Add metadata quality checker tool

metadata_quality_checker/README.md

@@ -0,0 +1,17 @@
+# Metadata Quality Checker Tool
+
+A Python CLI tool that analyzes OWASP project metadata and reports
+missing or low-quality fields affecting project discovery.
+
+## Checks Performed
+- Tags presence and count
+- Project type
+- Difficulty level
+- Pitch quality
+- Repository URL
+- Activity (last commit)
+
+## Usage
+
+```bash
+python checker.py

metadata_quality_checker/checker.py

@@ -0,0 +1,47 @@
+import json
+import sys
+from pathlib import Path
+from rules import check_rules
+from score import calculate_score, get_status
+
+
+def load_metadata():
+    # If user passes a file path: python checker.py file.json
+    if len(sys.argv) > 1:
+        metadata_path = Path(sys.argv[1])
+    else:
+        # Default to sample file
+        metadata_path = Path(__file__).parent / "sample_metadata.json"
+
+    if not metadata_path.exists():
+        print(f"❌ Metadata file not found: {metadata_path}")
+        sys.exit(1)
+
+    with open(metadata_path, "r", encoding="utf-8") as f:
+        return json.load(f)
+
+
+def main():
+    metadata = load_metadata()
+
+    print("\n🔍 OWASP Metadata Quality Report\n")
+
+    for project in metadata:
+        issues = check_rules(project)
+        score = calculate_score(project)
+        status = get_status(score)
+
+        name = project.get("name", "Unnamed Project")
+        print(f"📦 Project: {name}")
+        print(f"📊 Score: {score}/100 ({status})")
+
+        if not issues:
+            print("✅ No issues found\n")
+        else:
+            for issue in issues:
+                print(f"❌ {issue}")
+            print("")
+
+
+if __name__ == "__main__":
+    main()

metadata_quality_checker/rules.py

@@ -0,0 +1,38 @@
+from datetime import datetime, timedelta
+
+
+def check_rules(project: dict) -> list[str]:
+    issues = []
+
+    if not project.get("name"):
+        issues.append("Missing project name")
+
+    tags = project.get("tags", [])
+    if not isinstance(tags, list) or len(tags) < 2:
+        issues.append("Missing or insufficient tags")
+
+    if not project.get("type"):
+        issues.append("Missing project type")
+
+    if not project.get("level"):
+        issues.append("Missing difficulty level")
+
+    pitch = project.get("pitch", "")
+    if not pitch or len(pitch) < 30:
+        issues.append("Pitch too short or missing")
+
+    if not project.get("repo_url"):
+        issues.append("Missing repository URL")
+
+    last_commit = project.get("last_commit")
+    if last_commit:
+        try:
+            commit_date = datetime.fromisoformat(last_commit)
+            if commit_date < datetime.now() - timedelta(days=365):
+                issues.append("Project inactive (no commits in last 12 months)")
+        except ValueError:
+            issues.append("Invalid last_commit date format")
+    else:
+        issues.append("Missing activity data")
+
+    return issues

metadata_quality_checker/sample_metadata.json

@@ -0,0 +1,20 @@
+[
+  {
+    "name": "OWASP Example Tool",
+    "tags": [],
+    "type": "tool",
+    "level": "",
+    "pitch": "Short",
+    "repo_url": "https://github.com/owasp/example",
+    "last_commit": "2022-01-10"
+  },
+  {
+    "name": "OWASP Juice Shop",
+    "tags": ["appsec", "training", "nodejs"],
+    "type": "training",
+    "level": "beginner",
+    "pitch": "An intentionally insecure web application for security training.",
+    "repo_url": "https://github.com/juice-shop/juice-shop",
+    "last_commit": "2025-11-20"
+  }
+]

metadata_quality_checker/score.py

@@ -0,0 +1,32 @@
+def calculate_score(project: dict) -> int:
+    score = 0
+
+    if project.get("name"):
+        score += 10
+
+    if isinstance(project.get("tags"), list) and len(project["tags"]) >= 2:
+        score += 25
+
+    if project.get("type"):
+        score += 15
+
+    if project.get("level"):
+        score += 15
+
+    pitch = project.get("pitch", "")
+    if pitch and len(pitch) >= 30:
+        score += 20
+
+    if project.get("last_commit"):
+        score += 15
+
+    return score
+
+
+def get_status(score: int) -> str:
+    if score >= 80:
+        return "good"
+    if score >= 50:
+        return "needs improvement"
+    return "poor"
+