com.asp.tranlog.ImportTsv.java Source code

Java tutorial

Introduction

Here is the source code for com.asp.tranlog.ImportTsv.java

Source

/**
 * Copyright 2010 The Apache Software Foundation
 *
 * 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.asp.tranlog;

import java.io.IOException;
import java.util.ArrayList;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HConstants;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Put;
import org.apache.hadoop.hbase.io.ImmutableBytesWritable;
import org.apache.hadoop.hbase.mapreduce.HFileOutputFormat;
import org.apache.hadoop.hbase.mapreduce.PutSortReducer;
import org.apache.hadoop.hbase.mapreduce.TableMapReduceUtil;
import org.apache.hadoop.hbase.util.Base64;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.hadoop.mapreduce.Job;
import org.apache.hadoop.mapreduce.lib.input.FileInputFormat;
import org.apache.hadoop.mapreduce.lib.input.TextInputFormat;
import org.apache.hadoop.mapreduce.lib.output.FileOutputFormat;
import org.apache.hadoop.util.GenericOptionsParser;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import com.google.common.base.Preconditions;
import com.google.common.base.Splitter;
import com.google.common.collect.Lists;
import com.hadoop.mapreduce.LzoTextInputFormat;

/**
 * Tool to import data from a TSV file.
 * 
 * This tool is rather simplistic - it doesn't do any quoting or escaping, but
 * is useful for many data loads.
 * 
 * @see ImportTsv#usage(String)
 */
public class ImportTsv {

    final static Logger LOG = LoggerFactory.getLogger(ImportTsv.class);
    final static String PRE = ">>>>>>>>>>>>>>>";

    final static String NAME = "importtsv";

    final static String MAPPER_CONF_KEY = "importtsv.mapper.class";
    final static String SKIP_LINES_CONF_KEY = "importtsv.skip.bad.lines";
    final static String BULK_OUTPUT_CONF_KEY = "importtsv.bulk.output";
    final static String COLUMNS_CONF_KEY = "importtsv.columns";
    final static String KEYCOLUMNS_CONF_KEY = "importtsv.key.columns";
    final static String SEPARATOR_CONF_KEY = "importtsv.separator";
    final static String TIMESTAMP_CONF_KEY = "importtsv.timestamp";
    final static String INPUT_LZO_KEY = "importtsv.input.codec";
    final static String DEFAULT_SEPARATOR = "\t";
    final static String SEPARATOR_CONF_ROWKEY = "importtsv.separator.rowkey";
    final static Class DEFAULT_MAPPER = TsvImporterMapper.class;
    final static String CHARSET_CONF_KEY = "importtsv.charset.rowkey";

    public final static byte COL_TYPE_STRING = 0;
    public final static byte COL_TYPE_INT = 1;
    public final static byte COL_TYPE_LONG = 2;
    public final static byte COL_TYPE_DOUBLE = 3;
    public final static byte COL_TYPE_DATETIME = 4;// if the source type is
    // datetime, then will parse
    // it to long

    static class TsvParser {
        /**
         * Column families and qualifiers mapped to the TSV columns
         */
        private final byte[][] families;
        private final byte[][] qualifiers;
        private final byte[] colType; // 0- String, 1- int, 2- long, 3- double,
        // 4- timestamp
        private int[] keyColIndex = null;// Save the columns that will make up
        // the row key.
        private int[] keyColLen = null;// Save the length of ever column that
        // will compose the row key.

        private final byte separatorByte;

        // private int rowKeyColumnIndex;

        public static String ROWKEY_COLUMN_SPEC = "HBASE_ROW_KEY";

        /**
         * @param columnsSpecification
         *            the list of columns to parser out, comma separated. The
         *            row key should be the special token
         *            TsvParser.ROWKEY_COLUMN_SPEC
         */
        public TsvParser(String columnsSpecification, String[] keyColumns, String separatorStr) {
            // Configure separator
            byte[] separator = Bytes.toBytes(separatorStr);
            Preconditions.checkArgument(separator.length == 1, "TsvParser only supports single-byte separators");
            separatorByte = separator[0];

            // Configure columns
            ArrayList<String> columnStrings = Lists
                    .newArrayList(Splitter.on(',').trimResults().split(columnsSpecification));

            families = new byte[columnStrings.size()][];
            qualifiers = new byte[columnStrings.size()][];
            colType = new byte[columnStrings.size()];

