Hbase入門(五)——客戶端(Java,Shell,Thrift,Rest,MR,WebUI)

file

Hbase的客戶端有原生java客戶端,Hbase Shell,Thrift,Rest,Mapreduce,WebUI等等。java

下面是這幾種客戶端的常見用法。python

file

1、原生Java客戶端

原生java客戶端是hbase最主要,最高效的客戶端。c++

涵蓋了增刪改查等API,還實現了建立,刪除,修改表等DDL操做。web

配置java鏈接hbase

Java鏈接HBase須要兩個類:shell

  • HBaseConfiguration
  • ConnectionFactory

首先,配置一個hbase鏈接:apache

好比zookeeper的地址端口
hbase.zookeeper.quorum
hbase.zookeeper.property.clientPort複製代碼

更通用的作法是編寫hbase-site.xml文件,實現配置文件的加載:bootstrap

hbase-site.xml示例:數組

<configuration>

<property>
<name>hbase.master</name>
<value>hdfs://host1:60000</value>
</property>

<property>
<name>hbase.zookeeper.quorum</name>
<value>host1,host2,host3</value>
</property>

<property>
<name>hbase.zookeeper.property.clientPort</name>
<value>2181</value>
</property>
</configuration>複製代碼

隨後咱們加載配置文件,建立鏈接:ruby

config.addResource(new Path(System.getenv("HBASE_CONF_DIR"), "hbase-site.xml"));
 Connection connection = ConnectionFactory.createConnection(config);複製代碼

建立表

要建立表咱們須要首先建立一個Admin對象服務器

Admin admin = connection.getAdmin(); //使用鏈接對象獲取Admin對象
TableName tableName = TableName.valueOf("test");//定義表名

HTableDescriptor htd = new HTableDescriptor(tableName);//定義表對象

HColumnDescriptor hcd = new HColumnDescriptor("data");//定義列族對象

htd.addFamily(hcd); //添加

admin.createTable(htd);//建立表複製代碼

HBase2.X建立表

HBase2.X 的版本中建立表使用了新的 API

TableName tableName = TableName.valueOf("test");//定義表名
//TableDescriptor對象經過TableDescriptorBuilder構建;
TableDescriptorBuilder tableDescriptor = TableDescriptorBuilder.newBuilder(tableName);
ColumnFamilyDescriptor family = ColumnFamilyDescriptorBuilder.newBuilder(Bytes.toBytes("data")).build();//構建列族對象
tableDescriptor.setColumnFamily(family);//設置列族
admin.createTable(tableDescriptor.build());//建立表複製代碼

添加數據

Table table = connection.getTable(tableName);//獲取Table對象
try {
    byte[] row = Bytes.toBytes("row1"); //定義行
    Put put = new Put(row);             //建立Put對象
    byte[] columnFamily = Bytes.toBytes("data");    //列
    byte[] qualifier = Bytes.toBytes(String.valueOf(1)); //列族修飾詞
    byte[] value = Bytes.toBytes("張三丰");    //值
    put.addColumn(columnFamily, qualifier, value);
    table.put(put);     //向表中添加數據

} finally {
    //使用完了要釋放資源
    table.close();
}複製代碼

獲取指定行數據

//獲取數據
Get get = new Get(Bytes.toBytes("row1"));   //定義get對象
Result result = table.get(get);         //經過table對象獲取數據
System.out.println("Result: " + result);
//不少時候咱們只須要獲取「值」 這裏表示獲取 data:1 列族的值
byte[] valueBytes = result.getValue(Bytes.toBytes("data"), Bytes.toBytes("1")); //獲取到的是字節數組
//將字節轉成字符串
String valueStr = new String(valueBytes,"utf-8");
System.out.println("value:" + valueStr);複製代碼

掃描表中的數據

Scan scan = new Scan();
ResultScanner scanner = table.getScanner(scan);
try {
    for (Result scannerResult: scanner) {
        System.out.println("Scan: " + scannerResult);
         byte[] row = scannerResult.getRow();
         System.out.println("rowName:" + new String(row,"utf-8"));
    }
} finally {
    scanner.close();
}複製代碼

刪除表

TableName tableName = TableName.valueOf("test");
admin.disableTable(tableName);  //禁用表
admin.deleteTable(tableName);   //刪除表複製代碼

Hbase Java API表DDL完整示例:

package com.example.hbase.admin;

import java.io.IOException;

