From 9a382669e5b161e21c16507a2a2a2454235b6b82 Mon Sep 17 00:00:00 2001
From: Jason Park <joonbin0319@gmail.com>
Date: Mon, 12 Jun 2023 22:20:41 +0900
Subject: [PATCH] feat: adding case 3 for merging period and location for
 exceptions

---
 lib/configs/event/schedule.ts          |  2 +-
 src/lambda/syllabus-scraper/const.py   |  2 +-
 src/lambda/syllabus-scraper/crawler.py |  2 ++
 src/lambda/syllabus-scraper/utils.py   | 37 ++++++++++++++------------
 4 files changed, 24 insertions(+), 19 deletions(-)

diff --git a/lib/configs/event/schedule.ts b/lib/configs/event/schedule.ts
index 58ac75882..d71b76f2d 100644
--- a/lib/configs/event/schedule.ts
+++ b/lib/configs/event/schedule.ts
@@ -4,7 +4,7 @@ export const syllabusSchedule: { [name: string]: events.Schedule } = {
   'regular': events.Schedule.cron({
     minute: '0',
     hour: '16',
-    day: '1,2',
+    day: '1,12',
     month: '*',
     year: '*',
   }),
diff --git a/src/lambda/syllabus-scraper/const.py b/src/lambda/syllabus-scraper/const.py
index 3afbdf6d6..d4dbd31be 100644
--- a/src/lambda/syllabus-scraper/const.py
+++ b/src/lambda/syllabus-scraper/const.py
@@ -237,6 +237,6 @@
 
 cron_schedule = ["01-01", "02-01", "02-14", "02-24", "03-01", "03-04", "03-07", "03-10", "03-16", "03-18", "03-21",
                  "03-24", "03-27", "04-01", "04-03", "04-05", "04-08", "04-16", "04-20", "04-24", "04-26", "04-28",
-                 "05-01", "05-09", "05-12", "05-14", "05-16", "06-01", "06-02", "07-01", "07-19", "07-21", "07-23", "08-01",
+                 "05-01", "05-09", "05-12", "05-14", "05-16", "06-01", "06-12", "07-01", "07-19", "07-21", "07-23", "08-01",
                  "08-19", "08-21", "08-23", "09-01", "09-04", "09-07", "09-10", "09-13", "09-15", "09-17", "09-20",
                  "09-23", "09-25", "09-28", "09-30", "10-01", "10-03", "10-05", "10-08", "11-01", "12-01"]
diff --git a/src/lambda/syllabus-scraper/crawler.py b/src/lambda/syllabus-scraper/crawler.py
index 78a3e8def..94f440467 100644
--- a/src/lambda/syllabus-scraper/crawler.py
+++ b/src/lambda/syllabus-scraper/crawler.py
@@ -85,6 +85,8 @@ def scrape_course(self, course_id):
                 "n": 'array', # eval
                 "o": 'string', # code
                 "p": 'string', # subtitle
+                "q": 'string', #category
+                "r": 'string', #modality
             }
         """
         req_en = requests.Request(url=build_url(
diff --git a/src/lambda/syllabus-scraper/utils.py b/src/lambda/syllabus-scraper/utils.py
index 639b0222d..e58d3a6ac 100644
--- a/src/lambda/syllabus-scraper/utils.py
+++ b/src/lambda/syllabus-scraper/utils.py
@@ -149,24 +149,27 @@ def merge_period_location(periods, locations):
         for p in periods:
             p["l"] = locations[0]
         return periods
-    # TODO find other cases
-    # Case 2: multiple periods and multiple locations string divided with a '/'
-    elif len(periods) == len(locations):
-        for i in range(len(periods)):
-            locs = locations[i].split('/')
-            temp_period = periods[i]
-            for loc in locs:
-                temp_period_copy = temp_period.copy()
-                temp_period_copy["l"] = loc.strip()
-                occurrences.append(temp_period_copy)
-        return occurrences
-
-    # Case 3: More no. of periods than no. of locations
-    else:
-        zipped = list(itertools.zip_longest(periods, locations))
-        for (p, loc) in zipped:
+    # Case 2: More no. of periods than no. of locations
+    zipped = list(itertools.zip_longest(periods, locations))
+    for (p, loc) in zipped:
+        if p is None:
+            logging.error(f"Unexpected None in periods. loc={loc}")
+            continue
+
+        if loc is not None:
             p["l"] = loc
-            occurrences.append(p)
+        else:
+            logging.warning(
+                f"Missing location for period {p}. Assigning default value.")
+            p["l"] = "undecided"
+
+        occurrences.append(p)
+
+    # Case 3: Logging error for unusual scenarios
+    if not occurrences:
+        logging.error(
+            f"merge_period_location resulted in no occurrences for input periods={periods}, locations={locations}")
+
     return occurrences