Project

General

Profile

1 39222 claudio.at
<?xml version="1.0" encoding="UTF-8"?>
2
<RESOURCE_PROFILE xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
3
	<HEADER>
4 48139 alessia.ba
		<RESOURCE_IDENTIFIER value="452dc13e-0544-478b-8b23-bc3f90cc7531_V29ya2Zsb3dEU1Jlc291cmNlcy9Xb3JrZmxvd0RTUmVzb3VyY2VUeXBl"/>
5
		<RESOURCE_TYPE value="WorkflowDSResourceType"/>
6
		<RESOURCE_KIND value="WorkflowDSResources"/>
7
		<RESOURCE_URI value=""/>
8
		<DATE_OF_CREATION value="2006-05-04T18:13:51.0Z"/>
9 39222 claudio.at
	</HEADER>
10
	<BODY>
11 39302 claudio.at
		<WORKFLOW_NAME>Export HBase Table</WORKFLOW_NAME>
12 39222 claudio.at
		<WORKFLOW_TYPE>IIS</WORKFLOW_TYPE>
13
		<WORKFLOW_PRIORITY>30</WORKFLOW_PRIORITY>
14
		<CONFIGURATION start="manual">
15 48139 alessia.ba
			<NODE name="setCsvPath" type="SetEnvParameter" isStart="true">
16 39222 claudio.at
				<DESCRIPTION>Set the CSV file path on HDFS</DESCRIPTION>
17
				<PARAMETERS>
18
					<PARAM managedBy="system" name="parameterName" required="true" type="string">csvPath</PARAM>
19
					<PARAM managedBy="user" name="parameterValue" required="true" type="string"></PARAM>
20
				</PARAMETERS>
21
				<ARCS>
22 48139 alessia.ba
					<ARC to="cleanupCsv"/>
23 39222 claudio.at
				</ARCS>
24
			</NODE>
25 48139 alessia.ba
26 39222 claudio.at
			<NODE name="hadoopConfig" type="SetClusterAndTable" isStart="true">
27
				<DESCRIPTION>Set table name</DESCRIPTION>
28
				<PARAMETERS>
29
					<PARAM required="true" type="string" name="cluster" managedBy="system">DM</PARAM>
30
					<PARAM required="true" type="string" name="tableParam" managedBy="system">tableName</PARAM>
31
					<PARAM required="true" type="string" name="table" managedBy="user"/>
32
				</PARAMETERS>
33
				<ARCS>
34 48139 alessia.ba
					<ARC to="cleanupCsv"/>
35 39222 claudio.at
				</ARCS>
36 48139 alessia.ba
			</NODE>
37
38 39222 claudio.at
			<NODE name="cleanupCsv" type="DeleteHdfsPathJob" isJoin="true">
39
				<DESCRIPTION>CSV files cleanup</DESCRIPTION>
40
				<PARAMETERS>
41
					<PARAM required="true" type="string" name="envParams" managedBy="system">
42 48139 alessia.ba
						{
43
						'path' : 'csvPath',
44
						'cluster' : 'cluster'
45 39222 claudio.at
						}
46 48139 alessia.ba
					</PARAM>
47 39222 claudio.at
				</PARAMETERS>
48
				<ARCS>
49 48139 alessia.ba
					<ARC to="export"/>
50 39222 claudio.at
				</ARCS>
51
			</NODE>
52 48139 alessia.ba
53 39222 claudio.at
			<NODE name="export" type="SubmitHadoopJob">
54
				<DESCRIPTION>export the information space as sequence file</DESCRIPTION>
55
				<PARAMETERS>
56
					<PARAM required="true" type="string" name="hadoopJob" managedBy="system">informationSpaceExportJob</PARAM>
57
					<PARAM required="true" type="string" name="envParams" managedBy="system">
58 48139 alessia.ba
						{
59
						'cluster' : 'cluster',
60
						'hbase.mapred.inputtable' : 'tableName',
61
						'hbase.mapreduce.inputtable' : 'tableName',
62
						'mapred.output.dir' : 'csvPath'
63 39222 claudio.at
						}
64
					</PARAM>
65
				</PARAMETERS>
66
				<ARCS>
67 48139 alessia.ba
					<ARC to="success"/>
68 39222 claudio.at
				</ARCS>
69
			</NODE>
70
		</CONFIGURATION>
71 48139 alessia.ba
		<STATUS/>
72 39222 claudio.at
	</BODY>
73
</RESOURCE_PROFILE>
74
75
76
77
78