fix: 修復多頁PDF頁碼分配錯誤和logging配置問題

Critical Bug #1: 多頁PDF頁碼分配錯誤
問題：
- 在處理多頁PDF時，雖然text_regions有正確的頁碼標記
- 但layout_data.elements（表格）和images_metadata（圖片）都保持page=0
- 導致所有頁面的表格和圖片都被錯誤地繪製在第1頁
- 造成嚴重的版面錯誤、元素重疊和位置錯誤

根本原因：
- ocr_service.py (第359-372行) 在累積多頁結果時
- text_regions有添加頁碼：region['page'] = page_num
- 但images_metadata和layout_data.elements沒有更新頁碼
- 它們保持單頁處理時的默認值page=0

修復方案：
- backend/app/services/ocr_service.py (第359-372行)
  - 為layout_data.elements中的每個元素添加正確的頁碼
  - 為images_metadata中的每個圖片添加正確的頁碼
  - 確保多頁PDF的每個元素都有正確的page標記

Critical Bug #2: Logging配置被uvicorn覆蓋
問題：
- uvicorn啟動時會設置自己的logging配置
- 這會覆蓋應用程式的logging.basicConfig()
- 導致應用層的INFO/WARNING/ERROR log完全消失
- 只能看到uvicorn的HTTP請求log和第三方庫的DEBUG log
- 無法診斷PDF生成過程中的問題

修復方案：
- backend/app/main.py (第17-36行)
  - 添加force=True參數強制重新配置logging (Python 3.8+)
  - 顯式設置root logger的level
  - 配置app-specific loggers (app.services.pdf_generator_service等)
  - 啟用log propagation確保訊息能傳遞到root logger

其他修復：
- backend/app/services/pdf_generator_service.py
  - 將重要的debug logging改為info level (第371, 379, 490, 613行)
    原因：預設log level是INFO，debug log不會顯示
  - 修復max_cols UnboundLocalError (第507-509行)
    將logger.info()移到max_cols定義之後
  - 移除危險的.get('page', 0)默認值 (第762行)
    改為.get('page')，沒有page的元素會被正確跳過

影響：
✅ 多頁PDF的表格和圖片現在會正確分配到對應頁面
✅ 詳細的PDF生成log現在可以正確顯示（座標轉換、縮放比例等）
✅ 能夠診斷文字擠壓、間距和位置錯誤的問題

測試建議：
1. 重新啟動後端清除Python cache
2. 上傳多頁PDF進行OCR處理
3. 檢查生成的JSON中每個元素是否有正確的page標記
4. 檢查終端log是否顯示詳細的PDF生成過程
5. 驗證生成的PDF中每頁的元素位置是否正確

