data-pipelines.openapi.yaml

openapi: 3.0.2
x-readme-deploy-id: data-pipelines-api
info:
  title: Data Pipelines API
  description: Create and manage a continious pipeline with an external warehouse.
  license:
    name: MIT
    url: https://opensource.org/licenses/MIT
  version: 1.0.0
  contact:
    url: https://mixpanel.com/get-support
servers:
  - $ref: ./common/export-api.yaml#/server
security:
  - ServiceAccount: []
  - ProjectSecret: []
tags:
  - name: Create Pipelines
    description: Operations to add schemas to a project
  - name: Delete Pipelines
    description: Remove a pipeline from a project
  - name: Edit Pipelines
    description: Edit the params for a pipeline from a project
  - name: Pause Pipelines
    description: Pause a running pipeline
  - name: Resume Pipelines
    description: Resume a paused pipeline
  - name: Retrieve Pipelines
    description: Get information about Pipelines
paths:
  /nessie/pipeline/jobs:
    get:
      operationId: list-warehouse-pipeline-jobs
      tags:
        - Retrieve Pipelines
      summary: List Pipelines
      description: >-
        This API endpoint returns the list of all the pipelines scheduled for a
        project.
      parameters:
        - $ref: ./common/parameters.yaml#/query/projectId
      responses:
        '200':
          description: Success
          content:
            application/json:
              examples:
                example:
                  value:
                    '9876543210':
                      - name: events-daily-bigquery-monoschema
                        Dispatcher: backfill
                        last_dispatched: '2019-02-01 12:00:00 US/Pacific'
                        frequency: hourly
                        sync_enabled: 'true'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
  /nessie/pipeline/create:
    post:
      tags:
        - Create Pipelines
      operationId: create-warehouse-pipeline
      summary: Create Pipeline
      description: ''
      requestBody:
        required: true
        content:
          application/x-www-form-urlencoded:
            schema:
              oneOf:
                - $ref: '#/components/schemas/RawGCSPipeline'
                - $ref: '#/components/schemas/RawAmazonS3Pipeline'
                - $ref: '#/components/schemas/RawAzurePipeline'
                - $ref: '#/components/schemas/SchematizedBigQueryPipeline'
                - $ref: '#/components/schemas/SchematizedSnowflakePipeline'
                - $ref: '#/components/schemas/SchematizedAWSPipeline'
                - $ref: '#/components/schemas/SchematizedAzurePipeline'
                - $ref: '#/components/schemas/SchematizedGCSPipeline'
              discriminator:
                propertyName: type
                mapping:
                  gcs-raw: '#/components/schemas/RawGCSPipeline'
                  s3-raw: '#/components/schemas/RawAmazonS3Pipeline'
                  azure-raw: '#/components/schemas/RawAzurePipeline'
                  bigquery: '#/components/schemas/SchematizedBigQueryPipeline'
                  snowflake: '#/components/schemas/SchematizedSnowflakePipeline'
                  aws: '#/components/schemas/SchematizedAWSPipeline'
                  azure-blob: '#/components/schemas/SchematizedAzurePipeline'
                  gcs-schema: '#/components/schemas/SchematizedGCSPipeline'
      responses:
        '200':
          description: >-
            Returns the name of the pipeline created. Use the name of the
            pipeline to check the status of or cancel the pipeline.
          content:
            application/json:
              examples:
                example:
                  value:
                    pipeline_names:
                      - trial-events-daily-bigquery-monoschema
                      - trial-people-daily-bigquery-monoschema
                    bigquery_dataset_name: >-
                      https://bigquery.cloud.google.com/dataset/mixpanel-prod-1:sample_dataset_name
        '400':
          $ref: '#/components/responses/BadRequest'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
  /nessie/pipeline/edit:
    post:
      tags:
        - Edit Pipelines
      operationId: edit-warehouse-pipeline
      summary: Edit Pipeline
      description: >
        This request edit the params for an export pipeline.
      requestBody:
        required: true
        content:
          application/x-www-form-urlencoded:
            schema:
              oneOf:
                - title: Raw GCS Pipeline
                  $ref: '#/components/schemas/RawEditParams'
                - title: Raw Amazon S3 Pipeline
                  $ref: '#/components/schemas/RawEditParams'
                - title: Raw Azure Pipeline
                  $ref: '#/components/schemas/RawAzureEditParams'
                - title: Schematized BigQuery Pipeline
                  $ref: '#/components/schemas/BigQueryEditParams'
                - title: Schematized Snowflake Pipeline
                  $ref: '#/components/schemas/SchematizedEditParams'
                - title: Schematized AWS Pipeline
                  $ref: '#/components/schemas/SchematizedAWSEditParams'
                - title: Schematized Azure Pipeline
                  $ref: '#/components/schemas/SchematizedAzureEditParams'
                - title: Schematized GCS Pipeline
                  $ref: '#/components/schemas/SchematizedEditParams'
      responses:
        '200':
          description: Success
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
  /nessie/pipeline/cancel:
    post:
      tags:
        - Delete Pipelines
      summary: Delete Pipeline
      operationId: cancel-warehouse-pipeline
      description: >-
        For a given pipeline name, this request deletes the pipeline and stops
        any future jobs to be scheduled for the pipeline. 
        Deleting the pipeline will result in the loss of all its historical data. If you wish to retain the history, it is recommended to pause the pipeline instead.
      requestBody:
        required: true
        content:
          application/x-www-form-urlencoded:
            schema:
              type: object
              properties:
                name:
                  type: string
                  description: The name that uniquely identifies the pipeline.
                project_id:
                  $ref: '#/components/schemas/ProjectId'
              required:
                - name
      responses:
        '200':
          description: Success
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
  /nessie/pipeline/pause:
    post:
      tags:
        - Pause Pipelines
      summary: Pause Pipeline
      operationId: pause-warehouse-pipeline
      description: >-
        For a given pipeline name, this request pauses the pipeline which stops the ongoing jobs and
        prevents any future jobs to be scheduled for the pipeline
      requestBody:
        required: true
        content:
          application/x-www-form-urlencoded:
            schema:
              type: object
              properties:
                name:
                  type: string
                  description: The name that uniquely identifies the pipeline.
                project_id:
                  $ref: '#/components/schemas/ProjectId'
              required:
                - name
      responses:
        '200':
          description: Success
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
  /nessie/pipeline/resume:
    post:
      tags:
        - Resume Pipelines
      summary: Resume Pipeline
      operationId: resume-warehouse-pipeline
      description: >-
        For a given pipeline name, this request resumes the pipeline if it's paused
      requestBody:
        required: true
        content:
          application/x-www-form-urlencoded:
            schema:
              type: object
              properties:
                name:
                  type: string
                  description: The name that uniquely identifies the pipeline.
                project_id:
                  $ref: '#/components/schemas/ProjectId'
              required:
                - name
      responses:
        '200':
          description: Success
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
        '404':
          $ref: '#/components/responses/NotFound'
  /nessie/pipeline/status:
    get:
      operationId: get-warehouse-pipeline-status
      summary: Get Pipeline
      tags:
        - Retrieve Pipelines
      description: ''
      parameters:
        - $ref: ./common/parameters.yaml#/query/projectId
        - in: query
          name: name
          schema:
            type: string
          description: The name that uniquely identifies the pipeline.
          required: true
        - in: query
          name: summary
          schema:
            type: string
          description: 'Default: `false`. Only lists task count by status and no details.'
        - in: query
          name: status
          schema:
            type: array
            items:
              type: string
          description: |
            Filters the tasks by the given status. Valid options for status are `pending`, `running`, `retried`, `failed`, `canceled`, and `timed_out`.
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/PipelineStatusResponse'
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
  /nessie/pipeline/timeline:
    get:
      operationId: list-warehouse-pipeline-sync-dates
      tags:
        - Retrieve Pipelines
      summary: List Pipeline Logs
      description: This endpoint returns the timestamps of all syncs grouped by date.
      parameters:
        - $ref: ./common/parameters.yaml#/query/projectId
        - in: query
          name: name
          schema:
            type: string
          description: The name that uniquely identifies the pipeline.
      responses:
        '200':
          description: Success
          content:
            application/json:
              examples:
                example:
                  value:
                    day_syncs:
                      - date: '2019-08-19'
                        sync_times:
                          - '2019-08-19 14:27:46.044605 -0700 PDT'
                        status: synced
                      - date: '2019-08-20'
                        sync_times:
                          - ' 2019-08-20 14:33:09.315098 -0700 PDT'
                        status: synced
        '401':
          $ref: '#/components/responses/Unauthorized'
        '403':
          $ref: '#/components/responses/Forbidden'
components:
  securitySchemes:
    $ref: ./common/securitySchemes.yaml
  schemas:
    PipelineType:
      type: string
      enum:
        - gcs-raw
        - s3-raw
        - azure-raw
        - bigquery
        - snowflake
        - aws
        - azure-blob
        - gcs-schema
    ProjectId:
      type: number
      description: Your project id (must be specified when using service account based authentication)
    RawGCSPipeline:
      title: Raw GCS Pipeline
      type: object
      properties:
        project_id:
          $ref: '#/components/schemas/ProjectId'
        type:
          type: string
          default: gcs-raw
        trial:
          type: boolean
          default: false
          description: >
            **Default**: `false`


            A trial pipeline will be created if value is true.


            The trial exports all of your events and user data for thirty
            calendar days, starting from one day before the API call was made. A
            trial pipeline has default values for the following parameters:


            **data_source**: `events`

            **from_date**: `<defaults to previous day>`

            **to_date**: `<no value>`

            **frequency**: `daily`

            **events**: `<no value>`
        data_source:
          type: string
          enum:
            - events
          default: events
          description: >
            **Default**: `events`


            **data_source** In this type of pipeline it can only be `events` which exports
            Mixpanel event data.
        from_date:
          type: string
          format: date
          description: >
            The starting date of the export window. It is formatted as
            `YYYY-MM-DD` and cannot be more than six months in the past.


            If **trial** is set to `true` this will default to the previous day;
            otherwise, it is a required parameter.
        to_date:
          type: string
          format: date
          description: >-
            The ending date of the export window. It is formatted as
            `YYYY-MM-DD`. The export will continue indefinitely if **to_date**
            is empty.
        frequency:
          type: string
          default: daily
          enum:
           - daily
           - hourly
          description: >
            **Default**: `daily`


            **frequency** can be either `hourly` or `daily`. `hourly` exports
            the data every hour. `daily` exports the data at midnight (based on
            the projects timezone). **frequency** should only be passed if your
            export window is indefinite.
        events:
          type: string
          description: |
            A whitelist for the event(s) you intend to export. For multiple events, you will need to pass in each event name as separate `events` parameters like so: `--data 'events=event1' \ --data 'events=event2'`


            All events in the project will be exported if no events are
            specified.
        where:
          type: string
          description: >-
            A selector expression used to filter by events data, such as event
            properties. Learn more about how to construct event selector
            expressions [here](ref:segmentation-expressions).
        data_format:
          type: string
          default: json
          enum:
           - json
          description: >
            **Default**: `json`


            The file format of the exported data. **data_format** for this pipeline type can be only
            `json` .
        gcs_bucket:
          type: string
          description: |
            The GCS bucket to export the Mixpanel data to.
        gcs_prefix:
          type: string
          description: |
            The GCS path prefix of the bucket.
        gcs_region:
          type: string
          description: |
            The GCS region for the bucket.
          enum:
            - northamerica-northeast1
            - us-central1
            - us-east1
            - us-east4
            - us-west1
            - us-west2
            - southamerica-east1
            - europe-north1
            - europe-west1
            - europe-west2
            - europe-west3
            - europe-west4
            - europe-west6
            - asia-east1
            - asia-east2
            - asia-northeast1
            - asia-northeast2
            - asia-northeast3
            - asia-south1
            - asia-southeast1
            - australia-southeast1
      required:
        - type
        - from_date
        - gcs_bucket
        - gcs_region

    RawAmazonS3Pipeline:
      title: Raw Amazon S3 Pipeline
      type: object
      properties:
        project_id:
          $ref: '#/components/schemas/ProjectId'
        type:
          type: string
          default: s3-raw
        trial:
          type: boolean
          default: false
          description: >
            **Default**: `false`


            A trial pipeline will be created if value is true.


            The trial exports all of your events and user data for thirty
            calendar days, starting from one day before the API call was made. A
            trial pipeline has default values for the following parameters:


            **data_source**: `events`


            **from_date**: `<defaults to previous day>`

            **to_date**: `<no value>`

            **frequency**: `daily`

            **events**: `<no value>`
        data_source:
          type: string
          enum:
            - events
          default: events
          description: >
            **Default**: `events`


            **data_source** In this type of pipeline it can only be `events` which exports
            Mixpanel event data.
        from_date:
          type: string
          format: date
          description: >
            The starting date of the export window. It is formatted as
            `YYYY-MM-DD` and cannot be more than six months in the past.


            If **trial** is set to `true` this will default to the previous day;
            otherwise, it is a required parameter.
        to_date:
          type: string
          format: date
          description: >-
            The ending date of the export window. It is formatted as
            `YYYY-MM-DD`. The export will continue indefinitely if **to_date**
            is empty.
        frequency:
          type: string
          default: daily
          enum:
           - daily
           - hourly
          description: >
            **Default**: `daily`


            **frequency** can be either `hourly` or `daily`. `hourly` exports
            the data every hour. `daily` exports the data at midnight (based on
            the projects timezone). **frequency** should only be passed if your
            export window is indefinite.
        events:
          type: string
          description: |
            A whitelist for the event(s) you intend to export. For multiple events, you will need to pass in each event name as separate `events` parameters like so: `--data 'events=event1' \ --data 'events=event2'`


            All events in the project will be exported if no events are
            specified.
        where:
          type: string
          description: >-
            A selector expression used to filter by events data, such as event
            properties. Learn more about how to construct event selector
            expressions [here](ref:segmentation-expressions).
        data_format:
          type: string
          default: json
          enum:
           - json
          description: >
            **Default**: `json`


            The file format of the exported data. **data_format** for this pipeline type can be only
            `json` .

        s3_bucket:
          type: string
          description: The S3 bucket to which the data needs to be exported.
        s3_region:
          type: string
          enum:
            - us-east-1
            - us-east-2
            - us-west-1
            - us-west-2
            - ap-northeast-1
            - ap-northeast-2
            - ap-northeast-3
            - ap-southeast-1
            - ap-southeast-2
            - ap-south-1
            - ca-central-1
            - cn-north-1
            - cn-northwest-1
            - eu-central-1
            - eu-north-1
            - eu-west-1
            - eu-west-2
            - eu-west-3
            - sa-east-1
            - me-south-1
          description: The valid S3 region for the bucket.
        s3_role:
          type: string
          description: >-
            There is no default value. AWS Role the writer should assume when
            writing to s3 e.g. arn:aws:iam::<account-id>:role/example-s3-role
        s3_prefix:
          type: string
          description: There is no default value. The path prefix for the export. e.g. example_custom_prefix
        s3_encryption:
          type: string
          default: none
          enum:
           - none
           - aes
           - kms
          description: >
            At rest encryption used by the
            s3 bucket.
        s3_kms_key_id:
          type: string
          description: >-
            There is no default value. If s3_encryption is set to kms, this can
            specify the custom key id you desire to use.
      required:
        - type
        - from_date
        - s3_bucket
        - s3_region
        - s3_role

    RawAzurePipeline:
      title: Raw Azure Pipeline
      type: object
      properties:
        project_id:
          $ref: '#/components/schemas/ProjectId'
        type:
          type: string
          default: azure-raw
        trial:
          type: boolean
          default: false
          description: >
            **Default**: `false`


            A trial pipeline will be created if value is true.


            The trial exports all of your events and user data for thirty
            calendar days, starting from one day before the API call was made. A
            trial pipeline has default values for the following parameters:


            **data_source**: `events`

            **from_date**: `<defaults to previous day>`

            **to_date**: `<no value>`

            **frequency**: `daily`

            **events**: `<no value>`
        data_source:
          type: string
          enum:
            - events
          default: events
          description: >
            **Default**: `events`


            **data_source** In this type of pipeline it is `events` which exports
            Mixpanel event data.
        from_date:
          type: string
          format: date
          description: >
            The starting date of the export window. It is formatted as
            `YYYY-MM-DD` and cannot be more than six months in the past.


            If **trial** is set to `true` this will default to the previous day;
            otherwise, it is a required parameter.
        to_date:
          type: string
          format: date
          description: >-
            The ending date of the export window. It is formatted as
            `YYYY-MM-DD`. The export will continue indefinitely if **to_date**
            is empty.
        frequency:
          type: string
          default: daily
          enum:
           - daily
           - hourly
          description: >
            **Default**: `daily`


            **frequency** can be either `hourly` or `daily`. `hourly` exports
            the data every hour. `daily` exports the data at midnight (based on
            the projects timezone). **frequency** should only be passed if your
            export window is indefinite.
        events:
          type: string
          description: |
            A whitelist for the event(s) you intend to export. For multiple events, you will need to pass in each event name as separate `events` parameters like so: `--data 'events=event1' \ --data 'events=event2'`


            All events in the project will be exported if no events are
            specified.
        where:
          type: string
          description: >-
            A selector expression used to filter by events data, such as event
            properties. Learn more about how to construct event selector
            expressions [here](ref:segmentation-expressions).
        data_format:
          type: string
          default: json
          enum:
           - json
          description: >
            **Default**: `json`


            The file format of the exported data. **data_format** for this pipeline type can be only
            `json` .
        storage_account:
          type: string
          description: Blob Storage Account where the data will be exported.
        container_name:
          type: string
          description: The Blob Container within the account where data will be exported.
        prefix:
          type: string
          description: A custom prefix for all the data being exported to the container.
        client_id:
          type: string
          description: |
            `clientId` from the Service Principal credentials.
        client_secret:
          type: string
          description: |
            `clientSecret` from the Service Principal credentials.
        tenant_id:
          type: string
          description: >
            `tenantId` from the Service Principal credentials. This is specific
            to the Active Directory instance where the Service Principal
            resides.
      required:
        - type
        - from_date
        - storage_account
        - container_name
        - client_id
        - client_secret
        - tenant_id
    SchematizedBigQueryPipeline:
      title: Schematized BigQuery Pipeline
      type: object
      properties:
        project_id:
          $ref: '#/components/schemas/ProjectId'
        type:
          type: string
          default: bigquery
        trial:
          type: boolean
          default: false
          description: >
            **Default**: `false`


            A trial pipeline will be created if value is true.


            The trial exports all of your events and user data for thirty
            calendar days, starting from one day before the API call was made. A
            trial pipeline has default values for the following parameters:


            **data_source**: `events and people`

            **sync**: `false`

            **from_date**: `<defaults to previous day>`

            **to_date**: `<no value>`

            **frequency**: `daily`

            **events**: `<no value>`
        schema_type:
          type: string
          enum:
            - monoschema
            - multischema
          default: monoschema
          description: >
            **Default**: `monoschema`


            Allowed options are `monoschema` and `multischema`. `monoschema`
            loads all events into a single table. `multischema` loads every
            event into its own dedicated table. All user data is exported as
            `monoschema`. This param is not supported for people data_source.
        data_source:
          type: string
          enum:
            - events
            - people
          default: events
          description: >
            **Default**: `events`


            **data_source** can be either `events` or `people`. `events` exports
            Mixpanel event data. `people` exports Mixpanel user data.
        sync:
          type: boolean
          enum:
            - true
          default: true
          description: >
            A value of `true` updates exported data with any changes that occur
            in your Mixpanel dataset. These changes include deletions, late
            data, and imports that fall into your export window.
        from_date:
          type: string
          format: date
          description: >
            The starting date of the export window. It is formatted as
            `YYYY-MM-DD` and cannot be more than six months in the past.


            If **trial** is set to `true` this will default to the previous day;
            otherwise, it is a required parameter.
        to_date:
          type: string
          format: date
          description: >-
            The ending date of the export window. It is formatted as
            `YYYY-MM-DD`. The export will continue indefinitely if **to_date**
            is empty.
        frequency:
          type: string
          default: daily
          enum:
            - daily
            - hourly
          description: >
            **Default**: `daily`


            **frequency** can be either `hourly` or `daily`. `hourly` exports
            the data every hour. `daily` exports the data at midnight (based on
            the projects timezone). **frequency** should only be passed if your
            export window is indefinite.
        events:
          type: string
          description: |
            A whitelist for the event(s) you intend to export. For multiple events, you will need to pass in each event name as separate `events` parameters like so: `--data 'events=event1' \ --data 'events=event2'`


            All events in the project will be exported if no events are
            specified.
        where:
          type: string
          description: >-
            A selector expression used to filter by events data, such as event
            properties. Learn more about how to construct event selector
            expressions [here](ref:segmentation-expressions). This parameter is only valid when **data_source**
            is `events`.
        bq_region:
          type: string
          enum:
            - US
            - US_CENTRAL_1
            - US_EAST_1
            - US_WEST_1
            - US_WEST_2
            - US_EAST_4
            - NORTH_AMERICA_NORTHEAST_1
            - SOUTH_AMERICA_EAST_1
            - EU
            - EUROPE_NORTH_1
            - EUROPE_WEST_2
            - EUROPE_WEST_3
            - EUROPE_WEST_4
            - EUROPE_WEST_6
            - ASIA_SOUTH_1
            - ASIA_EAST_1
            - ASIA_EAST_2
            - ASIA_NORTHEAST_1
            - ASIA_NORTHEAST_2
            - ASIA_NORTHEAST_3
            - ASIA_SOUTHEAST_1
            - ASIA_SOUTHEAST_2
            - AUSTRALIA_SOUTHEAST_1
          description: The region used for BigQuery.
        bq_share_with_group:
          type: string
          description: Group account email address to share the data-set with if managed by mixpanel. e.g. bq-access-alias@somecompany.com
        bq_prefix:
          type: string
          description: The table prefix to be added to all the tables exported as part of the this pipeline. Only alphanumeric characters and underscores can be used.
        gcp_project:
          type: string
          description: Customer's project id where bigquery dataset is present. If this field isn't provided the default dataset will be created on mixpanel managed bigquery.
        bq_dataset_name:
          type: string
          description: Dataset created by customer on their own gcp project to which mixpanel needs to export data.
      required:
        - type
        - from_date
        - bq_region
        - sync
        - schema_type

    SchematizedSnowflakePipeline:
      title: Schematized Snowflake Pipeline
      type: object
      properties:
        project_id:
          $ref: '#/components/schemas/ProjectId'
        type:
          type: string
          default: snowflake
        trial:
          type: boolean
          default: false
          description: >
            **Default**: `false`


            A trial pipeline will be created if value is true.


            The trial exports all of your events and user data for thirty
            calendar days, starting from one day before the API call was made. A
            trial pipeline has default values for the following parameters:


            **data_source**: `events and people`

            **sync**: `false`

            **from_date**: `<defaults to previous day>`

            **to_date**: `<no value>`

            **frequency**: `daily`

            **events**: `<no value>`
        schema_type:
          type: string
          enum:
            - monoschema
            - multischema
          default: monoschema
          description: >
            **Default**: `monoschema`


            Allowed options are `monoschema` and `multischema`. `monoschema`
            loads all events into a single table. `multischema` loads every
            event into its own dedicated table. All user data is exported as
            `monoschema`. This param is not supported for people data_source.
        data_source:
          type: string
          enum:
            - events
            - people
          default: events
          description: >
            **Default**: `events`


            **data_source** can be either `events` or `people`. `events` exports
            Mixpanel event data. `people` exports Mixpanel user data.
        sync:
          type: boolean
          enum:
            - true
          default: true
          description: >
            A value of `true` updates exported data with any changes that occur
            in your Mixpanel dataset. These changes include deletions, late
            data, and imports that fall into your export window.
        from_date:
          type: string
          format: date
          description: >
            The starting date of the export window. It is formatted as
            `YYYY-MM-DD` and cannot be more than six months in the past.


            If **trial** is set to `true` this will default to the previous day;
            otherwise, it is a required parameter.
        to_date:
          type: string
          format: date
          description: >-
            The ending date of the export window. It is formatted as
            `YYYY-MM-DD`. The export will continue indefinitely if **to_date**
            is empty.
        frequency:
          type: string
          default: daily
          enum:
            - daily
            - hourly
          description: >
            **Default**: `daily`


            **frequency** can be either `hourly` or `daily`. `hourly` exports
            the data every hour. `daily` exports the data at midnight (based on
            the projects timezone). **frequency** should only be passed if your
            export window is indefinite.
        events:
          type: string
          description: |
            A whitelist for the event(s) you intend to export. For multiple events, you will need to pass in each event name as separate `events` parameters like so: `--data 'events=event1' \ --data 'events=event2'`


            All events in the project will be exported if no events are
            specified.
        where:
          type: string
          description: >-
            A selector expression used to filter by events data, such as event
            properties. Learn more about how to construct event selector
            expressions [here](ref:segmentation-expressions). This parameter is only valid when **data_source**
            is `events`.
        snowflake_prefix:
          type: string
          description: prefix for created views and tables
        snowflake_share_with:
          type: string
          description: Name of the account with which the data-set should be shared. e.g. mysnowflakeaccountname
        region:
          type: string
          enum:
            - us-west-aws
            - us-east-aws
            - us-east-2-aws
            - eu-west-1-aws
            - eu-central-1-aws
            - ap-southeast-2-aws
          description: The valid region for the Snowflake instance
      required:
        - type
        - from_date
        - snowflake_share_with
        - region
        - sync
        - schema_type

    SchematizedAWSPipeline:
      title: Schematized AWS Pipeline
      type: object
      properties:
        project_id:
          $ref: '#/components/schemas/ProjectId'
        type:
          type: string
          default: aws
        trial:
          type: boolean
          default: false
          description: >
            **Default**: `false`


            A trial pipeline will be created if value is true.


            The trial exports all of your events and user data for thirty
            calendar days, starting from one day before the API call was made. A
            trial pipeline has default values for the following parameters:


            **data_source**: `events and people`

            **sync**: `false`

            **from_date**: `<defaults to previous day>`

            **to_date**: `<no value>`

            **frequency**: `daily`

            **events**: `<no value>`
        schema_type:
          type: string
          enum:
            - monoschema
            - multischema
          default: monoschema
          description: >
            **Default**: `monoschema`


            Allowed options are `monoschema` and `multischema`. `monoschema`
            loads all events into a single table. `multischema` loads every
            event into its own dedicated table. All user data is exported as
            `monoschema`. This param is not supported for people data_source.
        data_source:
          type: string
          enum:
            - events
            - people
          default: events
          description: >
            **Default**: `events`


            **data_source** can be either `events` or `people`. `events` exports
            Mixpanel event data. `people` exports Mixpanel user data.
        sync:
          type: boolean
          enum:
            - true
          default: true
          description: >
            A value of `true` updates exported data with any changes that occur
            in your Mixpanel dataset. These changes include deletions, late
            data, and imports that fall into your export window.
        from_date:
          type: string
          format: date
          description: >
            The starting date of the export window. It is formatted as
            `YYYY-MM-DD` and cannot be more than six months in the past.


            If **trial** is set to `true` this will default to the previous day;
            otherwise, it is a required parameter.
        to_date:
          type: string
          format: date
          description: >-
            The ending date of the export window. It is formatted as
            `YYYY-MM-DD`. The export will continue indefinitely if **to_date**
            is empty.
        frequency:
          type: string
          default: daily
          enum:
            - daily
            - hourly
          description: >
            **Default**: `daily`


            **frequency** can be either `hourly` or `daily`. `hourly` exports
            the data every hour. `daily` exports the data at midnight (based on
            the projects timezone). **frequency** should only be passed if your
            export window is indefinite.
        events:
          type: string
          description: |
            A whitelist for the event(s) you intend to export. For multiple events, you will need to pass in each event name as separate `events` parameters like so: `--data 'events=event1' \ --data 'events=event2'`


            All events in the project will be exported if no events are
            specified.
        where:
          type: string
          description: >-
            A selector expression used to filter by events data, such as event
            properties. Learn more about how to construct event selector
            expressions [here](ref:segmentation-expressions). This parameter is only valid when **data_source**
            is `events`.
        data_format:
          type: string
          default: json
          enum:
            - json
            - parquet
          description: >
            **Default**: `json`


            The file format of the exported data. **data_format** can be either
            `json` or `parquet`.
        s3_bucket:
          type: string
          description: The S3 bucket to which the data needs to be exported.
        s3_region:
          type: string
          enum:
            - us-east-1
            - us-east-2
            - us-west-1
            - us-west-2
            - ap-northeast-1
            - ap-northeast-2
            - ap-northeast-3
            - ap-southeast-1
            - ap-southeast-2
            - ap-south-1
            - ca-central-1
            - cn-north-1
            - cn-northwest-1
            - eu-central-1
            - eu-north-1
            - eu-west-1
            - eu-west-2
            - eu-west-3
            - sa-east-1
          description: The valid S3 region for the bucket.
        s3_role:
          type: string
          description: >-
            There is no default value. AWS Role the writer should assume when
            writing to s3 e.g. arn:aws:iam::<account-id>:role/example-s3-role.
        s3_prefix:
          type: string
          description: There is no default value. The path prefix for the export.
        s3_encryption:
          type: string
          default: none
          enum:
            - none
            - aes
            - kms
          description: >
            At rest encryption used by the s3 bucket.
        s3_kms_key_id:
          type: string
          description: >-
            There is no default value. If s3_encryption is set to kms, this can
            specify the custom key id you desire to use.
        use_glue:
          type: boolean
          default: false
          description: |
            **Default**: `false`

            Use glue schema export.
        glue_database:
          type: string
          description: |
            Required if **use_glue** is `true`.

            The glue database to which the schema needs to be exported.
        glue_role:
          type: string
          description: >
            Required if **use_glue** is `true`. e.g. arn:aws:iam::<account-id>:role/example-glue-role


            There is no default value. The role that needs to be assumed for
            updating glue.
        glue_table_prefix:
          type: string
          description: >-
            There is no default value. Prefix to add to table names when
            creating them.
      required:
        - type
        - from_date
        - s3_bucket
        - s3_region
        - s3_role
        - sync
        - schema_type

    SchematizedAzurePipeline:
      title: Schematized Azure Pipeline
      type: object
      properties:
        project_id:
          $ref: '#/components/schemas/ProjectId'
        type:
          type: string
          default: azure-blob
        trial:
          type: boolean
          default: false
          description: >
            **Default**: `false`


            A trial pipeline will be created if value is true.


            The trial exports all of your events and user data for thirty
            calendar days, starting from one day before the API call was made. A
            trial pipeline has default values for the following parameters:


            **data_source**: `events and people`

            **sync**: `false`

            **from_date**: `<defaults to previous day>`

            **to_date**: `<no value>`

            **frequency**: `daily`

            **events**: `<no value>`
        schema_type:
          type: string
          enum:
            - monoschema
            - multischema
          default: monoschema
          description: >
            **Default**: `monoschema`


            Allowed options are `monoschema` and `multischema`. `monoschema`
            loads all events into a single table. `multischema` loads every
            event into its own dedicated table. All user data is exported as
            `monoschema`. This param is not supported for people data_source.
        data_source:
          type: string
          enum:
            - events
            - people
          default: events
          description: >
            **Default**: `events`


            **data_source** can be either `events` or `people`. `events` exports
            Mixpanel event data. `people` exports Mixpanel user data.
        sync:
          type: boolean
          enum:
            - true
          default: true
          description: >
            A value of `true` updates exported data with any changes that occur
            in your Mixpanel dataset. These changes include deletions, late
            data, and imports that fall into your export window.
        from_date:
          type: string
          format: date
          description: >
            The starting date of the export window. It is formatted as
            `YYYY-MM-DD` and cannot be more than six months in the past.


            If **trial** is set to `true` this will default to the previous day;
            otherwise, it is a required parameter.
        to_date:
          type: string
          format: date
          description: >-
            The ending date of the export window. It is formatted as
            `YYYY-MM-DD`. The export will continue indefinitely if **to_date**
            is empty.
        frequency:
          type: string
          default: daily
          enum:
           - daily
           - hourly
          description: >
            **Default**: `daily`


            **frequency** can be either `hourly` or `daily`. `hourly` exports
            the data every hour. `daily` exports the data at midnight (based on
            the projects timezone). **frequency** should only be passed if your
            export window is indefinite.
        events:
          type: string
          description: |
            A whitelist for the event(s) you intend to export. For multiple events, you will need to pass in each event name as separate `events` parameters like so: `--data 'events=event1' \ --data 'events=event2'`


            All events in the project will be exported if no events are
            specified.
        where:
          type: string
          description: >-
            A selector expression used to filter by events data, such as event
            properties. Learn more about how to construct event selector
            expressions [here](ref:segmentation-expressions). This parameter is only valid when **data_source**
            is `events`.
        data_format:
          type: string
          default: json
          enum:
           - json
           - parquet
          description: >
            **Default**: `json`


            The file format of the exported data. **data_format** can be either
            `json` or `parquet`.
        storage_account:
          type: string
          description: Blob Storage Account where the data will be exported.
        container_name:
          type: string
          description: The Blob Container within the account where data will be exported.
        prefix:
          type: string
          description: A custom prefix for all the data being exported to the container.
        client_id:
          type: string
          description: |
            `clientId` from the Service Principal credentials.
        client_secret:
          type: string
          description: |
            `clientSecret` from the Service Principal credentials.
        tenant_id:
          type: string
          description: >
            `tenantId` from the Service Principal credentials. This is specific
            to the Active Directory instance where the Service Principal
            resides.
      required:
        - type
        - from_date
        - storage_account
        - container_name
        - client_id
        - client_secret
        - tenant_id
        - sync
        - schema_type

    SchematizedGCSPipeline:
      title: Schematized GCS Pipeline
      type: object
      properties:
        project_id:
          $ref: '#/components/schemas/ProjectId'
        type:
          type: string
          default: gcs-schema
        trial:
          type: boolean
          default: false
          description: >
            **Default**: `false`
            A trial pipeline will be created if value is true.
            The trial exports all of your events and user data for thirty
            calendar days, starting from one day before the API call was made. A
            trial pipeline has default values for the following parameters:
            **data_source**: `events and people`
            **sync**: `false`
            **from_date**: `<defaults to previous day>`
            **to_date**: `<no value>`
            **frequency**: `daily`
            **events**: `<no value>`
        schema_type:
          type: string
          enum:
            - monoschema
            - multischema
          default: monoschema
          description: >
            **Default**: `monoschema`
            Allowed options are `monoschema` and `multischema`. `monoschema`
            loads all events into a single table. `multischema` loads every
            event into its own dedicated table. All user data is exported as
            `monoschema`. This param is not supported for people data_source.
        data_source:
          type: string
          enum:
            - events
            - people
          default: events
          description: >
            **Default**: `events`
            **data_source** can be either `events` or `people`. `events` exports
            Mixpanel event data. `people` exports Mixpanel user data.
        sync:
          type: boolean
          enum:
            - true
          default: true
          description: >
            A value of `true` updates exported data with any changes that occur
            in your Mixpanel dataset. These changes include deletions, late
            data, and imports that fall into your export window.
        from_date:
          type: string
          format: date
          description: >
            The starting date of the export window. It is formatted as
            `YYYY-MM-DD` and cannot be more than six months in the past.


            If **trial** is set to `true` this will default to the previous day;
            otherwise, it is a required parameter.
        to_date:
          type: string
          format: date
          description: >-
            The ending date of the export window. It is formatted as
            `YYYY-MM-DD`. The export will continue indefinitely if **to_date**
            is empty.
        frequency:
          type: string
          default: daily
          enum:
           - daily
           - hourly
          description: >
            **Default**: `daily`
            **frequency** can be either `hourly` or `daily`. `hourly` exports
            the data every hour. `daily` exports the data at midnight (based on
            the projects timezone). **frequency** should only be passed if your
            export window is indefinite.
        events:
          type: string
          description: |
            A whitelist for the event(s) you intend to export. For multiple events, you will need to pass in each event name as separate `events` parameters like so: `--data 'events=event1' \ --data 'events=event2'`
            
            All events in the project will be exported if no events are
            specified.
        where:
          type: string
          description: >-
            A selector expression used to filter by events data, such as event
            properties. Learn more about how to construct event selector
            expressions [here](ref:segmentation-expressions). This parameter is only valid when **data_source**
            is `events`.
        data_format:
          type: string
          default: json
          enum:
           - json
           - parquet
          description: >
            **Default**: `json`
            The file format of the exported data. **data_format** can be either
            `json` or `parquet`.
        gcs_bucket:
          type: string
          description: |
            *Required if **type** is `gcs-schema`
            The GCS bucket to export the Mixpanel data to.
        gcs_prefix:
          type: string
          description: |
            *Required if **type** is `gcs-schema`
            The GCS path prefix of the bucket.
        gcs_region:
          type: string
          description: |
            *Required if **type** is `gcs-schema`
            The GCS region for the bucket.
          enum:
            - northamerica-northeast1
            - us-central1
            - us-east1
            - us-east4
            - us-west1
            - us-west2
            - southamerica-east1
            - europe-north1
            - europe-west1
            - europe-west2
            - europe-west3
            - europe-west4
            - europe-west6
            - asia-east1
            - asia-east2
            - asia-northeast1
            - asia-northeast2
            - asia-northeast3
            - asia-south1
            - asia-southeast1
            - australia-southeast1
      required:
        - type
        - from_date
        - gcs_bucket
        - gcs_region
        - sync
        - schema_type
    ErrorResponse:
      type: object
      properties:
        error:
          type: string
        status:
          type: string
          enum:
            - error
    RawEditParams:
      type: object
      properties:
        name:
          type: string
          description: The name that uniquely identifies the pipeline.
        project_id:
          $ref: '#/components/schemas/ProjectId'
        events:
          type: string
          description: |
            A whitelist for the event(s) you intend to export. For multiple events, you will need to pass in each event name as separate `events` parameters like so: `--data 'events=event1' \ --data 'events=event2'`


            Please note that after this update, the sync of older dates to your data warehouse
            (if enabled) will only contain the new set of whitelisted events.
        where:
          type: string
          description: >-
            A selector expression used to filter by events data, such as event properties.


            Please note that after this update, the sync of older dates to your data warehouse
            (if enabled) will only contain events matching your new where clause.
      required:
        - name
    SchematizedEditParams:
      allOf:
        - $ref: '#/components/schemas/RawEditParams'
    AzureCommonEditParams:
      type: object
      properties:
        azure_client_id:
          type: string
          description: |
            `clientId` from the Service Principal credentials.
        azure_client_secret:
          type: string
          description: |
            `clientSecret` from the Service Principal credentials.
        azure_tenant_id:
          type: string
          description: >
            `tenantId` from the Service Principal credentials. This is specific
            to the Active Directory instance where the Service Principal
            resides.
    RawAzureEditParams:
      allOf:
        - $ref: '#/components/schemas/RawEditParams'
        - $ref: '#/components/schemas/AzureCommonEditParams'
    SchematizedAzureEditParams:
      allOf:
        - $ref: '#/components/schemas/SchematizedEditParams'
        - $ref: '#/components/schemas/AzureCommonEditParams'
    BigQueryEditParams:
      allOf:
        - $ref: '#/components/schemas/SchematizedEditParams'
        - type: object
          properties:
            bq_share_with_group:
              type: array
              description: >
                Group account email addresses to share the data-set with if managed by mixpanel. e.g. bq-access-alias@somecompany.com.


                Please note that this will only add new shares and won't remove the old ones.
              items:
                type: string
    SchematizedAWSEditParams:
      allOf:
        - $ref: '#/components/schemas/SchematizedEditParams'
        - type: object
          properties:
            glue_database:
              type: string
              description: >
                The glue database to which the schema needs to be exported.
            glue_role:
              type: string
              description: >
                There is no default value. The role that needs to be assumed for
                updating glue  e.g. arn:aws:iam::<account-id>:role/example-glue-role
            glue_table_prefix:
              type: string
              description: >
                Prefix to add to table names when creating them.

    PipelineStatusJobList:
      type: array
      items:
        type: object
        properties:
          project_id:
            $ref: '#/components/schemas/ProjectId'
          name:
            type: string
          state:
            type: string
          last_finish:
            type: string
          run_at:
            type: string
          from_date:
            type: string
          to_date:
            type: string
    PipelineStatusResponse:
      type: object
      properties:
        canceled:
          $ref: '#/components/schemas/PipelineStatusJobList'
        retried:
          $ref: '#/components/schemas/PipelineStatusJobList'
        succeeded:
          $ref: '#/components/schemas/PipelineStatusJobList'
  responses:
    BadRequest:
      description: Bad Request
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    Unauthorized:
      description: Unauthorized
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    Forbidden:
      description: Forbidden
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
    NotFound:
      description: Not Found
      content:
        application/json:
          schema:
            $ref: '#/components/schemas/ErrorResponse'
x-explorer-enabled: true
x-proxy-enabled: true
x-samples-enabled: true
x-samples-languages:
  - curl
  - node
  - ruby
  - javascript
  - python