| <html><body> | |
| <style> | |
| body, h1, h2, h3, div, span, p, pre, a { | |
| margin: 0; | |
| padding: 0; | |
| border: 0; | |
| font-weight: inherit; | |
| font-style: inherit; | |
| font-size: 100%; | |
| font-family: inherit; | |
| vertical-align: baseline; | |
| } | |
| body { | |
| font-size: 13px; | |
| padding: 1em; | |
| } | |
| h1 { | |
| font-size: 26px; | |
| margin-bottom: 1em; | |
| } | |
| h2 { | |
| font-size: 24px; | |
| margin-bottom: 1em; | |
| } | |
| h3 { | |
| font-size: 20px; | |
| margin-bottom: 1em; | |
| margin-top: 1em; | |
| } | |
| pre, code { | |
| line-height: 1.5; | |
| font-family: Monaco, 'DejaVu Sans Mono', 'Bitstream Vera Sans Mono', 'Lucida Console', monospace; | |
| } | |
| pre { | |
| margin-top: 0.5em; | |
| } | |
| h1, h2, h3, p { | |
| font-family: Arial, sans serif; | |
| } | |
| h1, h2, h3 { | |
| border-bottom: solid #CCC 1px; | |
| } | |
| .toc_element { | |
| margin-top: 0.5em; | |
| } | |
| .firstline { | |
| margin-left: 2 em; | |
| } | |
| .method { | |
| margin-top: 1em; | |
| border: solid 1px #CCC; | |
| padding: 1em; | |
| background: #EEE; | |
| } | |
| .details { | |
| font-weight: bold; | |
| font-size: 14px; | |
| } | |
| </style> | |
| <h1><a href="documentai_v1beta2.html">Cloud Document AI API</a> . <a href="documentai_v1beta2.projects.html">projects</a> . <a href="documentai_v1beta2.projects.documents.html">documents</a></h1> | |
| <h2>Instance Methods</h2> | |
| <p class="toc_element"> | |
| <code><a href="#batchProcess">batchProcess(parent, body=None, x__xgafv=None)</a></code></p> | |
| <p class="firstline">LRO endpoint to batch process many documents. The output is written</p> | |
| <p class="toc_element"> | |
| <code><a href="#process">process(parent, body=None, x__xgafv=None)</a></code></p> | |
| <p class="firstline">Processes a single document.</p> | |
| <h3>Method Details</h3> | |
| <div class="method"> | |
| <code class="details" id="batchProcess">batchProcess(parent, body=None, x__xgafv=None)</code> | |
| <pre>LRO endpoint to batch process many documents. The output is written | |
| to Cloud Storage as JSON in the [Document] format. | |
| Args: | |
| parent: string, Target project and location to make a call. | |
| Format: `projects/{project-id}/locations/{location-id}`. | |
| If no location is specified, a region will be chosen automatically. (required) | |
| body: object, The request body. | |
| The object takes the form of: | |
| { # Request to batch process documents as an asynchronous operation. The output | |
| # is written to Cloud Storage as JSON in the [Document] format. | |
| "requests": [ # Required. Individual requests for each document. | |
| { # Request to process one document. | |
| "ocrParams": { # Parameters to control Optical Character Recognition (OCR) behavior. # Controls OCR behavior. If not specified, the system will decide reasonable | |
| # defaults. | |
| "languageHints": [ # List of languages to use for OCR. In most cases, an empty value | |
| # yields the best results since it enables automatic language detection. For | |
| # languages based on the Latin alphabet, setting `language_hints` is not | |
| # needed. In rare cases, when the language of the text in the image is known, | |
| # setting a hint will help get better results (although it will be a | |
| # significant hindrance if the hint is wrong). Document processing returns an | |
| # error if one or more of the specified languages is not one of the | |
| # supported languages. | |
| "A String", | |
| ], | |
| }, | |
| "tableExtractionParams": { # Parameters to control table extraction behavior. # Controls table extraction behavior. If not specified, the system will | |
| # decide reasonable defaults. | |
| "tableBoundHints": [ # Optional. Table bounding box hints that can be provided to complex cases | |
| # which our algorithm cannot locate the table(s) in. | |
| { # A hint for a table bounding box on the page for table parsing. | |
| "pageNumber": 42, # Optional. Page number for multi-paged inputs this hint applies to. If not | |
| # provided, this hint will apply to all pages by default. This value is | |
| # 1-based. | |
| "boundingBox": { # A bounding polygon for the detected image annotation. # Bounding box hint for a table on this page. The coordinates must be | |
| # normalized to [0,1] and the bounding box must be an axis-aligned rectangle. | |
| "normalizedVertices": [ # The bounding polygon normalized vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the normalized vertex coordinates are relative to the original image | |
| # and range from 0 to 1. | |
| "x": 3.14, # X coordinate. | |
| "y": 3.14, # Y coordinate. | |
| }, | |
| ], | |
| "vertices": [ # The bounding polygon vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the vertex coordinates are in the same scale as the original image. | |
| "x": 42, # X coordinate. | |
| "y": 42, # Y coordinate. | |
| }, | |
| ], | |
| }, | |
| }, | |
| ], | |
| "headerHints": [ # Optional. Reserved for future use. | |
| "A String", | |
| ], | |
| "modelVersion": "A String", # Model version of the table extraction system. Default is "builtin/stable". | |
| # Specify "builtin/latest" for the latest model. | |
| "enabled": True or False, # Whether to enable table extraction. | |
| }, | |
| "automlParams": { # Parameters to control AutoML model prediction behavior. # Controls AutoML model prediction behavior. AutoMlParams cannot be used | |
| # together with other Params. | |
| "model": "A String", # Resource name of the AutoML model. | |
| # | |
| # Format: `projects/{project-id}/locations/{location-id}/models/{model-id}`. | |
| }, | |
| "inputConfig": { # The desired input location and metadata. # Required. Information about the input file. | |
| "gcsSource": { # The Google Cloud Storage location where the input file will be read from. # The Google Cloud Storage location to read the input from. This must be a | |
| # single file. | |
| "uri": "A String", | |
| }, | |
| "contents": "A String", # Content in bytes, represented as a stream of bytes. | |
| # Note: As with all `bytes` fields, proto buffer messages use a pure binary | |
| # representation, whereas JSON representations use base64. | |
| # | |
| # This field only works for synchronous ProcessDocument method. | |
| "mimeType": "A String", # Required. Mimetype of the input. Current supported mimetypes are application/pdf, | |
| # image/tiff, and image/gif. | |
| # In addition, application/json type is supported for requests with | |
| # ProcessDocumentRequest.automl_params field set. The JSON file needs to | |
| # be in Document format. | |
| }, | |
| "formExtractionParams": { # Parameters to control form extraction behavior. # Controls form extraction behavior. If not specified, the system will | |
| # decide reasonable defaults. | |
| "modelVersion": "A String", # Model version of the form extraction system. Default is | |
| # "builtin/stable". Specify "builtin/latest" for the latest model. | |
| # For custom form models, specify: “custom/{model_name}". Model name | |
| # format is "bucket_name/path/to/modeldir" corresponding to | |
| # "gs://bucket_name/path/to/modeldir" where annotated examples are stored. | |
| "enabled": True or False, # Whether to enable form extraction. | |
| "keyValuePairHints": [ # Reserved for future use. | |
| { # Reserved for future use. | |
| "valueTypes": [ # Type of the value. This is case-insensitive, and could be one of: | |
| # ADDRESS, LOCATION, ORGANIZATION, PERSON, PHONE_NUMBER, | |
| # ID, NUMBER, EMAIL, PRICE, TERMS, DATE, NAME. Types not in this list will | |
| # be ignored. | |
| "A String", | |
| ], | |
| "key": "A String", # The key text for the hint. | |
| }, | |
| ], | |
| }, | |
| "documentType": "A String", # Specifies a known document type for deeper structure detection. Valid | |
| # values are currently "general" and "invoice". If not provided, "general"\ | |
| # is used as default. If any other value is given, the request is rejected. | |
| "parent": "A String", # Target project and location to make a call. | |
| # | |
| # Format: `projects/{project-id}/locations/{location-id}`. | |
| # | |
| # If no location is specified, a region will be chosen automatically. | |
| # This field is only populated when used in ProcessDocument method. | |
| "outputConfig": { # The desired output location and metadata. # The desired output location. This field is only needed in | |
| # BatchProcessDocumentsRequest. | |
| "pagesPerShard": 42, # The max number of pages to include into each output Document shard JSON on | |
| # Google Cloud Storage. | |
| # | |
| # The valid range is [1, 100]. If not specified, the default value is 20. | |
| # | |
| # For example, for one pdf file with 100 pages, 100 parsed pages will be | |
| # produced. If `pages_per_shard` = 20, then 5 Document shard JSON files each | |
| # containing 20 parsed pages will be written under the prefix | |
| # OutputConfig.gcs_destination.uri and suffix pages-x-to-y.json where | |
| # x and y are 1-indexed page numbers. | |
| # | |
| # Example GCS outputs with 157 pages and pages_per_shard = 50: | |
| # | |
| # <prefix>pages-001-to-050.json | |
| # <prefix>pages-051-to-100.json | |
| # <prefix>pages-101-to-150.json | |
| # <prefix>pages-151-to-157.json | |
| "gcsDestination": { # The Google Cloud Storage location where the output file will be written to. # The Google Cloud Storage location to write the output to. | |
| "uri": "A String", | |
| }, | |
| }, | |
| "entityExtractionParams": { # Parameters to control entity extraction behavior. # Controls entity extraction behavior. If not specified, the system will | |
| # decide reasonable defaults. | |
| "enabled": True or False, # Whether to enable entity extraction. | |
| "modelVersion": "A String", # Model version of the entity extraction. Default is | |
| # "builtin/stable". Specify "builtin/latest" for the latest model. | |
| }, | |
| }, | |
| ], | |
| } | |
| x__xgafv: string, V1 error format. | |
| Allowed values | |
| 1 - v1 error format | |
| 2 - v2 error format | |
| Returns: | |
| An object of the form: | |
| { # This resource represents a long-running operation that is the result of a | |
| # network API call. | |
| "metadata": { # Service-specific metadata associated with the operation. It typically | |
| # contains progress information and common metadata such as create time. | |
| # Some services might not provide such metadata. Any method that returns a | |
| # long-running operation should document the metadata type, if any. | |
| "a_key": "", # Properties of the object. Contains field @type with type URL. | |
| }, | |
| "name": "A String", # The server-assigned name, which is only unique within the same service that | |
| # originally returns it. If you use the default HTTP mapping, the | |
| # `name` should be a resource name ending with `operations/{unique_id}`. | |
| "error": { # The `Status` type defines a logical error model that is suitable for # The error result of the operation in case of failure or cancellation. | |
| # different programming environments, including REST APIs and RPC APIs. It is | |
| # used by [gRPC](https://github.com/grpc). Each `Status` message contains | |
| # three pieces of data: error code, error message, and error details. | |
| # | |
| # You can find out more about this error model and how to work with it in the | |
| # [API Design Guide](https://cloud.google.com/apis/design/errors). | |
| "message": "A String", # A developer-facing error message, which should be in English. Any | |
| # user-facing error message should be localized and sent in the | |
| # google.rpc.Status.details field, or localized by the client. | |
| "details": [ # A list of messages that carry the error details. There is a common set of | |
| # message types for APIs to use. | |
| { | |
| "a_key": "", # Properties of the object. Contains field @type with type URL. | |
| }, | |
| ], | |
| "code": 42, # The status code, which should be an enum value of google.rpc.Code. | |
| }, | |
| "response": { # The normal response of the operation in case of success. If the original | |
| # method returns no data on success, such as `Delete`, the response is | |
| # `google.protobuf.Empty`. If the original method is standard | |
| # `Get`/`Create`/`Update`, the response should be the resource. For other | |
| # methods, the response should have the type `XxxResponse`, where `Xxx` | |
| # is the original method name. For example, if the original method name | |
| # is `TakeSnapshot()`, the inferred response type is | |
| # `TakeSnapshotResponse`. | |
| "a_key": "", # Properties of the object. Contains field @type with type URL. | |
| }, | |
| "done": True or False, # If the value is `false`, it means the operation is still in progress. | |
| # If `true`, the operation is completed, and either `error` or `response` is | |
| # available. | |
| }</pre> | |
| </div> | |
| <div class="method"> | |
| <code class="details" id="process">process(parent, body=None, x__xgafv=None)</code> | |
| <pre>Processes a single document. | |
| Args: | |
| parent: string, Target project and location to make a call. | |
| Format: `projects/{project-id}/locations/{location-id}`. | |
| If no location is specified, a region will be chosen automatically. | |
| This field is only populated when used in ProcessDocument method. (required) | |
| body: object, The request body. | |
| The object takes the form of: | |
| { # Request to process one document. | |
| "ocrParams": { # Parameters to control Optical Character Recognition (OCR) behavior. # Controls OCR behavior. If not specified, the system will decide reasonable | |
| # defaults. | |
| "languageHints": [ # List of languages to use for OCR. In most cases, an empty value | |
| # yields the best results since it enables automatic language detection. For | |
| # languages based on the Latin alphabet, setting `language_hints` is not | |
| # needed. In rare cases, when the language of the text in the image is known, | |
| # setting a hint will help get better results (although it will be a | |
| # significant hindrance if the hint is wrong). Document processing returns an | |
| # error if one or more of the specified languages is not one of the | |
| # supported languages. | |
| "A String", | |
| ], | |
| }, | |
| "tableExtractionParams": { # Parameters to control table extraction behavior. # Controls table extraction behavior. If not specified, the system will | |
| # decide reasonable defaults. | |
| "tableBoundHints": [ # Optional. Table bounding box hints that can be provided to complex cases | |
| # which our algorithm cannot locate the table(s) in. | |
| { # A hint for a table bounding box on the page for table parsing. | |
| "pageNumber": 42, # Optional. Page number for multi-paged inputs this hint applies to. If not | |
| # provided, this hint will apply to all pages by default. This value is | |
| # 1-based. | |
| "boundingBox": { # A bounding polygon for the detected image annotation. # Bounding box hint for a table on this page. The coordinates must be | |
| # normalized to [0,1] and the bounding box must be an axis-aligned rectangle. | |
| "normalizedVertices": [ # The bounding polygon normalized vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the normalized vertex coordinates are relative to the original image | |
| # and range from 0 to 1. | |
| "x": 3.14, # X coordinate. | |
| "y": 3.14, # Y coordinate. | |
| }, | |
| ], | |
| "vertices": [ # The bounding polygon vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the vertex coordinates are in the same scale as the original image. | |
| "x": 42, # X coordinate. | |
| "y": 42, # Y coordinate. | |
| }, | |
| ], | |
| }, | |
| }, | |
| ], | |
| "headerHints": [ # Optional. Reserved for future use. | |
| "A String", | |
| ], | |
| "modelVersion": "A String", # Model version of the table extraction system. Default is "builtin/stable". | |
| # Specify "builtin/latest" for the latest model. | |
| "enabled": True or False, # Whether to enable table extraction. | |
| }, | |
