Blame - docs/dyn/documentai_v1beta2.projects.documents.html - platform/external/python/google-api-python-client

<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>

76

<h2>Instance Methods</h2>

77

78

<code><a href="#batchProcess">batchProcess(parent, body=None, x__xgafv=None)</a></code></p>

79

<p class="firstline">LRO endpoint to batch process many documents. The output is written</p>

80

81

<code><a href="#process">process(parent, body=None, x__xgafv=None)</a></code></p>

82

<p class="firstline">Processes a single document.</p>

83

<h3>Method Details</h3>

84

85

<code class="details" id="batchProcess">batchProcess(parent, body=None, x__xgafv=None)</code>

86

<pre>LRO endpoint to batch process many documents. The output is written

87

to Cloud Storage as JSON in the [Document] format.

88

89

Args:

90

parent: string, Target project and location to make a call.

91

92

Format: `projects/{project-id}/locations/{location-id}`.

93

94

If no location is specified, a region will be chosen automatically. (required)

95

body: object, The request body.

96

The object takes the form of:

97

98

{ # Request to batch process documents as an asynchronous operation. The output

99

# is written to Cloud Storage as JSON in the [Document] format.

100

"requests": [ # Required. Individual requests for each document.

101

{ # Request to process one document.

102

"ocrParams": { # Parameters to control Optical Character Recognition (OCR) behavior. # Controls OCR behavior. If not specified, the system will decide reasonable

103

# defaults.

104

"languageHints": [ # List of languages to use for OCR. In most cases, an empty value

105

# yields the best results since it enables automatic language detection. For

106

# languages based on the Latin alphabet, setting `language_hints` is not

107

# needed. In rare cases, when the language of the text in the image is known,

108

# setting a hint will help get better results (although it will be a

109

# significant hindrance if the hint is wrong). Document processing returns an

110

# error if one or more of the specified languages is not one of the

111

# supported languages.

"A String",

],

},

"tableExtractionParams": { # Parameters to control table extraction behavior. # Controls table extraction behavior. If not specified, the system will

116

# decide reasonable defaults.

117

"tableBoundHints": [ # Optional. Table bounding box hints that can be provided to complex cases

118

# which our algorithm cannot locate the table(s) in.

119

{ # A hint for a table bounding box on the page for table parsing.

120

"pageNumber": 42, # Optional. Page number for multi-paged inputs this hint applies to. If not

121

# provided, this hint will apply to all pages by default. This value is

122

# 1-based.

123

"boundingBox": { # A bounding polygon for the detected image annotation. # Bounding box hint for a table on this page. The coordinates must be

124

# normalized to [0,1] and the bounding box must be an axis-aligned rectangle.

125

"normalizedVertices": [ # The bounding polygon normalized vertices.

126

{ # A vertex represents a 2D point in the image.

127

# NOTE: the normalized vertex coordinates are relative to the original image

128

# and range from 0 to 1.

129

"x": 3.14, # X coordinate.

130

"y": 3.14, # Y coordinate.

131

},

132

],

133

"vertices": [ # The bounding polygon vertices.

134

{ # A vertex represents a 2D point in the image.

135

# NOTE: the vertex coordinates are in the same scale as the original image.

136

"x": 42, # X coordinate.

137

"y": 42, # Y coordinate.

},

],

},

},

],

"headerHints": [ # Optional. Reserved for future use.

144

"A String",

145

],

146

"modelVersion": "A String", # Model version of the table extraction system. Default is "builtin/stable".

147

# Specify "builtin/latest" for the latest model.

148

"enabled": True or False, # Whether to enable table extraction.

149

},

150

"automlParams": { # Parameters to control AutoML model prediction behavior. # Controls AutoML model prediction behavior. AutoMlParams cannot be used

151

# together with other Params.

152

"model": "A String", # Resource name of the AutoML model.

153

#

154

# Format: `projects/{project-id}/locations/{location-id}/models/{model-id}`.

155

},

156

"inputConfig": { # The desired input location and metadata. # Required. Information about the input file.

157

"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.

162

# Note: As with all `bytes` fields, proto buffer messages use a pure binary

163

# representation, whereas JSON representations use base64.

164

#

165

# This field only works for synchronous ProcessDocument method.

166

"mimeType": "A String", # Required. Mimetype of the input. Current supported mimetypes are application/pdf,

167

# image/tiff, and image/gif.

168

# In addition, application/json type is supported for requests with

169

# ProcessDocumentRequest.automl_params field set. The JSON file needs to

170

# be in Document format.

171

},

172

"formExtractionParams": { # Parameters to control form extraction behavior. # Controls form extraction behavior. If not specified, the system will

173

# decide reasonable defaults.

174

"modelVersion": "A String", # Model version of the form extraction system. Default is

175

# "builtin/stable". Specify "builtin/latest" for the latest model.

176

# For custom form models, specify: “custom/{model_name}". Model name

177

# format is "bucket_name/path/to/modeldir" corresponding to

178

# "gs://bucket_name/path/to/modeldir" where annotated examples are stored.

179

"enabled": True or False, # Whether to enable form extraction.

180

"keyValuePairHints": [ # Reserved for future use.

181

{ # Reserved for future use.

182

"valueTypes": [ # Type of the value. This is case-insensitive, and could be one of:

183

# ADDRESS, LOCATION, ORGANIZATION, PERSON, PHONE_NUMBER,

184

# 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

193

# values are currently "general" and "invoice". If not provided, "general"\

194

# is used as default. If any other value is given, the request is rejected.

195

"parent": "A String", # Target project and location to make a call.

196

#

197

# Format: `projects/{project-id}/locations/{location-id}`.

198

#

199

# If no location is specified, a region will be chosen automatically.

200

# This field is only populated when used in ProcessDocument method.

201

"outputConfig": { # The desired output location and metadata. # The desired output location. This field is only needed in

202

# BatchProcessDocumentsRequest.

203

"pagesPerShard": 42, # The max number of pages to include into each output Document shard JSON on

204

# Google Cloud Storage.

205

#

206

# The valid range is [1, 100]. If not specified, the default value is 20.

207

#

208

# For example, for one pdf file with 100 pages, 100 parsed pages will be

209

# produced. If `pages_per_shard` = 20, then 5 Document shard JSON files each

210

# containing 20 parsed pages will be written under the prefix

211

# OutputConfig.gcs_destination.uri and suffix pages-x-to-y.json where

212

# x and y are 1-indexed page numbers.

213

#

214

# Example GCS outputs with 157 pages and pages_per_shard = 50:

215

#

216

# <prefix>pages-001-to-050.json

217

# <prefix>pages-051-to-100.json

218

# <prefix>pages-101-to-150.json

219

# <prefix>pages-151-to-157.json

220

"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

225

# decide reasonable defaults.

226

"enabled": True or False, # Whether to enable entity extraction.

