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
|