add fuzzy

app.py

@@ -60,6 +60,36 @@ def normalize(text: str) -> str:
     text = text.replace("เแ", "แ").replace("เเ", "แ")
     return text.strip().lower()
 
+def smart_tokenize(text: str) -> list:
+    tokens = word_tokenize(text.strip(), engine="newmm")
+    if not tokens or len("".join(tokens)) < len(text.strip()) * 0.5:
+        return [text.strip()]
+    return tokens
+
+def correct_query_merge_phrases(query: str, whitelist, threshold=80, max_ngram=3):
+    query_norm = normalize(query)
+    tokens = smart_tokenize(query_norm)
+    corrected = []
+    i = 0
+
+    while i < len(tokens):
+        matched = False
+        for n in range(min(max_ngram, len(tokens) - i), 0, -1):
+            phrase = "".join(tokens[i:i+n])
+            match, score, _ = process.extractOne(phrase, whitelist, scorer=fuzz.token_sort_ratio)
+            if score >= threshold:
+                corrected.append(match)
+                i += n
+                matched = True
+                break
+        if not matched:
+            corrected.append(tokens[i])
+            i += 1
+
+    # ✅ ตัดคำที่มีความยาว 1 ตัวอักษรและไม่ได้อยู่ใน whitelist
+    cleaned = [word for word in corrected if len(word) > 1 or word in whitelist]
+    return " ".join(cleaned)
+
 
 # 🌟 Main search function
 def search_product(query, model_name):
@@ -68,7 +98,7 @@ def search_product(query, model_name):
         return "<p>❌ ไม่พบโมเดล</p>"
 
     latest_query_result["raw_query"] = query
-    corrected_query = normalize(query)
+    corrected_query = correct_query_merge_phrases(query,keyword_whitelist)
 
     query_embed = model_config[model_name]["func"](corrected_query)
     collection_name = model_config[model_name]["collection"]