Files
LEDMatrix/test/test_redaction.py
T
Claude 9171d82562 fix(redaction): make Authorization-header redaction linear too
_REDACT_AUTH_HEADER matched the value's opening as `\s*["\']?\s*`: two
`\s*` separated only by an optional quote. With no quote, a whitespace
run could be split between them in every possible way, and when no
credential followed (end of text, or `,` `"` `<` ...) the engine tried
them all before giving up: quadratic, 8s for `authorization:` and 20k
spaces, 17s with `Proxy-Authorization:` (tried again at the inner
`authorization`). Same stall as the URL pattern: re.sub holds the GIL,
and the display service redacts everything it publishes.

The quote and the whitespace after it are now one optional unit,
`\s*(?:["\']\s*)?`, which matches the same strings with only one way to
split them. Output is identical to the old pattern on 300k fuzzed
inputs; 20k spaces now take ~1.6ms. A scan of all three redaction
patterns over prefix/run/suffix shapes finds none left that scales
superlinearly.

test/test_redaction.py pins exact output for quoted, tabbed, multi-line
and credential-less headers, and bounds header + 20k whitespace at 1s;
against the previous pattern those fail at 8-17s each.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01KMXdS2S4NXTJ8ET96GymhK
2026-09-24 16:00:37 +00:00

111 lines
4.8 KiB
Python

"""redact_credentials must stay linear in the length of its input.
Regressions under test, both quadratic regexes in src/redaction.py:
- The URL-userinfo pattern (`scheme://user:password@`) could start a match at
every letter of a run of scheme characters, and each attempt read to the end
of the run looking for `://`: 1.6s for a 20k-character run.
- The Authorization-header pattern had two `\\s*` separated only by an
optional quote, so a header followed by whitespace and no credential tried
every split of that whitespace between them: 8s for 20k spaces.
The display service redacts every message, stack trace and context value it
publishes in the error snapshot, and re.sub holds the GIL throughout, so an
exception quoting a hex digest or a long ID stalled the render loop with it.
test_error_snapshot_cross_process.py's snapshot-size test spent 140s here.
The fixed patterns have to redact exactly what the old ones did.
"""
import time
import pytest
from src.redaction import redact_credentials
# Each timed input took seconds before the fix and takes about a millisecond
# after it; the bound leaves CI plenty of headroom while still failing on a
# quadratic pattern.
_TIME_LIMIT = 1.0
def _timed(text):
start = time.perf_counter()
result = redact_credentials(text)
return result, time.perf_counter() - start
class TestUrlUserinfo:
@pytest.mark.parametrize("text,expected", [
("401 for https://user:hunter2@example.com/api",
"401 for https://user:<redacted>@example.com/api"),
("HTTPS://USER:HUNTER2@EXAMPLE.COM",
"HTTPS://USER:<redacted>@EXAMPLE.COM"),
("git+ssh://deploy:hunter2@host/repo",
"git+ssh://deploy:<redacted>@host/repo"),
# The scheme starts after digits or +.- in the same run. Those
# characters must survive, and the password must still go.
("1http://user:hunter2@host", "1http://user:<redacted>@host"),
("+.-http://user:hunter2@host", "+.-http://user:<redacted>@host"),
("a1+http://user:hunter2@host", "a1+http://user:<redacted>@host"),
("see a://u:first@b and c://v:second@d",
"see a://u:<redacted>@b and c://v:<redacted>@d"),
])
def test_password_is_redacted_and_the_rest_kept(self, text, expected):
assert redact_credentials(text) == expected
def test_a_url_without_a_password_is_untouched(self):
text = "GET https://user@example.com/path failed"
assert redact_credentials(text) == text
class TestAuthorizationHeader:
@pytest.mark.parametrize("text,expected", [
("Authorization: Bearer eyJ.SECRET.sig", "Authorization: Bearer <redacted>"),
("Proxy-Authorization: Basic dXNlcg==", "Proxy-Authorization: Basic <redacted>"),
("authorization: barecredential", "authorization: <redacted>"),
# Whitespace and an opening quote around the value, in either order.
('authorization=" Bearer tok"', 'authorization=" Bearer <redacted>"'),
("authorization: ' tok'", "authorization: ' <redacted>'"),
("authorization:\n\tBearer tok", "authorization:\n\tBearer <redacted>"),
])
def test_credential_is_redacted_and_the_rest_kept(self, text, expected):
assert redact_credentials(text) == expected
@pytest.mark.parametrize("text", ["authorization: ", "authorization: , next"])
def test_a_header_without_a_credential_is_untouched(self, text):
assert redact_credentials(text) == text
class TestLinearTime:
@pytest.mark.parametrize("unit", ["x", "0123456789abcdef", "1a", "a+", "1"])
def test_long_scheme_character_runs(self, unit):
text = (unit * 50_000)[:50_000]
result, elapsed = _timed(text)
assert result == text
assert elapsed < _TIME_LIMIT, f"{elapsed:.2f}s to redact {len(text)} chars of {unit!r}"
def test_a_credential_after_a_long_run_is_still_found(self):
run = "ab12" * 10_000
result, elapsed = _timed(f"{run} https://user:hunter2@example.com")
assert result == f"{run} https://user:<redacted>@example.com"
assert elapsed < _TIME_LIMIT
@pytest.mark.parametrize("header,whitespace", [
("authorization:", " "),
("Proxy-Authorization:", "\t"),
("authorization=", "\n"),
])
def test_a_header_followed_by_long_whitespace(self, header, whitespace):
text = header + whitespace * 20_000 + ","
result, elapsed = _timed(text)
assert result == text
assert elapsed < _TIME_LIMIT, (
f"{elapsed:.2f}s to redact {header!r} and {len(text) - len(header)} more chars")
def test_a_credential_after_long_whitespace_is_still_found(self):
gap = " " * 20_000
result, elapsed = _timed(f"authorization:{gap}Bearer tok")
assert result == f"authorization:{gap}Bearer <redacted>"
assert elapsed < _TIME_LIMIT