Skip to content

Instantly share code, notes, and snippets.

@mattyb149

mattyb149/FetchOnFileExists.xml

Created December 12, 2016 14:35
Show Gist options
  • Star 1 You must be signed in to star a gist
  • Fork 0 You must be signed in to fork a gist
  • Save mattyb149/c2890dd17ad1ba21199718f6eea88279 to your computer and use it in GitHub Desktop.
Save mattyb149/c2890dd17ad1ba21199718f6eea88279 to your computer and use it in GitHub Desktop.
Download ZIP
NiFi template to check for the existence of a file, then transfers all flow files to success
Raw
FetchOnFileExists.xml
<?xml version="1.0" ?>
<template encoding-version="1.0">
<description>This template uses ExecuteScript to check for the existence of a file, then transfers all flow files to success while the file exists. This can be used to start and stop the movement of files external to NiFi.</description>
<groupId>f35864f5-0158-1000-f261-0c18ddb7fb1b</groupId>
<name>FetchOnFileExists</name>
<snippet>
<connections>
<id>f3597301-0158-1000-0000-000000000000</id>
<parentGroupId>f35864f5-0158-1000-0000-000000000000</parentGroupId>
<backPressureDataSizeThreshold>1 GB</backPressureDataSizeThreshold>
<backPressureObjectThreshold>10000</backPressureObjectThreshold>
<destination>
<groupId>f35864f5-0158-1000-0000-000000000000</groupId>
<id>f3590d6b-0158-1000-0000-000000000000</id>
<type>PROCESSOR</type>
</destination>
<flowFileExpiration>0 sec</flowFileExpiration>
<labelIndex>1</labelIndex>
<name></name>
<selectedRelationships>success</selectedRelationships>
<source>
<groupId>f35864f5-0158-1000-0000-000000000000</groupId>
<id>f358fd6b-0158-1000-0000-000000000000</id>
<type>PROCESSOR</type>
</source>
<zIndex>0</zIndex>
</connections>
<connections>
<id>f359ac50-0158-1000-0000-000000000000</id>
<parentGroupId>f35864f5-0158-1000-0000-000000000000</parentGroupId>
<backPressureDataSizeThreshold>1 GB</backPressureDataSizeThreshold>
<backPressureObjectThreshold>10000</backPressureObjectThreshold>
<destination>
<groupId>f35864f5-0158-1000-0000-000000000000</groupId>
<id>f3591ea9-0158-1000-0000-000000000000</id>
<type>PROCESSOR</type>
</destination>
<flowFileExpiration>0 sec</flowFileExpiration>
<labelIndex>1</labelIndex>
<name></name>
<selectedRelationships>success</selectedRelationships>
<source>
<groupId>f35864f5-0158-1000-0000-000000000000</groupId>
<id>f3590d6b-0158-1000-0000-000000000000</id>
<type>PROCESSOR</type>
</source>
<zIndex>0</zIndex>
</connections>
<connections>
<id>f359ce3d-0158-1000-0000-000000000000</id>
<parentGroupId>f35864f5-0158-1000-0000-000000000000</parentGroupId>
<backPressureDataSizeThreshold>1 GB</backPressureDataSizeThreshold>
<backPressureObjectThreshold>10000</backPressureObjectThreshold>
<destination>
<groupId>f35864f5-0158-1000-0000-000000000000</groupId>
<id>f3595a53-0158-1000-0000-000000000000</id>
<type>PROCESSOR</type>
</destination>
<flowFileExpiration>0 sec</flowFileExpiration>
<labelIndex>1</labelIndex>
<name></name>
<selectedRelationships>success</selectedRelationships>
<source>
<groupId>f35864f5-0158-1000-0000-000000000000</groupId>
<id>f3591ea9-0158-1000-0000-000000000000</id>
<type>PROCESSOR</type>
</source>
<zIndex>0</zIndex>
</connections>
<processors>
<id>f358fd6b-0158-1000-0000-000000000000</id>
<parentGroupId>f35864f5-0158-1000-0000-000000000000</parentGroupId>
<position>
<x>0.0</x>
<y>0.0</y>
</position>
<config>
<bulletinLevel>WARN</bulletinLevel>
<comments></comments>
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount>
<descriptors>
<entry>
<key>Input Directory</key>
<value>
<name>Input Directory</name>
</value>
</entry>
<entry>
<key>Recurse Subdirectories</key>
<value>
<name>Recurse Subdirectories</name>
</value>
</entry>
<entry>
<key>Input Directory Location</key>
<value>
<name>Input Directory Location</name>
</value>
</entry>
<entry>
<key>File Filter</key>
<value>
<name>File Filter</name>
</value>
</entry>
<entry>
<key>Path Filter</key>
<value>
<name>Path Filter</name>
</value>
</entry>
<entry>
<key>Minimum File Age</key>
<value>
<name>Minimum File Age</name>
</value>
</entry>
<entry>
<key>Maximum File Age</key>
<value>
<name>Maximum File Age</name>
</value>
</entry>
<entry>
<key>Minimum File Size</key>
<value>
<name>Minimum File Size</name>
</value>
</entry>
<entry>
<key>Maximum File Size</key>
<value>
<name>Maximum File Size</name>
</value>
</entry>
<entry>
<key>Ignore Hidden Files</key>
<value>
<name>Ignore Hidden Files</name>
</value>
</entry>
</descriptors>
<executionNode>ALL</executionNode>
<lossTolerant>false</lossTolerant>
<penaltyDuration>30 sec</penaltyDuration>
<properties>
<entry>
<key>Input Directory</key>
<value>/Users/mburgess/tmp/wait</value>
</entry>
<entry>
<key>Recurse Subdirectories</key>
<value>true</value>
</entry>
<entry>
<key>Input Directory Location</key>
<value>Local</value>
</entry>
<entry>
<key>File Filter</key>
<value>^(?!_success$).+</value>
</entry>
<entry>
<key>Path Filter</key>
</entry>
<entry>
<key>Minimum File Age</key>
<value>0 sec</value>
</entry>
<entry>
<key>Maximum File Age</key>
</entry>
<entry>
<key>Minimum File Size</key>
<value>0 B</value>
</entry>
<entry>
<key>Maximum File Size</key>
</entry>
<entry>
<key>Ignore Hidden Files</key>
<value>true</value>
</entry>
</properties>
<runDurationMillis>0</runDurationMillis>
<schedulingPeriod>0 sec</schedulingPeriod>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<yieldDuration>1 sec</yieldDuration>
</config>
<name>ListFile</name>
<relationships>
<autoTerminate>false</autoTerminate>
<name>success</name>
</relationships>
<style></style>
<type>org.apache.nifi.processors.standard.ListFile</type>
</processors>
<processors>
<id>f3590d6b-0158-1000-0000-000000000000</id>
<parentGroupId>f35864f5-0158-1000-0000-000000000000</parentGroupId>
<position>
<x>0.0</x>
<y>228.0</y>
</position>
<config>
<bulletinLevel>WARN</bulletinLevel>
<comments></comments>
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount>
<descriptors>
<entry>
<key>Script Engine</key>
<value>
<name>Script Engine</name>
</value>
</entry>
<entry>
<key>Script File</key>
<value>
<name>Script File</name>
</value>
</entry>
<entry>
<key>Script Body</key>
<value>
<name>Script Body</name>
</value>
</entry>
<entry>
<key>Module Directory</key>
<value>
<name>Module Directory</name>
</value>
</entry>
<entry>
<key>batchSize</key>
<value>
<name>batchSize</name>
</value>
</entry>
<entry>
<key>fileExists</key>
<value>
<name>fileExists</name>
</value>
</entry>
</descriptors>
<executionNode>ALL</executionNode>
<lossTolerant>false</lossTolerant>
<penaltyDuration>30 sec</penaltyDuration>
<properties>
<entry>
<key>Script Engine</key>
<value>Groovy</value>
</entry>
<entry>
<key>Script File</key>
</entry>
<entry>
<key>Script Body</key>
<value>if(!new File(fileExists.value).exists()) return
session.transfer(session.get(batchSize.asInteger()), REL_SUCCESS)</value>
</entry>
<entry>
<key>Module Directory</key>
</entry>
<entry>
<key>batchSize</key>
<value>1000</value>
</entry>
<entry>
<key>fileExists</key>
<value>/Users/mburgess/tmp/wait/_success</value>
</entry>
</properties>
<runDurationMillis>0</runDurationMillis>
<schedulingPeriod>0 sec</schedulingPeriod>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<yieldDuration>1 sec</yieldDuration>
</config>
<name>ExecuteScript</name>
<relationships>
<autoTerminate>true</autoTerminate>
<name>failure</name>
</relationships>
<relationships>
<autoTerminate>false</autoTerminate>
<name>success</name>
</relationships>
<style></style>
<type>org.apache.nifi.processors.script.ExecuteScript</type>
</processors>
<processors>
<id>f3591ea9-0158-1000-0000-000000000000</id>
<parentGroupId>f35864f5-0158-1000-0000-000000000000</parentGroupId>
