Amazon Glue #X Amz Target=AWSGlue.CreateCrawler API

openapi: 3.0.0
info:
  version: '2017-03-31'
  x-release: v4
  title: 'AWS Glue #X Amz Target=AWSGlue.BatchCreatePartition #X Amz Target=AWSGlue.BatchCreatePartition #X Amz Target=AWSGlue.CreateCrawler API'
  description: <fullname>Glue</fullname> <p>Defines the public endpoint for the Glue service.</p>
  x-logo:
    url: https://api.apis.guru/v2/cache/logo/https_twitter.com_awscloud_profile_image.png
    backgroundColor: '#FFFFFF'
  termsOfService: https://aws.amazon.com/service-terms/
  contact:
    name: Mike Ralphson
    email: mike.ralphson@gmail.com
    url: https://github.com/mermade/aws2openapi
    x-twitter: PermittedSoc
  license:
    name: Apache 2.0 License
    url: http://www.apache.org/licenses/
  x-providerName: amazonaws.com
  x-serviceName: glue
  x-origin:
  - contentType: application/json
    url: https://raw.githubusercontent.com/aws/aws-sdk-js/master/apis/glue-2017-03-31.normal.json
    converter:
      url: https://github.com/mermade/aws2openapi
      version: 1.0.0
    x-apisguru-driver: external
  x-apiClientRegistration:
    url: https://portal.aws.amazon.com/gp/aws/developer/registration/index.html?nc2=h_ct
  x-apisguru-categories:
  - cloud
  x-preferred: true
servers:
- url: http://glue.{region}.amazonaws.com
  variables:
    region:
      description: The AWS region
      enum:
      - us-east-1
      - us-east-2
      - us-west-1
      - us-west-2
      - us-gov-west-1
      - us-gov-east-1
      - ca-central-1
      - eu-north-1
      - eu-west-1
      - eu-west-2
      - eu-west-3
      - eu-central-1
      - eu-south-1
      - af-south-1
      - ap-northeast-1
      - ap-northeast-2
      - ap-northeast-3
      - ap-southeast-1
      - ap-southeast-2
      - ap-east-1
      - ap-south-1
      - sa-east-1
      - me-south-1
      default: us-east-1
  description: The AWS Glue multi-region endpoint
- url: https://glue.{region}.amazonaws.com
  variables:
    region:
      description: The AWS region
      enum:
      - us-east-1
      - us-east-2
      - us-west-1
      - us-west-2
      - us-gov-west-1
      - us-gov-east-1
      - ca-central-1
      - eu-north-1
      - eu-west-1
      - eu-west-2
      - eu-west-3
      - eu-central-1
      - eu-south-1
      - af-south-1
      - ap-northeast-1
      - ap-northeast-2
      - ap-northeast-3
      - ap-southeast-1
      - ap-southeast-2
      - ap-east-1
      - ap-south-1
      - sa-east-1
      - me-south-1
      default: us-east-1
  description: The AWS Glue multi-region endpoint
- url: http://glue.{region}.amazonaws.com.cn
  variables:
    region:
      description: The AWS region
      enum:
      - cn-north-1
      - cn-northwest-1
      default: cn-north-1
  description: The AWS Glue endpoint for China (Beijing) and China (Ningxia)
- url: https://glue.{region}.amazonaws.com.cn
  variables:
    region:
      description: The AWS region
      enum:
      - cn-north-1
      - cn-northwest-1
      default: cn-north-1
  description: The AWS Glue endpoint for China (Beijing) and China (Ningxia)
security:
- hmac: []
tags:
- name: '#X Amz Target=AWSGlue.CreateCrawler'
paths:
  /#X-Amz-Target=AWSGlue.CreateCrawler:
    parameters:
    - $ref: '#/components/parameters/X-Amz-Content-Sha256'
    - $ref: '#/components/parameters/X-Amz-Date'
    - $ref: '#/components/parameters/X-Amz-Algorithm'
    - $ref: '#/components/parameters/X-Amz-Credential'
    - $ref: '#/components/parameters/X-Amz-Security-Token'
    - $ref: '#/components/parameters/X-Amz-Signature'
    - $ref: '#/components/parameters/X-Amz-SignedHeaders'
    post:
      operationId: CreateCrawler
      description: Creates a new crawler with specified targets, role, configuration, and optional schedule. At least one crawl target must be specified, in the <code>s3Targets</code> field, the <code>jdbcTargets</code> field, or the <code>DynamoDBTargets</code> field.
