HtmlInputFormat.java Source code

Introduction

Here is the source code for HtmlInputFormat.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.
 */

import java.io.IOException;
import java.nio.charset.StandardCharsets;

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.io.DataOutputBuffer;
import org.apache.hadoop.io.LongWritable;
import org.apache.hadoop.io.Text;
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.TextInputFormat;

public class HtmlInputFormat extends TextInputFormat {

    public static final String START_TAG_KEY = "htmlinput.start";
    public static final String END_TAG_KEY = "htmlinput.end";

    @Override
    public RecordReader<LongWritable, Text> createRecordReader(InputSplit split, TaskAttemptContext context) {
        try {
            return new HtmlRecordReader((FileSplit) split, context.getConfiguration());
        } catch (IOException ioe) {
            return null;
        }
    }

    /**
     * HTMLRecordReader class to read through a given html document to output html blocks as records as specified
     * by the start tag and end tag
     *
     */
    public static class HtmlRecordReader extends RecordReader<LongWritable, Text> {

        private final byte[] startTag;
        private final byte[] endTag;
        private final long start;
        private final long end;
        private final FSDataInputStream fsin;
        private final DataOutputBuffer buffer = new DataOutputBuffer();
        private LongWritable currentKey;
        private Text currentValue;

        public HtmlRecordReader(FileSplit split, Configuration conf) throws IOException {
            startTag = conf.get(START_TAG_KEY).getBytes(StandardCharsets.UTF_8);
            endTag = conf.get(END_TAG_KEY).getBytes(StandardCharsets.UTF_8);

            // open the file and seek to the start of the split
            start = split.getStart();
            end = start + split.getLength();
            Path file = split.getPath();
            FileSystem fs = file.getFileSystem(conf);
            fsin = fs.open(split.getPath());
            fsin.seek(start);
        }

        private boolean next(LongWritable key, Text value) throws IOException {
            if (fsin.getPos() < end && readUntilMatch(startTag, false)) {
                try {
                    buffer.write(startTag);
                    if (readUntilMatch(endTag, true)) {
                        key.set(fsin.getPos());
                        value.set(buffer.getData(), 0, buffer.getLength());
                        return true;
                    }
                } finally {
                    buffer.reset();
                }
            }
            return false;
        }

        @Override
        public void close() throws IOException {
            fsin.close();
        }

        @Override
        public float getProgress() throws IOException {
            return (fsin.getPos() - start) / (float) (end - start);
        }

        private boolean readUntilMatch(byte[] match, boolean withinBlock) throws IOException {
            int i = 0;
            while (true) {
                int b = fsin.read();
                // end of file:
                if (b == -1) {
                    return false;
                }
                // save to buffer:
                if (withinBlock) {
                    buffer.write(b);
                }

                // check if we're matching:
                if (b == match[i]) {
                    i++;
                    if (i >= match.length) {
                        return true;
                    }
                } else {
                    i = 0;
                }
                // see if we've passed the stop point:
                if (!withinBlock && i == 0 && fsin.getPos() >= end) {
                    return false;
                }
            }
        }

        @Override
        public LongWritable getCurrentKey() throws IOException, InterruptedException {
            return currentKey;
        }

        @Override
        public Text getCurrentValue() throws IOException, InterruptedException {
            return currentValue;
        }

        @Override
        public void initialize(InputSplit split, TaskAttemptContext context)
                throws IOException, InterruptedException {
        }

        @Override
        public boolean nextKeyValue() throws IOException, InterruptedException {
            currentKey = new LongWritable();
            currentValue = new Text();
            return next(currentKey, currentValue);
        }
    }
}