sdks/python/apache_beam/yaml/tests/iceberg_add_files_batch.yaml

#
# 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.
#

fixtures:
  - name: TEMP_DIR
    type: "tempfile.TemporaryDirectory"


pipelines:
  # Pipeline 1: Write dummy Parquet files
  - pipeline:
      type: chain
      transforms:
        - type: Create
          config:
            elements:
              - {label: "11a", rank: 0, bool: true}
              - {label: "37a", rank: 1, bool: false}
              - {label: "389a", rank: 2, bool: false}
              - {label: "3821b", rank: 3, bool: true}
              - {label: "990c", rank: 4, bool: true}
              - {label: "1024d", rank: 5, bool: false}
        - type: WriteToParquet
          config:
            path: "{TEMP_DIR}/data/data"
            file_name_suffix: ".parquet"
            num_shards: 6

  # Pipeline 2: Register our generated files in our Iceberg table
  - pipeline:
      type: chain
      transforms:
        - type: ReadMatchFiles
          config:
            file_pattern: "{TEMP_DIR}/data/data*.parquet"
        - type: MapToFields
          config:
            language: python
            fields:
              path:
                callable: "lambda row: row.path"
                output_type: string
        - type: IcebergAddFiles
          config:
            table: "default.table"
            catalog_properties:
              type: "hadoop"
              warehouse: "{TEMP_DIR}/dir"

    providers:
      - type: python
        config: { }
        transforms:
          ReadMatchFiles: 'apache_beam.io.fileio.MatchFiles'

  # Pipeline 3: Read from Iceberg and verify the contents
  - pipeline:
      type: chain
      transforms:
        - type: ReadFromIceberg
          config:
            table: "default.table"
            catalog_properties:
              type: "hadoop"
              warehouse: "{TEMP_DIR}/dir"
        - type: AssertEqual
          config:
            elements:
              - {label: "11a", rank: 0, bool: true}
              - {label: "37a", rank: 1, bool: false}
              - {label: "389a", rank: 2, bool: false}
              - {label: "3821b", rank: 3, bool: true}
              - {label: "990c", rank: 4, bool: true}
              - {label: "1024d", rank: 5, bool: false}