def test_usage_and_help_return_a_correct_script_name_on_all_platforms():
result = run_scan_click(['--help'])
assert 'Usage: scancode [OPTIONS]' in result.output
# this was showing up on Windows
assert 'scancode-script.py' not in result.output
result = run_scan_click([])
assert 'Usage: scancode [OPTIONS]' in result.output
# this was showing up on Windows
assert 'scancode-script.py' not in result.output
result = run_scan_click(['-xyz'])
# this was showing up on Windows
assert 'scancode-script.py' not in result.output
def test_scan_works_with_multiple_processes():
test_dir = test_env.get_test_loc('multiprocessing', copy=True)
# run the same scan with one or three processes
result_file_1 = test_env.get_temp_file('json')
result1 = run_scan_click([ '--copyright', '--processes', '1', '--format', 'json', test_dir, result_file_1])
assert result1.exit_code == 0
result_file_3 = test_env.get_temp_file('json')
result3 = run_scan_click([ '--copyright', '--processes', '3', '--format', 'json', test_dir, result_file_3])
assert result3.exit_code == 0
res1 = json.loads(open(result_file_1).read())
res3 = json.loads(open(result_file_3).read())
assert sorted(res1['files']) == sorted(res3['files'])
def test_scan_works_with_no_processes_in_single_threaded_mode():
test_dir = test_env.get_test_loc('multiprocessing', copy=True)
# run the same scan with zero or one process
result_file_0 = test_env.get_temp_file('json')
result0 = run_scan_click([ '--copyright', '--processes', '0', '--format', 'json', test_dir, result_file_0])
assert result0.exit_code == 0
assert 'Disabling multi-processing and multi-threading...' in result0.output
result_file_1 = test_env.get_temp_file('json')
result1 = run_scan_click([ '--copyright', '--processes', '1', '--format', 'json', test_dir, result_file_1])
assert result1.exit_code == 0
res0 = json.loads(open(result_file_0).read())
res1 = json.loads(open(result_file_1).read())
assert sorted(res0['files']) == sorted(res1['files'])
def test_scan_quiet_to_stdout_only_echoes_json_results():
test_dir = test_env.extract_test_tar('info/basic.tgz')
result1_file = test_env.get_temp_file('json')
result1 = run_scan_click(['--quiet', '--info', test_dir, result1_file])
assert result1.exit_code == 0
assert not result1.output
# also test with an output of JSON to stdout
result2 = run_scan_click(['--quiet', '--info', test_dir])
assert result2.exit_code == 0
# outputs to file or stdout should be identical
result1_output = open(result1_file).read()
assert result1_output == result2.output
def test_scan_only_findings(monkeypatch):
test_dir = test_env.extract_test_tar('info/basic.tgz')
result_file = test_env.get_temp_file('json')
expected_file = test_env.get_test_loc('only_findings/expected.json')
_result = run_scan_click(['--only-findings', test_dir, result_file], monkeypatch)
check_json_scan(expected_file, result_file)
def test_scan_mark_source_with_info(monkeypatch):
test_dir = test_env.extract_test_tar('mark_source/JGroups.tgz')
result_file = test_env.get_temp_file('json')
expected_file = test_env.get_test_loc('mark_source/with_info.expected.json')
_result = run_scan_click(['--info', '--mark-source', test_dir, result_file], monkeypatch)
check_json_scan(expected_file, result_file)
def test_custom_html_output_can_handle_non_ascii_paths():
test_file = test_env.get_test_loc('unicode.json')
result_file = test_env.get_temp_file(extension='html',
file_name='test_html')
custom_template = test_env.get_test_loc('templated/sample-template.html')
args = [
'--from-json', test_file, '--custom-template', custom_template,
'--custom-output', result_file
]
run_scan_click(args)
with io.open(result_file, encoding='utf-8') as res:
results = res.read()
assert '<td>han/据.svg</td>' in results
def test_scan_license_with_url_template():
test_dir = test_env.get_test_loc('plugin_license/license_url', copy=True)
result_file = test_env.get_temp_file('json')
args = [
'--license',
'--license-url-template',
'https://example.com/urn:{}',
'--unknown-licenses',
'--json-pp',
result_file,
test_dir,
]
test_loc = test_env.get_test_loc(
'plugin_license/license_url.expected.json')
run_scan_click(args)
check_json_scan(test_loc, result_file, regen=False)
def test_spdx_rdf_tree():
test_dir = test_env.get_test_loc('spdx/tree/scan')
result_file = test_env.get_temp_file('rdf')
expected_file = test_env.get_test_loc('spdx/tree/expected.rdf')
result = run_scan_click(['--format', 'spdx-rdf', test_dir, result_file])
assert result.exit_code == 0
check_rdf_scan(expected_file, result_file)
def test_package_list_command(self, regen=REGEN_TEST_FIXTURES):
expected_file = self.get_test_loc('plugin/help.txt')
result = run_scan_click(['--list-packages'])
if regen:
with open(expected_file, 'w') as ef:
ef.write(result.output)
assert result.output == open(expected_file).read()
def test_scan_can_handle_licenses_with_unicode_metadata():
test_dir = test_env.get_test_loc('license_with_unicode_meta')
result_file = test_env.get_temp_file('json')
result = run_scan_click(['--license', test_dir, result_file])
assert result.exit_code == 0
assert 'Scanning done' in result.output
def test_scan_does_not_fail_when_scanning_unicode_files_and_paths():
test_dir = test_env.get_test_loc(u'unicodepath/uc')
result_file = test_env.get_temp_file('json')
if on_linux:
test_dir = path_to_bytes(test_dir)
result_file = path_to_bytes(result_file)
args = ['--info', '--license', '--copyright',
'--package', '--email', '--url', '--strip-root',
test_dir , result_file]
result = run_scan_click(args)
if result.exit_code != 0:
raise Exception(result.output, args)
assert result.exit_code == 0
assert 'Scanning done' in result.output
# the paths for each OS end up encoded differently.
# See for details:
# https://github.com/nexB/scancode-toolkit/issues/390
# https://github.com/nexB/scancode-toolkit/issues/688
if on_linux:
expected = 'unicodepath/unicodepath.expected-linux.json'
elif on_mac:
expected = 'unicodepath/unicodepath.expected-mac.json'
elif on_windows:
expected = 'unicodepath/unicodepath.expected-win.json'
check_json_scan(test_env.get_test_loc(expected), result_file, strip_dates=True, regen=False)
def test_scan_quiet_to_file_does_not_echo_anything():
test_dir = test_env.extract_test_tar('info/basic.tgz')
result1_file = test_env.get_temp_file('json')
result1 = run_scan_click(['--quiet', '--info', test_dir, result1_file])
assert result1.exit_code == 0
assert not result1.output
def test_scan_works_with_multiple_processes_and_timeouts():
# this contains test files with a lot of copyrights that should
# take more thant timeout to scan
test_dir = test_env.get_test_loc('timeout', copy=True)
# add some random bytes to the test files to ensure that the license results will
# not be cached
import time, random
for tf in fileutils.file_iter(test_dir):
with open(tf, 'ab') as tfh:
tfh.write('(c)' + str(time.time()) + repr([random.randint(0, 10 ** 6) for _ in range(10000)]) + '(c)')
result_file = test_env.get_temp_file('json')
result = run_scan_click(
[ '--copyright', '--processes', '2',
'--timeout', '0.000001',
'--strip-root', '--format', 'json', test_dir, result_file],
)
assert result.exit_code == 1
assert 'Scanning done' in result.output
expected = [
[(u'path', u'test1.txt'), (u'scan_errors', [u'ERROR: Processing interrupted: timeout after 0 seconds.'])],
[(u'path', u'test2.txt'), (u'scan_errors', [u'ERROR: Processing interrupted: timeout after 0 seconds.'])],
[(u'path', u'test3.txt'), (u'scan_errors', [u'ERROR: Processing interrupted: timeout after 0 seconds.'])],
]
result_json = json.loads(open(result_file).read(), object_pairs_hook=OrderedDict)
assert sorted(expected) == sorted(x.items() for x in result_json['files'])
def test_scan_does_not_fail_when_scanning_unicode_test_files_from_express():
# On Windows, Python tar cannot extract these files. Other
# extractors either fail or change the file name, making the test
# moot. Git cannot check these files. So for now it makes no sense
# to test this on Windows at all. Extractcode works fine, but does
# rename the problematic files.
test_dir = test_env.extract_test_tar_raw(b'unicode_fixtures.tar.gz')
test_dir = fsencode(test_dir)
args = [
'-n0', '--info', '--license', '--copyright', '--package', '--email',
'--url', '--strip-root', '--json', '-', test_dir
]
run_scan_click(args)
def test_scan_does_not_fail_when_scanning_unicode_files_and_paths():
test_dir = test_env.get_test_loc(u'unicodepath/uc')
result_file = test_env.get_temp_file('json')
if on_linux:
test_dir = path_to_bytes(test_dir)
result_file = path_to_bytes(result_file)
args = [
'--info', '--license', '--copyright', '--package', '--email', '--url',
'--strip-root', test_dir, result_file
]
result = run_scan_click(args)
if result.exit_code != 0:
raise Exception(result.output, args)
assert result.exit_code == 0
assert 'Scanning done' in result.output
# the paths for each OS end up encoded differently.
# See for details:
# https://github.com/nexB/scancode-toolkit/issues/390
# https://github.com/nexB/scancode-toolkit/issues/688
if on_linux:
expected = 'unicodepath/unicodepath.expected-linux.json'
elif on_mac:
expected = 'unicodepath/unicodepath.expected-mac.json'
elif on_windows:
expected = 'unicodepath/unicodepath.expected-win.json'
check_json_scan(test_env.get_test_loc(expected),
result_file,
strip_dates=True,
regen=False)
def test_csv_tree():
test_dir = test_env.get_test_loc('csv/tree/scan')
result_file = test_env.get_temp_file('csv')
expected_file = test_env.get_test_loc('csv/tree/expected.csv')
result = run_scan_click(['--copyright', '--format', 'csv', test_dir, result_file])
assert result.exit_code == 0
check_csvs(result_file, expected_file)
def test_scan_can_handle_non_utf8_file_names_on_posix():
test_dir = test_env.extract_test_tar_raw('non_utf8/non_unicode.tgz')
result_file = test_env.get_temp_file('json')
if on_linux:
test_dir = path_to_bytes(test_dir)
result_file = path_to_bytes(result_file)
result = run_scan_click(['-i', '--strip-root', test_dir, result_file])
assert result.exit_code == 0
assert 'Scanning done' in result.output
# the paths for each OS end up encoded differently.
# See for details:
# https://github.com/nexB/scancode-toolkit/issues/390
# https://github.com/nexB/scancode-toolkit/issues/688
if on_linux:
expected = 'non_utf8/expected-linux.json'
elif on_mac:
expected = 'non_utf8/expected-mac.json'
elif on_windows:
expected = 'non_utf8/expected-win.json'
check_json_scan(test_env.get_test_loc(expected), result_file, regen=False)
def test_license_option_reports_license_texts():
test_dir = test_env.get_test_loc('plugin_license/text/scan', copy=True)
result_file = test_env.get_temp_file('json')
args = [
'--license',
'--license-text',
'--strip-root',
'--verbose',
'--json',
result_file,
test_dir,
]
run_scan_click(args)
test_loc = test_env.get_test_loc('plugin_license/text/scan.expected.json')
check_json_scan(test_loc, result_file, regen=False)
def test_scan_progress_display_is_not_damaged_with_long_file_names(
monkeypatch):
test_dir = test_env.get_test_loc('long_file_name')
result_file = test_env.get_temp_file('json')
args = ['--copyright', test_dir, '--json', result_file]
result = run_scan_click(args, monkeypatch=monkeypatch)
if on_windows:
expected1 = 'Scanned: 0123456789012345678901234567890123456789.c'
expected2 = 'Scanned: abcdefghijklmnopqrt...0123456789012345678'
