sqlframe 1.7.1__tar.gz → 1.9.0__tar.gz

{sqlframe-1.7.1 → sqlframe-1.9.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 1.7.1
+Version: 1.9.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-1.7.1 → sqlframe-1.9.0}/docs/spark.md

@@ -183,6 +183,8 @@ df.show(5)
 * [acos](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.acos.html)
 * [acosh](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.acosh.html)
 * [add_months](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.add_months.html)
+* [aes_encrypt](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.aes_encrypt.html)
+* [aes_decrypt](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.aes_decrypt.html)
 * [aggregate](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.aggregate.html)
 * [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)
@@ -310,6 +312,7 @@ df.show(5)
 * [lpad](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.lpad.html)
 * [ltrim](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.ltrim.html)
 * [make_date](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.make_date.html)
+* [make_interval](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.make_interval.html)
 * [map_concat](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.map_concat.html)
 * [map_entries](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.map_entries.html)
 * [map_filter](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.map_filter.html)
@@ -397,6 +400,7 @@ df.show(5)
 * [timestamp_seconds](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.timestamp_seconds.html)
 * [toDegrees](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.toDegrees.html)
 * [toRadians](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.toRadians.html)
+* [to_binary](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_binary.html)
 * [to_csv](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_csv.html)
 * [to_date](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_date.html)
 * [to_json](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.to_json.html)
@@ -408,6 +412,14 @@ df.show(5)
 * [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)
+* [try_add](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.try_add.html)
+* [try_avg](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.try_avg.html)
+* [try_divide](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.try_divide.html)
+* [try_multiply](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.try_multiply.html)
+* [try_subtract](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.try_subtract.html)
+* [try_sum](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.try_sum.html)
+* [try_to_binary](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.try_to_binary.html)
+* [try_to_number](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.try_to_number.html)
 * [typeof](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.typeof.html)
 * [unbase64](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.unbase64.html)
 * [unhex](https://spark.apache.org/docs/latest/api/python/reference/pyspark.sql/api/pyspark.sql.functions.unhex.html)

{sqlframe-1.7.1 → sqlframe-1.9.0}/setup.py

@@ -20,7 +20,7 @@ setup(
     python_requires=">=3.8",
     install_requires=[
         "prettytable<3.11.0",
-        "sqlglot>=24.0.0,<25.1",
+        "sqlglot>=24.0.0,<25.4",
         "typing_extensions>=4.8,<5",
     ],
     extras_require={
@@ -31,7 +31,7 @@ setup(
         "dev": [
             "duckdb>=0.9,<1.1",
             "mypy>=1.10.0,<1.11",
-            "openai>=1.30,<1.34",
+            "openai>=1.30,<1.36",
             "pandas>=2,<3",
             "pandas-stubs>=2,<3",
             "psycopg>=3.1,<4",
@@ -57,7 +57,7 @@ setup(
             "pandas>=2,<3",
         ],
         "openai": [
-            "openai>=1.30,<1.34",
+            "openai>=1.30,<1.36",
         ],
         "pandas": [
             "pandas>=2,<3",
@@ -69,7 +69,7 @@ setup(
             "redshift_connector>=2.1.1,<2.2.0",
         ],
         "snowflake": [
-            "snowflake-connector-python[secure-local-storage]>=3.10.0,<3.11",
+            "snowflake-connector-python[secure-local-storage]>=3.10.0,<3.12",
         ],
         "spark": [
             "pyspark>=2,<3.6",

{sqlframe-1.7.1 → sqlframe-1.9.0}/sqlframe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '1.7.1'
-__version_tuple__ = version_tuple = (1, 7, 1)
+__version__ = version = '1.9.0'
+__version_tuple__ = version_tuple = (1, 9, 0)

{sqlframe-1.7.1 → sqlframe-1.9.0}/sqlframe/base/column.py

@@ -229,7 +229,7 @@ class Column:
         return Column(op)
 
     def unary_op(self, klass: t.Callable, **kwargs) -> Column:
-        return Column(klass(this=self.column_expression, **kwargs))
+        return Column(klass(this=exp.Paren(this=self.column_expression), **kwargs))
 
     @property
     def is_alias(self):

{sqlframe-1.7.1 → sqlframe-1.9.0}/sqlframe/base/functions.py

@@ -1682,6 +1682,98 @@ def stack(*cols: ColumnOrName) -> Column:
     )
 
 
+@meta(unsupported_engines="*")
+def make_interval(
+    years: t.Optional[ColumnOrName] = None,
+    months: t.Optional[ColumnOrName] = None,
+    weeks: t.Optional[ColumnOrName] = None,
+    days: t.Optional[ColumnOrName] = None,
+    hours: t.Optional[ColumnOrName] = None,
+    mins: t.Optional[ColumnOrName] = None,
+    secs: t.Optional[ColumnOrName] = None,
+) -> Column:
+    columns = _ensure_column_of_optionals([years, months, weeks, days, hours, mins, secs])
+    if not columns:
+        raise ValueError("At least one value must be provided")
+    return Column.invoke_anonymous_function(columns[0], "MAKE_INTERVAL", *columns[1:])
+
+
+@meta(unsupported_engines="*")
+def try_add(left: ColumnOrName, right: ColumnOrName) -> Column:
+    return Column.invoke_anonymous_function(left, "TRY_ADD", right)
+
+
+@meta(unsupported_engines="*")
+def try_avg(col: ColumnOrName) -> Column:
+    return Column.invoke_anonymous_function(col, "TRY_AVG")
+
+
+@meta(unsupported_engines="*")
+def try_divide(left: ColumnOrName, right: ColumnOrName) -> Column:
+    return Column.invoke_anonymous_function(left, "TRY_DIVIDE", right)
+
+
+@meta(unsupported_engines="*")
+def try_multiply(left: ColumnOrName, right: ColumnOrName) -> Column:
+    return Column.invoke_anonymous_function(left, "TRY_MULTIPLY", right)
+
+
+@meta(unsupported_engines="*")
+def try_subtract(left: ColumnOrName, right: ColumnOrName) -> Column:
+    return Column.invoke_anonymous_function(left, "TRY_SUBTRACT", right)
+
+
+@meta(unsupported_engines="*")
+def try_sum(col: ColumnOrName) -> Column:
+    return Column.invoke_anonymous_function(col, "TRY_SUM")
+
+
+@meta(unsupported_engines="*")
+def try_to_binary(col: ColumnOrName, format: t.Optional[ColumnOrName] = None) -> Column:
+    if format is not None:
+        return Column.invoke_anonymous_function(col, "TRY_TO_BINARY", format)
+    return Column.invoke_anonymous_function(col, "TRY_TO_BINARY")
+
+
+@meta(unsupported_engines="*")
+def try_to_number(col: ColumnOrName, format: t.Optional[ColumnOrName] = None) -> Column:
+    if format is not None:
+        return Column.invoke_anonymous_function(col, "TRY_TO_NUMBER", format)
+    return Column.invoke_anonymous_function(col, "TRY_TO_NUMBER")
+
+
+@meta(unsupported_engines="*")
+def aes_decrypt(
+    input: ColumnOrName,
+    key: ColumnOrName,
+    mode: t.Optional[ColumnOrName] = None,
+    padding: t.Optional[ColumnOrName] = None,
+    aad: t.Optional[ColumnOrName] = None,
+) -> Column:
+    columns = _ensure_column_of_optionals([key, mode, padding, aad])
+    return Column.invoke_anonymous_function(input, "AES_DECRYPT", *columns)
+
+
+@meta(unsupported_engines="*")
+def aes_encrypt(
+    input: ColumnOrName,
+    key: ColumnOrName,
+    mode: t.Optional[ColumnOrName] = None,
+    padding: t.Optional[ColumnOrName] = None,
+    iv: t.Optional[ColumnOrName] = None,
+    aad: t.Optional[ColumnOrName] = None,
+) -> Column:
+    columns = _ensure_column_of_optionals([key, mode, padding, iv, aad])
+    return Column.invoke_anonymous_function(input, "AES_ENCRYPT", *columns)
+
+
+@meta(unsupported_engines="*")
+def to_binary(col: ColumnOrName, format: t.Optional[ColumnOrName] = None) -> Column:
+    if format is not None:
+        return Column.invoke_anonymous_function(col, "TO_BINARY", format)
+    return Column.invoke_anonymous_function(col, "TO_BINARY")
+
+
 @meta()
 def _lambda_quoted(value: str) -> t.Optional[bool]:
     return False if value == "_" else None
@@ -1697,3 +1789,11 @@ def _get_lambda_from_func(lambda_expression: t.Callable):
         this=lambda_expression(*[Column(x) for x in variables]).expression,
         expressions=variables,
     )
+
+
+def _ensure_column_of_optionals(optionals: t.List[t.Optional[ColumnOrName]]) -> t.List[Column]:
+    for value in reversed(optionals.copy()):
+        if value is not None:
+            break
+        optionals = optionals[:-1]
+    return [Column.ensure_col(x) if x is not None else lit(None) for x in optionals]

{sqlframe-1.7.1 → sqlframe-1.9.0}/sqlframe/spark/catalog.py

@@ -519,7 +519,10 @@ class SparkCatalog(
                 )
                 for col in df.columns
             ]
-        return [Column(*x) for x in self._spark_catalog.listColumns(tableName, dbName)]
+        return [
+            Column(**{name: x._asdict()[name] for name in Column._fields})
+            for x in self._spark_catalog.listColumns(tableName, dbName)
+        ]
 
     def listFunctions(
         self, dbName: t.Optional[str] = None, pattern: t.Optional[str] = None

{sqlframe-1.7.1 → sqlframe-1.9.0}/sqlframe/spark/functions.pyi

@@ -7,6 +7,8 @@ from sqlframe.base.functions import (
     abs as abs,
     acos as acos,
     acosh as acosh,
+    aes_encrypt as aes_encrypt,
+    aes_decrypt as aes_decrypt,
     aggregate as aggregate,
     approxCountDistinct as approxCountDistinct,
     approx_count_distinct as approx_count_distinct,
@@ -132,6 +134,7 @@ from sqlframe.base.functions import (
     lpad as lpad,
     ltrim as ltrim,
     make_date as make_date,
+    make_interval as make_interval,
     map_concat as map_concat,
     map_entries as map_entries,
     map_filter as map_filter,
@@ -217,6 +220,7 @@ from sqlframe.base.functions import (
     timestamp_seconds as timestamp_seconds,
     toDegrees as toDegrees,
     toRadians as toRadians,
+    to_binary as to_binary,
     to_csv as to_csv,
     to_date as to_date,
     to_json as to_json,
@@ -228,6 +232,14 @@ from sqlframe.base.functions import (
     translate as translate,
     trim as trim,
     trunc as trunc,
+    try_add as try_add,
+    try_avg as try_avg,
+    try_divide as try_divide,
+    try_multiply as try_multiply,
+    try_subtract as try_subtract,
+    try_sum as try_sum,
+    try_to_binary as try_to_binary,
+    try_to_number as try_to_number,
     typeof as typeof,
     unbase64 as unbase64,
     unhex as unhex,

{sqlframe-1.7.1 → sqlframe-1.9.0}/sqlframe.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 1.7.1
+Version: 1.9.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-1.7.1 → sqlframe-1.9.0}/sqlframe.egg-info/requires.txt

@@ -1,5 +1,5 @@
 prettytable<3.11.0
-sqlglot<25.1,>=24.0.0
+sqlglot<25.4,>=24.0.0
 typing_extensions<5,>=4.8
 
 [bigquery]
@@ -9,7 +9,7 @@ google-cloud-bigquery[pandas]<4,>=3
 [dev]
 duckdb<1.1,>=0.9
 mypy<1.11,>=1.10.0
-openai<1.34,>=1.30
+openai<1.36,>=1.30
 pandas-stubs<3,>=2
 pandas<3,>=2
 psycopg<4,>=3.1
@@ -39,7 +39,7 @@ duckdb<1.1,>=0.9
 pandas<3,>=2
 
 [openai]
-openai<1.34,>=1.30
+openai<1.36,>=1.30
 
 [pandas]
 pandas<3,>=2
@@ -51,7 +51,7 @@ psycopg2<3,>=2.8
 redshift_connector<2.2.0,>=2.1.1
 
 [snowflake]
-snowflake-connector-python[secure-local-storage]<3.11,>=3.10.0
+snowflake-connector-python[secure-local-storage]<3.12,>=3.10.0
 
 [spark]
 pyspark<3.6,>=2

{sqlframe-1.7.1 → sqlframe-1.9.0}/tests/conftest.py

@@ -7,7 +7,7 @@ import pytest
 
 def pytest_collection_modifyitems(items, *args, **kwargs):
     for item in items:
-        if not list(item.iter_markers()):
+        if not [x for x in item.iter_markers() if x.name != "parametrize"]:
             item.add_marker("fast")
 
 

{sqlframe-1.7.1 → sqlframe-1.9.0}/tests/integration/engines/bigquery/test_bigquery_session.py

@@ -16,5 +16,5 @@ def test_session_from_config():
     conn.cursor().execute("CREATE SCHEMA IF NOT EXISTS db1")
     conn.cursor().execute("CREATE TABLE IF NOT EXISTS db1.test_table (cola INT, colb STRING)")
     session = BigQuerySession.builder.config("default_dataset", "sqlframe.db1").getOrCreate()
-    columns = session.catalog.get_columns("test_table")
+    columns = session.catalog.get_columns("db1.test_table")
     assert columns == {"`cola`": exp.DataType.build("BIGINT"), "`colb`": exp.DataType.build("TEXT")}

{sqlframe-1.7.1 → sqlframe-1.9.0}/tests/integration/engines/duck/test_duckdb_session.py

@@ -10,4 +10,4 @@ def test_session_from_config():
     conn.execute("CREATE TABLE test_table (cola INT, colb STRING)")
     session = DuckDBSession.builder.config("sqlframe.conn", conn).getOrCreate()
     columns = session.catalog.get_columns("test_table")
-    assert columns == {'"cola"': exp.DataType.build("INT"), '"colb"': exp.DataType.build("VARCHAR")}
+    assert columns == {'"cola"': exp.DataType.build("INT"), '"colb"': exp.DataType.build("TEXT")}