I'm trying to make a script to check if there is any file missing in a hdfs path. The idea is to include it in an oozie workflow that when no file is found fails and does not continue with the flow
ALTRAFI="/input/ALTrafi*.txt"
ALTDATOS="/ALTDatos*.txt"
ALTARVA="/ALTarva*.txt"
TRAFCIER="/TrafCier*.txt"
if hdfs dfs -test -e $ALTRAFI; then
echo "[$ALTRAFI] Archive not found"
exit 1
fi
if hdfs dfs -test -e $ALTDATOS; then
echo "[$ALTDATOS] Archive not found"
exit 2
fi
if hdfs dfs -test -e $ALTARVA; then
echo "[$ALTARVA] Archive not found"
exit 3
fi
if hdfs dfs -test -e $TRAFCIER; then
echo "[$TRAFCIER] Archive not found"
exit 4
fi
But the script does not fail when it does not find a file and continues the flow of the workflow in oozie
oozie flow:
<start to="ValidateFiles"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<action name="ValidateFiles">
<shell xmlns="uri:oozie:shell-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>mapred.job.queue.name</name>
<value>${queueName}</value>
</property>
<property>
<name>tez.lib.uris</name>
<value>/hdp/apps/2.5.0.0-1245/tez/tez.tar.gz</value>
</property>
</configuration>
<exec>/produccion/apps/traficotasado/ValidateFiles.sh</exec>
<file>/produccion/apps/traficotasado/ValidateFiles.sh#ValidateFiles.sh</file> <!--Copy the executable to compute node's current working directory -->
</shell>
<ok to="CopyFiles"/>
<error to="Kill"/>
</action>
<action name="CopyFiles">
<shell xmlns="uri:oozie:shell-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>mapred.job.queue.name</name>
<value>${queueName}</value>
</property>
<property>
<name>tez.lib.uris</name>
<value>/hdp/apps/2.5.0.0-1245/tez/tez.tar.gz</value>
</property>
</configuration>
<exec>/produccion/apps/traficotasado/CopyFiles.sh</exec>
<file>/produccion/apps/traficotasado/CopyFiles.sh#CopyFiles.sh</file> <!--Copy the executable to compute node's current working directory -->
</shell>
<ok to="DepuraFilesStage"/>
<error to="Kill"/>
</action>
Thanks for the help