Add pre-commit hook to check for secrets (#156)

* add hub files from Samples/azure-ai and update README

* Add secrets check to pre-commit

* Remove unrelated changes

* Don't run secrets check on remote, only local check

Author: diondrapeck

.github/workflows/pre-commit.yml

@@ -20,4 +20,4 @@ jobs:
           python-version: "3.8"
       - run: pip install -r dev-requirements.txt
       - name: Run Pre-Commit
-        run: pre-commit run --all-files
+        run: pre-commit run --all-files --config .pre-commit-config-remote.yaml

.pre-commit-config-remote.yaml

@@ -0,0 +1,36 @@
+# See https://pre-commit.com for more information
+# See https://pre-commit.com/hooks.html for more hooks
+repos:
+-   repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v3.2.0
+    hooks:
+    -   id: check-added-large-files
+-   repo: local
+    hooks:
+    - id: nb-clean
+      name: nb-clean
+      description: "Clean Jupyter notebooks of outputs, metadata, and empty cells, with Git integration"
+      entry: tox -qqq run -e nb-clean  -- clean
+      require_serial: true
+      language: python
+      types_or: [jupyter]
+      minimum_pre_commit_version: 2.9.2
+    - id: ruff
+      name: ruff
+      description: "Run 'ruff' for extremely fast Python linting"
+      entry: tox -qqq run -e ruff -- check --force-exclude
+      language: python
+      types_or: [python, pyi, jupyter]
+      require_serial: true
+      additional_dependencies: []
+      minimum_pre_commit_version: "2.9.2"
+      args: ["--fix", "--exit-non-zero-on-fix", "--exclude", "detect_azure_secrets.py"]
+    - id: black
+      name: black
+      description: "Black: The uncompromising Python code formatter"
+      minimum_pre_commit_version: 2.9.2
+      require_serial: true
+      types_or: [python, pyi, jupyter]
+      entry: python
+      language: system
+      args: ["-m", "tox", "-qqq", "run", "-e", "black", "--"]

.pre-commit-config.yaml

@@ -24,7 +24,7 @@ repos:
       require_serial: true
       additional_dependencies: []
       minimum_pre_commit_version: "2.9.2"
-      args: ["--fix", "--exit-non-zero-on-fix"]
+      args: ["--fix", "--exit-non-zero-on-fix", "--exclude", "detect_azure_secrets.py"]
     - id: black
       name: black
       description: "Black: The uncompromising Python code formatter"
@@ -34,3 +34,8 @@ repos:
       entry: python
       language: system
       args: ["-m", "tox", "-qqq", "run", "-e", "black", "--"]
+    - id: detect-azure-secrets-custom
+      name: Detect Azure Secrets
+      entry: python detect_azure_secrets.py
+      language: python
+      types: [file]

detect_azure_secrets.py

@@ -0,0 +1,64 @@
+import re
+import sys
+import json
+import os
+from typing import Union
+
+
+SECRET_PATTERNS = [
+    re.compile(r'[\'"]?subscription_id[\'"]?\s*[:=]\s*[\'"][0-9a-f\-]{36}[\'"]', re.IGNORECASE),
+    re.compile(r'[\'"]?resource_group_name[\'"]?\s*[:=]\s*[\'"][a-zA-Z0-9\-_]+[\'"]', re.IGNORECASE),
+    re.compile(r'[\'"]?project_name[\'"]?\s*[:=]\s*[\'"][a-zA-Z0-9\-_]+[\'"]', re.IGNORECASE),
+    re.compile(r'[\'"]?api_key[\'"]?\s*[:=]\s*[\'"][A-Za-z0-9\-_]{40,}[\'"]', re.IGNORECASE),
+    re.compile(
+        r'[\'"]?azure_endpoint[\'"]?\s*[:=]\s*[\'"]https:\/\/[a-zA-Z0-9\-\.]+\.azure\.com[\/a-zA-Z0-9\.\-]*[\'"]',
+        re.IGNORECASE,
+    ),
+    re.compile(r'export\s+[A-Z_][A-Z0-9_]*\s*=\s*["\'][^"\']+["\']', re.IGNORECASE),
+    re.compile(r'os\.environ\["\s*[A-Za-z0-9_]*(API_KEY|ENDPOINT)[A-Za-z0-9_]*\s*"\]', re.IGNORECASE),
+]
+
+
+def check_ipynb_for_secrets(filename: Union[str, os.PathLike]) -> bool:
+    """Jupyter notebooks can't be parsed directly - need to convert to JSON first"""
+    try:
+        with open(filename, "r", encoding="utf-8") as file:
+            notebook_data = json.load(file)
+            failed = False
+            for cell in notebook_data.get("cells", []):
+                if cell["cell_type"] == "code":
+                    for line_number, line in enumerate(cell["source"], start=1):
+                        for pattern in SECRET_PATTERNS:
+                            if pattern.search(line):
+                                print(f"Secret detected in {filename} on line {line_number}: {line.strip()}")
+                                failed = True
+            return failed
+    except (UnicodeDecodeError, json.JSONDecodeError) as e:
+        print(f"Failed to read {filename}. Skipping secrets check. Error: {e}")
+        return True
+
+
+def main():
+    failed = False
+
+    for filename in sys.argv[1:]:
+        if filename.endswith((".py", ".yaml", ".yml", ".md")):
+            try:
+                with open(filename, "r", encoding="utf-8") as file:
+                    for line_number, line in enumerate(file, start=1):
+                        for pattern in SECRET_PATTERNS:
+                            if pattern.search(line):
+                                print(f"Secret detected in {filename} on line {line_number}: {line.strip()}")
+                                failed = True
+            except UnicodeDecodeError:
+                print(f"Failed to read {filename}. Skipping secrets check.")
+        elif filename.endswith(".ipynb"):
+            if check_ipynb_for_secrets(filename):
+                failed = True
+
+    if failed:
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()