problem with schema evolution

apache · Jan 22, 2024 · c09e7e9 · c09e7e9
1 parent 94d288a
commit c09e7e9
Show file tree

Hide file tree

Showing 2 changed files with 9 additions and 1 deletion.
diff --git a/pyiceberg/table/__init__.py b/pyiceberg/table/__init__.py
@@ -504,6 +504,9 @@ def _(update: AddSchemaUpdate, base_metadata: TableMetadata, context: _TableMeta
     if update.last_column_id < base_metadata.last_column_id:
         raise ValueError(f"Invalid last column id {update.last_column_id}, must be >= {base_metadata.last_column_id}")
 
+    # PROBLEM: `update.schema_`'s `schema_id` starts with 0 but should be 1
+    # fresh_schema = assign_fresh_schema_ids(update.schema_)
+
     context.add_update(update)
     return base_metadata.model_copy(
         update={

diff --git a/tests/catalog/test_base.py b/tests/catalog/test_base.py
@@ -371,6 +371,11 @@ def test_commit_table(catalog: InMemoryCatalog) -> None:
         NestedField(4, "add", LongType()),
     )
 
+    assert given_table.metadata.current_schema_id == 0
+    assert len(given_table.metadata.schemas) == 1
+    assert given_table.metadata.schemas[0] == TEST_TABLE_SCHEMA
+    assert given_table.metadata.last_column_id == TEST_TABLE_SCHEMA.highest_field_id
+
     # When
     response = given_table.catalog._commit_table(  # pylint: disable=W0212
         CommitTableRequest(
@@ -384,7 +389,7 @@ def test_commit_table(catalog: InMemoryCatalog) -> None:
 
     # Then
     assert response.metadata.table_uuid == given_table.metadata.table_uuid
-    # assert len(response.metadata.schemas) == 1
+    assert len(response.metadata.schemas) == 1
     # assert response.metadata.schemas[0] == new_schema