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/CreateCrawlerResponse'
              examples:
                CreateCrawler200Example:
                  summary: Default CreateCrawler 200 response
                  x-microcks-default: true
                  value:
                    JobRunId: jr_abc123
                    State: SUCCEEDED
        '480':
          description: InvalidInputException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InvalidInputException'
              examples:
                CreateCrawler480Example:
                  summary: Default CreateCrawler 480 response
                  x-microcks-default: true
                  value:
                    JobRunId: jr_abc123
                    State: SUCCEEDED
        '481':
          description: AlreadyExistsException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/AlreadyExistsException'
              examples:
                CreateCrawler481Example:
                  summary: Default CreateCrawler 481 response
                  x-microcks-default: true
                  value:
                    JobRunId: jr_abc123
                    State: SUCCEEDED
        '482':
          description: OperationTimeoutException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/OperationTimeoutException'
              examples:
                CreateCrawler482Example:
                  summary: Default CreateCrawler 482 response
                  x-microcks-default: true
                  value:
                    JobRunId: jr_abc123
                    State: SUCCEEDED
        '483':
          description: ResourceNumberLimitExceededException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ResourceNumberLimitExceededException'
              examples:
                CreateCrawler483Example:
                  summary: Default CreateCrawler 483 response
                  x-microcks-default: true
                  value:
                    JobRunId: jr_abc123
                    State: SUCCEEDED
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/CreateCrawlerRequest'
      parameters:
      - name: X-Amz-Target
        in: header
        required: true
        schema:
          type: string
          enum:
          - AWSGlue.CreateCrawler
      summary: Amazon Glue Create Crawler
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
      tags:
      - '#X Amz Target=AWSGlue.CreateCrawler'
components:
  schemas:
    TagsMap:
      type: object
      minProperties: 0
      maxProperties: 50
      additionalProperties:
        $ref: '#/components/schemas/TagValue'
    DescriptionString:
      type: string
      minLength: 0
      maxLength: 2048
      x-pattern: '[\u0020-\uD7FF\uE000-\uFFFD\uD800\uDC00-\uDBFF\uDFFF\r\n\t]*'
    MongoDBTarget:
      type: object
      properties:
        ConnectionName:
          allOf:
          - $ref: '#/components/schemas/ConnectionName'
          - description: The name of the connection to use to connect to the Amazon DocumentDB or MongoDB target.
        Path:
          allOf:
          - $ref: '#/components/schemas/Path'
          - description: The path of the Amazon DocumentDB or MongoDB target (database/collection).
        ScanAll:
          allOf:
          - $ref: '#/components/schemas/NullableBoolean'
          - description: <p>Indicates whether to scan all the records, or to sample rows from the table. Scanning all the records can take a long time when the table is not a high throughput table.</p> <p>A value of <code>true</code> means to scan all records, while a value of <code>false</code> means to sample the records. If no value is specified, the value defaults to <code>true</code>.</p>
      description: Specifies an Amazon DocumentDB or MongoDB data store to crawl.
    CrawlerConfiguration:
      type: string
    MongoDBTargetList:
      type: array
      items:
        $ref: '#/components/schemas/MongoDBTarget'
    NullableInteger:
      type: integer
    AccountId:
      type: string
      minLength: 0
      maxLength: 12
    NullableBoolean:
      type: boolean
    Role:
      type: string
    DatabaseName:
      type: string
    ClassifierNameList:
      type: array
      items:
        $ref: '#/components/schemas/NameString'
    RecrawlBehavior:
      type: string
      enum:
      - CRAWL_EVERYTHING
      - CRAWL_NEW_FOLDERS_ONLY
      - CRAWL_EVENT_MODE
    CrawlerSecurityConfiguration:
      type: string
      minLength: 0
      maxLength: 128
    JdbcMetadataEntry:
      type: string
      enum:
      - COMMENTS
      - RAWTYPES
    Path:
      type: string
    CatalogTargetList:
      type: array
      items:
        $ref: '#/components/schemas/CatalogTarget'
    TablePrefix:
      type: string
      minLength: 0
      maxLength: 128
    OperationTimeoutException: {}
    CreateCrawlerRequest:
      type: object
      required:
      - Name
      - Role
      - Targets
      title: CreateCrawlerRequest
      properties:
        Name:
          allOf:
          - $ref: '#/components/schemas/NameString'
          - description: Name of the new crawler.
        Role:
          allOf:
          - $ref: '#/components/schemas/Role'
          - description: The IAM role or Amazon Resource Name (ARN) of an IAM role used by the new crawler to access customer resources.
        DatabaseName:
          allOf:
          - $ref: '#/components/schemas/DatabaseName'
          - description: 'The Glue database where results are written, such as: <code>arn:aws:daylight:us-east-1::database/sometable/*</code>.'
        Description:
          allOf:
          - $ref: '#/components/schemas/DescriptionString'
          - description: A description of the new crawler.
        Targets:
          allOf:
          - $ref: '#/components/schemas/CrawlerTargets'
          - description: A list of collection of targets to crawl.
        Schedule:
          allOf:
          - $ref: '#/components/schemas/CronExpression'
          - description: 'A <code>cron</code> expression used to specify the schedule (see <a href="https://docs.aws.amazon.com/glue/latest/dg/monitor-data-warehouse-schedule.html">Time-Based Schedules for Jobs and Crawlers</a>. For example, to run something every day at 12:15 UTC, you would specify: <code>cron(15 12 * * ? *)</code>.'
        Classifiers:
          allOf:
          - $ref: '#/components/schemas/ClassifierNameList'
          - description: A list of custom classifiers that the user has registered. By default, all built-in classifiers are included in a crawl, but these custom classifiers always override the default classifiers for a given classification.
        TablePrefix:
          allOf:
          - $ref: '#/components/schemas/TablePrefix'
          - description: The table prefix used for catalog tables that are created.
        SchemaChangePolicy:
          allOf:
          - $ref: '#/components/schemas/SchemaChangePolicy'
          - description: The policy for the crawler's update and deletion behavior.
        RecrawlPolicy:
          allOf:
          - $ref: '#/components/schemas/RecrawlPolicy'
          - description: A policy that specifies whether to crawl the entire dataset again, or to crawl only folders that were added since the last crawler run.
        LineageConfiguration:
          allOf:
          - $ref: '#/components/schemas/LineageConfiguration'
          - description: Specifies data lineage configuration settings for the crawler.
        LakeFormationConfiguration:
          allOf:
          - $ref: '#/components/schemas/LakeFormationConfiguration'
          - description: Specifies Lake Formation configuration settings for the crawler.
        Configuration:
          allOf:
          - $ref: '#/components/schemas/CrawlerConfiguration'
          - description: Crawler configuration information. This versioned JSON string allows users to specify aspects of a crawler's behavior. For more information, see <a href="https://docs.aws.amazon.com/glue/latest/dg/crawler-configuration.html">Setting crawler configuration options</a>.
        CrawlerSecurityConfiguration:
          allOf:
          - $ref: '#/components/schemas/CrawlerSecurityConfiguration'
          - description: The name of the <code>SecurityConfiguration</code> structure to be used by this crawler.
        Tags:
          allOf:
          - $ref: '#/components/schemas/TagsMap'
          - description: The tags to use with this crawler request. You may use tags to limit access to the crawler. For more information about tags in Glue, see <a href="https://docs.aws.amazon.com/glue/latest/dg/monitor-tags.html">Amazon Web Services Tags in Glue</a> in the developer guide.
    AlreadyExistsException: {}
    CatalogTarget:
      type: object
      required:
      - DatabaseName
      - Tables
      properties:
        DatabaseName:
          allOf:
          - $ref: '#/components/schemas/NameString'
          - description: The name of the database to be synchronized.
        Tables:
          allOf:
          - $ref: '#/components/schemas/CatalogTablesList'
          - description: A list of the tables to be synchronized.
        ConnectionName:
          allOf:
          - $ref: '#/components/schemas/ConnectionName'
          - description: The name of the connection for an Amazon S3-backed Data Catalog table to be a target of the crawl when using a <code>Catalog</code> connection type paired with a <code>NETWORK</code> Connection type.
        EventQueueArn:
          allOf:
          - $ref: '#/components/schemas/EventQueueArn'
          - description: A valid Amazon SQS ARN. For example, <code>arn:aws:sqs:region:account:sqs</code>.
        DlqEventQueueArn:
          allOf:
          - $ref: '#/components/schemas/EventQueueArn'
          - description: A valid Amazon dead-letter SQS ARN. For example, <code>arn:aws:sqs:region:account:deadLetterQueue</code>.
      description: Specifies an Glue Data Catalog target.
    CatalogTablesList:
      type: array
      items:
        $ref: '#/components/schemas/NameString'
      minItems: 1
    DynamoDBTarget:
      type: object
      properties:
        Path:
          allOf:
          - $ref: '#/components/schemas/Path'
          - description: The name of the DynamoDB table to crawl.
        scanAll:
          allOf:
          - $ref: '#/components/schemas/NullableBoolean'
          - description: <p>Indicates whether to scan all the records, or to sample rows from the table. Scanning all the records can take a long time when the table is not a high throughput table.</p> <p>A value of <code>true</code> means to scan all records, while a value of <code>false</code> means to sample the records. If no value is specified, the value defaults to <code>true</code>.</p>
        scanRate:
          allOf:
          - $ref: '#/components/schemas/NullableDouble'
          - description: <p>The percentage of the configured read capacity units to use by the Glue crawler. Read capacity units is a term defined by DynamoDB, and is a numeric value that acts as rate limiter for the number of reads that can be performed on that table per second.</p> <p>The valid values are null or a value between 0.1 to 1.5. A null value is used when user does not provide a value, and defaults to 0.5 of the configured Read Capacity Unit (for provisioned tables), or 0.25 of the max configured Read Capacity Unit (for tables using on-demand mode).</p>
      description: Specifies an Amazon DynamoDB table to crawl.
    UpdateBehavior:
      type: string
      enum:
      - LOG
      - UPDATE_IN_DATABASE
    CrawlerLineageSettings:
      type: string
      enum:
      - ENABLE
      - DISABLE
    ConnectionName:
      type: string
    CreateCrawlerResponse:
      type: object
      properties: {}
    DeltaTarget:
      type: object
      properties:
        DeltaTables:
          allOf:
          - $ref: '#/components/schemas/PathList'
          - description: A list of the Amazon S3 paths to the Delta tables.
        ConnectionName:
          allOf:
          - $ref: '#/components/schemas/ConnectionName'
          - description: The name of the connection to use to connect to the Delta table target.
        WriteManifest:
          allOf:
          - $ref: '#/components/schemas/NullableBoolean'
          - description: Specifies whether to write the manifest files to the Delta table path.
        CreateNativeDeltaTable:
          allOf:
          - $ref: '#/components/schemas/NullableBoolean'
          - description: Specifies whether the crawler will create native tables, to allow integration with query engines that support querying of the Delta transaction log directly.
      description: Specifies a Delta data store to crawl one or more Delta tables.
    EventQueueArn:
      type: string
    RecrawlPolicy:
      type: object
      properties:
        RecrawlBehavior:
          allOf:
          - $ref: '#/components/schemas/RecrawlBehavior'
          - description: <p>Specifies whether to crawl the entire dataset again or to crawl only folders that were added since the last crawler run.</p> <p>A value of <code>CRAWL_EVERYTHING</code> specifies crawling the entire dataset again.</p> <p>A value of <code>CRAWL_NEW_FOLDERS_ONLY</code> specifies crawling only folders that were added since the last crawler run.</p> <p>A value of <code>CRAWL_EVENT_MODE</code> specifies crawling only the changes identified by Amazon S3 events.</p>
      description: When crawling an Amazon S3 data source after the first crawl is complete, specifies whether to crawl the entire dataset again or to crawl only folders that were added since the last crawler run. For more information, see <a href="https://docs.aws.amazon.com/glue/latest/dg/incremental-crawls.html">Incremental Crawls in Glue</a> in the developer guide.
    NullableDouble:
      type: number
      format: double
    JdbcTargetList:
      type: array
      items:
        $ref: '#/components/schemas/JdbcTarget'
    EnableAdditionalMetadata:
      type: array
      items:
        $ref: '#/components/schemas/JdbcMetadataEntry'
    SchemaChangePolicy:
      type: object
      properties:
        UpdateBehavior:
          allOf:
          - $ref: '#/components/schemas/UpdateBehavior'
          - description: The update behavior when the crawler finds a changed schema.
        DeleteBehavior:
          allOf:
          - $ref: '#/components/schemas/DeleteBehavior'
          - description: The deletion behavior when the crawler finds a deleted object.
      description: A policy that specifies update and deletion behaviors for the crawler.
    DeleteBehavior:
      type: string
      enum:
      - LOG
      - DELETE_FROM_DATABASE
      - DEPRECATE_IN_DATABASE
    TagValue:
      type: string
      minLength: 0
      maxLength: 256
    S3Target:
      type: object
      properties:
        Path:
          allOf:
          - $ref: '#/components/schemas/Path'
          - description: The path to the Amazon S3 target.
        Exclusions:
          allOf:
          - $ref: '#/components/schemas/PathList'
          - description: A list of glob patterns used to exclude from the crawl. For more information, see <a href="https://docs.aws.amazon.com/glue/latest/dg/add-crawler.html">Catalog Tables with a Crawler</a>.
        ConnectionName:
          allOf:
          - $ref: '#/components/schemas/ConnectionName'
          - description: The name of a connection which allows a job or crawler to access data in Amazon S3 within an Amazon Virtual Private Cloud environment (Amazon VPC).
        SampleSize:
          allOf:
          - $ref: '#/components/schemas/NullableInteger'
          - description: Sets the number of files in each leaf folder to be crawled when crawling sample files in a dataset. If not set, all the files are crawled. A valid value is an integer between 1 and 249.
        EventQueueArn:
          allOf:
          - $ref: '#/components/schemas/EventQueueArn'
          - description: A valid Amazon SQS ARN. For example, <code>arn:aws:sqs:region:account:sqs</code>.
        DlqEventQueueArn:
          allOf:
          - $ref: '#/components/schemas/EventQueueArn'
          - description: A valid Amazon dead-letter SQS ARN. For example, <code>arn:aws:sqs:region:account:deadLetterQueue</code>.
      description: Specifies a data store in Amazon Simple Storage Service (Amazon S3).
    NameString:
      type: string
      minLength: 1
      maxLength: 255
      x-pattern: '[\u0020-\uD7FF\uE000-\uFFFD\uD800\uDC00-\uDBFF\uDFFF\t]*'
    InvalidInputException: {}
    LakeFormationConfiguration:
      type: object
      properties:
        UseLakeFormationCredentials:
          allOf:
          - $ref: '#/components/schemas/NullableBoolean'
          - description: Specifies whether to use Lake Formation credentials for the crawler instead of the IAM role credentials.
        AccountId:
          allOf:
          - $ref: '#/components/schemas/AccountId'
          - description: Required for cross account crawls. For same account crawls as the target data, this can be left as null.
      description: Specifies Lake Formation configuration settings for the crawler.
    DeltaTargetList:
      type: array
      items:
        $ref: '#/components/schemas/DeltaTarget'
    CrawlerTargets:
      type: object
      properties:
        S3Targets:
          allOf:
          - $ref: '#/components/schemas/S3TargetList'
          - description: Specifies Amazon Simple Storage Service (Amazon S3) targets.
