Skip to content

Instantly share code, notes, and snippets.

@abajwa-hw

abajwa-hw/flow.xml

Last active December 14, 2018 06:53
Show Gist options
  • Save abajwa-hw/815757d9446c246ee9a1407449f7ff45 to your computer and use it in GitHub Desktop.
Save abajwa-hw/815757d9446c246ee9a1407449f7ff45 to your computer and use it in GitHub Desktop.
Download ZIP
flow.xml for twitter including atlas reporting task
Raw
flow.xml
<?xml version="1.0" encoding="UTF-8" standalone="no"?>
<flowController encoding-version="1.3">
<maxTimerDrivenThreadCount>10</maxTimerDrivenThreadCount>
<maxEventDrivenThreadCount>5</maxEventDrivenThreadCount>
<registries/>
<rootGroup>
<id>94d19823-0163-1000-97c6-e7c5579e4a0c</id>
<name>NiFi Flow</name>
<position x="0.0" y="0.0"/>
<comment/>
<processGroup>
<id>f5ca9391-0f9a-4e95-8db5-576f9804e8ce</id>
<name>Twitter Dashboard 2 - Push tweets into HDFS/Solr</name>
<position x="1647.000244140625" y="479.78326416015625"/>
<comment/>
<processor>
<id>d3c85c30-7a66-4351-a2b3-9addd5f1ba28</id>
<name>ReplaceText</name>
<position x="347.4908657243287" y="331.2840828508703"/>
<styles/>
<comment/>
<class>org.apache.nifi.processors.standard.ReplaceText</class>
<bundle>
<group>org.apache.nifi</group>
<artifact>nifi-standard-nar</artifact>
<version>1.5.0.3.1.0.0-564</version>
</bundle>
<maxConcurrentTasks>1</maxConcurrentTasks>
<schedulingPeriod>0 sec</schedulingPeriod>
<penalizationPeriod>30 sec</penalizationPeriod>
<yieldPeriod>1 sec</yieldPeriod>
<bulletinLevel>WARN</bulletinLevel>
<lossTolerant>false</lossTolerant>
<scheduledState>RUNNING</scheduledState>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<executionNode>ALL</executionNode>
<runDurationNanos>0</runDurationNanos>
<property>
<name>Regular Expression</name>
<value>(?s:^(.*)$)</value>
</property>
<property>
<name>Replacement Value</name>
<value>${twitter.tweet_id}|${twitter.unixtime}|${twitter.time}|${twitter.handle}|${twitter.msg:replace('$',''):replace('\n','')}|$1</value>
</property>
<property>
<name>Character Set</name>
<value>UTF-8</value>
</property>
<property>
<name>Maximum Buffer Size</name>
<value>1 MB</value>
</property>
<property>
<name>Replacement Strategy</name>
<value>Regex Replace</value>
</property>
<property>
<name>Evaluation Mode</name>
<value>Entire text</value>
</property>
<autoTerminatedRelationship>failure</autoTerminatedRelationship>
</processor>
<processor>
<id>2c9405dd-f5cf-41eb-b4a3-c1f238aecc60</id>
<name>Grab Garden Hose</name>
<position x="-101.8350917029849" y="-66.59999615192999"/>
<styles/>
<comment/>
<class>org.apache.nifi.processors.twitter.GetTwitter</class>
<bundle>
<group>org.apache.nifi</group>
<artifact>nifi-social-media-nar</artifact>
<version>1.5.0.3.1.0.0-564</version>
</bundle>
<maxConcurrentTasks>1</maxConcurrentTasks>
<schedulingPeriod>0 sec</schedulingPeriod>
<penalizationPeriod>30 sec</penalizationPeriod>
<yieldPeriod>1 sec</yieldPeriod>
<bulletinLevel>WARN</bulletinLevel>
<lossTolerant>false</lossTolerant>
<scheduledState>RUNNING</scheduledState>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<executionNode>ALL</executionNode>
<runDurationNanos>0</runDurationNanos>
<property>
<name>Twitter Endpoint</name>
<value>Filter Endpoint</value>
</property>
<property>
<name>Consumer Key</name>
<value></value>
</property>
<property>
<name>Consumer Secret</name>
<value></value>
</property>
<property>
<name>Access Token</name>
<value></value>
</property>
<property>
<name>Access Token Secret</name>
<value></value>
</property>
<property>
<name>Languages</name>
</property>
<property>
<name>Terms to Filter On</name>
<value>AAPL,ORCL,GOOG,MSFT</value>
</property>
<property>
<name>IDs to Follow</name>
</property>
<property>
<name>Locations to Filter On</name>
</property>
</processor>
<processor>
<id>63500cda-60fc-433e-b68c-b01d40d16624</id>
<name>MergeContent</name>
<position x="890.901616061057" y="285.4346310401422"/>
<styles/>
<comment/>
<class>org.apache.nifi.processors.standard.MergeContent</class>
<bundle>
<group>org.apache.nifi</group>
<artifact>nifi-standard-nar</artifact>
<version>1.5.0.3.1.0.0-564</version>
</bundle>
<maxConcurrentTasks>1</maxConcurrentTasks>
<schedulingPeriod>0 sec</schedulingPeriod>
<penalizationPeriod>30 sec</penalizationPeriod>
<yieldPeriod>1 sec</yieldPeriod>
<bulletinLevel>WARN</bulletinLevel>
<lossTolerant>false</lossTolerant>
<scheduledState>RUNNING</scheduledState>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<executionNode>ALL</executionNode>
<runDurationNanos>0</runDurationNanos>
<property>
<name>Merge Strategy</name>
<value>Bin-Packing Algorithm</value>
</property>
<property>
<name>Merge Format</name>
<value>Binary Concatenation</value>
</property>
<property>
<name>Attribute Strategy</name>
<value>Keep Only Common Attributes</value>
</property>
<property>
<name>Correlation Attribute Name</name>
</property>
<property>
<name>mergecontent-metadata-strategy</name>
<value>Do Not Merge Uncommon Metadata</value>
</property>
<property>
<name>Minimum Number of Entries</name>
<value>20</value>
</property>
<property>
<name>Maximum Number of Entries</name>
<value>1000</value>
</property>
<property>
<name>Minimum Group Size</name>
<value>0 B</value>
</property>
<property>
<name>Maximum Group Size</name>
</property>
<property>
<name>Max Bin Age</name>
<value>120 seconds</value>
</property>
<property>
<name>Maximum number of Bins</name>
<value>100</value>
</property>
<property>
<name>Delimiter Strategy</name>
<value>Filename</value>
</property>
<property>
<name>Header File</name>
</property>
<property>
<name>Footer File</name>
</property>
<property>
<name>Demarcator File</name>
</property>
<property>
<name>Compression Level</name>
<value>1</value>
</property>
<property>
<name>Keep Path</name>
<value>false</value>
</property>
<property>
<name>Tar Modified Time</name>
<value>${file.lastModifiedTime}</value>
</property>
<autoTerminatedRelationship>failure</autoTerminatedRelationship>
<autoTerminatedRelationship>original</autoTerminatedRelationship>
</processor>
<processor>
<id>6360c55a-a0e3-4fd9-9011-46fb8acdba97</id>
<name>PutHDFS</name>
<position x="976.1673094034688" y="499.18609362192194"/>
<styles/>
<comment/>
<class>org.apache.nifi.processors.hadoop.PutHDFS</class>
<bundle>
<group>org.apache.nifi</group>
<artifact>nifi-hadoop-nar</artifact>
<version>1.5.0.3.1.0.0-564</version>
</bundle>
<maxConcurrentTasks>1</maxConcurrentTasks>
<schedulingPeriod>0 sec</schedulingPeriod>
<penalizationPeriod>30 sec</penalizationPeriod>
<yieldPeriod>1 sec</yieldPeriod>
<bulletinLevel>WARN</bulletinLevel>
<lossTolerant>false</lossTolerant>
<scheduledState>RUNNING</scheduledState>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<executionNode>ALL</executionNode>
<runDurationNanos>0</runDurationNanos>
<property>
<name>Hadoop Configuration Resources</name>
<value>/etc/hadoop/conf/core-site.xml,/etc/hadoop/conf/hdfs-site.xml</value>
</property>
<property>
<name>Kerberos Principal</name>
<value>nifi/[email protected]</value>
</property>
<property>
<name>Kerberos Keytab</name>
<value>/etc/security/keytabs/nifi.service.keytab</value>
</property>
<property>
<name>Kerberos Relogin Period</name>
<value>4 hours</value>
</property>
<property>
<name>Additional Classpath Resources</name>
</property>
<property>
<name>Directory</name>
<value>/tmp/twitter_staging</value>
</property>
<property>
<name>Conflict Resolution Strategy</name>
<value>replace</value>
</property>
<property>
<name>Block Size</name>
</property>
<property>
<name>IO Buffer Size</name>
</property>
<property>
<name>Replication</name>
<value>1</value>
</property>
<property>
<name>Permissions umask</name>
</property>
<property>
<name>Remote Owner</name>
</property>
<property>
<name>Remote Group</name>
</property>
<property>
<name>Compression codec</name>
<value>NONE</value>
</property>
<autoTerminatedRelationship>success</autoTerminatedRelationship>
</processor>
<processor>
<id>6f28e92f-9486-45ad-8f63-c7a3e6ad9157</id>
<name>PutFile</name>
<position x="462.41607100345675" y="510.6240575752739"/>
<styles/>
<comment/>
<class>org.apache.nifi.processors.standard.PutFile</class>
<bundle>
<group>org.apache.nifi</group>
<artifact>nifi-standard-nar</artifact>
<version>1.5.0.3.1.0.0-564</version>
</bundle>
<maxConcurrentTasks>1</maxConcurrentTasks>
<schedulingPeriod>0 sec</schedulingPeriod>
<penalizationPeriod>30 sec</penalizationPeriod>
<yieldPeriod>1 sec</yieldPeriod>
<bulletinLevel>WARN</bulletinLevel>
<lossTolerant>false</lossTolerant>
<scheduledState>RUNNING</scheduledState>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<executionNode>ALL</executionNode>
<runDurationNanos>0</runDurationNanos>
<property>
<name>Directory</name>
<value>/tmp/tweets</value>
</property>
<property>
<name>Conflict Resolution Strategy</name>
<value>fail</value>
</property>
<property>
<name>Create Missing Directories</name>
<value>true</value>
</property>
<property>
<name>Maximum File Count</name>
</property>
<property>
<name>Last Modified Time</name>
</property>
<property>
<name>Permissions</name>
</property>
<property>
<name>Owner</name>
</property>
<property>
<name>Group</name>
</property>
<autoTerminatedRelationship>success</autoTerminatedRelationship>
<autoTerminatedRelationship>failure</autoTerminatedRelationship>
</processor>
<processor>
<id>3ee301f8-d1b6-4d09-b706-095a37dd0b5c</id>
<name>Pull Key Attributes</name>
<position x="-110.79999648814115" y="181.37032931804072"/>
<styles/>
<comment/>
<class>org.apache.nifi.processors.standard.EvaluateJsonPath</class>
<bundle>
<group>org.apache.nifi</group>
<artifact>nifi-standard-nar</artifact>
<version>1.5.0.3.1.0.0-564</version>
</bundle>
<maxConcurrentTasks>4</maxConcurrentTasks>
<schedulingPeriod>0 sec</schedulingPeriod>
<penalizationPeriod>30 sec</penalizationPeriod>
<yieldPeriod>1 sec</yieldPeriod>
<bulletinLevel>ERROR</bulletinLevel>
<lossTolerant>false</lossTolerant>
<scheduledState>RUNNING</scheduledState>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<executionNode>ALL</executionNode>
<runDurationNanos>25000000</runDurationNanos>
<property>
<name>Destination</name>
<value>flowfile-attribute</value>
</property>
<property>
<name>Return Type</name>
<value>auto-detect</value>
</property>
<property>
<name>Path Not Found Behavior</name>
<value>ignore</value>
</property>
<property>
<name>Null Value Representation</name>
<value>empty string</value>
</property>
<property>
<name>twitter.handle</name>
<value>$.user.screen_name</value>
</property>
<property>
<name>twitter.user</name>
<value>$.user.name</value>
</property>
<property>
<name>twitter.tweet_id</name>
<value>$.id</value>
</property>
<property>
<name>language</name>
<value>$.lang</value>
</property>
<property>
<name>twitter.hashtags</name>
<value>$.entities.hashtags[0].text</value>
</property>
<property>
<name>twitter.unixtime</name>
<value>$.timestamp_ms</value>
</property>
<property>
<name>twitter.msg</name>
<value>$.text</value>
</property>
<property>
<name>twitter.time</name>
<value>$.created_at</value>
</property>
<autoTerminatedRelationship>failure</autoTerminatedRelationship>
<autoTerminatedRelationship>unmatched</autoTerminatedRelationship>
</processor>
<processor>
<id>f6327477-fb7d-4af0-b80d-edd2001b808a</id>
<name>PutSolrContentStream</name>
<position x="467.54397601551534" y="126.61621687404391"/>
<styles/>
<comment/>
<class>org.apache.nifi.processors.solr.PutSolrContentStream</class>
<bundle>
<group>org.apache.nifi</group>
<artifact>nifi-solr-nar</artifact>
<version>1.5.0.3.1.0.0-564</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>Solr Type</name>
<value>Cloud</value>
</property>
<property>
<name>Solr Location</name>
<value>localhost:2181</value>
</property>
<property>
<name>Collection</name>
<value>tweets</value>
</property>
<property>
<name>Content Stream Path</name>
<value>/update/json/docs</value>
</property>
<property>
<name>Content-Type</name>
<value>application/json</value>
</property>
<property>
<name>Commit Within</name>
<value>1000</value>
</property>
<property>
<name>JAAS Client App Name</name>
</property>
<property>
<name>Username</name>
</property>
<property>
<name>Password</name>
</property>
<property>
<name>SSL Context Service</name>
</property>
<property>
<name>Solr Socket Timeout</name>
<value>10 seconds</value>
</property>
<property>
<name>Solr Connection Timeout</name>
<value>10 seconds</value>
</property>
<property>
<name>Solr Maximum Connections</name>
<value>10</value>
</property>
<property>
<name>Solr Maximum Connections Per Host</name>
<value>5</value>
</property>
<property>
<name>ZooKeeper Client Timeout</name>
<value>10 seconds</value>
</property>
<property>
<name>ZooKeeper Connection Timeout</name>
<value>10 seconds</value>
</property>
<property>
<name>f.3</name>
<value>screenName_s:/user/screen_name</value>
</property>
<property>
<name>f.7</name>
<value>originalposter_s:/retweeted_status/user/screen_name</value>
</property>
<property>
<name>split</name>
<value>/</value>
</property>
<property>
<name>f.2</name>
<value>text_t:/text</value>
</property>
<property>
<name>f.11</name>
<value>place_s:/place</value>
</property>
<property>
<name>f.6</name>
<value>tag_ss:/entities/hashtags</value>
</property>
<property>
<name>f.9</name>
<value>geo_s:/geo</value>
</property>
<property>
<name>f.1</name>
<value>id:/id</value>
</property>
<property>
<name>f.5</name>
<value>twitter_created_at_dt:/created_at</value>
</property>
<property>
<name>f.8</name>
<value>source_s:/source</value>
</property>
<property>
<name>f.10</name>
<value>coordinates_s:/coordinates</value>
</property>
<property>
<name>f.4</name>
<value>language_s:/lang</value>
</property>
<autoTerminatedRelationship>success</autoTerminatedRelationship>
<autoTerminatedRelationship>failure</autoTerminatedRelationship>
<autoTerminatedRelationship>connection_failure</autoTerminatedRelationship>
</processor>
<processor>
<id>d0e55145-6505-48ec-b165-8f58d317ea39</id>
<name>Find only Tweets</name>
<position x="-101.12229263071927" y="415.77229159831415"/>
<styles/>
<comment/>
<class>org.apache.nifi.processors.standard.RouteOnAttribute</class>
<bundle>
<group>org.apache.nifi</group>
<artifact>nifi-standard-nar</artifact>
<version>1.5.0.3.1.0.0-564</version>
</bundle>
<maxConcurrentTasks>2</maxConcurrentTasks>
<schedulingPeriod>0 sec</schedulingPeriod>
<penalizationPeriod>30 sec</penalizationPeriod>
<yieldPeriod>1 sec</yieldPeriod>
<bulletinLevel>WARN</bulletinLevel>
<lossTolerant>false</lossTolerant>
<scheduledState>RUNNING</scheduledState>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<executionNode>ALL</executionNode>
<runDurationNanos>25000000</runDurationNanos>
<property>
<name>Routing Strategy</name>
<value>Route to Property name</value>
</property>
<property>
<name>tweet</name>
<value>${twitter.msg:isEmpty():not()}</value>
</property>
<autoTerminatedRelationship>unmatched</autoTerminatedRelationship>
</processor>
<connection>
<id>bb162957-16b6-4818-ba36-16d6d2da52f8</id>
<name/>
<bendPoints/>
<labelIndex>1</labelIndex>
<zIndex>0</zIndex>
<sourceId>d3c85c30-7a66-4351-a2b3-9addd5f1ba28</sourceId>
<sourceGroupId>f5ca9391-0f9a-4e95-8db5-576f9804e8ce</sourceGroupId>
<sourceType>PROCESSOR</sourceType>
<destinationId>63500cda-60fc-433e-b68c-b01d40d16624</destinationId>
<destinationGroupId>f5ca9391-0f9a-4e95-8db5-576f9804e8ce</destinationGroupId>
<destinationType>PROCESSOR</destinationType>
<relationship>success</relationship>
<maxWorkQueueSize>0</maxWorkQueueSize>
<maxWorkQueueDataSize>0 MB</maxWorkQueueDataSize>
<flowFileExpiration>0 sec</flowFileExpiration>
</connection>
<connection>
<id>cbd79ce4-aa7f-47d5-a273-6d323e77f1f8</id>
<name/>
<bendPoints/>
<labelIndex>1</labelIndex>
<zIndex>0</zIndex>
<sourceId>2c9405dd-f5cf-41eb-b4a3-c1f238aecc60</sourceId>
<sourceGroupId>f5ca9391-0f9a-4e95-8db5-576f9804e8ce</sourceGroupId>
<sourceType>PROCESSOR</sourceType>
<destinationId>3ee301f8-d1b6-4d09-b706-095a37dd0b5c</destinationId>
<destinationGroupId>f5ca9391-0f9a-4e95-8db5-576f9804e8ce</destinationGroupId>
<destinationType>PROCESSOR</destinationType>
<relationship>success</relationship>
<maxWorkQueueSize>0</maxWorkQueueSize>
<maxWorkQueueDataSize>0 MB</maxWorkQueueDataSize>
<flowFileExpiration>0 sec</flowFileExpiration>
</connection>
<connection>
<id>8554ca84-cc2a-4ad2-9534-2c57f5163385</id>
<name/>
<bendPoints/>
<labelIndex>1</labelIndex>
<zIndex>0</zIndex>
<sourceId>3ee301f8-d1b6-4d09-b706-095a37dd0b5c</sourceId>
<sourceGroupId>f5ca9391-0f9a-4e95-8db5-576f9804e8ce</sourceGroupId>
<sourceType>PROCESSOR</sourceType>
<destinationId>d0e55145-6505-48ec-b165-8f58d317ea39</destinationId>
<destinationGroupId>f5ca9391-0f9a-4e95-8db5-576f9804e8ce</destinationGroupId>
<destinationType>PROCESSOR</destinationType>
<relationship>matched</relationship>
<maxWorkQueueSize>0</maxWorkQueueSize>
<maxWorkQueueDataSize>0 MB</maxWorkQueueDataSize>
<flowFileExpiration>0 sec</flowFileExpiration>
</connection>
<connection>
<id>865fcabf-5b5c-4e2e-9878-d45d1c44fae8</id>
<name/>
<bendPoints/>
<labelIndex>1</labelIndex>
<zIndex>0</zIndex>
<sourceId>d0e55145-6505-48ec-b165-8f58d317ea39</sourceId>
<sourceGroupId>f5ca9391-0f9a-4e95-8db5-576f9804e8ce</sourceGroupId>
<sourceType>PROCESSOR</sourceType>
<destinationId>d3c85c30-7a66-4351-a2b3-9addd5f1ba28</destinationId>
<destinationGroupId>f5ca9391-0f9a-4e95-8db5-576f9804e8ce</destinationGroupId>
<destinationType>PROCESSOR</destinationType>
<relationship>tweet</relationship>
<maxWorkQueueSize>0</maxWorkQueueSize>
<maxWorkQueueDataSize>0 MB</maxWorkQueueDataSize>
<flowFileExpiration>0 sec</flowFileExpiration>
</connection>
<connection>
<id>d4dff594-70e0-4d02-a922-37d563853a59</id>
<name/>
<bendPoints>
<bendPoint x="1385.1673094034688" y="524.1860936219219"/>
<bendPoint x="1385.1673094034688" y="574.1860936219219"/>
</bendPoints>
<labelIndex>1</labelIndex>
<zIndex>0</zIndex>
<sourceId>6360c55a-a0e3-4fd9-9011-46fb8acdba97</sourceId>
<sourceGroupId>f5ca9391-0f9a-4e95-8db5-576f9804e8ce</sourceGroupId>
<sourceType>PROCESSOR</sourceType>
<destinationId>6360c55a-a0e3-4fd9-9011-46fb8acdba97</destinationId>
<destinationGroupId>f5ca9391-0f9a-4e95-8db5-576f9804e8ce</destinationGroupId>
<destinationType>PROCESSOR</destinationType>
<relationship>failure</relationship>
<maxWorkQueueSize>0</maxWorkQueueSize>
<maxWorkQueueDataSize>0 MB</maxWorkQueueDataSize>
<flowFileExpiration>0 sec</flowFileExpiration>
</connection>
<connection>
<id>717511b2-0372-418f-8cad-dda0407dcc7a</id>
<name/>
<bendPoints/>
<labelIndex>1</labelIndex>
<zIndex>0</zIndex>
<sourceId>63500cda-60fc-433e-b68c-b01d40d16624</sourceId>
<sourceGroupId>f5ca9391-0f9a-4e95-8db5-576f9804e8ce</sourceGroupId>
<sourceType>PROCESSOR</sourceType>
<destinationId>6360c55a-a0e3-4fd9-9011-46fb8acdba97</destinationId>
<destinationGroupId>f5ca9391-0f9a-4e95-8db5-576f9804e8ce</destinationGroupId>
<destinationType>PROCESSOR</destinationType>
<relationship>merged</relationship>
<maxWorkQueueSize>0</maxWorkQueueSize>
<maxWorkQueueDataSize>0 MB</maxWorkQueueDataSize>
<flowFileExpiration>0 sec</flowFileExpiration>
</connection>
<connection>
<id>211507c9-92e6-49ea-ac9f-bc2f25333cee</id>
<name/>
<bendPoints/>
<labelIndex>1</labelIndex>
<zIndex>0</zIndex>
<sourceId>63500cda-60fc-433e-b68c-b01d40d16624</sourceId>
<sourceGroupId>f5ca9391-0f9a-4e95-8db5-576f9804e8ce</sourceGroupId>
<sourceType>PROCESSOR</sourceType>
<destinationId>6f28e92f-9486-45ad-8f63-c7a3e6ad9157</destinationId>
<destinationGroupId>f5ca9391-0f9a-4e95-8db5-576f9804e8ce</destinationGroupId>
<destinationType>PROCESSOR</destinationType>
<relationship>merged</relationship>
<maxWorkQueueSize>0</maxWorkQueueSize>
<maxWorkQueueDataSize>0 MB</maxWorkQueueDataSize>
<flowFileExpiration>0 sec</flowFileExpiration>
</connection>
</processGroup>
<template>
<description>Push tweets to HDFS/Solr and visualize using Banana dashboard</description>
<id>29d2bce2-4894-3e36-8af5-cd354a16c814</id>
<name>Twitter Dashboard</name>
<snippet>
<processGroups>
<id>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</id>
<parentGroupId>7c84501d-d10c-407c-b9f3-1d80e38fe36a</parentGroupId>
<position>
<x>-17.876335903686083</x>
<y>58.777631201824505</y>
</position>
<comments/>
<contents>
<connections>
<id>211507c9-92e6-49ea-a1bb-0666683e46ec</id>
<parentGroupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</parentGroupId>
<backPressureDataSizeThreshold>0 MB</backPressureDataSizeThreshold>
<backPressureObjectThreshold>0</backPressureObjectThreshold>
<destination>
<groupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</groupId>
<id>6f28e92f-9486-45ad-a1e3-b02e4e00bf7c</id>
<type>PROCESSOR</type>
</destination>
<flowFileExpiration>0 sec</flowFileExpiration>
<labelIndex>1</labelIndex>
<name/>
<selectedRelationships>merged</selectedRelationships>
<source>
<groupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</groupId>
<id>63500cda-60fc-433e-9d34-0250c7fe57ba</id>
<type>PROCESSOR</type>
</source>
<zIndex>0</zIndex>
</connections>
<connections>
<id>d4dff594-70e0-4d02-8620-e68afd8e684d</id>
<parentGroupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</parentGroupId>
<backPressureDataSizeThreshold>0 MB</backPressureDataSizeThreshold>
<backPressureObjectThreshold>0</backPressureObjectThreshold>
<bends>
<x>1375.1673094034688</x>
<y>504.1860631043438</y>
</bends>
<bends>
<x>1375.1673094034688</x>
<y>554.1860631043438</y>
</bends>
<destination>
<groupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</groupId>
<id>6360c55a-a0e3-4fd9-ab55-f5910c6932c6</id>
<type>PROCESSOR</type>
</destination>
<flowFileExpiration>0 sec</flowFileExpiration>
<labelIndex>1</labelIndex>
<name/>
<selectedRelationships>failure</selectedRelationships>
<source>
<groupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</groupId>
<id>6360c55a-a0e3-4fd9-ab55-f5910c6932c6</id>
<type>PROCESSOR</type>
</source>
<zIndex>0</zIndex>
</connections>
<connections>
<id>bb162957-16b6-4818-882a-1767dd49b86c</id>
<parentGroupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</parentGroupId>
<backPressureDataSizeThreshold>0 MB</backPressureDataSizeThreshold>
<backPressureObjectThreshold>0</backPressureObjectThreshold>
<destination>
<groupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</groupId>
<id>63500cda-60fc-433e-9d34-0250c7fe57ba</id>
<type>PROCESSOR</type>
</destination>
<flowFileExpiration>0 sec</flowFileExpiration>
<labelIndex>1</labelIndex>
<name/>
<selectedRelationships>success</selectedRelationships>
<source>
<groupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</groupId>
<id>d3c85c30-7a66-4351-96b7-0cbd4ff8e809</id>
<type>PROCESSOR</type>
</source>
<zIndex>0</zIndex>
</connections>
<connections>
<id>8554ca84-cc2a-4ad2-ae0d-840b1b6f46ff</id>
<parentGroupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</parentGroupId>
<backPressureDataSizeThreshold>0 MB</backPressureDataSizeThreshold>
<backPressureObjectThreshold>0</backPressureObjectThreshold>
<destination>
<groupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</groupId>
<id>d0e55145-6505-48ec-b5bd-272100e70f46</id>
<type>PROCESSOR</type>
</destination>
<flowFileExpiration>0 sec</flowFileExpiration>
<labelIndex>1</labelIndex>
<name/>
<selectedRelationships>matched</selectedRelationships>
<source>
<groupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</groupId>
<id>3ee301f8-d1b6-4d09-9d10-2060632e9db0</id>
<type>PROCESSOR</type>
</source>
<zIndex>0</zIndex>
</connections>
<connections>
<id>cbd79ce4-aa7f-47d5-ae7e-665279a4c3c0</id>
<parentGroupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</parentGroupId>
<backPressureDataSizeThreshold>0 MB</backPressureDataSizeThreshold>
<backPressureObjectThreshold>0</backPressureObjectThreshold>
<destination>
<groupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</groupId>
<id>3ee301f8-d1b6-4d09-9d10-2060632e9db0</id>
<type>PROCESSOR</type>
</destination>
<flowFileExpiration>0 sec</flowFileExpiration>
<labelIndex>1</labelIndex>
<name/>
<selectedRelationships>success</selectedRelationships>
<source>
<groupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</groupId>
<id>2c9405dd-f5cf-41eb-a4e6-5eeb1070d658</id>
<type>PROCESSOR</type>
</source>
<zIndex>0</zIndex>
</connections>
<connections>
<id>717511b2-0372-418f-b344-a864a5c306a3</id>
<parentGroupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</parentGroupId>
<backPressureDataSizeThreshold>0 MB</backPressureDataSizeThreshold>
<backPressureObjectThreshold>0</backPressureObjectThreshold>
<destination>
<groupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</groupId>
<id>6360c55a-a0e3-4fd9-ab55-f5910c6932c6</id>
<type>PROCESSOR</type>
</destination>
<flowFileExpiration>0 sec</flowFileExpiration>
<labelIndex>1</labelIndex>
<name/>
<selectedRelationships>merged</selectedRelationships>
<source>
<groupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</groupId>
<id>63500cda-60fc-433e-9d34-0250c7fe57ba</id>
<type>PROCESSOR</type>
</source>
<zIndex>0</zIndex>
</connections>
<connections>
<id>865fcabf-5b5c-4e2e-8d1d-1fc509a5ddb1</id>
<parentGroupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</parentGroupId>
<backPressureDataSizeThreshold>0 MB</backPressureDataSizeThreshold>
<backPressureObjectThreshold>0</backPressureObjectThreshold>
<destination>
<groupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</groupId>
<id>d3c85c30-7a66-4351-96b7-0cbd4ff8e809</id>
<type>PROCESSOR</type>
</destination>
<flowFileExpiration>0 sec</flowFileExpiration>
<labelIndex>1</labelIndex>
<name/>
<selectedRelationships>tweet</selectedRelationships>
<source>
<groupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</groupId>
<id>d0e55145-6505-48ec-b5bd-272100e70f46</id>
<type>PROCESSOR</type>
</source>
<zIndex>0</zIndex>
</connections>
<connections>
<id>fe96993e-137d-4282-94bf-a3e9ce176367</id>
<parentGroupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</parentGroupId>
<backPressureDataSizeThreshold>0 MB</backPressureDataSizeThreshold>
<backPressureObjectThreshold>0</backPressureObjectThreshold>
<destination>
<groupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</groupId>
<id>f6327477-fb7d-4af0-a2c2-1ee50e03249e</id>
<type>PROCESSOR</type>
</destination>
<flowFileExpiration>0 sec</flowFileExpiration>
<labelIndex>1</labelIndex>
<name/>
<selectedRelationships>tweet</selectedRelationships>
<source>
<groupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</groupId>
<id>d0e55145-6505-48ec-b5bd-272100e70f46</id>
<type>PROCESSOR</type>
</source>
<zIndex>0</zIndex>
</connections>
<processors>
<id>d0e55145-6505-48ec-b5bd-272100e70f46</id>
<parentGroupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</parentGroupId>
<position>
<x>-101.12229263071927</x>
<y>415.77229159831415</y>
</position>
<config>
<bulletinLevel>WARN</bulletinLevel>
<comments/>
<concurrentlySchedulableTaskCount>2</concurrentlySchedulableTaskCount>
<descriptors>
<entry>
<key>Routing Strategy</key>
<value>
<name>Routing Strategy</name>
</value>
</entry>
<entry>
<key>tweet</key>
<value>
<name>tweet</name>
</value>
</entry>
</descriptors>
<lossTolerant>false</lossTolerant>
<penaltyDuration>30 sec</penaltyDuration>
<properties>
<entry>
<key>Routing Strategy</key>
<value>Route to Property name</value>
</entry>
<entry>
<key>tweet</key>
<value>${twitter.msg:isEmpty():not()}</value>
</entry>
</properties>
<runDurationMillis>25</runDurationMillis>
<schedulingPeriod>0 sec</schedulingPeriod>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<yieldDuration>1 sec</yieldDuration>
</config>
<name>Find only Tweets</name>
<relationships>
<autoTerminate>false</autoTerminate>
<name>tweet</name>
</relationships>
<relationships>
<autoTerminate>true</autoTerminate>
<name>unmatched</name>
</relationships>
<state>STOPPED</state>
<style/>
<type>org.apache.nifi.processors.standard.RouteOnAttribute</type>
</processors>
<processors>
<id>f6327477-fb7d-4af0-a2c2-1ee50e03249e</id>
<parentGroupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</parentGroupId>
<position>
<x>467.54397601551534</x>
<y>126.61621687404391</y>
</position>
<config>
<bulletinLevel>WARN</bulletinLevel>
<comments/>
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount>
<descriptors>
<entry>
<key>f.11</key>
<value>
<name>f.11</name>
</value>
</entry>
<entry>
<key>f.1</key>
<value>
<name>f.1</name>
</value>
</entry>
<entry>
<key>f.10</key>
<value>
<name>f.10</name>
</value>
</entry>
<entry>
<key>f.3</key>
<value>
<name>f.3</name>
</value>
</entry>
<entry>
<key>f.2</key>
<value>
<name>f.2</name>
</value>
</entry>
<entry>
<key>f.5</key>
<value>
<name>f.5</name>
</value>
</entry>
<entry>
<key>f.4</key>
<value>
<name>f.4</name>
</value>
</entry>
<entry>
<key>f.7</key>
<value>
<name>f.7</name>
</value>
</entry>
<entry>
<key>f.6</key>
<value>
<name>f.6</name>
</value>
</entry>
<entry>
<key>f.9</key>
<value>
<name>f.9</name>
</value>
</entry>
<entry>
<key>f.8</key>
<value>
<name>f.8</name>
</value>
</entry>
<entry>
<key>split</key>
<value>
<name>split</name>
</value>
</entry>
<entry>
<key>Collection</key>
<value>
<name>Collection</name>
</value>
</entry>
<entry>
<key>Solr Location</key>
<value>
<name>Solr Location</name>
</value>
</entry>
<entry>
<key>Content Stream Path</key>
<value>
<name>Content Stream Path</name>
</value>
</entry>
<entry>
<key>Solr Type</key>
<value>
<name>Solr Type</name>
</value>
</entry>
<entry>
<key>Content-Type</key>
<value>
<name>Content-Type</name>
</value>
</entry>
<entry>
<key>Commit Within</key>
<value>
<name>Commit Within</name>
</value>
</entry>
</descriptors>
<lossTolerant>false</lossTolerant>
<penaltyDuration>30 sec</penaltyDuration>
<properties>
<entry>
<key>f.11</key>
<value>place_s:/place</value>
</entry>
<entry>
<key>Solr Socket Timeout</key>
<value>10 seconds</value>
</entry>
<entry>
<key>f.10</key>
<value>coordinates_s:/coordinates</value>
</entry>
<entry>
<key>ZooKeeper Connection Timeout</key>
<value>10 seconds</value>
</entry>
<entry>
<key>Solr Maximum Connections</key>
<value>10</value>
</entry>
<entry>
<key>ZooKeeper Client Timeout</key>
<value>10 seconds</value>
</entry>
<entry>
<key>split</key>
<value>/</value>
</entry>
<entry>
<key>Solr Location</key>
<value>localhost:2181</value>
</entry>
<entry>
<key>Solr Type</key>
<value>Cloud</value>
</entry>
<entry>
<key>Content-Type</key>
<value>application/json</value>
</entry>
<entry>
<key>Password</key>
</entry>
<entry>
<key>f.1</key>
<value>id:/id</value>
</entry>
<entry>
<key>f.3</key>
<value>screenName_s:/user/screen_name</value>
</entry>
<entry>
<key>f.2</key>
<value>text_t:/text</value>
</entry>
<entry>
<key>f.5</key>
<value>twitter_created_at_dt:/created_at</value>
</entry>
<entry>
<key>f.4</key>
<value>language_s:/lang</value>
</entry>
<entry>
<key>f.7</key>
<value>originalposter_s:/retweeted_status/user/screen_name</value>
</entry>
<entry>
<key>f.6</key>
<value>tag_ss:/entities/hashtags</value>
</entry>
<entry>
<key>f.9</key>
<value>geo_s:/geo</value>
</entry>
<entry>
<key>f.8</key>
<value>source_s:/source</value>
</entry>
<entry>
<key>SSL Context Service</key>
</entry>
<entry>
<key>JAAS Client App Name</key>
</entry>
<entry>
<key>Solr Maximum Connections Per Host</key>
<value>5</value>
</entry>
<entry>
<key>Username</key>
</entry>
<entry>
<key>Solr Connection Timeout</key>
<value>10 seconds</value>
</entry>
<entry>
<key>Collection</key>
<value>tweets</value>
</entry>
<entry>
<key>Content Stream Path</key>
<value>/update/json/docs</value>
</entry>
<entry>
<key>Commit Within</key>
<value>1000</value>
</entry>
</properties>
<runDurationMillis>0</runDurationMillis>
<schedulingPeriod>0 sec</schedulingPeriod>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<yieldDuration>1 sec</yieldDuration>
</config>
<name>PutSolrContentStream</name>
<relationships>
<autoTerminate>true</autoTerminate>
<name>connection_failure</name>
</relationships>
<relationships>
<autoTerminate>true</autoTerminate>
<name>failure</name>
</relationships>
<relationships>
<autoTerminate>true</autoTerminate>
<name>success</name>
</relationships>
<state>STOPPED</state>
<style/>
<type>org.apache.nifi.processors.solr.PutSolrContentStream</type>
</processors>
<processors>
<id>6f28e92f-9486-45ad-a1e3-b02e4e00bf7c</id>
<parentGroupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</parentGroupId>
<position>
<x>459.41607100345675</x>
<y>468.6240270576958</y>
</position>
<config>
<bulletinLevel>WARN</bulletinLevel>
<comments/>
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount>
<descriptors>
<entry>
<key>Group</key>
<value>
<name>Group</name>
</value>
</entry>
<entry>
<key>Owner</key>
<value>
<name>Owner</name>
</value>
</entry>
<entry>
<key>Create Missing Directories</key>
<value>
<name>Create Missing Directories</name>
</value>
</entry>
<entry>
<key>Permissions</key>
<value>
<name>Permissions</name>
</value>
</entry>
<entry>
<key>Maximum File Count</key>
<value>
<name>Maximum File Count</name>
</value>
</entry>
<entry>
<key>Last Modified Time</key>
<value>
<name>Last Modified Time</name>
</value>
</entry>
<entry>
<key>Directory</key>
<value>
<name>Directory</name>
</value>
</entry>
<entry>
<key>Conflict Resolution Strategy</key>
<value>
<name>Conflict Resolution Strategy</name>
</value>
</entry>
</descriptors>
<lossTolerant>false</lossTolerant>
<penaltyDuration>30 sec</penaltyDuration>
<properties>
<entry>
<key>Group</key>
</entry>
<entry>
<key>Owner</key>
</entry>
<entry>
<key>Create Missing Directories</key>
<value>true</value>
</entry>
<entry>
<key>Permissions</key>
</entry>
<entry>
<key>Maximum File Count</key>
</entry>
<entry>
<key>Last Modified Time</key>
</entry>
<entry>
<key>Directory</key>
<value>/tmp/tweets</value>
</entry>
<entry>
<key>Conflict Resolution Strategy</key>
<value>fail</value>
</entry>
</properties>
<runDurationMillis>0</runDurationMillis>
<schedulingPeriod>0 sec</schedulingPeriod>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<yieldDuration>1 sec</yieldDuration>
</config>
<name>PutFile</name>
<relationships>
<autoTerminate>true</autoTerminate>
<name>failure</name>
</relationships>
<relationships>
<autoTerminate>true</autoTerminate>
<name>success</name>
</relationships>
<state>STOPPED</state>
<style/>
<type>org.apache.nifi.processors.standard.PutFile</type>
</processors>
<processors>
<id>6360c55a-a0e3-4fd9-ab55-f5910c6932c6</id>
<parentGroupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</parentGroupId>
<position>
<x>966.1673094034688</x>
<y>479.1860631043438</y>
</position>
<config>
<bulletinLevel>WARN</bulletinLevel>
<comments/>
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount>
<descriptors>
<entry>
<key>Permissions umask</key>
<value>
<name>Permissions umask</name>
</value>
</entry>
<entry>
<key>Hadoop Configuration Resources</key>
<value>
<name>Hadoop Configuration Resources</name>
</value>
</entry>
<entry>
<key>Remote Owner</key>
<value>
<name>Remote Owner</name>
</value>
</entry>
<entry>
<key>Compression codec</key>
<value>
<name>Compression codec</name>
</value>
</entry>
<entry>
<key>IO Buffer Size</key>
<value>
<name>IO Buffer Size</name>
</value>
</entry>
<entry>
<key>Remote Group</key>
<value>
<name>Remote Group</name>
</value>
</entry>
<entry>
<key>Block Size</key>
<value>
<name>Block Size</name>
</value>
</entry>
<entry>
<key>Kerberos Keytab</key>
<value>
<name>Kerberos Keytab</name>
</value>
</entry>
<entry>
<key>Kerberos Principal</key>
<value>
<name>Kerberos Principal</name>
</value>
</entry>
<entry>
<key>Replication</key>
<value>
<name>Replication</name>
</value>
</entry>
<entry>
<key>Kerberos Relogin Period</key>
<value>
<name>Kerberos Relogin Period</name>
</value>
</entry>
<entry>
<key>Directory</key>
<value>
<name>Directory</name>
</value>
</entry>
<entry>
<key>Conflict Resolution Strategy</key>
<value>
<name>Conflict Resolution Strategy</name>
</value>
</entry>
</descriptors>
<lossTolerant>false</lossTolerant>
<penaltyDuration>30 sec</penaltyDuration>
<properties>
<entry>
<key>Permissions umask</key>
</entry>
<entry>
<key>Hadoop Configuration Resources</key>
<value>/etc/hadoop/conf/core-site.xml,/etc/hadoop/conf/hdfs-site.xml</value>
</entry>
<entry>
<key>Remote Owner</key>
</entry>
<entry>
<key>Additional Classpath Resources</key>
</entry>
<entry>
<key>Compression codec</key>
<value>NONE</value>
</entry>
<entry>
<key>IO Buffer Size</key>
</entry>
<entry>
<key>Remote Group</key>
</entry>
<entry>
<key>Block Size</key>
</entry>
<entry>
<key>Kerberos Keytab</key>
</entry>
<entry>
<key>Kerberos Principal</key>
</entry>
<entry>
<key>Replication</key>
<value>1</value>
</entry>
<entry>
<key>Kerberos Relogin Period</key>
<value>4 hours</value>
</entry>
<entry>
<key>Directory</key>
<value>/tmp/tweets_staging</value>
</entry>
<entry>
<key>Conflict Resolution Strategy</key>
<value>replace</value>
</entry>
</properties>
<runDurationMillis>0</runDurationMillis>
<schedulingPeriod>0 sec</schedulingPeriod>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<yieldDuration>1 sec</yieldDuration>
</config>
<name>PutHDFS</name>
<relationships>
<autoTerminate>false</autoTerminate>
<name>failure</name>
</relationships>
<relationships>
<autoTerminate>true</autoTerminate>
<name>success</name>
</relationships>
<state>STOPPED</state>
<style/>
<type>org.apache.nifi.processors.hadoop.PutHDFS</type>
</processors>
<processors>
<id>2c9405dd-f5cf-41eb-a4e6-5eeb1070d658</id>
<parentGroupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</parentGroupId>
<position>
<x>-101.8350917029849</x>
<y>-66.59999615192999</y>
</position>
<config>
<bulletinLevel>WARN</bulletinLevel>
<comments/>
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount>
<descriptors>
<entry>
<key>Consumer Key</key>
<value>
<name>Consumer Key</name>
</value>
</entry>
<entry>
<key>Consumer Secret</key>
<value>
<name>Consumer Secret</name>
</value>
</entry>
<entry>
<key>Access Token</key>
<value>
<name>Access Token</name>
</value>
</entry>
<entry>
<key>Languages</key>
<value>
<name>Languages</name>
</value>
</entry>
<entry>
<key>IDs to Follow</key>
<value>
<name>IDs to Follow</name>
</value>
</entry>
<entry>
<key>Twitter Endpoint</key>
<value>
<name>Twitter Endpoint</name>
</value>
</entry>
<entry>
<key>Locations to Filter On</key>
<value>
<name>Locations to Filter On</name>
</value>
</entry>
<entry>
<key>Terms to Filter On</key>
<value>
<name>Terms to Filter On</name>
</value>
</entry>
<entry>
<key>Access Token Secret</key>
<value>
<name>Access Token Secret</name>
</value>
</entry>
</descriptors>
<lossTolerant>false</lossTolerant>
<penaltyDuration>30 sec</penaltyDuration>
<properties>
<entry>
<key>Consumer Key</key>
<value>g28NxesU1Vpk12IBXCnIWs2Ur</value>
</entry>
<entry>
<key>Consumer Secret</key>
</entry>
<entry>
<key>Access Token</key>
<value>2885109412-UDQfXEUV2cQTYqCIbnsU7JtYqOaAksJCi6gbMgS</value>
</entry>
<entry>
<key>Languages</key>
</entry>
<entry>
<key>IDs to Follow</key>
</entry>
<entry>
<key>Twitter Endpoint</key>
<value>Filter Endpoint</value>
</entry>
<entry>
<key>Locations to Filter On</key>
</entry>
<entry>
<key>Terms to Filter On</key>
<value>AAPL,ORCL,GOOG,MSFT,DELL</value>
</entry>
<entry>
<key>Access Token Secret</key>
</entry>
</properties>
<runDurationMillis>0</runDurationMillis>
<schedulingPeriod>0 sec</schedulingPeriod>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<yieldDuration>1 sec</yieldDuration>
</config>
<name>Grab Garden Hose</name>
<relationships>
<autoTerminate>false</autoTerminate>
<name>success</name>
</relationships>
<state>STOPPED</state>
<style/>
<type>org.apache.nifi.processors.twitter.GetTwitter</type>
</processors>
<processors>
<id>d3c85c30-7a66-4351-96b7-0cbd4ff8e809</id>
<parentGroupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</parentGroupId>
<position>
<x>347.4908657243287</x>
<y>331.2840828508703</y>
</position>
<config>
<bulletinLevel>WARN</bulletinLevel>
<comments/>
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount>
<descriptors>
<entry>
<key>Regular Expression</key>
<value>
<name>Regular Expression</name>
</value>
</entry>
<entry>
<key>Replacement Value</key>
<value>
<name>Replacement Value</name>
</value>
</entry>
<entry>
<key>Evaluation Mode</key>
<value>
<name>Evaluation Mode</name>
</value>
</entry>
<entry>
<key>Character Set</key>
<value>
<name>Character Set</name>
</value>
</entry>
<entry>
<key>Maximum Buffer Size</key>
<value>
<name>Maximum Buffer Size</name>
</value>
</entry>
<entry>
<key>Replacement Strategy</key>
<value>
<name>Replacement Strategy</name>
</value>
</entry>
</descriptors>
<lossTolerant>false</lossTolerant>
<penaltyDuration>30 sec</penaltyDuration>
<properties>
<entry>
<key>Regular Expression</key>
<value>(?s:^(.*)$)</value>
</entry>
<entry>
<key>Replacement Value</key>
<value>${twitter.tweet_id}|${twitter.unixtime}|${twitter.time}|${twitter.handle}|${twitter.msg:replace('$',''):replace('\n','')}|$1</value>
</entry>
<entry>
<key>Evaluation Mode</key>
<value>Entire text</value>
</entry>
<entry>
<key>Character Set</key>
<value>UTF-8</value>
</entry>
<entry>
<key>Maximum Buffer Size</key>
<value>1 MB</value>
</entry>
<entry>
<key>Replacement Strategy</key>
<value>Regex Replace</value>
</entry>
</properties>
<runDurationMillis>0</runDurationMillis>
<schedulingPeriod>0 sec</schedulingPeriod>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<yieldDuration>1 sec</yieldDuration>
</config>
<name>ReplaceText</name>
<relationships>
<autoTerminate>true</autoTerminate>
<name>failure</name>
</relationships>
<relationships>
<autoTerminate>false</autoTerminate>
<name>success</name>
</relationships>
<state>STOPPED</state>
<style/>
<type>org.apache.nifi.processors.standard.ReplaceText</type>
</processors>
<processors>
<id>3ee301f8-d1b6-4d09-9d10-2060632e9db0</id>
<parentGroupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</parentGroupId>
<position>
<x>-110.79999648814115</x>
<y>181.37032931804072</y>
</position>
<config>
<bulletinLevel>ERROR</bulletinLevel>
<comments/>
<concurrentlySchedulableTaskCount>4</concurrentlySchedulableTaskCount>
<descriptors>
<entry>
<key>twitter.handle</key>
<value>
<name>twitter.handle</name>
</value>
</entry>
<entry>
<key>twitter.tweet_id</key>
<value>
<name>twitter.tweet_id</name>
</value>
</entry>
<entry>
<key>Destination</key>
<value>
<name>Destination</name>
</value>
</entry>
<entry>
<key>twitter.msg</key>
<value>
<name>twitter.msg</name>
</value>
</entry>
<entry>
<key>twitter.user</key>
<value>
<name>twitter.user</name>
</value>
</entry>
<entry>
<key>Return Type</key>
<value>
<name>Return Type</name>
</value>
</entry>
<entry>
<key>twitter.hashtags</key>
<value>
<name>twitter.hashtags</name>
</value>
</entry>
<entry>
<key>Null Value Representation</key>
<value>
<name>Null Value Representation</name>
</value>
</entry>
<entry>
<key>language</key>
<value>
<name>language</name>
</value>
</entry>
<entry>
<key>twitter.time</key>
<value>
<name>twitter.time</name>
</value>
</entry>
<entry>
<key>twitter.unixtime</key>
<value>
<name>twitter.unixtime</name>
</value>
</entry>
<entry>
<key>Path Not Found Behavior</key>
<value>
<name>Path Not Found Behavior</name>
</value>
</entry>
</descriptors>
<lossTolerant>false</lossTolerant>
<penaltyDuration>30 sec</penaltyDuration>
<properties>
<entry>
<key>twitter.handle</key>
<value>$.user.screen_name</value>
</entry>
<entry>
<key>twitter.tweet_id</key>
<value>$.id</value>
</entry>
<entry>
<key>Destination</key>
<value>flowfile-attribute</value>
</entry>
<entry>
<key>twitter.msg</key>
<value>$.text</value>
</entry>
<entry>
<key>twitter.user</key>
<value>$.user.name</value>
</entry>
<entry>
<key>Return Type</key>
<value>auto-detect</value>
</entry>
<entry>
<key>twitter.hashtags</key>
<value>$.entities.hashtags[0].text</value>
</entry>
<entry>
<key>Null Value Representation</key>
<value>empty string</value>
</entry>
<entry>
<key>language</key>
<value>$.lang</value>
</entry>
<entry>
<key>twitter.time</key>
<value>$.created_at</value>
</entry>
<entry>
<key>twitter.unixtime</key>
<value>$.timestamp_ms</value>
</entry>
<entry>
<key>Path Not Found Behavior</key>
<value>ignore</value>
</entry>
</properties>
<runDurationMillis>25</runDurationMillis>
<schedulingPeriod>0 sec</schedulingPeriod>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<yieldDuration>1 sec</yieldDuration>
</config>
<name>Pull Key Attributes</name>
<relationships>
<autoTerminate>true</autoTerminate>
