sqlframe 3.1.1__tar.gz → 3.3.0__tar.gz

{sqlframe-3.1.1 → sqlframe-3.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.1.1
+Version: 3.3.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-3.1.1 → sqlframe-3.3.0}/docs/standalone.md

@@ -84,7 +84,7 @@ from sqlframe.standalone import StandaloneSession
 session = StandaloneSession()
 
 session.catalog.add_table("test_table", column_mapping={"a": "int", "b": "int", "c": "int"})
-df = session.read.table("my_table")
+df = session.read.table("test_table")
 df.sql()
 ```
 

{sqlframe-3.1.1 → sqlframe-3.3.0}/setup.py

@@ -20,7 +20,7 @@ setup(
     python_requires=">=3.8",
     install_requires=[
         "prettytable<3.11.1",
-        "sqlglot>=24.0.0,<25.18",
+        "sqlglot>=24.0.0,<25.22",
         "typing_extensions>=4.8,<5",
     ],
     extras_require={
@@ -29,10 +29,10 @@ setup(
             "google-cloud-bigquery-storage>=2,<3",
         ],
         "dev": [
-            "duckdb>=0.9,<1.1",
+            "duckdb>=0.9,<1.2",
             "findspark>=2,<3",
             "mypy>=1.10.0,<1.12",
-            "openai>=1.30,<1.43",
+            "openai>=1.30,<1.46",
             "pandas>=2,<3",
             "pandas-stubs>=2,<3",
             "psycopg>=3.1,<4",
@@ -54,11 +54,11 @@ setup(
             "pymdown-extensions",
         ],
         "duckdb": [
-            "duckdb>=0.9,<1.1",
+            "duckdb>=0.9,<1.2",
             "pandas>=2,<3",
         ],
         "openai": [
-            "openai>=1.30,<1.43",
+            "openai>=1.30,<1.46",
         ],
         "pandas": [
             "pandas>=2,<3",

{sqlframe-3.1.1 → sqlframe-3.3.0}/sqlframe/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.1.1'
-__version_tuple__ = version_tuple = (3, 1, 1)
+__version__ = version = '3.3.0'
+__version_tuple__ = version_tuple = (3, 3, 0)

{sqlframe-3.1.1 → sqlframe-3.3.0}/sqlframe/base/dataframe.py

@@ -1627,7 +1627,11 @@ class _BaseDataFrame(t.Generic[SESSION, WRITER, NA, STAT, GROUP_DATA]):
 
     def createOrReplaceTempView(self, name: str) -> None:
         name = normalize_string(name, from_dialect="input")
-        self.session.temp_views[name] = self.copy()._convert_leaf_to_cte()
+        df = self.copy()._convert_leaf_to_cte()
+        self.session.temp_views[name] = df
+        self.session.catalog.add_table(
+            name, [x.alias_or_name for x in self._get_outer_select_columns(df.expression)]
+        )
 
     def count(self) -> int:
         if not self.session._has_connection:

{sqlframe-3.1.1 → sqlframe-3.3.0}/sqlframe/base/functions.py

@@ -2052,7 +2052,7 @@ def cardinality(col: ColumnOrName) -> Column:
 
 @meta()
 def char(col: ColumnOrName) -> Column:
-    return Column.invoke_expression_over_column(col, expression.Chr)
+    return Column(expression.Chr(expressions=Column.ensure_col(col).expression))
 
 
 @meta(unsupported_engines="*")
@@ -2703,7 +2703,7 @@ def inline(col: ColumnOrName) -> Column:
     |  3|  4|
     +---+---+
     """
-    return Column.invoke_anonymous_function(col, "inline")
+    return Column.invoke_expression_over_column(col, expression.Inline)
 
 
 @meta(unsupported_engines="*")

{sqlframe-3.1.1 → sqlframe-3.3.0}/sqlframe/base/group.py

@@ -68,7 +68,7 @@ class _BaseGroupedData(t.Generic[DF]):
                 )
                 group_by_cols.extend(grouping_set)  # type: ignore
             group_by_cols = list(dict.fromkeys(group_by_cols))
-            group_by = exp.Group(grouping_sets=all_grouping_sets)
+            group_by = exp.Group(grouping_sets=[exp.GroupingSets(expressions=all_grouping_sets)])
             expression.set("group", group_by)
         for col in cols:
             # Spark supports having an empty grouping_id which means all of the columns but other dialects

{sqlframe-3.1.1 → sqlframe-3.3.0}/sqlframe/base/session.py

@@ -391,7 +391,11 @@ class _BaseSession(t.Generic[CATALOG, READER, WRITER, DF, CONN, UDF_REGISTRATION
         )
         if qualify:
             expression = qualify_func(
-                expression, dialect=dialect, quote_identifiers=False, identify=False
+                expression,
+                dialect=dialect,
+                quote_identifiers=False,
+                identify=False,
+                schema=self.catalog._schema,
             )
         if self.temp_views:
             replacement_mapping = {}

{sqlframe-3.1.1 → sqlframe-3.3.0}/sqlframe/base/util.py

@@ -306,7 +306,6 @@ def quote_preserving_alias_or_name(col: t.Union[exp.Column, exp.Alias]) -> str:
 def sqlglot_to_spark(sqlglot_dtype: exp.DataType) -> types.DataType:
     from sqlframe.base import types
 
-    sqlglot_to_spark
     primitive_mapping = {
         exp.DataType.Type.VARCHAR: types.VarcharType,
         exp.DataType.Type.CHAR: types.CharType,
@@ -325,6 +324,7 @@ def sqlglot_to_spark(sqlglot_dtype: exp.DataType) -> types.DataType:
         exp.DataType.Type.TIMESTAMPLTZ: types.TimestampType,
         exp.DataType.Type.TIMESTAMPNTZ: types.TimestampType,
         exp.DataType.Type.DATE: types.DateType,
+        exp.DataType.Type.JSON: types.StringType,
     }
     if sqlglot_dtype.this in primitive_mapping:
         pyspark_class = primitive_mapping[sqlglot_dtype.this]

{sqlframe-3.1.1 → sqlframe-3.3.0}/sqlframe/duckdb/readwriter.py

@@ -85,12 +85,16 @@ class DuckDBDataFrameReader(_BaseDataFrameReader["DuckDBSession", "DuckDBDataFra
                 options["columns"] = "{" + duckdb_columns + "}"
         else:
             select_columns = [exp.Star()]
-        if format:
+        if format == "delta":
+            from_clause = f"delta_scan('{path}')"
+        elif format:
             paths = ",".join([f"'{path}'" for path in ensure_list(path)])
             from_clause = f"read_{format}([{paths}], {to_csv(options)})"
         else:
             from_clause = f"'{path}'"
         df = self.session.sql(exp.select(*select_columns).from_(from_clause), qualify=False)
+        if select_columns == [exp.Star()]:
+            return self.load(path=path, format=format, schema=df.schema, **options)
         self.session._last_loaded_file = path  # type: ignore
         return df
 

{sqlframe-3.1.1 → sqlframe-3.3.0}/sqlframe/duckdb/session.py

@@ -54,8 +54,14 @@ class DuckDBSession(
 
     @classmethod
     def _try_get_map(cls, value: t.Any) -> t.Optional[t.Dict[str, t.Any]]:
-        if value and isinstance(value, dict) and "key" in value and "value" in value:
-            return dict(zip(value["key"], value["value"]))
+        if value and isinstance(value, dict):
+            # DuckDB < 1.1.0 support
+            if "key" in value and "value" in value:
+                return dict(zip(value["key"], value["value"]))
+            # DuckDB >= 1.1.0 support
+            # If a key is not a string then it must not represent a column and therefore must be a map
+            if len([k for k in value if not isinstance(k, str)]) > 0:
+                return value
         return None
 
     def _execute(self, sql: str) -> None:

{sqlframe-3.1.1 → sqlframe-3.3.0}/sqlframe/spark/catalog.py

@@ -569,7 +569,9 @@ class SparkCatalog(
         return [
             Table(
                 name=normalize_string(x.name, from_dialect="execution", to_dialect="output"),
-                catalog=normalize_string(x.catalog, from_dialect="execution", to_dialect="output"),
+                catalog=normalize_string(x.catalog, from_dialect="execution", to_dialect="output")
+                if x.catalog
+                else None,
                 namespace=[
                     normalize_string(y, from_dialect="execution", to_dialect="output")
                     for y in x.namespace

{sqlframe-3.1.1 → sqlframe-3.3.0}/sqlframe.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sqlframe
-Version: 3.1.1
+Version: 3.3.0
 Summary: Turning PySpark Into a Universal DataFrame API
 Home-page: https://github.com/eakmanrq/sqlframe
 Author: Ryan Eakman

{sqlframe-3.1.1 → sqlframe-3.3.0}/sqlframe.egg-info/SOURCES.txt

@@ -171,6 +171,119 @@ tests/fixtures/employee.csv
 tests/fixtures/employee.json
 tests/fixtures/employee.parquet
 tests/fixtures/employee_extra_line.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
+tests/fixtures/employee_delta/.part-00006-64f07e25-c30e-4075-acc6-b3c69c4ce80b-c000.snappy.parquet.crc
+tests/fixtures/employee_delta/.part-00008-89ccad8d-df73-4ad5-8850-82ef3884db60-c000.snappy.parquet.crc
+tests/fixtures/employee_delta/.part-00010-812b3382-8c7f-4c4e-9bcd-09ce8664f6e0-c000.snappy.parquet.crc
+tests/fixtures/employee_delta/part-00000-e5965c7b-e58f-4d3c-ad56-002876814e3a-c000.snappy.parquet
+tests/fixtures/employee_delta/part-00002-3fed7f18-370f-4b16-b232-504d6194eb52-c000.snappy.parquet
+tests/fixtures/employee_delta/part-00004-143c5da1-d5ab-4706-8e84-0d2a324c6894-c000.snappy.parquet
+tests/fixtures/employee_delta/part-00006-64f07e25-c30e-4075-acc6-b3c69c4ce80b-c000.snappy.parquet
+tests/fixtures/employee_delta/part-00008-89ccad8d-df73-4ad5-8850-82ef3884db60-c000.snappy.parquet
+tests/fixtures/employee_delta/part-00010-812b3382-8c7f-4c4e-9bcd-09ce8664f6e0-c000.snappy.parquet
+tests/fixtures/employee_delta/_delta_log/.00000000000000000000.json.crc
+tests/fixtures/employee_delta/_delta_log/00000000000000000000.json
+tests/fixtures/tpcds/tpcds1.sql
+tests/fixtures/tpcds/tpcds10.sql
+tests/fixtures/tpcds/tpcds11.sql
+tests/fixtures/tpcds/tpcds12.sql
+tests/fixtures/tpcds/tpcds13.sql
+tests/fixtures/tpcds/tpcds14.sql
+tests/fixtures/tpcds/tpcds15.sql
+tests/fixtures/tpcds/tpcds16.sql
+tests/fixtures/tpcds/tpcds17.sql
+tests/fixtures/tpcds/tpcds18.sql
+tests/fixtures/tpcds/tpcds19.sql
+tests/fixtures/tpcds/tpcds2.sql
+tests/fixtures/tpcds/tpcds20.sql
+tests/fixtures/tpcds/tpcds21.sql
+tests/fixtures/tpcds/tpcds22.sql
+tests/fixtures/tpcds/tpcds23.sql
+tests/fixtures/tpcds/tpcds24.sql
+tests/fixtures/tpcds/tpcds25.sql
+tests/fixtures/tpcds/tpcds26.sql
+tests/fixtures/tpcds/tpcds27.sql
+tests/fixtures/tpcds/tpcds28.sql
+tests/fixtures/tpcds/tpcds29.sql
+tests/fixtures/tpcds/tpcds3.sql
+tests/fixtures/tpcds/tpcds30.sql
+tests/fixtures/tpcds/tpcds31.sql
+tests/fixtures/tpcds/tpcds32.sql
+tests/fixtures/tpcds/tpcds33.sql
+tests/fixtures/tpcds/tpcds34.sql
+tests/fixtures/tpcds/tpcds35.sql
+tests/fixtures/tpcds/tpcds36.sql
+tests/fixtures/tpcds/tpcds37.sql
+tests/fixtures/tpcds/tpcds38.sql
+tests/fixtures/tpcds/tpcds39.sql
+tests/fixtures/tpcds/tpcds4.sql
+tests/fixtures/tpcds/tpcds40.sql
+tests/fixtures/tpcds/tpcds41.sql
+tests/fixtures/tpcds/tpcds42.sql
+tests/fixtures/tpcds/tpcds43.sql
+tests/fixtures/tpcds/tpcds44.sql
+tests/fixtures/tpcds/tpcds45.sql
+tests/fixtures/tpcds/tpcds46.sql
+tests/fixtures/tpcds/tpcds47.sql
+tests/fixtures/tpcds/tpcds48.sql
+tests/fixtures/tpcds/tpcds49.sql
+tests/fixtures/tpcds/tpcds5.sql
+tests/fixtures/tpcds/tpcds50.sql
+tests/fixtures/tpcds/tpcds51.sql
+tests/fixtures/tpcds/tpcds52.sql
+tests/fixtures/tpcds/tpcds53.sql
+tests/fixtures/tpcds/tpcds54.sql
+tests/fixtures/tpcds/tpcds55.sql
+tests/fixtures/tpcds/tpcds56.sql
+tests/fixtures/tpcds/tpcds57.sql
+tests/fixtures/tpcds/tpcds58.sql
+tests/fixtures/tpcds/tpcds59.sql
+tests/fixtures/tpcds/tpcds6.sql
+tests/fixtures/tpcds/tpcds60.sql
+tests/fixtures/tpcds/tpcds61.sql
+tests/fixtures/tpcds/tpcds62.sql
+tests/fixtures/tpcds/tpcds63.sql
+tests/fixtures/tpcds/tpcds64.sql
+tests/fixtures/tpcds/tpcds65.sql
+tests/fixtures/tpcds/tpcds66.sql
+tests/fixtures/tpcds/tpcds67.sql
+tests/fixtures/tpcds/tpcds68.sql
+tests/fixtures/tpcds/tpcds69.sql
+tests/fixtures/tpcds/tpcds7.sql
+tests/fixtures/tpcds/tpcds70.sql
+tests/fixtures/tpcds/tpcds71.sql
+tests/fixtures/tpcds/tpcds72.sql
+tests/fixtures/tpcds/tpcds73.sql
+tests/fixtures/tpcds/tpcds74.sql
+tests/fixtures/tpcds/tpcds75.sql
+tests/fixtures/tpcds/tpcds76.sql
+tests/fixtures/tpcds/tpcds77.sql
+tests/fixtures/tpcds/tpcds78.sql
+tests/fixtures/tpcds/tpcds79.sql
+tests/fixtures/tpcds/tpcds8.sql
+tests/fixtures/tpcds/tpcds80.sql
+tests/fixtures/tpcds/tpcds81.sql
+tests/fixtures/tpcds/tpcds82.sql
+tests/fixtures/tpcds/tpcds83.sql
+tests/fixtures/tpcds/tpcds84.sql
+tests/fixtures/tpcds/tpcds85.sql
+tests/fixtures/tpcds/tpcds86.sql
+tests/fixtures/tpcds/tpcds87.sql
+tests/fixtures/tpcds/tpcds88.sql
+tests/fixtures/tpcds/tpcds89.sql
+tests/fixtures/tpcds/tpcds9.sql
+tests/fixtures/tpcds/tpcds90.sql
+tests/fixtures/tpcds/tpcds91.sql
+tests/fixtures/tpcds/tpcds92.sql
+tests/fixtures/tpcds/tpcds93.sql
+tests/fixtures/tpcds/tpcds94.sql
+tests/fixtures/tpcds/tpcds95.sql
+tests/fixtures/tpcds/tpcds96.sql
+tests/fixtures/tpcds/tpcds97.sql
+tests/fixtures/tpcds/tpcds98.sql
+tests/fixtures/tpcds/tpcds99.sql
 tests/integration/__init__.py
 tests/integration/fixtures.py
 tests/integration/test_int_dataframe.py
@@ -196,6 +309,7 @@ tests/integration/engines/duck/test_duckdb_dataframe.py
 tests/integration/engines/duck/test_duckdb_reader.py
 tests/integration/engines/duck/test_duckdb_session.py
 tests/integration/engines/duck/test_duckdb_udf.py
+tests/integration/engines/duck/test_tpcds.py
 tests/integration/engines/postgres/__init__.py
 tests/integration/engines/postgres/test_postgres_activate.py
 tests/integration/engines/postgres/test_postgres_catalog.py

{sqlframe-3.1.1 → sqlframe-3.3.0}/sqlframe.egg-info/requires.txt

@@ -1,5 +1,5 @@
 prettytable<3.11.1
-sqlglot<25.18,>=24.0.0
+sqlglot<25.22,>=24.0.0
 typing_extensions<5,>=4.8
 
 [bigquery]
@@ -7,10 +7,10 @@ google-cloud-bigquery-storage<3,>=2
 google-cloud-bigquery[pandas]<4,>=3
 
 [dev]
-duckdb<1.1,>=0.9
+duckdb<1.2,>=0.9
 findspark<3,>=2
 mypy<1.12,>=1.10.0
-openai<1.43,>=1.30
+openai<1.46,>=1.30
 pandas-stubs<3,>=2
 pandas<3,>=2
 psycopg<4,>=3.1
@@ -36,11 +36,11 @@ mkdocs==1.4.2
 pymdown-extensions
 
 [duckdb]
-duckdb<1.1,>=0.9
+duckdb<1.2,>=0.9
 pandas<3,>=2
 
 [openai]
-openai<1.43,>=1.30
+openai<1.46,>=1.30
 
 [pandas]
 pandas<3,>=2

{sqlframe-3.1.1 → sqlframe-3.3.0}/tests/common_fixtures.py

@@ -2,12 +2,15 @@ from __future__ import annotations
 
 import os
 import typing as t
+from pathlib import Path
 
+import duckdb
 import pytest
 from pyspark import SparkConf
 from pyspark.sql import SparkSession as PySparkSession
 from pytest_postgresql.janitor import DatabaseJanitor
 
+from sqlframe.base.session import _BaseSession
 from sqlframe.bigquery.session import BigQuerySession
 from sqlframe.duckdb.session import DuckDBSession
 from sqlframe.postgres.session import PostgresSession
@@ -28,8 +31,57 @@ if t.TYPE_CHECKING:
     from tests.types import EmployeeData
 
 
+def load_tpcds(paths: t.List[Path], session: t.Union[_BaseSession, PySparkSession]):
+    for path in paths:
+        table_name = path.name
+        session.read.parquet(str(path / "*.parquet")).createOrReplaceTempView(table_name)
+
+
 @pytest.fixture(scope="session")
-def pyspark_session(tmp_path_factory) -> PySparkSession:
+def gen_tpcds(tmp_path_factory) -> t.List[Path]:
+    path_root = tmp_path_factory.mktemp("tpcds")
+    results = []
+    tables = [
+        "web_site",
+        "web_sales",
+        "web_returns",
+        "web_page",
+        "warehouse",
+        "time_dim",
+        "store_sales",
+        "store_returns",
+        "store",
+        "ship_mode",
+        "reason",
+        "promotion",
+        "item",
+        "inventory",
+        "income_band",
+        "household_demographics",
+        "date_dim",
+        "customer_demographics",
+        "customer_address",
+        "customer",
+        "catalog_sales",
+        "catalog_returns",
+        "catalog_page",
+        "call_center",
+    ]
+    con = duckdb.connect()
+    con.sql("CALL dsdgen(sf=0.01)")
+    for table in tables:
+        path = path_root / table
+        path.mkdir(parents=True)
+        con.sql(
+            f"COPY (SELECT * FROM {table}) TO '{path}' (FORMAT PARQUET, PER_THREAD_OUTPUT TRUE)"
+        )
+        results.append(path)
+    con.close()
+    return results
+
+
+@pytest.fixture(scope="session")
+def pyspark_session(tmp_path_factory, gen_tpcds: t.List[Path]) -> PySparkSession:
     data_dir = tmp_path_factory.mktemp("spark_connection")
     derby_dir = tmp_path_factory.mktemp("derby")
     spark = (
@@ -49,6 +101,7 @@ def pyspark_session(tmp_path_factory) -> PySparkSession:
     spark.sql("CREATE TABLE db1.table1 (id INTEGER, name STRING)")
     spark.catalog.registerFunction("add", lambda x, y: x + y)
     spark.catalog.setCurrentDatabase("db1")
+    load_tpcds(gen_tpcds, spark)
     return spark
 
 
@@ -64,11 +117,7 @@ def spark_session(pyspark_session: PySparkSession) -> SparkSession:
 
 @pytest.fixture(scope="function")
 def duckdb_session() -> DuckDBSession:
-    from duckdb import connect
-
-    # https://github.com/duckdb/duckdb/issues/11404
-    connection = connect()
-    connection.sql("set TimeZone = 'UTC'")
+    connection = duckdb.connect(config={"TimeZone": "UTC"})
     return DuckDBSession(conn=connection)
 
 

sqlframe-3.3.0/tests/fixtures/employee_delta/_delta_log/00000000000000000000.json

@@ -0,0 +1,8 @@
