Ⅰ 如何使用java API操作Hbase
写了个Hbase新的api的增删改查的工具类,以供参考,直接拷贝代码就能用,散仙觉得基础的功能,都有了,代码如下:
package com.dhgate.hbase.test;
import java.util.ArrayList;
import java.util.List;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.Cell;
import org.apache.hadoop.hbase.CellUtil;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.client.Delete;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.client.HBaseAdmin;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Put;
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.filter.PageFilter;
import org.apache.hadoop.hbase.filter.PrefixFilter;
import org.apache.hadoop.hbase.util.Bytes;
/**
* 基于新的API
* Hbase0.96版本
* 写的工具类
*
* @author qindongliang
* 大数据技术交流群: 376932160
*
* **/
public class HbaseCommons {
static Configuration conf=HBaseConfiguration.create();
static String tableName="";
public static void main(String[] args)throws Exception {
//String tableName="test";
//createTable(tableName, null);
}
/**
* 批量添加数据
* @param tableName 标名字
* @param rows rowkey行健的集合
* 本方法仅作示例,其他的内容需要看自己义务改变
*
* **/
public static void insertList(String tableName,String rows[])throws Exception{
HTable table=new HTable(conf, tableName);
List<Put> list=new ArrayList<Put>();
for(String r:rows){
Put p=new Put(Bytes.toBytes(r));
//此处示例添加其他信息
//p.add(Bytes.toBytes("family"),Bytes.toBytes("column"), 1000, Bytes.toBytes("value"));
list.add(p);
}
table.put(list);//批量添加
table.close();//释放资源
}
/**
* 创建一个表
* @param tableName 表名字
* @param columnFamilys 列簇
*
* **/
public static void createTable(String tableName,String[] columnFamilys)throws Exception{
//admin 对象
HBaseAdmin admin=new HBaseAdmin(conf);
if(admin.tableExists(tableName)){
System.out.println("此表,已存在!");
}else{
//旧的写法
//HTableDescriptor tableDesc=new HTableDescriptor(tableName);
//新的api
HTableDescriptor tableDesc=new HTableDescriptor(TableName.valueOf(tableName));
for(String columnFamily:columnFamilys){
tableDesc.addFamily(new HColumnDescriptor(columnFamily));
}
admin.createTable(tableDesc);
System.out.println("建表成功!");
}
admin.close();//关闭释放资源
}
/**
* 删除一个表
* @param tableName 删除的表名
* */
public static void deleteTable(String tableName)throws Exception{
HBaseAdmin admin=new HBaseAdmin(conf);
if(admin.tableExists(tableName)){
admin.disableTable(tableName);//禁用表
admin.deleteTable(tableName);//删除表
System.out.println("删除表成功!");
}else{
System.out.println("删除的表不存在!");
}
admin.close();
}
/**
* 插入一条数据
* @param tableName 表明
* @param columnFamily 列簇
* @param column 列
* @param value 值
*
* ***/
public static void insertOneRow(String tableName,String rowkey,String columnFamily,String column,String value)throws Exception{
HTable table=new HTable(conf, tableName);
Put put=new Put(Bytes.toBytes(rowkey));
put.add(Bytes.toBytes(columnFamily), Bytes.toBytes(column), Bytes.toBytes(value));
table.put(put);//放入表
table.close();//释放资源
}
/**
* 删除一条数据
* @param tableName 表名
* @param row rowkey行键
*
* */
public static void deleteOneRow(String tableName,String row)throws Exception{
HTable table=new HTable(conf, tableName);
Delete delete=new Delete(Bytes.toBytes(row));
table.delete(delete);
table.close();
}
/**
* 删除多条数据
* @param tableName 表名
* @param rows 行健集合
*
* **/
public static void deleteList(String tableName,String rows[])throws Exception{
HTable table=new HTable(conf, tableName);
List<Delete> list=new ArrayList<Delete>();
for(String row:rows){
Delete del=new Delete(Bytes.toBytes(row));
list.add(del);
}
table.delete(list);
table.close();//释放资源
}
/**
* 获取一条数据,根据rowkey
* @param tableName 表名
* @param row 行健
*
* **/
public static void getOneRow(String tableName,String row)throws Exception{
HTable table=new HTable(conf, tableName);
Get get=new Get(Bytes.toBytes(row));
Result result=table.get(get);
printRecoder(result);//打印记录
table.close();//释放资源
}
/**
* 查看某个表下的所有数据
*
* @param tableName 表名
* */
public static void showAll(String tableName)throws Exception{
HTable table=new HTable(conf, tableName);
Scan scan=new Scan();
ResultScanner rs=table.getScanner(scan);
for(Result r:rs){
printRecoder(r);//打印记录
}
table.close();//释放资源
}
/**
* 查看某个表下的所有数据
*
* @param tableName 表名
* @param rowKey 行健
* */
public static void ScanPrefixByRowKey(String tableName,String rowKey)throws Exception{
HTable table=new HTable(conf, tableName);
Scan scan=new Scan();
scan.setFilter(new PrefixFilter(Bytes.toBytes(rowKey)));
ResultScanner rs=table.getScanner(scan);
for(Result r:rs){
printRecoder(r);//打印记录
}
table.close();//释放资源
}
/**
* 查看某个表下的所有数据
*
* @param tableName 表名
* @param rowKey 行健扫描
* @param limit 限制返回数据量
* */
public static void ScanPrefixByRowKeyAndLimit(String tableName,String rowKey,long limit)throws Exception{
HTable table=new HTable(conf, tableName);
Scan scan=new Scan();
scan.setFilter(new PrefixFilter(Bytes.toBytes(rowKey)));
scan.setFilter(new PageFilter(limit));
ResultScanner rs=table.getScanner(scan);
for(Result r:rs){
printRecoder(r);//打印记录
}
table.close();//释放资源
}
/**
* 根据rowkey扫描一段范围
* @param tableName 表名
* @param startRow 开始的行健
* @param stopRow 结束的行健
* **/
public void scanByStartAndStopRow(String tableName,String startRow,String stopRow)throws Exception{
HTable table=new HTable(conf, tableName);
Scan scan=new Scan();
scan.setStartRow(Bytes.toBytes(startRow));
scan.setStopRow(Bytes.toBytes(stopRow));
ResultScanner rs=table.getScanner(scan);
for(Result r:rs){
printRecoder(r);
}
table.close();//释放资源
}
/**
* 扫描整个表里面具体的某个字段的值
* @param tableName 表名
* @param columnFalimy 列簇
* @param column 列
* **/
public static void getValueDetail(String tableName,String columnFalimy,String column)throws Exception{
HTable table=new HTable(conf, tableName);
Scan scan=new Scan();
ResultScanner rs=table.getScanner(scan);
for(Result r:rs){
System.out.println("值: " +new String(r.getValue(Bytes.toBytes(columnFalimy), Bytes.toBytes(column))));
}
table.close();//释放资源
}
/**
* 打印一条记录的详情
*
* */
public static void printRecoder(Result result)throws Exception{
for(Cell cell:result.rawCells()){
System.out.print("行健: "+new String(CellUtil.cloneRow(cell)));
System.out.print("列簇: "+new String(CellUtil.cloneFamily(cell)));
System.out.print(" 列: "+new String(CellUtil.cloneQualifier(cell)));
System.out.print(" 值: "+new String(CellUtil.cloneValue(cell)));
System.out.println("时间戳: "+cell.getTimestamp());
}
}
}
Ⅱ 如何使用Java API操作Hbase
先导入hbase的相关jar包。
再根据api进行操作。
package com.util;
import java.io.IOException;
import java.util.ArrayList;
import java.util.List;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.hbase.HBaseConfiguration;
import org.apache.hadoop.hbase.HColumnDescriptor;
import org.apache.hadoop.hbase.HTableDescriptor;
import org.apache.hadoop.hbase.KeyValue;
import org.apache.hadoop.hbase.MasterNotRunningException;
import org.apache.hadoop.hbase.TableName;
import org.apache.hadoop.hbase.ZooKeeperConnectionException;
import org.apache.hadoop.hbase.client.Connection;
import org.apache.hadoop.hbase.client.ConnectionFactory;
import org.apache.hadoop.hbase.client.Delete;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.client.HBaseAdmin;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.HTablePool;
import org.apache.hadoop.hbase.client.Put;
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.client.Table;
import org.apache.hadoop.hbase.filter.CompareFilter.CompareOp;
import org.apache.hadoop.hbase.filter.Filter;
import org.apache.hadoop.hbase.filter.FilterList;
import org.apache.hadoop.hbase.filter.SingleColumnValueFilter;
import org.apache.hadoop.hbase.util.Bytes;
public class HBaseUtil {
public static Configuration configuration;
static {
configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.property.clientPort", "2181");
configuration.set("hbase.zookeeper.quorum", "192.168.1.103");
configuration.set("hbase.master", "192.168.1.103:600000");
}
public static void main(String[] args) throws IOException {
createTable("abc");
insertData("abc");
QueryAll("abc");
}
/**
* 创建表
* @param tableName
*/
public static void createTable(String tableName) {
System.out.println("start create table ......");
try {
HBaseAdmin hBaseAdmin = new HBaseAdmin(configuration);
if (hBaseAdmin.tableExists(tableName)) {// 如果存在要创建的表,那么先删除,再创建
hBaseAdmin.disableTable(tableName);
hBaseAdmin.deleteTable(tableName);
System.out.println(tableName + " is exist,detele....");
}
HTableDescriptor tableDescriptor = new HTableDescriptor(TableName.valueOf(tableName));
tableDescriptor.addFamily(new HColumnDescriptor("column1"));
tableDescriptor.addFamily(new HColumnDescriptor("column2"));
tableDescriptor.addFamily(new HColumnDescriptor("column3"));
hBaseAdmin.createTable(tableDescriptor);
hBaseAdmin.close();
} catch (MasterNotRunningException e) {
e.printStackTrace();
} catch (ZooKeeperConnectionException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
System.out.println("end create table ......");
}
/**
* 插入数据
* @param tableName
* @throws IOException
*/
public static void insertData(String tableName) throws IOException {
System.out.println("start insert data ......");
Connection connection = ConnectionFactory.createConnection(configuration);
Table table = connection.getTable(TableName.valueOf(tableName));
Put put = new Put("112233bbbcccc".getBytes());// 一个PUT代表一行数据,再NEW一个PUT表示第二行数据,每行一个唯一的ROWKEY,此处rowkey为put构造方法中传入的值
put.add("column1".getBytes(), null, "aaa".getBytes());// 本行数据的第一列
put.add("column2".getBytes(), null, "bbb".getBytes());// 本行数据的第三列
put.add("column3".getBytes(), null, "ccc".getBytes());// 本行数据的第三列
try {
table.put(put);
} catch (IOException e) {
e.printStackTrace();
}
System.out.println("end insert data ......");
}
/**
* 删除一张表
* @param tableName
*/
public static void dropTable(String tableName) {
try {
HBaseAdmin admin = new HBaseAdmin(configuration);
admin.disableTable(tableName);
admin.deleteTable(tableName);
} catch (MasterNotRunningException e) {
e.printStackTrace();
} catch (ZooKeeperConnectionException e) {
e.printStackTrace();
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 根据 rowkey删除一条记录
* @param tablename
* @param rowkey
*/
public static void deleteRow(String tablename, String rowkey) {
try {
HTable table = new HTable(configuration, tablename);
List list = new ArrayList();
Delete d1 = new Delete(rowkey.getBytes());
list.add(d1);
table.delete(list);
System.out.println("删除行成功!");
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 组合条件删除