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HConstants;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Admin;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.io.compress.Compression.Algorithm;

public class Example {

  private static final String TABLE_NAME = "MY_TABLE_NAME_TOO";
  private static final String CF_DEFAULT = "DEFAULT_COLUMN_FAMILY";

  public static void createOrOverwrite(Admin admin, HTableDescriptor table) throws IOException {
    if (admin.tableExists(table.getTableName())) {
      admin.disableTable(table.getTableName());
      admin.deleteTable(table.getTableName());
    }
    admin.createTable(table);
  }

  public static void createSchemaTables(Configuration config) throws IOException {
    try (Connection connection = ConnectionFactory.createConnection(config);
         Admin admin = connection.getAdmin()) {

      HTableDescriptor table = new HTableDescriptor(TableName.valueOf(TABLE_NAME));
      table.addFamily(new HColumnDescriptor(CF_DEFAULT).setCompressionType(Algorithm.NONE));

      System.out.print("Creating table. ");
      createOrOverwrite(admin, table);
      System.out.println(" Done.");
    }
  }

  public static void modifySchema (Configuration config) throws IOException {
    try (Connection connection = ConnectionFactory.createConnection(config);
         Admin admin = connection.getAdmin()) {

      TableName tableName = TableName.valueOf(TABLE_NAME);
      if (!admin.tableExists(tableName)) {
        System.out.println("Table does not exist.");
        System.exit(-1);
      }

      HTableDescriptor table = admin.getTableDescriptor(tableName);

      // 更新表格
      HColumnDescriptor newColumn = new HColumnDescriptor("NEWCF");
      newColumn.setCompactionCompressionType(Algorithm.GZ);
      newColumn.setMaxVersions(HConstants.ALL_VERSIONS);
      admin.addColumn(tableName, newColumn);

      // 更新列族
      HColumnDescriptor existingColumn = new HColumnDescriptor(CF_DEFAULT);
      existingColumn.setCompactionCompressionType(Algorithm.GZ);
      existingColumn.setMaxVersions(HConstants.ALL_VERSIONS);
      table.modifyFamily(existingColumn);
      admin.modifyTable(tableName, table);

      // 禁用表格
      admin.disableTable(tableName);

      // 刪除列族
      admin.deleteColumn(tableName, CF_DEFAULT.getBytes("UTF-8"));

      // 刪除表格(需提早禁用)
      admin.deleteTable(tableName);
    }
  }

  public static void main(String... args) throws IOException {
    Configuration config = HBaseConfiguration.create();

    //添加必要配置文件(hbase-site.xml, core-site.xml)
    config.addResource(new Path(System.getenv("HBASE_CONF_DIR"), "hbase-site.xml"));
    config.addResource(new Path(System.getenv("HADOOP_CONF_DIR"), "core-site.xml"));
    createSchemaTables(config);
    modifySchema(config);
  }
}複製代碼

2、使用Hbase Shell工具操做Hbase

在 HBase 安裝目錄 bin/ 目錄下使用hbase shell命令鏈接正在運行的 HBase 實例。

$ ./bin/hbase shell
hbase(main):001:0>複製代碼

預覽 HBase Shell 的幫助文本

輸入help並回車, 能夠看到 HBase Shell 的基本信息和一些示例命令.

建立表

使用 create建立一個表 必須指定一個表名和列族名

hbase(main):001:0> create 'test', 'cf'
0 row(s) in 0.4170 seconds

=> Hbase::Table - test複製代碼

表信息

使用 list 查看存在表

hbase(main):002:0> list 'test'
TABLE
test
1 row(s) in 0.0180 seconds

=> ["test"]複製代碼

使用 describe 查看錶細節及配置

hbase(main):003:0> describe 'test'
Table test is ENABLED
test
COLUMN FAMILIES DESCRIPTION
{NAME => 'cf', VERSIONS => '1', EVICT_BLOCKS_ON_CLOSE => 'false', NEW_VERSION_BEHAVIOR => 'false', KEEP_DELETED_CELLS => 'FALSE', CACHE_DATA_ON_WRITE =>
'false', DATA_BLOCK_ENCODING => 'NONE', TTL => 'FOREVER', MIN_VERSIONS => '0', REPLICATION_SCOPE => '0', BLOOMFILTER => 'ROW', CACHE_INDEX_ON_WRITE => 'f
alse', IN_MEMORY => 'false', CACHE_BLOOMS_ON_WRITE => 'false', PREFETCH_BLOCKS_ON_OPEN => 'false', COMPRESSION => 'NONE', BLOCKCACHE => 'true', BLOCKSIZE
 => '65536'}
1 row(s)
Took 0.9998 seconds複製代碼

插入數據

使用 put 插入數據

hbase(main):003:0> put 'test', 'row1', 'cf:a', 'value1'
0 row(s) in 0.0850 seconds

hbase(main):004:0> put 'test', 'row2', 'cf:b', 'value2'
0 row(s) in 0.0110 seconds

hbase(main):005:0> put 'test', 'row3', 'cf:c', 'value3'
0 row(s) in 0.0100 seconds複製代碼

