Newer
Older
# Copyright (C) 2017-2018 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
import attr
from hypothesis import given, strategies, settings, HealthCheck
from swh.model.hashutil import hash_to_bytes
from swh.indexer.codemeta import CODEMETA_TERMS, CROSSWALK_TABLE
from swh.indexer.codemeta import merge_documents
from swh.indexer.metadata_dictionary import MAPPINGS
from swh.indexer.metadata_dictionary.base import merge_values
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.metadata_detector import (
)
from swh.indexer.metadata import (
ContentMetadataIndexer, RevisionMetadataIndexer
)

vlorentz
committed
BASE_TEST_CONFIG, fill_obj_storage, fill_storage,
YARN_PARSER_METADATA, json_document_strategy,
xml_document_strategy,
TRANSLATOR_TOOL = {
'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.
"""
def parse_config_file(self, *args, **kwargs):
assert False, 'should not be called; the rev indexer configures it.'
REVISION_METADATA_CONFIG = {
**BASE_TEST_CONFIG,
'tools': TRANSLATOR_TOOL,
}
Morane Otilia Gruenpeter
committed
class Metadata(unittest.TestCase):
"""
Tests metadata_mock_tool tool for Metadata detection
"""
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_crosstable(self):
self.assertEqual(CROSSWALK_TABLE['NodeJS'], {
'repository': 'http://schema.org/codeRepository',
'os': 'http://schema.org/operatingSystem',
'cpu': 'http://schema.org/processorRequirements',
'http://schema.org/processorRequirements',
'author': 'http://schema.org/author',
'author.email': 'http://schema.org/email',
'author.name': 'http://schema.org/name',
'contributor': 'http://schema.org/contributor',
'keywords': 'http://schema.org/keywords',
'license': 'http://schema.org/license',
'version': 'http://schema.org/version',
'description': 'http://schema.org/description',
'name': 'http://schema.org/name',
'bugs': 'https://codemeta.github.io/terms/issueTracker',
def test_merge_values(self):
self.assertEqual(
merge_values('a', 'b'),
['a', 'b'])
self.assertEqual(
merge_values(['a', 'b'], 'c'),
['a', 'b', 'c'])
self.assertEqual(
merge_values('a', ['b', 'c']),
['a', 'b', 'c'])
self.assertEqual(
merge_values({'@list': ['a']}, {'@list': ['b']}),
{'@list': ['a', 'b']})
self.assertEqual(
merge_values({'@list': ['a', 'b']}, {'@list': ['c']}),
{'@list': ['a', 'b', 'c']})
with self.assertRaises(ValueError):
merge_values({'@list': ['a']}, 'b')
with self.assertRaises(ValueError):
merge_values('a', {'@list': ['b']})
with self.assertRaises(ValueError):
merge_values({'@list': ['a']}, ['b'])
with self.assertRaises(ValueError):
merge_values(['a'], {'@list': ['b']})
self.assertEqual(
merge_values('a', None),
'a')
self.assertEqual(
merge_values(['a', 'b'], None),
['a', 'b'])
self.assertEqual(
merge_values(None, ['b', 'c']),
['b', 'c'])
self.assertEqual(
merge_values({'@list': ['a']}, None),
{'@list': ['a']})
self.assertEqual(
merge_values(None, {'@list': ['a']}),
{'@list': ['a']})
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',
'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)
"""
Test the creation of a coherent minimal metadata set
"""
# given
metadata_list = [{
'@context': 'https://doi.org/10.5063/schema/codemeta-2.0',
'name': 'test_1',
'version': '0.0.2',
'description': 'Simple package.json test for indexer',
'codeRepository':
'git+https://github.com/moranegg/metadata_test',
'@context': 'https://doi.org/10.5063/schema/codemeta-2.0',
'name': 'test_0_1',
'version': '0.0.2',
'description': 'Simple package.json test for indexer',
'codeRepository':
'@context': 'https://doi.org/10.5063/schema/codemeta-2.0',
'name': 'test_metadata',
'version': '0.0.2',
'author': {
'type': 'Person',
'name': 'moranegg',
},
}]
# when
results = merge_documents(metadata_list)
# then
expected_results = {
'@context': 'https://doi.org/10.5063/schema/codemeta-2.0',
"version": '0.0.2',
"description": 'Simple package.json test for indexer',
"name": ['test_1', 'test_0_1', 'test_metadata'],
"author": [{
'type': 'Person',
'name': 'moranegg'
}],
"codeRepository":
'git+https://github.com/moranegg/metadata_test',
}
self.assertEqual(expected_results, results)
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
def test_merge_documents_ids(self):
# given
metadata_list = [{
'@context': 'https://doi.org/10.5063/schema/codemeta-2.0',
'id': 'http://example.org/test1',
'name': 'test_1',
}, {
'@context': 'https://doi.org/10.5063/schema/codemeta-2.0',
'id': 'http://example.org/test2',
'name': 'test_2',
}]
# when
results = merge_documents(metadata_list)
# then
expected_results = {
'@context': 'https://doi.org/10.5063/schema/codemeta-2.0',
'id': 'http://example.org/test1',
'schema:sameAs': 'http://example.org/test2',
"name": ['test_1', 'test_2']
}
self.assertEqual(expected_results, results)
def test_merge_documents_duplicate_ids(self):
# given
metadata_list = [{
'@context': 'https://doi.org/10.5063/schema/codemeta-2.0',
'id': 'http://example.org/test1',
'name': 'test_1',
}, {
'@context': 'https://doi.org/10.5063/schema/codemeta-2.0',
'id': 'http://example.org/test1',
'name': 'test_1b',
}, {
'@context': 'https://doi.org/10.5063/schema/codemeta-2.0',
'id': 'http://example.org/test2',
'name': 'test_2',
}]
# when
results = merge_documents(metadata_list)
# then
expected_results = {
'@context': 'https://doi.org/10.5063/schema/codemeta-2.0',
'id': 'http://example.org/test1',
'schema:sameAs': 'http://example.org/test2',
"name": ['test_1', 'test_1b', 'test_2']
}
self.assertEqual(expected_results, results)
Morane Otilia Gruenpeter
committed
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
sha1s = [
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()
config['tools'] = [TRANSLATOR_TOOL]
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))
Morane Otilia Gruenpeter
committed
'@context': 'https://doi.org/10.5063/schema/codemeta-2.0',
'codeRepository':
'git+https://github.com/moranegg/metadata_test',
'description': 'Simple package.json test for indexer',
'name': 'test_metadata',
'version': '0.0.1'
Morane Otilia Gruenpeter
committed
},
'id': hash_to_bytes('26a9f72a7c87cc9205725cfd879f514ff4f3d8d5'),
Morane Otilia Gruenpeter
committed
}, {
'@context': 'https://doi.org/10.5063/schema/codemeta-2.0',
'issueTracker':
'type': 'Person',
'name': 'Isaac Z. Schlueter',
'email': 'i@izs.me',
'url': 'http://blog.izs.me',
}],
'codeRepository':
'description': 'a package manager for JavaScript',
'license': 'https://spdx.org/licenses/Artistic-2.0',
'version': '5.0.3',
'name': 'npm',
'keywords': [
Morane Otilia Gruenpeter
committed
'install',
'modules',
'package manager',
'package.json'
],
'url': 'https://docs.npmjs.com/'
Morane Otilia Gruenpeter
committed
},
'id': hash_to_bytes('d4c647f0fc257591cc9ba1722484229780d1c607')
}]
Morane Otilia Gruenpeter
committed
# 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',
})
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
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)
expected_results = {
'NpmMapping': [
b'cde'
]
}
# then
self.assertEqual(expected_results, results)
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
def test_compute_metadata_valid_codemeta(self):
raw_content = (
b"""{
"@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",
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
"@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"
}""") # noqa
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",
"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",
"funder": {
"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"
}
result = self.codemeta_mapping.translate(raw_content)
self.assertEqual(result, expected_result)
def test_compute_metadata_codemeta_alternate_context(self):
raw_content = (
b"""{
"@context": "https://raw.githubusercontent.com/codemeta/codemeta/master/codemeta.jsonld",
"@type": "SoftwareSourceCode",
"identifier": "CodeMeta"
}""") # noqa
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',
'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',
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
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
})
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',
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
})
def test_compute_metadata_maven_multiple(self):
'''Tests when there are multiple code repos and licenses.'''
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',
]
})
def test_compute_metadata_pkginfo(self):
raw_content = (b"""\
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
""") # noqa
result = self.pkginfo_mapping.translate(raw_content)
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',
}],