sqlframe 3.18.1__tar.gz → 3.20.0__tar.gz

{sqlframe-3.18.1 → sqlframe-3.20.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.18.1
+Version: 3.20.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-3.18.1 → sqlframe-3.20.0}/docs/bigquery.md

@@ -312,6 +312,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [array_min](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_min.html)
 * [array_position](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_position.html)
 * [array_remove](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_remove.html)
+* [array_size](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_size.html)
 * [array_sort](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_sort.html)
     * Arrays are not allowed to have None (NULL) values
 * [array_union](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_union.html)
@@ -505,6 +506,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [toRadians](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.toRadians.html)
 * [to_date](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_date.html)
 * [to_timestamp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_timestamp.html)
+* [to_timestamp_ntz](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_timestamp_ntz.html)
 * [translate](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.translate.html)
 * [trim](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.trim.html)
 * [trunc](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.trunc.html)

{sqlframe-3.18.1 → sqlframe-3.20.0}/docs/duckdb.md

@@ -266,7 +266,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [acos](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.acos.html)
 * [add_months](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.add_months.html)
 * [any_value](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.any_value.html)
-  * Always ignores nulls
+    * Always ignores nulls
 * [approxCountDistinct](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.approxCountDistinct.html)
 * [approx_count_distinct](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.approx_count_distinct.html)
 * [array](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array.html)
@@ -278,6 +278,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [array_min](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_min.html)
 * [array_position](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_position.html)
 * [array_remove](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_remove.html)
+* [array_size](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_size.html)
 * [array_sort](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_sort.html)
 * [array_union](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_union.html)
 * [arrays_overlap](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.arrays_overlap.html)
@@ -467,6 +468,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [toRadians](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.toRadians.html)
 * [to_date](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_date.html)
 * [to_timestamp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_timestamp.html)
+* [to_timestamp_ntz](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_timestamp_ntz.html)
 * [to_unix_timestamp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_unix_timestamp.html)
     * The values must match the format string (null will not be returned if they do not)
 * [translate](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.translate.html)

{sqlframe-3.18.1 → sqlframe-3.20.0}/docs/postgres.md

@@ -289,6 +289,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [array_min](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_min.html)
 * [array_position](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_position.html)
 * [array_remove](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_remove.html)
+* [array_size](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_size.html)
 * [arrays_overlap](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.arrays_overlap.html)
 * [asc](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.asc.html)
 * [asc_nulls_first](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.asc_nulls_first.html)
@@ -458,6 +459,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [to_date](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_date.html)
 * [to_number](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_number.html)
 * [to_timestamp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_timestamp.html)
+* [to_timestamp_ntz](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_timestamp_ntz.html)
 * [translate](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.translate.html)
 * [trim](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.trim.html)
 * [trunc](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.trunc.html)

{sqlframe-3.18.1 → sqlframe-3.20.0}/docs/snowflake.md

@@ -311,6 +311,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [array_min](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_min.html)
 * [array_position](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_position.html)
 * [array_remove](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_remove.html)
+* [array_size](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_size.html)
 * [array_sort](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_sort.html)
 * [array_union](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.array_union.html)
 * [arrays_overlap](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.arrays_overlap.html)
@@ -509,6 +510,7 @@ See something that you would like to see supported? [Open an issue](https://gith
 * [to_date](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_date.html)
 * [to_number](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_number.html)
 * [to_timestamp](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_timestamp.html)
+* [to_timestamp_ntz](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_timestamp_ntz.html)
 * [translate](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.translate.html)
 * [trim](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.trim.html)
 * [trunc](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.trunc.html)

{sqlframe-3.18.1 → sqlframe-3.20.0}/setup.py

@@ -20,7 +20,7 @@ setup(
     python_requires=">=3.9",
     install_requires=[
         "prettytable<4",
-        "sqlglot>=24.0.0,<26.5",
+        "sqlglot>=24.0.0,<26.7",
         "typing_extensions",
     ],
     extras_require={

{sqlframe-3.18.1 → sqlframe-3.20.0}/sqlframe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.18.1'
-__version_tuple__ = version_tuple = (3, 18, 1)
+__version__ = version = '3.20.0'
+__version_tuple__ = version_tuple = (3, 20, 0)

{sqlframe-3.18.1 → sqlframe-3.20.0}/sqlframe/base/functions.py

@@ -8,6 +8,7 @@ import typing as t
 
 from sqlglot import Dialect
 from sqlglot import exp as expression
+from sqlglot.dialects.dialect import time_format
 from sqlglot.helper import ensure_list
 from sqlglot.helper import flatten as _flatten
 
@@ -2016,9 +2017,12 @@ def array_prepend(col: ColumnOrName, value: ColumnOrLiteral) -> Column:
     return Column.invoke_anonymous_function(col, "ARRAY_PREPEND", value)
 
 
-@meta(unsupported_engines="*")
+@meta()
 def array_size(col: ColumnOrName) -> Column:
-    return Column.invoke_anonymous_function(col, "ARRAY_SIZE")
+    session = _get_session()
+    if session._is_spark or session._is_databricks:
+        return Column.invoke_anonymous_function(col, "ARRAY_SIZE")
+    return Column.invoke_expression_over_column(col, expression.ArraySize)
 
 
 @meta(unsupported_engines="*")
@@ -3129,20 +3133,14 @@ def datepart(field: ColumnOrName, source: ColumnOrName) -> Column:
 
 @meta(unsupported_engines=["bigquery", "postgres", "snowflake"])
 def day(col: ColumnOrName) -> Column:
-    from sqlframe.base.function_alternatives import day_with_try_to_timestamp
-
     session = _get_session()
 
     if session._is_duckdb:
         try_to_timestamp = get_func_from_session("try_to_timestamp")
         to_date = get_func_from_session("to_date")
-        when = get_func_from_session("when")
         _is_string = get_func_from_session("_is_string")
         coalesce = get_func_from_session("coalesce")
-        col = when(
-            _is_string(col),
-            coalesce(try_to_timestamp(col), to_date(col)),
-        ).otherwise(col)
+        col = coalesce(try_to_timestamp(Column.ensure_col(col).cast("VARCHAR")), to_date(col))
 
     return Column.invoke_expression_over_column(col, expression.Day)
 
@@ -6088,7 +6086,7 @@ def to_timestamp_ltz(
         return Column.invoke_anonymous_function(timestamp, "to_timestamp_ltz")
 
 
-@meta(unsupported_engines="*")
+@meta()
 def to_timestamp_ntz(
     timestamp: ColumnOrName,
     format: t.Optional[ColumnOrName] = None,
@@ -6118,6 +6116,32 @@ def to_timestamp_ntz(
     ... # doctest: +SKIP
     [Row(r=datetime.datetime(2016, 4, 8, 0, 0))]
     """
+    session = _get_session()
+
+    if session._is_duckdb:
+        to_timestamp_func = get_func_from_session("to_timestamp")
+        return to_timestamp_func(timestamp, format)
+
+    if session._is_bigquery:
+        if format is not None:
+            return Column.invoke_anonymous_function(
+                session.format_execution_time(format),  # type: ignore
+                "parse_datetime",
+                timestamp,
+            )
+        else:
+            return Column.ensure_col(timestamp).cast("datetime", dialect="bigquery")
+
+    if session._is_postgres:
+        if format is not None:
+            return Column.invoke_anonymous_function(
+                timestamp,
+                "to_timestamp",
+                session.format_execution_time(format),  # type: ignore
+            )
+        else:
+            return Column.ensure_col(timestamp).cast("timestamp", dialect="postgres")
+
     if format is not None:
         return Column.invoke_anonymous_function(timestamp, "to_timestamp_ntz", format)
     else:
@@ -6442,12 +6466,25 @@ def unix_micros(col: ColumnOrName) -> Column:
     """
     from sqlframe.base.function_alternatives import unix_micros_multiply_epoch
 
