sqlframe 3.34.0__py3-none-any.whl → 3.35.1__py3-none-any.whl

sqlframe/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.34.0'
-__version_tuple__ = version_tuple = (3, 34, 0)
+__version__ = version = '3.35.1'
+__version_tuple__ = version_tuple = (3, 35, 1)

sqlframe/base/dataframe.py

@@ -1524,6 +1524,52 @@ 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)
+    def withColumnsRenamed(self, colsMap: t.Dict[str, str]) -> Self:
+        """
+        Returns a new :class:`DataFrame` by renaming multiple columns. If a non-existing column is
+        provided, it will be silently ignored.
+
+        .. versionadded:: 3.5.0
+
+        Parameters
+        ----------
+        colsMap : dict
+            a dict of column name and new column name.
+
+        Returns
+        -------
+        :class:`DataFrame`
+            DataFrame with renamed columns.
+
+        Examples
+        --------
+        >>> df = spark.createDataFrame([(2, "Alice"), (5, "Bob")], schema=["age", "name"])
+        >>> df.withColumnsRenamed({"age": "years", "name": "firstName"}).show()
+        +-----+---------+
+        |years|firstName|
+        +-----+---------+
+        |    2|    Alice|
+        |    5|      Bob|
+        +-----+---------+
+        """
+        expression = self.expression.copy()
+        columns = self._get_outer_select_columns(expression)
+        results = []
+
+        # Normalize the keys in colsMap
+        normalized_cols_map = {self.session._normalize_string(k): v for k, v in colsMap.items()}
+
+        for column in columns:
+            col_name = column.alias_or_name
+            if col_name in normalized_cols_map:
+                new_name = normalized_cols_map[col_name]
+                column = column.alias(new_name)
+                self._update_display_name_mapping([column], [new_name])
+            results.append(column)
+
+        return self.select.__wrapped__(self, *results, skip_update_display_name_mapping=True)  # type: ignore
+
     @operation(Operation.SELECT)
     def withColumns(self, *colsMap: t.Dict[str, Column]) -> Self:
         """

sqlframe/base/function_alternatives.py

@@ -999,27 +999,6 @@ def element_at_using_brackets(col: ColumnOrName, value: ColumnOrLiteral) -> Colu
     )
 
 
-def array_remove_using_filter(col: ColumnOrName, value: ColumnOrLiteral) -> Column:
-    lit = get_func_from_session("lit")
-    col_func = get_func_from_session("col")
-
-    value = value if isinstance(value, Column) else lit(value)
-    return Column(
-        expression.Anonymous(
-            this="LIST_FILTER",
-            expressions=[
-                col_func(col).column_expression,
-                expression.Lambda(
-                    this=expression.NEQ(
-                        this=expression.Identifier(this="x"), expression=value.column_expression
-                    ),
-                    expressions=[expression.Identifier(this="x")],
-                ),
-            ],
-        )
-    )
-
-
 def array_union_using_list_concat(col1: ColumnOrName, col2: ColumnOrName) -> Column:
     col_func = get_func_from_session("col")
 
@@ -1664,41 +1643,6 @@ def array_position_bgutil(col: ColumnOrName, value: ColumnOrLiteral) -> Column:
     )
 
 
-def array_remove_bgutil(col: ColumnOrName, value: ColumnOrLiteral) -> Column:
-    lit = get_func_from_session("lit")
-
-    value_col = value if isinstance(value, Column) else lit(value)
-
-    filter_subquery = expression.select(
-        "*",
-    ).from_(
-        expression.Unnest(
-            expressions=[Column.ensure_col(col).column_expression],
-            alias=expression.TableAlias(
-                columns=[expression.to_identifier("x")],
-            ),
-        )
-    )
-
-    agg_subquery = (
-        expression.select(
-            expression.Anonymous(
-                this="ARRAY_AGG",
-                expressions=[expression.column("x")],
-            ),
-        )
-        .from_(filter_subquery.subquery("t"))
-        .where(
-            expression.NEQ(
-                this=expression.column("x", "t"),
-                expression=value_col.column_expression,
-            )
-        )
-    )
-
-    return Column(agg_subquery.subquery())
-
-
 def array_distinct_bgutil(col: ColumnOrName) -> Column:
     return Column(
         expression.Anonymous(

sqlframe/base/functions.py

@@ -2268,21 +2268,10 @@ def element_at(col: ColumnOrName, value: ColumnOrLiteral) -> Column:
 
 @meta()
 def array_remove(col: ColumnOrName, value: ColumnOrLiteral) -> Column:
-    from sqlframe.base.function_alternatives import (
-        array_remove_bgutil,
-        array_remove_using_filter,
-    )
-
-    session = _get_session()
-
-    if session._is_bigquery:
-        return array_remove_bgutil(col, value)
-
-    if session._is_duckdb:
-        return array_remove_using_filter(col, value)
-
     value_col = value if isinstance(value, Column) else lit(value)
-    return Column.invoke_anonymous_function(col, "ARRAY_REMOVE", value_col)
+    return Column.invoke_expression_over_column(
+        col, expression.ArrayRemove, expression=value_col.column_expression
+    )
 
 
 @meta(unsupported_engines="postgres")

sqlframe/base/types.py

@@ -104,22 +104,22 @@ class FloatType(DataType):
 
 
 class ByteType(DataType):
-    def __str__(self) -> str:
+    def simpleString(self) -> str:
         return "tinyint"
 
 
 class IntegerType(DataType):
-    def __str__(self) -> str:
+    def simpleString(self) -> str:
         return "int"
 
 
 class LongType(DataType):
-    def __str__(self) -> str:
+    def simpleString(self) -> str:
         return "bigint"
 
 
 class ShortType(DataType):
-    def __str__(self) -> str:
+    def simpleString(self) -> str:
         return "smallint"
 
 

sqlframe/bigquery/session.py

@@ -51,7 +51,7 @@ class BigQuerySession(
             super().__init__(conn or connect())
             if self._client.default_query_job_config is None:
                 self._client.default_query_job_config = bigquery.QueryJobConfig()
-            self.default_dataset = default_dataset
+            self.default_dataset = default_dataset  # type: ignore
 
     @property
     def _client(self) -> BigQueryClient:

{sqlframe-3.34.0.dist-info → sqlframe-3.35.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.34.0
+Version: 3.35.1
 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 <26.22,>=24.0.0
+Requires-Dist: sqlglot <26.26,>=24.0.0
 Requires-Dist: typing-extensions
 Provides-Extra: bigquery
 Requires-Dist: google-cloud-bigquery-storage <3,>=2 ; extra == 'bigquery'
@@ -27,7 +27,7 @@ Requires-Dist: databricks-sql-connector[pyarrow] <5,>=3.6 ; extra == 'databricks
 Provides-Extra: dev
 Requires-Dist: duckdb <1.4,>=1.2 ; extra == 'dev'
 Requires-Dist: findspark <3,>=2 ; extra == 'dev'
-Requires-Dist: mypy <1.16,>=1.10.0 ; extra == 'dev'
+Requires-Dist: mypy <1.17,>=1.10.0 ; extra == 'dev'
 Requires-Dist: openai <2,>=1.30 ; extra == 'dev'
 Requires-Dist: pandas-stubs <3,>=2 ; extra == 'dev'
 Requires-Dist: pandas <3,>=2 ; extra == 'dev'
@@ -38,7 +38,7 @@ 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 <8.4,>=8.2.0 ; extra == 'dev'
+Requires-Dist: pytest <8.5,>=8.2.0 ; extra == 'dev'
 Requires-Dist: ruff <0.12,>=0.4.4 ; extra == 'dev'
 Requires-Dist: types-psycopg2 <3,>=2.9 ; extra == 'dev'
 Provides-Extra: docs

{sqlframe-3.34.0.dist-info → sqlframe-3.35.1.dist-info}/RECORD

@@ -1,15 +1,15 @@
 sqlframe/__init__.py,sha256=SB80yLTITBXHI2GCDS6n6bN5ObHqgPjfpRPAUwxaots,3403
-sqlframe/_version.py,sha256=TDHrtjzk60_8g7Xp1dLjvarUF8D5EEPwDjuqMz2FD-8,513
+sqlframe/_version.py,sha256=kPcRtrGIJvBSXjEXIsPZ4vA33McEBwn6hXm6zOraFmM,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=-YulM2BMK8MoWbXi05AsJIPxd4AuiZDBCZuk4HoeMlE,38900
 sqlframe/base/column.py,sha256=5ZnZcn6gCCrAL53-EEHxVQWXG2oijN3RCOhlWmsjbJM,21147
-sqlframe/base/dataframe.py,sha256=6L8xTdwwQCkUzpJ6K3QlCcz5zqk2QQmGzteI-1EJ23A,84374
+sqlframe/base/dataframe.py,sha256=0diYONDlet8iZt49LC3vcmfXHAAZ2MovPL2pTXYHj2U,85974
 sqlframe/base/decorators.py,sha256=IhE5xNQDkwJHacCvulq5WpUKyKmXm7dL2A3o5WuKGP4,2131
 sqlframe/base/exceptions.py,sha256=9Uwvqn2eAkDpqm4BrRgbL61qM-GMCbJEMAW8otxO46s,370
-sqlframe/base/function_alternatives.py,sha256=dEymHSOQgUzhoYtfY5acC9AxpMoGoHXX7v6yTadKzn8,53527
-sqlframe/base/functions.py,sha256=3tV8RPgmzNs8Cz0SeUmvCCMxZGpgAGMbUnYBCPbArRU,226241
+sqlframe/base/function_alternatives.py,sha256=EKtDgYyaJSfaSfhs_IemDkpy6VK2E8V6fDvjAqKR_tM,51880
+sqlframe/base/functions.py,sha256=geB8QRQvyOipB3v_gOC5KhhB--UpKJH0z2dbyRNCNaI,225983
 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
@@ -17,7 +17,7 @@ sqlframe/base/readerwriter.py,sha256=Nb2VJ_HBmLQp5mK8JhnFooZh2ydAaboCAFVPb-4MNX4
 sqlframe/base/session.py,sha256=djXPmuW0cIQYuoE7hegfyvZuKC2D3ABZCjvw-fa1C24,27260
 sqlframe/base/table.py,sha256=rCeh1W5SWbtEVfkLAUiexzrZwNgmZeptLEmLcM1ABkE,6961
 sqlframe/base/transforms.py,sha256=y0j3SGDz3XCmNGrvassk1S-owllUWfkHyMgZlY6SFO4,467
-sqlframe/base/types.py,sha256=iBNk9bpFtb2NBIogYS8i7OlQZMRvpR6XxqzBebsjQDU,12280
+sqlframe/base/types.py,sha256=0gebYkJUtaijaqBis2uqE3CRr3PfVTriwyUJ9-7ly_0,12300
 sqlframe/base/udf.py,sha256=O6hMhBUy9NVv-mhJRtfFhXTIa_-Z8Y_FkmmuOHu0l90,1117
 sqlframe/base/util.py,sha256=gv_kRc3LxCuQy3t4dHFldV7elB8RU5PMqIN5-xSkWSo,19107
 sqlframe/base/window.py,sha256=7NaKDTlhun-95LEghukBCjFBwq0RHrPaajWQNCsLxok,4818
@@ -34,7 +34,7 @@ sqlframe/bigquery/functions.py,sha256=MYLs6-sXXqe5o6ghJHHtEpFJlYMeyKzx9-rT3wwXlc
 sqlframe/bigquery/functions.pyi,sha256=KXgV46eZFNIXwXIhPuSJ08BG18iLQzDCQjyI3REBEXg,11925
 sqlframe/bigquery/group.py,sha256=UVBNBRTo8OqS-_cS5YwvTeJYgYxeG-d6R3kfyHmlFqw,391
 sqlframe/bigquery/readwriter.py,sha256=2uQhGe0THiLPb-_NF5jDdbizwjYJk854MuhEcnLghaE,949
-sqlframe/bigquery/session.py,sha256=5-SNh1sHd4Q6zPEmlinL9LLwsqlzBTqT-ZNRAFpU1_s,2931
+sqlframe/bigquery/session.py,sha256=89aFgFkN7tknJUaNRP9XK0C8vyvfDymV1dDarkjkqsY,2947
 sqlframe/bigquery/table.py,sha256=pSSRFeKcStyFuE1B4uiheP22tHHq5SdQ-uuaNQpbsfI,661
 sqlframe/bigquery/types.py,sha256=KwNyuXIo-2xVVd4bZED3YrQOobKCtemlxGrJL7DrTC8,34
 sqlframe/bigquery/udf.py,sha256=ZZ1-P1zWZhQqmhBqwAxfNeKl31nDkkZgkuz7Dn28P_0,264
@@ -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-3.34.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-3.34.0.dist-info/METADATA,sha256=qg2s46Gb6gGCR5eB3HYrRvdx0BSE4QEmhaKsLl0vfOM,8987
-sqlframe-3.34.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-sqlframe-3.34.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-3.34.0.dist-info/RECORD,,
+sqlframe-3.35.1.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-3.35.1.dist-info/METADATA,sha256=T1Zjv7wX8XssCXYaXa0mrRAR8Br1Udv8Brw0ZqeWj3I,8987
+sqlframe-3.35.1.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+sqlframe-3.35.1.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-3.35.1.dist-info/RECORD,,