1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
|
"""
raven.utils.encoding
~~~~~~~~~~~~~~~~~~~~~~~~~~~~
:copyright: (c) 2010-2012 by the Sentry Team, see AUTHORS for more details.
:license: BSD, see LICENSE for more details.
"""
from __future__ import absolute_import, unicode_literals
import warnings
from raven.utils.compat import integer_types, text_type, binary_type, \
string_types, PY2
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_text(strings_only=True).
"""
import Decimal
import datetime
return isinstance(obj, integer_types + (type(None), float, Decimal,
datetime.datetime, datetime.date, datetime.time))
def force_text(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
# text_type. This function gets called often in that setting.
if isinstance(s, text_type):
return s
if strings_only and is_protected_type(s):
return s
try:
if not isinstance(s, string_types):
if hasattr(s, '__unicode__'):
s = s.__unicode__()
else:
if not PY2:
if isinstance(s, bytes):
s = text_type(s, encoding, errors)
else:
s = text_type(s)
else:
s = text_type(bytes(s), encoding, errors)
else:
# Note: We use .decode() here, instead of 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_text(arg, encoding, strings_only,
errors) for arg in s])
return s
def transform(value):
from raven.utils.serializer import transform
warnings.warn('You should switch to raven.utils.serializer.'
'transform', DeprecationWarning)
return transform(value)
def to_unicode(value):
try:
value = text_type(force_text(value))
except (UnicodeEncodeError, UnicodeDecodeError):
value = '(Error decoding value)'
except Exception: # in some cases we get a different exception
try:
value = text_type(force_text(repr(type(value))))
except Exception:
value = '(Error decoding value)'
return value
def to_string(value):
try:
return binary_type(value.decode('utf-8').encode('utf-8'))
except Exception:
return to_unicode(value).encode('utf-8')
|