掃描所有數據

從 HBase 獲取數據的途徑之一就是 scan 。使用 scan 命令掃描表數據。你能夠對掃描作限制。

hbase(main):006:0> scan 'test'
ROW                                      COLUMN+CELL
 row1                                    column=cf:a, timestamp=1421762485768, value=value1
 row2                                    column=cf:b, timestamp=1421762491785, value=value2
 row3                                    column=cf:c, timestamp=1421762496210, value=value3
3 row(s) in 0.0230 seconds複製代碼

獲取一條數據

使用 get 命令一次獲取一條數據

hbase(main):007:0> get 'test', 'row1'
COLUMN                                   CELL
 cf:a                                    timestamp=1421762485768, value=value1
1 row(s) in 0.0350 seconds複製代碼

禁用表

使用 disable 命令禁用表

hbase(main):008:0> disable 'test'
0 row(s) in 1.1820 seconds

hbase(main):009:0> enable 'test'
0 row(s) in 0.1770 seconds複製代碼

使用 enable 命令啓用表

hbase(main):010:0> disable 'test'
0 row(s) in 1.1820 seconds複製代碼

刪除表

hbase(main):011:0> drop 'test'
0 row(s) in 0.1370 seconds複製代碼

退出 HBase Shell

使用quit命令退出命令行並從集羣斷開鏈接。

3、使用Thrift客戶端訪問HBase

因爲Hbase是用Java寫的,所以它原生地提供了Java接口,對非Java程序人員,怎麼辦呢?幸虧它提供了thrift接口服務器,所以也能夠採用其餘語言來編寫Hbase的客戶端,這裏是經常使用的Hbase python接口的介紹。其餘語言也相似。

1.啓動thrift-server

要使用Hbase的thrift接口,必須將它的服務啓動,啓動Hbase的thrift-server進程以下:

cd /app/zpy/hbase/bin
./hbase-daemon.sh start thrift 
執行jps命令檢查:
34533 ThriftServer複製代碼

thrift默認端口是9090,啓動成功後能夠查看端口是否起來。

2.安裝thrift所需依賴

(1)安裝依賴

yum install automake libtool flex bison pkgconfig gcc-c++ boost-devel libevent-devel zlib-devel python-devel ruby-devel openssl-devel

(2)安裝boost

wget http://sourceforge.net/projects/boost/files/boost/1.53.0/boost_1_53_0.tar.gz 
tar xvf boost_1_53_0.tar.gz 
cd boost_1_53_0 
./bootstrap.sh 
./b2 install複製代碼

3.安裝thrift客戶端

官網下載 thrift-0.11.0.tar.gz,解壓並安裝

wget http://mirrors.hust.edu.cn/apache/thrift/0.11.0/thrift-0.11.0.tar.gz
tar xzvf thrift-0.11.0.tar.gz
cd thrift-0.11.0
mkdir /app/zpy/thrift
./configure --prefix=/app/zpy/thrift
make 
make install複製代碼

make可能報錯以下:

g++: error: /usr/lib64/libboost_unit_test_framework.a: No such file or directory

解決:

find / -name libboost_unit_test_framework.*
cp /usr/local/lib/libboost_unit_test_framework.a  /usr/lib64/複製代碼

4.使用python3鏈接Hbase

安裝所需包

pip install thrift
pip install hbase-thrift複製代碼

python 腳本以下:

from thrift import Thrift
from thrift.transport import TSocket
from thrift.transport import TTransport
from thrift.protocol import TBinaryProtocol

from hbase import Hbase
from hbase.ttypes import *

transport = TSocket.TSocket('localhost', 9090)
protocol = TBinaryProtocol.TBinaryProtocol(transport)

client = Hbase.Client(protocol)
transport.open()
a = client.getTableNames()
print(a)複製代碼

4、Rest客戶端

一、啓動REST服務 

  a.啓動一個非守護進程模式的REST服務器(ctrl+c 終止)

     bin/hbase rest start 

  b.啓動守護進程模式的REST服務器

     bin/hbase-daemon.sh start rest

默認啓動的是8080端口(可使用參數在啓動時指定端口),能夠被訪問。curl  http:// :8080/

二、java調用示例:

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.client.ResultScanner;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.rest.client.Client;
import org.apache.hadoop.hbase.rest.client.Cluster;
import org.apache.hadoop.hbase.rest.client.RemoteHTable;
import org.apache.hadoop.hbase.util.Bytes;
import util.HBaseHelper;
import java.io.IOException;

/**
 * Created by root on 15-1-9.
 */
public class RestExample {
    public static void main(String[] args) throws IOException {
       Configuration conf = HBaseConfiguration.create();

