Mercurial > libervia-backend

comparison sat/plugins/plugin_exp_lang_detect.py @ 2562:26edcf3a30eb

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
core, setup: huge cleaning: - moved directories from src and frontends/src to sat and sat_frontends, which is the recommanded naming convention - move twisted directory to root - removed all hacks from setup.py, and added missing dependencies, it is now clean - use https URL for website in setup.py - removed "Environment :: X11 Applications :: GTK", as wix is deprecated and removed - renamed sat.sh to sat and fixed its installation - added python_requires to specify Python version needed - replaced glib2reactor which use deprecated code by gtk3reactor sat can now be installed directly from virtualenv without using --system-site-packages anymore \o/
author Goffi <goffi@goffi.org>
date Mon, 02 Apr 2018 19:44:50 +0200
parents src/plugins/plugin_exp_lang_detect.py@0046283a285d
children 56f94936df1e
comparison
equal deleted inserted replaced
2561:bd30dc3ffe5a 2562:26edcf3a30eb
1 #!/usr/bin/env python2
2 # -*- coding: utf-8 -*-
3
4 # SAT plugin to detect language (experimental)
5 # Copyright (C) 2009-2018 Jérôme Poisson (goffi@goffi.org)
6
7 # This program is free software: you can redistribute it and/or modify
8 # it under the terms of the GNU Affero General Public License as published by
9 # the Free Software Foundation, either version 3 of the License, or
10 # (at your option) any later version.
11
12 # This program is distributed in the hope that it will be useful,
13 # but WITHOUT ANY WARRANTY; without even the implied warranty of
14 # MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
15 # GNU Affero General Public License for more details.
16
17 # You should have received a copy of the GNU Affero General Public License
18 # along with this program. If not, see <http://www.gnu.org/licenses/>.
19
20 from sat.core.i18n import _, D_
21 from sat.core.constants import Const as C
22 from sat.core.log import getLogger
23 log = getLogger(__name__)
24 from sat.core import exceptions
25
26 try:
27 from langid.langid import LanguageIdentifier, model
28 except ImportError:
29 raise exceptions.MissingModule(u'Missing module langid, please download/install it with "pip install langid")')
30
31 identifier = LanguageIdentifier.from_modelstring(model, norm_probs=False)
32
33
34 PLUGIN_INFO = {
35 C.PI_NAME: "Language detection plugin",
36 C.PI_IMPORT_NAME: "EXP-LANG-DETECT",
37 C.PI_TYPE: "EXP",
38 C.PI_PROTOCOLS: [],
39 C.PI_DEPENDENCIES: [],
40 C.PI_MAIN: "LangDetect",
41 C.PI_HANDLER: "no",
42 C.PI_DESCRIPTION: _("""Detect and set message language when unknown""")
43 }
44
45 CATEGORY = D_(u"Misc")
46 NAME = u"lang_detect"
47 LABEL = D_(u"language detection")
48 PARAMS = """
49 <params>
50 <individual>
51 <category name="{category_name}">
52 <param name="{name}" label="{label}" type="bool" value="true" />
53 </category>
54 </individual>
55 </params>
56 """.format(category_name=CATEGORY,
57 name=NAME,
58 label=_(LABEL),
59 )
60
61
62 class LangDetect(object):
63
64 def __init__(self, host):
65 log.info(_(u"Language detection plugin initialization"))
66 self.host = host
67 host.memory.updateParams(PARAMS)
68 host.trigger.add("MessageReceived", self.MessageReceivedTrigger)
69 host.trigger.add("sendMessage", self.MessageSendTrigger)
70
71 def addLanguage(self, mess_data):
72 message = mess_data['message']
73 if len(message) == 1 and message.keys()[0] == '':
74 msg = message.values()[0]
75 lang = identifier.classify(msg)[0]
76 mess_data["message"] = {lang: msg}
77 return mess_data
78
79 def MessageReceivedTrigger(self, client, message_elt, post_treat):
80 """ Check if source is linked and repeat message, else do nothing """
81
82 lang_detect = self.host.memory.getParamA(NAME, CATEGORY, profile_key=client.profile)
83 if lang_detect:
84 post_treat.addCallback(self.addLanguage)
85 return True
86
87 def MessageSendTrigger(self, client, data, pre_xml_treatments, post_xml_treatments):
88 lang_detect = self.host.memory.getParamA(NAME, CATEGORY, profile_key=client.profile)
89 if lang_detect:
90 self.addLanguage(data)
91 return True