expected3 = 'abcdefghijklmnopqrtu0123456789012345678901234567890123456789abcdefghijklmnopqrtu0123456789012345678901234567890123456789.c'
try:
assert expected1 in result.output
assert expected2 not in result.output
assert expected3 not in result.output
except:
print()
print('output:')
print(result.output)
print()
raise
else:
expected1 = 'Scanned: abcdefghijklmnopqr...234567890123456789.c'
expected2 = 'Scanned: 0123456789012345678901234567890123456789.c'
expected3 = 'abcdefghijklmnopqrtu0123456789012345678901234567890123456789abcdefghijklmnopqrtu0123456789012345678901234567890123456789.c'
assert expected1 in result.output
assert expected2 in result.output
assert expected3 not in result.output
def test_custom_format_with_custom_filename_fails_for_directory():
test_dir = test_env.get_temp_dir('html')
result_file = test_env.get_temp_file('html')
result = run_scan_click(['--format', test_dir, test_dir, result_file])
assert result.exit_code != 0
assert 'Unknwow <format> or invalid template file path' in result.output
def test_scan_to_json_without_FILE_does_not_write_to_next_option():
test_file = test_env.get_test_loc('license_text/test.txt')
args = ['--json', '--info', test_file]
result = run_scan_click(args, expected_rc=2)
assert ('Error: Invalid value for "--json": Illegal file name '
'conflicting with an option name: --info.').replace(
"'", '"') in result.output.replace("'", '"')
def test_VirtualCodebase_output_with_from_json_is_same_as_original():
test_file = test_env.get_test_loc('virtual_idempotent/codebase.json')
result_file = test_env.get_temp_file('json')
args = ['--from-json', test_file, '--json-pp', result_file]
run_scan_click(args)
expected = load_json_result(test_file, remove_file_date=True)
results = load_json_result(result_file, remove_file_date=True)
expected.pop('summary', None)
results.pop('summary', None)
expected_headers = expected.pop('headers', [])
results_headers = results.pop('headers', [])
assert json.dumps(results, indent=2) == json.dumps(expected, indent=2)
assert len(results_headers) == len(expected_headers) + 1
def test_spdx_tv_basic():
test_dir = test_env.get_test_loc('spdx/simple/test.txt')
result_file = test_env.get_temp_file('tv')
expected_file = test_env.get_test_loc('spdx/simple/expected.tv')
result = run_scan_click(['--format', 'spdx-tv', test_dir, result_file])
assert result.exit_code == 0
check_tv_scan(expected_file, result_file)
def test_scan_can_handle_non_utf8_file_names_on_posix():
test_dir = test_env.extract_test_tar_raw('non_utf8/non_unicode.tgz')
result_file = test_env.get_temp_file('json')
if on_linux:
test_dir = path_to_bytes(test_dir)
result_file = path_to_bytes(result_file)
result = run_scan_click(['-i', '--strip-root', test_dir, result_file])
assert result.exit_code == 0
assert 'Scanning done' in result.output
# the paths for each OS end up encoded differently.
# See for details:
# https://github.com/nexB/scancode-toolkit/issues/390
# https://github.com/nexB/scancode-toolkit/issues/688
if on_linux:
expected = 'non_utf8/expected-linux.json'
elif on_mac:
expected = 'non_utf8/expected-mac.json'
elif on_windows:
expected = 'non_utf8/expected-win.json'
check_json_scan(test_env.get_test_loc(expected), result_file, regen=False)
def check_scan_does_not_fail_when_scanning_unicode_files_and_paths(verbosity):
test_dir = test_env.get_test_loc(u'unicodepath/uc')
result_file = test_env.get_temp_file('json')
if on_linux and py2:
test_dir = fsencode(test_dir)
result_file = fsencode(result_file)
args = [
'--info', '--license', '--copyright', '--package', '--email', '--url',
'--strip-root', test_dir, '--json', result_file
] + ([verbosity] if verbosity else [])
results = run_scan_click(args)