| "automlParams": { # Parameters to control AutoML model prediction behavior. # Controls AutoML model prediction behavior. AutoMlParams cannot be used | |
| # together with other Params. | |
| "model": "A String", # Resource name of the AutoML model. | |
| # | |
| # Format: `projects/{project-id}/locations/{location-id}/models/{model-id}`. | |
| }, | |
| "inputConfig": { # The desired input location and metadata. # Required. Information about the input file. | |
| "gcsSource": { # The Google Cloud Storage location where the input file will be read from. # The Google Cloud Storage location to read the input from. This must be a | |
| # single file. | |
| "uri": "A String", | |
| }, | |
| "contents": "A String", # Content in bytes, represented as a stream of bytes. | |
| # Note: As with all `bytes` fields, proto buffer messages use a pure binary | |
| # representation, whereas JSON representations use base64. | |
| # | |
| # This field only works for synchronous ProcessDocument method. | |
| "mimeType": "A String", # Required. Mimetype of the input. Current supported mimetypes are application/pdf, | |
| # image/tiff, and image/gif. | |
| # In addition, application/json type is supported for requests with | |
| # ProcessDocumentRequest.automl_params field set. The JSON file needs to | |
| # be in Document format. | |
| }, | |
| "formExtractionParams": { # Parameters to control form extraction behavior. # Controls form extraction behavior. If not specified, the system will | |
| # decide reasonable defaults. | |
| "modelVersion": "A String", # Model version of the form extraction system. Default is | |
| # "builtin/stable". Specify "builtin/latest" for the latest model. | |
| # For custom form models, specify: “custom/{model_name}". Model name | |
| # format is "bucket_name/path/to/modeldir" corresponding to | |
| # "gs://bucket_name/path/to/modeldir" where annotated examples are stored. | |
| "enabled": True or False, # Whether to enable form extraction. | |
| "keyValuePairHints": [ # Reserved for future use. | |
| { # Reserved for future use. | |
| "valueTypes": [ # Type of the value. This is case-insensitive, and could be one of: | |
| # ADDRESS, LOCATION, ORGANIZATION, PERSON, PHONE_NUMBER, | |
| # ID, NUMBER, EMAIL, PRICE, TERMS, DATE, NAME. Types not in this list will | |
| # be ignored. | |
| "A String", | |
| ], | |
| "key": "A String", # The key text for the hint. | |
| }, | |
| ], | |
| }, | |
| "documentType": "A String", # Specifies a known document type for deeper structure detection. Valid | |
| # values are currently "general" and "invoice". If not provided, "general"\ | |
| # is used as default. If any other value is given, the request is rejected. | |
| "parent": "A String", # Target project and location to make a call. | |
| # | |
| # Format: `projects/{project-id}/locations/{location-id}`. | |
| # | |
| # If no location is specified, a region will be chosen automatically. | |
| # This field is only populated when used in ProcessDocument method. | |
| "outputConfig": { # The desired output location and metadata. # The desired output location. This field is only needed in | |
| # BatchProcessDocumentsRequest. | |
| "pagesPerShard": 42, # The max number of pages to include into each output Document shard JSON on | |
| # Google Cloud Storage. | |
| # | |
| # The valid range is [1, 100]. If not specified, the default value is 20. | |
| # | |
| # For example, for one pdf file with 100 pages, 100 parsed pages will be | |
| # produced. If `pages_per_shard` = 20, then 5 Document shard JSON files each | |
| # containing 20 parsed pages will be written under the prefix | |
| # OutputConfig.gcs_destination.uri and suffix pages-x-to-y.json where | |
| # x and y are 1-indexed page numbers. | |
| # | |
| # Example GCS outputs with 157 pages and pages_per_shard = 50: | |
| # | |
| # <prefix>pages-001-to-050.json | |
| # <prefix>pages-051-to-100.json | |
| # <prefix>pages-101-to-150.json | |
| # <prefix>pages-151-to-157.json | |
| "gcsDestination": { # The Google Cloud Storage location where the output file will be written to. # The Google Cloud Storage location to write the output to. | |
| "uri": "A String", | |
| }, | |
| }, | |
| "entityExtractionParams": { # Parameters to control entity extraction behavior. # Controls entity extraction behavior. If not specified, the system will | |
| # decide reasonable defaults. | |
| "enabled": True or False, # Whether to enable entity extraction. | |
| "modelVersion": "A String", # Model version of the entity extraction. Default is | |
| # "builtin/stable". Specify "builtin/latest" for the latest model. | |
| }, | |
| } | |
| x__xgafv: string, V1 error format. | |
| Allowed values | |
| 1 - v1 error format | |
| 2 - v2 error format | |
| Returns: | |
| An object of the form: | |
| { # Document represents the canonical document resource in Document Understanding | |
| # AI. | |
| # It is an interchange format that provides insights into documents and allows | |
| # for collaboration between users and Document Understanding AI to iterate and | |
| # optimize for quality. | |
| "content": "A String", # Inline document content, represented as a stream of bytes. | |
| # Note: As with all `bytes` fields, protobuffers use a pure binary | |
| # representation, whereas JSON representations use base64. | |
| "labels": [ # Labels for this document. | |
| { # Label attaches schema information and/or other metadata to segments within | |
| # a Document. Multiple Labels on a single field can denote either | |
| # different labels, different instances of the same label created at | |
| # different times, or some combination of both. | |
| "automlModel": "A String", # Label is generated AutoML model. This field stores the full resource | |
| # name of the AutoML model. | |
| # | |
| # Format: | |
| # `projects/{project-id}/locations/{location-id}/models/{model-id}` | |
| "confidence": 3.14, # Confidence score between 0 and 1 for label assignment. | |
| "name": "A String", # Name of the label. | |
| # | |
| # When the label is generated from AutoML Text Classification model, this | |
| # field represents the name of the category. | |
| }, | |
| ], | |
| "uri": "A String", # Currently supports Google Cloud Storage URI of the form | |
| # `gs://bucket_name/object_name`. Object versioning is not supported. | |
| # See [Google Cloud Storage Request | |
| # URIs](https://cloud.google.com/storage/docs/reference-uris) for more | |
| # info. | |
| "error": { # The `Status` type defines a logical error model that is suitable for # Any error that occurred while processing this document. | |
| # different programming environments, including REST APIs and RPC APIs. It is | |
| # used by [gRPC](https://github.com/grpc). Each `Status` message contains | |
| # three pieces of data: error code, error message, and error details. | |
| # | |
| # You can find out more about this error model and how to work with it in the | |
| # [API Design Guide](https://cloud.google.com/apis/design/errors). | |
| "message": "A String", # A developer-facing error message, which should be in English. Any | |
| # user-facing error message should be localized and sent in the | |
| # google.rpc.Status.details field, or localized by the client. | |
| "details": [ # A list of messages that carry the error details. There is a common set of | |
| # message types for APIs to use. | |
| { | |
| "a_key": "", # Properties of the object. Contains field @type with type URL. | |
| }, | |
| ], | |
| "code": 42, # The status code, which should be an enum value of google.rpc.Code. | |
| }, | |
| "pages": [ # Visual page layout for the Document. | |
| { # A page in a Document. | |
| "dimension": { # Dimension for the page. # Physical dimension of the page. | |
| "width": 3.14, # Page width. | |
| "height": 3.14, # Page height. | |
| "unit": "A String", # Dimension unit. | |
| }, | |
| "detectedLanguages": [ # A list of detected languages together with confidence. | |
| { # Detected language for a structural component. | |
| "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more | |
| # information, see | |
| # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. | |
| "confidence": 3.14, # Confidence of detected language. Range [0, 1]. | |
| }, | |
| ], | |
| "tables": [ # A list of visually detected tables on the page. | |
| { # A table representation similar to HTML table structure. | |
| "layout": { # Visual element describing a layout unit on a page. # Layout for Table. | |
| "orientation": "A String", # Detected orientation for the Layout. | |
| "boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout. | |
| "normalizedVertices": [ # The bounding polygon normalized vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the normalized vertex coordinates are relative to the original image | |
| # and range from 0 to 1. | |
| "x": 3.14, # X coordinate. | |
| "y": 3.14, # Y coordinate. | |
| }, | |
| ], | |
| "vertices": [ # The bounding polygon vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the vertex coordinates are in the same scale as the original image. | |
| "x": 42, # X coordinate. | |
| "y": 42, # Y coordinate. | |
| }, | |
| ], | |
| }, | |
| "confidence": 3.14, # Confidence of the current Layout within context of the object this | |
| # layout is for. e.g. confidence can be for a single token, a table, | |
| # a visual element, etc. depending on context. Range [0, 1]. | |
| "textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text. | |
| "textSegments": [ # The text segments from the Document.text. | |
| { # A text segment in the Document.text. The indices may be out of bounds | |
| # which indicate that the text extends into another document shard for | |
| # large sharded documents. See ShardInfo.text_offset | |
| "startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text. | |
| "endIndex": "A String", # TextSegment half open end UTF-8 char index in the | |
| # Document.text. | |
| }, | |
| ], | |
| }, | |
| }, | |
| "detectedLanguages": [ # A list of detected languages together with confidence. | |
| { # Detected language for a structural component. | |
| "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more | |
| # information, see | |
| # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. | |
| "confidence": 3.14, # Confidence of detected language. Range [0, 1]. | |
| }, | |
| ], | |
| "bodyRows": [ # Body rows of the table. | |
| { # A row of table cells. | |
| "cells": [ # Cells that make up this row. | |
| { # A cell representation inside the table. | |
| "detectedLanguages": [ # A list of detected languages together with confidence. | |
| { # Detected language for a structural component. | |
| "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more | |
| # information, see | |
| # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. | |
| "confidence": 3.14, # Confidence of detected language. Range [0, 1]. | |
| }, | |
| ], | |
| "rowSpan": 42, # How many rows this cell spans. | |
| "layout": { # Visual element describing a layout unit on a page. # Layout for TableCell. | |
| "orientation": "A String", # Detected orientation for the Layout. | |
| "boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout. | |
| "normalizedVertices": [ # The bounding polygon normalized vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the normalized vertex coordinates are relative to the original image | |
| # and range from 0 to 1. | |
| "x": 3.14, # X coordinate. | |
| "y": 3.14, # Y coordinate. | |
| }, | |
| ], | |
| "vertices": [ # The bounding polygon vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the vertex coordinates are in the same scale as the original image. | |
| "x": 42, # X coordinate. | |
| "y": 42, # Y coordinate. | |
| }, | |
| ], | |
| }, | |
| "confidence": 3.14, # Confidence of the current Layout within context of the object this | |
| # layout is for. e.g. confidence can be for a single token, a table, | |
| # a visual element, etc. depending on context. Range [0, 1]. | |
| "textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text. | |
| "textSegments": [ # The text segments from the Document.text. | |
| { # A text segment in the Document.text. The indices may be out of bounds | |
| # which indicate that the text extends into another document shard for | |
| # large sharded documents. See ShardInfo.text_offset | |
| "startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text. | |
| "endIndex": "A String", # TextSegment half open end UTF-8 char index in the | |
| # Document.text. | |
| }, | |
| ], | |
| }, | |
| }, | |
| "colSpan": 42, # How many columns this cell spans. | |
| }, | |
| ], | |
| }, | |
| ], | |
| "headerRows": [ # Header rows of the table. | |
| { # A row of table cells. | |
| "cells": [ # Cells that make up this row. | |
| { # A cell representation inside the table. | |
| "detectedLanguages": [ # A list of detected languages together with confidence. | |
| { # Detected language for a structural component. | |
| "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more | |
| # information, see | |
| # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. | |
| "confidence": 3.14, # Confidence of detected language. Range [0, 1]. | |
| }, | |
| ], | |
| "rowSpan": 42, # How many rows this cell spans. | |
| "layout": { # Visual element describing a layout unit on a page. # Layout for TableCell. | |
| "orientation": "A String", # Detected orientation for the Layout. | |
| "boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout. | |
| "normalizedVertices": [ # The bounding polygon normalized vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the normalized vertex coordinates are relative to the original image | |
| # and range from 0 to 1. | |
| "x": 3.14, # X coordinate. | |
| "y": 3.14, # Y coordinate. | |
| }, | |
| ], | |
| "vertices": [ # The bounding polygon vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the vertex coordinates are in the same scale as the original image. | |
| "x": 42, # X coordinate. | |
| "y": 42, # Y coordinate. | |
| }, | |
| ], | |
| }, | |
| "confidence": 3.14, # Confidence of the current Layout within context of the object this | |
| # layout is for. e.g. confidence can be for a single token, a table, | |
| # a visual element, etc. depending on context. Range [0, 1]. | |
| "textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text. | |
| "textSegments": [ # The text segments from the Document.text. | |
| { # A text segment in the Document.text. The indices may be out of bounds | |
| # which indicate that the text extends into another document shard for | |
| # large sharded documents. See ShardInfo.text_offset | |
| "startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text. | |
| "endIndex": "A String", # TextSegment half open end UTF-8 char index in the | |
| # Document.text. | |
| }, | |
| ], | |
| }, | |
| }, | |
| "colSpan": 42, # How many columns this cell spans. | |
| }, | |
| ], | |
| }, | |
| ], | |
| }, | |
| ], | |
| "layout": { # Visual element describing a layout unit on a page. # Layout for the page. | |
| "orientation": "A String", # Detected orientation for the Layout. | |
| "boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout. | |
| "normalizedVertices": [ # The bounding polygon normalized vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the normalized vertex coordinates are relative to the original image | |
| # and range from 0 to 1. | |
| "x": 3.14, # X coordinate. | |
| "y": 3.14, # Y coordinate. | |
| }, | |
| ], | |
| "vertices": [ # The bounding polygon vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the vertex coordinates are in the same scale as the original image. | |
| "x": 42, # X coordinate. | |
| "y": 42, # Y coordinate. | |
| }, | |
| ], | |
| }, | |
| "confidence": 3.14, # Confidence of the current Layout within context of the object this | |
| # layout is for. e.g. confidence can be for a single token, a table, | |
| # a visual element, etc. depending on context. Range [0, 1]. | |
| "textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text. | |
| "textSegments": [ # The text segments from the Document.text. | |
| { # A text segment in the Document.text. The indices may be out of bounds | |
| # which indicate that the text extends into another document shard for | |
| # large sharded documents. See ShardInfo.text_offset | |
| "startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text. | |
| "endIndex": "A String", # TextSegment half open end UTF-8 char index in the | |
| # Document.text. | |
| }, | |
| ], | |
| }, | |
| }, | |
| "lines": [ # A list of visually detected text lines on the page. | |
| # A collection of tokens that a human would perceive as a line. | |
| { # A collection of tokens that a human would perceive as a line. | |
| # Does not cross column boundaries, can be horizontal, vertical, etc. | |
| "layout": { # Visual element describing a layout unit on a page. # Layout for Line. | |
| "orientation": "A String", # Detected orientation for the Layout. | |
| "boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout. | |
| "normalizedVertices": [ # The bounding polygon normalized vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the normalized vertex coordinates are relative to the original image | |
| # and range from 0 to 1. | |
| "x": 3.14, # X coordinate. | |
| "y": 3.14, # Y coordinate. | |
| }, | |
| ], | |
| "vertices": [ # The bounding polygon vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the vertex coordinates are in the same scale as the original image. | |
| "x": 42, # X coordinate. | |
| "y": 42, # Y coordinate. | |
| }, | |
| ], | |
| }, | |
| "confidence": 3.14, # Confidence of the current Layout within context of the object this | |
| # layout is for. e.g. confidence can be for a single token, a table, | |
| # a visual element, etc. depending on context. Range [0, 1]. | |
| "textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text. | |
| "textSegments": [ # The text segments from the Document.text. | |
| { # A text segment in the Document.text. The indices may be out of bounds | |
| # which indicate that the text extends into another document shard for | |
| # large sharded documents. See ShardInfo.text_offset | |
| "startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text. | |
| "endIndex": "A String", # TextSegment half open end UTF-8 char index in the | |
| # Document.text. | |
| }, | |
| ], | |
| }, | |
| }, | |
| "detectedLanguages": [ # A list of detected languages together with confidence. | |
| { # Detected language for a structural component. | |
| "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more | |
| # information, see | |
| # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. | |
| "confidence": 3.14, # Confidence of detected language. Range [0, 1]. | |
| }, | |
| ], | |
| }, | |
| ], | |
| "paragraphs": [ # A list of visually detected text paragraphs on the page. | |
| # A collection of lines that a human would perceive as a paragraph. | |
| { # A collection of lines that a human would perceive as a paragraph. | |
| "detectedLanguages": [ # A list of detected languages together with confidence. | |
| { # Detected language for a structural component. | |
| "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more | |
| # information, see | |
| # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. | |
| "confidence": 3.14, # Confidence of detected language. Range [0, 1]. | |
| }, | |
| ], | |
| "layout": { # Visual element describing a layout unit on a page. # Layout for Paragraph. | |
| "orientation": "A String", # Detected orientation for the Layout. | |
| "boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout. | |
| "normalizedVertices": [ # The bounding polygon normalized vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the normalized vertex coordinates are relative to the original image | |
| # and range from 0 to 1. | |
| "x": 3.14, # X coordinate. | |
| "y": 3.14, # Y coordinate. | |
| }, | |
| ], | |
| "vertices": [ # The bounding polygon vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the vertex coordinates are in the same scale as the original image. | |
| "x": 42, # X coordinate. | |
| "y": 42, # Y coordinate. | |
| }, | |
| ], | |
| }, | |
| "confidence": 3.14, # Confidence of the current Layout within context of the object this | |
| # layout is for. e.g. confidence can be for a single token, a table, | |
| # a visual element, etc. depending on context. Range [0, 1]. | |
| "textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text. | |
| "textSegments": [ # The text segments from the Document.text. | |
| { # A text segment in the Document.text. The indices may be out of bounds | |
| # which indicate that the text extends into another document shard for | |
| # large sharded documents. See ShardInfo.text_offset | |
| "startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text. | |
| "endIndex": "A String", # TextSegment half open end UTF-8 char index in the | |
| # Document.text. | |
| }, | |
| ], | |
| }, | |
| }, | |
| }, | |
| ], | |
| "formFields": [ # A list of visually detected form fields on the page. | |
| { # A form field detected on the page. | |
| "valueType": "A String", # If the value is non-textual, this field represents the type. Current | |
| # valid values are: | |
| # - blank (this indicates the field_value is normal text) | |
| # - "unfilled_checkbox" | |
| # - "filled_checkbox" | |
| "fieldName": { # Visual element describing a layout unit on a page. # Layout for the FormField name. e.g. `Address`, `Email`, | |
| # `Grand total`, `Phone number`, etc. | |
| "orientation": "A String", # Detected orientation for the Layout. | |
| "boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout. | |
| "normalizedVertices": [ # The bounding polygon normalized vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the normalized vertex coordinates are relative to the original image | |
| # and range from 0 to 1. | |
| "x": 3.14, # X coordinate. | |
| "y": 3.14, # Y coordinate. | |
| }, | |
| ], | |
| "vertices": [ # The bounding polygon vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the vertex coordinates are in the same scale as the original image. | |
| "x": 42, # X coordinate. | |
| "y": 42, # Y coordinate. | |
| }, | |
| ], | |
| }, | |
| "confidence": 3.14, # Confidence of the current Layout within context of the object this | |
| # layout is for. e.g. confidence can be for a single token, a table, | |
| # a visual element, etc. depending on context. Range [0, 1]. | |
| "textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text. | |
| "textSegments": [ # The text segments from the Document.text. | |
| { # A text segment in the Document.text. The indices may be out of bounds | |
| # which indicate that the text extends into another document shard for | |
| # large sharded documents. See ShardInfo.text_offset | |
| "startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text. | |
| "endIndex": "A String", # TextSegment half open end UTF-8 char index in the | |
| # Document.text. | |
| }, | |
| ], | |
| }, | |
| }, | |
| "nameDetectedLanguages": [ # A list of detected languages for name together with confidence. | |
| { # Detected language for a structural component. | |
| "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more | |
| # information, see | |
| # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. | |
| "confidence": 3.14, # Confidence of detected language. Range [0, 1]. | |
| }, | |
| ], | |
| "valueDetectedLanguages": [ # A list of detected languages for value together with confidence. | |
| { # Detected language for a structural component. | |
| "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more | |
| # information, see | |
| # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. | |
| "confidence": 3.14, # Confidence of detected language. Range [0, 1]. | |
| }, | |
| ], | |
| "fieldValue": { # Visual element describing a layout unit on a page. # Layout for the FormField value. | |
| "orientation": "A String", # Detected orientation for the Layout. | |
| "boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout. | |
