[DOP-9653] Update Excel package version to 0.20.1

.github/workflows/data/local-fs/matrix.yml

@@ -16,12 +16,6 @@ min_excel: &min_excel
   java-version: 8
   os: ubuntu-latest
 
-max_excel: &max_excel
-  spark-version: 3.4.1
-  python-version: '3.11'
-  java-version: 20
-  os: ubuntu-latest
-
 max: &max
   spark-version: 3.5.0
   python-version: '3.11'
@@ -36,13 +30,11 @@ latest: &latest
 
 matrix:
   small:
-  - <<: *max_excel
   - <<: *max
   full:
   - <<: *min
   - <<: *min_avro
   - <<: *min_excel
-  - <<: *max_excel
   - <<: *max
   nightly:
   - <<: *min

.github/workflows/data/local-fs/tracked.txt

@@ -1 +1,2 @@
 **/*local_fs*
+**/*local-fs*

docs/changelog/next_release/161.feature.rst

@@ -0,0 +1 @@
+Update ``Excel`` package version to 0.20.2.

onetl/file/format/excel.py

@@ -100,7 +100,7 @@ class Excel(ReadWriteFileFormat):
         from pyspark.sql import SparkSession
 
         # Create Spark session with Excel package loaded
-        maven_packages = Excel.get_packages(spark_version="3.4.1")
+        maven_packages = Excel.get_packages(spark_version="3.5.0")
         spark = (
             SparkSession.builder.appName("spark-app-name")
             .config("spark.jars.packages", ",".join(maven_packages))
@@ -150,7 +150,7 @@ def get_packages(
             If ``None``, ``spark_version`` is used to determine Scala version.
 
         version: str, optional
-            Package version in format ``major.minor.patch``. Default is ``0.19.0``.
+            Package version in format ``major.minor.patch``. Default is ``0.20.2``.
 
             .. warning::
 
@@ -168,12 +168,12 @@ def get_packages(
 
             from onetl.file.format import Excel
 
-            Excel.get_packages(spark_version="3.4.1")
-            Excel.get_packages(spark_version="3.4.1", scala_version="2.13")
+            Excel.get_packages(spark_version="3.5.0")
+            Excel.get_packages(spark_version="3.5.0", scala_version="2.13")
             Excel.get_packages(
-                spark_version="3.4.1",
+                spark_version="3.5.0",
                 scala_version="2.13",
-                package_version="0.19.0",
+                package_version="0.20.2",
             )
 
         """
@@ -187,7 +187,7 @@ def get_packages(
                 raise ValueError(f"Package version should be at least 0.15, got {package_version}")
             log.warning("Passed custom package version %r, it is not guaranteed to be supported", package_version)
         else:
-            version = Version.parse("0.19.0")
+            version = Version.parse("0.20.2")
 
         spark_ver = Version.parse(spark_version)
         if spark_ver < (3, 2):

tests/fixtures/spark.py

@@ -77,10 +77,9 @@ def maven_packages():
         # There is no MongoDB connector for Spark less than 3.2
         packages.extend(MongoDB.get_packages(spark_version=pyspark_version))
 
-        if pyspark_version < (3, 5):
-            # There is no Excel files support for Spark less than 3.2
-            # And there is still no package released for 3.5.0 https://github.com/crealytics/spark-excel/issues/787
-            packages.extend(Excel.get_packages(spark_version=pyspark_version))
+        # There is no Excel files support for Spark less than 3.2
+        # And there is still no package released for 3.5.0 https://github.com/crealytics/spark-excel/issues/787
+        packages.extend(Excel.get_packages(spark_version=pyspark_version))
 
     return packages
 

tests/tests_integration/test_file_format_integration/test_excel_integration.py

@@ -33,8 +33,6 @@ def test_excel_reader_with_infer_schema(
     spark_version = get_spark_version(spark)
     if spark_version < (3, 2):
         pytest.skip("Excel files are supported on Spark 3.2+ only")
-    if spark_version >= (3, 5):
-        pytest.skip("Excel files are not supported on Spark 3.5+ yet")
 
     file_df_connection, source_path, _ = local_fs_file_df_connection_with_path_and_files
     df = file_df_dataframe
@@ -83,8 +81,6 @@ def test_excel_reader_with_options(
     spark_version = get_spark_version(spark)
     if spark_version < (3, 2):
         pytest.skip("Excel files are supported on Spark 3.2+ only")
-    if spark_version >= (3, 5):
-        pytest.skip("Excel files are not supported on Spark 3.5+ yet")
 
     local_fs, source_path, _ = local_fs_file_df_connection_with_path_and_files
     df = file_df_dataframe
@@ -121,8 +117,6 @@ def test_excel_writer(
     spark_version = get_spark_version(spark)
     if spark_version < (3, 2):
         pytest.skip("Excel files are supported on Spark 3.2+ only")
-    if spark_version >= (3, 5):
-        pytest.skip("Excel files are not supported on Spark 3.5+ yet")
 
     file_df_connection, source_path = local_fs_file_df_connection_with_path
     df = file_df_dataframe

tests/tests_unit/test_file/test_format_unit/test_excel_unit.py

@@ -32,16 +32,16 @@ def test_excel_get_packages_package_version_not_supported():
     "spark_version, scala_version, package_version, packages",
     [
         # Detect Scala version by Spark version
-        ("3.2.4", None, None, ["com.crealytics:spark-excel_2.12:3.2.4_0.19.0"]),
-        ("3.4.1", None, None, ["com.crealytics:spark-excel_2.12:3.4.1_0.19.0"]),
+        ("3.2.4", None, None, ["com.crealytics:spark-excel_2.12:3.2.4_0.20.2"]),
+        ("3.5.0", None, None, ["com.crealytics:spark-excel_2.12:3.5.0_0.20.2"]),
         # Override Scala version
-        ("3.2.4", "2.12", None, ["com.crealytics:spark-excel_2.12:3.2.4_0.19.0"]),
-        ("3.2.4", "2.13", None, ["com.crealytics:spark-excel_2.13:3.2.4_0.19.0"]),
-        ("3.4.1", "2.12", None, ["com.crealytics:spark-excel_2.12:3.4.1_0.19.0"]),
-        ("3.4.1", "2.13", None, ["com.crealytics:spark-excel_2.13:3.4.1_0.19.0"]),
+        ("3.2.4", "2.12", None, ["com.crealytics:spark-excel_2.12:3.2.4_0.20.2"]),
+        ("3.2.4", "2.13", None, ["com.crealytics:spark-excel_2.13:3.2.4_0.20.2"]),
+        ("3.5.0", "2.12", None, ["com.crealytics:spark-excel_2.12:3.5.0_0.20.2"]),
+        ("3.5.0", "2.13", None, ["com.crealytics:spark-excel_2.13:3.5.0_0.20.2"]),
         # Override package version
         ("3.2.0", None, "0.16.0", ["com.crealytics:spark-excel_2.12:3.2.0_0.16.0"]),
-        ("3.4.1", None, "0.18.0", ["com.crealytics:spark-excel_2.12:3.4.1_0.18.0"]),
+        ("3.5.0", None, "0.18.0", ["com.crealytics:spark-excel_2.12:3.5.0_0.18.0"]),
     ],
 )
 def test_excel_get_packages(caplog, spark_version, scala_version, package_version, packages):