_tickit_sources.yml

version: 2

sources:
  - name: tickit_external
    description: Sales activity for the fictional TICKIT web site, where users buy and sell tickets online for sporting events, shows, and concerts.
    database: demo
    schema: tickit_external
    loader: s3
    tables:
      - name: category
        description: dimension table - TICKIT categories
        external:
          location: "s3://<your_s3_bucket_name>/raw_tickit_data/category/"
          row_format: >
            serde 'org.apache.hadoop.hive.serde2.OpenCSVSerde'
            with serdeproperties (
                'separatorChar'='|'
            )
          table_properties: "('skip.header.line.count'='1')"
        columns:
          - name: catid
            data_type: int
            description: primary key
            tests:
              - unique
              - not_null
          - name: catgroup
            data_type: varchar(20)
          - name: catname
            data_type: varchar(20)
          - name: catdesc
            data_type: varchar(50)