[DOP-21445] add orc, parquest tests

Author: maxim-lixakov

syncmaster/dto/transfers.py

@@ -4,7 +4,7 @@
 from dataclasses import dataclass
 from typing import ClassVar
 
-from onetl.file.format import CSV, JSON, XML, Excel, JSONLine
+from onetl.file.format import CSV, JSON, ORC, XML, Excel, JSONLine, Parquet
 
 
 @dataclass
@@ -30,6 +30,8 @@ class FileTransferDTO(TransferDTO):
         "json": JSON,
         "excel": Excel,
         "xml": XML,
+        "orc": ORC,
+        "parquet": Parquet,
     }
 
     def __post_init__(self):

syncmaster/worker/spark.py

@@ -39,12 +39,17 @@ def get_worker_spark_session(
 def get_packages(db_type: str) -> list[str]:
     import pyspark
     from onetl.connection import MSSQL, Clickhouse, MySQL, Oracle, Postgres, SparkS3
-    from onetl.file.format import XML, Excel
+    from onetl.file.format import ORC, XML, Excel, Parquet
 
     spark_version = pyspark.__version__
     # see supported versions from https://mvnrepository.com/artifact/com.crealytics/spark-excel
-    file_formats_spark_packages: list[str] = XML.get_packages(spark_version=spark_version) + Excel.get_packages(
-        spark_version=spark_version,
+    file_formats_spark_packages: list[str] = (
+        XML.get_packages(spark_version=spark_version)
+        + Excel.get_packages(
+            spark_version=spark_version,
+        )
+        + ORC.get_packages(spark_version=spark_version)
+        + Parquet.get_packages(spark_version=spark_version)
     )
 
     if db_type == "postgres":

tests/test_integration/test_run_transfer/conftest.py

@@ -11,7 +11,7 @@
 from onetl.connection import MSSQL, Clickhouse, Hive, MySQL, Oracle, Postgres, SparkS3
 from onetl.connection.file_connection.s3 import S3
 from onetl.db import DBWriter
-from onetl.file.format import CSV, JSON, XML, Excel, JSONLine
+from onetl.file.format import CSV, JSON, ORC, XML, Excel, JSONLine, Parquet
 from pyspark.sql import DataFrame, SparkSession
 from pyspark.sql.types import (
     DateType,
@@ -116,8 +116,13 @@ def spark(settings: Settings, request: FixtureRequest) -> SparkSession:
     if "hdfs" in markers or "s3" in markers:
         spark_version = pyspark.__version__
         # see supported versions from https://mvnrepository.com/artifact/com.crealytics/spark-excel
-        file_formats_spark_packages: list[str] = XML.get_packages(spark_version=spark_version) + Excel.get_packages(
-            spark_version=spark_version,
+        file_formats_spark_packages: list[str] = (
+            XML.get_packages(spark_version=spark_version)
+            + Excel.get_packages(
+                spark_version=spark_version,
+            )
+            + ORC.get_packages(spark_version=spark_version)
+            + Parquet.get_packages(spark_version=spark_version)
         )
         maven_packages.extend(file_formats_spark_packages)
 
@@ -808,7 +813,9 @@ def fill_with_data(df: DataFrame):
         pass
 
 
-@pytest.fixture(params=[("csv", {}), ("jsonline", {}), ("json", {}), ("excel", {}), ("xml", {})])
+@pytest.fixture(
+    params=[("csv", {}), ("jsonline", {}), ("json", {}), ("excel", {}), ("xml", {}), ("orc", {}), ("parquet", {})],
+)
 def source_file_format(request: FixtureRequest):
     name, params = request.param
     if name == "csv":
@@ -845,10 +852,20 @@ def source_file_format(request: FixtureRequest):
             **params,
         )
 
+    if name == "orc":
+        return "orc", ORC(
+            **params,
+        )
+
+    if name == "parquet":
+        return "parquet", Parquet(
+            **params,
+        )
+
     raise ValueError(f"Unsupported file format: {name}")
 
 
-@pytest.fixture(params=[("csv", {}), ("jsonline", {}), ("excel", {}), ("xml", {})])
+@pytest.fixture(params=[("csv", {}), ("jsonline", {}), ("excel", {}), ("xml", {}), ("orc", {}), ("parquet", {})])
 def target_file_format(request: FixtureRequest):
     name, params = request.param
     if name == "csv":
@@ -879,6 +896,16 @@ def target_file_format(request: FixtureRequest):
             **params,
         )
 
+    if name == "orc":
+        return "orc", ORC(
+            **params,
+        )
+
+    if name == "parquet":
+        return "parquet", Parquet(
+            **params,
+        )
+
     raise ValueError(f"Unsupported file format: {name}")
 
 

tests/test_integration/test_run_transfer/test_hdfs.py

@@ -133,6 +133,16 @@ async def postgres_to_hdfs(
             "without_compression",
             id="xml",
         ),
+        pytest.param(
+            ("orc", {}),
+            "without_compression",
+            id="orc",
+        ),
+        pytest.param(
+            ("parquet", {}),
+            "without_compression",
+            id="parquet",
+        ),
     ],
     indirect=["source_file_format", "file_format_flavor"],
 )
@@ -212,6 +222,16 @@ async def test_run_transfer_hdfs_to_postgres(
             "without_compression",
             id="xml",
         ),
+        pytest.param(
+            ("orc", {}),
+            "without_compression",
+            id="orc",
+        ),
+        pytest.param(
+            ("parquet", {}),
+            "without_compression",
+            id="parquet",
+        ),
     ],
     indirect=["target_file_format", "file_format_flavor"],
 )

tests/test_integration/test_run_transfer/test_s3.py

@@ -133,6 +133,16 @@ async def postgres_to_s3(
             "without_compression",
             id="xml",
         ),
+        pytest.param(
+            ("orc", {}),
+            "without_compression",
+            id="orc",
+        ),
+        pytest.param(
+            ("parquet", {}),
+            "without_compression",
+            id="parquet",
+        ),
     ],
     indirect=["source_file_format", "file_format_flavor"],
 )
@@ -193,11 +203,6 @@ async def test_run_transfer_s3_to_postgres(
 @pytest.mark.parametrize(
     "target_file_format, file_format_flavor",
     [
-        pytest.param(
-            ("xml", {}),
-            "without_compression",
-            id="xml",
-        ),
         pytest.param(
             ("csv", {}),
             "with_header",
@@ -213,6 +218,21 @@ async def test_run_transfer_s3_to_postgres(
             "with_header",
             id="excel",
         ),
+        pytest.param(
+            ("xml", {}),
+            "without_compression",
+            id="xml",
+        ),
+        pytest.param(
+            ("orc", {}),
+            "without_compression",
+            id="orc",
+        ),
+        pytest.param(
+            ("parquet", {}),
+            "without_compression",
+            id="parquet",
+        ),
     ],
     indirect=["target_file_format", "file_format_flavor"],
 )