sqlframe 3.35.1__py3-none-any.whl → 3.36.0__py3-none-any.whl

sqlframe/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.35.1'
-__version_tuple__ = version_tuple = (3, 35, 1)
+__version__ = version = '3.36.0'
+__version_tuple__ = version_tuple = (3, 36, 0)

sqlframe/base/function_alternatives.py

@@ -1300,10 +1300,6 @@ def day_with_try_to_timestamp(col: ColumnOrName) -> Column:
     )
 
 
-def endswith_with_underscore(str: ColumnOrName, suffix: ColumnOrName) -> Column:
-    return Column.invoke_anonymous_function(str, "ENDS_WITH", suffix)
-
-
 def endswith_using_like(str: ColumnOrName, suffix: ColumnOrName) -> Column:
     concat = get_func_from_session("concat")
     lit = get_func_from_session("lit")

sqlframe/base/functions.py

@@ -2288,14 +2288,14 @@ def array_distinct(col: ColumnOrName) -> Column:
 
 @meta(unsupported_engines=["bigquery", "postgres"])
 def array_intersect(col1: ColumnOrName, col2: ColumnOrName) -> Column:
-    from sqlframe.base.function_alternatives import array_intersect_using_intersection
-
-    session = _get_session()
-
-    if session._is_snowflake:
-        return array_intersect_using_intersection(col1, col2)
-
-    return Column.invoke_anonymous_function(col1, "ARRAY_INTERSECT", Column.ensure_col(col2))
+    return Column(
+        expression.ArrayIntersect(
+            expressions=[
+                Column.ensure_col(col1).column_expression,
+                Column.ensure_col(col2).column_expression,
+            ]
+        )
+    )
 
 
 @meta(unsupported_engines=["postgres"])
@@ -3226,18 +3226,16 @@ def elt(*inputs: ColumnOrName) -> Column:
 def endswith(str: ColumnOrName, suffix: ColumnOrName) -> Column:
     from sqlframe.base.function_alternatives import (
         endswith_using_like,
-        endswith_with_underscore,
     )
 
     session = _get_session()
 
-    if session._is_bigquery or session._is_duckdb:
-        return endswith_with_underscore(str, suffix)
-
     if session._is_postgres:
         return endswith_using_like(str, suffix)
 
-    return Column.invoke_anonymous_function(str, "endswith", suffix)
+    return Column.invoke_expression_over_column(
+        str, expression.EndsWith, expression=Column.ensure_col(suffix).column_expression
+    )
 
 
 @meta(unsupported_engines="*")
@@ -5655,10 +5653,9 @@ def replace(
     ):
         replace = expression.Literal.string("")  # type: ignore
 
-    if replace is not None:
-        return Column.invoke_anonymous_function(src, "replace", search, replace)
-    else:
-        return Column.invoke_anonymous_function(src, "replace", search)
+    return Column.invoke_expression_over_column(
+        src, expression.Replace, expression=search, replacement=replace
+    )
 
 
 @meta()

sqlframe/base/group.py

@@ -2,10 +2,16 @@
 
 from __future__ import annotations
 
+import sys
 import typing as t
 
 from sqlframe.base.operations import Operation, group_operation, operation
 
+if sys.version_info >= (3, 11):
+    from typing import Self
+else:
+    from typing_extensions import Self
+
 if t.TYPE_CHECKING:
     from sqlframe.base.column import Column
     from sqlframe.base.session import DF
@@ -28,6 +34,8 @@ class _BaseGroupedData(t.Generic[DF]):
         self.session = df.session
         self.last_op = last_op
         self.group_by_cols = group_by_cols
+        self.pivot_col: t.Optional[str] = None
+        self.pivot_values: t.Optional[t.List[t.Any]] = None
 
     def _get_function_applied_columns(
         self, func_name: str, cols: t.Tuple[str, ...]
@@ -56,6 +64,79 @@ class _BaseGroupedData(t.Generic[DF]):
         )
         cols = self._df._ensure_and_normalize_cols(columns)
 
+        # Handle pivot transformation
+        if self.pivot_col is not None and self.pivot_values is not None:
+            from sqlglot import exp
+
+            from sqlframe.base import functions as F
+
+            # Build the pivot expression
+            # First, we need to convert the DataFrame to include the pivot logic
+            df = self._df.copy()
+
+            # Create the base query with group by columns, pivot column, and aggregation columns
+            select_cols = []
+            # Add group by columns
+            for col in self.group_by_cols:
+                select_cols.append(col.expression)  # type: ignore
+            # Add pivot column
+            select_cols.append(Column.ensure_col(self.pivot_col).expression)
+            # Add the value columns that will be aggregated
+            for agg_col in cols:
+                # Extract the column being aggregated from the aggregation function
+                # For example, from SUM(earnings), we want to extract 'earnings'
+                if (
+                    isinstance(agg_col.column_expression, exp.AggFunc)
+                    and agg_col.column_expression.this
+                ):
+                    if agg_col.column_expression.this not in select_cols:
+                        select_cols.append(agg_col.column_expression.this)
+
+            # Create the base query
+            base_query = df.expression.select(*select_cols, append=False)
+
+            # Build pivot expression
+            pivot_expressions = []
+            for agg_col in cols:
+                if isinstance(agg_col.column_expression, exp.AggFunc):
+                    # Clone the aggregation function
+                    # Snowflake doesn't support alias in the pivot, so we need to use the column_expression
+                    agg_func = (
+                        agg_col.column_expression.copy()
+                        if self.session._is_snowflake
+                        else agg_col.expression.copy()
+                    )
+                    pivot_expressions.append(agg_func)
+
+            # Create the IN clause with pivot values
+            in_values = []
+            for v in self.pivot_values:
+                if isinstance(v, str):
+                    in_values.append(exp.Literal.string(v))
+                else:
+                    in_values.append(exp.Literal.number(v))
+
+            # Build the pivot node with the fields parameter
+            pivot = exp.Pivot(
+                expressions=pivot_expressions,
+                fields=[
+                    exp.In(
+                        this=Column.ensure_col(self.pivot_col).column_expression,
+                        expressions=in_values,
+                    )
+                ],
+            )
+
+            # Create a subquery with the pivot attached
+            subquery = base_query.subquery()
+            subquery.set("pivots", [pivot])
+
+            # Create the final select from the pivoted subquery
+            expression = exp.select("*").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
@@ -104,5 +185,43 @@ class _BaseGroupedData(t.Generic[DF]):
     def sum(self, *cols: str) -> DF:
         return self.agg(*self._get_function_applied_columns("sum", cols))
 
-    def pivot(self, *cols: str) -> DF:
-        raise NotImplementedError("Sum distinct is not currently implemented")
+    def pivot(self, pivot_col: str, values: t.Optional[t.List[t.Any]] = None) -> Self:
+        """
+        Pivots a column of the current DataFrame and perform the specified aggregation.
+
+        There are two versions of the pivot function: one that requires the caller
+        to specify the list of distinct values to pivot on, and one that does not.
+        The latter is more concise but less efficient, because Spark needs to first
+        compute the list of distinct values internally.
+
+        Parameters
+        ----------
+        pivot_col : str
+            Name of the column to pivot.
+        values : list, optional
+            List of values that will be translated to columns in the output DataFrame.
+
+        Returns
+        -------
+        GroupedData
+            Returns self to allow chaining with aggregation methods.
+        """
+        if self.session._is_postgres:
+            raise NotImplementedError(
+                "Pivot operation is not supported in Postgres. Please create an issue if you would like a workaround implemented."
+            )
+
+        self.pivot_col = pivot_col
+
+        if values is None:
+            # Eagerly compute distinct values
+            from sqlframe.base.column import Column
+
+            distinct_df = self._df.select(pivot_col).distinct()
+            distinct_rows = distinct_df.collect()
+            # Sort to make the results deterministic
+            self.pivot_values = sorted([row[0] for row in distinct_rows])
+        else:
+            self.pivot_values = values
+
+        return self

sqlframe/databricks/session.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
+import logging
 import typing as t
-import warnings
 
 from sqlframe.base.session import _BaseSession
 from sqlframe.databricks.catalog import DatabricksCatalog
@@ -19,6 +19,9 @@ else:
     DatabricksConnection = t.Any
 
 
+logger = logging.getLogger(__name__)
+
+
 class DatabricksSession(
     _BaseSession[  # type: ignore
         DatabricksCatalog,
@@ -43,14 +46,60 @@ class DatabricksSession(
         server_hostname: t.Optional[str] = None,
         http_path: t.Optional[str] = None,
         access_token: t.Optional[str] = None,
+        **kwargs: t.Any,
     ):
         from databricks import sql
 
+        self._conn_kwargs = (
+            {}
+            if conn
+            else {
+                "server_hostname": server_hostname,
+                "http_path": http_path,
+                "access_token": access_token,
+                "disable_pandas": True,
+                **kwargs,
+            }
+        )
+
         if not hasattr(self, "_conn"):
             super().__init__(
-                conn or sql.connect(server_hostname, http_path, access_token, disable_pandas=True)
+                conn or sql.connect(**self._conn_kwargs),
             )
 
+    def _execute(self, sql: str) -> None:
+        from databricks.sql import connect
+        from databricks.sql.exc import DatabaseError, RequestError
+
+        try:
+            super()._execute(sql)
+        except (DatabaseError, RequestError) as e:
+            logger.warning("Failed to execute query")
+            if not self._is_session_expired_error(e):
+                logger.error("Error is not related to session expiration, re-raising")
+                raise e
+            if self._conn_kwargs:
+                logger.info("Attempting to reconnect with provided connection parameters")
+                self._connection = connect(**self._conn_kwargs)
+                # Clear the cached cursor
+                if hasattr(self, "_cur"):
+                    delattr(self, "_cur")
+                super()._execute(sql)
+            else:
+                logger.error("No connection parameters provided so could not reconnect")
+                raise
+
+    def _is_session_expired_error(self, error: Exception) -> bool:
+        error_str = str(error).lower()
+        session_keywords = [
+            "invalid sessionhandle",
+            "session is closed",
+            "session expired",
+            "session not found",
+            "sessionhandle",
+        ]
+        return any(keyword in error_str for keyword in session_keywords)
+
     @classmethod
     def _try_get_map(cls, value: t.Any) -> t.Optional[t.Dict[str, t.Any]]:
         if (

{sqlframe-3.35.1.dist-info → sqlframe-3.36.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.35.1
+Version: 3.36.0
 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 <26.26,>=24.0.0
+Requires-Dist: sqlglot <26.32,>=24.0.0
 Requires-Dist: typing-extensions
 Provides-Extra: bigquery
 Requires-Dist: google-cloud-bigquery-storage <3,>=2 ; extra == 'bigquery'
@@ -39,7 +39,7 @@ 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 <8.5,>=8.2.0 ; extra == 'dev'
-Requires-Dist: ruff <0.12,>=0.4.4 ; extra == 'dev'
+Requires-Dist: ruff <0.13,>=0.4.4 ; extra == 'dev'
 Requires-Dist: types-psycopg2 <3,>=2.9 ; extra == 'dev'
 Provides-Extra: docs
 Requires-Dist: mkdocs-include-markdown-plugin ==6.0.6 ; extra == 'docs'

{sqlframe-3.35.1.dist-info → sqlframe-3.36.0.dist-info}/RECORD

@@ -1,5 +1,5 @@
 sqlframe/__init__.py,sha256=SB80yLTITBXHI2GCDS6n6bN5ObHqgPjfpRPAUwxaots,3403
-sqlframe/_version.py,sha256=kPcRtrGIJvBSXjEXIsPZ4vA33McEBwn6hXm6zOraFmM,513
+sqlframe/_version.py,sha256=bkUPQ6OdlXKrD5knIV3EChl0OWjLm_VJDu9m0db4vwg,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
@@ -8,9 +8,9 @@ sqlframe/base/column.py,sha256=5ZnZcn6gCCrAL53-EEHxVQWXG2oijN3RCOhlWmsjbJM,21147
 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=EKtDgYyaJSfaSfhs_IemDkpy6VK2E8V6fDvjAqKR_tM,51880
-sqlframe/base/functions.py,sha256=geB8QRQvyOipB3v_gOC5KhhB--UpKJH0z2dbyRNCNaI,225983
-sqlframe/base/group.py,sha256=OY4w1WRsCqLgW-Pi7DjF63zbbxSLISCF3qjAbzI2CQ4,4283
+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/normalize.py,sha256=nXAJ5CwxVf4DV0GsH-q1w0p8gmjSMlv96k_ez1eVul8,3880
 sqlframe/base/operations.py,sha256=g-YNcbvNKTOBbYm23GKfB3fmydlR7ZZDAuZUtXIHtzw,4438
 sqlframe/base/readerwriter.py,sha256=Nb2VJ_HBmLQp5mK8JhnFooZh2ydAaboCAFVPb-4MNX4,31241
@@ -47,7 +47,7 @@ sqlframe/databricks/functions.py,sha256=La8rjAwO0hD4FBO0QxW5CtZtFAPvOrVc6lG4OtPG
 sqlframe/databricks/functions.pyi,sha256=FzVBpzXCJzxIp73sIAo_R8Wx8uOJrix-W12HsgyeTcQ,23799
 sqlframe/databricks/group.py,sha256=dU3g0DVLRlfOSCamKchQFXRd1WTFbdxoXkpEX8tPD6Y,399
 sqlframe/databricks/readwriter.py,sha256=cuGRI1G627JEZgGNtirrT8LAwT6xQCdgkSAETmLKNXU,14777
-sqlframe/databricks/session.py,sha256=iw4uczkJHkpVO8vusEEmfCrhxHWyAHpCFmOZ-0qlkms,2343
+sqlframe/databricks/session.py,sha256=i2CgrLIHJb53Cx1qu_rE1-cmmm19S-Sw1MhTISX1zYU,4013
 sqlframe/databricks/table.py,sha256=Q0Vnrl5aUqnqFTQpTwfWMRyQ9AQnagtpnSnXmP6IKRs,678
 sqlframe/databricks/types.py,sha256=KwNyuXIo-2xVVd4bZED3YrQOobKCtemlxGrJL7DrTC8,34
 sqlframe/databricks/udf.py,sha256=3rmxv_6zSLfIxH8P8P050ZO-ki0aqBb9wWuUQBtl4m8,272
@@ -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-3.35.1.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,,
+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,,