Differential D4261 Diff 15091 swh/deposit/cli/client.py

Changeset View

Standalone View

swh/deposit/cli/client.py

# Copyright (C) 2017-2020 The Software Heritage developers		# Copyright (C) 2017-2020 The Software Heritage developers
# See the AUTHORS file at the top-level directory of this distribution		# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version		# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information		# See top-level LICENSE file for more information

from __future__ import annotations		from __future__ import annotations

		from datetime import datetime, timezone
import logging		import logging

# WARNING: do not import unnecessary things here to keep cli startup time under		# WARNING: do not import unnecessary things here to keep cli startup time under
# control		# control
import os		import os
import sys		import sys
from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple		from typing import TYPE_CHECKING, Any, Dict, List, Optional, Tuple

Show All 36 Lines	Returns:
Top level api url to actually request		Top level api url to actually request

"""		"""
if not url.endswith("/1"):		if not url.endswith("/1"):
url = "%s/1" % url		url = "%s/1" % url
return url		return url


def generate_metadata_file(		def generate_metadata(
name: str, external_id: str, authors: List[str], temp_dir: str		deposit_client: str, name: str, external_id: str, authors: List[str]
) -> str:		) -> str:
"""Generate a temporary metadata file with the minimum required metadata		"""Generate sword compliant xml metadata with the minimum required metadata.

This generates a xml file in a temporary location and returns the		The Atom spec, https://tools.ietf.org/html/rfc4287, says that:
path to that file.

This is up to the client of that function to clean up the		- atom:entry elements MUST contain one or more atom:author elements
temporary file.		- atom:entry elements MUST contain exactly one atom:title element.
		- atom:entry elements MUST contain exactly one atom:updated element.

		However, we are also using CodeMeta, so we want some basic information to be
		mandatory.

		Therefore, we generate the following mandatory fields:
		- http://www.w3.org/2005/Atom#updated
		- http://www.w3.org/2005/Atom#author
		- http://www.w3.org/2005/Atom#title
		- https://doi.org/10.5063/SCHEMA/CODEMETA-2.0#name (yes, in addition to
		http://www.w3.org/2005/Atom#title, even if they have somewhat the same meaning)
		- https://doi.org/10.5063/SCHEMA/CODEMETA-2.0#author

Args:		Args:
name: Software's name		deposit_client: Deposit client username,
		name: Software name
external_id: External identifier (slug) or generated one		external_id: External identifier (slug) or generated one
authors: List of author names		authors: List of author names

Returns:		Returns:
Filepath to the metadata generated file		metadata xml string

"""		"""
import xmltodict		import xmltodict

path = os.path.join(temp_dir, "metadata.xml")
# generate a metadata file with the minimum required metadata		# generate a metadata file with the minimum required metadata
codemetadata = {		codemetadata = {
"entry": {		"entry": {
"@xmlns": "http://www.w3.org/2005/Atom",		"@xmlns:atom": "http://www.w3.org/2005/Atom",
		vlorentzUnsubmitted Not Done Inline Actions yay, I like it when we avoid default namespaces vlorentz: yay, I like it when we avoid default namespaces
		ardumontAuthorUnsubmitted Done Inline Actions yes, i don't like it either, I just did not understand how to properly use those before. ardumont: yes, i don't like it either, I just did not understand how to properly use those before.
"@xmlns:codemeta": "https://doi.org/10.5063/SCHEMA/CODEMETA-2.0",		"@xmlns:codemeta": "https://doi.org/10.5063/SCHEMA/CODEMETA-2.0",
"codemeta:name": name,
"codemeta:identifier": external_id,		"codemeta:identifier": external_id,
"codemeta:author": [		"atom:updated": datetime.now(tz=timezone.utc), # mandatory, cf. docstring
		"atom:author": deposit_client, # mandatory, cf. docstring
		"atom:title": name, # mandatory, cf. docstring
		"codemeta:name": name, # mandatory, cf. docstring
		"codemeta:author": [ # mandatory, cf. docstring
{"codemeta:name": author_name} for author_name in authors		{"codemeta:name": author_name} for author_name in authors
],		],
},		},
}		}

logging.debug("Temporary file: %s", path)
logging.debug("Metadata dict to generate as xml: %s", codemetadata)		logging.debug("Metadata dict to generate as xml: %s", codemetadata)
		vlorentzUnsubmitted Not Done Inline Actions could you add a comment explaining which fields are mandatory (and why the duplicates, etc.) You can probably just copy-paste my comment on T2701 vlorentz: could you add a comment explaining which fields are mandatory (and why the duplicates, etc.)…
		ardumontAuthorUnsubmitted Done Inline Actions ok ardumont: ok
s = xmltodict.unparse(codemetadata, pretty=True)		return xmltodict.unparse(codemetadata, pretty=True)
logging.debug("Metadata dict as xml generated: %s", s)
with open(path, "w") as fp:
fp.write(s)
return path


def _client(url: str, username: str, password: str) -> PublicApiDepositClient:		def _client(url: str, username: str, password: str) -> PublicApiDepositClient:
"""Instantiate a client to access the deposit api server		"""Instantiate a client to access the deposit api server

Args:		Args:
url (str): Deposit api server		url (str): Deposit api server
username (str): User		username (str): User
▲ Show 20 Lines • Show All 91 Lines • ▼ Show 20 Lines	) -> Dict[str, Any]:

if not metadata:		if not metadata:
if metadata_deposit:		if metadata_deposit:
raise InputError(		raise InputError(
"Metadata deposit must be provided for metadata "		"Metadata deposit must be provided for metadata "
"deposit, either a filepath with --metadata or --name and --author"		"deposit, either a filepath with --metadata or --name and --author"
)		)
if name and authors:		if name and authors:
metadata = generate_metadata_file(name, slug, authors, temp_dir)		metadata_path = os.path.join(temp_dir, "metadata.xml")
		logging.debug("Temporary file: %s", metadata_path)
		metadata_xml = generate_metadata(username, name, slug, authors)
		logging.debug("Metadata xml generated: %s", metadata_xml)
		with open(metadata_path, "w") as f:
		f.write(metadata_xml)
		metadata = metadata_path
elif not archive_deposit and not partial and not deposit_id:		elif not archive_deposit and not partial and not deposit_id:
# If we meet all the following conditions:		# If we meet all the following conditions:
# * this is not an archive-only deposit request		# * this is not an archive-only deposit request
# * it is not part of a multipart deposit (either create/update		# * it is not part of a multipart deposit (either create/update
# or finish)		# or finish)
# * it misses either name or authors		# * it misses either name or authors
raise InputError(		raise InputError(
"For metadata deposit request, either a metadata file with "		"For metadata deposit request, either a metadata file with "
▲ Show 20 Lines • Show All 312 Lines • Show Last 20 Lines