{
  "name": "Cloud Bigtable to Parquet in GCS filtered by regex",
  "description": "A pipeline which reads in Cloud Bigtable table filtered by regex and writes it to Google Cloud Storage in Parquet format.",
  "parameters": [
    {
      "name": "bigtableProjectId",
      "label": "Project ID",
      "helpText": "The ID of the Google Cloud project of the Cloud Bigtable instance that you want to read data from",
      "regexes": [
        "[a-z0-9\\-\\.\\:]+"
      ],
      "paramType": "TEXT"
    },
    {
      "name": "bigtableInstanceId",
      "label": "Instance ID",
      "helpText": "The ID of the Cloud Bigtable instance that contains the table",
      "regexes": [
        "[a-z][a-z0-9\\-]+[a-z0-9]"
      ],
      "paramType": "TEXT"
    },
    {
      "name": "bigtableTableId",
      "label": "Table ID",
      "helpText": "The ID of the Cloud Bigtable table to export",
      "regexes": [
        "[_a-zA-Z0-9][-_.a-zA-Z0-9]*"
      ],
      "paramType": "TEXT"
    },
    {
      "name": "outputDirectory",
      "label": "Output directory",
      "helpText": "GCS path where data should be written. Ex: gs://your-bucket/your-path",
      "regexes": [
        "^gs:\\/\\/[^\\n\\r]+$"
      ],
      "paramType": "GCS_WRITE_FOLDER"
    },
    {
      "name": "filenamePrefix",
      "label": "Parquet file prefix",
      "helpText": "The prefix of the Parquet file name. For example, \"table1-\"",
      "paramType": "TEXT"
    },
    {
      "name": "numShards",
      "label": "Number of file shards",
      "helpText": "The number of parquet files",
      "regexes": [
        "^[1-9][0-9]*$"
      ],
      "paramType": "TEXT"
    },
    {
      "name": "regex",
      "label": "Regular expression filter",
      "helpText": "Regex to filter row keys, e.g. .*(201[0-9]-[01][0-9]-[0-3][0-9]).*",
      "paramType": "TEXT"
    }
  ]
}