feat: add spark-submit output parser

tests/unit/test_log_parser.py

@@ -0,0 +1,32 @@
+# coding=utf-8
+import pytest
+
+from spark_executor.core.log_parser import parse_spark_submit_output
+
+
+def test_parses_submitted_application_line():
+    stderr = "Warning: ignoring...\nSubmitted application application_17400000001\n"
+    app_id, url = parse_spark_submit_output(stderr)
+    assert app_id == "application_17400000001"
+    assert url is None
+
+
+def test_parses_tracking_url_line():
+    stderr = "tracking URL: http://rm:8088/proxy/application_17400000002/\n"
+    app_id, url = parse_spark_submit_output(stderr)
+    assert app_id == "application_17400000002"
+    assert url == "http://rm:8088/proxy/application_17400000002/"
+
+
+def test_prefers_submitted_application_line_over_tracking_url():
+    stderr = (
+        "tracking URL: http://rm:8088/proxy/application_9999/\n"
+        "Submitted application application_1234\n"
+    )
+    app_id, _ = parse_spark_submit_output(stderr)
+    assert app_id == "application_1234"
+
+
+def test_raises_when_no_application_id_found():
+    with pytest.raises(ValueError, match="application_id"):
+        parse_spark_submit_output("some unrelated output\n")