Skip to content

gh-62040: Raise ValueError on invalid *errors* argument in several codecs #136611

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.

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
wants to merge 6 commits into
base: main
Choose a base branch
from
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
14 changes: 10 additions & 4 deletions Lib/encodings/base64_codec.py
Original file line number Diff line number Diff line change
Expand Up @@ -8,14 +8,20 @@
import codecs
import base64

### Codec Helpers

def _assert_strict(errors):
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Maybe _check_strict from the original patch would be better?

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I prefer assert_strict since it is closer to what was there before, and it is more obvious, to me at least, that it will fail if errors != 'strict', whereas check_strict, seems like something that will enable more verbose errors or the like.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

IMO, it's not fully correct to name method assert_something and don't make any assert checks or raising an AssertionError.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@malemburg which do you prefer? _check_strict or _assert_strict

if errors != 'strict':
raise ValueError(f'Unsupported error handling mode: "{errors}" - must be "strict"')

### Codec APIs

def base64_encode(input, errors='strict'):
assert errors == 'strict'
_assert_strict(errors)
return (base64.encodebytes(input), len(input))

def base64_decode(input, errors='strict'):
assert errors == 'strict'
_assert_strict(errors)
return (base64.decodebytes(input), len(input))

class Codec(codecs.Codec):
Expand All @@ -26,12 +32,12 @@ def decode(self, input, errors='strict'):

class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
assert self.errors == 'strict'
_assert_strict(self.errors)
return base64.encodebytes(input)

class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
assert self.errors == 'strict'
_assert_strict(self.errors)
return base64.decodebytes(input)

class StreamWriter(Codec, codecs.StreamWriter):
Expand Down
14 changes: 10 additions & 4 deletions Lib/encodings/bz2_codec.py
Original file line number Diff line number Diff line change
Expand Up @@ -10,14 +10,20 @@
import codecs
import bz2 # this codec needs the optional bz2 module !

### Codec Helpers

def _assert_strict(errors):
if errors != 'strict':
raise ValueError(f'Unsupported error handling mode: "{errors}" - must be "strict"')

### Codec APIs

def bz2_encode(input, errors='strict'):
assert errors == 'strict'
_assert_strict(errors)
return (bz2.compress(input), len(input))

def bz2_decode(input, errors='strict'):
assert errors == 'strict'
_assert_strict(errors)
return (bz2.decompress(input), len(input))

class Codec(codecs.Codec):
Expand All @@ -28,7 +34,7 @@ def decode(self, input, errors='strict'):

class IncrementalEncoder(codecs.IncrementalEncoder):
def __init__(self, errors='strict'):
assert errors == 'strict'
_assert_strict(errors)
self.errors = errors
self.compressobj = bz2.BZ2Compressor()

Expand All @@ -44,7 +50,7 @@ def reset(self):

class IncrementalDecoder(codecs.IncrementalDecoder):
def __init__(self, errors='strict'):
assert errors == 'strict'
_assert_strict(errors)
self.errors = errors
self.decompressobj = bz2.BZ2Decompressor()

Expand Down
14 changes: 10 additions & 4 deletions Lib/encodings/hex_codec.py
Original file line number Diff line number Diff line change
Expand Up @@ -8,14 +8,20 @@
import codecs
import binascii

### Codec Helpers

def _assert_strict(errors):
if errors != 'strict':
raise ValueError(f'Unsupported error handling mode: "{errors}" - must be "strict"')

### Codec APIs

def hex_encode(input, errors='strict'):
assert errors == 'strict'
_assert_strict(errors)
return (binascii.b2a_hex(input), len(input))

def hex_decode(input, errors='strict'):
assert errors == 'strict'
_assert_strict(errors)
return (binascii.a2b_hex(input), len(input))

class Codec(codecs.Codec):
Expand All @@ -26,12 +32,12 @@ def decode(self, input, errors='strict'):

class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
assert self.errors == 'strict'
_assert_strict(self.errors)
return binascii.b2a_hex(input)

class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
assert self.errors == 'strict'
_assert_strict(self.errors)
return binascii.a2b_hex(input)

class StreamWriter(Codec, codecs.StreamWriter):
Expand Down
12 changes: 10 additions & 2 deletions Lib/encodings/quopri_codec.py
Original file line number Diff line number Diff line change
Expand Up @@ -7,15 +7,23 @@
import quopri
from io import BytesIO

### Codec Helpers

def _assert_strict(errors):
if errors != 'strict':
raise ValueError(f'Unsupported error handling mode: "{errors}" - must be "strict"')

### Codec APIs

def quopri_encode(input, errors='strict'):
assert errors == 'strict'
_assert_strict(errors)
f = BytesIO(input)
g = BytesIO()
quopri.encode(f, g, quotetabs=True)
return (g.getvalue(), len(input))

def quopri_decode(input, errors='strict'):
assert errors == 'strict'
_assert_strict(errors)
f = BytesIO(input)
g = BytesIO()
quopri.decode(f, g)
Expand Down
10 changes: 8 additions & 2 deletions Lib/encodings/uu_codec.py
Original file line number Diff line number Diff line change
Expand Up @@ -11,10 +11,16 @@
import binascii
from io import BytesIO

### Codec Helpers

def _assert_strict(errors):
if errors != 'strict':
raise ValueError(f'Unsupported error handling mode: "{errors}" - must be "strict"')

### Codec APIs

def uu_encode(input, errors='strict', filename='<data>', mode=0o666):
assert errors == 'strict'
_assert_strict(errors)
infile = BytesIO(input)
outfile = BytesIO()
read = infile.read
Expand All @@ -35,7 +41,7 @@ def uu_encode(input, errors='strict', filename='<data>', mode=0o666):
return (outfile.getvalue(), len(input))

def uu_decode(input, errors='strict'):
assert errors == 'strict'
_assert_strict(errors)
infile = BytesIO(input)
outfile = BytesIO()
readline = infile.readline
Expand Down
14 changes: 10 additions & 4 deletions Lib/encodings/zlib_codec.py
Original file line number Diff line number Diff line change
Expand Up @@ -8,14 +8,20 @@
import codecs
import zlib # this codec needs the optional zlib module !

### Codec Helpers

def _assert_strict(errors):
if errors != 'strict':
raise ValueError(f'Unsupported error handling mode: "{errors}" - must be "strict"')

### Codec APIs

def zlib_encode(input, errors='strict'):
assert errors == 'strict'
_assert_strict(errors)
return (zlib.compress(input), len(input))

def zlib_decode(input, errors='strict'):
assert errors == 'strict'
_assert_strict(errors)
return (zlib.decompress(input), len(input))

class Codec(codecs.Codec):
Expand All @@ -26,7 +32,7 @@ def decode(self, input, errors='strict'):

class IncrementalEncoder(codecs.IncrementalEncoder):
def __init__(self, errors='strict'):
assert errors == 'strict'
_assert_strict(errors)
self.errors = errors
self.compressobj = zlib.compressobj()

Expand All @@ -42,7 +48,7 @@ def reset(self):

class IncrementalDecoder(codecs.IncrementalDecoder):
def __init__(self, errors='strict'):
assert errors == 'strict'
_assert_strict(errors)
self.errors = errors
self.decompressobj = zlib.decompressobj()

Expand Down
14 changes: 14 additions & 0 deletions Lib/test/test_codecs.py
Original file line number Diff line number Diff line change
Expand Up @@ -3128,6 +3128,20 @@ def test_uu_invalid(self):
# Missing "begin" line
self.assertRaises(ValueError, codecs.decode, b"", "uu-codec")

def test_invalid_error_input(self):
for encoding in bytes_transform_encodings:
with self.subTest(encoding=encoding):
encoder = codecs.getencoder(encoding)
decoder = codecs.getdecoder(encoding)

self.assertRaises(ValueError, encoder, 'in', errors='notstrict')
self.assertRaises(ValueError, decoder, 'in', errors='notstrict')

incdev = codecs.getincrementaldecoder(encoding)
if encoding not in ('base64_codec', 'uu_codec', 'quopri_codec', 'hex_codec'):
self.assertRaises(ValueError, incdev, errors='notstrict')



# The codec system tries to add notes to exceptions in order to ensure
# the error mentions the operation being performed and the codec involved.
Expand Down
Original file line number Diff line number Diff line change
@@ -0,0 +1,4 @@
The ``base64_codec``, ``uu_codec``, ``quopri_codec``, ``hex_codec``,
``zlib_codec`` and ``bz2_codec`` now raise a :exc:`ValueError` when their
decoder/encoder is provided an *errors* parameter that is not equal to
``'strict'``.
Loading
pFad - Phonifier reborn

Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy