Created
May 21, 2017 20:43
-
-
Save YolandaMDavis/9638cb9a124320eff025bf34e7a04c98 to your computer and use it in GitHub Desktop.
Managing Data Flow with NiFi - Demo Templates
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?xml version="1.0" ?> | |
<template encoding-version="1.1"> | |
<description></description> | |
<groupId>142ee790-015c-1000-9a0d-a31aac7e0eb3</groupId> | |
<name>GetTwitterDataSQLMongo-2017</name> | |
<snippet> | |
<connections> | |
<id>bcbbda47-e17a-32fb-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<backPressureDataSizeThreshold>1 GB</backPressureDataSizeThreshold> | |
<backPressureObjectThreshold>10000</backPressureObjectThreshold> | |
<destination> | |
<groupId>e5a17068-5da9-3260-0000-000000000000</groupId> | |
<id>5e74cd11-b091-337a-0000-000000000000</id> | |
<type>PROCESSOR</type> | |
</destination> | |
<flowFileExpiration>0 sec</flowFileExpiration> | |
<labelIndex>1</labelIndex> | |
<name></name> | |
<selectedRelationships>success</selectedRelationships> | |
<source> | |
<groupId>e5a17068-5da9-3260-0000-000000000000</groupId> | |
<id>95e97293-a576-3592-0000-000000000000</id> | |
<type>PROCESSOR</type> | |
</source> | |
<zIndex>0</zIndex> | |
</connections> | |
<connections> | |
<id>c7356249-dc89-39ee-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<backPressureDataSizeThreshold>1 GB</backPressureDataSizeThreshold> | |
<backPressureObjectThreshold>10000</backPressureObjectThreshold> | |
<destination> | |
<groupId>e5a17068-5da9-3260-0000-000000000000</groupId> | |
<id>56381546-0b2e-3924-0000-000000000000</id> | |
<type>PROCESSOR</type> | |
</destination> | |
<flowFileExpiration>0 sec</flowFileExpiration> | |
<labelIndex>1</labelIndex> | |
<name></name> | |
<selectedRelationships>success</selectedRelationships> | |
<source> | |
<groupId>e5a17068-5da9-3260-0000-000000000000</groupId> | |
<id>5e74cd11-b091-337a-0000-000000000000</id> | |
<type>PROCESSOR</type> | |
</source> | |
<zIndex>0</zIndex> | |
</connections> | |
<connections> | |
<id>e998c447-b463-3fe5-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<backPressureDataSizeThreshold>1 GB</backPressureDataSizeThreshold> | |
<backPressureObjectThreshold>10000</backPressureObjectThreshold> | |
<destination> | |
<groupId>e5a17068-5da9-3260-0000-000000000000</groupId> | |
<id>04389c9f-7be7-3f7d-0000-000000000000</id> | |
<type>PROCESSOR</type> | |
</destination> | |
<flowFileExpiration>0 sec</flowFileExpiration> | |
<labelIndex>1</labelIndex> | |
<name></name> | |
<selectedRelationships>sql</selectedRelationships> | |
<source> | |
<groupId>e5a17068-5da9-3260-0000-000000000000</groupId> | |
<id>613ed4cc-8e2a-32d3-0000-000000000000</id> | |
<type>PROCESSOR</type> | |
</source> | |
<zIndex>0</zIndex> | |
</connections> | |
<connections> | |
<id>2c8b71b3-9ad0-358e-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<backPressureDataSizeThreshold>1 GB</backPressureDataSizeThreshold> | |
<backPressureObjectThreshold>10000</backPressureObjectThreshold> | |
<destination> | |
<groupId>e5a17068-5da9-3260-0000-000000000000</groupId> | |
<id>f7e5f138-c92c-37ab-0000-000000000000</id> | |
<type>PROCESSOR</type> | |
</destination> | |
<flowFileExpiration>0 sec</flowFileExpiration> | |
<labelIndex>1</labelIndex> | |
<name></name> | |
<selectedRelationships>success</selectedRelationships> | |
<source> | |
<groupId>e5a17068-5da9-3260-0000-000000000000</groupId> | |
<id>5e74cd11-b091-337a-0000-000000000000</id> | |
<type>PROCESSOR</type> | |
</source> | |
<zIndex>0</zIndex> | |
</connections> | |
<connections> | |
<id>3180b373-66b5-3254-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<backPressureDataSizeThreshold>1 GB</backPressureDataSizeThreshold> | |
<backPressureObjectThreshold>10000</backPressureObjectThreshold> | |
<destination> | |
<groupId>e5a17068-5da9-3260-0000-000000000000</groupId> | |
<id>613ed4cc-8e2a-32d3-0000-000000000000</id> | |
<type>PROCESSOR</type> | |
</destination> | |
<flowFileExpiration>0 sec</flowFileExpiration> | |
<labelIndex>1</labelIndex> | |
<name></name> | |
<selectedRelationships>success</selectedRelationships> | |
<source> | |
<groupId>e5a17068-5da9-3260-0000-000000000000</groupId> | |
<id>5e74cd11-b091-337a-0000-000000000000</id> | |
<type>PROCESSOR</type> | |
</source> | |
<zIndex>0</zIndex> | |
</connections> | |
<controllerServices> | |
<id>2b06aa19-db49-3da9-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<bundle> | |
<artifact>nifi-dbcp-service-nar</artifact> | |
<group>org.apache.nifi</group> | |
<version>1.3.0-SNAPSHOT</version> | |
</bundle> | |
<comments></comments> | |
<descriptors> | |
<entry> | |
<key>Database Connection URL</key> | |
<value> | |
<name>Database Connection URL</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Database Driver Class Name</key> | |
<value> | |
<name>Database Driver Class Name</name> | |
</value> | |
</entry> | |
<entry> | |
<key>database-driver-locations</key> | |
<value> | |
<name>database-driver-locations</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Database User</key> | |
<value> | |
<name>Database User</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Password</key> | |
<value> | |
<name>Password</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Max Wait Time</key> | |
<value> | |
<name>Max Wait Time</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Max Total Connections</key> | |
<value> | |
<name>Max Total Connections</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Validation-query</key> | |
<value> | |
<name>Validation-query</name> | |
</value> | |
</entry> | |
</descriptors> | |
<name>DBCPConnectionPool</name> | |
<persistsState>false</persistsState> | |
<properties> | |
<entry> | |
<key>Database Connection URL</key> | |
<value>jdbc:mysql://localhost:3306/twitter_dump</value> | |
</entry> | |
<entry> | |
<key>Database Driver Class Name</key> | |
<value>com.mysql.jdbc.Driver</value> | |
</entry> | |
<entry> | |
<key>database-driver-locations</key> | |
<value>/Users/ydavis/dev/tools/mysql-connector-java-5.1.42/mysql-connector-java-5.1.42-bin.jar</value> | |
</entry> | |
<entry> | |
<key>Database User</key> | |
<value>devanalyst</value> | |
</entry> | |
<entry> | |
<key>Password</key> | |
</entry> | |
<entry> | |
<key>Max Wait Time</key> | |
<value>500 millis</value> | |
</entry> | |
<entry> | |
<key>Max Total Connections</key> | |
<value>8</value> | |
</entry> | |
<entry> | |
<key>Validation-query</key> | |
</entry> | |
</properties> | |
<state>ENABLED</state> | |
<type>org.apache.nifi.dbcp.DBCPConnectionPool</type> | |
</controllerServices> | |
<processors> | |
<id>95e97293-a576-3592-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<position> | |
<x>0.0</x> | |
<y>245.19835042953494</y> | |
</position> | |
<bundle> | |
<artifact>nifi-social-media-nar</artifact> | |
<group>org.apache.nifi</group> | |
<version>1.3.0-SNAPSHOT</version> | |
</bundle> | |
<config> | |
<bulletinLevel>WARN</bulletinLevel> | |
<comments></comments> | |
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount> | |
<descriptors> | |
<entry> | |
<key>Twitter Endpoint</key> | |
<value> | |
<name>Twitter Endpoint</name> | |
</value> | |
</entry> | |
<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>Access Token Secret</key> | |
<value> | |
<name>Access Token Secret</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Languages</key> | |
<value> | |
<name>Languages</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Terms to Filter On</key> | |
<value> | |
<name>Terms to Filter On</name> | |
</value> | |
</entry> | |
<entry> | |
<key>IDs to Follow</key> | |
<value> | |
<name>IDs to Follow</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Locations to Filter On</key> | |
<value> | |
<name>Locations to Filter On</name> | |
</value> | |
</entry> | |
</descriptors> | |
<executionNode>ALL</executionNode> | |
<lossTolerant>false</lossTolerant> | |
<penaltyDuration>30 sec</penaltyDuration> | |
<properties> | |
<entry> | |
<key>Twitter Endpoint</key> | |
<value>Filter Endpoint</value> | |
</entry> | |
<entry> | |
<key>Consumer Key</key> | |
<value>PWGWQqIIlnMw1mVtlLqKap2tc</value> | |
</entry> | |
<entry> | |
<key>Consumer Secret</key> | |
</entry> | |
<entry> | |
<key>Access Token</key> | |
<value>548586960-SKaZmb67v7R33Nh6sz05BqaYVilRvXpBFvYUDOu5</value> | |
</entry> | |
<entry> | |
<key>Access Token Secret</key> | |
</entry> | |
<entry> | |
<key>Languages</key> | |
</entry> | |
<entry> | |
<key>Terms to Filter On</key> | |
<value>Baltimore</value> | |
</entry> | |
<entry> | |
<key>IDs to Follow</key> | |
</entry> | |
<entry> | |
<key>Locations to Filter On</key> | |
</entry> | |
</properties> | |
<runDurationMillis>0</runDurationMillis> | |
<schedulingPeriod>5 sec</schedulingPeriod> | |
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy> | |
<yieldDuration>1 sec</yieldDuration> | |
</config> | |
<name>GetTwitter</name> | |
<relationships> | |
<autoTerminate>false</autoTerminate> | |
<name>success</name> | |
</relationships> | |
<style></style> | |
<type>org.apache.nifi.processors.twitter.GetTwitter</type> | |
</processors> | |
<processors> | |
<id>f7e5f138-c92c-37ab-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<position> | |
<x>648.9961853027344</x> | |
<y>683.5735080488874</y> | |
</position> | |
<bundle> | |
<artifact>nifi-standard-nar</artifact> | |
<group>org.apache.nifi</group> | |
<version>1.3.0-SNAPSHOT</version> | |
</bundle> | |
<config> | |
<bulletinLevel>WARN</bulletinLevel> | |
<comments></comments> | |
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount> | |
<descriptors> | |
<entry> | |
<key>Directory</key> | |
<value> | |
<name>Directory</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Conflict Resolution Strategy</key> | |
<value> | |
<name>Conflict Resolution Strategy</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Create Missing Directories</key> | |
<value> | |
<name>Create Missing Directories</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>Permissions</key> | |
<value> | |
<name>Permissions</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Owner</key> | |
<value> | |
<name>Owner</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Group</key> | |
<value> | |
<name>Group</name> | |
</value> | |
</entry> | |
</descriptors> | |
<executionNode>ALL</executionNode> | |
<lossTolerant>false</lossTolerant> | |
<penaltyDuration>30 sec</penaltyDuration> | |
<properties> | |
<entry> | |
<key>Directory</key> | |
<value>/Users/ydavis/Documents/Work/Hortonworks/HDF/Customer Presentations/Capital One/twitter-demo</value> | |
</entry> | |
<entry> | |
<key>Conflict Resolution Strategy</key> | |
<value>fail</value> | |
</entry> | |
<entry> | |
<key>Create Missing Directories</key> | |
<value>true</value> | |
</entry> | |
<entry> | |
<key>Maximum File Count</key> | |
</entry> | |
<entry> | |
<key>Last Modified Time</key> | |
</entry> | |
<entry> | |
<key>Permissions</key> | |
</entry> | |
<entry> | |
<key>Owner</key> | |
</entry> | |
<entry> | |
<key>Group</key> | |
</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> | |
<style></style> | |
<type>org.apache.nifi.processors.standard.PutFile</type> | |
</processors> | |
<processors> | |
<id>04389c9f-7be7-3f7d-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<position> | |
<x>1318.0425720214844</x> | |
<y>679.7179168041337</y> | |
</position> | |
<bundle> | |
<artifact>nifi-standard-nar</artifact> | |
<group>org.apache.nifi</group> | |
<version>1.3.0-SNAPSHOT</version> | |
</bundle> | |
<config> | |
<bulletinLevel>WARN</bulletinLevel> | |
<comments></comments> | |
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount> | |
<descriptors> | |
<entry> | |
<key>JDBC Connection Pool</key> | |
<value> | |
<identifiesControllerService>org.apache.nifi.dbcp.DBCPService</identifiesControllerService> | |
<name>JDBC Connection Pool</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Support Fragmented Transactions</key> | |
<value> | |
<name>Support Fragmented Transactions</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Transaction Timeout</key> | |
<value> | |
<name>Transaction Timeout</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Batch Size</key> | |
<value> | |
<name>Batch Size</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Obtain Generated Keys</key> | |
<value> | |
<name>Obtain Generated Keys</name> | |
</value> | |
</entry> | |
<entry> | |
<key>rollback-on-failure</key> | |
<value> | |
<name>rollback-on-failure</name> | |
</value> | |
</entry> | |
</descriptors> | |
<executionNode>ALL</executionNode> | |
<lossTolerant>false</lossTolerant> | |
<penaltyDuration>30 sec</penaltyDuration> | |
<properties> | |
<entry> | |
<key>JDBC Connection Pool</key> | |
<value>2b06aa19-db49-3da9-0000-000000000000</value> | |
</entry> | |
<entry> | |
<key>Support Fragmented Transactions</key> | |
<value>true</value> | |
</entry> | |
<entry> | |
<key>Transaction Timeout</key> | |
</entry> | |
<entry> | |
<key>Batch Size</key> | |
<value>100</value> | |
</entry> | |
<entry> | |
<key>Obtain Generated Keys</key> | |
<value>false</value> | |
</entry> | |
<entry> | |
<key>rollback-on-failure</key> | |
<value>false</value> | |
</entry> | |
</properties> | |
<runDurationMillis>0</runDurationMillis> | |
<schedulingPeriod>0 sec</schedulingPeriod> | |
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy> | |
<yieldDuration>1 sec</yieldDuration> | |
</config> | |
<name>PutSQL</name> | |
<relationships> | |
<autoTerminate>true</autoTerminate> | |
<name>failure</name> | |
</relationships> | |
<relationships> | |
<autoTerminate>true</autoTerminate> | |
<name>retry</name> | |
</relationships> | |
<relationships> | |
<autoTerminate>true</autoTerminate> | |
<name>success</name> | |
</relationships> | |
<style></style> | |
<type>org.apache.nifi.processors.standard.PutSQL</type> | |
</processors> | |
<processors> | |
<id>56381546-0b2e-3924-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<position> | |
<x>1301.1581115722656</x> | |
<y>0.0</y> | |
</position> | |
<bundle> | |
<artifact>nifi-mongodb-nar</artifact> | |
<group>org.apache.nifi</group> | |
<version>1.3.0-SNAPSHOT</version> | |
</bundle> | |
<config> | |
<bulletinLevel>WARN</bulletinLevel> | |
<comments></comments> | |
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount> | |
<descriptors> | |
<entry> | |
<key>Mongo URI</key> | |
<value> | |
<name>Mongo URI</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Mongo Database Name</key> | |
<value> | |
<name>Mongo Database Name</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Mongo Collection Name</key> | |
<value> | |
<name>Mongo Collection Name</name> | |
</value> | |
</entry> | |
<entry> | |
<key>ssl-context-service</key> | |
<value> | |
<identifiesControllerService>org.apache.nifi.ssl.SSLContextService</identifiesControllerService> | |
<name>ssl-context-service</name> | |
</value> | |
</entry> | |
<entry> | |
<key>ssl-client-auth</key> | |
<value> | |
<name>ssl-client-auth</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Mode</key> | |
<value> | |
<name>Mode</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Upsert</key> | |
<value> | |
<name>Upsert</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Update Query Key</key> | |
<value> | |
<name>Update Query Key</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Write Concern</key> | |
<value> | |
<name>Write Concern</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Character Set</key> | |
<value> | |
<name>Character Set</name> | |
</value> | |
</entry> | |
</descriptors> | |
<executionNode>ALL</executionNode> | |
<lossTolerant>false</lossTolerant> | |
<penaltyDuration>30 sec</penaltyDuration> | |
<properties> | |
<entry> | |
<key>Mongo URI</key> | |
<value>mongodb://localhost:27017</value> | |
</entry> | |
<entry> | |
<key>Mongo Database Name</key> | |
<value>twitter_dump</value> | |
</entry> | |
<entry> | |
<key>Mongo Collection Name</key> | |
<value>subset-tweets</value> | |
</entry> | |
<entry> | |
<key>ssl-context-service</key> | |
</entry> | |
<entry> | |
<key>ssl-client-auth</key> | |
<value>REQUIRED</value> | |
</entry> | |
<entry> | |
<key>Mode</key> | |
<value>insert</value> | |
</entry> | |
