sqlframe 3.36.0__py3-none-any.whl → 3.36.2__py3-none-any.whl

sqlframe/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.36.0'
-__version_tuple__ = version_tuple = (3, 36, 0)
+__version__ = version = '3.36.2'
+__version_tuple__ = version_tuple = (3, 36, 2)

sqlframe/base/functions.py

@@ -1796,7 +1796,9 @@ def substring_index(str: ColumnOrName, delim: str, count: int) -> Column:
     if session._is_bigquery:
         return substring_index_bgutil(str, delim, count)
 
-    return Column.invoke_anonymous_function(str, "SUBSTRING_INDEX", lit(delim), lit(count))
+    return Column.invoke_expression_over_column(
+        str, expression.SubstringIndex, delimiter=lit(delim), count=lit(count)
+    )
 
 
 @meta(unsupported_engines="bigquery")
@@ -2205,7 +2207,9 @@ def slice(
 
     start_col = lit(start) if isinstance(start, int) else start
     length_col = lit(length) if isinstance(length, int) else length
-    return Column.invoke_anonymous_function(x, "SLICE", start_col, length_col)
+    return Column.invoke_expression_over_column(
+        x, expression.ArraySlice, start=start_col, end=length_col
+    )
 
 
 @meta()
@@ -2748,7 +2752,7 @@ def typeof(col: ColumnOrName) -> Column:
     if session._is_snowflake:
         return typeof_from_variant(col)
 
-    return Column.invoke_anonymous_function(col, "TYPEOF")
+    return Column.invoke_expression_over_column(col, expression.Typeof)
 
 
 @meta()

sqlframe/base/group.py

@@ -70,6 +70,11 @@ class _BaseGroupedData(t.Generic[DF]):
 
             from sqlframe.base import functions as F
 
+            if self.session._is_snowflake and len(cols) > 1:
+                raise ValueError(
+                    "Snowflake does not support multiple aggregation functions in a single group by operation."
+                )
+
             # Build the pivot expression
             # First, we need to convert the DataFrame to include the pivot logic
             df = self._df.copy()
@@ -132,11 +137,55 @@ class _BaseGroupedData(t.Generic[DF]):
             subquery.set("pivots", [pivot])
 
             # Create the final select from the pivoted subquery
-            expression = exp.select("*").from_(subquery)
+            final_select_in_values = []
+            for col in in_values:  # type: ignore
+                for agg_col in cols:
+                    original_name = col.alias_or_name  # type: ignore
+                    if self.session._is_snowflake:
+                        # Snowflake takes the provided values, like 'Java', and creates the column as "'Java'"
+                        # Therefore the user to select the column would need to use "'Java'"
+                        # This does not conform to the PySpark API, nor is it very user-friendly.
+                        # Therefore, we select the column as expected, and tell SQLFrame it is case-sensitive, but then
+                        # alias is to case-insensitive "Java" so that the user can select it without quotes.
+                        # This has a downside that if a user really needed case-sensitive column names then it wouldn't work.
+                        new_col = exp.to_column(
+                            col.alias_or_name,  # type: ignore
+                            quoted=True,
+                            dialect=self.session.execution_dialect,
+                        )
+                        new_col.this.set("this", f"'{new_col.this.this}'")
+                        new_col = exp.alias_(new_col, original_name)
+                        new_col.unalias()._meta = {"case_sensitive": True}
+                    elif self.session._is_bigquery:
+                        # BigQuery flips the alias order to <alias>_<value> instead of <value>_<alias>
+                        new_col = exp.to_column(
+                            f"{agg_col.alias_or_name}_{original_name}",
+                            dialect=self.session.execution_dialect,
+                        )
+                        new_col = (
+                            exp.alias_(new_col, original_name)
+                            if len(cols) == 1
+                            else exp.alias_(new_col, f"{original_name}_{agg_col.alias_or_name}")
+                        )
+                    elif self.session._is_duckdb:
+                        # DuckDB always respects the alias if if num_cols == 1
+                        new_col = exp.column(f"{original_name}_{agg_col.expression.alias_or_name}")
+                        if len(cols) == 1:
+                            new_col = exp.alias_(new_col, original_name)
+                    else:
+                        new_col = (
+                            exp.column(original_name)
+                            if len(cols) == 1
+                            else exp.column(f"{original_name}_{agg_col.expression.alias_or_name}")
+                        )
+                    final_select_in_values.append(new_col)
+
+            expression = exp.select(
+                *[x.column_expression for x in self.group_by_cols] + final_select_in_values  # type: ignore
+            ).from_(subquery)
 
             return self._df.copy(expression=expression)
 
-        # Original non-pivot logic
         if not self.group_by_cols or not isinstance(self.group_by_cols[0], (list, tuple, set)):
             expression = self._df.expression.group_by(
                 # User column_expression for group by to avoid alias in group by

sqlframe/base/mixins/table_mixins.py

@@ -3,6 +3,7 @@ import logging
 import typing as t
 
 from sqlglot import exp
+from typing_extensions import ParamSpec
 
 try:
     from sqlglot.expressions import Whens
@@ -28,21 +29,22 @@ if t.TYPE_CHECKING:
 logger = logging.getLogger(__name__)
 
 
-def ensure_cte() -> t.Callable[[t.Callable], t.Callable]:
-    def decorator(func: t.Callable) -> t.Callable:
-        @functools.wraps(func)
-        def wrapper(self: _BaseTable, *args, **kwargs) -> t.Any:
-            if len(self.expression.ctes) > 0:
-                return func(self, *args, **kwargs)  # type: ignore
-            self_class = self.__class__
-            self = self._convert_leaf_to_cte()
-            self = self_class(**object_to_dict(self))
-            return func(self, *args, **kwargs)  # type: ignore
+P = ParamSpec("P")
+T = t.TypeVar("T")
+
 
-        wrapper.__wrapped__ = func  # type: ignore
-        return wrapper
+def ensure_cte(func: t.Callable[P, T]) -> t.Callable[P, T]:
+    @functools.wraps(func)
+    def wrapper(self: _BaseTable, *args: P.args, **kwargs: P.kwargs) -> T:
+        if len(self.expression.ctes) > 0:
+            return func(self, *args, **kwargs)  # type: ignore
+        self_class = self.__class__
+        self = self._convert_leaf_to_cte()
+        self = self_class(**object_to_dict(self))
+        return func(self, *args, **kwargs)  # type: ignore
 
-    return decorator
+    wrapper.__wrapped__ = func  # type: ignore
+    return wrapper  # type: ignore[return-value]
 
 
 class _BaseTableMixins(_BaseTable, t.Generic[DF]):
@@ -68,7 +70,7 @@ class _BaseTableMixins(_BaseTable, t.Generic[DF]):
 
 
 class UpdateSupportMixin(_BaseTableMixins, t.Generic[DF]):
-    @ensure_cte()
+    @ensure_cte
     def update(
         self,
         set_: t.Dict[t.Union[Column, str], t.Union[Column, "ColumnOrLiteral", exp.Expression]],
@@ -119,7 +121,7 @@ class UpdateSupportMixin(_BaseTableMixins, t.Generic[DF]):
 
 
 class DeleteSupportMixin(_BaseTableMixins, t.Generic[DF]):
-    @ensure_cte()
+    @ensure_cte
     def delete(
         self,
         where: t.Optional[t.Union[Column, str, bool]] = None,
@@ -141,7 +143,7 @@ class MergeSupportMixin(_BaseTable, t.Generic[DF]):
     ]
     _merge_support_star: bool
 
-    @ensure_cte()
+    @ensure_cte
     def merge(
         self,
         other_df: DF,

{sqlframe-3.36.0.dist-info → sqlframe-3.36.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.36.0
+Version: 3.36.2
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman
@@ -17,7 +17,7 @@ Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: prettytable <4
-Requires-Dist: sqlglot <26.32,>=24.0.0
+Requires-Dist: sqlglot <26.34,>=24.0.0
 Requires-Dist: typing-extensions
 Provides-Extra: bigquery
 Requires-Dist: google-cloud-bigquery-storage <3,>=2 ; extra == 'bigquery'
@@ -37,7 +37,7 @@ Requires-Dist: pyarrow <21,>=10 ; extra == 'dev'
 Requires-Dist: pyspark <3.6,>=2 ; extra == 'dev'
 Requires-Dist: pytest-forked ; extra == 'dev'
 Requires-Dist: pytest-postgresql <8,>=6 ; extra == 'dev'
-Requires-Dist: pytest-xdist <3.8,>=3.6 ; extra == 'dev'
+Requires-Dist: pytest-xdist <3.9,>=3.6 ; extra == 'dev'
 Requires-Dist: pytest <8.5,>=8.2.0 ; extra == 'dev'
 Requires-Dist: ruff <0.13,>=0.4.4 ; extra == 'dev'
 Requires-Dist: types-psycopg2 <3,>=2.9 ; extra == 'dev'
@@ -59,7 +59,7 @@ Requires-Dist: psycopg2 <3,>=2.8 ; extra == 'postgres'
 Provides-Extra: redshift
 Requires-Dist: redshift-connector <2.2.0,>=2.1.1 ; extra == 'redshift'
 Provides-Extra: snowflake
-Requires-Dist: snowflake-connector-python[secure-local-storage] <3.16,>=3.10.0 ; extra == 'snowflake'
+Requires-Dist: snowflake-connector-python[secure-local-storage] <3.17,>=3.10.0 ; extra == 'snowflake'
 Provides-Extra: spark
 Requires-Dist: pyspark <3.6,>=2 ; extra == 'spark'
 

{sqlframe-3.36.0.dist-info → sqlframe-3.36.2.dist-info}/RECORD

@@ -1,5 +1,5 @@
 sqlframe/__init__.py,sha256=SB80yLTITBXHI2GCDS6n6bN5ObHqgPjfpRPAUwxaots,3403
-sqlframe/_version.py,sha256=bkUPQ6OdlXKrD5knIV3EChl0OWjLm_VJDu9m0db4vwg,513
+sqlframe/_version.py,sha256=8n9kfLZeiKlOVTLEVFfs0B2MLJQ8xc2SyKauUUuFT3s,513
 sqlframe/py.typed,sha256=Nqnn8clbgv-5l0PgxcTOldg8mkMKrFn4TvPL-rYUUGg,1
 sqlframe/base/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sqlframe/base/_typing.py,sha256=b2clI5HI1zEZKB_3Msx3FeAJQyft44ubUifJwQRVXyQ,1298
@@ -9,8 +9,8 @@ sqlframe/base/dataframe.py,sha256=0diYONDlet8iZt49LC3vcmfXHAAZ2MovPL2pTXYHj2U,85
 sqlframe/base/decorators.py,sha256=IhE5xNQDkwJHacCvulq5WpUKyKmXm7dL2A3o5WuKGP4,2131
 sqlframe/base/exceptions.py,sha256=9Uwvqn2eAkDpqm4BrRgbL61qM-GMCbJEMAW8otxO46s,370
 sqlframe/base/function_alternatives.py,sha256=aTu3nQhIAkZoxrI1IpjpaHEAMxBNms0AnhS0EMR-TwY,51727
-sqlframe/base/functions.py,sha256=qyV-4R4CPSkuS-0S3dPza0BZykoKAanxjQq83tu8L34,225778
-sqlframe/base/group.py,sha256=PGxUAnZkNlYKBIVNzoEDtoHbsP9Rhy1bGcSg2eYuWF4,9015
+sqlframe/base/functions.py,sha256=n1MsfJt2WWUk7-YwbfByWG065g0W45AwJVIME5H-QJU,225875
+sqlframe/base/group.py,sha256=fBm8EUve7W7xz11nybTXr09ih-yZxL_vvEiZVE1eb_0,12025
 sqlframe/base/normalize.py,sha256=nXAJ5CwxVf4DV0GsH-q1w0p8gmjSMlv96k_ez1eVul8,3880
 sqlframe/base/operations.py,sha256=g-YNcbvNKTOBbYm23GKfB3fmydlR7ZZDAuZUtXIHtzw,4438
 sqlframe/base/readerwriter.py,sha256=Nb2VJ_HBmLQp5mK8JhnFooZh2ydAaboCAFVPb-4MNX4,31241
@@ -25,7 +25,7 @@ sqlframe/base/mixins/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hS
 sqlframe/base/mixins/catalog_mixins.py,sha256=9fZGWToz9xMJSzUl1vsVtj6TH3TysP3fBCKJLnGUQzE,23353
 sqlframe/base/mixins/dataframe_mixins.py,sha256=8D2AFtfc0tj9Q5qzlNAXdXOYw9RuD8kpe8wixo8pY5o,1534
 sqlframe/base/mixins/readwriter_mixins.py,sha256=ItQ_0jZ5RljgmLjGDIzLMRP_NQdy3wAyKwJ6K5NjaqA,4954
-sqlframe/base/mixins/table_mixins.py,sha256=2TnGFpbDSGw_NswpZwLACqvdD4zCA7hXekQ9IEkoTOk,13784
+sqlframe/base/mixins/table_mixins.py,sha256=3MhsOARkplwED1GRD0wq1vR8GNuop34kt3Jg8MATIjc,13791
 sqlframe/bigquery/__init__.py,sha256=kbaomhYAANPdxeDQhajv8IHfMg_ENKivtYK-rPwaV08,939
 sqlframe/bigquery/catalog.py,sha256=Dcpp1JKftc3ukdYpn6M1ujqixA-6_1k8aY21Y5Johyc,11899
 sqlframe/bigquery/column.py,sha256=E1tUa62Y5HajkhgFuebU9zohrGyieudcHzTT8gfalio,40
@@ -130,8 +130,8 @@ sqlframe/standalone/udf.py,sha256=azmgtUjHNIPs0WMVNId05SHwiYn41MKVBhKXsQJ5dmY,27
 sqlframe/standalone/window.py,sha256=6GKPzuxeSapJakBaKBeT9VpED1ACdjggDv9JRILDyV0,35
 sqlframe/testing/__init__.py,sha256=VVCosQhitU74A3NnE52O4mNtGZONapuEXcc20QmSlnQ,132
 sqlframe/testing/utils.py,sha256=PFsGZpwNUE_4-g_f43_vstTqsK0AQ2lBneb5Eb6NkFo,13008
-sqlframe-3.36.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-3.36.0.dist-info/METADATA,sha256=F56M3UKMA8CZN2Ps3dAkputINvX8rhBcPKTiAuC5iEs,8987
-sqlframe-3.36.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-sqlframe-3.36.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-3.36.0.dist-info/RECORD,,
+sqlframe-3.36.2.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-3.36.2.dist-info/METADATA,sha256=G40goRUAdQg115DFuLq6-RYZ_6OSyBJ0zRsPHu7mhMQ,8987
+sqlframe-3.36.2.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+sqlframe-3.36.2.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-3.36.2.dist-info/RECORD,,