Amazon Comprehend #X Amz Target=Comprehend 20171127.StartPiiEntitiesDetectionJob API

openapi: 3.0.0
info:
  version: '2017-11-27'
  x-release: v4
  title: 'Amazon Comprehend #X Amz Target=Comprehend 20171127.BatchDetectDominantLanguage #X Amz Target=Comprehend 20171127.BatchDetectDominantLanguage #X Amz Target=Comprehend 20171127.StartPiiEntitiesDetectionJob API'
  description: Amazon Comprehend is an Amazon Web Services service for gaining insight into the content of documents. Use these actions to determine the topics contained in your documents, the topics they discuss, the predominant sentiment expressed in them, the predominant language used, and more.
  x-logo:
    url: https://twitter.com/awscloud/profile_image?size=original
    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: comprehend
  x-aws-signingName: comprehend
  x-origin:
  - contentType: application/json
    url: https://raw.githubusercontent.com/aws/aws-sdk-js/master/apis/comprehend-2017-11-27.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://comprehend.{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 Amazon Comprehend multi-region endpoint
- url: https://comprehend.{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 Amazon Comprehend multi-region endpoint
- url: http://comprehend.{region}.amazonaws.com.cn
  variables:
    region:
      description: The AWS region
      enum:
      - cn-north-1
      - cn-northwest-1
      default: cn-north-1
  description: The Amazon Comprehend endpoint for China (Beijing) and China (Ningxia)
- url: https://comprehend.{region}.amazonaws.com.cn
  variables:
    region:
      description: The AWS region
      enum:
      - cn-north-1
      - cn-northwest-1
      default: cn-north-1
  description: The Amazon Comprehend endpoint for China (Beijing) and China (Ningxia)
security:
- hmac: []
tags:
- name: '#X Amz Target=Comprehend 20171127.StartPiiEntitiesDetectionJob'
paths:
  /#X-Amz-Target=Comprehend_20171127.StartPiiEntitiesDetectionJob:
    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: StartPiiEntitiesDetectionJob
      description: Starts an asynchronous PII entity detection job for a collection of documents.
      responses:
        '200':
          description: Success
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/StartPiiEntitiesDetectionJobResponse'
              examples:
                StartPiiEntitiesDetectionJob200Example:
                  summary: Default StartPiiEntitiesDetectionJob 200
                  x-microcks-default: true
                  value:
                    JobId: example
                    JobArn: example
                    JobStatus: example
        '480':
          description: InvalidRequestException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InvalidRequestException'
              examples:
                StartPiiEntitiesDetectionJob480Example:
                  summary: Default StartPiiEntitiesDetectionJob 480
                  x-microcks-default: true
                  value: example
        '481':
          description: TooManyRequestsException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TooManyRequestsException'
              examples:
                StartPiiEntitiesDetectionJob481Example:
                  summary: Default StartPiiEntitiesDetectionJob 481
                  x-microcks-default: true
                  value: example
        '482':
          description: KmsKeyValidationException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/KmsKeyValidationException'
              examples:
                StartPiiEntitiesDetectionJob482Example:
                  summary: Default StartPiiEntitiesDetectionJob 482
                  x-microcks-default: true
                  value: example
        '483':
          description: TooManyTagsException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/TooManyTagsException'
              examples:
                StartPiiEntitiesDetectionJob483Example:
                  summary: Default StartPiiEntitiesDetectionJob 483
                  x-microcks-default: true
                  value: example
        '484':
          description: ResourceInUseException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ResourceInUseException'
              examples:
                StartPiiEntitiesDetectionJob484Example:
                  summary: Default StartPiiEntitiesDetectionJob 484
                  x-microcks-default: true
                  value: example
        '485':
          description: InternalServerException
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/InternalServerException'
              examples:
                StartPiiEntitiesDetectionJob485Example:
                  summary: Default StartPiiEntitiesDetectionJob 485
                  x-microcks-default: true
                  value: example
      requestBody:
        required: true
        content:
          application/json:
            schema:
              $ref: '#/components/schemas/StartPiiEntitiesDetectionJobRequest'
      parameters:
      - name: X-Amz-Target
        in: header
        required: true
        schema:
          type: string
          enum:
          - Comprehend_20171127.StartPiiEntitiesDetectionJob
      summary: Amazon Comprehend Start Pii Entities Detection Job
      x-microcks-operation:
        delay: 0
        dispatcher: FALLBACK
      tags:
      - '#X Amz Target=Comprehend 20171127.StartPiiEntitiesDetectionJob'
components:
  schemas:
    IamRoleArn:
      type: string
      pattern: arn:aws(-[^:]+)?:iam::[0-9]{12}:role/.+
      minLength: 20
      maxLength: 2048
    LanguageCode:
      type: string
      enum:
      - en
      - es
      - fr
      - de
      - it
      - pt
      - ar
      - hi
      - ja
      - ko
      - zh
      - zh-TW
    ClientRequestTokenString:
      type: string
      pattern: ^[a-zA-Z0-9-]+$
      minLength: 1
      maxLength: 64
    DocumentReadMode:
      type: string
      enum:
      - SERVICE_DEFAULT
      - FORCE_DOCUMENT_READ_ACTION
    TooManyTagsException: {}
    PiiEntityType:
      type: string
      enum:
      - BANK_ACCOUNT_NUMBER
      - BANK_ROUTING
      - CREDIT_DEBIT_NUMBER
      - CREDIT_DEBIT_CVV
      - CREDIT_DEBIT_EXPIRY
      - PIN
      - EMAIL
      - ADDRESS
      - NAME
      - PHONE
      - SSN
      - DATE_TIME
      - PASSPORT_NUMBER
      - DRIVER_ID
      - URL
      - AGE
      - USERNAME
      - PASSWORD
      - AWS_ACCESS_KEY
      - AWS_SECRET_KEY
      - IP_ADDRESS
      - MAC_ADDRESS
      - ALL
      - LICENSE_PLATE
      - VEHICLE_IDENTIFICATION_NUMBER
      - UK_NATIONAL_INSURANCE_NUMBER
      - CA_SOCIAL_INSURANCE_NUMBER
      - US_INDIVIDUAL_TAX_IDENTIFICATION_NUMBER
      - UK_UNIQUE_TAXPAYER_REFERENCE_NUMBER
      - IN_PERMANENT_ACCOUNT_NUMBER
      - IN_NREGA
      - INTERNATIONAL_BANK_ACCOUNT_NUMBER
      - SWIFT_CODE
      - UK_NATIONAL_HEALTH_SERVICE_NUMBER
      - CA_HEALTH_NUMBER
      - IN_AADHAAR
      - IN_VOTER_NUMBER
    JobStatus:
      type: string
      enum:
      - SUBMITTED
      - IN_PROGRESS
      - COMPLETED
      - FAILED
      - STOP_REQUESTED
      - STOPPED
    KmsKeyId:
      type: string
      pattern: ^\p{ASCII}+$
      maxLength: 2048
    S3Uri:
      type: string
      pattern: s3://[a-z0-9][\.\-a-z0-9]{1,61}[a-z0-9](/.*)?
      maxLength: 1024
    DocumentReaderConfig:
      type: object
      required:
      - DocumentReadAction
      properties:
        DocumentReadAction:
          allOf:
          - $ref: '#/components/schemas/DocumentReadAction'
          - description: <p>This field defines the Amazon Textract API operation that Amazon Comprehend uses to extract text from PDF files and image files. Enter one of the following values:</p> <ul> <li> <p> <code>TEXTRACT_DETECT_DOCUMENT_TEXT</code> - The Amazon Comprehend service uses the <code>DetectDocumentText</code> API operation. </p> </li> <li> <p> <code>TEXTRACT_ANALYZE_DOCUMENT</code> - The Amazon Comprehend service uses the <code>AnalyzeDocument</code> API operation. </p> </li> </ul>
        DocumentReadMode:
          allOf:
          - $ref: '#/components/schemas/DocumentReadMode'
          - description: <p>Determines the text extraction actions for PDF files. Enter one of the following values:</p> <ul> <li> <p> <code>SERVICE_DEFAULT</code> - use the Amazon Comprehend service defaults for PDF files.</p> </li> <li> <p> <code>FORCE_DOCUMENT_READ_ACTION</code> - Amazon Comprehend uses the Textract API specified by DocumentReadAction for all PDF files, including digital PDF files. </p> </li> </ul>
        FeatureTypes:
          allOf:
          - $ref: '#/components/schemas/ListOfDocumentReadFeatureTypes'
          - description: <p>Specifies the type of Amazon Textract features to apply. If you chose <code>TEXTRACT_ANALYZE_DOCUMENT</code> as the read action, you must specify one or both of the following values:</p> <ul> <li> <p> <code>TABLES</code> - Returns information about any tables that are detected in the input document. </p> </li> <li> <p> <code>FORMS</code> - Returns information and the data from any forms that are detected in the input document. </p> </li> </ul>
      description: '<p>Provides configuration parameters to override the default actions for extracting text from PDF documents and image files. </p> <p> By default, Amazon Comprehend performs the following actions to extract text from files, based on the input file type: </p> <ul> <li> <p> <b>Word files</b> - Amazon Comprehend parser extracts the text. </p> </li> <li> <p> <b>Digital PDF files</b> - Amazon Comprehend parser extracts the text. </p> </li> <li> <p> <b>Image files and scanned PDF files</b> - Amazon Comprehend uses the Amazon Textract <code>DetectDocumentText</code> API to extract the text. </p> </li> </ul> <p> <code>DocumentReaderConfig</code> does not apply to plain text files or Word files.</p> <p> For image files and PDF documents, you can override these default actions using the fields listed below. For more information, see <a href="https://docs.aws.amazon.com/comprehend/latest/dg/idp-set-textract-options.html"> Setting text extraction options</a> in the Comprehend Developer Guide. </p>'
    InputFormat:
      type: string
      enum:
      - ONE_DOC_PER_FILE
      - ONE_DOC_PER_LINE
    JobId:
      type: string
      pattern: ^([\p{L}\p{Z}\p{N}_.:/=+\-%@]*)$
      minLength: 1
      maxLength: 32
    ListOfPiiEntityTypes:
      type: array
      items:
        $ref: '#/components/schemas/PiiEntityType'
    OutputDataConfig:
      type: object
      required:
      - S3Uri
      properties:
        S3Uri:
          allOf:
          - $ref: '#/components/schemas/S3Uri'
          - description: <p>When you use the <code>OutputDataConfig</code> object with asynchronous operations, you specify the Amazon S3 location where you want to write the output data. The URI must be in the same Region as the API endpoint that you are calling. The location is used as the prefix for the actual location of the output file.</p> <p>When the topic detection job is finished, the service creates an output file in a directory specific to the job. The <code>S3Uri</code> field contains the location of the output file, called <code>output.tar.gz</code>. It is a compressed archive that contains the ouput of the operation.</p> <p> For a PII entity detection job, the output file is plain text, not a compressed archive. The output file name is the same as the input file, with <code>.out</code> appended at the end. </p>
        KmsKeyId:
          allOf:
          - $ref: '#/components/schemas/KmsKeyId'
          - description: '<p>ID for the Amazon Web Services Key Management Service (KMS) key that Amazon Comprehend uses to encrypt the output results from an analysis job. The KmsKeyId can be one of the following formats:</p> <ul> <li> <p>KMS Key ID: <code>"1234abcd-12ab-34cd-56ef-1234567890ab"</code> </p> </li> <li> <p>Amazon Resource Name (ARN) of a KMS Key: <code>"arn:aws:kms:us-west-2:111122223333:key/1234abcd-12ab-34cd-56ef-1234567890ab"</code> </p> </li> <li> <p>KMS Key Alias: <code>"alias/ExampleAlias"</code> </p> </li> <li> <p>ARN of a KMS Key Alias: <code>"arn:aws:kms:us-west-2:111122223333:alias/ExampleAlias"</code> </p> </li> </ul>'
      description: <p>Provides configuration parameters for the output of inference jobs.</p> <p/>
    JobName:
      type: string
      pattern: ^([\p{L}\p{Z}\p{N}_.:/=+\-%@]*)$
      minLength: 1
      maxLength: 256
    InvalidRequestException: {}
    DocumentReadFeatureTypes:
      type: string
      enum:
      - TABLES
      - FORMS
      description: <p>Specifies the type of Amazon Textract features to apply. If you chose <code>TEXTRACT_ANALYZE_DOCUMENT</code> as the read action, you must specify one or both of the following values:</p> <ul> <li> <p> <code>TABLES</code> - Returns additional information about any tables that are detected in the input document. </p> </li> <li> <p> <code>FORMS</code> - Returns additional information about any forms that are detected in the input document. </p> </li> </ul>
    StartPiiEntitiesDetectionJobRequest:
      type: object
      required:
      - InputDataConfig
      - OutputDataConfig
      - Mode
      - DataAccessRoleArn
      - LanguageCode
      title: StartPiiEntitiesDetectionJobRequest
      properties:
        InputDataConfig:
          allOf:
          - $ref: '#/components/schemas/InputDataConfig'
          - description: The input properties for a PII entities detection job.
        OutputDataConfig:
          allOf:
          - $ref: '#/components/schemas/OutputDataConfig'
          - description: Provides configuration parameters for the output of PII entity detection jobs.
        Mode:
          allOf:
          - $ref: '#/components/schemas/PiiEntitiesDetectionMode'
          - description: Specifies whether the output provides the locations (offsets) of PII entities or a file in which PII entities are redacted.
        RedactionConfig:
          allOf:
          - $ref: '#/components/schemas/RedactionConfig'
          - description: <p>Provides configuration parameters for PII entity redaction.</p> <p>This parameter is required if you set the <code>Mode</code> parameter to <code>ONLY_REDACTION</code>. In that case, you must provide a <code>RedactionConfig</code> definition that includes the <code>PiiEntityTypes</code> parameter.</p>
        DataAccessRoleArn:
          allOf:
          - $ref: '#/components/schemas/IamRoleArn'
          - description: The Amazon Resource Name (ARN) of the IAM role that grants Amazon Comprehend read access to your input data.
        JobName:
          allOf:
          - $ref: '#/components/schemas/JobName'
          - description: The identifier of the job.
        LanguageCode:
          allOf:
          - $ref: '#/components/schemas/LanguageCode'
          - description: The language of the input documents. Currently, English is the only valid language.
        ClientRequestToken:
          allOf:
          - $ref: '#/components/schemas/ClientRequestTokenString'
          - description: A unique identifier for the request. If you don't set the client request token, Amazon Comprehend generates one.
        Tags:
          allOf:
          - $ref: '#/components/schemas/TagList'
          - description: Tags to associate with the PII entities detection job. A tag is a key-value pair that adds metadata to a resource used by Amazon Comprehend. For example, a tag with "Sales" as the key might be added to a resource to indicate its use by the sales department.
    PiiEntitiesDetectionMode:
      type: string
      enum:
      - ONLY_REDACTION
      - ONLY_OFFSETS
    ResourceInUseException: {}
    TagKey:
      type: string
      minLength: 1
      maxLength: 128
    MaskCharacter:
      type: string
      pattern: '[!@#$%&*]'
      minLength: 1
      maxLength: 1
    InputDataConfig:
      type: object
      required:
      - S3Uri
      properties:
        S3Uri:
          allOf:
          - $ref: '#/components/schemas/S3Uri'
          - description: <p>The Amazon S3 URI for the input data. The URI must be in same Region as the API endpoint that you are calling. The URI can point to a single input file or it can provide the prefix for a collection of data files. </p> <p>For example, if you use the URI <code>S3://bucketName/prefix</code>, if the prefix is a single file, Amazon Comprehend uses that file as input. If more than one file begins with the prefix, Amazon Comprehend uses all of them as input.</p>
        InputFormat:
          allOf:
          - $ref: '#/components/schemas/InputFormat'
          - description: <p>Specifies how the text in an input file should be processed:</p> <ul> <li> <p> <code>ONE_DOC_PER_FILE</code> - Each file is considered a separate document. Use this option when you are processing large documents, such as newspaper articles or scientific papers.</p> </li> <li> <p> <code>ONE_DOC_PER_LINE</code> - Each line in a file is considered a separate document. Use this option when you are processing many short documents, such as text messages.</p> </li> </ul>
        DocumentReaderConfig:
          allOf:
          - $ref: '#/components/schemas/DocumentReaderConfig'
          - description: Provides configuration parameters to override the default actions for extracting text from PDF documents and image files.
      description: The input properties for an inference job. The document reader config field applies only to non-text inputs for custom analysis.
    ListOfDocumentReadFeatureTypes:
      type: array
      items:
        $ref: '#/components/schemas/DocumentReadFeatureTypes'
      minItems: 1
      maxItems: 2
    StartPiiEntitiesDetectionJobResponse:
      type: object
      properties:
        JobId:
          allOf:
          - $ref: '#/components/schemas/JobId'
          - description: The identifier generated for the job.
        JobArn:
          allOf:
          - $ref: '#/components/schemas/ComprehendArn'
          - description: <p>The Amazon Resource Name (ARN) of the PII entity detection job. It is a unique, fully qualified identifier for the job. It includes the Amazon Web Services account, Amazon Web Services Region, and the job ID. The format of the ARN is as follows:</p> <p> <code>arn:&lt;partition&gt;:comprehend:&lt;region&gt;:&lt;account-id&gt;:pii-entities-detection-job/&lt;job-id&gt;</code> </p> <p>The following is an example job ARN:</p> <p> <code>arn:aws:comprehend:us-west-2:111122223333:pii-entities-detection-job/1234abcd12ab34cd56ef1234567890ab</code> </p>
        JobStatus:
          allOf:
          - $ref: '#/components/schemas/JobStatus'
          - description: The status of the job.
    TooManyRequestsException: {}
    RedactionConfig:
      type: object
      properties:
        PiiEntityTypes:
          allOf:
          - $ref: '#/components/schemas/ListOfPiiEntityTypes'
          - description: An array of the types of PII entities that Amazon Comprehend detects in the input text for your request.
        MaskMode:
          allOf:
          - $ref: '#/components/schemas/PiiEntitiesDetectionMaskMode'
          - description: Specifies whether the PII entity is redacted with the mask character or the entity type.
        MaskCharacter:
          allOf:
          - $ref: '#/components/schemas/MaskCharacter'
          - description: A character that replaces each character in the redacted PII entity.
      description: Provides configuration parameters for PII entity redaction.
    TagValue:
      type: string
      minLength: 0
      maxLength: 256
    InternalServerException: {}
    DocumentReadAction:
      type: string
      enum:
      - TEXTRACT_DETECT_DOCUMENT_TEXT
      - TEXTRACT_ANALYZE_DOCUMENT
    KmsKeyValidationException: {}
    ComprehendArn:
      type: string
      pattern: arn:aws(-[^:]+)?:comprehend:[a-zA-Z0-9-]*:[0-9]{12}:[a-zA-Z0-9-]{1,64}/[a-zA-Z0-9](-*[a-zA-Z0-9])*((/dataset/[a-zA-Z0-9](-*[a-zA-Z0-9])*)|(/version/[a-zA-Z0-9](-*[a-zA-Z0-9])*))?
      maxLength: 256
    PiiEntitiesDetectionMaskMode:
      type: string
      enum:
      - MASK
      - REPLACE_WITH_PII_ENTITY_TYPE
    Tag:
      type: object
      required:
      - Key
      properties:
        Key:
          allOf:
          - $ref: '#/components/schemas/TagKey'
          - description: 'The initial part of a key-value pair that forms a tag associated with a given resource. For instance, if you want to show which resources are used by which departments, you might use “Department” as the key portion of the pair, with multiple possible values such as “sales,” “legal,” and “administration.” '
        Value:
          allOf:
          - $ref: '#/components/schemas/TagValue'
          - description: ' The second part of a key-value pair that forms a tag associated with a given resource. For instance, if you want to show which resources are used by which departments, you might use “Department” as the initial (key) portion of the pair, with a value of “sales” to indicate the sales department. '
      description: 'A key-value pair that adds as a metadata to a resource used by Amazon Comprehend. For example, a tag with the key-value pair ‘Department’:’Sales’ might be added to a resource to indicate its use by a particular department. '
    TagList:
      type: array
      items:
        $ref: '#/components/schemas/Tag'
  parameters:
    X-Amz-Date:
      name: X-Amz-Date
      in: header
      schema:
        type: string
      required: false
    X-Amz-SignedHeaders:
      name: X-Amz-SignedHeaders
      in: header
      schema:
        type: string
      required: false
    X-Amz-Credential:
      name: X-Amz-Credential
      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-Algorithm:
      name: X-Amz-Algorithm
      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
  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/comprehend/
x-hasEquivalentPaths: true