<entry> | |
<key>Upsert</key> | |
<value>false</value> | |
</entry> | |
<entry> | |
<key>Update Query Key</key> | |
<value>_id</value> | |
</entry> | |
<entry> | |
<key>Write Concern</key> | |
<value>ACKNOWLEDGED</value> | |
</entry> | |
<entry> | |
<key>Character Set</key> | |
<value>UTF-8</value> | |
</entry> | |
</properties> | |
<runDurationMillis>0</runDurationMillis> | |
<schedulingPeriod>0 sec</schedulingPeriod> | |
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy> | |
<yieldDuration>1 sec</yieldDuration> | |
</config> | |
<name>PutMongo</name> | |
<relationships> | |
<autoTerminate>true</autoTerminate> | |
<name>failure</name> | |
</relationships> | |
<relationships> | |
<autoTerminate>true</autoTerminate> | |
<name>success</name> | |
</relationships> | |
<style></style> | |
<type>org.apache.nifi.processors.mongodb.PutMongo</type> | |
</processors> | |
<processors> | |
<id>5e74cd11-b091-337a-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<position> | |
<x>643.7197265625</x> | |
<y>251.77098941802979</y> | |
</position> | |
<bundle> | |
<artifact>nifi-standard-nar</artifact> | |
<group>org.apache.nifi</group> | |
<version>1.3.0-SNAPSHOT</version> | |
</bundle> | |
<config> | |
<bulletinLevel>WARN</bulletinLevel> | |
<comments></comments> | |
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount> | |
<descriptors> | |
<entry> | |
<key>jolt-transform</key> | |
<value> | |
<name>jolt-transform</name> | |
</value> | |
</entry> | |
<entry> | |
<key>jolt-custom-class</key> | |
<value> | |
<name>jolt-custom-class</name> | |
</value> | |
</entry> | |
<entry> | |
<key>jolt-custom-modules</key> | |
<value> | |
<name>jolt-custom-modules</name> | |
</value> | |
</entry> | |
<entry> | |
<key>jolt-spec</key> | |
<value> | |
<name>jolt-spec</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Transform Cache Size</key> | |
<value> | |
<name>Transform Cache Size</name> | |
</value> | |
</entry> | |
</descriptors> | |
<executionNode>ALL</executionNode> | |
<lossTolerant>false</lossTolerant> | |
<penaltyDuration>30 sec</penaltyDuration> | |
<properties> | |
<entry> | |
<key>jolt-transform</key> | |
<value>jolt-transform-chain</value> | |
</entry> | |
<entry> | |
<key>jolt-custom-class</key> | |
</entry> | |
<entry> | |
<key>jolt-custom-modules</key> | |
</entry> | |
<entry> | |
<key>jolt-spec</key> | |
<value>[{ | |
"operation": "shift", | |
"spec": { | |
"id": "tweet_id", | |
"text": "tweet_text" | |
} | |
},{ | |
"operation": "modify-default-beta", | |
"spec": { | |
"~in_reply_to_status_id": 0, | |
"~in_reply_to_user_id": "", | |
"~in_reply_to_user_id_str": 0, | |
"~in_reply_to_screen_name": "" | |
} | |
}]</value> | |
</entry> | |
<entry> | |
<key>Transform Cache Size</key> | |
<value>1000</value> | |
</entry> | |
</properties> | |
<runDurationMillis>0</runDurationMillis> | |
<schedulingPeriod>0 sec</schedulingPeriod> | |
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy> | |
<yieldDuration>1 sec</yieldDuration> | |
</config> | |
<name>JoltTransformJSON</name> | |
<relationships> | |
<autoTerminate>true</autoTerminate> | |
<name>failure</name> | |
</relationships> | |
<relationships> | |
<autoTerminate>false</autoTerminate> | |
<name>success</name> | |
</relationships> | |
<style></style> | |
<type>org.apache.nifi.processors.standard.JoltTransformJSON</type> | |
</processors> | |
<processors> | |
<id>613ed4cc-8e2a-32d3-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<position> | |
<x>1315.9320983886719</x> | |
<y>260.43652663069304</y> | |
</position> | |
<bundle> | |
<artifact>nifi-standard-nar</artifact> | |
<group>org.apache.nifi</group> | |
<version>1.3.0-SNAPSHOT</version> | |
</bundle> | |
<config> | |
<bulletinLevel>WARN</bulletinLevel> | |
<comments></comments> | |
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount> | |
<descriptors> | |
<entry> | |
<key>JDBC Connection Pool</key> | |
<value> | |
<identifiesControllerService>org.apache.nifi.dbcp.DBCPService</identifiesControllerService> | |
