sqlframe 3.27.1__py3-none-any.whl → 3.28.1__py3-none-any.whl

sqlframe/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.27.1'
-__version_tuple__ = version_tuple = (3, 27, 1)
+__version__ = version = '3.28.1'
+__version_tuple__ = version_tuple = (3, 28, 1)

sqlframe/base/dataframe.py

@@ -910,6 +910,8 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
 
     @operation(Operation.GROUP_BY)
     def groupBy(self, *cols, **kwargs) -> GROUP_DATA:
+        if cols and isinstance(cols[0], list):
+            cols = cols[0]  # type: ignore
         columns = self._ensure_and_normalize_cols(cols)
         return self._group_data(self, columns, self.last_op)
 
@@ -1084,7 +1086,7 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
                     for left_col, right_col in join_column_pairs
                 ]
                 # To match spark behavior only the join clause gets deduplicated and it gets put in the front of the column list
-                select_column_names = [
+                select_column_names: list[str | Column] = [
                     (
                         column.alias_or_name
                         if not isinstance(column.expression.this, exp.Star)

sqlframe/base/decorators.py

@@ -1,19 +1,23 @@
-from __future__ import annotations
-
+import functools
 import re
 import typing as t
 
 from sqlglot import exp
 from sqlglot.helper import ensure_list
+from typing_extensions import ParamSpec
 
 from sqlframe.base.column import Column
 
-CALLING_CLASS = t.TypeVar("CALLING_CLASS")
+P = ParamSpec("P")
+T = t.TypeVar("T")
 
 
-def func_metadata(unsupported_engines: t.Optional[t.Union[str, t.List[str]]] = None) -> t.Callable:
-    def _metadata(func: t.Callable) -> t.Callable:
-        def wrapper(*args, **kwargs):
+def func_metadata(
+    unsupported_engines: t.Optional[t.Union[str, t.List[str]]] = None,
+) -> t.Callable[[t.Callable[P, T]], t.Callable[P, T]]:
+    def _metadata(func: t.Callable[P, T]) -> t.Callable[P, T]:
+        @functools.wraps(func)
+        def wrapper(*args: P.args, **kwargs: P.kwargs) -> T:
             funcs_to_not_auto_alias = [
                 "posexplode",
                 "explode_outer",
@@ -34,14 +38,17 @@ def func_metadata(unsupported_engines: t.Optional[t.Union[str, t.List[str]]] = N
                 and not isinstance(result.expression, exp.Alias)
                 and func.__name__ not in funcs_to_not_auto_alias
             ):
-                col_name = result.column_expression.find(exp.Identifier)
-                if col_name:
-                    col_name = col_name.name
+                col_name = ""
+                col_name_exp: t.Optional[exp.Expression] = result.column_expression.find(
+                    exp.Identifier
+                )
+                if col_name_exp:
+                    col_name = col_name_exp.name
                 else:
-                    col_name = result.column_expression.find(exp.Literal)
-                    if col_name:
-                        col_name = col_name.this
-                alias_name = f"{func.__name__}__{col_name or ''}__"
+                    col_name_exp = result.column_expression.find(exp.Literal)
+                    if col_name_exp:
+                        col_name = col_name_exp.this
+                alias_name = f"{func.__name__}__{col_name}__"
                 # BigQuery has restrictions on alias names so we constrain it to alphanumeric characters and underscores
                 return result.alias(re.sub(r"\W", "_", alias_name))  # type: ignore
             return result

sqlframe/base/functions.py

@@ -3481,12 +3481,9 @@ def hll_union(
     +------------+
     """
     if allowDifferentLgConfigK is not None:
-        allowDifferentLgConfigK = (
-            lit(allowDifferentLgConfigK)
-            if isinstance(allowDifferentLgConfigK, bool)
-            else allowDifferentLgConfigK
+        return Column.invoke_anonymous_function(
+            col1, "hll_union", col2, lit(allowDifferentLgConfigK)
         )
-        return Column.invoke_anonymous_function(col1, "hll_union", col2, allowDifferentLgConfigK)  # type: ignore
     else:
         return Column.invoke_anonymous_function(col1, "hll_union", col2)
 

sqlframe/base/group.py

@@ -47,7 +47,10 @@ class _BaseGroupedData(t.Generic[DF]):
         from sqlframe.base.column import Column
 
         columns = (
-            [Column(f"{agg_func}({column_name})") for column_name, agg_func in exprs[0].items()]
+            [
+                self._get_function_applied_columns(agg_func, (column_name,))[0]
+                for column_name, agg_func in exprs[0].items()
+            ]
             if isinstance(exprs[0], dict)
             else exprs
         )
@@ -55,7 +58,8 @@ class _BaseGroupedData(t.Generic[DF]):
 
         if not self.group_by_cols or not isinstance(self.group_by_cols[0], (list, tuple, set)):
             expression = self._df.expression.group_by(
-                *[x.expression for x in self.group_by_cols]  # type: ignore
+                # User column_expression for group by to avoid alias in group by
+                *[x.column_expression for x in self.group_by_cols]  # type: ignore
             ).select(*[x.expression for x in self.group_by_cols + cols], append=False)  # type: ignore
             group_by_cols = self.group_by_cols
         else:
@@ -66,7 +70,7 @@ class _BaseGroupedData(t.Generic[DF]):
             group_by_cols = []
             for grouping_set in self.group_by_cols:
                 all_grouping_sets.append(
-                    exp.Tuple(expressions=[x.expression for x in grouping_set])  # type: ignore
+                    exp.Tuple(expressions=[x.column_expression for x in grouping_set])  # type: ignore
                 )
                 group_by_cols.extend(grouping_set)  # type: ignore
             group_by_cols = list(dict.fromkeys(group_by_cols))

{sqlframe-3.27.1.dist-info → sqlframe-3.28.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.27.1
+Version: 3.28.1
 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 <26.12,>=24.0.0
+Requires-Dist: sqlglot <26.13,>=24.0.0
 Requires-Dist: typing-extensions
 Provides-Extra: bigquery
 Requires-Dist: google-cloud-bigquery-storage <3,>=2 ; extra == 'bigquery'

{sqlframe-3.27.1.dist-info → sqlframe-3.28.1.dist-info}/RECORD

@@ -1,16 +1,16 @@
 sqlframe/__init__.py,sha256=SB80yLTITBXHI2GCDS6n6bN5ObHqgPjfpRPAUwxaots,3403
-sqlframe/_version.py,sha256=ZAp4ahp_nzqXiTlSnHrC3b9ZrxOfEiZs09wNO5x1QHo,513
+sqlframe/_version.py,sha256=A-DozXRgJ1GLBl_eHEhQbTd1M98mV_YRq5bK5pd8Y5s,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
 sqlframe/base/catalog.py,sha256=ZuU_qmt4yjSoTYgecSGnOhitOdh3rJbGCUjnUBp5mlc,38564
 sqlframe/base/column.py,sha256=AG9Z_6RNhVxLhLU29kRCgzMgDNSm-_GFg96xLqk1-bs,19838
-sqlframe/base/dataframe.py,sha256=OgEUlDI5Y4rWrVngW5LttCUMC40WR-Pyr5af6aqbMNU,84028
-sqlframe/base/decorators.py,sha256=ms-CvDOIW3T8IVB9VqDmLwAiaEsqXLYRXEqVQaxktiM,1890
+sqlframe/base/dataframe.py,sha256=YaXf2rixLRz8CIqyH__XZNz6zhtW3cLwJcHMezUv_BU,84138
+sqlframe/base/decorators.py,sha256=IhE5xNQDkwJHacCvulq5WpUKyKmXm7dL2A3o5WuKGP4,2131
 sqlframe/base/exceptions.py,sha256=9Uwvqn2eAkDpqm4BrRgbL61qM-GMCbJEMAW8otxO46s,370
 sqlframe/base/function_alternatives.py,sha256=Bs1bwl25fN3Yy9rb4GnUWBGunQ1C_yelkb2yV9DSZIY,53918
-sqlframe/base/functions.py,sha256=mazXkUuyvs_8YWD_ssesDXPO0TZ2sIjvUsaeUpIeNE0,224343
-sqlframe/base/group.py,sha256=4R9sOZm4ZRlTfShq2j3_HQOiL_Tj1bYkouenYsgnlII,4115
+sqlframe/base/functions.py,sha256=Rc9GfD3tIDg73FPqBAgqIDlrxH-A1c-ZWO76bcViX3w,224169
+sqlframe/base/group.py,sha256=OY4w1WRsCqLgW-Pi7DjF63zbbxSLISCF3qjAbzI2CQ4,4283
 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
@@ -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-3.27.1.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-3.27.1.dist-info/METADATA,sha256=WxKSgFqAdUeUmo7Jtln6JLRZsz950oGjDzM7uyFJUig,8971
-sqlframe-3.27.1.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-sqlframe-3.27.1.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-3.27.1.dist-info/RECORD,,
+sqlframe-3.28.1.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-3.28.1.dist-info/METADATA,sha256=Uj6Y7-cFVwC36CpmSaZLn3Ual76hfPkqr2jjF7TqFLg,8971
+sqlframe-3.28.1.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+sqlframe-3.28.1.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-3.28.1.dist-info/RECORD,,