五、HBase 的 Java API 开发
1. 开发 javaAPI 操作 HBase 表数据
- 创建表 myuser
@Test
public void createTable() throws IOException {
//创建配置文件对象，并指定zookeeper的连接地址
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.property.clientPort", "2181");
configuration.set("hbase.zookeeper.quorum", "node01,node02,node03");
//集群配置↓
//configuration.set("hbase.zookeeper.quorum", "101.236.39.141,101.236.46.114,101.236.46.113");
configuration.set("hbase.master", "node01:60000");
Connection connection = ConnectionFactory.createConnection(configuration);
Admin admin = connection.getAdmin();
//通过HTableDescriptor来实现我们表的参数设置，包括表名，列族等等
HTableDescriptor hTableDescriptor = new HTableDescriptor(TableName.valueOf("myuser"));
//添加列族
hTableDescriptor.addFamily(new HColumnDescriptor("f1"));
//添加列族
hTableDescriptor.addFamily(new HColumnDescriptor("f2"));
//创建表
boolean myuser = admin.tableExists(TableName.valueOf("myuser"));
if(!myuser){
admin.createTable(hTableDescriptor);
}
//关闭客户端连接
admin.close();
}
- 向表中添加数据
@Test
public void addDatas() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum", "node01:2181,node02:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
//获取表
Table myuser = connection.getTable(TableName.valueOf("myuser"));
//创建put对象，并指定rowkey
Put put = new Put("0001".getBytes());
put.addColumn("f1".getBytes(),"id".getBytes(), Bytes.toBytes(1));
put.addColumn("f1".getBytes(),"name".getBytes(), Bytes.toBytes("张三"));
put.addColumn("f1".getBytes(),"age".getBytes(), Bytes.toBytes(18));
put.addColumn("f2".getBytes(),"address".getBytes(), Bytes.toBytes("地球人"));
put.addColumn("f2".getBytes(),"phone".getBytes(), Bytes.toBytes("15874102589"));
//插入数据
myuser.put(put);
//关闭表
myuser.close();
}
- 查询数据
初始化一批数据到 HBase 当中用于查询
@Test
public void insertBatchData() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum", "node01:2181,node02:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
//获取表
Table myuser = connection.getTable(TableName.valueOf("myuser"));
//创建put对象，并指定rowkey
Put put = new Put("0002".getBytes());
put.addColumn("f1".getBytes(),"id".getBytes(),Bytes.toBytes(1));
put.addColumn("f1".getBytes(),"name".getBytes(),Bytes.toBytes("曹操"));
put.addColumn("f1".getBytes(),"age".getBytes(),Bytes.toBytes(30));
put.addColumn("f2".getBytes(),"sex".getBytes(),Bytes.toBytes("1"));
put.addColumn("f2".getBytes(),"address".getBytes(),Bytes.toBytes("沛国谯县"));
put.addColumn("f2".getBytes(),"phone".getBytes(),Bytes.toBytes("16888888888"));
put.addColumn("f2".getBytes(),"say".getBytes(),Bytes.toBytes("helloworld"));
Put put2 = new Put("0003".getBytes());
put2.addColumn("f1".getBytes(),"id".getBytes(),Bytes.toBytes(2));
put2.addColumn("f1".getBytes(),"name".getBytes(),Bytes.toBytes("刘备"));
put2.addColumn("f1".getBytes(),"age".getBytes(),Bytes.toBytes(32));
put2.addColumn("f2".getBytes(),"sex".getBytes(),Bytes.toBytes("1"));
put2.addColumn("f2".getBytes(),"address".getBytes(),Bytes.toBytes("幽州涿郡涿县"));
put2.addColumn("f2".getBytes(),"phone".getBytes(),Bytes.toBytes("17888888888"));
put2.addColumn("f2".getBytes(),"say".getBytes(),Bytes.toBytes("talk is cheap , show me the code"));
Put put3 = new Put("0004".getBytes());
put3.addColumn("f1".getBytes(),"id".getBytes(),Bytes.toBytes(3));
put3.addColumn("f1".getBytes(),"name".getBytes(),Bytes.toBytes("孙权"));
put3.addColumn("f1".getBytes(),"age".getBytes(),Bytes.toBytes(35));
put3.addColumn("f2".getBytes(),"sex".getBytes(),Bytes.toBytes("1"));
put3.addColumn("f2".getBytes(),"address".getBytes(),Bytes.toBytes("下邳"));
put3.addColumn("f2".getBytes(),"phone".getBytes(),Bytes.toBytes("12888888888"));
put3.addColumn("f2".getBytes(),"say".getBytes(),Bytes.toBytes("what are you 弄啥嘞！"));
Put put4 = new Put("0005".getBytes());
put4.addColumn("f1".getBytes(),"id".getBytes(),Bytes.toBytes(4));
put4.addColumn("f1".getBytes(),"name".getBytes(),Bytes.toBytes("诸葛亮"));
put4.addColumn("f1".getBytes(),"age".getBytes(),Bytes.toBytes(28));
put4.addColumn("f2".getBytes(),"sex".getBytes(),Bytes.toBytes("1"));
put4.addColumn("f2".getBytes(),"address".getBytes(),Bytes.toBytes("四川隆中"));
put4.addColumn("f2".getBytes(),"phone".getBytes(),Bytes.toBytes("14888888888"));
put4.addColumn("f2".getBytes(),"say".getBytes(),Bytes.toBytes("出师表你背了嘛"));
Put put5 = new Put("0005".getBytes());
put5.addColumn("f1".getBytes(),"id".getBytes(),Bytes.toBytes(5));
put5.addColumn("f1".getBytes(),"name".getBytes(),Bytes.toBytes("司马懿"));
put5.addColumn("f1".getBytes(),"age".getBytes(),Bytes.toBytes(27));
put5.addColumn("f2".getBytes(),"sex".getBytes(),Bytes.toBytes("1"));
put5.addColumn("f2".getBytes(),"address".getBytes(),Bytes.toBytes("哪里人有待考究"));
put5.addColumn("f2".getBytes(),"phone".getBytes(),Bytes.toBytes("15888888888"));
put5.addColumn("f2".getBytes(),"say".getBytes(),Bytes.toBytes("跟诸葛亮死掐"));
Put put6 = new Put("0006".getBytes());
put6.addColumn("f1".getBytes(),"id".getBytes(),Bytes.toBytes(5));
put6.addColumn("f1".getBytes(),"name".getBytes(),Bytes.toBytes("xiaobubu—吕布"));
put6.addColumn("f1".getBytes(),"age".getBytes(),Bytes.toBytes(28));
put6.addColumn("f2".getBytes(),"sex".getBytes(),Bytes.toBytes("1"));
put6.addColumn("f2".getBytes(),"address".getBytes(),Bytes.toBytes("内蒙人"));
put6.addColumn("f2".getBytes(),"phone".getBytes(),Bytes.toBytes("15788888888"));
put6.addColumn("f2".getBytes(),"say".getBytes(),Bytes.toBytes("貂蝉去哪了"));
List<Put> listPut = new ArrayList<Put>();
listPut.add(put);
listPut.add(put2);
listPut.add(put3);
listPut.add(put4);
listPut.add(put5);
listPut.add(put6);
myuser.put(listPut);
myuser.close();
}
按照 rowkey 进行查询获取所有列的所有值
查询主键 rowkey 为 0003 的人：
@Test
public void searchData() throws IOException {
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Get get = new Get(Bytes.toBytes("0003"));
Result result = myuser.get(get);
Cell[] cells = result.rawCells();
//获取所有的列名称以及列的值
for (Cell cell : cells) {
//注意，如果列属性是int类型，那么这里就不会显示
System.out.println(Bytes.toString(cell.getQualifierArray(),cell.getQualifierOffset(),cell.getQualifierLength()));
System.out.println(Bytes.toString(cell.getValueArray(),cell.getValueOffset(),cell.getValueLength()));
}
myuser.close();
}
按照 rowkey 查询指定列族下面的指定列的值：
@Test
public void searchData2() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
//通过rowKey进行查询
Get get = new Get("0003".getBytes());
get.addColumn("f1".getBytes(),"id".getBytes());
Result result = myuser.get(get);
System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "age".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
myuser.close();
}
通过 startRowKey 和 endRowKey 进行扫描：
@Test
public void scanRowKey() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Scan scan = new Scan();
scan.setStartRow("0004".getBytes());
scan.setStopRow("0006".getBytes());
ResultScanner resultScanner = myuser.getScanner(scan);
for (Result result : resultScanner) {
//获取rowkey
System.out.println(Bytes.toString(result.getRow()));
//遍历获取得到所有的列族以及所有的列的名称
KeyValue[] raw = result.raw();
for (KeyValue keyValue : raw) {
//获取所属列族
System.out.println(Bytes.toString(keyValue.getFamilyArray(),keyValue.getFamilyOffset(),keyValue.getFamilyLength()));
System.out.println(Bytes.toString(keyValue.getQualifierArray(),keyValue.getQualifierOffset(),keyValue.getQualifierLength()));
}
//指定列族以及列打印列当中的数据出来
System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "age".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
}
myuser.close();
}
通过 scan 进行全表扫描：
@Test
public void scanAllData() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Scan scan = new Scan();
ResultScanner resultScanner = myuser.getScanner(scan);
for (Result result : resultScanner) {
//获取rowkey
System.out.println(Bytes.toString(result.getRow()));
//指定列族以及列打印列当中的数据出来
System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "age".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
}
myuser.close();
}
2. 过滤器查询
过滤器的类型很多，但是可以分为两大类——比较过滤器，专用过滤器。
过滤器的作用是在服务端判断数据是否满足条件，然后只将满足条件的数据返回给客户端；
hbase 过滤器的比较运算符：
LESS <
LESS_OR_EQUAL <=
EQUAL =
NOT_EQUAL <>
GREATER_OR_EQUAL >=
GREATER >
NO_OP 排除所有
Hbase 过滤器的比较器（指定比较机制）：
BinaryComparator 按字节索引顺序比较指定字节数组，采用Bytes.compareTo(byte[])
BinaryPrefixComparator 跟前面相同，只是比较左端的数据是否相同
NullComparator 判断给定的是否为空
BitComparator 按位比较
RegexStringComparator 提供一个正则的比较器，仅支持 EQUAL 和非EQUAL
SubstringComparator 判断提供的子串是否出现在value中。
1) 比较过滤器
- rowKey 过滤器 RowFilter
通过 RowFilter 过滤比 rowKey 0003 小的所有值出来
@Test
public void rowKeyFilter() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Scan scan = new Scan();
RowFilter rowFilter = new RowFilter(CompareFilter.CompareOp.LESS_OR_EQUAL, new BinaryComparator(Bytes.toBytes("0003")));
scan.setFilter(rowFilter);
ResultScanner resultScanner = myuser.getScanner(scan);
for (Result result : resultScanner) {
//获取rowkey
System.out.println(Bytes.toString(result.getRow()));
//指定列族以及列打印列当中的数据出来
System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "age".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
}
myuser.close();
}
- 列族过滤器 FamilyFilter
查询比 f2 列族小的所有的列族内的数据
@Test
public void familyFilter() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Scan scan = new Scan();
FamilyFilter familyFilter = new FamilyFilter(CompareFilter.CompareOp.LESS, new SubstringComparator("f2"));
scan.setFilter(familyFilter);
ResultScanner resultScanner = myuser.getScanner(scan);
for (Result result : resultScanner) {
//获取rowkey
System.out.println(Bytes.toString(result.getRow()));
//指定列族以及列打印列当中的数据出来
System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "age".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
}
myuser.close();
}
- 列过滤器 QualifierFilter
只查询 name 列的值
@Test
public void qualifierFilter() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Scan scan = new Scan();
QualifierFilter qualifierFilter = new QualifierFilter(CompareFilter.CompareOp.EQUAL, new SubstringComparator("name"));
scan.setFilter(qualifierFilter);
ResultScanner resultScanner = myuser.getScanner(scan);
for (Result result : resultScanner) {
//获取rowkey
System.out.println(Bytes.toString(result.getRow()));
//指定列族以及列打印列当中的数据出来
// System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
}
myuser.close();
}
- 列值过滤器 ValueFilter
查询所有列当中包含 8 的数据
@Test
public void valueFilter() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Scan scan = new Scan();
ValueFilter valueFilter = new ValueFilter(CompareFilter.CompareOp.EQUAL, new SubstringComparator("8"));
scan.setFilter(valueFilter);
ResultScanner resultScanner = myuser.getScanner(scan);
for (Result result : resultScanner) {
//获取rowkey
System.out.println(Bytes.toString(result.getRow()));
//指定列族以及列打印列当中的数据出来
// System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
}
myuser.close();
}
2) 专用过滤器
- 单列值过滤器 SingleColumnValueFilter
SingleColumnValueFilter 会返回满足条件的整列值的所有字段
@Test
public void singleColumnFilter() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Scan scan = new Scan();
SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter("f1".getBytes(), "name".getBytes(), CompareFilter.CompareOp.EQUAL, "刘备".getBytes());
scan.setFilter(singleColumnValueFilter);
ResultScanner resultScanner = myuser.getScanner(scan);
for (Result result : resultScanner) {
//获取rowkey
System.out.println(Bytes.toString(result.getRow()));
//指定列族以及列打印列当中的数据出来
System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
}
myuser.close();
}
- 列值排除过滤器 SingleColumnValueExcludeFilter
与 SingleColumnValueFilter 相反，会排除掉指定的列，其他的列全部返回
- rowkey 前缀过滤器 PrefixFilter
查询以 00 开头的所有前缀的 rowkey
@Test
public void preFilter() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Scan scan = new Scan();
PrefixFilter prefixFilter = new PrefixFilter("00".getBytes());
scan.setFilter(prefixFilter);
ResultScanner resultScanner = myuser.getScanner(scan);
for (Result result : resultScanner) {
//获取rowkey
System.out.println(Bytes.toString(result.getRow()));
//指定列族以及列打印列当中的数据出来
System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
}
myuser.close();
}
- 分页过滤器 PageFilter
分页过滤器 PageFilter
@Test
public void pageFilter2() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
int pageNum = 3;
int pageSize = 2;
Scan scan = new Scan();
if (pageNum == 1) {
PageFilter filter = new PageFilter(pageSize);
scan.setStartRow(Bytes.toBytes(""));
scan.setFilter(filter);
scan.setMaxResultSize(pageSize);
ResultScanner scanner = myuser.getScanner(scan);
for (Result result : scanner) {
//获取rowkey
System.out.println(Bytes.toString(result.getRow()));
//指定列族以及列打印列当中的数据出来
// System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
//System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
}
}else{
String startRowKey ="";
PageFilter filter = new PageFilter((pageNum - 1) * pageSize + 1 );
scan.setStartRow(startRowKey.getBytes());
scan.setMaxResultSize((pageNum - 1) * pageSize + 1);
scan.setFilter(filter);
ResultScanner scanner = myuser.getScanner(scan);
for (Result result : scanner) {
byte[] row = result.getRow();
startRowKey = new String(row);
}
Scan scan2 = new Scan();
scan2.setStartRow(startRowKey.getBytes());
scan2.setMaxResultSize(Long.valueOf(pageSize));
PageFilter filter2 = new PageFilter(pageSize);
scan2.setFilter(filter2);
ResultScanner scanner1 = myuser.getScanner(scan2);
for (Result result : scanner1) {
byte[] row = result.getRow();
System.out.println(new String(row));
}
}
myuser.close();
}
3) 多过滤器综合查询 FilterList
需求：使用 SingleColumnValueFilter 查询 f1 列族，name 为刘备的数据，并且同时满足 rowkey 的前缀以 00 开头的数据（PrefixFilter）
@Test
public void manyFilter() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum", "node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Scan scan = new Scan();
FilterList filterList = new FilterList();
SingleColumnValueFilter singleColumnValueFilter = new SingleColumnValueFilter("f1".getBytes(), "name".getBytes(), CompareFilter.CompareOp.EQUAL, "刘备".getBytes());
PrefixFilter prefixFilter = new PrefixFilter("00".getBytes());
filterList.addFilter(singleColumnValueFilter);
filterList.addFilter(prefixFilter);
scan.setFilter(filterList);
ResultScanner scanner = myuser.getScanner(scan);
for (Result result : scanner) {
//获取rowkey
System.out.println(Bytes.toString(result.getRow()));
//指定列族以及列打印列当中的数据出来
// System.out.println(Bytes.toInt(result.getValue("f1".getBytes(), "id".getBytes())));
System.out.println(Bytes.toString(result.getValue("f1".getBytes(), "name".getBytes())));
//System.out.println(Bytes.toString(result.getValue("f2".getBytes(), "phone".getBytes())));
}
myuser.close();
}
3. 根据 rowkey 删除数据
@Test
public void deleteByRowKey() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Table myuser = connection.getTable(TableName.valueOf("myuser"));
Delete delete = new Delete("0001".getBytes());
myuser.delete(delete);
myuser.close();
}
4. 删除表操作
@Test
public void deleteTable() throws IOException {
//获取连接
Configuration configuration = HBaseConfiguration.create();
configuration.set("hbase.zookeeper.quorum","node01:2181,node02:2181,node03:2181");
Connection connection = ConnectionFactory.createConnection(configuration);
Admin admin = connection.getAdmin();
admin.disableTable(TableName.valueOf("myuser"));
admin.deleteTable(TableName.valueOf("myuser"));
admin.close();
}