Add dev container

Author: lauris-tw

.devcontainer/devcontainer.json

@@ -0,0 +1,38 @@
+{
+  "name": "Transformation - Python",
+  "image": "mcr.microsoft.com/devcontainers/base:1-debian",
+  "features": {
+    "ghcr.io/devcontainers/features/java:1": {
+      "version": "17",
+      "jdkDistro": "open",
+      "gradleVersion": "latest",
+      "mavenVersion": "latest",
+      "antVersion": "latest",
+      "groovyVersion": "latest"
+    },
+    "ghcr.io/devcontainers/features/python:1": {
+      "version": "3.13"
+    },
+    "ghcr.io/devcontainers-extra/features/poetry:2": {
+      "version": "latest"
+    }
+  },
+  "containerEnv": {
+    "PYTHONUNBUFFERED": "1"
+  },
+  "postCreateCommand": "poetry install",
+  "customizations": {
+    "vscode": {
+      "extensions": [
+        "ms-python.python",
+        "ms-python.vscode-pylance",
+        "charliermarsh.ruff",
+        "ms-toolsai.jupyter"
+      ],
+      "settings": {
+        "python.testing.pytestEnabled": true,
+        "python.testing.pytestArgs": ["tests"]
+      }
+    }
+  }
+}

tests/integration/test_validate_spark_environment.py

@@ -34,13 +34,15 @@ def __extract_version_line(java_version_output: str) -> str:
         (line for line in java_version_output.splitlines() if "version" in line), None
     )
     if not version_line:
-        pytest.fail("Couldn't find version information in `java -version` output.")
+        pytest.fail(
+            "Couldn't find version information in `java -version` output.")
     return version_line
 
 
 # pylint: disable=R1710
 def __parse_major_version(version_line: str) -> int:
-    version_regex = re.compile(r'version "(?P<major>\d+)\.(?P<minor>\d+)\.\w+"')
+    version_regex = re.compile(
+        r'version "(?P<major>\d+)\.(?P<minor>\d+)\.\w+"')
     match = version_regex.search(version_line)
     if match is not None:
         major_version = int(match.group("major"))
@@ -49,4 +51,11 @@ def __parse_major_version(version_line: str) -> int:
             # https://softwareengineering.stackexchange.com/questions/175075/why-is-java-version-1-x-referred-to-as-java-x
             major_version = int(match.group("minor"))
         return major_version
+
+    # Opensource versions follow an alternative system
+    alternative_version_regex = re.compile(r'version "(?P<major>\d+)"')
+    match = alternative_version_regex.search(version_line)
+    if match is not None:
+        major_version = int(match.group("major"))
+        return major_version
     pytest.fail(f"Couldn't parse Java version from {version_line}.")