java - 如何对十六进制行键进行HBase范围扫描？

Question

当尝试在 HBase shell 上执行范围扫描时，以下内容在 HBase shell 中有效。

scan 'mytable', {STARTROW => "\x00\x00\x00\x00\x01\x8F\xF6\x83", ENDROW => "\x00\x00\x00\x00\x01\x8F\xF6\x8D"}

但是当尝试实现 Java 客户端来执行相同的操作时，它没有检索到结果。

Scan scan = new Scan(Bytes.ToBytes("\x00\x00\x00\x00\x01\x8F\xF6\x83"),Bytes.toBytes("\x00\x00\x00\x00\x01\x8F\xF6\x8D"); 
scan.setFilter(colFilter);
scan.setOtherStuff...

ResultScanner scanner = table.getScanner(scan);
for (Result result = scanner.next(); result != null; result = scanner.next()) {
    ....
}

我尝试转义“\”字符并传递开始和结束行键。但并没有达到预期效果。

我将输入数据作为命令行参数传递。

time java -jar $ARIADNE3D_CLI PCRangeSearchTxt -table_name $TABLE_NAME -m 4 -start_key "\x00\x00\x00\x00\x01\x8F\xF6\x8D" -end_key "\x00\x00\x00\x00\x01\x8F\xF6\x8D" -o $SCRATCH/txt-1.txt

PCRangeSearchTxt的Java实现如下

/*
 * To change this license header, choose License Headers in Project Properties.
 * To change this template file, choose Tools | Templates
 * and open the template in the editor.
 */
package umg.ariadne3d.core.query.pc;

import java.io.*;
import org.apache.commons.cli.CommandLine;
import org.apache.commons.cli.CommandLineParser;
import org.apache.commons.cli.HelpFormatter;
import org.apache.commons.cli.Option;
import org.apache.commons.cli.Options;
import org.apache.commons.cli.PosixParser;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.*;
import org.apache.hadoop.hbase.util.Bytes;
import org.apache.log4j.Level;
import org.apache.log4j.Logger;
import umg.ariadne3d.core.common.Constants;
import umg.core.common.Executable;

/**
 * Point cloud range search.
 * @author VVo
 */
public class PCRangeSearchTxt implements Executable {

    static Logger LOGGER = Logger.getLogger(PCRangeSearchTxt.class);
    public static final String NAME = "PCRANGESEARCHTXT"; //PCRangeSearchTxt

    public static void main(String[] args) {
        args = new String[]{
               // "-t", "d15-tiny-m4",
               // "-m", "4",
               // "-index", "/Users/vu/scratch/ariadne3d/pointcloud/meta/hilbert.json",
               // "-query", "/Users/vu/scratch/ariadne3d/query/q0.json",
               // "-las_meta", "/Users/vu/scratch/ariadne3d/pointcloud/meta/d15-meta.json",
               // "-o", "/Users/vu/tmp/a.las"
        };

        Executable prog = new PCRangeSearchTxt();
        int err = prog.run(args);
        System.exit(err);
    }

    @Override
    public int run(String[] args) {
        CommandLine cmd = parseArgs(args);
        String tableName = cmd.getOptionValue("t");

          String start_key = cmd.getOptionValue("start_key");
          String end_key = cmd.getOptionValue("end_key");
          final String FILENAME = cmd.getOptionValue("o");

        int modelNo = Integer.parseInt(cmd.getOptionValue("m"));

        try{
            File file = new File(FILENAME);
            // if file doesnt exists, then create it
            if (!file.exists()) {
                file.createNewFile();
            }
        }catch (IOException e) {

            e.printStackTrace();

        }

        Configuration conf = HBaseConfiguration.create();

        String[] connectionParams = null;
        if (cmd.hasOption("conn")) {
            connectionParams = cmd.getOptionValues("conn");
        }

        if (connectionParams != null) {
            conf.set(Constants.HBASE_CONFIGURATION_ZOOKEEPER_QUORUM, connectionParams[0]);
            LOGGER.debug(String.format("Set quorum string %s", conf.get(Constants.HBASE_CONFIGURATION_ZOOKEEPER_QUORUM)));
            conf.setInt(Constants.HBASE_CONFIGURATION_ZOOKEEPER_CLIENTPORT, Integer.parseInt(connectionParams[1]));
            LOGGER.debug(String.format("Set port %d", conf.getInt(Constants.HBASE_CONFIGURATION_ZOOKEEPER_CLIENTPORT, 0)));
        }

        try {

            long start = System.currentTimeMillis();

            Connection connection = ConnectionFactory.createConnection(conf);

            HBaseConfiguration.addHbaseResources(conf);

            Table table = connection.getTable(TableName.valueOf(tableName));

            byte[] keyStart = Bytes.toBytes(start_key);
            byte[] keyEnd  = Bytes.toBytes(end_key);

            Scan scan = new Scan(keyStart, keyEnd);

            ResultScanner scanner = table.getScanner(scan);
            FileWriter writer = new FileWriter(FILENAME, true);
            try{
                for (Result result = scanner.next(); result != null; result = scanner.next()) {
                    writer.write(result.toString()+"\n");


                }
            }finally {
                writer.close();
                scanner.close();
            }
            long end = System.currentTimeMillis();

            System.out.printf("Total time %d \n", end - start);

            table.close();
            connection.close();

            return 0;
        } catch (IOException ex) {
            LOGGER.error(ex);
            return 1;
        }
    }

    private static CommandLine parseArgs(String[] args) {
        Options options = new Options();

        Option o;

        // table name
        o = new Option("t","table_name", true, "HBase table name");
        options.addOption(o);

        o = new Option("m", "model_number", true, "model number");
        options.addOption(o);

        o = new Option("start_key", true, "start key for range scan");
        options.addOption(o);

        o = new Option("end_key", true, "end key for range scan");
        options.addOption(o);
        o = new Option("o", "output", true, "create output file");
        o.setRequired(false);
        options.addOption(o);

        // connection parameters
        o = new Option("conn", "connection", true, "Zookepper quorum and port");
        o.setArgs(2);
        o.setRequired(false);
        options.addOption(o);

        // debug flag
        options.addOption("d", "debug", false, "switch on DEBUG log level");

        CommandLineParser parser = new PosixParser();
        CommandLine cmd = null;

        try {
            cmd = parser.parse(options, args);
        } catch (Exception e) {
            System.err.println("ERROR: " + e.getMessage() + "\n");
            HelpFormatter formatter = new HelpFormatter();
            formatter.printHelp(NAME + " ", options, true);
            System.exit(-1);
        }

        if (cmd.hasOption("d")) {
            LOGGER.setLevel(Level.DEBUG);
            System.out.println("DEBUG ON");
        }

        return cmd;
    }

}

对十六进制行键实现 HBase 范围搜索的正确方法是什么？

Answer 1

我想您知道 HBase 表中的键是什么，所以我不明白为什么您不能这样做:

byte[]start = Hex.decodeHex("startKey".toCharArray());
byte[]end = Hex.decodeHex("endKey".toCharArray());
Scan scan = new Scan(start, end)

只是不确定为什么你要尝试相反的做法。

否则这里有您的问题的答案: What are the non-hex characters in HBase Shell RowKey?

希望有帮助:)