Python最佳编码实践

译自: http://www.fantascienza.net/leonardo/ar/python_best_practices.html

++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++

有时候，甚至优秀的程序员在他们首次尝试用Python时，会很少使用最佳方案和数据结构。在过去数年中，Python也逐渐累积了一些诸如：冗余，缺点等瑕疵(它们中的一部分会从Python3.0中移除，这篇文章主要基于Python 2.5，不针对之后的版本，比如说Python 2.6，同样不针对Jython 或 PyPy 或 IronPython 它们之间有点微妙的差异)，但是总而言之，Python依然是非常干净、简洁的语言，本文也像这样，目的是为了让你避免程序开发实践中最可能碰到的误区。本文同样简短，你甚至能发现在线解释。

当然啦，我也许可能是错误的，但该页(文)来自一些练习，因此当你不同意我观点的时候，我建议你通过邮件组或者网页去查找答案，而不是想当然的自以为是。如果你的确发现我错误，或者有任何建议，看法。请通过邮件练习我们，我们会非常高兴，并改正错误.

差的代码格式	好的代码格式
x=5 if ( (x==8) and (y>5) ) : ... 1<<5&2 return(5); while (x<5) : ... 7.	x = 5 if x == 8 and y > 5: ... (1 << 5) & 2  return 5 while x < 5: ... 7.0
print x,x*x+1 v[i + 1 + a] + v[i + 2 + b]	# 有时候规则可以打破，比如要展示组的时候，可以下面这样 print x, x*x + 1  v[i+a+1] + v[i+b+2]
def Function ( x ): ...	def function(x): ...
class fooclass: ...	class Fooclass(object): ...
d = dict()	freqs = {} # 变量最好用描述性名称 # 小范围来说，短的变量名业务不错的选择。
list = [1, 2, 3]  dict = {'alpha': 0x1234} sum = x + y	# 不要用内置的保留字来做变量名 values = [1, 2, 3] symbol_address = {'alpha': 0x1234} tot = x + y
	"some string" and 'some string' and """some string""" and '''some string''' # 上述的格式是一样，一样，一样的
mapping = { 5 :"5", 6:"6" }	mapping = {5: "5", 6: "6"}
mapping = {5 : "5", 6 : "6"} if mapping.has_key(6): ...	mapping = {5: "5", 6: "6"} if 6 in mapping: ...
def function( x, l = [] ): ...	# 通常不用可变对象，比如列表来做默认值 def function(x, items=None): ...     if items is None:         items = []
if x == None: ...	if x is None: ...
x = 1 if z > 5:   var1 = 55	# 总是用4个空格作为缩进 # (或者总是用TAB键作为缩进，但这样同样不好) x = 1 if z > 5:     var1 = 55
mapping = {5 : "5", 6 : "6"} for key, val in mapping.items(): ... for key in mapping.keys(): ...	# 尽可能使用iter*开头的迭代方法 mapping = {5: "5", 6: "6"} for key, val in mapping.iteritems(): ... for key in mapping: ...
for i in range(10, 20000): ...	for i in xrange(10, 20000): ...
	# Use to denote the code that has to # run when a module is executed and not # imported: if __name__ == '__main__':
	# Python profiler:  python -m profile -o stats myscript.py >>> import pstats >>> p = pstats.Stats('stats') >>> p.sort_stats('time').print_stats(15)
	对于含非ASCII编码的字符，在首行添加： # -*- coding: UTF-8 -*- # 或者如果你电脑内存不足，就干脆使用latin编码 # coding: latin
al = [1, 2, 3] for i in xrange(len(al)-1, -1, -1):     del al[i]	items = [1, 2, 3] del items[:] # 如果程序速度不是最重要的话，可以仅仅新增加以个空列表： items = [] # 如果你只想移除一个列表的引用值时，可以使用: del items
repeat     xxx until yyy	# 等价于: while True     xxx     if yyy: break
	# 增加一个包含所需模块压缩文件到搜索路径中 sys.path.append("some.zip")
a = 5 b = 6 aux = a a = b b = aux	a = 5 b = 6 a, b = b, a # 两个变量交换值，无需中间变量
if x < 10 and x > 2: ...	if 2 < x < 10: ...
a = 5 b = 5 c = 5	a = b = c = 5
if x == 1: y = fun1(x) else if x == 2: y = fun2(x) else if x == 3: y = fun3(x) else: y = None	if x == 1: y = fun1(x) elif x == 2: y = fun2(x) elif x == 3: y = fun3(x) else: y = None  # 但又时候，使用字典无疑更好些: funs = {1: fun1, 2: fun2, 3: fun3} y = funs.get(x, lambda x:None)(x)
mapping = {5 : "5", 6 : "6"} for key in mapping.iterkeys(): ...	mapping = {5: "5", 6: "6"} for key in mapping: ...
al = [1, 2, 3] for i in xrange(len(al)):     print al[i]	al = [1, 2, 3] for el in al:     print el
al = [1, 2, 3] for i in xrange(len(al)-1, -1, -1):     print al[i]	al = [1, 2, 3] for el in reversed(al):     print el
class Test(object):     def __init__(I, x): ...	class Test(object):     def __init__(self, x): ...
# Compute the sum of the ... def sum_of(x, y, z): ...	def sum_of(x, y, z): ...     """Compute the sum of the ..."""
from operator import add sl = ["ab", "cd", "ef"]  all = "" for s in sl:     all += s # Or: sl = ["ab", "cd", "ef"] all = reduce(lambda x,y: x+y, sl, "")	sl = ["ab", "cd", "ef"] all = "".join(sl)
