1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990
// This file is @generated by prost-build.
/// A vertex represents a 2D point in the image.
/// NOTE: the vertex coordinates are in the same scale as the original image.
#[derive(Clone, Copy, PartialEq, ::prost::Message)]
pub struct Vertex {
/// X coordinate.
#[prost(int32, tag = "1")]
pub x: i32,
/// Y coordinate.
#[prost(int32, tag = "2")]
pub y: i32,
}
/// 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.
#[derive(Clone, Copy, PartialEq, ::prost::Message)]
pub struct NormalizedVertex {
/// X coordinate.
#[prost(float, tag = "1")]
pub x: f32,
/// Y coordinate.
#[prost(float, tag = "2")]
pub y: f32,
}
/// A bounding polygon for the detected image annotation.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct BoundingPoly {
/// The bounding polygon vertices.
#[prost(message, repeated, tag = "1")]
pub vertices: ::prost::alloc::vec::Vec<Vertex>,
/// The bounding polygon normalized vertices.
#[prost(message, repeated, tag = "2")]
pub normalized_vertices: ::prost::alloc::vec::Vec<NormalizedVertex>,
}
/// Request to batch process documents as an asynchronous operation.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct BatchProcessDocumentsRequest {
/// Required. Individual requests for each document.
#[prost(message, repeated, tag = "1")]
pub requests: ::prost::alloc::vec::Vec<ProcessDocumentRequest>,
/// 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.
#[prost(string, tag = "2")]
pub parent: ::prost::alloc::string::String,
}
/// Request to process one document.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ProcessDocumentRequest {
/// Required. Information about the input file.
#[prost(message, optional, tag = "1")]
pub input_config: ::core::option::Option<InputConfig>,
/// Required. The desired output location.
#[prost(message, optional, tag = "2")]
pub output_config: ::core::option::Option<OutputConfig>,
/// 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.
#[prost(string, tag = "3")]
pub document_type: ::prost::alloc::string::String,
/// Controls table extraction behavior. If not specified, the system will
/// decide reasonable defaults.
#[prost(message, optional, tag = "4")]
pub table_extraction_params: ::core::option::Option<TableExtractionParams>,
/// Controls form extraction behavior. If not specified, the system will
/// decide reasonable defaults.
#[prost(message, optional, tag = "5")]
pub form_extraction_params: ::core::option::Option<FormExtractionParams>,
/// Controls entity extraction behavior. If not specified, the system will
/// decide reasonable defaults.
#[prost(message, optional, tag = "6")]
pub entity_extraction_params: ::core::option::Option<EntityExtractionParams>,
/// Controls OCR behavior. If not specified, the system will decide reasonable
/// defaults.
#[prost(message, optional, tag = "7")]
pub ocr_params: ::core::option::Option<OcrParams>,
}
/// Response to an batch document processing request. This is returned in
/// the LRO Operation after the operation is complete.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct BatchProcessDocumentsResponse {
/// Responses for each individual document.
#[prost(message, repeated, tag = "1")]
pub responses: ::prost::alloc::vec::Vec<ProcessDocumentResponse>,
}
/// Response to a single document processing request.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct ProcessDocumentResponse {
/// Information about the input file. This is the same as the corresponding
/// input config in the request.
#[prost(message, optional, tag = "1")]
pub input_config: ::core::option::Option<InputConfig>,
/// The output location of the parsed responses. The responses are written to
/// this location as JSON-serialized `Document` objects.
#[prost(message, optional, tag = "2")]
pub output_config: ::core::option::Option<OutputConfig>,
}
/// Parameters to control Optical Character Recognition (OCR) behavior.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct OcrParams {
/// 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.
#[prost(string, repeated, tag = "1")]
pub language_hints: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
}
/// Parameters to control table extraction behavior.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct TableExtractionParams {
/// Whether to enable table extraction.
#[prost(bool, tag = "1")]
pub enabled: bool,
/// Optional. Table bounding box hints that can be provided to complex cases
/// which our algorithm cannot locate the table(s) in.
#[prost(message, repeated, tag = "2")]
pub table_bound_hints: ::prost::alloc::vec::Vec<TableBoundHint>,
/// Optional. Table header hints. The extraction will bias towards producing
/// these terms as table headers, which may improve accuracy.
#[prost(string, repeated, tag = "3")]
pub header_hints: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
/// Model version of the table extraction system. Default is "builtin/stable".
/// Specify "builtin/latest" for the latest model.
#[prost(string, tag = "4")]
pub model_version: ::prost::alloc::string::String,
}
/// A hint for a table bounding box on the page for table parsing.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct TableBoundHint {
/// 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.
#[prost(int32, tag = "1")]
pub page_number: i32,
/// 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.
#[prost(message, optional, tag = "2")]
pub bounding_box: ::core::option::Option<BoundingPoly>,
}
/// Parameters to control form extraction behavior.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct FormExtractionParams {
/// Whether to enable form extraction.
#[prost(bool, tag = "1")]
pub enabled: bool,
/// User can provide pairs of (key text, value type) to improve the parsing
/// result.
///
/// For example, if a document has a field called "Date" that holds a date
/// value and a field called "Amount" that may hold either a currency value
/// (e.g., "$500.00") or a simple number value (e.g., "20"), you could use the
/// following hints: \[ {"key": "Date", value_types: [ "DATE"\]}, {"key":
/// "Amount", "value_types": \[ "PRICE", "NUMBER" \]} ]
///
/// If the value type is unknown, but you want to provide hints for the keys,
/// you can leave the value_types field blank. e.g. {"key": "Date",
/// "value_types": \[\]}
#[prost(message, repeated, tag = "2")]
pub key_value_pair_hints: ::prost::alloc::vec::Vec<KeyValuePairHint>,
/// Model version of the form extraction system. Default is
/// "builtin/stable". Specify "builtin/latest" for the latest model.
#[prost(string, tag = "3")]
pub model_version: ::prost::alloc::string::String,
}
/// User-provided hint for key value pair.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct KeyValuePairHint {
/// The key text for the hint.
#[prost(string, tag = "1")]
pub key: ::prost::alloc::string::String,
/// 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.
#[prost(string, repeated, tag = "2")]
pub value_types: ::prost::alloc::vec::Vec<::prost::alloc::string::String>,
}
/// Parameters to control entity extraction behavior.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct EntityExtractionParams {
/// Whether to enable entity extraction.
#[prost(bool, tag = "1")]
pub enabled: bool,
/// Model version of the entity extraction. Default is
/// "builtin/stable". Specify "builtin/latest" for the latest model.
#[prost(string, tag = "2")]
pub model_version: ::prost::alloc::string::String,
}
/// The desired input location and metadata.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct InputConfig {
/// Required. Mimetype of the input. Current supported mimetypes are
/// application/pdf, image/tiff, and image/gif.
#[prost(string, tag = "2")]
pub mime_type: ::prost::alloc::string::String,
/// Required.
#[prost(oneof = "input_config::Source", tags = "1")]
pub source: ::core::option::Option<input_config::Source>,
}
/// Nested message and enum types in `InputConfig`.
pub mod input_config {
/// Required.
#[derive(Clone, PartialEq, ::prost::Oneof)]
pub enum Source {
/// The Google Cloud Storage location to read the input from. This must be a
/// single file.
#[prost(message, tag = "1")]
GcsSource(super::GcsSource),
}
}
/// The desired output location and metadata.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct OutputConfig {
/// 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
#[prost(int32, tag = "2")]
pub pages_per_shard: i32,
/// Required.
#[prost(oneof = "output_config::Destination", tags = "1")]
pub destination: ::core::option::Option<output_config::Destination>,
}
/// Nested message and enum types in `OutputConfig`.
pub mod output_config {
/// Required.
#[derive(Clone, PartialEq, ::prost::Oneof)]
pub enum Destination {
/// The Google Cloud Storage location to write the output to.
#[prost(message, tag = "1")]
GcsDestination(super::GcsDestination),
}
}
/// The Google Cloud Storage location where the input file will be read from.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct GcsSource {
#[prost(string, tag = "1")]
pub uri: ::prost::alloc::string::String,
}
/// The Google Cloud Storage location where the output file will be written to.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct GcsDestination {
#[prost(string, tag = "1")]
pub uri: ::prost::alloc::string::String,
}
/// Contains metadata for the BatchProcessDocuments operation.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct OperationMetadata {
/// The state of the current batch processing.
#[prost(enumeration = "operation_metadata::State", tag = "1")]
pub state: i32,
/// A message providing more details about the current state of processing.
#[prost(string, tag = "2")]
pub state_message: ::prost::alloc::string::String,
/// The creation time of the operation.
