sqlframe 3.9.3__tar.gz → 3.10.1__tar.gz

{sqlframe-3.9.3 → sqlframe-3.10.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.9.3
+Version: 3.10.1
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-3.9.3 → sqlframe-3.10.1}/setup.py

@@ -20,7 +20,7 @@ setup(
     python_requires=">=3.8",
     install_requires=[
         "prettytable<3.12.1",
-        "sqlglot>=24.0.0,<25.33",
+        "sqlglot>=24.0.0,<26.1",
         "typing_extensions>=4.8,<5",
     ],
     extras_require={
@@ -32,13 +32,14 @@ setup(
             "duckdb>=0.9,<1.2",
             "findspark>=2,<3",
             "mypy>=1.10.0,<1.14",
-            "openai>=1.30,<1.56",
+            "openai>=1.30,<1.59",
             "pandas>=2,<3",
             "pandas-stubs>=2,<3",
             "psycopg>=3.1,<4",
             "pyarrow>=10,<19",
             "pyspark>=2,<3.6",
             "pytest>=8.2.0,<8.4",
+            "pytest-forked",
             "pytest-postgresql>=6,<7",
             "pytest-xdist>=3.6,<3.7",
             "pre-commit>=3.5;python_version=='3.8'",
@@ -58,7 +59,7 @@ setup(
             "pandas>=2,<3",
         ],
         "openai": [
-            "openai>=1.30,<1.56",
+            "openai>=1.30,<1.59",
         ],
         "pandas": [
             "pandas>=2,<3",

{sqlframe-3.9.3 → sqlframe-3.10.1}/sqlframe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.9.3'
-__version_tuple__ = version_tuple = (3, 9, 3)
+__version__ = version = '3.10.1'
+__version_tuple__ = version_tuple = (3, 10, 1)

{sqlframe-3.9.3 → sqlframe-3.10.1}/sqlframe/base/dataframe.py

@@ -1624,9 +1624,7 @@ class _BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
             raise NotImplementedError("Vertical show is not yet supported")
         if truncate:
             logger.warning("Truncate is ignored so full results will be displayed")
-        # Make sure that the limit we add doesn't affect the results
-        df = self._convert_leaf_to_cte()
-        result = df.limit(n).collect()
+        result = self.limit(n).collect()
         table = PrettyTable()
         if row := seq_get(result, 0):
             table.field_names = row._unique_field_names

{sqlframe-3.9.3 → sqlframe-3.10.1}/sqlframe/base/function_alternatives.py

@@ -64,6 +64,39 @@ def first_always_ignore_nulls(col: ColumnOrName, ignorenulls: t.Optional[bool] =
     return first(col)
 
 
+def to_timestamp_with_time_zone(col: ColumnOrName, format: t.Optional[str] = None) -> Column:
+    from sqlframe.base.session import _BaseSession
+
+    if format is not None:
+        return Column.invoke_expression_over_column(
+            col, expression.StrToTime, format=_BaseSession().format_time(format)
+        )
+
+    return Column.ensure_col(col).cast("timestamp with time zone", dialect="postgres")
+
+
+def to_timestamp_tz(col: ColumnOrName, format: t.Optional[str] = None) -> Column:
+    from sqlframe.base.session import _BaseSession
+
+    if format is not None:
+        return Column.invoke_expression_over_column(
+            col, expression.StrToTime, format=_BaseSession().format_time(format)
+        )
+
+    return Column.ensure_col(col).cast("timestamptz", dialect="duckdb")
+
+
+def to_timestamp_just_timestamp(col: ColumnOrName, format: t.Optional[str] = None) -> Column:
+    from sqlframe.base.session import _BaseSession
+
+    if format is not None:
+        return Column.invoke_expression_over_column(
+            col, expression.StrToTime, format=_BaseSession().format_time(format)
+        )
+
+    return Column.ensure_col(col).cast("datetime", dialect="bigquery")
+
+
 def bitwise_not_from_bitnot(col: ColumnOrName) -> Column:
     return Column.invoke_anonymous_function(col, "BITNOT")
 

{sqlframe-3.9.3 → sqlframe-3.10.1}/sqlframe/base/functions.py

@@ -900,7 +900,7 @@ def to_timestamp(col: ColumnOrName, format: t.Optional[str] = None) -> Column:
             col, expression.StrToTime, format=_BaseSession().format_time(format)
         )
 
-    return Column.ensure_col(col).cast("timestamp")
+    return Column.ensure_col(col).cast("timestampltz")
 
 
 @meta()

{sqlframe-3.9.3 → sqlframe-3.10.1}/sqlframe/base/session.py

@@ -570,6 +570,8 @@ class _BaseSession(t.Generic[CATALOG, READER, WRITER, DF, CONN, UDF_REGISTRATION
             return cls._to_row(list(value.keys()), list(value.values()))
         elif isinstance(value, (list, set, tuple)) and value:
             return [cls._to_value(x) for x in value]
+        elif isinstance(value, datetime.datetime):
+            return value.replace(tzinfo=None)
         return value
 
     @classmethod

{sqlframe-3.9.3 → sqlframe-3.10.1}/sqlframe/bigquery/functions.py

@@ -73,6 +73,7 @@ from sqlframe.base.function_alternatives import (  # noqa
     _is_string_using_typeof_string as _is_string,
     array_append_using_array_cat as array_append,
     endswith_with_underscore as endswith,
+    to_timestamp_just_timestamp as to_timestamp,
 )
 
 

{sqlframe-3.9.3 → sqlframe-3.10.1}/sqlframe/duckdb/functions.py

@@ -53,4 +53,5 @@ from sqlframe.base.function_alternatives import (  # noqa
     endswith_with_underscore as endswith,
     last_day_with_cast as last_day,
     regexp_replace_global_option as regexp_replace,
+    to_timestamp_tz as to_timestamp,
 )

{sqlframe-3.9.3 → sqlframe-3.10.1}/sqlframe/duckdb/functions.pyi

@@ -29,6 +29,7 @@ from sqlframe.base.function_alternatives import (  # noqa
     try_element_at_zero_based as try_element_at,
     to_unix_timestamp_include_default_format as to_unix_timestamp,
     regexp_replace_global_option as regexp_replace,
+    to_timestamp_tz as to_timestamp,
 )
 from sqlframe.base.functions import (
     abs as abs,

{sqlframe-3.9.3 → sqlframe-3.10.1}/sqlframe/postgres/functions.py

@@ -70,4 +70,5 @@ from sqlframe.base.function_alternatives import (  # noqa
     endswith_using_like as endswith,
     last_day_with_cast as last_day,
     regexp_replace_global_option as regexp_replace,
+    to_timestamp_with_time_zone as to_timestamp,
 )

{sqlframe-3.9.3 → sqlframe-3.10.1}/sqlframe.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.9.3
+Version: 3.10.1
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-3.9.3 → sqlframe-3.10.1}/sqlframe.egg-info/SOURCES.txt

@@ -185,6 +185,7 @@ tests/fixtures/employee.csv
 tests/fixtures/employee.json
 tests/fixtures/employee.parquet
 tests/fixtures/employee_extra_line.csv
+tests/fixtures/issue_219.csv
 tests/fixtures/employee_delta/.part-00000-e5965c7b-e58f-4d3c-ad56-002876814e3a-c000.snappy.parquet.crc
 tests/fixtures/employee_delta/.part-00002-3fed7f18-370f-4b16-b232-504d6194eb52-c000.snappy.parquet.crc
 tests/fixtures/employee_delta/.part-00004-143c5da1-d5ab-4706-8e84-0d2a324c6894-c000.snappy.parquet.crc

