com.geneix.bottle.WordRecordReader.java Source code

Java tutorial

Introduction

Here is the source code for com.geneix.bottle.WordRecordReader.java

Source

/**
 * 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.geneix.bottle;

import org.apache.commons.logging.Log;
import org.apache.commons.logging.LogFactory;
import org.apache.hadoop.classification.InterfaceAudience;
import org.apache.hadoop.classification.InterfaceStability;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.FSDataInputStream;
import org.apache.hadoop.fs.FileSystem;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.fs.Seekable;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
import org.apache.hadoop.io.compress.CodecPool;
import org.apache.hadoop.io.compress.CompressionCodec;
import org.apache.hadoop.io.compress.CompressionCodecFactory;
import org.apache.hadoop.io.compress.Decompressor;
import org.apache.hadoop.mapreduce.InputSplit;
import org.apache.hadoop.mapreduce.RecordReader;
import org.apache.hadoop.mapreduce.TaskAttemptContext;
import org.apache.hadoop.mapreduce.lib.input.FileSplit;
import org.apache.hadoop.mapreduce.lib.input.LineRecordReader;

import java.io.IOException;

/**
 * Treats keys as offset in file and value as line.
 */
@InterfaceAudience.LimitedPrivate({ "MapReduce", "Pig" })
@InterfaceStability.Evolving
public class WordRecordReader extends RecordReader<LongWritable, Word> {
    public static final String MAX_WORD_LENGTH = "mapreduce.input.wordrecordreader.word.maxlength";
    private static final Log LOG = LogFactory.getLog(WordRecordReader.class);
    private final WordParser wordParser = new FakeWordParser();
    private long start;
    private long pos;
    private long end;
    private WordReader in;
    private FSDataInputStream fileIn;
    private Seekable filePosition;
    private int maxWordLength;
    private LongWritable key;
    private Text value;
    private Decompressor decompressor;
    private boolean isCompressedInput = false;

    public WordRecordReader() {
    }

    public void initialize(InputSplit genericSplit, TaskAttemptContext context) throws IOException {
        if (LOG.isInfoEnabled()) {
            LOG.info("Initializing WordRecordReader");
        }
        FileSplit split = (FileSplit) genericSplit;
        Configuration job = context.getConfiguration();
        this.maxWordLength = job.getInt(MAX_WORD_LENGTH, Integer.MAX_VALUE);
        start = split.getStart();
        end = start + split.getLength();
        final Path file = split.getPath();

        // open the file and seek to the start of the split
        final FileSystem fs = file.getFileSystem(job);
        fileIn = fs.open(file);

        CompressionCodec codec = new CompressionCodecFactory(job).getCodec(file);
        if (null != codec) {
            throw new IOException("Cannot handle compressed files right now");
        } else {
            fileIn.seek(start);
            in = new WordReader(fileIn, job);
            filePosition = fileIn;
        }
        // If this is not the first split, we always throw away first record
        // because we always (except the last split) read one extra line in
        // next() method.
        if (start != 0) {
            start += in.readWord(new Text(), 0, maxBytesToConsume(start));
        }
        this.pos = start;
    }

    private int maxBytesToConsume(long pos) {
        return isCompressedInput ? Integer.MAX_VALUE
                : (int) Math.max(Math.min(Integer.MAX_VALUE, end - pos), maxWordLength);
    }

    private long getFilePosition() throws IOException {
        long retVal;
        if (isCompressedInput && null != filePosition) {
            retVal = filePosition.getPos();
        } else {
            retVal = pos;
        }
        return retVal;
    }

    //TODO: I'm not sure this works exactly correctly with the code point reader
    private int skipUtfByteOrderMark() throws IOException {
        // Strip BOM(Byte Order Mark)
        // Text only support UTF-8, we only need to check UTF-8 BOM
        // (0xEF,0xBB,0xBF) at the start of the text stream.
        int newMaxLineLength = (int) Math.min(3L + (long) maxWordLength, Integer.MAX_VALUE);
        int newSize = in.readWord(value, newMaxLineLength, maxBytesToConsume(pos));
        // Even we read 3 extra bytes for the first line,
        // we won't alter existing behavior (no backwards incompat issue).
        // Because the newSize is less than maxLineLength and
        // the number of bytes copied to Text is always no more than newSize.
        // If the return size from readLine is not less than maxLineLength,
        // we will discard the current line and read the next line.
        pos += newSize;
        int textLength = value.getLength();
        byte[] textBytes = value.getBytes();
        if ((textLength >= 3) && (textBytes[0] == (byte) 0xEF) && (textBytes[1] == (byte) 0xBB)
                && (textBytes[2] == (byte) 0xBF)) {
            // find UTF-8 BOM, strip it.
            LOG.info("Found UTF-8 BOM and skipped it");
            textLength -= 3;
            newSize -= 3;
            if (textLength > 0) {
                // It may work to use the same buffer and not do the copyBytes
                textBytes = value.copyBytes();
                value.set(textBytes, 3, textLength);
            } else {
                value.clear();
            }
        }
        return newSize;
    }

    public boolean nextKeyValue() throws IOException {
        if (LOG.isInfoEnabled()) {
            LOG.info("Getting next kvp");
            LOG.info(String.format("POS:%s; END:%s; MAX_LENGTH:%s;", pos, end, maxWordLength));
        }
        if (key == null) {
            key = new LongWritable();
        }
        key.set(pos);
        if (value == null) {
            value = new Text();
        }
        int newSize = 0;
        // We always read one extra line, which lies outside the upper
        // split limit i.e. (end - 1)
        while (getFilePosition() <= end) { //|| in.needAdditionalRecordAfterSplit()) {
            if (pos == 0) {
                newSize = skipUtfByteOrderMark();
            } else {
                newSize = in.readWord(value, maxWordLength, maxBytesToConsume(pos));
                pos += newSize;
            }

            if ((newSize == 0) || (newSize < maxWordLength)) {
                break;
            }

            // line too long. try again
            if (LOG.isInfoEnabled()) {
                LOG.info("Skipped word of size " + newSize + " at pos " + (pos - newSize));
            }
        }
        if (newSize == 0) {
            if (LOG.isInfoEnabled()) {
                LOG.info("Empty word?");
            }
            key = null;
            value = null;
            return false;
        } else {
            return true;
        }
    }

    @Override
    public LongWritable getCurrentKey() {
        return key;
    }

    @Override
    public Word getCurrentValue() {
        return Word.fromText(value, wordParser);
    }

    /**
     * Get the progress within the split
     */
    public float getProgress() throws IOException {
        if (start == end) {
            return 0.0f;
        } else {
            return Math.min(1.0f, (getFilePosition() - start) / (float) (end - start));
        }
    }

    public synchronized void close() throws IOException {
        try {
            if (in != null) {
                in.close();
            }
        } finally {
            if (decompressor != null) {
                CodecPool.returnDecompressor(decompressor);
            }
        }
    }
}