pymongo教程(3)——自定义数据类型

pymongo提供一些常用的数据类型，如：数据、字符串、日期等。如果感觉还不能满足需求，那么还可以自定义数据类型。

首先定义一个类：

class Custom(object):
    def __init__(self, x):
        self.__x = x

    def x(self):
        return self.__x

要将自定义类型的数据存入数据库中需要先进行编码；将数据从数据库读取出来后又需要再解码。

手动编码/解码

我们可以定义两个方法，在插入和查询数据时进行手动的编码、解码。

def encode_custom(custom):
    return {"_type": "custom", "x": custom.x()}

def decode_custom(document):
    assert document["_type"] == "custom"
    return Custom(document["x"])

print(db.test.insert({"custom": encode_custom(Custom(5))}))
print(db.test.find_one()['custom'])

自动编码/解码

手动地进行编码虽然可行，但是还是不太方便。我们还可以使用 SONManipulator 进行自动编码。

from pymongo.son_manipulator import SONManipulator
class Transform(SONManipulator):
    def transform_incoming(self, son, collection):
        for (key, value) in son.items():
            if isinstance(value, Custom):
                son[key] = encode_custom(value)
            elif isinstance(value, dict): # Make sure we recurse into sub-docs
                son[key] = self.transform_incoming(value, collection)
        return son

    def transform_outgoing(self, son, collection):
        for (key, value) in son.items():
            if isinstance(value, dict):
                if "_type" in value and value["_type"] == "custom":
                    son[key] = decode_custom(value)
                else: # Again, make sure to recurse into sub-docs
                    son[key] = self.transform_outgoing(value, collection)
        return son

db.add_son_manipulator(Transform())
print(db.test.insert({"custom": Custom(5)}))
print(db.test.find_one())

二进制编码

我们也可以将其编码成二进制进行存储。

from bson.binary import Binary
def to_binary(custom):
    return Binary(str(custom.x()), 128)

def from_binary(binary):
    return Custom(int(binary))

class TransformToBinary(SONManipulator):
    def transform_incoming(self, son, collection):
        for (key, value) in son.items():
            if isinstance(value, Custom):
                son[key] = to_binary(value)
            elif isinstance(value, dict):
                son[key] = self.transform_incoming(value, collection)
        return son

    def transform_outgoing(self, son, collection):
        for (key, value) in son.items():
            if isinstance(value, Binary) and value.subtype == 128:
                son[key] = from_binary(value)
            elif isinstance(value, dict):
                son[key] = self.transform_outgoing(value, collection)
        return son

db.add_son_manipulator(TransformToBinary())
print(db.test.insert({"custom": Custom(5)}))
print(db.test.find_one())