        JdbcTargets:
          allOf:
          - $ref: '#/components/schemas/JdbcTargetList'
          - description: Specifies JDBC targets.
        MongoDBTargets:
          allOf:
          - $ref: '#/components/schemas/MongoDBTargetList'
          - description: Specifies Amazon DocumentDB or MongoDB targets.
        DynamoDBTargets:
          allOf:
          - $ref: '#/components/schemas/DynamoDBTargetList'
          - description: Specifies Amazon DynamoDB targets.
        CatalogTargets:
          allOf:
          - $ref: '#/components/schemas/CatalogTargetList'
          - description: Specifies Glue Data Catalog targets.
        DeltaTargets:
          allOf:
          - $ref: '#/components/schemas/DeltaTargetList'
          - description: Specifies Delta data store targets.
      description: Specifies data stores to crawl.
    S3TargetList:
      type: array
      items:
        $ref: '#/components/schemas/S3Target'
    PathList:
      type: array
      items:
        $ref: '#/components/schemas/Path'
    DynamoDBTargetList:
      type: array
      items:
        $ref: '#/components/schemas/DynamoDBTarget'
    LineageConfiguration:
      type: object
      properties:
        CrawlerLineageSettings:
          allOf:
          - $ref: '#/components/schemas/CrawlerLineageSettings'
          - description: '<p>Specifies whether data lineage is enabled for the crawler. Valid values are:</p> <ul> <li> <p>ENABLE: enables data lineage for the crawler</p> </li> <li> <p>DISABLE: disables data lineage for the crawler</p> </li> </ul>'
      description: Specifies data lineage configuration settings for the crawler.
    ResourceNumberLimitExceededException: {}
    JdbcTarget:
      type: object
      properties:
        ConnectionName:
          allOf:
          - $ref: '#/components/schemas/ConnectionName'
          - description: The name of the connection to use to connect to the JDBC target.
        Path:
          allOf:
          - $ref: '#/components/schemas/Path'
          - description: The path of the JDBC target.
        Exclusions:
          allOf:
          - $ref: '#/components/schemas/PathList'
          - description: A list of glob patterns used to exclude from the crawl. For more information, see <a href="https://docs.aws.amazon.com/glue/latest/dg/add-crawler.html">Catalog Tables with a Crawler</a>.
        EnableAdditionalMetadata:
          allOf:
          - $ref: '#/components/schemas/EnableAdditionalMetadata'
          - description: <p>Specify a value of <code>RAWTYPES</code> or <code>COMMENTS</code> to enable additional metadata in table responses. <code>RAWTYPES</code> provides the native-level datatype. <code>COMMENTS</code> provides comments associated with a column or table in the database.</p> <p>If you do not need additional metadata, keep the field empty.</p>
      description: Specifies a JDBC data store to crawl.
    CronExpression:
      type: string
  parameters:
    X-Amz-SignedHeaders:
      name: X-Amz-SignedHeaders
      in: header
      schema:
        type: string
      required: false
    X-Amz-Signature:
      name: X-Amz-Signature
      in: header
      schema:
        type: string
      required: false
    X-Amz-Security-Token:
      name: X-Amz-Security-Token
      in: header
      schema:
        type: string
      required: false
    X-Amz-Content-Sha256:
      name: X-Amz-Content-Sha256
      in: header
      schema:
        type: string
      required: false
    X-Amz-Date:
      name: X-Amz-Date
      in: header
      schema:
        type: string
      required: false
    X-Amz-Credential:
      name: X-Amz-Credential
      in: header
      schema:
        type: string
      required: false
    X-Amz-Algorithm:
      name: X-Amz-Algorithm
      in: header
      schema:
        type: string
      required: false
  securitySchemes:
    hmac:
      type: apiKey
      name: Authorization
      in: header
      description: Amazon Signature authorization v4
      x-amazon-apigateway-authtype: awsSigv4
externalDocs:
  description: Amazon Web Services documentation
  url: https://docs.aws.amazon.com/glue/
x-hasEquivalentPaths: true