Skip to content

Classify damaged archives with python-magic #218

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
bjk7119 merged 1 commit into from
Sep 16, 2026
Merged

Classify damaged archives with python-magic #218

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 11 additions & 4 deletions src/fosslight_binary/_simple_mode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,10 +4,10 @@
# Copyright (c) 2024 LG Electronics Inc.
# SPDX-License-Identifier: Apache-2.0
import os
import re
import logging
import zipfile
import tarfile
import magic
import yaml
import fosslight_util.constant as constant
from fosslight_util.set_log import init_log
Expand All @@ -18,7 +18,14 @@


def is_compressed_file(filename):
return zipfile.is_zipfile(filename) or tarfile.is_tarfile(filename)
if zipfile.is_zipfile(filename) or tarfile.is_tarfile(filename):
return True

try:
file_type = magic.from_file(filename).lower()
return 'archive' in file_type or 'compressed' in file_type
except Exception:
return False


def is_jar_file(filename):
Expand All @@ -35,9 +42,9 @@ def exclude_bin_for_simple_mode(binary_list):

path = bin.bin_name_with_path

if is_jar_file(path) and not re.search(r".*sources\.jar", path.lower()):
if is_jar_file(path) and not path.lower().endswith('-sources.jar'):
bin_list_exclude_compressed.append(path)
elif re.search(r".*sources\.jar", path.lower()) or is_compressed_file(path):
elif path.lower().endswith('-sources.jar') or is_compressed_file(path):
compressed_list.append(path)
else:
bin_list_exclude_compressed.append(path)
Expand Down
Loading