-    if (
-        _get_session()._is_bigquery
-        or _get_session()._is_duckdb
-        or _get_session()._is_postgres
-        or _get_session()._is_snowflake
-    ):
+    if _get_session()._is_duckdb:
+        return Column.invoke_anonymous_function(col, "epoch_us")
+
+    if _get_session()._is_bigquery:
+        return Column(
+            expression.Anonymous(
+                this="UNIX_MICROS",
+                expressions=[
+                    expression.Anonymous(
+                        this="TIMESTAMP",
+                        expressions=[
+                            Column.ensure_col(col).column_expression,
+                        ],
+                    )
+                ],
+            )
+        )
+
+    if _get_session()._is_postgres or _get_session()._is_snowflake:
         return unix_micros_multiply_epoch(col)
 
     return Column.invoke_anonymous_function(col, "unix_micros")

{sqlframe-3.18.1 → sqlframe-3.20.0}/sqlframe/base/session.py

@@ -267,10 +267,6 @@ class _BaseSession(t.Generic[CATALOG, READER, WRITER, DF, TABLE, CONN, UDF_REGIS
         else:
             column_mapping = {}
 
-        column_mapping = {
-            normalize_identifiers(k, self.input_dialect).sql(dialect=self.input_dialect): v
-            for k, v in column_mapping.items()
-        }
         empty_df = not data
         rows = [[None] * len(column_mapping)] if empty_df else list(data)  # type: ignore
 
@@ -327,7 +323,6 @@ class _BaseSession(t.Generic[CATALOG, READER, WRITER, DF, TABLE, CONN, UDF_REGIS
             if isinstance(sample_row, Row):
                 sample_row = sample_row.asDict()
             if isinstance(sample_row, dict):
-                sample_row = normalize_dict(self, sample_row)
                 default_data_type = get_default_data_type(sample_row[name])
                 updated_mapping[name] = (
                     exp.DataType.build(default_data_type, dialect="spark")
@@ -387,7 +382,11 @@ class _BaseSession(t.Generic[CATALOG, READER, WRITER, DF, TABLE, CONN, UDF_REGIS
         sel_expression = exp.Select(**select_kwargs)
         if empty_df:
             sel_expression = sel_expression.where(exp.false())
-        return self._create_df(sel_expression)
+        df = self._create_df(sel_expression)
+        df._update_display_name_mapping(
+            df._ensure_and_normalize_cols(list(column_mapping.keys())), list(column_mapping.keys())
+        )
+        return df
 
     def sql(
         self,
@@ -526,7 +525,9 @@ class _BaseSession(t.Generic[CATALOG, READER, WRITER, DF, TABLE, CONN, UDF_REGIS
             col_id._meta = {"case_sensitive": True, **(col_id._meta or {})}
             case_sensitive_cols.append(col_id)
         columns = [
-            normalize_string(x, from_dialect="execution", to_dialect="output")
+            normalize_string(
+                x, from_dialect="execution", to_dialect="output", to_string_literal=True
+            )
             for x in case_sensitive_cols
         ]
         return [self._to_row(columns, row) for row in result]

{sqlframe-3.18.1 → sqlframe-3.20.0}/sqlframe/base/util.py

@@ -316,6 +316,7 @@ def sqlglot_to_spark(sqlglot_dtype: exp.DataType) -> types.DataType:
         exp.DataType.Type.INT: types.IntegerType,
         exp.DataType.Type.BIGINT: types.LongType,
         exp.DataType.Type.SMALLINT: types.ShortType,
+        exp.DataType.Type.TINYINT: types.ByteType,
         exp.DataType.Type.FLOAT: types.FloatType,
         exp.DataType.Type.DOUBLE: types.DoubleType,
         exp.DataType.Type.DECIMAL: types.DecimalType,

{sqlframe-3.18.1 → sqlframe-3.20.0}/sqlframe/spark/session.py

@@ -86,7 +86,7 @@ class SparkSession(
                 col_id = exp.parse_identifier(k, dialect=self.execution_dialect)
                 col_id._meta = {"case_sensitive": True, **(col_id._meta or {})}
                 col_name = normalize_string(
-                    col_id, from_dialect="execution", to_dialect="output", is_column=True
+                    col_id, from_dialect="execution", to_dialect="output", to_string_literal=True
                 )
                 rows_normalized[col_name] = v
             results.append(Row(**rows_normalized))

