app.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
🤖 Arabic OCR - Hugging Face Spaces Version
Model: Qwen3.5-0.8B-VL with LoRA
No Quantization - Full Precision
"""

import os
import time
import torch
from PIL import Image
import gradio as gr
from transformers import AutoProcessor, Qwen3_5ForConditionalGeneration
from qwen_vl_utils import process_vision_info

# ==================== ⚙️ إعدادات الجهاز ====================
if torch.cuda.is_available():
    device = "cuda"
    dtype = torch.float16
    print(f"✅ Using GPU: {torch.cuda.get_device_name(0)}")
elif torch.backends.mps.is_available():
    device = "mps"
    dtype = torch.float16
    print("✅ Using Apple Silicon (MPS)")
else:
    device = "cpu"
    dtype = torch.float32
    print("⚠️ Using CPU (slower inference)")

print(f"[INFO] Device: {device} | Dtype: {dtype}")

# ==================== 🔄 تحميل النموذج ====================
def load_model():
    """تحميل النموذج والمعالج مع إدارة الذاكرة"""
    model_path = os.getenv("MODEL_PATH", "sherif1313/Arabic-Qwen3.5-OCR-v4")
    
    print(f"[INFO] Loading model from: {model_path}")
    
    processor = AutoProcessor.from_pretrained(model_path, trust_remote_code=True)
    
    model = Qwen3_5ForConditionalGeneration.from_pretrained(
        model_path,
        torch_dtype=dtype,
        device_map="auto" if device == "cuda" else None,
        trust_remote_code=True,
        low_cpu_mem_usage=True,
    )
    
    model.eval()
    print("[INFO] Model loaded successfully!")
    return model, processor

# تحميل عالمي (يتم مرة واحدة عند بدء التطبيق)
try:
    model, processor = load_model()
except Exception as e:
    print(f"[ERROR] Failed to load model: {e}")
    model = None
    processor = None

# ==================== 🧹 دوال مساعدة ====================
def prepare_image(image: Image.Image, max_size: int = 768) -> Image.Image:
    """تحضير الصورة: ضغط + ضبط الأبعاد لمضاعفات 64"""
    if max(image.size) > max_size:
        image.thumbnail((max_size, max_size), Image.Resampling.LANCZOS)
    
    w, h = image.size
    new_w = ((w + 63) // 64) * 64
    new_h = ((h + 63) // 64) * 64
    if (new_w, new_h) != image.size:
        image = image.resize((new_w, new_h), Image.Resampling.LANCZOS)
    
    return image

def clean_output(text: str, max_repetitions: int = 2) -> str:
    """تنظيف التكرار في المخرجات"""
    if not text:
        return text
    
    import re
    text = re.sub(r'(.)\1{4,}', r'\1\1\1', text)
    
    lines = text.strip().split('\n')
    cleaned = []
    seen = {}
    for line in lines:
        line_stripped = line.strip()
        if not line_stripped:
            continue
        count = seen.get(line_stripped, 0) + 1
        if count <= max_repetitions:
            cleaned.append(line)
        seen[line_stripped] = count
    
    return '\n'.join(cleaned).strip()

# ==================== 🔍 دالة الاستدلال ====================
def extract_text(image, prompt: str = None) -> tuple[str, str]:
    """استخراج النص من الصورة"""
    if model is None or processor is None:
        return "❌ Error: Model not loaded", "0.00"
    
    if image is None:
        return "⚠️ Please upload an image", "0.00"
    
    start_time = time.time()
    
    try:
        if isinstance(image, str):
            image_pil = Image.open(image).convert("RGB")
        elif isinstance(image, Image.Image):
            image_pil = image.convert("RGB")
        else:
            image_pil = Image.fromarray(image).convert("RGB")
        
        image_pil = prepare_image(image_pil)
        
        if prompt is None or not prompt.strip():
            prompt = "اقرأ النص في هذه الصورة كاملاً من البداية إلى النهاية."
        
        messages = [{
            "role": "user",
            "content": [
                {"type": "image", "image": image_pil},
                {"type": "text", "text": prompt}
            ]
        }]
        
        text_input = processor.apply_chat_template(
            messages, tokenize=False, add_generation_prompt=True
        )
        image_inputs, _ = process_vision_info(messages)
        
        inputs = processor(
            text=[text_input],
            images=image_inputs,
            padding=True,
            return_tensors="pt"
        ).to(device)
        
        with torch.inference_mode():
            generated_ids = model.generate(
                **inputs,
                max_new_tokens=512,
                do_sample=False,
                temperature=1.0,
                repetition_penalty=1.2,
                no_repeat_ngram_size=3,
                pad_token_id=processor.tokenizer.pad_token_id,
                eos_token_id=processor.tokenizer.eos_token_id,
            )
        
        input_len = inputs.input_ids.shape[1]
        output_text = processor.batch_decode(
            generated_ids[:, input_len:],
            skip_special_tokens=True,
            clean_up_tokenization_spaces=False
        )[0]
        
        output_text = clean_output(output_text.strip())
        
        elapsed = time.time() - start_time
        
        return output_text, f"{elapsed:.2f} seconds"
        
    except torch.cuda.OutOfMemoryError:
        torch.cuda.empty_cache()
        return "❌ Out of Memory. Try a smaller image.", "0.00"
    except Exception as e:
        print(f"[ERROR] {e}")
        import traceback
        traceback.print_exc()
        return f"❌ Error: {str(e)}", "0.00"

# ==================== 🎨 واجهة Gradio ====================
def create_interface():
    """إنشاء واجهة المستخدم"""
    
    with gr.Blocks(
        title="Arabic OCR - Qwen3.5-0.8B",
        theme=gr.themes.Soft(),
        css="""
        .header { text-align: center; margin-bottom: 20px; }
        .output-box { min-height: 200px; }
        """
    ) as demo:
        
        gr.Markdown("""
        # 📝 Arabic Handwritten & Printed OCR V4
        ### Powered by Qwen3.5-0.8B
        
        Upload an image containing Arabic text, and the model will extract it.
        
        ✨ **Features:**
        - 🌍 Arabic support
        - ✍️ Handwritten & printed text
        - 🔤 Preserves diacritics (تشكيل)
        - ⚡ Full precision (no quantization)
        """, elem_classes="header")
        
        with gr.Row():
            with gr.Column(scale=1):
                # ✅ تعريف المكونات أولاً
                image_input = gr.Image(
                    label="📷 Upload Image",
                    type="pil",
                    height=300,
                    sources=["upload", "clipboard"]
                )
                
                prompt_input = gr.Textbox(
                    label="📝 Custom Prompt (Optional)",
                    placeholder="اقرأ النص في هذه الصورة...",
                    value="اقرأ النص في هذه الصورة كاملاً من البداية إلى النهاية.",
                    lines=2
                )
                
                submit_btn = gr.Button(
                    "🔍 Extract Text",
                    variant="primary",
                    size="lg"
                )
                
                # ✅ الأمثلة داخل الدالة - مسارات محلية فقط (لا روابط خارجية)
                # لإضافة أمثلة، انسخ الصور إلى مجلد 'examples/' في مستودع الـ Space
                # ثم استخدم: examples=[["examples/sample1.jpg"], ...]
                gr.Examples(
                    label="📋 Examples (Optional)",
                                examples=[
                ["https://huggingface.co/sherif1313/Arabic-Qwen3.5-OCR-v4/blob/main/00009.png"],
                ["https://huggingface.co/sherif1313/Arabic-Qwen3.5-OCR-v4/blob/main/00013.png"],
                ["https://huggingface.co/sherif1313/Arabic-Qwen3.5-OCR-v4/blob/main/00014.png"],
                ["https://huggingface.co/sherif1313/Arabic-Qwen3.5-OCR-v4/blob/main/00029.png"],
                ["https://huggingface.co/sherif1313/Arabic-Qwen3.5-OCR-v4/blob/main/00241.png"],
                ["https://huggingface.co/sherif1313/Arabic-Qwen3.5-OCR-v4/blob/main/00310.png"],
            ],  # اتركها فارغة أو استخدم مسارات محلية
                    inputs=[image_input],  # ✅ الآن يعمل لأن image_input مُعرّف أعلاه
                    cache_examples=False
                )
                
            with gr.Column(scale=1):
                output_text = gr.Textbox(
                    label="📄 Extracted Text",
                    lines=12,
                    show_copy_button=True,
                    elem_classes="output-box"
                )
                
                time_output = gr.Textbox(
                    label="⏱️ Inference Time",
                    interactive=False,
                    value="-"
                )
                
                clear_btn = gr.Button("🗑️ Clear", variant="secondary")
        
        # ✅ ربط الأحداث (بعد تعريف جميع المكونات)
        submit_btn.click(
            fn=extract_text,
            inputs=[image_input, prompt_input],
            outputs=[output_text, time_output]
        )
        
        clear_btn.click(
            fn=lambda: (None, "", "-"),
            inputs=[],
            outputs=[image_input, prompt_input, time_output]
        )
        
        gr.Markdown("""
        ### 💡 Tips for Best Results:
        1. Use clear, well-lit images
        2. Crop to the text region if possible
        3. For handwritten text, ensure good contrast
        4. Custom prompts can improve accuracy for specific formats
        """)
    
    return demo  # ✅ إرجاع الـ demo

# ==================== 🚀 نقطة الدخول ====================
if __name__ == "__main__":
    print("[INFO] Creating Gradio interface...")
    
    demo = create_interface()
    
    # إعدادات التشغيل لـ Spaces
    demo.launch(
        server_name="0.0.0.0",
        server_port=int(os.getenv("PORT", 7860)),
        share=False,
        debug=os.getenv("DEBUG", "false").lower() == "true",
        show_error=True
    )