利用Python去除重复的下划线的解决方法

import re

def normalize_underscores(text):
    """
    规范化字符串中的下划线
    Args:
        text (str): 输入字符串
    Returns:
        str: 规范化后的字符串
    """
    return re.sub(r'_{2,}', '_', text)

test_cases = [
    ('country___area', 'country_area'),
    ('hello__world', 'hello_world'),
    ('a___b', 'a_b'),
    ('__start__', '_start_'),
    ('___multiple___sections___', '_multiple_sections_'),
    ('no_change', 'no_change'),
    ('123___456', '123_456'),
    ('trailing___', 'trailing_'),
    ('___leading', '_leading'),
    ('a_b_c', 'a_b_c')
]

# 执行测试
for input_str, expected in test_cases:
    result = normalize_underscores(input_str)
    assert result == expected, f"❌ 测试失败: {input_str} → {result} (期望: {expected})"
    print(f"✅ 测试通过: {input_str} → {result}")

✅ 测试通过: country___area → country_area
✅ 测试通过: hello__world → hello_world
✅ 测试通过: a___b → a_b
...
✅ 测试通过: a_b_c → a_b_c

# 诊断隐藏字符
def debug_string(s):
    print(f"原始字符串: {s}")
    print("ASCII码:", [f"{ord(c):08b}" for c in s])

# 测试特殊字符
print(normalize_underscores('test_\u200b_\u200b_test'))  # 处理零宽字符

def clean_data_pipeline(data):
    return [normalize_underscores(item) for item in data]

# 示例数据清洗
dirty_data = ['first__name', 'last___name', 'phone_number']
clean_data = clean_data_pipeline(dirty_data)
# 输出: ['first_name', 'last_name', 'phone_number']

# Flask路由规范化
@app.route('/user/<normalized_username>')
def user_profile(normalized_username):
    raw_username = re.sub(r'_{2,}', '_', normalized_username)
    # ...后续处理