mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-04 00:48:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

gh-85287: Change codecs to raise precise UnicodeEncodeError and UnicodeDecodeError (#113674)

Browse source 
Co-authored-by: Inada Naoki <songofacandy@gmail.com>
This commit is contained in:
John Sloboda 2024-03-17 00:58:42 -04:00 • committed by GitHub
parent c514a975ab
commit 649857a157
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 306 additions and 81 deletions
Download patch file Download diff file Expand all files Collapse all files

42
Lib/encodings/punycode.py
View file

@ -1,4 +1,4 @@
""" Codec for the Punicode encoding, as specified in RFC 3492
""" Codec for the Punycode encoding, as specified in RFC 3492
Written by Martin v. Löwis.
"""
@ -131,10 +131,11 @@ def decode_generalized_number(extended, extpos, bias, errors):
j = 0
while 1:
try:
char = ord(extended[extpos])
char = extended[extpos]
except IndexError:
if errors == "strict":
raise UnicodeError("incomplete punicode string")
raise UnicodeDecodeError("punycode", extended, extpos, extpos+1,
"incomplete punycode string")
return extpos + 1, None
extpos += 1
if 0x41 <= char <= 0x5A: # A-Z
@ -142,8 +143,8 @@ def decode_generalized_number(extended, extpos, bias, errors):
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", extended, extpos-1, extpos,
f"Invalid extended code point '{extended[extpos-1]}'")
else:
return extpos, None
t = T(j, bias)
@ -155,11 +156,14 @@ def decode_generalized_number(extended, extpos, bias, errors):
def insertion_sort(base, extended, errors):
"""3.2 Insertion unsort coding"""
"""3.2 Insertion sort coding"""
# This function raises UnicodeDecodeError with position in the extended.
# Caller should add the offset.
char = 0x80
pos = -1
bias = 72
extpos = 0
while extpos < len(extended):
newpos, delta = decode_generalized_number(extended, extpos,
bias, errors)
@ -171,7 +175,9 @@ 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", extended, pos-1, pos,
f"Invalid character U+{char:x}")
char = ord('?')
pos = pos % (len(base) + 1)
base = base[:pos] + chr(char) + base[pos:]
@ -187,11 +193,21 @@ def punycode_decode(text, errors):
pos = text.rfind(b"-")
if pos == -1:
base = ""
extended = str(text, "ascii").upper()
extended = text.upper()
else:
base = str(text[:pos], "ascii", errors)
extended = str(text[pos+1:], "ascii").upper()
return insertion_sort(base, extended, errors)
try:
base = str(text[:pos], "ascii", errors)
except UnicodeDecodeError as exc:
raise UnicodeDecodeError("ascii", text, exc.start, exc.end,
exc.reason) from None
extended = text[pos+1:].upper()
try:
return insertion_sort(base, extended, errors)
except UnicodeDecodeError as exc:
offset = pos + 1
raise UnicodeDecodeError("punycode", text,
offset+exc.start, offset+exc.end,
exc.reason) from None
### Codec APIs
@ -203,7 +219,7 @@ class Codec(codecs.Codec):
def decode(self, input, errors='strict'):
if errors not in ('strict', 'replace', 'ignore'):
raise UnicodeError("Unsupported error handling "+errors)
raise UnicodeError(f"Unsupported error handling: {errors}")
res = punycode_decode(input, errors)
return res, len(input)
@ -214,7 +230,7 @@ class IncrementalEncoder(codecs.IncrementalEncoder):
class IncrementalDecoder(codecs.IncrementalDecoder):
def decode(self, input, final=False):
if self.errors not in ('strict', 'replace', 'ignore'):
raise UnicodeError("Unsupported error handling "+self.errors)
raise UnicodeError(f"Unsupported error handling: {self.errors}")
return punycode_decode(input, self.errors)
class StreamWriter(Codec,codecs.StreamWriter):