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
|
#!/usr/bin/python
# this indexes ding-like dictionary
# dictionary consists of lines, each line is one entry and looks like this:
# first : second
# where first is a word in first language, second is translation
# : is separator, can be changed below (sep)
# there can be more words as entries:
# first : second1, second2, second3
# separated by , (see sep1 below)
sep = " : "
sep1 = ", "
import sys, string
from utils import decb64
nulltrans = lambda x: (x,)
trans = lambda x: (string.strip(x),)
def addword(word, pos, l):
nw = trans(word)
if nw:
pos = decb64(pos)
l = decb64(l)
for i in nw:
print "%s\t%s\t%s" % (i, pos, l)
f = open(sys.argv[1], "r")
pos = 0
lastlinepos = 0
inword = 0
word = ""
def readblock(f):
bl = ""
while 1:
l = f.readline()
bl = bl+l
if (not l) or l=='\n':
return bl
block = ""
while 1:
#i = readblock(f) # or f.readline
i = f.readline()
if not i:
break
endpos = pos+len(i)
i = string.replace(i, '\n', '')
spl = string.split(i, sep)
one, two = spl[:2]
one = string.split(one, sep1)
two = string.split(two, sep1)
words = one+two
for j in words:
addword(j, pos, len(i))
pos = endpos
|