227

"modelVersion": "A String", # Model version of the entity extraction. Default is

228

# "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:

241

242

{ # This resource represents a long-running operation that is the result of a

243

# network API call.

244

"metadata": { # Service-specific metadata associated with the operation. It typically

245

# contains progress information and common metadata such as create time.

246

# Some services might not provide such metadata. Any method that returns a

247

# long-running operation should document the metadata type, if any.

248

"a_key": "", # Properties of the object. Contains field @type with type URL.

249

},

250

"name": "A String", # The server-assigned name, which is only unique within the same service that

251

# originally returns it. If you use the default HTTP mapping, the

252

# `name` should be a resource name ending with `operations/{unique_id}`.

253

"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.

254

# different programming environments, including REST APIs and RPC APIs. It is

255

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

256

# three pieces of data: error code, error message, and error details.

257

#

258

# You can find out more about this error model and how to work with it in the

259

# [API Design Guide](https://cloud.google.com/apis/design/errors).

260

"message": "A String", # A developer-facing error message, which should be in English. Any

261

# user-facing error message should be localized and sent in the

262

# google.rpc.Status.details field, or localized by the client.

263

"details": [ # A list of messages that carry the error details. There is a common set of

264

# message types for APIs to use.

265

{

266

"a_key": "", # Properties of the object. Contains field @type with type URL.

267

},

268

],

269

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

270

},

271

"response": { # The normal response of the operation in case of success. If the original

272

# method returns no data on success, such as `Delete`, the response is

273

# `google.protobuf.Empty`. If the original method is standard

274

# `Get`/`Create`/`Update`, the response should be the resource. For other

275

# methods, the response should have the type `XxxResponse`, where `Xxx`

276

# is the original method name. For example, if the original method name

277

# is `TakeSnapshot()`, the inferred response type is

278

# `TakeSnapshotResponse`.

279

"a_key": "", # Properties of the object. Contains field @type with type URL.

280

},

281

"done": True or False, # If the value is `false`, it means the operation is still in progress.

282

# If `true`, the operation is completed, and either `error` or `response` is

# available.

}</pre>

</div>

<code class="details" id="process">process(parent, body=None, x__xgafv=None)</code>

289

<pre>Processes a single document.

290

291

Args:

292

parent: string, Target project and location to make a call.

293

294

Format: `projects/{project-id}/locations/{location-id}`.

295

296

If no location is specified, a region will be chosen automatically.

297

This field is only populated when used in ProcessDocument method. (required)

298

body: object, The request body.

299

The object takes the form of:

300

301

{ # Request to process one document.

302

"ocrParams": { # Parameters to control Optical Character Recognition (OCR) behavior. # Controls OCR behavior. If not specified, the system will decide reasonable

303

# defaults.

304

"languageHints": [ # List of languages to use for OCR. In most cases, an empty value

305

# yields the best results since it enables automatic language detection. For

306

# languages based on the Latin alphabet, setting `language_hints` is not

307

# needed. In rare cases, when the language of the text in the image is known,

308

# setting a hint will help get better results (although it will be a

309

# significant hindrance if the hint is wrong). Document processing returns an

310

# error if one or more of the specified languages is not one of the

311

# supported languages.

"A String",

],

},

"tableExtractionParams": { # Parameters to control table extraction behavior. # Controls table extraction behavior. If not specified, the system will

316

# decide reasonable defaults.

317

"tableBoundHints": [ # Optional. Table bounding box hints that can be provided to complex cases

318

# which our algorithm cannot locate the table(s) in.

319

{ # A hint for a table bounding box on the page for table parsing.

320

"pageNumber": 42, # Optional. Page number for multi-paged inputs this hint applies to. If not

321

# provided, this hint will apply to all pages by default. This value is

322

# 1-based.

323

"boundingBox": { # A bounding polygon for the detected image annotation. # Bounding box hint for a table on this page. The coordinates must be

324

# normalized to [0,1] and the bounding box must be an axis-aligned rectangle.

325

"normalizedVertices": [ # The bounding polygon normalized vertices.

326

{ # A vertex represents a 2D point in the image.

327

# NOTE: the normalized vertex coordinates are relative to the original image

328

# and range from 0 to 1.

329

"x": 3.14, # X coordinate.

330

"y": 3.14, # Y coordinate.

331

},

332

],

333

"vertices": [ # The bounding polygon vertices.

334

{ # A vertex represents a 2D point in the image.

335

# NOTE: the vertex coordinates are in the same scale as the original image.

336

"x": 42, # X coordinate.

337

"y": 42, # Y coordinate.

},

],

},

},

],

"headerHints": [ # Optional. Reserved for future use.

344

"A String",

345

],

346

"modelVersion": "A String", # Model version of the table extraction system. Default is "builtin/stable".

347

# Specify "builtin/latest" for the latest model.

348

"enabled": True or False, # Whether to enable table extraction.

349

},

350

"automlParams": { # Parameters to control AutoML model prediction behavior. # Controls AutoML model prediction behavior. AutoMlParams cannot be used

351

# together with other Params.

352

"model": "A String", # Resource name of the AutoML model.

353

#

354

# Format: `projects/{project-id}/locations/{location-id}/models/{model-id}`.

355

},

356

"inputConfig": { # The desired input location and metadata. # Required. Information about the input file.

357

"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.

362

# Note: As with all `bytes` fields, proto buffer messages use a pure binary

363

# representation, whereas JSON representations use base64.

364

#

365

# This field only works for synchronous ProcessDocument method.

366

"mimeType": "A String", # Required. Mimetype of the input. Current supported mimetypes are application/pdf,

367

# image/tiff, and image/gif.

368

# In addition, application/json type is supported for requests with

369

# ProcessDocumentRequest.automl_params field set. The JSON file needs to

370

# be in Document format.

371

},

372

"formExtractionParams": { # Parameters to control form extraction behavior. # Controls form extraction behavior. If not specified, the system will

373

# decide reasonable defaults.

374

"modelVersion": "A String", # Model version of the form extraction system. Default is

375

# "builtin/stable". Specify "builtin/latest" for the latest model.

376

# For custom form models, specify: “custom/{model_name}". Model name

377

# format is "bucket_name/path/to/modeldir" corresponding to

378

# "gs://bucket_name/path/to/modeldir" where annotated examples are stored.

379

"enabled": True or False, # Whether to enable form extraction.

380

"keyValuePairHints": [ # Reserved for future use.

381

{ # Reserved for future use.

382

"valueTypes": [ # Type of the value. This is case-insensitive, and could be one of:

383

# ADDRESS, LOCATION, ORGANIZATION, PERSON, PHONE_NUMBER,

384

# 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

393

# values are currently "general" and "invoice". If not provided, "general"\

394

# is used as default. If any other value is given, the request is rejected.

395

"parent": "A String", # Target project and location to make a call.

396

#

397

# Format: `projects/{project-id}/locations/{location-id}`.

398

#

399

# If no location is specified, a region will be chosen automatically.

400

# This field is only populated when used in ProcessDocument method.

401

"outputConfig": { # The desired output location and metadata. # The desired output location. This field is only needed in

402

# BatchProcessDocumentsRequest.

403

"pagesPerShard": 42, # The max number of pages to include into each output Document shard JSON on

404

# Google Cloud Storage.

405

#

406

# The valid range is [1, 100]. If not specified, the default value is 20.

407

#

408

# For example, for one pdf file with 100 pages, 100 parsed pages will be

409

# produced. If `pages_per_shard` = 20, then 5 Document shard JSON files each

410

# containing 20 parsed pages will be written under the prefix

411

# OutputConfig.gcs_destination.uri and suffix pages-x-to-y.json where

412

# x and y are 1-indexed page numbers.

413

#

414

# Example GCS outputs with 157 pages and pages_per_shard = 50:

415

#

416

# <prefix>pages-001-to-050.json

417

# <prefix>pages-051-to-100.json

418

# <prefix>pages-101-to-150.json

419

# <prefix>pages-151-to-157.json

420

"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

425

# decide reasonable defaults.

426

"enabled": True or False, # Whether to enable entity extraction.

427

"modelVersion": "A String", # Model version of the entity extraction. Default is

428

# "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:

439

440

{ # Document represents the canonical document resource in Document Understanding

441

# AI.

442

# It is an interchange format that provides insights into documents and allows

443

# for collaboration between users and Document Understanding AI to iterate and

444

# optimize for quality.

445

"content": "A String", # Inline document content, represented as a stream of bytes.

446

# Note: As with all `bytes` fields, protobuffers use a pure binary

447

# representation, whereas JSON representations use base64.

448

"labels": [ # Labels for this document.

449

{ # Label attaches schema information and/or other metadata to segments within

450

# a Document. Multiple Labels on a single field can denote either

451

# different labels, different instances of the same label created at

452

# different times, or some combination of both.

453

"automlModel": "A String", # Label is generated AutoML model. This field stores the full resource

454

# name of the AutoML model.

455

#

456

# Format:

457

# `projects/{project-id}/locations/{location-id}/models/{model-id}`

458

"confidence": 3.14, # Confidence score between 0 and 1 for label assignment.

459

"name": "A String", # Name of the label.

460

#

461

# When the label is generated from AutoML Text Classification model, this

462

# field represents the name of the category.

463

},

464

],

465

"uri": "A String", # Currently supports Google Cloud Storage URI of the form

466

# `gs://bucket_name/object_name`. Object versioning is not supported.

467

# See [Google Cloud Storage Request

468

# URIs](https://cloud.google.com/storage/docs/reference-uris) for more

469

# info.

470

"error": { # The `Status` type defines a logical error model that is suitable for # Any error that occurred while processing this document.

471

# different programming environments, including REST APIs and RPC APIs. It is

472

# used by [gRPC](https://github.com/grpc). Each `Status` message contains

473

# three pieces of data: error code, error message, and error details.

474

#

475

# You can find out more about this error model and how to work with it in the

476

# [API Design Guide](https://cloud.google.com/apis/design/errors).

477

"message": "A String", # A developer-facing error message, which should be in English. Any

478

# user-facing error message should be localized and sent in the

479

# google.rpc.Status.details field, or localized by the client.

480

"details": [ # A list of messages that carry the error details. There is a common set of

481

# message types for APIs to use.

482

{

483

"a_key": "", # Properties of the object. Contains field @type with type URL.

484

},

485

],

486

"code": 42, # The status code, which should be an enum value of google.rpc.Code.

487

},

488

"pages": [ # Visual page layout for the Document.

489

{ # A page in a Document.

490

"dimension": { # Dimension for the page. # Physical dimension of the page.

491

"width": 3.14, # Page width.

492

"height": 3.14, # Page height.

493

"unit": "A String", # Dimension unit.

494

},

495

"detectedLanguages": [ # A list of detected languages together with confidence.

496

{ # Detected language for a structural component.

497

"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more

498

# information, see

499

# http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.

500

"confidence": 3.14, # Confidence of detected language. Range [0, 1].

501

},

502

],

503

"tables": [ # A list of visually detected tables on the page.

504

{ # A table representation similar to HTML table structure.

505

"layout": { # Visual element describing a layout unit on a page. # Layout for Table.

506

"orientation": "A String", # Detected orientation for the Layout.

507

"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.

508

"normalizedVertices": [ # The bounding polygon normalized vertices.

509

{ # A vertex represents a 2D point in the image.

510

# NOTE: the normalized vertex coordinates are relative to the original image

511

# and range from 0 to 1.

512

"x": 3.14, # X coordinate.

513

"y": 3.14, # Y coordinate.

514

},

515

],

516

"vertices": [ # The bounding polygon vertices.

517

{ # A vertex represents a 2D point in the image.

518

# NOTE: the vertex coordinates are in the same scale as the original image.

519

"x": 42, # X coordinate.

520

"y": 42, # Y coordinate.

},

],

},

"confidence": 3.14, # Confidence of the current Layout within context of the object this

525

# layout is for. e.g. confidence can be for a single token, a table,

526

# a visual element, etc. depending on context. Range [0, 1].

527

"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.

528

"textSegments": [ # The text segments from the Document.text.

529

{ # A text segment in the Document.text. The indices may be out of bounds

530

# which indicate that the text extends into another document shard for

531

# large sharded documents. See ShardInfo.text_offset

532

"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.

533

"endIndex": "A String", # TextSegment half open end UTF-8 char index in the

# Document.text.

},

],

},

},

"detectedLanguages": [ # A list of detected languages together with confidence.

540

{ # Detected language for a structural component.

