Contents

in:
  type: file
  path_prefix: ./example/data.tsv
  parser:
    type: csv
    delimiter: "\t"
    skip_header_lines: 0
    null_string: ""
    columns:
      - { name: id, type: long }
      - { name: description, type: string }
      - { name: name, type: string }
      - { name: t, type: timestamp, format: "%Y-%m-%d %H:%M:%S %z"}
      - { name: payload, type: json}
    stop_on_invalid_record: true

out:
  type: s3_parquet
  bucket: dev-baikal-workspace
  path_prefix: path/to/my-obj-2.
  file_ext: snappy.parquet
  compression_codec: snappy
  default_timezone: Asia/Tokyo
  canned_acl: bucket-owner-full-control
  column_options:
    id:
      logical_type: "int64"
    payload:
      logical_type: "json"
  type_options:
    timestamp:
      logical_type: "timestamp-millis"
  catalog:
    database: example_db
    table: example_tbl

Version data entries

1 entries across 1 versions & 1 rubygems

Version	Path
embulk-output-s3_parquet-0.1.0	example/with_catalog.yml