utils/text_utils.py

import difflib
import json
import re
from typing import List

def compare_texts(text1: str, text2: str) -> str:
    """对比两段文本，返回差异"""
    lines1 = text1.splitlines(keepends=True)
    lines2 = text2.splitlines(keepends=True)

    diff = difflib.unified_diff(lines1, lines2, lineterm='')
    return ''.join(diff)

def batch_replace(text: str, replacements: dict) -> str:
    """批量文本替换"""
    result = text
    for old, new in replacements.items():
        result = result.replace(old, new)
    return result

def format_json(json_str: str, indent: int = 2) -> str:
    """格式化JSON"""
    try:
        data = json.loads(json_str)
        return json.dumps(data, indent=indent, ensure_ascii=False)
    except json.JSONDecodeError as e:
        return f"JSON解析错误: {str(e)}"

def minify_json(json_str: str) -> str:
    """压缩JSON"""
    try:
        data = json.loads(json_str)
        return json.dumps(data, separators=(',', ':'), ensure_ascii=False)
    except json.JSONDecodeError as e:
        return f"JSON解析错误: {str(e)}"

def count_chars(text: str) -> dict:
    """统计字数"""
    total_chars = len(text)
    chinese_chars = len(re.findall(r'[一-鿿]', text))
    english_chars = len(re.findall(r'[a-zA-Z]', text))
    digits = len(re.findall(r'\d', text))
    spaces = len(re.findall(r'\s', text))
    punctuation = total_chars - chinese_chars - english_chars - digits - spaces

    return {
        '总字符数': total_chars,
        '中文字数': chinese_chars,
        '英文字母': english_chars,
        '数字': digits,
        '空格': spaces,
        '标点符号': punctuation,
        '总行数': len(text.splitlines())
    }