sqlframe 3.36.1__py3-none-any.whl → 3.36.3__py3-none-any.whl

sqlframe/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.36.1'
-__version_tuple__ = version_tuple = (3, 36, 1)
+__version__ = version = '3.36.3'
+__version_tuple__ = version_tuple = (3, 36, 3)

sqlframe/base/functions.py

@@ -1475,6 +1475,32 @@ def timestamp_seconds(col: ColumnOrName) -> Column:
     return Column.invoke_expression_over_column(col, expression.UnixToTime)
 
 
+@meta()
+def timestamp_add(unit: str, quantity: ColumnOrName, ts: ColumnOrName) -> Column:
+    session = _get_session()
+
+    if session._is_duckdb or session._is_postgres:
+        quantity = lit(quantity) if isinstance(quantity, int) else quantity
+        if (
+            isinstance(quantity, Column)
+            and isinstance(quantity.expression, expression.Literal)
+            and quantity.expression.is_number
+            and int(quantity.expression.this) < 0
+        ):
+            # If quantity is a negative literal, we use DateSub
+            expr = expression.DateSub
+            quantity.expression.set("this", str(-int(quantity.expression.this)))
+        else:
+            expr = expression.DateAdd  # type: ignore
+        return Column.invoke_expression_over_column(
+            ts, expr, expression=quantity, unit=expression.Var(this=unit.upper())
+        )
+
+    return Column.invoke_expression_over_column(
+        ts, expression.TimestampAdd, expression=quantity, unit=expression.Var(this=unit.upper())
+    )
+
+
 @meta(unsupported_engines=["*", "spark"])
 def window(
     timeColumn: ColumnOrName,
@@ -1796,7 +1822,9 @@ 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 +2233,9 @@ 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 +2778,7 @@ 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-3.36.1.dist-info → sqlframe-3.36.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.36.1
+Version: 3.36.3
 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 +37,8 @@ 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-rerunfailures ; 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 +60,7 @@ 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-3.36.1.dist-info → sqlframe-3.36.3.dist-info}/RECORD

@@ -1,5 +1,5 @@
 sqlframe/__init__.py,sha256=SB80yLTITBXHI2GCDS6n6bN5ObHqgPjfpRPAUwxaots,3403
-sqlframe/_version.py,sha256=aFVkO79_dcSzv2bBviVfMu6iWSclcSYamQO4TGPQNMo,513
+sqlframe/_version.py,sha256=k0__IYrsLFXLDTAPbWVSipvAv_-Gzp6mw1szlQWJb_o,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=jcZZZkylIy6jktXkyqVgSpJgUSgA0g8qjO0SGDwQD30,226902
+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
@@ -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-3.36.1.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-3.36.1.dist-info/METADATA,sha256=9Osg-ZJKc1nPTLTUkZ6Xz45RmGRqPoHA-0FYCLXv_7U,8987
-sqlframe-3.36.1.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-sqlframe-3.36.1.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-3.36.1.dist-info/RECORD,,
+sqlframe-3.36.3.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-3.36.3.dist-info/METADATA,sha256=1G_ICerBb0qaFNlT8OdNQrmHtkI_gIbW8xOQyPlrAO0,9040
+sqlframe-3.36.3.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+sqlframe-3.36.3.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-3.36.3.dist-info/RECORD,,