diff options
Diffstat (limited to 'django/utils/encoding.py')
| -rw-r--r-- | django/utils/encoding.py | 68 |
1 files changed, 43 insertions, 25 deletions
diff --git a/django/utils/encoding.py b/django/utils/encoding.py index f2295444bf..eb60cfde8b 100644 --- a/django/utils/encoding.py +++ b/django/utils/encoding.py @@ -24,9 +24,13 @@ class DjangoUnicodeDecodeError(UnicodeDecodeError): class StrAndUnicode(object): """ - A class whose __str__ returns its __unicode__ as a UTF-8 bytestring. + A class that derives __str__ from __unicode__. - Useful as a mix-in. + On Python 2, __str__ returns the output of __unicode__ encoded as a UTF-8 + bytestring. On Python 3, __str__ returns the output of __unicode__. + + 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__. """ if six.PY3: def __str__(self): @@ -35,37 +39,36 @@ class StrAndUnicode(object): def __str__(self): return self.__unicode__().encode('utf-8') -def smart_unicode(s, encoding='utf-8', strings_only=False, errors='strict'): +def smart_text(s, encoding='utf-8', strings_only=False, errors='strict'): """ - Returns a unicode object representing 's'. Treats bytestrings using the - 'encoding' codec. + Returns a text object representing 's' -- unicode on Python 2 and str on + Python 3. Treats bytestrings using the 'encoding' codec. 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_unicode(s, encoding, strings_only, errors) + return force_text(s, encoding, strings_only, errors) 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). + force_text(strings_only=True). """ return isinstance(obj, six.integer_types + (type(None), float, Decimal, datetime.datetime, datetime.date, datetime.time)) -def force_unicode(s, encoding='utf-8', strings_only=False, errors='strict'): +def force_text(s, encoding='utf-8', strings_only=False, errors='strict'): """ - Similar to smart_unicode, except that lazy instances are resolved to + 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% in performance when s - # is an instance of unicode. This function gets called often in that - # setting. + # 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): @@ -92,9 +95,9 @@ def force_unicode(s, encoding='utf-8', strings_only=False, errors='strict'): # without raising a further exception. We do an # approximation to what the Exception's standard str() # output should be. - s = ' '.join([force_unicode(arg, encoding, strings_only, + s = ' '.join([force_text(arg, encoding, strings_only, errors) for arg in s]) - elif not isinstance(s, six.text_type): + 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. @@ -108,21 +111,26 @@ def force_unicode(s, encoding='utf-8', strings_only=False, errors='strict'): # 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, + s = ' '.join([force_text(arg, encoding, strings_only, errors) for arg in s]) return s -def smart_str(s, encoding='utf-8', strings_only=False, errors='strict'): +def smart_bytes(s, encoding='utf-8', strings_only=False, errors='strict'): """ Returns a bytestring version of 's', encoded as specified in 'encoding'. If strings_only is True, don't convert (some) non-string-like objects. """ + if isinstance(s, bytes): + if encoding == 'utf-8': + return s + else: + return s.decode('utf-8', errors).encode(encoding, errors) if strings_only and (s is None or isinstance(s, int)): return s if isinstance(s, Promise): return six.text_type(s).encode(encoding, errors) - elif not isinstance(s, six.string_types): + if not isinstance(s, six.string_types): try: if six.PY3: return six.text_type(s).encode(encoding) @@ -133,15 +141,25 @@ def smart_str(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_str(arg, encoding, strings_only, + return ' '.join([smart_bytes(arg, encoding, strings_only, errors) for arg in s]) return six.text_type(s).encode(encoding, errors) - elif isinstance(s, six.text_type): - return s.encode(encoding, errors) - elif s and encoding != 'utf-8': - return s.decode('utf-8', errors).encode(encoding, errors) else: - return s + return s.encode(encoding, errors) + +if six.PY3: + smart_str = smart_text +else: + smart_str = smart_bytes + # backwards compatibility for Python 2 + smart_unicode = smart_text + force_unicode = force_text + +smart_str.__doc__ = """\ +Apply smart_text in Python 3 and smart_bytes in Python 2. + +This is suitable for writing to sys.stdout (for instance). +""" def iri_to_uri(iri): """ @@ -168,7 +186,7 @@ def iri_to_uri(iri): # converted. if iri is None: return iri - return quote(smart_str(iri), safe=b"/#%[]=:;$&()+,!?*@'~") + return quote(smart_bytes(iri), safe=b"/#%[]=:;$&()+,!?*@'~") def filepath_to_uri(path): """Convert an file system path to a URI portion that is suitable for @@ -187,7 +205,7 @@ 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_str(path).replace("\\", "/"), safe=b"/~!*()'") + return quote(smart_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 |