Merge pull request #17 from Anas-Elhounsri/dev

Skip somef feature added and updated the README

Author: Anas-Elhounsri

README.md

@@ -48,13 +48,13 @@ repositories you want to analyze.
 ### 2. Directory Structure [NEEDS AN UPDATE]
 ```
 project/ detect_pitfalls_main.py 
-        +-- somef_outputs/ # Directory containing SoMEF JSON files ¦ 
-            +-- repository1.json ¦ 
-            +-- repository2.json ¦ 
+        +-- somef_outputs/ # Directory containing SoMEF JSON files   
+            +-- repository1.json   
+            +-- repository2.json   
             +-- ... 
-        +-- scripts/ # Individual pitfall detector modules ¦ 
-            +-- p001.py ¦ 
-            +-- p002.py ¦ 
+        +-- scripts/ # Individual pitfall detector modules   
+            +-- p001.py   
+            +-- p002.py   
             +-- ... 
         +-- all_pitfalls_results.json # Generated output file
 
@@ -108,6 +108,15 @@ The results will be like the following:
 ./results/pitfalls/
 ./results/summary.json
 ```
+
+If you have already ran SoMEF individually before running this package and wish to run the analysis, you can skip SoMEF by running this command:
+  
+`python -m metacheck.cli --skip-somef --input somef_outputs/*.json
+`
+or if you wish to run for multiple paths:
+
+`python -m metacheck.cli --skip-somef --input my_somef_outputs_1/*.json my_somef_outputs_2/*.json
+`
 ### 4. Output
 
 The tool will:
@@ -130,7 +139,7 @@ The output file contains:
 
 1. **"There is no valid repository URL" error**: Ensure the JSON file that contains the repositories 
 has a valid structure and that you are inputing the correct path
-2. **Network timeouts**: Some pitfalls validate URLs and may time out—this is normal behavior
+2. **Network timeouts**: Some pitfalls validate URLs and may time out this is normal behavior
 
 ### Performance Notes
 

src/metacheck/cli.py

@@ -1,46 +1,73 @@
-import argparse
-import os
-from metacheck.run_somef import run_somef_batch
-from metacheck.run_analyzer import run_analysis
-
-def cli():
-    parser = argparse.ArgumentParser(description="Detect metadata pitfalls in software repositories using SoMEF.")
-    parser.add_argument(
-        "--input",
-        nargs="+",  # <-- accepts multiple files
-        required=True,
-        help="One or more JSON files containing repositories (e.g., GitHub, GitLab)."
-    )
-    parser.add_argument(
-        "--pitfalls-output",
-        default=os.path.join(os.getcwd(), "pitfalls_outputs"),
-        help="Directory to store pitfall JSON-LD files (default: ./pitfalls_outputs)."
-    )
-    parser.add_argument(
-        "--analysis-output",
-        default=os.path.join(os.getcwd(), "analysis_results.json"),
-        help="File path for summary results (default: ./analysis_results.json)."
-    )
-    parser.add_argument(
-        "--threshold",
-        type=float,
-        default=0.8,
-        help="SoMEF confidence threshold (default: 0.8)."
-    )
-
-    args = parser.parse_args()
-    threshold = args.threshold
-    somef_output_dir = os.path.join(os.getcwd(), "somef_outputs")
-
-    print(f"Detected {len(args.input)} input files:")
-    for json_path in args.input:
-        if not os.path.exists(json_path):
-            print(f"Skipping missing file: {json_path}")
-            continue
-        print(f"Processing repositories from {json_path}")
-        run_somef_batch(json_path, somef_output_dir, threshold)
-
-    run_analysis(somef_output_dir, args.pitfalls_output, args.analysis_output)
-
-if __name__ == "__main__":
-    cli()
+import argparse
+import os
+from pathlib import Path
+from metacheck.run_somef import run_somef_batch
+from metacheck.run_analyzer import run_analysis
+
+
+def cli():
+    parser = argparse.ArgumentParser(description="Detect metadata pitfalls in software repositories using SoMEF.")
+    parser.add_argument(
+        "--input",
+        nargs="+",
+        required=True,
+        help="One or more JSON files containing repositories (e.g., GitHub, GitLab) OR existing SoMEF output files when using --skip-somef."
+    )
+    parser.add_argument(
+        "--skip-somef",
+        action="store_true",
+        help="Skip SoMEF execution and analyze existing SoMEF output files directly. --input should point to SoMEF JSON files."
+    )
+    parser.add_argument(
+        "--pitfalls-output",
+        default=os.path.join(os.getcwd(), "pitfalls_outputs"),
+        help="Directory to store pitfall JSON-LD files (default: ./pitfalls_outputs)."
+    )
+    parser.add_argument(
+        "--analysis-output",
+        default=os.path.join(os.getcwd(), "analysis_results.json"),
+        help="File path for summary results (default: ./analysis_results.json)."
+    )
+    parser.add_argument(
+        "--threshold",
+        type=float,
+        default=0.8,
+        help="SoMEF confidence threshold (default: 0.8). Only used when running SoMEF."
+    )
+
+    args = parser.parse_args()
+
+    if args.skip_somef:
+        print(f"Skipping SoMEF execution. Analyzing {len(args.input)} existing SoMEF output files...")
+
+        somef_json_paths = []
+        for json_path in args.input:
+            if not os.path.exists(json_path):
+                print(f"Warning: File not found, skipping: {json_path}")
+                continue
+            somef_json_paths.append(Path(json_path))
+
+        if not somef_json_paths:
+            print("Error: No valid SoMEF output files found.")
+            return
+
+        print(f"Analyzing {len(somef_json_paths)} SoMEF output files...")
+        run_analysis(somef_json_paths, args.pitfalls_output, args.analysis_output)
+
+    else:
+        threshold = args.threshold
+        somef_output_dir = os.path.join(os.getcwd(), "somef_outputs")
+
+        print(f"Detected {len(args.input)} input files:")
+        for json_path in args.input:
+            if not os.path.exists(json_path):
+                print(f"Skipping missing file: {json_path}")
+                continue
+            print(f"Processing repositories from {json_path}")
+            run_somef_batch(json_path, somef_output_dir, threshold)
+
+        run_analysis(somef_output_dir, args.pitfalls_output, args.analysis_output)
+
+
+if __name__ == "__main__":
+    cli()