Hbase Java API: Retrieving all rows that match a P

问题:

In the Python module happybase, I can retrieve all rows that have a row key starting with a given string (i.e, search using a partial row key).

Let's say I have a rowkey in the format of (ID|TYPE|DATE), I would be able to find all rows with an ID of 1 and a TYPE of A by:

import happybase
connection = happybase.Connection('hmaster-host.com')
table = connection.table('table_name')
for key, data in table.scan(row_prefix="1|A|"):
    print key, data

This is what I have so far as a totally client side Java program for anyone trying to do the basics using the Java HBase API, but I can only search for a row using the full row key:

import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.client.Get;
import org.apache.hadoop.hbase.client.HTable;
import org.apache.hadoop.hbase.client.Result;
import org.apache.hadoop.hbase.util.Bytes;
//class foo {
public static void main(String[] args) {
    Configuration conf = new Configuration();
    conf.addResource(new Path("C:\\core-site.xml"));
    conf.addResource(new Path("C:\\hbase-site.xml"));
    HTable table = new HTable(conf, "table_name");
    Result row = table.get(new Get(Bytes.toBytes("1|A|2014-01-01 00:00")));
    printRow(row); 
}
public static void printRow(Result result) {
    String returnString = "";
    returnString += Bytes.toString(result.getValue(Bytes.toBytes("cf"), Bytes.toBytes("id"))) + ", ";
    returnString += Bytes.toString(result.getValue(Bytes.toBytes("cf"), Bytes.toBytes("type"))) + ", ";
    returnString += Bytes.toString(result.getValue(Bytes.toBytes("cf"), Bytes.toBytes("date")));
    System.out.println(returnString);
}
//}

Where "cf" is the name of the column family.

ANSWER:

import java.io.IOException;
import java.util.Iterator;
import org.apache.hadoop.conf.Configuration;
import org.apache.hadoop.fs.Path;
import org.apache.hadoop.hbase.client.HTable;
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.Filter;
import org.apache.hadoop.hbase.filter.PrefixFilter;
import org.apache.hadoop.hbase.util.Bytes;
//class foo {
public static void main(String[] args) {
    Configuration conf = new Configuration();
    conf.addResource(new Path("C:\\core-site.xml"));
    conf.addResource(new Path("C:\\hbase-site.xml"));
    HTable table = new HTable(conf, "table_name");
    byte[] prefix = Bytes.toBytes("1|A|");
    Scan scan = new Scan(prefix);
    Filter prefixFilter = new PrefixFilter(prefix);
    scan.setFilter(prefixFilter);
    ResultScanner resultScanner = table.getScanner(scan);
    printRows(resultScanner);
    //Result row = table.get(new Get(Bytes.toBytes("1|A|2014-01-01 00:00")));
    //printRow(row); 
}
public static void printRows(ResultScanner resultScanner) {
    for (Iterator<Result> iterator = results.iterator(); iterator.hasNext();) {
        printRow(iterator.next();
    }
}
public static void printRow(Result result) {
    String returnString = "";
    returnString += Bytes.toString(result.getValue(Bytes.toBytes("cf"), Bytes.toBytes("id"))) + ", ";
    returnString += Bytes.toString(result.getValue(Bytes.toBytes("cf"), Bytes.toBytes("type"))) + ", ";
    returnString += Bytes.toString(result.getValue(Bytes.toBytes("cf"), Bytes.toBytes("date")));
    System.out.println(returnString);
}
//}

Note that I use the setFilter method, whereas the answer below uses the addFilter method, on account of us using different APIs.

回答1:

You are using the HTable get operation so you're only getting back one row (note that you can specify a prefix here as well and you don't have to give the complete key)

If you want to get back multiple rows you should use a Scan

byte[] prefix=Bytes.toBytes("1|A|");
Scan scan = new Scan(prefix);
PrefixFilter prefixFilter = new PrefixFilter(prefix);
scan.addFilter(prefixFilter);
ResultScanner resultScanner = table.getScanner(scan);