realist: refactor, lowercase

flake.nix

@@ -9,7 +9,7 @@
       let pkgs = nixpkgs.legacyPackages.${system};
       in rec {
         packages = import ./default.nix { inherit pkgs; };
-        apps.xls-to-csv = flake-utils.lib.mkApp { drv = packages.ut3_survival; exePath = "/bin/xls-to-csv"; };
+        apps.realist-students-xls2csv = flake-utils.lib.mkApp { drv = packages.ut3_survival; exePath = "/bin/realist-students-xls2csv"; };
         defaultPackage = packages.ut3_survival;
       }
     );

pyproject.toml

@@ -28,4 +28,4 @@ dependencies = [
 ]
 
 [project.scripts]
-xls-to-csv = "ut3_survival.cmd.xls_to_csv:main"
+realist-students-xls2csv = "ut3_survival.cmd.realist_students_xls_to_csv:main"

ut3_survival/cmd/xls_to_csv.py → ut3_survival/cmd/realist_students_xls_to_csv.py

@@ -9,8 +9,9 @@ from ut3_survival import realist
 @click.command()
 @click.argument('xls_file', required=True, nargs=-1)
 @click.option('-o', '--output', default=None, help='If set, parsed students are written as CSV to this file.')
-def main(xls_file, output):
-    students = realist.read_parse_several_xls(xls_file)
+@click.option('--lower', is_flag=True, show_default=True, default=False, help='Sets text data to lowercase.')
+def main(xls_file, output, lower):
+    students = realist.read_parse_several_xls(xls_file, lower)
 
     output_file = sys.stdout
     if output is not None:

ut3_survival/realist.py

@@ -12,34 +12,51 @@ import xlrd
 student_columns = ['id', 'lastname', 'firstname', 'email', 'group']
 StudentEntry = namedtuple('StudentEntry', student_columns)
 
-def read_parse_xls(xls_filename: str) -> [StudentEntry]:
+def read_parse_xls(xls_filename: str, lower: bool=None) -> [StudentEntry]:
     '''Read and parse a XLS file into a list of students.'''
+    set_lowercase = False
+    if lower is not None:
+        if not isinstance(lower, bool):
+            raise TypeError(f'lower is not a bool (type=type{type(lower)})')
+        set_lowercase = lower
+
     students_xls = xlrd.open_workbook(xls_filename, logfile=sys.stderr)
     group_names = students_xls.sheet_names()
     group_names.pop(0) # first XLS sheet is useless
-    students = []
 
+    students = []
     for group_name in group_names:
         sheet = students_xls.sheet_by_name(group_name)
         if sheet.cell_value(1,0) != "GROUPE : " + group_name:
             raise AssertionError("SGCE's xls format has changed")
 
         for row in range(3, sheet.nrows):
-            students.append(StudentEntry(
+            entry = StudentEntry(
                 id=sheet.cell_value(row,0),
                 lastname=sheet.cell_value(row,1),
                 firstname=sheet.cell_value(row,2),
                 email=sheet.cell_value(row,3),
                 group=group_name,
-            ))
+            )
+
+            if set_lowercase:
+                entry = StudentEntry(
+                    id=entry.id,
+                    lastname=entry.lastname.lower(),
+                    firstname=entry.firstname.lower(),
+                    email=entry.email.lower(),
+                    group=entry.group.lower(),
+                )
+
+            students.append(entry)
     return students
 
-def read_parse_several_xls(xls_filenames: [str]) -> [StudentEntry]:
+def read_parse_several_xls(xls_filenames: [str], lower: bool=None) -> [StudentEntry]:
     '''read_parse_xls wrapper when several files are to be used.'''
     all_students = []
     for xls_filename in xls_filenames:
         try:
-            students = read_parse_xls(xls_filename)
+            students = read_parse_xls(xls_filename, lower)
             all_students.extend(students)
         except Exception as exception:
             raise RuntimeError(f"could not read/parse xls file '{xls_filename}'") from exception