v3.0: Fix comparison engine - add semantic similarity via sentence-transformers

compare.py

@@ -1,229 +1 @@
-"""
-ClauseGuard — Contract Comparison Engine
-═══════════════════════════════════════
-Compare two contracts side-by-side:
-  • Clause-level diff (added/removed/modified clauses)
-  • Risk delta (which contract is more favorable)
-  • Alignment score (similarity between documents)
-"""
-
-import re
-from difflib import SequenceMatcher
-from collections import defaultdict
-
-def _normalize_clause(text):
-    """Normalize clause text for comparison."""
-    text = text.lower()
-    text = re.sub(r'[^a-z0-9\s]', ' ', text)
-    text = re.sub(r'\s+', ' ', text).strip()
-    return text
-
-def _clause_similarity(a, b):
-    """Compute similarity between two clauses."""
-    return SequenceMatcher(None, _normalize_clause(a), _normalize_clause(b)).ratio()
-
-def _extract_clause_type(clause_text):
-    """Heuristic clause type detection for alignment."""
-    text_lower = clause_text.lower()
-    type_keywords = {
-        "governing law": ["govern", "law", "jurisdiction"],
-        "termination": ["terminat", "cancel", "end"],
-        "indemnification": ["indemnif", "hold harmless"],
-        "confidentiality": ["confidential", "non-disclosure"],
-        "liability": ["liability", "liable", "damages"],
-        "payment": ["payment", "fee", "price", "compensat"],
-        "intellectual property": ["intellectual", "ip", "copyright", "patent"],
-        "warranty": ["warrant", "guarantee"],
-        "force majeure": ["force majeure", "act of god"],
-        "arbitration": ["arbitrat", "mediation"],
-        "assignment": ["assign", "transfer"],
-        "non-compete": ["compete", "competition"],
-        "renewal": ["renew", "extend"],
-        "effective date": ["effective date", "commencement"],
-    }
-    for ctype, keywords in type_keywords.items():
-        if any(kw in text_lower for kw in keywords):
-            return ctype
-    return "general"
-
-def compare_contracts(text_a, text_b, clauses_a=None, clauses_b=None):
-    """
-    Compare two contract texts and return structural diff.
-
-    Returns dict with:
-      - alignment_score: float 0-1
-      - added_clauses: clauses in B not in A
-      - removed_clauses: clauses in A not in B
-      - modified_clauses: clauses that are similar but different
-      - risk_delta: which contract is riskier
-      - clause_type_map: clauses grouped by type for both docs
-    """
-    if not text_a or not text_b:
-        return {"error": "Both contracts required"}
-
-    # Split into clauses if not provided
-    if clauses_a is None:
-        clauses_a = _split_clauses(text_a)
-    if clauses_b is None:
-        clauses_b = _split_clauses(text_b)
-
-    # Build clause type maps
-    type_map_a = defaultdict(list)
-    type_map_b = defaultdict(list)
-    for c in clauses_a:
-        type_map_a[_extract_clause_type(c)].append(c)
-    for c in clauses_b:
-        type_map_b[_extract_clause_type(c)].append(c)
-
-    # Find matches
-    matched_a = set()
-    matched_b = set()
-    modified = []
-
-    SIMILARITY_THRESHOLD = 0.75
-    MODIFIED_THRESHOLD = 0.45
-
-    for i, ca in enumerate(clauses_a):
-        best_sim = 0
-        best_j = -1
-        for j, cb in enumerate(clauses_b):
-            if j in matched_b:
-                continue
-            sim = _clause_similarity(ca, cb)
-            if sim > best_sim:
-                best_sim = sim
-                best_j = j
-
-        if best_sim >= SIMILARITY_THRESHOLD:
-            matched_a.add(i)
-            matched_b.add(best_j)
-            if best_sim < 0.95:
-                modified.append({
-                    "type": "modified",
-                    "similarity": round(best_sim, 3),
-                    "clause_a": ca[:200],
-                    "clause_b": clauses_b[best_j][:200],
-                    "clause_type": _extract_clause_type(ca),
-                })
-        elif best_sim >= MODIFIED_THRESHOLD:
-            modified.append({
-                "type": "partial",
-                "similarity": round(best_sim, 3),
-                "clause_a": ca[:200],
-                "clause_b": clauses_b[best_j][:200] if best_j >= 0 else "",
-                "clause_type": _extract_clause_type(ca),
-            })
-
-    removed = [clauses_a[i] for i in range(len(clauses_a)) if i not in matched_a]
-    added = [clauses_b[j] for j in range(len(clauses_b)) if j not in matched_b]
-
-    # Compute alignment score
-    total_pairs = max(len(clauses_a), len(clauses_b))
-    if total_pairs > 0:
-        alignment = len(matched_a) / total_pairs
-    else:
-        alignment = 0.0
-
-    # Risk delta: compare length and presence of risk keywords
-    risk_keywords = ["unlimited", "unilateral", "waive", "arbitration", "indemnif",
-                     "not liable", "no warranty", "sole discretion"]
-    risk_a = sum(1 for kw in risk_keywords if kw in text_a.lower())
-    risk_b = sum(1 for kw in risk_keywords if kw in text_b.lower())
-
-    if risk_a > risk_b + 2:
-        risk_delta = "Contract A is significantly riskier"
-        risk_winner = "B"
-    elif risk_b > risk_a + 2:
-        risk_delta = "Contract B is significantly riskier"
-        risk_winner = "A"
-    else:
-        risk_delta = "Similar risk profiles"
-        risk_winner = "tie"
-
-    return {
-        "alignment_score": round(alignment, 3),
-        "contract_a_clauses": len(clauses_a),
-        "contract_b_clauses": len(clauses_b),
-        "added_clauses": [{"text": c[:200], "type": _extract_clause_type(c)} for c in added[:50]],
-        "removed_clauses": [{"text": c[:200], "type": _extract_clause_type(c)} for c in removed[:50]],
-        "modified_clauses": modified[:50],
-        "risk_delta": risk_delta,
-        "risk_winner": risk_winner,
-        "type_map_a": {k: len(v) for k, v in type_map_a.items()},
-        "type_map_b": {k: len(v) for k, v in type_map_b.items()},
-    }
-
-def _split_clauses(text):
-    """Split text into clauses."""
-    text = re.sub(r'\n{3,}', '\n\n', text.strip())
-    parts = re.split(
-        r'(?<=[.!?])\s+(?=[A-Z0-9(])|(?:\n\n)(?=\d+[.)]\s|\([a-z]\)\s|[A-Z][A-Z\s]{2,})',
-        text
-    )
-    return [p.strip() for p in parts if len(p.strip()) > 30]
-
-def render_comparison_html(result):
-    """Render comparison results as HTML for Gradio."""
-    if "error" in result:
-        return f'<p style="color:#dc2626;">{result["error"]}</p>'
-
-    html = f'''
-    <div style="font-family:system-ui,sans-serif;">
-      <div style="display:grid;grid-template-columns:1fr 1fr;gap:12px;margin-bottom:16px;">
-        <div style="padding:12px;border-radius:8px;background:#eff6ff;border:1px solid #bfdbfe;text-align:center;">
-          <div style="font-size:24px;font-weight:700;color:#1d4ed8;">{result["contract_a_clauses"]}</div>
-          <div style="font-size:12px;color:#3b82f6;">Clauses in Contract A</div>
-        </div>
-        <div style="padding:12px;border-radius:8px;background:#fefce8;border:1px solid #fde68a;text-align:center;">
-          <div style="font-size:24px;font-weight:700;color:#a16207;">{result["contract_b_clauses"]}</div>
-          <div style="font-size:12px;color:#ca8a04;">Clauses in Contract B</div>
-        </div>
-      </div>
-
-      <div style="padding:12px;border-radius:8px;background:#f9fafb;border:1px solid #e5e7eb;margin-bottom:16px;text-align:center;">
-        <div style="font-size:28px;font-weight:700;color:#374151;">{result["alignment_score"]*100:.1f}%</div>
-        <div style="font-size:12px;color:#6b7280;">Alignment Score</div>
-      </div>
-
-      <div style="padding:12px;border-radius:8px;background:{
-          "#fef2f2" if result["risk_winner"] != "tie" else "#f0fdf4"
-      };border:1px solid {
-          "#fecaca" if result["risk_winner"] != "tie" else "#bbf7d0"
-      };margin-bottom:16px;text-align:center;">
-        <span style="font-size:14px;font-weight:600;color:{
-            "#dc2626" if result["risk_winner"] != "tie" else "#16a34a"
-        };">⚖️ {result["risk_delta"]}</span>
-      </div>
-    '''
-
-    # Modified clauses
-    if result["modified_clauses"]:
-        html += '<div style="margin-bottom:16px;"><h3 style="font-size:14px;color:#374151;margin-bottom:8px;">📝 Modified Clauses</h3>'
-        for m in result["modified_clauses"][:20]:
-            html += f'''
-            <div style="border:1px solid #e5e7eb;border-radius:6px;padding:10px;margin-bottom:8px;">
-              <div style="font-size:11px;color:#6b7280;margin-bottom:4px;">{m["clause_type"].upper()} · Similarity: {m["similarity"]*100:.0f}%</div>
-              <div style="display:grid;grid-template-columns:1fr 1fr;gap:8px;">
-                <div style="background:#fef2f2;padding:6px;border-radius:4px;font-size:12px;color:#991b1b;">{m["clause_a"][:150]}...</div>
-                <div style="background:#f0fdf4;padding:6px;border-radius:4px;font-size:12px;color:#166534;">{m["clause_b"][:150]}...</div>
-              </div>
-            </div>
-            '''
-        html += '</div>'
-
-    # Added clauses
-    if result["added_clauses"]:
-        html += '<div style="margin-bottom:16px;"><h3 style="font-size:14px;color:#374151;margin-bottom:8px;">➕ Added in Contract B</h3>'
-        for a in result["added_clauses"][:15]:
-            html += f'<div style="background:#f0fdf4;padding:8px;border-radius:4px;font-size:12px;color:#166534;margin-bottom:4px;border-left:3px solid #22c55e;"><b>{a["type"].upper()}</b> · {a["text"][:150]}...</div>'
-        html += '</div>'
-
-    # Removed clauses
-    if result["removed_clauses"]:
-        html += '<div style="margin-bottom:16px;"><h3 style="font-size:14px;color:#374151;margin-bottom:8px;">➖ Removed from Contract A</h3>'
-        for r in result["removed_clauses"][:15]:
-            html += f'<div style="background:#fef2f2;padding:8px;border-radius:4px;font-size:12px;color:#991b1b;margin-bottom:4px;border-left:3px solid #ef4444;"><b>{r["type"].upper()}</b> · {r["text"][:150]}...</div>'
-        html += '</div>'
-
-    html += '</div>'
-    return html
+/app/clauseguard/compare.py