Update analyze_email_main.py

analyze_email_main.py

@@ -4,23 +4,24 @@ from body_analyzer import analyze_body
 from url_analyzer import analyze_urls
 
 def analyze(file_path):
-    # --- Parse the email ---
-    headers, body, urls = parse_email(file_path)
+    # Parse
+    headers, body, urls = parse_email(file_path or "")
 
-    # --- Analyze headers ---
-    header_findings, header_score = analyze_headers(headers)
+    # Analyze
+    header_findings, header_score = analyze_headers(headers or {})
+    body_findings, body_score, highlighted_body, body_verdict = analyze_body(body or "")
+    url_findings, url_score = analyze_urls(urls or [])
 
-    # --- Analyze body (updated analyzer with improvements) ---
-    body_findings, body_score, highlighted_body, body_verdict = analyze_body(body)
+    # Score
+    total_score = (header_score or 0) + (body_score or 0) + (url_score or 0) * 1.5
+    try:
+        total_score = float(total_score)
+    except Exception:
+        total_score = 0.0
+    total_score = max(0.0, min(total_score, 100.0))
+    total_score_rounded = round(total_score)
 
-    # --- Analyze URLs ---
-    url_findings, url_score = analyze_urls(urls)
-
-    # --- Calculate total score ---
-    total_score = header_score + body_score + (url_score * 1.5)
-    total_score = min(total_score, 100)
-
-    # --- Determine final verdict ---
+    # Verdict
     if total_score >= 70:
         verdict = "🚨 Malicious"
     elif 50 <= total_score < 70:
@@ -30,9 +31,9 @@ def analyze(file_path):
     else:
         verdict = "✅ Safe"
 
-    # --- Determine attack type ---
-    body_lower = body.lower()
-    attack_type = "General Phishing"  # default
+    # Attack type
+    body_lower = (body or "").lower()
+    attack_type = "General Phishing"
     if any(word in body_lower for word in ["invoice", "payment", "wire transfer", "bank details"]):
         attack_type = "Invoice/Payment Fraud (BEC)"
     elif any(word in body_lower for word in ["password", "verify", "account", "login", "credentials"]):
@@ -44,51 +45,33 @@ def analyze(file_path):
     elif verdict == "✅ Safe":
         attack_type = "Benign / Normal Email"
 
-    # --- Collect tags ---
+    # Tags
     tags = []
-    for finding in header_findings + body_findings + url_findings:
-        f_lower = finding.lower()
-        if "domain" in f_lower:
+    for finding in (header_findings + body_findings + url_findings):
+        fl = finding.lower()
+        if "domain" in fl:
             tags.append("Suspicious Sender Domain")
-        if "phishing" in f_lower or "malicious url" in f_lower:
+        if "phishing" in fl or "malicious url" in fl or "urlhaus" in fl:
             tags.append("Phishing / Malicious URL")
-        if "urgent" in f_lower or "suspicious phrase" in f_lower:
+        if "urgent" in fl or "suspicious phrase" in fl:
             tags.append("Urgent Language")
-        if "spam" in f_lower or "marketing" in f_lower:
+        if "spam" in fl or "marketing" in fl:
             tags.append("Spam Tone")
+        if "spf" in fl or "dkim" in fl or "dmarc" in fl:
+            tags.append("Auth Failures (SPF/DKIM/DMARC)")
 
-    # --- Summary report ---
     summary = {
         "Final Verdict": verdict,
         "Attack Type": attack_type,
-        "Attack Score": total_score,
-        "Main Tags": ", ".join(sorted(set(tags))) if tags else "No special tags"
+        "Attack Score": total_score_rounded,
+        "Main Tags": ", ".join(sorted(set(tags))) if tags else "No special tags",
     }
 
-    # --- Detailed findings ---
     details = {
-        "Header Findings": header_findings,
-        "Body Findings": body_findings,
-        "URL Findings": url_findings,
-        "Highlighted Body": highlighted_body
+        "Header Findings": header_findings or [],
+        "Body Findings": body_findings or [],
+        "URL Findings": url_findings or [],
+        "Highlighted Body": highlighted_body or "",
     }
 
     return summary, details
-
-# --- Local testing ---
-if __name__ == "__main__":
-    file_path = "sample.eml"
-    summary, details = analyze(file_path)
-    
-    print("==== SUMMARY ====")
-    for k, v in summary.items():
-        print(f"{k}: {v}")
-    
-    print("\n==== DETAILS ====")
-    for section, findings in details.items():
-        print(f"\n-- {section} --")
-        if isinstance(findings, list):
-            for f in findings:
-                print(f)
-        else:
-            print(findings)