ClearML/clearml
1
0
Fork 0
mirror of https://github.com/clearml/clearml synced 2025-06-26 18:16:07 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Adding appropriate error when inputing URL's in add_files function (instead of using add_external_files)

Browse Source
This commit is contained in:
morzahavi 2024-09-25 17:03:12 +03:00 committed by GitHub
parent eaeadb18e3
commit 50ad7b09a1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 62 additions and 45 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

107
clearml/datasets/dataset.py
View File

@ -380,58 +380,75 @@ class Dataset(object):
:param tags: A list of tags which describe the Task to add. :param tags: A list of tags which describe the Task to add.
""" """
self._task.add_tags(tags) self._task.add_tags(tags)
import re
def add_files( def is_url(path):
self, """
path, # type: Union[str, Path, _Path] Helper function to check if the provided path is an external URL (e.g., s3://, http://).
wildcard=None, # type: Optional[Union[str, Sequence[str]]] """
local_base_folder=None, # type: Optional[str] url_regex = re.compile(
dataset_path=None, # type: Optional[str] r'^(?:http|ftp|s3|gs|azure)://' # schemes: http, ftp, s3, gs, azure
recursive=True, # type: bool )
verbose=False, # type: bool return url_regex.match(path) is not None
max_workers=None, # type: Optional[int]
):
# type: (...) -> ()
"""
Add a folder into the current dataset. calculate file hash,
and compare against parent, mark files to be uploaded
:param path: Add a folder/file to the dataset def add_files(
:param wildcard: add only specific set of files. self,
Wildcard matching, can be a single string or a list of wildcards. path, # type: Union[str, Path, _Path]
:param local_base_folder: files will be located based on their relative path from local_base_folder wildcard=None, # type: Optional[Union[str, Sequence[str]]]
:param dataset_path: where in the dataset the folder/files should be located local_base_folder=None, # type: Optional[str]
:param recursive: If True, match all wildcard files recursively dataset_path=None, # type: Optional[str]
:param verbose: If True, print to console files added/modified recursive=True, # type: bool
:param max_workers: The number of threads to add the files with. Defaults to the number of logical cores verbose=False, # type: bool
:return: number of files added max_workers=None, # type: Optional[int]
""" ):
max_workers = max_workers or psutil.cpu_count() # type: (...) -> ()
self._dirty = True """
self._task.get_logger().report_text( Add a folder into the current dataset. calculate file hash,
'Adding files to dataset: {}'.format( and compare against parent, mark files to be uploaded
dict(path=path, wildcard=wildcard, local_base_folder=local_base_folder,
dataset_path=dataset_path, recursive=recursive, verbose=verbose)),
print_console=False)
num_added, num_modified = self._add_files( :param path: Add a folder/file to the dataset
path=path, :param wildcard: add only specific set of files.
wildcard=wildcard, Wildcard matching, can be a single string or a list of wildcards.
local_base_folder=local_base_folder, :param local_base_folder: files will be located based on their relative path from local_base_folder
dataset_path=dataset_path, :param dataset_path: where in the dataset the folder/files should be located
recursive=recursive, :param recursive: If True, match all wildcard files recursively
verbose=verbose, :param verbose: If True, print to console files added/modified
max_workers=max_workers, :param max_workers: The number of threads to add the files with. Defaults to the number of logical cores
:return: number of files added
"""
# Check if the path provided is a URL, if so, raise an error and suggest using add_external_files
if is_url(path):
raise ValueError(
"The path provided seems to be an external URL (e.g., s3://, http://). "
"Please use `add_external_files()` to add external files to the dataset."
) )
# update the task script max_workers = max_workers or psutil.cpu_count()
self._add_script_call( self._dirty = True
'add_files', path=path, wildcard=wildcard, local_base_folder=local_base_folder, self._task.get_logger().report_text(
dataset_path=dataset_path, recursive=recursive) 'Adding files to dataset: {}'.format(
dict(path=path, wildcard=wildcard, local_base_folder=local_base_folder,
dataset_path=dataset_path, recursive=recursive, verbose=verbose)),
print_console=False)
self._serialize() num_added, num_modified = self._add_files(
path=path,
wildcard=wildcard,
local_base_folder=local_base_folder,
dataset_path=dataset_path,
recursive=recursive,
verbose=verbose,
max_workers=max_workers,
)
return num_added # update the task script
self._add_script_call(
'add_files', path=path, wildcard=wildcard, local_base_folder=local_base_folder,
dataset_path=dataset_path, recursive=recursive)
self._serialize()
return num_added
def add_external_files( def add_external_files(
self, self,