remove redundant code

Author: sfc-gh-yuwang

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

@@ -51,10 +51,8 @@
 
 from snowflake.snowpark._internal.analyzer import analyzer_utils
 from snowflake.snowpark._internal.analyzer.analyzer_utils import (
-    quote_name_without_upper_casing,
     result_scan_statement,
     schema_value_statement,
-    unquote_if_quoted,
 )
 from snowflake.snowpark._internal.analyzer.binary_expression import And
 from snowflake.snowpark._internal.analyzer.expression import (
@@ -87,7 +85,6 @@
     has_invalid_projection_merge_functions,
 )
 from snowflake.snowpark._internal.utils import (
-    ALREADY_QUOTED,
     ExprAliasUpdateDict,
     is_sql_select_statement,
     quote_name,
@@ -1596,9 +1593,10 @@ 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 normalized name, (2) walk new.projection, (3) only handle plain
-        # columns or Alias(column), (4) resolve source via quoted-identifier-aware lookup,
-        # (5) assign only if every output column was inferred (length matches projection).
+        # 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
@@ -1609,9 +1607,9 @@ def select(self, cols: List[Expression]) -> "SelectStatement":
                 attributes_by_normalized: Dict[str, Attribute] = {}
                 collision = False
                 for attr in parent_attributes:
-                    key = _normalized_snowflake_identifier_key(attr.name)
+                    key = quote_name(attr.name)
                     existing = attributes_by_normalized.get(key)
-                    # Skip: two parent columns normalize to the same 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
@@ -1639,7 +1637,7 @@ def select(self, cols: List[Expression]) -> "SelectStatement":
                             inferred_attributes = []
                             break
                         source_attr = attributes_by_normalized.get(
-                            _normalized_snowflake_identifier_key(source_column_name)
+                            quote_name(source_column_name)
                         )
                         # Skip: no parent column for this source name.
                         if source_attr is None:
@@ -2156,13 +2154,6 @@ class DeriveColumnDependencyError(Exception):
     """When deriving column dependencies from the subquery."""
 
 
-def _normalized_snowflake_identifier_key(name: str) -> str:
-    """Canonical quoted key: delimited identifiers preserve case; unquoted follow Snowflake uppercasing."""
-    if ALREADY_QUOTED.match(name):
-        return quote_name_without_upper_casing(unquote_if_quoted(name))
-    return quote_name(name)
-
-
 def parse_column_name(
     column: Expression,
     analyzer: "Analyzer",

tests/integ/test_reduce_describe_query.py

@@ -17,8 +17,10 @@
 from snowflake.snowpark._internal.analyzer.schema_utils import analyze_attributes
 from snowflake.snowpark._internal.utils import (
     TempObjectType,
+    quote_name,
     random_name_for_temp_object,
 )
+from snowflake.snowpark.exceptions import SnowparkPlanException
 from snowflake.snowpark.functions import (
     avg,
     col,
@@ -663,6 +665,21 @@ def test_select_inference_skips_on_duplicate_parent_keys_and_missing_alias_name(
     assert new_ss.attributes is None
 
 
+def test_quote_name_malformed_delimited_identifier_not_accepted():
+    """Keys for reduce-describe attribute inference use quote_name; malformed delimited names raise (SNOW-3384967)."""
+    for bad in ('"ab"c"', '""col"', '"col""'):
+        with pytest.raises(SnowparkPlanException) as ex_info:
+            quote_name(bad)
+        assert ex_info.value.error_code == "1200"
+        assert "Invalid identifier" in str(ex_info.value)
+
+
+def test_quote_name_valid_keys_for_reduce_describe_inference():
+    """quote_name keys used for inference: case-sensitive quoted id; unquoted uppercased."""
+    assert quote_name('"MixedCase"') == '"MixedCase"'
+    assert quote_name("a") == '"A"'
+
+
 def test_select_star_after_cached_parent(session):
     """SELECT * after parent schema is cached: infer_metadata can copy child attributes when reduce_describe is on."""
     df = session.create_dataframe([[1, 2]], schema=["a", "b"])