view libervia/backend/plugins/plugin_exp_lang_detect.py @ 4306:94e0968987cd

plugin XEP-0033: code modernisation, improve delivery, data validation: - Code has been rewritten using Pydantic models and `async` coroutines for data validation and cleaner element parsing/generation. - Delivery has been completely rewritten. It now works even if server doesn't support multicast, and send to local multicast service first. Delivering to local multicast service first is due to bad support of XEP-0033 in server (notably Prosody which has an incomplete implementation), and the current impossibility to detect if a sub-domain service handles fully multicast or only for local domains. This is a workaround to have a good balance between backward compatilibity and use of bandwith, and to make it work with the incoming email gateway implementation (the gateway will only deliver to entities of its own domain). - disco feature checking now uses `async` corountines. `host` implementation still use Deferred return values for compatibility with legacy code. rel 450
author Goffi <goffi@goffi.org>
date Thu, 26 Sep 2024 16:12:01 +0200
parents 0d7bb4df2343
children
line wrap: on
line source

#!/usr/bin/env python3


# SAT plugin to detect language (experimental)
# Copyright (C) 2009-2021 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 libervia.backend.core.i18n import _, D_
from libervia.backend.core.constants import Const as C
from libervia.backend.core.log import getLogger

log = getLogger(__name__)
from libervia.backend.core import exceptions

try:
    from langid.langid import LanguageIdentifier, model
except ImportError:
    raise exceptions.MissingModule(
        'Missing module langid, please download/install it with "pip install langid")'
    )

identifier = LanguageIdentifier.from_modelstring(model, norm_probs=False)


PLUGIN_INFO = {
    C.PI_NAME: "Language detection plugin",
    C.PI_IMPORT_NAME: "EXP-LANG-DETECT",
    C.PI_TYPE: "EXP",
    C.PI_PROTOCOLS: [],
    C.PI_DEPENDENCIES: [],
    C.PI_MAIN: "LangDetect",
    C.PI_HANDLER: "no",
    C.PI_DESCRIPTION: _("""Detect and set message language when unknown"""),
}

CATEGORY = D_("Misc")
NAME = "lang_detect"
LABEL = D_("language detection")
PARAMS = """
    <params>
    <individual>
    <category name="{category_name}">
        <param name="{name}" label="{label}" type="bool" value="true" />
    </category>
    </individual>
    </params>
    """.format(
    category_name=CATEGORY, name=NAME, label=_(LABEL)
)


class LangDetect(object):
    def __init__(self, host):
        log.info(_("Language detection plugin initialization"))
        self.host = host
        host.memory.update_params(PARAMS)
        host.trigger.add("message_received", self.message_received_trigger)
        host.trigger.add("sendMessage", self.message_send_trigger)

    def add_language(self, mess_data):
        message = mess_data["message"]
        if len(message) == 1 and list(message.keys())[0] == "":
            msg = list(message.values())[0].strip()
            if msg:
                lang = identifier.classify(msg)[0]
                mess_data["message"] = {lang: msg}
        return mess_data

    def message_received_trigger(self, client, message_elt, post_treat):
        """Check if source is linked and repeat message, else do nothing"""

        lang_detect = self.host.memory.param_get_a(
            NAME, CATEGORY, profile_key=client.profile
        )
        if lang_detect:
            post_treat.addCallback(self.add_language)
        return True

    def message_send_trigger(self, client, data, pre_xml_treatments, post_xml_treatments):
        lang_detect = self.host.memory.param_get_a(
            NAME, CATEGORY, profile_key=client.profile
        )
        if lang_detect:
            self.add_language(data)
        return True