# the paths for each OS ends up encoded differently.
# See for details:
# https://github.com/nexB/scancode-toolkit/issues/390
# https://github.com/nexB/scancode-toolkit/issues/688
# https://github.com/nexB/scancode-toolkit/issues/1635
if on_macos_14_or_higher:
expected = 'unicodepath/unicodepath.expected-mac14.json' + verbosity
elif on_linux:
expected = 'unicodepath/unicodepath.expected-linux.json' + verbosity
elif on_mac:
expected = 'unicodepath/unicodepath.expected-mac.json' + verbosity
elif on_windows:
expected = 'unicodepath/unicodepath.expected-win.json' + verbosity
check_json_scan(test_env.get_test_loc(expected),
result_file,
remove_file_date=True,
regen=False)
return results
def test_custom_format_with_custom_filename_fails_for_directory():
test_dir = test_env.get_temp_dir('html')
result_file = test_env.get_temp_file('html')
result = run_scan_click(['--format', test_dir, test_dir, result_file])
assert result.exit_code != 0
assert 'Unknwow <format> or invalid template file path' in result.output
def test_scan_cli_help(regen=False):
expected_file = test_env.get_test_loc('help/help.txt')
result = run_scan_click(['--help'])
if regen:
with io.open(expected_file, 'w', encoding='utf-8') as ef:
ef.write(result.output)
assert open(expected_file).read() == result.output
def test_scan_info_returns_full_root():
test_dir = test_env.extract_test_tar('info/basic.tgz')
result = run_scan_click(['--info', '--full-root', test_dir])
assert result.exit_code == 0
assert 'Scanning done' in result.output
assert fileutils.as_posixpath(test_dir) in result.output
def test_scan_can_handle_licenses_with_unicode_metadata():
test_dir = test_env.get_test_loc('license_with_unicode_meta')
result_file = test_env.get_temp_file('json')
result = run_scan_click(['--license', test_dir, result_file])
assert result.exit_code == 0
assert 'Scanning done' in result.output
def test_scancode_ignore_glob_path(self):
test_dir = self.extract_test_tar('plugin_ignore/user.tgz')
result_file = self.get_temp_file('json')
args = ['--copyright', '--strip-root', '--ignore', '*/src/test/*', test_dir, '--json', result_file]
run_scan_click(args)
scan_result = load_json_result(result_file)
assert 2 == scan_result['headers'][0]['extra_data']['files_count']
scan_locs = [x['path'] for x in scan_result['files']]
expected = [
u'user',
u'user/ignore.doc',
u'user/src',
u'user/src/ignore.doc',
u'user/src/test'
]
assert expected == scan_locs
def test_scan_quiet_to_file_does_not_echo_anything():
test_dir = test_env.extract_test_tar('info/basic.tgz')
result1_file = test_env.get_temp_file('json')
result1 = run_scan_click(['--quiet', '--info', test_dir, result1_file])
assert result1.exit_code == 0
assert not result1.output
def test_spdx_tv_with_license_ref_with_text():
test_dir = test_env.get_test_loc('spdx/license_ref/scan')
result_file = test_env.get_temp_file('tv')
expected_file = test_env.get_test_loc('spdx/license_ref/expected_with_text.tv')
result = run_scan_click(['--format', 'spdx-tv', '--license-text', test_dir, result_file])
assert result.exit_code == 0
check_tv_scan(expected_file, result_file)
def test_spdx_rdf_with_known_licenses_with_text():
test_dir = test_env.get_test_loc('spdx/license_known/scan')
result_file = test_env.get_temp_file('rdf')
expected_file = test_env.get_test_loc('spdx/license_known/expected_with_text.rdf')
result = run_scan_click(['--format', 'spdx-rdf', '--license-text', test_dir, result_file])
assert result.exit_code == 0
check_rdf_scan(expected_file, result_file)
def test_full_summary_by_facet(self):
test_dir = self.get_test_loc('tallies/full_tallies/scan')
result_file = self.get_temp_file('json')
expected_file = self.get_test_loc(
'tallies/full_tallies/tallies_by_facet.expected.json')
run_scan_click([
'-clpieu', '--facet', 'dev=*.java', '--facet', 'dev=*.cs',
'--facet', 'dev=*ada*', '--facet', 'data=*.S', '--facet',
'tests=*infback9*', '--facet', 'docs=*README', '--tallies',
'--tallies-by-facet', '--json-pp', result_file, test_dir
])
check_json_scan(expected_file,
result_file,
remove_uuid=True,
remove_file_date=True,
regen=REGEN_TEST_FIXTURES)
def test_scan_should_not_fail_on_faulty_pdf_or_pdfminer_bug_but_instead_report_errors_and_keep_trucking_with_html_app():
test_file = test_env.get_test_loc('failing/patchelf.pdf')
result_file = test_env.get_temp_file('test.app.html')
result = run_scan_click([ '--copyright', '--format', 'html-app', test_file, result_file])
assert result.exit_code == 1
assert 'Scanning done' in result.output
def test_scan_works_with_multiple_processes_and_timeouts():
# this contains test files with a lot of copyrights that should
# take more thant timeout to scan
test_dir = test_env.get_test_loc('timeout', copy=True)
# add some random bytes to the test files to ensure that the license results will
# not be cached
import time, random
for tf in fileutils.resource_iter(test_dir, with_dirs=False):
with open(tf, 'ab') as tfh:
tfh.write('(c)' + str(time.time()) +
repr([random.randint(0, 10**6)
for _ in range(10000)]) + '(c)')
result_file = test_env.get_temp_file('json')
args = [
'--copyright', '--processes', '2', '--timeout', '0.000001',
'--strip-root', test_dir, '--json', result_file
]
run_scan_click(args, expected_rc=1)
expected = [
[(u'path', u'test1.txt'), (u'type', u'file'), (u'authors', []),
(u'copyrights', []), (u'holders', []),
(u'scan_errors',
[
u'ERROR: for scanner: copyrights:\nERROR: Processing interrupted: timeout after 0 seconds.'
])],
[(u'path', u'test2.txt'), (u'type', u'file'), (u'authors', []),
(u'copyrights',
[]),
(u'holders',
[]),
(u'scan_errors', [
u'ERROR: for scanner: copyrights:\nERROR: Processing interrupted: timeout after 0 seconds.'
])],
[(u'path', u'test3.txt'), (u'type', u'file'), (u'authors', []),
(u'copyrights', []), (u'holders', []),
(u'scan_errors', [
u'ERROR: for scanner: copyrights:\nERROR: Processing interrupted: timeout after 0 seconds.'
])]
]
result_json = json.loads(open(result_file).read(),
object_pairs_hook=OrderedDict)
assert sorted(sorted(x) for x in expected) == sorted(
sorted(x.items()) for x in result_json['files'])
def test_csv_tree():
test_dir = test_env.get_test_loc('csv/tree/scan')
result_file = test_env.get_temp_file('csv')
expected_file = test_env.get_test_loc('csv/tree/expected.csv')
result = run_scan_click(
['--copyright', '--format', 'csv', test_dir, result_file])
assert result.exit_code == 0
check_csvs(result_file, expected_file)
def test_scan_license_with_url_template():
test_dir = test_env.get_test_loc('license_url', copy=True)
result = run_scan_click(['--license', '--license-url-template', 'https://example.com/urn:{}', test_dir])
assert result.exit_code == 0
assert 'Scanning done' in result.output
assert 'https://example.com/urn:apache-1.0' in result.output
assert 'https://example.com/urn:public-domain' in result.output
def test_merge_multiple_scans():
test_file_1 = test_env.get_test_loc(
'resource/virtual_codebase/sample.json')
test_file_2 = test_env.get_test_loc(
'resource/virtual_codebase/thirdparty.json')
result_file = test_env.get_temp_file('json')
args = [
'--from-json', test_file_1, '--from-json', test_file_2, '--json',
result_file
]
run_scan_click(args, expected_rc=0)
expected = test_env.get_test_loc('resource/virtual_codebase/out.json')
with open(expected, read_mode) as f:
expected_files = json.loads(f.read())['files']
with open(result_file, read_mode) as f:
result_files = json.loads(f.read())['files']
assert expected_files == result_files
def test_scan_can_return_matched_license_text():
test_file = test_env.get_test_loc('license_text/test.txt')
expected_file = test_env.get_test_loc('license_text/test.expected')
result_file = test_env.get_temp_file('json')
result = run_scan_click(['--license', '--license-text', '--strip-root', test_file, result_file])
assert result.exit_code == 0
check_json_scan(test_env.get_test_loc(expected_file), result_file)
def test_paths_are_posix_in_html_format_output():
test_dir = test_env.get_test_loc('templated/simple')
result_file = test_env.get_temp_file('html')
result = run_scan_click(['--copyright', '--format', 'html', test_dir, result_file])
assert result.exit_code == 0
assert 'Scanning done' in result.output
assert '/copyright_acme_c-c.c' in open(result_file).read()
def test_custom_format_with_custom_filename():
test_dir = test_env.get_test_loc('templated/simple')
custom_template = test_env.get_test_loc('templated/sample-template.html')
result_file = test_env.get_temp_file('html')
result = run_scan_click(['--format', custom_template, test_dir, result_file])
assert result.exit_code == 0
assert 'Custom Template' in open(result_file).read()
def test_scan_only_findings(monkeypatch):
test_dir = test_env.extract_test_tar('info/basic.tgz')
result_file = test_env.get_temp_file('json')
expected_file = test_env.get_test_loc('only_findings/expected.json')
_result = run_scan_click(['--only-findings', test_dir, result_file],
monkeypatch)
check_json_scan(expected_file, result_file)
def test_consolidate_package_files_should_not_be_considered_in_license_holder_consolidated_component(
self):
scan_loc = self.get_test_loc(
'plugin_consolidate/package-files-not-counted-in-license-holders')
result_file = self.get_temp_file('json')
# There should not be a consolidated component for license-holder, even
# though every single file in this directory contains the same license
# expression and holder
expected_file = self.get_test_loc(
'plugin_consolidate/package-files-not-counted-in-license-holders-expected.json'
)
run_scan_click(
['-clip', scan_loc, '--consolidate', '--json', result_file])
check_json_scan(expected_file,
result_file,
regen=False,
remove_file_date=True)
def test_scan_noinfo_license_copyrights_with_root():
test_dir = test_env.extract_test_tar('info/basic.tgz')
result_file = test_env.get_temp_file('json')
result = run_scan_click(['--email', '--url', '--license', '--copyright', test_dir, result_file])
assert result.exit_code == 0
assert 'Scanning done' in result.output
check_json_scan(test_env.get_test_loc('info/all.rooted.expected.json'), result_file)
def test_scan_info_does_collect_infos_with_root():
test_dir = test_env.extract_test_tar('info/basic.tgz')
result_file = test_env.get_temp_file('json')
result = run_scan_click(['--info', test_dir, result_file])
assert result.exit_code == 0
assert 'Scanning done' in result.output
check_json_scan(test_env.get_test_loc('info/basic.rooted.expected.json'), result_file)
def test_verbose_option_with_copyrights(monkeypatch):
test_dir = test_env.get_test_loc('copyright', copy=True)
result_file = test_env.get_temp_file('json')
args = ['--copyright', '--verbose', test_dir, '--json', result_file]
result = run_scan_click(args, monkeypatch=monkeypatch)
assert os.path.exists(result_file)
assert 'copyright_acme_c-c.c' in result.output
assert len(open(result_file).read()) > 10
def test_scan_email_url_info():
test_dir = test_env.extract_test_tar('info/basic.tgz')
result_file = test_env.get_temp_file('json')
result = run_scan_click(['--email', '--url', '--info', '--strip-root', test_dir, result_file])
assert result.exit_code == 0
assert 'Scanning done' in result.output
check_json_scan(test_env.get_test_loc('info/email_url_info.expected.json'), result_file)
def test_csv_minimal():
test_dir = test_env.get_test_loc('csv/srp')
result_file = test_env.get_temp_file('csv')
expected_file = test_env.get_test_loc('csv/srp.csv')
result = run_scan_click(['--copyright', '--format', 'csv', test_dir, result_file])
assert result.exit_code == 0
assert 'Scanning done' in result.output
check_csvs(result_file, expected_file)
def test_scan_errors_out_with_conflicting_verbosity_options():
test_file = test_env.get_test_loc('license_text/test.txt')
result_file = test_env.get_temp_file('results.json')
args = ['--quiet', '--verbose', '--json', result_file, '--info', test_file]
result = run_scan_click(args, expected_rc=2)
assert ('Error: The option --quiet cannot be used together with the '
'--verbose option(s) and --verbose is used. You can set only one of '
'these options at a time.') in result.output
def test_scan_quiet_to_stdout_only_echoes_json_results():
test_dir = test_env.extract_test_tar('info/basic.tgz')
result_file = test_env.get_temp_file('json')
args = ['--quiet', '--info', test_dir, '--json-pp', result_file]
result_to_file = run_scan_click(args)
assert not result_to_file.output
# also test with an output of JSON to stdout
args = ['--quiet', '--info', test_dir, '--json-pp', '-']
result_to_stdout = run_scan_click(args)
# outputs to file or stdout should be identical
result1_output = open(result_file).read()
json_result1_output = load_json_result_from_string(result1_output)
json_result_to_stdout = load_json_result_from_string(result_to_stdout.output)
# cleanup JSON
assert json_result_to_stdout == json_result1_output
def test_full_summary_by_facet(self):
test_dir = self.get_test_loc('full_summary/scan')
result_file = self.get_temp_file('json')
expected_file = self.get_test_loc('full_summary/summary_by_facet.expected.json')
run_scan_click([
'-clpieu',
'--facet', 'dev=*.java',
'--facet', 'dev=*.cs',
'--facet', 'dev=*ada*',
'--facet', 'data=*.S',
'--facet', 'tests=*infback9*',
'--facet', 'docs=*README',
'--summary',
'--summary-by-facet',
'--json-pp', result_file, test_dir
])
check_json_scan(expected_file, result_file, remove_file_date=True, regen=False)
def test_scancode_ignore_single_file(self):
test_dir = self.extract_test_tar('plugin_ignore/user.tgz')
result_file = self.get_temp_file('json')
args = [
'--copyright', '--strip-root', '--ignore', 'sample.doc', test_dir,
'--json', result_file
]
run_scan_click(args)
scan_result = load_json_result(result_file)
assert scan_result['headers'][0]['extra_data']['files_count'] == 3
# FIXME: add assert 3 == scan_result['dirs_count']
scan_locs = [x['path'] for x in scan_result['files']]
expected = [
'user', 'user/ignore.doc', 'user/src', 'user/src/ignore.doc',
'user/src/test', 'user/src/test/sample.txt'
]
assert scan_locs == expected
def test_verbose_option_with_packages(monkeypatch):
test_dir = test_env.get_test_loc('package', copy=True)
result_file = test_env.get_temp_file('json')
args = ['--package', '--verbose', test_dir, '--json', result_file]
result = run_scan_click(args, monkeypatch=monkeypatch)
assert 'package.json' in result.output
assert os.path.exists(result_file)
result = open(result_file).read()
assert 'package.json' in result
def test_scan_should_not_fail_on_faulty_pdf_or_pdfminer_bug_but_instead_keep_trucking_with_json():
test_file = test_env.get_test_loc('failing/patchelf.pdf')
result_file = test_env.get_temp_file('test.json')
args = ['--copyright', '--strip-root', test_file, '--json', result_file]
result = run_scan_click(args, expected_rc=0)
expected = test_env.get_test_loc('failing/patchelf.expected.json')
check_json_scan(expected, result_file, regen=False)
assert 'Some files failed to scan' not in result.output
assert 'patchelf.pdf' not in result.output
def test_scan_does_scan_php_composer():
test_file = test_env.get_test_loc('composer/composer.json')
expected_file = test_env.get_test_loc('composer/composer.expected.json')
result_file = test_env.get_temp_file('results.json')
result = run_scan_click(['--package', test_file, result_file])
assert result.exit_code == 0
assert 'Scanning done' in result.output
check_json_scan(expected_file, result_file)
def test_scan_does_scan_rpm():
test_file = test_env.get_test_loc('rpm/fping-2.4-0.b2.rhfc1.dag.i386.rpm')
expected_file = test_env.get_test_loc('rpm/fping-2.4-0.b2.rhfc1.dag.i386.rpm.expected.json')
result_file = test_env.get_temp_file('results.json')
result = run_scan_click(['--package', test_file, result_file])
assert result.exit_code == 0
assert 'Scanning done' in result.output
check_json_scan(expected_file, result_file, regen=False)
def test_copyright_option_detects_copyrights():
test_dir = test_env.get_test_loc('copyright', copy=True)
result_file = test_env.get_temp_file('json')
result = run_scan_click(['--copyright', test_dir, result_file])
assert result.exit_code == 0
assert 'Scanning done' in result.output
assert os.path.exists(result_file)
assert len(open(result_file).read()) > 10
def test_json_pretty_print():
test_dir = test_env.get_test_loc('json/simple')
result_file = test_env.get_temp_file('json')
result = run_scan_click(['-clip', '--format', 'json-pp', test_dir, result_file])
assert result.exit_code == 0
assert 'Scanning done' in result.output
expected = test_env.get_test_loc('json/simple-expected.jsonpp')
check_json_scan(test_env.get_test_loc(expected), result_file, strip_dates=True, regen=False)
