详解Python小数据池和代码块缓存机制

s1 = 'janes@！#*ewq'
s2 = 'janes@！#*ewq'
print(s1 is s2)	 # True 

a1 = 'janes45613256132!@#$%#^%@$%' * 1
b1 = 'janes45613256132!@#$%#^%@$%' * 1
print(a1 is b1) # True

s1 = 'hah_' * 6
s2 = 'hah_' * 6
print(s1 is s2) # True

# cmd, -5~256 的小整数虽然不在同一代码块中, 但是它们适用小数据池机制
>>>a = 245
>>>b = 245
>>>a is b # True

# 长度为0与1的字符串一定会被驻留;
# 字符串驻留发生在程序编译时;
# 被驻留的字符串必须由 ASCll字母, 数字以及下划线组成;
>>>s1 = '@'
>>>s2 = '@'
>>>s1 is s2 # True

>>>s1 = ''
>>>s2 = ''
>>>s1 is s2 # True

>>>s1 = 'a_b_c'
>>>s2 = 'a_b_c'
>>>s1 is s2 # True

>>>s1 = 'a b_c'
>>>s2 = 'a b_c'
>>>s1 is s2 # False

>>>s1 = 'a_b_c' * 1
>>>s2 = 'a_b_c' * 1
>>>s1 is s2 # True

>>>s1 = 'abd_d23' * 3
>>>s2 = 'abd_d23' * 3
>>>s1 is s2 # True

>>>a, b = "some_thing!", "some_thing!"
>>>a is b # False

>>>a, b = "some_thing", "some_thing"
>>>a is b # True

a1 = 1000
b1 = 1000
a1 is b1 # True

class C1(object): 
   a = 100
   b = 100
   c = 1000
   d = 1000
 
 
class C2(object):
   a = 100
   b = 1000

print(C1.a is C1.b)  # True
print(C1.a is C2.a)  # True
print(C1.c is C1.d)  # True
print(C1.c is C2.b)  # False

# 3.7.5, ipython7.18.1
a = -5
b = -5
a is b # True

a = -6
b = -6
a is b # False

a = 256
b = 256
a is b # True

a = 257
b = 257
a is b # Flase

# cmd 终端
a = 1000
b = 1000
a is b # False
--------------------
class C1(object): 
   a = 100
   b = 100
   c = 1000
   d = 1000
 
 
class C2(object):
   a = 100
   b = 1000

print(C1.a is C1.b)  # True
print(C1.a is C2.a)  # True
print(C1.c is C1.d)  # True ?? 难道 cmd 中也有大整数池 ?? 类加载的时候是在一块内存中,同值同地址 ?? 
print(C1.c is C2.b)  # False

# pycharm 等编辑器中
a = 1000
b = 1000
a is b # True
--------------------
class C1(object): 
   a = 100
   b = 100
   c = 1000
   d = 1000
 
 
class C2(object):
   a = 100
   b = 1000

print(C1.a is C1.b)  # True
print(C1.a is C2.a)  # True
print(C1.c is C1.d)  # True
print(C1.c is C2.b)  # False

# cmd 中浮点数没有被缓存
a = 1.0
b = 1.0
a is b # False

# cmd 中并非全部的字符串都会采用intern机制; 仅 包括下划线、数字、字母的字符串才会被 intern--类标识符
s1="hello"
s2="hello"
s1 is s2 # True

# 如果有空格，默认不启用intern机制
s1="hell o"
s2="hell o"
s1 is s2 # False

s1 = "hell!*o"
s2 = "hell!*o"
print(s1 is s2) # False

# 如果一个字符串长度超过20个字符，不启动intern机制 -- 看网上很多都是这么写的, 不超过二十个就为真，但是我在自己 3.7/8.5 版本上试了一下，发现好像没有限制，不知道是 Python 更新了，还是什么问题……
s1 = "a" * 20
s2 = "a" * 20
s1 is s2 # True

s1 = "a" * 21
s2 = "a" * 21
s1 is s2 # True

s1 = "ab" * 10
s2 = "ab" * 10
s1 is s2 # True

s1 = "ab" * 11
s2 = "ab" * 11
s1 is s2 # True

# 'kz' + 'c' 编译时已经变成 'kzc'，而 s1 + 'c' 中 s1 是变量, 会在运行时进行拼接,所以没有被intern?
'kz' + 'c' is 'kzc' # True

s1 = 'kz'
s2 = 'kzc'
s1+'c' is 'kzc' # False

# pycharm 等编辑器中，只要是同一个字符串，都为 True，并不用是下划线、数字、字母的字符串
s1 = "hell o"
s2 = "hell o"
print(s1 is s2) # True

s1 = "hell!*o"
s2 = "hell!*o"
print(s1 is s2) # True

s1 = "a" * 20
s2 = "a" * 20
print(s1 is s2) # True

s1 = "a" * 21
s2 = "a" * 21
print(s1 is s2) # True

s1 = "ab" * 10
s2 = "ab" * 10
print(s1 is s2) # True

s1 = "ab" * 11
s2 = "ab" * 11
print(s1 is s2) # True

'kz' + 'c' is 'kzc' # True

s1 = 'kz'
s2 = 'kzc'
s1+'c' is 'kzc' # False

# 编辑器中，float 也被缓存了
a = 1.0
b = 1.0
a is b