more data

controller/template_controller.py

@@ -49,8 +49,25 @@ def _read_csv(relative_path):
         return list(csv.DictReader(f))
 
 
+def _to_int(value, default=0):
+    try:
+        return int(float(value))
+    except (TypeError, ValueError):
+        return default
+
+
 def load_data():
-    """Loads all dummy CSVs into plain dict/list structures."""
+    """
+    Loads the real UORM CSV data into plain dict/list structures.
+
+    courses/courses.csv is the full course catalog in the university's
+    wide export format (Department_Name, Program_Name, Course_Code,
+    T_Contact_Hours, P_Contact_Hours, ...). courses/course_offering.csv is
+    a curated subset of that catalog — only rows with an instructor
+    assigned there are schedulable. Course rows are looked up by
+    Course_Code (e.g. "BBA-300"), which is what course_offering.csv's
+    course_id column refers to.
+    """
     rooms = _read_csv(os.path.join("blocks", "rooms.csv"))
     blocks = _read_csv(os.path.join("blocks", "blocks.csv"))
     instructors = _read_csv(os.path.join("instructor", "instructors.csv"))
@@ -65,22 +82,51 @@ def load_data():
     instructor_names_by_code = {i["instructor_code"]: i["instructor_name"] for i in instructors}
     batches_by_code = {b["batch_code"]: b for b in batches}
 
-    # normalize courses: numeric fields + a lookup by id
+    # normalize courses: derive scheduler fields from the real catalog's
+    # contact-hour columns, and key by Course_Code (what offerings reference).
     courses_by_id = {}
     for c in courses:
-        c["credit_hours"] = int(c["credit_hours"])
-        c["lectures_per_week"] = int(c["lectures_per_week"])
-        c["labs_per_week"] = int(c["labs_per_week"])
-        c["is_general"] = c["is_general"].lower() == "yes"
-        c["lecture_duration_minutes"] = int(c.get("lecture_duration_minutes") or 90)
-        courses_by_id[c["course_id"]] = c
+        course_code = c["Course_Code"].strip()
+        t_contact_hours = _to_int(c.get("T_Contact_Hours"))
+        p_contact_hours = _to_int(c.get("P_Contact_Hours"))
+        courses_by_id[course_code] = {
+            "course_id": course_code,
+            "course_name": c["Course_Title"].strip(),
+            "department": c["Department_Name"],
+            "program": c["Program_Name"],
+            "credit_hours": _to_int(c.get("Total_Credit_Hours")),
+            # One 90-minute lecture slot per weekly theory contact hour;
+            # no reliable "general" flag exists in this data, so every
+            # course is treated as non-general (see solver/phase1_general.py).
+            "lectures_per_week": t_contact_hours,
+            # A course with any practical/lab contact hours gets exactly
+            # one 180-minute lab session/week (never more), per spec.
+            "labs_per_week": 1 if p_contact_hours > 0 else 0,
+            "is_general": False,
+            "lecture_duration_minutes": 90,
+            # No per-course room assignment in this data yet; leaving
+            # these unset makes room_candidates() fall back to the full
+            # room pool with no preference (handled by PlacementBoard).
+            "lecture_room_id": None,
+            "lab_room_id": None,
+        }
 
     # normalize offerings: expand "batch1|batch2" section batch groups into
-    # a list of batch codes, and attach the course record for convenience
+    # a list of batch codes (kept for forward compatibility even though
+    # this real data has one batch per offering), and attach the course
+    # record for convenience. Offerings whose course_id has no matching
+    # catalog row are skipped (curated subset referencing a typo/removed
+    # course) rather than crashing the whole load.
+    normalized_offerings = []
     for off in offerings:
+        course = courses_by_id.get(off["course_id"])
+        if course is None:
+            print(f"WARNING: course_offering.csv references unknown course_id '{off['course_id']}' — skipping")
+            continue
         off["batch_codes"] = off["batch_codes"].split("|")
-        off["course"] = courses_by_id[off["course_id"]]
+        off["course"] = course
         off["instructor_name"] = instructor_names_by_code.get(off["instructor_code"], off["instructor_code"])
+        normalized_offerings.append(off)
 
     return {
         "rooms": rooms,
@@ -90,7 +136,7 @@ def load_data():
         "instructor_names_by_code": instructor_names_by_code,
         "courses": courses,
         "courses_by_id": courses_by_id,
-        "offerings": offerings,
+        "offerings": normalized_offerings,
         "students": students,
         "batches": batches,
         "batches_by_code": batches_by_code,