Add configurable course prefix handling

README.md

@@ -106,9 +106,11 @@ usage: python3 -m syncmymoodle [-h] [--secretservice] [--secretservicetotpsecret
                                [--config CONFIG] [--cookiefile COOKIEFILE]
                                [--courses COURSES] [--skipcourses SKIPCOURSES]
                                [--semester SEMESTER] [--basedir BASEDIR]
-                               [--nolinks]
+                               [--courseprefix {keep,remove,suffix}] [--nolinks]
                                [--excludefiletypes EXCLUDEFILETYPES]
-                               [--updatefiles] [-v]
+                               [--updatefiles]
+                               [--updatefilesconflict {rename,keep,overwrite}]
+                               [-v]
 
 Synchronization client for RWTH Moodle. All optional arguments override those
 in config.json.
@@ -139,6 +141,9 @@ options:
                         separated. Defaults to all semesters, if no additional
                         restrictions e.g. courses are defined.
   --basedir BASEDIR     specify the directory where all files will be synced
+  --courseprefix {keep,remove,suffix}
+                        handle leading two-character course prefixes in local
+                        folder names: 'keep' (default), 'remove', or 'suffix'
   --nolinks             define whether various links in moodle pages should
                         also be inspected e.g. youtube videos, wikipedia
                         articles
@@ -173,6 +178,7 @@ configuration does:
     "totp": "", // RWTH SSO TOTP "Serial Number", format: TOTP0000000A, see https://idm.rwth-aachen.de/selfservice/MFATokenManager
     "totpsecret": "", // The TOTP Secret for your TOTP generator (optional)
     "basedir": "./", // The base directory where all your files will be synced to
+    "course_prefix_handling": "suffix", // How to handle local course folders starting with a two-character prefix like "(VO) ": "keep" (backwards-compatible default), "remove", or "suffix" (recommended)
     "cookie_file": "./session", // The location of the session/cookie file, which can be used instead of a password.
     "use_secret_service": false, // Use the system keyring (see README), instead of a password.
     "secret_service_store_totp_secret": false, // Store the TOTP secret in the system keyring.
@@ -199,6 +205,15 @@ configuration does:
 }
 ```
 
+`course_prefix_handling` controls local course folder names that start with a
+prefix of exactly two characters in parentheses, followed by a space. For
+example, `(VO) Analysis` stays unchanged with `keep`, becomes `Analysis` with
+`remove`, and becomes `Analysis (VO)` with `suffix`. If not set, the default
+is `keep` for backwards compatibility, however `suffix` is recommended.
+`remove` can create folder-name conflicts when multiple course types share
+the same title; syncMyMoodle resolves those by adding a stable suffix to the
+conflicting folders.
+
 `exclude_sections` skips complete Moodle course sections, i.e. top-level
 topic/week blocks such as `General`, `Week 1` or `Exercise Sheets`. Matching a
 section skips all modules, files and links inside it.

config.json.example

@@ -7,6 +7,7 @@
     "totp": "",
     "totpsecret": "",
     "basedir": "./",
+    "course_prefix_handling": "suffix",
     "cookie_file": "./session",
     "use_secret_service": false,
     "secret_service_store_totp_secret": false,

syncmymoodle/__main__.py

@@ -58,6 +58,8 @@
     "statuslabel_wartung",
     "statuslabel_warnung",
 }
+COURSE_PREFIX_RE = re.compile(r"^\((?P<prefix>[^()]{2})\) +(?P<course_name>.+)$")
+COURSE_PREFIX_HANDLING_OPTIONS = ("keep", "remove", "suffix")
 
 logger = logging.getLogger(__name__)
 
@@ -230,7 +232,10 @@ def remove_children_nameclashes(self):
             self.children.remove(child)
             unclashed_children.append(child)
             siblings = [
-                c for c in self.children if c.name == child.name and c.url != child.url
+                c
+                for c in self.children
+                if c.name == child.name
+                and (c.url != child.url or c.name_clash_id != child.name_clash_id)
             ]
             if len(siblings) > 0:
                 # if a filename is still duplicate in its directory, we rename it by appending its id (urlsafe base64 so it also works for urls).
@@ -646,6 +651,27 @@ def _configured_patterns(self, *keys, course_id=None):
                 patterns.extend(self._as_list(value))
         return [str(pattern) for pattern in patterns if pattern is not None]
 
+    def _format_course_name(self, course_name):
+        prefix_handling = self.config.get("course_prefix_handling", "keep")
+        if prefix_handling == "keep":
+            return course_name
+        if prefix_handling not in COURSE_PREFIX_HANDLING_OPTIONS:
+            logger.warning(
+                "Unsupported course_prefix_handling value %r; using keep",
+                prefix_handling,
+            )
+            return course_name
+
+        match = COURSE_PREFIX_RE.match(course_name)
+        if not match:
+            return course_name
+
+        name = match.group("course_name")
+        prefix = match.group("prefix")
+        if prefix_handling == "remove":
+            return name
+        return f"{name} ({prefix})"
+
     def _matches_any_pattern(self, values, patterns):
         for value in values:
             if value is None:
@@ -1339,7 +1365,7 @@ def sync(self):
 
         # Syncing all courses
         for course in self.get_all_courses():
-            course_name = course["shortname"]
+            course_name = self._format_course_name(course["shortname"])
             course_id = course["id"]
 
             if (
@@ -2809,6 +2835,15 @@ def main():
         default=None,
         help="specify the directory where all files will be synced",
     )
+    parser.add_argument(
+        "--courseprefix",
+        choices=COURSE_PREFIX_HANDLING_OPTIONS,
+        default=None,
+        help=(
+            "handle leading two-character course prefixes in local folder names: "
+            "'keep' (default), 'remove', or 'suffix'"
+        ),
+    )
     parser.add_argument(
         "--nolinks",
         action="store_true",
@@ -2881,6 +2916,9 @@ def main():
         else config.get("only_sync_semester", [])
     )
     config["basedir"] = args.basedir or config.get("basedir", "./")
+    config["course_prefix_handling"] = args.courseprefix or config.get(
+        "course_prefix_handling", "keep"
+    )
     config["use_secret_service"] = (
         args.secretservice if keyring else None
     ) or config.get("use_secret_service")

tests/test_course_prefix_handling.py

@@ -0,0 +1,89 @@
+import unittest
+
+from syncmymoodle.__main__ import Node, SyncMyMoodle
+
+
+class CoursePrefixHandlingTest(unittest.TestCase):
+    def format_course_name(self, handling, name):
+        smm = SyncMyMoodle({"course_prefix_handling": handling})
+        return smm._format_course_name(name)
+
+    def test_keep_preserves_course_name(self):
+        self.assertEqual(
+            self.format_course_name("keep", "(VO) Analysis"),
+            "(VO) Analysis",
+        )
+
+    def test_remove_strips_two_character_prefix(self):
+        self.assertEqual(
+            self.format_course_name("remove", "(VO) Analysis"),
+            "Analysis",
+        )
+
+    def test_suffix_moves_two_character_prefix_to_end(self):
+        self.assertEqual(
+            self.format_course_name("suffix", "(VU) Software Quality Assurance"),
+            "Software Quality Assurance (VU)",
+        )
+
+    def test_other_two_character_prefixes_are_supported(self):
+        self.assertEqual(
+            self.format_course_name("suffix", "(RE) Exercise Session"),
+            "Exercise Session (RE)",
+        )
+
+    def test_non_matching_names_are_preserved(self):
+        self.assertEqual(self.format_course_name("remove", "Analysis"), "Analysis")
+        self.assertEqual(
+            self.format_course_name("remove", "(VO)Analysis"), "(VO)Analysis"
+        )
+        self.assertEqual(
+            self.format_course_name("remove", "(V) Analysis"), "(V) Analysis"
+        )
+        self.assertEqual(
+            self.format_course_name("remove", "(ABC) Analysis"),
+            "(ABC) Analysis",
+        )
+
+    def test_invalid_mode_preserves_course_name(self):
+        with self.assertLogs("syncmymoodle.__main__", level="WARNING"):
+            self.assertEqual(
+                self.format_course_name("invalid", "(VO) Analysis"),
+                "(VO) Analysis",
+            )
+
+
+class CourseNameClashTest(unittest.TestCase):
+    def test_same_course_folder_name_without_url_gets_stable_suffixes(self):
+        root = Node("", -1, "Root", None)
+        semester = root.add_child("26ss", None, "Semester")
+        semester.add_child("Software Quality Assurance", 101, "Course")
+        semester.add_child("Software Quality Assurance", 102, "Course")
+
+        root.remove_children_nameclashes()
+
+        names = [course.name for course in semester.children]
+        self.assertEqual(len(names), 2)
+        self.assertEqual(len(set(names)), 2)
+        self.assertNotIn("Software Quality Assurance", names)
+        for name in names:
+            self.assertTrue(name.startswith("Software Quality Assurance_"))
+
+    def test_same_name_with_different_urls_still_gets_stable_suffixes(self):
+        root = Node("", -1, "Root", None)
+        section = root.add_child("General", None, "Section")
+        section.add_child("Slides", 201, "URL", url="https://example.com/slides-a")
+        section.add_child("Slides", 202, "URL", url="https://example.com/slides-b")
+
+        root.remove_children_nameclashes()
+
+        names = [link.name for link in section.children]
+        self.assertEqual(len(names), 2)
+        self.assertEqual(len(set(names)), 2)
+        self.assertNotIn("Slides", names)
+        for name in names:
+            self.assertTrue(name.startswith("Slides_"))
+
+
+if __name__ == "__main__":
+    unittest.main()