            for (int i = 0; i < columnStrings.size(); i++) {
                String str = columnStrings.get(i);
                // if (ROWKEY_COLUMN_SPEC.equals(str)) {
                // rowKeyColumnIndex = i;
                // continue;
                // }
                String[] parts = str.split(":", 3);
                if (parts.length == 1) {
                    families[i] = str.getBytes();
                    qualifiers[i] = HConstants.EMPTY_BYTE_ARRAY;
                    colType[i] = COL_TYPE_STRING;
                } else {
                    families[i] = parts[0].getBytes();
                    qualifiers[i] = parts[1].getBytes();
                    if (parts.length > 2) {
                        colType[i] = parseColType(parts[2]);
                    } else
                        colType[i] = COL_TYPE_STRING;
                }
                // System.out.println(str + ", idex " + i + ", coltpe: " +
                // colType[i]);
            }
            if (keyColumns != null) {
                keyColIndex = new int[keyColumns.length];
                keyColLen = new int[keyColumns.length];
                for (int i = 0; i < keyColumns.length; i++) {
                    String[] strKdef = keyColumns[i].split(":", 2);
                    keyColIndex[i] = Integer.parseInt(strKdef[0]);
                    if (keyColIndex[i] >= qualifiers.length)
                        keyColIndex[i] = 0;
                    if (strKdef.length > 1)
                        keyColLen[i] = Integer.parseInt(strKdef[1]);
                    else
                        keyColLen[i] = 0;// 0 means not specify the length
                }
            }
        }

        public byte parseColType(String strCT) {
            if (strCT.equalsIgnoreCase("int"))
                return COL_TYPE_INT;
            else if (strCT.equalsIgnoreCase("string"))
                return COL_TYPE_STRING;
            else if (strCT.equalsIgnoreCase("long"))
                return COL_TYPE_LONG;
            else if (strCT.equalsIgnoreCase("datetime"))
                return COL_TYPE_DATETIME;
            else if (strCT.equalsIgnoreCase("double"))
                return COL_TYPE_DOUBLE;
            else
                return COL_TYPE_STRING;
        }

        public int[] getRowKeyColumnIndex() {
            return keyColIndex;
        }

        public int[] getRowKeyColumnLen() {
            return keyColLen;
        }

        public byte[] getFamily(int idx) {
            return families[idx];
        }

        public byte[] getQualifier(int idx) {
            return qualifiers[idx];
        }

        public byte[] getColType() {
            return colType;
        }

        public ParsedLine parse(byte[] lineBytes, int length) throws BadTsvLineException {
            // Enumerate separator offsets
            ArrayList<Integer> tabOffsets = new ArrayList<Integer>(families.length);
            for (int i = 0; i < length; i++) {
                if (lineBytes[i] == separatorByte) {
                    tabOffsets.add(i);
                }
            }
            if (tabOffsets.isEmpty()) {
                throw new BadTsvLineException("No delimiter");
            }

            tabOffsets.add(length);

            if (tabOffsets.size() > families.length) {
                throw new BadTsvLineException("Excessive columns");
            } /*
              * else if (tabOffsets.size() <= getRowKeyColumnIndex()) { throw new
              * BadTsvLineException("No row key"); }
              */
            return new ParsedLine(tabOffsets, lineBytes);
        }

        class ParsedLine {
            private final ArrayList<Integer> tabOffsets;
            private byte[] lineBytes;

            ParsedLine(ArrayList<Integer> tabOffsets, byte[] lineBytes) {
                this.tabOffsets = tabOffsets;
                this.lineBytes = lineBytes;
            }

            public int getColumnOffset(int idx) {
                if (idx > 0)
                    return tabOffsets.get(idx - 1) + 1;
                else
                    return 0;
            }

            public int getColumnLength(int idx) {
                return tabOffsets.get(idx) - getColumnOffset(idx);
            }

            public int getColumnCount() {
                return tabOffsets.size();
            }

            public byte[] getLineBytes() {
                return lineBytes;
            }
        }

        public static class BadTsvLineException extends Exception {
            public BadTsvLineException(String err) {
                super(err);
            }

            private static final long serialVersionUID = 1L;
        }
    }

    /**
     * Sets up the actual job.
     * 
     * @param conf
     *            The current configuration.
     * @param args
     *            The command line parameters.
     * @return The newly created job.
     * @throws IOException
     *             When setting up the job fails.
     */
    public static Job createSubmittableJob(Configuration conf, String[] args)
            throws IOException, ClassNotFoundException {

        // Support non-XML supported characters
        // by re-encoding the passed separator as a Base64 string.
        String actualSeparator = conf.get(SEPARATOR_CONF_KEY);
        if (actualSeparator != null) {
            conf.set(SEPARATOR_CONF_KEY, new String(Base64.encodeBytes(actualSeparator.getBytes())));
        }

        // See if a non-default Mapper was set
        String mapperClassName = conf.get(MAPPER_CONF_KEY);
        Class mapperClass = mapperClassName != null ? Class.forName(mapperClassName) : DEFAULT_MAPPER;

        String tableName = args[0];
        Path inputDir = new Path(args[1]);
        Job job = new Job(conf, NAME + "_" + tableName);
        job.setJarByClass(mapperClass);
        FileInputFormat.setInputPaths(job, inputDir);

