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
|
#!/usr/bin/python
# convert ding-like dictionary into .tei format
# 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 = ", " # set this to some nonsense if you have one phrase per line
import sys, string
f = open(sys.argv[1], "r")
pos = 0
lastlinepos = 0
inword = 0
word = ""
def teiheader():
print """<!DOCTYPE TEI.2 PUBLIC "-//TEI P3//DTD Main Document Type//EN" [
<!ENTITY % TEI.dictionaries "INCLUDE" >
]>
<tei.2>
<teiHeader>
<filedesc>
<titlestmt>
<title> </title>
</titlestmt>
<publicationstmt>
<authority>Freedict.de</authority>
</publicationstmt>
<sourcedesc>
<p>http://www.freedict.de</p>
</sourcedesc>
</filedesc>
</teiHeader>
"""
words = {}
block = ""
teiheader()
print "<text>"
print "<body>"
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]
if len(spl)==3:
clen="[%s]" % spl[2]
else:
clen=""
# uncomment this line to change order of languages
one, two = two, one
if clen:
two = clen+" "+two
two = [two] # or:
#two = string.split(two, sep1)
if words.has_key(one):
words[one].extend(two)
else:
words[one] = two
for i, j in words.items():
print "<entry>"
print " <form>"
for k in string.split(i, sep1):
print " <orth>"+k+"</orth>"
print " </form>"
print " <trans>"
for k in j:
print " <tr>"+k+"</tr>"
print " </trans>"
print "</entry>"
print "</body>"
print "</text>"
print "</tei.2>"
|