       HBaseHelper helper = HBaseHelper.getHelper(conf);
       helper.dropTable("testtable");
       helper.createTable("testtable", "colfam1");
       System.out.println("Adding rows to table...");
       helper.fillTable("testtable", 1, 10, 5, "colfam1");

       Cluster cluster=new Cluster();
       cluster.add("hadoop",8080);

       Client client=new Client(cluster);
 

       Get get = new Get(Bytes.toBytes("row-30")); 
       get.addColumn(Bytes.toBytes("colfam1"), Bytes.toBytes("col-3"));
       Result result1 = table.get(get);
 
       System.out.println("Get result1: " + result1);

       Scan scan = new Scan();
       scan.setStartRow(Bytes.toBytes("row-10"));
       scan.setStopRow(Bytes.toBytes("row-15"));
       scan.addColumn(Bytes.toBytes("colfam1"), Bytes.toBytes("col-5"));
       ResultScanner scanner = table.getScanner(scan); 
          for (Result result2 : scanner) {
         System.out.println("Scan row[" + Bytes.toString(result2.getRow()) +
                    "]: " + result2);
        }
    }
}複製代碼

5、MapReduce操做Hbase

Apache MapReduce 是Hadoop提供的軟件框架,用來進行大規模數據分析.

mapred and mapreduce

與 MapReduce 同樣,在 HBase 中也有 2 種 mapreduce API 包.org.apache.hadoop.hbase.mapred and org.apache.hadoop.hbase.mapreduce.前者使用舊式風格的 API,後者採用新的模式.相比於前者,後者更加靈活。

HBase MapReduce 示例

HBase MapReduce 讀示例

Configuration config = HBaseConfiguration.create();
Job job = new Job(config, "ExampleRead");
job.setJarByClass(MyReadJob.class);     // class that contains mapper

Scan scan = new Scan();
scan.setCaching(500);        // 1 is the default in Scan, which will be bad for MapReduce jobs
scan.setCacheBlocks(false);  // don't set to true for MR jobs
// set other scan attrs
...

TableMapReduceUtil.initTableMapperJob(
  tableName,        // input HBase table name
  scan,             // Scan instance to control CF and attribute selection
  MyMapper.class,   // mapper
  null,             // mapper output key
  null,             // mapper output value
  job);
job.setOutputFormatClass(NullOutputFormat.class);   // because we aren't emitting anything from mapper

boolean b = job.waitForCompletion(true);
if (!b) {
  throw new IOException("error with job!");
}複製代碼

public static class MyMapper extends TableMapper<Text, Text> {

  public void map(ImmutableBytesWritable row, Result value, Context context) throws InterruptedException, IOException {
    // process data for the row from the Result instance.
   }
}複製代碼

HBase MapReduce 讀寫示例

Configuration config = HBaseConfiguration.create();
Job job = new Job(config,"ExampleReadWrite");
job.setJarByClass(MyReadWriteJob.class);    // class that contains mapper

Scan scan = new Scan();
scan.setCaching(500);        // 1 is the default in Scan, which will be bad for MapReduce jobs
scan.setCacheBlocks(false);  // don't set to true for MR jobs
// set other scan attrs

TableMapReduceUtil.initTableMapperJob(
  sourceTable,      // input table
  scan,             // Scan instance to control CF and attribute selection
  MyMapper.class,   // mapper class
  null,             // mapper output key
  null,             // mapper output value
  job);
TableMapReduceUtil.initTableReducerJob(
  targetTable,      // output table
  null,             // reducer class
  job);
job.setNumReduceTasks(0);

boolean b = job.waitForCompletion(true);
if (!b) {
    throw new IOException("error with job!");
}複製代碼

6、Hbase Web UI

Hbase提供了一種Web方式的用戶接口,用戶能夠經過Web界面查看Hbase集羣的屬性等狀態信息,web頁面分爲:Master狀態界面,和Zookeeper統計信息頁面。

默認訪問地址分別是:

ip:60010

ip::60030

ip:60010/zk.jsp

Master狀態界面會看到Master狀態的詳情。

該頁面大概分HBase集羣信息,任務信息,表信息,RegionServer信息。每一部分又包含了一些具體的屬性。

RegionServer狀態界面會看到RegionServer狀態的詳情。

RegionServer的節點屬性信息,任務信息和Region信息。

Zookeeper統計信息頁面是很是簡單的半結構化文本打印信息。

file

更多實時計算,Hbase,Flink,Kafka等相關技術博文,歡迎關注實時流式計算

file

本文由博客一文多發平臺 OpenWrite 發佈!

相關文章
相關標籤/搜索