| "normalizedVertices": [ # The bounding polygon normalized vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the normalized vertex coordinates are relative to the original image | |
| # and range from 0 to 1. | |
| "x": 3.14, # X coordinate. | |
| "y": 3.14, # Y coordinate. | |
| }, | |
| ], | |
| "vertices": [ # The bounding polygon vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the vertex coordinates are in the same scale as the original image. | |
| "x": 42, # X coordinate. | |
| "y": 42, # Y coordinate. | |
| }, | |
| ], | |
| }, | |
| "confidence": 3.14, # Confidence of the current Layout within context of the object this | |
| # layout is for. e.g. confidence can be for a single token, a table, | |
| # a visual element, etc. depending on context. Range [0, 1]. | |
| "textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text. | |
| "textSegments": [ # The text segments from the Document.text. | |
| { # A text segment in the Document.text. The indices may be out of bounds | |
| # which indicate that the text extends into another document shard for | |
| # large sharded documents. See ShardInfo.text_offset | |
| "startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text. | |
| "endIndex": "A String", # TextSegment half open end UTF-8 char index in the | |
| # Document.text. | |
| }, | |
| ], | |
| }, | |
| }, | |
| }, | |
| ], | |
| "blocks": [ # A list of visually detected text blocks on the page. | |
| # A block has a set of lines (collected into paragraphs) that have a common | |
| # line-spacing and orientation. | |
| { # A block has a set of lines (collected into paragraphs) that have a | |
| # common line-spacing and orientation. | |
| "layout": { # Visual element describing a layout unit on a page. # Layout for Block. | |
| "orientation": "A String", # Detected orientation for the Layout. | |
| "boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout. | |
| "normalizedVertices": [ # The bounding polygon normalized vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the normalized vertex coordinates are relative to the original image | |
| # and range from 0 to 1. | |
| "x": 3.14, # X coordinate. | |
| "y": 3.14, # Y coordinate. | |
| }, | |
| ], | |
| "vertices": [ # The bounding polygon vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the vertex coordinates are in the same scale as the original image. | |
| "x": 42, # X coordinate. | |
| "y": 42, # Y coordinate. | |
| }, | |
| ], | |
| }, | |
| "confidence": 3.14, # Confidence of the current Layout within context of the object this | |
| # layout is for. e.g. confidence can be for a single token, a table, | |
| # a visual element, etc. depending on context. Range [0, 1]. | |
| "textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text. | |
| "textSegments": [ # The text segments from the Document.text. | |
| { # A text segment in the Document.text. The indices may be out of bounds | |
| # which indicate that the text extends into another document shard for | |
| # large sharded documents. See ShardInfo.text_offset | |
| "startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text. | |
| "endIndex": "A String", # TextSegment half open end UTF-8 char index in the | |
| # Document.text. | |
| }, | |
| ], | |
| }, | |
| }, | |
| "detectedLanguages": [ # A list of detected languages together with confidence. | |
| { # Detected language for a structural component. | |
| "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more | |
| # information, see | |
| # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. | |
| "confidence": 3.14, # Confidence of detected language. Range [0, 1]. | |
| }, | |
| ], | |
| }, | |
| ], | |
| "tokens": [ # A list of visually detected tokens on the page. | |
| { # A detected token. | |
| "detectedBreak": { # Detected break at the end of a Token. # Detected break at the end of a Token. | |
| "type": "A String", # Detected break type. | |
| }, | |
| "detectedLanguages": [ # A list of detected languages together with confidence. | |
| { # Detected language for a structural component. | |
| "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more | |
| # information, see | |
| # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. | |
| "confidence": 3.14, # Confidence of detected language. Range [0, 1]. | |
| }, | |
| ], | |
| "layout": { # Visual element describing a layout unit on a page. # Layout for Token. | |
| "orientation": "A String", # Detected orientation for the Layout. | |
| "boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout. | |
| "normalizedVertices": [ # The bounding polygon normalized vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the normalized vertex coordinates are relative to the original image | |
| # and range from 0 to 1. | |
| "x": 3.14, # X coordinate. | |
| "y": 3.14, # Y coordinate. | |
| }, | |
| ], | |
| "vertices": [ # The bounding polygon vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the vertex coordinates are in the same scale as the original image. | |
| "x": 42, # X coordinate. | |
| "y": 42, # Y coordinate. | |
| }, | |
| ], | |
| }, | |
| "confidence": 3.14, # Confidence of the current Layout within context of the object this | |
| # layout is for. e.g. confidence can be for a single token, a table, | |
| # a visual element, etc. depending on context. Range [0, 1]. | |
| "textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text. | |
| "textSegments": [ # The text segments from the Document.text. | |
| { # A text segment in the Document.text. The indices may be out of bounds | |
| # which indicate that the text extends into another document shard for | |
| # large sharded documents. See ShardInfo.text_offset | |
| "startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text. | |
| "endIndex": "A String", # TextSegment half open end UTF-8 char index in the | |
| # Document.text. | |
| }, | |
| ], | |
| }, | |
| }, | |
| }, | |
| ], | |
| "pageNumber": 42, # 1-based index for current Page in a parent Document. | |
| # Useful when a page is taken out of a Document for individual | |
| # processing. | |
| "visualElements": [ # A list of detected non-text visual elements e.g. checkbox, | |
| # signature etc. on the page. | |
| { # Detected non-text visual elements e.g. checkbox, signature etc. on the | |
| # page. | |
| "detectedLanguages": [ # A list of detected languages together with confidence. | |
| { # Detected language for a structural component. | |
| "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more | |
| # information, see | |
| # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. | |
| "confidence": 3.14, # Confidence of detected language. Range [0, 1]. | |
| }, | |
| ], | |
| "type": "A String", # Type of the VisualElement. | |
| "layout": { # Visual element describing a layout unit on a page. # Layout for VisualElement. | |
| "orientation": "A String", # Detected orientation for the Layout. | |
| "boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout. | |
| "normalizedVertices": [ # The bounding polygon normalized vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the normalized vertex coordinates are relative to the original image | |
| # and range from 0 to 1. | |
| "x": 3.14, # X coordinate. | |
| "y": 3.14, # Y coordinate. | |
| }, | |
| ], | |
| "vertices": [ # The bounding polygon vertices. | |
| { # A vertex represents a 2D point in the image. | |
| # NOTE: the vertex coordinates are in the same scale as the original image. | |
| "x": 42, # X coordinate. | |
| "y": 42, # Y coordinate. | |
| }, | |
| ], | |
| }, | |
| "confidence": 3.14, # Confidence of the current Layout within context of the object this | |
| # layout is for. e.g. confidence can be for a single token, a table, | |
| # a visual element, etc. depending on context. Range [0, 1]. | |
| "textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text. | |
| "textSegments": [ # The text segments from the Document.text. | |
| { # A text segment in the Document.text. The indices may be out of bounds | |
| # which indicate that the text extends into another document shard for | |