a = "this isn't a word, right?" a = a.replace("'", " ") a = a.replace(".", " ") a = a.replace("?", " ") a = a.replace(",", "")	# 用.来代替，效果及速度更快些 from string import maketrans tab = maketrans("'.?", "   ") a = "this isn't a word, right." afilt = a.translate(tab, ",")
values = ["stop",0,0]	values = ["stop", 0, 0]
def mul(x, y): return x*y l = [2, 3] print apply(mul, l)	def mul(x, y):     return x * y l = [2, 3] print mul(*l)
vals = [2, 3, -5, 0] result = [] for el in vals:     if el > 0:         result.append(el * el)	vals = [2, 3, -5, 0] result = [el * el for el in vals if el > 0]
l = [0] * 4 m = [l] * 4 m[1][1] = 5 print m	# 一个正确的做法是创建一个矩阵: m = [[0] * 4 for _ in xrange(4)] m[1][1] = 5 print m
a = 1 print a / 2, a / float(2)	# 一种可替代方案: from __future__ import division a = 1 print a // 2, a / 2
class Foo(object):     def __init__(self, x, y, z):         self.x_public = x         self.y_private = y         self.z_veryprivate = z     def getx(self):         return self.x_public print Foo(1, 2, 3).getx()	# Generally getters and setters are not used. # Instance names starting with _ are meant as # 'to not mess with' by convention. # Instance names starting with __ are private # and receive name mangling. class Foo(object):     def __init__(self, x, y, z):         self.x_public = x         self._y_private = y         self.__z_veryprivate = z print Foo(1, 2, 3).x_public
finder = re.compile("^\s*([\[\]])\s*([-+]?\d+) \s*,\s*([-+]?\d+)\s*([\[\]])\s*$")	finder = re.compile(r"""     ^ \s*             # start at beginning+ opt spaces     ( [\[\]] )        # Group 1: opening bracket         \s*           # optional spaces         ( [-+]? \d+ ) # Group 2: first number         \s* , \s*     # opt spaces+ comma+ opt spaces         ( [-+]? \d+ ) # Group 3: second number         \s*           # opt spaces     ( [\[\]] )        # Group 4: closing bracket     \s* $             # opt spaces+ end at the end     """, flags=re.VERBOSE) # 上面的关于正则表达式代码就很容易读懂. # 每行就像代码一样. # 下面是另外一个不错的关于正则表达式排版方式: spaces = r"\s*"            # optional spaces number = r"( [-+]? \d+ )"  # Group bracket = r"( [\[\]] )"    # Group. Closing bracket parts = ["^", bracket, number, ",", number, bracket, "$"] finder = re.compile(spaces.join(parts), flags=re.VERBOSE)
def function(data):     """A comment"""     ...implementation...	# 使用doctests模块(或者tests模块): def function(data):     """A comment     >>> function()     None     >>> function(1)     result1     >>> function("a")     Traceback (most recent call last):       ...     TypeError     """     ...implementation... if __name__ == "__main__":     import doctest     doctest.testmod()     print "Tests done."
x = (1, 2, 6, 55, 63, 96, 125, 256, \      301, 456, 958, 1256, \      1359, 2568, 3597)	x = (1, 2, 6, 55, 63, 96, 125, 256,      301, 456, 958, 1256,      1359, 2568, 3597) # 太多的行，必须用\来作为分割符 # 但\在() [] {}中是不必要的
from Tkinter import * from mymodule import *	import Tkinter as tk from mymodule import fun1, Class1, baseconvert as bc
import psyco psyco.bind(myfun1)  a = [3.56, 2.12]	try:     import psyco     # psyco中的类非常有用     from psyco.classes import __metaclass__     psyco.bind(myfun1) except ImportError: pass # 使用psyco array.array中 # 双精度值可以更快些 import array a = array.array("d", [3.56, 2.12]) # 在一些情形下，使用字符串数组同样很快 # psyco同map,filter,生成器一起使用也会很慢 can be slow with itertools, map, filter # 但会比列表解析快 # 最快的Psyco是使用低级别的编码格式
	# 打印一个不包含空格的字符串: from sys import stdout stdout.write(string1) stdout.write(string2)
	This is good enough: words = ['me', 'do' 'bye', 'taz', 'foo', 'bar']  A shorter, more readable, but slower alternative: words = 'me do bye taz foo bar'.split()
# sorting on the second item of the tuple # try to remove the i index from the temporary tuples lp = [(5J,"b"),(2J,"c"),(3+1J,"a"),(1+2J,"a")] lp2 = [(c, i, n) for i,(n, c) in enumerate(lp)] lp2.sort() print [(n, c) for (c, i, n) in lp2]	from operator import itemgetter lp = [(5J, "b"), (2J, "c"), (3+1J, "a"), (1+2J, "a")] print sorted(lp, key=itemgetter(1))
vals = [5, 7 ,8] tot = -2.0 for v in vals:     tot += v	vals = [5, 7 ,8] tot = sum(vals, -2.0)
ll = [[1, 2, 3], [4], [5, 6]] print sum(ll, [])	data = [[1, 2, 3], [4], [5, 6]] result = [] for sublist in data:     result.extend(sublist) # 最快速度实现 from itertools import imap data = [[1, 2, 3], [4], [5, 6]] result = [None] * sum(imap(len, data)) pos = 0 for sublist in data:     lensl = len(sublist)     result[pos : pos+lensl] = sublist     pos += lensl
print "%s %s" % (string1, string2) print '"' + chr(c) + '":', freq[c]	print string1, string2 print '"%c": %d' % (c, freq[c])
[' ', c][c.isalpha()]	# Python 2.5以上版本支持: (c if c.isalpha() else ' ')
	# 如何反转一个字符串，列表等. alist[::-1] astring[::-1]
# To negate (inplace) each second #  element of alist: result = [] for (i, v) in enumerate(alist):     # faster than i % 2     if i & 1 == 0:          result.append(v)     else:         result.append(-v) alist[:] = result	from operator import neg alist[1::2] = map(neg, alist[1::2]) # 下面方式虽慢点，但是易读: alist[1::2] = [-el for el in alist[1::2]]
	# 隐式拷贝一个字典或列表: # (元祖无需拷贝) newlist = list(alist) newdict = dict(adict) # 或者仅仅是: newlist = list[:]
import sys sys.exit()	# 停掉一个控制台: raise SystemExit #或者仅仅是: exit()
if type(s) == type(""): ... if type(seq) == list or \    type(seq) == tuple: ...	if isinstance(s, basestring): ... if isinstance(seq, (list, tuple)): ... # Or even: if hasattr(seq, "__getitem__"): ... # But quite often in dynamic languages you # don't test types, you just use them (look # for duck typing), catching exception that # may occur.
name1 = 5; name2 = 20; print name2 a = 1 b = 2 c = 3	name1 = 5 name2 = 20 print name2 a, b, c = 1, 2, 3
prima = 1 rossa = "Il colore rosso" léger = 30	# 只能用英文字母做变量名: first = 1 red = "Il colore rosso" light = 30
	__del__ method of classes is  usually left undefined.
try:     fin = file("absent_file.txt") except:     ... try:     something() except:     ...	# 通常的声明异常并捕获: try:     fin = file("absent_file.txt") except IOError:     ... try:     something() except someException:     ...
except ImportError, IOError: ...	except (ImportError, IOError): ...
bytes = array.array('B', [0] * nbytes) # 或者: from itertools import repeat bytes = array.array('B', repeat(0, nbytes))	# 下面的方式更快些 bytes = array.array('B', [0]) * nbytes
freqs = {} for c in "abracadabra":     try:         freqs[c] += 1     except:         freqs[c] = 1	# 简单方式: freqs = {} for c in "abracadabra":     freqs[c] = freqs.get(c, 0) + 1 # 常用方式: freqs = {} for c in "abracadabra":     if c in freqs:         freqs[c] += 1     else:         freqs[c] = 1 # 或者在Python 2.5以上版本使用: from collections import defaultdict freqs = defaultdict(int) for c in "abracadabra":     freqs[c] += 1
someitems = set([1, 2, 3]) somemap = {1:2, 3:4, 5:6} print list(someitems)[0] print list(somemap)[0]	someitems = set([1, 2, 3]) somemap = {1: 2, 3: 4, 5: 6} print iter(someitems).next() print iter(somemap).next()
from time import clock	# 下面的导入方式在Windows和LINUX下都工作正常: from timeit import default_timer as clock # 或者经常使用timeit模块来计算程序运行时间

请同时参阅Python代码规范: http://www.python.org/dev/peps/pep-0008/