feat(telemetry): Unique User IDs in kedro-telemetry - merge only for kedro-telemetry release 0.4.0 #596
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,11 +1,11 @@ | ||
| """Kedro Telemetry plugin for collecting Kedro usage data.""" | ||
|
|
||
| import hashlib | ||
| import json | ||
| import logging | ||
| import os | ||
| import sys | ||
| import uuid | ||
| from copy import deepcopy | ||
| from datetime import datetime | ||
| from pathlib import Path | ||
|
|
@@ -15,6 +15,7 @@ | |
| import requests | ||
| import toml | ||
| import yaml | ||
| from appdirs import user_config_dir | ||
|
There was a problem hiding this comment.
yes, we added it to the dependencies list |
||
| 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 +42,7 @@ | |
| "BUILDKITE", # https://buildkite.com/docs/pipelines/environment-variables | ||
| } | ||
| TIMESTAMP_FORMAT = "%Y-%m-%dT%H:%M:%S.%fZ" | ||
| CONFIG_FILENAME = "telemetry.toml" | ||
|
|
||
| logger = logging.getLogger(__name__) | ||
|
|
||
|
|
@@ -49,15 +51,45 @@ def _hash(string: str) -> str: | |
| return hashlib.sha512(bytes(string, encoding="utf8")).hexdigest() | ||
|
|
||
|
|
||
| def _get_or_create_uuid() -> str: | ||
| """ | ||
| Reads a UUID from a configuration file or generates and saves a new one if not present. | ||
| """ | ||
| config_path = user_config_dir("kedro") | ||
astrojuanlu marked this conversation as resolved.
Show resolved
Hide resolved
|
||
| full_path = os.path.join(config_path, CONFIG_FILENAME) | ||
|
|
||
| try: | ||
| if os.path.exists(full_path): | ||
| with open(full_path) as f: | ||
| config = toml.load(f) | ||
|
|
||
| if "telemetry" in config and "uuid" in config["telemetry"]: | ||
| return uuid.UUID(config["telemetry"]["uuid"]).hex | ||
|
|
||
| # Generate a new UUID and save it to the config file | ||
| new_uuid = _generate_new_uuid(full_path) | ||
|
|
||
| return new_uuid | ||
|
|
||
| except Exception as e: | ||
| logging.error(f"Failed to retrieve UUID: {e}") | ||
| return "" | ||
|
|
||
|
|
||
| def _generate_new_uuid(full_path: str) -> str: | ||
| try: | ||
| config = {} | ||
| config["telemetry"] = {} | ||
| new_uuid = uuid.uuid4().hex | ||
| config["telemetry"]["uuid"] = new_uuid | ||
|
|
||
| os.makedirs(os.path.dirname(full_path), exist_ok=True) | ||
| with open(full_path, "w") as f: | ||
| toml.dump(config, f) | ||
|
|
||
| return new_uuid | ||
| except Exception as e: | ||
| logging.error(f"Failed to create UUID: {e}") | ||
| return "" | ||
|
|
||
|
|
||
|
|
@@ -90,17 +122,17 @@ def before_command_run( | |
| main_command = masked_command_args[0] if masked_command_args else "kedro" | ||
|
There was a problem hiding this comment. I can't comment on the line above since it hasn't been changed but could line 117 be changed to - |
||
|
|
||
| logger.debug("You have opted into product usage analytics.") | ||
| user_uuid = _get_or_create_uuid() | ||
| project_properties = _get_project_properties( | ||
| user_uuid, project_metadata.project_path | ||
| ) | ||
| cli_properties = _format_user_cli_data( | ||
| project_properties, masked_command_args | ||
| ) | ||
|
|
||
| _send_heap_event( | ||
| event_name=f"Command run: {main_command}", | ||
| identity=user_uuid, | ||
| properties=cli_properties, | ||
| ) | ||
|
|
||
|
|
@@ -109,7 +141,7 @@ def before_command_run( | |
| generic_properties["main_command"] = main_command | ||
| _send_heap_event( | ||
| event_name="CLI command", | ||
| identity=user_uuid, | ||
| properties=generic_properties, | ||
| ) | ||
| except Exception as exc: | ||
|
|
@@ -141,16 +173,16 @@ def after_catalog_created(self, catalog): | |
| logger.debug("You have opted into product usage analytics.") | ||
|
|
||
| default_pipeline = pipelines.get("__default__") # __default__ | ||
| user_uuid = _get_or_create_uuid() | ||
|
|
||
| project_properties = _get_project_properties(user_uuid, self.project_path) | ||
|
|
||
| project_statistics_properties = _format_project_statistics_data( | ||
| project_properties, catalog, default_pipeline, pipelines | ||
| ) | ||
| _send_heap_event( | ||
| event_name="Kedro Project Statistics", | ||
| identity=user_uuid, | ||
| properties=project_statistics_properties, | ||
| ) | ||
|
|
||
|
|
@@ -163,10 +195,10 @@ def _is_known_ci_env(known_ci_env_var_keys=KNOWN_CI_ENV_VAR_KEYS): | |
| return any(os.getenv(key) for key in known_ci_env_var_keys) | ||
|
|
||
|
|
||
| def _get_project_properties(user_uuid: str, project_path: str) -> Dict: | ||
| hashed_package_name = _hash(PACKAGE_NAME) if PACKAGE_NAME else "undefined" | ||
| properties = { | ||
| "username": user_uuid, | ||
| "package_name": hashed_package_name, | ||
| "project_version": KEDRO_VERSION, | ||
| "telemetry_version": TELEMETRY_VERSION, | ||
|
|
||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
The heading will say the release number anyway