Change data-type to datatype (#196)

* Change data-type to datatype on CLI argument.

* Change data-type to datatype in docs.

* Make other small changes in code documentation.

* Fix tests.

* Replace data_type with datatype everywhere.

* Fix the space case data type to datatype.

* Fix missed case in README.md

README.md

@@ -8,7 +8,7 @@ Datashuttle includes tools for automated generation and transfer of neuroscience
 
 * Manage files across multiple data-collection computers by synchronising all data to with a centrally stored project.
 
-* Simplify data transfers by selecting only a sub-set of data to move (e.g. specific subjects, sessions or data types)
+* Simplify data transfers by selecting only a sub-set of data to move (e.g. specific subjects, sessions or datatypes)
 
 See the [DataShuttle Documentation](https://datashuttle.neuroinformatics.dev) to get started or join the [Zulip chat](https://neuroinformatics.zulipchat.com/#narrow/stream/405999-DataShuttle) to discuss any questions, comments or feedback.
 

datashuttle/command_line_interface.py

@@ -613,11 +613,10 @@ def construct_parser():
         nargs="+",
         type=str,
         required=False,
-        help="Optional: (str, single or multiple) (selection of data types, or 'all')",
+        help="Optional: (str, single or multiple) (selection of datatypes, or 'all')",
     )
     make_sub_folders_parser.add_argument(
-        "--data-type",
-        "--data_type",
+        "--datatype",
         "-dt",
         type=str,
         nargs="+",
@@ -659,13 +658,12 @@ def construct_parser():
         help=help("required_str_single_or_multiple_or_all"),
     )
     upload_parser.add_argument(
-        "--data-type",
-        "--data_type",
+        "--datatype",
         "-dt",
         type=str,
         nargs="+",
         required=False,
-        help="Optional: (str, single or multiple) (selection of data types, or 'all') (default 'all')",
+        help="Optional: (str, single or multiple) (selection of datatypes, or 'all') (default 'all')",
     )
     upload_parser.add_argument(
         "--dry-run",
@@ -732,8 +730,7 @@ def construct_parser():
         help=help("required_str_single_or_multiple_or_all"),
     )
     download_parser.add_argument(
-        "--data-type",
-        "--data_type",
+        "--datatype",
         "-dt",
         type=str,
         nargs="+",

datashuttle/configs/canonical_configs.py

@@ -38,15 +38,15 @@ def get_canonical_config_dict() -> dict:
         "show_transfer_progress": None,
     }
 
-    data_type_configs = get_data_types(as_dict=True)
-    config_dict.update(data_type_configs)
+    datatype_configs = get_datatypes(as_dict=True)
+    config_dict.update(datatype_configs)
 
     return config_dict
 
 
-def get_data_types(as_dict: bool = False):
+def get_datatypes(as_dict: bool = False):
     """
-    Canonical list of data_type flags. This is used
+    Canonical list of datatype flags. This is used
     to define get_canonical_config_dict() as well
     as in testing.
     """
@@ -63,7 +63,7 @@ def get_flags() -> List[str]:
     Return all configs that are bool flags. This is used in
     testing and type checking config inputs.
     """
-    return get_data_types() + [
+    return get_datatypes() + [
         "overwrite_old_files",
         "show_transfer_progress",
     ]
@@ -151,10 +151,10 @@ def check_dict_values_raise_on_fail(config_dict: Configs) -> None:
                 "with no ~ syntax."
             )
 
-    if not any([config_dict[key] for key in get_data_types()]):
+    if not any([config_dict[key] for key in get_datatypes()]):
         utils.log_and_raise_error(
-            f"At least one data type must be True in "
-            f"configs, from: {' '.join(get_data_types())}."
+            f"At least one datatype must be True in "
+            f"configs, from: {' '.join(get_datatypes())}."
         )
 
     # Check SSH settings

datashuttle/configs/canonical_folders.py

@@ -8,7 +8,7 @@
 from datashuttle.utils.folder_class import Folder
 
 
-def get_data_type_folders(cfg: Configs) -> dict:
+def get_datatype_folders(cfg: Configs) -> dict:
     """
     This function holds the canonical folders
     managed by datashuttle.
@@ -23,12 +23,12 @@ def get_data_type_folders(cfg: Configs) -> dict:
 
     When adding a new folder, the
     key should be the canonical key used to refer
-    to the data_type in datashuttle and SWC-BIDs.
+    to the datatype in datashuttle and SWC-BIDs.
 
     The value is a Folder() class instance with
     the required fields
 
-    name : The display name for the data_type, that will
+    name : The display name for the datatype, that will
         be used for making and transferring files in practice.
         This should always match the canonical name, but left as
         an option for rare cases in which advanced users want to change it.
@@ -80,8 +80,8 @@ def get_non_sub_names():
     return [
         "all_ses",
         "all_non_ses",
-        "all_data_type",
-        "all_ses_level_non_data_type",
+        "all_datatype",
+        "all_ses_level_non_datatype",
     ]
 
 
@@ -93,8 +93,8 @@ def get_non_ses_names():
     return [
         "all_sub",
         "all_non_sub",
-        "all_data_type",
-        "all_ses_level_non_data_type",
+        "all_datatype",
+        "all_ses_level_non_datatype",
     ]
 
 

datashuttle/configs/config_class.py

@@ -49,7 +49,7 @@ def __init__(
 
         self.top_level_folder: str
 
-        self.data_type_folders: dict
+        self.datatype_folders: dict
         self.logging_path: Path
         self.hostkeys_path: Path
         self.ssh_key_path: Path
@@ -300,67 +300,67 @@ def make_and_get_logging_path(self) -> Path:
         folders.make_folders(logging_path)
         return logging_path
 
-    def init_data_type_folders(self):
+    def init_datatype_folders(self):
         """"""
-        self.data_type_folders = canonical_folders.get_data_type_folders(self)
+        self.datatype_folders = canonical_folders.get_datatype_folders(self)
 
-    def get_data_type_items(
-        self, data_type: Union[str, list]
+    def get_datatype_items(
+        self, datatype: Union[str, list]
     ) -> Union[ItemsView, zip]:
         """
-        Get the .items() structure of the data type, either all of
-        them (stored in self.data_type_folders) or as a single item.
+        Get the .items() structure of the datatype, either all of
+        them (stored in self.datatype_folders) or as a single item.
         """
-        if isinstance(data_type, str):
-            data_type = [data_type]
+        if isinstance(datatype, str):
+            datatype = [datatype]
 
         items: Union[ItemsView, zip]
 
-        if "all" in data_type:
-            items = self.data_type_folders.items()
+        if "all" in datatype:
+            items = self.datatype_folders.items()
         else:
             items = zip(
-                data_type,
-                [self.data_type_folders[key] for key in data_type],
+                datatype,
+                [self.datatype_folders[key] for key in datatype],
             )
 
         return items
 
-    def items_from_data_type_input(
+    def items_from_datatype_input(
         self,
         local_or_central: str,
-        data_type: Union[list, str],
+        datatype: Union[list, str],
         sub: str,
         ses: Optional[str] = None,
     ) -> Union[ItemsView, zip]:
         """
-        Get the list of data_types to transfer, either
+        Get the list of datatypes to transfer, either
         directly from user input, or by searching
         what is available if "all" is passed.
 
         Parameters
         ----------
 
-        see _transfer_data_type() for parameters.
+        see _transfer_datatype() for parameters.
         """
         base_folder = self.get_base_folder(local_or_central)
 
-        if data_type not in [
+        if datatype not in [
             "all",
             ["all"],
-            "all_data_type",
-            ["all_data_type"],
+            "all_datatype",
+            ["all_datatype"],
         ]:
-            data_type_items = self.get_data_type_items(
-                data_type,
+            datatype_items = self.get_datatype_items(
+                datatype,
             )
         else:
-            data_type_items = folders.search_data_folders_sub_or_ses_level(
+            datatype_items = folders.search_data_folders_sub_or_ses_level(
                 self,
                 base_folder,
                 local_or_central,
                 sub,
                 ses,
             )
 
-        return data_type_items
+        return datatype_items

datashuttle/datashuttle.py

@@ -119,7 +119,7 @@ def _set_attributes_after_config_load(self) -> None:
 
         self._make_project_metadata_if_does_not_exist()
 
-        self.cfg.init_data_type_folders()
+        self.cfg.init_datatype_folders()
 
     # -------------------------------------------------------------------------
     # Public Folder Makers
@@ -159,7 +159,7 @@ def make_sub_folders(
         self,
         sub_names: Union[str, list],
         ses_names: Optional[Union[str, list]] = None,
-        data_type: str = "all",
+        datatype: str = "all",
     ) -> None:
         """
         Create a subject / session folder tree in the project
@@ -178,12 +178,12 @@ def make_sub_folders(
                 (if not already, these will be prefixed with
                 "ses-"). If no session is provided, no session-level
                 folders are made.
-        data_type :
-                The data_type to make in the sub / ses folders.
-                (e.g. "ephys", "behav", "histology"). Only data_types
+        datatype :
+                The datatype to make in the sub / ses folders.
+                (e.g. "ephys", "behav", "histology"). Only datatypes
                 that are enabled in the configs (e.g. use_behav) will be
                 created. If "all" is selected, folders will be created
-                for all data_type enabled in config. Use empty string "" for
+                for all datatype enabled in config. Use empty string "" for
                 none.
 
         Notes
@@ -204,7 +204,7 @@ def make_sub_folders(
 
         Examples
         --------
-        project.make_sub_folders("sub-001", data_type="all")
+        project.make_sub_folders("sub-001", datatype="all")
 
         project.make_sub_folders("sub-002@TO@005",
                              ["ses-001", "ses-002"],
@@ -251,7 +251,7 @@ def make_sub_folders(
             self.cfg,
             sub_names,
             ses_names,
-            data_type,
+            datatype,
             log=True,
         )
 
@@ -294,7 +294,7 @@ def upload(
         self,
         sub_names: Union[str, list],
         ses_names: Union[str, list],
-        data_type: str = "all",
+        datatype: str = "all",
         dry_run: bool = False,
         init_log: bool = True,
     ) -> None:
@@ -313,15 +313,15 @@ def upload(
             be prefixed with "sub-", or the prefix will be
             automatically added. "@*@" can be used as a wildcard.
             "all" will search for all sub-folders in the
-            data type folder to upload.
+            datatype folder to upload.
         ses_names :
             a session name / list of session names, similar to
             sub_names but requiring a "ses-" prefix.
         dry_run :
             perform a dry-run of upload. This will output as if file
             transfer was taking place, but no files will be moved. Useful
             to check which files will be moved on data transfer.
-        data_type :
+        datatype :
             see make_sub_folders()
 
         init_log :
@@ -357,7 +357,7 @@ def upload(
             "upload",
             sub_names,
             ses_names,
-            data_type,
+            datatype,
             dry_run,
             log=True,
         )
@@ -368,7 +368,7 @@ def download(
         self,
         sub_names: Union[str, list],
         ses_names: Union[str, list],
-        data_type: str = "all",
+        datatype: str = "all",
         dry_run: bool = False,
         init_log: bool = True,
     ) -> None:
@@ -393,7 +393,7 @@ def download(
             "download",
             sub_names,
             ses_names,
-            data_type,
+            datatype,
             dry_run,
             log=True,
         )