我在HBASE中有数百万行,其中包含可计数的运行时列限定符(即小于10)。很难扫描HBASE表中的整个行。有没有办法通过hbase shell或任何可用于打印的实用程序打印列族中的列限定符?
答案 0 :(得分:0)
到目前为止,我还没有意识到预定义的实用程序。可能是您可以使用以下代码获取表中列族的列限定符。
用法:HbaseCqIdentifier [tableName] [columnFamily]
import java.io.IOException;
import java.util.Set;
import org.apache.hadoop.hbase.HBaseConfiguration;
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.client.ResultScanner;
import org.apache.hadoop.hbase.client.Scan;
import org.apache.hadoop.hbase.client.Table;
import org.apache.hadoop.hbase.util.Bytes;
public class HbaseCqIdentifier {
private static Connection conn;
private static Set<byte[]> columnQualifiers;
public static Admin getConnection() throws IOException {
if (conn == null) {
conn = ConnectionFactory.createConnection(HBaseConfiguration.create());
}
return conn.getAdmin();
}
public static void main(String args[]) throws IOException {
getConnection();
scan(args[0], args[1]);
columnQualifiers.forEach((k) -> System.out.println("Column Qualifier : " + Bytes.toString(k)));
}
public static void scan(String tableName, String columnFamily) throws IOException {
System.out.println("Table Name : " + tableName);
Table table = conn.getTable(TableName.valueOf(tableName));
Scan scan = new Scan();
scan.addFamily(Bytes.toBytes(columnFamily));
ResultScanner rs = table.getScanner(scan);
while(rs.iterator().hasNext()){
rs.forEach((k)-> columnQualifiers = k.getFamilyMap(Bytes.toBytes(columnFamily)).keySet());
}
}
}
注意:在类路径中添加hadoop和hbase jar以及hbase-site.xml