* @param tablename
* @param rowkey
*/
public static void deleteByCondition(String tablename, String rowkey) {
//目前还没有发现有效的API能够实现 根据非rowkey的条件删除 这个功能能,还有清空表全部数据的API操作
}
/**
* 查询所有数据
* @param tableName
* @throws IOException
*/
public static void QueryAll(String tableName) throws IOException {
Connection connection = ConnectionFactory.createConnection(configuration);
Table table = connection.getTable(TableName.valueOf(tableName));
try {
ResultScanner rs = table.getScanner(new Scan());
for (Result r : rs) {
System.out.println("获得到rowkey:" + new String(r.getRow()));
for (KeyValue keyValue : r.raw()) {
System.out.println("列:" + new String(keyValue.getFamily())
+ "====值:" + new String(keyValue.getValue()));
}
}
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 单条件查询,根据rowkey查询唯一一条记录
* @param tableName
*/
public static void QueryByCondition1(String tableName) {
HTablePool pool = new HTablePool(configuration, 1000);
HTable table = (HTable) pool.getTable(tableName);
try {
Get scan = new Get("abcdef".getBytes());// 根据rowkey查询
Result r = table.get(scan);
System.out.println("获得到rowkey:" + new String(r.getRow()));
for (KeyValue keyValue : r.raw()) {
System.out.println("列:" + new String(keyValue.getFamily())
+ "====值:" + new String(keyValue.getValue()));
}
} catch (IOException e) {
e.printStackTrace();
}
}
/**
* 单条件按查询,查询多条记录
* @param tableName
*/
public static void QueryByCondition2(String tableName) {
try {
HTablePool pool = new HTablePool(configuration, 1000);
HTable table = (HTable) pool.getTable(tableName);
Filter filter = new SingleColumnValueFilter(Bytes
.toBytes("column1"), null, CompareOp.EQUAL, Bytes
.toBytes("aaa")); // 当列column1的值为aaa时进行查询
Scan s = new Scan();
s.setFilter(filter);
ResultScanner rs = table.getScanner(s);
for (Result r : rs) {
System.out.println("获得到rowkey:" + new String(r.getRow()));
for (KeyValue keyValue : r.raw()) {
System.out.println("列:" + new String(keyValue.getFamily())
+ "====值:" + new String(keyValue.getValue()));
}
}
} catch (Exception e) {
e.printStackTrace();
}
}
/**
* 组合条件查询
* @param tableName
*/
public static void QueryByCondition3(String tableName) {
try {
HTablePool pool = new HTablePool(configuration, 1000);
HTable table = (HTable) pool.getTable(tableName);
List<Filter> filters = new ArrayList<Filter>();
Filter filter1 = new SingleColumnValueFilter(Bytes
.toBytes("column1"), null, CompareOp.EQUAL, Bytes
.toBytes("aaa"));
filters.add(filter1);
Filter filter2 = new SingleColumnValueFilter(Bytes
.toBytes("column2"), null, CompareOp.EQUAL, Bytes
.toBytes("bbb"));
filters.add(filter2);
Filter filter3 = new SingleColumnValueFilter(Bytes
.toBytes("column3"), null, CompareOp.EQUAL, Bytes
.toBytes("ccc"));
filters.add(filter3);
FilterList filterList1 = new FilterList(filters);
Scan scan = new Scan();
scan.setFilter(filterList1);
ResultScanner rs = table.getScanner(scan);
for (Result r : rs) {
System.out.println("获得到rowkey:" + new String(r.getRow()));
for (KeyValue keyValue : r.raw()) {
System.out.println("列:" + new String(keyValue.getFamily())
+ "====值:" + new String(keyValue.getValue()));
}
}
rs.close();
} catch (Exception e) {
e.printStackTrace();
}
}
}
Ⅲ 大数据和Java开发哪个更有前途
两者关系抄
java是计算机的一门编程语言;可以用来做很多工作,大数据开发属于其中一种;
大数据属于互联网方向,就像现在建立在大数据基础上的AI方向一样,
他两不是一个同类,但是属于包含和被包含的关系;
java可以用来做大数据工作,大数据开发或者应用不必要用java,可以Python,Scala,go语言等。
再有就是就业前景
看看职友集的数据,
Java工程师
最后根据自己的需要可以自己选择适合自己的才是最好的,