Page History

...

Code Block

title	PGEConfig.xml

<?xml version="1.0" encoding="UTF-8"?>
<pgeConfig>

        <!-- How to run the PGE -->
        <exe dir="[JobDir]" shell="/bin/bash">
          <!-- cd to PGE root -->
          <cmd>cd [PGE_ROOT]/file_concatenator</cmd>
              	<cmd>cp [InputFile1] [OutputFile]</cmd>
              	<cmd>cat [InputFile2] >> [OutputFile]</cmd>
        </exe>

	    <!-- Files to ingest -->
	    <output>
        	<!-- one or more of these -->
       	 	<dir path="[JobDir]" createBeforeExe="false">
            
            	<!-- one or more of these ** regExp or name can be used-->
            	<files regExp=".*\.txt" metFileWriterClass="org.apache.oodt.pge.examples.fileconcatenator.writers.ConcactenatingFilenameExtractorWriter"  args="[PGE_ROOT]/file_concatenator/extractors/concatenatingfilename.extractor.config.xml"/>
                <files regExp=".*\.txt" metFileWriterClass="org.apache.oodt.cas.pge.writers.metlist.MetadataListPcsMetFileWriter" args="[PGE_ROOT]/file_concatenator/extractors/metlistwriter/metout.xml"/>
            </dir>
        </output>

  <!--      <!-- Custom Custom metadata to add to output files -->
        <customMetadata>
                <!-- helpful keys -->
                <metadata key="LessThan" val="&#x3C;"/>
                <metadata key="LessThanOrEqualTo" val="[LessThan]="/>
                <metadata key="GreaterThan" val="&#x3E;"/>
                <metadata key="GreaterThanOrEqualTo" val="[GreaterThan]="/>
            "/>
    <metadata key="Exclamation" val="&#33;"/>
                <metadata key="Ampersand" val="&#38;"/>
                <metadata key="NotEqualTo" val="[Ampersand]="/>
                <metadata key="LogicalAnd" val="[Ampersand][Ampersand]"/>
          >
      <metadata key="CshPipeToStdOutAndError" val="[GreaterThan][Ampersand][Exclamation]"/>

				    <metadata key="ProductionDateTime" val="[DATE.UTC]"/>
				    <metadata key="JobDir" val="[PGE_ROOT]/file_concatenator/output/jobs/job-[ProductionDateTime]"/>
				    <metadata key="InputFile1" val="[PGE_ROOT]/file_concatenator/files/concatenatingInputFile1.txt"/>
				    <metadata key="InputFile2" val="[PGE_ROOT]/file_concatenator/files/concatenatingInputFile2.txt"/>
				    <metadata key="OutputFile" val="[JobDir]/concatenatedOutputFile-[ProductionDateTime].txt"/>        
      </customMetadata>

</pgeConfig>

...

Navigate to your deployed CAS-Workflow’s policy directory
No Format
cd $WORKFLOW_HOME/policy

Modify events.xml
Add the following entry to this file:

Code Block

title	events.xml

    <event name="fileconcatenator-pge">
    	<workflow id="urn:oodt:FileConcatenatorWorkflow"/>
    </event>

Create a new policy file titled: fileconcatenator-pge.workflow.xml.
Add the following entries to this file:

Code Block

title	fileconcatenator-pge.workflow.xml

    <cas:workflow xmlns:cas="http://oodt.jpl.nasa.gov/1.0/cas"
      name="FileConcatenatorWorkflow"
      id="urn:oodt:FileConcatenatorWorkflow">
      
      <tasks>
      	<task id="urn:oodt:FileConcatenator"/>
      </tasks>
    </cas:workflow>

Modify tasks.xml
Add the following entries to this file:

Code Block

title	tasks.xml

   <task id="urn:oodt:FileConcatenator" name="FileConcatenator"
     class="org.apache.oodt.pge.examples.fileconcatenator.FileConcatenatorPGETask">

     <conditions/>

     <configuration>
        <property name="PGETask_Name" value="FileConcatenator"/>
        <property name="PGETask_ConfigFilePath" value="[PGE_ROOT]/file_concatenator/pge-configs/PGEConfig.xml" envReplace="true"/>
        <property name="PGETask_DumpMetadata" value="true"/>
        />
        <property name="PCS_WorkflowManagerUrl" value="[WORKFLOW_URL]" envReplace="true" />
                <property name="PCS_FileManagerUrl"     value="[FILEMGR_URL]" envReplace="true"/>
                <property name="PCS_MetFileExtension" value="met"/>
                <property name="PCS_ClientTransferServiceFactory" value="org.apache.oodt.cas.filemgr.datatransfer.LocalDataTransferFactory"/>
        <property name="PCS_ActionRepoFile" value="file:[CRAWLER_HOME]/policy/crawler-config.xml" envReplace="true"/>
        </configuration>

        <requiredMetFields>
                <metfield name="RunID"/>
        </requiredMetFields>

   </task>

Modify workflow-lifecycles.xml
Add the following entries to this file (if not already present):

Code Block

title	workflow-lifecycles.xml

  <stage name="pge_setup_build_config_file">
    <status>BUILDING CONFIG FILE</status>
  </stage>
  <stage name="pge_staging_input">
    <status>STAGING INPUT</status>
  </stage>
  <stage name="pge_exec">
    <status>PGE EXEC</status>
  </stage>
  <stage name="pcs_crawl">
    <status>CRAWLING</status>
  </stage>

Modify workflow-instance-met.xml
Add the following entry to this file:
Code Block
title workflow-instance-met.xml
<workflow id="urn:oodt:FileConcatenatorWorkflow"> <field name="RunID"/> </workflow>
Restart CAS-Workflow
No Format
cd $WORKFLOW_HOME/bin ./wmgr restart

...

Space shortcuts

Page tree

Versions Compared

Old Version 2

New Version 3

Key