#
# 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: 'spark'

  # segmentGenerationJobRunnerClassName: class name implements org.apache.pinot.spi.batch.ingestion.runner.SegmentGenerationJobRunner interface.
  segmentGenerationJobRunnerClassName: 'org.apache.pinot.plugin.ingestion.batch.spark.SparkSegmentGenerationJobRunner'

  # segmentTarPushJobRunnerClassName: class name implements org.apache.pinot.spi.batch.ingestion.runner.SegmentTarPushJobRunner interface.
  segmentTarPushJobRunnerClassName: 'org.apache.pinot.plugin.ingestion.batch.spark.SparkSegmentTarPushJobRunner'

  # segmentUriPushJobRunnerClassName: class name implements org.apache.pinot.spi.batch.ingestion.runner.SegmentUriPushJobRunner interface.
  segmentUriPushJobRunnerClassName: 'org.apache.pinot.plugin.ingestion.batch.spark.SparkSegmentUriPushJobRunner'

  # extraConfigs: extra configs for execution framework.
  extraConfigs:

    stagingDir: gs://{bucket_name}/tmp

# jobType: Pinot ingestion job type.
# Supported job types are:
#   'SegmentCreation'
#   'SegmentTarPush'
#   'SegmentUriPush'
#   'SegmentCreationAndTarPush'
#   'SegmentCreationAndUriPush'
jobType: SegmentCreationAndUriPush

# inputDirURI: Root directory of input data, expected to have scheme configured in PinotFS.
inputDirURI: 'gs://{bucket_name}/rule_logs'

# 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:**/*.avro'

# 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: 'gs://{bucket_name}/data'

# overwriteOutput: Overwrite output segments if existed.
overwriteOutput: true

pinotFSSpecs:

  - # scheme: used to identify a PinotFS.
    # E.g. local, hdfs, dbfs, etc
    scheme: gs
    className: org.apache.pinot.plugin.filesystem.GcsPinotFS
    configs:
      'projectId': 'xxxx'
      'gcpKey' : 'xxx.json'

# recordReaderSpec: defines all record reader
recordReaderSpec:

  # dataFormat: Record data format, e.g. 'avro', 'parquet', 'orc', 'csv', 'json', 'thrift' etc.
  dataFormat: 'avro'
  #   org.apache.pinot.plugin.inputformat.avro.AvroRecordReader
  #   org.apache.pinot.plugin.inputformat.csv.CSVRecordReader
  #   org.apache.pinot.plugin.inputformat.parquet.ParquetRecordReader
  #   org.apache.pinot.plugin.inputformat.json.JSONRecordReader
  #   org.apache.pinot.plugin.inputformat.orc.ORCRecordReader
  #   org.apache.pinot.plugin.inputformat.thrift.ThriftRecordReader
  className: 'org.apache.pinot.plugin.inputformat.avro.AvroRecordReader'

# tableSpec: defines table name and where to fetch corresponding table config and table schema.
tableSpec:

  # tableName: Table name
  tableName: 'RuleLogsUAT'
  # schemaURI: defines where to read the table schema, supports PinotFS or HTTP.a
  schemaURI: '<http://localhost:9000/tables/RuleLogsUAT/schema>'
  # Note that the API to read Pinot table config directly from pinot controller contains a JSON wrapper.
  # The real table config is the object under the field 'OFFLINE'.
  tableConfigURI: '<http://localhost:9000/tables/RuleLogsUAT>'

# segmentNameGeneratorSpec: defines how to init a SegmentNameGenerator.
segmentNameGeneratorSpec:

  # type: Current supported type is 'simple' and 'normalizedDate'.
  type: normalizedDate

  # configs: Configs to init SegmentNameGenerator.
  configs:
    segment.name.prefix: 'rule_logs_uat'
    exclude.sequence.id: true

# pinotClusterSpecs: defines the Pinot Cluster Access Point.
pinotClusterSpecs:
  - # controllerURI: used to fetch table/schema information and data push.
    controllerURI: '<http://localhost:9000>'

# pushJobSpec: defines segment push job related configuration.
pushJobSpec:

  # pushParallelism: push job parallelism, default is 1.
  pushParallelism: 2

  # pushAttempts: number of attempts for push job, default is 1, which means no retry.
  pushAttempts: 2

  # pushRetryIntervalMillis: retry wait Ms, default to 1 second.
  pushRetryIntervalMillis: 1000

URI src = new URI(srcUri.getScheme(), srcUri.getHost(), directoryEntry, null);
String relativeSrcPath = srcPath.relativize(Paths.get(directoryEntry)).toString();

directoryEntry

directoryEntry

URI srcUri = new URI("<gs://bucket_name/tmp/>");
String dest = "<gs://bucket_name/tmp/file1.xxx>";

URI src = new URI(srcUri.getScheme(), srcUri.getHost(), dest, null);
Output is => gs:<gs://bucket_name/tmp/file1.xxx>

srcUri.getHost()

/