def check_ignorable_clues(rule):
"""
Validate that all ignorable clues defined in a `rule` Rule object are
properly detected in that rule text file.
"""
from itertools import chain
from scancode import api
text_file = rule.text_file
# scan clues
scan_data = {}
scan_data.update(api.get_copyrights(text_file))
scan_data.update(api.get_urls(text_file, threshold=0))
scan_data.update(api.get_emails(text_file, threshold=0))
results = OrderedDict()
for what, detections in scan_data.items():
# remove lines
for detected in detections:
detected.pop('start_line', None)
detected.pop('end_line', None)
# remove keys and keep only values e.g. a list of detected copyrights,
# emails, etc
detections = sorted(
set(chain(*(detected.values() for detected in detections))))
results['ignorable_' + what] = detections
# collect ignorables
expected = OrderedDict([
('ignorable_copyrights', rule.ignorable_copyrights or []),
('ignorable_holders', rule.ignorable_holders or []),
('ignorable_authors', rule.ignorable_authors or []),
('ignorable_urls', rule.ignorable_urls or []),
('ignorable_emails', rule.ignorable_emails or []),
])
results = OrderedDict([(k, v) for k, v in sorted(results.items()) if v])
expected = OrderedDict([(k, v) for k, v in sorted(expected.items()) if v])
try:
assert expected == results
except:
# On failure, we compare againto get additional failure details such as
# a clickable text_file path
data_file = rule.data_file
if not data_file:
data_file = text_file.replace('.LICENSE', '.yml')
results['files'] = [
'file://{data_file}'.format(**locals()),
'file://{text_file}'.format(**locals()),
]
# this assert will always fail and provide a more detailed failure trace
assert saneyaml.dump(expected) == saneyaml.dump(results)
def test_get_copyrights_include_copyrights_and_authors(self):
test_file = self.get_test_loc('api/copyright/iproute.c')
cops = list(api.get_copyrights(test_file))
expected = [
OrderedDict([
(u'statements', [u'Copyright (c) 2010 Patrick McHardy']),
(u'holders', [u'Patrick McHardy']),
(u'authors', []),
(u'start_line', 2), (u'end_line', 2)]),
OrderedDict([
(u'statements', []),
(u'holders', []),
(u'authors', [u'Patrick McHardy <*****@*****.**>']),
(u'start_line', 11), (u'end_line', 11)])
]
assert expected == cops
def test_get_copyrights_include_copyrights_and_authors(self):
test_file = self.get_test_loc('api/copyright/iproute.c')
cops = api.get_copyrights(test_file)
expected = OrderedDict([
('copyrights', [
OrderedDict([(u'value', u'Copyright (c) 2010 Patrick McHardy'), (u'start_line', 2), (u'end_line', 2)])
]),
('holders', [
OrderedDict([(u'value', u'Patrick McHardy'), (u'start_line', 2), (u'end_line', 2)])
]),
('authors', [
OrderedDict([(u'value', u'Patrick McHardy <*****@*****.**>'), (u'start_line', 11), (u'end_line', 11)])
]),
])
assert expected == cops
def scan_one(input_file, copyright, license, verbose=False):
"""
Scan one file and return scanned data.
"""
if verbose:
click.secho('Scanning: %(input_file)s: ' % locals(), nl=False, fg='blue')
data = {'location': input_file}
if copyright:
if verbose:
click.secho('copyrights. ', nl=False, fg='green')
data['copyrights'] = list(get_copyrights(input_file))
if license:
if verbose:
click.secho('licenses. ', nl=False, fg='green')
data['licenses'] = list(get_licenses(input_file))
if verbose:
click.secho('', nl=True)
return data
def scan_one(input_file,
copyright,
license,
verbose=False): # @ReservedAssignment
"""
Scan one file and return scanned data.
"""
if verbose:
click.secho('Scanning: %(input_file)s: ' % locals(),
nl=False,
fg='blue')
data = {'location': input_file}
if copyright:
if verbose:
click.secho('copyrights. ', nl=False, fg='green')
data['copyrights'] = list(get_copyrights(input_file))
if license:
if verbose:
click.secho('licenses. ', nl=False, fg='green')
data['licenses'] = list(get_licenses(input_file))
if verbose:
click.secho('', nl=True)
return data
