jackjlli commented on a change in pull request #6750:
URL: https://github.com/apache/incubator-pinot/pull/6750#discussion_r610809638
##########
File path:
pinot-tools/src/main/resources/examples/batch/dimBaseballTeams/rawdata/dimBaseballTeams_data.csv
##########
@@ -0,0 +1,52 @@
+teamID,teamName
Review comment:
Missing open source header?
##########
File path:
pinot-tools/src/main/resources/examples/batch/dimBaseballTeams/ingestionJobSpec.yaml
##########
@@ -0,0 +1,138 @@
+#
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license agreements. See the NOTICE file
+# distributed with this work for additional information
+# regarding copyright ownership. The ASF licenses this file
+# to you under the Apache License, Version 2.0 (the
+# "License"); you may not use this file except in compliance
+# with the License. You may obtain a copy of the License at
+#
+# http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing,
+# software distributed under the License is distributed on an
+# "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
+# KIND, either express or implied. See the License for the
+# specific language governing permissions and limitations
+# under the License.
+#
+
+# executionFrameworkSpec: Defines ingestion jobs to be running.
+executionFrameworkSpec:
+
+ # name: execution framework name
+ name: 'standalone'
+
+ # segmentGenerationJobRunnerClassName: class name implements
org.apache.pinot.spi.batch.ingestion.runner.SegmentGenerationJobRunner
interface.
+ segmentGenerationJobRunnerClassName:
'org.apache.pinot.plugin.ingestion.batch.standalone.SegmentGenerationJobRunner'
+
+ # segmentTarPushJobRunnerClassName: class name implements
org.apache.pinot.spi.batch.ingestion.runner.SegmentTarPushJobRunner interface.
+ segmentTarPushJobRunnerClassName:
'org.apache.pinot.plugin.ingestion.batch.standalone.SegmentTarPushJobRunner'
+
+ # segmentUriPushJobRunnerClassName: class name implements
org.apache.pinot.spi.batch.ingestion.runner.SegmentUriPushJobRunner interface.
+ segmentUriPushJobRunnerClassName:
'org.apache.pinot.plugin.ingestion.batch.standalone.SegmentUriPushJobRunner'
+
+# jobType: Pinot ingestion job type.
+# Supported job types are:
+# 'SegmentCreation'
+# 'SegmentTarPush'
+# 'SegmentUriPush'
+# 'SegmentCreationAndTarPush'
+# 'SegmentCreationAndUriPush'
+jobType: SegmentCreationAndTarPush
+
+# inputDirURI: Root directory of input data, expected to have scheme
configured in PinotFS.
+inputDirURI: 'examples/batch/dimBaseballTeams/rawdata'
+
+# includeFileNamePattern: include file name pattern, supported glob pattern.
+# Sample usage:
+# 'glob:*.avro' will include all avro files just under the inputDirURI, not
sub directories;
+# 'glob:**/*.avro' will include all the avro files under inputDirURI
recursively.
+includeFileNamePattern: 'glob:**/*.csv'
+
+# excludeFileNamePattern: exclude file name pattern, supported glob pattern.
+# Sample usage:
+# 'glob:*.avro' will exclude all avro files just under the inputDirURI, not
sub directories;
+# 'glob:**/*.avro' will exclude all the avro files under inputDirURI
recursively.
+# _excludeFileNamePattern: ''
+
+# outputDirURI: Root directory of output segments, expected to have scheme
configured in PinotFS.
+outputDirURI: 'examples/batch/dimBaseballTeams/segments'
+
+# overwriteOutput: Overwrite output segments if existed.
+overwriteOutput: true
+
+# pinotFSSpecs: defines all related Pinot file systems.
+pinotFSSpecs:
+
+ - # scheme: used to identify a PinotFS.
+ # E.g. local, hdfs, dbfs, etc
+ scheme: file
+
+ # className: Class name used to create the PinotFS instance.
+ # E.g.
+ # org.apache.pinot.spi.filesystem.LocalPinotFS is used for local
filesystem
+ # org.apache.pinot.plugin.filesystem.AzurePinotFS is used for Azure Data
Lake
+ # org.apache.pinot.plugin.filesystem.HadoopPinotFS is used for HDFS
+ className: org.apache.pinot.spi.filesystem.LocalPinotFS
+
+# recordReaderSpec: defines all record reader
+recordReaderSpec:
+
+ # dataFormat: Record data format, e.g. 'avro', 'parquet', 'orc', 'csv',
'json', 'thrift' etc.
+ dataFormat: 'csv'
Review comment:
Isn't it a bit redundant to specify the data format there since the
related RecordReader has already been set down below?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
