Skip to content

Instantly share code, notes, and snippets.

@alopresto
Created January 4, 2018 16:26
Show Gist options
  • Save alopresto/86eb04437c079cf2a48e2aeadf2df7c0 to your computer and use it in GitHub Desktop.
Save alopresto/86eb04437c079cf2a48e2aeadf2df7c0 to your computer and use it in GitHub Desktop.
Flow for testing CountText processor with local or remote input
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<flowController encoding-version="1.2">
<maxTimerDrivenThreadCount>10</maxTimerDrivenThreadCount>
<maxEventDrivenThreadCount>5</maxEventDrivenThreadCount>
<rootGroup>
<id>c1cbc231-0160-1000-a257-527d2f64f75f</id>
<name>NiFi Flow</name>
<position x="0.0" y="0.0"/>
<comment/>
<processor>
<id>c1f7e2f3-0160-1000-6aea-bb3325e339a3</id>
<name>InvokeHTTP</name>
<position x="1040.0" y="24.0"/>
<styles/>
<comment/>
<class>org.apache.nifi.processors.standard.InvokeHTTP</class>
<bundle>
<group>org.apache.nifi</group>
<artifact>nifi-standard-nar</artifact>
<version>1.5.0-SNAPSHOT</version>
</bundle>
<maxConcurrentTasks>1</maxConcurrentTasks>
<schedulingPeriod>5 sec</schedulingPeriod>
<penalizationPeriod>30 sec</penalizationPeriod>
<yieldPeriod>1 sec</yieldPeriod>
<bulletinLevel>WARN</bulletinLevel>
<lossTolerant>false</lossTolerant>
<scheduledState>STOPPED</scheduledState>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<executionNode>ALL</executionNode>
<runDurationNanos>0</runDurationNanos>
<property>
<name>HTTP Method</name>
<value>GET</value>
</property>
<property>
<name>Remote URL</name>
<value>http://raw.githubusercontent.com/dwyl/english-words/master/words_alpha.txt</value>
</property>
<property>
<name>SSL Context Service</name>
</property>
<property>
<name>Connection Timeout</name>
<value>5 secs</value>
</property>
<property>
<name>Read Timeout</name>
<value>15 secs</value>
</property>
<property>
<name>Include Date Header</name>
<value>True</value>
</property>
<property>
<name>Follow Redirects</name>
<value>True</value>
</property>
<property>
<name>Attributes to Send</name>
</property>
<property>
<name>Basic Authentication Username</name>
</property>
<property>
<name>Basic Authentication Password</name>
</property>
<property>
<name>Proxy Host</name>
</property>
<property>
<name>Proxy Port</name>
</property>
<property>
<name>invokehttp-proxy-user</name>
</property>
<property>
<name>invokehttp-proxy-password</name>
</property>
<property>
<name>Put Response Body In Attribute</name>
</property>
<property>
<name>Max Length To Put In Attribute</name>
<value>256</value>
</property>
<property>
<name>Digest Authentication</name>
<value>false</value>
</property>
<property>
<name>Always Output Response</name>
<value>false</value>
</property>
<property>
<name>Trusted Hostname</name>
</property>
<property>
<name>Add Response Headers to Request</name>
<value>false</value>
</property>
<property>
<name>Content-Type</name>
<value>${mime.type}</value>
</property>
<property>
<name>send-message-body</name>
<value>true</value>
</property>
<property>
<name>Use Chunked Encoding</name>
<value>false</value>
</property>
<property>
<name>Penalize on "No Retry"</name>
<value>false</value>
</property>
<autoTerminatedRelationship>Original</autoTerminatedRelationship>
<autoTerminatedRelationship>Failure</autoTerminatedRelationship>
<autoTerminatedRelationship>Retry</autoTerminatedRelationship>
<autoTerminatedRelationship>No Retry</autoTerminatedRelationship>
</processor>
<processor>
<id>c1cd447f-0160-1000-835e-2981e5c1b6af</id>
<name>CountText</name>
<position x="645.0" y="254.0"/>
<styles/>
<comment/>
<class>org.apache.nifi.processors.standard.CountText</class>
<bundle>
<group>org.apache.nifi</group>
<artifact>nifi-standard-nar</artifact>
<version>1.5.0-SNAPSHOT</version>
</bundle>
<maxConcurrentTasks>1</maxConcurrentTasks>
<schedulingPeriod>0 sec</schedulingPeriod>
<penalizationPeriod>30 sec</penalizationPeriod>
<yieldPeriod>1 sec</yieldPeriod>
<bulletinLevel>WARN</bulletinLevel>
<lossTolerant>false</lossTolerant>
<scheduledState>STOPPED</scheduledState>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<executionNode>ALL</executionNode>
<runDurationNanos>0</runDurationNanos>
<property>
<name>text-line-count</name>
<value>true</value>
</property>
<property>
<name>text-line-nonempty-count</name>
<value>true</value>
</property>
<property>
<name>text-word-count</name>
<value>true</value>
</property>
<property>
<name>text-character-count</name>
<value>true</value>
</property>
<property>
<name>split-words-on-symbols</name>
<value>false</value>
</property>
<property>
<name>character-encoding</name>
<value>UTF-8</value>
</property>
<autoTerminatedRelationship>failure</autoTerminatedRelationship>
</processor>
<processor>
<id>c1cd2a14-0160-1000-0e67-e954d27310bb</id>
<name>Jabberwocky</name>
<position x="261.5" y="24.0"/>
<styles/>
<comment/>
<class>org.apache.nifi.processors.standard.GetFile</class>
<bundle>
<group>org.apache.nifi</group>
<artifact>nifi-standard-nar</artifact>
<version>1.5.0-SNAPSHOT</version>
</bundle>
<maxConcurrentTasks>1</maxConcurrentTasks>
<schedulingPeriod>1 sec</schedulingPeriod>
<penalizationPeriod>30 sec</penalizationPeriod>
<yieldPeriod>1 sec</yieldPeriod>
<bulletinLevel>WARN</bulletinLevel>
<lossTolerant>false</lossTolerant>
<scheduledState>STOPPED</scheduledState>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<executionNode>ALL</executionNode>
<runDurationNanos>0</runDurationNanos>
<property>
<name>Input Directory</name>
<value>/Users/alopresto/Workspace/nifi/nifi-nar-bundles/nifi-standard-bundle/nifi-standard-processors/src/test/resources/TestCountText</value>
</property>
<property>
<name>File Filter</name>
<value>[^\.].*</value>
</property>
<property>
<name>Path Filter</name>
</property>
<property>
<name>Batch Size</name>
<value>10</value>
</property>
<property>
<name>Keep Source File</name>
<value>true</value>
</property>
<property>
<name>Recurse Subdirectories</name>
<value>true</value>
</property>
<property>
<name>Polling Interval</name>
<value>0 sec</value>
</property>
<property>
<name>Ignore Hidden Files</name>
<value>true</value>
</property>
<property>
<name>Minimum File Age</name>
<value>0 sec</value>
</property>
<property>
<name>Maximum File Age</name>
</property>
<property>
<name>Minimum File Size</name>
<value>0 B</value>
</property>
<property>
<name>Maximum File Size</name>
</property>
</processor>
<processor>
<id>c1f4165f-0160-1000-9276-ad009adfcde0</id>
<name>Words List</name>
<position x="645.0" y="24.0"/>
<styles/>
<comment/>
<class>org.apache.nifi.processors.standard.GetFile</class>
<bundle>
<group>org.apache.nifi</group>
<artifact>nifi-standard-nar</artifact>
<version>1.5.0-SNAPSHOT</version>
</bundle>
<maxConcurrentTasks>1</maxConcurrentTasks>
<schedulingPeriod>1 sec</schedulingPeriod>
<penalizationPeriod>30 sec</penalizationPeriod>
<yieldPeriod>1 sec</yieldPeriod>
<bulletinLevel>WARN</bulletinLevel>
<lossTolerant>false</lossTolerant>
<scheduledState>STOPPED</scheduledState>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<executionNode>ALL</executionNode>
<runDurationNanos>0</runDurationNanos>
<property>
<name>Input Directory</name>
<value>/Users/alopresto/Workspace/scratch/wordlists</value>
</property>
<property>
<name>File Filter</name>
<value>[^\.].*</value>
</property>
<property>
<name>Path Filter</name>
</property>
<property>
<name>Batch Size</name>
<value>10</value>
</property>
<property>
<name>Keep Source File</name>
<value>true</value>
</property>
<property>
<name>Recurse Subdirectories</name>
<value>true</value>
</property>
<property>
<name>Polling Interval</name>
<value>0 sec</value>
</property>
<property>
<name>Ignore Hidden Files</name>
<value>true</value>
</property>
<property>
<name>Minimum File Age</name>
<value>0 sec</value>
</property>
<property>
<name>Maximum File Age</name>
</property>
<property>
<name>Minimum File Size</name>
<value>0 B</value>
</property>
<property>
<name>Maximum File Size</name>
</property>
</processor>
<processor>
<id>c1cd5b55-0160-1000-4c08-d17c517e8684</id>
<name>LogAttribute</name>
