From 607e5569276e68fc9b7bd6803b2748e6028007e1 Mon Sep 17 00:00:00 2001
From: "lancedb-gatefixer[bot]"
 <313497061+lancedb-gatefixer[bot]@users.noreply.github.com>
Date: Fri, 7 Aug 2026 17:32:28 +0800
Subject: [PATCH] test(python): cover search after schema merge (#3784)

## Summary

- add an end-to-end regression for indexed vector search after merging a
pandas column
- verify unmatched rows retain a null merged value instead of failing
Arrow batch assembly

## Root cause

Historical Lance readers could assemble schema-evolved columns in
physical data-file order. Indexed row-ID reads after a merge could
therefore omit or misorder the newly merged column for unmatched rows.
The currently pinned Lance release contains the reader correction, but
LanceDB did not cover the reported merge-then-search path.

## Validation

- uv run --extra tests pytest python/tests/test_table.py::test_merge
python/tests/test_table.py::test_search_after_merge -q
- uv run --project python --extra dev ruff check .
- uv run --project python --extra dev ruff format --check
python/python/tests/test_table.py

Fixes #599

<!-- lance-gatekeeper-fix:v1 agent=4e17331e0542c132eae31e86da508629
generation=1 -->

---------

Co-authored-by: Gatefixer <313497061+lancedb-gatefixer[bot]@users.noreply.github.com>
---
 python/python/tests/test_table.py | 39 +++++++++++++++++++++++++++++++
 1 file changed, 39 insertions(+)

diff --git a/python/python/tests/test_table.py b/python/python/tests/test_table.py
index 4ad5d7c3d..eb6eaefaa 100644
--- a/python/python/tests/test_table.py
+++ b/python/python/tests/test_table.py
@@ -2218,6 +2218,45 @@ def test_merge(tmp_db: DBConnection, tmp_path):
     table.merge(other_dataset, left_on="id")
 
 
+@pytest.mark.parametrize("storage_version", ["legacy", "stable"])
+def test_search_after_merge(tmp_path, storage_version):
+    pytest.importorskip("lance")
+    pd = pytest.importorskip("pandas")
+
+    db = lancedb.connect(
+        tmp_path,
+        storage_options={"new_table_data_storage_version": storage_version},
+    )
+    rng = np.random.default_rng(42)
+    row_count = 512
+    vectors = rng.standard_normal((row_count, 8)).astype(np.float32)
+    table = db.create_table(
+        "search_after_merge",
+        data=pd.DataFrame(
+            {
+                "id": [str(i) for i in range(row_count)],
+                "vector": list(vectors),
+            }
+        ),
+    )
+    table.create_index("vector", config=IvfPq(num_partitions=1, num_sub_vectors=2))
+
+    links = pd.DataFrame(
+        {
+            "id": [str(i) for i in range(row_count // 2)],
+            "link": [f"https://example.com/{i}" for i in range(row_count // 2)],
+        }
+    )
+    table.merge(links, left_on="id")
+
+    query = table.search(vectors[-1]).refine_factor(50).limit(10)
+    assert "ANN" in query.explain_plan(verbose=True)
+
+    result = query.to_arrow()
+    links_by_id = dict(zip(result["id"].to_pylist(), result["link"].to_pylist()))
+    assert links_by_id[str(row_count - 1)] is None
+
+
 def test_delete(mem_db: DBConnection):
     table = mem_db.create_table(
         "my_table",