Viewing file:  encoding.py (2.22 KB) -rw-r--r--
Select action/file-type:
 (+) |  (+) |  (+) | Code (+) | Session (+) |  (+) | SDB (+) |  (+) |  (+) |  (+) |  (+) |  (+) |
import datetime
from decimal import Decimal
import types
import six
def is_protected_type(obj):
"""Determine if the object instance is of a protected type.
Objects of protected types are preserved as-is when passed to
force_unicode(strings_only=True).
"""
return isinstance(obj, (
six.integer_types +
(types.NoneType,
datetime.datetime, datetime.date, datetime.time,
float, Decimal))
)
def force_unicode(s, encoding='utf-8', strings_only=False, errors='strict'):
"""
Similar to smart_text, except that lazy instances are resolved to
strings, rather than kept as lazy objects.
If strings_only is True, don't convert (some) non-string-like objects.
"""
# Handle the common case first, saves 30-40% when s is an instance of
# six.text_type. This function gets called often in that setting.
if isinstance(s, six.text_type):
return s
if strings_only and is_protected_type(s):
return s
try:
if not isinstance(s, six.string_types):
if hasattr(s, '__unicode__'):
s = s.__unicode__()
else:
if six.PY3:
if isinstance(s, bytes):
s = six.text_type(s, encoding, errors)
else:
s = six.text_type(s)
else:
s = six.text_type(bytes(s), encoding, errors)
else:
# Note: We use .decode() here, instead of six.text_type(s,
# encoding, errors), so that if s is a SafeBytes, it ends up being
# a SafeText at the end.
s = s.decode(encoding, errors)
except UnicodeDecodeError as e:
if not isinstance(s, Exception):
raise UnicodeDecodeError(*e.args)
else:
# If we get to here, the caller has passed in an Exception
# subclass populated with non-ASCII bytestring data without a
# working unicode method. Try to handle this without raising a
# further exception by individually forcing the exception args
# to unicode.
s = ' '.join([force_unicode(arg, encoding, strings_only,
errors) for arg in s])
return s
|