bpo-41115: Modified src to raise rather `Unicode{Encode, Decode}Error` rather than plain `UnicodeError` by utkarsh261 · Pull Request #21170 · python/cpython · GitHub
Skip to content

bpo-41115: Modified src to raise rather Unicode{Encode, Decode}Error rather than plain UnicodeError #21170

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

Closed
utkarsh261 wants to merge 2 commits into from
Closed

bpo-41115: Modified src to raise rather Unicode{Encode, Decode}Error rather than plain UnicodeError #21170

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
14da3ee
Modified src to raise rather than plain
utkarsh261 Jun 26, 2020
c005cde
added missing space charaters because PEP8
utkarsh261 Jun 26, 2020
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
30 changes: 19 additions & 11 deletions Lib/encodings/idna.py
View file
Open in desktop
9 changes: 5 additions & 4 deletions Lib/encodings/punycode.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,16 +134,17 @@ def decode_generalized_number(extended, extpos, bias, errors):
char = ord(extended[extpos])
except IndexError:
if errors == "strict":
raise UnicodeError("incomplete punicode string")
raise UnicodeDecodeError("punycode", bytes(extended[extpos], "utf-8"), extpos, extpos+1,
"incomplete punycode string")
return extpos + 1, None
extpos += 1
if 0x41 <= char <= 0x5A: # A-Z
digit = char - 0x41
elif 0x30 <= char <= 0x39:
digit = char - 22 # 0x30-26
elif errors == "strict":
raise UnicodeError("Invalid extended code point '%s'"
% extended[extpos-1])
raise UnicodeDecodeError("punycode", bytes(extended[extpos-1], "utf-8"), extpos-1, extpos,
"Invalid extended code point '%s'" % extended[extpos-1])
else:
return extpos, None
t = T(j, bias)
Expand Down Expand Up @@ -171,7 +172,7 @@ def insertion_sort(base, extended, errors):
char += pos // (len(base) + 1)
if char > 0x10FFFF:
if errors == "strict":
raise UnicodeError("Invalid character U+%x" % char)
raise UnicodeDecodeError("punycode", bytes(char, "utf-8"), 0, len(char), "Invalid character U+%x" % char)
char = ord('?')
pos = pos % (len(base) + 1)
base = base[:pos] + chr(char) + base[pos:]
Expand Down
10 changes: 5 additions & 5 deletions Lib/encodings/undefined.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
""" Python 'undefined' Codec

This codec will always raise a ValueError exception when being
This codec will always raise a UnicodeEncodeError | UnicodeDecodeError exception when being
used. It is intended for use by the site.py file to switch off
automatic string to Unicode coercion.

Expand All @@ -16,18 +16,18 @@
class Codec(codecs.Codec):

def encode(self,input,errors='strict'):
raise UnicodeError("undefined encoding")
raise UnicodeEncodeError("undefined", str(input), 0, len(input), "undefined encoding")

def decode(self,input,errors='strict'):
raise UnicodeError("undefined encoding")
raise UnicodeDecodeError("undefined", bytes(input), 0, len(input), "undefined decoding")

class IncrementalEncoder(codecs.IncrementalEncoder):
def encode(self, input, final=False):
raise UnicodeError("undefined encoding")
raise UnicodeEncodeError("undefined", str(input), 0, len(input), "undefined encoding")

class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
raise UnicodeError("undefined encoding")
raise UnicodeDecodeError("undefined", bytes(input), 0, len(input), "undefined decoding")

class StreamWriter(Codec,codecs.StreamWriter):
pass
Expand Down
4 changes: 2 additions & 2 deletions Lib/encodings/utf_16.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -64,7 +64,7 @@ def _buffer_decode(self, input, errors, final):
elif byteorder == 1:
self.decoder = codecs.utf_16_be_decode
elif consumed >= 2:
raise UnicodeError("UTF-16 stream does not start with BOM")
raise UnicodeDecodeError("utc-16", input, 0, 0, "UTF-16 stream does not start with BOM")
return (output, consumed)
return self.decoder(input, self.errors, final)

Expand Down Expand Up @@ -138,7 +138,7 @@ def decode(self, input, errors='strict'):
elif byteorder == 1:
self.decode = codecs.utf_16_be_decode
elif consumed>=2:
raise UnicodeError("UTF-16 stream does not start with BOM")
raise UnicodeDecodeError("utf-16", input, 0, 0, "UTF-16 stream does not start with BOM")
return (object, consumed)

### encodings module API
Expand Down
4 changes: 2 additions & 2 deletions Lib/encodings/utf_32.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,7 @@ def _buffer_decode(self, input, errors, final):
elif byteorder == 1:
self.decoder = codecs.utf_32_be_decode
elif consumed >= 4:
raise UnicodeError("UTF-32 stream does not start with BOM")
raise UnicodeDecodeError("utf-32", input, 0, 0, "UTF-32 stream does not start with BOM")
return (output, consumed)
return self.decoder(input, self.errors, final)

Expand Down Expand Up @@ -133,7 +133,7 @@ def decode(self, input, errors='strict'):
elif byteorder == 1:
self.decode = codecs.utf_32_be_decode
elif consumed>=4:
raise UnicodeError("UTF-32 stream does not start with BOM")
raise UnicodeDecodeError("utf-32", input, 0, 0, "UTF-32 stream does not start with BOM")
return (object, consumed)

### encodings module API
Expand Down
4 changes: 2 additions & 2 deletions Lib/test/test_codecs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1334,13 +1334,13 @@ def test_decode(self):

def test_decode_invalid(self):
testcases = [
(b"xn--w&", "strict", UnicodeError()),
(b"xn--w&", "strict", UnicodeDecodeError("punycode", b"xn--w&", 0, 0, "")),
(b"xn--w&", "ignore", "xn-"),
]
for puny, errors, expected in testcases:
with self.subTest(puny=puny, errors=errors):
if isinstance(expected, Exception):
self.assertRaises(UnicodeError, puny.decode, "punycode", errors)
self.assertRaises(UnicodeDecodeError, puny.decode, "punycode", errors)
else:
self.assertEqual(puny.decode("punycode", errors), expected)

Expand Down
2 changes: 2 additions & 0 deletions Misc/NEWS.d/next/Library/2020-06-26-21-36-00.bpo-41115.DpUba5.rst
View file
Open in desktop