    +  @NotNull
    +  @Size(min = 1)
    +  private String files;
    +  private String filePatternRegularExp;
    +  @Min(0)
    +  private long scanIntervalMillis;
    +  private boolean recursive = true;
    +  private boolean sequencialFileRead = false;
    +  private int readersCount;
    +  @Min(1)
    +  protected int blocksThreshold;
    +  
    +  public final transient ProxyOutputPort<byte[]> records = new ProxyOutputPort<byte[]>();
    +  
    +  /**
    +   * Criteria for record split
    +   */
    +  private RECORD_READER_MODE mode;
    +  
    +  /**
    +   * Length for fixed width record
    +   */
    +  private int recordLength;
    +  
    +  public FileSplitterInput createFileSplitter()
    +  {
    +    return new FileSplitterInput();
    +  }
    +  
    +  public FSRecordReader createBlockReader()
    +  {
    +    FSRecordReader recordReader = new FSRecordReader();
    +    recordReader.setMode(mode);
    +    recordReader.setRecordLength(recordLength);
    +    
    +    return recordReader;
    +  }
    +  
    +  @Override
    +  public void populateDAG(DAG dag, Configuration configuration)
    +  {
    +    FileSplitterInput fileSplitter = dag.addOperator("FileSplitter", createFileSplitter());
    +    FSRecordReader recordReader = dag.addOperator("BlockReader", createBlockReader());
    +
    +    dag.addStream("BlockMetadata", fileSplitter.blocksMetadataOutput, recordReader.blocksMetadataInput);
    +
    +    if (sequencialFileRead) {
    +      dag.setInputPortAttribute(recordReader.blocksMetadataInput, Context.PortContext.STREAM_CODEC,
    +          new SequentialFileBlockMetadataCodec());
    +    }
    +
    +    FileSplitterInput.TimeBasedDirectoryScanner fileScanner = fileSplitter.getScanner();
    +    fileScanner.setFiles(files);
    +    if (scanIntervalMillis != 0) {
    +      fileScanner.setScanIntervalMillis(scanIntervalMillis);
    +    }
    +    fileScanner.setRecursive(recursive);
    +    if (filePatternRegularExp != null) {
    +      fileSplitter.getScanner().setFilePatternRegularExp(filePatternRegularExp);
    +    }
    +
    +    recordReader.setBasePath(files);
    +    if (readersCount != 0) {
    +      dag.setAttribute(recordReader, Context.OperatorContext.PARTITIONER,
    +          new StatelessPartitioner<FSSliceReader>(readersCount));
    +    }
    +    fileSplitter.setBlocksThreshold(blocksThreshold);
    +    records.set(recordReader.records);
    +  }
    +
    +  /**
    +   * 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
    +   */
    +  public void setFiles(String files)
    +  {
    +    this.files = files;
    +  }
    +
    +  /**
    +   * Gets the files to be scanned.
    +   *
    +   * @return files to be scanned.
    +   */
    +  public String getFiles()
    +  {
    +    return files;
    +  }
    +
    +  /**
    +   * Gets the regular expression for file names to split
    +   *
    +   * @return regular expression
    +   */
    +  public String getFilePatternRegularExp()
    +  {
    +    return filePatternRegularExp;
    +  }
    +
    +  /**
    +   * Only files with names matching the given java regular expression are split
    +   *
    +   * @param filePatternRegexp
    +   *          regular expression
    +   */
    +  public void setFilePatternRegularExp(String filePatternRegexp)
    +  {
    +    this.filePatternRegularExp = filePatternRegexp;
    +  }
    +
    +  /**
    +   * Gets scan interval in milliseconds, interval between two scans to discover new files
in input directory
    +   *
    +   * @return scanInterval milliseconds
    +   */
    +  public long getScanIntervalMillis()
    +  {
    +    return scanIntervalMillis;
    +  }
    +
    +  /**
    +   * Sets scan interval in milliseconds, interval between two scans to discover new files
in input directory
    +   *
    +   * @param scanIntervalMillis
    +   */
    +  public void setScanIntervalMillis(long scanIntervalMillis)
    +  {
    +    this.scanIntervalMillis = scanIntervalMillis;
    +  }
    +
    +  /**
    +   * Get is scan recursive
    +   *
    +   * @return isRecursive
    +   */
    +  public boolean isRecursive()
    +  {
    +    return recursive;
    +  }
    +
    +  /**
    +   * set is scan recursive
    +   *
    +   * @param recursive
    +   */
    +  public void setRecursive(boolean recursive)
    +  {
    +    this.recursive = recursive;
    +  }
    +
    +  /**
    +   * Gets readers count
    +   * @return readersCount
    +   */
    +  public int getReadersCount()
    +  {
    +    return readersCount;
    +  }
    +
    +  /**
    +   * Static count of readers to read input file
    +   * @param readersCount
    +   */
    +  public void setReadersCount(int readersCount)
    +  {
    +    this.readersCount = readersCount;
    +  }
    +
    +  /**
    +   * Gets is sequencial file read
    --- End diff --
    
    sequencial => sequential (multiple places)


---
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 infrastructure@apache.org or file a JIRA ticket
with INFRA.
---

Mime
View raw message