L1_XTuner_code/change_script.py

import json
import argparse
from tqdm import tqdm

def process_line(line, old_text, new_text):
    # 解析 JSON 行
    data = json.loads(line)
    
    # 递归函数来处理嵌套的字典和列表
    def replace_text(obj):
        if isinstance(obj, dict):
            return {k: replace_text(v) for k, v in obj.items()}
        elif isinstance(obj, list):
            return [replace_text(item) for item in obj]
        elif isinstance(obj, str):
            return obj.replace(old_text, new_text)
        else:
            return obj
    
    # 处理整个 JSON 对象
    processed_data = replace_text(data)
    
    # 将处理后的对象转回 JSON 字符串
    return json.dumps(processed_data, ensure_ascii=False)

def main(input_file, output_file, old_text, new_text):
    with open(input_file, 'r', encoding='utf-8') as infile, \
         open(output_file, 'w', encoding='utf-8') as outfile:
        
        # 计算总行数用于进度条
        total_lines = sum(1 for _ in infile)
        infile.seek(0)  # 重置文件指针到开头
        
        # 使用 tqdm 创建进度条
        for line in tqdm(infile, total=total_lines, desc="Processing"):
            processed_line = process_line(line.strip(), old_text, new_text)
            outfile.write(processed_line + '\n')

if __name__ == "__main__":
    parser = argparse.ArgumentParser(description="Replace text in a JSONL file.")
    parser.add_argument("input_file", help="Input JSONL file to process")
    parser.add_argument("output_file", help="Output file for processed JSONL")
    parser.add_argument("--old_text", default="尖米", help="Text to be replaced")
    parser.add_argument("--new_text", default="机智流", help="Text to replace with")
    args = parser.parse_args()

    main(args.input_file, args.output_file, args.old_text, args.new_text)