Revert "SNOW-3384967: reduce describe query generated by alias" (#4207)

Author: sfc-gh-yuwang

CHANGELOG.md

@@ -18,10 +18,6 @@
 
 - Added `artifact_repository` support to `udtf_configs` in `session.read.dbapi()`, enabling users to specify a custom artifact repository (e.g. PyPI) for packages used by the internal UDTF during distributed ingestion.
 
-#### Improvements
-
-- When `Session.reduce_describe_query_enabled` is enabled, fewer DESCRIBE queries are issued when the outer query only projects or renames columns from an inner subquery whose column types are already known.
-
 #### Bug Fixes
 
 - Fixed a bug where `TRY_CAST` reader option is ignored when calling `DataFrameReader.schema().csv()`.

src/snowflake/snowpark/_internal/analyzer/select_statement.py

@@ -85,9 +85,8 @@
     has_invalid_projection_merge_functions,
 )
 from snowflake.snowpark._internal.utils import (
-    ExprAliasUpdateDict,
     is_sql_select_statement,
-    quote_name,
+    ExprAliasUpdateDict,
 )
 import snowflake.snowpark.context as context
 
@@ -1593,72 +1592,6 @@ def select(self, cols: List[Expression]) -> "SelectStatement":
                 )
             )
 
-        # When describe reduction is on and the inner select already has resolved
-        # attributes, infer new.attributes for this outer select by reusing datatype and
-        # nullable from the subquery: (0) skip if parent column names collide, (1) index
-        # attributes by quote_name (Snowflake identifier rules; invalid delimited forms
-        # raise), (2) walk new.projection, (3) only handle plain columns or Alias(column),
-        # (4) resolve source via the same quote_name key lookup, (5) assign only if every
-        # output column was inferred (length matches projection).
-        if self._session.reduce_describe_query_enabled and self.attributes is not None:
-            parent_attributes = self.attributes
-            projection = new.projection
-            inferred_attributes: Optional[List[Attribute]] = None
-            # Skip: no projection to walk (do not assert; leave new.attributes unchanged).
-            if projection is not None:
-                # Skip: duplicate output names on the parent — dict/lookup would be ambiguous.
-                attributes_by_normalized: Dict[str, Attribute] = {}
-                collision = False
-                for attr in parent_attributes:
-                    key = quote_name(attr.name)
-                    existing = attributes_by_normalized.get(key)
-                    # Skip: two parent columns map to the same quote_name key.
-                    if existing is not None and existing is not attr:
-                        collision = True
-                        break
-                    attributes_by_normalized[key] = attr
-                if not collision:
-                    inferred_attributes = []
-                    for expr in projection:
-                        source_column_name: Optional[str] = None
-                        projected_column_name: Optional[str] = None
-                        if isinstance(expr, (Attribute, UnresolvedAttribute)):
-                            source_column_name = expr.name
-                            projected_column_name = expr.name
-                        elif isinstance(expr, Alias) and isinstance(
-                            expr.child, (Attribute, UnresolvedAttribute)
-                        ):
-                            source_column_name = expr.child.name
-                            projected_column_name = expr.name
-                        else:
-                            # Skip: not a plain column or Alias(Attribute|UnresolvedAttribute).
-                            inferred_attributes = []
-                            break
-
-                        if source_column_name is None or projected_column_name is None:
-                            # Skip: missing projected output name.
-                            inferred_attributes = []
-                            break
-                        source_attr = attributes_by_normalized.get(
-                            quote_name(source_column_name)
-                        )
-                        # Skip: no parent column for this source name.
-                        if source_attr is None:
-                            inferred_attributes = []
-                            break
-                        inferred_attributes.append(
-                            Attribute(
-                                projected_column_name,
-                                source_attr.datatype,
-                                source_attr.nullable,
-                            )
-                        )
-                    if len(inferred_attributes) != len(projection):
-                        # Skip: incomplete inference (includes defensive mismatch).
-                        inferred_attributes = None
-            if inferred_attributes is not None:
-                new.attributes = inferred_attributes
-
         new.flatten_disabled = disable_next_level_flatten
         assert new.projection is not None
         new._column_states = derive_column_states_from_subquery(

tests/integ/test_cte.py

@@ -259,7 +259,7 @@ def test_binary(session, type, action):
 
 def test_join_with_alias_dataframe(session):
     expected_describe_count = (
-        2
+        3
         if (session.reduce_describe_query_enabled and session.sql_simplifier_enabled)
         else 4
     )