test: update python expectations for lance 9.1

python/python/lancedb/query.py

@@ -3875,18 +3875,18 @@ class AsyncHybridQuery(AsyncStandardQuery, AsyncVectorQueryBase):
         >>> asyncio.run(doctest_example()) # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
         RRFReranker(K=60)
             ProjectionExec: expr=[vector@0 as vector, text@3 as text, _distance@2 as _distance]
-              Take: columns="vector, _rowid, _distance, (text)"
-                CoalesceBatchesExec: target_batch_size=1024
-                  GlobalLimitExec: skip=0, fetch=10
-                    FilterExec: _distance@2 IS NOT NULL
-                      SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST, _rowid@1 ASC NULLS LAST], preserve_partitioning=[false]
-                        KNNVectorDistance: metric=l2
-                          LanceRead: uri=..., projection=[vector], ...
+            Take: columns="vector, _rowid, _distance, (text)"
+              CoalesceBatchesExec: target_batch_size=1024
+                GlobalLimitExec: skip=0, fetch=10
+                  FilterExec: _distance@2 IS NOT NULL
+                    SortExec: TopK(fetch=10), expr=[_distance@2 ASC NULLS LAST, _rowid@1 ASC NULLS LAST], preserve_partitioning=[false]
+                      KNNVectorDistance: metric=l2
+                        LanceRead: uri=..., projection=[vector], ...
             ProjectionExec: expr=[vector@2 as vector, text@3 as text, _score@1 as _score]
-              Take: columns="_rowid, _score, (vector), (text)"
-                CoalesceBatchesExec: target_batch_size=1024
-                  GlobalLimitExec: skip=0, fetch=10
-                    MatchQuery: column=text, query=hello
+            Take: columns="_rowid, _score, (vector), (text)"
+              CoalesceBatchesExec: target_batch_size=1024
+                GlobalLimitExec: skip=0, fetch=10
+                  MatchQuery: column=text, query=[hello]
 
         Parameters
         ----------

python/python/tests/test_permutation.py

@@ -128,9 +128,16 @@ def test_split_hash(mem_db):
 
 def test_split_hash_with_discard(mem_db):
     """Test hash-based splitting with discard weight."""
+    total_rows = 1000
     tbl = mem_db.create_table(
         "test_table",
-        pa.table({"id": range(100), "category": ["A", "B"] * 50, "value": range(100)}),
+        pa.table(
+            {
+                "id": range(total_rows),
+                "category": [f"category-{i}" for i in range(total_rows)],
+                "value": range(total_rows),
+            }
+        ),
     )
 
     permutation_tbl = (
@@ -142,10 +149,12 @@ def test_split_hash_with_discard(mem_db):
         .execute()
     )
 
-    # Should have fewer than 100 rows due to discard
+    # Should have fewer rows due to discard, but should not be empty.
     row_count = permutation_tbl.count_rows()
-    assert row_count < 100
-    assert row_count > 0  # But not empty
+    assert 0 < row_count < total_rows
+
+    data = permutation_tbl.search(None).to_arrow().to_pydict()
+    assert set(data["split_id"]) == {0, 1}
 
 
 def test_split_sequential(mem_db):

python/python/tests/test_query.py

@@ -1273,7 +1273,7 @@ async def test_explain_plan_fts(table_async: AsyncTable):
     query = await table_async.search("dog", query_type="fts", fts_columns="text")
     plan = await query.explain_plan()
     # Should show FTS details (issue #2465 is now fixed)
-    assert "MatchQuery: column=text, query=dog" in plan
+    assert "MatchQuery: column=text, query=[dog]" in plan
     assert "GlobalLimitExec" in plan  # Default limit
 
     # Test FTS query with limit
@@ -1281,7 +1281,7 @@ async def test_explain_plan_fts(table_async: AsyncTable):
         "dog", query_type="fts", fts_columns="text"
     )
     plan_with_limit = await query_with_limit.limit(1).explain_plan()
-    assert "MatchQuery: column=text, query=dog" in plan_with_limit
+    assert "MatchQuery: column=text, query=[dog]" in plan_with_limit
     assert "GlobalLimitExec: skip=0, fetch=1" in plan_with_limit
 
     # Test FTS query with offset and limit
@@ -1289,7 +1289,7 @@ async def test_explain_plan_fts(table_async: AsyncTable):
         "dog", query_type="fts", fts_columns="text"
     )
     plan_with_offset = await query_with_offset.offset(1).limit(1).explain_plan()
-    assert "MatchQuery: column=text, query=dog" in plan_with_offset
+    assert "MatchQuery: column=text, query=[dog]" in plan_with_offset
     assert "GlobalLimitExec: skip=1, fetch=1" in plan_with_offset
 
 
@@ -1333,7 +1333,7 @@ async def test_explain_plan_with_filters(table_async: AsyncTable):
         "dog", query_type="fts", fts_columns="text"
     )
     plan_fts_filter = await query_fts_filter.where("id = 1").explain_plan()
-    assert "MatchQuery: column=text, query=dog" in plan_fts_filter
+    assert "MatchQuery: column=text, query=[dog]" in plan_fts_filter
     assert "LanceRead" in plan_fts_filter
     assert "full_filter=id = Int64(1)" in plan_fts_filter  # Should show filter details