Differential D1720 Diff 6220 swh/indexer/tests/test_fossology_license.py

Changeset View

Standalone View

swh/indexer/tests/test_fossology_license.py

# Copyright (C) 2017-2018 The Software Heritage developers		# Copyright (C) 2017-2018 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 unittest		import unittest
from unittest.mock import patch		from unittest.mock import patch

import pytest		import pytest

		from swh.model.hashutil import hash_to_bytes
from swh.indexer import fossology_license		from swh.indexer import fossology_license
from swh.indexer.fossology_license import (		from swh.indexer.fossology_license import (
FossologyLicenseIndexer, FossologyLicenseRangeIndexer,		FossologyLicenseIndexer, FossologyLicenseRangeIndexer,
compute_license		compute_license
)		)

from swh.indexer.tests.utils import (		from swh.indexer.tests.utils import (
SHA1_TO_LICENSES, CommonContentIndexerTest, CommonContentIndexerRangeTest,		SHA1_TO_LICENSES, CommonContentIndexerTest, CommonContentIndexerRangeTest,
▲ Show 20 Lines • Show All 56 Lines • ▼ Show 20 Lines	class TestFossologyLicenseIndexer(CommonContentIndexerTest, unittest.TestCase):
"""Language indexer test scenarios:		"""Language indexer test scenarios:

- Known sha1s in the input list have their data indexed		- Known sha1s in the input list have their data indexed
- Unknown sha1 in the input list are not indexed		- Unknown sha1 in the input list are not indexed

"""		"""

def get_indexer_results(self, ids):		def get_indexer_results(self, ids):
yield from self.idx_storage.content_fossology_license_get(ids)		return self.idx_storage.content_fossology_license_get(ids)

def setUp(self):		def setUp(self):
super().setUp()		super().setUp()
# replace actual license computation with a mock		# replace actual license computation with a mock
self.orig_compute_license = fossology_license.compute_license		self.orig_compute_license = fossology_license.compute_license
fossology_license.compute_license = mock_compute_license		fossology_license.compute_license = mock_compute_license

self.indexer = FossologyLicenseIndexer(CONFIG)		self.indexer = FossologyLicenseIndexer(CONFIG)
self.indexer.catch_exceptions = False		self.indexer.catch_exceptions = False
self.idx_storage = self.indexer.idx_storage		self.idx_storage = self.indexer.idx_storage
fill_storage(self.indexer.storage)		fill_storage(self.indexer.storage)
fill_obj_storage(self.indexer.objstorage)		fill_obj_storage(self.indexer.objstorage)

self.id0 = '01c9379dfc33803963d07c1ccc748d3fe4c96bb5'		self.id0 = '01c9379dfc33803963d07c1ccc748d3fe4c96bb5'
self.id1 = '688a5ef812c53907562fe379d4b3851e69c7cb15'		self.id1 = '688a5ef812c53907562fe379d4b3851e69c7cb15'
self.id2 = 'da39a3ee5e6b4b0d3255bfef95601890afd80709' # empty content		self.id2 = 'da39a3ee5e6b4b0d3255bfef95601890afd80709' # empty content

tool = {k.replace('tool_', ''): v		tool = {k.replace('tool_', ''): v
for (k, v) in self.indexer.tool.items()}		for (k, v) in self.indexer.tool.items()}
# then		# then
self.expected_results = {		self.expected_results = {
self.id0: {		self.id0: [{
'tool': tool,		'tool': tool,
'licenses': SHA1_TO_LICENSES[self.id0],		'licenses': SHA1_TO_LICENSES[self.id0],
},		}],
self.id1: {		self.id1: [{
'tool': tool,		'tool': tool,
'licenses': SHA1_TO_LICENSES[self.id1],		'licenses': SHA1_TO_LICENSES[self.id1],
},		}],
self.id2: {		self.id2: [{
'tool': tool,		'tool': tool,
'licenses': SHA1_TO_LICENSES[self.id2],		'licenses': SHA1_TO_LICENSES[self.id2],
}		}]
}		}

def tearDown(self):		def tearDown(self):
super().tearDown()		super().tearDown()
fossology_license.compute_license = self.orig_compute_license		fossology_license.compute_license = self.orig_compute_license

		def assert_results_ok(self, sha1s, expected_results=None):
		if self.legacy_get_format:
		self.assert_legacy_results_ok(sha1s, expected_results)
		return
		vlorentzAuthorUnsubmitted Done Inline Actions This conditional is not needed vlorentz: This conditional is not needed

		sha1s = [sha1 if isinstance(sha1, bytes) else hash_to_bytes(sha1)
		for sha1 in sha1s]
		vlorentzAuthorUnsubmitted Done Inline Actions Neither is this one vlorentz: Neither is this one
		actual_results = self.get_indexer_results(sha1s)

		if expected_results is None:
		expected_results = self.expected_results
		vlorentzAuthorUnsubmitted Done Inline Actions I'm not sure this one is either vlorentz: I'm not sure this one is either

		for _id, indexed_data in expected_results.items():
		actual_data = actual_results[hash_to_bytes(_id)]
		self.assertEqual(indexed_data, actual_data)
		vlorentzAuthorUnsubmitted Done Inline Actions You can replace this for loop with simply: `self.assertEqual(expected_results, actual_results)`. This will also check there is no extra/unwanted items in `actual_results`. vlorentz: You can replace this for loop with simply: `self.assertEqual(expected_results, actual_results)`.


class TestFossologyLicenseRangeIndexer(		class TestFossologyLicenseRangeIndexer(
CommonContentIndexerRangeTest, unittest.TestCase):		CommonContentIndexerRangeTest, unittest.TestCase):
"""Range Fossology License Indexer tests.		"""Range Fossology License Indexer tests.

- new data within range are indexed		- new data within range are indexed
- no data outside a range are indexed		- no data outside a range are indexed
- with filtering existing indexed data prior to compute new index		- with filtering existing indexed data prior to compute new index
▲ Show 20 Lines • Show All 50 Lines • Show Last 20 Lines