sqlframe 3.43.0__py3-none-any.whl → 3.43.2__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 = '3.43.0'
-__version_tuple__ = version_tuple = (3, 43, 0)
+__version__ = version = '3.43.2'
+__version_tuple__ = version_tuple = (3, 43, 2)
 
-__commit_id__ = commit_id = 'g38d15d998'
+__commit_id__ = commit_id = 'gf6f09ead9'

sqlframe/base/dataframe.py

@@ -921,8 +921,30 @@ class BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
     def groupBy(self, *cols, **kwargs) -> GROUP_DATA:
         if cols and isinstance(cols[0], list):
             cols = cols[0]  # type: ignore
+
+        # Special handling for groupBy operations with column aliases
+        # `_ensure_and_normalize_cols` sets CTE aliases that may not exist in the final context.
         columns = self._ensure_and_normalize_cols(cols)
-        return self._group_data(self, columns, self.last_op)
+
+        # Post-process the columns to fix any issues with CTE aliases
+        from sqlframe.base.normalize import (
+            _extract_column_name,
+            is_column_unambiguously_available,
+        )
+
+        processed_columns: t.List[Column] = []
+
+        for col in columns:
+            # Check if this column has a table qualifier that might be problematic
+            if col.column_expression.args.get("table"):
+                # Check if the column is unambiguously available without the qualifier
+                column_name = _extract_column_name(this) if (this := col.expression.this) else None
+                if column_name and is_column_unambiguously_available(self.expression, column_name):
+                    # Remove the table qualifier if the column is unambiguous
+                    col.column_expression.set("table", None)
+            processed_columns.append(col)
+
+        return self._group_data(self, processed_columns, self.last_op)
 
     groupby = groupBy
 

sqlframe/base/functions.py

@@ -2067,7 +2067,7 @@ def bit_length(col: ColumnOrName) -> Column:
     if session._is_bigquery:
         return bit_length_from_length(col)
 
-    return Column.invoke_anonymous_function(col, "BIT_LENGTH")
+    return Column.invoke_expression_over_column(col, expression.BitLength)
 
 
 @meta()
@@ -2729,7 +2729,7 @@ def aggregate(
     return Column.invoke_expression_over_column(col, expression.Reduce, **kwargs)
 
 
-@meta(unsupported_engines="postgres")
+@meta(unsupported_engines=["bigquery", "postgres", "snowflake"])
 def transform(
     col: ColumnOrName,
     f: t.Union[t.Callable[[Column], Column], t.Callable[[Column, Column], Column]],
@@ -7169,12 +7169,32 @@ def _lambda_quoted(value: str) -> t.Optional[bool]:
 
 @meta()
 def _get_lambda_from_func(lambda_expression: t.Callable):
-    variables = [
-        expression.to_identifier(x, quoted=_lambda_quoted(x))
-        for x in lambda_expression.__code__.co_varnames
-    ]
+    import inspect
+
+    # Get the function signature
+    sig = inspect.signature(lambda_expression)
+    param_names = list(sig.parameters.keys())
+
+    # Check if this looks like a column function (single 'col' parameter)
+    if len(param_names) == 1 and param_names[0] in ["col", "column"]:
+        # Wrap column functions to work with transform
+        variables = [expression.to_identifier("x", quoted=_lambda_quoted("x"))]
+        result = lambda_expression(Column("x"))
+        return expression.Lambda(
+            this=result.column_expression,
+            expressions=variables,
+        )
+
+    # Handle regular functions and lambdas
+    var_names = lambda_expression.__code__.co_varnames[: lambda_expression.__code__.co_argcount]
+
+    variables = [expression.to_identifier(x, quoted=_lambda_quoted(x)) for x in var_names]
+
+    # Call with Column objects for each parameter
+    result = lambda_expression(*[Column(x) for x in var_names])
+
     return expression.Lambda(
-        this=lambda_expression(*[Column(x) for x in variables]).column_expression,
+        this=result.column_expression,
         expressions=variables,
     )
 

{sqlframe-3.43.0.dist-info → sqlframe-3.43.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.43.0
+Version: 3.43.2
 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 <27.16,>=24.0.0
+Requires-Dist: sqlglot <27.18,>=24.0.0
 Requires-Dist: typing-extensions
 Provides-Extra: bigquery
 Requires-Dist: google-cloud-bigquery-storage <3,>=2 ; extra == 'bigquery'

{sqlframe-3.43.0.dist-info → sqlframe-3.43.2.dist-info}/RECORD

@@ -1,15 +1,15 @@
 sqlframe/__init__.py,sha256=SB80yLTITBXHI2GCDS6n6bN5ObHqgPjfpRPAUwxaots,3403
-sqlframe/_version.py,sha256=GkrwqhnbavsDQW5LQsruCWe67_xixzoHIDhkzjlbf38,714
+sqlframe/_version.py,sha256=knS0nTLrJHzmkAlJL2R2It95jMGAeQSdYXwXqtFA5lE,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=wT3R2Qmq4edOefxXCRepiMDNJfVOIvSf6eHd6GOn4i0,88543
+sqlframe/base/dataframe.py,sha256=3vlZij84GUKpS23DZSrTRm0mi5SRFjZv_BSn4rAJ0IE,89614
 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=QaCeMMBLz69LE-73x4ksXN6NbZlsshYADg-F8yRXTPA,228816
+sqlframe/base/functions.py,sha256=6b1v8-CvYoHEOK_8kJMibk9TrGwQJkSVO0i_pXL5m7s,229614
 sqlframe/base/group.py,sha256=fBm8EUve7W7xz11nybTXr09ih-yZxL_vvEiZVE1eb_0,12025
 sqlframe/base/normalize.py,sha256=YPeopWr8ZRjevArYfrM-DZBkQp4t4UfAEwynoj4VvcU,11773
 sqlframe/base/operations.py,sha256=g-YNcbvNKTOBbYm23GKfB3fmydlR7ZZDAuZUtXIHtzw,4438
@@ -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-3.43.0.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-3.43.0.dist-info/METADATA,sha256=-M-YLCPxdylEzhy7aPCDjVQc4lkJN47zxzJJdWmvVUo,9070
-sqlframe-3.43.0.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
-sqlframe-3.43.0.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-3.43.0.dist-info/RECORD,,
+sqlframe-3.43.2.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-3.43.2.dist-info/METADATA,sha256=ctg26s2x6TsSTpQLS28UcHYuSvPbRbT6EBEav0L9zuw,9070
+sqlframe-3.43.2.dist-info/WHEEL,sha256=oiQVh_5PnQM0E3gPdiz09WCNmwiHDMaGer_elqB3coM,92
+sqlframe-3.43.2.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-3.43.2.dist-info/RECORD,,