1 |
53707
|
claudio.at
|
<RESOURCE_PROFILE>
|
2 |
|
|
<HEADER>
|
3 |
|
|
<RESOURCE_IDENTIFIER value="16845094-5871-4584-b934-590b5d005836_SGFkb29wSm9iQ29uZmlndXJhdGlvbkRTUmVzb3VyY2VzL0hhZG9vcEpvYkNvbmZpZ3VyYXRpb25EU1Jlc291cmNlVHlwZQ=="/>
|
4 |
|
|
<RESOURCE_TYPE value="HadoopJobConfigurationDSResourceType"/>
|
5 |
|
|
<RESOURCE_KIND value="HadoopJobConfigurationDSResources"/>
|
6 |
|
|
<RESOURCE_URI value=""/>
|
7 |
|
|
<DATE_OF_CREATION value="2018-10-22T10:34:48+00:00"/>
|
8 |
|
|
</HEADER>
|
9 |
|
|
<BODY>
|
10 |
|
|
<HADOOP_JOB name="xmlRecordCounterJob" type="mapreduce">
|
11 |
|
|
<DESCRIPTION>map only job that count information from the index xml records</DESCRIPTION>
|
12 |
|
|
<STATIC_CONFIGURATION><!-- I/O FORMAT -->
|
13 |
|
|
<PROPERTY key="mapreduce.inputformat.class" value="org.apache.hadoop.mapreduce.lib.input.SequenceFileInputFormat"/>
|
14 |
|
|
<PROPERTY key="mapreduce.outputformat.class" value="org.apache.hadoop.mapreduce.lib.output.NullOutputFormat"/><!-- MAPPER -->
|
15 |
|
|
<PROPERTY key="mapreduce.map.class" value="eu.dnetlib.data.mapreduce.hbase.index.CountXmlRecordsMapper"/>
|
16 |
|
|
<PROPERTY key="mapred.mapoutput.key.class" value="org.apache.hadoop.io.NullWritable"/>
|
17 |
|
|
<PROPERTY key="mapred.mapoutput.value.class" value="org.apache.hadoop.io.NullWritable"/><!-- JOB GLOBAL -->
|
18 |
|
|
<PROPERTY key="mapred.output.key.class" value="org.apache.hadoop.io.NullWritable"/>
|
19 |
|
|
<PROPERTY key="mapred.output.value.class" value="org.apache.hadoop.io.NullWritable"/><!-- MISC -->
|
20 |
|
|
<PROPERTY key="mapred.map.tasks.speculative.execution" value="false"/>
|
21 |
|
|
<PROPERTY key="mapreduce.map.speculative" value="false"/>
|
22 |
|
|
<PROPERTY key="mapred.reduce.tasks" value="0"/><!-- <PROPERTY key="user.name" value="dnet" /> --><!-- Uncomment to override the default lib path -->
|
23 |
|
|
<!-- <PROPERTY key="job.lib" value="/lib/dnet/snapshots/dnet-mapreduce-jobs-assembly-1.1.4-BETA-SNAPSHOT-FilterXmlRecordsMapper.jar"/> -->
|
24 |
|
|
</STATIC_CONFIGURATION>
|
25 |
|
|
<JOB_INTERFACE>
|
26 |
|
|
<PARAM description="input sequence file" name="mapred.input.dir" required="true"/>
|
27 |
|
|
</JOB_INTERFACE>
|
28 |
|
|
</HADOOP_JOB>
|
29 |
|
|
<STATUS>
|
30 |
|
|
<LAST_SUBMISSION_DATE value="2018-10-22T10:35:08+00:00"/>
|
31 |
|
|
<RUNNING_INSTANCES value="0"/>
|
32 |
|
|
<CUMULATIVE_RUN value="20"/>
|
33 |
|
|
</STATUS>
|
34 |
|
|
<SECURITY_PARAMETERS>SECURITY_PARAMETERS</SECURITY_PARAMETERS>
|
35 |
|
|
</BODY>
|
36 |
|
|
</RESOURCE_PROFILE>
|