<name>JDBC Connection Pool</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Statement Type</key> | |
<value> | |
<name>Statement Type</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Table Name</key> | |
<value> | |
<name>Table Name</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Catalog Name</key> | |
<value> | |
<name>Catalog Name</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Schema Name</key> | |
<value> | |
<name>Schema Name</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Translate Field Names</key> | |
<value> | |
<name>Translate Field Names</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Unmatched Field Behavior</key> | |
<value> | |
<name>Unmatched Field Behavior</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Unmatched Column Behavior</key> | |
<value> | |
<name>Unmatched Column Behavior</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Update Keys</key> | |
<value> | |
<name>Update Keys</name> | |
</value> | |
</entry> | |
<entry> | |
<key>jts-quoted-identifiers</key> | |
<value> | |
<name>jts-quoted-identifiers</name> | |
</value> | |
</entry> | |
<entry> | |
<key>jts-quoted-table-identifiers</key> | |
<value> | |
<name>jts-quoted-table-identifiers</name> | |
</value> | |
</entry> | |
</descriptors> | |
<executionNode>ALL</executionNode> | |
<lossTolerant>false</lossTolerant> | |
<penaltyDuration>30 sec</penaltyDuration> | |
<properties> | |
<entry> | |
<key>JDBC Connection Pool</key> | |
<value>2b06aa19-db49-3da9-0000-000000000000</value> | |
</entry> | |
<entry> | |
<key>Statement Type</key> | |
<value>INSERT</value> | |
</entry> | |
<entry> | |
<key>Table Name</key> | |
<value>twitter_dump.`subset-tweets`</value> | |
</entry> | |
<entry> | |
<key>Catalog Name</key> | |
</entry> | |
<entry> | |
<key>Schema Name</key> | |
</entry> | |
<entry> | |
<key>Translate Field Names</key> | |
<value>true</value> | |
</entry> | |
<entry> | |
<key>Unmatched Field Behavior</key> | |
<value>Ignore Unmatched Fields</value> | |
</entry> | |
<entry> | |
<key>Unmatched Column Behavior</key> | |
<value>Fail on Unmatched Columns</value> | |
</entry> | |
<entry> | |
<key>Update Keys</key> | |
</entry> | |
<entry> | |
<key>jts-quoted-identifiers</key> | |
<value>false</value> | |
</entry> | |
<entry> | |
<key>jts-quoted-table-identifiers</key> | |
<value>false</value> | |
</entry> | |
</properties> | |
<runDurationMillis>0</runDurationMillis> | |
<schedulingPeriod>0 sec</schedulingPeriod> | |
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy> | |
<yieldDuration>1 sec</yieldDuration> | |
</config> | |
<name>ConvertJSONToSQL</name> | |
<relationships> | |
<autoTerminate>true</autoTerminate> | |
<name>failure</name> | |
</relationships> | |
<relationships> | |
<autoTerminate>true</autoTerminate> | |
<name>original</name> | |
</relationships> | |
<relationships> | |
<autoTerminate>false</autoTerminate> | |
<name>sql</name> | |
</relationships> | |
<style></style> | |
<type>org.apache.nifi.processors.standard.ConvertJSONToSQL</type> | |
</processors> | |
</snippet> | |
<timestamp>05/21/2017 16:36:53 EDT</timestamp> | |
</template> |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
<?xml version="1.0" ?> | |
<template encoding-version="1.1"> | |
<description></description> | |
<groupId>142ee790-015c-1000-9a0d-a31aac7e0eb3</groupId> | |
<name>GetTwitterData-2017</name> | |
<snippet> | |
<connections> | |
<id>bcbbda47-e17a-32fb-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<backPressureDataSizeThreshold>1 GB</backPressureDataSizeThreshold> | |
<backPressureObjectThreshold>10000</backPressureObjectThreshold> | |
<destination> | |
<groupId>e5a17068-5da9-3260-0000-000000000000</groupId> | |
<id>5e74cd11-b091-337a-0000-000000000000</id> | |
<type>PROCESSOR</type> | |
</destination> | |
<flowFileExpiration>0 sec</flowFileExpiration> | |
<labelIndex>1</labelIndex> | |
<name></name> | |
<selectedRelationships>success</selectedRelationships> | |
<source> | |
<groupId>e5a17068-5da9-3260-0000-000000000000</groupId> | |
<id>95e97293-a576-3592-0000-000000000000</id> | |