        String inputCodec = conf.get(INPUT_LZO_KEY);
        if (inputCodec == null) {
            FileInputFormat.setMaxInputSplitSize(job, 67108864l); // max split
            // size =
            // 64m
            job.setInputFormatClass(TextInputFormat.class);
        } else {
            if (inputCodec.equalsIgnoreCase("lzo"))
                job.setInputFormatClass(LzoTextInputFormat.class);
            else {
                usage("not supported compression codec!");
                System.exit(-1);
            }
        }

        job.setMapperClass(mapperClass);

        String hfileOutPath = conf.get(BULK_OUTPUT_CONF_KEY);
        if (hfileOutPath != null) {
            HTable table = new HTable(conf, tableName);
            job.setReducerClass(PutSortReducer.class);
            Path outputDir = new Path(hfileOutPath);
            FileOutputFormat.setOutputPath(job, outputDir);
            job.setMapOutputKeyClass(ImmutableBytesWritable.class);
            job.setMapOutputValueClass(Put.class);
            HFileOutputFormat.configureIncrementalLoad(job, table);
        } else {
            // No reducers. Just write straight to table. Call
            // initTableReducerJob
            // to set up the TableOutputFormat.
            TableMapReduceUtil.initTableReducerJob(tableName, null, job);
            job.setNumReduceTasks(0);
        }

        TableMapReduceUtil.addDependencyJars(job);
        TableMapReduceUtil.addDependencyJars(job.getConfiguration(), com.google.common.base.Function.class /*
                                                                                                           * Guava used by TsvParser
                                                                                                           */);
        return job;
    }

    /*
     * @param errorMsg Error message. Can be null.
     */
    private static void usage(final String errorMsg) {
        if (errorMsg != null && errorMsg.length() > 0) {
            System.err.println("ERROR: " + errorMsg);
        }
        String usage = "Usage: " + NAME
                + " -Dimporttsv.columns=a,b,c -Dimporttsv.key.columns=0,3 <tablename> <inputdir>\n" + "\n"
                + "Imports the given input directory of TSV data into the specified table.\n" + "\n"
                + "The column names of the TSV data must be specified using the -Dimporttsv.columns\n"
                + "option. This option takes the form of comma-separated column names, where each\n"
                + "column name is either a simple column family, or a columnfamily:qualifier. The special\n"
                + "column name HBASE_ROW_KEY is used to designate that this column should be used\n"
                + "as the row key for each imported record. You must specify exactly one column\n"
                + "to be the row key, and you must specify a column name for every column that exists in the\n"
                + "input data.\n" + "\n"
                + "By default importtsv will load data directly into HBase. To instead generate\n"
                + "HFiles of data to prepare for a bulk data load, pass the option:\n" + "  -D"
                + BULK_OUTPUT_CONF_KEY + "=/path/for/output\n"
                + "  Note: if you do not use this option, then the target table must already exist in HBase\n"
                + "\n" + "Other options that may be specified with -D include:\n" + "   -D" + SEPARATOR_CONF_ROWKEY
                + "=  - default:,hbase rowkey separator" + "  -D" + SKIP_LINES_CONF_KEY
                + "=false - fail if encountering an invalid line\n" + "  '-D" + SEPARATOR_CONF_KEY
                + "=|' - eg separate on pipes instead of tabs\n" + "  -D" + TIMESTAMP_CONF_KEY
                + "=currentTimeAsLong - use the specified timestamp for the import\n" + "  -D" + MAPPER_CONF_KEY
                + "=my.Mapper - A user-defined Mapper to use instead of " + DEFAULT_MAPPER.getName() + "\n" + "  -D"
                + CHARSET_CONF_KEY + "=charset of rowkey, gb18030 " + "\n";

        System.err.println(usage);
    }

    /**
     * Main entry point.
     * 
     * @param args
     *            The command line parameters.
     * @throws Exception
     *             When running the job fails.
     */
    public static void main(String[] args) throws Exception {
        System.out.println("==============================================");
        Configuration conf = HBaseConfiguration.create();

        LOG.error(PRE + "conf.toString() == " + conf.toString());

        String[] otherArgs = new GenericOptionsParser(conf, args).getRemainingArgs();
        if (otherArgs.length < 2) {
            usage("Wrong number of arguments: " + otherArgs.length);
            System.exit(-1);
        }

        String columns[] = conf.getStrings(COLUMNS_CONF_KEY);

        if (columns == null) {
            usage("No columns specified. Please specify with -D" + COLUMNS_CONF_KEY + "=...");
            System.exit(-1);
        }

        // Make sure one or more columns are specified
        if (columns.length < 2) {
            usage("One or more columns in addition to the row key are required");
            System.exit(-1);
        }
        columns = conf.getStrings(COLUMNS_CONF_KEY);
        if (columns == null) {
            usage("One or more key columns are required");
            System.exit(-1);
        }

        Job job = createSubmittableJob(conf, otherArgs);

        System.exit(job.waitForCompletion(true) ? 0 : 1);
    }

}