Differential D8772 Diff 31665 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

from rdflib import RDF, BNode, Graph, Literal, URIRef		from rdflib import RDF, BNode, Graph, Literal, URIRef

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

from .base import JsonMapping, SingleFileIntrinsicMapping		from .base import JsonMapping, SingleFileIntrinsicMapping
from .utils import add_list, prettyprint_graph # noqa		from .utils import add_list, add_url_if_valid, prettyprint_graph # noqa

SPDX = URIRef("https://spdx.org/licenses/")		SPDX = URIRef("https://spdx.org/licenses/")


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 65 Lines • ▼ Show 20 Lines	def normalize_bugs(self, d):
"""		"""
if isinstance(d, dict) and isinstance(d.get("url"), str):		if isinstance(d, dict) and isinstance(d.get("url"), str):
url = d["url"]		url = d["url"]
elif isinstance(d, str):		elif isinstance(d, str):
url = d		url = d
else:		else:
url = ""		url = ""

parsed_url = urllib.parse.urlparse(url)
if parsed_url.netloc:
return URIRef(url)		return URIRef(url)
else:
return None

_parse_author = re.compile(		_parse_author = re.compile(
r"^ " r"(?P<name>.?)" r"( +<(?P<email>.)>)?" r"( +$(?P<url>.)$)?" r" *$"		r"^ " r"(?P<name>.?)" r"( +<(?P<email>.)>)?" r"( +$(?P<url>.)$)?" r" *$"
)		)

def translate_author(self, graph: Graph, root, d):		def translate_author(self, graph: Graph, root, d):
r"""https://docs.npmjs.com/files/package.json#people-fields-author-contributors'		r"""https://docs.npmjs.com/files/package.json#people-fields-author-contributors'

▲ Show 20 Lines • Show All 76 Lines • ▼ Show 20 Lines	def translate_author(self, graph: Graph, root, d):
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):
graph.add((author, SCHEMA.name, Literal(name)))		graph.add((author, SCHEMA.name, Literal(name)))
if email and isinstance(email, str):		if email and isinstance(email, str):
graph.add((author, SCHEMA.email, Literal(email)))		graph.add((author, SCHEMA.email, Literal(email)))
if url and isinstance(url, str):		add_url_if_valid(graph, author, SCHEMA.url, url)
# Workaround for https://github.com/digitalbazaar/pyld/issues/91 : drop
# URLs that are blatantly invalid early, so PyLD does not crash.
parsed_url = urllib.parse.urlparse(url)
if parsed_url.netloc:
graph.add((author, SCHEMA.url, URIRef(url)))

add_list(graph, root, SCHEMA.author, [author])		add_list(graph, root, SCHEMA.author, [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 91 Lines • Show Last 20 Lines