From 8987e9c790fe8da7921b2b4fbd6240671cf6b835 Mon Sep 17 00:00:00 2001
From: Shubham Dhal <shubham.dhal@databricks.com>
Date: Tue, 21 Apr 2026 17:25:47 +0530
Subject: [PATCH 1/2] test: add UTF-8 round-trip regression test for dbt seed

Seeds a CSV containing Arabic, Greek, Chinese, emoji, and accented Latin
then asserts each cell round-trips byte-exact through the seed path.
Covers both V1 and V2 materialization.

Guards the fix for #332, which reported non-ASCII characters being
mangled on seed in 1.4.x. The current parameterized-insert path
(adapter.add_query + bindings) handles UTF-8 correctly; this test
locks that in.

Co-authored-by: Isaac
---
 .../adapter/simple_seed/test_utf8_seed.py     | 32 +++++++++++++++++++
 1 file changed, 32 insertions(+)
 create mode 100644 tests/functional/adapter/simple_seed/test_utf8_seed.py

diff --git a/tests/functional/adapter/simple_seed/test_utf8_seed.py b/tests/functional/adapter/simple_seed/test_utf8_seed.py
new file mode 100644
index 000000000..c0059bbd2
--- /dev/null
+++ b/tests/functional/adapter/simple_seed/test_utf8_seed.py
@@ -0,0 +1,32 @@
+import pytest
+from dbt.tests import util
+
+from tests.functional.adapter.fixtures import MaterializationV2Mixin
+
+
+UTF8_DATA = {
+    "arabic": "مرحبا بالعالم",
+    "greek": "Γειά σου Κόσμε",
+    "chinese": "你好世界",
+    "emoji": "Hello 🌍 World ✨",
+    "mixed": "café naïve résumé — ",
+}
+SEED_CSV = "label,value\n" + "\n".join(f"{k},{v}" for k, v in UTF8_DATA.items())
+
+
+class TestUtf8SeedRoundTrip:
+    @pytest.fixture(scope="class")
+    def seeds(self):
+        return {"utf8_roundtrip.csv": SEED_CSV}
+
+    def test_utf8_roundtrip(self, project):
+        results = util.run_dbt(["seed"])
+        assert len(results) == 1
+
+        relation = util.relation_from_name(project.adapter, "utf8_roundtrip")
+        rows = project.run_sql(f"select label, value from {relation}", fetch="all")
+        assert dict(rows) == UTF8_DATA
+
+
+class TestUtf8SeedRoundTripV2(TestUtf8SeedRoundTrip, MaterializationV2Mixin):
+    pass

From 37bf26801c62b44ac2a33be1c74c9982b3df1d4c Mon Sep 17 00:00:00 2001
From: Shubham Dhal <shubham.dhal@databricks.com>
Date: Tue, 21 Apr 2026 17:48:07 +0530
Subject: [PATCH 2/2] style: ruff import block formatting

Co-authored-by: Isaac
---
 tests/functional/adapter/simple_seed/test_utf8_seed.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tests/functional/adapter/simple_seed/test_utf8_seed.py b/tests/functional/adapter/simple_seed/test_utf8_seed.py
index c0059bbd2..cd75d71d3 100644
--- a/tests/functional/adapter/simple_seed/test_utf8_seed.py
+++ b/tests/functional/adapter/simple_seed/test_utf8_seed.py
@@ -3,7 +3,6 @@
 
 from tests.functional.adapter.fixtures import MaterializationV2Mixin
 
-
 UTF8_DATA = {
     "arabic": "مرحبا بالعالم",
     "greek": "Γειά σου Κόσμε",