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
|
import re
from django.conf import settings
# Capitalizes the first letter of a string.
capfirst = lambda x: x and x[0].upper() + x[1:]
def wrap(text, width):
"""
A word-wrap function that preserves existing line breaks and most spaces in
the text. Expects that existing line breaks are posix newlines.
"""
def _generator():
it = iter(text.split(' '))
word = it.next()
yield word
pos = len(word) - word.rfind('\n') - 1
for word in it:
if "\n" in word:
lines = word.splitlines()
else:
lines = (word,)
pos += len(lines[0]) + 1
if pos > width:
yield '\n'
pos = len(lines[-1])
else:
yield ' '
if len(lines) > 1:
pos = len(lines[-1])
yield word
return "".join(_generator())
def truncate_words(s, num):
"Truncates a string after a certain number of words."
length = int(num)
words = s.split()
if len(words) > length:
words = words[:length]
if not words[-1].endswith('...'):
words.append('...')
return ' '.join(words)
def get_valid_filename(s):
"""
Returns the given string converted to a string that can be used for a clean
filename. Specifically, leading and trailing spaces are removed; other
spaces are converted to underscores; and all non-filename-safe characters
are removed.
>>> get_valid_filename("john's portrait in 2004.jpg")
'johns_portrait_in_2004.jpg'
"""
s = s.strip().replace(' ', '_')
return re.sub(r'[^-A-Za-z0-9_.]', '', s)
def get_text_list(list_, last_word='or'):
"""
>>> get_text_list(['a', 'b', 'c', 'd'])
'a, b, c or d'
>>> get_text_list(['a', 'b', 'c'], 'and')
'a, b and c'
>>> get_text_list(['a', 'b'], 'and')
'a and b'
>>> get_text_list(['a'])
'a'
>>> get_text_list([])
''
"""
if len(list_) == 0: return ''
if len(list_) == 1: return list_[0]
return '%s %s %s' % (', '.join([str(i) for i in list_][:-1]), last_word, list_[-1])
def normalize_newlines(text):
return re.sub(r'\r\n|\r|\n', '\n', text)
def recapitalize(text):
"Recapitalizes text, placing caps after end-of-sentence punctuation."
# capwords = ()
text = text.lower()
capsRE = re.compile(r'(?:^|(?<=[\.\?\!] ))([a-z])')
text = capsRE.sub(lambda x: x.group(1).upper(), text)
# for capword in capwords:
# capwordRE = re.compile(r'\b%s\b' % capword, re.I)
# text = capwordRE.sub(capword, text)
return text
def phone2numeric(phone):
"Converts a phone number with letters into its numeric equivalent."
letters = re.compile(r'[A-PR-Y]', re.I)
char2number = lambda m: {'a': '2', 'c': '2', 'b': '2', 'e': '3',
'd': '3', 'g': '4', 'f': '3', 'i': '4', 'h': '4', 'k': '5',
'j': '5', 'm': '6', 'l': '5', 'o': '6', 'n': '6', 'p': '7',
's': '7', 'r': '7', 'u': '8', 't': '8', 'w': '9', 'v': '8',
'y': '9', 'x': '9'}.get(m.group(0).lower())
return letters.sub(char2number, phone)
# From http://www.xhaus.com/alan/python/httpcomp.html#gzip
# Used with permission.
def compress_string(s):
import cStringIO, gzip
zbuf = cStringIO.StringIO()
zfile = gzip.GzipFile(mode='wb', compresslevel=6, fileobj=zbuf)
zfile.write(s)
zfile.close()
return zbuf.getvalue()
ustring_re = re.compile(u"([\u0080-\uffff])")
def javascript_quote(s, quote_double_quotes=False):
def fix(match):
return r"\u%04x" % ord(match.group(1))
if type(s) == str:
s = s.decode(settings.DEFAULT_CHARSET)
elif type(s) != unicode:
raise TypeError, s
s = s.replace('\\', '\\\\')
s = s.replace('\r', '\\r')
s = s.replace('\n', '\\n')
s = s.replace('\t', '\\t')
s = s.replace("'", "\\'")
if quote_double_quotes:
s = s.replace('"', '"')
return str(ustring_re.sub(fix, s))
smart_split_re = re.compile('("(?:[^"\\\\]*(?:\\\\.[^"\\\\]*)*)"|\'(?:[^\'\\\\]*(?:\\\\.[^\'\\\\]*)*)\'|[^\\s]+)')
def smart_split(text):
"""
Generator that splits a string by spaces, leaving quoted phrases together.
Supports both single and double quotes, and supports escaping quotes with
backslashes. In the output, strings will keep their initial and trailing
quote marks.
>>> list(smart_split('This is "a person\'s" test.'))
['This', 'is', '"a person\'s"', 'test.']
"""
for bit in smart_split_re.finditer(text):
bit = bit.group(0)
if bit[0] == '"':
yield '"' + bit[1:-1].replace('\\"', '"').replace('\\\\', '\\') + '"'
elif bit[0] == "'":
yield "'" + bit[1:-1].replace("\\'", "'").replace("\\\\", "\\") + "'"
else:
yield bit
|