| # large sharded documents. See ShardInfo.text_offset | |
| "startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text. | |
| "endIndex": "A String", # TextSegment half open end UTF-8 char index in the | |
| # Document.text. | |
| }, | |
| ], | |
| }, | |
| }, | |
| }, | |
| ], | |
| }, | |
| ], | |
| "text": "A String", # UTF-8 encoded text in reading order from the document. | |
| "mimeType": "A String", # An IANA published MIME type (also referred to as media type). For more | |
| # information, see | |
| # https://www.iana.org/assignments/media-types/media-types.xhtml. | |
| "entityRelations": [ # Relationship among Document.entities. | |
| { # Relationship between Entities. | |
| "objectId": "A String", # Object entity id. | |
| "relation": "A String", # Relationship description. | |
| "subjectId": "A String", # Subject entity id. | |
| }, | |
| ], | |
| "translations": [ # A list of translations on Document.text. For document shards, | |
| # translations in this list may cross shard boundaries. | |
| { # A translation of the text segment. | |
| "textAnchor": { # Text reference indexing into the Document.text. # Provenance of the translation. | |
| # Text anchor indexing into the Document.text. | |
| "textSegments": [ # The text segments from the Document.text. | |
| { # A text segment in the Document.text. The indices may be out of bounds | |
| # which indicate that the text extends into another document shard for | |
| # large sharded documents. See ShardInfo.text_offset | |
| "startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text. | |
| "endIndex": "A String", # TextSegment half open end UTF-8 char index in the | |
| # Document.text. | |
| }, | |
| ], | |
| }, | |
| "languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more | |
| # information, see | |
| # http://www.unicode.org/reports/tr35/#Unicode_locale_identifier. | |
| "translatedText": "A String", # Text translated into the target language. | |
| }, | |
| ], | |
| "shardInfo": { # For a large document, sharding may be performed to produce several # Information about the sharding if this document is sharded part of a larger | |
| # document. If the document is not sharded, this message is not specified. | |
| # document shards. Each document shard contains this field to detail which | |
| # shard it is. | |
| "shardIndex": "A String", # The 0-based index of this shard. | |
| "textOffset": "A String", # The index of the first character in Document.text in the overall | |
| # document global text. | |
| "shardCount": "A String", # Total number of shards. | |
| }, | |
| "textStyles": [ # Styles for the Document.text. | |
| { # Annotation for common text style attributes. This adheres to CSS | |
| # conventions as much as possible. | |
| "fontWeight": "A String", # Font weight. Possible values are normal, bold, bolder, and lighter. | |
| # https://www.w3schools.com/cssref/pr_font_weight.asp | |
| "textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text. | |
| "textSegments": [ # The text segments from the Document.text. | |
| { # A text segment in the Document.text. The indices may be out of bounds | |
| # which indicate that the text extends into another document shard for | |
| # large sharded documents. See ShardInfo.text_offset | |
| "startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text. | |
| "endIndex": "A String", # TextSegment half open end UTF-8 char index in the | |
| # Document.text. | |
| }, | |
| ], | |
| }, | |
| "textDecoration": "A String", # Text decoration. Follows CSS standard. | |
| # <text-decoration-line> <text-decoration-color> <text-decoration-style> | |
| # https://www.w3schools.com/cssref/pr_text_text-decoration.asp | |
| "color": { # Represents a color in the RGBA color space. This representation is designed # Text color. | |
| # for simplicity of conversion to/from color representations in various | |
| # languages over compactness; for example, the fields of this representation | |
| # can be trivially provided to the constructor of "java.awt.Color" in Java; it | |
| # can also be trivially provided to UIColor's "+colorWithRed:green:blue:alpha" | |
| # method in iOS; and, with just a little work, it can be easily formatted into | |
| # a CSS "rgba()" string in JavaScript, as well. | |
| # | |
| # Note: this proto does not carry information about the absolute color space | |
| # that should be used to interpret the RGB value (e.g. sRGB, Adobe RGB, | |
| # DCI-P3, BT.2020, etc.). By default, applications SHOULD assume the sRGB color | |
| # space. | |
| # | |
| # Note: when color equality needs to be decided, implementations, unless | |
| # documented otherwise, will treat two colors to be equal if all their red, | |
| # green, blue and alpha values each differ by at most 1e-5. | |
| # | |
| # Example (Java): | |
| # | |
| # import com.google.type.Color; | |
| # | |
| # // ... | |
| # public static java.awt.Color fromProto(Color protocolor) { | |
| # float alpha = protocolor.hasAlpha() | |
| # ? protocolor.getAlpha().getValue() | |
| # : 1.0; | |
| # | |
| # return new java.awt.Color( | |
| # protocolor.getRed(), | |
| # protocolor.getGreen(), | |
| # protocolor.getBlue(), | |
| # alpha); | |
| # } | |
| # | |
| # public static Color toProto(java.awt.Color color) { | |
| # float red = (float) color.getRed(); | |
| # float green = (float) color.getGreen(); | |
| # float blue = (float) color.getBlue(); | |
| # float denominator = 255.0; | |
| # Color.Builder resultBuilder = | |
| # Color | |
| # .newBuilder() | |
| # .setRed(red / denominator) | |
| # .setGreen(green / denominator) | |
| # .setBlue(blue / denominator); | |
| # int alpha = color.getAlpha(); | |
| # if (alpha != 255) { | |
| # result.setAlpha( | |
| # FloatValue | |
| # .newBuilder() | |
| # .setValue(((float) alpha) / denominator) | |
| # .build()); | |
| # } | |
| # return resultBuilder.build(); | |
| # } | |
| # // ... | |
| # | |
| # Example (iOS / Obj-C): | |
| # | |
| # // ... | |
| # static UIColor* fromProto(Color* protocolor) { | |
| # float red = [protocolor red]; | |
| # float green = [protocolor green]; | |
| # float blue = [protocolor blue]; | |
| # FloatValue* alpha_wrapper = [protocolor alpha]; | |
| # float alpha = 1.0; | |
| # if (alpha_wrapper != nil) { | |
| # alpha = [alpha_wrapper value]; | |
| # } | |
| # return [UIColor colorWithRed:red green:green blue:blue alpha:alpha]; | |
| # } | |
| # | |
| # static Color* toProto(UIColor* color) { | |
| # CGFloat red, green, blue, alpha; | |
| # if (![color getRed:&red green:&green blue:&blue alpha:&alpha]) { | |
| # return nil; | |
| # } | |
| # Color* result = [[Color alloc] init]; | |
| # [result setRed:red]; | |
| # [result setGreen:green]; | |
| # [result setBlue:blue]; | |
| # if (alpha <= 0.9999) { | |
| # [result setAlpha:floatWrapperWithValue(alpha)]; | |
| # } | |
| # [result autorelease]; | |
| # return result; | |
| # } | |
| # // ... | |
| # | |
| # Example (JavaScript): | |
| # | |
| # // ... | |
| # | |
| # var protoToCssColor = function(rgb_color) { | |
| # var redFrac = rgb_color.red || 0.0; | |
| # var greenFrac = rgb_color.green || 0.0; | |
| # var blueFrac = rgb_color.blue || 0.0; | |
| # var red = Math.floor(redFrac * 255); | |
| # var green = Math.floor(greenFrac * 255); | |
| # var blue = Math.floor(blueFrac * 255); | |
| # | |
| # if (!('alpha' in rgb_color)) { | |
| # return rgbToCssColor_(red, green, blue); | |
| # } | |
| # | |
| # var alphaFrac = rgb_color.alpha.value || 0.0; | |
| # var rgbParams = [red, green, blue].join(','); | |
| # return ['rgba(', rgbParams, ',', alphaFrac, ')'].join(''); | |
| # }; | |
| # | |
| # var rgbToCssColor_ = function(red, green, blue) { | |
| # var rgbNumber = new Number((red << 16) | (green << 8) | blue); | |
| # var hexString = rgbNumber.toString(16); | |
| # var missingZeros = 6 - hexString.length; | |
| # var resultBuilder = ['#']; | |
| # for (var i = 0; i < missingZeros; i++) { | |
| # resultBuilder.push('0'); | |
| # } | |
| # resultBuilder.push(hexString); | |
| # return resultBuilder.join(''); | |
