Differential D8263 Diff 29906 swh/indexer/metadata_dictionary/nuget.py

Changeset View

Standalone View

swh/indexer/metadata_dictionary/nuget.py

# Copyright (C) 2022 The Software Heritage developers		# Copyright (C) 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 os.path		import os.path
import re		import re
from typing import Any, Dict, List, Optional		from typing import Any, Dict, List, Optional

import xmltodict		import xmltodict

from swh.indexer.codemeta import _DATA_DIR, SCHEMA_URI, _read_crosstable		from swh.indexer.codemeta import _DATA_DIR, _read_crosstable
		from swh.indexer.namespaces import SCHEMA
from swh.indexer.storage.interface import Sha1		from swh.indexer.storage.interface import Sha1

from .base import DictMapping, DirectoryLsEntry, SingleFileIntrinsicMapping		from .base import DictMapping, DirectoryLsEntry, SingleFileIntrinsicMapping

NUGET_TABLE_PATH = os.path.join(_DATA_DIR, "nuget.csv")		NUGET_TABLE_PATH = os.path.join(_DATA_DIR, "nuget.csv")

with open(NUGET_TABLE_PATH) as fd:		with open(NUGET_TABLE_PATH) as fd:
(CODEMETA_TERMS, NUGET_TABLE) = _read_crosstable(fd)		(CODEMETA_TERMS, NUGET_TABLE) = _read_crosstable(fd)
▲ Show 20 Lines • Show All 67 Lines • ▼ Show 20 Lines	class NuGetMapping(DictMapping, SingleFileIntrinsicMapping):
def normalize_licenseUrl(self, s):		def normalize_licenseUrl(self, s):
if isinstance(s, str):		if isinstance(s, str):
return {"@id": s}		return {"@id": s}

def normalize_authors(self, s):		def normalize_authors(self, s):
if isinstance(s, str):		if isinstance(s, str):
author_names = [a.strip() for a in s.split(",")]		author_names = [a.strip() for a in s.split(",")]
authors = [		authors = [
{"@type": SCHEMA_URI + "Person", SCHEMA_URI + "name": name}		{"@type": SCHEMA.Person, SCHEMA.name: name} for name in author_names
for name in author_names
]		]
return {"@list": authors}		return {"@list": authors}

def translate_releaseNotes(self, translated_metadata, s):		def translate_releaseNotes(self, translated_metadata, s):
if isinstance(s, str):		if isinstance(s, str):
translated_metadata.setdefault("http://schema.org/releaseNotes", []).append(		translated_metadata.setdefault("http://schema.org/releaseNotes", []).append(
s		s
)		)

def normalize_tags(self, s):		def normalize_tags(self, s):
if isinstance(s, str):		if isinstance(s, str):
return s.split(" ")		return s.split(" ")