541

"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more

542

# information, see

543

# http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.

544

"confidence": 3.14, # Confidence of detected language. Range [0, 1].

545

},

546

],

547

"bodyRows": [ # Body rows of the table.

548

{ # A row of table cells.

549

"cells": [ # Cells that make up this row.

550

{ # A cell representation inside the table.

551

"detectedLanguages": [ # A list of detected languages together with confidence.

552

{ # Detected language for a structural component.

553

"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more

554

# information, see

555

# http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.

556

"confidence": 3.14, # Confidence of detected language. Range [0, 1].

557

},

558

],

559

"rowSpan": 42, # How many rows this cell spans.

560

"layout": { # Visual element describing a layout unit on a page. # Layout for TableCell.

561

"orientation": "A String", # Detected orientation for the Layout.

562

"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.

563

"normalizedVertices": [ # The bounding polygon normalized vertices.

564

{ # A vertex represents a 2D point in the image.

565

# NOTE: the normalized vertex coordinates are relative to the original image

566

# and range from 0 to 1.

567

"x": 3.14, # X coordinate.

568

"y": 3.14, # Y coordinate.

569

},

570

],

571

"vertices": [ # The bounding polygon vertices.

572

{ # A vertex represents a 2D point in the image.

573

# NOTE: the vertex coordinates are in the same scale as the original image.

574

"x": 42, # X coordinate.

575

"y": 42, # Y coordinate.

},

],

},

"confidence": 3.14, # Confidence of the current Layout within context of the object this

580

# layout is for. e.g. confidence can be for a single token, a table,

581

# a visual element, etc. depending on context. Range [0, 1].

582

"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.

583

"textSegments": [ # The text segments from the Document.text.

584

{ # A text segment in the Document.text. The indices may be out of bounds

585

# which indicate that the text extends into another document shard for

586

# large sharded documents. See ShardInfo.text_offset

587

"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.

588

"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.

600

{ # A row of table cells.

601

"cells": [ # Cells that make up this row.

602

{ # A cell representation inside the table.

603

"detectedLanguages": [ # A list of detected languages together with confidence.

604

{ # Detected language for a structural component.

605

"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more

606

# information, see

607

# http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.

608

"confidence": 3.14, # Confidence of detected language. Range [0, 1].

609

},

610

],

611

"rowSpan": 42, # How many rows this cell spans.

612

"layout": { # Visual element describing a layout unit on a page. # Layout for TableCell.

613

"orientation": "A String", # Detected orientation for the Layout.

614

"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.

615

"normalizedVertices": [ # The bounding polygon normalized vertices.

616

{ # A vertex represents a 2D point in the image.

617

# NOTE: the normalized vertex coordinates are relative to the original image

618

# and range from 0 to 1.

619

"x": 3.14, # X coordinate.

620

"y": 3.14, # Y coordinate.

621

},

622

],

623

"vertices": [ # The bounding polygon vertices.

624

{ # A vertex represents a 2D point in the image.

625

# NOTE: the vertex coordinates are in the same scale as the original image.

626

"x": 42, # X coordinate.

627

"y": 42, # Y coordinate.

},

],

},

"confidence": 3.14, # Confidence of the current Layout within context of the object this

632

# layout is for. e.g. confidence can be for a single token, a table,

633

# a visual element, etc. depending on context. Range [0, 1].

634

"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.

635

"textSegments": [ # The text segments from the Document.text.

636

{ # A text segment in the Document.text. The indices may be out of bounds

637

# which indicate that the text extends into another document shard for

638

# large sharded documents. See ShardInfo.text_offset

639

"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.

640

"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.

654

"orientation": "A String", # Detected orientation for the Layout.

655

"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.

656

"normalizedVertices": [ # The bounding polygon normalized vertices.

657

{ # A vertex represents a 2D point in the image.

658

# NOTE: the normalized vertex coordinates are relative to the original image

659

# and range from 0 to 1.

660

"x": 3.14, # X coordinate.

661

"y": 3.14, # Y coordinate.

662

},

663

],

664

"vertices": [ # The bounding polygon vertices.

665

{ # A vertex represents a 2D point in the image.

666

# NOTE: the vertex coordinates are in the same scale as the original image.

667

"x": 42, # X coordinate.

668

"y": 42, # Y coordinate.

},

],

},

"confidence": 3.14, # Confidence of the current Layout within context of the object this

673

# layout is for. e.g. confidence can be for a single token, a table,

674

# a visual element, etc. depending on context. Range [0, 1].

675

"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.

676

"textSegments": [ # The text segments from the Document.text.

677

{ # A text segment in the Document.text. The indices may be out of bounds

678

# which indicate that the text extends into another document shard for

679

# large sharded documents. See ShardInfo.text_offset

680

"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.

681

"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.

688

# A collection of tokens that a human would perceive as a line.

689

{ # A collection of tokens that a human would perceive as a line.

690

# Does not cross column boundaries, can be horizontal, vertical, etc.

691

"layout": { # Visual element describing a layout unit on a page. # Layout for Line.

692

"orientation": "A String", # Detected orientation for the Layout.

693

"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.

694

"normalizedVertices": [ # The bounding polygon normalized vertices.

695

{ # A vertex represents a 2D point in the image.

696

# NOTE: the normalized vertex coordinates are relative to the original image

697

# and range from 0 to 1.

698

"x": 3.14, # X coordinate.

699

"y": 3.14, # Y coordinate.

700

},

701

],

702

"vertices": [ # The bounding polygon vertices.

703

{ # A vertex represents a 2D point in the image.

704

# NOTE: the vertex coordinates are in the same scale as the original image.

705

"x": 42, # X coordinate.

706

"y": 42, # Y coordinate.

},

],

},

"confidence": 3.14, # Confidence of the current Layout within context of the object this

711

# layout is for. e.g. confidence can be for a single token, a table,

712

# a visual element, etc. depending on context. Range [0, 1].

713

"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.

714

"textSegments": [ # The text segments from the Document.text.

715

{ # A text segment in the Document.text. The indices may be out of bounds

716

# which indicate that the text extends into another document shard for

717

# large sharded documents. See ShardInfo.text_offset

718

"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.

719

"endIndex": "A String", # TextSegment half open end UTF-8 char index in the

# Document.text.

},

],

},

},

"detectedLanguages": [ # A list of detected languages together with confidence.

726

{ # Detected language for a structural component.

727

"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more

728

# information, see

729

# http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.

730

"confidence": 3.14, # Confidence of detected language. Range [0, 1].

},

],

},

],

"paragraphs": [ # A list of visually detected text paragraphs on the page.

