resolve merge conf

Signed-off-by: Labanya Mukhopadhyay <labanya.mukhopadhyay@snowflake.com>

CHANGELOG.md

@@ -27,6 +27,9 @@
 - Added support for `Index.to_numpy`.
 - Added support for `DataFrame.align` and `Series.align` for `axis=0`.
 - Added support for `size` in `GroupBy.aggregate`, `DataFrame.aggregate`, and `Series.aggregate`.
+- Added support for `pd.read_pickle` (Uses native pandas for processing).
+- Added support for `pd.read_html` (Uses native pandas for processing).
+- Added support for `pd.read_xml` (Uses native pandas for processing).
 - Added support for `DataFrame.align` and `Series.align` for `axis=1 and None`.
 
 ### Snowpark Local Testing Updates
@@ -55,6 +58,7 @@
 - Disables sql simplification when sort is performed after limit.
   - Previously, `df.sort().limit()` and `df.limit().sort()` generates the same query with sort in front of limit. Now, `df.limit().sort()` will generate query that reads `df.limit().sort()`.
   - Improve performance of generated query for `df.limit().sort()`, because limit stops table scanning as soon as the number of records is satisfied.
+- Added a client side error message for when an invalid stage location is passed to DataFrame read functions.
 
 #### Bug Fixes
 

docs/source/modin/io.rst

@@ -14,6 +14,9 @@ Input/Output
     read_json
     read_parquet
     read_sas
+    read_pickle
+    read_html
+    read_xml
 
 .. rubric:: SQL
 

docs/source/modin/supported/general_supported.rst

@@ -50,6 +50,8 @@ Data manipulations
 +-----------------------------+---------------------------------+----------------------------------+----------------------------------------------------+
 | ``qcut``                    | P                               |                                  | ``N`` if ``labels!=False`` or ``retbins=True``.    |
 +-----------------------------+---------------------------------+----------------------------------+----------------------------------------------------+
+| ``read_pickle``             | Y                               |                                  | Uses native pandas for reading.                    | 
++-----------------------------+---------------------------------+----------------------------------+----------------------------------------------------+
 | ``read_csv``                | P                               |                                  | Reads both local and staged file(s) into a Snowpark|
 |                             |                                 |                                  | pandas DataFrame. Note, the order of rows in the   |
 |                             |                                 |                                  | may differ from the order of rows in the original  |
@@ -84,6 +86,10 @@ Data manipulations
 |                             |                                 | ``dtype_backend``, and           |                                                    |
 |                             |                                 | ``storage_options`` are ignored. |                                                    |
 +-----------------------------+---------------------------------+----------------------------------+----------------------------------------------------+
+| ``read_html``               | Y                               |                                  | Uses native pandas for reading.                    | 
++-----------------------------+---------------------------------+----------------------------------+----------------------------------------------------+
+| ``read_xml``                | Y                               |                                  | Uses native pandas for reading.                    | 
++-----------------------------+---------------------------------+----------------------------------+----------------------------------------------------+
 | ``read_parquet``            | P                               | ``use_nullable_dtypes``,         | Supported parameter(s) are: ``columns``            |
 |                             |                                 | ``filesystem``, and ``filters``  |                                                    |
 |                             |                                 | will raise an error if used.     |                                                    |

docs/source/snowpark/functions.rst

@@ -277,6 +277,7 @@ Functions
     sum
     sum_distinct
     sysdate
+    system_reference
     table_function
     tan
     tanh

setup.py

@@ -52,6 +52,7 @@
     "pytest-assume",  # sql counter check
     "decorator",  # sql counter check
     "protoc-wheel-0",  # Protocol buffer compiler, for Snowpark IR
+    "lxml",  # used in read_xml tests
 ]
 
 # read the version

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

@@ -77,6 +77,7 @@ def infer_metadata(
     )
     from snowflake.snowpark._internal.analyzer.snowflake_plan import SnowflakePlan
     from snowflake.snowpark._internal.analyzer.unary_plan_node import (
+        Aggregate,
         Filter,
         Project,
         Sample,
@@ -97,6 +98,13 @@ def infer_metadata(
         # When source_plan is a SnowflakeValues, metadata is already defined locally
         elif isinstance(source_plan, SnowflakeValues):
             attributes = source_plan.output
+        # When source_plan is Aggregate or Project, we already have quoted_identifiers
+        elif isinstance(source_plan, Aggregate):
+            quoted_identifiers = infer_quoted_identifiers_from_expressions(
+                source_plan.aggregate_expressions,  # type: ignore
+                analyzer,
+                df_aliased_col_name_to_real_col_name,
+            )
         elif isinstance(source_plan, Project):
             quoted_identifiers = infer_quoted_identifiers_from_expressions(
                 source_plan.project_list,  # type: ignore

src/snowflake/snowpark/dataframe_reader.py

@@ -20,6 +20,7 @@
 from snowflake.snowpark._internal.type_utils import ColumnOrName, convert_sf_to_sp_type
 from snowflake.snowpark._internal.utils import (
     INFER_SCHEMA_FORMAT_TYPES,
+    SNOWFLAKE_PATH_PREFIXES,
     TempObjectType,
     get_aliased_option_name,
     get_copy_into_table_options,
@@ -59,6 +60,15 @@
 }
 
 
+def _validate_stage_path(path: str) -> str:
+    stripped_path = path.strip("\"'")
+    if not any(stripped_path.startswith(prefix) for prefix in SNOWFLAKE_PATH_PREFIXES):
+        raise ValueError(
+            f"'{path}' is an invalid Snowflake stage location. DataFrameReader can only read files from stage locations."
+        )
+    return path
+
+
 class DataFrameReader:
     """Provides methods to load data in various supported formats from a Snowflake
     stage to a :class:`DataFrame`. The paths provided to the DataFrameReader must refer
@@ -411,6 +421,7 @@ def csv(self, path: str) -> DataFrame:
         Returns:
             a :class:`DataFrame` that is set up to load data from the specified CSV file(s) in a Snowflake stage.
         """
+        path = _validate_stage_path(path)
         self._file_path = path
         self._file_type = "CSV"
 
@@ -706,6 +717,7 @@ def _read_semi_structured_file(self, path: str, format: str) -> DataFrame:
 
         if self._user_schema:
             raise ValueError(f"Read {format} does not support user schema")
+        path = _validate_stage_path(path)
         self._file_path = path
         self._file_type = format