[DOP-21445] Add XML integration 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, Excel, JSONLine
+from onetl.file.format import CSV, JSON, XML, Excel, JSONLine
 
 
 @dataclass
@@ -20,7 +20,7 @@ class DBTransferDTO(TransferDTO):
 @dataclass
 class FileTransferDTO(TransferDTO):
     directory_path: str
-    file_format: CSV | JSONLine | JSON | Excel
+    file_format: CSV | JSONLine | JSON | Excel | XML
     options: dict
     df_schema: dict | None = None
 
@@ -29,6 +29,7 @@ class FileTransferDTO(TransferDTO):
         "jsonline": JSONLine,
         "json": JSON,
         "excel": Excel,
+        "xml": XML,
     }
 
     def __post_init__(self):

syncmaster/worker/spark.py

@@ -37,7 +37,12 @@ def get_worker_spark_session(
 
 def get_packages(db_type: str) -> list[str]:
     from onetl.connection import MSSQL, Clickhouse, MySQL, Oracle, Postgres, SparkS3
-    from onetl.file.format import Excel
+    from onetl.file.format import XML, Excel
+
+    # see supported versions from https://mvnrepository.com/artifact/com.crealytics/spark-excel
+    file_formats_spark_packages: list[str] = XML.get_packages(spark_version="3.5.1") + Excel.get_packages(
+        spark_version="3.5.1",
+    )
 
     if db_type == "postgres":
         return Postgres.get_packages()
@@ -55,10 +60,11 @@ def get_packages(db_type: str) -> list[str]:
 
         spark_version = pyspark.__version__
         # see supported versions from https://mvnrepository.com/artifact/com.crealytics/spark-excel
-        return SparkS3.get_packages(spark_version=spark_version) + Excel.get_packages(spark_version="3.5.1")
+
+        return SparkS3.get_packages(spark_version=spark_version) + file_formats_spark_packages
     if db_type == "hdfs":
         # see supported versions from https://mvnrepository.com/artifact/com.crealytics/spark-excel
-        return Excel.get_packages(spark_version="3.5.1")
+        return file_formats_spark_packages
 
     # If the database type does not require downloading .jar packages
     return []

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, Excel, JSONLine
+from onetl.file.format import CSV, JSON, XML, Excel, JSONLine
 from pyspark.sql import DataFrame, SparkSession
 from pyspark.sql.types import (
     DateType,
@@ -115,7 +115,10 @@ def spark(settings: Settings, request: FixtureRequest) -> SparkSession:
 
     if "hdfs" in markers or "s3" in markers:
         # see supported versions from https://mvnrepository.com/artifact/com.crealytics/spark-excel
-        maven_packages.extend(Excel.get_packages(spark_version="3.5.1"))
+        file_formats_spark_packages: list[str] = XML.get_packages(spark_version="3.5.1") + Excel.get_packages(
+            spark_version="3.5.1",
+        )
+        maven_packages.extend(file_formats_spark_packages)
 
     if maven_packages:
         spark = spark.config("spark.jars.packages", ",".join(maven_packages))
@@ -804,7 +807,7 @@ def fill_with_data(df: DataFrame):
         pass
 
 
-@pytest.fixture(params=[("csv", {}), ("jsonline", {}), ("json", {}), ("excel", {})])
+@pytest.fixture(params=[("csv", {}), ("jsonline", {}), ("json", {}), ("excel", {}), ("xml", {})])
 def source_file_format(request: FixtureRequest):
     name, params = request.param
     if name == "csv":
@@ -835,10 +838,16 @@ def source_file_format(request: FixtureRequest):
             **params,
         )
 
+    if name == "xml":
+        return "xml", XML(
+            row_tag="item",
+            **params,
+        )
+
     raise ValueError(f"Unsupported file format: {name}")
 
 
-@pytest.fixture(params=[("csv", {}), ("jsonline", {}), ("excel", {})])
+@pytest.fixture(params=[("csv", {}), ("jsonline", {}), ("excel", {}), ("xml", {})])
 def target_file_format(request: FixtureRequest):
     name, params = request.param
     if name == "csv":
@@ -863,6 +872,12 @@ def target_file_format(request: FixtureRequest):
             **params,
         )
 
+    if name == "xml":
+        return "xml", XML(
+            row_tag="item",
+            **params,
+        )
+
     raise ValueError(f"Unsupported file format: {name}")
 
 

tests/test_integration/test_run_transfer/test_hdfs.py

@@ -128,6 +128,11 @@ async def postgres_to_hdfs(
             "with_header",
             id="excel",
         ),
+        pytest.param(
+            ("xml", {}),
+            "without_compression",
+            id="xml",
+        ),
     ],
     indirect=["source_file_format", "file_format_flavor"],
 )
@@ -202,6 +207,11 @@ async def test_run_transfer_hdfs_to_postgres(
             "with_header",
             id="excel",
         ),
+        pytest.param(
+            ("xml", {}),
+            "without_compression",
+            id="xml",
+        ),
     ],
     indirect=["target_file_format", "file_format_flavor"],
 )

tests/test_integration/test_run_transfer/test_s3.py

@@ -128,6 +128,11 @@ async def postgres_to_s3(
             "with_header",
             id="excel",
         ),
+        pytest.param(
+            ("xml", {}),
+            "without_compression",
+            id="xml",
+        ),
     ],
     indirect=["source_file_format", "file_format_flavor"],
 )
@@ -178,7 +183,6 @@ async def test_run_transfer_s3_to_postgres(
     if file_format == "excel":
         df = df.withColumn("REGISTERED_AT", date_trunc("second", col("REGISTERED_AT")))
         init_df = init_df.withColumn("REGISTERED_AT", date_trunc("second", col("REGISTERED_AT")))
-
     for field in init_df.schema:
         df = df.withColumn(field.name, df[field.name].cast(field.dataType))
 
@@ -203,6 +207,11 @@ async def test_run_transfer_s3_to_postgres(
             "with_header",
             id="excel",
         ),
+        pytest.param(
+            ("xml", {}),
+            "without_compression",
+            id="xml",
+        ),
     ],
     indirect=["target_file_format", "file_format_flavor"],
 )