python - 使用 ruamel.yaml 安全转储和加载 defaultdict
问题描述
我正在尝试(反)序列化具有ruamel.yamlcollections.defaultdict
属性的类类(在我的情况下为 3.6+)。
这将是我想开始工作的一个最小示例:
from collections import defaultdict
import ruamel.yaml
from pathlib import Path
class Foo:
def __init__(self):
self.x = defaultdict()
YAML = ruamel.yaml.YAML(typ="safe")
YAML.register_class(Foo)
YAML.register_class(defaultdict)
fp = Path("./test.yaml")
YAML.dump(Foo(), fp)
YAML.load(fp)
但这失败了:
AttributeError: 'collections.defaultdict' object has no attribute '__dict__'
任何不需要为每个“Foo-like”类编写自定义代码的想法?我希望我可以添加一个不同的代表defaultdict
对象添加一个不同的表示器,但到目前为止我的尝试都是徒劳的。
完整追溯:
Traceback (most recent call last):
File "./tests/test_yaml.py", line 18, in <module>
YAML.dump(Foo(), fp)
File "C:\miniconda-windows\envs\ratio\lib\site-packages\ruamel\yaml\main.py", line 439, in dump
return self.dump_all([data], stream, _kw, transform=transform)
File "C:\miniconda-windows\envs\ratio\lib\site-packages\ruamel\yaml\main.py", line 453, in dump_all
self._context_manager.dump(data)
File "C:\miniconda-windows\envs\ratio\lib\site-packages\ruamel\yaml\main.py", line 801, in dump
self._yaml.representer.represent(data)
File "C:\miniconda-windows\envs\ratio\lib\site-packages\ruamel\yaml\representer.py", line 81, in represent
node = self.represent_data(data)
File "C:\miniconda-windows\envs\ratio\lib\site-packages\ruamel\yaml\representer.py", line 108, in represent_data
node = self.yaml_representers[data_types[0]](self, data)
File "C:\miniconda-windows\envs\ratio\lib\site-packages\ruamel\yaml\main.py", line 638, in t_y
tag, data, cls, flow_style=representer.default_flow_style
File "C:\miniconda-windows\envs\ratio\lib\site-packages\ruamel\yaml\representer.py", line 384, in represent_yaml_object
return self.represent_mapping(tag, state, flow_style=flow_style)
File "C:\miniconda-windows\envs\ratio\lib\site-packages\ruamel\yaml\representer.py", line 218, in represent_mapping
node_value = self.represent_data(item_value)
File "C:\miniconda-windows\envs\ratio\lib\site-packages\ruamel\yaml\representer.py", line 108, in represent_data
node = self.yaml_representers[data_types[0]](self, data)
File "C:\miniconda-windows\envs\ratio\lib\site-packages\ruamel\yaml\main.py", line 638, in t_y
tag, data, cls, flow_style=representer.default_flow_style
File "C:\miniconda-windows\envs\ratio\lib\site-packages\ruamel\yaml\representer.py", line 383, in represent_yaml_object
state = data.__dict__.copy()
AttributeError: 'collections.defaultdict' object has no attribute '__dict__'
解决方案
这是因为defaultdict
它是内置类的子类dict
,它没有__dict__
属性供 YAML 编码器生成类属性名称。在这种情况下defaultdict
应该被视为一个dict
,但问题是该类的represent_data
方法ruamel.yaml.representer.BaseRepresenter
只查看对象本身的类来确定是否存在该对象的表示器:
data_types = type(data).__mro__
# ...skipped
if data_types[0] in self.yaml_representers:
node = self.yaml_representers[data_types[0]](self, data)
相反,应该做的是检查其中的任何数据类型__mro__
是否具有表示器,如果找到则使用它:
if any(data_type in self.yaml_representers for data_type in data_types):
node = self.yaml_representers[next(data_type for data_type in data_types if data_type in self.yaml_representers)](self, data)
所以我们可以自己猴子修补这个方法:
def represent_data(self, data):
# type: (Any) -> Any
if self.ignore_aliases(data):
self.alias_key = None
else:
self.alias_key = id(data)
if self.alias_key is not None:
if self.alias_key in self.represented_objects:
node = self.represented_objects[self.alias_key]
# if node is None:
# raise RepresenterError(
# "recursive objects are not allowed: %r" % data)
return node
# self.represented_objects[alias_key] = None
self.object_keeper.append(data)
data_types = type(data).__mro__
if representer.PY2:
# if type(data) is types.InstanceType:
if isinstance(data, representer.types.InstanceType):
data_types = representer.get_classobj_bases(data.__class__) + list(data_types)
if any(data_type in self.yaml_representers for data_type in data_types):
node = self.yaml_representers[next(data_type for data_type in data_types if data_type in self.yaml_representers)](self, data)
else:
for data_type in data_types:
if data_type in self.yaml_multi_representers:
node = self.yaml_multi_representers[data_type](self, data)
break
else:
if None in self.yaml_multi_representers:
node = self.yaml_multi_representers[None](self, data)
elif None in self.yaml_representers:
node = self.yaml_representers[None](self, data)
else:
node = representer.ScalarNode(None, representer.text_type(data))
# if alias_key is not None:
# self.represented_objects[alias_key] = node
return node
representer.BaseRepresenter.represent_data = represent_data
这样您的代码无需注册即可工作defaultdict
:
class Foo:
def __init__(self):
self.x = defaultdict()
YAML = ruamel.yaml.YAML(typ="safe")
YAML.register_class(Foo)
# YAML.register_class(defaultdict)
fp = Path("/temp/test.yaml")
YAML.dump(Foo(), fp)
YAML.load(fp)
编辑:一个更优雅的解决方案是简单地将SafeRepresenter.represent_dict
方法添加为代表defaultdict
:
from ruamel.yaml import representer
representer.SafeRepresenter.add_representer(defaultdict, representer.SafeRepresenter.represent_dict)
推荐阅读
- c# - 如何在 C# 中正确反序列化 JSON
- google-cloud-platform - BigQueryIO - 尽管有 CreateDisposition.CREATE_IF_NEEDED,但只能创建第一天表
- python - Python3,word2vec,如何在我的模型中获取关于“价格”的相似度排名列表
- event-handling - 如何在父 Svelte 组件中使用事件委托
- c - strtok 不返回任何值
- microsoft-graph-api - Microsoft Graph API - 获取订阅问题
- python - 根据另一个数据帧的索引从一个数据帧中保留索引
- powershell - Get-child Item Output 的文件夹名称问题
- gitlab - 当 GitLab 的新版本发布时,我如何收到通知电子邮件?
- python - 风格指南:如何在大项目中不陷入混乱