#[prost(message, optional, tag = "3")]
pub create_time: ::core::option::Option<::prost_types::Timestamp>,
/// The last update time of the operation.
#[prost(message, optional, tag = "4")]
pub update_time: ::core::option::Option<::prost_types::Timestamp>,
}
/// Nested message and enum types in `OperationMetadata`.
pub mod operation_metadata {
#[derive(
Clone,
Copy,
Debug,
PartialEq,
Eq,
Hash,
PartialOrd,
Ord,
::prost::Enumeration
)]
#[repr(i32)]
pub enum State {
/// The default value. This value is used if the state is omitted.
Unspecified = 0,
/// Request is received.
Accepted = 1,
/// Request operation is waiting for scheduling.
Waiting = 2,
/// Request is being processed.
Running = 3,
/// The batch processing completed successfully.
Succeeded = 4,
/// The batch processing was cancelled.
Cancelled = 5,
/// The batch processing has failed.
Failed = 6,
}
impl State {
/// String value of the enum field names used in the ProtoBuf definition.
///
/// The values are not transformed in any way and thus are considered stable
/// (if the ProtoBuf definition does not change) and safe for programmatic use.
pub fn as_str_name(&self) -> &'static str {
match self {
State::Unspecified => "STATE_UNSPECIFIED",
State::Accepted => "ACCEPTED",
State::Waiting => "WAITING",
State::Running => "RUNNING",
State::Succeeded => "SUCCEEDED",
State::Cancelled => "CANCELLED",
State::Failed => "FAILED",
}
}
/// Creates an enum from field names used in the ProtoBuf definition.
pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
match value {
"STATE_UNSPECIFIED" => Some(Self::Unspecified),
"ACCEPTED" => Some(Self::Accepted),
"WAITING" => Some(Self::Waiting),
"RUNNING" => Some(Self::Running),
"SUCCEEDED" => Some(Self::Succeeded),
"CANCELLED" => Some(Self::Cancelled),
"FAILED" => Some(Self::Failed),
_ => None,
}
}
}
}
/// Generated client implementations.
pub mod document_understanding_service_client {
#![allow(unused_variables, dead_code, missing_docs, clippy::let_unit_value)]
use tonic::codegen::*;
use tonic::codegen::http::Uri;
/// Service to parse structured information from unstructured or semi-structured
/// documents using state-of-the-art Google AI such as natural language,
/// computer vision, and translation.
#[derive(Debug, Clone)]
pub struct DocumentUnderstandingServiceClient<T> {
inner: tonic::client::Grpc<T>,
}
impl<T> DocumentUnderstandingServiceClient<T>
where
T: tonic::client::GrpcService<tonic::body::BoxBody>,
T::Error: Into<StdError>,
T::ResponseBody: Body<Data = Bytes> + std::marker::Send + 'static,
<T::ResponseBody as Body>::Error: Into<StdError> + std::marker::Send,
{
pub fn new(inner: T) -> Self {
let inner = tonic::client::Grpc::new(inner);
Self { inner }
}
pub fn with_origin(inner: T, origin: Uri) -> Self {
let inner = tonic::client::Grpc::with_origin(inner, origin);
Self { inner }
}
pub fn with_interceptor<F>(
inner: T,
interceptor: F,
) -> DocumentUnderstandingServiceClient<InterceptedService<T, F>>
where
F: tonic::service::Interceptor,
T::ResponseBody: Default,
T: tonic::codegen::Service<
http::Request<tonic::body::BoxBody>,
Response = http::Response<
<T as tonic::client::GrpcService<tonic::body::BoxBody>>::ResponseBody,
>,
>,
<T as tonic::codegen::Service<
http::Request<tonic::body::BoxBody>,
>>::Error: Into<StdError> + std::marker::Send + std::marker::Sync,
{
DocumentUnderstandingServiceClient::new(
InterceptedService::new(inner, interceptor),
)
}
/// Compress requests with the given encoding.
///
/// This requires the server to support it otherwise it might respond with an
/// error.
#[must_use]
pub fn send_compressed(mut self, encoding: CompressionEncoding) -> Self {
self.inner = self.inner.send_compressed(encoding);
self
}
/// Enable decompressing responses.
#[must_use]
pub fn accept_compressed(mut self, encoding: CompressionEncoding) -> Self {
self.inner = self.inner.accept_compressed(encoding);
self
}
/// Limits the maximum size of a decoded message.
