多线程下载示例__SDK示例_批量数据通道_大数据计算服务-阿里云
import java.io.IOException;import java.util.ArrayList;import java.util.Date;import java.util.List;import java.util.concurrent.Callable;import java.util.concurrent.ExecutionException;import java.util.concurrent.ExecutorService;import java.util.concurrent.Executors;import java.util.concurrent.Future;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;class DownloadThread implements Callable<Long> {private long id;private RecordReader recordReader;private TableSchema tableSchema;public DownloadThread(int id,RecordReader recordReader, TableSchema tableSchema) {this.id = id;this.recordReader = recordReader;this.tableSchema = tableSchema;}@Overridepublic Long call() {Long recordNum = 0L;try {Record record;while ((record = recordReader.read()) != null) {recordNum++;System.out.print("Thread " + id + "t");consumeRecord(record, tableSchema);}recordReader.close();} catch (IOException e) {e.printStackTrace();}return recordNum;}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();}}public class DownloadThreadSample {private static String accessId = "<your access id>";private static String accessKey = "<your access Key>";private static String odpsUrl = "https://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>";private static int threadNum = 10;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);DownloadSession downloadSession;try {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);ExecutorService pool = Executors.newFixedThreadPool(threadNum);ArrayList<Callable<Long>> callers = new ArrayList<Callable<Long>>();long start = 0;long step = count / threadNum;for (int i = 0; i < threadNum - 1; i++) {RecordReader recordReader = downloadSession.openRecordReader(step * i, step);callers.add(new DownloadThread( i, recordReader, downloadSession.getSchema()));}RecordReader recordReader = downloadSession.openRecordReader(step * (threadNum - 1), count- ((threadNum - 1) * step));callers.add(new DownloadThread( threadNum - 1, recordReader, downloadSession.getSchema()));Long downloadNum = 0L;List<Future<Long>> recordNum = pool.invokeAll(callers);for (Future<Long> num : recordNum)downloadNum += num.get();System.out.println("Record Count is: " + downloadNum);pool.shutdown();} catch (TunnelException e) {e.printStackTrace();} catch (IOException e) {e.printStackTrace();} catch (InterruptedException e) {e.printStackTrace();} catch (ExecutionException e) {e.printStackTrace();}}}
注意:对于tunnel endpoint,支持指定或者不指定。如果指定,按照指定的下载。如果不指定,按照我们的自动路由下载。
最后更新:2016-07-12 15:17:54
上一篇:
多线程上传示例__SDK示例_批量数据通道_大数据计算服务-阿里云
下一篇:
SQL 概要__SQL_大数据计算服务-阿里云
CreateVirtualMFADevice__用户管理接口_RAM API文档_访问控制-阿里云
防盗链__存储空间管理_最佳实践_对象存储 OSS-阿里云
SetListenerAccessControlStatus__Listener相关API_API 参考_负载均衡-阿里云
查询伸缩配置__伸缩配置_用户指南_弹性伸缩-阿里云
设置参数__实例管理_用户指南_云数据库 RDS 版-阿里云
为什么我的作业一直失败?__技术分享_技术运维问题_媒体转码-阿里云
邮箱设置___邮箱常见问题_企业邮箱-阿里云
GetCallerIdentity__操作接口_STS API文档_访问控制-阿里云
配置转发策略__实例管理_用户指南_负载均衡-阿里云
GroupDesc__数据类型_API文档_批量计算-阿里云
相关内容
常见错误说明__附录_大数据计算服务-阿里云
发送短信接口__API使用手册_短信服务-阿里云
接口文档__Android_安全组件教程_移动安全-阿里云
运营商错误码(联通)__常见问题_短信服务-阿里云
设置短信模板__使用手册_短信服务-阿里云
OSS 权限问题及排查__常见错误及排除_最佳实践_对象存储 OSS-阿里云
消息通知__操作指南_批量计算-阿里云
设备端快速接入(MQTT)__快速开始_阿里云物联网套件-阿里云
查询API调用流量数据__API管理相关接口_API_API 网关-阿里云
使用STS访问__JavaScript-SDK_SDK 参考_对象存储 OSS-阿里云