<name>failure</name>
</relationships>
<relationships>
<autoTerminate>false</autoTerminate>
<name>matched</name>
</relationships>
<relationships>
<autoTerminate>true</autoTerminate>
<name>unmatched</name>
</relationships>
<state>STOPPED</state>
<style/>
<type>org.apache.nifi.processors.standard.EvaluateJsonPath</type>
</processors>
<processors>
<id>63500cda-60fc-433e-9d34-0250c7fe57ba</id>
<parentGroupId>f5ca9391-0f9a-4e95-8a27-3aa3a2d044ac</parentGroupId>
<position>
<x>890.901616061057</x>
<y>285.4346310401422</y>
</position>
<config>
<bulletinLevel>WARN</bulletinLevel>
<comments/>
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount>
<descriptors>
<entry>
<key>Keep Path</key>
<value>
<name>Keep Path</name>
</value>
</entry>
<entry>
<key>Maximum Group Size</key>
<value>
<name>Maximum Group Size</name>
</value>
</entry>
<entry>
<key>Merge Strategy</key>
<value>
<name>Merge Strategy</name>
</value>
</entry>
<entry>
<key>Attribute Strategy</key>
<value>
<name>Attribute Strategy</name>
</value>
</entry>
<entry>
<key>Compression Level</key>
<value>
<name>Compression Level</name>
</value>
</entry>
<entry>
<key>Maximum Number of Entries</key>
<value>
<name>Maximum Number of Entries</name>
</value>
</entry>
<entry>
<key>Minimum Group Size</key>
<value>
<name>Minimum Group Size</name>
</value>
</entry>
<entry>
<key>Maximum number of Bins</key>
<value>
<name>Maximum number of Bins</name>
</value>
</entry>
<entry>
<key>Delimiter Strategy</key>
<value>
<name>Delimiter Strategy</name>
</value>
</entry>
<entry>
<key>Merge Format</key>
<value>
<name>Merge Format</name>
</value>
</entry>
<entry>
<key>Footer File</key>
<value>
<name>Footer File</name>
</value>
</entry>
<entry>
<key>Max Bin Age</key>
<value>
<name>Max Bin Age</name>
</value>
</entry>
<entry>
<key>Demarcator File</key>
<value>
<name>Demarcator File</name>
</value>
</entry>
<entry>
<key>Correlation Attribute Name</key>
<value>
<name>Correlation Attribute Name</name>
</value>
</entry>
<entry>
<key>Header File</key>
<value>
<name>Header File</name>
</value>
</entry>
<entry>
<key>Minimum Number of Entries</key>
<value>
<name>Minimum Number of Entries</name>
</value>
</entry>
</descriptors>
<lossTolerant>false</lossTolerant>
<penaltyDuration>30 sec</penaltyDuration>
<properties>
<entry>
<key>Keep Path</key>
<value>false</value>
</entry>
<entry>
<key>Maximum Group Size</key>
</entry>
<entry>
<key>Merge Strategy</key>
<value>Bin-Packing Algorithm</value>
</entry>
<entry>
<key>Attribute Strategy</key>
<value>Keep Only Common Attributes</value>
</entry>
<entry>
<key>Compression Level</key>
<value>1</value>
</entry>
<entry>
<key>Maximum Number of Entries</key>
<value>1000</value>
</entry>
<entry>
<key>Minimum Group Size</key>
<value>0 B</value>
</entry>
<entry>
<key>Maximum number of Bins</key>
<value>100</value>
</entry>
<entry>
<key>Tar Modified Time</key>
<value>${file.lastModifiedTime}</value>
</entry>
<entry>
<key>Delimiter Strategy</key>
<value>Filename</value>
</entry>
<entry>
<key>Merge Format</key>
<value>Binary Concatenation</value>
</entry>
<entry>
<key>Footer File</key>
</entry>
<entry>
<key>Max Bin Age</key>
<value>120 seconds</value>
</entry>
<entry>
<key>Demarcator File</key>
</entry>
<entry>
<key>Correlation Attribute Name</key>
</entry>
<entry>
<key>Header File</key>
</entry>
<entry>
<key>Minimum Number of Entries</key>
<value>20</value>
</entry>
<entry>
<key>mergecontent-metadata-strategy</key>
<value>Do Not Merge Uncommon Metadata</value>
</entry>
</properties>
<runDurationMillis>0</runDurationMillis>
<schedulingPeriod>0 sec</schedulingPeriod>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<yieldDuration>1 sec</yieldDuration>
</config>
<name>MergeContent</name>
<relationships>
<autoTerminate>true</autoTerminate>
<name>failure</name>
</relationships>
<relationships>
<autoTerminate>false</autoTerminate>
<name>merged</name>
</relationships>
<relationships>
<autoTerminate>true</autoTerminate>
<name>original</name>
</relationships>
<state>STOPPED</state>
<style/>
<type>org.apache.nifi.processors.standard.MergeContent</type>
</processors>
</contents>
<name>Twitter Dashboard - Push tweets into HDFS/Solr</name>
</processGroups>
</snippet>
<timestamp>05/25/2018 01:15:25 UTC</timestamp>
</template>
</rootGroup>
<controllerServices/>
<reportingTasks>
<reportingTask>
<id>94d7cc57-0163-1000-ffff-fffffb184a9d</id>
<name>ReportLineageToAtlas</name>
<comment/>
<class>org.apache.nifi.atlas.reporting.ReportLineageToAtlas</class>
<bundle>
<group>org.apache.nifi</group>
<artifact>nifi-atlas-nar</artifact>
<version>1.5.0.3.1.0.0-564</version>
</bundle>
<schedulingPeriod>10 seconds</schedulingPeriod>
<scheduledState>RUNNING</scheduledState>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<property>
<name>atlas-urls</name>
<value>http://demo.hortonworks.com:21000</value>
</property>
<property>
<name>atlas-authentication-method</name>
<value>kerberos</value>
</property>
<property>
<name>atlas-username</name>
<value>admin</value>
</property>
<property>
<name>atlas-password</name>
<value>enc{8a6bd3aa0adb503f1defec3f42dc81b10ca4dd1a03d79aabc659cdffcf76c96a}</value>
</property>
<property>
<name>atlas-conf-dir</name>
<value>/tmp/</value>
</property>
<property>
<name>atlas-nifi-url</name>
<value>http://demo.hortonworks.com:9090/nifi</value>
</property>
<property>
<name>atlas-default-cluster-name</name>
<value>hdp</value>
</property>
<property>
<name>nifi-lineage-strategy</name>
<value>SimplePath</value>
</property>
<property>
<name>provenance-start-position</name>
<value>end-of-stream</value>
</property>
<property>
<name>provenance-batch-size</name>
<value>100</value>
</property>
<property>
<name>ssl-context-service</name>
</property>
<property>
<name>atlas-conf-create</name>
<value>true</value>
</property>
<property>
<name>nifi-kerberos-principal</name>
<value>nifi/[email protected]</value>
</property>
<property>
<name>nifi-kerberos-keytab</name>
<value>/etc/security/keytabs/nifi.service.keytab</value>
</property>
<property>
<name>kafka-bootstrap-servers</name>
<value>demo.hortonworks.com:6667</value>
</property>
<property>
<name>kafka-security-protocol</name>
<value>SASL_PLAINTEXT</value>
</property>
</reportingTask>
</reportingTasks>
</flowController>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment