php通过thrift获取hadoop资源

php可以通过thrift连接hbase,同样php可以通过thrift读取hadoop资源(HDFS资源)。
准备:
php需要thrift的libary
packages:hadoop-0.20.2\src\contrib\thriftfs\gen-php
源码:
<?php
	$GLOBALS['THRIFT_ROOT'] = ROOTPATH . '/lib/thrift';
	require_once($GLOBALS['THRIFT_ROOT'].'/Thrift.php');
	require_once($GLOBALS['THRIFT_ROOT'].'/transport/TSocket.php');
	require_once($GLOBALS['THRIFT_ROOT'].'/transport/TBufferedTransport.php');
	require_once($GLOBALS['THRIFT_ROOT'].'/protocol/TBinaryProtocol.php');
	require_once($GLOBALS["THRIFT_ROOT"] . "/packages/hadoopfs/ThriftHadoopFileSystem.php");
	$hadoop_socket = new TSocket("localhost", 59256);
	$hadoop_socket -> setSendTimeout(10000); // Ten seconds
	$hadoop_socket -> setRecvTimeout(20000); // Twenty seconds
	$hadoop_transport = new TBufferedTransport($hadoop_socket);
	$hadoop_protocol = new TBinaryProtocol($hadoop_transport);
	$hadoopClient = new ThriftHadoopFileSystemClient($hadoop_protocol);
	$hadoop_transport -> open();
	try {
		// create directory
		$dirpathname = new hadoopfs_Pathname(array("pathname" => "/user/root/hadoop"));
		if($hadoopClient -> exists($dirpathname) == TRUE) {
			echo $dirpathname -> pathname . " exists.\n";
		} else {
			$result = $hadoopClient -> mkdirs($dirpathname);
		}
		// put file
		$filepathname = new hadoopfs_Pathname(array("pathname" => $dirpathname -> pathname . "/hello.txt"));
		$localfile = fopen("hello.txt", "rb");
		$hdfsfile = $hadoopClient -> create($filepathname);
		while(true) {
			$data = fread($localfile, 1024);
			if(strlen($data) == 0)
				break;
			$hadoopClient -> write($hdfsfile, $data);
		}
		$hadoopClient -> close($hdfsfile);
		fclose($localfile);
		// get file
		echo "read file:\n";
		print_r($filepathname);
		$data = "";
		$hdfsfile = $hadoopClient -> open($filepathname);
		print_r($hdfsfile);
		while(true) {
			$data = $hadoopClient -> read($hdfsfile, 0, 1024);
			if(strlen($data) == 0)
				break;
			print $data;
		}
		$hadoopClient -> close($hdfsfile);
		echo "listStatus:\n";
		$result = $hadoopClient -> listStatus($dirpathname);
		print_r($result);
		foreach($result as $key => $value) {
			if($value -> isdir == "1")
				print "dir\t";
			else
				print "file\t";
			print $value -> block_replication . "\t" . $value -> length . "\t" . $value -> modification_time . "\t" . $value -> permission . "\t" . $value -> owner . "\t" . $value -> group . "\t" . $value -> path . "\n";
		}
		$hadoop_transport -> close();
	} catch(Exception $e) {
		print_r($e);
	}
?>

启动hadoop的thrift
hadoop-0.20.2\src\contrib\thriftfs\scripts\start_thrift_server.sh 59256

problem one:
在系统目录创建文件,而不是在hadoop目录中创建文件
原因:
thrift启动时加载默认的配置文件
解决方法:
修改start_thrift_server.sh文件
TOP=/usr/local/hadoop-0.20.2
CLASSPATH=$CLASSPATH:$TOP/conf

problem two:
java.lang.NullPointerException
    at     org.apache.hadoop.thriftfs.HadoopThriftServer$HadoopThriftHandler.write(HadoopThriftServer.java:282)
at     org.apache.hadoop.thriftfs.api.ThriftHadoopFileSystem$Processor$write.process(Unknown Source)
at org.apache.hadoop.thriftfs.api.ThriftHadoopFileSystem$Processor.process(Unknown Source)
at com.facebook.thrift.server.TThreadPoolServer$WorkerProcess.run(Unknown Source)
at         java.util.concurrent.ThreadPoolExecutor$Worker.runTask(ThreadPoolExecutor.java:886)
at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:908)
at java.lang.Thread.run(Thread.java:662)
原因:
java返回的map hash id为long类型,而php(32位)无法存储long类型的数据,导致转换成float数据后丢失精度。
private long nextId = new Random().nextLong();
java返回数据:4207488029786584864
php获取数据:4.2074880297866E+18
java获得php传递数据:4207488029786585088
解决方法:
修改hadoop-0.20.2\src\contrib\thriftfs\if\hadoopfs.thrift文件
修改
struct ThriftHandle {
  i64 id
}

struct ThriftHandle {
  string id
}
重新生成php packages
thrift --gen php hadoopfs.thrift
修改org.apache.hadoop.thriftfs.api.ThriftHandle类
修改
public long id;
为:
public String id;
修改相应的程序
org.apache.hadoop.thriftfs.HadoopThriftServer
修改
long id = insert(out);
ThriftHandle obj = new ThriftHandle(id);

long id = insert(out);
String _id = String.valueOf(id);
ThriftHandle obj = new ThriftHandle(_id);
修改相应的程序
重新打包,启动hadoop的thrift:
hadoop-0.20.2\src\contrib\thriftfs\scripts\start_thrift_server.sh 59256

这样php就可以连接并且获取hadoop中的资源了

猜你喜欢

转载自zhangcs053.iteye.com/blog/1213564