F fix url formatting

Summary

Part of https://gitlab.indiscale.com/caosdb/customers/geomar/management/-/issues/302. Use urllib.parse.join instead of string concatenation for link generation.

Focus

Nothing new, just use built-in functions to prevent missing or extra / and the like.

Test Environment

Run with Geomar server profile, set crawler in profile.yml to this branch, upload some samples and look into the sendmail_to_file output in /tmp/mail to verify that the URIs are generated correctly.

Also, new unit test.

Check List for the Author

Please, prepare your MR for a review. Be sure to write a summary and a focus and create gitlab comments for the reviewer. They should guide the reviewer through the changes, explain your changes and also point out open questions. For further good practices have a look at our review guidelines

• All automated tests pass
• Reference related issues
• Up-to-date CHANGELOG.md (or not necessary)
• Up-to-date JSON schema (or not necessary)
• Appropriate user and developer documentation (or not necessary)
  • How do I use the software? Assume "stupid" users.
  • How do I develop or debug the software? Assume novice developers.
• Annotations in code (Gitlab comments)
  • Intent of new code
  • Problems with old code
  • Why this implementation?

Check List for the Reviewer

• I understand the intent of this MR
• All automated tests pass
• Up-to-date CHANGELOG.md (or not necessary)
• Appropriate user and developer documentation (or not necessary)
• The test environment setup works and the intended behavior is reproducible in the test environment
• In-code documentation and comments are up-to-date.
• Check: Are there specifications? Are they satisfied?

For further good practices have a look at our review guidelines.

src/caoscrawler/crawl.py

@@ -39,6 +39,7 @@ import sys
 import traceback
 import uuid
 import warnings
+
 from argparse import RawTextHelpFormatter
 from copy import deepcopy
 from datetime import datetime
@@ -72,6 +73,7 @@ from .scanner import (create_converter_registry, initialize_converters,
 from .stores import GeneralStore
 from .structure_elements import StructureElement
 from .sync_graph import SyncGraph
+from .utils import get_shared_resource_link
 
 logger = logging.getLogger(__name__)
 
@@ -750,16 +752,17 @@ one with the entities that need to be updated and the other with entities to be
         # Sending an Email with a link to a form to authorize updates is
         if get_config_setting("send_crawler_notifications"):
             filename = OldCrawler.save_form([el[3] for el in pending_changes], path, run_id)
-            text = """Dear Curator,
+            link_address = get_shared_resource_link(db.configuration.get_config()[
+                                                    "Connection"]["url"], filename)
+            changes = "\n".join([el[3] for el in pending_changes])
+            text = f"""Dear Curator,
     there where changes that need your authorization. Please check the following
     carefully and if the changes are ok, click on the following link:
 
-    {url}/Shared/{filename}
+    {link_address}
 
     {changes}
-            """.format(url=db.configuration.get_config()["Connection"]["url"],
-                       filename=filename,
-                       changes="\n".join([el[3] for el in pending_changes]))
+            """
             try:
                 fro = get_config_setting("sendmail_from_address")
                 to = get_config_setting("sendmail_to_address")
@@ -899,7 +902,7 @@ the CaosDB Crawler successfully crawled the data and
     if get_config_setting("create_crawler_status_records"):
         text += ("You can checkout the CrawlerRun Record for more information:\n"
                  f"{domain}/Entity/?P=0L10&query=find%20crawlerrun%20with%20run_id=%27{run_id}%27\n\n")
-    text += (f"You can download the logfile here:\n{domain}/Shared/" + logfile)
+    text += (f"You can download the logfile here:\n{get_shared_resource_link(domain, logfile)}")
     send_mail(
         from_addr=get_config_setting("sendmail_from_address"),
         to=get_config_setting("sendmail_to_address"),
@@ -1059,7 +1062,7 @@ def crawler_main(crawled_directory_path: str,
             userlog_public, htmluserlog_public, debuglog_public = configure_server_side_logging()
             # TODO make this optional
             _create_status_record(
-                get_config_setting("public_host_url") + "/Shared/" + htmluserlog_public,
+                get_shared_resource_link(get_config_setting("public_host_url"), htmluserlog_public),
                 crawler.run_id)
         else:  # setup stdout logging for other cases
             root_logger = logging.getLogger()
@@ -1128,7 +1131,7 @@ def crawler_main(crawled_directory_path: str,
             # pylint: disable=E0601
             domain = get_config_setting("public_host_url")
             logger.error("Unexpected Error: Please tell your administrator about this and provide "
-                         f"the following path.\n{domain}/Shared/" + debuglog_public)
+                         f"the following path.\n{get_shared_resource_link(domain, debuglog_public)}")
         _update_status_record(crawler.run_id, 0, 0, status="FAILED")
         return 1