common language interface and wordreference backend
Conflicts: modules/wordreference/pages.py weboob/applications/translaboob/translaboob.py
This commit is contained in:
lucien
Romain Bignon
parent
9efbeff8a4
commit
657e2213ac
11 changed files with 287 additions and 19 deletions
|
|
@ -19,7 +19,7 @@
|
|||
"backend for http://translate.google.com"
|
||||
|
||||
|
||||
from weboob.capabilities.translate import ICapTranslate, Translation, TranslationFail
|
||||
from weboob.capabilities.translate import ICapTranslate, Translation, TranslationFail, LanguageNotSupported
|
||||
from weboob.tools.backend import BaseBackend
|
||||
|
||||
from .browser import GoogleTranslateBrowser
|
||||
|
|
@ -36,12 +36,30 @@ class GoogleTranslateBackend(BaseBackend, ICapTranslate):
|
|||
NAME = 'googletranslate'
|
||||
DESCRIPTION = u'Google translation web service'
|
||||
BROWSER = GoogleTranslateBrowser
|
||||
GOOGLELANGUAGE = {
|
||||
'Arabic':'ar', 'Afrikaans':'af', 'Albanian':'sq', 'Armenian':'hy', 'Azerbaijani':'az', 'Basque':'eu', 'Belarusian':'be',
|
||||
'Bengali':'bn', 'Bulgarian':'bg', 'Catalan':'ca', 'Chinese':'zh-CN', 'Croatian':'hr', 'Czech':'cs', 'Danish':'da',
|
||||
'Dutch':'nl', 'English':'en', 'Esperanto':'eo', 'Estonian':'et', 'Filipino':'tl', 'Finnish':'fi', 'French':'fr',
|
||||
'Galician':'gl', 'Georgian':'ka', 'German':'de', 'Greek':'gr', 'Gujarati':'gu', 'Haitian':'ht', 'Hebrew':'iw',
|
||||
'Hindi':'hi', 'Hungaric':'hu', 'Icelandic':'is', 'Indonesian':'id', 'Irish':'ga', 'Italian':'it', 'Japanese':'ja',
|
||||
'Kannada':'kn', 'Korean':'ko', 'Latin':'la', 'Latvian':'lv', 'Lithuanian':'lt', 'Macedonian':'mk', 'Malay':'ms',
|
||||
'Maltese':'mt', 'Norwegian':'no', 'Persian':'fa', 'Polish':'pl', 'Portuguese':'pt', 'Romanian':'ro', 'Russian':'ru',
|
||||
'Serbian':'sr', 'Slovak':'sk', 'Slovenian':'sl', 'Spanish':'es', 'Swahili':'sw', 'Swedish':'sv', 'Tamil':'ta',
|
||||
'Telugu':'te', 'Thai':'th', 'Turkish':'tr', 'Ukrainian':'uk', 'Urdu':'ur', 'Vietnamese':'vi', 'Welsh':'cy', 'Yiddish':'yi',
|
||||
}
|
||||
|
||||
|
||||
def translate(self, lan_from, lan_to, text):
|
||||
if not lan_from in self.GOOGLELANGUAGE.keys():
|
||||
raise LanguageNotSupported()
|
||||
|
||||
if not lan_to in self.GOOGLELANGUAGE.keys():
|
||||
raise LanguageNotSupported()
|
||||
|
||||
translation = Translation(0)
|
||||
translation.lang_src = unicode(lan_from)
|
||||
translation.lang_dst = unicode(lan_to)
|
||||
translation.text = self.browser.translate(lan_from, lan_to, text)
|
||||
translation.lang_src = unicode(self.GOOGLELANGUAGE[lan_from])
|
||||
translation.lang_dst = unicode(self.GOOGLELANGUAGE[lan_to])
|
||||
translation.text = self.browser.translate(self.GOOGLELANGUAGE[lan_from], self.GOOGLELANGUAGE[lan_to], text)
|
||||
|
||||
if translation.text is None:
|
||||
raise TranslationFail()
|
||||
|
|
|
|||
|
|
@ -35,7 +35,7 @@ class GoogleTranslateBrowser(BaseBrowser):
|
|||
PAGES = {
|
||||
'https?://translate\.google\.com': TranslatePage
|
||||
}
|
||||
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
BaseBrowser.__init__(self, *args, **kwargs)
|
||||
|
||||
|
|
|
|||
|
|
@ -30,4 +30,4 @@ class TranslatePage(BasePage):
|
|||
if len(boxes) == 0:
|
||||
return None
|
||||
|
||||
return u'\n'.join([unicode(box.text) for box in boxes])
|
||||
return u''.join([unicode(box.text) for box in boxes])
|
||||
|
|
|
|||
|
|
@ -28,5 +28,5 @@ class GoogleTranslateTest(BackendTest):
|
|||
BACKEND = 'googletranslate'
|
||||
|
||||
def test_translate(self):
|
||||
tr = self.backend.translate('fr', 'en', 'je mange du chocolat')
|
||||
tr = self.backend.translate('French', 'English', 'je mange du chocolat')
|
||||
self.assertTrue(tr.text == u'I eat chocolate')
|
||||
|
|
|
|||
24
modules/wordreference/__init__.py
Normal file
24
modules/wordreference/__init__.py
Normal file
|
|
@ -0,0 +1,24 @@
|
|||
"WordReferenceBackend init"
|
||||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright(C) 2012 Lucien Loiseau
|
||||
#
|
||||
# This file is part of weboob.
|
||||
#
|
||||
# weboob is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU Affero General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
#
|
||||
# weboob is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU Affero General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Affero General Public License
|
||||
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
from .backend import WordReferenceBackend
|
||||
|
||||
|
||||
__all__ = ['WordReferenceBackend']
|
||||
60
modules/wordreference/backend.py
Normal file
60
modules/wordreference/backend.py
Normal file
|
|
@ -0,0 +1,60 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright(C) 2012 Lucien Loiseau
|
||||
#
|
||||
# This file is part of weboob.
|
||||
#
|
||||
# weboob is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU Affero General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
#
|
||||
# weboob is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU Affero General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Affero General Public License
|
||||
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
|
||||
"backend for http://www.wordreference.com"
|
||||
|
||||
|
||||
from weboob.capabilities.translate import ICapTranslate, Translation, TranslationFail, LanguageNotSupported
|
||||
from weboob.tools.backend import BaseBackend
|
||||
|
||||
from .browser import WordReferenceBrowser
|
||||
|
||||
|
||||
__all__ = ['WordReferenceBackend']
|
||||
|
||||
|
||||
class WordReferenceBackend(BaseBackend, ICapTranslate):
|
||||
MAINTAINER = 'Lucien Loiseau'
|
||||
EMAIL = 'loiseau.lucien@gmail.com'
|
||||
VERSION = '0.c'
|
||||
LICENSE = 'AGPLv3+'
|
||||
NAME = 'wordreference'
|
||||
DESCRIPTION = u'Free online translator'
|
||||
BROWSER = WordReferenceBrowser
|
||||
WRLANGUAGE = {
|
||||
'Arabic':'ar', 'Chinese':'zh', 'Czech':'cz', 'English':'en', 'French':'fr', 'Greek':'gr',
|
||||
'Italian':'it', 'Japanese':'ja', 'Korean':'ko', 'Polish':'pl', 'Portuguese':'pt',
|
||||
'Romanian':'ro', 'Spanish':'es', 'Turkish':'tr',
|
||||
}
|
||||
|
||||
def translate(self, lan_from, lan_to, text):
|
||||
if not lan_from in self.WRLANGUAGE.keys():
|
||||
raise LanguageNotSupported()
|
||||
|
||||
if not lan_to in self.WRLANGUAGE.keys():
|
||||
raise LanguageNotSupported()
|
||||
|
||||
translation = Translation(0)
|
||||
translation.lang_src = unicode(self.WRLANGUAGE[lan_from])
|
||||
translation.lang_dst = unicode(self.WRLANGUAGE[lan_to])
|
||||
translation.text = self.browser.translate(self.WRLANGUAGE[lan_from], self.WRLANGUAGE[lan_to], text)
|
||||
|
||||
if translation.text is None:
|
||||
raise TranslationFail()
|
||||
|
||||
return translation
|
||||
51
modules/wordreference/browser.py
Normal file
51
modules/wordreference/browser.py
Normal file
|
|
@ -0,0 +1,51 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright(C) 2012 Lucien Loiseau
|
||||
#
|
||||
# This file is part of weboob.
|
||||
#
|
||||
# weboob is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU Affero General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
#
|
||||
# weboob is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU Affero General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Affero General Public License
|
||||
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
|
||||
import urllib
|
||||
|
||||
from weboob.tools.browser import BaseBrowser
|
||||
|
||||
from .pages import TranslatePage
|
||||
|
||||
|
||||
__all__ = ['WordReferenceBrowser']
|
||||
|
||||
|
||||
class WordReferenceBrowser(BaseBrowser):
|
||||
DOMAIN = 'www.wordreference.com'
|
||||
ENCODING = 'UTF-8'
|
||||
USER_AGENT = BaseBrowser.USER_AGENTS['desktop_firefox']
|
||||
PAGES = {
|
||||
'https?://www\.wordreference\.com/.*/.*': TranslatePage
|
||||
}
|
||||
|
||||
def __init__(self, *args, **kwargs):
|
||||
BaseBrowser.__init__(self, *args, **kwargs)
|
||||
|
||||
def translate(self, source, to, text):
|
||||
"""
|
||||
translate 'text' from 'source' language to 'to' language
|
||||
"""
|
||||
sl = source.encode('utf-8')
|
||||
tl = to.encode('utf-8')
|
||||
text = text.encode('utf-8')
|
||||
self.location('http://'+self.DOMAIN+'/'+sl+tl+'/'+urllib.quote(text))
|
||||
translation = self.page.get_translation()
|
||||
return translation
|
||||
32
modules/wordreference/pages.py
Normal file
32
modules/wordreference/pages.py
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
# -*- coding: utf-8 -*-
|
||||
|
||||
# Copyright(C) 2012 Lucien Loiseau
|
||||
#
|
||||
# This file is part of weboob.
|
||||
#
|
||||
# weboob is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU Affero General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
#
|
||||
# weboob is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU Affero General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Affero General Public License
|
||||
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
|
||||
from weboob.tools.browser import BasePage
|
||||
|
||||
|
||||
__all__ = ['TranslatePage']
|
||||
|
||||
|
||||
class TranslatePage(BasePage):
|
||||
def get_translation(self):
|
||||
for tr in self.document.getiterator('tr'):
|
||||
if tr.attrib.get('class','') == 'odd' or tr.attrib.get('class','') == 'even':
|
||||
return u''+tr.getchildren()[0].getchildren()[0].text
|
||||
|
||||
32
modules/wordreference/test.py
Normal file
32
modules/wordreference/test.py
Normal file
|
|
@ -0,0 +1,32 @@
|
|||
# -*- CODing: utf-8 -*-
|
||||
|
||||
# Copyright(C) 2012 Lucien Loiseau
|
||||
#
|
||||
# This file is part of weboob.
|
||||
#
|
||||
# weboob is free software: you can redistribute it and/or modify
|
||||
# it under the terms of the GNU Affero General Public License as published by
|
||||
# the Free Software Foundation, either version 3 of the License, or
|
||||
# (at your option) any later version.
|
||||
#
|
||||
# weboob is distributed in the hope that it will be useful,
|
||||
# but WITHOUT ANY WARRANTY; without even the implied warranty of
|
||||
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
||||
# GNU Affero General Public License for more details.
|
||||
#
|
||||
# You should have received a copy of the GNU Affero General Public License
|
||||
# along with weboob. If not, see <http://www.gnu.org/licenses/>.
|
||||
|
||||
|
||||
from weboob.tools.test import BackendTest
|
||||
|
||||
|
||||
__all__ = ['WordReferenceTest']
|
||||
|
||||
|
||||
class WordReferenceTest(BackendTest):
|
||||
BACKEND = 'wordreference'
|
||||
|
||||
def test_translate(self):
|
||||
tr = self.backend.translate('French', 'English', 'chat')
|
||||
self.assertTrue(tr.text == u'cat')
|
||||
Loading…
Add table
Add a link
Reference in a new issue