<position x="645.0" y="479.0"/>
<styles/>
<comment/>
<class>org.apache.nifi.processors.standard.LogAttribute</class>
<bundle>
<group>org.apache.nifi</group>
<artifact>nifi-standard-nar</artifact>
<version>1.5.0-SNAPSHOT</version>
</bundle>
<maxConcurrentTasks>1</maxConcurrentTasks>
<schedulingPeriod>0 sec</schedulingPeriod>
<penalizationPeriod>30 sec</penalizationPeriod>
<yieldPeriod>1 sec</yieldPeriod>
<bulletinLevel>WARN</bulletinLevel>
<lossTolerant>false</lossTolerant>
<scheduledState>STOPPED</scheduledState>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<executionNode>ALL</executionNode>
<runDurationNanos>0</runDurationNanos>
<property>
<name>Log Level</name>
<value>info</value>
</property>
<property>
<name>Log Payload</name>
<value>false</value>
</property>
<property>
<name>Attributes to Log</name>
</property>
<property>
<name>attributes-to-log-regex</name>
<value>.*</value>
</property>
<property>
<name>Attributes to Ignore</name>
</property>
<property>
<name>attributes-to-ignore-regex</name>
</property>
<property>
<name>Log prefix</name>
</property>
<property>
<name>character-set</name>
<value>UTF-8</value>
</property>
<autoTerminatedRelationship>success</autoTerminatedRelationship>
</processor>
<connection>
<id>c1ce9cf5-0160-1000-3a03-f3e937e48b5e</id>
<name/>
<bendPoints/>
<labelIndex>1</labelIndex>
<zIndex>0</zIndex>
<sourceId>c1cd447f-0160-1000-835e-2981e5c1b6af</sourceId>
<sourceGroupId>c1cbc231-0160-1000-a257-527d2f64f75f</sourceGroupId>
<sourceType>PROCESSOR</sourceType>
<destinationId>c1cd5b55-0160-1000-4c08-d17c517e8684</destinationId>
<destinationGroupId>c1cbc231-0160-1000-a257-527d2f64f75f</destinationGroupId>
<destinationType>PROCESSOR</destinationType>
<relationship>success</relationship>
<maxWorkQueueSize>10000</maxWorkQueueSize>
<maxWorkQueueDataSize>1 GB</maxWorkQueueDataSize>
<flowFileExpiration>0 sec</flowFileExpiration>
</connection>
<connection>
<id>c1f507a6-0160-1000-8edc-e421dc97f556</id>
<name/>
<bendPoints/>
<labelIndex>1</labelIndex>
<zIndex>0</zIndex>
<sourceId>c1f4165f-0160-1000-9276-ad009adfcde0</sourceId>
<sourceGroupId>c1cbc231-0160-1000-a257-527d2f64f75f</sourceGroupId>
<sourceType>PROCESSOR</sourceType>
<destinationId>c1cd447f-0160-1000-835e-2981e5c1b6af</destinationId>
<destinationGroupId>c1cbc231-0160-1000-a257-527d2f64f75f</destinationGroupId>
<destinationType>PROCESSOR</destinationType>
<relationship>success</relationship>
<maxWorkQueueSize>10000</maxWorkQueueSize>
<maxWorkQueueDataSize>1 GB</maxWorkQueueDataSize>
<flowFileExpiration>0 sec</flowFileExpiration>
</connection>
<connection>
<id>c1ce20fe-0160-1000-0ec2-6cc5ae780d85</id>
<name/>
<bendPoints/>
<labelIndex>1</labelIndex>
<zIndex>0</zIndex>
<sourceId>c1cd2a14-0160-1000-0e67-e954d27310bb</sourceId>
<sourceGroupId>c1cbc231-0160-1000-a257-527d2f64f75f</sourceGroupId>
<sourceType>PROCESSOR</sourceType>
<destinationId>c1cd447f-0160-1000-835e-2981e5c1b6af</destinationId>
<destinationGroupId>c1cbc231-0160-1000-a257-527d2f64f75f</destinationGroupId>
<destinationType>PROCESSOR</destinationType>
<relationship>success</relationship>
<maxWorkQueueSize>10000</maxWorkQueueSize>
<maxWorkQueueDataSize>1 GB</maxWorkQueueDataSize>
<flowFileExpiration>0 sec</flowFileExpiration>
</connection>
<connection>
<id>c1f92308-0160-1000-4737-fea30b89c0b6</id>
<name/>
<bendPoints/>
<labelIndex>1</labelIndex>
<zIndex>0</zIndex>
<sourceId>c1f7e2f3-0160-1000-6aea-bb3325e339a3</sourceId>
<sourceGroupId>c1cbc231-0160-1000-a257-527d2f64f75f</sourceGroupId>
<sourceType>PROCESSOR</sourceType>
<destinationId>c1cd447f-0160-1000-835e-2981e5c1b6af</destinationId>
<destinationGroupId>c1cbc231-0160-1000-a257-527d2f64f75f</destinationGroupId>
<destinationType>PROCESSOR</destinationType>
<relationship>Response</relationship>
<maxWorkQueueSize>10000</maxWorkQueueSize>
<maxWorkQueueDataSize>1 GB</maxWorkQueueDataSize>
<flowFileExpiration>0 sec</flowFileExpiration>
</connection>
</rootGroup>
<controllerServices/>
<reportingTasks/>
</flowController>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment