Skip to content

Fix Base45 dropping trailing bytes on non-ASCII input #45

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
gaoflow wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix Base45 dropping trailing bytes on non-ASCII input #45

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 5 additions & 2 deletions src/codext/base/base45.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,10 @@ def base45_encode(mode):
b45 = _get_charset(B45, mode)
def encode(text, errors="strict"):
t, s = b(text), ""
for i in range(0, len(text), 2):
# iterate over the byte sequence (t), not len(text): when the input
# holds non-ASCII characters, b(text) is longer than text and using
# len(text) silently drops the trailing bytes
for i in range(0, len(t), 2):
n = 256 * __ord(t[i])
try:
n += __ord(t[i+1])
Expand All @@ -54,7 +57,7 @@ def base45_decode(mode):
def decode(text, errors="strict"):
t, s = b(text), ""
ehandler = handle_error("base45", errors, decode=True)
for i in range(0, len(text), 3):
for i in range(0, len(t), 3):
try:
n = b45[__chr(t[i])]
except KeyError:
Expand Down
13 changes: 13 additions & 0 deletions tests/test_base.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -211,6 +211,19 @@ def test_codec_base100(self):
self.assertRaises(ValueError, codecs.decode, b(B100)[1:], "base100")
self.assertIsNotNone(codecs.decode(b(B100) + b"\n", "base100", "ignore"))

def test_codec_base45(self):
# RFC 9285 test vectors
for s, b45 in [("AB", "BB8"), ("Hello!!", "%69 VD92EX0"), ("base-45", "UJCLQE7W581")]:
self.assertEqual(codecs.encode(s, "base45"), b45)
self.assertEqual(codecs.encode(b(s), "base45"), b(b45))
self.assertEqual(codecs.decode(b45, "base45"), s)
self.assertEqual(codecs.decode(b(b45), "base45"), b(s))
# a trailing non-ASCII byte must not be dropped (byte length, not str length, drives encoding)
self.assertEqual(codecs.encode(b"\xcf\xb1\x1b", "base45"), b"OBQR0")
self.assertEqual(codecs.decode(b"OBQR0", "base45"), b"\xcf\xb1\x1b")
for data in [b"\xff\xfe", b"hello", b"\x00", b"\x80\x81\x82\x83\x84"]:
self.assertEqual(codecs.decode(codecs.encode(data, "base45"), "base45"), data)

def test_codec_base_generic(self):
for n in range(2, 255):
bn = "base{}_generic".format(n)
Expand Down