a few more

Author: kevinjqliu

mkdocs/docs/api.md

@@ -418,7 +418,7 @@ This produces the following result with `tbl.scan().to_arrow()`:
 
 ```python
 pyarrow.Table
-city: large_string
+city: string
 lat: double
 long: double
 ----
@@ -476,7 +476,7 @@ This produces the following result with `tbl.scan().to_arrow()`:
 
 ```python
 pyarrow.Table
-city: large_string
+city: string
 lat: double
 long: double
 ----
@@ -957,14 +957,14 @@ split_offsets: list<item: int64>
 equality_ids: list<item: int32>
   child 0, item: int32
 sort_order_id: int32
-readable_metrics: struct<city: struct<column_size: int64, value_count: int64, null_value_count: int64, nan_value_count: int64, lower_bound: large_string, upper_bound: large_string> not null, lat: struct<column_size: int64, value_count: int64, null_value_count: int64, nan_value_count: int64, lower_bound: double, upper_bound: double> not null, long: struct<column_size: int64, value_count: int64, null_value_count: int64, nan_value_count: int64, lower_bound: double, upper_bound: double> not null>
+readable_metrics: struct<city: struct<column_size: int64, value_count: int64, null_value_count: int64, nan_value_count: int64, lower_bound: string, upper_bound: string> not null, lat: struct<column_size: int64, value_count: int64, null_value_count: int64, nan_value_count: int64, lower_bound: double, upper_bound: double> not null, long: struct<column_size: int64, value_count: int64, null_value_count: int64, nan_value_count: int64, lower_bound: double, upper_bound: double> not null>
   child 0, city: struct<column_size: int64, value_count: int64, null_value_count: int64, nan_value_count: int64, lower_bound: string, upper_bound: string> not null
       child 0, column_size: int64
       child 1, value_count: int64
       child 2, null_value_count: int64
       child 3, nan_value_count: int64
-      child 4, lower_bound: large_string
-      child 5, upper_bound: large_string
+      child 4, lower_bound: string
+      child 5, upper_bound: string
   child 1, lat: struct<column_size: int64, value_count: int64, null_value_count: int64, nan_value_count: int64, lower_bound: double, upper_bound: double> not null
       child 0, column_size: int64
       child 1, value_count: int64
@@ -998,7 +998,7 @@ equality_ids:[[[],[]]]
 sort_order_id:[[[],[]]]
 readable_metrics: [
   -- is_valid: all not null
-  -- child 0 type: struct<column_size: int64, value_count: int64, null_value_count: int64, nan_value_count: int64, lower_bound: large_string, upper_bound: large_string>
+  -- child 0 type: struct<column_size: int64, value_count: int64, null_value_count: int64, nan_value_count: int64, lower_bound: string, upper_bound: string>
     -- is_valid: all not null
     -- child 0 type: int64
 [140]
@@ -1008,9 +1008,9 @@ readable_metrics: [
 [0]
     -- child 3 type: int64
 [null]
-    -- child 4 type: large_string
+    -- child 4 type: string
 ["Amsterdam"]
-    -- child 5 type: large_string
+    -- child 5 type: string
 ["San Francisco"]
   -- child 1 type: struct<column_size: int64, value_count: int64, null_value_count: int64, nan_value_count: int64, lower_bound: double, upper_bound: double>
     -- is_valid: all not null

tests/catalog/test_sql.py

@@ -404,7 +404,7 @@ def test_write_pyarrow_schema(catalog: SqlCatalog, table_identifier: Identifier)
         ],
         schema=pa.schema(
             [
-                pa.field("foo", pa.large_string(), nullable=True),
+                pa.field("foo", pa.string(), nullable=True),
                 pa.field("bar", pa.int32(), nullable=False),
                 pa.field("baz", pa.bool_(), nullable=True),
                 pa.field("large", pa.large_string(), nullable=True),
@@ -1462,7 +1462,7 @@ def test_write_and_evolve(catalog: SqlCatalog, format_version: int) -> None:
         {
             "foo": ["a", None, "z"],
         },
-        schema=pa.schema([pa.field("foo", pa.large_string(), nullable=True)]),
+        schema=pa.schema([pa.field("foo", pa.string(), nullable=True)]),
     )
 
     tbl = catalog.create_table(identifier=identifier, schema=pa_table.schema, properties={"format-version": str(format_version)})
@@ -1474,7 +1474,7 @@ def test_write_and_evolve(catalog: SqlCatalog, format_version: int) -> None:
         },
         schema=pa.schema(
             [
-                pa.field("foo", pa.large_string(), nullable=True),
+                pa.field("foo", pa.string(), nullable=True),
                 pa.field("bar", pa.int32(), nullable=True),
             ]
         ),
@@ -1514,7 +1514,7 @@ def test_create_table_transaction(catalog: SqlCatalog, format_version: int) -> N
         {
             "foo": ["a", None, "z"],
         },
-        schema=pa.schema([pa.field("foo", pa.large_string(), nullable=True)]),
+        schema=pa.schema([pa.field("foo", pa.string(), nullable=True)]),
     )
 
     pa_table_with_column = pa.Table.from_pydict(
@@ -1524,7 +1524,7 @@ def test_create_table_transaction(catalog: SqlCatalog, format_version: int) -> N
         },
         schema=pa.schema(
             [
-                pa.field("foo", pa.large_string(), nullable=True),
+                pa.field("foo", pa.string(), nullable=True),
                 pa.field("bar", pa.int32(), nullable=True),
             ]
         ),

tests/conftest.py

@@ -2510,8 +2510,8 @@ def pa_schema() -> "pa.Schema":
     return pa.schema(
         [
             ("bool", pa.bool_()),
-            ("string", pa.large_string()),
-            ("string_long", pa.large_string()),
+            ("string", pa.string()),
+            ("string_long", pa.string()),
             ("int", pa.int32()),
             ("long", pa.int64()),
             ("float", pa.float32()),
@@ -2525,7 +2525,7 @@ def pa_schema() -> "pa.Schema":
             # ("time", pa.time64("us")),
             # Not natively supported by Arrow
             # ("uuid", pa.fixed(16)),
-            ("binary", pa.large_binary()),
+            ("binary", pa.binary()),
             ("fixed", pa.binary(16)),
         ]
     )

tests/integration/test_writes/test_partitioned_writes.py

@@ -891,7 +891,7 @@ def test_unsupported_transform(
 
     with pytest.raises(
         ValueError,
-        match="FeatureUnsupported => Unsupported data type for truncate transform: LargeBinary",
+        match="FeatureUnsupported => Unsupported data type for truncate transform: Binary",
     ):
         tbl.append(arrow_table_with_null)