Android对工程中的String中文字符的整理

​
本文主要介绍使用python快速整理工程中的中文字符，为app国际化提供便利。

1. 查找Android工程中的所有中文字符串(find_chinese.py)

import os
import re
import argparsedef is_comment_line(line, file_ext):"""判断一行是否是注释:param line: 代码行:param file_ext: 文件扩展名:return: 是否是注释行"""line = line.strip()if not line:return True# 根据不同文件类型判断注释if file_ext in {'.java', '.kt', '.gradle', '.kts'}:return line.startswith('//') or line.startswith('/*') or line.endswith('*/') or line.startswith('/**')or line.startswith('*')elif file_ext in {'.xml', '.html'}:return line.startswith('<!--') or '<!--' in lineelif file_ext == '.py':return line.startswith('#')return Falsedef remove_xml_comments(content):"""移除XML文件中的注释"""return re.sub(r'<!--.*?-->', '', content, flags=re.DOTALL)def remove_java_comments(content):# 移除多行注释content = re.sub(r'/\*\*(?:[^*]|\*(?!/))*\*/', '', content, flags=re.DOTALL)# 移除单行注释content = re.sub(r'//.*', '', content)return content
def is_log_statement(line):"""判断是否是Log或Debug开头的日志语句"""line = line.strip()return line.startswith(('Log.', 'LogUtils.', 'DebugLog.'))def remove_code_comments(content, file_ext):if file_ext in {'.java', '.kt', '.gradle', '.kts'}:return remove_java_comments(content)# 移除多行注释#content = re.sub(r'/\*\*(?:[^*]|\*(?!/))*\*/', '', content, flags=re.DOTALL)# 移除单行注释#content = re.sub(r'//.*', '', content)elif file_ext in {'.xml', '.html'}:# 移除XML/HTML注释 <!-- ... -->content = re.sub(r'<!--.*?-->', '', content, flags=re.DOTALL)elif file_ext == '.py':# 移除Python注释content = re.sub(r'#.*', '', content)return contentdef find_chinese_in_files(project_dir, output_file):"""扫描Android工程目录，找出非strings.xml文件中的中文内容:param project_dir: Android工程根目录:param output_file: 输出文件路径"""# 匹配中文字符的正则表达式chinese_pattern = re.compile(r'[\u4e00-\u9fa5]+')# 排除的目录# excluded_dirs = {'.git', '.idea', 'build', 'gradle', 'libs', 'assets', 'bin', 'gen', 'captures'}excluded_dirs = {'.git', '.idea', 'build', 'gradle', 'libs', 'assets', 'bin', 'gen', 'captures','.gradle', '.kts', '.py', '.html', '.js', '.ts', '.json', '.txt'}# 排除的文件类型excluded_exts = {'.png', '.jpg', '.jpeg', '.gif', '.webp', '.ico', '.svg','.mp3', '.wav', '.ogg', '.mp4', '.avi', '.mkv','.pdf', '.doc', '.docx', '.xls', '.xlsx','.jar', '.aar', '.so', '.keystore', '.pro', '.iml', '.dex','.txt'}# 需要检查的文件类型included_exts = {'.xml', '.java', '.kt'}# included_exts = {'.xml', '.java', '.kt', '.gradle', '.kts', '.py', '.html', '.js', '.ts', '.json', '.txt'}with open(output_file, 'w', encoding='utf-8') as out_f:for root, dirs, files in os.walk(project_dir):# 跳过排除的目录dirs[:] = [d for d in dirs if d not in excluded_dirs]for file in files:file_path = os.path.join(root, file)rel_path = os.path.relpath(file_path, project_dir)ext = os.path.splitext(file)[1].lower()# 跳过strings.xml文件if file == 'strings.xml':continue# 跳过排除的文件类型if ext in excluded_exts:continue# 如果指定了包含的文件类型，跳过不在列表中的文件if included_exts and ext not in included_exts:continuetry:with open(file_path, 'r', encoding='utf-8') as f:lines = f.readlines()found_chinese = []for line_num, line in enumerate(lines, start=1):original_line = lineline = line.strip()# 跳过空行和注释行if not line or is_comment_line(line, ext):continue# 预处理：移除注释内容if ext == '.xml':processed_line = remove_xml_comments(original_line)else:processed_line = remove_code_comments(original_line, ext)# 如果预处理后为空，跳过if not processed_line.strip():continue# 跳过空行和日志语句if is_log_statement(processed_line):continue# 检查中文内容matches = chinese_pattern.findall(processed_line)if matches:found_chinese.append({'line_num': line_num,'content': original_line.strip(),'matches': matches})if found_chinese:out_f.write(f"文件: {rel_path}\n")for item in found_chinese:# out_f.write(f"行号: {item['line_num']}\n")out_f.write(f"内容: {item['content']}\n")# out_f.write("找到的中文: " + ", ".join(item['matches']) + "\n")out_f.write("-" * 50 + "\n")out_f.write("\n")except (UnicodeDecodeError, PermissionError):# 跳过二进制文件或无权限文件continueexcept Exception as e:print(f"处理文件 {file_path} 时出错: {str(e)}")continueif __name__ == "__main__":parser = argparse.ArgumentParser(description='扫描Android工程中的非strings.xml中文内容（排除注释，带行号）')parser.add_argument('project_dir', help='Android工程根目录路径')parser.add_argument('output_file', help='输出文件路径')args = parser.parse_args()find_chinese_in_files(args.project_dir, args.output_file)print(f"扫描完成，结果已保存到 {args.output_file}")

2. 将xml中的中文字符转成Execl表格输出(xml_to_excel.py)

import xml.etree.ElementTree as ET
import pandas as pddef convert_xml_to_excel(xml_file, excel_file):tree = ET.parse(xml_file)root = tree.getroot()data = []for child in root:if child.tag == 'string':data.append({'name': child.attrib['name'],'value': child.text if child.text else ''})df = pd.DataFrame(data)df.to_excel(excel_file, index=False)# 使用示例
convert_xml_to_excel('app/src/main/res/values/strings.xml', 'strings.xlsx')

3. 具体使用

3.1.将中文提取出来

python [find_chinese.py目录] [你的工程所在的目录] [生成的txt目录(如：c:\chinese_content.txt)]

3.2. 将string.xml 转成string.xlsx，在你工程目录下执行

python [xml_to_excel.py]