sqlframe 3.22.1__tar.gz → 3.23.0__tar.gz

{sqlframe-3.22.1 → sqlframe-3.23.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.22.1
+Version: 3.23.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-3.22.1 → sqlframe-3.23.0}/setup.py

@@ -20,7 +20,7 @@ setup(
     python_requires=">=3.9",
     install_requires=[
         "prettytable<4",
-        "sqlglot>=24.0.0,<26.7",
+        "sqlglot>=24.0.0,<26.9",
         "typing_extensions",
     ],
     extras_require={
@@ -29,7 +29,7 @@ setup(
             "google-cloud-bigquery-storage>=2,<3",
         ],
         "dev": [
-            "duckdb>=0.9,<1.2",
+            "duckdb>=1.2,<1.3",
             "findspark>=2,<3",
             "mypy>=1.10.0,<1.16",
             "openai>=1.30,<2",
@@ -54,7 +54,7 @@ setup(
             "pymdown-extensions",
         ],
         "duckdb": [
-            "duckdb>=0.9,<1.2",
+            "duckdb>=1.2,<1.3",
             "pandas>=2,<3",
         ],
         "openai": [
@@ -70,7 +70,7 @@ setup(
             "redshift_connector>=2.1.1,<2.2.0",
         ],
         "snowflake": [
-            "snowflake-connector-python[secure-local-storage]>=3.10.0,<3.14",
+            "snowflake-connector-python[secure-local-storage]>=3.10.0,<3.15",
         ],
         "spark": [
             "pyspark>=2,<3.6",

{sqlframe-3.22.1 → sqlframe-3.23.0}/sqlframe/_version.py

@@ -17,5 +17,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.22.1'
-__version_tuple__ = version_tuple = (3, 22, 1)
+__version__ = version = '3.23.0'
+__version_tuple__ = version_tuple = (3, 23, 0)

{sqlframe-3.22.1 → sqlframe-3.23.0}/sqlframe/base/functions.py

@@ -856,15 +856,21 @@ def expr(str: str) -> Column:
 
 @meta(unsupported_engines=["postgres"])
 def struct(col: t.Union[ColumnOrName, t.Iterable[ColumnOrName]], *cols: ColumnOrName) -> Column:
-    from sqlframe.base.function_alternatives import struct_with_eq
-
     session = _get_session()
-
-    if session._is_snowflake:
-        return struct_with_eq(col, *cols)
-
-    columns = ensure_list(col) + list(cols)
-    return Column.invoke_expression_over_column(None, expression.Struct, expressions=columns)
+    col_func = get_func_from_session("col")
+
+    columns = [col_func(x) for x in ensure_list(col) + list(cols)]
+    expressions = []
+    for column in columns:
+        expressions.append(
+            expression.PropertyEQ(
+                this=expression.parse_identifier(
+                    column.alias_or_name, dialect=session.input_dialect
+                ),
+                expression=column.column_expression,
+            )
+        )
+    return Column(expression.Struct(expressions=expressions))
 
 
 @meta(unsupported_engines=["bigquery", "duckdb", "postgres", "snowflake"])

{sqlframe-3.22.1 → sqlframe-3.23.0}/sqlframe.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.22.1
+Version: 3.23.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-3.22.1 → sqlframe-3.23.0}/sqlframe.egg-info/requires.txt

@@ -1,5 +1,5 @@
 prettytable<4
-sqlglot<26.7,>=24.0.0
+sqlglot<26.9,>=24.0.0
 typing_extensions
 
 [bigquery]
@@ -10,7 +10,7 @@ google-cloud-bigquery[pandas]<4,>=3
 databricks-sql-connector<5,>=3.6
 
 [dev]
-duckdb<1.2,>=0.9
+duckdb<1.3,>=1.2
 findspark<3,>=2
 mypy<1.16,>=1.10.0
 openai<2,>=1.30
@@ -35,7 +35,7 @@ mkdocs==1.4.2
 pymdown-extensions
 
 [duckdb]
-duckdb<1.2,>=0.9
+duckdb<1.3,>=1.2
 pandas<3,>=2
 
 [openai]
@@ -51,7 +51,7 @@ psycopg2<3,>=2.8
 redshift_connector<2.2.0,>=2.1.1
 
 [snowflake]
-snowflake-connector-python[secure-local-storage]<3.14,>=3.10.0
+snowflake-connector-python[secure-local-storage]<3.15,>=3.10.0
 
 [spark]
 pyspark<3.6,>=2

{sqlframe-3.22.1 → sqlframe-3.23.0}/tests/integration/engines/duck/test_duckdb_catalog.py

@@ -57,25 +57,15 @@ def test_set_current_database(duckdb_session: DuckDBSession):
 
 def test_list_databases(duckdb_session: DuckDBSession):
     assert sorted(duckdb_session.catalog.listDatabases(), key=lambda x: (x.catalog, x.name)) == [
-        Database(name="information_schema", catalog="catalog1", description=None, locationUri=""),
         Database(name="main", catalog="catalog1", description=None, locationUri=""),
-        Database(name="pg_catalog", catalog="catalog1", description=None, locationUri=""),
-        Database(name="information_schema", catalog="catalog2", description=None, locationUri=""),
         Database(name="main", catalog="catalog2", description=None, locationUri=""),
-        Database(name="pg_catalog", catalog="catalog2", description=None, locationUri=""),
         Database(name="db1", catalog="default", description=None, locationUri=""),
-        Database(name="information_schema", catalog="default", description=None, locationUri=""),
         Database(name="main", catalog="default", description=None, locationUri=""),
-        Database(name="pg_catalog", catalog="default", description=None, locationUri=""),
-        Database(name="information_schema", catalog="memory", description=None, locationUri=""),
         Database(name="main", catalog="memory", description=None, locationUri=""),
-        Database(name="pg_catalog", catalog="memory", description=None, locationUri=""),
         Database(name="information_schema", catalog="system", description=None, locationUri=""),
         Database(name="main", catalog="system", description=None, locationUri=""),
         Database(name="pg_catalog", catalog="system", description=None, locationUri=""),
-        Database(name="information_schema", catalog="temp", description=None, locationUri=""),
         Database(name="main", catalog="temp", description=None, locationUri=""),
-        Database(name="pg_catalog", catalog="temp", description=None, locationUri=""),
     ]
 
 
@@ -99,8 +89,8 @@ def test_get_database_name_only(duckdb_session: DuckDBSession):
 
 
 def test_get_database_name_and_catalog(duckdb_session: DuckDBSession):
-    assert duckdb_session.catalog.getDatabase("catalog1.information_schema") == Database(
-        name="information_schema", catalog="catalog1", description=None, locationUri=""
+    assert duckdb_session.catalog.getDatabase("system.information_schema") == Database(
+        name="information_schema", catalog="system", description=None, locationUri=""
     )
 
 

{sqlframe-3.22.1 → sqlframe-3.23.0}/tests/integration/engines/duck/test_duckdb_reader.py

@@ -1,3 +1,7 @@
+import os
+
+import pytest
+
 from sqlframe.base.types import Row
 from sqlframe.duckdb import DuckDBSession
 from sqlframe.duckdb import functions as F
@@ -102,6 +106,10 @@ def test_employee_extra_line_csv_multiple(duckdb_session: DuckDBSession):
 
 
 def test_employee_delta(duckdb_session: DuckDBSession):
+    if os.environ.get("CI"):
+        pytest.skip(
+            "DuckDB Delta is not working in CI with DuckDB 1.2.1. Error: `duckdb.duckdb.Error: An error occurred while trying to automatically install the required extension 'delta'`"
+        )
     df = duckdb_session.read.load(
         "tests/fixtures/employee_delta",
         format="delta",

{sqlframe-3.22.1 → sqlframe-3.23.0}/tests/integration/engines/test_int_functions.py

