From 80c7f456c1653a515c391634a59e376686d4d5fe Mon Sep 17 00:00:00 2001
From: Jordan Storms <jordan.storms@datadoghq.com>
Date: Mon, 4 Oct 2021 11:59:34 -0400
Subject: [PATCH] Add pre commit configuration (#96)

* add pre-commit

* change py to go file types for pre-commit

* test

* another test

* allow pull_requests to trigger git workflow
---
 .github/.git-hooks/detect-api-keys.py | 73 +++++++++++++++++++++++++++
 .github/workflows/build.yml           |  2 +-
 .pre-commit-config.yaml               | 13 +++++
 3 files changed, 87 insertions(+), 1 deletion(-)
 create mode 100755 .github/.git-hooks/detect-api-keys.py
 create mode 100644 .pre-commit-config.yaml

diff --git a/.github/.git-hooks/detect-api-keys.py b/.github/.git-hooks/detect-api-keys.py
new file mode 100755
index 00000000..8d4092a9
--- /dev/null
+++ b/.github/.git-hooks/detect-api-keys.py
@@ -0,0 +1,73 @@
+#!/usr/bin/env python
+from __future__ import print_function
+
+import argparse
+import re
+import sys
+
+
+def detect_aws_access_key(line):
+    match = re.search(r"(?<![A-Z0-9])[A-Z0-9]{20}(?![A-Z0-9])", line)
+    return match, "AWS access key"
+
+
+def detect_aws_secret_key(line):
+    match = re.search(r"(?<![A-Za-z0-9/+=])[A-Za-z0-9/+=]{40}(?![A-Za-z0-9/+=])", line)
+    return match, "AWS secret key"
+
+
+def detect_dd_api_key(line):
+    match = re.search(r"(?<![a-fA-F0-9])[a-fA-F0-9]{32}(?![a-fA-F0-9])", line)
+    return match, "Datadog API key"
+
+
+def detect_dd_app_key(line):
+    match = re.search(r"(?<![a-fA-F0-9])[a-fA-F0-9]{40}(?![a-fA-F0-9])", line)
+    return match, "Datadog app key"
+
+
+def key_found_message(args):
+    return (
+        "\033[91m"
+        "Potential {} found in {} at line {} and column {}. "
+        "Please remove the key before committing these changes."
+        "\033[0m".format(*args)
+    )
+
+
+def main(argv=None):
+    parser = argparse.ArgumentParser()
+    parser.add_argument("filenames", nargs="*", help="Filenames to check.")
+    args = parser.parse_args(argv)
+
+    # add or remove functions here
+    functions_to_run = [
+        detect_aws_access_key,
+        detect_aws_secret_key,
+        detect_dd_api_key,
+        detect_dd_app_key,
+    ]
+
+    files_with_key = []
+
+    for filename in args.filenames:
+        with open(filename, "r") as f:
+            content = f.readlines()
+            f.close()
+
+        for i, line in enumerate(content):
+            for func in functions_to_run:
+                match, name = func(line)
+                if match != None:
+                    files_with_key.append((name, filename, i + 1, match.end()))
+
+    if files_with_key:
+        for file in files_with_key:
+            print(key_found_message(file))
+        return 1
+    else:
+        return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main())
diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml
index b866244b..bf09ed4c 100644
--- a/.github/workflows/build.yml
+++ b/.github/workflows/build.yml
@@ -1,6 +1,6 @@
 name: build
 
-on: [push]
+on: [push, pull_request]
 
 jobs:
   lint:
diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml
new file mode 100644
index 00000000..043e0658
--- /dev/null
+++ b/.pre-commit-config.yaml
@@ -0,0 +1,13 @@
+repos:
+  - repo: git@github.com:pre-commit/pre-commit-hooks
+    rev: v2.1.0
+    hooks:
+      - id: check-merge-conflict
+        files: \.go$
+  - repo: local
+    hooks:
+      - id: detect-api-keys
+        name: detect-api-keys
+        description: Checks for AWS or Datadog API keys
+        entry: ".github/.git-hooks/detect-api-keys.py"
+        language: python