一文详解Python集合(Set)的核心特性和应用指南

# 1. 基础字面量创建
s1 = {1, 2, 3, 3}  # 结果: {1, 2, 3}

# 2. 从可迭代对象创建（常用技巧）
s2 = set([1, 2, 3])       # 从列表
s3 = set("hello")         # 结果: {'h', 'e', 'l', 'o'}，字符串被拆分为字符
s4 = set((1, 2, 3))       # 从元组

# 3. 空集合的特殊性（新手易错点）
empty_list = [] 
empty_set_literal = {}   # 这实际上是空字典！
empty_set_constructor = set() # 这才是空集合

raw_logs = ["192.168.1.1", "10.0.0.1", "192.168.1.1", "172.16.0.1"]
unique_ips = set(raw_logs)
# 结果: {'10.0.0.1', '172.16.0.1', '192.168.1.1'}

s = {None, 1, "test"}
print(None in s)  # True

# 错误示范
data = {1, 2, None, 4}
# 假设你想求和
try:
    total = sum(data) 
except TypeError as e:
    print(f"出错: {e}") # 'NoneType' object is not callable (如果是其他场景) 或者 sum 不支持包含 None
    # 实际上 sum() 会直接报错: TypeError: unsupported operand type(s) for +: 'int' and 'NoneType'

def safe_set_conversion(data):
    if data is None:
        return set()
    # 如果 data 已经是集合，直接返回；如果是列表/元组，进行转换
    return set(data) if not isinstance(data, set) else data

print(safe_set_conversion(None))      # set()
print(safe_set_conversion([1, 2]))    # {1, 2}
print(safe_set_conversion({1, 2}))    # {1, 2}

# 这会报错: TypeError: unhashable type: 'list'
# invalid_set = {[1, 2], [3, 4]}

valid_set = {(1, 2), (3, 4)}  # OK

import unittest

# --- 被测代码 (Production Code) ---

def get_common_tags(tags_a, tags_b):
    """获取两个标签集合的交集，安全处理 None 输入"""
    if tags_a is None: tags_a = set()
    if tags_b is None: tags_b = set()
    return tags_a & tags_b  # 集合交集操作

def add_tags(existing_tags, new_tag):
    """添加新标签，existing_tags 可能是 None"""
    if existing_tags is None:
        existing_tags = set()
    # 确保 existing_tags 是集合类型
    if not isinstance(existing_tags, set):
        existing_tags = set(existing_tags)
    
    existing_tags.add(new_tag)
    return existing_tags

# --- 测试代码 (Test Code) ---

class TestSetOperations(unittest.TestCase):

    def test_common_tags_basic(self):
        a = {'python', 'java', 'go'}
        b = {'python', 'rust', 'go'}
        result = get_common_tags(a, b)
        # 使用 assertEqual 比较集合，顺序无关
        self.assertEqual(result, {'python', 'go'})

    def test_common_tags_with_none(self):
        """测试包含 None 输入的情况"""
        a = {'python', None} # 集合可以包含 None
        b = None
        result = get_common_tags(a, b)
        # 预期结果应为空集合，因为 None 被转换为空集，交集为空
        self.assertEqual(result, set())

    def test_add_tags_handles_none(self):
        """测试向 None 添加标签"""
        result = add_tags(None, 'new_tag')
        self.assertIn('new_tag', result)
        self.assertIsInstance(result, set)

    def test_add_tags_duplicate(self):
        """测试添加重复标签"""
        existing = {'tag1', 'tag2'}
        result = add_tags(existing, 'tag1')
        # 集合大小不应改变
        self.assertEqual(len(result), 2)
        self.assertEqual(result, {'tag1', 'tag2'})

if __name__ == '__main__':
    unittest.main()

# 过滤掉列表中的负数并去重
numbers = [1, -2, 3, -2, 5, 1]
positive_set = {x for x in numbers if x > 0}
# 结果: {1, 3, 5}

fs = frozenset([1, 2, 3])
d = {fs: "value"}  # OK
# fs.add(1)  # 报错，不可变