feat: A new field schema_override is added to message ProcessOptions

Google APIs · copybara-github · commit 9a9bc9b427e4 · 2024-02-14T16:59:14.000-08:00
feat: A new field `labels` is added to messages `ProcessRequest` and `BatchProcessRequest`
feat: A new field `display_name` is added to message `DocumentSchema`
docs: updated comments

PiperOrigin-RevId: 607148983
diff --git a/google/cloud/documentai/v1/document.proto b/google/cloud/documentai/v1/document.proto
@@ -754,7 +754,8 @@ message Document {
           [deprecated = true, (google.api.field_behavior) = OPTIONAL];
 
       // Optional. Identifies the bounding polygon of a layout element on the
-      // page.
+      // page. If `layout_type` is set, the bounding polygon must be exactly the
+      // same to the layout element it's referring to.
       BoundingPoly bounding_poly = 4 [(google.api.field_behavior) = OPTIONAL];
 
       // Optional. Confidence of detected page element, if applicable. Range
diff --git a/google/cloud/documentai/v1/document_processor_service.proto b/google/cloud/documentai/v1/document_processor_service.proto
@@ -352,9 +352,16 @@ message ProcessOptions {
     int32 from_end = 7;
   }
 
-  // Only applicable to `OCR_PROCESSOR`. Returns error if set on other
-  // processor types.
+  // Only applicable to `OCR_PROCESSOR` and `FORM_PARSER_PROCESSOR`.
+  // Returns error if set on other processor types.
   OcrConfig ocr_config = 1;
+
+  // Optional. Override the schema of the
+  // [ProcessorVersion][google.cloud.documentai.v1.ProcessorVersion]. Will
+  // return an Invalid Argument error if this field is set when the underlying
+  // [ProcessorVersion][google.cloud.documentai.v1.ProcessorVersion] doesn't
+  // support schema override.
+  DocumentSchema schema_override = 8 [(google.api.field_behavior) = OPTIONAL];
 }
 
 // Request message for the
@@ -400,6 +407,14 @@ message ProcessRequest {
 
   // Inference-time options for the process API
   ProcessOptions process_options = 7;
+
+  // Optional. The labels with user-defined metadata for the request.
+  //
+  // Label keys and values can be no longer than 63 characters
+  // (Unicode codepoints) and can only contain lowercase letters, numeric
+  // characters, underscores, and dashes. International characters are allowed.
+  // Label values are optional. Label keys must start with a letter.
+  map<string, string> labels = 10 [(google.api.field_behavior) = OPTIONAL];
 }
 
 // The status of human review on a processed document.
@@ -483,6 +498,14 @@ message BatchProcessRequest {
 
   // Inference-time options for the process API
   ProcessOptions process_options = 7;
+
+  // Optional. The labels with user-defined metadata for the request.
+  //
+  // Label keys and values can be no longer than 63 characters
+  // (Unicode codepoints) and can only contain lowercase letters, numeric
+  // characters, underscores, and dashes. International characters are allowed.
+  // Label values are optional. Label keys must start with a letter.
+  map<string, string> labels = 9 [(google.api.field_behavior) = OPTIONAL];
 }
 
 // Response message for
@@ -803,7 +826,8 @@ message CreateProcessorRequest {
 
   // Required. The processor to be created, requires
   // [Processor.type][google.cloud.documentai.v1.Processor.type] and
-  // [Processor.display_name]][] to be set. Also, the
+  // [Processor.display_name][google.cloud.documentai.v1.Processor.display_name]
+  // to be set. Also, the
   // [Processor.kms_key_name][google.cloud.documentai.v1.Processor.kms_key_name]
   // field must be set if the processor is under CMEK.
   Processor processor = 2 [(google.api.field_behavior) = REQUIRED];
diff --git a/google/cloud/documentai/v1/document_schema.proto b/google/cloud/documentai/v1/document_schema.proto
@@ -39,13 +39,13 @@ message DocumentSchema {
     // Defines properties that can be part of the entity type.
     message Property {
       // Types of occurrences of the entity type in the document.  This
-      // represents the number of instances of an entity, not number of mentions
-      // of an entity.  For example, a bank statement may only have one
-      // `account_number`, but this account number may be mentioned in several
-      // places on the document.  In this case the 'account_number' would be
+      // represents the number of instances, not mentions, of an entity.
+      // For example, a bank statement might only have one
+      // `account_number`, but this account number can be mentioned in several
+      // places on the document.  In this case, the `account_number` is
       // considered a `REQUIRED_ONCE` entity type. If, on the other hand, we
       // expect a bank statement to contain the status of multiple different
-      // accounts for the customers, the occurrence type will be set to
+      // accounts for the customers, the occurrence type is set to
       // `REQUIRED_MULTIPLE`.
       enum OccurrenceType {
         // Unspecified occurrence type.
@@ -70,6 +70,9 @@ message DocumentSchema {
       // EntityType name.
       string name = 1;
 
+      // User defined name for the property.
+      string display_name = 6;
+
       // A reference to the value type of the property.  This type is subject
       // to the same conventions as the `Entity.base_types` field.
       string value_type = 2;
