feat: Support serializing dataclasses (#206)

* Support serializing dataclasses

* Update version

* Run black

* Fix for Python 3.9

Author: rossgray

CHANGELOG.md

@@ -1,4 +1,6 @@
+## 3.21.0 – 2025-03-17
 
+1. Support serializing dataclasses.
 
 ## 3.20.0 – 2025-03-13
 

posthog/test/test_utils.py

@@ -1,4 +1,5 @@
 import unittest
+from dataclasses import dataclass
 from datetime import date, datetime, timedelta
 from decimal import Decimal
 from typing import Optional
@@ -56,7 +57,10 @@ def test_clean(self):
         self.assertEqual(combined.keys(), pre_clean_keys)
 
         # test UUID separately, as the UUID object doesn't equal its string representation according to Python
-        self.assertEqual(utils.clean(UUID("12345678123456781234567812345678")), "12345678-1234-5678-1234-567812345678")
+        self.assertEqual(
+            utils.clean(UUID("12345678123456781234567812345678")),
+            "12345678-1234-5678-1234-567812345678",
+        )
 
     def test_clean_with_dates(self):
         dict_with_dates = {
@@ -100,7 +104,8 @@ class NestedModel(BaseModel):
         self.assertEqual(utils.clean(ModelV2(foo="1", bar=2)), {"foo": "1", "bar": 2, "baz": None})
         self.assertEqual(utils.clean(ModelV1(foo=1, bar="2")), {"foo": 1, "bar": "2"})
         self.assertEqual(
-            utils.clean(NestedModel(foo=ModelV2(foo="1", bar=2, baz="3"))), {"foo": {"foo": "1", "bar": 2, "baz": "3"}}
+            utils.clean(NestedModel(foo=ModelV2(foo="1", bar=2, baz="3"))),
+            {"foo": {"foo": "1", "bar": 2, "baz": "3"}},
         )
 
         class Dummy:
@@ -110,6 +115,47 @@ def model_dump(self, required_param):
         # Skips a class with a defined non-Pydantic `model_dump` method.
         self.assertEqual(utils.clean({"test": Dummy()}), {})
 
+    def test_clean_dataclass(self):
+        @dataclass
+        class InnerDataClass:
+            inner_foo: str
+            inner_bar: int
+            inner_uuid: UUID
+            inner_date: datetime
+            inner_optional: Optional[str] = None
+
+        @dataclass
+        class TestDataClass:
+            foo: str
+            bar: int
+            nested: InnerDataClass
+
+        self.assertEqual(
+            utils.clean(
+                TestDataClass(
+                    foo="1",
+                    bar=2,
+                    nested=InnerDataClass(
+                        inner_foo="3",
+                        inner_bar=4,
+                        inner_uuid=UUID("12345678123456781234567812345678"),
+                        inner_date=datetime(2025, 1, 1),
+                    ),
+                )
+            ),
+            {
+                "foo": "1",
+                "bar": 2,
+                "nested": {
+                    "inner_foo": "3",
+                    "inner_bar": 4,
+                    "inner_uuid": "12345678-1234-5678-1234-567812345678",
+                    "inner_date": datetime(2025, 1, 1),
+                    "inner_optional": None,
+                },
+            },
+        )
+
 
 class TestSizeLimitedDict(unittest.TestCase):
     def test_size_limited_dict(self):

posthog/utils.py

@@ -2,6 +2,7 @@
 import numbers
 import re
 from collections import defaultdict
+from dataclasses import asdict, is_dataclass
 from datetime import date, datetime, timezone
 from decimal import Decimal
 from uuid import UUID
@@ -68,6 +69,8 @@ def clean(item):
         pass
     if isinstance(item, dict):
         return _clean_dict(item)
+    if is_dataclass(item) and not isinstance(item, type):
+        return _clean_dataclass(item)
     return _coerce_unicode(item)
 
 
@@ -90,6 +93,12 @@ def _clean_dict(dict_):
     return data
 
 
+def _clean_dataclass(dataclass_):
+    data = asdict(dataclass_)
+    data = _clean_dict(data)
+    return data
+
+
 def _coerce_unicode(cmplx):
     try:
         item = cmplx.decode("utf-8", "strict")

posthog/version.py

@@ -1,4 +1,4 @@
-VERSION = "3.20.0"
+VERSION = "3.21.0"
 
 if __name__ == "__main__":
     print(VERSION, end="")  # noqa: T201