| <?xml version="1.0" encoding="UTF-8"?> |
| |
| <pgeConfig> |
| |
| <!-- How to run the PGE --> |
| <exe dir="[JobDir]" shell="/bin/bash"> |
| <cmd>export PATH=$HOME/bin/:${PATH}</cmd> |
| <cmd>shopt -s expand_aliases</cmd> |
| <cmd>echo "Creating working dirs"</cmd> |
| <cmd>mkdir [JobInputDir] ; mkdir [JobOutputDir]; mkdir [JobLogDir]</cmd> |
| <cmd>echo "Running RAT aggregator"</cmd> |
| <cmd>[RatAggregatorScript] `python -c "print(' '.join('[InputFiles]'.split(',')))"` > [JobOutputDir]/rat_aggregate_stats_[DateMilis].csv</cmd> |
| </exe> |
| |
| <!-- Files to ingest --> |
| <output> |
| <!-- one or more of these --> |
| <dir path="[JobOutputDir]" createBeforeExe="false"> |
| <files regExp=".*\.csv" metFileWriterClass="org.apache.oodt.cas.pge.writers.metlist.MetadataListPcsMetFileWriter" args="[DRAT_HOME]/pge/policy/metout/rat_aggregate_log_metout.xml"/> |
| </dir> |
| |
| </output> |
| |
| <!-- Custom metadata to add to output files --> |
| <customMetadata> |
| <!-- helpful keys --> |
| <metadata key="LessThan" val="<"/> |
| <metadata key="LessThanOrEqualTo" val="[LessThan]="/> |
| <metadata key="GreaterThan" val=">"/> |
| <metadata key="GreaterThanOrEqualTo" val="[GreaterThan]="/> |
| <metadata key="Exclamation" val="!"/> |
| <metadata key="Ampersand" val="&"/> |
| <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="DateMilis" val="[DATE_TO_MILLIS([ProductionDateTime],UTC_FORMAT,1970-01-01)]"/> |
| <metadata key="JobDir" val="[DRAT_HOME]/data/jobs/rataggregate/[DateMilis]"/> |
| <metadata key="JobInputDir" val="[JobDir]/input"/> |
| <metadata key="JobOutputDir" val="[JobDir]/output"/> |
| <metadata key="JobLogDir" val="[JobDir]/logs"/> |
| <metadata key="ProductType" val="RatAggregateLog"/> |
| <metadata key="InputFiles" val="SQL(FORMAT='$FileLocation/$Filename',SORT_BY='CAS.ProductReceivedTime'){SELECT FileLocation,Filename,CAS.ProductReceivedTime FROM RatLog}"/> |
| </customMetadata> |
| |
| </pgeConfig> |