changes in validation script to change engine location (#22)

* standards

* rules

* remove sheet .xpt

* rules and test data sorted

* env

* remove xlsx results

* script

* use_case, usdm, results.csv

* results processed

* usdm trim

* usdm, multiple sub folders

* last tables

* update

* moved stray adam file

* update datasets and variables csv and docs

* remove .xpt extension

* allow to override engine location in validation script

* modified five rules to test by workflow

* validation script change to support creating two reports

* rollback metadata files names

* fixed cycle in validation script. rolled back test data

* replace committed/generated with expected/actual

* got->actual

* better details when results.csv is missing

* change csv conversion to an engine output format

* python instead of python3

---------

Co-authored-by: Samuel Johnson <sfjohnson24@gmail.com>
Co-authored-by: Samuel Johnson <96841389+SFJohnson24@users.noreply.github.com>
Co-authored-by: gerrycampion <85252124+gerrycampion@users.noreply.github.com>
Co-authored-by: Gerry Campion <gcampion@cdisc.org>

Author: 3 people

.github/scripts/convert_results.py

@@ -1,14 +1,15 @@
 """
-diff_results.py — compares a committed results.csv against a freshly generated one.
+diff_results.py — compares an actual results.csv against an expected one.
 
 Usage:
-    python .github/scripts/diff_results.py <committed.csv> <generated.csv> <case_label>
+    python .github/scripts/diff_results.py <expected.csv> <actual.csv> <case_label>
 
 Exit codes:
     0  — results match
     1  — results differ (failure)
     2  — error
 """
+
 import csv
 import sys
 from itertools import zip_longest
@@ -22,40 +23,42 @@ def load(path: str) -> list[tuple]:
     return sorted(rows)
 
 
-def diff(committed_path: str, generated_path: str) -> list[str]:
+def diff(expected_path: str, actual_path: str) -> list[str]:
     diffs = []
-    c_rows = load(committed_path)
-    g_rows = load(generated_path)
+    c_rows = load(expected_path)
+    g_rows = load(actual_path)
 
     if len(c_rows) != len(g_rows):
         diffs.append(
-            f"Row count changed: {len(c_rows)} committed -> {len(g_rows)} generated"
+            f"Row count changed: {len(c_rows)} expected -> {len(g_rows)} actual"
         )
 
     _ABSENT = object()
-    for i, (c_row, g_row) in enumerate(zip_longest(c_rows, g_rows, fillvalue=_ABSENT), start=1):
+    for i, (c_row, g_row) in enumerate(
+        zip_longest(c_rows, g_rows, fillvalue=_ABSENT), start=1
+    ):
         if c_row is _ABSENT:
-            diffs.append(f"  Row {i}: present in generated only -> {g_row}")
+            diffs.append(f"  Row {i}: present in actual only -> {g_row}")
         elif g_row is _ABSENT:
-            diffs.append(f"  Row {i}: present in committed only -> {c_row}")
+            diffs.append(f"  Row {i}: present in expected only -> {c_row}")
         elif c_row != g_row:
-            diffs.append(f"  Row {i}: committed={c_row} -> generated={g_row}")
+            diffs.append(f"  Row {i}: expected={c_row} -> actual={g_row}")
 
     return diffs
 
 
 def main():
     if len(sys.argv) != 4:
         print(
-            f"Usage: {sys.argv[0]} <committed.csv> <generated.csv> <case_label>",
+            f"Usage: {sys.argv[0]} <expected.csv> <actual.csv> <case_label>",
             file=sys.stderr,
         )
         sys.exit(2)
 
-    committed_path, generated_path, case_label = sys.argv[1], sys.argv[2], sys.argv[3]
+    expected_path, actual_path, case_label = sys.argv[1], sys.argv[2], sys.argv[3]
 
     try:
-        diffs = diff(committed_path, generated_path)
+        diffs = diff(expected_path, actual_path)
     except Exception as e:
         print(f"ERROR comparing results for {case_label}: {e}", file=sys.stderr)
         sys.exit(2)