Project

General

Profile

« Previous | Next » 

Revision 57428

Hadoop Job for propagation of community results through organization

View differences:

modules/dnet-openaireplus-profiles/trunk/src/main/resources/eu/dnetlib/test/profiles/HadoopJobConfigurationDSResources/HadoopJobConfigurationDSResourceType/propagationResultToCommunityThroughOrganizationJob.xml
1
<RESOURCE_PROFILE>
2
    <HEADER>
3
        <RESOURCE_IDENTIFIER value="404f8175-02a2-4b1f-9130-6216598716e7_SGFkb29wSm9iQ29uZmlndXJhdGlvbkRTUmVzb3VyY2VzL0hhZG9vcEpvYkNvbmZpZ3VyYXRpb25EU1Jlc291cmNlVHlwZQ=="/>
4
        <RESOURCE_TYPE value="HadoopJobConfigurationDSResourceType"/>
5
        <RESOURCE_KIND value="HadoopJobConfigurationDSResources"/>
6
        <RESOURCE_URI value=""/>
7
        <DATE_OF_CREATION value="2019-08-07T14:39:58+00:00"/>
8
    </HEADER>
9
    <BODY>
10
        <HADOOP_JOB name="propagationResultToCommunityThroughOrganization" type="mapreduce">
11
            <DESCRIPTION>map reduce job that propagates result to a community through the affiliation to organizations</DESCRIPTION>
12
            <STATIC_CONFIGURATION><!-- I/O FORMAT -->
13
                <PROPERTY key="mapreduce.inputformat.class" value="org.apache.hadoop.hbase.mapreduce.TableInputFormat"/>
14
                <PROPERTY key="mapreduce.outputformat.class" value="org.apache.hadoop.hbase.mapreduce.TableOutputFormat"/><!-- MAPPER -->
15
                <PROPERTY key="mapreduce.map.class" value="eu.dnetlib.data.mapreduce.hbase.propagation.communitythroughorganization.PropagationCommunityThroughOrganizationMapper"/>
16
                <PROPERTY key="mapred.mapoutput.key.class" value="org.apache.hadoop.hbase.io.ImmutableBytesWritable"/>
17
                <PROPERTY key="mapred.mapoutput.value.class" value="org.apache.hadoop.io.Text"/><!-- REDUCER -->
18
                <PROPERTY key="mapreduce.reduce.class" value="eu.dnetlib.data.mapreduce.hbase.propagation.communitythroughorganization.PropagationCommunityThroughOrganizationReducer"/>
19
                <PROPERTY key="mapred.output.key.class" value="org.apache.hadoop.hbase.io.ImmutableBytesWritable"/>
20
                <PROPERTY key="mapred.output.value.class" value="org.apache.hadoop.io.Text"/><!-- MISC -->
21
                <PROPERTY key="mapred.compress.map.output" value="true"/>
22
                <PROPERTY key="mapred.map.tasks.speculative.execution" value="false"/>
23
                <PROPERTY key="mapreduce.map.speculative" value="false"/>
24
                <PROPERTY key="mapreduce.reduce.speculative" value="false"/>
25
                <PROPERTY key="mapred.reduce.tasks.speculative.execution" value="false"/>
26
                <PROPERTY key="mapred.reduce.tasks" value="20"/><!-- <PROPERTY key="user.name" value="dnet" /> --><!--  	Uncomment to override the default lib path --><!--<PROPERTY key="job.lib" value="/user/dnet/openaire/dnet-mapreduce-jobs-assembly-country_propagation-1.1.1-SNAPSHOT.jar"/>-->
27
                <PROPERTY key="job.lib" value="/lib/dnet/snapshots/propagation_community2organization.jar"/>
28
            </STATIC_CONFIGURATION>
29
            <JOB_INTERFACE>
30
                <PARAM description="source hbase table" name="hbase.mapred.inputtable" required="true"/>
31
                <PARAM description="target hbase table" name="hbase.mapred.outputtable" required="true"/>
32
                <PARAM description="source hbase table" name="hbase.mapreduce.inputtable" required="true"/>
33
                <PARAM description="target hbase table" name="hbase.mapreduce.outputtable" required="true"/>
34
                <!--add needed param to get association between community and organization -->
35
                <PARAM description="map organization to communities" name="organization.community.map" required="true"/>
36
            </JOB_INTERFACE>
37
            <SCAN>
38
                <FILTERS/>
39
                <FAMILIES/>
40
            </SCAN>
41
        </HADOOP_JOB>
42
        <STATUS>
43
            <LAST_SUBMISSION_DATE value="2019-08-07T14:50:14+00:00"/>
44
            <RUNNING_INSTANCES value="2"/>
45
            <CUMULATIVE_RUN value="34"/>
46
        </STATUS>
47
        <SECURITY_PARAMETERS>SECURITY_PARAMETERS</SECURITY_PARAMETERS>
48
    </BODY>
49
</RESOURCE_PROFILE>
modules/dnet-openaireplus-profiles/trunk/src/main/resources/eu/dnetlib/test/profiles/HadoopJobConfigurationDSResources/HadoopJobConfigurationDSResourceType/propagationResultToCommunityThorughOrganizationSaveToFileJob.xml
1
<RESOURCE_PROFILE>
2
    <HEADER>
3
        <RESOURCE_IDENTIFIER value="c5f60933-2582-4f73-86b7-810ab4ba4c7e_SGFkb29wSm9iQ29uZmlndXJhdGlvbkRTUmVzb3VyY2VzL0hhZG9vcEpvYkNvbmZpZ3VyYXRpb25EU1Jlc291cmNlVHlwZQ=="/>
4
        <RESOURCE_TYPE value="HadoopJobConfigurationDSResourceType"/>
5
        <RESOURCE_KIND value="HadoopJobConfigurationDSResources"/>
6
        <RESOURCE_URI value=""/>
7
        <DATE_OF_CREATION value="2019-07-12T12:34:20+00:00"/>
8
    </HEADER>
9
    <BODY>
10
        <HADOOP_JOB name="propagationResultToCommunityThroughOrganizationSaveToFile" type="mapreduce">
11
            <DESCRIPTION>map reduce job that propagates result to a community through the affiliation to organizations</DESCRIPTION>
12
            <STATIC_CONFIGURATION><!-- I/O FORMAT -->
13
                <PROPERTY key="mapreduce.inputformat.class" value="org.apache.hadoop.hbase.mapreduce.TableInputFormat"/>
14
                <PROPERTY key="mapreduce.outputformat.class" value="org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat"/><!-- MAPPER -->
15
                <PROPERTY key="mapreduce.map.class" value="eu.dnetlib.data.mapreduce.hbase.propagation.communitythroughorganization.PropagationCommunityThroughOrganizationMapper"/>
16
                <PROPERTY key="mapred.mapoutput.key.class" value="org.apache.hadoop.hbase.io.ImmutableBytesWritable"/>
17
                <PROPERTY key="mapred.mapoutput.value.class" value="org.apache.hadoop.io.Text"/><!-- REDUCER -->
18
                <PROPERTY key="mapreduce.reduce.class" value="eu.dnetlib.data.mapreduce.hbase.propagation.communitythroughorganization.PropagationCommunityThroughOrganizationFileReducer"/>
19
                <PROPERTY key="mapred.output.key.class" value="org.apache.hadoop.io.Text"/>
20
                <PROPERTY key="mapred.output.value.class" value="org.apache.hadoop.io.Text"/><!-- MISC -->
21
                <PROPERTY key="mapred.compress.map.output" value="true"/>
22
                <PROPERTY key="mapred.map.tasks.speculative.execution" value="false"/>
23
                <PROPERTY key="mapreduce.map.speculative" value="false"/>
24
                <PROPERTY key="mapreduce.reduce.speculative" value="false"/>
25
                <PROPERTY key="mapred.reduce.tasks.speculative.execution" value="false"/>
26
                <PROPERTY key="mapred.reduce.tasks" value="1"/><!-- <PROPERTY key="user.name" value="dnet" /> --><!--  	Uncomment to override the default lib path --><!--<PROPERTY key="job.lib" value="/user/dnet/openaire/dnet-mapreduce-jobs-assembly-country_propagation-1.1.1-SNAPSHOT.jar"/>-->
27
                <PROPERTY key="job.lib" value="/lib/dnet/snapshots/propagation_community2organization.jar"/>
28
            </STATIC_CONFIGURATION>
29
            <JOB_INTERFACE>
30
                <PARAM description="source hbase table" name="hbase.mapred.inputtable" required="true"/>
31
                <PARAM description="target hbase table" name="hbase.mapred.outputtable" required="true"/>
32
                <PARAM description="source hbase table" name="hbase.mapreduce.inputtable" required="true"/>
33
                <PARAM description="target hbase table" name="hbase.mapreduce.outputtable" required="true"/><!--<PARAM name="countryPropagation.conf" required="true" description="configuration for country propagation" />-->
34
                <PARAM description="target sequence file on hdfs" name="mapred.output.dir" required="true"/>
35
                <!--add needed param to get association between community and organization -->
36
                <PARAM description="map organization to communities" name="organization.community.map" required="true"/>
37
            </JOB_INTERFACE>
38
            <SCAN>
39
                <FILTERS/>
40
                <FAMILIES/>
41
            </SCAN>
42
        </HADOOP_JOB>
43
        <STATUS>
44
            <LAST_SUBMISSION_DATE value="2019-08-06T16:02:35+00:00"/>
45
            <RUNNING_INSTANCES value="1"/>
46
            <CUMULATIVE_RUN value="43"/>
47
        </STATUS>
48
        <SECURITY_PARAMETERS>SECURITY_PARAMETERS</SECURITY_PARAMETERS>
49
    </BODY>
50
</RESOURCE_PROFILE>
51

  

Also available in: Unified diff