<type>PROCESSOR</type> | |
</source> | |
<zIndex>0</zIndex> | |
</connections> | |
<connections> | |
<id>2c8b71b3-9ad0-358e-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<backPressureDataSizeThreshold>1 GB</backPressureDataSizeThreshold> | |
<backPressureObjectThreshold>10000</backPressureObjectThreshold> | |
<destination> | |
<groupId>e5a17068-5da9-3260-0000-000000000000</groupId> | |
<id>f7e5f138-c92c-37ab-0000-000000000000</id> | |
<type>PROCESSOR</type> | |
</destination> | |
<flowFileExpiration>0 sec</flowFileExpiration> | |
<labelIndex>1</labelIndex> | |
<name></name> | |
<selectedRelationships>success</selectedRelationships> | |
<source> | |
<groupId>e5a17068-5da9-3260-0000-000000000000</groupId> | |
<id>5e74cd11-b091-337a-0000-000000000000</id> | |
<type>PROCESSOR</type> | |
</source> | |
<zIndex>0</zIndex> | |
</connections> | |
<processors> | |
<id>95e97293-a576-3592-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<position> | |
<x>0.0</x> | |
<y>0.0</y> | |
</position> | |
<bundle> | |
<artifact>nifi-social-media-nar</artifact> | |
<group>org.apache.nifi</group> | |
<version>1.3.0-SNAPSHOT</version> | |
</bundle> | |
<config> | |
<bulletinLevel>WARN</bulletinLevel> | |
<comments></comments> | |
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount> | |
<descriptors> | |
<entry> | |
<key>Twitter Endpoint</key> | |
<value> | |
<name>Twitter Endpoint</name> | |
</value> | |
</entry> | |
<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>Access Token Secret</key> | |
<value> | |
<name>Access Token Secret</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Languages</key> | |
<value> | |
<name>Languages</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Terms to Filter On</key> | |
<value> | |
<name>Terms to Filter On</name> | |
</value> | |
</entry> | |
<entry> | |
<key>IDs to Follow</key> | |
<value> | |
<name>IDs to Follow</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Locations to Filter On</key> | |
<value> | |
<name>Locations to Filter On</name> | |
</value> | |
</entry> | |
</descriptors> | |
<executionNode>ALL</executionNode> | |
<lossTolerant>false</lossTolerant> | |
<penaltyDuration>30 sec</penaltyDuration> | |
<properties> | |
<entry> | |
<key>Twitter Endpoint</key> | |
<value>Filter Endpoint</value> | |
</entry> | |
<entry> | |
<key>Consumer Key</key> | |
<value>PWGWQqIIlnMw1mVtlLqKap2tc</value> | |
</entry> | |
<entry> | |
<key>Consumer Secret</key> | |
</entry> | |
<entry> | |
<key>Access Token</key> | |
<value>548586960-SKaZmb67v7R33Nh6sz05BqaYVilRvXpBFvYUDOu5</value> | |
</entry> | |
<entry> | |
<key>Access Token Secret</key> | |
</entry> | |
<entry> | |
<key>Languages</key> | |
</entry> | |
<entry> | |
<key>Terms to Filter On</key> | |
<value>Baltimore</value> | |
</entry> | |
<entry> | |
<key>IDs to Follow</key> | |
</entry> | |
<entry> | |
<key>Locations to Filter On</key> | |
</entry> | |
</properties> | |
<runDurationMillis>0</runDurationMillis> | |
<schedulingPeriod>5 sec</schedulingPeriod> | |
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy> | |
<yieldDuration>1 sec</yieldDuration> | |
</config> | |
<name>GetTwitter</name> | |
<relationships> | |
<autoTerminate>false</autoTerminate> | |
<name>success</name> | |
</relationships> | |
<style></style> | |
<type>org.apache.nifi.processors.twitter.GetTwitter</type> | |
</processors> | |
<processors> | |
<id>f7e5f138-c92c-37ab-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<position> | |
<x>648.9961853027344</x> | |
<y>438.37515761935254</y> | |
</position> | |
<bundle> | |
<artifact>nifi-standard-nar</artifact> | |
<group>org.apache.nifi</group> | |
<version>1.3.0-SNAPSHOT</version> | |
</bundle> | |
<config> | |
<bulletinLevel>WARN</bulletinLevel> | |
<comments></comments> | |
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount> | |
<descriptors> | |
<entry> | |
<key>Directory</key> | |
<value> | |
<name>Directory</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Conflict Resolution Strategy</key> | |
<value> | |
