diff src/plugins/plugin_exp_lang_detect.py @ 1965:4c5d8cd35690

plugin exp_lang_detect: language detection plugin, first draft This plugin try to autodetect outgoing and ingoing messages language when it is not specified by sender
author Goffi <goffi@goffi.org>
date Mon, 20 Jun 2016 18:44:27 +0200
parents
children d95a6d553bec
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/src/plugins/plugin_exp_lang_detect.py	Mon Jun 20 18:44:27 2016 +0200
@@ -0,0 +1,68 @@
+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+
+# SAT plugin to detect language (experimental)
+# Copyright (C) 2009-2016 Jérôme Poisson (goffi@goffi.org)
+
+# This program 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.
+
+# This program 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 this program.  If not, see <http://www.gnu.org/licenses/>.
+
+from sat.core.i18n import _
+from sat.core.log import getLogger
+log = getLogger(__name__)
+from sat.core import exceptions
+
+try:
+    from langid.langid import LanguageIdentifier, model
+except ImportError:
+    raise exceptions.MissingModule(u'Missing module langid, please download/install it with "pip install langid")')
+
+identifier = LanguageIdentifier.from_modelstring(model, norm_probs=False)
+
+
+PLUGIN_INFO = {
+    "name": "Language detection plugin",
+    "import_name": "EXP-LANG-DETECT",
+    "type": "EXP",
+    "protocols": [],
+    "dependencies": [],
+    "main": "LangDetect",
+    "handler": "no",
+    "description": _("""Detect and set message language when unknown""")
+}
+
+
+class LangDetect(object):
+
+    def __init__(self, host):
+        log.info(_(u"Language detection plugin initialization"))
+        self.host = host
+        host.trigger.add("MessageReceived", self.MessageReceivedTrigger)
+        host.trigger.add("messageSend", self.MessageSendTrigger)
+
+    def addLanguage(self, mess_data):
+        message = mess_data['message']
+        if len(message) == 1 and message.keys()[0] == '':
+            msg = message.values()[0]
+            lang = identifier.classify(msg)[0]
+            mess_data["message"] = {lang: msg}
+        return mess_data
+
+    def MessageReceivedTrigger(self, client, message_elt, post_treat):
+        """ Check if source is linked and repeat message, else do nothing  """
+        post_treat.addCallback(self.addLanguage)
+        return True
+
+    def MessageSendTrigger(self, client, data, pre_xml_treatments, post_xml_treatments):
+        self.addLanguage(data)
+        return True