+{"commitInfo":{"timestamp":1725137989496,"operation":"WRITE","operationParameters":{"mode":"ErrorIfExists","partitionBy":"[]"},"isolationLevel":"Serializable","isBlindAppend":true,"operationMetrics":{"numFiles":"6","numOutputRows":"5","numOutputBytes":"7800"},"engineInfo":"Apache-Spark/3.5.2 Delta-Lake/3.2.0","txnId":"17633aa0-b065-49d6-9893-022103f7364e"}}
+{"metaData":{"id":"73709a6c-bb75-4ac7-a78e-635400886d74","format":{"provider":"parquet","options":{}},"schemaString":"{\"type\":\"struct\",\"fields\":[{\"name\":\"employee_id\",\"type\":\"integer\",\"nullable\":true,\"metadata\":{}},{\"name\":\"fname\",\"type\":\"string\",\"nullable\":true,\"metadata\":{}},{\"name\":\"lname\",\"type\":\"string\",\"nullable\":true,\"metadata\":{}},{\"name\":\"age\",\"type\":\"integer\",\"nullable\":true,\"metadata\":{}},{\"name\":\"store_id\",\"type\":\"integer\",\"nullable\":true,\"metadata\":{}}]}","partitionColumns":[],"configuration":{},"createdTime":1725137987547}}
+{"protocol":{"minReaderVersion":1,"minWriterVersion":2}}
+{"add":{"path":"part-00002-3fed7f18-370f-4b16-b232-504d6194eb52-c000.snappy.parquet","partitionValues":{},"size":1437,"modificationTime":1725137989427,"dataChange":true,"stats":"{\"numRecords\":1,\"minValues\":{\"employee_id\":1,\"fname\":\"Jack\",\"lname\":\"Shephard\",\"age\":37,\"store_id\":1},\"maxValues\":{\"employee_id\":1,\"fname\":\"Jack\",\"lname\":\"Shephard\",\"age\":37,\"store_id\":1},\"nullCount\":{\"employee_id\":0,\"fname\":0,\"lname\":0,\"age\":0,\"store_id\":0}}"}}
+{"add":{"path":"part-00004-143c5da1-d5ab-4706-8e84-0d2a324c6894-c000.snappy.parquet","partitionValues":{},"size":1417,"modificationTime":1725137989428,"dataChange":true,"stats":"{\"numRecords\":1,\"minValues\":{\"employee_id\":2,\"fname\":\"John\",\"lname\":\"Locke\",\"age\":65,\"store_id\":1},\"maxValues\":{\"employee_id\":2,\"fname\":\"John\",\"lname\":\"Locke\",\"age\":65,\"store_id\":1},\"nullCount\":{\"employee_id\":0,\"fname\":0,\"lname\":0,\"age\":0,\"store_id\":0}}"}}
+{"add":{"path":"part-00006-64f07e25-c30e-4075-acc6-b3c69c4ce80b-c000.snappy.parquet","partitionValues":{},"size":1424,"modificationTime":1725137989428,"dataChange":true,"stats":"{\"numRecords\":1,\"minValues\":{\"employee_id\":3,\"fname\":\"Kate\",\"lname\":\"Austen\",\"age\":37,\"store_id\":2},\"maxValues\":{\"employee_id\":3,\"fname\":\"Kate\",\"lname\":\"Austen\",\"age\":37,\"store_id\":2},\"nullCount\":{\"employee_id\":0,\"fname\":0,\"lname\":0,\"age\":0,\"store_id\":0}}"}}
+{"add":{"path":"part-00008-89ccad8d-df73-4ad5-8850-82ef3884db60-c000.snappy.parquet","partitionValues":{},"size":1459,"modificationTime":1725137989427,"dataChange":true,"stats":"{\"numRecords\":1,\"minValues\":{\"employee_id\":4,\"fname\":\"Claire\",\"lname\":\"Littleton\",\"age\":27,\"store_id\":2},\"maxValues\":{\"employee_id\":4,\"fname\":\"Claire\",\"lname\":\"Littleton\",\"age\":27,\"store_id\":2},\"nullCount\":{\"employee_id\":0,\"fname\":0,\"lname\":0,\"age\":0,\"store_id\":0}}"}}
+{"add":{"path":"part-00010-812b3382-8c7f-4c4e-9bcd-09ce8664f6e0-c000.snappy.parquet","partitionValues":{},"size":1417,"modificationTime":1725137989428,"dataChange":true,"stats":"{\"numRecords\":1,\"minValues\":{\"employee_id\":5,\"fname\":\"Hugo\",\"lname\":\"Reyes\",\"age\":29,\"store_id\":100},\"maxValues\":{\"employee_id\":5,\"fname\":\"Hugo\",\"lname\":\"Reyes\",\"age\":29,\"store_id\":100},\"nullCount\":{\"employee_id\":0,\"fname\":0,\"lname\":0,\"age\":0,\"store_id\":0}}"}}

sqlframe-3.3.0/tests/fixtures/tpcds/tpcds1.sql

@@ -0,0 +1,23 @@
+WITH  customer_total_return  AS
