import os
import subprocess
import uuid

# 获取MathType对应的Latex公式
def get_latex_list(docx_file):
    # 获取当前目录的父级目录
    current_dir = os.path.dirname(os.path.abspath(__file__))
    current_dir = os.path.dirname(current_dir)
    mtef = os.path.join(current_dir, 'mtef-go-3', 'mtef-go.exe')
    res = []
    output = os.path.join(os.environ['TEMP'], uuid.uuid4().hex + '.txt')
    command = mtef + r" -w " + docx_file + " -o " + output
    os.system(command)
    # 如果output没有正确生成
    if not os.path.exists(output):
        return res
    with open(output, 'r', encoding='utf-8') as file:
        for i, line in enumerate(file):
            res.append(line.strip().replace("$$",""))
    return res

def get_docx_content_by_pandoc(docx_file):
    # 一、获取Latex公式列表
    formula_list = get_latex_list(docx_file)
    # 最后拼接的内容
    content = ""
    # output_file 设置为临时目录下的uuid.md
    file_name = uuid.uuid4().hex
    # 将docx_file去掉扩展名
    prefix = docx_file.split(".")[0].split("/")[-1]
    temp_markdown = os.path.join('./static/markdown/', prefix + '.md')
    # 调用pandoc将docx文件转换成markdown
    os.mkdir("./static/Images/" + file_name)
    subprocess.run(['pandoc', docx_file, '-f', 'docx', '-t', 'markdown', '-o', temp_markdown,
                    '--extract-media=./static/Images/' + file_name])
    # 读取然后修改内容，输出到新的文件
    wmf_idx = 0  # wmf索引
    img_idx = 0  # 图片索引
    with open(temp_markdown, 'r', encoding='utf-8') as f:
        for line in f:
            line = line.strip()
            if not line:
                continue
            # 跳过图片高度描述行
            if line.startswith('height=') and line.endswith('in"}'):
                continue
            # 使用find()方法安全地检查图片模式
            is_wmf = line.find("![](") >= 0 and line.find(".wmf") > 0
            # 使用find()方法安全地检查图片模式
            is_img = line.find("![](") >= 0 and (
                    line.find(".png") > 0 or
                    line.find(".jpg") > 0 or
                    line.find(".jpeg") > 0
            )
            if is_wmf:
                content += formula_list[wmf_idx] + "\n"
                wmf_idx += 1
            elif is_img:
                # ![](media/image3.png){width="3.1251607611548557in"
                # height="3.694634733158355in"}
                # ![](../static/Images/01b20e04085e406ea5375791da58a60f/media/image3.png){width="3.1251607611548557in"
                pos = line.find(")")
                q = line[:pos + 1]
                img_idx += 1
                content += q + "\n"
            else:
                content += line.strip().replace("**", "") + "\n"

    # 删除临时文件 output_file
    #os.remove(temp_markdown)
    return content.replace("\n\n", "\n").replace("\\", "")