fix!: normalize blob layouts and support external byte ranges (#4589)

2026-10-27 14:06:14 +00:00 · 2026-10-19 16:44:00 -07:00
parent 6507615a6f
commit 4a03859b2a
20 changed files with 2837 additions and 131 deletions
@@ -3254,6 +3254,89 @@ BLOB_DESCRIBE_RESPONSE = {
 }


+@pytest.mark.asyncio
+@pytest.mark.parametrize("use_async", [False, True])
+@pytest.mark.parametrize("mode", ["merge", "overwrite"])
+@pytest.mark.parametrize("target_with_ranges", [False, True])
+async def test_remote_writes_normalize_blob_layouts(
+    use_async, mode, target_with_ranges
+):
+    description = json.loads(json.dumps(BLOB_DESCRIBE_RESPONSE))
+    if target_with_ranges:
+        description["schema"]["fields"][1]["type"]["fields"].extend(
+            {"name": name, "type": {"type": "uint64"}, "nullable": True}
+            for name in ("position", "size")
+        )
+    received = []
+
+    def handler(request):
+        if request.path == "/v1/table/test/describe/":
+            response = description
+        else:
+            expected = "merge_insert" if mode == "merge" else "insert"
+            assert urlparse(request.path).path == f"/v1/table/test/{expected}/"
+            if request.headers.get("Transfer-Encoding") == "chunked":
+                body = bytearray()
+                while size := int(request.rfile.readline().split(b";")[0], 16):
+                    body.extend(request.rfile.read(size))
+                    assert request.rfile.read(2) == b"\r\n"
+                assert request.rfile.read(2) == b"\r\n"
+            else:
+                body = request.rfile.read(int(request.headers["Content-Length"]))
+            received.append(pa.ipc.open_stream(body).read_all())
+            response = {
+                "version": 2,
+                "num_updated_rows": 0,
+                "num_inserted_rows": 2,
+                "num_deleted_rows": 0,
+            }
+        request.send_response(200)
+        request.send_header("Content-Type", "application/json")
+        request.send_header("phalanx-version", "0.5.0")
+        request.end_headers()
+        request.wfile.write(json.dumps(response).encode())
+
+    field = lancedb.blob("image")
+    storage_type = field.type.storage_type
+    if target_with_ranges:
+        storage_type = pa.struct(list(storage_type)[:2])
+        field = pa.field(
+            "image",
+            storage_type,
+            metadata={"ARROW:extension:name": "lance.blob.v2"},
+        )
+    images = pa.array([{"data": b"payload"}, None], type=storage_type)
+    if isinstance(field.type, pa.ExtensionType):
+        images = pa.ExtensionArray.from_storage(field.type, images)
+    data = pa.Table.from_arrays(
+        [pa.array([1, 2], type=pa.int64()), images],
+        schema=pa.schema([pa.field("id", pa.int64()), field]),
+    )
+
+    with mock_lancedb_connection(handler) as db:
+        remote_table = db.open_table("test")
+        table = remote_table._table if use_async else remote_table
+        if mode == "merge":
+            result = (
+                table.merge_insert("id").when_not_matched_insert_all().execute(data)
+            )
+        else:
+            result = table.add(data, mode="overwrite")
+        if use_async:
+            await result
+
+    assert len(received) == 1
+    images = received[0]["image"].combine_chunks()
+    if isinstance(images.type, pa.ExtensionType):
+        images = images.storage
+    with_ranges = target_with_ranges if mode == "merge" else not target_with_ranges
+    assert images.type.num_fields == (4 if with_ranges else 2)
+    expected = {"data": b"payload", "uri": None}
+    if with_ranges:
+        expected.update(position=None, size=None)
+    assert images.to_pylist() == [expected, None]
+
+
 def blob_query_response_table():
    image_field = pa.field(
        "image",