mirror/github-octodns
1
0
Fork 0
mirror of https://github.com/github/octodns.git synced 2024-05-11 05:55:00 +00:00
Code Issues Releases Activity

Improve _ChunkedValue's handling of split chunks with unexpected whitespace

Browse Source
This commit is contained in:
Ross McFarland
2024-05-08 15:02:39 -07:00
parent fae406af21
commit 89b3650c4c
3 changed files with 102 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
CHANGELOG.md
View File

@ -1,6 +1,8 @@
## v1.?.? - 2024-??-?? - ???
* Fix CAA rdata parsing to allow values with tags
* Improve TXT (and SPF) record handling of unexpected whitespace
before/after/in-between quotes.
## v1.7.0 - 2024-04-29 - All the knobs and dials

5
octodns/record/chunked.py
View File

@ -34,6 +34,7 @@ class _ChunkedValuesMixin(ValuesMixin):
class _ChunkedValue(str):
_unescaped_semicolon_re = re.compile(r'\w;')
_chunk_sep_re = re.compile(r'"\s+"')
@classmethod
def parse_rdata_text(cls, value):
@ -62,9 +63,11 @@ class _ChunkedValue(str):
def process(cls, values):
ret = []
for v in values:
# remove leading/trailing whitespace
v = v.strip()
if v and v[0] == '"':
v = v[1:-1]
ret.append(cls(v.replace('" "', '')))
ret.append(cls(cls._chunk_sep_re.sub('', v)))
return ret
@property

96
tests/test_octodns_record_chunked.py
View File

@ -67,3 +67,99 @@ class TestChunkedValue(TestCase):
['non ASCII character in "Déjà vu"'],
_ChunkedValue.validate('Déjà vu', 'TXT'),
)
def test_large_values(self):
# There is additional testing in TXT
# "standard" format quoted and split value
value = (
'"Lorem ipsum dolor sit amet, consectetur '
'adipiscing elit, sed do eiusmod tempor incididunt ut '
'labore et dolore magna aliqua. Ut enim ad minim veniam, '
'quis nostrud exercitation ullamco laboris nisi ut aliquip '
'ex" " ea commodo consequat. Duis aute irure dolor in '
'reprehenderit in voluptate velit esse cillum dolore eu '
'fugiat nulla pariatur. Excepteur sint occaecat cupidatat '
'non proident, sunt in culpa qui officia deserunt mollit '
'anim id est laborum."'
)
chunked = _ChunkedValue.process([value])
self.assertEqual(1, len(chunked))
chunked = chunked[0]
self.assertIsInstance(chunked, _ChunkedValue)
dechunked_value = (
'Lorem ipsum dolor sit amet, consectetur '
'adipiscing elit, sed do eiusmod tempor incididunt ut '
'labore et dolore magna aliqua. Ut enim ad minim veniam, '
'quis nostrud exercitation ullamco laboris nisi ut aliquip '
'ex ea commodo consequat. Duis aute irure dolor in '
'reprehenderit in voluptate velit esse cillum dolore eu '
'fugiat nulla pariatur. Excepteur sint occaecat cupidatat '
'non proident, sunt in culpa qui officia deserunt mollit '
'anim id est laborum.'
)
self.assertEqual(dechunked_value, chunked)
# already dechunked, noop
chunked = _ChunkedValue.process([dechunked_value])[0]
self.assertEqual(dechunked_value, chunked)
# leading whitespace
chunked = _ChunkedValue.process([f' {value}'])[0]
self.assertEqual(dechunked_value, chunked)
chunked = _ChunkedValue.process([f' {value}'])[0]
self.assertEqual(dechunked_value, chunked)
chunked = _ChunkedValue.process([f'\t{value}'])[0]
self.assertEqual(dechunked_value, chunked)
chunked = _ChunkedValue.process([f'\t\t{value}'])[0]
self.assertEqual(dechunked_value, chunked)
chunked = _ChunkedValue.process([f' \t{value}'])[0]
self.assertEqual(dechunked_value, chunked)
# trailing whitespace
chunked = _ChunkedValue.process([f'{value} '])[0]
self.assertEqual(dechunked_value, chunked)
chunked = _ChunkedValue.process([f'{value} '])[0]
self.assertEqual(dechunked_value, chunked)
chunked = _ChunkedValue.process([f'{value}\t'])[0]
self.assertEqual(dechunked_value, chunked)
chunked = _ChunkedValue.process([f'{value}\t\t'])[0]
self.assertEqual(dechunked_value, chunked)
chunked = _ChunkedValue.process([f'{value} \t'])[0]
self.assertEqual(dechunked_value, chunked)
# both
chunked = _ChunkedValue.process([f' {value} '])[0]
self.assertEqual(dechunked_value, chunked)
chunked = _ChunkedValue.process([f'\t{value} '])[0]
self.assertEqual(dechunked_value, chunked)
chunked = _ChunkedValue.process([f' {value}\t'])[0]
self.assertEqual(dechunked_value, chunked)
# variations of whitepsace in the chunk seperator
multi = value.replace('" "', '" "')
chunked = _ChunkedValue.process([multi])[0]
self.assertEqual(dechunked_value, chunked)
multi = value.replace('" "', '"\t"')
chunked = _ChunkedValue.process([multi])[0]
self.assertEqual(dechunked_value, chunked)
multi = value.replace('" "', '"\t\t"')
chunked = _ChunkedValue.process([multi])[0]
self.assertEqual(dechunked_value, chunked)
multi = value.replace('" "', '" \t"')
chunked = _ChunkedValue.process([multi])[0]
self.assertEqual(dechunked_value, chunked)
# ~real world test case
values = [
'before',
' "v=DKIM1\\; h=sha256\\; k=rsa\\; p=MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAx78E7PtJvr8vpoNgHdIAe+llFKoy8WuTXDd6Z5mm3D4AUva9MBt5fFetxg/kcRy3KMDnMw6kDybwbpS/oPw1ylk6DL1xit7Cr5xeYYSWKukxXURAlHwT2K72oUsFKRUvN1X9lVysAeo+H8H/22Z9fJ0P30sOuRIRqCaiz+OiUYicxy4x" "rpfH2s9a+o3yRwX3zhlp8GjRmmmyK5mf7CkQTCfjnKVsYtB7mabXXmClH9tlcymnBMoN9PeXxaS5JRRysVV8RBCC9/wmfp9y//cck8nvE/MavFpSUHvv+TfTTdVKDlsXPjKX8iZQv0nO3xhspgkqFquKjydiR8nf4meHhwIDAQAB" ',
'z after',
]
chunked = _ChunkedValue.process(values)
expected = [
'before',
'v=DKIM1\\; h=sha256\\; k=rsa\\; p=MIIBIjANBgkqhkiG9w0BAQEFAAOCAQ8AMIIBCgKCAQEAx78E7PtJvr8vpoNgHdIAe+llFKoy8WuTXDd6Z5mm3D4AUva9MBt5fFetxg/kcRy3KMDnMw6kDybwbpS/oPw1ylk6DL1xit7Cr5xeYYSWKukxXURAlHwT2K72oUsFKRUvN1X9lVysAeo+H8H/22Z9fJ0P30sOuRIRqCaiz+OiUYicxy4xrpfH2s9a+o3yRwX3zhlp8GjRmmmyK5mf7CkQTCfjnKVsYtB7mabXXmClH9tlcymnBMoN9PeXxaS5JRRysVV8RBCC9/wmfp9y//cck8nvE/MavFpSUHvv+TfTTdVKDlsXPjKX8iZQv0nO3xhspgkqFquKjydiR8nf4meHhwIDAQAB',
'z after',
]
self.assertEqual(expected, chunked)