diff --git a/backend/app/services/ocr_service_original.py b/backend/app/services/ocr_service_original.py deleted file mode 100644 index 0e24d7f..0000000 --- a/backend/app/services/ocr_service_original.py +++ /dev/null @@ -1,835 +0,0 @@ -""" -Tool_OCR - Core OCR Service -PaddleOCR-VL integration for text and structure extraction -""" - -import json -import logging -from pathlib import Path -from typing import Dict, List, Optional, Tuple -from datetime import datetime -import uuid - -from paddleocr import PaddleOCR, PPStructureV3 -from PIL import Image -from pdf2image import convert_from_path -import paddle - -from app.core.config import settings -from app.services.office_converter import OfficeConverter, OfficeConverterError - -logger = logging.getLogger(__name__) - - -class OCRService: - """ - Core OCR service using PaddleOCR-VL - Handles text recognition and document structure analysis - """ - - def __init__(self): - """Initialize PaddleOCR and PPStructure engines with GPU detection""" - self.ocr_languages = settings.ocr_languages_list - self.confidence_threshold = settings.ocr_confidence_threshold - - # Initialize PaddleOCR engine (will be lazy-loaded per language) - self.ocr_engines = {} - - # Initialize PP-Structure for layout analysis - self.structure_engine = None - - # Initialize Office document converter - self.office_converter = OfficeConverter() - - # GPU Detection and Configuration - self.gpu_available = False - self.use_gpu = False - self.gpu_info = {} - - self._detect_and_configure_gpu() - - logger.info("OCR Service initialized") - - def _detect_and_configure_gpu(self): - """Detect GPU availability and configure usage""" - try: - # Check if forced CPU mode - if settings.force_cpu_mode: - logger.info("GPU mode forced to CPU by configuration") - self.use_gpu = False - self.gpu_info = { - 'available': False, - 'reason': 'CPU mode forced by configuration', - } - return - - # Check if PaddlePaddle is compiled with CUDA - if paddle.is_compiled_with_cuda(): - # Check if GPU devices are available - gpu_count = paddle.device.cuda.device_count() - - if gpu_count > 0: - self.gpu_available = True - self.use_gpu = True - - # Get GPU device information - device_id = settings.gpu_device_id if settings.gpu_device_id < gpu_count else 0 - gpu_props = paddle.device.cuda.get_device_properties(device_id) - - self.gpu_info = { - 'available': True, - 'device_count': gpu_count, - 'device_id': device_id, - 'device_name': gpu_props.name, - 'total_memory': gpu_props.total_memory, - 'compute_capability': f"{gpu_props.major}.{gpu_props.minor}", - } - - # Set GPU memory fraction - try: - paddle.device.set_device(f'gpu:{device_id}') - logger.info(f"GPU {device_id} selected: {gpu_props.name}") - logger.info(f"GPU memory: {gpu_props.total_memory / (1024**3):.2f} GB") - logger.info(f"Compute capability: {gpu_props.major}.{gpu_props.minor}") - logger.info(f"GPU memory fraction set to: {settings.gpu_memory_fraction}") - except Exception as e: - logger.warning(f"Failed to configure GPU device: {e}") - self.use_gpu = False - self.gpu_info['available'] = False - self.gpu_info['reason'] = f'GPU configuration failed: {str(e)}' - else: - logger.warning("CUDA is available but no GPU devices found") - self.gpu_info = { - 'available': False, - 'reason': 'CUDA compiled but no GPU devices detected', - } - else: - logger.info("PaddlePaddle not compiled with CUDA support") - self.gpu_info = { - 'available': False, - 'reason': 'PaddlePaddle not compiled with CUDA', - } - - except Exception as e: - logger.error(f"GPU detection failed: {e}") - self.use_gpu = False - self.gpu_info = { - 'available': False, - 'reason': f'GPU detection error: {str(e)}', - } - - # Log final GPU status - if self.use_gpu: - logger.info(f"✓ GPU acceleration ENABLED - Using {self.gpu_info.get('device_name', 'Unknown GPU')}") - else: - reason = self.gpu_info.get('reason', 'Unknown') - logger.info(f"ℹ GPU acceleration DISABLED - {reason} - Using CPU mode") - - def get_gpu_status(self) -> Dict: - """ - Get current GPU status and information - - Returns: - Dictionary with GPU status information - """ - status = { - 'gpu_enabled': self.use_gpu, - 'gpu_available': self.gpu_available, - **self.gpu_info, - } - - # Add current GPU memory usage if GPU is being used - if self.use_gpu and self.gpu_available: - try: - device_id = self.gpu_info.get('device_id', 0) - # Get memory info (returns allocated, total in bytes) - memory_allocated = paddle.device.cuda.memory_allocated(device_id) - memory_reserved = paddle.device.cuda.memory_reserved(device_id) - total_memory = self.gpu_info.get('total_memory', 0) - - status['memory_allocated_mb'] = memory_allocated / (1024**2) - status['memory_reserved_mb'] = memory_reserved / (1024**2) - status['memory_total_mb'] = total_memory / (1024**2) - status['memory_utilization'] = (memory_allocated / total_memory * 100) if total_memory > 0 else 0 - except Exception as e: - logger.warning(f"Failed to get GPU memory info: {e}") - - return status - - def get_ocr_engine(self, lang: str = 'ch') -> PaddleOCR: - """ - Get or create OCR engine for specified language with GPU support - - Args: - lang: Language code (ch, en, japan, korean, etc.) - - Returns: - PaddleOCR engine instance - """ - if lang not in self.ocr_engines: - logger.info(f"Initializing PaddleOCR engine for language: {lang} (GPU: {self.use_gpu})") - - try: - # PaddleOCR 3.x: Device is set globally via paddle.set_device() - # No need to pass device/use_gpu/gpu_mem parameters - self.ocr_engines[lang] = PaddleOCR( - lang=lang, - use_textline_orientation=True, # Replaces deprecated use_angle_cls - ) - logger.info(f"PaddleOCR engine ready for {lang} (PaddlePaddle {paddle.__version__}, {'GPU' if self.use_gpu else 'CPU'} mode)") - - except Exception as e: - # If GPU initialization fails, fall back to CPU - if self.use_gpu: - logger.warning(f"GPU initialization failed, falling back to CPU: {e}") - self.use_gpu = False - # Switch to CPU device globally - paddle.set_device('cpu') - self.ocr_engines[lang] = PaddleOCR( - lang=lang, - use_textline_orientation=True, - ) - logger.info(f"PaddleOCR engine ready for {lang} (CPU mode - fallback)") - else: - raise - - return self.ocr_engines[lang] - - def get_structure_engine(self) -> PPStructureV3: - """ - Get or create PP-Structure engine for layout analysis with GPU support - - Returns: - PPStructure engine instance - """ - if self.structure_engine is None: - logger.info(f"Initializing PP-StructureV3 engine (GPU: {self.use_gpu})") - - try: - # PaddleOCR 3.x: Device is set globally via paddle.set_device() - # No need to pass device/use_gpu/gpu_mem parameters - self.structure_engine = PPStructureV3( - use_doc_orientation_classify=False, - use_doc_unwarping=False, - use_textline_orientation=False, - use_table_recognition=True, - use_formula_recognition=True, - use_chart_recognition=True, # Enable chart recognition (requires PaddlePaddle >= 3.2.0 for fused_rms_norm_ext) - layout_threshold=0.5, - ) - logger.info(f"PP-StructureV3 engine ready (PaddlePaddle {paddle.__version__}, {'GPU' if self.use_gpu else 'CPU'} mode)") - - except Exception as e: - # If GPU initialization fails, fall back to CPU - if self.use_gpu: - logger.warning(f"GPU initialization failed for PP-Structure, falling back to CPU: {e}") - self.use_gpu = False - # Switch to CPU device globally - paddle.set_device('cpu') - self.structure_engine = PPStructureV3( - use_doc_orientation_classify=False, - use_doc_unwarping=False, - use_textline_orientation=False, - use_table_recognition=True, - use_formula_recognition=True, - use_chart_recognition=True, # Enable chart recognition (CPU fallback mode) - layout_threshold=0.5, - ) - logger.info("PP-StructureV3 engine ready (CPU mode - fallback)") - else: - raise - - return self.structure_engine - - def convert_pdf_to_images(self, pdf_path: Path, output_dir: Path) -> List[Path]: - """ - Convert PDF to images (one per page) - - Args: - pdf_path: Path to PDF file - output_dir: Directory to save converted images - - Returns: - List of paths to converted images - """ - try: - output_dir.mkdir(parents=True, exist_ok=True) - - logger.info(f"Converting PDF {pdf_path.name} to images") - - # Convert PDF to images (300 DPI for good quality) - images = convert_from_path( - str(pdf_path), - dpi=300, - fmt='png' - ) - - image_paths = [] - for i, image in enumerate(images): - # Save each page as PNG - image_path = output_dir / f"{pdf_path.stem}_page_{i+1}.png" - image.save(str(image_path), 'PNG') - image_paths.append(image_path) - logger.info(f"Saved page {i+1} to {image_path.name}") - - logger.info(f"Converted {len(image_paths)} pages from PDF") - return image_paths - - except Exception as e: - logger.error(f"PDF conversion error: {str(e)}") - raise - - def process_image( - self, - image_path: Path, - lang: str = 'ch', - detect_layout: bool = True, - confidence_threshold: Optional[float] = None, - output_dir: Optional[Path] = None, - current_page: int = 0 - ) -> Dict: - """ - Process single image with OCR and layout analysis - - Args: - image_path: Path to image file - lang: Language for OCR - detect_layout: Whether to perform layout analysis - confidence_threshold: Minimum confidence threshold (uses default if None) - output_dir: Optional output directory for saving extracted images - current_page: Current page number (0-based) for multi-page documents - - Returns: - Dictionary with OCR results and metadata - """ - start_time = datetime.now() - threshold = confidence_threshold if confidence_threshold is not None else self.confidence_threshold - - try: - # Check if file is Office document - if self.office_converter.is_office_document(image_path): - logger.info(f"Detected Office document: {image_path.name}, converting to PDF") - try: - # Convert Office document to PDF - pdf_path = self.office_converter.convert_to_pdf(image_path) - logger.info(f"Office document converted to PDF: {pdf_path.name}") - - # Process the PDF (will be handled by PDF processing logic below) - image_path = pdf_path - except OfficeConverterError as e: - logger.error(f"Office conversion failed: {str(e)}") - raise - - # Check if file is PDF - is_pdf = image_path.suffix.lower() == '.pdf' - - if is_pdf: - # Convert PDF to images - logger.info(f"Detected PDF file: {image_path.name}, converting to images") - pdf_images_dir = image_path.parent / f"{image_path.stem}_pages" - image_paths = self.convert_pdf_to_images(image_path, pdf_images_dir) - - # Process all pages - all_text_regions = [] - total_confidence_sum = 0.0 - total_valid_regions = 0 - all_layout_data = [] - all_images_metadata = [] - all_ocr_dimensions = [] - - for page_num, page_image_path in enumerate(image_paths, 1): - logger.info(f"Processing PDF page {page_num}/{len(image_paths)}") - - # Process each page with correct page number (0-based for layout data) - page_result = self.process_image( - page_image_path, - lang=lang, - detect_layout=detect_layout, - confidence_threshold=confidence_threshold, - output_dir=output_dir, - current_page=page_num - 1 # Convert to 0-based page number for layout data - ) - - # Accumulate results - if page_result['status'] == 'success': - # Add page number to each text region - for region in page_result['text_regions']: - region['page'] = page_num - all_text_regions.append(region) - - total_confidence_sum += page_result['average_confidence'] * page_result['total_text_regions'] - total_valid_regions += page_result['total_text_regions'] - - # Accumulate layout data (page numbers already set correctly in analyze_layout) - if page_result.get('layout_data'): - layout_data = page_result['layout_data'] - all_layout_data.append(layout_data) - - # Accumulate images metadata (page numbers already set correctly in analyze_layout) - if page_result.get('images_metadata'): - all_images_metadata.extend(page_result['images_metadata']) - - # Store OCR dimensions for each page - if page_result.get('ocr_dimensions'): - all_ocr_dimensions.append({ - 'page': page_num, - 'width': page_result['ocr_dimensions']['width'], - 'height': page_result['ocr_dimensions']['height'] - }) - - # Calculate overall average confidence - avg_confidence = total_confidence_sum / total_valid_regions if total_valid_regions > 0 else 0.0 - - # Combine layout data from all pages - combined_layout = None - if all_layout_data: - combined_elements = [] - for layout in all_layout_data: - if layout.get('elements'): - combined_elements.extend(layout['elements']) - if combined_elements: - combined_layout = { - 'elements': combined_elements, - 'total_elements': len(combined_elements), - 'reading_order': list(range(len(combined_elements))), - } - - # Generate combined markdown - markdown_content = self.generate_markdown(all_text_regions, combined_layout) - - # Calculate processing time - processing_time = (datetime.now() - start_time).total_seconds() - - logger.info( - f"PDF processing completed: {image_path.name} - " - f"{len(image_paths)} pages, " - f"{len(all_text_regions)} regions, " - f"{avg_confidence:.2f} avg confidence, " - f"{processing_time:.2f}s" - ) - - return { - 'status': 'success', - 'file_name': image_path.name, - 'language': lang, - 'text_regions': all_text_regions, - 'total_text_regions': len(all_text_regions), - 'average_confidence': avg_confidence, - 'layout_data': combined_layout, - 'images_metadata': all_images_metadata, - 'markdown_content': markdown_content, - 'processing_time': processing_time, - 'timestamp': datetime.utcnow().isoformat(), - 'total_pages': len(image_paths), - 'ocr_dimensions': all_ocr_dimensions if all_ocr_dimensions else None, - } - - # Get OCR engine (for non-PDF images) - ocr_engine = self.get_ocr_engine(lang) - - # Get the actual image dimensions that OCR will use - from PIL import Image - with Image.open(image_path) as img: - ocr_width, ocr_height = img.size - logger.info(f"OCR processing image dimensions: {ocr_width}x{ocr_height}") - - # Perform OCR - logger.info(f"Processing image: {image_path.name}") - # Note: In PaddleOCR 3.x, use_angle_cls is set during initialization, not in ocr() call - ocr_results = ocr_engine.ocr(str(image_path)) - - # Parse OCR results (PaddleOCR 3.x format) - text_regions = [] - total_confidence = 0.0 - valid_regions = 0 - - if ocr_results and isinstance(ocr_results, (list, tuple)) and len(ocr_results) > 0: - # PaddleOCR 3.x returns a list of dictionaries (one per page) - for page_result in ocr_results: - if isinstance(page_result, dict): - # New format: {'rec_texts': [...], 'rec_scores': [...], 'rec_polys': [...]} - texts = page_result.get('rec_texts', []) - scores = page_result.get('rec_scores', []) - polys = page_result.get('rec_polys', []) - - # Process each recognized text - for idx, text in enumerate(texts): - # Get corresponding score and bbox - confidence = scores[idx] if idx < len(scores) else 1.0 - bbox = polys[idx] if idx < len(polys) else [] - - # Convert numpy array bbox to list for JSON serialization - if hasattr(bbox, 'tolist'): - bbox = bbox.tolist() - - # Filter by confidence threshold - if confidence >= threshold: - text_regions.append({ - 'text': text, - 'bbox': bbox, - 'confidence': float(confidence), - }) - total_confidence += confidence - valid_regions += 1 - - avg_confidence = total_confidence / valid_regions if valid_regions > 0 else 0.0 - - logger.info(f"Parsed {len(text_regions)} text regions with avg confidence {avg_confidence:.3f}") - - # Layout analysis (if requested) - layout_data = None - images_metadata = [] - - if detect_layout: - # Pass current_page to analyze_layout for correct page numbering - layout_data, images_metadata = self.analyze_layout(image_path, output_dir=output_dir, current_page=current_page) - - # Generate Markdown - markdown_content = self.generate_markdown(text_regions, layout_data) - - # Calculate processing time - processing_time = (datetime.now() - start_time).total_seconds() - - result = { - 'status': 'success', - 'file_name': image_path.name, - 'language': lang, - 'text_regions': text_regions, - 'total_text_regions': len(text_regions), - 'average_confidence': avg_confidence, - 'layout_data': layout_data, - 'images_metadata': images_metadata, - 'markdown_content': markdown_content, - 'processing_time': processing_time, - 'timestamp': datetime.utcnow().isoformat(), - 'ocr_dimensions': { - 'width': ocr_width, - 'height': ocr_height - } - } - - logger.info( - f"OCR completed: {image_path.name} - " - f"{len(text_regions)} regions, " - f"{avg_confidence:.2f} avg confidence, " - f"{processing_time:.2f}s" - ) - - return result - - except Exception as e: - import traceback - error_trace = traceback.format_exc() - logger.error(f"OCR processing error for {image_path.name}: {str(e)}\n{error_trace}") - return { - 'status': 'error', - 'file_name': image_path.name, - 'error_message': str(e), - 'processing_time': (datetime.now() - start_time).total_seconds(), - } - - def _extract_table_text(self, html_content: str) -> str: - """ - Extract text from HTML table content for translation purposes - - Args: - html_content: HTML content containing table - - Returns: - Extracted text from table cells - """ - try: - from html.parser import HTMLParser - - class TableTextExtractor(HTMLParser): - def __init__(self): - super().__init__() - self.text_parts = [] - self.in_table = False - - def handle_starttag(self, tag, attrs): - if tag == 'table': - self.in_table = True - - def handle_endtag(self, tag): - if tag == 'table': - self.in_table = False - elif tag in ('td', 'th') and self.in_table: - self.text_parts.append(' | ') # Cell separator - elif tag == 'tr' and self.in_table: - self.text_parts.append('\n') # Row separator - - def handle_data(self, data): - if self.in_table: - stripped = data.strip() - if stripped: - self.text_parts.append(stripped) - - parser = TableTextExtractor() - parser.feed(html_content) - - # Clean up the extracted text - extracted = ''.join(parser.text_parts) - # Remove multiple separators - import re - extracted = re.sub(r'\s*\|\s*\|+\s*', ' | ', extracted) - extracted = re.sub(r'\n+', '\n', extracted) - extracted = extracted.strip() - - return extracted - - except Exception as e: - logger.warning(f"Failed to extract table text: {e}") - # Fallback: just remove HTML tags - import re - text = re.sub(r'<[^>]+>', ' ', html_content) - text = re.sub(r'\s+', ' ', text) - return text.strip() - - def analyze_layout(self, image_path: Path, output_dir: Optional[Path] = None, current_page: int = 0) -> Tuple[Optional[Dict], List[Dict]]: - """ - Analyze document layout using PP-StructureV3 - - Args: - image_path: Path to image file - output_dir: Optional output directory for saving extracted images (defaults to image_path.parent) - current_page: Current page number (0-based) for multi-page documents - - Returns: - Tuple of (layout_data, images_metadata) - """ - try: - structure_engine = self.get_structure_engine() - - # Perform structure analysis using predict() method (PaddleOCR 3.x API) - logger.info(f"Running layout analysis on {image_path.name}") - results = structure_engine.predict(str(image_path)) - - layout_elements = [] - images_metadata = [] - - # Process each page result (for images, usually just one page) - for page_idx, page_result in enumerate(results): - # Get markdown dictionary from result object - if hasattr(page_result, 'markdown'): - markdown_dict = page_result.markdown - logger.info(f"Page {page_idx} markdown keys: {markdown_dict.keys() if isinstance(markdown_dict, dict) else type(markdown_dict)}") - - # Extract layout information from markdown structure - if isinstance(markdown_dict, dict): - # Get markdown texts (HTML format with tables and structure) - markdown_texts = markdown_dict.get('markdown_texts', '') - markdown_images = markdown_dict.get('markdown_images', {}) - - # Create a layout element for the structured content - if markdown_texts: - # Parse HTML content to identify tables and text - import re - - # Check if content contains tables - has_table = ' str: - """ - Generate Markdown from OCR results - - Args: - text_regions: List of text regions with bbox and text - layout_data: Optional layout structure information - - Returns: - Markdown formatted string - """ - markdown_lines = [] - - if layout_data and layout_data.get('elements'): - # Generate structured Markdown based on layout - for element in layout_data['elements']: - element_type = element.get('type', 'text') - content = element.get('content', '') - - if element_type == 'title': - markdown_lines.append(f"# {content}\n") - elif element_type == 'table': - # Table in HTML format - markdown_lines.append(content) - markdown_lines.append("") - elif element_type == 'figure': - element_id = element.get('element_id') - markdown_lines.append(f"![Figure {element_id}](./images/img_{element_id}.jpg)\n") - else: - markdown_lines.append(f"{content}\n") - - else: - # Simple Markdown from text regions only - # Sort by vertical position (top to bottom) - def get_y_coord(region): - """Safely extract Y coordinate from bbox""" - bbox = region.get('bbox', []) - if isinstance(bbox, (list, tuple)) and len(bbox) > 0: - if isinstance(bbox[0], (list, tuple)) and len(bbox[0]) > 1: - return bbox[0][1] # [[x1,y1], [x2,y2], ...] format - elif len(bbox) > 1: - return bbox[1] # [x1, y1, x2, y2, ...] format - return 0 # Default to 0 if can't extract - - sorted_regions = sorted(text_regions, key=get_y_coord) - - for region in sorted_regions: - text = region['text'] - markdown_lines.append(text) - - return "\n".join(markdown_lines) - - def save_results( - self, - result: Dict, - output_dir: Path, - file_id: str, - source_file_path: Optional[Path] = None - ) -> Tuple[Optional[Path], Optional[Path], Optional[Path]]: - """ - Save OCR results to JSON, Markdown, and layout-preserving PDF files - - Args: - result: OCR result dictionary - output_dir: Output directory - file_id: Unique file identifier - source_file_path: Optional path to original source file for PDF generation - - Returns: - Tuple of (json_path, markdown_path, pdf_path) - """ - try: - output_dir.mkdir(parents=True, exist_ok=True) - - # Save JSON - json_path = output_dir / f"{file_id}_result.json" - with open(json_path, 'w', encoding='utf-8') as f: - json.dump(result, f, ensure_ascii=False, indent=2) - - # Save Markdown - markdown_path = output_dir / f"{file_id}_output.md" - markdown_content = result.get('markdown_content', '') - with open(markdown_path, 'w', encoding='utf-8') as f: - f.write(markdown_content) - - logger.info(f"Results saved: {json_path.name}, {markdown_path.name}") - - # Generate layout-preserving PDF - pdf_path = None - try: - from app.services.pdf_generator_service import pdf_generator_service - - pdf_filename = f"{file_id}_layout.pdf" - pdf_path = output_dir / pdf_filename - - logger.info(f"Generating layout-preserving PDF: {pdf_filename}") - - success = pdf_generator_service.generate_layout_pdf( - json_path=json_path, - output_path=pdf_path, - source_file_path=source_file_path - ) - - if success: - logger.info(f"✓ PDF generated successfully: {pdf_path.name}") - else: - logger.warning(f"✗ PDF generation failed for {file_id}") - pdf_path = None - - except Exception as e: - logger.error(f"Error generating PDF for {file_id}: {str(e)}") - import traceback - traceback.print_exc() - pdf_path = None - - return json_path, markdown_path, pdf_path - - except Exception as e: - logger.error(f"Error saving results: {str(e)}") - return None, None, None diff --git a/backend/app/services/pdf_font_manager.py b/backend/app/services/pdf_font_manager.py deleted file mode 100644 index d56f265..0000000 --- a/backend/app/services/pdf_font_manager.py +++ /dev/null @@ -1,312 +0,0 @@ -""" -PDF Font Manager - Handles font loading, registration, and fallback. - -This module provides unified font management for PDF generation, -including CJK font support and font fallback mechanisms. -""" - -import logging -from dataclasses import dataclass -from pathlib import Path -from typing import Dict, List, Optional, Tuple - -from reportlab.pdfbase import pdfmetrics -from reportlab.pdfbase.ttfonts import TTFont - -logger = logging.getLogger(__name__) - - -# ============================================================================ -# Configuration -# ============================================================================ - -@dataclass -class FontConfig: - """Configuration for font management.""" - # Primary fonts - chinese_font_name: str = "NotoSansSC" - chinese_font_path: Optional[Path] = None - - # Fallback fonts (built-in) - fallback_font_name: str = "Helvetica" - fallback_cjk_font_name: str = "HeiseiMin-W3" # Built-in ReportLab CJK - - # Font sizes - default_font_size: int = 10 - min_font_size: int = 6 - max_font_size: int = 14 - - # Font registration options - auto_register: bool = True - enable_cjk_fallback: bool = True - - -# ============================================================================ -# Font Manager -# ============================================================================ - -class FontManager: - """ - Manages font registration and selection for PDF generation. - - Features: - - Lazy font registration - - CJK (Chinese/Japanese/Korean) font support - - Automatic fallback to built-in fonts - - Font caching to avoid duplicate registration - """ - - _instance = None - _registered_fonts: Dict[str, Path] = {} - - def __new__(cls, *args, **kwargs): - """Singleton pattern to avoid duplicate font registration.""" - if cls._instance is None: - cls._instance = super().__new__(cls) - cls._instance._initialized = False - return cls._instance - - def __init__(self, config: Optional[FontConfig] = None): - """ - Initialize FontManager. - - Args: - config: FontConfig instance (uses defaults if None) - """ - if self._initialized: - return - - self.config = config or FontConfig() - self._primary_font_registered = False - self._cjk_fallback_available = False - - # Auto-register fonts if enabled - if self.config.auto_register: - self._register_fonts() - - self._initialized = True - - @property - def primary_font_name(self) -> str: - """Get the primary font name to use.""" - if self._primary_font_registered: - return self.config.chinese_font_name - return self.config.fallback_font_name - - @property - def is_cjk_enabled(self) -> bool: - """Check if CJK fonts are available.""" - return self._primary_font_registered or self._cjk_fallback_available - - @classmethod - def reset(cls): - """Reset singleton instance (for testing).""" - cls._instance = None - cls._registered_fonts = {} - - def get_font_for_text(self, text: str) -> str: - """ - Get appropriate font name for given text. - - Args: - text: Text to render - - Returns: - Font name suitable for the text content - """ - if self._contains_cjk(text): - if self._primary_font_registered: - return self.config.chinese_font_name - elif self._cjk_fallback_available: - return self.config.fallback_cjk_font_name - return self.primary_font_name - - def get_font_size( - self, - text: str, - available_width: float, - available_height: float, - pdf_canvas=None - ) -> int: - """ - Calculate optimal font size for text to fit within bounds. - - Args: - text: Text to render - available_width: Maximum width available - available_height: Maximum height available - pdf_canvas: Optional canvas for precise measurement - - Returns: - Font size that fits within bounds - """ - font_name = self.get_font_for_text(text) - - for size in range(self.config.max_font_size, self.config.min_font_size - 1, -1): - if pdf_canvas: - # Precise measurement with canvas - text_width = pdf_canvas.stringWidth(text, font_name, size) - else: - # Approximate measurement - text_width = len(text) * size * 0.6 # Rough estimate - - text_height = size * 1.2 # Line height - - if text_width <= available_width and text_height <= available_height: - return size - - return self.config.min_font_size - - def register_font( - self, - font_name: str, - font_path: Path, - force: bool = False - ) -> bool: - """ - Register a custom font. - - Args: - font_name: Name to register font under - font_path: Path to TTF font file - force: Force re-registration if already registered - - Returns: - True if registration successful - """ - if font_name in self._registered_fonts and not force: - logger.debug(f"Font {font_name} already registered") - return True - - try: - if not font_path.exists(): - logger.error(f"Font file not found: {font_path}") - return False - - pdfmetrics.registerFont(TTFont(font_name, str(font_path))) - self._registered_fonts[font_name] = font_path - logger.info(f"Font registered: {font_name} from {font_path}") - return True - - except Exception as e: - logger.error(f"Failed to register font {font_name}: {e}") - return False - - def get_registered_fonts(self) -> List[str]: - """Get list of registered custom font names.""" - return list(self._registered_fonts.keys()) - - # ========================================================================= - # Private Methods - # ========================================================================= - - def _register_fonts(self): - """Register configured fonts.""" - # Register primary Chinese font - if self.config.chinese_font_path: - self._register_chinese_font() - - # Setup CJK fallback - if self.config.enable_cjk_fallback: - self._setup_cjk_fallback() - - def _register_chinese_font(self): - """Register the primary Chinese font.""" - font_path = self.config.chinese_font_path - - if font_path is None: - # Try to load from settings - try: - from app.core.config import settings - font_path = Path(settings.chinese_font_path) - except Exception as e: - logger.debug(f"Could not load font path from settings: {e}") - return - - # Resolve relative path - if not font_path.is_absolute(): - # Try project root - project_root = Path(__file__).resolve().parent.parent.parent.parent - font_path = project_root / font_path - - if not font_path.exists(): - logger.warning(f"Chinese font not found at {font_path}") - return - - try: - pdfmetrics.registerFont(TTFont(self.config.chinese_font_name, str(font_path))) - self._registered_fonts[self.config.chinese_font_name] = font_path - self._primary_font_registered = True - logger.info(f"Chinese font registered: {self.config.chinese_font_name}") - except Exception as e: - logger.error(f"Failed to register Chinese font: {e}") - - def _setup_cjk_fallback(self): - """Setup CJK fallback using built-in fonts.""" - try: - # ReportLab includes CID fonts for CJK - from reportlab.pdfbase.cidfonts import UnicodeCIDFont - - # Register CJK fonts if not already registered - try: - pdfmetrics.registerFont(UnicodeCIDFont('HeiseiMin-W3')) - self._cjk_fallback_available = True - logger.debug("CJK fallback font available: HeiseiMin-W3") - except Exception: - pass # Font may already be registered - - except ImportError: - logger.debug("CID fonts not available for CJK fallback") - - def _contains_cjk(self, text: str) -> bool: - """ - Check if text contains CJK characters. - - Args: - text: Text to check - - Returns: - True if text contains Chinese, Japanese, or Korean characters - """ - if not text: - return False - - for char in text: - code = ord(char) - # CJK Unified Ideographs and related ranges - if any([ - 0x4E00 <= code <= 0x9FFF, # CJK Unified Ideographs - 0x3400 <= code <= 0x4DBF, # CJK Extension A - 0x20000 <= code <= 0x2A6DF, # CJK Extension B - 0x3000 <= code <= 0x303F, # CJK Punctuation - 0x3040 <= code <= 0x309F, # Hiragana - 0x30A0 <= code <= 0x30FF, # Katakana - 0xAC00 <= code <= 0xD7AF, # Korean Hangul - ]): - return True - return False - - -# ============================================================================ -# Convenience Functions -# ============================================================================ - -_default_manager: Optional[FontManager] = None - - -def get_font_manager() -> FontManager: - """Get the default FontManager instance.""" - global _default_manager - if _default_manager is None: - _default_manager = FontManager() - return _default_manager - - -def register_font(font_name: str, font_path: Path) -> bool: - """Register a font using the default manager.""" - return get_font_manager().register_font(font_name, font_path) - - -def get_font_for_text(text: str) -> str: - """Get appropriate font for text using the default manager.""" - return get_font_manager().get_font_for_text(text) diff --git a/backend/app/services/preprocessor.py b/backend/app/services/preprocessor.py deleted file mode 100644 index 4953f13..0000000 --- a/backend/app/services/preprocessor.py +++ /dev/null @@ -1,230 +0,0 @@ -""" -Tool_OCR - Document Preprocessor Service -Handles file validation, format detection, and preprocessing -""" - -import magic -from pathlib import Path -from typing import Tuple, Optional -import logging -from PIL import Image -import cv2 -import numpy as np - -from app.core.config import settings - -logger = logging.getLogger(__name__) - - -class DocumentPreprocessor: - """ - Document preprocessing service for format standardization - Validates and prepares documents for OCR processing - """ - - SUPPORTED_IMAGE_FORMATS = ['png', 'jpg', 'jpeg', 'bmp', 'tiff', 'tif'] - SUPPORTED_PDF_FORMAT = ['pdf'] - ALL_SUPPORTED_FORMATS = SUPPORTED_IMAGE_FORMATS + SUPPORTED_PDF_FORMAT - - def __init__(self): - self.allowed_extensions = settings.allowed_extensions_list - self.max_file_size = settings.max_upload_size - logger.info(f"DocumentPreprocessor initialized with allowed_extensions: {self.allowed_extensions}") - - def validate_file(self, file_path: Path) -> Tuple[bool, Optional[str], Optional[str]]: - """ - Validate file format, size, and integrity - - Args: - file_path: Path to the file to validate - - Returns: - Tuple of (is_valid, file_format, error_message) - """ - try: - # Check file exists - if not file_path.exists(): - return False, None, f"File not found: {file_path}" - - # Check file size - file_size = file_path.stat().st_size - if file_size > self.max_file_size: - max_mb = self.max_file_size / (1024 * 1024) - actual_mb = file_size / (1024 * 1024) - return False, None, f"File too large: {actual_mb:.2f}MB (max {max_mb:.2f}MB)" - - # Detect file format using magic numbers - mime = magic.Magic(mime=True) - mime_type = mime.from_file(str(file_path)) - - # Map MIME type to format - file_format = self._mime_to_format(mime_type) - if not file_format: - return False, None, f"Unsupported file type: {mime_type}" - - # Check if format is in allowed extensions - if file_format not in self.allowed_extensions: - return False, None, f"File format '{file_format}' not allowed" - - # Validate file integrity - is_valid, error = self._validate_integrity(file_path, file_format) - if not is_valid: - return False, file_format, f"File corrupted: {error}" - - logger.info(f"File validated successfully: {file_path.name} ({file_format})") - return True, file_format, None - - except Exception as e: - logger.error(f"File validation error: {str(e)}") - return False, None, f"Validation error: {str(e)}" - - def _mime_to_format(self, mime_type: str) -> Optional[str]: - """Convert MIME type to file format""" - mime_map = { - 'image/png': 'png', - 'image/jpeg': 'jpg', - 'image/jpg': 'jpg', - 'image/bmp': 'bmp', - 'image/tiff': 'tiff', - 'image/x-tiff': 'tiff', - 'application/pdf': 'pdf', - 'application/msword': 'doc', - 'application/vnd.openxmlformats-officedocument.wordprocessingml.document': 'docx', - 'application/vnd.ms-powerpoint': 'ppt', - 'application/vnd.openxmlformats-officedocument.presentationml.presentation': 'pptx', - } - return mime_map.get(mime_type) - - def _validate_integrity(self, file_path: Path, file_format: str) -> Tuple[bool, Optional[str]]: - """ - Validate file integrity by attempting to open it - - Args: - file_path: Path to file - file_format: Detected file format - - Returns: - Tuple of (is_valid, error_message) - """ - try: - if file_format in self.SUPPORTED_IMAGE_FORMATS: - # Try to open image - with Image.open(file_path) as img: - img.verify() # Verify image integrity - # Reopen for actual check (verify() closes the file) - with Image.open(file_path) as img: - _ = img.size # Force load to detect corruption - return True, None - - elif file_format == 'pdf': - # Basic PDF validation - check file starts with PDF signature - with open(file_path, 'rb') as f: - header = f.read(5) - if header != b'%PDF-': - return False, "Invalid PDF header" - return True, None - - elif file_format in ['doc', 'docx', 'ppt', 'pptx']: - # Office documents - basic validation (check file size and can be opened) - # Modern Office formats (docx, pptx) are ZIP-based - if file_format in ['docx', 'pptx']: - import zipfile - try: - with zipfile.ZipFile(file_path, 'r') as zf: - # Check if it has the required Office structure - if file_format == 'docx' and 'word/document.xml' not in zf.namelist(): - return False, "Invalid DOCX structure" - elif file_format == 'pptx' and 'ppt/presentation.xml' not in zf.namelist(): - return False, "Invalid PPTX structure" - except zipfile.BadZipFile: - return False, "Invalid Office file (corrupt ZIP)" - # Old formats (doc, ppt) - just check file exists and has content - return True, None - - else: - return False, f"Unknown format: {file_format}" - - except Exception as e: - return False, str(e) - - def preprocess_image( - self, - image_path: Path, - enhance: bool = True, - output_path: Optional[Path] = None - ) -> Tuple[bool, Optional[Path], Optional[str]]: - """ - Preprocess image to improve OCR accuracy - - Args: - image_path: Path to input image - enhance: Whether to apply enhancement - output_path: Optional output path (defaults to temp directory) - - Returns: - Tuple of (success, processed_image_path, error_message) - """ - try: - # Read image - img = cv2.imread(str(image_path)) - if img is None: - return False, None, "Failed to read image" - - if not enhance: - # No preprocessing, return original - return True, image_path, None - - # Convert to grayscale - gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) - - # Apply adaptive thresholding to handle varying lighting - processed = cv2.adaptiveThreshold( - gray, - 255, - cv2.ADAPTIVE_THRESH_GAUSSIAN_C, - cv2.THRESH_BINARY, - 11, - 2 - ) - - # Denoise - processed = cv2.fastNlMeansDenoising(processed, None, 10, 7, 21) - - # Determine output path - if output_path is None: - output_path = Path(settings.processed_dir) / f"processed_{image_path.name}" - - # Save processed image - cv2.imwrite(str(output_path), processed) - - logger.info(f"Image preprocessed: {image_path.name} -> {output_path.name}") - return True, output_path, None - - except Exception as e: - logger.error(f"Image preprocessing error: {str(e)}") - return False, None, f"Preprocessing error: {str(e)}" - - def get_file_info(self, file_path: Path) -> dict: - """ - Get comprehensive file information - - Args: - file_path: Path to file - - Returns: - Dictionary with file information - """ - stat = file_path.stat() - mime = magic.Magic(mime=True) - mime_type = mime.from_file(str(file_path)) - - return { - 'name': file_path.name, - 'path': str(file_path), - 'size': stat.st_size, - 'size_mb': stat.st_size / (1024 * 1024), - 'mime_type': mime_type, - 'format': self._mime_to_format(mime_type), - 'created_at': stat.st_ctime, - 'modified_at': stat.st_mtime, - } diff --git a/frontend/src/components/Layout.tsx b/frontend/src/components/Layout.tsx index 0db8f5a..799a5f7 100644 --- a/frontend/src/components/Layout.tsx +++ b/frontend/src/components/Layout.tsx @@ -1,7 +1,6 @@ import { Outlet, NavLink, useNavigate } from 'react-router-dom' import { useTranslation } from 'react-i18next' import { useAuthStore } from '@/store/authStore' -import { apiClient } from '@/services/api' import { apiClientV2 } from '@/services/apiV2' import { Upload, @@ -29,12 +28,7 @@ export default function Layout() { const handleLogout = async () => { try { - // Use V2 API if authenticated with V2 - if (apiClientV2.isAuthenticated()) { - await apiClientV2.logout() - } else { - apiClient.logout() - } + await apiClientV2.logout() } catch (error) { console.error('Logout error:', error) } finally { diff --git a/frontend/src/components/MarkdownPreview.tsx b/frontend/src/components/MarkdownPreview.tsx deleted file mode 100644 index 3ad5a09..0000000 --- a/frontend/src/components/MarkdownPreview.tsx +++ /dev/null @@ -1,26 +0,0 @@ -import { Card, CardContent, CardHeader, CardTitle } from '@/components/ui/card' - -interface MarkdownPreviewProps { - title?: string - content: string - className?: string -} - -export default function MarkdownPreview({ title, content, className }: MarkdownPreviewProps) { - return ( - - {title && ( - - {title} - - )} - -
- 
-            {content}
-
-
- - - ) -} diff --git a/frontend/src/components/ResultsTable.tsx b/frontend/src/components/ResultsTable.tsx deleted file mode 100644 index 1fac66c..0000000 --- a/frontend/src/components/ResultsTable.tsx +++ /dev/null @@ -1,90 +0,0 @@ -import { useTranslation } from 'react-i18next' -import { Table, TableBody, TableCell, TableHead, TableHeader, TableRow } from '@/components/ui/table' -import { Badge } from '@/components/ui/badge' -import { Button } from '@/components/ui/button' -import type { FileResult } from '@/types/apiV2' - -interface ResultsTableProps { - files: FileResult[] - onViewResult?: (fileId: number) => void - onDownloadPDF?: (fileId: number) => void -} - -export default function ResultsTable({ files, onViewResult, onDownloadPDF }: ResultsTableProps) { - const { t } = useTranslation() - - const getStatusBadge = (status: FileResult['status']) => { - switch (status) { - case 'completed': - return {t('processing.completed')} - case 'processing': - return {t('processing.processing')} - case 'failed': - return {t('processing.failed')} - default: - return {t('processing.pending')} - } - } - - const formatTime = (seconds?: number) => { - if (!seconds) return 'N/A' - return `${seconds.toFixed(2)}s` - } - - return ( -
- - - - {t('results.filename')} - {t('results.status')} - {t('results.processingTime')} - {t('results.actions')} - - - - {files.length === 0 ? ( - - - {t('results.noResults')} - - - ) : ( - files.map((file) => ( - - {file.filename} - {getStatusBadge(file.status)} - {formatTime(file.processing_time)} - -
- {file.status === 'completed' && ( - <> - - - - )} - {file.status === 'failed' && file.error && ( - {file.error} - )} -
- - - )) - )} - -
-
- ) -} diff --git a/frontend/src/pages/SettingsPage.tsx b/frontend/src/pages/SettingsPage.tsx index ff3a9e9..4b686bb 100644 --- a/frontend/src/pages/SettingsPage.tsx +++ b/frontend/src/pages/SettingsPage.tsx @@ -4,7 +4,7 @@ import { useQuery, useMutation, useQueryClient } from '@tanstack/react-query' import { Card, CardContent, CardHeader, CardTitle } from '@/components/ui/card' import { Button } from '@/components/ui/button' import { useToast } from '@/components/ui/toast' -import { apiClient } from '@/services/api' +import { apiClientV2 } from '@/services/apiV2' import type { ExportRule } from '@/types/apiV2' export default function SettingsPage() { @@ -25,12 +25,12 @@ export default function SettingsPage() { // Fetch export rules const { data: exportRules, isLoading } = useQuery({ queryKey: ['exportRules'], - queryFn: () => apiClient.getExportRules(), + queryFn: () => apiClientV2.getExportRules(), }) // Create rule mutation const createRuleMutation = useMutation({ - mutationFn: (rule: any) => apiClient.createExportRule(rule), + mutationFn: (rule: any) => apiClientV2.createExportRule(rule), onSuccess: () => { queryClient.invalidateQueries({ queryKey: ['exportRules'] }) setIsCreating(false) @@ -53,7 +53,7 @@ export default function SettingsPage() { // Update rule mutation const updateRuleMutation = useMutation({ mutationFn: ({ ruleId, rule }: { ruleId: number; rule: any }) => - apiClient.updateExportRule(ruleId, rule), + apiClientV2.updateExportRule(ruleId, rule), onSuccess: () => { queryClient.invalidateQueries({ queryKey: ['exportRules'] }) setEditingRule(null) @@ -75,7 +75,7 @@ export default function SettingsPage() { // Delete rule mutation const deleteRuleMutation = useMutation({ - mutationFn: (ruleId: number) => apiClient.deleteExportRule(ruleId), + mutationFn: (ruleId: number) => apiClientV2.deleteExportRule(ruleId), onSuccess: () => { queryClient.invalidateQueries({ queryKey: ['exportRules'] }) toast({ diff --git a/frontend/src/services/api.ts b/frontend/src/services/api.ts deleted file mode 100644 index 5cc97a9..0000000 --- a/frontend/src/services/api.ts +++ /dev/null @@ -1,271 +0,0 @@ -import axios, { AxiosError } from 'axios' -import type { AxiosInstance } from 'axios' -import type { - LoginRequest, - LoginResponse, - UploadResponse, - ProcessRequest, - ProcessResponse, - BatchStatus, - OCRResult, - ExportRequest, - ExportRule, - CSSTemplate, - TranslateRequest, - TranslateResponse, - ApiError, -} from '@/types/api' - -/** - * API Client Configuration - * - In Docker: VITE_API_BASE_URL is empty string, use relative path - * - In development: Use VITE_API_BASE_URL from .env or default to localhost:8000 - */ -const envApiBaseUrl = import.meta.env.VITE_API_BASE_URL -const API_BASE_URL = envApiBaseUrl !== undefined ? envApiBaseUrl : 'http://localhost:8000' -const API_VERSION = 'v2' - -class ApiClient { - private client: AxiosInstance - private token: string | null = null - - constructor() { - this.client = axios.create({ - baseURL: `${API_BASE_URL}/api/${API_VERSION}`, - timeout: 30000, - headers: { - 'Content-Type': 'application/json', - }, - }) - - // Request interceptor to add auth token - this.client.interceptors.request.use( - (config) => { - if (this.token) { - config.headers.Authorization = `Bearer ${this.token}` - } - return config - }, - (error) => Promise.reject(error) - ) - - // Response interceptor for error handling - this.client.interceptors.response.use( - (response) => response, - (error: AxiosError) => { - if (error.response?.status === 401) { - // Token expired or invalid - this.clearToken() - window.location.href = '/login' - } - return Promise.reject(error) - } - ) - - // Load token from localStorage - this.loadToken() - } - - /** - * Set authentication token - */ - setToken(token: string) { - this.token = token - localStorage.setItem('auth_token', token) - } - - /** - * Clear authentication token - */ - clearToken() { - this.token = null - localStorage.removeItem('auth_token') - } - - /** - * Load token from localStorage - */ - private loadToken() { - const token = localStorage.getItem('auth_token') - if (token) { - this.token = token - } - } - - /** - * Check if user is authenticated - */ - isAuthenticated(): boolean { - return this.token !== null - } - - // ==================== Authentication ==================== - - /** - * Login - */ - async login(data: LoginRequest): Promise { - const response = await this.client.post('/auth/login', { - username: data.username, - password: data.password, - }) - - this.setToken(response.data.access_token) - return response.data - } - - /** - * Logout - */ - logout() { - this.clearToken() - } - - // ==================== File Upload ==================== - - /** - * Upload files - */ - async uploadFiles(files: File[]): Promise { - const formData = new FormData() - files.forEach((file) => { - formData.append('files', file) - }) - - const response = await this.client.post('/upload', formData, { - headers: { - 'Content-Type': 'multipart/form-data', - }, - }) - - return response.data - } - - // ==================== OCR Processing ==================== - - /** - * Process OCR - */ - async processOCR(data: ProcessRequest): Promise { - const response = await this.client.post('/ocr/process', data) - return response.data - } - - /** - * Get OCR result by file ID - * Note: Backend uses file-level tracking, not task-level - */ - async getOCRResult(fileId: number): Promise { - const response = await this.client.get(`/ocr/result/${fileId}`) - return response.data - } - - /** - * Get batch status - */ - async getBatchStatus(batchId: number): Promise { - const response = await this.client.get(`/batch/${batchId}/status`) - return response.data - } - - // ==================== Export ==================== - - /** - * Export results - */ - async exportResults(data: ExportRequest): Promise { - const response = await this.client.post('/export', data, { - responseType: 'blob', - }) - return response.data - } - - /** - * Generate and download PDF - */ - async exportPDF(fileId: number, cssTemplate?: string): Promise { - const params = cssTemplate ? { css_template: cssTemplate } : {} - const response = await this.client.get(`/export/pdf/${fileId}`, { - params, - responseType: 'blob', - }) - return response.data - } - - /** - * Get export rules - */ - async getExportRules(): Promise { - const response = await this.client.get('/export/rules') - return response.data - } - - /** - * Create export rule - */ - async createExportRule(rule: Omit): Promise { - const response = await this.client.post('/export/rules', rule) - return response.data - } - - /** - * Update export rule - */ - async updateExportRule(ruleId: number, rule: Partial): Promise { - const response = await this.client.put(`/export/rules/${ruleId}`, rule) - return response.data - } - - /** - * Delete export rule - */ - async deleteExportRule(ruleId: number): Promise { - await this.client.delete(`/export/rules/${ruleId}`) - } - - /** - * Get CSS templates - */ - async getCSSTemplates(): Promise { - const response = await this.client.get('/export/css-templates') - return response.data - } - - // ==================== Translation (FUTURE FEATURE - STUB) ==================== - - /** - * Translate document (STUB - Not yet implemented) - * This is a placeholder for future translation functionality - * @throws Will throw error with status 501 (Not Implemented) - */ - async translateDocument(data: TranslateRequest): Promise { - // This endpoint is expected to return 501 Not Implemented until Phase 5 - const response = await this.client.post('/translate/document', data) - return response.data - } - - /** - * Get translation configs (NOT IMPLEMENTED) - * This endpoint does not exist on backend - configs will be part of Phase 5 - * @deprecated Backend endpoint does not exist - will return 404 - */ - // async getTranslationConfigs(): Promise { - // const response = await this.client.get('/translate/configs') - // return response.data - // } - - /** - * Create translation config (NOT IMPLEMENTED) - * This endpoint does not exist on backend - configs will be part of Phase 5 - * @deprecated Backend endpoint does not exist - will return 404 - */ - // async createTranslationConfig( - // config: Omit - // ): Promise { - // const response = await this.client.post('/translate/configs', config) - // return response.data - // } -} - -// Export singleton instance -export const apiClient = new ApiClient() diff --git a/frontend/src/services/apiV2.ts b/frontend/src/services/apiV2.ts index 3c36969..5717101 100644 --- a/frontend/src/services/apiV2.ts +++ b/frontend/src/services/apiV2.ts @@ -38,6 +38,7 @@ import type { TranslationStatusResponse, TranslationListResponse, TranslationResult, + ExportRule, } from '@/types/apiV2' /** @@ -713,6 +714,39 @@ class ApiClientV2 { link.click() window.URL.revokeObjectURL(link.href) } + + // ==================== Export Rules APIs ==================== + + /** + * Get export rules + */ + async getExportRules(): Promise { + const response = await this.client.get('/export/rules') + return response.data + } + + /** + * Create export rule + */ + async createExportRule(rule: Omit): Promise { + const response = await this.client.post('/export/rules', rule) + return response.data + } + + /** + * Update export rule + */ + async updateExportRule(ruleId: number, rule: Partial): Promise { + const response = await this.client.put(`/export/rules/${ruleId}`, rule) + return response.data + } + + /** + * Delete export rule + */ + async deleteExportRule(ruleId: number): Promise { + await this.client.delete(`/export/rules/${ruleId}`) + } } // Export singleton instance diff --git a/frontend/src/types/api.ts b/frontend/src/types/api.ts deleted file mode 100644 index eca1a36..0000000 --- a/frontend/src/types/api.ts +++ /dev/null @@ -1,182 +0,0 @@ -/** - * API Type Definitions - * Based on backend OpenAPI specification - */ - -// Authentication -export interface LoginRequest { - username: string - password: string -} - -export interface LoginResponse { - access_token: string - token_type: string - expires_in: number // Token expiration time in seconds -} - -export interface User { - id: number - username: string - email?: string - displayName?: string | null -} - -// File Upload (V2 API) -export interface UploadResponse { - task_id: string - filename: string - file_size: number - file_type: string - status: 'pending' | 'processing' | 'completed' | 'failed' -} - -export interface FileInfo { - id: number - filename: string - file_size: number - file_format: string // Changed from 'format' to match backend - status: 'pending' | 'processing' | 'completed' | 'failed' -} - -// OCR Processing -export interface ProcessRequest { - batch_id: number - lang?: string - detect_layout?: boolean // Changed from confidence_threshold to match backend -} - -export interface ProcessResponse { - message: string // Added to match backend - batch_id: number - total_files: number // Added to match backend - status: string - // Removed task_id - backend uses batch-level tracking instead -} - -export interface TaskStatus { - task_id: string - status: 'pending' | 'processing' | 'completed' | 'failed' - progress_percentage: number - current_file?: string - files_processed: number - total_files: number - error?: string -} - -export interface BatchStatus { - batch: { - id: number - status: 'pending' | 'processing' | 'completed' | 'failed' - progress_percentage: number - created_at: string - completed_at?: string - } - files: FileResult[] -} - -export interface FileResult { - id: number - filename: string - status: 'pending' | 'processing' | 'completed' | 'failed' - processing_time?: number - error?: string -} - -// OCR Results -export interface OCRResult { - file_id: number - filename: string - status: string - markdown_content: string - json_data: OCRJsonData - confidence: number - processing_time: number -} - -export interface OCRJsonData { - total_text_regions: number - average_confidence: number - text_blocks: TextBlock[] - layout_info?: LayoutInfo -} - -export interface TextBlock { - text: string - confidence: number - bbox: [number, number, number, number] - position: number -} - -export interface LayoutInfo { - tables_detected: number - images_detected: number - structure: string -} - -// Export -export interface ExportRequest { - batch_id: number - format: 'txt' | 'json' | 'excel' | 'markdown' | 'pdf' - rule_id?: number - options?: ExportOptions -} - -export interface ExportOptions { - confidence_threshold?: number - include_metadata?: boolean - filename_pattern?: string - css_template?: string -} - -export interface ExportRule { - id: number - rule_name: string - config_json: Record - css_template?: string - created_at: string -} - -export interface CSSTemplate { - name: string - description: string - // filename is not returned by backend - use name as identifier -} - -// Translation (FUTURE FEATURE) -export interface TranslateRequest { - file_id: number - source_lang: string - target_lang: string - engine_type?: 'argos' | 'ernie' | 'google' -} - -export interface TranslateResponse { - task_id: string - file_id: number - status: 'pending' | 'processing' | 'completed' | 'failed' - translated_content?: string -} - -export interface TranslationConfig { - id: number - source_lang: string - target_lang: string - engine_type: 'argos' | 'ernie' | 'google' - engine_config: Record - created_at: string -} - -// API Response -export interface ApiResponse { - success: boolean - data?: T - error?: string - message?: string -} - -// Error Response -export interface ApiError { - detail: string - status_code: number -}