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
|
import string, struct
# size of an integer
INT_SIZE = struct.calcsize('i')
strategies = {
'exact' : (0, 'Match words exactly'),
'prefix' : (1, 'Match prefixes'),
'substring' : (2, 'Match substring occurring anywhere in word'),
'suffix' : (3, 'Match suffixes'),
'soundex' : (4, 'Match using SOUNDEX algorithm'),
'lev' : (5, 'Match words within Levenshtein distance one'),
're' : (6, 'POSIX 1003.2 regular expressions'),
'fnmatch' : (7, 'fnmatch-like (* ? as wildcards)'),
'metaphone' : (8, 'metaphone algorithm')
}
b64_list = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+/"
def b64_encode(val):
"""Takes as input an integer val and returns a string of it encoded
with the base64 algorithm used by dict indexes."""
startfound = 0
retval = ""
for i in range(5, -1, -1):
thispart = (val >> (6 * i)) & ((2 ** 6) - 1)
if (not startfound) and (not thispart):
# Both zero -- keep going.
continue
startfound = 1
retval += b64_list[thispart]
if len(retval):
return retval
else:
return b64_list[0]
def b64_decode(str):
"""Takes as input a string and returns an integer value of it decoded
with the base64 algorithm used by dict indexes."""
if not len(str):
return 0
retval = 0
shiftval = 0
for i in range(len(str) - 1, -1, -1):
val = b64_list.index(str[i])
retval = retval | (val << shiftval)
shiftval += 6
return retval
CRLF = "\r\n"
TAB = "\t"
def quote_reply(s):
s = string.replace(s, "\n.", "\n..")
s = string.replace(s, "\n", CRLF)
return s
# compare two words, trying to be case insensitive
# input is assumed as two tuples of (strings, position),
# string is in UTF-8 encoding
def dict_compare(v1, v2):
u1 = unicode(v1[0], 'utf-8').lower()
u2 = unicode(v2[0], 'utf-8').lower()
return cmp(u1,u2)
|
