feat(telemetry): Unique User IDs in kedro-telemetry - merge only for kedro-telemetry release 0.4.0

kedro-telemetry/RELEASE.md

@@ -1,4 +1,5 @@
 # Upcoming release
+* Updated the plugin to generate an unique UUID for each user of `kedro-telemetry`.
 
 # Release 0.3.2
 * Updated plugin to share if a project is being run in a ci environment.

kedro-telemetry/kedro_telemetry/plugin.py

@@ -1,11 +1,12 @@
 """Kedro Telemetry plugin for collecting Kedro usage data."""
 
-import getpass
 import hashlib
 import json
 import logging
 import os
 import sys
+import uuid
+from configparser import ConfigParser
 from copy import deepcopy
 from datetime import datetime
 from pathlib import Path
@@ -15,6 +16,7 @@
 import requests
 import toml
 import yaml
+from appdirs import user_config_dir
 from kedro import __version__ as KEDRO_VERSION
 from kedro.framework.cli.cli import KedroCLI
 from kedro.framework.cli.hooks import cli_hook_impl
@@ -41,6 +43,7 @@
     "BUILDKITE",  # https://buildkite.com/docs/pipelines/environment-variables
 }
 TIMESTAMP_FORMAT = "%Y-%m-%dT%H:%M:%S.%fZ"
+CONFIG_FILENAME = "telemetry.conf"
 
 logger = logging.getLogger(__name__)
 
@@ -49,15 +52,38 @@ def _hash(string: str) -> str:
     return hashlib.sha512(bytes(string, encoding="utf8")).hexdigest()
 
 
-def _get_hashed_username():
+def _get_or_create_uuid():
+    """
+    Reads a UUID from a configuration file or generates and saves a new one if not present.
+    """
+    config_path = user_config_dir("kedro")
+    full_path = os.path.join(config_path, CONFIG_FILENAME)
+    config = ConfigParser()
+
     try:
-        username = getpass.getuser()
-        return _hash(username)
-    except Exception as exc:
-        logger.warning(
-            "Something went wrong with getting the username. Exception: %s",
-            exc,
-        )
+        if os.path.exists(full_path):
+            config.read(full_path)
+
+            if config.has_section("telemetry") and "uuid" in config["telemetry"]:
+                try:
+                    return uuid.UUID(config["telemetry"]["uuid"]).hex
+                except ValueError:
+                    pass  # Invalid UUID found, will generate a new one
+
+        # Generate a new UUID and save it to the config file
+        if not config.has_section("telemetry"):
+            config.add_section("telemetry")
+        new_uuid = uuid.uuid4().hex
+        config.set("telemetry", "uuid", new_uuid)
+
+        os.makedirs(config_path, exist_ok=True)
+        with open(full_path, "w") as configfile:
+            config.write(configfile)
+
+        return new_uuid
+
+    except Exception as e:
+        logging.error(f"Failed to get or create UUID: {e}")
         return ""
 
 
@@ -90,7 +116,7 @@ def before_command_run(
             main_command = masked_command_args[0] if masked_command_args else "kedro"
 
             logger.debug("You have opted into product usage analytics.")
-            hashed_username = _get_hashed_username()
+            hashed_username = _get_or_create_uuid()
             project_properties = _get_project_properties(
                 hashed_username, project_metadata.project_path
             )
@@ -141,7 +167,7 @@ def after_catalog_created(self, catalog):
         logger.debug("You have opted into product usage analytics.")
 
         default_pipeline = pipelines.get("__default__")  # __default__
-        hashed_username = _get_hashed_username()
+        hashed_username = _get_or_create_uuid()
 
         project_properties = _get_project_properties(hashed_username, self.project_path)
 

kedro-telemetry/pyproject.toml

@@ -13,6 +13,7 @@ license = {text = "Apache Software License (Apache 2.0)"}
 dependencies = [
     "kedro>=0.18.0",
     "requests~=2.20",
+    "appdirs>=1.4.4",
 ]
 dynamic = ["readme", "version"]
 

kedro-telemetry/tests/test_plugin.py

@@ -131,7 +131,7 @@ def test_before_command_run(self, mocker, fake_metadata):
         mocked_anon_id.return_value = "digested"
         mocker.patch("kedro_telemetry.plugin.PACKAGE_NAME", "spaceflights")
         mocker.patch(
-            "kedro_telemetry.plugin._get_hashed_username",
+            "kedro_telemetry.plugin._get_or_create_uuid",
             return_value="hashed_username",
         )
 
@@ -177,7 +177,7 @@ def test_before_command_run_with_tools(self, mocker, fake_metadata):
         mocked_anon_id.return_value = "digested"
         mocker.patch("kedro_telemetry.plugin.PACKAGE_NAME", "spaceflights")
         mocker.patch(
-            "kedro_telemetry.plugin._get_hashed_username",
+            "kedro_telemetry.plugin._get_or_create_uuid",
             return_value="hashed_username",
         )
 
@@ -226,13 +226,17 @@ def test_before_command_run_empty_args(self, mocker, fake_metadata):
         mocked_anon_id = mocker.patch("kedro_telemetry.plugin._hash")
         mocked_anon_id.return_value = "digested"
         mocker.patch("kedro_telemetry.plugin.PACKAGE_NAME", "spaceflights")
+        mocker.patch(
+            "kedro_telemetry.plugin._get_or_create_uuid",
+            return_value="hashed_username",
+        )
 
         mocked_heap_call = mocker.patch("kedro_telemetry.plugin._send_heap_event")
         telemetry_hook = KedroTelemetryCLIHooks()
         command_args = []
         telemetry_hook.before_command_run(fake_metadata, command_args)
         expected_properties = {
-            "username": "digested",
+            "username": "hashed_username",
             "package_name": "digested",
             "project_version": kedro_version,
             "telemetry_version": TELEMETRY_VERSION,
@@ -249,12 +253,12 @@ def test_before_command_run_empty_args(self, mocker, fake_metadata):
         expected_calls = [
             mocker.call(
                 event_name="Command run: kedro",
-                identity="digested",
+                identity="hashed_username",
                 properties=expected_properties,
             ),
             mocker.call(
                 event_name="CLI command",
-                identity="digested",
+                identity="hashed_username",
                 properties=generic_properties,
             ),
         ]
@@ -296,7 +300,7 @@ def test_before_command_run_anonymous(self, mocker, fake_metadata):
         mocked_anon_id = mocker.patch("kedro_telemetry.plugin._hash")
         mocked_anon_id.return_value = "digested"
         mocker.patch("kedro_telemetry.plugin.PACKAGE_NAME", "spaceflights")
-        mocker.patch("getpass.getuser", side_effect=Exception)
+        mocker.patch("builtins.open", side_effect=Exception)
 
         mocked_heap_call = mocker.patch("kedro_telemetry.plugin._send_heap_event")
         telemetry_hook = KedroTelemetryCLIHooks()
@@ -474,7 +478,7 @@ def test_after_context_created_without_kedro_run(  # noqa: PLR0913
         mocker.patch("kedro_telemetry.plugin._hash", return_value="digested")
         mocker.patch("kedro_telemetry.plugin.PACKAGE_NAME", "spaceflights")
         mocker.patch(
-            "kedro_telemetry.plugin._get_hashed_username",
+            "kedro_telemetry.plugin._get_or_create_uuid",
             return_value="hashed_username",
         )
         mocked_heap_call = mocker.patch("kedro_telemetry.plugin._send_heap_event")
@@ -530,7 +534,7 @@ def test_after_context_created_with_kedro_run(  # noqa: PLR0913
         mocker.patch("kedro_telemetry.plugin._hash", return_value="digested")
         mocker.patch("kedro_telemetry.plugin.PACKAGE_NAME", "spaceflights")
         mocker.patch(
-            "kedro_telemetry.plugin._get_hashed_username",
+            "kedro_telemetry.plugin._get_or_create_uuid",
             return_value="hashed_username",
         )
         mocked_heap_call = mocker.patch("kedro_telemetry.plugin._send_heap_event")
@@ -589,7 +593,7 @@ def test_after_context_created_with_kedro_run_and_tools(  # noqa: PLR0913
         mocker.patch("kedro_telemetry.plugin._hash", return_value="digested")
         mocker.patch("kedro_telemetry.plugin.PACKAGE_NAME", "spaceflights")
         mocker.patch(
-            "kedro_telemetry.plugin._get_hashed_username",
+            "kedro_telemetry.plugin._get_or_create_uuid",
             return_value="hashed_username",
         )
         mocked_heap_call = mocker.patch("kedro_telemetry.plugin._send_heap_event")