Skip to content

Instantly share code, notes, and snippets.

@ijokarumawak

ijokarumawak/Example_CSV_to_Database.xml

Created May 18, 2017 04:40
Show Gist options
  • Star 0 You must be signed in to star a gist
  • Fork 1 You must be signed in to fork a gist
  • Save ijokarumawak/ddf8a67162a97d022e226c706d9f3386 to your computer and use it in GitHub Desktop.
Save ijokarumawak/ddf8a67162a97d022e226c706d9f3386 to your computer and use it in GitHub Desktop.
Download ZIP
Example NiFi flow template to read records from CSV file and put those into database.
Raw
Example_CSV_to_Database.xml
<?xml version="1.0" ?>
<template encoding-version="1.1">
<description></description>
<groupId>e13efe89-015b-1000-9a4c-10881ee259c9</groupId>
<name>Example CSV to Database</name>
<snippet>
<processGroups>
<id>634b599a-8ee7-3ea4-0000-000000000000</id>
<parentGroupId>8925b4b3-f0af-3a75-0000-000000000000</parentGroupId>
<position>
<x>0.0</x>
<y>0.0</y>
</position>
<comments></comments>
<contents>
<connections>
<id>9c217220-263a-3c7e-0000-000000000000</id>
<parentGroupId>634b599a-8ee7-3ea4-0000-000000000000</parentGroupId>
<backPressureDataSizeThreshold>1 GB</backPressureDataSizeThreshold>
<backPressureObjectThreshold>10000</backPressureObjectThreshold>
<bends>
<x>731.0</x>
<y>500.0</y>
</bends>
<destination>
<groupId>634b599a-8ee7-3ea4-0000-000000000000</groupId>
<id>5f5322ef-ee3f-30aa-0000-000000000000</id>
<type>PROCESSOR</type>
</destination>
<flowFileExpiration>0 sec</flowFileExpiration>
<labelIndex>0</labelIndex>
<name></name>
<selectedRelationships>failure</selectedRelationships>
<source>
<groupId>634b599a-8ee7-3ea4-0000-000000000000</groupId>
<id>c2962d55-20ed-322c-0000-000000000000</id>
<type>PROCESSOR</type>
</source>
<zIndex>0</zIndex>
</connections>
<connections>
<id>c33233e3-f2cc-3610-0000-000000000000</id>
<parentGroupId>634b599a-8ee7-3ea4-0000-000000000000</parentGroupId>
<backPressureDataSizeThreshold>1 GB</backPressureDataSizeThreshold>
<backPressureObjectThreshold>10000</backPressureObjectThreshold>
<destination>
<groupId>634b599a-8ee7-3ea4-0000-000000000000</groupId>
<id>c2962d55-20ed-322c-0000-000000000000</id>
<type>PROCESSOR</type>
</destination>
<flowFileExpiration>0 sec</flowFileExpiration>
<labelIndex>1</labelIndex>
<name></name>
<selectedRelationships>success</selectedRelationships>
<source>
<groupId>634b599a-8ee7-3ea4-0000-000000000000</groupId>
<id>8f92b5aa-a96b-3b0b-0000-000000000000</id>
<type>PROCESSOR</type>
</source>
<zIndex>0</zIndex>
</connections>
<connections>
<id>6bc0a303-d3b8-338a-0000-000000000000</id>
<parentGroupId>634b599a-8ee7-3ea4-0000-000000000000</parentGroupId>
<backPressureDataSizeThreshold>1 GB</backPressureDataSizeThreshold>
<backPressureObjectThreshold>10000</backPressureObjectThreshold>
<destination>
<groupId>634b599a-8ee7-3ea4-0000-000000000000</groupId>
<id>5f5322ef-ee3f-30aa-0000-000000000000</id>
<type>PROCESSOR</type>
</destination>
<flowFileExpiration>0 sec</flowFileExpiration>
<labelIndex>0</labelIndex>
<name></name>
<selectedRelationships>success</selectedRelationships>
<source>
<groupId>634b599a-8ee7-3ea4-0000-000000000000</groupId>
<id>c2962d55-20ed-322c-0000-000000000000</id>
<type>PROCESSOR</type>
</source>
<zIndex>0</zIndex>
</connections>
<connections>
<id>76a6ff23-55e3-3615-0000-000000000000</id>
<parentGroupId>634b599a-8ee7-3ea4-0000-000000000000</parentGroupId>
<backPressureDataSizeThreshold>1 GB</backPressureDataSizeThreshold>
<backPressureObjectThreshold>10000</backPressureObjectThreshold>
<bends>
<x>726.0</x>
<y>377.0</y>
</bends>
<bends>
<x>726.0</x>
<y>427.0</y>
</bends>
<destination>
<groupId>634b599a-8ee7-3ea4-0000-000000000000</groupId>
<id>c2962d55-20ed-322c-0000-000000000000</id>
<type>PROCESSOR</type>
</destination>
<flowFileExpiration>0 sec</flowFileExpiration>
<labelIndex>1</labelIndex>
<name></name>
<selectedRelationships>retry</selectedRelationships>
<source>
<groupId>634b599a-8ee7-3ea4-0000-000000000000</groupId>
<id>c2962d55-20ed-322c-0000-000000000000</id>
<type>PROCESSOR</type>
</source>
<zIndex>0</zIndex>
</connections>
<controllerServices>
<id>935058ee-a40c-3164-0000-000000000000</id>
<parentGroupId>634b599a-8ee7-3ea4-0000-000000000000</parentGroupId>
<bundle>
<artifact>nifi-record-serialization-services-nar</artifact>
<group>org.apache.nifi</group>
<version>1.2.0</version>
</bundle>
<descriptors>
<entry>
<key>schema-access-strategy</key>
<value>
<name>schema-access-strategy</name>
</value>
</entry>
<entry>
<key>schema-registry</key>
<value>
<identifiesControllerService>org.apache.nifi.schemaregistry.services.SchemaRegistry</identifiesControllerService>
<name>schema-registry</name>
</value>
</entry>
<entry>
<key>schema-name</key>
<value>
<name>schema-name</name>
</value>
</entry>
<entry>
<key>schema-text</key>
<value>
<name>schema-text</name>
</value>
</entry>
<entry>
<key>Date Format</key>
<value>
<name>Date Format</name>
</value>
</entry>
<entry>
<key>Time Format</key>
<value>
<name>Time Format</name>
</value>
</entry>
<entry>
<key>Timestamp Format</key>
<value>
<name>Timestamp Format</name>
</value>
</entry>
<entry>
<key>CSV Format</key>
<value>
<name>CSV Format</name>
</value>
</entry>
<entry>
<key>Value Separator</key>
<value>
<name>Value Separator</name>
</value>
</entry>
<entry>
<key>Skip Header Line</key>
<value>
<name>Skip Header Line</name>
</value>
</entry>
<entry>
<key>Quote Character</key>
<value>
<name>Quote Character</name>
</value>
</entry>
<entry>
<key>Escape Character</key>
<value>
<name>Escape Character</name>
</value>
</entry>
<entry>
<key>Comment Marker</key>
<value>
<name>Comment Marker</name>
</value>
</entry>
<entry>
<key>Null String</key>
<value>
<name>Null String</name>
</value>
</entry>
<entry>
<key>Trim Fields</key>
<value>
<name>Trim Fields</name>
</value>
</entry>
</descriptors>
<name>CSVReader</name>
<persistsState>false</persistsState>
<properties>
<entry>
<key>schema-access-strategy</key>
</entry>
<entry>
<key>schema-registry</key>
</entry>
<entry>
<key>schema-name</key>
</entry>
<entry>
<key>schema-text</key>
</entry>
<entry>
<key>Date Format</key>
</entry>
<entry>
<key>Time Format</key>
</entry>
<entry>
<key>Timestamp Format</key>
</entry>
<entry>
<key>CSV Format</key>
</entry>
<entry>
<key>Value Separator</key>
</entry>
<entry>
<key>Skip Header Line</key>
</entry>
<entry>
<key>Quote Character</key>
</entry>
<entry>
<key>Escape Character</key>
</entry>
<entry>
<key>Comment Marker</key>
</entry>
<entry>
<key>Null String</key>
</entry>
<entry>
<key>Trim Fields</key>
</entry>
</properties>
<state>ENABLED</state>
<type>org.apache.nifi.csv.CSVReader</type>
</controllerServices>
<controllerServices>
<id>04ce5ccf-b89f-36c4-0000-000000000000</id>
<parentGroupId>634b599a-8ee7-3ea4-0000-000000000000</parentGroupId>
<bundle>
<artifact>nifi-dbcp-service-nar</artifact>
<group>org.apache.nifi</group>
<version>1.2.0</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://192.168.99.100:3306/nifi_test</value>
</entry>
<entry>
<key>Database Driver Class Name</key>
<value>com.mysql.jdbc.Driver</value>
</entry>
<entry>
<key>database-driver-locations</key>
<value>/Users/koji/Downloads/mysql-connector-java-5.0.8/mysql-connector-java-5.0.8-bin.jar</value>
</entry>
<entry>
<key>Database User</key>
<value>root</value>
</entry>
<entry>
<key>Password</key>
</entry>
<entry>
<key>Max Wait Time</key>
</entry>
<entry>
<key>Max Total Connections</key>
</entry>
<entry>
<key>Validation-query</key>
</entry>
</properties>
<state>ENABLED</state>
<type>org.apache.nifi.dbcp.DBCPConnectionPool</type>
</controllerServices>
<processors>
<id>8f92b5aa-a96b-3b0b-0000-000000000000</id>
<parentGroupId>634b599a-8ee7-3ea4-0000-000000000000</parentGroupId>
<position>
<x>266.0</x>
<y>130.0</y>
</position>
<bundle>
<artifact>nifi-standard-nar</artifact>
<group>org.apache.nifi</group>
<version>1.2.0</version>
</bundle>
<config>
<bulletinLevel>WARN</bulletinLevel>
<comments></comments>
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount>
<descriptors>
<entry>
<key>File Size</key>
<value>
<name>File Size</name>
</value>
</entry>
<entry>
<key>Batch Size</key>
<value>
<name>Batch Size</name>
</value>
</entry>
<entry>
<key>Data Format</key>
<value>
<name>Data Format</name>
</value>
</entry>
<entry>
<key>Unique FlowFiles</key>
<value>
<name>Unique FlowFiles</name>
</value>
</entry>
<entry>
<key>generate-ff-custom-text</key>
<value>
<name>generate-ff-custom-text</name>
</value>
</entry>
</descriptors>
<executionNode>ALL</executionNode>
<lossTolerant>false</lossTolerant>
<penaltyDuration>30 sec</penaltyDuration>
<properties>
<entry>
<key>File Size</key>
<value>0B</value>
</entry>
<entry>
<key>Batch Size</key>
<value>1</value>
</entry>
<entry>
<key>Data Format</key>
<value>Text</value>
</entry>
<entry>
<key>Unique FlowFiles</key>
<value>false</value>
</entry>
<entry>
<key>generate-ff-custom-text</key>
<value>a, b, c
1, two, 3
</value>
</entry>
</properties>
<runDurationMillis>0</runDurationMillis>
<schedulingPeriod>1d</schedulingPeriod>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<yieldDuration>1 sec</yieldDuration>
</config>
<name>GenerateFlowFile</name>
<relationships>
<autoTerminate>false</autoTerminate>
<name>success</name>
</relationships>
<style></style>
<type>org.apache.nifi.processors.standard.GenerateFlowFile</type>
</processors>
<processors>
<id>c2962d55-20ed-322c-0000-000000000000</id>
<parentGroupId>634b599a-8ee7-3ea4-0000-000000000000</parentGroupId>
<position>
<x>271.0</x>
<y>337.0</y>
</position>
<bundle>
<artifact>nifi-standard-nar</artifact>
<group>org.apache.nifi</group>
<version>1.2.0</version>
</bundle>
<config>
<bulletinLevel>WARN</bulletinLevel>
<comments></comments>
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount>
<descriptors>
<entry>
<key>put-db-record-record-reader</key>
<value>
<identifiesControllerService>org.apache.nifi.serialization.RecordReaderFactory</identifiesControllerService>
<name>put-db-record-record-reader</name>
</value>
</entry>
<entry>
<key>put-db-record-statement-type</key>
<value>
<name>put-db-record-statement-type</name>
</value>
</entry>
<entry>
<key>put-db-record-dcbp-service</key>
<value>
<identifiesControllerService>org.apache.nifi.dbcp.DBCPService</identifiesControllerService>
<name>put-db-record-dcbp-service</name>
</value>
</entry>
<entry>
<key>put-db-record-catalog-name</key>
<value>
<name>put-db-record-catalog-name</name>
</value>
</entry>
<entry>
<key>put-db-record-schema-name</key>
<value>
<name>put-db-record-schema-name</name>
</value>
</entry>
<entry>
<key>put-db-record-table-name</key>
<value>
<name>put-db-record-table-name</name>
</value>
</entry>
<entry>
<key>put-db-record-translate-field-names</key>
<value>
<name>put-db-record-translate-field-names</name>
</value>
</entry>
<entry>
<key>put-db-record-unmatched-field-behavior</key>
<value>
<name>put-db-record-unmatched-field-behavior</name>
</value>
</entry>
<entry>
<key>put-db-record-unmatched-column-behavior</key>
<value>
<name>put-db-record-unmatched-column-behavior</name>
</value>
</entry>
<entry>
<key>put-db-record-update-keys</key>
<value>
<name>put-db-record-update-keys</name>
</value>
</entry>
<entry>
<key>put-db-record-field-containing-sql</key>
<value>
<name>put-db-record-field-containing-sql</name>
</value>
</entry>
<entry>
<key>put-db-record-quoted-identifiers</key>
<value>