<position>
<x>0.0</x>
<y>457.0</y>
</position>
<config>
<bulletinLevel>WARN</bulletinLevel>
<comments></comments>
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount>
<descriptors>
<entry>
<key>File to Fetch</key>
<value>
<name>File to Fetch</name>
</value>
</entry>
<entry>
<key>Completion Strategy</key>
<value>
<name>Completion Strategy</name>
</value>
</entry>
<entry>
<key>Move Destination Directory</key>
<value>
<name>Move Destination Directory</name>
</value>
</entry>
<entry>
<key>Move Conflict Strategy</key>
<value>
<name>Move Conflict Strategy</name>
</value>
</entry>
<entry>
<key>Log level when file not found</key>
<value>
<name>Log level when file not found</name>
</value>
</entry>
<entry>
<key>Log level when permission denied</key>
<value>
<name>Log level when permission denied</name>
</value>
</entry>
</descriptors>
<executionNode>ALL</executionNode>
<lossTolerant>false</lossTolerant>
<penaltyDuration>30 sec</penaltyDuration>
<properties>
<entry>
<key>File to Fetch</key>
<value>${absolute.path}/${filename}</value>
</entry>
<entry>
<key>Completion Strategy</key>
<value>Move File</value>
</entry>
<entry>
<key>Move Destination Directory</key>
<value>/Users/mburgess/tmp/done</value>
</entry>
<entry>
<key>Move Conflict Strategy</key>
<value>Fail</value>
</entry>
<entry>
<key>Log level when file not found</key>
<value>ERROR</value>
</entry>
<entry>
<key>Log level when permission denied</key>
<value>ERROR</value>
</entry>
</properties>
<runDurationMillis>0</runDurationMillis>
<schedulingPeriod>0 sec</schedulingPeriod>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<yieldDuration>1 sec</yieldDuration>
</config>
<name>FetchFile</name>
<relationships>
<autoTerminate>true</autoTerminate>
<name>failure</name>
</relationships>
<relationships>
<autoTerminate>true</autoTerminate>
<name>not.found</name>
</relationships>
<relationships>
<autoTerminate>true</autoTerminate>
<name>permission.denied</name>
</relationships>
<relationships>
<autoTerminate>false</autoTerminate>
<name>success</name>
</relationships>
<style></style>
<type>org.apache.nifi.processors.standard.FetchFile</type>
</processors>
<processors>
<id>f3595a53-0158-1000-0000-000000000000</id>
<parentGroupId>f35864f5-0158-1000-0000-000000000000</parentGroupId>
<position>
<x>2.0</x>
<y>673.0</y>
</position>
<config>
<bulletinLevel>WARN</bulletinLevel>
<comments></comments>
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount>
<descriptors>
<entry>
<key>Log Level</key>
<value>
<name>Log Level</name>
</value>
</entry>
<entry>
<key>Log Payload</key>
<value>
<name>Log Payload</name>
</value>
</entry>
<entry>
<key>Attributes to Log</key>
<value>
<name>Attributes to Log</name>
</value>
</entry>
<entry>
<key>Attributes to Ignore</key>
<value>
<name>Attributes to Ignore</name>
</value>
</entry>
<entry>
<key>Log prefix</key>
<value>
<name>Log prefix</name>
</value>
</entry>
</descriptors>
<executionNode>ALL</executionNode>
<lossTolerant>false</lossTolerant>
<penaltyDuration>30 sec</penaltyDuration>
<properties>
<entry>
<key>Log Level</key>
<value>info</value>
</entry>
<entry>
<key>Log Payload</key>
<value>false</value>
</entry>
<entry>
<key>Attributes to Log</key>
</entry>
<entry>
<key>Attributes to Ignore</key>
</entry>
<entry>
<key>Log prefix</key>
</entry>
</properties>
<runDurationMillis>0</runDurationMillis>
<schedulingPeriod>0 sec</schedulingPeriod>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<yieldDuration>1 sec</yieldDuration>
</config>
<name>LogAttribute</name>
<relationships>
<autoTerminate>true</autoTerminate>
<name>success</name>
</relationships>
<style></style>
<type>org.apache.nifi.processors.standard.LogAttribute</type>
</processors>
</snippet>
<timestamp>12/12/2016 09:31:22 EST</timestamp>
</template>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment