feat: make page_range field public

fix: `OcrConfig.compute_style_info` is deprecated. Use `PremiumFeatures.compute_style_info` instead.

PiperOrigin-RevId: 568225060

google/cloud/documentai/v1/document_io.proto

@@ -39,7 +39,7 @@ message RawDocument {
   // the following:
   // `*`, `?`, `[`, `]`, `%`, `{`, `}`,`'`, `\"`, `,`
   // `~`, `=` and `:` are reserved.
-  // If not specified, a default ID will be generated.
+  // If not specified, a default ID is generated.
   string display_name = 3;
 }
 
@@ -122,6 +122,19 @@ 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;
 
@@ -146,7 +159,16 @@ 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.
-  // Use PremiumFeatures.compute_style_info instead.
+  // Turn on font identification model and return font style information.
+  // Deprecated, use
+  // [PremiumFeatures.compute_style_info][google.cloud.documentai.v1.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;
 }

google/cloud/documentai/v1/document_processor_service.proto

@@ -328,6 +328,30 @@ 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,
+  // [Document.Page.page_number][google.cloud.documentai.v1.Document.Page.page_number]
+  // is referring to the page number in the original document. This
+  // configuration only applies to sync requests.
+  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 fewer 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;