docs: update client libraries for Enterprise OCR add-ons

Google APIs · copybara-github · commit 8d03450c69eb · 2023-09-12T10:31:50.000-07:00
PiperOrigin-RevId: 564763833
diff --git a/google/cloud/documentai/v1beta3/document_io.proto b/google/cloud/documentai/v1beta3/document_io.proto
@@ -115,6 +115,19 @@ message OcrConfig {
     repeated string language_hints = 1;
   }
 
+  // Configurations for premium OCR features.
+  message PremiumFeatures {
+    // Turn on selection mark detector in OCR engine. Only available in OCR 2.0+
+    // processors.
+    bool enable_selection_mark_detection = 3;
+
+    // Turn on font identification model and return font style information.
+    bool compute_style_info = 4;
+
+    // Turn on the model that can extract LaTeX math formulas.
+    bool enable_math_ocr = 5;
+  }
+
   // Hints for the OCR model.
   Hints hints = 2;
 
@@ -139,6 +152,16 @@ message OcrConfig {
   // Includes symbol level OCR information if set to true.
   bool enable_symbol = 6;
 
-  // Turn on font id model and returns font style information.
-  bool compute_style_info = 8;
+  // Turn on font identification model and return font style information.
+  // Deprecated, use
+  // [PremiumFeatures.compute_style_info][google.cloud.documentai.v1beta3.OcrConfig.PremiumFeatures.compute_style_info]
+  // instead.
+  bool compute_style_info = 8 [deprecated = true];
+
+  // Turn off character box detector in OCR engine. Character box detection is
+  // enabled by default in OCR 2.0+ processors.
+  bool disable_character_boxes_detection = 10;
+
+  // Configurations for premium OCR features.
+  PremiumFeatures premium_features = 11;
 }
diff --git a/google/cloud/documentai/v1beta3/document_processor_service.proto b/google/cloud/documentai/v1beta3/document_processor_service.proto
@@ -342,6 +342,28 @@ service DocumentProcessorService {
 
 // Options for Process API
 message ProcessOptions {
+  // A list of individual page numbers.
+  message IndividualPageSelector {
+    // Optional. Indices of the pages (starting from 1).
+    repeated int32 pages = 1 [(google.api.field_behavior) = OPTIONAL];
+  }
+
+  // A subset of pages to process. If not specified, all pages will be
+  // processed. NOTICE: If any of the page range is set, we will extract and
+  // process only the given pages from the document. In the output document,
+  // the page_number is referring to the page number in the original document.
+  oneof page_range {
+    // Which pages to process (1-indexed).
+    IndividualPageSelector individual_page_selector = 5;
+
+    // Only process certain pages from the start, process all if the document
+    // has less pages.
+    int32 from_start = 6;
+
+    // Only process certain pages from the end, same as above.
+    int32 from_end = 7;
+  }
+
   // Only applicable to `OCR_PROCESSOR`. Returns error if set on other
   // processor types.
   OcrConfig ocr_config = 1;
