如何在ruamel.yaml中实现tuple与np.array的隐式解析器及健壮表示器？

我有一个项目，要求用户手动编写YAML文件，其中部分条目需要以tuple或numpy数组格式填写。Python内部会区分tuple和list来提供便捷接口，比如(1, 2, 3)和[1, 2, 3]是不同的。为提升用户体验，希望用户能直接用括号输入tuple（如name: (1,2,3)），用np.array([1,2,3])格式输入numpy数组（已接受精度损失的妥协）。我使用ruamel.yaml是因为它能保留注释。

目前已实现可用功能，但解析部分不够规范：未使用合适的隐式解析器，而是用了不够健壮的eval。以下是最小可运行示例，注释标注了实现不够健壮或不规范的地方：

import sys
import numpy as np
import ruamel.yaml


def _tupleRepresenter(dumper, data):
    # TODO: Make this more robust
    return dumper.represent_scalar(u'tag:yaml.org,2002:str', str(data))


def _numpyRepresenter(dumper, data):
    # TODO: Make this more robust
    as_string = 'np.array(' + np.array2string(data, max_line_width=np.inf, precision=16, prefix='np.array(', separator=', ', suffix=')') + ')'
    return dumper.represent_scalar(u'tag:yaml.org,2002:str', as_string)


def load_yaml(file):
    # TODO: Resolve tuples and arrays properly when loading
    yaml = ruamel.yaml.YAML()
    yaml.Representer.add_representer(tuple, _tupleRepresenter)
    yaml.Representer.add_representer(np.ndarray, _numpyRepresenter)
    return yaml.load(file)


def dump_yaml(data, file):
    yaml = ruamel.yaml.YAML()
    yaml.Representer.add_representer(tuple, _tupleRepresenter)
    yaml.Representer.add_representer(np.ndarray, _numpyRepresenter)
    return yaml.dump(data, file)


yaml_file = """
test_tuple: (1, 2, 3)
test_array: np.array([4,5,6])
"""

data = load_yaml(yaml_file)

data['test_tuple'] = eval(data['test_tuple']) # This feels dirty
data['test_array'] = eval(data['test_array']) # This feels dirty

dump_yaml(data, sys.stdout)
# test_tuple: (1, 2, 3)
# test_array: np.array([4, 5, 6])

我希望能优化该实现，使用规范的隐式解析器、健壮的表示器，更符合ruamel.yaml的设计意图。

更新 #

在帮助下，我实现了几乎完整的功能（暂时忽略用正规解析替代eval的需求），但仍存一个问题：新标签被导出为字符串，重新加载时会变为字符串，无法实现多次往返解析。如何解决该问题？以下是最小可运行示例：

import sys
import numpy as np
import ruamel.yaml

# TODO: Replace evals by actual parsing
# TODO: Represent custom types without the string quotes

_tuple_re = "^(?:\\((?:.|\\n|\\r)*,(?:.|\\n|\\r)*\\){1}(?: |\\n|\\r)*$)"
_array_re = "^(?:(np\\.|)array\\(\\[(?:.|\\n|\\r)*,(?:.|\\n|\\r)*\\]\\){1}(?: |\\n|\\r)*$)"
_complex_re = "^(?:(?:\\d+(?:(?:\\.\\d+)?(?:e[+\\-]\\d+)?)?)?(?: *[+\\-] *))?(?:\\d+(?:(?:\\.\\d+)?(?:e[+\\-]\\d+)?)?)?[jJ]$"


def _tuple_constructor(self, node):
    return eval(self.construct_scalar(node))


def _array_constructor(self, node):
    value = node.value
    if not value.startswith('np.'):
        value = 'np.' + value
    return eval(value)


def _complex_constructor(self, node):
    return eval(node.value)


def _tuple_representer(dumper, data):
    return dumper.represent_scalar(u'tag:yaml.org,2002:str', str(data))


def _array_representer(dumper, data):
    as_string = 'np.array(' + np.array2string(data, max_line_width=np.inf, precision=16, prefix='np.array(', separator=', ', suffix=')') + ')'
    as_string = as_string.replace(' ', '').replace(',', ', ')
    return dumper.represent_scalar(u'tag:yaml.org,2002:str', as_string)


def _complex_representer(dumper, data):
    repr = str(data).replace('(', '').replace(')', '')
    return dumper.represent_scalar(u'tag:yaml.org,2002:str', repr)


custom_types = {
    '!tuple':   {'re':_tuple_re,   'constructor': _tuple_constructor,   'representer':_tuple_representer,   'type': tuple,      'first':list('(')             },
    '!nparray': {'re':_array_re,   'constructor': _array_constructor,   'representer':_array_representer,   'type': np.ndarray, 'first':list('an')            },
    '!complex': {'re':_complex_re, 'constructor': _complex_constructor, 'representer':_complex_representer, 'type': complex,    'first':list('0123456789+-jJ')},
}


def load_yaml(file):
    yaml = ruamel.yaml.YAML()
    for tag,ct in custom_types.items():
        yaml.Constructor.add_constructor(tag, ct['constructor'])
        yaml.Resolver.add_implicit_resolver(tag, ruamel.yaml.util.RegExp(ct['re']), ct['first'])
        yaml.Representer.add_representer(ct['type'], ct['representer'])
    return yaml.load(file)


def dump_yaml(data, file):
    yaml = ruamel.yaml.YAML()
    for tag,ct in custom_types.items():
        yaml.Constructor.add_constructor(tag, ct['constructor'])
        yaml.Resolver.add_implicit_resolver(tag, ruamel.yaml.util.RegExp(ct['re']), ct['first'])
        yaml.Representer.add_representer(ct['type'], ct['representer'])
    return yaml.dump(data, file)

yaml_file = """
test_tuple: (1, 2, 3)
test_array: array([4.0,5+0j,6.0j])
test_complex: 3 + 2j
"""

data = load_yaml(yaml_file)

dump_yaml(data, sys.stdout)
# test_tuple: '(1, 2, 3)'
# test_array: 'np.array([4.+0.j, 5.+0.j, 0.+6.j])'
# test_complex: '3+2j'

感谢您的帮助！

内容的提问来源于stack exchange，提问作者JeanOlivier