sqlframe 1.6.1__py3-none-any.whl → 1.6.3__py3-none-any.whl

sqlframe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '1.6.1'
-__version_tuple__ = version_tuple = (1, 6, 1)
+__version__ = version = '1.6.3'
+__version_tuple__ = version_tuple = (1, 6, 3)

sqlframe/base/dataframe.py

@@ -17,7 +17,7 @@ import sqlglot
 from prettytable import PrettyTable
 from sqlglot import Dialect
 from sqlglot import expressions as exp
-from sqlglot.helper import ensure_list, object_to_dict, seq_get
+from sqlglot.helper import ensure_list, flatten, object_to_dict, seq_get
 from sqlglot.optimizer.pushdown_projections import pushdown_projections
 from sqlglot.optimizer.qualify import qualify
 from sqlglot.optimizer.qualify_columns import quote_identifiers
@@ -649,11 +649,16 @@ class _BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
         columns = self._ensure_and_normalize_cols(cols)
         kwargs["append"] = kwargs.get("append", False)
         if self.expression.args.get("joins"):
-            ambiguous_cols = [
-                col
-                for col in columns
-                if isinstance(col.column_expression, exp.Column) and not col.column_expression.table
-            ]
+            ambiguous_cols: t.List[exp.Column] = list(
+                flatten(
+                    [
+                        sub_col
+                        for col in columns
+                        for sub_col in col.expression.find_all(exp.Column)
+                        if not sub_col.table
+                    ]
+                )
+            )
             if ambiguous_cols:
                 join_table_identifiers = [
                     x.this for x in get_tables_from_expression_with_join(self.expression)
@@ -662,13 +667,15 @@ class _BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
                 # If we have columns that resolve to multiple CTE expressions then we want to use each CTE left-to-right
                 # and therefore we allow multiple columns with the same name in the result. This matches the behavior
                 # of Spark.
-                resolved_column_position: t.Dict[Column, int] = {col: -1 for col in ambiguous_cols}
+                resolved_column_position: t.Dict[exp.Column, int] = {
+                    col.copy(): -1 for col in ambiguous_cols
+                }
                 for ambiguous_col in ambiguous_cols:
                     ctes_with_column = [
                         cte
                         for cte in self.expression.ctes
                         if cte.alias_or_name in cte_names_in_join
-                        and ambiguous_col.column_alias_or_name in cte.this.named_selects
+                        and ambiguous_col.alias_or_name in cte.this.named_selects
                     ]
                     # Check if there is a CTE with this column that we haven't used before. If so, use it. Otherwise,
                     # use the same CTE we used before
@@ -677,9 +684,7 @@ class _BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
                         resolved_column_position[ambiguous_col] += 1
                     else:
                         cte = ctes_with_column[resolved_column_position[ambiguous_col]]
-                    ambiguous_col.column_expression.set(
-                        "table", exp.to_identifier(cte.alias_or_name)
-                    )
+                    ambiguous_col.set("table", exp.to_identifier(cte.alias_or_name))
         # If an expression is `CAST(x AS DATETYPE)` then we want to alias so that `x` is the result column name
         columns = [
             col.alias(col.expression.alias_or_name)
@@ -776,6 +781,8 @@ class _BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
         how: str = "inner",
         **kwargs,
     ) -> Self:
+        from sqlframe.base.functions import coalesce
+
         if on is None:
             logger.warning("Got no value for on. This appears change the join to a cross join.")
             how = "cross"
@@ -835,7 +842,15 @@ class _BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
                         for left_column, right_column in join_column_pairs
                     ],
                 )
-                join_column_names = [left_col.alias_or_name for left_col, _ in join_column_pairs]
+                join_column_names = [
+                    coalesce(
+                        left_col.sql(dialect=self.session.input_dialect),
+                        right_col.sql(dialect=self.session.input_dialect),
+                    ).alias(left_col.alias_or_name)
+                    if how == "full"
+                    else left_col.alias_or_name
+                    for left_col, right_col in join_column_pairs
+                ]
                 # To match spark behavior only the join clause gets deduplicated and it gets put in the front of the column list
                 select_column_names = [
                     (
@@ -848,7 +863,10 @@ class _BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
                 select_column_names = [
                     column_name
                     for column_name in select_column_names
-                    if column_name not in join_column_names
+                    if column_name
+                    not in [
+                        x.alias_or_name if not isinstance(x, str) else x for x in join_column_names
+                    ]
                 ]
                 select_column_names = join_column_names + select_column_names
             else:

{sqlframe-1.6.1.dist-info → sqlframe-1.6.3.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 1.6.1
+Version: 1.6.3
 Summary: Taking the Spark out of PySpark by converting to SQL
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman
@@ -18,14 +18,14 @@ Requires-Python: >=3.8
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: prettytable (<3.11.0)
-Requires-Dist: sqlglot (<24.2,>=24.0.0)
+Requires-Dist: sqlglot (<25.1,>=24.0.0)
 Provides-Extra: bigquery
 Requires-Dist: google-cloud-bigquery-storage (<3,>=2) ; extra == 'bigquery'
 Requires-Dist: google-cloud-bigquery[pandas] (<4,>=3) ; extra == 'bigquery'
 Provides-Extra: dev
 Requires-Dist: duckdb (<1.1,>=0.9) ; extra == 'dev'
 Requires-Dist: mypy (<1.11,>=1.10.0) ; extra == 'dev'
-Requires-Dist: openai (<1.32,>=1.30) ; extra == 'dev'
+Requires-Dist: openai (<1.33,>=1.30) ; extra == 'dev'
 Requires-Dist: pandas-stubs (<3,>=2) ; extra == 'dev'
 Requires-Dist: pandas (<3,>=2) ; extra == 'dev'
 Requires-Dist: psycopg (<4,>=3.1) ; extra == 'dev'
@@ -49,7 +49,7 @@ Provides-Extra: duckdb
 Requires-Dist: duckdb (<1.1,>=0.9) ; extra == 'duckdb'
 Requires-Dist: pandas (<3,>=2) ; extra == 'duckdb'
 Provides-Extra: openai
-Requires-Dist: openai (<1.32,>=1.30) ; extra == 'openai'
+Requires-Dist: openai (<1.33,>=1.30) ; extra == 'openai'
 Provides-Extra: pandas
 Requires-Dist: pandas (<3,>=2) ; extra == 'pandas'
 Provides-Extra: postgres

{sqlframe-1.6.1.dist-info → sqlframe-1.6.3.dist-info}/RECORD

@@ -1,10 +1,10 @@
 sqlframe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sqlframe/_version.py,sha256=edFVVa8HpVPfLqL2y6CKtViSqJREfmXxInA-HCy-134,411
+sqlframe/_version.py,sha256=mQ_8947spH9F9E4bJgRMJ3LZK_sGORi1ak9UVDzTrr8,411
 sqlframe/base/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 sqlframe/base/_typing.py,sha256=DuTay8-o9W-pw3RPZCgLunKNJLS9PkaV11G_pxXp9NY,1256
 sqlframe/base/catalog.py,sha256=ATDGirouUjal05P4ymL-wIi8rgjg_8w4PoACamiO64A,37245
 sqlframe/base/column.py,sha256=0WgIRBfF8Fkbx_OtiaUB1-BsX3qCd4W5IL534Q2BkCA,16137
-sqlframe/base/dataframe.py,sha256=FbVEoAuRCglXl_tySeNjK-Xn7o_XFPlPL51SMZyhDfo,67062
+sqlframe/base/dataframe.py,sha256=uL4neDTMy1a9XJH46YLQryzdDci4iDxNXBtiJOzfHfs,67718
 sqlframe/base/decorators.py,sha256=I5osMgx9BuCgbtp4jVM2DNwYJVLzCv-OtTedhQEik0g,1882
 sqlframe/base/exceptions.py,sha256=pCB9hXX4jxZWzNg3JN1i38cv3BmpUlee5NoLYx3YXIQ,208
 sqlframe/base/function_alternatives.py,sha256=NDXs2igY7PBsStzTSRZvJcCshBOJkPQl2GbhpVFU6To,42931
@@ -96,8 +96,8 @@ sqlframe/standalone/readwriter.py,sha256=EZNyDJ4ID6sGNog3uP4-e9RvchX4biJJDNtc5hk
 sqlframe/standalone/session.py,sha256=wQmdu2sv6KMTAv0LRFk7TY7yzlh3xvmsyqilEtRecbY,1191
 sqlframe/standalone/types.py,sha256=KwNyuXIo-2xVVd4bZED3YrQOobKCtemlxGrJL7DrTC8,34
 sqlframe/standalone/window.py,sha256=6GKPzuxeSapJakBaKBeT9VpED1ACdjggDv9JRILDyV0,35
-sqlframe-1.6.1.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
-sqlframe-1.6.1.dist-info/METADATA,sha256=C4oa_WB2WwjVauPsXYo5jKiE6SnwWFkM-GNUio-XfTY,7330
-sqlframe-1.6.1.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
-sqlframe-1.6.1.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
-sqlframe-1.6.1.dist-info/RECORD,,
+sqlframe-1.6.3.dist-info/LICENSE,sha256=VZu79YgW780qxaFJMr0t5ZgbOYEh04xWoxaWOaqIGWk,1068
+sqlframe-1.6.3.dist-info/METADATA,sha256=edYCJbKjAmY0rrInh7BRmOhNHFr36bSsXtaPsD9AzFI,7330
+sqlframe-1.6.3.dist-info/WHEEL,sha256=G16H4A3IeoQmnOrYV4ueZGKSjhipXx8zc8nu9FGlvMA,92
+sqlframe-1.6.3.dist-info/top_level.txt,sha256=T0_RpoygaZSF6heeWwIDQgaP0varUdSK1pzjeJZRjM8,9
+sqlframe-1.6.3.dist-info/RECORD,,