Add basic call to scarf to get anonymous analytics (#1705)

There is a built in option to not send data by setting an env var,
SCARF_NO_ANALYTICS=true.

DoD:
- When importing or running unstructured package it will make a get call
to scarf
- When env variable is set to not track, call is not made

CHANGELOG.md

@@ -1,3 +1,7 @@
+## 0.10.21
+
+* **Adds Scarf analytics**.
+
 ## 0.10.20
 
 ### Enhancements

README.md

@@ -256,4 +256,5 @@ Encountered a bug? Please create a new [GitHub issue](https://github.com/Unstruc
 
 ## :chart_with_upwards_trend: Analytics
 
-We’ve partnered with Scarf (https://scarf.sh) to collect anonymized user statistics to understand which features our community is using and how to prioritize product decision-making in the future. To learn more about how we collect and use this data, please read our [Privacy Policy](https://unstructured.io/privacy-policy).
+We’ve partnered with Scarf (https://scarf.sh) to collect anonymized user statistics to understand which features our community is using and how to prioritize product decision-making in the future. To learn more about how we collect and use this data, please read our [Privacy Policy](https://unstructured.io/privacy-policy).
+To opt out of this data collection, you can set the environment variable `SCARF_NO_ANALYTICS=true` before running any `unstructured` commands.

unstructured/__version__.py

@@ -1 +1 @@
-__version__ = "0.10.20"  # pragma: no cover
+__version__ = "0.10.21"  # pragma: no cover

unstructured/logger.py

@@ -1,5 +1,7 @@
 import logging
 
+from unstructured.utils import scarf_analytics
+
 logger = logging.getLogger("unstructured")
 trace_logger = logging.getLogger("unstructured.trace")
 
@@ -14,5 +16,9 @@ def detail(self, message, *args, **kws):
         self._log(DETAIL, message, args, **kws)
 
 
+# Note(Trevor,Crag): to opt out of scarf analytics, set the environment variable:
+# SCARF_NO_ANALYTICS=true. See the README for more info.
+scarf_analytics()
+
 # Add the custom log method to the logging.Logger class
 logging.Logger.detail = detail  # type: ignore

unstructured/utils.py

@@ -1,12 +1,17 @@
 import functools
 import importlib
 import json
+import os
+import platform
 from datetime import datetime
 from functools import wraps
 from typing import Any, Callable, Dict, Generic, List, Optional, TypeVar, Union, cast
 
+import requests
 from typing_extensions import ParamSpec
 
+from unstructured.__version__ import __version__
+
 DATE_FORMATS = ("%Y-%m-%d", "%Y-%m-%dT%H:%M:%S", "%Y-%m-%d+%H:%M:%S", "%Y-%m-%dT%H:%M:%S%z")
 
 
@@ -189,3 +194,16 @@ def validate_date_args(date: Optional[str] = None):
         f"The argument {date} does not satisfy the format: "
         "YYYY-MM-DD or YYYY-MM-DDTHH:MM:SS or YYYY-MM-DD+HH:MM:SS or YYYY-MM-DDTHH:MM:SStz",
     )
+
+
+def scarf_analytics():
+    try:
+        if os.getenv("SCARF_NO_ANALYTICS") != "true" and os.getenv("DO_NOT_TRACK") != "true":
+            requests.get(
+                "https://packages.unstructured.io/python-telemetry?version="
+                + __version__
+                + "&platform="
+                + platform.system()
+            )
+    except Exception:
+        pass