|
|
@ -108,7 +108,7 @@ except ImportError: |
|
|
|
|
|
|
|
compat_urllib_parse_asciire = re.compile('([\x00-\x7f]+)') |
|
|
|
|
|
|
|
def new_compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'): |
|
|
|
def compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'): |
|
|
|
"""Replace %xx escapes by their single-character equivalent. The optional |
|
|
|
encoding and errors parameters specify how to decode percent-encoded |
|
|
|
sequences into Unicode characters, as accepted by the bytes.decode() |
|
|
@ -142,45 +142,6 @@ except ImportError: |
|
|
|
append(bar) |
|
|
|
return ''.join(res) |
|
|
|
|
|
|
|
def old_compat_urllib_parse_unquote(string, encoding='utf-8', errors='replace'): |
|
|
|
if string == '': |
|
|
|
return string |
|
|
|
res = string.split('%') |
|
|
|
if len(res) == 1: |
|
|
|
return string |
|
|
|
if encoding is None: |
|
|
|
encoding = 'utf-8' |
|
|
|
if errors is None: |
|
|
|
errors = 'replace' |
|
|
|
# pct_sequence: contiguous sequence of percent-encoded bytes, decoded |
|
|
|
pct_sequence = b'' |
|
|
|
string = res[0] |
|
|
|
for item in res[1:]: |
|
|
|
try: |
|
|
|
if not item: |
|
|
|
raise ValueError |
|
|
|
if not re.match('[0-9a-fA-F][0-9a-fA-F]',item[:2]): |
|
|
|
raise ValueError |
|
|
|
pct_sequence += item[:2].decode('hex') |
|
|
|
rest = item[2:] |
|
|
|
if not rest: |
|
|
|
# This segment was just a single percent-encoded character. |
|
|
|
# May be part of a sequence of code units, so delay decoding. |
|
|
|
# (Stored in pct_sequence). |
|
|
|
continue |
|
|
|
except ValueError: |
|
|
|
rest = '%' + item |
|
|
|
# Encountered non-percent-encoded characters. Flush the current |
|
|
|
# pct_sequence. |
|
|
|
string += pct_sequence.decode(encoding, errors) + rest |
|
|
|
pct_sequence = b'' |
|
|
|
if pct_sequence: |
|
|
|
# Flush the final pct_sequence |
|
|
|
string += pct_sequence.decode(encoding, errors) |
|
|
|
return string |
|
|
|
|
|
|
|
compat_urllib_parse_unquote = new_compat_urllib_parse_unquote |
|
|
|
|
|
|
|
try: |
|
|
|
compat_str = unicode # Python 2 |
|
|
|
except NameError: |
|
|
|