1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
|
"""
Bytes-to-human / human-to-bytes converter.
Based on: http://goo.gl/kTQMs
Working with Python 2.x and 3.x.
Author: Giampaolo Rodola' <g.rodola [AT] gmail [DOT] com>
License: MIT
"""
# see: http://goo.gl/kTQMs
SYMBOLS = {
'customary': ('B', 'K', 'M', 'G', 'T', 'P', 'E', 'Z', 'Y'),
'customary_ext': ('byte', 'kilo', 'mega', 'giga', 'tera', 'peta', 'exa',
'zetta', 'iotta'),
'iec': ('Bi', 'Ki', 'Mi', 'Gi', 'Ti', 'Pi', 'Ei', 'Zi', 'Yi'),
'iec_ext': ('byte', 'kibi', 'mebi', 'gibi', 'tebi', 'pebi', 'exbi',
'zebi', 'yobi'),
}
def bytes2human(n, format='%(value).1f %(symbol)s', symbols='customary'):
"""
Convert n bytes into a human readable string based on format.
symbols can be either "customary", "customary_ext", "iec" or "iec_ext",
see: http://goo.gl/kTQMs
>>> bytes2human(0)
'0.0 B'
>>> bytes2human(0.9)
'0.0 B'
>>> bytes2human(1)
'1.0 B'
>>> bytes2human(1.9)
'1.0 B'
>>> bytes2human(1024)
'1.0 K'
>>> bytes2human(1048576)
'1.0 M'
>>> bytes2human(1099511627776127398123789121)
'909.5 Y'
>>> bytes2human(9856, symbols="customary")
'9.6 K'
>>> bytes2human(9856, symbols="customary_ext")
'9.6 kilo'
>>> bytes2human(9856, symbols="iec")
'9.6 Ki'
>>> bytes2human(9856, symbols="iec_ext")
'9.6 kibi'
>>> bytes2human(10000, "%(value).1f %(symbol)s/sec")
'9.8 K/sec'
>>> # precision can be adjusted by playing with %f operator
>>> bytes2human(10000, format="%(value).5f %(symbol)s")
'9.76562 K'
"""
n = int(n)
if n < 0:
raise ValueError("n < 0")
symbols = SYMBOLS[symbols]
prefix = {}
for i, s in enumerate(symbols[1:]):
prefix[s] = 1 << (i + 1) * 10
for symbol in reversed(symbols[1:]):
if n >= prefix[symbol]:
value = float(n) / prefix[symbol]
return format % locals()
return format % dict(symbol=symbols[0], value=n)
def human2bytes(s):
"""
Attempts to guess the string format based on default symbols
set and return the corresponding bytes as an integer.
When unable to recognize the format ValueError is raised.
>>> human2bytes('0 B')
0
>>> human2bytes('1 K')
1024
>>> human2bytes('1 M')
1048576
>>> human2bytes('1 Gi')
1073741824
>>> human2bytes('1 tera')
1099511627776
>>> human2bytes('0.5kilo')
512
>>> human2bytes('0.1 byte')
0
>>> human2bytes('1 k') # k is an alias for K
1024
>>> human2bytes('12 foo')
Traceback (most recent call last):
...
ValueError: can't interpret '12 foo'
"""
init = s
num = ""
while s and s[0:1].isdigit() or s[0:1] == '.':
num += s[0]
s = s[1:]
num = float(num)
letter = s.strip()
for name, sset in SYMBOLS.items():
if letter in sset:
break
else:
if letter == 'k':
# treat 'k' as an alias for 'K' as per: http://goo.gl/kTQMs
sset = SYMBOLS['customary']
letter = letter.upper()
else:
raise ValueError("can't interpret %r" % init)
prefix = {sset[0]: 1}
for i, s in enumerate(sset[1:]):
prefix[s] = 1 << (i + 1) * 10
return int(num * prefix[letter])
|