diff options
Diffstat (limited to 'django/utils/encoding.py')
| -rw-r--r-- | django/utils/encoding.py | 49 |
1 files changed, 44 insertions, 5 deletions
diff --git a/django/utils/encoding.py b/django/utils/encoding.py index eb60cfde8b..3b284f3ed0 100644 --- a/django/utils/encoding.py +++ b/django/utils/encoding.py @@ -8,6 +8,7 @@ try: from urllib.parse import quote except ImportError: # Python 2 from urllib import quote +import warnings from django.utils.functional import Promise from django.utils import six @@ -32,6 +33,12 @@ class StrAndUnicode(object): Useful as a mix-in. If you support Python 2 and 3 with a single code base, you can inherit this mix-in and just define __unicode__. """ + def __init__(self, *args, **kwargs): + warnings.warn("StrAndUnicode is deprecated. Define a __str__ method " + "and apply the @python_2_unicode_compatible decorator " + "instead.", PendingDeprecationWarning, stacklevel=2) + super(StrAndUnicode, self).__init__(*args, **kwargs) + if six.PY3: def __str__(self): return self.__unicode__() @@ -39,6 +46,19 @@ class StrAndUnicode(object): def __str__(self): return self.__unicode__().encode('utf-8') +def python_2_unicode_compatible(klass): + """ + A decorator that defines __unicode__ and __str__ methods under Python 2. + Under Python 3 it does nothing. + + To support Python 2 and 3 with a single code base, define a __str__ method + returning text and apply this decorator to the class. + """ + if not six.PY3: + klass.__unicode__ = klass.__str__ + klass.__str__ = lambda self: self.__unicode__().encode('utf-8') + return klass + def smart_text(s, encoding='utf-8', strings_only=False, errors='strict'): """ Returns a text object representing 's' -- unicode on Python 2 and str on @@ -99,8 +119,8 @@ def force_text(s, encoding='utf-8', strings_only=False, errors='strict'): errors) for arg in s]) else: # Note: We use .decode() here, instead of six.text_type(s, encoding, - # errors), so that if s is a SafeString, it ends up being a - # SafeUnicode at the end. + # 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): @@ -121,6 +141,19 @@ def smart_bytes(s, encoding='utf-8', strings_only=False, errors='strict'): If strings_only is True, don't convert (some) non-string-like objects. """ + if isinstance(s, Promise): + # The input is the result of a gettext_lazy() call. + return s + return force_bytes(s, encoding, strings_only, errors) + + +def force_bytes(s, encoding='utf-8', strings_only=False, errors='strict'): + """ + Similar to smart_bytes, 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. + """ if isinstance(s, bytes): if encoding == 'utf-8': return s @@ -141,7 +174,7 @@ def smart_bytes(s, encoding='utf-8', strings_only=False, errors='strict'): # An Exception subclass containing non-ASCII data that doesn't # know how to print itself properly. We shouldn't raise a # further exception. - return ' '.join([smart_bytes(arg, encoding, strings_only, + return b' '.join([force_bytes(arg, encoding, strings_only, errors) for arg in s]) return six.text_type(s).encode(encoding, errors) else: @@ -149,8 +182,10 @@ def smart_bytes(s, encoding='utf-8', strings_only=False, errors='strict'): if six.PY3: smart_str = smart_text + force_str = force_text else: smart_str = smart_bytes + force_str = force_bytes # backwards compatibility for Python 2 smart_unicode = smart_text force_unicode = force_text @@ -161,6 +196,10 @@ Apply smart_text in Python 3 and smart_bytes in Python 2. This is suitable for writing to sys.stdout (for instance). """ +force_str.__doc__ = """\ +Apply force_text in Python 3 and force_bytes in Python 2. +""" + def iri_to_uri(iri): """ Convert an Internationalized Resource Identifier (IRI) portion to a URI @@ -186,7 +225,7 @@ def iri_to_uri(iri): # converted. if iri is None: return iri - return quote(smart_bytes(iri), safe=b"/#%[]=:;$&()+,!?*@'~") + return quote(force_bytes(iri), safe=b"/#%[]=:;$&()+,!?*@'~") def filepath_to_uri(path): """Convert an file system path to a URI portion that is suitable for @@ -205,7 +244,7 @@ def filepath_to_uri(path): return path # I know about `os.sep` and `os.altsep` but I want to leave # some flexibility for hardcoding separators. - return quote(smart_bytes(path).replace("\\", "/"), safe=b"/~!*()'") + return quote(force_bytes(path.replace("\\", "/")), safe=b"/~!*()'") # The encoding of the default system locale but falls back to the # given fallback encoding if the encoding is unsupported by python or could |