@@ -1062,8 +1062,23 @@ def test_struct(get_session_and_func):
         if not isinstance(session, SnowflakeSession)
         else [Row(value={"age": 2, "name": "Alice"}), Row(value={"age": 5, "name": "Bob"})]
     )
-    assert df.select(struct("age", "name").alias("struct")).collect() == expected
-    assert df.select(struct([df.age, df.name]).alias("struct")).collect() == expected
+    expected_field_names = ["age", "name"]
+    result = df.select(struct("age", "name").alias("struct")).collect()
+    assert result == expected
+    if isinstance(session, (SparkSession, PySparkSession)):
+        pass
+    elif isinstance(session, SnowflakeSession):
+        assert list(result[0][0]) == expected_field_names
+    else:
+        assert result[0][0]._unique_field_names == expected_field_names
+    result = df.select(struct([df.age, df.name]).alias("struct")).collect()
+    assert result == expected
+    if isinstance(session, (SparkSession, PySparkSession)):
+        pass
+    elif isinstance(session, SnowflakeSession):
+        assert list(result[0][0]) == expected_field_names
+    else:
+        assert result[0][0]._unique_field_names == expected_field_names
 
 
 def test_greatest(get_session_and_func):
@@ -1576,7 +1591,7 @@ def test_hash(get_session_and_func):
     df = session.createDataFrame([("ABC", "DEF")], ["c1", "c2"])
     if isinstance(session, DuckDBSession):
         assert df.select(hash("c1").alias("hash")).first()[0] == 1241521928161919141
-        assert df.select(hash("c1", "c2").alias("hash")).first()[0] == 13305036188712072380
+        assert df.select(hash("c1", "c2").alias("hash")).first()[0] == 7524280102280623017
     # Bigquery only supports hashing a single column
     elif isinstance(session, BigQuerySession):
         assert df.select(hash("c1").alias("hash")).first()[0] == 228873345217803866
@@ -4879,9 +4894,9 @@ def test_try_element_at(get_session_and_func, get_func):
     else:
         assert df.select(try_element_at(df.data, lit(-1)).alias("r")).first()[0] == "c"
     df = session.createDataFrame([({"a": 1.0, "b": 2.0},)], ["data"])
-    if isinstance(session, DuckDBSession):
-        assert df.select(try_element_at(df.data, lit("a")).alias("r")).first()[0] == [1.0]
-    elif isinstance(session, PostgresSession):
+    # if isinstance(session, DuckDBSession):
+    #     assert df.select(try_element_at(df.data, lit("a")).alias("r")).first()[0] == [1.0]
+    if isinstance(session, PostgresSession):
         pass
     else:
         assert df.select(try_element_at(df.data, lit("a")).alias("r")).first()[0] == 1.0

{sqlframe-3.22.1 → sqlframe-3.23.0}/tests/unit/standalone/test_functions.py

@@ -1070,10 +1070,13 @@ def test_expr():
 @pytest.mark.parametrize(
     "expression, expected",
     [
-        (SF.struct("cola", "colb", "colc"), "STRUCT(cola, colb, colc)"),
-        (SF.struct(SF.col("cola"), SF.col("colb"), SF.col("colc")), "STRUCT(cola, colb, colc)"),
-        (SF.struct("cola"), "STRUCT(cola)"),
-        (SF.struct(["cola", "colb", "colc"]), "STRUCT(cola, colb, colc)"),
+        (SF.struct("cola", "colb", "colc"), "STRUCT(cola AS cola, colb AS colb, colc AS colc)"),
+        (
+            SF.struct(SF.col("cola"), SF.col("colb"), SF.col("colc")),
+            "STRUCT(cola AS cola, colb AS colb, colc AS colc)",
+        ),
+        (SF.struct("cola"), "STRUCT(cola AS cola)"),
+        (SF.struct(["cola", "colb", "colc"]), "STRUCT(cola AS cola, colb AS colb, colc AS colc)"),
     ],
 )
 def test_struct(expression, expected):