| # }; | |
| # | |
| # // ... | |
| "alpha": 3.14, # The fraction of this color that should be applied to the pixel. That is, | |
| # the final pixel color is defined by the equation: | |
| # | |
| # pixel color = alpha * (this color) + (1.0 - alpha) * (background color) | |
| # | |
| # This means that a value of 1.0 corresponds to a solid color, whereas | |
| # a value of 0.0 corresponds to a completely transparent color. This | |
| # uses a wrapper message rather than a simple float scalar so that it is | |
| # possible to distinguish between a default value and the value being unset. | |
| # If omitted, this color object is to be rendered as a solid color | |
| # (as if the alpha value had been explicitly given with a value of 1.0). | |
| "blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1]. | |
| "green": 3.14, # The amount of green in the color as a value in the interval [0, 1]. | |
| "red": 3.14, # The amount of red in the color as a value in the interval [0, 1]. | |
| }, | |
| "fontSize": { # Font size with unit. # Font size. | |
| "size": 3.14, # Font size for the text. | |
| "unit": "A String", # Unit for the font size. Follows CSS naming (in, px, pt, etc.). | |
| }, | |
| "backgroundColor": { # Represents a color in the RGBA color space. This representation is designed # Text background color. | |
| # for simplicity of conversion to/from color representations in various | |
| # languages over compactness; for example, the fields of this representation | |
| # can be trivially provided to the constructor of "java.awt.Color" in Java; it | |
| # can also be trivially provided to UIColor's "+colorWithRed:green:blue:alpha" | |
| # method in iOS; and, with just a little work, it can be easily formatted into | |
| # a CSS "rgba()" string in JavaScript, as well. | |
| # | |
| # Note: this proto does not carry information about the absolute color space | |
| # that should be used to interpret the RGB value (e.g. sRGB, Adobe RGB, | |
| # DCI-P3, BT.2020, etc.). By default, applications SHOULD assume the sRGB color | |
| # space. | |
| # | |
| # Note: when color equality needs to be decided, implementations, unless | |
| # documented otherwise, will treat two colors to be equal if all their red, | |
| # green, blue and alpha values each differ by at most 1e-5. | |
| # | |
| # Example (Java): | |
| # | |
| # import com.google.type.Color; | |
| # | |
| # // ... | |
| # public static java.awt.Color fromProto(Color protocolor) { | |
| # float alpha = protocolor.hasAlpha() | |
| # ? protocolor.getAlpha().getValue() | |
| # : 1.0; | |
| # | |
| # return new java.awt.Color( | |
| # protocolor.getRed(), | |
| # protocolor.getGreen(), | |
| # protocolor.getBlue(), | |
| # alpha); | |
| # } | |
| # | |
| # public static Color toProto(java.awt.Color color) { | |
| # float red = (float) color.getRed(); | |
| # float green = (float) color.getGreen(); | |
| # float blue = (float) color.getBlue(); | |
| # float denominator = 255.0; | |
| # Color.Builder resultBuilder = | |
| # Color | |
| # .newBuilder() | |
| # .setRed(red / denominator) | |
| # .setGreen(green / denominator) | |
| # .setBlue(blue / denominator); | |
| # int alpha = color.getAlpha(); | |
| # if (alpha != 255) { | |
| # result.setAlpha( | |
| # FloatValue | |
| # .newBuilder() | |
| # .setValue(((float) alpha) / denominator) | |
| # .build()); | |
| # } | |
| # return resultBuilder.build(); | |
| # } | |
| # // ... | |
| # | |
| # Example (iOS / Obj-C): | |
| # | |
| # // ... | |
| # static UIColor* fromProto(Color* protocolor) { | |
| # float red = [protocolor red]; | |
| # float green = [protocolor green]; | |
| # float blue = [protocolor blue]; | |
| # FloatValue* alpha_wrapper = [protocolor alpha]; | |
| # float alpha = 1.0; | |
| # if (alpha_wrapper != nil) { | |
| # alpha = [alpha_wrapper value]; | |
| # } | |
| # return [UIColor colorWithRed:red green:green blue:blue alpha:alpha]; | |
| # } | |
| # | |
| # static Color* toProto(UIColor* color) { | |
| # CGFloat red, green, blue, alpha; | |
| # if (![color getRed:&red green:&green blue:&blue alpha:&alpha]) { | |
| # return nil; | |
| # } | |
| # Color* result = [[Color alloc] init]; | |
| # [result setRed:red]; | |
| # [result setGreen:green]; | |
| # [result setBlue:blue]; | |
| # if (alpha <= 0.9999) { | |
| # [result setAlpha:floatWrapperWithValue(alpha)]; | |
| # } | |
| # [result autorelease]; | |
| # return result; | |
| # } | |
| # // ... | |
| # | |
| # Example (JavaScript): | |
| # | |
| # // ... | |
| # | |
| # var protoToCssColor = function(rgb_color) { | |
| # var redFrac = rgb_color.red || 0.0; | |
| # var greenFrac = rgb_color.green || 0.0; | |
| # var blueFrac = rgb_color.blue || 0.0; | |
| # var red = Math.floor(redFrac * 255); | |
| # var green = Math.floor(greenFrac * 255); | |
| # var blue = Math.floor(blueFrac * 255); | |
| # | |
| # if (!('alpha' in rgb_color)) { | |
| # return rgbToCssColor_(red, green, blue); | |
| # } | |
| # | |
| # var alphaFrac = rgb_color.alpha.value || 0.0; | |
| # var rgbParams = [red, green, blue].join(','); | |
| # return ['rgba(', rgbParams, ',', alphaFrac, ')'].join(''); | |
| # }; | |
| # | |
| # var rgbToCssColor_ = function(red, green, blue) { | |
| # var rgbNumber = new Number((red << 16) | (green << 8) | blue); | |
| # var hexString = rgbNumber.toString(16); | |
| # var missingZeros = 6 - hexString.length; | |
| # var resultBuilder = ['#']; | |
| # for (var i = 0; i < missingZeros; i++) { | |
| # resultBuilder.push('0'); | |
| # } | |
| # resultBuilder.push(hexString); | |
| # return resultBuilder.join(''); | |
| # }; | |
| # | |
| # // ... | |
| "alpha": 3.14, # The fraction of this color that should be applied to the pixel. That is, | |
| # the final pixel color is defined by the equation: | |
| # | |
| # pixel color = alpha * (this color) + (1.0 - alpha) * (background color) | |
| # | |
| # This means that a value of 1.0 corresponds to a solid color, whereas | |
| # a value of 0.0 corresponds to a completely transparent color. This | |
| # uses a wrapper message rather than a simple float scalar so that it is | |
| # possible to distinguish between a default value and the value being unset. | |
| # If omitted, this color object is to be rendered as a solid color | |
| # (as if the alpha value had been explicitly given with a value of 1.0). | |
| "blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1]. | |
| "green": 3.14, # The amount of green in the color as a value in the interval [0, 1]. | |
| "red": 3.14, # The amount of red in the color as a value in the interval [0, 1]. | |
| }, | |
| "textStyle": "A String", # Text style. Possible values are normal, italic, and oblique. | |
| # https://www.w3schools.com/cssref/pr_font_font-style.asp | |
| }, | |
| ], | |
| "entities": [ # A list of entities detected on Document.text. For document shards, | |
| # entities in this list may cross shard boundaries. | |
| { # A phrase in the text that is a known entity type, such as a person, an | |
| # organization, or location. | |
| "textAnchor": { # Text reference indexing into the Document.text. # Provenance of the entity. | |
| # Text anchor indexing into the Document.text. | |
| "textSegments": [ # The text segments from the Document.text. | |
| { # A text segment in the Document.text. The indices may be out of bounds | |
| # which indicate that the text extends into another document shard for | |
| # large sharded documents. See ShardInfo.text_offset | |
| "startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text. | |
| "endIndex": "A String", # TextSegment half open end UTF-8 char index in the | |
| # Document.text. | |
| }, | |
| ], | |
| }, | |
| "mentionId": "A String", # Deprecated. Use `id` field instead. | |
| "type": "A String", # Entity type from a schema e.g. `Address`. | |
| "confidence": 3.14, # Optional. Confidence of detected Schema entity. Range [0, 1]. | |
| "mentionText": "A String", # Text value in the document e.g. `1600 Amphitheatre Pkwy`. | |
| }, | |
| ], | |
| }</pre> | |
| </div> | |
| </body></html> |