Revision 48139
Added by Alessia Bardi almost 7 years ago
exportHBaseTable.xml | ||
---|---|---|
1 | 1 |
<?xml version="1.0" encoding="UTF-8"?> |
2 | 2 |
<RESOURCE_PROFILE xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"> |
3 | 3 |
<HEADER> |
4 |
<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" />
|
|
4 |
<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 | 9 |
</HEADER> |
10 | 10 |
<BODY> |
11 | 11 |
<WORKFLOW_NAME>Export HBase Table</WORKFLOW_NAME> |
12 | 12 |
<WORKFLOW_TYPE>IIS</WORKFLOW_TYPE> |
13 | 13 |
<WORKFLOW_PRIORITY>30</WORKFLOW_PRIORITY> |
14 | 14 |
<CONFIGURATION start="manual"> |
15 |
<NODE name="setCsvPath" type="SetEnvParameter" isStart="true">
|
|
15 |
<NODE name="setCsvPath" type="SetEnvParameter" isStart="true">
|
|
16 | 16 |
<DESCRIPTION>Set the CSV file path on HDFS</DESCRIPTION> |
17 | 17 |
<PARAMETERS> |
18 | 18 |
<PARAM managedBy="system" name="parameterName" required="true" type="string">csvPath</PARAM> |
19 | 19 |
<PARAM managedBy="user" name="parameterValue" required="true" type="string"></PARAM> |
20 | 20 |
</PARAMETERS> |
21 | 21 |
<ARCS> |
22 |
<ARC to="cleanupCsv" />
|
|
22 |
<ARC to="cleanupCsv"/> |
|
23 | 23 |
</ARCS> |
24 | 24 |
</NODE> |
25 |
|
|
25 |
|
|
26 | 26 |
<NODE name="hadoopConfig" type="SetClusterAndTable" isStart="true"> |
27 | 27 |
<DESCRIPTION>Set table name</DESCRIPTION> |
28 | 28 |
<PARAMETERS> |
... | ... | |
31 | 31 |
<PARAM required="true" type="string" name="table" managedBy="user"/> |
32 | 32 |
</PARAMETERS> |
33 | 33 |
<ARCS> |
34 |
<ARC to="cleanupCsv" />
|
|
34 |
<ARC to="cleanupCsv"/> |
|
35 | 35 |
</ARCS> |
36 |
</NODE>
|
|
37 |
|
|
36 |
</NODE> |
|
37 |
|
|
38 | 38 |
<NODE name="cleanupCsv" type="DeleteHdfsPathJob" isJoin="true"> |
39 | 39 |
<DESCRIPTION>CSV files cleanup</DESCRIPTION> |
40 | 40 |
<PARAMETERS> |
41 | 41 |
<PARAM required="true" type="string" name="envParams" managedBy="system"> |
42 |
{
|
|
43 |
'path' : 'csvPath',
|
|
44 |
'cluster' : 'cluster'
|
|
42 |
{ |
|
43 |
'path' : 'csvPath', |
|
44 |
'cluster' : 'cluster' |
|
45 | 45 |
} |
46 |
</PARAM>
|
|
46 |
</PARAM> |
|
47 | 47 |
</PARAMETERS> |
48 | 48 |
<ARCS> |
49 |
<ARC to="export" />
|
|
49 |
<ARC to="export"/> |
|
50 | 50 |
</ARCS> |
51 | 51 |
</NODE> |
52 |
|
|
52 |
|
|
53 | 53 |
<NODE name="export" type="SubmitHadoopJob"> |
54 | 54 |
<DESCRIPTION>export the information space as sequence file</DESCRIPTION> |
55 | 55 |
<PARAMETERS> |
56 | 56 |
<PARAM required="true" type="string" name="hadoopJob" managedBy="system">informationSpaceExportJob</PARAM> |
57 | 57 |
<PARAM required="true" type="string" name="envParams" managedBy="system"> |
58 |
{
|
|
59 |
'cluster' : 'cluster',
|
|
60 |
'hbase.mapred.inputtable' : 'tableName',
|
|
61 |
'hbase.mapreduce.inputtable' : 'tableName',
|
|
62 |
'mapred.output.dir' : 'csvPath'
|
|
58 |
{ |
|
59 |
'cluster' : 'cluster', |
|
60 |
'hbase.mapred.inputtable' : 'tableName',
|
|
61 |
'hbase.mapreduce.inputtable' : 'tableName', |
|
62 |
'mapred.output.dir' : 'csvPath' |
|
63 | 63 |
} |
64 | 64 |
</PARAM> |
65 | 65 |
</PARAMETERS> |
66 | 66 |
<ARCS> |
67 |
<ARC to="success" />
|
|
67 |
<ARC to="success"/> |
|
68 | 68 |
</ARCS> |
69 | 69 |
</NODE> |
70 | 70 |
</CONFIGURATION> |
71 |
<STATUS />
|
|
71 |
<STATUS/> |
|
72 | 72 |
</BODY> |
73 | 73 |
</RESOURCE_PROFILE> |
74 | 74 |
|
Also available in: Unified diff
integrated (hopefully) all required changes from dnet40