736

# A collection of lines that a human would perceive as a paragraph.

737

{ # A collection of lines that a human would perceive as a paragraph.

738

"detectedLanguages": [ # A list of detected languages together with confidence.

739

{ # Detected language for a structural component.

740

"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more

741

# information, see

742

# http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.

743

"confidence": 3.14, # Confidence of detected language. Range [0, 1].

744

},

745

],

746

"layout": { # Visual element describing a layout unit on a page. # Layout for Paragraph.

747

"orientation": "A String", # Detected orientation for the Layout.

748

"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.

749

"normalizedVertices": [ # The bounding polygon normalized vertices.

750

{ # A vertex represents a 2D point in the image.

751

# NOTE: the normalized vertex coordinates are relative to the original image

752

# and range from 0 to 1.

753

"x": 3.14, # X coordinate.

754

"y": 3.14, # Y coordinate.

755

},

756

],

757

"vertices": [ # The bounding polygon vertices.

758

{ # A vertex represents a 2D point in the image.

759

# NOTE: the vertex coordinates are in the same scale as the original image.

760

"x": 42, # X coordinate.

761

"y": 42, # Y coordinate.

},

],

},

"confidence": 3.14, # Confidence of the current Layout within context of the object this

766

# layout is for. e.g. confidence can be for a single token, a table,

767

# a visual element, etc. depending on context. Range [0, 1].

768

"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.

769

"textSegments": [ # The text segments from the Document.text.

770

{ # A text segment in the Document.text. The indices may be out of bounds

771

# which indicate that the text extends into another document shard for

772

# large sharded documents. See ShardInfo.text_offset

773

"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.

774

"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.

783

{ # A form field detected on the page.

784

"valueType": "A String", # If the value is non-textual, this field represents the type. Current

785

# valid values are:

786

# - blank (this indicates the field_value is normal text)

787

# - "unfilled_checkbox"

788

# - "filled_checkbox"

789

"fieldName": { # Visual element describing a layout unit on a page. # Layout for the FormField name. e.g. `Address`, `Email`,

790

# `Grand total`, `Phone number`, etc.

791

"orientation": "A String", # Detected orientation for the Layout.

792

"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.

793

"normalizedVertices": [ # The bounding polygon normalized vertices.

794

{ # A vertex represents a 2D point in the image.

795

# NOTE: the normalized vertex coordinates are relative to the original image

796

# and range from 0 to 1.

797

"x": 3.14, # X coordinate.

798

"y": 3.14, # Y coordinate.

799

},

800

],

801

"vertices": [ # The bounding polygon vertices.

802

{ # A vertex represents a 2D point in the image.

803

# NOTE: the vertex coordinates are in the same scale as the original image.

804

"x": 42, # X coordinate.

805

"y": 42, # Y coordinate.

},

],

},

"confidence": 3.14, # Confidence of the current Layout within context of the object this

810

# layout is for. e.g. confidence can be for a single token, a table,

811

# a visual element, etc. depending on context. Range [0, 1].

812

"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.

813

"textSegments": [ # The text segments from the Document.text.

814

{ # A text segment in the Document.text. The indices may be out of bounds

815

# which indicate that the text extends into another document shard for

816

# large sharded documents. See ShardInfo.text_offset

817

"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.

818

"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.

825

{ # Detected language for a structural component.

826

"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more

827

# information, see

828

# http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.

829

"confidence": 3.14, # Confidence of detected language. Range [0, 1].

830

},

831

],

832

"valueDetectedLanguages": [ # A list of detected languages for value together with confidence.

833

{ # Detected language for a structural component.

834

"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more

835

# information, see

836

# http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.

837

"confidence": 3.14, # Confidence of detected language. Range [0, 1].

838

},

839

],

840

"fieldValue": { # Visual element describing a layout unit on a page. # Layout for the FormField value.

841

"orientation": "A String", # Detected orientation for the Layout.

842

"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.

843

"normalizedVertices": [ # The bounding polygon normalized vertices.

844

{ # A vertex represents a 2D point in the image.

845

# NOTE: the normalized vertex coordinates are relative to the original image

846

# and range from 0 to 1.

847

"x": 3.14, # X coordinate.

848

"y": 3.14, # Y coordinate.

849

},

850

],

851

"vertices": [ # The bounding polygon vertices.

852

{ # A vertex represents a 2D point in the image.

853

# NOTE: the vertex coordinates are in the same scale as the original image.

854

"x": 42, # X coordinate.

855

"y": 42, # Y coordinate.

},

],

},

"confidence": 3.14, # Confidence of the current Layout within context of the object this

860

# layout is for. e.g. confidence can be for a single token, a table,

861

# a visual element, etc. depending on context. Range [0, 1].

862

"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.

863

"textSegments": [ # The text segments from the Document.text.

864

{ # A text segment in the Document.text. The indices may be out of bounds

865

# which indicate that the text extends into another document shard for

866

# large sharded documents. See ShardInfo.text_offset

867

"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.

868

"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.

877

# A block has a set of lines (collected into paragraphs) that have a common

878

# line-spacing and orientation.

879

{ # A block has a set of lines (collected into paragraphs) that have a

880

# common line-spacing and orientation.

881

"layout": { # Visual element describing a layout unit on a page. # Layout for Block.

882

"orientation": "A String", # Detected orientation for the Layout.

883

"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.

884

"normalizedVertices": [ # The bounding polygon normalized vertices.

885

{ # A vertex represents a 2D point in the image.

886

# NOTE: the normalized vertex coordinates are relative to the original image

887

# and range from 0 to 1.

888

"x": 3.14, # X coordinate.

889

"y": 3.14, # Y coordinate.

890

},

891

],

892

"vertices": [ # The bounding polygon vertices.

893

{ # A vertex represents a 2D point in the image.

894

# NOTE: the vertex coordinates are in the same scale as the original image.

895

"x": 42, # X coordinate.

896

"y": 42, # Y coordinate.

},

],

},

"confidence": 3.14, # Confidence of the current Layout within context of the object this

901

# layout is for. e.g. confidence can be for a single token, a table,

902

# a visual element, etc. depending on context. Range [0, 1].

903

"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.

904

"textSegments": [ # The text segments from the Document.text.

905

{ # A text segment in the Document.text. The indices may be out of bounds

906

# which indicate that the text extends into another document shard for

907

# large sharded documents. See ShardInfo.text_offset

908

"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.

909

"endIndex": "A String", # TextSegment half open end UTF-8 char index in the

# Document.text.

},

],

},

},

"detectedLanguages": [ # A list of detected languages together with confidence.

