Update app.py

app.py

@@ -6,6 +6,7 @@ import base64
 import logging
 import uuid
 import time
+import re
 from typing import List, Dict, Any, Tuple, Optional
 
 from flask import Flask, request, jsonify
@@ -48,6 +49,106 @@ if FIREBASE_ADMIN_JSON and not FIREBASE_ADMIN_AVAILABLE:
 app = Flask(__name__)
 CORS(app)
 
+# ---------- Category mapping (must match frontend) ----------
+# These values intentionally match the CATEGORY_OPTIONS array on the frontend.
+CATEGORIES = [
+    "Heels",
+    "Sneakers",
+    "Loafers",
+    "Boots",
+    "Dress",
+    "Jeans",
+    "Skirt",
+    "Jacket",
+    "Blazer",
+    "T-Shirt",
+    "Coat",
+    "Shorts",
+]
+
+# simple synonyms / keyword -> category mapping (lowercase keys)
+SYNONYMS: Dict[str, str] = {
+    "heel": "Heels",
+    "heels": "Heels",
+    "sneaker": "Sneakers",
+    "sneakers": "Sneakers",
+    "trainer": "Sneakers",
+    "trainers": "Sneakers",
+    "loafer": "Loafers",
+    "loafers": "Loafers",
+    "boot": "Boots",
+    "boots": "Boots",
+    "dress": "Dress",
+    "gown": "Dress",
+    "jean": "Jeans",
+    "jeans": "Jeans",
+    "denim": "Jeans",
+    "skirt": "Skirt",
+    "jacket": "Jacket",
+    "coat": "Coat",
+    "blazer": "Blazer",
+    "t-shirt": "T-Shirt",
+    "t shirt": "T-Shirt",
+    "tee": "T-Shirt",
+    "shirt": "T-Shirt",
+    "top": "T-Shirt",
+    "short": "Shorts",
+    "shorts": "Shorts",
+    "shoe": "Sneakers",  # generic shoe -> map to Sneakers as fallback
+    "shoes": "Sneakers",
+    "sandal": "Heels",  # if ambiguous, map sandals to Heels bucket (you can adjust)
+    "sandals": "Heels",
+}
+
+def normalize_text(s: str) -> str:
+    return re.sub(r'[^a-z0-9\s\-]', ' ', s.lower()).strip()
+
+def choose_category_from_candidates(*candidates: Optional[str], tags: Optional[List[str]] = None) -> str:
+    """
+    Given a list of candidate strings (analysis.type, label, summary, etc.) and optional tags,
+    attempt to pick a category from CATEGORIES. Returns a category string guaranteed to be in CATEGORIES.
+    Falls back to "T-Shirt" if nothing matches.
+    """
+    # try tags first (explicit tag likely to indicate category)
+    if tags:
+        for t in tags:
+            if not t: 
+                continue
+            tok = normalize_text(str(t))
+            # direct synonym match
+            if tok in SYNONYMS:
+                return SYNONYMS[tok]
+            # partial substring match
+            for key, cat in SYNONYMS.items():
+                if key in tok:
+                    return cat
+            # try direct category name match
+            for cat in CATEGORIES:
+                if tok == cat.lower() or cat.lower() in tok:
+                    return cat
+
+    # iterate through candidate strings in order provided
+    for c in candidates:
+        if not c:
+            continue
+        s = normalize_text(str(c))
+        # exact category match
+        for cat in CATEGORIES:
+            if s == cat.lower() or cat.lower() in s:
+                return cat
+        # check synonyms dictionary words
+        words = s.split()
+        for w in words:
+            if w in SYNONYMS:
+                return SYNONYMS[w]
+        # check substrings (e.g., "sneaker" inside longer text)
+        for key, cat in SYNONYMS.items():
+            if key in s:
+                return cat
+
+    # If nothing found, return a safe default present in CATEGORIES
+    return "T-Shirt"
+
 # ---------- Firebase init helpers ----------
 _firebase_app = None
 
