import re
import os

from xml.dom import minidom

# 配置区域:
PATTERN = "\{=\w+\}.+"  # 转换值的正则表达式
TARGET_ATTRS = ("name", "text")      # 目标的类型
OUTDIR_NAME = "output"   # 输出文件夹的名称

# 下面都是代码
OUTDIR = os.sep.join([os.path.dirname(__file__), OUTDIR_NAME])

BASE_ATTRS = (('xmlns:xsi', 'http://www.w3.org/2001/XMLSchema-instance'),
             ('xmlns:xsd', 'http://www.w3.org/2001/XMLSchema'),
             ('xsi:schemaLocation', 'https://www.w3schools.com/xml ../../../../../../resources/language.xsd'),
             ('type', 'string'))

os.chdir(os.path.dirname(__file__))

if not os.path.exists(OUTDIR):
    os.mkdir(OUTDIR)

assert os.path.isdir(OUTDIR), f"{OUTDIR} 不是文件夹"


def mk_result_dom():
    dom = minidom.Document()
    base = dom.createElement("base")
    tags = dom.createElement("tags")
    tag = dom.createElement("tag")
    strings = dom.createElement("strings")
    dom.appendChild(base)
    base.appendChild(tags)
    base.appendChild(strings)
    tags.appendChild(tag)
    for k, v in BASE_ATTRS:
        base.setAttribute(k, v)
    tag.setAttribute("language", "简体中文")
    return dom

def scan_string(node, strings):
    """对节点的 name 和 text 属性进行扫描并添加到 strings 中"""
    count = 0
    if not hasattr(node, "getAttribute"):
        return count
    for attr in TARGET_ATTRS:
        val = node.getAttribute(attr)
        if re.fullmatch(PATTERN, val):
            count += 1
            string = strings.ownerDocument.createElement("string")
            end_idx = val.find("}")
            string.setAttribute("id", val[2:end_idx])
            string.setAttribute("text", val[end_idx + 1 :])
            strings.appendChild(string)
    return count


def convert(dom, strings):
    """遍历每个节点
    dom 被处理的文件
    strings 输出文件的 strings 节点
    """
    count = 0
    for child in dom.childNodes:
        count += scan_string(child, strings)
        if child.hasChildNodes():
            count += convert(child, strings)
    return count


def read_and_convert(fpath, outdir):
    """读取 fpath 的文件并输出同名文件到 outdir"""
    try:
        encoding = "utf-8"
        dom = minidom.parse(open(fpath, encoding=encoding))
    except UnicodeDecodeError:
        encoding = "gbk"
        dom = minidom.parse(open(fpath, encoding=encoding))
    out_dom = mk_result_dom()
    count = convert(dom, out_dom.getElementsByTagName("strings")[0])
    out_path = os.sep.join([outdir, os.path.basename(fpath)])
    with open(out_path, "w", encoding=encoding) as f_obj:
        out_dom.writexml(f_obj, encoding='UTF-8', indent='\n', addindent=' ')
        print("发现", count, "个匹配属性, 结果已写入到", out_path)


def main():
    while True:
        path = input(">> 输入文件路径\n>> ")
        if os.path.isfile(path):
            targets = [path]
        else:
            targets = [os.sep.join([path, fname]) for fname in os.listdir(path)]
        for target in targets:
            try:
                if target.upper()[-4:] == ".XML":
                    read_and_convert(target, OUTDIR)
            except Exception as e:
                print(target, "处理错误", repr(e))


if __name__ == "__main__":
    main()