916

{ # Detected language for a structural component.

917

"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more

918

# information, see

919

# http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.

920

"confidence": 3.14, # Confidence of detected language. Range [0, 1].

},

],

},

],

"tokens": [ # A list of visually detected tokens on the page.

926

{ # A detected token.

927

"detectedBreak": { # Detected break at the end of a Token. # Detected break at the end of a Token.

928

"type": "A String", # Detected break type.

929

},

930

"detectedLanguages": [ # A list of detected languages together with confidence.

931

{ # Detected language for a structural component.

932

"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more

933

# information, see

934

# http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.

935

"confidence": 3.14, # Confidence of detected language. Range [0, 1].

936

},

937

],

938

"layout": { # Visual element describing a layout unit on a page. # Layout for Token.

939

"orientation": "A String", # Detected orientation for the Layout.

940

"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.

941

"normalizedVertices": [ # The bounding polygon normalized vertices.

942

{ # A vertex represents a 2D point in the image.

943

# NOTE: the normalized vertex coordinates are relative to the original image

944

# and range from 0 to 1.

945

"x": 3.14, # X coordinate.

946

"y": 3.14, # Y coordinate.

947

},

948

],

949

"vertices": [ # The bounding polygon vertices.

950

{ # A vertex represents a 2D point in the image.

951

# NOTE: the vertex coordinates are in the same scale as the original image.

952

"x": 42, # X coordinate.

953

"y": 42, # Y coordinate.

},

],

},

"confidence": 3.14, # Confidence of the current Layout within context of the object this

958

# layout is for. e.g. confidence can be for a single token, a table,

959

# a visual element, etc. depending on context. Range [0, 1].

960

"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.

961

"textSegments": [ # The text segments from the Document.text.

962

{ # A text segment in the Document.text. The indices may be out of bounds

963

# which indicate that the text extends into another document shard for

964

# large sharded documents. See ShardInfo.text_offset

965

"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.

966

"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.

975

# Useful when a page is taken out of a Document for individual

976

# processing.

977

"visualElements": [ # A list of detected non-text visual elements e.g. checkbox,

978

# signature etc. on the page.

979

{ # Detected non-text visual elements e.g. checkbox, signature etc. on the

980

# page.

981

"detectedLanguages": [ # A list of detected languages together with confidence.

982

{ # Detected language for a structural component.

983

"languageCode": "A String", # The BCP-47 language code, such as "en-US" or "sr-Latn". For more

984

# information, see

985

# http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.

986

"confidence": 3.14, # Confidence of detected language. Range [0, 1].

987

},

988

],

989

"type": "A String", # Type of the VisualElement.

990

"layout": { # Visual element describing a layout unit on a page. # Layout for VisualElement.

991

"orientation": "A String", # Detected orientation for the Layout.

992

"boundingPoly": { # A bounding polygon for the detected image annotation. # The bounding polygon for the Layout.

993

"normalizedVertices": [ # The bounding polygon normalized vertices.

994

{ # A vertex represents a 2D point in the image.

995

# NOTE: the normalized vertex coordinates are relative to the original image

996

# and range from 0 to 1.

997

"x": 3.14, # X coordinate.

998

"y": 3.14, # Y coordinate.

999

},

1000

],

1001

"vertices": [ # The bounding polygon vertices.

1002

{ # A vertex represents a 2D point in the image.

1003

# NOTE: the vertex coordinates are in the same scale as the original image.

1004

"x": 42, # X coordinate.

1005

"y": 42, # Y coordinate.

},

],

},

"confidence": 3.14, # Confidence of the current Layout within context of the object this

1010

# layout is for. e.g. confidence can be for a single token, a table,

1011

# a visual element, etc. depending on context. Range [0, 1].

1012

"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.

1013

"textSegments": [ # The text segments from the Document.text.

1014

{ # A text segment in the Document.text. The indices may be out of bounds

1015

# which indicate that the text extends into another document shard for

1016

# large sharded documents. See ShardInfo.text_offset

1017

"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.

1018

"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.

1029

"mimeType": "A String", # An IANA published MIME type (also referred to as media type). For more

1030

# information, see

1031

# https://www.iana.org/assignments/media-types/media-types.xhtml.

1032

"entityRelations": [ # Relationship among Document.entities.

1033

{ # Relationship between Entities.

1034

"objectId": "A String", # Object entity id.

1035

"relation": "A String", # Relationship description.

1036

"subjectId": "A String", # Subject entity id.

1037

},

1038

],

1039

"translations": [ # A list of translations on Document.text. For document shards,

1040

# translations in this list may cross shard boundaries.

1041

{ # A translation of the text segment.

1042

"textAnchor": { # Text reference indexing into the Document.text. # Provenance of the translation.

1043

# Text anchor indexing into the Document.text.

1044

"textSegments": [ # The text segments from the Document.text.

1045

{ # A text segment in the Document.text. The indices may be out of bounds

1046

# which indicate that the text extends into another document shard for

1047

# large sharded documents. See ShardInfo.text_offset

1048

"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.

1049

"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

1055

# information, see

1056

# http://www.unicode.org/reports/tr35/#Unicode_locale_identifier.

1057

"translatedText": "A String", # Text translated into the target language.

1058

},

1059

],

1060

"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

1061

# document. If the document is not sharded, this message is not specified.

1062

# document shards. Each document shard contains this field to detail which

1063

# shard it is.

1064

"shardIndex": "A String", # The 0-based index of this shard.

1065

"textOffset": "A String", # The index of the first character in Document.text in the overall

1066

# document global text.

1067

"shardCount": "A String", # Total number of shards.

1068

},

1069

"textStyles": [ # Styles for the Document.text.

1070

{ # Annotation for common text style attributes. This adheres to CSS

1071

# conventions as much as possible.

1072

"fontWeight": "A String", # Font weight. Possible values are normal, bold, bolder, and lighter.

1073

# https://www.w3schools.com/cssref/pr_font_weight.asp

1074

"textAnchor": { # Text reference indexing into the Document.text. # Text anchor indexing into the Document.text.

1075

"textSegments": [ # The text segments from the Document.text.

1076

{ # A text segment in the Document.text. The indices may be out of bounds

1077

# which indicate that the text extends into another document shard for

1078

# large sharded documents. See ShardInfo.text_offset

1079

"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.

1080

"endIndex": "A String", # TextSegment half open end UTF-8 char index in the

# Document.text.

},

],

},

"textDecoration": "A String", # Text decoration. Follows CSS standard.

1086

# <text-decoration-line> <text-decoration-color> <text-decoration-style>

1087

# https://www.w3schools.com/cssref/pr_text_text-decoration.asp

1088

"color": { # Represents a color in the RGBA color space. This representation is designed # Text color.

1089

# for simplicity of conversion to/from color representations in various

1090

# languages over compactness; for example, the fields of this representation

1091

# can be trivially provided to the constructor of "java.awt.Color" in Java; it

1092

# can also be trivially provided to UIColor's "+colorWithRed:green:blue:alpha"

1093

# method in iOS; and, with just a little work, it can be easily formatted into

1094

# a CSS "rgba()" string in JavaScript, as well.

1095

#

1096

# Note: this proto does not carry information about the absolute color space

1097

# that should be used to interpret the RGB value (e.g. sRGB, Adobe RGB,

1098

# DCI-P3, BT.2020, etc.). By default, applications SHOULD assume the sRGB color

1099

# space.

1100

#

1101

# Note: when color equality needs to be decided, implementations, unless

1102

# documented otherwise, will treat two colors to be equal if all their red,

1103

# green, blue and alpha values each differ by at most 1e-5.

#

# Example (Java):

#

# import com.google.type.Color;

1108

#

1109

# // ...

1110

# public static java.awt.Color fromProto(Color protocolor) {

1111

# float alpha = protocolor.hasAlpha()

1112

# ? protocolor.getAlpha().getValue()

1113

# : 1.0;

1114

#

1115

# return new java.awt.Color(

1116

# protocolor.getRed(),

1117

# protocolor.getGreen(),

1118

# protocolor.getBlue(),

# alpha);

# }

#

# public static Color toProto(java.awt.Color color) {

1123

# float red = (float) color.getRed();

1124

# float green = (float) color.getGreen();

1125

# float blue = (float) color.getBlue();

1126

# float denominator = 255.0;

1127

# Color.Builder resultBuilder =

1128

# Color

1129

# .newBuilder()

1130

# .setRed(red / denominator)

1131

# .setGreen(green / denominator)

1132

# .setBlue(blue / denominator);

1133

# int alpha = color.getAlpha();

1134

# if (alpha != 255) {

# result.setAlpha(

# FloatValue

# .newBuilder()

# .setValue(((float) alpha) / denominator)

1139

# .build());

1140

# }

1141

# return resultBuilder.build();

# }

# // ...

#

# Example (iOS / Obj-C):

1146

#

1147

# // ...

1148

# static UIColor* fromProto(Color* protocolor) {

1149

# float red = [protocolor red];

1150

# float green = [protocolor green];

1151

# float blue = [protocolor blue];

1152

# FloatValue* alpha_wrapper = [protocolor alpha];

1153

# float alpha = 1.0;

1154

# if (alpha_wrapper != nil) {

1155

# alpha = [alpha_wrapper value];

1156

# }

1157

# return [UIColor colorWithRed:red green:green blue:blue alpha:alpha];

1158

# }

1159

#

1160

# static Color* toProto(UIColor* color) {

1161

# CGFloat red, green, blue, alpha;

1162

# if (![color getRed:&red green:&green blue:&blue alpha:&alpha]) {

1163

# return nil;

1164

# }

1165

# Color* result = [[Color alloc] init];

1166

# [result setRed:red];

1167

# [result setGreen:green];

1168

# [result setBlue:blue];

1169

# if (alpha <= 0.9999) {

1170

# [result setAlpha:floatWrapperWithValue(alpha)];

1171

# }

1172

# [result autorelease];

# return result;

# }

# // ...

#

# Example (JavaScript):

#

# // ...

#

# var protoToCssColor = function(rgb_color) {

1182

# var redFrac = rgb_color.red || 0.0;

1183

# var greenFrac = rgb_color.green || 0.0;

1184

# var blueFrac = rgb_color.blue || 0.0;

1185

# var red = Math.floor(redFrac * 255);

1186

# var green = Math.floor(greenFrac * 255);

1187

# var blue = Math.floor(blueFrac * 255);

1188

#

1189

# if (!('alpha' in rgb_color)) {

1190

# return rgbToCssColor_(red, green, blue);

1191

# }

1192

#

1193

# var alphaFrac = rgb_color.alpha.value || 0.0;

1194

# var rgbParams = [red, green, blue].join(',');

1195

# return ['rgba(', rgbParams, ',', alphaFrac, ')'].join('');

1196

# };

1197

#

1198

# var rgbToCssColor_ = function(red, green, blue) {

1199

# var rgbNumber = new Number((red << 16) | (green << 8) | blue);

1200

# var hexString = rgbNumber.toString(16);

1201

# var missingZeros = 6 - hexString.length;

1202

# var resultBuilder = ['#'];

1203

# for (var i = 0; i < missingZeros; i++) {

1204

# resultBuilder.push('0');

1205

# }

1206

# resultBuilder.push(hexString);

1207

# return resultBuilder.join('');

# };

#

# // ...

"alpha": 3.14, # The fraction of this color that should be applied to the pixel. That is,

1212

# the final pixel color is defined by the equation:

1213

#

1214

# pixel color = alpha * (this color) + (1.0 - alpha) * (background color)

1215

#

1216

# This means that a value of 1.0 corresponds to a solid color, whereas

1217

# a value of 0.0 corresponds to a completely transparent color. This

1218

# uses a wrapper message rather than a simple float scalar so that it is

1219

# possible to distinguish between a default value and the value being unset.

1220

# If omitted, this color object is to be rendered as a solid color

1221

# (as if the alpha value had been explicitly given with a value of 1.0).

1222

"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].

1223

"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].

1224

"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].

1225

},

1226

"fontSize": { # Font size with unit. # Font size.

1227

"size": 3.14, # Font size for the text.

1228

"unit": "A String", # Unit for the font size. Follows CSS naming (in, px, pt, etc.).

1229

},

1230

"backgroundColor": { # Represents a color in the RGBA color space. This representation is designed # Text background color.

1231

# for simplicity of conversion to/from color representations in various

1232

# languages over compactness; for example, the fields of this representation

1233

# can be trivially provided to the constructor of "java.awt.Color" in Java; it

1234

# can also be trivially provided to UIColor's "+colorWithRed:green:blue:alpha"

1235

# method in iOS; and, with just a little work, it can be easily formatted into

1236

# a CSS "rgba()" string in JavaScript, as well.

1237

#

1238

# Note: this proto does not carry information about the absolute color space

1239

# that should be used to interpret the RGB value (e.g. sRGB, Adobe RGB,

1240

# DCI-P3, BT.2020, etc.). By default, applications SHOULD assume the sRGB color

1241

# space.

1242

#

1243

# Note: when color equality needs to be decided, implementations, unless

1244

# documented otherwise, will treat two colors to be equal if all their red,

1245

# green, blue and alpha values each differ by at most 1e-5.

#

# Example (Java):

#

# import com.google.type.Color;

1250

#

1251

# // ...

1252

# public static java.awt.Color fromProto(Color protocolor) {

1253

# float alpha = protocolor.hasAlpha()

1254

# ? protocolor.getAlpha().getValue()

1255

# : 1.0;

1256

#

1257

# return new java.awt.Color(

1258

# protocolor.getRed(),

1259

# protocolor.getGreen(),

1260

# protocolor.getBlue(),

# alpha);

# }

#

# public static Color toProto(java.awt.Color color) {

1265

# float red = (float) color.getRed();

1266

# float green = (float) color.getGreen();

1267

# float blue = (float) color.getBlue();

1268

# float denominator = 255.0;

1269

# Color.Builder resultBuilder =

1270

# Color

1271

# .newBuilder()

1272

# .setRed(red / denominator)

1273

# .setGreen(green / denominator)

1274

# .setBlue(blue / denominator);

1275

# int alpha = color.getAlpha();

1276

# if (alpha != 255) {

# result.setAlpha(

# FloatValue

# .newBuilder()

# .setValue(((float) alpha) / denominator)

1281

# .build());

1282

# }

1283

# return resultBuilder.build();

# }

# // ...

#

# Example (iOS / Obj-C):

1288

#

1289

# // ...

1290

# static UIColor* fromProto(Color* protocolor) {

1291

# float red = [protocolor red];

1292

# float green = [protocolor green];

1293

# float blue = [protocolor blue];

1294

# FloatValue* alpha_wrapper = [protocolor alpha];

1295

# float alpha = 1.0;

1296

# if (alpha_wrapper != nil) {

1297

# alpha = [alpha_wrapper value];

1298

# }

1299

# return [UIColor colorWithRed:red green:green blue:blue alpha:alpha];

1300

# }

1301

#

1302

# static Color* toProto(UIColor* color) {

1303

# CGFloat red, green, blue, alpha;

1304

# if (![color getRed:&red green:&green blue:&blue alpha:&alpha]) {

1305

# return nil;

1306

# }

1307

# Color* result = [[Color alloc] init];

1308

# [result setRed:red];

1309

# [result setGreen:green];

1310

# [result setBlue:blue];

1311

# if (alpha <= 0.9999) {

1312

# [result setAlpha:floatWrapperWithValue(alpha)];

1313

# }

1314

# [result autorelease];

# return result;

# }

# // ...

#

# Example (JavaScript):

#

# // ...

#

# var protoToCssColor = function(rgb_color) {

1324

# var redFrac = rgb_color.red || 0.0;

1325

# var greenFrac = rgb_color.green || 0.0;

1326

# var blueFrac = rgb_color.blue || 0.0;

1327

# var red = Math.floor(redFrac * 255);

1328

# var green = Math.floor(greenFrac * 255);

1329

# var blue = Math.floor(blueFrac * 255);

1330

#

1331

# if (!('alpha' in rgb_color)) {

1332

# return rgbToCssColor_(red, green, blue);

1333

# }

1334

#

1335

# var alphaFrac = rgb_color.alpha.value || 0.0;

1336

# var rgbParams = [red, green, blue].join(',');

1337

# return ['rgba(', rgbParams, ',', alphaFrac, ')'].join('');

1338

# };

1339

#

1340

# var rgbToCssColor_ = function(red, green, blue) {

1341

# var rgbNumber = new Number((red << 16) | (green << 8) | blue);

1342

# var hexString = rgbNumber.toString(16);

1343

# var missingZeros = 6 - hexString.length;

1344

# var resultBuilder = ['#'];

1345

# for (var i = 0; i < missingZeros; i++) {

1346

# resultBuilder.push('0');

1347

# }

1348

# resultBuilder.push(hexString);

1349

# return resultBuilder.join('');

# };

#

# // ...

"alpha": 3.14, # The fraction of this color that should be applied to the pixel. That is,

1354

# the final pixel color is defined by the equation:

1355

#

1356

# pixel color = alpha * (this color) + (1.0 - alpha) * (background color)

1357

#

1358

# This means that a value of 1.0 corresponds to a solid color, whereas

1359

# a value of 0.0 corresponds to a completely transparent color. This

1360

# uses a wrapper message rather than a simple float scalar so that it is

1361

# possible to distinguish between a default value and the value being unset.

1362

# If omitted, this color object is to be rendered as a solid color

1363

# (as if the alpha value had been explicitly given with a value of 1.0).

1364

"blue": 3.14, # The amount of blue in the color as a value in the interval [0, 1].

1365

"green": 3.14, # The amount of green in the color as a value in the interval [0, 1].

1366

"red": 3.14, # The amount of red in the color as a value in the interval [0, 1].

1367

},

1368

"textStyle": "A String", # Text style. Possible values are normal, italic, and oblique.

1369

# https://www.w3schools.com/cssref/pr_font_font-style.asp

1370

},

1371

],

1372

"entities": [ # A list of entities detected on Document.text. For document shards,

1373

# entities in this list may cross shard boundaries.

1374

{ # A phrase in the text that is a known entity type, such as a person, an

1375

# organization, or location.

1376

"textAnchor": { # Text reference indexing into the Document.text. # Provenance of the entity.

1377

# Text anchor indexing into the Document.text.

1378

"textSegments": [ # The text segments from the Document.text.

1379

{ # A text segment in the Document.text. The indices may be out of bounds

1380

# which indicate that the text extends into another document shard for

1381

# large sharded documents. See ShardInfo.text_offset

1382

"startIndex": "A String", # TextSegment start UTF-8 char index in the Document.text.

1383

"endIndex": "A String", # TextSegment half open end UTF-8 char index in the

# Document.text.

},

],

},

"mentionId": "A String", # Deprecated. Use `id` field instead.

1389

"type": "A String", # Entity type from a schema e.g. `Address`.

1390

"confidence": 3.14, # Optional. Confidence of detected Schema entity. Range [0, 1].

1391

"mentionText": "A String", # Text value in the document e.g. `1600 Amphitheatre Pkwy`.

},

],

}</pre>

</div>

</body></html>