python dict和set的实现

dict：

"""
哈希表，实现字典
"""


class MyArray(object):
    def __init__(self, size=32, init=None):
        self.size = size
        self._items = [init]*self.size

    def __getitem__(self, item):
        return self._items[item]

    def __setitem__(self, item, value=None):
        self._items[item] = value

    def __len__(self):
        return self.size

    def clear(self, value=None):
        for i in range(len(self._items)):
            self._items[i] = value

    def __iter__(self):
        for i in self._items:
            yield i


class Slot(object):
    """定义一个 hash 表 数组的槽
    注意，一个槽有三种状态，看你能否想明白，相比链接法解决冲突，二次查探法删除一个 key 的操作稍微复杂
    1. 从未使用 HashMap.UNUSED. 此槽没有被使用过和冲突过，查找时只要找到 UNUSED 就不用继续查探了
    2. 使用过，但是 remove 了，此时时 HashMap.EMPTY，该探查点后边的元素仍可能时有 Key
    3. 槽正在使用 Slot 节点
    """
    def __init__(self, key, value):
        self.key, self.value = key, value


class HashTable(object):
    UNUSED = None  # slot 没有被使用过
    EMPTY = Slot(None, None)  # 使用过被删除了

    def __init__(self):
        self._table = MyArray(8, init=HashTable.UNUSED)  # 这个东西其实就是寻址表
        self.length = 0

    @property
    def _load_factor(self):
        return self.length / float(len(self._table))

    def __len__(self):
        return self.length

    def _hash(self, key):  # 哈希函数，得到寻址表的下标，为了实现冲突最小化，而这里，就是实现冲突最小化的方法
        # 槽里面放的是 key
        return abs(hash(key)) % len(self._table)

    def _find_key(self, key):  # 根据 key 寻找槽，获取key对应的值
        index = self._hash(key)
        _len = len(self._table)
        while self._table[index] is not HashTable.UNUSED:  # 如果寻址表的槽中的值是 UNUSED,就是这个槽没被使用过，坑定不会有key了
            if self._table[index] is HashTable.EMPTY:  # 这个槽被用过，删除了
                index= (index*5 + 1) % _len  # 寻找下一个槽，这个就是解决哈希冲突的最底层代码了
                continue
            elif self._table[index].key == key:  # 这个槽正在被使用，且槽中的key刚好是需要寻找的key
                return index
            else:
                index = (index*5 + 1) % _len  # 寻找下一个槽
        return None  # 什么都没有找到

    def _slot_can_insert(self, index):
        return self._table[index] is HashTable.EMPTY or self._table[index] is HashTable.UNUSED

    def _find_slot_for_insert(self, key):
        index = self._hash(key)
        _len = len(self._table)
        while not self._slot_can_insert(index):
            index = (index*5 + 1) % _len
        return index

    def __contains__(self, item):
        index = self._find_key(item)
        return index is not None

    def add(self, key, value):
        if key in self:  # 如果key已经存在，则执行update操作
            index = self._find_key(key)
            self._table[index].value = value
            return False
        else:  # 如果key不在表中，寻找一个槽，插入key，value
            index = self._find_slot_for_insert(key)
            self._table[index] = Slot(key, value)
            self.length += 1
            if self._load_factor >= 0.8:
                self._rehash()
                return True

    def _rehash(self):
        old_table = self._table
        newsize = len(self._table) * 2
        self._table = MyArray(newsize, HashTable.UNUSED)
        self.length = 0
        for slot in old_table:
            if slot is not HashTable.UNUSED and slot is not HashTable.EMPTY:
                index = self._find_slot_for_insert(slot.key)
                self._table[index] = slot
                self.length += 1

    def get(self, key):
        index = self._find_key(key)
        if index is not None:
            return self._table[index].value
        else:
            return None

    def remove(self,key):
        index = self._find_key(key=key)
        if index is None:
            raise KeyError
        value = self._table[index].value
        self._table[index] = HashTable.EMPTY
        self.length -= 1
        return value

    def __iter__(self):
        for slot in self._table:
            if slot not in (HashTable.EMPTY, HashTable.UNUSED):
                yield slot.key


class DictADT(HashTable):

    def __setitem__(self, key, value):
        self.add(key, value)

    def __getitem__(self, item):
        if item not in self:
            raise KeyError
        else:
            return self.get(key=item)

    def _iter_slot(self):
        for slot in self._table:
            if slot not in (HashTable.EMPTY, HashTable.UNUSED):
                yield slot

    def items(self):
        for slot in self._iter_slot():
            yield slot.key, slot.value

    def keys(self):
        for slot in self._iter_slot():
            yield slot.key

    def values(self):
        for slot in self._iter_slot():
            yield slot.value

set：

"""
哈希表，实现集合
"""


class MyArray(object):
    def __init__(self, size=32, init=None):
        self.size = size
        self._items = [init]*self.size

    def __getitem__(self, item):
        return self._items[item]

    def __setitem__(self, item, value=None):
        self._items[item] = value

    def __len__(self):
        return self.size

    def clear(self, value=None):
        for i in range(len(self._items)):
            self._items[i] = value

    def __iter__(self):
        for i in self._items:
            yield i


class Slot(object):
    """定义一个 hash 表 数组的槽
    注意，一个槽有三种状态，看你能否想明白，相比链接法解决冲突，二次查探法删除一个 key 的操作稍微复杂
    1. 从未使用 HashMap.UNUSED. 此槽没有被使用过和冲突过，查找时只要找到 UNUSED 就不用继续查探了
    2. 使用过，但是 remove 了，此时时 HashMap.EMPTY，该探查点后边的元素仍可能时有 Key
    3. 槽正在使用 Slot 节点
    """
    def __init__(self, key, value):
        self.key, self.value = key, value


class HashTable(object):
    UNUSED = None  # slot 没有被使用过
    EMPTY = Slot(None, None)  # 使用过被删除了

    def __init__(self):
        self._table = MyArray(8, init=HashTable.UNUSED)  # 这个东西其实就是寻址表
        self.length = 0

    @property
    def _load_factor(self):
        return self.length / float(len(self._table))

    def __len__(self):
        return self.length

    def _hash(self, key):  # 哈希函数，得到寻址表的下标，为了实现冲突最小化，而这里，就是实现冲突最小化的方法
        # 槽里面放的是 key
        return abs(hash(key)) % len(self._table)

    def _find_key(self, key):  # 根据 key 寻找槽，获取key对应的值
        index = self._hash(key)
        _len = len(self._table)
        while self._table[index] is not HashTable.UNUSED:  # 如果寻址表的槽中的值是 UNUSED,就是这个槽没被使用过，坑定不会有key了
            if self._table[index] is HashTable.EMPTY:  # 这个槽被用过，删除了
                index= (index*5 + 1) % _len  # 寻找下一个槽，这个就是解决哈希冲突的最底层代码了
                continue
            elif self._table[index].key == key:  # 这个槽正在被使用，且槽中的key刚好是需要寻找的key
                return index
            else:
                index = (index*5 + 1) % _len  # 寻找下一个槽
        return None  # 什么都没有找到

    def _slot_can_insert(self, index):
        return self._table[index] is HashTable.EMPTY or self._table[index] is HashTable.UNUSED

    def _find_slot_for_insert(self, key):
        index = self._hash(key)
        _len = len(self._table)
        while not self._slot_can_insert(index):
            index = (index*5 + 1) % _len
        return index

    def __contains__(self, item):
        index = self._find_key(item)
        return index is not None

    def add(self, key, value):
        if key in self:  # 如果key已经存在，则执行update操作
            index = self._find_key(key)
            self._table[index].value = value
            return False
        else:  # 如果key不在表中，寻找一个槽，插入key，value
            index = self._find_slot_for_insert(key)
            self._table[index] = Slot(key, value)
            self.length += 1
            if self._load_factor >= 0.8:
                self._rehash()
                return True

    def _rehash(self):
        old_table = self._table
        newsize = len(self._table) * 2
        self._table = MyArray(newsize, HashTable.UNUSED)
        self.length = 0
        for slot in old_table:
            if slot is not HashTable.UNUSED and slot is not HashTable.EMPTY:
                index = self._find_slot_for_insert(slot.key)
                self._table[index] = slot
                self.length += 1

    def get(self, key):
        index = self._find_key(key)
        if index is not None:
            return self._table[index].value
        else:
            return None

    def remove(self,key):
        index = self._find_key(key=key)
        if index is None:
            raise KeyError
        value = self._table[index].value
        self._table[index] = HashTable.EMPTY
        self.length -= 1
        return value

    def __iter__(self):
        for slot in self._table:
            if slot not in (HashTable.EMPTY, HashTable.UNUSED):
                yield slot.key


class SetADT(HashTable):

    def add(self, key):
        return super(SetADT, self).add(key, True)

    def __and__(self, other_set):
        new_set = SetADT()
        for element_a in self:
            if element_a in other_set:
                new_set.add(element_a)
        return new_set

    def __sub__(self, other):
        new_set = SetADT()
        for element_a in self:
            if element_a not in other:
                new_set.add(element_a)
        return new_set

    def __or__(self, other):
        new_set = SetADT()
        for element_a in self:
            new_set.add(element_a)
        for element_b in other:
            new_set.add(element_b)
        return new_set