first

backend/scripts/create_demo_images.py

@@ -0,0 +1,163 @@
+#!/usr/bin/env python3
+"""
+Create demo images for testing Tool_OCR
+"""
+
+from PIL import Image, ImageDraw, ImageFont
+from pathlib import Path
+
+# Demo docs directory
+DEMO_DIR = Path("/Users/egg/Projects/Tool_OCR/demo_docs")
+
+def create_text_image(text, filename, size=(800, 600), font_size=40):
+    """Create an image with text"""
+    # Create white background
+    img = Image.new('RGB', size, color='white')
+    draw = ImageDraw.Draw(img)
+
+    # Try to use a font, fallback to default
+    try:
+        # Try system fonts
+        font = ImageFont.truetype("/System/Library/Fonts/STHeiti Light.ttc", font_size)
+    except:
+        try:
+            font = ImageFont.truetype("/System/Library/Fonts/Helvetica.ttc", font_size)
+        except:
+            font = ImageFont.load_default()
+
+    # Calculate text position (centered)
+    bbox = draw.textbbox((0, 0), text, font=font)
+    text_width = bbox[2] - bbox[0]
+    text_height = bbox[3] - bbox[1]
+    position = ((size[0] - text_width) // 2, (size[1] - text_height) // 2)
+
+    # Draw text
+    draw.text(position, text, fill='black', font=font)
+
+    # Save image
+    img.save(filename)
+    print(f"Created: {filename}")
+
+def create_multiline_text_image(lines, filename, size=(800, 1000), font_size=30):
+    """Create an image with multiple lines of text"""
+    img = Image.new('RGB', size, color='white')
+    draw = ImageDraw.Draw(img)
+
+    try:
+        font = ImageFont.truetype("/System/Library/Fonts/STHeiti Light.ttc", font_size)
+    except:
+        try:
+            font = ImageFont.truetype("/System/Library/Fonts/Helvetica.ttc", font_size)
+        except:
+            font = ImageFont.load_default()
+
+    # Draw each line
+    y = 50
+    for line in lines:
+        draw.text((50, y), line, fill='black', font=font)
+        y += font_size + 20
+
+    img.save(filename)
+    print(f"Created: {filename}")
+
+def create_table_image(filename, size=(800, 600)):
+    """Create a simple table image"""
+    img = Image.new('RGB', size, color='white')
+    draw = ImageDraw.Draw(img)
+
+    try:
+        font = ImageFont.truetype("/System/Library/Fonts/STHeiti Light.ttc", 24)
+    except:
+        try:
+            font = ImageFont.truetype("/System/Library/Fonts/Helvetica.ttc", 24)
+        except:
+            font = ImageFont.load_default()
+
+    # Draw table borders
+    # Header row
+    draw.rectangle([50, 50, 750, 100], outline='black', width=2)
+    # Row 1
+    draw.rectangle([50, 100, 750, 150], outline='black', width=2)
+    # Row 2
+    draw.rectangle([50, 150, 750, 200], outline='black', width=2)
+    # Row 3
+    draw.rectangle([50, 200, 750, 250], outline='black', width=2)
+
+    # Vertical lines
+    draw.line([250, 50, 250, 250], fill='black', width=2)
+    draw.line([450, 50, 450, 250], fill='black', width=2)
+    draw.line([650, 50, 650, 250], fill='black', width=2)
+
+    # Add text
+    draw.text((60, 65), "姓名", fill='black', font=font)
+    draw.text((260, 65), "年齡", fill='black', font=font)
+    draw.text((460, 65), "部門", fill='black', font=font)
+    draw.text((660, 65), "職位", fill='black', font=font)
+
+    draw.text((60, 115), "張三", fill='black', font=font)
+    draw.text((260, 115), "28", fill='black', font=font)
+    draw.text((460, 115), "技術部", fill='black', font=font)
+    draw.text((660, 115), "工程師", fill='black', font=font)
+
+    draw.text((60, 165), "李四", fill='black', font=font)
+    draw.text((260, 165), "32", fill='black', font=font)
+    draw.text((460, 165), "銷售部", fill='black', font=font)
+    draw.text((660, 165), "經理", fill='black', font=font)
+
+    draw.text((60, 215), "王五", fill='black', font=font)
+    draw.text((260, 215), "25", fill='black', font=font)
+    draw.text((460, 215), "人事部", fill='black', font=font)
+    draw.text((660, 215), "專員", fill='black', font=font)
+
+    img.save(filename)
+    print(f"Created: {filename}")
+
+def main():
+    # Create basic text images
+    basic_dir = DEMO_DIR / "basic"
+    create_text_image(
+        "這是中文繁體測試文檔\nTool_OCR 系統測試",
+        basic_dir / "chinese_traditional.png"
+    )
+
+    create_text_image(
+        "这是中文简体测试文档\nTool_OCR 系统测试",
+        basic_dir / "chinese_simple.png"
+    )
+
+    create_text_image(
+        "This is English Test Document\nTool_OCR System Testing",
+        basic_dir / "english.png"
+    )
+
+    # Create multiline document
+    layout_lines = [
+        "Tool_OCR 文檔處理系統",
+        "",
+        "一、系統簡介",
+        "Tool_OCR 是一個強大的文檔識別系統，支援批次處理、",
+        "版面分析、表格識別等功能。",
+        "",
+        "二、主要功能",
+        "1. 批次文件上傳與處理",
+        "2. OCR 文字識別（支援中英文）",
+        "3. 版面保留 PDF 導出",
+        "4. 表格結構識別",
+        "5. 多種格式導出（TXT, JSON, Excel, MD, PDF）",
+    ]
+    layout_dir = DEMO_DIR / "layout"
+    create_multiline_text_image(layout_lines, layout_dir / "document.png")
+
+    # Create table image
+    tables_dir = DEMO_DIR / "tables"
+    create_table_image(tables_dir / "simple_table.png")
+
+    print("\n✅ Demo images created successfully!")
+    print(f"\n📁 Location: {DEMO_DIR}")
+    print("\nYou can now test these images with Tool_OCR:")
+    print("  - Basic OCR: demo_docs/basic/")
+    print("  - Layout: demo_docs/layout/")
+    print("  - Tables: demo_docs/tables/")
+
+if __name__ == "__main__":
+    main()