Added code to remove pycache from splunklib installation directory be…

…fore generating PR.

README.md

@@ -304,6 +304,13 @@ def stream_events(input_script: smi.Script, inputs: smi.InputDefinition, event_w
 * required: false
 * default: "bin"
 
+#### is_remove_pyc_from_splunklib_dir
+* description: "Remove `.pyc` files and `__pycache__` directory from splunk-python-sdk (splunklib) installation path before generating Pull Request. Do not turn this off unless you are facing any issues explicitly."
+* required: false
+* default: true
+
+
+
 
 
 ## Troubleshooting
@@ -328,6 +335,7 @@ def stream_events(input_script: smi.Script, inputs: smi.InputDefinition, event_w
 
 ### v4.1
 * Added `splunk_python_sdk_install_path` parameter for `splunk_python_sdk` utility. Default value is still `bin` folder, but now user can change based on their needs.
+* Avoid `.pyc` files and `__pycache__` files getting into `splunk_python_sdk` installation folder and getting into Pull Request by default. You can turn this off with `is_remove_pyc_from_splunklib_dir` parameter.
 
 
 ### v4

action.yml

@@ -59,6 +59,12 @@ inputs:
     required: false
     default: "bin"
 
+  is_remove_pyc_from_splunklib_dir:
+    description: "Remove `.pyc` files and `__pycache__` directory from splunk-python-sdk (splunklib) installation path before generating Pull Request. Do not turn this off unless you are facing any issues explicitly."
+    required: false
+    default: true
+
+
 outputs:
   stdout:
     description: "Program stdout"
@@ -98,6 +104,7 @@ runs:
         echo "logger_log_files_prefix -> ${{inputs.logger_log_files_prefix}}"
         echo "logger_sourcetype -> ${{inputs.logger_sourcetype}}"
         echo "splunk_python_sdk_install_path -> ${{inputs.splunk_python_sdk_install_path}}"
+        echo "is_remove_pyc_from_splunklib_dir -> ${{inputs.is_remove_pyc_from_splunklib_dir}}"
 
     - name: "Install Python"
       uses: actions/setup-python@v5
@@ -125,6 +132,7 @@ runs:
         SPLUNK_logger_log_files_prefix: ${{inputs.logger_log_files_prefix}}
         SPLUNK_logger_sourcetype: ${{inputs.logger_sourcetype}}
         SPLUNK_splunk_python_sdk_install_path: ${{inputs.splunk_python_sdk_install_path}}
+        SPLUNK_is_remove_pyc_from_splunklib_dir: ${{inputs.is_remove_pyc_from_splunklib_dir}}
       run: |
         python -u ${{ github.action_path }}/src/main.py
 

src/utilities/splunk_sdk_python/__init__.py

@@ -1,6 +1,7 @@
 
 import os
 import re
+import shutil
 
 import helpers.github_action_utils as utils
 from utilities.base_utility import BaseUtility
@@ -19,6 +20,16 @@ def _get_splunklib_version(self, file_path):
             utils.info("Error with getting the splunklib version.")
 
 
+    def remove_pycache(self, directory):
+        for root, dirs, files in os.walk(directory):
+            for file in files:
+                if file.endswith(".pyc"):
+                    os.remove(os.path.join(root, file))
+            for dir in dirs:
+                if dir == "__pycache__":
+                    shutil.rmtree(os.path.join(root, dir))
+
+
     def implement_utility(self):
         utils.info("Adding SplunkPythonSDKUtility")
 
@@ -27,6 +38,10 @@ def implement_utility(self):
         if not splunk_python_sdk_install_path or splunk_python_sdk_install_path == "NONE":
             splunk_python_sdk_install_path = "bin"
 
+        is_remove_pyc_from_splunklib_dir = utils.str_to_boolean_default_true(
+            utils.get_input('is_remove_pyc_from_splunklib_dir'))
+        utils.info(f"is_remove_pyc_from_splunklib_dir: {is_remove_pyc_from_splunklib_dir}")
+
         folder_to_install_splunklib = os.path.join(
             self.app_write_dir, splunk_python_sdk_install_path)
 
@@ -60,6 +75,10 @@ def implement_utility(self):
             utils.execute_system_command(
                 f'pip install splunk-sdk --target "{folder_to_install_splunklib}"')
 
+        # Removing .pyc and __pycache__
+        if is_remove_pyc_from_splunklib_dir:
+            self.remove_pycache(folder_to_install_splunklib)
+
         new_version = self._get_splunklib_version(init_file)
         utils.info(f"New splunklib version = {new_version}")
 

tests/helper.py

@@ -18,7 +18,8 @@ def setup_action_yml(test_app_repo,
                             current_branch="NONE",
                             logger_log_files_prefix="NONE",
                             logger_sourcetype="NONE",
-                            splunk_python_sdk_install_path="bin"):
+                            splunk_python_sdk_install_path="bin",
+                            is_remove_pyc_from_splunklib_dir="true"):
 
     app_dir_path = os.path.join(os.path.dirname(__file__), "test_app_repos", test_app_repo)
     print(f"TestIntegration.setup_action_yml_work -> app_dir_path={app_dir_path}")
@@ -39,6 +40,7 @@ def setup_action_yml(test_app_repo,
     os.environ["SPLUNK_logger_log_files_prefix"] = logger_log_files_prefix
     os.environ["SPLUNK_logger_sourcetype"] = logger_sourcetype
     os.environ["SPLUNK_splunk_python_sdk_install_path"] = splunk_python_sdk_install_path
+    os.environ["SPLUNK_is_remove_pyc_from_splunklib_dir"] = is_remove_pyc_from_splunklib_dir
 
     try:
         yield

tests/test_utility_python_sdk.py

@@ -6,6 +6,17 @@
 from helpers import github_action_utils as utils
 
 
+def check_no_pycache(folder_path):
+    for root, dirs, files in os.walk(folder_path):
+        for file in files:
+            if file.endswith(".pyc"):
+                return False
+        for dir in dirs:
+            if dir == "__pycache__":
+                return False
+    return True
+
+
 def test_splunk_sdk_utility_installed_new():
     with get_temp_directory() as temp_dir:
         sdk_utility = SplunkPythonSDKUtility("nothing", temp_dir)
@@ -16,16 +27,16 @@ def test_splunk_sdk_utility_installed_new():
         splunklib_dir = os.path.join(folder_path, 'splunklib')
         init_file = os.path.join(splunklib_dir, '__init__.py')
 
-        print(f"init_file={init_file}")
-
         assert result == init_file
         assert os.path.exists(init_file)
+        assert check_no_pycache(folder_path)
 
 
 def test_splunk_sdk_utility_installed_new_2():
     with get_temp_directory() as temp_dir:
         with setup_temporary_env_vars({
-            "SPLUNK_splunk_python_sdk_install_path": "lib", 
+            "SPLUNK_splunk_python_sdk_install_path": "lib",
+            "SPLUNK_is_remove_pyc_from_splunklib_dir": "true"
         }):
             sdk_utility = SplunkPythonSDKUtility("nothing", temp_dir)
             result = sdk_utility.implement_utility()
@@ -35,10 +46,9 @@ def test_splunk_sdk_utility_installed_new_2():
             splunklib_dir = os.path.join(folder_path, 'splunklib')
             init_file = os.path.join(splunklib_dir, '__init__.py')
 
-            print(f"init_file={init_file}")
-
             assert result == init_file
             assert os.path.exists(init_file)
+            assert check_no_pycache(folder_path)
 
 
 def test_splunk_sdk_utility_upgraded_existing():
@@ -66,6 +76,7 @@ def test_splunk_sdk_utility_upgraded_existing():
         # Validate the result
         assert os.path.exists(init_file)
         assert result == init_file
+        assert check_no_pycache(folder_path)
 
 
 def test_splunk_sdk_utility_upgraded_existing_2():
@@ -96,6 +107,7 @@ def test_splunk_sdk_utility_upgraded_existing_2():
             # Validate the result
             assert os.path.exists(init_file)
             assert result == init_file
+            assert check_no_pycache(folder_path)
 
 
 def test_splunk_sdk_utility_skipped_due_to_existing_and_same_version():
@@ -118,6 +130,7 @@ def test_splunk_sdk_utility_skipped_due_to_existing_and_same_version():
         # Validate the result
         assert not os.path.exists(os.path.join(folder_path, 'splunk-sdk'))
         assert result is None
+        assert check_no_pycache(folder_path)
 
 
 def test_splunk_sdk_utility_skipped_due_to_existing_and_same_version_2():
@@ -143,29 +156,34 @@ def test_splunk_sdk_utility_skipped_due_to_existing_and_same_version_2():
             # Validate the result
             assert not os.path.exists(os.path.join(folder_path, 'splunk-sdk'))
             assert result is None
+            assert check_no_pycache(folder_path)
 
 
 def test_splunk_sdk_utility_error_upgrading_existing():
     with get_temp_directory() as temp_dir:
-        # Prepare the temporary directory
-        folder_path = os.path.join(temp_dir, 'bin')
-        os.makedirs(folder_path)
-        splunklib_dir = os.path.join(folder_path, 'splunklib')
-        os.makedirs(splunklib_dir)
-        init_file = os.path.join(splunklib_dir, '__init__.py')
-        with open(init_file, 'w') as f:
-            f.write('__version_info__ = "1.0.0"')
+        with setup_temporary_env_vars({
+            "SPLUNK_is_remove_pyc_from_splunklib_dir": "true",
+        }):
+            # Prepare the temporary directory
+            folder_path = os.path.join(temp_dir, 'bin')
+            os.makedirs(folder_path)
+            splunklib_dir = os.path.join(folder_path, 'splunklib')
+            os.makedirs(splunklib_dir)
+            init_file = os.path.join(splunklib_dir, '__init__.py')
+            with open(init_file, 'w') as f:
+                f.write('__version_info__ = "1.0.0"')
 
-        # Initialize SplunkPythonSDKUtility instance
-        sdk_utility = SplunkPythonSDKUtility("nothing", temp_dir)
+            # Initialize SplunkPythonSDKUtility instance
+            sdk_utility = SplunkPythonSDKUtility("nothing", temp_dir)
 
-        # Call implement_utility function with failing upgrade
-        with patch.object(SplunkPythonSDKUtility, '_get_splunklib_version', return_value="2.2.2"):
-            with patch.object(utils, 'execute_system_command', return_value=(1, '')):
-                result = sdk_utility.implement_utility()
+            # Call implement_utility function with failing upgrade
+            with patch.object(SplunkPythonSDKUtility, '_get_splunklib_version', return_value="2.2.2"):
+                with patch.object(utils, 'execute_system_command', return_value=(1, '')):
+                    result = sdk_utility.implement_utility()
 
-        # Validate the result
-        assert result is None
+            # Validate the result
+            assert result is None
+            assert check_no_pycache(folder_path)
 
 
 def test_splunk_sdk_utility_error_upgrading_existing_2():
@@ -192,3 +210,4 @@ def test_splunk_sdk_utility_error_upgrading_existing_2():
 
             # Validate the result
             assert result is None
+            assert check_no_pycache(folder_path)