+    (SELECT  sr_customer_sk  AS  ctr_customer_sk,
+                    sr_store_sk  AS  ctr_store_sk,
+                    sum(sr_return_amt)  AS  ctr_total_return
+      FROM  store_returns,
+                date_dim
+      WHERE  sr_returned_date_sk  =  d_date_sk
+          AND  d_year  =  2000
+      GROUP  BY  sr_customer_sk,
+                        sr_store_sk)
+SELECT  c_customer_id
+FROM  customer_total_return  ctr1,
+          store,
+          customer
+WHERE  ctr1.ctr_total_return  >
+        (SELECT  avg(ctr_total_return)*1.2
+          FROM  customer_total_return  ctr2
+          WHERE  ctr1.ctr_store_sk  =  ctr2.ctr_store_sk)
+    AND  s_store_sk  =  ctr1.ctr_store_sk
+    AND  s_state  =  'TN'
+    AND  ctr1.ctr_customer_sk  =  c_customer_sk
+ORDER  BY  c_customer_id
+LIMIT  100;

sqlframe-3.3.0/tests/fixtures/tpcds/tpcds10.sql

@@ -0,0 +1,65 @@
+SELECT  cd_gender,
+              cd_marital_status,
+              cd_education_status,
+              count(*)  cnt1,
+              cd_purchase_estimate,
+              count(*)  cnt2,
+              cd_credit_rating,
+              count(*)  cnt3,
+              cd_dep_count,
+              count(*)  cnt4,
+              cd_dep_employed_count,
+              count(*)  cnt5,
+              cd_dep_college_count,
+              count(*)  cnt6
+FROM  customer  c,
+          customer_address  ca,
+          customer_demographics
+WHERE  c.c_current_addr_sk  =  ca.ca_address_sk
+    AND  ca_county  IN  ('Rush  County',
+                                        'Toole  County',
+                                        'Jefferson  County',
+                                        'Dona  Ana  County',
+                                        'La  Porte  County')
+    AND  cd_demo_sk  =  c.c_current_cdemo_sk
+    AND  EXISTS
+        (SELECT  *
+          FROM  store_sales,
+                    date_dim
+          WHERE  c.c_customer_sk  =  ss_customer_sk
+              AND  ss_sold_date_sk  =  d_date_sk
+              AND  d_year  =  2002
+              AND  d_moy  BETWEEN  1  AND  1+3)
+    AND  (EXISTS
+                  (SELECT  *
+                    FROM  web_sales,
+                              date_dim
+                    WHERE  c.c_customer_sk  =  ws_bill_customer_sk
+                        AND  ws_sold_date_sk  =  d_date_sk
+                        AND  d_year  =  2002
+                        AND  d_moy  BETWEEN  1  AND  1+3)
+              OR  EXISTS
+                  (SELECT  *
+                    FROM  catalog_sales,
+                              date_dim
+                    WHERE  c.c_customer_sk  =  cs_ship_customer_sk
+                        AND  cs_sold_date_sk  =  d_date_sk
+                        AND  d_year  =  2002
+                        AND  d_moy  BETWEEN  1  AND  1+3))
+GROUP  BY  cd_gender,
+                  cd_marital_status,
+                  cd_education_status,
+                  cd_purchase_estimate,
+                  cd_credit_rating,
+                  cd_dep_count,
+                  cd_dep_employed_count,
+                  cd_dep_college_count
+ORDER  BY  cd_gender,
+                  cd_marital_status,
+                  cd_education_status,
+                  cd_purchase_estimate,
+                  cd_credit_rating,
+                  cd_dep_count,
+                  cd_dep_employed_count,
+                  cd_dep_college_count
+LIMIT  100;