fix: make usage of name and slug consistent

renku/command/checks/datasets.py

@@ -77,17 +77,17 @@ def check_missing_files(dataset_gateway: IDatasetGateway, **_):
             path = project_context.path / file_.entity.path
             file_exists = path.exists() or (file_.is_external and os.path.lexists(path))
             if not file_exists:
-                missing[dataset.name].append(file_.entity.path)
+                missing[dataset.slug].append(file_.entity.path)
 
     if not missing:
         return True, False, None
 
     problems = WARNING + "There are missing files in datasets."
 
-    for dataset_name, files in missing.items():
+    for dataset_slug, files in missing.items():
         problems += (
             "\n\t"
-            + click.style(dataset_name, fg="yellow")
+            + click.style(dataset_slug, fg="yellow")
             + ":\n\t  "
             + "\n\t  ".join(click.style(path, fg="red") for path in files)
         )
@@ -114,9 +114,9 @@ def fix_or_report(dataset):
             dataset.unfreeze()
             dataset.derived_from = None
             dataset.freeze()
-            communication.info(f"Fixing dataset '{dataset.name}'")
+            communication.info(f"Fixing dataset '{dataset.slug}'")
         else:
-            invalid_datasets.append(dataset.name)
+            invalid_datasets.append(dataset.slug)
 
     for dataset in dataset_gateway.get_provenance_tails():
         while dataset.derived_from is not None and dataset.derived_from.url_id is not None:
@@ -137,7 +137,7 @@ def fix_or_report(dataset):
         WARNING
         + "There are invalid dataset metadata in the project (use 'renku doctor --fix' to fix them):"
         + "\n\n\t"
-        + "\n\t".join(click.style(name, fg="yellow") for name in invalid_datasets)
+        + "\n\t".join(click.style(slug, fg="yellow") for slug in invalid_datasets)
         + "\n"
     )
 
@@ -177,12 +177,12 @@ def check_dataset_files_outside_datadir(fix, dataset_gateway: IDatasetGateway, *
             continue
 
         if fix:
-            communication.info(f"Fixing dataset '{dataset.name}' files.")
+            communication.info(f"Fixing dataset '{dataset.slug}' files.")
             dataset.unfreeze()
             for file in detected_files:
                 dataset.unlink_file(file.entity.path)
             dataset.freeze()
-            add_to_dataset(dataset.name, urls=[file.entity.path for file in detected_files], link=True)
+            add_to_dataset(dataset.slug, urls=[file.entity.path for file in detected_files], link=True)
         else:
             invalid_files.extend(detected_files)
 
@@ -220,7 +220,7 @@ def check_external_files(fix, dataset_gateway: IDatasetGateway, **_):
         for file in dataset.files:
             if file.is_external:
                 external_files.append(file.entity.path)
-                datasets[dataset.name].append(file)
+                datasets[dataset.slug].append(file)
 
     if not external_files:
         return True, False, None
@@ -240,7 +240,7 @@ def check_external_files(fix, dataset_gateway: IDatasetGateway, **_):
         f"dataset with an external storage backend:\n\t{external_files_str}"
     )
 
-    for name, files in datasets.items():
-        file_unlink(name=name, yes=True, dataset_files=files)
+    for slug, files in datasets.items():
+        file_unlink(slug=slug, yes=True, dataset_files=files)
 
     return True, False, None

renku/command/checks/validate_shacl.py

@@ -104,15 +104,15 @@ def check_datasets_structure(dataset_gateway: IDatasetGateway, **_):
         try:
             conform, graph, t = _check_shacl_structure(data)
         except (Exception, BaseException) as e:
-            problems.append(f"Couldn't validate dataset '{dataset.name}': {e}\n\n")
+            problems.append(f"Couldn't validate dataset '{dataset.slug}': {e}\n\n")
             continue
 
         if conform:
             continue
 
         ok = False
 
-        problems.append(f"{dataset.name}\n\t{_shacl_graph_to_string(graph)}\n")
+        problems.append(f"{dataset.slug}\n\t{_shacl_graph_to_string(graph)}\n")
 
     if ok:
         return True, False, None

renku/command/dataset.py

@@ -1,6 +1,5 @@
-#
-# Copyright 2017-2023 - Swiss Data Science Center (SDSC)
-# A partnership between École Polytechnique Fédérale de Lausanne (EPFL) and
+# Copyright Swiss Data Science Center (SDSC). A partnership between
+# École Polytechnique Fédérale de Lausanne (EPFL) and
 # Eidgenössische Technische Hochschule Zürich (ETHZ).
 #
 # Licensed under the Apache License, Version 2.0 (the "License");
@@ -39,7 +38,7 @@
 
 
 def search_datasets_command():
-    """Command to get all the datasets whose name starts with the given string."""
+    """Command to get all the datasets whose slug starts with the given string."""
     return Command().command(search_datasets).require_migration().with_database()
 
 

renku/command/format/dataset_files.py

@@ -73,7 +73,10 @@ def get_lfs_tracking():
                 record.is_lfs = False
 
     def naturalize(value) -> str:
-        return naturalsize(value).upper().replace("BYTES", " B")
+        try:
+            return naturalsize(value).upper().replace("BYTES", " B")
+        except ValueError:
+            return str(value)
 
     def get_file_sizes():
         if not any(r for r in records if r.size is None):  # All records already have a size
@@ -181,8 +184,8 @@ def json(records, **_):
     "dataset": ("title", "dataset"),
     "full_path": ("full_path", None),
     "path": ("path", None),
-    "short_name": ("dataset_name", "dataset name"),
-    "dataset_name": ("dataset_name", "dataset name"),
+    "short_name": ("dataset_slug", "dataset slug"),
+    "dataset_slug": ("dataset_slug", "dataset slug"),
     "size": ("size", None),
     "lfs": ("is_lfs", "lfs"),
     "source": ("source", None),

renku/command/format/datasets.py

@@ -90,13 +90,14 @@ def json(datasets, **kwargs):
     "id": ("identifier", "id"),
     "created": ("date_created", None),
     "date_created": ("date_created", None),
-    "short_name": ("name", None),
+    "short_name": ("slug", None),
     "name": ("name", None),
+    "slug": ("slug", None),
     "creators": ("creators_csv", "creators"),
     "creators_full": ("creators_full_csv", "creators"),
     "tags": ("tags_csv", "tags"),
     "version": ("version", None),
-    "title": ("title", "title"),
+    "title": ("name", None),
     "keywords": ("keywords_csv", "keywords"),
     "description": ("short_description", "description"),
     "storage": ("storage", None),

renku/command/move.py

@@ -57,7 +57,7 @@ def _move(sources: List[str], destination: str, force: bool, verbose: bool, to_d
     absolute_sources = [_get_absolute_path(src) for src in sources]
 
     if to_dataset:
-        target_dataset = DatasetsProvenance().get_by_name(to_dataset, strict=True)
+        target_dataset = DatasetsProvenance().get_by_slug(to_dataset, strict=True)
         if not is_subpath(absolute_destination, _get_absolute_path(target_dataset.get_datadir())):
             raise errors.ParameterError(
                 f"Destination {destination} must be in {target_dataset.get_datadir()} when moving to a dataset."
@@ -112,7 +112,7 @@ def _move(sources: List[str], destination: str, force: bool, verbose: bool, to_d
     # NOTE: Force-add to include possible ignored files
     repository.add(*files.values(), force=True)
 
-    move_files(files=files, to_dataset_name=to_dataset)
+    move_files(files=files, to_dataset_slug=to_dataset)
 
     if verbose:
         _show_moved_files(project_context.path, files)

renku/command/schema/dataset.py

@@ -202,11 +202,11 @@ class Meta:
     in_language = Nested(schema.inLanguage, LanguageSchema, load_default=None)
     keywords = fields.List(schema.keywords, fields.String(), load_default=None)
     license = Uri(schema.license, load_default=None)
-    name = fields.String(renku.slug)
+    slug = fields.String(renku.slug)
     initial_identifier = fields.String(renku.originalIdentifier)
     project_id = fields.IRI(renku.hasDataset, reverse=True)
     same_as = Nested(schema.sameAs, UrlSchema, load_default=None)
-    title = fields.String(schema.name)
+    name = fields.String(schema.name)
     version = fields.String(schema.version, load_default=None)
 
     @pre_dump(pass_many=True)

renku/command/view_model/dataset.py

@@ -23,14 +23,14 @@
 class DatasetViewModel:
     """A view model for a ``Dataset``."""
 
-    def __init__(self, name: str, same_as: Optional[str]):
-        self.name: str = name
+    def __init__(self, slug: str, same_as: Optional[str]):
+        self.slug: str = slug
         self.same_as: Optional[str] = same_as
 
     @classmethod
     def from_dataset(cls, dataset: Dataset) -> "DatasetViewModel":
         """Create view model from ``Dataset``."""
-        return cls(name=dataset.name, same_as=dataset.same_as.value if dataset.same_as else None)
+        return cls(slug=dataset.slug, same_as=dataset.same_as.value if dataset.same_as else None)
 
 
 class DatasetFileViewModel:

renku/command/view_model/log.py

@@ -90,7 +90,7 @@ class DatasetChangeDetailsViewModel:
     modified: bool = False
     files_added: Optional[List[str]] = None
     files_removed: Optional[List[str]] = None
-    title_changed: Optional[str] = None
+    name_changed: Optional[str] = None
     description_changed: Optional[str] = None
     creators_added: Optional[List[str]] = None
     creators_removed: Optional[List[str]] = None
@@ -181,7 +181,7 @@ def from_dataset(cls, dataset: "Dataset") -> "DatasetLogViewModel":
 
         dataset_gateway = inject.instance(IDatasetGateway)
 
-        descriptions = [f"Dataset '{dataset.name}': "]
+        descriptions = [f"Dataset '{dataset.slug}': "]
         details = DatasetChangeDetailsViewModel()
 
         if not dataset.derived_from and not dataset.same_as:
@@ -231,8 +231,8 @@ def from_dataset(cls, dataset: "Dataset") -> "DatasetLogViewModel":
 
         if not previous_dataset:
             # NOTE: Check metadata changes on create/import
-            if dataset.title:
-                details.title_changed = dataset.title
+            if dataset.name:
+                details.name_changed = dataset.name
 
             if dataset.description:
                 details.description_changed = dataset.description
@@ -248,8 +248,8 @@ def from_dataset(cls, dataset: "Dataset") -> "DatasetLogViewModel":
         elif not details.deleted:
             # NOTE: Check metadata changes to previous dataset
             modified = False
-            if dataset.title != previous_dataset.title:
-                details.title_changed = dataset.title
+            if dataset.name != previous_dataset.name:
+                details.name_changed = dataset.name
                 modified = True
             if dataset.description != previous_dataset.description:
                 details.description_changed = dataset.description
@@ -286,7 +286,7 @@ def from_dataset(cls, dataset: "Dataset") -> "DatasetLogViewModel":
                 descriptions.append("metadata modified")
 
         return DatasetLogViewModel(
-            id=dataset.name,
+            id=dataset.slug,
             date=dataset.date_removed
             if dataset.date_removed
             else (

renku/core/dataset/context.py

@@ -31,14 +31,14 @@ class DatasetContext:
 
     def __init__(
         self,
-        name: str,
+        slug: str,
         create: Optional[bool] = False,
         commit_database: Optional[bool] = False,
         creator: Optional[Person] = None,
         datadir: Optional[Path] = None,
         storage: Optional[str] = None,
     ) -> None:
-        self.name = name
+        self.slug = slug
         self.create = create
         self.commit_database = commit_database
         self.creator = creator
@@ -49,17 +49,17 @@ def __init__(
 
     def __enter__(self):
         """Enter context."""
-        self.dataset = self.dataset_provenance.get_by_name(name=self.name)
+        self.dataset = self.dataset_provenance.get_by_slug(slug=self.slug)
         if self.dataset is None:
             if not self.create:
-                raise errors.DatasetNotFound(name=self.name)
+                raise errors.DatasetNotFound(slug=self.slug)
 
             # NOTE: Don't update provenance when creating here because it will be updated later
             self.dataset = create_dataset(
-                name=self.name, update_provenance=False, datadir=self.datadir, storage=self.storage
+                slug=self.slug, update_provenance=False, datadir=self.datadir, storage=self.storage
             )
         elif self.create:
-            raise errors.DatasetExistsError(self.name)
+            raise errors.DatasetExistsError(self.slug)
 
         return self.dataset