@@ -397,6 +498,16 @@ def process_image():
 
                 itm["analysis"] = analysis
 
+                # choose a frontend-category-compatible title
+                # prefer analysis.type, then label, then tags, then summary
+                title = choose_category_from_candidates(
+                    analysis.get("type", ""),
+                    itm.get("label", ""),
+                    ' '.join(analysis.get("tags", [])),
+                    tags=analysis.get("tags", [])
+                )
+                itm["title"] = title
+
                 item_id = itm.get("id") or str(uuid.uuid4())
                 path = f"detected/{safe_uid}/{item_id}.jpg"
                 try:
@@ -410,13 +521,14 @@ def process_image():
                         "ai_brand": analysis.get("brand",""),
                         "ai_summary": analysis.get("summary",""),
                         "ai_tags": json.dumps(analysis.get("tags", [])),
+                        "title": title,
                     }
                     url = upload_b64_to_firebase(b64, path, content_type="image/jpeg", metadata=metadata)
                     itm["thumbnail_url"] = url
                     itm["thumbnail_path"] = path
                     itm.pop("thumbnail_b64", None)
                     itm["_session_id"] = session_id
-                    log.debug("Auto-uploaded thumbnail for %s -> %s (session=%s)", item_id, url, session_id)
+                    log.debug("Auto-uploaded thumbnail for %s -> %s (session=%s) title=%s", item_id, url, session_id, title)
                 except Exception as up_e:
                     log.warning("Auto-upload failed for %s: %s", item_id, up_e)
                     # keep thumbnail_b64 and analysis for client fallback
@@ -425,6 +537,12 @@ def process_image():
                 log.info("FIREBASE_ADMIN_JSON not set; skipping server-side thumbnail upload.")
             else:
                 log.info("Firebase admin SDK not available; skipping server-side thumbnail upload.")
+            # For non-upload path, still add a title derived from label/unknown so frontend has it
+            for itm in items_out:
+                if "title" not in itm:
+                    analysis = itm.get("analysis") or {"type":"unknown","tags":[]}
+                    title = choose_category_from_candidates(analysis.get("type",""), itm.get("label",""), tags=analysis.get("tags", []))
+                    itm["title"] = title
 
         return jsonify({"ok": True, "items": items_out, "session_id": session_id, "debug": {"raw_model_text": (raw_text or "")[:1600]}}), 200
 
@@ -432,6 +550,10 @@ def process_image():
         log.exception("Processing error: %s", ex)
         try:
             items_out = fallback_contour_crops(bgr_img, max_items=8)
+            # give fallback items a default title so frontend can filter
+            for itm in items_out:
+                if "title" not in itm:
+                    itm["title"] = choose_category_from_candidates(itm.get("label","unknown"))
             return jsonify({"ok": True, "items": items_out, "session_id": session_id, "debug": {"error": str(ex)}}), 200
         except Exception as e2:
             log.exception("Fallback also failed: %s", e2)
@@ -509,10 +631,20 @@ def finalize_detections():
                     ai_brand = md.get("ai_brand") or ""
                     ai_summary = md.get("ai_summary") or ""
                     ai_tags_raw = md.get("ai_tags") or "[]"
+                    title_meta = md.get("title") or ""
                     try:
                         ai_tags = json.loads(ai_tags_raw) if isinstance(ai_tags_raw, str) else ai_tags_raw
                     except Exception:
                         ai_tags = []
+                    # derive title: prefer stored metadata title, then ai_type/tags/summary
+                    title = None
+                    if title_meta:
+                        try:
+                            title = json.loads(title_meta) if (title_meta.startswith('[') or title_meta.startswith('{')) else str(title_meta)
+                        except Exception:
+                            title = str(title_meta)
+                    if not title:
+                        title = choose_category_from_candidates(ai_type, ai_summary, tags=ai_tags)
                     kept.append({
                         "id": item_id,
                         "thumbnail_url": url,
@@ -522,7 +654,8 @@ def finalize_detections():
                           "brand": ai_brand,
                           "summary": ai_summary,
                           "tags": ai_tags
-                        }
+                        },
+                        "title": title
                     })
                 else:
                     try: