sqlframe 3.39.3__py3-none-any.whl → 3.39.4__py3-none-any.whl

sqlframe/_version.py

@@ -28,7 +28,7 @@ version_tuple: VERSION_TUPLE
 commit_id: COMMIT_ID
 __commit_id__: COMMIT_ID
 
-__version__ = version = '3.39.3'
-__version_tuple__ = version_tuple = (3, 39, 3)
+__version__ = version = '3.39.4'
+__version_tuple__ = version_tuple = (3, 39, 4)
 
-__commit_id__ = commit_id = 'g9d915cb1e'
+__commit_id__ = commit_id = 'g7103a1e73'

sqlframe/base/dataframe.py

@@ -16,7 +16,6 @@ from dataclasses import dataclass
 from uuid import uuid4
 
 import sqlglot
-from more_itertools import partition
 from prettytable import PrettyTable
 from sqlglot import Dialect, maybe_parse
 from sqlglot import expressions as exp
@@ -542,23 +541,16 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
         expression.set("with", exp.With(expressions=existing_ctes))
         return expression
 
-    @classmethod
-    def _get_outer_select_expressions(
-        cls, item: exp.Expression
-    ) -> t.List[t.Union[exp.Column, exp.Alias]]:
-        outer_select = item.find(exp.Select)
-        if outer_select:
-            return outer_select.expressions
-        return []
-
     @classmethod
     def _get_outer_select_columns(cls, item: exp.Expression) -> t.List[Column]:
         from sqlframe.base.session import _BaseSession
 
         col = get_func_from_session("col", _BaseSession())
 
-        outer_expressions = cls._get_outer_select_expressions(item)
-        return [col(quote_preserving_alias_or_name(x)) for x in outer_expressions]
+        outer_select = item.find(exp.Select)
+        if outer_select:
+            return [col(quote_preserving_alias_or_name(x)) for x in outer_select.expressions]
+        return []
 
     def _create_hash_from_expression(self, expression: exp.Expression) -> str:
         from sqlframe.base.session import _BaseSession
@@ -1512,23 +1504,20 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
         """
         return func(self, *args, **kwargs)  # type: ignore
 
-    @operation(Operation.SELECT_CONSTRAINED)
+    @operation(Operation.SELECT)
     def withColumn(self, colName: str, col: Column) -> Self:
         return self.withColumns.__wrapped__(self, {colName: col})  # type: ignore
 
-    @operation(Operation.SELECT_CONSTRAINED)
+    @operation(Operation.SELECT)
     def withColumnRenamed(self, existing: str, new: str) -> Self:
-        col_func = get_func_from_session("col", self.session)
         expression = self.expression.copy()
         existing = self.session._normalize_string(existing)
-        outer_expressions = self._get_outer_select_expressions(expression)
+        columns = self._get_outer_select_columns(expression)
         results = []
         found_match = False
-        for expr in outer_expressions:
-            column = col_func(expr.copy())
-            if existing == quote_preserving_alias_or_name(expr):
-                if isinstance(column.expression, exp.Alias):
-                    column.expression.set("alias", exp.to_identifier(new))
+        for column in columns:
+            if column.alias_or_name == existing:
+                column = column.alias(new)
                 self._update_display_name_mapping([column], [new])
                 found_match = True
             results.append(column)
@@ -1536,7 +1525,7 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
             raise ValueError("Tried to rename a column that doesn't exist")
         return self.select.__wrapped__(self, *results, skip_update_display_name_mapping=True)  # type: ignore
 
-    @operation(Operation.SELECT_CONSTRAINED)
+    @operation(Operation.SELECT)
     def withColumnsRenamed(self, colsMap: t.Dict[str, str]) -> Self:
         """
         Returns a new :class:`DataFrame` by renaming multiple columns. If a non-existing column is
@@ -1582,7 +1571,7 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
 
         return self.select.__wrapped__(self, *results, skip_update_display_name_mapping=True)  # type: ignore
 
-    @operation(Operation.SELECT_CONSTRAINED)
+    @operation(Operation.SELECT)
     def withColumns(self, *colsMap: t.Dict[str, Column]) -> Self:
         """
         Returns a new :class:`DataFrame` by adding multiple columns or replacing the
@@ -1620,14 +1609,13 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
         """
         if len(colsMap) != 1:
             raise ValueError("Only a single map is supported")
-        col_func = get_func_from_session("col")
         col_map = {
             self._ensure_and_normalize_col(k): (self._ensure_and_normalize_col(v), k)
             for k, v in colsMap[0].items()
         }
-        existing_expr = self._get_outer_select_expressions(self.expression)
-        existing_col_names = [x.alias_or_name for x in existing_expr]
-        select_columns = [col_func(x) for x in existing_expr]
+        existing_cols = self._get_outer_select_columns(self.expression)
+        existing_col_names = [x.alias_or_name for x in existing_cols]
+        select_columns = existing_cols
         for col, (col_value, display_name) in col_map.items():
             column_name = col.alias_or_name
             existing_col_index = (
@@ -1644,7 +1632,7 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
         )
         return self.select.__wrapped__(self, *select_columns, skip_update_display_name_mapping=True)  # type: ignore
 
-    @operation(Operation.SELECT_CONSTRAINED)
+    @operation(Operation.SELECT)
     def drop(self, *cols: t.Union[str, Column]) -> Self:
         # Separate string column names from Column objects for different handling
         column_objs, column_names = partition_to(lambda x: isinstance(x, str), cols, list, set)

sqlframe/base/functions.py

@@ -37,9 +37,7 @@ def _get_session() -> _BaseSession:
 
 @meta()
 def col(column_name: t.Union[ColumnOrName, t.Any]) -> Column:
-    from sqlframe.base.session import _BaseSession
-
-    dialect = _BaseSession().input_dialect
+    dialect = _get_session().input_dialect
     if isinstance(column_name, str):
         col_expression = expression.to_column(column_name, dialect=dialect).transform(
             dialect.normalize_identifier
@@ -662,9 +660,7 @@ def grouping_id(*cols: ColumnOrName) -> Column:
 
 @meta()
 def input_file_name() -> Column:
-    from sqlframe.base.session import _BaseSession
-
-    return Column(expression.Literal.string(_BaseSession()._last_loaded_file or ""))
+    return Column(expression.Literal.string(_get_session()._last_loaded_file or ""))
 
 
 @meta()
@@ -959,12 +955,10 @@ def current_timestamp() -> Column:
 
 @meta()
 def date_format(col: ColumnOrName, format: str) -> Column:
-    from sqlframe.base.session import _BaseSession
-
     return Column.invoke_expression_over_column(
         Column(expression.TimeStrToTime(this=Column.ensure_col(col).column_expression)),
         expression.TimeToStr,
-        format=_BaseSession().format_time(format),
+        format=_get_session().format_time(format),
     )
 
 
@@ -3378,10 +3372,9 @@ def get(col: ColumnOrName, index: t.Union[ColumnOrName, int]) -> Column:
 def get_active_spark_context() -> SparkContext:
     """Raise RuntimeError if SparkContext is not initialized,
     otherwise, returns the active SparkContext."""
-    from sqlframe.base.session import _BaseSession
     from sqlframe.spark.session import SparkSession
 
-    session: _BaseSession = _BaseSession()
+    session = _get_session()
     if not isinstance(session, SparkSession):
         raise RuntimeError("This function is only available in SparkSession.")
     return session.spark_session.sparkContext
@@ -6344,7 +6337,7 @@ def to_unix_timestamp(
     session = _get_session()
 
     if session._is_duckdb:
-        format = format or _BaseSession().default_time_format
+        format = format or session.default_time_format
         timestamp = Column.ensure_col(timestamp).cast("string")
 
     if format is not None:

sqlframe/base/operations.py

@@ -27,10 +27,9 @@ class Operation(IntEnum):
     WHERE = 2
     GROUP_BY = 3
     HAVING = 4
-    SELECT_CONSTRAINED = 5
-    SELECT = 6
-    ORDER_BY = 7
-    LIMIT = 8
+    SELECT = 5
+    ORDER_BY = 6
+    LIMIT = 7
 
 
 # We want to decorate a function (self: DF, *args, **kwargs) -> T

{sqlframe-3.39.3.dist-info → sqlframe-3.39.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.39.3
+Version: 3.39.4
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman
@@ -18,7 +18,7 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: more-itertools
 Requires-Dist: prettytable <4
-Requires-Dist: sqlglot <27.9,>=24.0.0
+Requires-Dist: sqlglot <27.10,>=24.0.0
 Requires-Dist: typing-extensions
 Provides-Extra: bigquery
 Requires-Dist: google-cloud-bigquery-storage <3,>=2 ; extra == 'bigquery'

{sqlframe-3.39.3.dist-info → sqlframe-3.39.4.dist-info}/RECORD

@@ -1,18 +1,18 @@
 sqlframe/__init__.py,sha256=SB80yLTITBXHI2GCDS6n6bN5ObHqgPjfpRPAUwxaots,3403
-sqlframe/_version.py,sha256=Vixv4hfZnHHXCXSmZD4wlHJUBkhCMzDLIyo5HqkJdes,714
+sqlframe/_version.py,sha256=RTACos9x6Q52oWKZxADQ1aU73aw2iil2MarQYuwWMsM,714
 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=-YulM2BMK8MoWbXi05AsJIPxd4AuiZDBCZuk4HoeMlE,38900
 sqlframe/base/column.py,sha256=f6rK6-hTiNx9WwJP7t6tqL3xEC2gwERPDlhWCS5iCBw,21417
-sqlframe/base/dataframe.py,sha256=HHjDaeap4_w4HRRj87lhQjFTczxLKhFD8b-9vhK2KsY,87592
+sqlframe/base/dataframe.py,sha256=-jeoqP5jS8Rk1fp_Og9ie_e2fjo19uX7JVpi9PeU5qI,86943
 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=RVNoRzM19BUwypdc0izYrrQe2Fe4_e9SbtpDkdD2bec,227981
+sqlframe/base/functions.py,sha256=lMwNtOAj7MbmaFtweo5N8DJp-8ent1fT6lr3J3YcQsA,227753
 sqlframe/base/group.py,sha256=fBm8EUve7W7xz11nybTXr09ih-yZxL_vvEiZVE1eb_0,12025
 sqlframe/base/normalize.py,sha256=nXAJ5CwxVf4DV0GsH-q1w0p8gmjSMlv96k_ez1eVul8,3880
-sqlframe/base/operations.py,sha256=8dkMNqjG3xP1w_6euAj8FpwweD7t590HYjoeoCr5LqI,4465
+sqlframe/base/operations.py,sha256=g-YNcbvNKTOBbYm23GKfB3fmydlR7ZZDAuZUtXIHtzw,4438
 sqlframe/base/readerwriter.py,sha256=Nb2VJ_HBmLQp5mK8JhnFooZh2ydAaboCAFVPb-4MNX4,31241
 sqlframe/base/session.py,sha256=99X-ShK9ohHCX6WdIJs0HhjfK23snaE3Gv6RYc5wqUI,27687
 sqlframe/base/table.py,sha256=rCeh1W5SWbtEVfkLAUiexzrZwNgmZeptLEmLcM1ABkE,6961
@@ -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-3.39.3.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-3.39.3.dist-info/METADATA,sha256=eyKm8nGawKAujUOiCBn4PEFpSh_UzsnEV7LpKQVecRM,9069
-sqlframe-3.39.3.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-sqlframe-3.39.3.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-3.39.3.dist-info/RECORD,,
+sqlframe-3.39.4.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-3.39.4.dist-info/METADATA,sha256=wv8nBkcg2ofsdZYo3qC0g8q_-QR_flvR1YPoKQ6uGeU,9070
+sqlframe-3.39.4.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+sqlframe-3.39.4.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-3.39.4.dist-info/RECORD,,