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
|
#!/usr/bin/env python
# coding=utf-8
"""
translate.py - Phenny Translation Module
Copyright 2008, Sean B. Palmer, inamidst.com
Licensed under the Eiffel Forum License 2.
http://inamidst.com/phenny/
"""
import re, time
import web
r_translation = re.compile(r'<div style=padding:10px;>([^<]+)</div>')
def guess_language(phrase):
languages = {
'english': 'en',
'french': 'fr',
'spanish': 'es',
'portuguese': 'pt',
'german': 'de',
'italian': 'it',
'korean': 'ko',
'japanese': 'ja',
'chinese': 'zh',
'dutch': 'nl',
'greek': 'el',
'russian': 'ru'
}
uri = 'http://www.xrce.xerox.com/cgi-bin/mltt/LanguageGuesser'
form = {'Text': phrase}
bytes = web.post(uri, form)
for line in bytes.splitlines():
if '<listing><font size=+1>' in line:
i = line.find('<listing><font size=+1>')
lang = line[i+len('<listing><font size=+1>'):].strip()
lang = lang.lower()
if '_' in lang:
j = lang.find('_')
lang = lang[:j]
try: return languages[lang]
except KeyError:
return lang
return 'Moon Language'
def translate(phrase, lang, target='en'):
babelfish = 'http://world.altavista.com/tr'
form = {
'doit': 'done',
'intl': '1',
'tt': 'urltext',
'trtext': phrase,
'lp': lang + '_' + target
}
bytes = web.post(babelfish, form)
m = r_translation.search(bytes)
if m:
translation = m.group(1)
translation = translation.replace('\r', ' ')
translation = translation.replace('\n', ' ')
while ' ' in translation:
translation = translation.replace(' ', ' ')
return translation.lower()
return None
def tr(phenny, input):
"""Translates a phrase, with an optional language hint."""
original_input = input
input, output, phrase = original_input.groups()
phrase = phrase.encode('utf-8')
if (len(phrase) > 350) and (not original_input.admin):
return phenny.reply('Phrase must be under 350 characters.')
input = input or guess_language(phrase)
if not input:
return phenny.reply('Unable to guess the language, sorry.')
input = input.encode('utf-8')
output = (output or 'en').encode('utf-8')
if not ((input == 'en') and (output == 'en')):
translation = translate(phrase, input, output)
if translation is not None:
translation = translation.decode('utf-8').encode('utf-8')
if output == 'en':
return phenny.reply('"%s" (%s)' % (translation, input))
else: return phenny.reply('"%s" (%s -> %s)' % \
(translation, input, output))
error = "I think it's %s, which I can't translate."
return phenny.reply(error % input.title())
# Otherwise, it's English, so mangle it for fun
for other in ['de', 'ja', 'de', 'ja', 'de', 'ja', 'de', 'ja', 'de', 'ja']:
phrase = translate(phrase, 'en', other)
phrase = translate(phrase, other, 'en')
time.sleep(0.1)
if phrase is not None:
return phenny.reply(u'"%s" (en-unmangled)' % phrase)
return phenny.reply("I think it's English already.")
# @@ or 'Why but that be English, sire.'
tr.rule = ('$nick', ur'(?:([a-z]{2}) +)?(?:([a-z]{2}) +)?["“](.+?)["”]\? *$')
tr.example = '$nickname: "mon chien"? or $nickname: fr "mon chien"?'
tr.priority = 'low'
# @@ mangle
if __name__ == '__main__':
print __doc__.strip()
|
