Files
mvt/tests/common/test_utils.py
T
Donncha Ó Cearbhaill dac4acb180 Load installed module packages via entry points (#883)
* Load installed module packages via entry points

Python packages can already register custom CLI commands which load
automatically, but custom modules still require --load-module or the
MVT_CUSTOM_MODULES environment variable on every invocation.

Add an mvt.modules entry-point group so installed packages can register
forensic modules which load automatically into every module-running
check-* command. An entry point resolves to an iterable of MVTModule
subclasses, or a callable returning one. Broken entry points are
skipped with a warning so a faulty package cannot break MVT.

* Record the source of loaded modules for auditability

Now that installed module packages load automatically, record where every
module came from:

- --list-modules groups the available modules by source, one line per
  source with the modules comma-separated: MVT itself with its version,
  each installed package with its version and VCS commit when recorded
  (PEP 610 direct_url.json), and each --load-module/MVT_CUSTOM_MODULES
  file with its SHA-256 hash.
- Commands log one line per module source with its version or hash and
  the modules loaded from it, so command.log records exactly which
  modules ran and where they came from.
- Make init_logging() idempotent: a loaded module package importing an
  MVT CLI module would previously add a second console handler and
  duplicate every console log line.

* Route loaded module logging under the mvt.ext namespace

Modules loaded from installed packages or file paths live outside the
mvt logger hierarchy, so their log records never reach MVT's console
and file handlers and instead fall through to logging.lastResort:
alerts print as bare unformatted lines and INFO messages are dropped
entirely.

Add get_module_logger() and use it everywhere module loggers are
created. Built-in mvt.* modules keep their existing logger names, and
everything external is parented under a dedicated mvt.ext namespace so
records reach the handlers and external names can never collide with
MVT's internal logger tree. File-path modules are named after their
file (mvt.ext.<stem>) instead of the mangled internal import name.

Document a naming convention for community module packages:
distribute as mvt-plugin-<name> with import package mvt_plugin_<name>,
including the publishing organization in the name. The prefix is
advisory (loading is by entry point, and it is no mark of
authenticity), but conforming packages get a cleaner logger namespace:
the mvt_plugin_ prefix is stripped, so mvt_plugin_amnesty_custom logs
as mvt.ext.amnesty_custom.
2026-08-19 23:15:48 +02:00

125 lines
4.0 KiB
Python

# Mobile Verification Toolkit (MVT)
# Copyright (c) 2021-2022 Claudio Guarnieri.
# Use of this software is governed by the MVT License 1.1 that can be found at
# https://license.mvt.re/1.1/
import json
import logging
import os
from datetime import datetime
from mvt.common.log import MVTLogHandler
from mvt.common.utils import (
CustomJSONEncoder,
convert_datetime_to_iso,
convert_mactime_to_iso,
convert_unix_to_iso,
convert_unix_to_utc_datetime,
generate_hashes_from_path,
get_sha256_from_file_path,
init_logging,
)
from ..utils import get_artifact_folder
TEST_DATE_EPOCH = 1626566400
TEST_DATE_ISO = "2021-07-18 00:00:00.000000"
TEST_DATE_MAC = TEST_DATE_EPOCH - 978307200
class TestDateConversions:
def test_convert_unix_to_iso(self):
assert convert_unix_to_iso(TEST_DATE_EPOCH) == TEST_DATE_ISO
def test_convert_mactime_to_iso(self):
assert convert_mactime_to_iso(TEST_DATE_MAC) == TEST_DATE_ISO
def test_convert_unix_to_utc_datetime(self):
converted = convert_unix_to_utc_datetime(TEST_DATE_EPOCH)
assert converted.year == 2021
assert converted.month == 7
assert converted.day == 18
def test_convert_datetime_to_iso(self):
converted = convert_unix_to_utc_datetime(TEST_DATE_EPOCH)
assert convert_datetime_to_iso(converted) == TEST_DATE_ISO
def test_convert_timezone_aware_to_iso(self):
assert (
convert_datetime_to_iso(
datetime.strptime("2024-09-30 11:21:20+0200", "%Y-%m-%d %H:%M:%S%z")
)
== "2024-09-30 09:21:20.000000"
)
class TestHashes:
def test_hash_from_file(self):
path = os.path.join(get_artifact_folder(), "androidqf", "backup.ab")
sha256 = get_sha256_from_file_path(path)
assert (
sha256 == "f0e32fe8a7fd5ac0e2de19636d123c0072e979396986139ba2bc49ec385dc325"
)
def test_hash_from_folder(self):
path = os.path.join(get_artifact_folder(), "androidqf")
hashes = list(generate_hashes_from_path(path, logging))
assert len(hashes) == 8
# Sort the files to have reliable order for tests.
hashes = sorted(hashes, key=lambda x: x["file_path"])
assert hashes[0]["file_path"] == os.path.join(path, "backup.ab")
assert (
hashes[0]["sha256"]
== "f0e32fe8a7fd5ac0e2de19636d123c0072e979396986139ba2bc49ec385dc325"
)
assert hashes[1]["file_path"] == os.path.join(path, "dumpsys.txt")
# This needs to be updated when we add or edit files in AndroidQF folder
assert (
hashes[1]["sha256"]
== "9fb6396b64cfff30e2a459a64496d3c1386926d09edd68be2d878de45fa7b3a9"
)
class TestCustomJSONEncoder:
def test__normal_input(self):
assert json.dumps({"a": "b"}, cls=CustomJSONEncoder) == '{"a": "b"}'
def test__datetime_object(self):
assert (
json.dumps(
{"timestamp": datetime(2023, 11, 13, 12, 21, 49, 727467)},
cls=CustomJSONEncoder,
)
== '{"timestamp": "2023-11-13 12:21:49.727467"}'
)
def test__bytes_non_utf_8(self):
assert (
json.dumps({"identifier": b"\xa8\xa9"}, cls=CustomJSONEncoder)
== """{"identifier": "\\\\xa8\\\\xa9"}"""
)
def test__bytes_valid_utf_8(self):
assert (
json.dumps({"name": "家".encode()}, cls=CustomJSONEncoder)
== '{"name": "\\u5bb6"}'
)
class TestInitLogging:
def test__init_logging_is_idempotent(self):
# Loaded module packages may import an MVT CLI module, which calls
# init_logging() again at import time. A second call must not add
# a duplicate console handler.
log = logging.getLogger("mvt")
init_logging()
handler_count = sum(
isinstance(handler, MVTLogHandler) for handler in log.handlers
)
init_logging()
assert (
sum(isinstance(handler, MVTLogHandler) for handler in log.handlers)
== handler_count
)