這篇文章裏面我們介紹一下如果我們要想從ODPS裏面讀到數據並加工處理,有一種通道叫批量數據通道。這個需要在程序裏面做處理。寫一個非常簡單的示例程序:
import java.io.IOException;
import java.util.Date;
import com.aliyun.odps.Column;
import com.aliyun.odps.Odps;
import com.aliyun.odps.PartitionSpec;
import com.aliyun.odps.TableSchema;
import com.aliyun.odps.account.Account;
import com.aliyun.odps.account.AliyunAccount;
import com.aliyun.odps.data.Record;
import com.aliyun.odps.data.RecordReader;
import com.aliyun.odps.tunnel.TableTunnel;
import com.aliyun.odps.tunnel.TableTunnel.DownloadSession;
import com.aliyun.odps.tunnel.TunnelException;
public class DownloadSample {
private static String accessId = "<your access id>";
private static String accessKey = "<your access Key>";
private static String odpsUrl = "http://service.odps.aliyun.com/api";
private static String project = "<your project>";
private static String table = "<your table name>";
private static String partition = "<your partition spec>";
public static void main(String args[]) {
Account account = new AliyunAccount(accessId, accessKey);
Odps odps = new Odps(account);
odps.setEndpoint(odpsUrl);
odps.setDefaultProject(project);
TableTunnel tunnel = new TableTunnel(odps);
PartitionSpec partitionSpec = new PartitionSpec(partition);
try {
DownloadSession downloadSession = tunnel.createDownloadSession(project, table,
partitionSpec);
System.out.println("Session Status is : "
+ downloadSession.getStatus().toString());
long count = downloadSession.getRecordCount();
System.out.println("RecordCount is: " + count);
RecordReader recordReader = downloadSession.openRecordReader(0,
count);
Record record;
while ((record = recordReader.read()) != null) {
consumeRecord(record, downloadSession.getSchema());
}
recordReader.close();
} catch (TunnelException e) {
e.printStackTrace();
} catch (IOException e1) {
e1.printStackTrace();
}
}
private static void consumeRecord(Record record, TableSchema schema) {
for (int i = 0; i < schema.getColumns().size(); i++) {
Column column = schema.getColumn(i);
String colValue = null;
switch (column.getType()) {
case BIGINT: {
Long v = record.getBigint(i);
colValue = v == null ? null : v.toString();
break;
}
case BOOLEAN: {
Boolean v = record.getBoolean(i);
colValue = v == null ? null : v.toString();
break;
}
case DATETIME: {
Date v = record.getDatetime(i);
colValue = v == null ? null : v.toString();
break;
}
case DOUBLE: {
Double v = record.getDouble(i);
colValue = v == null ? null : v.toString();
break;
}
case STRING: {
String v = record.getString(i);
colValue = v == null ? null : v.toString();
break;
}
default:
throw new RuntimeException("Unknown column type: "
+ column.getType());
}
System.out.print(colValue == null ? "null" : colValue);
if (i != schema.getColumns().size())
System.out.print("\t");
}
System.out.println();
}
}
使用這種方法最大的一個好處就是避免通過SDK讀的時候會有行限制。所以使用SDK的方法會有問題。建議採用這種方式去讀數據。
進一步優化的,如果讀到的數據量非常大比如百萬條,那處理的時候不可能等它全部處理完。可能需要一邊讀數據,一邊處理,採用流式計算來做。
參考如下代碼: