snowflake-snowpark-python 1.51.1__tar.gz → 1.52.0__tar.gz

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/CHANGELOG.md

@@ -1,5 +1,27 @@
 # Release History
 
+## 1.52.0 (2026-06-10)
+
+### Snowpark Python API Updates
+
+#### New Features
+
+- Added `get_wif_token` to `snowflake.snowpark.secrets` for workload identity federation tokens on the Snowflake server (not available in SPCS file-based secret environments).
+
+#### Bug Fixes
+
+- Fixed a bug where copying a `DataFrame` via `copy.copy()` lost post-aggregate state, causing subsequent `.limit()` or `.sort()` to generate incorrect SQL.
+- Fixed a bug where calling `DataFrame.alias()` twice on the same DataFrame (e.g. for a self-join) caused both aliases to share the same internal column-mapping dictionary. This made `col("R", "col")` resolve to the same column as `col("L", "col")`, producing incorrect join conditions and filter expressions.
+- Fixed a bug where `cloudpickle` could not be resolved when registering a Python stored procedure or UDF with `runtime_version='3.13'`.
+
+#### Improvements
+
+- Improved CTE optimization to deduplicate identical subtrees in self-joins, which were previously emitted as repeated subqueries.
+
+#### Deprecations
+
+- Removed support for Python 3.9.
+
 ## 1.51.1 (2026-05-28)
 
 #### Documentation

{snowflake_snowpark_python-1.51.1/src/snowflake_snowpark_python.egg-info → snowflake_snowpark_python-1.52.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: snowflake-snowpark-python
-Version: 1.51.1
+Version: 1.52.0
 Summary: Snowflake Snowpark for Python
 Home-page: https://www.snowflake.com/
 Author: Snowflake, Inc
@@ -22,7 +22,6 @@ Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Operating System :: OS Independent
 Classifier: Programming Language :: SQL
 Classifier: Programming Language :: Python :: 3 :: Only
-Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
@@ -33,7 +32,7 @@ Classifier: Topic :: Software Development :: Libraries
 Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Classifier: Topic :: Scientific/Engineering :: Information Analysis
-Requires-Python: >=3.9, <3.15
+Requires-Python: >=3.10, <3.15
 Description-Content-Type: text/markdown
 License-File: LICENSE.txt
 Requires-Dist: setuptools>=40.6.0
@@ -149,9 +148,9 @@ If you don't have a Snowflake account yet, you can [sign up for a 30-day free tr
 
 ### Create a Python virtual environment
 You can use [miniconda][miniconda], [anaconda][anaconda], or [virtualenv][virtualenv]
-to create a Python 3.9, 3.10, 3.11, 3.12 or 3.13 virtual environment.
+to create a Python 3.10, 3.11, 3.12 or 3.13 virtual environment.
 
-For Snowpark pandas, only Python 3.9, 3.10, or 3.11 is supported.
+For Snowpark pandas, only Python 3.10 or 3.11 is supported.
 
 To have the best experience when using it with UDFs, [creating a local conda environment with the Snowflake channel][use snowflake channel] is recommended.
 

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/README.md

@@ -18,9 +18,9 @@ If you don't have a Snowflake account yet, you can [sign up for a 30-day free tr
 
 ### Create a Python virtual environment
 You can use [miniconda][miniconda], [anaconda][anaconda], or [virtualenv][virtualenv]
-to create a Python 3.9, 3.10, 3.11, 3.12 or 3.13 virtual environment.
+to create a Python 3.10, 3.11, 3.12 or 3.13 virtual environment.
 
-For Snowpark pandas, only Python 3.9, 3.10, or 3.11 is supported.
+For Snowpark pandas, only Python 3.10 or 3.11 is supported.
 
 To have the best experience when using it with UDFs, [creating a local conda environment with the Snowflake channel][use snowflake channel] is recommended.
 

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/setup.py

@@ -32,10 +32,10 @@ INSTALL_REQ_LIST = [
     "python-dateutil",  # Snowpark IR
     "tzlocal",  # Snowpark IR
 ]
-REQUIRED_PYTHON_VERSION = ">=3.9, <3.15"
+REQUIRED_PYTHON_VERSION = ">=3.10, <3.15"
 
 if os.getenv("SNOWFLAKE_IS_PYTHON_RUNTIME_TEST", False):
-    REQUIRED_PYTHON_VERSION = ">=3.9"
+    REQUIRED_PYTHON_VERSION = ">=3.10"
 
 PANDAS_REQUIREMENTS = [
     f"snowflake-connector-python[pandas]{CONNECTOR_DEPENDENCY_VERSION}",
@@ -246,7 +246,6 @@ setup(
         "Operating System :: OS Independent",
         "Programming Language :: SQL",
         "Programming Language :: Python :: 3 :: Only",
-        "Programming Language :: Python :: 3.9",
         "Programming Language :: Python :: 3.10",
         "Programming Language :: Python :: 3.11",
         "Programming Language :: Python :: 3.12",

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/_internal/analyzer/analyzer_utils.py

@@ -6,7 +6,6 @@
 import json
 import math
 import os
-import sys
 import tempfile
 from typing import Any, Dict, List, Optional, Tuple, Union, Literal, Sequence
 
@@ -52,13 +51,7 @@ from snowflake.snowpark._internal.utils import (
 from snowflake.snowpark.row import Row
 from snowflake.snowpark.types import DataType
 
-# Python 3.8 needs to use typing.Iterable because collections.abc.Iterable is not subscriptable
-# Python 3.9 can use both
-# Python 3.10 needs to use collections.abc.Iterable because typing.Iterable is removed
-if sys.version_info <= (3, 9):
-    from typing import Iterable
-else:
-    from collections.abc import Iterable
+from collections.abc import Iterable
 
 LEFT_PARENTHESIS = "("
 RIGHT_PARENTHESIS = ")"

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/_internal/analyzer/select_statement.py

@@ -2,7 +2,6 @@
 # Copyright (c) 2012-2025 Snowflake Computing Inc. All rights reserved.
 #
 
-import sys
 import uuid
 import re
 from abc import ABC, abstractmethod
@@ -90,13 +89,7 @@ from snowflake.snowpark._internal.utils import (
 )
 import snowflake.snowpark.context as context
 
-# Python 3.8 needs to use typing.Iterable because collections.abc.Iterable is not subscriptable
-# Python 3.9 can use both
-# Python 3.10 needs to use collections.abc.Iterable because typing.Iterable is removed
-if sys.version_info <= (3, 9):
-    from typing import Iterable
-else:
-    from collections.abc import Iterable
+from collections.abc import Iterable
 
 SET_UNION = analyzer_utils.UNION
 SET_UNION_ALL = analyzer_utils.UNION_ALL
@@ -963,7 +956,7 @@ class SelectStatement(Selectable):
         new._snowflake_plan = None
         new.flatten_disabled = False  # by default a SelectStatement can be flattened.
         new._api_calls = self._api_calls.copy() if self._api_calls is not None else None
-        new.df_aliased_col_name_to_real_col_name = (
+        new.df_aliased_col_name_to_real_col_name = deepcopy(
             self.df_aliased_col_name_to_real_col_name
         )
         new._merge_projection_complexity_with_subquery = (

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/_internal/analyzer/snowflake_plan.py

@@ -143,13 +143,7 @@ from snowflake.snowpark.row import Row
 from snowflake.snowpark.types import StructType
 import snowflake.snowpark.context as context
 
-# Python 3.8 needs to use typing.Iterable because collections.abc.Iterable is not subscriptable
-# Python 3.9 can use both
-# Python 3.10 needs to use collections.abc.Iterable because typing.Iterable is removed
-if sys.version_info <= (3, 9):
-    from typing import Iterable
-else:
-    from collections.abc import Iterable
+from collections.abc import Iterable
 
 _logger = getLogger(__name__)
 

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/_internal/analyzer/snowflake_plan_node.py

@@ -3,7 +3,7 @@
 # Copyright (c) 2012-2025 Snowflake Computing Inc. All rights reserved.
 #
 
-import sys
+from collections.abc import Iterable
 from enum import Enum
 from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple
 
@@ -17,14 +17,6 @@ from snowflake.snowpark._internal.analyzer.query_plan_analysis_utils import (
 from snowflake.snowpark.row import Row
 from snowflake.snowpark.types import StructType
 
-# Python 3.8 needs to use typing.Iterable because collections.abc.Iterable is not subscriptable
-# Python 3.9 can use both
-# Python 3.10 needs to use collections.abc.Iterable because typing.Iterable is removed
-if sys.version_info <= (3, 9):
-    from typing import Iterable
-else:
-    from collections.abc import Iterable
-
 if TYPE_CHECKING:
     from snowflake.snowpark import Session
     from snowflake.snowpark.udtf import UserDefinedTableFunction

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/_internal/analyzer/table_function.py

@@ -2,7 +2,7 @@
 # Copyright (c) 2012-2025 Snowflake Computing Inc. All rights reserved.
 #
 
-import sys
+from collections.abc import Iterable
 from typing import Dict, List, Optional
 
 from snowflake.snowpark._internal.analyzer.expression import Expression
@@ -13,14 +13,6 @@ from snowflake.snowpark._internal.analyzer.query_plan_analysis_utils import (
 from snowflake.snowpark._internal.analyzer.snowflake_plan_node import LogicalPlan
 from snowflake.snowpark._internal.analyzer.sort_expression import SortOrder
 
-# Python 3.8 needs to use typing.Iterable because collections.abc.Iterable is not subscriptable
-# Python 3.9 can use both
-# Python 3.10 needs to use collections.abc.Iterable because typing.Iterable is removed
-if sys.version_info <= (3, 9):
-    from typing import Iterable
-else:
-    from collections.abc import Iterable
-
 
 class TableFunctionPartitionSpecDefinition(Expression):
     def __init__(

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/_internal/code_generation.py

@@ -17,13 +17,7 @@ from typing import Any, Dict, List, Set, Tuple, Union
 
 import opcode
 
-# Python 3.8 needs to use typing.Iterable because collections.abc.Iterable is not subscriptable
-# Python 3.9 can use both
-# Python 3.10 needs to use collections.abc.Iterable because typing.Iterable is removed
-if sys.version_info <= (3, 9):
-    from typing import Iterable
-else:
-    from collections.abc import Iterable
+from collections.abc import Iterable
 
 logger = getLogger(__name__)
 

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/_internal/compiler/cte_utils.py

@@ -307,7 +307,12 @@ def encode_query_id(node: "TreeNode") -> Optional[str]:
     if query_params:
         string = f"{string}#{query_params}"
     if hasattr(node, "expr_to_alias") and node.expr_to_alias:
-        string = f"{string}#{stringify(node.expr_to_alias)}"
+        # Hash by alias values only, not the UUID keys, since UUID keys are regenerated on every deep-copy/re-resolve (e.g. the two
+        # branches of a self-join). This lets nodes representing the same computation hash identically, enabling CTE dedup for self-joins.
+        # NOTE: since nodes with different UUID keys can now share a CTE, _replace_duplicate_node_with_cte must merge each duplicate's
+        # UUID→alias entries into the shared CTE so parent re-resolution can resolve any UUID variant (see companion comment there).
+        # Different alias values (e.g. a "_WITH_AD_GROUP" join suffix from _disambiguate) still hash differently, preserving SNOW-2261400.
+        string = f"{string}#{sorted(set(node.expr_to_alias.values()))}"
     if (
         hasattr(node, "df_aliased_col_name_to_real_col_name")
         and node.df_aliased_col_name_to_real_col_name

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/_internal/compiler/repeated_subquery_elimination.py

@@ -108,6 +108,24 @@ class RepeatedSubqueryElimination:
             total_num_ctes=self._total_number_ctes,
         )
 
+    @staticmethod
+    def _has_alias_conflict(
+        node: TreeNode, existing_cte: Optional[SnowflakePlan]
+    ) -> bool:
+        """Whether sharing ``existing_cte`` for ``node`` would map the same expr_id to a
+        different alias. encode_query_id hashes expr_to_alias by alias values only, so
+        nodes mapping the same expr_id to different aliases can collide. Merging such a
+        node into the shared CTE would silently drop an entry and corrupt parent column
+        resolution, so in that case we skip the CTE and render the node inline."""
+        if existing_cte is None:
+            return False
+        node_expr_to_alias = getattr(node, "expr_to_alias", None) or {}
+        return any(
+            key in existing_cte.expr_to_alias
+            and existing_cte.expr_to_alias[key] != alias
+            for key, alias in node_expr_to_alias.items()
+        )
+
     def _replace_duplicate_node_with_cte(
         self,
         root: TreeNode,
@@ -159,16 +177,20 @@ class RepeatedSubqueryElimination:
             if node in visited_nodes:
                 continue
 
-            # if the node is a duplicated node and deduplication is not done for the node,
-            # start the deduplication transformation use CTE
-            if node.encoded_node_id_with_query in duplicated_node_ids:
-                if node.encoded_node_id_with_query in resolved_with_block_map:
-                    # if the corresponding CTE block has been created, use the existing
-                    # one.
-                    resolved_with_block = resolved_with_block_map[
-                        node.encoded_node_id_with_query
-                    ]
-                else:
+            # Decide whether this node should be represented by a (new or shared) CTE:
+            # it must be a detected duplicate, and sharing the CTE must not introduce an
+            # alias conflict (see _has_alias_conflict). When it cannot be a CTE, the node
+            # is left inline and only the parent-propagation path applies, exactly like a
+            # non-duplicated node.
+            resolved_with_block = resolved_with_block_map.get(
+                node.encoded_node_id_with_query
+            )
+            is_cte_node = node.encoded_node_id_with_query in duplicated_node_ids and (
+                not self._has_alias_conflict(node, resolved_with_block)
+            )
+            if is_cte_node:
+                if resolved_with_block is None:
+                    # no CTE block has been created for this node yet, create one.
                     if (
                         self._query_generator.session.reduce_describe_query_enabled
                         and context._is_snowpark_connect_compatible_mode
@@ -187,6 +209,12 @@ class RepeatedSubqueryElimination:
                         node.encoded_node_id_with_query
                     ] = resolved_with_block
                     self._total_number_ctes += 1
+                elif getattr(node, "expr_to_alias", None):
+                    # reuse the existing CTE block. expr_ids are regenerated on copy, so
+                    # this node's keys differ from the node the CTE was built from; merge
+                    # this node's entries so every expr_id variant stays resolvable during
+                    # parent re-resolution.
+                    resolved_with_block.expr_to_alias.update(node.expr_to_alias)
                 _update_parents(
                     node, should_replace_child=True, new_child=resolved_with_block
                 )

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/_internal/debug_utils.py

@@ -64,7 +64,7 @@ class DataFrameTraceNode:
                     code_lines[0] = code_lines[0][start_column:]
                     code_lines[-1] = code_lines[-1][:end_column]
             else:
-                # For python 3.9/3.10, we do not extract the end line from the source code
+                # For python 3.10, we do not extract the end line from the source code
                 # so we just read the start line and return.
                 for line in itertools.islice(f, start_line - 1, start_line):
                     code_lines.append(line)

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/_internal/type_utils.py

@@ -83,13 +83,7 @@ from snowflake.snowpark.types import (
     File,
 )
 
-# Python 3.8 needs to use typing.Iterable because collections.abc.Iterable is not subscriptable
-# Python 3.9 can use both
-# Python 3.10 needs to use collections.abc.Iterable because typing.Iterable is removed
-try:
-    from typing import Iterable  # noqa: F401
-except ImportError:
-    from collections.abc import Iterable  # noqa: F401
+from collections.abc import Iterable  # noqa: F401
 
 if installed_pandas:
     from snowflake.snowpark.types import (

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/_internal/udf_utils.py

@@ -71,13 +71,7 @@ if installed_pandas:
         PandasSeriesType,
     )
 
-# Python 3.8 needs to use typing.Iterable because collections.abc.Iterable is not subscriptable
-# Python 3.9 can use both
-# Python 3.10 needs to use collections.abc.Iterable because typing.Iterable is removed
-if sys.version_info <= (3, 9):
-    from typing import Iterable
-else:
-    from collections.abc import Iterable
+from collections.abc import Iterable
 
 logger = getLogger(__name__)
 
@@ -1276,7 +1270,7 @@ def resolve_imports_and_packages(
                     any(pkg.startswith("cloudpickle") for pkg in packages)
                 )
             resolved_packages = packages + (
-                [f"cloudpickle=={cloudpickle.__version__}"]
+                [f"cloudpickle>={cloudpickle.__version__}"]
                 if not has_cloudpickle
                 else []
             )

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/_internal/utils.py

@@ -1955,6 +1955,7 @@ class TimeTravelConfig(NamedTuple):
     timestamp: Optional[str] = None
     timestamp_type: Optional[str] = None
     stream: Optional[str] = None
+    version: Optional[int] = None
 
     @staticmethod
     def validate_and_normalize_params(
@@ -1964,6 +1965,7 @@ class TimeTravelConfig(NamedTuple):
         timestamp: Optional[Union[str, datetime.datetime]] = None,
         timestamp_type: Optional[Union[str, "TimestampTimeZone"]] = None,
         stream: Optional[str] = None,
+        version: Optional[int] = None,
     ) -> Optional["TimeTravelConfig"]:
         """
         Validates and normalizes time travel parameters.
@@ -1986,7 +1988,7 @@ class TimeTravelConfig(NamedTuple):
             ValueError: If parameters are invalid.
         """
         time_travel_arg_count = sum(
-            arg is not None for arg in (statement, offset, timestamp, stream)
+            arg is not None for arg in (statement, offset, timestamp, stream, version)
         )
 
         # Validate mode
@@ -2003,10 +2005,28 @@ class TimeTravelConfig(NamedTuple):
                 f"Invalid time travel mode: {time_travel_mode}. Must be 'at' or 'before'."
             )
 
+        # version (Iceberg snapshot id) only works with 'at' mode — matches
+        # Snowflake's ``AT(VERSION => <id>)`` grammar and Spark Iceberg's
+        # ``snapshot-id`` option semantics ("read snapshot N", not "before N").
+        if version is not None and time_travel_mode.lower() != "at":
+            raise ValueError(
+                "Iceberg snapshot version time travel can only be used with "
+                "time_travel_mode='at', not 'before'."
+            )
+
+        # Validate version type — snapshot IDs are 64-bit integers in Iceberg.
+        # Reject bool explicitly because ``isinstance(True, int)`` is True in Python.
+        if version is not None and (
+            not isinstance(version, int) or isinstance(version, bool)
+        ):
+            raise ValueError(
+                f"'version' must be an int Iceberg snapshot id, got {type(version).__name__}."
+            )
+
         # Validate exactly one parameter is provided
         if time_travel_arg_count != 1:
             raise ValueError(
-                "Exactly one of 'statement', 'offset', 'timestamp', or 'stream' must be provided."
+                "Exactly one of 'statement', 'offset', 'timestamp', 'stream', or 'version' must be provided."
             )
 
         # Normalize timestamp
@@ -2040,6 +2060,7 @@ class TimeTravelConfig(NamedTuple):
             timestamp=normalized_timestamp,
             timestamp_type=timestamp_type,
             stream=stream,
+            version=version,
         )
 
     def generate_sql_clause(self) -> str:
@@ -2048,7 +2069,8 @@ class TimeTravelConfig(NamedTuple):
         Args:
             config: Time travel configuration.
         Returns:
-            SQL clause like " AT (TIMESTAMP => TO_TIMESTAMP_NTZ('...'))"
+            SQL clause like " AT (TIMESTAMP => TO_TIMESTAMP_NTZ('...'))" or
+            " AT (VERSION => 1234567890)" for Iceberg snapshot id time travel.
         """
         clause = f" {self.time_travel_mode.upper()} "
 
@@ -2058,6 +2080,8 @@ class TimeTravelConfig(NamedTuple):
             clause += f"(OFFSET => {self.offset})"
         elif self.stream is not None:
             clause += f"(STREAM => '{self.stream}')"
+        elif self.version is not None:
+            clause += f"(VERSION => {self.version})"
         elif self.timestamp is not None:
             if self.timestamp_type is not None:
                 timestamp_type = self.timestamp_type.upper()

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/_internal/xml_schema_inference.py

@@ -112,7 +112,7 @@ def _infer_primitive_type(text: str) -> DataType:
         pass
 
     # Timestamp (Spark default: TimestampFormatter with CAST logic)
-    # Backward compatibility: Python 3.9 fromisoformat doesn't support 'Z' suffix; replace with +00:00
+    # Backward compatibility: Python 3.10 fromisoformat doesn't support 'Z' suffix; replace with +00:00
     try:
         ts_text = text.replace("Z", "+00:00") if text.endswith("Z") else text
         datetime.fromisoformat(ts_text)

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/column.py

@@ -3,7 +3,6 @@
 # Copyright (c) 2012-2025 Snowflake Computing Inc. All rights reserved.
 #
 
-import sys
 import typing
 from typing import Any, Optional, Union
 
@@ -100,13 +99,7 @@ from snowflake.snowpark.types import (
 )
 from snowflake.snowpark.window import Window, WindowSpec
 
-# Python 3.8 needs to use typing.Iterable because collections.abc.Iterable is not subscriptable
-# Python 3.9 can use both
-# Python 3.10 needs to use collections.abc.Iterable because typing.Iterable is removed
-if sys.version_info <= (3, 9):
-    from typing import Iterable
-else:
-    from collections.abc import Iterable
+from collections.abc import Iterable
 
 
 def _to_col_if_lit(

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/dataframe.py

@@ -8,7 +8,6 @@ import datetime
 import itertools
 import random
 import re
-import sys
 from collections import Counter
 from decimal import Decimal
 from functools import cached_property, reduce
@@ -235,13 +234,7 @@ from snowflake.snowpark.types import (
     YearMonthIntervalType,
 )
 
-# Python 3.8 needs to use typing.Iterable because collections.abc.Iterable is not subscriptable
-# Python 3.9 can use both
-# Python 3.10 needs to use collections.abc.Iterable because typing.Iterable is removed
-if sys.version_info <= (3, 9):
-    from typing import Iterable
-else:
-    from collections.abc import Iterable
+from collections.abc import Iterable
 
 if TYPE_CHECKING:
     import modin.pandas  # pragma: no cover
@@ -1054,9 +1047,21 @@ class DataFrame:
         else:
             return copy.copy(self._plan)
 
+    def _copy_agg_state(self, target: "DataFrame") -> None:
+        """Copy post-aggregate state to target so operations like .limit() and
+        .sort() on the copy go through _build_post_agg_df and generate correct
+        SQL (ORDER BY inside the aggregate subquery, not on the outer query)."""
+        target._ops_after_agg = self._ops_after_agg
+        target._agg_base_plan = self._agg_base_plan
+        target._agg_base_select_statement = self._agg_base_select_statement
+        target._pending_havings = self._pending_havings
+        target._pending_order_bys = self._pending_order_bys
+
     def _copy_without_ast(self) -> "DataFrame":
         """Returns a shallow copy of the DataFrame without AST generation."""
-        return DataFrame(self._session, self._copy_plan(), _emit_ast=False)
+        result = DataFrame(self._session, self._copy_plan(), _emit_ast=False)
+        self._copy_agg_state(result)
+        return result
 
     def __copy__(self) -> "DataFrame":
         """Implements shallow copy protocol for copy.copy(...)."""
@@ -1065,12 +1070,14 @@ class DataFrame:
             stmt = self._session._ast_batch.bind()
             with_src_position(stmt.expr.dataframe_ref, stmt)
             self._set_ast_ref(stmt.expr)
-        return DataFrame(
+        result = DataFrame(
             self._session,
             self._copy_plan(),
             _ast_stmt=stmt,
             _emit_ast=self._session.ast_enabled,
         )
+        self._copy_agg_state(result)
+        return result
 
     if installed_pandas:
         import pandas  # pragma: no cover

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/dataframe_ai_functions.py

@@ -1109,7 +1109,7 @@ class DataFrameAIFunctions:
             >>> result = json.loads(result_df.collect()[0]["TRANSCRIPT"])
             >>> len(result["segments"]) > 0
             True
-            >>> result["segments"][0]["text"].lower()
+            >>> result["segments"][0]["text"].lower()  # doctest: +SKIP
             'the'
             >>> 'start' in result["segments"][0] and 'end' in result["segments"][0]
             True
@@ -1125,11 +1125,11 @@ class DataFrameAIFunctions:
             >>> result = json.loads(result_df.collect()[0]["TRANSCRIPT"])
             >>> result["audio_duration"] > 100 and len(result["segments"]) > 0
             True
-            >>> result["segments"][0]["speaker_label"]
+            >>> result["segments"][0]["speaker_label"]  # doctest: +SKIP
             'SPEAKER_00'
-            >>> 'jenny' in result["segments"][0]["text"].lower()
+            >>> 'jenny' in result["segments"][0]["text"].lower()  # doctest: +SKIP
             True
-            >>> 'start' in result["segments"][0] and 'end' in result["segments"][0]
+            >>> 'start' in result["segments"][0] and 'end' in result["segments"][0]  # doctest: +SKIP
             True
         """
         output_column_name = output_column or "AI_TRANSCRIBE_OUTPUT"

{snowflake_snowpark_python-1.51.1 → snowflake_snowpark_python-1.52.0}/src/snowflake/snowpark/dataframe_na_functions.py

@@ -4,7 +4,7 @@
 #
 
 import math
-import sys
+from collections.abc import Iterable
 from logging import getLogger
 from typing import Dict, Optional, Union
 
@@ -33,14 +33,6 @@ from snowflake.snowpark.types import (
     LongType,
 )
 
-# Python 3.8 needs to use typing.Iterable because collections.abc.Iterable is not subscriptable
-# Python 3.9 can use both
-# Python 3.10 needs to use collections.abc.Iterable because typing.Iterable is removed
-if sys.version_info <= (3, 9):
-    from typing import Iterable
-else:
-    from collections.abc import Iterable
-
 _logger = getLogger(__name__)