1204: improve error message if dataset files are not found

cdisc_rules_engine/utilities/utils.py

@@ -442,3 +442,12 @@ def replace_nan_values_in_df(df, columns):
             if mask.any():
                 df.loc[mask, col] = None
     return df
+
+
+def validate_dataset_files_exist(dataset_path: tuple[str], logger, ctx):
+    non_existing_files: list[str] = [
+        path for path in dataset_path if not os.path.exists(path)
+    ]
+    if non_existing_files:
+        logger.error(f'Files {", ".join(non_existing_files)} are not found')
+        ctx.exit(2)

core.py

@@ -26,6 +26,7 @@
 from cdisc_rules_engine.utilities.utils import (
     generate_report_filename,
     get_rules_cache_key,
+    validate_dataset_files_exist,
 )
 from cdisc_rules_engine.enums.dataformat_types import DataFormatTypes
 from scripts.list_dataset_metadata_handler import list_dataset_metadata_handler
@@ -393,6 +394,8 @@ def validate(
     logger = logging.getLogger("validator")
     load_dotenv()
 
+    validate_dataset_files_exist(dataset_path, logger, ctx)
+
     if raw_report is True:
         if not (len(output_format) == 1 and output_format[0] == ReportTypes.JSON.value):
             logger.error(

tests/QARegressionTests/test_Issues/test_CoreIssue1204.py

@@ -0,0 +1,40 @@
+import subprocess
+import pytest
+from conftest import get_python_executable
+
+
+@pytest.mark.regression
+def test_non_existing_dataset_shows_helpful_error():
+    """Test that the engine displays a helpful error message if dataset files are not found"""
+    command = [
+        get_python_executable(),
+        "-m",
+        "core",
+        "validate",
+        "-s",
+        "sdtmig",
+        "-v",
+        "3.4",
+        "-dp",
+        "ds.json",
+        "-dp",
+        "ds2.json",
+    ]
+
+    process = subprocess.Popen(command, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
+    stdout, stderr = process.communicate()
+
+    stderr_text = stderr.decode()
+    stdout_text = stdout.decode()
+
+    assert process.returncode == 2, "Expected non-zero exit code"
+    assert (
+        "FileNotFoundError" not in stderr_text
+    ), "Should not show FileNotFoundError crash"
+    assert (
+        "Failed to execute script" not in stderr_text
+    ), "Should not show script execution failure"
+    assert "Files ds.json, ds2.json are not found" in stderr_text, (
+        f"Expected helpful error message about non-existing dataset files. "
+        f"stderr: {stderr_text}, stdout: {stdout_text}"
+    )