report on reg changes

pipelines.py

@@ -1130,6 +1130,64 @@ def get_doc_generic(docid, bracket=1, verbose=0):
 
 
 
+def process_reg_history():
+    from collections import defaultdict
+    from itertools import groupby
+    from operator import itemgetter
+
+    def read_grouped_csv(path):
+        with open(path, newline='') as f:
+            fieldnames = ['datetime', 'crn', 'course', 'teacher', 'max', 'enrolled', 'waitlistmax', 'waitlisted']
+            reader = csv.DictReader(f, fieldnames=fieldnames)
+            rows = sorted(reader, key=lambda r: r['datetime'])        # Group by timestamp
+        grouped = {}
+        for ts, group in groupby(rows, key=itemgetter('datetime')):
+            grouped[ts] = {r['crn']: r for r in group}
+        return grouped
+
+    def detect_changes(prev, curr):
+        changes = defaultdict(list)
+
+        all_crns = prev.keys() | curr.keys()
+        for crn in all_crns:
+            o, n = prev.get(crn), curr.get(crn)
+            if not o:
+                changes[crn].append("Section was added.")
+            elif not n:
+                changes[crn].append("Section was removed.")
+            else:
+                if o['teacher'] != n['teacher']:
+                    changes[crn].append(f"Changed teacher to {n['teacher']}.")
+                if o['enrolled'] != n['enrolled']:
+                    if int(n['enrolled']) >= int(n.get('max', 9999)):
+                        changes[crn].append("Filled up.")
+                    else:
+                        changes[crn].append(f"Enrollment changed to {n['enrolled']}.")
+                if int(n.get('waitlisted', 0)) > 10 and o['waitlisted'] != n['waitlisted']:
+                    changes[crn].append(f"Waitlist exceeds 10: {n['waitlisted']}.")
+        return changes
+
+    def process_diff_timeline(path):
+        snapshots = read_grouped_csv(path)
+        timeline = sorted(snapshots.keys())
+        reports = []
+
+        for i in range(1, len(timeline)):
+            prev_ts, curr_ts = timeline[i-1], timeline[i]
+            prev, curr = snapshots[prev_ts], snapshots[curr_ts]
+            delta = detect_changes(prev, curr)
+            if delta:
+                reports.append((curr_ts, delta))
+        return reports
+
+    result = process_diff_timeline("cache/reg_history_fa25.csv")
+    for timestamp, changes in result:
+        print(f"\n[{timestamp}]")
+        for crn, msgs in sorted(changes.items()):
+            print(f"  CRN {crn}:")
+            for msg in msgs:
+                print(f"    - {msg}")    
+
 
 
 if __name__ == "__main__":
@@ -1138,6 +1196,7 @@ if __name__ == "__main__":
     options = { 1: ['Fetch rosters on schedule',fetch_current_rosters_auto] ,  
                 2: ['Get canvas data 2024 style', canvas_data_2024_run ],
                 3: ['Set up canvas data 2024 style', setup_canvas_data_2024_run],
+                4: ['Narrative timeline of section updates', process_reg_history],
     }
         
     '''1: ['Re-create schedule csv and json files from raw html',recent_schedules] ,