repositories:
- namespace: CHANGEME
  repository: csv
  # Catalog-specific metadata for the repository. Optional.
  metadata:
    readme:
      text: Readme
    description: Description of the repository
    topics:
    - sample_topic
  # Data source settings for the repository. Optional.
  external:
    # Name of the credential that the plugin uses. This can also be a credential_id if the
    # credential is already registered on Splitgraph.
    credential: csv
    plugin: csv
    # Plugin-specific parameters matching the plugin's parameters schema
    params:
      connection:  # Connection. Choose one of:
      - connection_type: http  # REQUIRED. Connection type. Constant
        url: '' # REQUIRED. URL. HTTP URL to the CSV file
      - connection_type: s3  # REQUIRED. Connection type. Constant
        s3_endpoint: '' # REQUIRED. S3 endpoint. S3 endpoint (including port if required)
        s3_bucket: '' # REQUIRED. Bucket name. Bucket the object is in
        s3_region: '' # S3 region. Region of the S3 bucket
        s3_secure: false # Secure. Whether to use HTTPS for S3 access
        s3_object: '' # S3 Object name. Limit the import to a single object
        s3_object_prefix: '' # S3 Object prefix. Prefix for object in S3 bucket
      autodetect_header: true # Autodetect header. Detect whether the CSV file has a header automatically
      autodetect_dialect: true # Autodetect dialect. Detect the CSV file's dialect (separator, quoting characters etc) automatically
      autodetect_encoding: true # Autodetect encoding. Detect the CSV file's encoding automatically
      autodetect_sample_size: 65536 # Sample size. Sample size, in bytes, for encoding/dialect/header detection
      schema_inference_rows: 100000 # Schema inference rows. Number of rows to use for schema inference
      encoding: utf-8 # Encoding. Encoding of the CSV file
      ignore_decode_errors: false # Ignore decoding errors. Ignore errors when decoding the file
      header: true # First line of the CSV file is its header
      delimiter: ',' # Delimiter. Character used to separate fields in the file
      quotechar: '"' # Quote character. Character used to quote fields
    tables:
      sample_table:
        # Plugin-specific table parameters matching the plugin's schema
        options:
          cursor_fields: []  # Replication cursor. Column(s) to use as a replication cursor. This must be always increasing in the source table and is used to track which rows should be replicated.
          url: '' # URL. HTTP URL to the CSV file
          s3_object: '' # S3 object. S3 object of the CSV file
          autodetect_header: true # Autodetect header. Detect whether the CSV file has a header automatically
          autodetect_dialect: true # Autodetect dialect. Detect the CSV file's dialect (separator, quoting characters etc) automatically
          autodetect_encoding: true # Autodetect encoding. Detect the CSV file's encoding automatically
          autodetect_sample_size: 65536 # Sample size. Sample size, in bytes, for encoding/dialect/header detection
          schema_inference_rows: 100000 # Schema inference rows. Number of rows to use for schema inference
          encoding: utf-8 # Encoding. Encoding of the CSV file
          ignore_decode_errors: false # Ignore decoding errors. Ignore errors when decoding the file
          header: true # First line of the CSV file is its header
          delimiter: ',' # Delimiter. Character used to separate fields in the file
          quotechar: '"' # Quote character. Character used to quote fields
        # Schema of the table, a list of objects with `name` and `type`. If set to `[]`, will infer. 
        schema: []
    # Whether live querying is enabled for the plugin (creates a "live" tag in the
    # repository proxying to the data source). The plugin must support live querying.
    is_live: true
    # Ingestion schedule settings. Disable this if you're using GitHub Actions or other methods
    # to trigger ingestion.
    schedule:
credentials:
  csv:  # This is the name of this credential that "external" sections can reference.
    plugin: csv
    # Credential-specific data matching the plugin's credential schema
    data:
      s3_access_key: ''  # AWS Access Key
      s3_secret_key: '' # AWS Secret Access Key