Update Published results.csv baselines (engine@main)

.github/scripts/filter_core_ids_by_standard.py

@@ -0,0 +1,102 @@
+#!/usr/bin/env python3
+"""Filter Published CORE rule IDs by Authorities.Standards.Name."""
+
+from __future__ import annotations
+
+import argparse
+import sys
+from pathlib import Path
+
+import yaml
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(
+        description="Return space-separated CORE IDs for Published rules matching standards."
+    )
+    parser.add_argument(
+        "--rules-root",
+        required=True,
+        help="Repository root containing Published/",
+    )
+    parser.add_argument(
+        "--standards",
+        nargs="+",
+        required=True,
+        help="Standards to match from Authorities[].Standards[].Name",
+    )
+    parser.add_argument(
+        "--core-ids",
+        default="",
+        help="Optional space-separated CORE IDs to intersect with the standard filter.",
+    )
+    return parser.parse_args()
+
+
+def iter_published_rule_files(rules_root: Path) -> list[Path]:
+    published_dir = rules_root / "Published"
+    files: list[Path] = []
+    for pattern in ("**/rule.yml", "**/rule.yaml"):
+        files.extend(published_dir.glob(pattern))
+    return sorted(set(files))
+
+
+def rule_matches_standard(rule: dict, target_standards: set[str]) -> bool:
+    for authority in rule.get("Authorities") or []:
+        if not isinstance(authority, dict):
+            continue
+        for standard in authority.get("Standards") or []:
+            if not isinstance(standard, dict):
+                continue
+            standard_name = str(standard.get("Name") or "").strip().upper()
+            if standard_name in target_standards:
+                return True
+    return False
+
+
+def collect_filtered_core_ids(rules_root: Path, standards: list[str]) -> list[str]:
+    target_standards = {name.strip().upper() for name in standards if name.strip()}
+    core_ids: list[str] = []
+
+    for rule_file in iter_published_rule_files(rules_root):
+        with rule_file.open("r", encoding="utf-8") as handle:
+            rule = yaml.safe_load(handle) or {}
+        if not isinstance(rule, dict):
+            continue
+        if not rule_matches_standard(rule, target_standards):
+            continue
+
+        core = rule.get("Core") or {}
+        if not isinstance(core, dict):
+            continue
+        core_id = str(core.get("Id") or "").strip()
+        if core_id:
+            core_ids.append(core_id)
+    return core_ids
+
+
+def intersect_with_requested(core_ids: list[str], requested_core_ids: str) -> list[str]:
+    requested = requested_core_ids.split()
+    if not requested:
+        return core_ids
+
+    allowed = set(core_ids)
+    return [core_id for core_id in requested if core_id in allowed]
+
+
+def main() -> int:
+    args = parse_args()
+    rules_root = Path(args.rules_root)
+    if not rules_root.is_dir():
+        print(f"rules-root does not exist: {rules_root}", file=sys.stderr)
+        return 1
+
+    filtered_core_ids = collect_filtered_core_ids(rules_root, args.standards)
+    output_core_ids = intersect_with_requested(filtered_core_ids, args.core_ids)
+    print(" ".join(filtered_core_ids))
+    print(" ".join(output_core_ids))
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())

.github/workflows/update-published-results.yml

@@ -79,20 +79,38 @@ jobs:
         run: venv/bin/pip install tabulate jmespath pyyaml ruamel.yaml
 
       # -----------------------------------------------------------------------
-      # 4. Run the engine for every Published rule, writing actual results.csv
-      #    directly into each case's results/ directory (overwriting the old baseline)
+      # 4. Run the engine for Published rules filtered by Authorities.Standards.Name,
+      #    writing actual results.csv directly into each case's results/ directory
+      #    (overwriting the old baseline)
       # -----------------------------------------------------------------------
       - name: Run engine and write results
         id: run_engine
         continue-on-error: true
         run: |
           chmod +x .github/scripts/run_validation.sh
+          FILTER_STANDARDS=("USDM" "TIG")
+          mapfile -t FILTER_RESULT < <(venv/bin/python .github/scripts/filter_core_ids_by_standard.py \
+            --rules-root "$(pwd)" \
+            --standards "${FILTER_STANDARDS[@]}" \
+            --core-ids "${{ inputs.core_ids }}")
+          FILTERED_CORE_IDS="${FILTER_RESULT[0]}"
+          CORE_IDS_TO_RUN="${FILTER_RESULT[1]}"
+
+          if [ -z "$FILTERED_CORE_IDS" ]; then
+            echo "No Published rules found for standards: ${FILTER_STANDARDS[*]}"
+            exit 0
+          fi
 
-          CORE_IDS_ARG=""
-          if [ -n "${{ inputs.core_ids }}" ]; then
-            CORE_IDS_ARG="--core-ids ${{ inputs.core_ids }}"
+          if [ -z "$CORE_IDS_TO_RUN" ]; then
+            echo "No requested core_ids matched Published rules for standards: ${FILTER_STANDARDS[*]}"
+            exit 0
           fi
 
+          echo "Running validation for standards: ${FILTER_STANDARDS[*]}"
+          echo "Rule count: $(echo "$CORE_IDS_TO_RUN" | wc -w | tr -d ' ')"
+
+          CORE_IDS_ARG="--core-ids $CORE_IDS_TO_RUN"
+
           ENGINE_DIR_OVERRIDE="$(pwd)/engine" \
           venv/bin/python engine/scripts/validate_published_rules.py \
             --rules-root "$(pwd)" \

Published/CORE-000007/negative/01/results/results.csv

@@ -1,7 +1,5 @@
 Dataset,Record,Variable,Value
 DM,3,DTHDTC,2018-06-10
 DM,3,DTHFL,
-DM,3,USUBJID,015246-099-0000-00002
 DM,4,DTHDTC,2018-09-04
 DM,4,DTHFL,N
-DM,4,USUBJID,015246-099-0000-00003

Published/CORE-000007/negative/02/results/results.csv

@@ -1,3 +1,3 @@
 Dataset,Record,Variable,Value
-DM,4,DTHDTC,2018-12-11
-DM,4,DTHFL,
+DM,3,DTHDTC,2018-12-11
+DM,3,DTHFL,

Published/CORE-000013/negative/01/results/results.csv

@@ -1,14 +1,2 @@
 Dataset,Record,Variable,Value
-AE,1,AESTAT,NOT DONE
-AE,2,AESTAT,NOT DONE
-AE,3,AESTAT,NOT DONE
-AE,4,AESTAT,NOT DONE
-AE,5,AESTAT,
-AE,6,AESTAT,
-AE,7,AESTAT,NOT DONE
-AE,8,AESTAT,
-AE,9,AESTAT,
-AE,10,AESTAT,
-AE,11,AESTAT,NOT DONE
-AE,12,AESTAT,
-AE,13,AESTAT,
+AE,,AESTAT,NOT DONE

Published/CORE-000013/negative/02/results/results.csv

@@ -1,14 +1,2 @@
 Dataset,Record,Variable,Value
-AE,1,AESTAT,
-AE,2,AESTAT,
-AE,3,AESTAT,
-AE,4,AESTAT,
-AE,5,AESTAT,
-AE,6,AESTAT,
-AE,7,AESTAT,NOT DONE
-AE,8,AESTAT,
-AE,9,AESTAT,
-AE,10,AESTAT,
-AE,11,AESTAT,
-AE,12,AESTAT,
-AE,13,AESTAT,
+AE,,AESTAT,

Published/CORE-000014/negative/01/results/results.csv

@@ -46,8 +46,10 @@ EC,1,ECPRESP,
 EC,1,ECSTAT,Not in dataset
 EC,2,ECOCCUR,N
 EC,2,ECPRESP,
+EC,2,ECSTAT,Not in dataset
 EC,3,ECOCCUR,Y
 EC,3,ECPRESP,
+EC,3,ECSTAT,Not in dataset
 HO,1,HOOCCUR,Y
 HO,1,HOPRESP,
 HO,1,HOSTAT,

Published/CORE-000014/positive/02/results/results.csv

@@ -1,4 +1 @@
 Dataset,Record,Variable,Value
-SU,1,SUOCCUR,
-SU,1,SUPRESP,N
-SU,1,SUSTAT,NOT DONE

Published/CORE-000015/negative/01/results/results.csv

@@ -1,46 +1,21 @@
 Dataset,Record,Variable,Value
-AG,1,AGOCCUR,
-AG,1,AGPRESP,Not in dataset
-AG,2,AGOCCUR,
-AG,3,AGOCCUR,
-BE,1,BEOCCUR,
-BE,1,BEPRESP,Not in dataset
-BE,2,BEOCCUR,
-BE,3,BEOCCUR,
-BE,4,BEOCCUR,
-CE,1,CEOCCUR,
-CE,1,CEPRESP,Not in dataset
-CE,2,CEOCCUR,
-CE,3,CEOCCUR,
-CE,4,CEOCCUR,
-CM,1,CMOCCUR,
-CM,1,CMPRESP,Not in dataset
-CM,2,CMOCCUR,
-CM,3,CMOCCUR,
-EC,1,ECOCCUR,
-EC,1,ECPRESP,Not in dataset
-EC,2,ECOCCUR,
-EC,3,ECOCCUR,
-EC,4,ECOCCUR,
-HO,1,HOOCCUR,
-HO,1,HOPRESP,Not in dataset
-HO,2,HOOCCUR,
-HO,3,HOOCCUR,
-HO,4,HOOCCUR,
-MH,1,MHOCCUR,
-MH,1,MHPRESP,Not in dataset
-MH,2,MHOCCUR,
-MH,3,MHOCCUR,
-MH,4,MHOCCUR,
-ML,1,MLOCCUR,
-ML,1,MLPRESP,Not in dataset
-ML,2,MLOCCUR,
-ML,3,MLOCCUR,
-PR,1,PROCCUR,
-PR,1,PRPRESP,Not in dataset
-PR,2,PROCCUR,
-PR,3,PROCCUR,
-SU,1,SUOCCUR,
-SU,1,SUPRESP,Not in dataset
-SU,2,SUOCCUR,
-SU,3,SUOCCUR,
+AG,,AGOCCUR,
+AG,,AGPRESP,Not in dataset
+BE,,BEOCCUR,
+BE,,BEPRESP,Not in dataset
+CE,,CEOCCUR,
+CE,,CEPRESP,Not in dataset
+CM,,CMOCCUR,
+CM,,CMPRESP,Not in dataset
+EC,,ECOCCUR,
+EC,,ECPRESP,Not in dataset
+HO,,HOOCCUR,
+HO,,HOPRESP,Not in dataset
+MH,,MHOCCUR,
+MH,,MHPRESP,Not in dataset
+ML,,MLOCCUR,
+ML,,MLPRESP,Not in dataset
+PR,,PROCCUR,
+PR,,PRPRESP,Not in dataset
+SU,,SUOCCUR,
+SU,,SUPRESP,Not in dataset

Published/CORE-000016/negative/03/results/results.csv

@@ -0,0 +1,65 @@
+Dataset,Record,Variable,Value
+AG,1,AGOCCUR,Y
+AG,1,AGPRESP,Not in dataset
+AG,2,AGOCCUR,N
+AG,2,AGPRESP,Not in dataset
+AG,3,AGOCCUR,Y
+AG,3,AGPRESP,Not in dataset
+BE,1,BEOCCUR,Y
+BE,1,BEPRESP,
+BE,2,BEOCCUR,N
+BE,2,BEPRESP,
+BE,3,BEOCCUR,Y
+BE,3,BEPRESP,
+BE,4,BEOCCUR,N
+BE,4,BEPRESP,
+CE,1,CEOCCUR,Y
+CE,1,CEPRESP,
+CE,2,CEOCCUR,Y
+CE,2,CEPRESP,
+CE,3,CEOCCUR,Y
+CE,3,CEPRESP,
+CE,4,CEOCCUR,N
+CE,4,CEPRESP,
+CM,3,CMOCCUR,Y
+CM,3,CMPRESP,
+EC,1,ECOCCUR,Y
+EC,1,ECPRESP,
+EC,2,ECOCCUR,N
+EC,2,ECPRESP,
+EC,3,ECOCCUR,Y
+EC,3,ECPRESP,
+HO,1,HOOCCUR,Y
+HO,1,HOPRESP,
+HO,2,HOOCCUR,Y
+HO,2,HOPRESP,
+HO,3,HOOCCUR,Y
+HO,3,HOPRESP,
+HO,4,HOOCCUR,N
+HO,4,HOPRESP,
+MH,1,MHOCCUR,Y
+MH,1,MHPRESP,
+MH,2,MHOCCUR,Y
+MH,2,MHPRESP,
+MH,3,MHOCCUR,Y
+MH,3,MHPRESP,
+MH,4,MHOCCUR,N
+MH,4,MHPRESP,
+ML,1,MLOCCUR,Y
+ML,1,MLPRESP,
+ML,2,MLOCCUR,N
+ML,2,MLPRESP,
+ML,3,MLOCCUR,Y
+ML,3,MLPRESP,
+PR,1,PROCCUR,Y
+PR,1,PRPRESP,
+PR,2,PROCCUR,N
+PR,2,PRPRESP,
+PR,3,PROCCUR,Y
+PR,3,PRPRESP,
+SU,1,SUOCCUR,Y
+SU,1,SUPRESP,
+SU,2,SUOCCUR,N
+SU,2,SUPRESP,
+SU,3,SUOCCUR,N
+SU,3,SUPRESP,

Published/CORE-000016/positive/03/results/results.csv

@@ -1,2 +1 @@
 Dataset,Record,Variable,Value
-EC,,,

Published/CORE-000017/positive/02/results/results.csv

@@ -1,2 +1 @@
 Dataset,Record,Variable,Value
-CO,,,