mirror of
https://github.com/mandiant/capa.git
synced 2025-12-06 12:51:03 -08:00
3cd97ae9f2
Replace the header from source code files using the following script:
```Python
for dir_path, dir_names, file_names in os.walk("capa"):
for file_name in file_names:
# header are only in `.py` and `.toml` files
if file_name[-3:] not in (".py", "oml"):
continue
file_path = f"{dir_path}/{file_name}"
f = open(file_path, "rb+")
content = f.read()
m = re.search(OLD_HEADER, content)
if not m:
continue
print(f"{file_path}: {m.group('year')}")
content = content.replace(m.group(0), NEW_HEADER % m.group("year"))
f.seek(0)
f.write(content)
```
Some files had the copyright headers inside a `"""` comment and needed
manual changes before applying the script. `hook-vivisect.py` and
`pyinstaller.spec` didn't include the license in the header and also
needed manual changes.
The old header had the confusing sentence `All rights reserved`, which
does not make sense for an open source license. Replace the header by
the default Google header that corrects this issue and keep capa
consistent with other Google projects.
Adapt the linter to work with the new header.
Replace also the copyright text in the `web/public/index.html` file for
consistency.
102 lines
3.2 KiB
Python
102 lines
3.2 KiB
Python
# Copyright 2023 Google LLC
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
import sys
|
|
import logging
|
|
import argparse
|
|
from pathlib import Path
|
|
|
|
import capa.main
|
|
import capa.rules
|
|
from capa.features.common import Feature
|
|
|
|
logger = logging.getLogger("detect_duplicate_features")
|
|
|
|
|
|
def get_features(rule_path: str) -> set[Feature]:
|
|
"""
|
|
Extracts all features from a given rule file.
|
|
|
|
Args:
|
|
rule_path (str): The path to the rule file to extract features from.
|
|
|
|
Returns:
|
|
set: A set of all feature statements contained within the rule file.
|
|
"""
|
|
with Path(rule_path).open("r", encoding="utf-8") as f:
|
|
try:
|
|
new_rule = capa.rules.Rule.from_yaml(f.read())
|
|
return new_rule.extract_all_features()
|
|
except Exception as e:
|
|
logger.error("Error: New rule %s %s %s", rule_path, str(type(e)), str(e))
|
|
sys.exit(-1)
|
|
|
|
|
|
def find_overlapping_rules(new_rule_path, rules_path):
|
|
if not new_rule_path.endswith(".yml"):
|
|
logger.error("FileNotFoundError ! New rule file name doesn't end with .yml")
|
|
sys.exit(-1)
|
|
|
|
# Loads features of new rule in a list.
|
|
new_rule_features = get_features(new_rule_path)
|
|
count = 0
|
|
overlapping_rules = []
|
|
|
|
# capa.rules.RuleSet stores all rules in given paths
|
|
ruleset = capa.rules.get_rules(rules_path)
|
|
|
|
for rule_name, rule in ruleset.rules.items():
|
|
rule_features = rule.extract_all_features()
|
|
|
|
if not len(rule_features):
|
|
continue
|
|
count += 1
|
|
# Checks if any features match between existing and new rule.
|
|
if any(feature in rule_features for feature in new_rule_features):
|
|
overlapping_rules.append(rule_name)
|
|
|
|
result = {"overlapping_rules": overlapping_rules, "count": count}
|
|
return result
|
|
|
|
|
|
def main():
|
|
parser = argparse.ArgumentParser(description="Find overlapping features in Capa rules.")
|
|
|
|
parser.add_argument("rules", type=str, action="append", help="Path to rules")
|
|
parser.add_argument("new_rule", type=str, help="Path to new rule")
|
|
|
|
args = parser.parse_args()
|
|
|
|
new_rule_path = args.new_rule
|
|
rules_path = [Path(rule) for rule in args.rules]
|
|
|
|
result = find_overlapping_rules(new_rule_path, rules_path)
|
|
|
|
print("\nNew rule path : %s" % new_rule_path)
|
|
print("Number of rules checked : %s " % result["count"])
|
|
if result["overlapping_rules"]:
|
|
print("Paths to overlapping rules : ")
|
|
for r in result["overlapping_rules"]:
|
|
print("- %s" % r)
|
|
else:
|
|
print("Paths to overlapping rules : None")
|
|
print("Number of rules containing same features : %s" % len(result["overlapping_rules"]))
|
|
print("\n")
|
|
|
|
return len(result["overlapping_rules"])
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|