#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
圖片 OCR 讀取工具
支持中文簡體、繁體、英文混合識別
用法：python ocr_image.py /path/to/image.jpg
"""

import sys
import os
from PIL import Image
import pytesseract


def ocr_image(image_path: str, lang: str = "chi_sim+chi_tra+eng") -> str:
    """
    對單張圖片進行 OCR 文字識別。
    :param image_path: 圖片路徑
    :param lang: tesseract 語言包，默認中文簡體+繁體+英文
    :return: 識別出的文字
    """
    if not os.path.exists(image_path):
        raise FileNotFoundError(f"圖片不存在：{image_path}")

    img = Image.open(image_path)
    # 自動轉為 RGB，避免某些格式不支持
    if img.mode != "RGB":
        img = img.convert("RGB")

    text = pytesseract.image_to_string(img, lang=lang)
    return text.strip()


def ocr_images(image_paths: list[str], lang: str = "chi_sim+chi_tra+eng") -> dict[str, str]:
    """
    批量對多張圖片進行 OCR。
    :param image_paths: 圖片路徑列表
    :param lang: tesseract 語言包
    :return: 字典 {filename: text}
    """
    results = {}
    for path in image_paths:
        try:
            results[os.path.basename(path)] = ocr_image(path, lang=lang)
        except Exception as e:
            results[os.path.basename(path)] = f"[ERROR] {e}"
    return results


if __name__ == "__main__":
    if len(sys.argv) < 2:
        print("用法：python ocr_image.py <圖片路徑1> [<圖片路徑2> ...]")
        sys.exit(1)

    paths = sys.argv[1:]
    results = ocr_images(paths)
    for filename, text in results.items():
        print(f"\n{'='*40}")
        print(f"文件：{filename}")
        print(f"{'='*40}")
        print(text)