{sqlframe-3.9.3 → sqlframe-3.10.1}/sqlframe.egg-info/requires.txt

@@ -1,5 +1,5 @@
 prettytable<3.12.1
-sqlglot<25.33,>=24.0.0
+sqlglot<26.1,>=24.0.0
 typing_extensions<5,>=4.8
 
 [bigquery]
@@ -13,12 +13,13 @@ databricks-sql-connector<4,>=3.6
 duckdb<1.2,>=0.9
 findspark<3,>=2
 mypy<1.14,>=1.10.0
-openai<1.56,>=1.30
+openai<1.59,>=1.30
 pandas-stubs<3,>=2
 pandas<3,>=2
 psycopg<4,>=3.1
 pyarrow<19,>=10
 pyspark<3.6,>=2
+pytest-forked
 pytest-postgresql<7,>=6
 pytest-xdist<3.7,>=3.6
 pytest<8.4,>=8.2.0
@@ -43,7 +44,7 @@ duckdb<1.2,>=0.9
 pandas<3,>=2
 
 [openai]
-openai<1.56,>=1.30
+openai<1.59,>=1.30
 
 [pandas]
 pandas<3,>=2

{sqlframe-3.9.3 → sqlframe-3.10.1}/tests/common_fixtures.py

@@ -92,7 +92,7 @@ def pyspark_session(tmp_path_factory, gen_tpcds: t.List[Path]) -> PySparkSession
         .config("spark.sql.warehouse.dir", data_dir)
         .config("spark.driver.extraJavaOptions", f"-Dderby.system.home={derby_dir}")
         .config("spark.sql.shuffle.partitions", 1)
-        .config("spark.sql.session.timeZone", "America/Los_Angeles")
+        .config("spark.sql.session.timeZone", "UTC")
         .master("local[1]")
         .appName("Unit-tests")
         .getOrCreate()
@@ -225,6 +225,7 @@ def snowflake_connection() -> SnowflakeConnection:
 @pytest.fixture
 def snowflake_session(snowflake_connection: SnowflakeConnection) -> SnowflakeSession:
     session = SnowflakeSession(snowflake_connection)
+    session._execute("ALTER SESSION SET TIMEZONE = 'UTC'")
     session._execute("CREATE SCHEMA IF NOT EXISTS db1")
     session._execute("CREATE TABLE IF NOT EXISTS db1.table1 (id INTEGER, name VARCHAR(100))")
     session._execute(

{sqlframe-3.9.3 → sqlframe-3.10.1}/tests/conftest.py

@@ -16,7 +16,7 @@ def pytest_collection_modifyitems(items, *args, **kwargs):
 def set_tz():
     import os
 
-    os.environ["TZ"] = "US/Pacific"
+    os.environ["TZ"] = "UTC"
     time.tzset()
     yield
     del os.environ["TZ"]

sqlframe-3.10.1/tests/fixtures/issue_219.csv

@@ -0,0 +1,10 @@
+kind,price,make
+standard,30,emcsquare
+capsule,40,emcsquare
+candle,10,emcsquare
+standard,20,maxwells
+capsule,45,maxwells
+candle,11,maxwells
+standard,90,voltaires
+capsule,95,voltaires
+candle,80,voltaires

{sqlframe-3.9.3 → sqlframe-3.10.1}/tests/integration/engines/duck/test_duckdb_reader.py

@@ -1,5 +1,6 @@
 from sqlframe.base.types import Row
 from sqlframe.duckdb import DuckDBSession
+from sqlframe.duckdb import functions as F
 
 pytest_plugins = ["tests.common_fixtures"]
 
@@ -114,3 +115,10 @@ def test_employee_delta(duckdb_session: DuckDBSession):
         ),
         Row(**{"employee_id": 5, "fname": "Hugo", "lname": "Reyes", "age": 29, "store_id": 100}),
     ]
+
+
+def test_issue_219(duckdb_session: DuckDBSession):
+    df1 = duckdb_session.read.csv("tests/fixtures/issue_219.csv")
+    df2 = df1.groupBy("kind", "make").agg(F.min("price"))
+    # Just making sure this doesn't raise like it did before
+    df2.show()

{sqlframe-3.9.3 → sqlframe-3.10.1}/tests/integration/engines/snowflake/test_snowflake_dataframe.py

@@ -54,8 +54,8 @@ def test_print_schema_basic(snowflake_employee: SnowflakeDataFrame, capsys):
         == """
 root
  |-- employee_id: decimal(38, 0) (nullable = true)
- |-- fname: string (nullable = true)
- |-- lname: string (nullable = true)
+ |-- fname: varchar(16777216) (nullable = true)
+ |-- lname: varchar(16777216) (nullable = true)
  |-- age: decimal(38, 0) (nullable = true)
  |-- store_id: decimal(38, 0) (nullable = true)""".strip()
     )
@@ -70,9 +70,9 @@ def test_print_schema_nested(snowflake_datatypes: SnowflakeDataFrame, capsys):
 root
  |-- bigint_col: decimal(38, 0) (nullable = true)
  |-- double_col: float (nullable = true)
- |-- string_col: string (nullable = true)
- |-- map_string_bigint__col: map<string, decimal(38, 0)> (nullable = true)
- |    |-- key: string (nullable = true)
+ |-- string_col: varchar(16777216) (nullable = true)
+ |-- map_string_bigint__col: map<varchar(16777216), decimal(38, 0)> (nullable = true)
+ |    |-- key: varchar(16777216) (nullable = true)
  |    |-- value: decimal(38, 0) (nullable = true)
  |-- array_struct_a_bigint_b_bigint__: array<object<a decimal(38, 0), b decimal(38, 0)>> (nullable = true)
  |    |-- element: object<a decimal(38, 0), b decimal(38, 0)> (nullable = true)
@@ -83,7 +83,7 @@ root
  |-- struct_a_bigint__col: object<a decimal(38, 0)> (nullable = true)
  |    |-- a: decimal(38, 0) (nullable = true)
  |-- date_col: date (nullable = true)
- |-- timestamp_col: timestamp_ntz (nullable = true)
+ |-- timestamp_col: timestamp (nullable = true)
  |-- timestamptz_col: timestamp (nullable = true)
  |-- boolean_col: boolean (nullable = true)""".strip()
     )
@@ -96,9 +96,9 @@ def test_schema(snowflake_employee: SnowflakeDataFrame):
     assert struct_fields[0].name == "employee_id"
     assert struct_fields[0].dataType == types.DecimalType(38, 0)
     assert struct_fields[1].name == "fname"
-    assert struct_fields[1].dataType == types.StringType()
+    assert struct_fields[1].dataType == types.VarcharType(16777216)
     assert struct_fields[2].name == "lname"
-    assert struct_fields[2].dataType == types.StringType()
+    assert struct_fields[2].dataType == types.VarcharType(16777216)
     assert struct_fields[3].name == "age"
     assert struct_fields[3].dataType == types.DecimalType(38, 0)
     assert struct_fields[4].name == "store_id"
@@ -114,10 +114,10 @@ def test_schema_nested(snowflake_datatypes: SnowflakeDataFrame):
     assert struct_fields[1].name == "double_col"
     assert struct_fields[1].dataType == types.FloatType()
     assert struct_fields[2].name == "string_col"
-    assert struct_fields[2].dataType == types.StringType()
+    assert struct_fields[2].dataType == types.VarcharType(16777216)
     assert struct_fields[3].name == "map_string_bigint__col"
     assert struct_fields[3].dataType == types.MapType(
-        types.StringType(),
+        types.VarcharType(16777216),
         types.DecimalType(38, 0),
     )
     assert struct_fields[4].name == "array_struct_a_bigint_b_bigint__"