Location or Page

Author: samuelclay

server/resources/book_open_resource.py

@@ -15,14 +15,7 @@
 from server.middleware.profile_middleware import ensure_user_profile_loaded
 from server.middleware.request_deduplication_middleware import deduplicate_request
 from server.middleware.response_handler import handle_automator_response
-from server.utils.ocr_utils import (
-    KindleOCR,
-    cycle_page_indicator_if_needed,
-    is_base64_requested,
-    is_ocr_requested,
-    parse_page_indicators,
-    process_screenshot_with_regions,
-)
+from server.utils.ocr_utils import is_base64_requested, is_ocr_requested
 from server.utils.request_utils import get_sindarin_email
 from views.core.app_state import AppState
 
@@ -235,28 +228,29 @@ def capture_book_state(already_open=False):
                 screenshot_path = os.path.join(automator.screenshots_dir, f"{screenshot_id}.png")
                 automator.driver.save_screenshot(screenshot_path)
 
-                # Get OCR text and page indicators
-                with open(screenshot_path, "rb") as img_file:
-                    image_data = img_file.read()
+                # Import process_screenshot_response
+                from server.utils.ocr_utils import process_screenshot_response
 
-                # Process screenshot with regions to extract both main text and page indicators
-                ocr_results = process_screenshot_with_regions(image_data)
+                # Use process_screenshot_response to get both OCR text and page indicators
+                ocr_data = process_screenshot_response(
+                    screenshot_id, screenshot_path, use_base64=False, perform_ocr=True
+                )
 
-                # Add main text if available
-                if ocr_results.get("main_text"):
-                    response_data["ocr_text"] = ocr_results["main_text"]
+                # Add OCR text if extracted
+                if "ocr_text" in ocr_data:
+                    response_data["ocr_text"] = ocr_data["ocr_text"]
 
-                # Add page indicators if extracted
-                page_indicator_text = ocr_results.get("page_indicator_text")
-                percentage_text = ocr_results.get("percentage_text")
+                # Update progress if page indicators were extracted
+                if "progress" in ocr_data and ocr_data["progress"]:
+                    # Merge the OCR-extracted progress with existing progress
+                    if response_data.get("progress"):
+                        response_data["progress"].update(ocr_data["progress"])
+                    else:
+                        response_data["progress"] = ocr_data["progress"]
 
-                if page_indicator_text or percentage_text:
-                    # Use the cycle function which will tap if needed for time-based indicators
-                    page_indicators = cycle_page_indicator_if_needed(
-                        automator.driver, page_indicator_text, percentage_text
-                    )
-                    if page_indicators:
-                        response_data["progress"].update(page_indicators)
+                # Add any OCR error if present
+                if "ocr_error" in ocr_data:
+                    response_data["ocr_error"] = ocr_data["ocr_error"]
 
                 # Delete the temporary screenshot
                 try:

tests/test_01_api_integration.py

@@ -598,6 +598,7 @@ def test_open_random_book(self):
                 [
                     progress.get("page") is not None,
                     progress.get("location") is not None,
+                    progress.get("current_location") is not None,
                     progress.get("percentage") is not None,
                 ]
             )
@@ -608,6 +609,8 @@ def test_open_random_book(self):
                 print(f"Extracted page: {progress['page']}")
             if progress.get("location"):
                 print(f"Extracted location: {progress['location']}")
+            if progress.get("current_location"):
+                print(f"Extracted current_location: {progress['current_location']}")
             if progress.get("percentage") is not None:
                 print(f"Extracted percentage: {progress['percentage']}%")
 
@@ -656,8 +659,10 @@ def test_navigate_preview(self):
 
             # Check that progress contains expected fields
             assert "percentage" in progress, f"Progress missing percentage field: {progress}"
-            assert "current_page" in progress, f"Progress missing current_page field: {progress}"
-            assert "total_pages" in progress, f"Progress missing total_pages field: {progress}"
+            # Accept either page or location information
+            has_page_info = ("current_page" in progress and "total_pages" in progress)
+            has_location_info = ("current_location" in progress and "total_locations" in progress)
+            assert has_page_info or has_location_info, f"Progress missing page/location fields: {progress}"
 
             # At least one of these should have a non-null value from OCR
             has_valid_data = any(