Added clamav integration (cvat-ai#1712)

* added clamav integration

* updated license headers and changelog

CHANGELOG.md

@@ -14,6 +14,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Shortcut to switch split mode (<https://github.com/opencv/cvat/pull/1683>)
 - Built-in search for labels when create an object or change a label (<https://github.com/opencv/cvat/pull/1683>)
 - Better validation of labels and attributes in raw viewer (<https://github.com/opencv/cvat/pull/1727>)
+- ClamAV antivirus integration (<https://github.com/opencv/cvat/pull/1712>)
 
 ### Changed
 - Removed information about e-mail from the basic user information (<https://github.com/opencv/cvat/pull/1627>)

Dockerfile

@@ -129,6 +129,19 @@ RUN if [ "$WITH_DEXTR" = "yes" ]; then \
         7z e ${DEXTR_MODEL_DIR}/dextr.zip -o${DEXTR_MODEL_DIR} && rm ${DEXTR_MODEL_DIR}/dextr.zip; \
     fi
 
+ARG CLAM_AV
+ENV CLAM_AV=${CLAM_AV}
+RUN if [ "$CLAM_AV" = "yes" ]; then \
+        apt-get update && \
+        apt-get --no-install-recommends install -yq \
+            clamav \
+            libclamunrar9 && \
+        sed -i 's/ReceiveTimeout 30/ReceiveTimeout 300/g' /etc/clamav/freshclam.conf && \
+        freshclam && \
+        chown -R ${USER}:${USER} /var/lib/clamav && \
+        rm -rf /var/lib/apt/lists/*; \
+    fi
+
 COPY ssh ${HOME}/.ssh
 COPY utils ${HOME}/utils
 COPY cvat/ ${HOME}/cvat

cvat/apps/auto_annotation/model_manager.py

@@ -19,6 +19,7 @@
 from cvat.apps.engine.serializers import LabeledDataSerializer
 from cvat.apps.dataset_manager.task import put_task_data, patch_task_data
 from cvat.apps.engine.frame_provider import FrameProvider
+from cvat.apps.engine.utils import av_scan_paths
 
 from .models import AnnotationModel, FrameworkChoice
 from .model_loader import load_labelmap
@@ -139,6 +140,7 @@ def save_file_as_tmp(data):
                 tmp_file.write(chunk)
         os.close(fd)
         return filename
+
     is_create_request = dl_model_id is None
     if is_create_request:
         dl_model_id = create_empty(owner=owner)
@@ -155,6 +157,17 @@ def save_file_as_tmp(data):
         labelmap_file = save_file_as_tmp(labelmap_file)
         interpretation_file = save_file_as_tmp(interpretation_file)
 
+    files_to_scan = []
+    if model_file:
+        files_to_scan.append(model_file)
+    if weights_file:
+        files_to_scan.append(weights_file)
+    if labelmap_file:
+        files_to_scan.append(labelmap_file)
+    if interpretation_file:
+        files_to_scan.append(interpretation_file)
+    av_scan_paths(*files_to_scan)
+
     if owner:
         restricted = not has_admin_role(owner)
     else:

cvat/apps/engine/task.py

@@ -1,5 +1,5 @@
 
-# Copyright (C) 2018 Intel Corporation
+# Copyright (C) 2018-2020 Intel Corporation
 #
 # SPDX-License-Identifier: MIT
 
@@ -15,6 +15,7 @@
 
 from cvat.apps.engine.media_extractors import get_mime, MEDIA_TYPES, Mpeg4ChunkWriter, ZipChunkWriter, Mpeg4CompressedChunkWriter, ZipCompressedChunkWriter
 from cvat.apps.engine.models import DataChoice
+from cvat.apps.engine.utils import av_scan_paths
 
 import django_rq
 from django.conf import settings
@@ -223,6 +224,8 @@ def _create_thread(tid, data):
     if data['server_files']:
         _copy_data_from_share(data['server_files'], upload_dir)
 
+    av_scan_paths(upload_dir)
+
     job = rq.get_current_job()
     job.meta['status'] = 'Media files are being extracted...'
     job.save_meta()

cvat/apps/engine/utils.py

@@ -1,8 +1,16 @@
+# Copyright (C) 2020 Intel Corporation
+#
+# SPDX-License-Identifier: MIT
+
 import ast
 from collections import namedtuple
 import importlib
 import sys
 import traceback
+import subprocess
+import os
+
+from django.core.exceptions import ValidationError
 
 Import = namedtuple("Import", ["module", "name", "alias"])
 
@@ -58,3 +66,11 @@ def execute_python_code(source_code, global_vars=None, local_vars=None):
         _, _, tb = sys.exc_info()
         line_number = traceback.extract_tb(tb)[-1][1]
         raise InterpreterError("{} at line {}: {}".format(error_class, line_number, details))
+
+def av_scan_paths(*paths):
+    if 'yes' == os.environ.get('CLAM_AV'):
+        command = ['clamscan', '--no-summary', '-i', '-o']
+        command.extend(paths)
+        res = subprocess.run(command, capture_output=True)
+        if res.returncode:
+            raise ValidationError(res.stdout)

cvat/apps/engine/views.py

@@ -1,4 +1,4 @@
-# Copyright (C) 2018-2019 Intel Corporation
+# Copyright (C) 2018-2020 Intel Corporation
 #
 # SPDX-License-Identifier: MIT
 
@@ -45,6 +45,7 @@
     LogEventSerializer, PluginSerializer, ProjectSerializer,
     RqStatusSerializer, TaskSerializer, UserSerializer)
 from cvat.settings.base import CSS_3RDPARTY, JS_3RDPARTY
+from cvat.apps.engine.utils import av_scan_paths
 
 from . import models, task
 from .log import clogger, slogger
@@ -821,6 +822,8 @@ def _import_annotations(request, rq_id, rq_func, pk, format_name):
             with open(filename, 'wb+') as f:
                 for chunk in anno_file.chunks():
                     f.write(chunk)
+
+            av_scan_paths(filename)
             rq_job = queue.enqueue_call(
                 func=rq_func,
                 args=(pk, filename, format_name),

docker-compose.yml

@@ -50,6 +50,7 @@ services:
         DJANGO_CONFIGURATION: "production"
         TZ: "Etc/UTC"
         OPENVINO_TOOLKIT: "no"
+        CLAM_AV: "no"
     environment:
       DJANGO_MODWSGI_EXTRA_ARGS: ""
       ALLOWED_HOSTS: '*'

supervisord.conf

@@ -47,6 +47,11 @@ command=%(ENV_HOME)s/wait-for-it.sh %(ENV_CVAT_REDIS_HOST)s:6379 -t 0 -- bash -i
 environment=SSH_AUTH_SOCK="/tmp/ssh-agent.sock"
 numprocs=1
 
+[program:clamav_update]
+command=bash -c "if [ \"${CLAM_AV}\" = 'yes' ]; then /usr/bin/freshclam -d \
+    -l %(ENV_HOME)s/logs/freshclam.log --foreground=true; fi"
+numprocs=1
+
 [program:runserver]
 ; Here need to run a couple of commands to initialize DB and copy static files.
 ; We cannot initialize DB on build because the DB should be online. Also some