merge skills

services/processor_utils.py

@@ -2506,6 +2506,7 @@ _CATEGORY_TITLE_KEYWORDS: Dict[str, List[str]] = {
         "cashier",
         "receptionist",
         "clerk",
+        "secretary",
     ],
     "Software Engineering": [
         "developer",
@@ -2528,6 +2529,7 @@ _CATEGORY_TITLE_KEYWORDS: Dict[str, List[str]] = {
         "sysadmin",
         "it administrator",
         "cloud engineer",
+        "platform engineer",
     ],
     "Cybersecurity": [
         "security",
@@ -2537,6 +2539,7 @@ _CATEGORY_TITLE_KEYWORDS: Dict[str, List[str]] = {
         "soc analyst",
         "penetration tester",
         "ethical hacker",
+        "information security",
     ],
     "Design & Creative": [
         "designer",
@@ -2547,6 +2550,7 @@ _CATEGORY_TITLE_KEYWORDS: Dict[str, List[str]] = {
         "visual",
         "illustrator",
         "photographer",
+        "art director",
     ],
     "Marketing & Growth": [
         "marketing",
@@ -2556,6 +2560,7 @@ _CATEGORY_TITLE_KEYWORDS: Dict[str, List[str]] = {
         "growth",
         "digital",
         "brand",
+        "communications",
     ],
     "Data & Analytics": [
         "data analyst",
@@ -2572,6 +2577,7 @@ _CATEGORY_TITLE_KEYWORDS: Dict[str, List[str]] = {
         "data pipeline",
         "data architect",
         "analytics engineer",
+        "data platform",
     ],
     "Finance & Accounting": [
         "accountant",
@@ -2599,6 +2605,7 @@ _CATEGORY_TITLE_KEYWORDS: Dict[str, List[str]] = {
         "account manager",
         "sales executive",
         "representative",
+        "business dev",
     ],
     "Healthcare": [
         "nurse",
@@ -2610,6 +2617,7 @@ _CATEGORY_TITLE_KEYWORDS: Dict[str, List[str]] = {
         "health",
         "therapist",
         "midwife",
+        "radiographer",
     ],
     "Legal": [
         "legal",
@@ -2638,6 +2646,7 @@ _CATEGORY_TITLE_KEYWORDS: Dict[str, List[str]] = {
         "fleet",
         "warehouse manager",
         "quality",
+        "planner",
     ],
     "Customer Support": [
         "customer support",
@@ -2645,6 +2654,7 @@ _CATEGORY_TITLE_KEYWORDS: Dict[str, List[str]] = {
         "call centre",
         "contact centre",
         "customer care",
+        "service desk",
     ],
     "Construction & Engineering": [
         "civil",
@@ -2654,6 +2664,7 @@ _CATEGORY_TITLE_KEYWORDS: Dict[str, List[str]] = {
         "quantity surveyor",
         "site engineer",
         "construction",
+        "autocad",
     ],
     "Hospitality & Property": [
         "hotel",
@@ -2663,9 +2674,31 @@ _CATEGORY_TITLE_KEYWORDS: Dict[str, List[str]] = {
         "housekeeping",
         "f&b",
         "restaurant",
+        "events",
     ],
 }
 
+_CATEGORY_ORDER = (
+    "Admin & Office",
+    "Construction & Engineering",
+    "Customer Support",
+    "Cybersecurity",
+    "Data & Analytics",
+    "Data Engineering",
+    "Design & Creative",
+    "Education & Training",
+    "Finance & Accounting",
+    "Healthcare",
+    "Hospitality & Property",
+    "Human Resources",
+    "Infrastructure & Cloud",
+    "Legal",
+    "Marketing & Growth",
+    "Operations & Logistics",
+    "Sales & Business Dev",
+    "Software Engineering",
+)
+
 
 def _infer_category(
     text: str,
@@ -2676,7 +2709,10 @@ def _infer_category(
         category_skills = DEFAULT_CATEGORY_SKILLS
     text_norm = _normalize(text)
     best, best_score = "Other", 0.0
-    for cat, cat_skills in category_skills.items():
+    category_order = [cat for cat in _CATEGORY_ORDER if cat in category_skills]
+    category_order.extend(cat for cat in category_skills if cat not in _CATEGORY_ORDER)
+    for cat in category_order:
+        cat_skills = category_skills[cat]
         skill_overlap = len(skills & cat_skills)
         kw_hits = sum(
             1 for kw in _CATEGORY_TITLE_KEYWORDS.get(cat, []) if kw in text_norm