Users can now specify the location for SoMEF outputs issue #53, along side some minor changes to the report (wid, N/A instead of empty suggestions)

Author: Anas-Elhounsri

README.md

@@ -97,6 +97,7 @@ The `repositories.json` file should be structured as follows:
 
 ```bash
 poetry run rsmetacheck --input repositories.json \
+  --somef-output ./results/somef \
   --pitfalls-output ./results/pitfalls \
   --analysis-output ./results/summary.json
 ```
@@ -127,7 +128,7 @@ poetry run rsmetacheck --input https://github.com/tidyverse/tidyverse --verbose
 
 The tool will:
 
-- Process all JSON files in the `somef_outputs` (by default created by the tool) directory
+- Process all JSON files in the SoMEF output directory (by default `somef_outputs` created by the tool)
 - Display progress messages showing detected pitfalls
 - Generate JSON-LD files of detailed Pitfalls and Warnings detected by the tool in `output_1_pitfalls.jsonld`,
   `output_2_pitfalls.jsonld`, etc... in `pitfalls` (by default created by the tool) directory

src/metacheck/cli.py

@@ -23,6 +23,11 @@ def cli():
         default=os.path.join(os.getcwd(), "pitfalls_outputs"),
         help="Directory to store pitfall JSON-LD files (default: ./pitfalls_outputs)."
     )
+    parser.add_argument(
+        "--somef-output",
+        default=os.path.join(os.getcwd(), "somef_outputs"),
+        help="Directory to store SoMEF output files (default: ./somef_outputs)."
+    )
     parser.add_argument(
         "--analysis-output",
         default=os.path.join(os.getcwd(), "analysis_results.json"),
@@ -62,7 +67,7 @@ def cli():
 
     else:
         threshold = args.threshold
-        somef_output_dir = os.path.join(os.getcwd(), "somef_outputs")
+        somef_output_dir = args.somef_output
 
         print(f"Detected {len(args.input)} input(s):")
 

src/metacheck/detect_pitfalls_main.py

@@ -374,7 +374,6 @@ def detect_all_pitfalls(json_files: Iterable[Path], pitfalls_output_dir: Union[s
             except Exception as e:
                 print(f"Error creating JSON-LD for {json_file.name}: {e}")
 
-            # Capture commit ID in evaluated_repositories summary
             try:
                 repo_name = json_file.name
                 if "full_name" in somef_data and somef_data["full_name"]:
@@ -413,6 +412,8 @@ def detect_all_pitfalls(json_files: Iterable[Path], pitfalls_output_dir: Union[s
     results["summary"]["total_warnings_detected"] = total_warnings
 
     for i, count in enumerate(pitfall_counts):
+        pitfall_code_str = pitfall_detectors[i][1]
+        results["pitfalls & warnings"][i]["pitfall"] = f"https://w3id.org/rsmetacheck/catalog/#{pitfall_code_str}"
         results["pitfalls & warnings"][i]["count"] = count
         if total_repos > 0:
             results["pitfalls & warnings"][i]["percentage"] = round((count / total_repos) * 100, 2)

src/metacheck/utils/json_ld_utils.py

@@ -484,7 +484,6 @@ def create_pitfall_jsonld(somef_data: Dict, pitfall_results: List[Dict], file_na
     """
     Create a JSON-LD structure for detected pitfalls following the sample format.
     """
-    import hashlib
     software_info = extract_software_info_from_somef(somef_data)
     description_info = extract_description_info(somef_data)
 
@@ -516,7 +515,7 @@ def create_pitfall_jsonld(somef_data: Dict, pitfall_results: List[Dict], file_na
 
             output_val = "true" if has_issue else "false"
             evidence_val = format_evidence_text(pitfall_code, pitfall_result) if has_issue else f"{pitfall_code} not detected:"
-            suggestion_val = get_suggestion_text(pitfall_code) if has_issue else ""
+            suggestion_val = get_suggestion_text(pitfall_code) if has_issue else "N/A"
 
             check_result = {
                 "@type": "CheckResult",
@@ -529,13 +528,11 @@ def create_pitfall_jsonld(somef_data: Dict, pitfall_results: List[Dict], file_na
                 },
                 "process": get_pitfall_description(pitfall_code),
                 "status": {"@id": "schema:CompletedActionStatus"},
+                "pitfall": f"https://w3id.org/rsmetacheck/catalog/#{pitfall_code}",
                 "output": output_val,
                 "evidence": evidence_val,
                 "suggestion": suggestion_val
             }
-            
-            check_hash = hashlib.sha256(json.dumps(check_result, sort_keys=True).encode("utf-8")).hexdigest()
-            check_result["checkId"] = check_hash
 
             jsonld_output["checks"].append(check_result)