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
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
|
from __future__ import (absolute_import, print_function, division)
import os
import datetime
import re
import time
import json
def timestamp():
"""
Returns a serializable UTC timestamp.
"""
return time.time()
def format_timestamp(s):
s = time.localtime(s)
d = datetime.datetime.fromtimestamp(time.mktime(s))
return d.strftime("%Y-%m-%d %H:%M:%S")
def format_timestamp_with_milli(s):
d = datetime.datetime.fromtimestamp(s)
return d.strftime("%Y-%m-%d %H:%M:%S.%f")[:-3]
def isBin(s):
"""
Does this string have any non-ASCII characters?
"""
for i in s:
i = ord(i)
if i < 9 or 13 < i < 32 or 126 < i:
return True
return False
def isMostlyBin(s):
s = s[:100]
return sum(isBin(ch) for ch in s) / len(s) > 0.3
def isXML(s):
for i in s:
if i in "\n \t":
continue
elif i == "<":
return True
else:
return False
def pretty_json(s):
try:
p = json.loads(s)
except ValueError:
return None
return json.dumps(p, sort_keys=True, indent=4)
def pretty_duration(secs):
formatters = [
(100, "{:.0f}s"),
(10, "{:2.1f}s"),
(1, "{:1.2f}s"),
]
for limit, formatter in formatters:
if secs >= limit:
return formatter.format(secs)
# less than 1 sec
return "{:.0f}ms".format(secs * 1000)
class Data:
def __init__(self, name):
m = __import__(name)
dirname, _ = os.path.split(m.__file__)
self.dirname = os.path.abspath(dirname)
def path(self, path):
"""
Returns a path to the package data housed at 'path' under this
module.Path can be a path to a file, or to a directory.
This function will raise ValueError if the path does not exist.
"""
fullpath = os.path.join(self.dirname, path)
if not os.path.exists(fullpath):
raise ValueError("dataPath: %s does not exist." % fullpath)
return fullpath
pkg_data = Data(__name__)
class LRUCache:
"""
A simple LRU cache for generated values.
"""
def __init__(self, size=100):
self.size = size
self.cache = {}
self.cacheList = []
def get(self, gen, *args):
"""
gen: A (presumably expensive) generator function. The identity of
gen is NOT taken into account by the cache.
*args: A list of immutable arguments, used to establish identiy by
*the cache, and passed to gen to generate values.
"""
if args in self.cache:
self.cacheList.remove(args)
self.cacheList.insert(0, args)
return self.cache[args]
else:
ret = gen(*args)
self.cacheList.insert(0, args)
self.cache[args] = ret
if len(self.cacheList) > self.size:
d = self.cacheList.pop()
self.cache.pop(d)
return ret
def clean_hanging_newline(t):
"""
Many editors will silently add a newline to the final line of a
document (I'm looking at you, Vim). This function fixes this common
problem at the risk of removing a hanging newline in the rare cases
where the user actually intends it.
"""
if t and t[-1] == "\n":
return t[:-1]
return t
def parse_size(s):
"""
Parses a size specification. Valid specifications are:
123: bytes
123k: kilobytes
123m: megabytes
123g: gigabytes
"""
if not s:
return None
mult = None
if s[-1].lower() == "k":
mult = 1024**1
elif s[-1].lower() == "m":
mult = 1024**2
elif s[-1].lower() == "g":
mult = 1024**3
if mult:
s = s[:-1]
else:
mult = 1
try:
return int(s) * mult
except ValueError:
raise ValueError("Invalid size specification: %s" % s)
def safe_subn(pattern, repl, target, *args, **kwargs):
"""
There are Unicode conversion problems with re.subn. We try to smooth
that over by casting the pattern and replacement to strings. We really
need a better solution that is aware of the actual content ecoding.
"""
return re.subn(str(pattern), str(repl), target, *args, **kwargs)
|