<name>Conflict Resolution Strategy</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Create Missing Directories</key> | |
<value> | |
<name>Create Missing Directories</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>Permissions</key> | |
<value> | |
<name>Permissions</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Owner</key> | |
<value> | |
<name>Owner</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Group</key> | |
<value> | |
<name>Group</name> | |
</value> | |
</entry> | |
</descriptors> | |
<executionNode>ALL</executionNode> | |
<lossTolerant>false</lossTolerant> | |
<penaltyDuration>30 sec</penaltyDuration> | |
<properties> | |
<entry> | |
<key>Directory</key> | |
<value>/Users/ydavis/Documents/Work/Hortonworks/HDF/Customer Presentations/Capital One/twitter-demo</value> | |
</entry> | |
<entry> | |
<key>Conflict Resolution Strategy</key> | |
<value>fail</value> | |
</entry> | |
<entry> | |
<key>Create Missing Directories</key> | |
<value>true</value> | |
</entry> | |
<entry> | |
<key>Maximum File Count</key> | |
</entry> | |
<entry> | |
<key>Last Modified Time</key> | |
</entry> | |
<entry> | |
<key>Permissions</key> | |
</entry> | |
<entry> | |
<key>Owner</key> | |
</entry> | |
<entry> | |
<key>Group</key> | |
</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> | |
<style></style> | |
<type>org.apache.nifi.processors.standard.PutFile</type> | |
</processors> | |
<processors> | |
<id>5e74cd11-b091-337a-0000-000000000000</id> | |
<parentGroupId>e5a17068-5da9-3260-0000-000000000000</parentGroupId> | |
<position> | |
<x>643.7197265625</x> | |
<y>6.572638988494845</y> | |
</position> | |
<bundle> | |
<artifact>nifi-standard-nar</artifact> | |
<group>org.apache.nifi</group> | |
<version>1.3.0-SNAPSHOT</version> | |
</bundle> | |
<config> | |
<bulletinLevel>WARN</bulletinLevel> | |
<comments></comments> | |
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount> | |
<descriptors> | |
<entry> | |
<key>jolt-transform</key> | |
<value> | |
<name>jolt-transform</name> | |
</value> | |
</entry> | |
<entry> | |
<key>jolt-custom-class</key> | |
<value> | |
<name>jolt-custom-class</name> | |
</value> | |
</entry> | |
<entry> | |
<key>jolt-custom-modules</key> | |
<value> | |
<name>jolt-custom-modules</name> | |
</value> | |
</entry> | |
<entry> | |
<key>jolt-spec</key> | |
<value> | |
<name>jolt-spec</name> | |
</value> | |
</entry> | |
<entry> | |
<key>Transform Cache Size</key> | |
<value> | |
<name>Transform Cache Size</name> | |
</value> | |
</entry> | |
</descriptors> | |
<executionNode>ALL</executionNode> | |
<lossTolerant>false</lossTolerant> | |
<penaltyDuration>30 sec</penaltyDuration> | |
<properties> | |
<entry> | |
<key>jolt-transform</key> | |
<value>jolt-transform-chain</value> | |
</entry> | |
<entry> | |
<key>jolt-custom-class</key> | |
</entry> | |
<entry> | |
<key>jolt-custom-modules</key> | |
</entry> | |
<entry> | |
<key>jolt-spec</key> | |
<value>[{ | |
"operation": "shift", | |
"spec": { | |
"id": "tweet_id", | |
"text": "tweet_text" | |
} | |
},{ | |
"operation": "modify-default-beta", | |
"spec": { | |
"~in_reply_to_status_id": 0, | |
"~in_reply_to_user_id": "", | |
"~in_reply_to_user_id_str": 0, | |
"~in_reply_to_screen_name": "" | |
} | |
}]</value> | |
</entry> | |
<entry> | |
<key>Transform Cache Size</key> | |
<value>1000</value> | |
</entry> | |
</properties> | |
<runDurationMillis>0</runDurationMillis> | |
<schedulingPeriod>0 sec</schedulingPeriod> | |
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy> | |
<yieldDuration>1 sec</yieldDuration> | |
</config> | |
<name>JoltTransformJSON</name> | |
<relationships> | |
<autoTerminate>true</autoTerminate> | |
<name>failure</name> | |
</relationships> | |
<relationships> | |
<autoTerminate>false</autoTerminate> | |
<name>success</name> | |
</relationships> | |
<style></style> | |
<type>org.apache.nifi.processors.standard.JoltTransformJSON</type> | |
</processors> | |
</snippet> | |
<timestamp>05/21/2017 16:35:57 EDT</timestamp> | |
</template> |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment