문자의 구성
인코딩 (방식)
unicode 타입
encode
(인코딩)/decode
(디코딩) 명령 사용Python 3에서는 unicode 타입이 기본
__repr__()
print()
명령
In [1]:
c = "a"
c
Out[1]:
In [2]:
print(c)
In [3]:
x = "가"
x
Out[3]:
In [4]:
print(x)
In [5]:
print(x.__repr__())
In [6]:
x = ["가"]
print(x)
In [7]:
x = "가"
len(x)
Out[7]:
In [14]:
x = "ABC"
y = "가나다"
print(len(x), len(y))
print(x[0], x[1], x[2])
print(y[0], y[1], y[2])
print(y[0], y[1], y[2], y[3])
In [9]:
y = u"가"
y
Out[9]:
In [10]:
print(y)
In [17]:
y = u"가나다"
print(y[0], y[1], y[2])
In [26]:
print(type(y))
z1 = y.encode("cp949")
print(type(z1))
print(z1)
In [27]:
print(type(y))
z2 = y.encode("utf-8")
print(type(z2))
print(z2)
In [28]:
print(type(z1))
y1 = z1.decode("cp949")
print(type(y1))
print(y1)
In [29]:
print(type(z2))
y2 = z2.decode("utf-8")
print(type(y2))
print(y2)
In [33]:
"가".encode("utf-8")
In [34]:
unicode("가", "ascii").encode("utf-8")
In [37]:
u"가".decode("utf-8")
In [38]:
u"가".encode("ascii").decode("utf-8")
In [39]:
u"가".encode("utf-8"), u"가".encode("cp949"), "가"
Out[39]:
In [40]:
import sys
print(sys.getdefaultencoding())
print(sys.stdin.encoding)
print(sys.stdout.encoding)
import locale
print(locale.getpreferredencoding())
PYTHONIOENCODING
로 지정가능#-*- coding: utf-8 -*-