///
/// Default: `4MB`
#[must_use]
pub fn max_decoding_message_size(mut self, limit: usize) -> Self {
self.inner = self.inner.max_decoding_message_size(limit);
self
}
/// Limits the maximum size of an encoded message.
///
/// Default: `usize::MAX`
#[must_use]
pub fn max_encoding_message_size(mut self, limit: usize) -> Self {
self.inner = self.inner.max_encoding_message_size(limit);
self
}
/// LRO endpoint to batch process many documents.
pub async fn batch_process_documents(
&mut self,
request: impl tonic::IntoRequest<super::BatchProcessDocumentsRequest>,
) -> std::result::Result<
tonic::Response<super::super::super::super::longrunning::Operation>,
tonic::Status,
> {
self.inner
.ready()
.await
.map_err(|e| {
tonic::Status::new(
tonic::Code::Unknown,
format!("Service was not ready: {}", e.into()),
)
})?;
let codec = tonic::codec::ProstCodec::default();
let path = http::uri::PathAndQuery::from_static(
"/google.cloud.documentai.v1beta1.DocumentUnderstandingService/BatchProcessDocuments",
);
let mut req = request.into_request();
req.extensions_mut()
.insert(
GrpcMethod::new(
"google.cloud.documentai.v1beta1.DocumentUnderstandingService",
"BatchProcessDocuments",
),
);
self.inner.unary(req, path, codec).await
}
}
}
/// 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.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct Document {
/// 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.>
#[prost(string, tag = "3")]
pub mime_type: ::prost::alloc::string::String,
/// UTF-8 encoded text in reading order from the document.
#[prost(string, tag = "4")]
pub text: ::prost::alloc::string::String,
/// Styles for the
/// [Document.text][google.cloud.documentai.v1beta1.Document.text].
#[prost(message, repeated, tag = "5")]
pub text_styles: ::prost::alloc::vec::Vec<document::Style>,
/// Visual page layout for the
/// [Document][google.cloud.documentai.v1beta1.Document].
#[prost(message, repeated, tag = "6")]
pub pages: ::prost::alloc::vec::Vec<document::Page>,
/// A list of entities detected on
/// [Document.text][google.cloud.documentai.v1beta1.Document.text]. For
/// document shards, entities in this list may cross shard boundaries.
#[prost(message, repeated, tag = "7")]
pub entities: ::prost::alloc::vec::Vec<document::Entity>,
/// Relationship among
/// [Document.entities][google.cloud.documentai.v1beta1.Document.entities].
#[prost(message, repeated, tag = "8")]
pub entity_relations: ::prost::alloc::vec::Vec<document::EntityRelation>,
/// 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.
#[prost(message, optional, tag = "9")]
pub shard_info: ::core::option::Option<document::ShardInfo>,
/// Any error that occurred while processing this document.
#[prost(message, optional, tag = "10")]
pub error: ::core::option::Option<super::super::super::rpc::Status>,
/// Original source document from the user.
#[prost(oneof = "document::Source", tags = "1, 2")]
pub source: ::core::option::Option<document::Source>,
}
/// Nested message and enum types in `Document`.
pub mod document {
/// For a large document, sharding may be performed to produce several
/// document shards. Each document shard contains this field to detail which
/// shard it is.
#[derive(Clone, Copy, PartialEq, ::prost::Message)]
pub struct ShardInfo {
/// The 0-based index of this shard.
#[prost(int64, tag = "1")]
pub shard_index: i64,
/// Total number of shards.
#[prost(int64, tag = "2")]
pub shard_count: i64,
/// The index of the first character in
/// [Document.text][google.cloud.documentai.v1beta1.Document.text] in the
/// overall document global text.
#[prost(int64, tag = "3")]
pub text_offset: i64,
}
/// Annotation for common text style attributes. This adheres to CSS
/// conventions as much as possible.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct Style {
/// Text anchor indexing into the
/// [Document.text][google.cloud.documentai.v1beta1.Document.text].
#[prost(message, optional, tag = "1")]
pub text_anchor: ::core::option::Option<TextAnchor>,
/// Text color.
#[prost(message, optional, tag = "2")]
pub color: ::core::option::Option<super::super::super::super::r#type::Color>,
/// Text background color.
#[prost(message, optional, tag = "3")]
pub background_color: ::core::option::Option<
super::super::super::super::r#type::Color,
>,
/// Font weight. Possible values are normal, bold, bolder, and lighter.
/// <https://www.w3schools.com/cssref/pr_font_weight.asp>
#[prost(string, tag = "4")]
pub font_weight: ::prost::alloc::string::String,
/// Text style. Possible values are normal, italic, and oblique.
/// <https://www.w3schools.com/cssref/pr_font_font-style.asp>
#[prost(string, tag = "5")]
pub text_style: ::prost::alloc::string::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>
#[prost(string, tag = "6")]
pub text_decoration: ::prost::alloc::string::String,
/// Font size.
#[prost(message, optional, tag = "7")]
pub font_size: ::core::option::Option<style::FontSize>,
}
/// Nested message and enum types in `Style`.
pub mod style {
/// Font size with unit.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct FontSize {
/// Font size for the text.
#[prost(float, tag = "1")]
pub size: f32,
/// Unit for the font size. Follows CSS naming (in, px, pt, etc.).
#[prost(string, tag = "2")]
pub unit: ::prost::alloc::string::String,
}
}
/// A page in a [Document][google.cloud.documentai.v1beta1.Document].
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct Page {
/// 1-based index for current
/// [Page][google.cloud.documentai.v1beta1.Document.Page] in a parent
/// [Document][google.cloud.documentai.v1beta1.Document]. Useful when a page
/// is taken out of a [Document][google.cloud.documentai.v1beta1.Document]
/// for individual processing.
#[prost(int32, tag = "1")]
pub page_number: i32,
/// Physical dimension of the page.
#[prost(message, optional, tag = "2")]
pub dimension: ::core::option::Option<page::Dimension>,
/// [Layout][google.cloud.documentai.v1beta1.Document.Page.Layout] for the
/// page.
#[prost(message, optional, tag = "3")]
pub layout: ::core::option::Option<page::Layout>,
/// A list of detected languages together with confidence.
#[prost(message, repeated, tag = "4")]
pub detected_languages: ::prost::alloc::vec::Vec<page::DetectedLanguage>,
/// 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.
#[prost(message, repeated, tag = "5")]
pub blocks: ::prost::alloc::vec::Vec<page::Block>,
/// A list of visually detected text paragraphs on the page.
/// A collection of lines that a human would perceive as a paragraph.
#[prost(message, repeated, tag = "6")]
pub paragraphs: ::prost::alloc::vec::Vec<page::Paragraph>,
/// A list of visually detected text lines on the page.
/// A collection of tokens that a human would perceive as a line.
#[prost(message, repeated, tag = "7")]
pub lines: ::prost::alloc::vec::Vec<page::Line>,
/// A list of visually detected tokens on the page.
#[prost(message, repeated, tag = "8")]
pub tokens: ::prost::alloc::vec::Vec<page::Token>,
/// A list of detected non-text visual elements e.g. checkbox,
/// signature etc. on the page.
#[prost(message, repeated, tag = "9")]
pub visual_elements: ::prost::alloc::vec::Vec<page::VisualElement>,
/// A list of visually detected tables on the page.
#[prost(message, repeated, tag = "10")]
pub tables: ::prost::alloc::vec::Vec<page::Table>,
/// A list of visually detected form fields on the page.
#[prost(message, repeated, tag = "11")]
pub form_fields: ::prost::alloc::vec::Vec<page::FormField>,
}
/// Nested message and enum types in `Page`.
pub mod page {
/// Dimension for the page.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct Dimension {
/// Page width.
#[prost(float, tag = "1")]
pub width: f32,
/// Page height.
#[prost(float, tag = "2")]
pub height: f32,
/// Dimension unit.
#[prost(string, tag = "3")]
pub unit: ::prost::alloc::string::String,
}
/// Visual element describing a layout unit on a page.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct Layout {
/// Text anchor indexing into the
/// [Document.text][google.cloud.documentai.v1beta1.Document.text].
#[prost(message, optional, tag = "1")]
pub text_anchor: ::core::option::Option<super::TextAnchor>,
/// Confidence of the current
/// [Layout][google.cloud.documentai.v1beta1.Document.Page.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 \[0, 1\].
#[prost(float, tag = "2")]
pub confidence: f32,
/// The bounding polygon for the
/// [Layout][google.cloud.documentai.v1beta1.Document.Page.Layout].
#[prost(message, optional, tag = "3")]
pub bounding_poly: ::core::option::Option<super::super::BoundingPoly>,
/// Detected orientation for the
/// [Layout][google.cloud.documentai.v1beta1.Document.Page.Layout].
#[prost(enumeration = "layout::Orientation", tag = "4")]
pub orientation: i32,
}
/// Nested message and enum types in `Layout`.
pub mod layout {
/// Detected human reading orientation.
#[derive(
Clone,
Copy,
Debug,
PartialEq,
Eq,
Hash,
PartialOrd,
Ord,
::prost::Enumeration
)]
#[repr(i32)]
pub enum Orientation {
/// Unspecified orientation.
Unspecified = 0,
/// Orientation is aligned with page up.
PageUp = 1,
/// Orientation is aligned with page right.
/// Turn the head 90 degrees clockwise from upright to read.
PageRight = 2,
/// Orientation is aligned with page down.
/// Turn the head 180 degrees from upright to read.
PageDown = 3,
/// Orientation is aligned with page left.
/// Turn the head 90 degrees counterclockwise from upright to read.
PageLeft = 4,
}
impl Orientation {
/// String value of the enum field names used in the ProtoBuf definition.
///
/// The values are not transformed in any way and thus are considered stable
/// (if the ProtoBuf definition does not change) and safe for programmatic use.
pub fn as_str_name(&self) -> &'static str {
match self {
Orientation::Unspecified => "ORIENTATION_UNSPECIFIED",
Orientation::PageUp => "PAGE_UP",
Orientation::PageRight => "PAGE_RIGHT",
Orientation::PageDown => "PAGE_DOWN",
Orientation::PageLeft => "PAGE_LEFT",
}
}
/// Creates an enum from field names used in the ProtoBuf definition.
pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
match value {
"ORIENTATION_UNSPECIFIED" => Some(Self::Unspecified),
"PAGE_UP" => Some(Self::PageUp),
"PAGE_RIGHT" => Some(Self::PageRight),
"PAGE_DOWN" => Some(Self::PageDown),
"PAGE_LEFT" => Some(Self::PageLeft),
_ => None,
}
}
}
}
/// A block has a set of lines (collected into paragraphs) that have a
/// common line-spacing and orientation.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct Block {
/// [Layout][google.cloud.documentai.v1beta1.Document.Page.Layout] for
/// [Block][google.cloud.documentai.v1beta1.Document.Page.Block].
#[prost(message, optional, tag = "1")]
pub layout: ::core::option::Option<Layout>,
/// A list of detected languages together with confidence.
#[prost(message, repeated, tag = "2")]
pub detected_languages: ::prost::alloc::vec::Vec<DetectedLanguage>,
}
/// A collection of lines that a human would perceive as a paragraph.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct Paragraph {
/// [Layout][google.cloud.documentai.v1beta1.Document.Page.Layout] for
/// [Paragraph][google.cloud.documentai.v1beta1.Document.Page.Paragraph].
#[prost(message, optional, tag = "1")]
pub layout: ::core::option::Option<Layout>,
/// A list of detected languages together with confidence.
#[prost(message, repeated, tag = "2")]
pub detected_languages: ::prost::alloc::vec::Vec<DetectedLanguage>,
}
/// A collection of tokens that a human would perceive as a line.
/// Does not cross column boundaries, can be horizontal, vertical, etc.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct Line {
/// [Layout][google.cloud.documentai.v1beta1.Document.Page.Layout] for
/// [Line][google.cloud.documentai.v1beta1.Document.Page.Line].
#[prost(message, optional, tag = "1")]
pub layout: ::core::option::Option<Layout>,
/// A list of detected languages together with confidence.
#[prost(message, repeated, tag = "2")]
pub detected_languages: ::prost::alloc::vec::Vec<DetectedLanguage>,
}
/// A detected token.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct Token {
/// [Layout][google.cloud.documentai.v1beta1.Document.Page.Layout] for
/// [Token][google.cloud.documentai.v1beta1.Document.Page.Token].
#[prost(message, optional, tag = "1")]
pub layout: ::core::option::Option<Layout>,
/// Detected break at the end of a
/// [Token][google.cloud.documentai.v1beta1.Document.Page.Token].
#[prost(message, optional, tag = "2")]
pub detected_break: ::core::option::Option<token::DetectedBreak>,
/// A list of detected languages together with confidence.
#[prost(message, repeated, tag = "3")]
pub detected_languages: ::prost::alloc::vec::Vec<DetectedLanguage>,
}
/// Nested message and enum types in `Token`.
pub mod token {
/// Detected break at the end of a
/// [Token][google.cloud.documentai.v1beta1.Document.Page.Token].
#[derive(Clone, Copy, PartialEq, ::prost::Message)]
pub struct DetectedBreak {
/// Detected break type.
#[prost(enumeration = "detected_break::Type", tag = "1")]
pub r#type: i32,
}
/// Nested message and enum types in `DetectedBreak`.
pub mod detected_break {
/// Enum to denote the type of break found.
#[derive(
Clone,
Copy,
Debug,
PartialEq,
Eq,
Hash,
PartialOrd,
Ord,
::prost::Enumeration
)]
#[repr(i32)]
pub enum Type {
/// Unspecified break type.
Unspecified = 0,
/// A single whitespace.
Space = 1,
/// A wider whitespace.
WideSpace = 2,
/// A hyphen that indicates that a token has been split across lines.
Hyphen = 3,
}
impl Type {
/// String value of the enum field names used in the ProtoBuf definition.
///
/// The values are not transformed in any way and thus are considered stable
/// (if the ProtoBuf definition does not change) and safe for programmatic use.
pub fn as_str_name(&self) -> &'static str {
match self {
Type::Unspecified => "TYPE_UNSPECIFIED",
Type::Space => "SPACE",
Type::WideSpace => "WIDE_SPACE",
Type::Hyphen => "HYPHEN",
}
}
/// Creates an enum from field names used in the ProtoBuf definition.
pub fn from_str_name(value: &str) -> ::core::option::Option<Self> {
match value {
"TYPE_UNSPECIFIED" => Some(Self::Unspecified),
"SPACE" => Some(Self::Space),
"WIDE_SPACE" => Some(Self::WideSpace),
"HYPHEN" => Some(Self::Hyphen),
_ => None,
}
}
}
}
}
/// Detected non-text visual elements e.g. checkbox, signature etc. on the
/// page.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct VisualElement {
/// [Layout][google.cloud.documentai.v1beta1.Document.Page.Layout] for
/// [Token][google.cloud.documentai.v1beta1.Document.Page.Token].
#[prost(message, optional, tag = "1")]
pub layout: ::core::option::Option<Layout>,
/// Type of the
/// [VisualElement][google.cloud.documentai.v1beta1.Document.Page.VisualElement].
#[prost(string, tag = "2")]
pub r#type: ::prost::alloc::string::String,
/// A list of detected languages together with confidence.
#[prost(message, repeated, tag = "3")]
pub detected_languages: ::prost::alloc::vec::Vec<DetectedLanguage>,
}
/// A table representation similar to HTML table structure.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct Table {
/// [Layout][google.cloud.documentai.v1beta1.Document.Page.Layout] for
/// [Table][google.cloud.documentai.v1beta1.Document.Page.Table].
#[prost(message, optional, tag = "1")]
pub layout: ::core::option::Option<Layout>,
/// Header rows of the table.
#[prost(message, repeated, tag = "2")]
pub header_rows: ::prost::alloc::vec::Vec<table::TableRow>,
/// Body rows of the table.
#[prost(message, repeated, tag = "3")]
pub body_rows: ::prost::alloc::vec::Vec<table::TableRow>,
/// A list of detected languages together with confidence.
#[prost(message, repeated, tag = "4")]
pub detected_languages: ::prost::alloc::vec::Vec<DetectedLanguage>,
}
/// Nested message and enum types in `Table`.
pub mod table {
/// A row of table cells.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct TableRow {
/// Cells that make up this row.
#[prost(message, repeated, tag = "1")]
pub cells: ::prost::alloc::vec::Vec<TableCell>,
}
/// A cell representation inside the table.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct TableCell {
/// [Layout][google.cloud.documentai.v1beta1.Document.Page.Layout] for
/// [TableCell][google.cloud.documentai.v1beta1.Document.Page.Table.TableCell].
#[prost(message, optional, tag = "1")]
pub layout: ::core::option::Option<super::Layout>,
/// How many rows this cell spans.
#[prost(int32, tag = "2")]
pub row_span: i32,
/// How many columns this cell spans.
#[prost(int32, tag = "3")]
pub col_span: i32,
/// A list of detected languages together with confidence.
#[prost(message, repeated, tag = "4")]
pub detected_languages: ::prost::alloc::vec::Vec<
super::DetectedLanguage,
>,
}
}
/// A form field detected on the page.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct FormField {
/// [Layout][google.cloud.documentai.v1beta1.Document.Page.Layout] for the
/// [FormField][google.cloud.documentai.v1beta1.Document.Page.FormField]
/// name. e.g. `Address`, `Email`, `Grand total`, `Phone number`, etc.
#[prost(message, optional, tag = "1")]
pub field_name: ::core::option::Option<Layout>,
/// [Layout][google.cloud.documentai.v1beta1.Document.Page.Layout] for the
/// [FormField][google.cloud.documentai.v1beta1.Document.Page.FormField]
/// value.
#[prost(message, optional, tag = "2")]
pub field_value: ::core::option::Option<Layout>,
/// A list of detected languages for name together with confidence.
#[prost(message, repeated, tag = "3")]
pub name_detected_languages: ::prost::alloc::vec::Vec<DetectedLanguage>,
/// A list of detected languages for value together with confidence.
#[prost(message, repeated, tag = "4")]
pub value_detected_languages: ::prost::alloc::vec::Vec<DetectedLanguage>,
}
/// Detected language for a structural component.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct DetectedLanguage {
/// 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.>
#[prost(string, tag = "1")]
pub language_code: ::prost::alloc::string::String,
/// Confidence of detected language. Range \[0, 1\].
#[prost(float, tag = "2")]
pub confidence: f32,
}
}
/// A phrase in the text that is a known entity type, such as a person, an
/// organization, or location.
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct Entity {
/// Provenance of the entity.
/// Text anchor indexing into the
/// [Document.text][google.cloud.documentai.v1beta1.Document.text].
#[prost(message, optional, tag = "1")]
pub text_anchor: ::core::option::Option<TextAnchor>,
/// Required. Entity type from a schema e.g. `Address`.
#[prost(string, tag = "2")]
pub r#type: ::prost::alloc::string::String,
/// Text value in the document e.g. `1600 Amphitheatre Pkwy`.
#[prost(string, tag = "3")]
pub mention_text: ::prost::alloc::string::String,
/// Canonical mention name. This will be a unique value in the entity list
/// for this document.
#[prost(string, tag = "4")]
pub mention_id: ::prost::alloc::string::String,
}
/// Relationship between
/// [Entities][google.cloud.documentai.v1beta1.Document.Entity].
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct EntityRelation {
/// Subject entity mention_id.
#[prost(string, tag = "1")]
pub subject_id: ::prost::alloc::string::String,
/// Object entity mention_id.
#[prost(string, tag = "2")]
pub object_id: ::prost::alloc::string::String,
/// Relationship description.
#[prost(string, tag = "3")]
pub relation: ::prost::alloc::string::String,
}
/// Text reference indexing into the
/// [Document.text][google.cloud.documentai.v1beta1.Document.text].
#[derive(Clone, PartialEq, ::prost::Message)]
pub struct TextAnchor {
/// The text segments from the
/// [Document.text][google.cloud.documentai.v1beta1.Document.text].
#[prost(message, repeated, tag = "1")]
pub text_segments: ::prost::alloc::vec::Vec<text_anchor::TextSegment>,
}
/// Nested message and enum types in `TextAnchor`.
pub mod text_anchor {
/// A text segment in the
/// [Document.text][google.cloud.documentai.v1beta1.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][google.cloud.documentai.v1beta1.Document.ShardInfo.text_offset]
#[derive(Clone, Copy, PartialEq, ::prost::Message)]
pub struct TextSegment {
/// [TextSegment][google.cloud.documentai.v1beta1.Document.TextAnchor.TextSegment]
/// start UTF-8 char index in the
/// [Document.text][google.cloud.documentai.v1beta1.Document.text].
#[prost(int64, tag = "1")]
pub start_index: i64,
/// [TextSegment][google.cloud.documentai.v1beta1.Document.TextAnchor.TextSegment]
/// half open end UTF-8 char index in the
/// [Document.text][google.cloud.documentai.v1beta1.Document.text].
#[prost(int64, tag = "2")]
pub end_index: i64,
}
}
/// Original source document from the user.
#[derive(Clone, PartialEq, ::prost::Oneof)]
pub enum Source {
/// 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.
#[prost(string, tag = "1")]
Uri(::prost::alloc::string::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.
#[prost(bytes, tag = "2")]
Content(::prost::bytes::Bytes),
}
}