rename AI snaps improvements

.gitignore

@@ -1 +1,2 @@
 .DS_Store
+/__pycache__

rename-ai-snaps

@@ -170,10 +170,10 @@ def extract_prompts(filepath):
     return pos, neg
 
 
-def extract_keywords(text, max_chars=40):
+def extract_all_candidates(text):
-    """Generate a short dash-separated keyword description from prompt text."""
+    """Extract all candidate keywords with position index for frequency scoring."""
     if not text:
-        return None
+        return []
 
     text_lower = text.lower()
 
@@ -183,9 +183,11 @@ def extract_keywords(text, max_chars=40):
     # Split on commas, periods, semicolons, exclamation/question marks
     segments = re.split(r"[,.;:!?]+", cleaned)
 
-    # Collect meaningful keywords, preserving order
+    # Collect meaningful keywords, preserving position order
     seen = set()
-    keywords = []
+    candidates = []
+    position = 0
+
     for seg in segments:
         seg = seg.strip()
         if not seg or len(seg) < 4:
@@ -218,43 +220,94 @@ def extract_keywords(text, max_chars=40):
             taken = 0
             for g in good:
                 if g not in seen and taken < 2:
-                    keywords.append(g)
+                    candidates.append((g, position))
                     seen.add(g)
                     taken += 1
+                    position += 1
 
+    return candidates
+
+
+def select_best_keywords(candidates, freq_map, total_images, max_keywords=5):
+    """Select most discriminating keywords by rarity and position.
+
+    Keywords that appear in fewer images across the batch score higher.
+    Later-position keywords get a small bonus for tiebreaking.
+    When total_images <= 1, falls back to first-N selection.
+    """
+    if not candidates:
+        return []
+
+    if total_images <= 1:
+        return [kw for kw, _ in candidates[:max_keywords]]
+
+    scored = []
+    for kw, pos in candidates:
+        freq = freq_map.get(kw, 1)
+        # Rarity: 1.0 = appears in 1 image, 0.0 = appears in all images
+        rarity = 1.0 - ((freq - 1) / max(total_images - 1, 1))
+        # Position bonus: slight preference for later words (up to 0.3)
+        max_pos = max(len(candidates), 1)
+        pos_bonus = (pos / max_pos) * 0.3
+        score = rarity + pos_bonus
+        scored.append((score, kw, pos))
+
+    # Sort by score desc, then by original position asc for stability
+    scored.sort(key=lambda x: (-x[0], x[2]))
+
+    selected = []
+    seen = set()
+    for _, kw, _ in scored:
+        if kw not in seen:
+            selected.append(kw)
+            seen.add(kw)
+        if len(selected) >= max_keywords:
+            break
+
+    return selected
+
+
+def keywords_to_name(keywords):
+    """Convert keyword list to 'schmeeve-AI-{keywords}.png' name."""
     if not keywords:
         return None
 
-    # Build description: up to 5 keywords
+    desc = "-".join(keywords)
-    desc = "-".join(keywords[:5])
-
-    # Replace any non-alphanumeric (except hyphen) with hyphens
     desc = re.sub(r"[^a-z0-9-]", "-", desc)
     desc = re.sub(r"-+", "-", desc).strip("-")
 
-    # Truncate at max_chars, breaking at a word boundary
+    # Truncate at 40 chars, breaking at a word boundary
-    if len(desc) > max_chars:
+    if len(desc) > 40:
-        desc = desc[:max_chars].rstrip("-")
+        desc = desc[:40].rstrip("-")
-        if max_chars > 10 and "-" in desc:
+        if "-" in desc:
             truncated = "-".join(desc.split("-")[:-1])
             if truncated and len(truncated) > 10:
                 desc = truncated
 
-    return desc if desc and len(desc) > 3 else None
+    return f"schmeeve-AI-{desc}.png" if desc and len(desc) > 3 else None
 
 
-def propose_name(filepath):
+def propose_name(filepath, freq_map=None, total_images=1):
-    """Propose 'schmeeve-AI-{keywords}.png' or None."""
+    """Propose 'schmeeve-AI-{keywords}.png' or None.
+
+    When freq_map and total_images > 1 are provided, uses frequency-aware
+    keyword selection that favors rare (discriminating) words.
+    """
     pos, neg = extract_prompts(filepath)
     source = pos or neg
     if not source:
         return None
 
-    desc = extract_keywords(source)
+    candidates = extract_all_candidates(source)
-    if not desc:
+    if not candidates:
         return None
 
-    return f"schmeeve-AI-{desc}.png"
+    if freq_map and total_images > 1:
+        keywords = select_best_keywords(candidates, freq_map, total_images)
+    else:
+        keywords = [kw for kw, _ in candidates[:5]]
+
+    return keywords_to_name(keywords)
 
 
 # ── main ───────────────────────────────────────────────────────────────────
@@ -282,40 +335,65 @@ def main():
 
     pngs = sorted(scan_dir.glob("*.png"))
 
-    # ── Phase 1: Analyze with spinner ──
+    # ── Phase 1: Collect candidates and build frequency map ──
     sys.stdout.write("  Analyzing PNGs")
     sys.stdout.flush()
     spin = spinner()
-    raw_proposals = {}
+    image_data = {}
+    word_images = {}
     for p in pngs:
         sys.stdout.write(f"\r  {next(spin)} Analyzing PNGs")
         sys.stdout.flush()
         # Skip already-renamed files
         if p.name.startswith("schmeeve-AI-"):
             continue
-        name = propose_name(str(p))
+        pos, neg = extract_prompts(str(p))
+        source = pos or neg
+        if source:
+            candidates = extract_all_candidates(source)
+            if candidates:
+                image_data[p] = candidates
+                for kw, _ in candidates:
+                    if kw not in word_images:
+                        word_images[kw] = set()
+                    word_images[kw].add(p)
+        time.sleep(0.02)
+
+    freq_map = {kw: len(images) for kw, images in word_images.items()}
+    total_images = len(image_data)
+
+    # ── Phase 1b: Propose names with frequency-aware selection ──
+    raw_proposals = {}
+    for p, candidates in image_data.items():
+        if total_images > 1:
+            keywords = select_best_keywords(candidates, freq_map, total_images)
+        else:
+            keywords = [kw for kw, _ in candidates[:5]]
+        name = keywords_to_name(keywords)
         if name:
             raw_proposals[p] = name
-        time.sleep(0.02)
 
     # Clear the spinner line
     sys.stdout.write("\r" + " " * 60 + "\r")
     sys.stdout.flush()
 
-    # Deduplicate proposed names
+    # Deduplicate proposed names; use short mtime tag for collisions
     proposals = {}
     name_counts = {}
     for p, name in raw_proposals.items():
         base = name
         if base in name_counts:
             name_counts[base] += 1
-            stem = base.rsplit(".", 1)[0]
-            ext = ".png"
-            name = f"{stem}_{name_counts[base]}{ext}"
         else:
-            name_counts[base] = 0
+            name_counts[base] = 1
         proposals[p] = name
 
+    for p, name in list(proposals.items()):
+        if name_counts[name] > 1:
+            ts = time.strftime("%m%d-%H%M%S", time.localtime(p.stat().st_mtime))
+            stem = name.rsplit(".", 1)[0]
+            proposals[p] = f"{stem}-{ts}.png"
+
     # ── Phase 2: Display proposed names ──
     if not proposals:
         print("  No renamable PNGs found.")