mirror of
https://github.com/mandiant/capa.git
synced 2025-12-10 23:00:37 -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.
46 lines
1.9 KiB
Python
46 lines
1.9 KiB
Python
# Copyright 2024 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 itertools
|
|
|
|
from capa.features.address import ThreadAddress, ProcessAddress
|
|
from capa.features.extractors.drakvuf.models import Call, DrakvufReport
|
|
|
|
|
|
def index_calls(report: DrakvufReport) -> dict[ProcessAddress, dict[ThreadAddress, list[Call]]]:
|
|
# this method organizes calls into processes and threads, and then sorts them based on
|
|
# timestamp so that we can address individual calls per index (CallAddress requires call index)
|
|
result: dict[ProcessAddress, dict[ThreadAddress, list[Call]]] = {}
|
|
for call in itertools.chain(report.syscalls, report.apicalls):
|
|
if call.pid == 0:
|
|
# DRAKVUF captures api/native calls from all processes running on the system.
|
|
# we ignore the pid 0 since it's a system process and it's unlikely for it to
|
|
# be hijacked or so on, in addition to capa addresses not supporting null pids
|
|
continue
|
|
proc_addr = ProcessAddress(pid=call.pid, ppid=call.ppid)
|
|
thread_addr = ThreadAddress(process=proc_addr, tid=call.tid)
|
|
if proc_addr not in result:
|
|
result[proc_addr] = {}
|
|
if thread_addr not in result[proc_addr]:
|
|
result[proc_addr][thread_addr] = []
|
|
|
|
result[proc_addr][thread_addr].append(call)
|
|
|
|
for proc, threads in result.items():
|
|
for thread in threads:
|
|
result[proc][thread].sort(key=lambda call: call.timestamp)
|
|
|
|
return result
|