cfc/docs/参考资料/dan_reports/process_all_pdfs.py

# -*- coding: utf-8 -*-
"""
Process remaining PDFs - analyze content to identify type and add proper prefix
"""
import os
import re
import fitz
from type_detector import detect_type

# Known patterns that already have prefix
ALREADY_PREFIXED = re.compile(r'^(A1_|A2_|B[0-9]_|[A-Z][0-9]\s)')

def identify_report_type(pdf_path):
    """Identify report type by reading PDF content (fingerprint-based)"""
    try:
        doc = fitz.open(pdf_path)
        text = ""
        for page in doc[:5]:
            text += page.get_text()
        doc.close()
        
        report_type, scores = detect_type(text, pdf_path)
        return report_type
    except Exception as e:
        print(f"Error reading {pdf_path}: {e}")
        return 'Error'

def process_files():
    # 自动计算项目根目录
    script_dir = os.path.dirname(os.path.abspath(__file__))
    project_dir = os.path.dirname(os.path.dirname(script_dir))
    reports_dir = os.path.join(project_dir, "报告")
    output_dir = os.path.join(project_dir, "报告")
    
    # Get all PDF files
    all_files = [f for f in os.listdir(reports_dir) if f.endswith('.pdf')]
    
    # Filter to unprocessed files (no proper prefix)
    unprocessed = []
    for f in all_files:
        if not ALREADY_PREFIXED.match(f):
            unprocessed.append(f)
    
    print(f"Total files: {len(all_files)}")
    print(f"Already processed (has prefix): {len(all_files) - len(unprocessed)}")
    print(f"Need to process: {len(unprocessed)}")
    
    # Process in batches
    results = {'A1': [], 'A2': [], 'B2': [], 'B3': [], 'B4': [], 'B5': [], 'B6': [], 'C1': [], 'Unknown': [], 'Error': []}
    
    for i, filename in enumerate(unprocessed):
        if i % 50 == 0:
            print(f"Processing {i}/{len(unprocessed)}...")
        
        pdf_path = os.path.join(reports_dir, filename)
        report_type = identify_report_type(pdf_path)
        results[report_type].append(filename)
        
        # Extract name from filename for renaming
        name_match = re.search(r'[_-](\w+)[_-]\d{13,}', filename)
        if name_match:
            name = name_match.group(1)
        else:
            # Try alternative pattern
            parts = re.split(r'[_\-]', filename)
            name = parts[-2] if len(parts) >= 2 else 'unknown'
        
        # Create new filename with proper prefix
        ext = '.pdf'
        # Get name part (before timestamp)
        name_match = re.search(r'(.+?)_\d{13,}', filename)
        if name_match:
            base_name = name_match.group(1).strip()
            new_filename = f"{report_type}_{base_name}{ext}"
        else:
            new_filename = f"{report_type}_{filename}"
        
        # Rename if not already correct
        if not filename.startswith(report_type + '_'):
            try:
                new_path = os.path.join(reports_dir, new_filename)
                # Check if target exists
                if not os.path.exists(new_path):
                    os.rename(pdf_path, new_path)
                    print(f"Renamed: {filename} -> {new_filename}")
                else:
                    print(f"Skipped (exists): {filename}")
            except Exception as e:
                print(f"Error renaming {filename}: {e}")
    
    # Print summary
    print("\n=== Summary ===")
    for t, files in results.items():
        print(f"{t}: {len(files)}")
    
    return results

if __name__ == "__main__":
    process_files()