remove hard coded file name. update readme

cleanup-roster.py

@@ -5,9 +5,9 @@
 
 def     is_hot_major(m, checksecond = False):
     if checksecond:
+        # some records are appended " as Second" and some " Second"
         if not m.endswith("Second"):
             return ""
-        m = m[-10:]
 
     if m.startswith("Computer Science & Engineering"):
         major = "CSE"
@@ -24,8 +24,9 @@ def     is_hot_major(m, checksecond = False):
     return major
 
 def     get_major_from_program(prog):
-    m = re.findall(r"[-/]([^/]+)", prog)
+    m = re.findall(r"(?: -|/)([^/]+)", prog)
 
+    print(m)
     assert len(m) > 0
 
     major = is_hot_major(m[0])
@@ -68,6 +69,7 @@ def     add_header(self, line):
 
     def     add(self, line):
         # replace & 
+        logging.debug(line)
         line1 = re.sub(r"&", "&", line)
         # remove br tag
         # s = re.sub(r"<br\s*/>", "", s)
@@ -134,7 +136,7 @@ def     is_tr(s):
 def     is_end_of_row(s):
     return s.startswith('<tr>') or s.startswith('</table>')
 
-parser = argparse.ArgumentParser(description='Clean up downloaded roster from HuskyCT')
+parser = argparse.ArgumentParser(description='Clean up downloaded roster from HuskyCT. Nov 2022.')
 parser.add_argument('infiles', nargs='*', default=[], help='Input files.')
 parser.add_argument('-o', nargs='?', default='', const='', help='Output file.')
 parser.add_argument('-f', nargs='+', default=[], help='Add the list of fields to the default list')
@@ -155,8 +157,7 @@ def     is_end_of_row(s):
 state = State.START
 row = ''
 try:
-#    for line in fileinput.input(args.infiles):
-    for line in fileinput.input("ps.xls"):
+    for line in fileinput.input(args.infiles):
         # remove spaces at the end of the line, including newline
         line = line.rstrip()
 

readme.MD

@@ -46,3 +46,22 @@ cat *.xls | py cleanup-roster.py -o all.csv
 # save student records in separate csv files
 dir *.xls | foreach { py cleanup-roster.py $_ -o ($_.name -replace '.xls','.csv') }
 ```
+
+## Notes
+
+### Nov 2022
+
+The format of downloaded files keeps changing, mainly in "Program and Plan" field. 
+The format in Nov 2022 is:
+
+    <school> - <\r><major>
+    <school> - <\r><major>/<minor>
+    <school> - <\r><major>/<minor1/>/<minor2>
+    <school> - <\r><major>/<major2> as Second
+    <school> - <\r><major>/<major2> Second
+
+The school can be :
+
+    Engineering
+    Liberal Arts & Sciences
+    CCS Non-Degree