Differential D8263 Diff 29841 swh/indexer/metadata_dictionary/npm.py

Changeset View

Standalone View

swh/indexer/metadata_dictionary/npm.py

# Copyright (C) 2018-2022 The Software Heritage developers		# Copyright (C) 2018-2022 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

import re		import re
import urllib.parse		import urllib.parse

from swh.indexer.codemeta import CROSSWALK_TABLE, SCHEMA_URI		from swh.indexer.codemeta import CROSSWALK_TABLE
		from swh.indexer.namespaces import SCHEMA

from .base import JsonMapping, SingleFileIntrinsicMapping		from .base import JsonMapping, SingleFileIntrinsicMapping


class NpmMapping(JsonMapping, SingleFileIntrinsicMapping):		class NpmMapping(JsonMapping, SingleFileIntrinsicMapping):
"""		"""
dedicated class for NPM (package.json) mapping and translation		dedicated class for NPM (package.json) mapping and translation
"""		"""
▲ Show 20 Lines • Show All 97 Lines • ▼ Show 20 Lines	def normalize_author(self, d):
... 'name': 'John Doe',		... 'name': 'John Doe',
... 'email': 'john.doe@example.org',		... 'email': 'john.doe@example.org',
... 'url': 'https:\\\\example.invalid/~john.doe',		... 'url': 'https:\\\\example.invalid/~john.doe',
... }))		... }))
{'@list': [{'@type': 'http://schema.org/Person',		{'@list': [{'@type': 'http://schema.org/Person',
'http://schema.org/email': 'john.doe@example.org',		'http://schema.org/email': 'john.doe@example.org',
'http://schema.org/name': 'John Doe'}]}		'http://schema.org/name': 'John Doe'}]}
""" # noqa		""" # noqa
author = {"@type": SCHEMA_URI + "Person"}		author = {"@type": SCHEMA.Person}
if isinstance(d, dict):		if isinstance(d, dict):
name = d.get("name", None)		name = d.get("name", None)
email = d.get("email", None)		email = d.get("email", None)
url = d.get("url", None)		url = d.get("url", None)
elif isinstance(d, str):		elif isinstance(d, str):
match = self._parse_author.match(d)		match = self._parse_author.match(d)
if not match:		if not match:
return None		return None
name = match.group("name")		name = match.group("name")
email = match.group("email")		email = match.group("email")
url = match.group("url")		url = match.group("url")
else:		else:
return None		return None

if name and isinstance(name, str):		if name and isinstance(name, str):
author[SCHEMA_URI + "name"] = name		author[SCHEMA.name] = name
if email and isinstance(email, str):		if email and isinstance(email, str):
author[SCHEMA_URI + "email"] = email		author[SCHEMA.email] = email
if url and isinstance(url, str):		if url and isinstance(url, str):
# Workaround for https://github.com/digitalbazaar/pyld/issues/91 : drop		# Workaround for https://github.com/digitalbazaar/pyld/issues/91 : drop
# URLs that are blatantly invalid early, so PyLD does not crash.		# URLs that are blatantly invalid early, so PyLD does not crash.
parsed_url = urllib.parse.urlparse(url)		parsed_url = urllib.parse.urlparse(url)
if parsed_url.netloc:		if parsed_url.netloc:
author[SCHEMA_URI + "url"] = {"@id": url}		author[SCHEMA.url] = {"@id": url}

return {"@list": [author]}		return {"@list": [author]}

def normalize_description(self, description):		def normalize_description(self, description):
r"""Try to re-decode ``description`` as UTF-16, as this is a somewhat common		r"""Try to re-decode ``description`` as UTF-16, as this is a somewhat common
mistake that causes issues in the database because of null bytes in JSON.		mistake that causes issues in the database because of null bytes in JSON.

>>> NpmMapping().normalize_description("foo bar")		>>> NpmMapping().normalize_description("foo bar")
▲ Show 20 Lines • Show All 88 Lines • Show Last 20 Lines