{sqlframe-3.18.1 → sqlframe-3.20.0}/sqlframe.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.18.1
+Version: 3.20.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-3.18.1 → sqlframe-3.20.0}/sqlframe.egg-info/requires.txt

@@ -1,5 +1,5 @@
 prettytable<4
-sqlglot<26.5,>=24.0.0
+sqlglot<26.7,>=24.0.0
 typing_extensions
 
 [bigquery]

{sqlframe-3.18.1 → sqlframe-3.20.0}/tests/integration/engines/test_engine_dataframe.py

@@ -2,6 +2,7 @@ from __future__ import annotations
 
 import typing as t
 
+from sqlframe.base.session import _BaseSession
 from sqlframe.base.types import Row
 from sqlframe.snowflake import SnowflakeSession
 from sqlframe.spark import SparkSession
@@ -88,3 +89,68 @@ def test_show_limit(
 |      1      |  Jack | Shephard |  37 |    1     |
 +-------------+-------+----------+-----+----------+\n"""
         )
+
+
+# https://github.com/eakmanrq/sqlframe/issues/294
+def test_show_from_create_version_1(get_session: t.Callable[[], _BaseSession], capsys):
+    session = get_session()
+    df = session.createDataFrame([(1, 4), (2, 5), (3, 6)], schema=["foo", "BAR"])
+    df.show()
+    captured = capsys.readouterr()
+    assert (
+        captured.out.strip()
+        == """
++-----+-----+
+| foo | BAR |
++-----+-----+
+|  1  |  4  |
+|  2  |  5  |
+|  3  |  6  |
++-----+-----+
+""".strip()
+    )
+
+
+# https://github.com/eakmanrq/sqlframe/issues/294
+def test_show_from_create_version_2(get_session: t.Callable[[], _BaseSession], capsys):
+    session = get_session()
+    df = session.createDataFrame(
+        [
+            {"a": 1, "BAR": 1},
+            {"a": 1, "BAR": 2},
+        ]
+    )
+    df.show()
+    captured = capsys.readouterr()
+    assert (
+        captured.out.strip()
+        == """
++---+-----+
+| a | BAR |
++---+-----+
+| 1 |  1  |
+| 1 |  2  |
++---+-----+
+""".strip()
+    )
+
+
+def test_show_from_create_with_space(get_session: t.Callable[[], _BaseSession], capsys):
+    session = get_session()
+    df = session.createDataFrame(
+        [
+            {"zor ro": 1},
+        ]
+    )
+    df.show()
+    captured = capsys.readouterr()
+    assert (
+        captured.out.strip()
+        == """
++--------+
+| zor ro |
++--------+
+|   1    |
++--------+
+""".strip()
+    )

{sqlframe-3.18.1 → sqlframe-3.20.0}/tests/integration/engines/test_int_functions.py

@@ -150,13 +150,11 @@ def test_lit(get_session_and_func, arg, expected):
     "input, output",
     [
         ("employee_id", "employee_id"),
-        ("employee id", "`employee id`"),
+        ("employee id", "employee id"),
     ],
 )
 def test_col(get_session_and_func, input, output):
     session, col = get_session_and_func("col")
-    if isinstance(session, PySparkSession):
-        output = output.replace("`", "")
     df = session.createDataFrame([(1,)], schema=[input])
     result = df.select(col(input)).first()
     assert result[0] == 1
@@ -230,20 +228,7 @@ def test_alias(get_session_and_func):
     df = session.createDataFrame([(1,)], schema=["employee_id"])
     assert df.select(col("employee_id").alias("test")).first().__fields__[0] == "test"
     space_result = df.select(col("employee_id").alias("A Space In New Name")).first().__fields__[0]
-    if isinstance(
-        session,
-        (
-            DuckDBSession,
-            BigQuerySession,
-            PostgresSession,
-            SnowflakeSession,
-            SparkSession,
-            DatabricksSession,
-        ),
-    ):
-        assert space_result == "`A Space In New Name`"
-    else:
-        assert space_result == "A Space In New Name"
+    assert space_result == "A Space In New Name"
 
 
 def test_asc(get_session_and_func):
@@ -2072,13 +2057,20 @@ def test_array_prepend(get_session_and_func):
     ]
 
 
-def test_array_size(get_session_and_func):
+def test_array_size(get_session_and_func, get_func):
     session, array_size = get_session_and_func("array_size")
-    df = session.createDataFrame([([2, 1, 3],), (None,)], ["data"])
-    assert df.select(array_size(df.data).alias("r")).collect() == [
-        Row(r=3),
-        Row(r=None),
-    ]
+    # Snowflake doesn't support arrays in VALUES so we need to do it in select
+    if isinstance(session, SnowflakeSession):
+        lit = get_func("lit", session)
+        assert session.range(1).select(
+            array_size(lit(["a", "b", "c"])), array_size(lit(None))
+        ).collect() == [Row(value=3, value2=None)]
+    else:
+        df = session.createDataFrame([([2, 1, 3],), (None,)], ["data"])
+        assert df.select(array_size(df.data).alias("r")).collect() == [
+            Row(r=3),
+            Row(r=None),
+        ]
 
 
 def test_create_map(get_session_and_func, get_func):
@@ -3648,6 +3640,10 @@ def test_day(get_session_and_func, get_func):
     session, day = get_session_and_func("day")
     df = session.createDataFrame([("2015-04-08",)], ["dt"])
     assert df.select(day("dt").alias("day")).first()[0] == 8
+    df = session.createDataFrame([(datetime.datetime(2025, 4, 8),)], ["dt"])
+    assert df.select(day("dt").alias("day")).first()[0] == 8
+    df = session.createDataFrame([("2015-04-08 01:00:00",)], ["dt"])
+    assert df.select(day("dt").alias("day")).first()[0] == 8
 
 
 def test_elt(get_session_and_func, get_func):
@@ -4923,6 +4919,9 @@ def test_unix_micros(get_session_and_func, get_func):
     to_timestamp = get_func("to_timestamp", session)
     df = session.createDataFrame([("2015-07-22 10:00:00",)], ["t"])
     assert df.select(unix_micros(to_timestamp(df.t)).alias("n")).first()[0] == 1437559200000000
+    if not isinstance(session, SnowflakeSession):
+        df = session.createDataFrame([(datetime.datetime(2021, 3, 1, 12, 34, 56, 49000),)], ["t"])
+        assert df.select(unix_micros(df.t).alias("n")).first()[0] == 1614602096049000
 
 
 def test_unix_millis(get_session_and_func, get_func):

{sqlframe-3.18.1 → sqlframe-3.20.0}/tests/unit/standalone/test_dataframe.py

@@ -128,14 +128,14 @@ def test_missing_method(standalone_employee: StandaloneDataFrame):
 def test_expand_star(standalone_employee: StandaloneDataFrame):
     assert (
         standalone_employee.select("*").sql(pretty=False, optimize=False)
-        == "WITH `t51718876` AS (SELECT CAST(`employee_id` AS INT) AS `employee_id`, CAST(`fname` AS STRING) AS `fname`, CAST(`lname` AS STRING) AS `lname`, CAST(`age` AS INT) AS `age`, CAST(`store_id` AS INT) AS `store_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)) SELECT `employee_id`, `fname`, `lname`, `age`, `store_id` FROM `t51718876`"
+        == "WITH `t51718876` AS (SELECT CAST(`employee_id` AS INT) AS `employee_id`, CAST(`fname` AS STRING) AS `fname`, CAST(`lname` AS STRING) AS `lname`, CAST(`age` AS INT) AS `age`, CAST(`store_id` AS INT) AS `store_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)) SELECT `employee_id` AS `employee_id`, `fname` AS `fname`, `lname` AS `lname`, `age` AS `age`, `store_id` AS `store_id` FROM `t51718876`"
     )
 
 
 def test_expand_star_table_alias(standalone_employee: StandaloneDataFrame):
     assert (
         standalone_employee.alias("blah").select("blah.*").sql(pretty=False, optimize=False)
-        == "WITH `t51718876` AS (SELECT CAST(`employee_id` AS INT) AS `employee_id`, CAST(`fname` AS STRING) AS `fname`, CAST(`lname` AS STRING) AS `lname`, CAST(`age` AS INT) AS `age`, CAST(`store_id` AS INT) AS `store_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)), `t37842204` AS (SELECT `employee_id`, `fname`, `lname`, `age`, `store_id` FROM `t51718876`) SELECT `t37842204`.`employee_id`, `t37842204`.`fname`, `t37842204`.`lname`, `t37842204`.`age`, `t37842204`.`store_id` FROM `t37842204`"
+        == "WITH `t51718876` AS (SELECT CAST(`employee_id` AS INT) AS `employee_id`, CAST(`fname` AS STRING) AS `fname`, CAST(`lname` AS STRING) AS `lname`, CAST(`age` AS INT) AS `age`, CAST(`store_id` AS INT) AS `store_id` FROM VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100) AS `a1`(`employee_id`, `fname`, `lname`, `age`, `store_id`)), `t37842204` AS (SELECT `employee_id`, `fname`, `lname`, `age`, `store_id` FROM `t51718876`) SELECT `t37842204`.`employee_id` AS `employee_id`, `t37842204`.`fname` AS `fname`, `t37842204`.`lname` AS `lname`, `t37842204`.`age` AS `age`, `t37842204`.`store_id` AS `store_id` FROM `t37842204`"
     )
 
 
@@ -154,5 +154,5 @@ def test_lineage(standalone_employee: StandaloneDataFrame):
 def test_unquoted_identifiers(standalone_employee: StandaloneDataFrame):
     assert (
         standalone_employee.sql(dialect="snowflake", pretty=False, quote_identifiers=False)
-        == "SELECT A1.EMPLOYEE_ID AS EMPLOYEE_ID, CAST(A1.FNAME AS TEXT) AS FNAME, CAST(A1.LNAME AS TEXT) AS LNAME, A1.AGE AS AGE, A1.STORE_ID AS STORE_ID FROM (VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100)) AS A1(EMPLOYEE_ID, FNAME, LNAME, AGE, STORE_ID)"
+        == """SELECT A1.EMPLOYEE_ID AS "employee_id", CAST(A1.FNAME AS TEXT) AS "fname", CAST(A1.LNAME AS TEXT) AS "lname", A1.AGE AS "age", A1.STORE_ID AS "store_id" FROM (VALUES (1, 'Jack', 'Shephard', 37, 1), (2, 'John', 'Locke', 65, 1), (3, 'Kate', 'Austen', 37, 2), (4, 'Claire', 'Littleton', 27, 2), (5, 'Hugo', 'Reyes', 29, 100)) AS A1(EMPLOYEE_ID, FNAME, LNAME, AGE, STORE_ID)"""
     )

{sqlframe-3.18.1 → sqlframe-3.20.0}/tests/unit/standalone/test_functions.py

@@ -2152,8 +2152,8 @@ def test_array_prepend(expression, expected):
 @pytest.mark.parametrize(
     "expression, expected",
     [
-        (SF.array_size("cola"), "ARRAY_SIZE(cola)"),
-        (SF.array_size(SF.col("cola")), "ARRAY_SIZE(cola)"),
+        (SF.array_size("cola"), "SIZE(cola)"),
+        (SF.array_size(SF.col("cola")), "SIZE(cola)"),
     ],
 )
 def test_array_size(expression, expected):

{sqlframe-3.18.1 → sqlframe-3.20.0}/tests/unit/test_util.py

@@ -39,6 +39,7 @@ def test_quote_preserving_alias_or_name(expression: t.Union[exp.Column, exp.Alia
         ("INTEGER", types.IntegerType()),
         ("BIGINT", types.LongType()),
         ("SMALLINT", types.ShortType()),
+        ("TINYINT", types.ByteType()),
         ("FLOAT", types.FloatType()),
         ("DOUBLE", types.DoubleType()),
         ("BOOLEAN", types.BooleanType()),