python collections 模块 之namedtuple

namedtuple

collections.namedtuple(typename, filed_name, *, rename=False, module=None)

创建一个以 typename 命名的 tuple 子类，这个子类用于创建类元组对象，这些对象可以像元组一样被索引和迭代。

field_name: 指定 namedtuple 的字段名，可以是列表，可以是用空格或逗号隔开的字符串。

rename: field_name 中无效的标识符（字符，数字，下划线，并且不以下划线或数字开头，不与内置变量名冲突）将被自动替换为下划线加索引（例：_1），

module: 设置__module__的值，默认为 '__main__'

from collections import namedtuple

Point = namedtuple('Point', ['x', 'y'])
a = Point(1, 2)

输出:

>>> a[0]
1
>>> a[1]
2
>>> a.x
1
>>> a.y
2
>>> c,d = a
>>> c, d
(1, 2)

namedtuple 除了继承 tuples 的方法外，还有3个额外的方法和2个额外的属性：

classmethod  somenamedtuple._make(iterable)

用已存在的列表或可迭代对象创建 namedtuple 实例：

>>> t = [1, 2]
>>> Point._make(t)
Point(x=1, y=2)

somenamedtuple._asdict()

将 namedtuple 转变为 OrderDict

>>> p = Point(x=11, y=22)
>>> p._asdict()
OrderedDict([('x', 11), ('y', 22)])

somenamedtuple._replace()

替换属性值，返还一个新的对象

>>> p = Point(x=11, y=22)
>>> p._replace(x=33)
Point(x=33, y=22)

_replace() 还有一个很有用的特性，就是当你的命名元组拥有可选字段或者缺失字段的时候，它能够方便的添加数据。

from collections import namedtuple
Stock = namedtuple('Stock', ['name', 'shares', 'price', 'date', 'time'])
# Create a prototype instance
stock_prototype = Stock('', 0, 0.0, None, None)
# Function to convert a dictionary to a Stock
def dict_to_stock(s):
return stock_prototype._replace(**s)

>>> a = {'name': 'ACME', 'shares': 100, 'price': 123.45}
>>> dict_to_stock(a)
Stock(name='ACME', shares=100, price=123.45, date=None, time=None)
>>> b = {'name': 'ACME', 'shares': 100, 'price': 123.45, 'date': '12/17/2012'}
>>> dict_to_stock(b)
Stock(name='ACME', shares=100, price=123.45, date='12/17/2012', time=None)
>>>

somenamedtuple._source()

somenamedtuple._fields

返回一个元祖，包含所有的属性

>>> p._fields            # view the field names
('x', 'y')
>>> Color = namedtuple('Color', 'red green blue')
>>> Pixel = namedtuple('Pixel', Point._fields + Color._fields)
>>> Pixel(11, 22, 128, 255, 0)
Pixel(x=11, y=22, red=128, green=255, blue=0)

将字典转变为 namedtuple:

>>> d = {'x': 11, 'y': 22}
>>> Point(**d)
Point(x=11, y=22)

默认值可以通过 _replace() 来重新定义，例：

>>> Account = namedtuple('Account', 'owner balance transaction_count')
>>> default_account = Account('<owner name>', 0.0, 0)
>>> johns_account = default_account._replace(owner='John')
>>> janes_account = default_account._replace(owner='Jane')
# _replace（）返回一个新的实例

 源码分析

def namedtuple(typename, field_names, *, rename=False, defaults=None, module=None):
    """Returns a new subclass of tuple with named fields.

    >>> Point = namedtuple('Point', ['x', 'y'])
    >>> Point.__doc__                   # docstring for the new class
    'Point(x, y)'
    >>> p = Point(11, y=22)             # instantiate with positional args or keywords
    >>> p[0] + p[1]                     # indexable like a plain tuple
    33
    >>> x, y = p                        # unpack like a regular tuple
    >>> x, y
    (11, 22)
    >>> p.x + p.y                       # fields also accessible by name
    33
    >>> d = p._asdict()                 # convert to a dictionary
    >>> d['x']
    11
    >>> Point(**d)                      # convert from a dictionary
    Point(x=11, y=22)
    >>> p._replace(x=100)               # _replace() is like str.replace() but targets named fields
    Point(x=100, y=22)

    """

    # Validate the field names.  At the user's option, either generate an error
    # message or automatically replace the field name with a valid name.
    if isinstance(field_names, str):
        field_names = field_names.replace(',', ' ').split()
    field_names = list(map(str, field_names))
    typename = _sys.intern(str(typename)) # 使用字符串驻留机制
    if rename:
        seen = set()
        for index, name in enumerate(field_names):
　　　　　　　# enumerate 将一个可遍历的数据对象组合成一个索引序列, 返回一个enumerate对象，可以用for遍历，返回索引和值
　　　　　　　# isidentifier 判断变量名知否合法, _iskeyword() 判断是否为内置关键字
            if (not name.isidentifier()
                or _iskeyword(name)
                or name.startswith('_')
                or name in seen):
                field_names[index] = f'_{index}' # f'' ==> 字符串格式化
            seen.add(name)

    for name in [typename] + field_names:
        if type(name) is not str:
            raise TypeError('Type names and field names must be strings')
        if not name.isidentifier():
            raise ValueError('Type names and field names must be valid '
                             f'identifiers: {name!r}') # !r 反映对象本体
        if _iskeyword(name):
            raise ValueError('Type names and field names cannot be a '
                             f'keyword: {name!r}')

    seen = set()
    for name in field_names:
        if name.startswith('_') and not rename:
            raise ValueError('Field names cannot start with an underscore: '
                             f'{name!r}')
        if name in seen:
            raise ValueError(f'Encountered duplicate field name: {name!r}')
        seen.add(name)

    # 为字段设置默认值，靠右
    field_defaults = {}
    if defaults is not None:
        defaults = tuple(defaults)
        if len(defaults) > len(field_names):
            raise TypeError('Got more default values than field names')
        field_defaults = dict(reversed(list(zip(reversed(field_names),
                                                reversed(defaults)))))

    # Variables used in the methods and docstrings
    field_names = tuple(map(_sys.intern, field_names))
    num_fields = len(field_names)
    arg_list = repr(field_names).replace("'", "")[1:-1]
    repr_fmt = '(' + ', '.join(f'{name}=%r' for name in field_names) + ')'
    tuple_new = tuple.__new__
    _len = len

    # Create all the named tuple methods to be added to the class namespace

    s = f'def __new__(_cls, {arg_list}): return _tuple_new(_cls, ({arg_list}))'
    namespace = {'_tuple_new': tuple_new, '__name__': f'namedtuple_{typename}'}
    # Note: exec() has the side-effect of interning the field names
    exec(s, namespace) # 执行 s 中的python 语句，namespace为参数，将__new__添加至 namespace
    __new__ = namespace['__new__']
    __new__.__doc__ = f'Create new instance of {typename}({arg_list})'
    if defaults is not None:
        __new__.__defaults__ = defaults

    @classmethod
    def _make(cls, iterable):
        result = tuple_new(cls, iterable) # 实例化
        if _len(result) != num_fields:
            raise TypeError(f'Expected {num_fields} arguments, got {len(result)}')
        return result

    _make.__func__.__doc__ = (f'Make a new {typename} object from a sequence '
                              'or iterable')

    def _replace(_self, **kwds):
        result = _self._make(map(kwds.pop, field_names, _self))
        if kwds:
            raise ValueError(f'Got unexpected field names: {list(kwds)!r}')
        return result

    _replace.__doc__ = (f'Return a new {typename} object replacing specified '
                        'fields with new values')

    def __repr__(self):
        'Return a nicely formatted representation string'
        return self.__class__.__name__ + repr_fmt % self

    def _asdict(self):
        'Return a new OrderedDict which maps field names to their values.'
        return OrderedDict(zip(self._fields, self))

    def __getnewargs__(self):
        'Return self as a plain tuple.  Used by copy and pickle.'
        return tuple(self)

    # Modify function metadata to help with introspection and debugging

    for method in (__new__, _make.__func__, _replace,
                   __repr__, _asdict, __getnewargs__):
        method.__qualname__ = f'{typename}.{metho　　.__name__}'

    # Build-up the class namespace dictionary
    # and use type() to build the result class
    # 类的各个属性和方法
    class_namespace = {
        '__doc__': f'{typename}({arg_list})',
        '__slots__': (),
        '_fields': field_names,
        '_fields_defaults': field_defaults,
        '__new__': __new__,
        '_make': _make,
        '_replace': _replace,
        '__repr__': __repr__,
        '_asdict': _asdict,
        '__getnewargs__': __getnewargs__,
    }
    cache = _nt_itemgetters
    # 将属性与属性值对应起来
    for index, name in enumerate(field_names):
        try:
            itemgetter_object, doc = cache[index]
        except KeyError:
            itemgetter_object = _itemgetter(index)
            doc = f'Alias for field number {index}'
            cache[index] = itemgetter_object, doc
        class_namespace[name] = property(itemgetter_object, doc=doc)

    result = type(typename, (tuple,), class_namespace) # 动态创建类

    # For pickling to work, the __module__ variable needs to be set to the frame
    # where the named tuple is created.  Bypass this step in environments where
    # sys._getframe is not defined (Jython for example) or sys._getframe is not
    # defined for arguments greater than 0 (IronPython), or where the user has
    # specified a particular module.
    if module is None:
        try:
            module = _sys._getframe(1).f_globals.get('__name__', '__main__')
        except (AttributeError, ValueError):
            pass
    if module is not None:
        result.__module__ = module

    return result