Add prek pre-commit hooks and CI

.github/workflows/prek-check.yml

@@ -0,0 +1,50 @@
+# SPDX-FileCopyrightText: © 2025 Phala Network <dstack@phala.network>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+name: Prek checks
+
+on:
+  push:
+    branches: [ master, next, dev-* ]
+  pull_request:
+    branches: [ master, next, dev-* ]
+
+permissions:
+  contents: read
+
+jobs:
+  prek:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        fetch-depth: 0
+
+    - name: Install Rust
+      uses: dtolnay/rust-toolchain@master
+      with:
+        toolchain: 1.92.0
+        components: rustfmt
+
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: '3.12'
+
+    - name: Set up Go
+      uses: actions/setup-go@v5
+      with:
+        go-version: '1.22'
+
+    - name: Install prek
+      run: pip install prek
+
+    - name: Run prek checks (PR)
+      if: github.event_name == 'pull_request'
+      run: prek run --from-ref ${{ github.event.pull_request.base.sha }} --to-ref ${{ github.event.pull_request.head.sha }} --show-diff-on-failure
+
+    - name: Run prek checks (push)
+      if: github.event_name == 'push'
+      run: prek run --from-ref ${{ github.event.before }} --to-ref ${{ github.event.after }} --show-diff-on-failure

prek.toml

@@ -0,0 +1,72 @@
+# SPDX-FileCopyrightText: © 2025 Phala Network <dstack@phala.network>
+#
+# SPDX-License-Identifier: Apache-2.0
+
+# =============================================================================
+# prek configuration for dstack
+# =============================================================================
+
+# --- General hooks (trailing whitespace, file checks, etc.) ---
+[[repos]]
+repo = "https://github.com/pre-commit/pre-commit-hooks"
+rev = "v5.0.0"
+hooks = [
+    { id = "trailing-whitespace", args = ["--markdown-linebreak-ext=md"] },
+    { id = "end-of-file-fixer" },
+    { id = "check-yaml", args = ["--allow-multiple-documents"], exclude = "gateway/templates/" },
+    { id = "check-toml" },
+    { id = "check-json" },
+    { id = "check-merge-conflict" },
+    { id = "check-added-large-files", args = ["--maxkb=500"] },
+    { id = "check-symlinks" },
+    { id = "mixed-line-ending", args = ["--fix=lf"] },
+]
+
+# --- Rust: rustfmt ---
+[[repos]]
+repo = "local"
+
+[[repos.hooks]]
+id = "cargo-fmt"
+name = "cargo fmt"
+entry = "cargo fmt --all"
+language = "system"
+types = ["rust"]
+pass_filenames = false
+
+# --- Python: ruff (lint + format) ---
+[[repos]]
+repo = "https://github.com/astral-sh/ruff-pre-commit"
+rev = "v0.11.4"
+hooks = [
+    { id = "ruff", args = ["--fix", "--select", "E,F,I,D", "--ignore", "D203,D213,E501"] },
+    { id = "ruff-format" },
+]
+
+# --- Go: go vet ---
+[[repos]]
+repo = "local"
+
+[[repos.hooks]]
+id = "go-vet"
+name = "go vet"
+entry = "bash -c 'cd sdk/go && go vet ./...'"
+language = "system"
+files = "sdk/go/.*\\.go$"
+pass_filenames = false
+
+# --- Shell: shellcheck ---
+[[repos]]
+repo = "https://github.com/shellcheck-py/shellcheck-py"
+rev = "v0.10.0.1"
+hooks = [
+    { id = "shellcheck" },
+]
+
+# --- Conventional commits (used by cliff.toml for changelog) ---
+[[repos]]
+repo = "https://github.com/compilerla/conventional-pre-commit"
+rev = "v4.1.0"
+hooks = [
+    { id = "conventional-pre-commit", stages = ["commit-msg"] },
+]

python/ct_monitor/ct_monitor.py

@@ -1,11 +1,13 @@
 # SPDX-FileCopyrightText: © 2024 Phala Network <dstack@phala.network>
 #
 # SPDX-License-Identifier: Apache-2.0
+"""Monitor certificate transparency logs for a given domain."""
 
+import argparse
 import sys
 import time
+
 import requests
-import argparse
 from cryptography import x509
 from cryptography.hazmat.backends import default_backend
 from cryptography.hazmat.primitives import serialization
@@ -14,38 +16,50 @@
 
 
 class PoisonedLog(Exception):
+    """Indicate a poisoned certificate transparency log entry."""
+
     pass
 
 
 class Monitor:
+    """Monitor certificate transparency logs for a domain."""
+
     def __init__(self, domain: str):
+        """Initialize the monitor with a validated domain."""
         if not self.validate_domain(domain):
             raise ValueError("Invalid domain name")
         self.domain = domain
         self.last_checked = None
 
     def get_logs(self, count: int = 100):
+        """Fetch recent certificate transparency log entries."""
         url = f"{BASE_URL}/?q={self.domain}&output=json&limit={count}"
         response = requests.get(url)
         return response.json()
-    
+
     def check_one_log(self, log: object):
+        """Fetch and inspect a single certificate log entry."""
         log_id = log["id"]
         cert_url = f"{BASE_URL}/?d={log_id}"
         cert_data = requests.get(cert_url).text
         # Extract PEM-encoded certificate
         import re
-        pem_match = re.search(r'-----BEGIN CERTIFICATE-----.*?-----END CERTIFICATE-----', cert_data, re.DOTALL)
+
+        pem_match = re.search(
+            r"-----BEGIN CERTIFICATE-----.*?-----END CERTIFICATE-----",
+            cert_data,
+            re.DOTALL,
+        )
         if pem_match:
             pem_cert = pem_match.group(0)
-            
+
             # Parse PEM certificate
             cert = x509.load_pem_x509_certificate(pem_cert.encode(), default_backend())
             # Extract the public key
             public_key = cert.public_key()
             pem_public_key = public_key.public_bytes(
                 encoding=serialization.Encoding.PEM,
-                format=serialization.PublicFormat.SubjectPublicKeyInfo
+                format=serialization.PublicFormat.SubjectPublicKeyInfo,
             )
             print("Public Key:")
             print(pem_public_key.hex())
@@ -62,18 +76,20 @@ def check_one_log(self, log: object):
             print("No valid certificate found in the response.")
 
     def check_new_logs(self):
+        """Check for new log entries since the last check."""
         logs = self.get_logs(count=10000)
         print("num logs", len(logs))
         for log in logs:
-            print(f"log id={log["id"]}")
+            print(f"log id={log['id']}")
             if log["id"] <= (self.last_checked or 0):
                 break
             self.check_one_log(log)
-            print('next')
+            print("next")
         if len(logs) > 0:
             self.last_checked = logs[0]["id"]
 
     def run(self):
+        """Run the monitor loop indefinitely."""
         print(f"Monitoring {self.domain}...")
         while True:
             try:
@@ -87,12 +103,12 @@ def run(self):
 
     @staticmethod
     def validate_domain(domain: str):
-        # ensure domain is a valid DNS domain
+        """Validate that the given string is a well-formed DNS domain name."""
         import re
 
         # Regular expression for validating domain names
         domain_regex = re.compile(
-            r'^(?:[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?\.)+[a-zA-Z]{2,}$'
+            r"^(?:[a-zA-Z0-9](?:[a-zA-Z0-9-]{0,61}[a-zA-Z0-9])?\.)+[a-zA-Z]{2,}$"
         )
 
         if not domain_regex.match(domain):
@@ -102,7 +118,10 @@ def validate_domain(domain: str):
 
 
 def main():
-    parser = argparse.ArgumentParser(description="Monitor certificate transparency logs")
+    """Parse arguments and start the certificate transparency monitor."""
+    parser = argparse.ArgumentParser(
+        description="Monitor certificate transparency logs"
+    )
     parser.add_argument("-d", "--domain", help="The domain to monitor")
     args = parser.parse_args()
     monitor = Monitor(args.domain)