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

.claude/settings.local.json

@@ -1,78 +1,7 @@
 {
   "permissions": {
     "allow": [
-      "Bash(openspec validate:*)",
+      "Bash(git commit:*)"
-      "Bash(openspec list:*)",
-      "Bash(openspec show:*)",
-      "Bash(conda env:*)",
-      "Bash(alembic init:*)",
-      "Bash(alembic revision:*)",
-      "Bash(python -m alembic revision:*)",
-      "Bash(python test_services.py:*)",
-      "Bash(source ~/.zshrc)",
-      "Bash(conda activate:*)",
-      "Bash(brew install:*)",
-      "Bash(/opt/homebrew/bin/brew install libmagic)",
-      "Bash(python:*)",
-      "Bash(/opt/homebrew/bin/brew install pango gdk-pixbuf libffi)",
-      "Bash(export DYLD_LIBRARY_PATH:*)",
-      "Bash(pip install:*)",
-      "Bash(timeout 5 python:*)",
-      "Bash(curl:*)",
-      "Bash(pkill:*)",
-      "Bash(bash -c \"source ~/.zshrc && conda activate tool_ocr && export DYLD_LIBRARY_PATH=/opt/homebrew/lib:$DYLD_LIBRARY_PATH && python -m app.main > /tmp/tool_ocr_startup.log 2>&1 &\")",
-      "Bash(TOKEN=\"eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOjMsInVzZXJuYW1lIjoiYWRtaW4iLCJleHAiOjE3NjI4ODM1NDF9.sm7zPq7ShErFg3UfBSrzGWxC5m5MgC_L0owKJb7Q4J4\":*)",
-      "Bash(/tmp/login_response.json)",
-      "Bash(cat:*)",
-      "Bash(conda run:*)",
-      "Bash(alembic upgrade:*)",
-      "Bash(lsof:*)",
-      "Bash(xargs kill:*)",
-      "Bash(brew list:*)",
-      "Bash(echo:*)",
-      "Bash(bash -c \"source ~/.zshrc && conda activate tool_ocr && cd /Users/egg/Projects/Tool_OCR/backend && pip list | grep pytest\")",
-      "Bash(bash -c:*)",
-      "Bash(find:*)",
-      "Bash(TOKEN=\"eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOjMsInVzZXJuYW1lIjoiYWRtaW4iLCJleHAiOjE3NjI5MTczMzl9.x5FYcKYpF8rp1M7M7pQsDGwJS1EeQ6RdgRxtNbA2W5E\")",
-      "Bash(TOKEN=\"eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOjMsInVzZXJuYW1lIjoiYWRtaW4iLCJleHAiOjE3NjI5MTczOTN9.oNPbj-SvIl_becIlulXb4DOJ6uHF70hnwlqI-Zfqs1g\")",
-      "Bash(TOKEN=\"eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIzIiwidXNlcm5hbWUiOiJhZG1pbiIsImV4cCI6MTc2MjkxNzQ1NH0.wtLv3n8bR_whzkuYILehy87IBDI_ph8FWEFd7laASEU\")",
-      "Bash(python3:*)",
-      "Bash(TOKEN=\"eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIzIiwidXNlcm5hbWUiOiJhZG1pbiIsImV4cCI6MTc2MjkyMDUzMn0.e_uG5pRTHsnsCEO3yVZDCR4vXXne81Evkw99VDGVZQU\")",
-      "Bash(unzip:*)",
-      "Bash(TOKEN=\"eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIzIiwidXNlcm5hbWUiOiJhZG1pbiIsImV4cCI6MTc2MjkyMDc0OH0.zOpB_2lTi-nVf5B7VMMB9GPeanuo0i-m6iauzjyhCno\")",
-      "Bash(TOKEN=\"eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIzIiwidXNlcm5hbWUiOiJhZG1pbiIsImV4cCI6MTc2MjkyMTExM30.q81VbDDIvQkL3VLl5sCvDEJlha3Rm4hkWMDQmWJyurs\")",
-      "Bash(TOKEN=\"eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIzIiwidXNlcm5hbWUiOiJhZG1pbiIsImV4cCI6MTc2MjkyMTI3OH0.7CQ9NMj5yekdtaRg4v0jHYQmfsbajTZ8aK8kKOo7ixQ\")",
-      "Bash(/Applications/LibreOffice.app/Contents/MacOS/soffice --headless --convert-to docx test_document.html --outdir .)",
-      "Bash(env)",
-      "Bash(node --version:*)",
-      "Bash(npm:*)",
-      "Bash(npx tailwindcss init -p)",
-      "Bash(sqlite3:*)",
-      "Bash(TOKEN=\"eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJzdWIiOiIzIiwidXNlcm5hbWUiOiJhZG1pbiIsImV4cCI6MTc2Mjk1ODUzOX0.S1JjFxVVmifdkN5F_dORt5jTRdTFN9MKJ8UJKuYacA8\")",
-      "Bash(tree:*)",
-      "Bash(done)",
-      "Bash(git add:*)",
-      "Bash(git commit:*)",
-      "Bash(git push)",
-      "Bash(docker --version:*)",
-      "Bash(dpkg:*)",
-      "Bash(pip3:*)",
-      "Bash(chmod:*)",
-      "Bash(sudo apt install:*)",
-      "Bash(/usr/bin/soffice:*)",
-      "Bash(git config:*)",
-      "Bash(source:*)",
-      "Bash(pip uninstall:*)",
-      "Bash(nvidia-smi:*)",
-      "Bash(journalctl:*)",
-      "Bash(ss:*)",
-      "Bash(pip index:*)",
-      "Bash(timeout 10 python:*)",
-      "Bash(alembic current:*)",
-      "Bash(git clean:*)",
-      "Bash(npx tsc:*)",
-      "Bash(./node_modules/.bin/tsc:*)",
-      "Bash(export LD_LIBRARY_PATH=/usr/lib/wsl/lib:$LD_LIBRARY_PATH echo \"Updated LD_LIBRARY_PATH:\" echo \"$LD_LIBRARY_PATH\" echo \"\" echo \"Testing CUDA library loading:\" ldconfig -p)"
     ],
     "deny": [],
     "ask": []

backend/app/main.py

@@ -14,7 +14,7 @@ from app.core.config import settings
 # Ensure log directory exists before configuring logging
 Path(settings.log_file).parent.mkdir(parents=True, exist_ok=True)
 
-# Configure logging
+# Configure logging - Force configuration to override uvicorn's settings
 logging.basicConfig(
     level=getattr(logging, settings.log_level),
     format="%(asctime)s - %(name)s - %(levelname)s - %(message)s",
@@ -22,7 +22,19 @@ logging.basicConfig(
         logging.FileHandler(settings.log_file),
         logging.StreamHandler(),
     ],
+    force=True  # Force reconfiguration (Python 3.8+)
 )
+
+# Also explicitly configure root logger and app loggers
+root_logger = logging.getLogger()
+root_logger.setLevel(getattr(logging, settings.log_level))
+
+# Configure app-specific loggers
+for logger_name in ['app', 'app.services', 'app.services.pdf_generator_service', 'app.services.ocr_service']:
+    app_logger = logging.getLogger(logger_name)
+    app_logger.setLevel(getattr(logging, settings.log_level))
+    app_logger.propagate = True  # Ensure logs propagate to root logger
+
 logger = logging.getLogger(__name__)
 
 

backend/app/services/ocr_service.py

@@ -356,12 +356,19 @@ class OCRService:
                         total_confidence_sum += page_result['average_confidence'] * page_result['total_text_regions']
                         total_valid_regions += page_result['total_text_regions']
 
-                        # Accumulate layout data
+                        # Accumulate layout data and update page numbers
                         if page_result.get('layout_data'):
-                            all_layout_data.append(page_result['layout_data'])
+                            layout_data = page_result['layout_data']
+                            # Update page number for all layout elements
+                            if layout_data.get('elements'):
+                                for element in layout_data['elements']:
+                                    element['page'] = page_num
+                            all_layout_data.append(layout_data)
 
-                        # Accumulate images metadata
+                        # Accumulate images metadata and update page numbers
                         if page_result.get('images_metadata'):
+                            for img_meta in page_result['images_metadata']:
+                                img_meta['page'] = page_num  # Update page number for multi-page PDFs
                             all_images_metadata.extend(page_result['images_metadata'])
 
                         # Store OCR dimensions for each page

backend/app/services/pdf_generator_service.py

@@ -368,7 +368,7 @@ class PDFGeneratorService:
             ocr_x_right = bbox[2][0]   # Right X
             ocr_y_bottom = bbox[2][1]  # Bottom Y in OCR coordinates
 
-            logger.debug(f"[文字] '{text[:20]}...' OCR原始座標: L={ocr_x_left:.0f}, T={ocr_y_top:.0f}, R={ocr_x_right:.0f}, B={ocr_y_bottom:.0f}")
+            logger.info(f"[文字] '{text[:20]}...' OCR原始座標: L={ocr_x_left:.0f}, T={ocr_y_top:.0f}, R={ocr_x_right:.0f}, B={ocr_y_bottom:.0f}")
 
             # Apply scale factors to convert from OCR space to PDF space
             scaled_x_left = ocr_x_left * scale_w
@@ -376,7 +376,7 @@ class PDFGeneratorService:
             scaled_x_right = ocr_x_right * scale_w
             scaled_y_bottom = ocr_y_bottom * scale_h
 
-            logger.debug(f"[文字] '{text[:20]}...' 縮放後(scale={scale_w:.3f},{scale_h:.3f}): L={scaled_x_left:.1f}, T={scaled_y_top:.1f}, R={scaled_x_right:.1f}, B={scaled_y_bottom:.1f}")
+            logger.info(f"[文字] '{text[:20]}...' 縮放後(scale={scale_w:.3f},{scale_h:.3f}): L={scaled_x_left:.1f}, T={scaled_y_top:.1f}, R={scaled_x_right:.1f}, B={scaled_y_bottom:.1f}")
 
             # Calculate bbox dimensions (after scaling)
             bbox_width = abs(scaled_x_right - scaled_x_left)
@@ -487,7 +487,7 @@ class PDFGeneratorService:
             ocr_x_right_raw = table_bbox[2][0]
             ocr_y_bottom_raw = table_bbox[2][1]
 
-            logger.debug(f"[表格] OCR原始座標: L={ocr_x_left_raw:.0f}, T={ocr_y_top_raw:.0f}, R={ocr_x_right_raw:.0f}, B={ocr_y_bottom_raw:.0f}")
+            logger.info(f"[表格] OCR原始座標: L={ocr_x_left_raw:.0f}, T={ocr_y_top_raw:.0f}, R={ocr_x_right_raw:.0f}, B={ocr_y_bottom_raw:.0f}")
 
             # Apply scaling
             ocr_x_left = ocr_x_left_raw * scale_w
@@ -502,11 +502,11 @@ class PDFGeneratorService:
             pdf_x = ocr_x_left
             pdf_y = page_height - ocr_y_bottom
 
-            logger.info(f"[表格] {len(rows)}行x{max_cols}列 → PDF位置: ({pdf_x:.1f}, {pdf_y:.1f}), 寬x高: {table_width:.0f}x{table_height:.0f}")
-
             # Build table data for ReportLab
             # Convert parsed structure to simple 2D array
             max_cols = max(len(row['cells']) for row in rows)
+
+            logger.info(f"[表格] {len(rows)}行x{max_cols}列 → PDF位置: ({pdf_x:.1f}, {pdf_y:.1f}), 寬x高: {table_width:.0f}x{table_height:.0f}")
             reportlab_data = []
 
             for row in rows:
@@ -610,7 +610,7 @@ class PDFGeneratorService:
             ocr_x_right_raw = bbox[2][0]
             ocr_y_bottom_raw = bbox[2][1]
 
-            logger.debug(f"[圖片] '{image_path_str}' OCR原始座標: L={ocr_x_left_raw:.0f}, T={ocr_y_top_raw:.0f}, R={ocr_x_right_raw:.0f}, B={ocr_y_bottom_raw:.0f}")
+            logger.info(f"[圖片] '{image_path_str}' OCR原始座標: L={ocr_x_left_raw:.0f}, T={ocr_y_top_raw:.0f}, R={ocr_x_right_raw:.0f}, B={ocr_y_bottom_raw:.0f}")
 
             # Apply scaling
             ocr_x_left = ocr_x_left_raw * scale_w
@@ -759,7 +759,7 @@ class PDFGeneratorService:
                     self.draw_text_region(pdf_canvas, region, target_height, scale_w, scale_h)
 
                 # Draw tables for this page
-                page_tables = [t for t in table_elements if t.get('page', 0) == page_num - 1]
+                page_tables = [t for t in table_elements if t.get('page') == page_num - 1]
                 logger.info(f"第 {page_num} 頁: 繪製 {len(page_tables)} 個表格")
                 for table_elem in page_tables:
                     self.draw_table_region(pdf_canvas, table_elem, images_metadata, target_height, scale_w, scale_h)