view sat/plugins/plugin_exp_lang_detect.py @ 3330:7b47f48d31f3

plugin XEP-0264: fix orientation of thumbnails: Rotation of thumbnailis is now modified according to EXIF orientation data. Original image is not modified as user may want to keep it, and orientation transformation can modify encoding parameters. Update `pillow` minimum version to the first one with `exif_transpose` implementation.
author Goffi <goffi@goffi.org>
date Thu, 13 Aug 2020 23:46:18 +0200
parents dcebc585c29f
children be6d91572633
line wrap: on
line source

#!/usr/bin/env python3


# SAT plugin to detect language (experimental)
# Copyright (C) 2009-2020 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 _, D_
from sat.core.constants import Const as C
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(
        '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.updateParams(PARAMS)
        host.trigger.add("messageReceived", self.messageReceivedTrigger)
        host.trigger.add("sendMessage", self.MessageSendTrigger)

    def addLanguage(self, mess_data):
        message = mess_data["message"]
        if len(message) == 1 and list(message.keys())[0] == "":
            msg = list(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  """

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

    def MessageSendTrigger(self, client, data, pre_xml_treatments, post_xml_treatments):
        lang_detect = self.host.memory.getParamA(
            NAME, CATEGORY, profile_key=client.profile
        )
        if lang_detect:
            self.addLanguage(data)
        return True