optimize the SCM URL sanitizer regex

\w+ is too greedy for large strings that don't contain URLs
ansible · Mar 11, 2020 · 7e3865c · 7e3865c
1 parent 208dbc1
commit 7e3865c
Show file tree

Hide file tree

Showing 2 changed files with 8 additions and 1 deletion.
diff --git a/awx/main/redact.py b/awx/main/redact.py
@@ -8,7 +8,7 @@
 
 class UriCleaner(object):
     REPLACE_STR = REPLACE_STR
-    SENSITIVE_URI_PATTERN = re.compile(r'(\w+:(\/?\/?)[^\s]+)', re.MULTILINE)  # NOQA
+    SENSITIVE_URI_PATTERN = re.compile(r'((http|https|ssh|git):(\/?\/?)[^\s]+)', re.MULTILINE)  # NOQA
 
     @staticmethod
     def remove_sensitive(cleartext):

diff --git a/awx/main/tests/unit/test_redact.py b/awx/main/tests/unit/test_redact.py
@@ -152,3 +152,10 @@ def test_uri_scm_cleartext_redact_and_replace(test_data):
     # Ensure the host didn't get redacted
     assert redacted_str.count(uri.host) == test_data['host_occurrences']
 
+
+@pytest.mark.timeout(1)
+def test_large_string_performance():
+    length = 100000
+    redacted = UriCleaner.remove_sensitive('x' * length)
+    assert len(redacted) == length
+