From 793520c5476d150c2830fe3304d99fa7c132b9b9 Mon Sep 17 00:00:00 2001
From: Xavier Vello <xavier@posthog.com>
Date: Fri, 1 Dec 2023 17:52:15 +0100
Subject: [PATCH] tests

---
 posthog/consumer.py           |  2 +-
 posthog/test/test_consumer.py | 13 +++++++++----
 2 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/posthog/consumer.py b/posthog/consumer.py
index 7f452b2..794c6cc 100644
--- a/posthog/consumer.py
+++ b/posthog/consumer.py
@@ -105,7 +105,7 @@ def next(self):
                 item = queue.get(block=True, timeout=self.flush_interval - elapsed)
                 item_size = len(json.dumps(item, cls=DatetimeSerializer).encode())
                 if item_size > MAX_MSG_SIZE:
-                    self.log.error("Item exceeds 32kb limit, dropping. (%s)", str(item))
+                    self.log.error("Item exceeds 900kib limit, dropping. (%s)", str(item))
                     continue
                 items.append(item)
                 total_size += item_size
diff --git a/posthog/test/test_consumer.py b/posthog/test/test_consumer.py
index 58600b6..9fbaf87 100644
--- a/posthog/test/test_consumer.py
+++ b/posthog/test/test_consumer.py
@@ -145,15 +145,20 @@ def test_pause(self):
     def test_max_batch_size(self):
         q = Queue()
         consumer = Consumer(q, TEST_API_KEY, flush_at=100000, flush_interval=3)
-        track = {"type": "track", "event": "python event", "distinct_id": "distinct_id"}
+        properties = {}
+        for n in range(0, 500):
+            properties[str(n)] = "one_long_property_value_to_build_a_big_event"
+        track = {"type": "track", "event": "python event", "distinct_id": "distinct_id", "properties": properties}
         msg_size = len(json.dumps(track).encode())
-        # number of messages in a maximum-size batch
-        n_msgs = int(475000 / msg_size)
+        # Let's capture 8MB of data, will trigger two batches
+        n_msgs = int(8_000_000 / msg_size)
 
         def mock_post_fn(_, data, **kwargs):
             res = mock.Mock()
             res.status_code = 200
-            self.assertTrue(len(data.encode()) < 500000, "batch size (%d) exceeds 500KB limit" % len(data.encode()))
+            request_size = len(data.encode())
+            # Batches close after the first message bringing it bigger than BATCH_SIZE_LIMIT, let's add 5% of margin
+            self.assertTrue(request_size < (5 * 1024 * 1024) * 1.05, "batch size (%d) higher than limit" % request_size)
             return res
 
         with mock.patch("posthog.request._session.post", side_effect=mock_post_fn) as mock_post: