第10章–序列的修改、散列和切片
这一章主要是通过一个例子–Vector类的实现来讲解序列的序列化、哈希化、格式化、和获取修改类属性的一些方法与技巧,下面是书本的源代码,我在代码的对应函数前面用###加了注释,并在最后列出了一些重要的知识点,我觉得这样有利于对书中概念的理解
# BEGIN VECTOR_V5
"""
A multi-dimensional ``Vector`` class, take 5
A ``Vector`` is built from an iterable of numbers::
>>> Vector([3.1, 4.2])
Vector([3.1, 4.2])
>>> Vector((3, 4, 5))
Vector([3.0, 4.0, 5.0])
>>> Vector(range(10))
Vector([0.0, 1.0, 2.0, 3.0, 4.0, ...])
Tests with 2-dimensions (same results as ``vector2d_v1.py``)::
>>> v1 = Vector([3, 4])
>>> x, y = v1
>>> x, y
(3.0, 4.0)
>>> v1
Vector([3.0, 4.0])
>>> v1_clone = eval(repr(v1))
>>> v1 == v1_clone
True
>>> print(v1)
(3.0, 4.0)
>>> octets = bytes(v1)
>>> octets
b'd\\x00\\x00\\x00\\x00\\x00\\x00\\x08@\\x00\\x00\\x00\\x00\\x00\\x00\\x10@'
>>> abs(v1)
5.0
>>> bool(v1), bool(Vector([0, 0]))
(True, False)
Test of ``.frombytes()`` class method:
>>> v1_clone = Vector.frombytes(bytes(v1))
>>> v1_clone
Vector([3.0, 4.0])
>>> v1 == v1_clone
True
Tests with 3-dimensions::
>>> v1 = Vector([3, 4, 5])
>>> x, y, z = v1
>>> x, y, z
(3.0, 4.0, 5.0)
>>> v1
Vector([3.0, 4.0, 5.0])
>>> v1_clone = eval(repr(v1))
>>> v1 == v1_clone
True
>>> print(v1)
(3.0, 4.0, 5.0)
>>> abs(v1) # doctest:+ELLIPSIS
7.071067811...
>>> bool(v1), bool(Vector([0, 0, 0]))
(True, False)
Tests with many dimensions::
>>> v7 = Vector(range(7))
>>> v7
Vector([0.0, 1.0, 2.0, 3.0, 4.0, ...])
>>> abs(v7) # doctest:+ELLIPSIS
9.53939201...
Test of ``.__bytes__`` and ``.frombytes()`` methods::
>>> v1 = Vector([3, 4, 5])
>>> v1_clone = Vector.frombytes(bytes(v1))
>>> v1_clone
Vector([3.0, 4.0, 5.0])
>>> v1 == v1_clone
True
Tests of sequence behavior::
>>> v1 = Vector([3, 4, 5])
>>> len(v1)
3
>>> v1[0], v1[len(v1)-1], v1[-1]
(3.0, 5.0, 5.0)
Test of slicing::
>>> v7 = Vector(range(7))
>>> v7[-1]
6.0
>>> v7[1:4]
Vector([1.0, 2.0, 3.0])
>>> v7[-1:]
Vector([6.0])
>>> v7[1,2]
Traceback (most recent call last):
...
TypeError: Vector indices must be integers
Tests of dynamic attribute access::
>>> v7 = Vector(range(10))
>>> v7.x
0.0
>>> v7.y, v7.z, v7.t
(1.0, 2.0, 3.0)
Dynamic attribute lookup failures::
>>> v7.k
Traceback (most recent call last):
...
AttributeError: 'Vector' object has no attribute 'k'
>>> v3 = Vector(range(3))
>>> v3.t
Traceback (most recent call last):
...
AttributeError: 'Vector' object has no attribute 't'
>>> v3.spam
Traceback (most recent call last):
...
AttributeError: 'Vector' object has no attribute 'spam'
Tests of hashing::
>>> v1 = Vector([3, 4])
>>> v2 = Vector([3.1, 4.2])
>>> v3 = Vector([3, 4, 5])
>>> v6 = Vector(range(6))
>>> hash(v1), hash(v3), hash(v6)
(7, 2, 1)
Most hash values of non-integers vary from a 32-bit to 64-bit CPython build::
>>> import sys
>>> hash(v2) == (384307168202284039 if sys.maxsize > 2**32 else 357915986)
True
Tests of ``format()`` with Cartesian coordinates in 2D::
>>> v1 = Vector([3, 4])
>>> format(v1)
'(3.0, 4.0)'
>>> format(v1, '.2f')
'(3.00, 4.00)'
>>> format(v1, '.3e')
'(3.000e+00, 4.000e+00)'
Tests of ``format()`` with Cartesian coordinates in 3D and 7D::
>>> v3 = Vector([3, 4, 5])
>>> format(v3)
'(3.0, 4.0, 5.0)'
>>> format(Vector(range(7)))
'(0.0, 1.0, 2.0, 3.0, 4.0, 5.0, 6.0)'
Tests of ``format()`` with spherical coordinates in 2D, 3D and 4D::
>>> format(Vector([1, 1]), 'h') # doctest:+ELLIPSIS
'<1.414213..., 0.785398...>'
>>> format(Vector([1, 1]), '.3eh')
'<1.414e+00, 7.854e-01>'
>>> format(Vector([1, 1]), '0.5fh')
'<1.41421, 0.78540>'
>>> format(Vector([1, 1, 1]), 'h') # doctest:+ELLIPSIS
'<1.73205..., 0.95531..., 0.78539...>'
>>> format(Vector([2, 2, 2]), '.3eh')
'<3.464e+00, 9.553e-01, 7.854e-01>'
>>> format(Vector([0, 0, 0]), '0.5fh')
'<0.00000, 0.00000, 0.00000>'
>>> format(Vector([-1, -1, -1, -1]), 'h') # doctest:+ELLIPSIS
'<2.0, 2.09439..., 2.18627..., 3.92699...>'
>>> format(Vector([2, 2, 2, 2]), '.3eh')
'<4.000e+00, 1.047e+00, 9.553e-01, 7.854e-01>'
>>> format(Vector([0, 1, 0, 0]), '0.5fh')
'<1.00000, 1.57080, 0.00000, 0.00000>'
"""
from array import array
import reprlib
import math
import numbers
import functools
import operator
import itertools # <1>
class Vector:
typecode = 'd'
### 接受可迭代的对象作为构造参数,而不是用*args传入多个参数
def __init__(self, components):
self._components = array(self.typecode, components)
### 让Verctor实现可迭代化
def __iter__(self):
return iter(self._components)
### 使用 reprlib.repr() 函数获取 self._components 的有限长度表示形式(如 array('d',[0.0, 1.0, 2.0, 3.0, 4.0, ...]))
def __repr__(self):
components = reprlib.repr(self._components)
components = components[components.find('['):-1]
return 'Vector({})'.format(components)
def __str__(self):
return str(tuple(self))
def __bytes__(self):
return (bytes([ord(self.typecode)]) +
bytes(self._components))
### 用zip模块方便了两个对象中不同向量的并行迭代
def __eq__(self, other):
return (len(self) == len(other) and
all(a == b for a, b in zip(self, other)))
### 用functools.reduce和operator.xor实现对每一维值的哈希值进行异或操作,设置默认值为0
def __hash__(self):
hashes = (hash(x) for x in self)
return functools.reduce(operator.xor, hashes, 0)
def __abs__(self):
return math.sqrt(sum(x * x for x in self))
def __bool__(self):
return bool(abs(self))
def __len__(self):
return len(self._components)
### 让Vercor实现切片操作,即vector[1] vector[3:4]这种,同时用isinstance判断index是否为slice类型,如果是的话用获得的多个维度值重新构造一个新的Vector并返回,如果index是整数类型,则直接返回数值
### numbers.Integral,这是一个抽象基类(Abstract Base Class,ABC)。在 isinstance 中使用抽象基类做测试能让 API 更灵活且更容易更新,
def __getitem__(self, index):
cls = type(self)
if isinstance(index, slice):
return cls(self._components[index])
elif isinstance(index, numbers.Integral):
return self._components[index]
else:
msg = '{.__name__} indices must be integers'
raise TypeError(msg.format(cls))
shortcut_names = 'xyzt'
### 实现用vector.x vector.y等来读向量的前几个维度值,只实现getattr的话只有读功能,如果此时vector.x=10,不会实现通过x来改变vector的第一个维度值,需要同时实现setattr才可以
def __getattr__(self, name):
cls = type(self)
if len(name) == 1:
pos = cls.shortcut_names.find(name)
if 0 <= pos < len(self._components):
return self._components[pos]
msg = '{.__name__!r} object has no attribute {!r}'
raise AttributeError(msg.format(cls, name))
### 通过setattr实现了用vector.x vector.y vector.z vector.t来修改vectoir的前几个维度值
def __setattr__(self, name, value):
cls = type(self)
if len(name) == 1:
if name in cls.shortcut_names:
error = 'readonly attribute {attr_name!r}'
elif name.islower():
error = "can't set attributes 'a' to 'z' in {cls_name!r}"
else:
error = ''
if error:
msg = error.format(cls_name=cls.__name__, attr_name=name)
raise AttributeError(msg)
super().__setattr__(name, value)
def angle(self, n): # <2>
r = math.sqrt(sum(x * x for x in self[n:]))
a = math.atan2(r, self[n-1])
if (n == len(self) - 1) and (self[-1] < 0):
return math.pi * 2 - a
else:
return a
def angles(self): # <3>
return (self.angle(n) for n in range(1, len(self)))
### 自定义format函数中h参数的表示
def __format__(self, fmt_spec=''):
if fmt_spec.endswith('h'): # hyperspherical coordinates
fmt_spec = fmt_spec[:-1]
coords = itertools.chain([abs(self)],
self.angles()) # <4>
outer_fmt = '<{}>' # <5>
else:
coords = self
outer_fmt = '({})' # <6>
components = (format(c, fmt_spec) for c in coords) # <7>
return outer_fmt.format(', '.join(components)) # <8>
@classmethod
def frombytes(cls, octets):
typecode = chr(octets[0])
memv = memoryview(octets[1:]).cast(typecode)
return cls(memv)
# END VECTOR_V5
知识点总结
- reprlib.repr 这个函数用于生成大型结构或递归结构的安全表示形式,它会限制输出字符串的长度,用 ‘…’ 表示截断的部分 https://docs.python.org/3.1/library/reprlib.html
- slice类 __getitem__(self,index)中如果是访问单个元素,比如vector[1]那么index就是整数类型,如果是切片访问多个元素,比如vector[1:3]那么index就是slice类型,slice的indices方法用于对slice中的负数参数和缺省值进行处理,让参数变为整数和补充缺省值
https://docs.python.org/3/c-api/slice.html
>>> slice #表明slice是内置类
<class 'slice'>
>>> s=slice(2,5) # slice的构造参数有三个start,end,step,其中start,可以省略,只传一个参数的话默认是end,start,step默认为None(实际序列中表现为start=0 step=1) 传两个参数的话默认step为None
>>> s
slice(2, 5, None)
>>> l=list(range(11)) # 构造0-10的列表
>>> l
[0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10]
>>> l[s] # 把slice实例传进去,输出跟l[2:5]一样
[2, 3, 4]
>>> l[2:5]
[2, 3, 4]
>>> s=slice(-2,5,-1)
>>> s.indices(len(l)) # indices方法对slice中的负数参数和缺省值进行处理,让参数变为整数和补充缺省值
(9, 5, -1)
>>> l[s]
[9, 8, 7, 6]
>>> l[9:5:-1]
[9, 8, 7, 6]
- 多个哈希值进行合并规约建议用异或操作
- operator 模块以函数的形式提供了 Python 的全部中缀运算符,从而减少使用 lambda 表达式。
- zip 函数生成一个由元组构成的生成器,元组中的元素来自参数传入的各个可迭代对象。如果传入的各个可迭代对象长短不一,则在处理完最短的可迭代对象后就会结束,不会报错,如果想要按最长的可迭代对象来处理可以用itertools.zip_longest函数,参数fillvalue会填充缺失的值
>>> a=list(range(5))
>>> b=list(range(7))
>>> c=list(range(10))
>>> for x,y,z in zip(a,b,c):
... print(x,y,z)
...
0 0 0
1 1 1
2 2 2
3 3 3
4 4 4
>>> from itertools import zip_longest
>>> for x,y,z in zip_longest(a,b,c):
... print(x,y,z)
...
0 0 0
1 1 1
2 2 2
3 3 3
4 4 4
None 5 5
None 6 6
None None 7
None None 8
None None 9
- format相关 扩展格式规范微语言(https://docs.python.org/3/library/string.html#formatspec)时,最好避免重用内置类型支持的格式代码。这里对微语言的扩展还会用到浮点数的格式代码 ‘eEfFgGn%’,而且保持原意,因此绝对要避免重用代码。整数使用的格式代码有’bcdoxXn’,字符串使用的是 ‘s’。