Escu:de汉化(一)——GBK编码

import os

import chardet

def convert_encoding(folder_path):

    """ 将文件夹内所有文本文件从 Shift-JIS 转为 UTF-8 """

    target_encodings = ['shift_jis', 'shift-jis', 'sjis', 'cp932', 'windows-31j', 'mskanji']

    for filename in os.listdir(folder_path):

        file_path = os.path.join(folder_path, filename)

        if not os.path.isfile(file_path):

            continue

        # 检测文件编码

        with open(file_path, 'rb') as f:

            raw_data = f.read()

            detected = chardet.detect(raw_data)

            encoding = detected['encoding']

            confidence = detected.get('confidence', 0)

        # 判断是否为目标编码（不区分大小写）

        is_target = False

        if encoding:

            is_target = encoding.lower() in target_encodings

        else:

            # 编码检测失败时，强制尝试转换

            is_target = True

        if is_target:

            try:

                # 优先使用 cp932 解码并替换非法字符

                with open(file_path, 'r', encoding='cp932', errors='replace') as f:

                    content = f.read()

                # 写回 UTF-8 编码

                with open(file_path, 'w', encoding='utf-8') as f:

                    f.write(content)

                print(f"[OK] 已转换: {filename}")

            except Exception as e:

                print(f"[Error] 转换失败: {filename} - {str(e)}")

        else:

            print(f"[跳过] 非目标文件: {filename} (检测编码: {encoding}, 置信度: {confidence:.2f})")

if __name__ == "__main__":

    folder_path = r"D:\Data\python_prj\Escude_Translate\script_source\output\script_txt"

    convert_encoding(folder_path)

    print("编码转换完成！")

import os

import json

import re

import glob

def process_text(text):

    """

    处理文本：

      1. 将 <ruby text='XXX'>YYY</ruby> 替换为 YYY

      2. （如有需要，可以添加其它处理规则）

    """

    # 使用正则表达式替换 ruby 标签

    # 匹配形式：<ruby text=' くさかべあきら '> 日下部彰 & lt;/ruby> 替换为 日下部彰

    # text = re.sub(r"<ruby\s+text='[^']*'>(.*?)</ruby>", r"\1", text)

    # 如果需要去掉 <r> 标签（如果它确实需要被删除），可以取消下面代码的注释

    # text = text.replace("<r>", "")

    return text

def convert(folder_path):

    # 用于存放所有处理后的对话列表

    dialogues = []

    # 读取文件夹中所有 txt 文件

    txt_files = glob.glob(os.path.join(folder_path, "*.txt"))

    for file_path in txt_files:

        with open(file_path, "r", encoding="utf-8") as f:

            # 使用 set 来去重同一文件内的重复文本

            seen_texts = set()

            for line in f:

                line = line.strip()

                if not line:

                    continue

                # 分割字符串，取 | 后面的文本（假定每行只有一个 | 分隔符）

                if "|" in line:

                    parts = line.split("|", 1)

                    text = parts[1].strip()

                    # 如果文本已存在则跳过（去除重复）

                    if text in seen_texts:

                        continue

                    seen_texts.add(text)

                    # 处理文本

                    processed_text = process_text(text)

                    # 添加到对话列表中，name 暂时为空字符串

                    dialogues.append({

                        "message": processed_text

                    })

    # 最终写入 JSON 文件（可根据需要修改输出路径）

    output_path = os.path.join(folder_path, "output.json")

    with open(output_path, "w", encoding="utf-8") as f:

        json.dump(dialogues, f, ensure_ascii=False, indent=4)

    print(f"处理完成，结果保存在 {output_path}")

if __name__ == "__main__":

    # 指定需要处理的文件夹路径

    folder_path = r"D:\Data\python_prj\Escude_Translate\script_source\output\script_txt"

    convert(folder_path)

import os

import json

import glob

import chardet  # 需要安装 `pip install chardet`

def detect_encoding(file_path):

    with open(file_path, "rb") as f:

        raw_data = f.read(10000)  # 读取部分数据用于检测

    result = chardet.detect(raw_data)

    return result["encoding"]

def main():

    translated_json_path = r"D:\Tool\GalTransl\GalTransl-v5.9.1-win\sampleProject\gt_output\script_jp.json"

    original_folder = r"D:\Data\python_prj\Escude_Translate\script_source\output\script_txt"

    new_folder = r"D:\Data\python_prj\Escude_Translate\script_source\output\script_txt"

    os.makedirs(new_folder, exist_ok=True)

    output_encoding = "gbk"

    with open(translated_json_path, "r", encoding="utf-8") as f:

        translated_data = json.load(f)

    translated_index = 0

    total_translated = len(translated_data)

    txt_files = sorted(glob.glob(os.path.join(original_folder, "*.txt")))

    for file_path in txt_files:

        detected_encoding = detect_encoding(file_path)

        if detected_encoding is None:

            print(f"警告：无法检测文件 {os.path.basename(file_path)} 的编码，默认使用 GBK。")

            detected_encoding = "gbk"

        new_lines = []

        mapping = {}

        try:

            with open(file_path, "r", encoding=detected_encoding, errors="replace") as f:

                for line in f:

                    line = line.rstrip("\n")

                    if "|" not in line:

                        new_lines.append(line)

                        continue

                    try:

                        prefix, orig_msg = line.split("|", 1)

                    except ValueError:

                        new_lines.append(line)

                        continue

                    if orig_msg not in mapping:

                        if translated_index >= total_translated:

                            print(f"错误：翻译后的条目不足以覆盖文件 {os.path.basename(file_path)}")

                            return

                        mapping[orig_msg] = translated_data[translated_index]["message"]

                        translated_index += 1

                    new_line = f"{prefix}|{mapping[orig_msg]}"

                    new_lines.append(new_line)

        except Exception as e:

            print(f"读取文件 {file_path} 失败: {e}")

            continue

        new_file_path = os.path.join(new_folder, os.path.basename(file_path))

        with open(new_file_path, "w", encoding=output_encoding, errors="replace") as f_out:

            f_out.write("\n".join(new_lines))

        # print (f"写入 {new_file_path}，共更新 {len (new_lines)} 行。")

    if translated_index < total_translated:

        print("注意：还有未使用的翻译条目。")

    elif translated_index > total_translated:

        print("错误：翻译条目不足以覆盖所有文件中的对话条目！")

    else:

        print("转换完成，所有翻译条目已按原始文件对应写入新 txt 文件中。")

if __name__ == "__main__":

    main()