-
Notifications
You must be signed in to change notification settings - Fork 155
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
5 changed files
with
300 additions
and
5 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,89 @@ | ||
import random | ||
|
||
import factory | ||
import factory.fuzzy | ||
from pygitguardian.models import Match, PolicyBreak, ScanResult | ||
|
||
from ggshield.core.scan.scannable import StringScannable | ||
from ggshield.utils.git_shell import Filemode | ||
from tests.factory_constants import DETECTOR_NAMES, MATCH_NAMES | ||
|
||
|
||
def get_line_index(content, index): | ||
"""Return the index of the line containing the caracter at the given index""" | ||
current_line_index = 0 | ||
lines = content.splitlines(keepends=True) | ||
while True: | ||
line = lines.pop(0) | ||
if index <= len(line): | ||
return current_line_index | ||
index -= len(line) | ||
current_line_index += 1 | ||
|
||
|
||
class ScannableFactory(factory.Factory): | ||
class Meta: | ||
model = StringScannable | ||
|
||
url = factory.Faker("hostname") | ||
content = factory.Faker("text") | ||
# Only returning FILE for new, since diff would need a custom content | ||
filemode = Filemode.FILE | ||
|
||
|
||
class MatchFactory(factory.Factory): | ||
class Meta: | ||
model = Match | ||
|
||
content = factory.Faker("text") | ||
match_len = factory.fuzzy.FuzzyInteger(5, 15) | ||
index_start = factory.lazy_attribute( | ||
lambda obj: random.randint(0, len(obj.content) - obj.match_len) | ||
) | ||
index_end = factory.lazy_attribute(lambda obj: obj.index_start + obj.match_len) | ||
match = factory.lazy_attribute( | ||
lambda obj: obj.content[obj.index_start : obj.index_end] | ||
) | ||
line_start = factory.lazy_attribute( | ||
lambda obj: get_line_index(obj.content, obj.index_start) | ||
) | ||
line_end = factory.lazy_attribute( | ||
lambda obj: get_line_index(obj.content, obj.index_end) | ||
) | ||
match_type = factory.lazy_attribute(lambda obj: random.choice(MATCH_NAMES)) | ||
|
||
|
||
class PolicyBreakFactory(factory.Factory): | ||
class Meta: | ||
model = PolicyBreak | ||
|
||
break_type = factory.lazy_attribute(lambda obj: random.choice(DETECTOR_NAMES)) | ||
policy = "Secrets detection" | ||
validity = "valid" | ||
known_secret = False | ||
incident_url = None | ||
is_excluded = False | ||
exclude_reason = None | ||
diff_kind = None | ||
content = factory.Faker("text") | ||
nb_matches = factory.fuzzy.FuzzyInteger(1, 2) | ||
|
||
@factory.lazy_attribute | ||
def matches(self): | ||
# Note: matches may overlap, but at least we ensure they | ||
# have different names | ||
match_names = random.sample(MATCH_NAMES, self.nb_matches) | ||
return [ | ||
MatchFactory(match_type=match_name, content=self.content) | ||
for match_name in match_names | ||
] | ||
|
||
|
||
class ScanResultFactory(factory.Factory): | ||
class Meta: | ||
model = ScanResult | ||
|
||
policy_break_count = factory.lazy_attribute(lambda obj: len(obj.policy_breaks)) | ||
policy_breaks = [] | ||
policies = ["Secrets detection"] | ||
is_diff = False |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,92 @@ | ||
DETECTOR_NAMES = [ | ||
"Basic Auth String", | ||
"Generic Password", | ||
"JSON Web Token", | ||
"Generic Terraform Variable Secret", | ||
"Generic Database Assignment", | ||
"Company Email Password", | ||
"Generic Password", | ||
"Base64 Generic High Entropy Secret", | ||
"Generic Database Assignment", | ||
"Generic CLI Option Secret", | ||
"Username Password", | ||
"Generic High Entropy Secret", | ||
"Base64 Basic Authentication", | ||
"Bearer Token", | ||
"Authentication Tuple", | ||
"Typeform API Token", | ||
"New Relic API Key", | ||
"Pingdom token v3", | ||
"Datadog Keys", | ||
"Databricks Authentication Token With Hostname", | ||
"GitGuardian Public Monitoring API Key", | ||
"GitHub Server-to-server Token", | ||
"Infracost API Key", | ||
"Facebook App Keys", | ||
"Firebase Cloud Messaging API Key", | ||
"Intercom Token", | ||
"Sourcegraph Access Token v1", | ||
"Stripe Webhook Secret", | ||
"GitLab Token", | ||
"New Relic API Service Key", | ||
"Eventbrite OAuth2 Token", | ||
"Base64 AWS SES Keys", | ||
"Doppler API Key", | ||
"Heartland API key", | ||
"Tailscale Pre-Authentication Key", | ||
"Kraken Keys", | ||
"Coveralls Repository Token", | ||
"Docker Credentials", | ||
"Algolia Monitoring Keys", | ||
"Grafana Token", | ||
"PackageCloud API Token", | ||
"Square Access Token", | ||
"DigitalOcean Token", | ||
"Sourcegraph Access Token v3", | ||
"Akamai API Credentials", | ||
"Linode Personal Access Token", | ||
"Scalr API Access Token", | ||
"FullContact Key", | ||
"Nylas API Key", | ||
"Plaid Access Token", | ||
] | ||
MATCH_NAMES = [ | ||
"apikey", | ||
"client_id", | ||
"client_secret", | ||
"host", | ||
"password", | ||
"username", | ||
"token", | ||
"port", | ||
"scheme", | ||
"connection_uri", | ||
"subdomain", | ||
"private_key", | ||
"domain", | ||
"secret_key", | ||
"access_token", | ||
"project_id", | ||
"cloud_name", | ||
"database", | ||
"client_token", | ||
"secret_token", | ||
"tenant_id", | ||
"private_key_id", | ||
"integration_key", | ||
"azure_endpoint", | ||
"app_id", | ||
"cluster", | ||
"pub_key", | ||
"sub_key", | ||
"environment", | ||
"refresh_token", | ||
"organization", | ||
"session_token", | ||
"connection_string", | ||
"account", | ||
"user", | ||
"client_certificate", | ||
"client_key", | ||
"config_value", | ||
] |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,23 @@ | ||
import pytest | ||
|
||
from tests.factories import get_line_index | ||
|
||
|
||
TEST_CONTENT = """aaa | ||
bb | ||
cccc""" | ||
|
||
|
||
@pytest.mark.parametrize( | ||
("index", "expected_line_index"), | ||
( | ||
(1, 0), | ||
(4, 0), | ||
(5, 1), | ||
(7, 1), | ||
(8, 2), | ||
(11, 2), | ||
), | ||
) | ||
def test_get_line_index(index, expected_line_index): | ||
assert get_line_index(TEST_CONTENT, index) == expected_line_index |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters