T13.9 follow-up 2: name PEM keys, forgive missing braces and double encoding, give a length hint (D23)

This commit is contained in:
2026-10-16 16:24:05 -07:00
parent 5cf6355a01
commit 5f8ebab5b2
3 changed files with 43 additions and 5 deletions

View File

@@ -395,3 +395,7 @@ space or line break, and it gave one message for every failure. The loader now f
marks, spaces, line breaks, missing padding, the URL-safe alphabet, a byte-order mark and a
one-key JWK Set, and each failure names its step (counts only, no key text). The new checks
in `tests/okta_sync_oauth_check.py` fail against the first loader and pass now.
T13.9 follow-up 2 (2026-10-16): the second deploy decoded the value but the text was not JSON.
The loader now also names a PEM key, adds missing outer braces, unwraps a value that was encoded
twice, and its "not JSON" message gives the length and the kind of first character (counts only).

View File

@@ -181,7 +181,7 @@ def _load_jwk() -> dict:
raise _fail("OKTA_SYNC_PRIVATE_KEY is not set")
if len(raw) >= 2 and raw[0] == raw[-1] and raw[0] in "\"'":
raw = raw[1:-1].strip()
if raw.startswith("{"):
if raw.startswith(("{", '"', "-----BEGIN")):
text = raw
else:
compact = re.sub(r"\s+", "", raw)
@@ -200,11 +200,28 @@ def _load_jwk() -> dict:
text = decoded.decode("utf-8-sig")
except UnicodeDecodeError:
raise _fail("OKTA_SYNC_PRIVATE_KEY decodes from base64 but the result is not text") from None
text = text.lstrip("\ufeff").strip()
via = "" if raw.startswith(("{", '"', "-----BEGIN")) else " after decoding base64"
if text.startswith("-----BEGIN"):
raise _fail("OKTA_SYNC_PRIVATE_KEY holds a PEM key (-----BEGIN ...). A JWK is needed: "
"JSON with the fields kty, kid, n, e and d")
if text.startswith('"'):
text = "{" + text.rstrip(",") + "}" # the fields were copied without the outer braces
try:
jwk = json.loads(text.lstrip("\ufeff"))
jwk = json.loads(text)
except ValueError:
raise _fail("OKTA_SYNC_PRIVATE_KEY is not JSON"
+ (" after decoding base64" if not raw.startswith("{") else "")) from None
# One more layer? A value that was encoded twice decodes to base64 text.
again = None
if not text.startswith("{"):
try:
again = base64.b64decode(re.sub(r"\s+", "", text) + "=" * (-len(re.sub(r"\s+", "", text)) % 4))
jwk = json.loads(again.decode("utf-8-sig").strip())
except Exception: # noqa: BLE001
again = None
if again is None:
shape = ("starts with a brace" if text.startswith("{") else
"starts with a letter or digit" if text[:1].isalnum() else "starts with a symbol")
raise _fail(f"OKTA_SYNC_PRIVATE_KEY is not JSON{via} ({len(text)} characters, {shape})") from None
if isinstance(jwk, dict) and isinstance(jwk.get("keys"), list):
if len(jwk["keys"]) != 1:
raise _fail("OKTA_SYNC_PRIVATE_KEY is a key set with more than one key; paste one key")

View File

@@ -200,11 +200,28 @@ for label, raw in variants.items():
chk(f"forgiven: {label}", isinstance(f.verified, dict) and f.user_calls == 1)
except OktaSyncError as e:
chk(f"forgiven: {label}", False, str(e))
# fields copied without the outer braces, and a value encoded twice, are forgiven
inner = json.dumps(rsa_jwk)[1:-1]
for label, raw in [("fields without braces (text)", inner),
("fields without braces (base64)", base64.b64encode(inner.encode()).decode()),
("encoded twice", base64.b64encode(b64.encode()).decode())]:
os.environ["OKTA_SYNC_PRIVATE_KEY"] = raw
try:
f = FakeOkta(rsa_pub)
okta_sync.fetch_users(http=f.client())
chk(f"forgiven: {label}", isinstance(f.verified, dict))
except OktaSyncError as e:
chk(f"forgiven: {label}", False, str(e))
pem = "-----BEGIN PRIVATE KEY-----\nMIIEvQIBADANBgkq\n-----END PRIVATE KEY-----"
for label, raw in [("PEM text", pem), ("PEM in base64", base64.b64encode(pem.encode()).decode())]:
os.environ["OKTA_SYNC_PRIVATE_KEY"] = raw
err = fetch_err(FakeOkta()) or ""
chk(f"PEM is named: {label}", "PEM" in err and "MIIEvQ" not in err, err)
os.environ["OKTA_SYNC_PRIVATE_KEY"] = json.dumps({"keys": [rsa_jwk, rsa_jwk]})
chk("a key set with two keys is refused", "more than one key" in (fetch_err(FakeOkta()) or ""))
for label, raw, want in [
("garbage characters", "!!!not*base64!!!", "not valid base64"),
("base64 of non-JSON", base64.b64encode(b"hello world").decode(), "not JSON after decoding base64"),
("base64 of non-JSON", base64.b64encode(b"hello world").decode(), "not JSON after decoding base64 (11 characters, starts with a letter or digit)"),
("base64 of bytes that are not text", base64.b64encode(b"\xff\xfe\xfd\xfc").decode(), "not text"),
("broken JSON", "{ not json", "not JSON"),
]: