[Security] Add Bandit (#795)

这个提交包含在:
Simon Alibert
2025-03-01 19:19:26 +01:00
提交者 GitHub
父节点 9c1a893ee3
当前提交 8861546ad8
共有 6 个文件被更改,包括 67 次插入 和 38 次删除

查看文件

@ -2,6 +2,7 @@ exclude: ^(tests/data)
default_language_version: default_language_version:
python: python3.10 python: python3.10
repos: repos:
##### Style / Misc. #####
- repo: https://github.com/pre-commit/pre-commit-hooks - repo: https://github.com/pre-commit/pre-commit-hooks
rev: v5.0.0 rev: v5.0.0
hooks: hooks:
@ -14,7 +15,7 @@ repos:
- id: end-of-file-fixer - id: end-of-file-fixer
- id: trailing-whitespace - id: trailing-whitespace
- repo: https://github.com/crate-ci/typos - repo: https://github.com/crate-ci/typos
rev: v1.29.10 rev: v1.30.0
hooks: hooks:
- id: typos - id: typos
args: [--force-exclude] args: [--force-exclude]
@ -23,16 +24,24 @@ repos:
hooks: hooks:
- id: pyupgrade - id: pyupgrade
- repo: https://github.com/astral-sh/ruff-pre-commit - repo: https://github.com/astral-sh/ruff-pre-commit
rev: v0.9.6 rev: v0.9.9
hooks: hooks:
- id: ruff - id: ruff
args: [--fix] args: [--fix]
- id: ruff-format - id: ruff-format
##### Security #####
- repo: https://github.com/gitleaks/gitleaks - repo: https://github.com/gitleaks/gitleaks
rev: v8.23.3 rev: v8.24.0
hooks: hooks:
- id: gitleaks - id: gitleaks
- repo: https://github.com/woodruffw/zizmor-pre-commit - repo: https://github.com/woodruffw/zizmor-pre-commit
rev: v1.3.1 rev: v1.4.1
hooks: hooks:
- id: zizmor - id: zizmor
- repo: https://github.com/PyCQA/bandit
rev: 1.8.3
hooks:
- id: bandit
args: ["-c", "pyproject.toml"]
additional_dependencies: ["bandit[toml]"]

查看文件

@ -17,6 +17,7 @@ import logging
import os import os
import os.path as osp import os.path as osp
import platform import platform
import subprocess
from copy import copy from copy import copy
from datetime import datetime, timezone from datetime import datetime, timezone
from pathlib import Path from pathlib import Path
@ -165,23 +166,31 @@ def capture_timestamp_utc():
def say(text, blocking=False): def say(text, blocking=False):
# Check if mac, linux, or windows. system = platform.system()
if platform.system() == "Darwin":
cmd = f'say "{text}"'
if not blocking:
cmd += " &"
elif platform.system() == "Linux":
cmd = f'spd-say "{text}"'
if blocking:
cmd += " --wait"
elif platform.system() == "Windows":
# TODO(rcadene): Make blocking option work for Windows
cmd = (
'PowerShell -Command "Add-Type -AssemblyName System.Speech; '
f"(New-Object System.Speech.Synthesis.SpeechSynthesizer).Speak('{text}')\""
)
os.system(cmd) if system == "Darwin":
cmd = ["say", text]
elif system == "Linux":
cmd = ["spd-say", text]
if blocking:
cmd.append("--wait")
elif system == "Windows":
cmd = [
"PowerShell",
"-Command",
"Add-Type -AssemblyName System.Speech; "
f"(New-Object System.Speech.Synthesis.SpeechSynthesizer).Speak('{text}')",
]
else:
raise RuntimeError("Unsupported operating system for text-to-speech.")
if blocking:
subprocess.run(cmd, check=True)
else:
subprocess.Popen(cmd, creationflags=subprocess.CREATE_NO_WINDOW if system == "Windows" else 0)
def log_say(text, play_sounds, blocking=False): def log_say(text, play_sounds, blocking=False):

查看文件

@ -454,7 +454,7 @@ def _compile_episode_data(
@parser.wrap() @parser.wrap()
def eval(cfg: EvalPipelineConfig): def eval_main(cfg: EvalPipelineConfig):
logging.info(pformat(asdict(cfg))) logging.info(pformat(asdict(cfg)))
# Check device is available # Check device is available
@ -499,4 +499,4 @@ def eval(cfg: EvalPipelineConfig):
if __name__ == "__main__": if __name__ == "__main__":
init_logging() init_logging()
eval() eval_main()

查看文件

@ -194,7 +194,7 @@ def run_server(
] ]
response = requests.get( response = requests.get(
f"https://huggingface.co/datasets/{repo_id}/resolve/main/meta/episodes.jsonl" f"https://huggingface.co/datasets/{repo_id}/resolve/main/meta/episodes.jsonl", timeout=5
) )
response.raise_for_status() response.raise_for_status()
# Split into lines and parse each line as JSON # Split into lines and parse each line as JSON
@ -318,7 +318,9 @@ def get_episode_language_instruction(dataset: LeRobotDataset, ep_index: int) ->
def get_dataset_info(repo_id: str) -> IterableNamespace: def get_dataset_info(repo_id: str) -> IterableNamespace:
response = requests.get(f"https://huggingface.co/datasets/{repo_id}/resolve/main/meta/info.json") response = requests.get(
f"https://huggingface.co/datasets/{repo_id}/resolve/main/meta/info.json", timeout=5
)
response.raise_for_status() # Raises an HTTPError for bad responses response.raise_for_status() # Raises an HTTPError for bad responses
dataset_info = response.json() dataset_info = response.json()
dataset_info["repo_id"] = repo_id dataset_info["repo_id"] = repo_id

查看文件

@ -111,10 +111,19 @@ exclude = [
"venv", "venv",
] ]
[tool.ruff.lint] [tool.ruff.lint]
select = ["E4", "E7", "E9", "F", "I", "N", "B", "C4", "SIM"] select = ["E4", "E7", "E9", "F", "I", "N", "B", "C4", "SIM"]
[tool.bandit]
exclude_dirs = [
"tests",
"benchmarks",
"lerobot/common/datasets/push_dataset_to_hub",
"lerobot/common/datasets/v2/convert_dataset_v1_to_v2",
"lerobot/common/policies/pi0/conversion_scripts",
"lerobot/scripts/push_dataset_to_hub.py",
]
skips = ["B101", "B311", "B404", "B603"]
[tool.typos] [tool.typos]
default.extend-ignore-re = [ default.extend-ignore-re = [