from flask import Blueprint, request, jsonify, send_file 
import os 
import subprocess 
import json 
import uuid 
import re

ocr = Blueprint("ocr", __name__)

# 目录配置
upload_dir = "./inference_pic"
output_dir = "./inference_json"
det_model_dir = "./inference_model/det_v4"
rec_model_dir = "./inference_model/rec_v4"
cls_model_dir = "./inference_model/ch_ppstructure_mobile_v2.0_SLANet_infer"
result_dir = "./inference_results/v4"

# 创建目录
os.makedirs(upload_dir, exist_ok=True)
os.makedirs(output_dir, exist_ok=True)
os.makedirs(result_dir, exist_ok=True)

@ocr.route("/process", methods=["POST"])
def ocr_inference():
    if "file" not in request.files:
        return jsonify({"error": "No file provided"}), 400
        
    file = request.files["file"]
    if file.filename == "":
        return jsonify({"error": "No selected file"}), 400
        
    # 生成唯一文件名
    uuid_str = str(uuid.uuid4())     
    filename = f"{uuid_str}.jpg"     
    image_path = os.path.join(upload_dir, filename)     
    file.save(image_path)
    
    try:
        # 调用 OCR 模型并捕获 stdout
        command = [
            "python",
            "tools/infer/predict_system.py",
            "--image_dir", image_path,
            "--det_model_dir", det_model_dir,
            "--rec_model_dir", rec_model_dir,
            "--cls_model_dir", cls_model_dir,
            "--draw_img_save_dir", result_dir,
        ]
        
        result = s|u|b|p|r|o|c|e|s|s.run(command, check=True, capture_output=True, text=True, encoding="utf-8")

        # 提取调试信息
        debug_lines = result.stdout.splitlines()
        pattern = re.compile(r"\[.*\] ppocr DEBUG: (.*?), (\d+\.\d+)")
        results = []