Newer
Older
# Copyright (C) 2017-2020 The Software Heritage developers
Morane Otilia Gruenpeter
committed
# See the AUTHORS file at the top-level directory of this distribution
# License: GNU General Public License version 3, or any later version
# See top-level LICENSE file for more information
Morane Otilia Gruenpeter
committed
import unittest
from hypothesis import HealthCheck, given, settings, strategies
from swh.indexer.codemeta import CODEMETA_TERMS
from swh.indexer.metadata import ContentMetadataIndexer, RevisionMetadataIndexer
from swh.indexer.metadata_detector import detect_metadata
from swh.indexer.metadata_dictionary import MAPPINGS
from swh.indexer.metadata_dictionary.maven import MavenMapping
from swh.indexer.metadata_dictionary.npm import NpmMapping
from swh.indexer.metadata_dictionary.ruby import GemspecMapping
from swh.indexer.storage.model import ContentMetadataRow
from swh.indexer.tests.utils import DIRECTORY2, REVISION
from swh.model.hashutil import hash_to_bytes
from swh.model.model import Directory, DirectoryEntry, Revision
fill_obj_storage,
fill_storage,
json_document_strategy,
xml_document_strategy,
"name": "swh-metadata-translator",
"version": "0.0.2",
"configuration": {"type": "local", "context": "NpmMapping"},
class ContentMetadataTestIndexer(ContentMetadataIndexer):
Morane Otilia Gruenpeter
committed
"""Specific Metadata whose configuration is enough to satisfy the
indexing tests.
"""
assert False, "should not be called; the rev indexer configures it."
REVISION_METADATA_CONFIG = {
**BASE_TEST_CONFIG,
Morane Otilia Gruenpeter
committed
class Metadata(unittest.TestCase):
"""
Tests metadata_mock_tool tool for Metadata detection
"""
Morane Otilia Gruenpeter
committed
def setUp(self):
"""
shows the entire diff in the results
"""
self.maxDiff = None
self.npm_mapping = MAPPINGS["NpmMapping"]()
self.codemeta_mapping = MAPPINGS["CodemetaMapping"]()
self.maven_mapping = MAPPINGS["MavenMapping"]()
self.pkginfo_mapping = MAPPINGS["PythonPkginfoMapping"]()
self.gemspec_mapping = MAPPINGS["GemspecMapping"]()
Morane Otilia Gruenpeter
committed
def test_compute_metadata_none(self):
"""
testing content empty content is empty
should return None
"""
# given
content = b""
# None if no metadata was found or an error occurred
declared_metadata = None
# when
result = self.npm_mapping.translate(content)
Morane Otilia Gruenpeter
committed
# then
self.assertEqual(declared_metadata, result)
def test_compute_metadata_npm(self):
"""
testing only computation of metadata with hard_mapping_npm
"""
# given
content = b"""
{
"name": "test_metadata",
Morane Otilia Gruenpeter
committed
"description": "Simple package.json test for indexer",
"repository": {
"type": "git",
"url": "https://github.com/moranegg/metadata_test"
},
"author": {
"email": "moranegg@example.com",
"name": "Morane G"
Morane Otilia Gruenpeter
committed
}
}
"""
declared_metadata = {
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"name": "test_metadata",
"version": "0.0.2",
"description": "Simple package.json test for indexer",
"codeRepository": "git+https://github.com/moranegg/metadata_test",
"author": [
{"type": "Person", "name": "Morane G", "email": "moranegg@example.com",}
],
Morane Otilia Gruenpeter
committed
}
# when
result = self.npm_mapping.translate(content)
Morane Otilia Gruenpeter
committed
# then
self.assertEqual(declared_metadata, result)
def test_index_content_metadata_npm(self):
"""
testing NPM with package.json
- one sha1 uses a file that can't be translated to metadata and
should return None in the translated metadata
"""
# given
hash_to_bytes("26a9f72a7c87cc9205725cfd879f514ff4f3d8d5"),
hash_to_bytes("d4c647f0fc257591cc9ba1722484229780d1c607"),
hash_to_bytes("02fb2c89e14f7fab46701478c83779c7beb7b069"),
Morane Otilia Gruenpeter
committed
# this metadata indexer computes only metadata for package.json
# in npm context with a hard mapping
config = BASE_TEST_CONFIG.copy()
metadata_indexer = ContentMetadataTestIndexer(config=config)
fill_obj_storage(metadata_indexer.objstorage)
fill_storage(metadata_indexer.storage)
Morane Otilia Gruenpeter
committed
# when
metadata_indexer.run(sha1s, policy_update="ignore-dups")
results = list(metadata_indexer.idx_storage.content_metadata_get(sha1s))
expected_results = [
ContentMetadataRow(
id=hash_to_bytes("26a9f72a7c87cc9205725cfd879f514ff4f3d8d5"),
tool=TRANSLATOR_TOOL,
metadata={
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"codeRepository": "git+https://github.com/moranegg/metadata_test",
"description": "Simple package.json test for indexer",
"name": "test_metadata",
"version": "0.0.1",
},
),
ContentMetadataRow(
id=hash_to_bytes("d4c647f0fc257591cc9ba1722484229780d1c607"),
tool=TRANSLATOR_TOOL,
metadata={
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"issueTracker": "https://github.com/npm/npm/issues",
"author": [
{
"type": "Person",
"name": "Isaac Z. Schlueter",
"email": "i@izs.me",
"url": "http://blog.izs.me",
}
],
"codeRepository": "git+https://github.com/npm/npm",
"description": "a package manager for JavaScript",
"license": "https://spdx.org/licenses/Artistic-2.0",
"version": "5.0.3",
"name": "npm",
"keywords": [
"install",
"modules",
"package manager",
"package.json",
],
"url": "https://docs.npmjs.com/",
},
Morane Otilia Gruenpeter
committed
del result.tool["id"]
# The assertion below returns False sometimes because of nested lists
Morane Otilia Gruenpeter
committed
self.assertEqual(expected_results, results)
def test_npm_bugs_normalization(self):
# valid dictionary
package_json = b"""{
"name": "foo",
"bugs": {
"url": "https://github.com/owner/project/issues",
"email": "foo@example.com"
}
}"""
result = self.npm_mapping.translate(package_json)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"name": "foo",
"issueTracker": "https://github.com/owner/project/issues",
"type": "SoftwareSourceCode",
},
)
# "invalid" dictionary
package_json = b"""{
"name": "foo",
"bugs": {
"email": "foo@example.com"
}
}"""
result = self.npm_mapping.translate(package_json)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"name": "foo",
"type": "SoftwareSourceCode",
},
)
# string
package_json = b"""{
"name": "foo",
"bugs": "https://github.com/owner/project/issues"
}"""
result = self.npm_mapping.translate(package_json)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"name": "foo",
"issueTracker": "https://github.com/owner/project/issues",
"type": "SoftwareSourceCode",
},
)
def test_npm_repository_normalization(self):
# normal
package_json = b"""{
"name": "foo",
"repository": {
"type" : "git",
"url" : "https://github.com/npm/cli.git"
}
}"""
result = self.npm_mapping.translate(package_json)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"name": "foo",
"codeRepository": "git+https://github.com/npm/cli.git",
"type": "SoftwareSourceCode",
},
)
# missing url
package_json = b"""{
"name": "foo",
"repository": {
"type" : "git"
}
}"""
result = self.npm_mapping.translate(package_json)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"name": "foo",
"type": "SoftwareSourceCode",
},
)
# github shortcut
package_json = b"""{
"name": "foo",
"repository": "github:npm/cli"
}"""
result = self.npm_mapping.translate(package_json)
expected_result = {
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"name": "foo",
"codeRepository": "git+https://github.com/npm/cli.git",
"type": "SoftwareSourceCode",
}
self.assertEqual(result, expected_result)
# github shortshortcut
package_json = b"""{
"name": "foo",
"repository": "npm/cli"
}"""
result = self.npm_mapping.translate(package_json)
self.assertEqual(result, expected_result)
# gitlab shortcut
package_json = b"""{
"name": "foo",
"repository": "gitlab:user/repo"
}"""
result = self.npm_mapping.translate(package_json)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"name": "foo",
"codeRepository": "git+https://gitlab.com/user/repo.git",
"type": "SoftwareSourceCode",
},
)
def test_detect_metadata_package_json(self):
# given
df = [
{
"sha1_git": b"abc",
"name": b"index.js",
"target": b"abc",
"length": 897,
"status": "visible",
"type": "file",
"perms": 33188,
"dir_id": b"dir_a",
"sha1": b"bcd",
"sha1_git": b"aab",
"name": b"package.json",
"target": b"aab",
"length": 712,
"status": "visible",
"type": "file",
"perms": 33188,
"dir_id": b"dir_a",
"sha1": b"cde",
},
]
# when
results = detect_metadata(df)
# then
self.assertEqual(expected_results, results)
def test_compute_metadata_valid_codemeta(self):
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"@type": "SoftwareSourceCode",
"identifier": "CodeMeta",
"description": "CodeMeta is a concept vocabulary that can be used to standardize the exchange of software metadata across repositories and organizations.",
"name": "CodeMeta: Minimal metadata schemas for science software and code, in JSON-LD",
"codeRepository": "https://github.com/codemeta/codemeta",
"issueTracker": "https://github.com/codemeta/codemeta/issues",
"license": "https://spdx.org/licenses/Apache-2.0",
"version": "2.0",
"author": [
{
"@type": "Person",
"givenName": "Carl",
"familyName": "Boettiger",
"email": "cboettig@gmail.com",
"@id": "http://orcid.org/0000-0002-1642-628X"
},
{
"@type": "Person",
"givenName": "Matthew B.",
"familyName": "Jones",
"email": "jones@nceas.ucsb.edu",
"@id": "http://orcid.org/0000-0003-0077-4738"
}
],
"maintainer": {
"@type": "Person",
"givenName": "Carl",
"familyName": "Boettiger",
"email": "cboettig@gmail.com",
"@id": "http://orcid.org/0000-0002-1642-628X"
},
"contIntegration": "https://travis-ci.org/codemeta/codemeta",
"developmentStatus": "active",
"downloadUrl": "https://github.com/codemeta/codemeta/archive/2.0.zip",
"@id": "https://doi.org/10.13039/100000001",
"@type": "Organization",
"name": "National Science Foundation"
},
"funding":"1549758; Codemeta: A Rosetta Stone for Metadata in Scientific Software",
"keywords": [
"metadata",
"software"
],
"version":"2.0",
"dateCreated":"2017-06-05",
"datePublished":"2017-06-05",
"programmingLanguage": "JSON-LD"
expected_result = {
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"identifier": "CodeMeta",
"description": "CodeMeta is a concept vocabulary that can "
"be used to standardize the exchange of software metadata "
"across repositories and organizations.",
"name": "CodeMeta: Minimal metadata schemas for science "
"software and code, in JSON-LD",
"codeRepository": "https://github.com/codemeta/codemeta",
"issueTracker": "https://github.com/codemeta/codemeta/issues",
"license": "https://spdx.org/licenses/Apache-2.0",
"version": "2.0",
"author": [
{
"type": "Person",
"givenName": "Carl",
"familyName": "Boettiger",
"email": "cboettig@gmail.com",
"id": "http://orcid.org/0000-0002-1642-628X",
},
{
"type": "Person",
"givenName": "Matthew B.",
"familyName": "Jones",
"email": "jones@nceas.ucsb.edu",
"id": "http://orcid.org/0000-0003-0077-4738",
},
],
"maintainer": {
"type": "Person",
"givenName": "Carl",
"familyName": "Boettiger",
"email": "cboettig@gmail.com",
},
"contIntegration": "https://travis-ci.org/codemeta/codemeta",
"developmentStatus": "active",
"downloadUrl": "https://github.com/codemeta/codemeta/archive/2.0.zip",
"funder": {
"id": "https://doi.org/10.13039/100000001",
"type": "Organization",
},
"funding": "1549758; Codemeta: A Rosetta Stone for Metadata "
"in Scientific Software",
"keywords": ["metadata", "software"],
"version": "2.0",
"dateCreated": "2017-06-05",
"datePublished": "2017-06-05",
result = self.codemeta_mapping.translate(raw_content)
self.assertEqual(result, expected_result)
def test_compute_metadata_codemeta_alternate_context(self):
"@context": "https://raw.githubusercontent.com/codemeta/codemeta/master/codemeta.jsonld",
"@type": "SoftwareSourceCode",
"identifier": "CodeMeta"
expected_result = {
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"identifier": "CodeMeta",
}
result = self.codemeta_mapping.translate(raw_content)
self.assertEqual(result, expected_result)
def test_compute_metadata_maven(self):
raw_content = b"""
<project>
<name>Maven Default Project</name>
<modelVersion>4.0.0</modelVersion>
<groupId>com.mycompany.app</groupId>
<artifactId>my-app</artifactId>
<version>1.2.3</version>
<repositories>
<repository>
<id>central</id>
<name>Maven Repository Switchboard</name>
<layout>default</layout>
<url>http://repo1.maven.org/maven2</url>
<snapshots>
<enabled>false</enabled>
</snapshots>
</repository>
</repositories>
<licenses>
<license>
<name>Apache License, Version 2.0</name>
<url>https://www.apache.org/licenses/LICENSE-2.0.txt</url>
<distribution>repo</distribution>
<comments>A business-friendly OSS license</comments>
</license>
</licenses>
result = self.maven_mapping.translate(raw_content)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"name": "Maven Default Project",
"identifier": "com.mycompany.app",
"version": "1.2.3",
"license": "https://www.apache.org/licenses/LICENSE-2.0.txt",
"codeRepository": (
"http://repo1.maven.org/maven2/com/mycompany/app/my-app"
),
},
)
def test_compute_metadata_maven_empty(self):
raw_content = b"""
<project>
</project>"""
result = self.maven_mapping.translate(raw_content)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
},
)
def test_compute_metadata_maven_almost_empty(self):
raw_content = b"""
<project>
<foo/>
</project>"""
result = self.maven_mapping.translate(raw_content)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
},
)
def test_compute_metadata_maven_invalid_xml(self):
expected_warning = (
"WARNING:swh.indexer.metadata_dictionary.maven.MavenMapping:"
"Error parsing XML from foo"
)
raw_content = b"""
<project>"""
with self.assertLogs("swh.indexer.metadata_dictionary", level="WARNING") as cm:
result = MAPPINGS["MavenMapping"]("foo").translate(raw_content)
self.assertEqual(cm.output, [expected_warning])
self.assertEqual(result, None)
raw_content = b"""
"""
with self.assertLogs("swh.indexer.metadata_dictionary", level="WARNING") as cm:
result = MAPPINGS["MavenMapping"]("foo").translate(raw_content)
self.assertEqual(cm.output, [expected_warning])
self.assertEqual(result, None)
def test_compute_metadata_maven_unknown_encoding(self):
expected_warning = (
"WARNING:swh.indexer.metadata_dictionary.maven.MavenMapping:"
"Error detecting XML encoding from foo"
)
raw_content = b"""<?xml version="1.0" encoding="foo"?>
<project>
</project>"""
with self.assertLogs("swh.indexer.metadata_dictionary", level="WARNING") as cm:
result = MAPPINGS["MavenMapping"]("foo").translate(raw_content)
self.assertEqual(cm.output, [expected_warning])
self.assertEqual(result, None)
raw_content = b"""<?xml version="1.0" encoding="UTF-7"?>
<project>
</project>"""
with self.assertLogs("swh.indexer.metadata_dictionary", level="WARNING") as cm:
result = MAPPINGS["MavenMapping"]("foo").translate(raw_content)
self.assertEqual(cm.output, [expected_warning])
self.assertEqual(result, None)
def test_compute_metadata_maven_invalid_encoding(self):
expected_warning = (
"WARNING:swh.indexer.metadata_dictionary.maven.MavenMapping:"
"Error unidecoding XML from foo"
)
raw_content = b"""<?xml version="1.0" encoding="UTF-8"?>
<foo\xe5ct>
</foo>"""
with self.assertLogs("swh.indexer.metadata_dictionary", level="WARNING") as cm:
result = MAPPINGS["MavenMapping"]("foo").translate(raw_content)
self.assertEqual(cm.output, [expected_warning])
self.assertEqual(result, None)
def test_compute_metadata_maven_minimal(self):
raw_content = b"""
<project>
<name>Maven Default Project</name>
<modelVersion>4.0.0</modelVersion>
<groupId>com.mycompany.app</groupId>
<artifactId>my-app</artifactId>
<version>1.2.3</version>
</project>"""
result = self.maven_mapping.translate(raw_content)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"name": "Maven Default Project",
"identifier": "com.mycompany.app",
"version": "1.2.3",
"codeRepository": (
"https://repo.maven.apache.org/maven2/com/mycompany/app/my-app"
),
},
)
def test_compute_metadata_maven_empty_nodes(self):
raw_content = b"""
<project>
<name>Maven Default Project</name>
<modelVersion>4.0.0</modelVersion>
<groupId>com.mycompany.app</groupId>
<artifactId>my-app</artifactId>
<version>1.2.3</version>
<repositories>
</repositories>
</project>"""
result = self.maven_mapping.translate(raw_content)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"name": "Maven Default Project",
"identifier": "com.mycompany.app",
"version": "1.2.3",
"codeRepository": (
"https://repo.maven.apache.org/maven2/com/mycompany/app/my-app"
),
},
)
raw_content = b"""
<project>
<name>Maven Default Project</name>
<modelVersion>4.0.0</modelVersion>
<groupId>com.mycompany.app</groupId>
<artifactId>my-app</artifactId>
<version></version>
</project>"""
result = self.maven_mapping.translate(raw_content)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"name": "Maven Default Project",
"identifier": "com.mycompany.app",
"codeRepository": (
"https://repo.maven.apache.org/maven2/com/mycompany/app/my-app"
),
},
)
raw_content = b"""
<project>
<name></name>
<modelVersion>4.0.0</modelVersion>
<groupId>com.mycompany.app</groupId>
<artifactId>my-app</artifactId>
<version>1.2.3</version>
</project>"""
result = self.maven_mapping.translate(raw_content)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"identifier": "com.mycompany.app",
"version": "1.2.3",
"codeRepository": (
"https://repo.maven.apache.org/maven2/com/mycompany/app/my-app"
),
},
)
raw_content = b"""
<project>
<name>Maven Default Project</name>
<modelVersion>4.0.0</modelVersion>
<groupId>com.mycompany.app</groupId>
<artifactId>my-app</artifactId>
<version>1.2.3</version>
<licenses>
</licenses>
</project>"""
result = self.maven_mapping.translate(raw_content)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"name": "Maven Default Project",
"identifier": "com.mycompany.app",
"version": "1.2.3",
"codeRepository": (
"https://repo.maven.apache.org/maven2/com/mycompany/app/my-app"
),
},
)
raw_content = b"""
<project>
<groupId></groupId>
<version>1.2.3</version>
</project>"""
result = self.maven_mapping.translate(raw_content)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"version": "1.2.3",
},
)
def test_compute_metadata_maven_invalid_licenses(self):
raw_content = b"""
<project>
<name>Maven Default Project</name>
<modelVersion>4.0.0</modelVersion>
<groupId>com.mycompany.app</groupId>
<artifactId>my-app</artifactId>
<version>1.2.3</version>
<licenses>
foo
</licenses>
</project>"""
result = self.maven_mapping.translate(raw_content)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"name": "Maven Default Project",
"identifier": "com.mycompany.app",
"version": "1.2.3",
"codeRepository": (
"https://repo.maven.apache.org/maven2/com/mycompany/app/my-app"
),
},
)
def test_compute_metadata_maven_multiple(self):
"""Tests when there are multiple code repos and licenses."""
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
raw_content = b"""
<project>
<name>Maven Default Project</name>
<modelVersion>4.0.0</modelVersion>
<groupId>com.mycompany.app</groupId>
<artifactId>my-app</artifactId>
<version>1.2.3</version>
<repositories>
<repository>
<id>central</id>
<name>Maven Repository Switchboard</name>
<layout>default</layout>
<url>http://repo1.maven.org/maven2</url>
<snapshots>
<enabled>false</enabled>
</snapshots>
</repository>
<repository>
<id>example</id>
<name>Example Maven Repo</name>
<layout>default</layout>
<url>http://example.org/maven2</url>
</repository>
</repositories>
<licenses>
<license>
<name>Apache License, Version 2.0</name>
<url>https://www.apache.org/licenses/LICENSE-2.0.txt</url>
<distribution>repo</distribution>
<comments>A business-friendly OSS license</comments>
</license>
<license>
<name>MIT license</name>
<url>https://opensource.org/licenses/MIT</url>
</license>
</licenses>
</project>"""
result = self.maven_mapping.translate(raw_content)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"name": "Maven Default Project",
"identifier": "com.mycompany.app",
"version": "1.2.3",
"license": [
"https://www.apache.org/licenses/LICENSE-2.0.txt",
"https://opensource.org/licenses/MIT",
],
"codeRepository": [
"http://repo1.maven.org/maven2/com/mycompany/app/my-app",
"http://example.org/maven2/com/mycompany/app/my-app",
],
},
)
Metadata-Version: 2.1
Name: swh.core
Version: 0.0.49
Summary: Software Heritage core utilities
Home-page: https://forge.softwareheritage.org/diffusion/DCORE/
Author: Software Heritage developers
Author-email: swh-devel@inria.fr
License: UNKNOWN
Project-URL: Bug Reports, https://forge.softwareheritage.org/maniphest
Project-URL: Funding, https://www.softwareheritage.org/donate
Project-URL: Source, https://forge.softwareheritage.org/source/swh-core
Description: swh-core
========
core library for swh's modules:
- config parser
- hash computations
- serialization
- logging mechanism
Platform: UNKNOWN
Classifier: Programming Language :: Python :: 3
Classifier: Intended Audience :: Developers
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Operating System :: OS Independent
Classifier: Development Status :: 5 - Production/Stable
Description-Content-Type: text/markdown
Provides-Extra: testing
result = self.pkginfo_mapping.translate(raw_content)
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
self.assertCountEqual(
result["description"],
[
"Software Heritage core utilities", # note the comma here
"swh-core\n"
"========\n"
"\n"
"core library for swh's modules:\n"
"- config parser\n"
"- hash computations\n"
"- serialization\n"
"- logging mechanism\n"
"",
],
result,
)
del result["description"]
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"url": "https://forge.softwareheritage.org/diffusion/DCORE/",
"name": "swh.core",
"author": [
{
"type": "Person",
"name": "Software Heritage developers",
"email": "swh-devel@inria.fr",
}
],
"version": "0.0.49",
},
)
def test_compute_metadata_pkginfo_utf8(self):
Metadata-Version: 1.1
Name: snowpyt
Description-Content-Type: UNKNOWN
Description: foo
Hydrology N\xc2\xb083
result = self.pkginfo_mapping.translate(raw_content)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"name": "snowpyt",
"description": "foo\nHydrology N°83",
},
)
def test_compute_metadata_pkginfo_keywords(self):
Metadata-Version: 2.1
Name: foo
Keywords: foo bar baz
result = self.pkginfo_mapping.translate(raw_content)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"name": "foo",
"keywords": ["foo", "bar", "baz"],
},
)
def test_compute_metadata_pkginfo_license(self):
Metadata-Version: 2.1
Name: foo
License: MIT
result = self.pkginfo_mapping.translate(raw_content)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"name": "foo",
"license": "MIT",
},
)
def test_gemspec_base(self):
raw_content = b"""
Gem::Specification.new do |s|
s.name = 'example'
s.version = '0.1.0'
s.licenses = ['MIT']
s.summary = "This is an example!"
s.description = "Much longer explanation of the example!"
s.authors = ["Ruby Coder"]
s.email = 'rubycoder@example.com'
s.files = ["lib/example.rb"]
s.homepage = 'https://rubygems.org/gems/example'
s.metadata = { "source_code_uri" => "https://github.com/example/example" }
end"""
result = self.gemspec_mapping.translate(raw_content)
self.assertCountEqual(
result.pop("description"),
["This is an example!", "Much longer explanation of the example!"],
)
self.assertEqual(
result,
{
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",
"author": [{"type": "Person", "name": "Ruby Coder"}],
"name": "example",
"license": "https://spdx.org/licenses/MIT",
"codeRepository": "https://rubygems.org/gems/example",
"email": "rubycoder@example.com",
"version": "0.1.0",
},
)
def test_gemspec_two_author_fields(self):
raw_content = b"""
Gem::Specification.new do |s|
s.authors = ["Ruby Coder1"]
s.author = "Ruby Coder2"
end"""
result = self.gemspec_mapping.translate(raw_content)
self.assertCountEqual(
result.pop("author"),
[
{"type": "Person", "name": "Ruby Coder1"},
{"type": "Person", "name": "Ruby Coder2"},
],
)
self.assertEqual(
result,
"@context": "https://doi.org/10.5063/schema/codemeta-2.0",
"type": "SoftwareSourceCode",