fa1abcd8e6
Major Features: - Add PDF generation service with Chinese font support - Parse HTML tables from PP-StructureV3 and rebuild with ReportLab - Extract table text for translation purposes - Auto-filter text regions inside tables to avoid overlaps Backend Changes: 1. pdf_generator_service.py (NEW) - HTMLTableParser: Parse HTML tables to extract structure - PDFGeneratorService: Generate layout-preserving PDFs - Coordinate transformation: OCR (top-left) → PDF (bottom-left) - Font size heuristics: 75% of bbox height with width checking - Table reconstruction: Parse HTML → ReportLab Table - Image embedding: Extract bbox from filenames 2. ocr_service.py - Add _extract_table_text() for translation support - Add output_dir parameter to save images to result directory - Extract bbox from image filenames (img_in_table_box_x1_y1_x2_y2.jpg) 3. tasks.py - Update process_task_ocr to use save_results() with PDF generation - Fix download_pdf endpoint to use database-stored PDF paths - Support on-demand PDF generation from JSON 4. config.py - Add chinese_font_path configuration - Add pdf_enable_bbox_debug flag Frontend Changes: 1. PDFViewer.tsx (NEW) - React PDF viewer with zoom and pagination - Memoized file config to prevent unnecessary reloads 2. TaskDetailPage.tsx & ResultsPage.tsx - Integrate PDF preview and download 3. main.tsx - Configure PDF.js worker via CDN 4. vite.config.ts - Add host: '0.0.0.0' for network access - Use VITE_API_URL environment variable for backend proxy Dependencies: - reportlab: PDF generation library - Noto Sans SC font: Chinese character support 🤖 Generated with Claude Code https://claude.com/claude-code Co-Authored-By: Claude <noreply@anthropic.com>
63 lines
1.8 KiB
Python
63 lines
1.8 KiB
Python
"""
|
|
Test script to verify ReportLab and Chinese font rendering
|
|
"""
|
|
from reportlab.pdfgen import canvas
|
|
from reportlab.pdfbase import pdfmetrics
|
|
from reportlab.pdfbase.ttfonts import TTFont
|
|
from pathlib import Path
|
|
import sys
|
|
|
|
def test_chinese_rendering():
|
|
"""Test if Chinese characters can be rendered in PDF"""
|
|
|
|
# Font path
|
|
font_path = "/home/egg/project/Tool_OCR/backend/fonts/NotoSansSC-Regular.ttf"
|
|
|
|
# Check if font file exists
|
|
if not Path(font_path).exists():
|
|
print(f"❌ Font file not found: {font_path}")
|
|
return False
|
|
|
|
print(f"✓ Font file found: {font_path}")
|
|
|
|
try:
|
|
# Register Chinese font
|
|
pdfmetrics.registerFont(TTFont('NotoSansSC', font_path))
|
|
print("✓ Font registered successfully")
|
|
|
|
# Create test PDF
|
|
test_pdf = "/tmp/test_chinese.pdf"
|
|
c = canvas.Canvas(test_pdf)
|
|
|
|
# Set Chinese font
|
|
c.setFont('NotoSansSC', 14)
|
|
|
|
# Draw test text
|
|
c.drawString(100, 750, "測試中文字符渲染 - Test Chinese Character Rendering")
|
|
c.drawString(100, 730, "HTD-S1 技術數據表")
|
|
c.drawString(100, 710, "這是一個 PDF 生成測試")
|
|
|
|
c.save()
|
|
print(f"✓ Test PDF created: {test_pdf}")
|
|
|
|
# Check file size
|
|
file_size = Path(test_pdf).stat().st_size
|
|
print(f"✓ PDF file size: {file_size} bytes")
|
|
|
|
if file_size > 0:
|
|
print("\n✅ Chinese font rendering test PASSED")
|
|
return True
|
|
else:
|
|
print("\n❌ PDF file is empty")
|
|
return False
|
|
|
|
except Exception as e:
|
|
print(f"❌ Error during testing: {e}")
|
|
import traceback
|
|
traceback.print_exc()
|
|
return False
|
|
|
|
if __name__ == "__main__":
|
|
success = test_chinese_rendering()
|
|
sys.exit(0 if success else 1)
|