代码中文抽取工具并替换工具（以ts为例）

文章目录

基本思路
目录结构
配置文件
AST解析
替换代码中文
生成Excel
启动脚本

基本思路

通过对应语言的AST解析出中文
相关信息（文件、所在行列等）存到临时文件
通过相关信息，逐个文件位置替换掉中文
基于临时文件，通过py脚本生成Excel表格

目录结构

在这里插入图片描述

配置文件

// config.json
{
    "_NOTE": "// _NOTE后缀都是注释, 无需修改",


    "start_id_NOTE": "// 生成配置表的起始id",
    "start_id": 10000,


    "funCls_NOTE": "// 静态替换函数的类名",
    "funCls": "LangUtil",


    "replaceFunc_NOTE": "// 替换函数, 形如: public static getLang(code: number, ...args): string; ",
    "replaceFunc": "LangUtil.getLang",


    "importAbsolute_NOTE": "// import的绝对路径",
    "importAbsolute": "import { LangUtil } from 'src/game/mod/common/utils/LangUtil';",


    "ignore_file_NOTE": "// 忽略的.ts文件名",
    "ignore_file": [
        "Const.ts",
        "CharConst.ts",
		"CharConstLog.ts",
		"CharConstFeat.ts",
		"CharConstMars.ts",
		"CharConstCommon.ts",
		"CharConstMeridian.ts",
		"LangUtil.ts"
    ],


    "ignore_dir_NOTE": "// 忽略的文件目录名",
    "ignore_dir": [
    ],


    "isReplaceStaticProperty_NOTE": "// 是否替换静态的属性的中文字符（建议第一波先不替换；第二波再统一替换，会报错，看能不能优化代码不要用静态的）",
    "isReplaceStaticProperty": false,

    "replacer_exe_NOTE": "// 是否执行代码中文替换",
    "replacer_exe": true,
    
    "gen_xls_exe_NOTE": "// 是否生成xls",
    "gen_xls_exe": true,

    "xls_name_NOTE": "// 生成的xls文件名",
    "xls_name": "lang_tool.xls",

    
    "OPTIONAL_PARAMS_NOTE": "// ==========================================下方一般都没必要修改=============================",
    "columns_NOTE": "// 生成表的列占位符",
    "columns": ["NOTE", "ID", "文本", "空列", "代码文件来源", "被替换的源代码"],
    
    "ecmaVersion_NOTE": "// 解析所需参数",
    "ecmaVersion": 2020,

    "sourceType_NOTE": "// 解析所需参数",
    "sourceType": "module",

    "genTsEnum_NOTE": "// 是否生成ts枚举类",
    "genTsEnum": true,

    "isPrettyJsn_NOTE": "// 是否美化的json",
    "isPrettyJsn": true,

    "tempJ_NOTE": " // json文件名",
    "tempJ": "tempJ.json"
}

AST解析

// tool_chinese_strings_extracted.js
const fs = require('fs');
const path = require('path');
const { parse } = require('@typescript-eslint/typescript-estree');
const readline = require('readline');

const POSTFIX_TS = ".ts"
let ENUM_START_ID = 1;
let tblStartId = 1; //表的id
const FILENAME_POSTFIX = "Lang";
const __Mark = "________";
const scriptDir = __dirname;
const CharConstClsName = "CharConst";
const IO_ENCODING = "utf8";
const COMBINE_NAME = `${CharConstClsName}${FILENAME_POSTFIX}`;
const CharConstTSFile = `${COMBINE_NAME}${POSTFIX_TS}`;
const input_dir = `${scriptDir}\\input\\`;
const output_dir = `${scriptDir}\\output\\`;
const output = `${COMBINE_NAME}.txt`;
const output_simple = `${COMBINE_NAME}_Simple.txt`;
const SHOW_FILE_LINE = true; // 必须为 true 才能获取文件行号生成注释
const IS_GEN_SIMPLE_STR = true;
let strings = new Set();
let strings_simple = new Set();
const tempJson = {};

function insertJson(tableId, srcTxt, replaceFullPath, line, type, tgtTxt, args = null) {
    tempJson[tableId] = {
        srcTxt: srcTxt,
        path: replaceFullPath,
        line: line,
        type: type,
        tgtTxt: tgtTxt,
    }
    if (args) {
        tempJson[tableId]['args'] = args;
    }
}
//single 解析 AST
function traverse(filePath) {
    const content = fs.readFileSync(filePath, IO_ENCODING);
    try {
        const ast = parse(content, {
            ecmaVersion: getValueByKey("ecmaVersion"),
            sourceType: getValueByKey("sourceType"),
            loc: true,
            range: true
        });
        traverseAST(ast, filePath, content); // 递归遍历 AST 节点
    } catch (e) {
        console.warn(`Parse error in ${filePath}`);
    }
}
function isStaticProperty(node) {
    if(getValueByKey("isReplaceStaticProperty")){
        return false; //要替换静态的时候，当做不是静态属性即可
    }
    if (node.type === 'PropertyDefinition' && node.static) {
        // if(node.key && node.key.type == "Identifier"){
        //     console.log(`忽略属性：${node.accessibility} static ${node.key.name}`);
        // }
        return true;
    }
    return false;
}
// 递归AST节点，查找中文字符串
function traverseAST(node, file, content) {
    if(isStaticProperty(node)){
        return;
    }
    if (node.type === 'Literal' &&
        typeof node.value === 'string' &&
        /[\u4e00-\u9fa5]/.test(node.value)) {
        handleStringLiteral(node, file, content, 0);
    }
    if (node.type === 'TemplateLiteral') {
        let processedStr = '';
        let argIndex = 0; // 参数索引计数器

        for (let i = 0; i < node.quasis.length; i++) {
            const quasi = node.quasis[i];
            processedStr += quasi.value.raw;
            if (i < node.quasis.length - 1) {
                processedStr += `{${argIndex++}}`; // 递增索引
            }
        }

        if (/[\u4e00-\u9fa5]/.test(processedStr)) {
            handleStringLiteral(/* {
                value: processedStr,
                loc: node.loc // 使用模板字符串整体位置
            } */node, file, content, 1, processedStr);
        }
    }
    for (let key in node) {
        if (node.hasOwnProperty(key) &&
            typeof node[key] === 'object' &&
            node[key] !== null) {
            traverseAST(node[key], file, content); // dfs
        }
    }
}

function handleStringLiteral(node, file, content, type/* 1有processedStr */, processedStr = null) {
    if (!node.loc) {
        console.error(`未知行，不予记录，跳过; file=>${file}`)
        return;
    }
    const newTblId = tblStartId++;
    const line = node.loc.start.line;
    const isLiterStringType = isLiteral(type);
    let srcTxt = "";
    let args = [];
    if(isLiterStringType){
        srcTxt = node.raw;
        args = null;
    }else{
        srcTxt = content.slice(node.range[0], node.range[1]);
        node.expressions.forEach(expr => {
            const [start, end] = expr.range;
            args.push(content.slice(start, end)); 
        });
    }

    const uid = `${__Mark}${newTblId}`;
    const tblSaveStr = isLiterStringType ? node.value : processedStr;
    insertJson(newTblId, srcTxt, file, line, type, tblSaveStr, args)
    if (SHOW_FILE_LINE) {
        // const line = node.loc ? node.loc.start.line : '未知行';
        strings.add(`${file}:${line}${uid}\n${/* node.value */tblSaveStr}`);
        // console.log(`enterCount-------------------->${testEnterCount}|||${strings.size}`)
    }

    if (IS_GEN_SIMPLE_STR) {
        strings_simple.add(`${/* node.value */tblSaveStr}${uid}`);
        // console.log(`enterCount-------------------->${testEnterCount}|||${strings_simple.size}`)
    }
}

function isLiteral(type){
    return type == 0;
}

function walkDir(currentPath) {
    if (!fs.existsSync(currentPath)) {
        console.error(`路径不存在: ${currentPath}`);
        return;
    }

    const files = fs.readdirSync(currentPath);

    for (const file of files) {
        const fullPath = path.join(currentPath, file);
        const stat = fs.statSync(fullPath);
        if (stat.isDirectory()) {
            if(ignore_dir.indexOf(file) > -1){
                console.log(`==========忽略文件夹：${file}`)
            }else{
                walkDir(fullPath);
            }
        } else if (file.endsWith(POSTFIX_TS)) {
            if(ignore_file.indexOf(file) > -1){
                console.log(`==========忽略文件：${file}`)
            }else{
                traverse(fullPath);
            }
        } else {

        }
    }
}


function generateEnumFile() {
    const entries = Array.from(strings).map(entry => {
        const [fileLine, value] = entry.split('\n');
        const lastColonIndex = fileLine.lastIndexOf(':');
        return {
            file: fileLine.slice(0, lastColonIndex),
            line: disposeUIdStrByReg(fileLine.slice(lastColonIndex + 1)),
            value: value
        };
    });

    const enumLines = entries.map(({ file, line, value }, index) => {
        const id = index + ENUM_START_ID;
        const key = `ID_${id}`;
        const fileName = path.basename(file); // 提取文件名（去除路径）
        // 使用 JSON.stringify 自动转义特殊字符（如 "、\n 等）
        return `\t// ${fileName}:${line}\n\t${key} = ${id}, //${JSON.stringify(value)}`;
    });
    const enumContent = `/** Attention! The annotations will not change along with the actual table. */\nexport enum ${COMBINE_NAME} {\n${enumLines.join('\n')}\n}`;
    fs.writeFileSync(output_dir + CharConstTSFile, enumContent, IO_ENCODING);
}
const enableDelOutput = true;
const delOutputTipsShow = false;

async function clearOutputDir() {
    const dirPath = output_dir;
    if (!enableDelOutput) return;
    console.log(`enableDelOutput：${output_dir}`)

    if (!fs.existsSync(dirPath)) {
        console.log(`目录不存在: ${dirPath}`);
        return;
    }

    // 创建 readline 接口
    const rl = readline.createInterface({
        input: process.stdin,
        output: process.stdout
    });

    try {
        // 等待用户确认
        let rst = "y";
        if (delOutputTipsShow) {
            rst = await new Promise(resolve => {
                rl.question(`即将清空目录 ${dirPath}，确认继续吗？(y/n) `, resolve);
            });
        }
        if (rst.trim().toLowerCase() === 'y') {
            // 执行删除操作
            fs.rmSync(dirPath, { recursive: true, force: true });
            fs.mkdirSync(dirPath);
            console.log('√ 目录已清空');
        } else {
            console.log('× 操作已取消');
        }
    } finally {
        rl.close();
    }
}

function disposeUIdStrByReg(s) {
    return s.replace(/________\d+/, '');
}
async function main() {
    try {
        await clearOutputDir();
        load_config();
        init_cfg_value();
        walkDir(input_dir);
        fs.writeFileSync(
            path.join(output_dir, output),
            Array.from(strings).map(s => disposeUIdStrByReg(s)).join('\n'),
            IO_ENCODING
        );
        fs.writeFileSync(path.join(output_dir, output_simple), Array.from(strings_simple).map(str => str.split(__Mark)[0]).join('\n'), IO_ENCODING);
        const genTsEnum = getValueByKey("genTsEnum");
        if(genTsEnum){
            generateEnumFile();
        }
        console.log(`
        √ 提取完成：
           - 找到 strings.size=>${strings.size}|||strings_simple.size=>${strings_simple.size} 条中文字符串（已写入 ${output} 和 ${output_simple}）
           ${genTsEnum ? "- 生成枚举文件 ${CharConstTSFile}" : ""}
        `);
        let jsonData;
        if(getValueByKey("isPrettyJsn")){
            jsonData = JSON.stringify(tempJson, null, 2);
        }else{
            jsonData = JSON.stringify(tempJson);
        }
        fs.writeFileSync(path.join(output_dir, getValueByKey("tempJ")), jsonData);
    } catch (err) {
        console.error('× 运行出错:', err);
        process.exit(1);
    }
}
main();


let json_obj;
let ignore_file;
let ignore_dir;
function init_cfg_value(){
    tblStartId = ENUM_START_ID = getValueByKey("start_id");
    ignore_file = getValueByKey("ignore_file") || [];
    ignore_dir = getValueByKey("ignore_dir") || [];
}
function load_config(){
    try {
        const data = fs.readFileSync('./config.json', 'utf8');
        json_obj = JSON.parse(data);
    } catch (err) {
        console.error('config.json解析失败:', err);
        process.exit(1);
    }
}

function getValueByKey(key) {
    if (json_obj && key in json_obj) {
        return json_obj[key];
    }
    return null;
}

替换代码中文

// tool_replacer.py
import json
import os
import re
from pathlib import Path
import logging
import os



def setup_logger():
    log_dir = "output"
    os.makedirs(log_dir, exist_ok=True)
    log_file = os.path.join(log_dir, "log.txt")

    logger = logging.getLogger("my_logger")
    logger.setLevel(logging.INFO)

    file_handler = logging.FileHandler(log_file, encoding="utf-8", mode="a")
    file_handler.setFormatter(logging.Formatter('[%(asctime)s] %(message)s'))
    logger.addHandler(file_handler)

    console_handler = logging.StreamHandler()
    console_handler.setFormatter(logging.Formatter('%(message)s'))
    logger.addHandler(console_handler)

    return logger


class TsTextReplacer:
    def __init__(self, config_path="config.json", data_path="output/tempJ.json"):
        self.config = self.load_config(config_path)
        self.json_data = self.load_data(data_path)
        str_cfg=self.config['funCls']
        pattern = r'^import\s+.*?\b{}\b'.format(re.escape(str_cfg))
        self.import_pattern = re.compile(pattern, re.MULTILINE)
        str_import_cfg=self.config['importAbsolute']
        self.import_statement = f"{str_import_cfg}\n"

    def load_config(self, path):
        with open(path, 'r', encoding='utf-8') as f:
            return json.load(f)

    def load_data(self, path):
        with open(path, 'r', encoding='utf-8') as f:
            return json.load(f)

    # 接收键和项作为参数
    def generate_replacement(self, key, item):
        base = f"{self.config['replaceFunc']}({key}"
        if item.get('type', 0)!= 0 and item.get('args'):
            args = ', '.join(item['args'])
            return f"{base}, {args})"
        return f"{base})"

    def add_import_statement(self, content):
        if not self.import_pattern.search(content):
            return self.import_statement + content
        return content

    def process_file(self, file_path, line, src_txt, replacement):
        try:
            with open(file_path, 'r', encoding='utf-8') as f:
                content = f.readlines()
            modified = False
            for i in range(line - 1, len(content)):
                if src_txt in content[i]:
                    content[i] = content[i].replace(src_txt, replacement, 1)
                    modified = True
                    break
            if modified:
                full_content = ''.join(content)
                full_content = self.add_import_statement(full_content)
                with open(file_path, 'w', encoding='utf-8') as f:
                    f.write(full_content)
                return True
            return False
        except Exception as e:
            logger.info(f"处理文件 {file_path} 失败: {str(e)}")
            return False

    def run(self):
        if self.config['replacer_exe']:
            success_count = 0
            for key, item in self.json_data.items():
                if not all(k in item for k in ['srcTxt', 'path', 'line']):
                    continue
                replacement = self.generate_replacement(key, item)
                file_path = Path(item['path']).resolve()
                if not file_path.exists():
                    # print(f"文件不存在: {file_path}")
                    logger.info(f"文件不存在: {file_path}")
                    continue
                if self.process_file(file_path, item['line'], item['srcTxt'], replacement):
                    # print(f"已处理: {file_path} [行{item['line']}]")
                    logger.info(f"已处理: {file_path} [行{item['line']}]")
                    success_count += 1
                else:
                    # print(f"未找到匹配: {file_path} [行{item['line']}]")
                    logger.info(f"未找到匹配: {file_path} [行{item['line']}]")
            # print(f"\n处理完成！成功替换 {success_count}/{len(self.json_data)} 处")
            endLog = f"************处理完成！成功替换 {success_count}/{len(self.json_data)} 处"
            logger.info(f"{endLog}")
            escape_info_str(endLog)
        else:
            endLog = "************跳过了替换代码中文步骤！"
            logger.info(f"{endLog}")
            escape_info_str(endLog)

def escape_info_str(value):
    escaped_value = value.replace("%", "%%")
    print(f'echo "{escaped_value}"')

if __name__ == "__main__":
    logger = setup_logger()
    replacer = TsTextReplacer()
    replacer.run()

生成Excel

// tool_excel_generator.py
import json
import os
from pathlib import Path
from openpyxl import Workbook
from openpyxl.utils import get_column_letter

class ExcelGenerator:
    def __init__(self):
        self.config = self.load_config()
        self.json_data = self.load_data()
        self.output_dir = Path("output")
        self.output_dir.mkdir(exist_ok=True)
    # ed
    def load_config(self):
        with open("config.json", "r", encoding="utf-8") as f:
            config = json.load(f)
        return {
            "xls_name": config.get("xls_name", "lang") + ".xls",
            "columns": ["NOTE", "ID", "文本", "空列", "代码文件来源", "被替换的源代码"]
        }
    # ed
    def load_data(self):
        with open("output/tempJ.json", "r", encoding="utf-8") as f:
            return json.load(f)
    # ed
    def get_filename_from_path(self, path):
        return Path(path).stem
    # ed
    def clean_output_xls_rtn_name(self):
        output_path = self.output_dir / self.config["xls_name"]
        if output_path.exists():
            os.remove(output_path)
        return output_path

    # ed
    def generate_excel(self):
        if self.config["gen_xls_exe"]:
            """生成Excel文件"""
            output_path = self.clean_output_xls_rtn_name()
            
            wb = Workbook()
            ws = wb.active
            ws.title = "Lang Data"
            
            ws.column_dimensions[get_column_letter(2)].width = 15  # Key列
            ws.column_dimensions[get_column_letter(3)].width = 40  # tgtTxt列
            ws.column_dimensions[get_column_letter(5)].width = 35  # Path:Line列
            ws.column_dimensions[get_column_letter(6)].width = 60  # srcTxt列

            # 写入标题行
            ws.append(self.config["columns"])

            # 写入数据
            row_counter = 0
            for idx, (key, item) in enumerate(sorted(self.json_data.items(), key=lambda x: int(x[0])), 1):
                filename = self.get_filename_from_path(item["path"])
                path_line = f"{filename}:{item['line']}"
                
                row = [
                    f"VALUE",
                    key,
                    item.get("tgtTxt", ""),
                    "",
                    path_line,
                    item.get("srcTxt", "")
                ]
                
                ws.append(row)
                row_counter += 1

                # 每20行插入空行
                if row_counter % 20 == 0:
                    ws.append([""]*len(self.config["columns"]))

            # 保存文件
            wb.save(output_path)
            print(f"生成成功！文件位置：{output_path}")
        else:
            print(f"跳过了生成xls文件步骤！")

            
if __name__ == "__main__":
    generator = ExcelGenerator()
    generator.generate_excel()

启动脚本

REM zstartup.bat
@echo off
echo start tool_chinese_strings_extracted...
node tool_chinese_strings_extracted.js
if errorlevel 1 (
    echo tool_chinese_strings_extracted fail.
    pause
    exit /b
)

echo start tool_replacer...
REM start tool_replacer.exe
call tool_replacer.exe > temp___vars.bat
call temp___vars.bat
del temp___vars.bat
if errorlevel 1 (
    echo tool_replacer fail.
	start log_show.bat
    pause
    exit /b
)

echo start tool_excel_generator...
start tool_excel_generator.exe
if errorlevel 1 (
    echo tool_excel_generator fail.
	start log_show.bat
    pause
    exit /b
)
call log_show.bat
echo success...
pause