<name>put-db-record-quoted-identifiers</name>
</value>
</entry>
<entry>
<key>put-db-record-quoted-table-identifiers</key>
<value>
<name>put-db-record-quoted-table-identifiers</name>
</value>
</entry>
<entry>
<key>put-db-record-query-timeout</key>
<value>
<name>put-db-record-query-timeout</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>put-db-record-record-reader</key>
<value>935058ee-a40c-3164-0000-000000000000</value>
</entry>
<entry>
<key>put-db-record-statement-type</key>
<value>INSERT</value>
</entry>
<entry>
<key>put-db-record-dcbp-service</key>
<value>04ce5ccf-b89f-36c4-0000-000000000000</value>
</entry>
<entry>
<key>put-db-record-catalog-name</key>
</entry>
<entry>
<key>put-db-record-schema-name</key>
</entry>
<entry>
<key>put-db-record-table-name</key>
<value>csvs</value>
</entry>
<entry>
<key>put-db-record-translate-field-names</key>
<value>true</value>
</entry>
<entry>
<key>put-db-record-unmatched-field-behavior</key>
<value>Ignore Unmatched Fields</value>
</entry>
<entry>
<key>put-db-record-unmatched-column-behavior</key>
<value>Fail on Unmatched Columns</value>
</entry>
<entry>
<key>put-db-record-update-keys</key>
</entry>
<entry>
<key>put-db-record-field-containing-sql</key>
</entry>
<entry>
<key>put-db-record-quoted-identifiers</key>
<value>false</value>
</entry>
<entry>
<key>put-db-record-quoted-table-identifiers</key>
<value>false</value>
</entry>
<entry>
<key>put-db-record-query-timeout</key>
<value>0 seconds</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>PutDatabaseRecord</name>
<relationships>
<autoTerminate>false</autoTerminate>
<name>failure</name>
</relationships>
<relationships>
<autoTerminate>false</autoTerminate>
<name>retry</name>
</relationships>
<relationships>
<autoTerminate>false</autoTerminate>
<name>success</name>
</relationships>
<style></style>
<type>org.apache.nifi.processors.standard.PutDatabaseRecord</type>
</processors>
<processors>
<id>5f5322ef-ee3f-30aa-0000-000000000000</id>
<parentGroupId>634b599a-8ee7-3ea4-0000-000000000000</parentGroupId>
<position>
<x>265.0</x>
<y>528.0</y>
</position>
<bundle>
<artifact>nifi-standard-nar</artifact>
<group>org.apache.nifi</group>
<version>1.2.0</version>
</bundle>
<config>
<bulletinLevel>WARN</bulletinLevel>
<comments></comments>
<concurrentlySchedulableTaskCount>1</concurrentlySchedulableTaskCount>
<descriptors>
<entry>
<key>Log Level</key>
<value>
<name>Log Level</name>
</value>
</entry>
<entry>
<key>Log Payload</key>
<value>
<name>Log Payload</name>
</value>
</entry>
<entry>
<key>Attributes to Log</key>
<value>
<name>Attributes to Log</name>
</value>
</entry>
<entry>
<key>Attributes to Ignore</key>
<value>
<name>Attributes to Ignore</name>
</value>
</entry>
<entry>
<key>Log prefix</key>
<value>
<name>Log prefix</name>
</value>
</entry>
</descriptors>
<executionNode>ALL</executionNode>
<lossTolerant>false</lossTolerant>
<penaltyDuration>30 sec</penaltyDuration>
<properties>
<entry>
<key>Log Level</key>
<value>info</value>
</entry>
<entry>
<key>Log Payload</key>
<value>false</value>
</entry>
<entry>
<key>Attributes to Log</key>
</entry>
<entry>
<key>Attributes to Ignore</key>
</entry>
<entry>
<key>Log prefix</key>
</entry>
</properties>
<runDurationMillis>0</runDurationMillis>
<schedulingPeriod>0 sec</schedulingPeriod>
<schedulingStrategy>TIMER_DRIVEN</schedulingStrategy>
<yieldDuration>1 sec</yieldDuration>
</config>
<name>LogAttribute</name>
<relationships>
<autoTerminate>false</autoTerminate>
<name>success</name>
</relationships>
<style></style>
<type>org.apache.nifi.processors.standard.LogAttribute</type>
</processors>
</contents>
<name>Example CSV to Database</name>
</processGroups>
</snippet>
<timestamp>05/18/2017 13:38:25 JST</timestamp>
</template>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment