from __future__ import unicode_literals import codecs import datetime from decimal import Decimal import locale from django.utils.functional import Promise from django.utils import six from django.utils.six.moves.urllib.parse import quote class DjangoUnicodeDecodeError(UnicodeDecodeError): def __init__(self, obj, *args): self.obj = obj UnicodeDecodeError.__init__(self, *args) def __str__(self): original = UnicodeDecodeError.__str__(self) return '%s. You passed in %r (%s)' % (original, self.obj, type(self.obj)) 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 six.PY2: 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 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_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_text(strings_only=True). """ return isinstance(obj, six.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 # 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 DjangoUnicodeDecodeError(s, *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 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, 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, six.memoryview): s = bytes(s) if isinstance(s, bytes): if encoding == 'utf-8': return s else: return s.decode('utf-8', errors).encode(encoding, errors) if strings_only and is_protected_type(s): return s if isinstance(s, Promise): return six.text_type(s).encode(encoding, errors) if not isinstance(s, six.string_types): try: if six.PY3: return six.text_type(s).encode(encoding) else: return bytes(s) except UnicodeEncodeError: if isinstance(s, Exception): # An Exception subclass containing non-ASCII data that doesn't # know how to print itself properly. We shouldn't raise a # further exception. return b' '.join([force_bytes(arg, encoding, strings_only, errors) for arg in s]) return six.text_type(s).encode(encoding, errors) else: return s.encode(encoding, errors) 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 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). """ 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 portion that is suitable for inclusion in a URL. This is the algorithm from section 3.1 of RFC 3987. However, since we are assuming input is either UTF-8 or unicode already, we can simplify things a little from the full method. Returns an ASCII string containing the encoded result. """ # The list of safe characters here is constructed from the "reserved" and # "unreserved" characters specified in sections 2.2 and 2.3 of RFC 3986: # reserved = gen-delims / sub-delims # gen-delims = ":" / "/" / "?" / "#" / "[" / "]" / "@" # sub-delims = "!" / "$" / "&" / "'" / "(" / ")" # / "*" / "+" / "," / ";" / "=" # unreserved = ALPHA / DIGIT / "-" / "." / "_" / "~" # Of the unreserved characters, urllib.quote already considers all but # the ~ safe. # The % character is also added to the list of safe characters here, as the # end of section 3.1 of RFC 3987 specifically mentions that % must not be # converted. if iri is None: return iri return quote(force_bytes(iri), safe=b"/#%[]=:;$&()+,!?*@'~") def filepath_to_uri(path): """Convert a file system path to a URI portion that is suitable for inclusion in a URL. We are assuming input is either UTF-8 or unicode already. This method will encode certain chars that would normally be recognized as special chars for URIs. Note that this method does not encode the ' character, as it is a valid character within URIs. See encodeURIComponent() JavaScript function for more details. Returns an ASCII string containing the encoded result. """ if path is None: return path # I know about `os.sep` and `os.altsep` but I want to leave # some flexibility for hardcoding separators. return quote(force_bytes(path).replace(b"\\", b"/"), safe=b"/~!*()'") def get_system_encoding(): """ The encoding of the default system locale but falls back to the given fallback encoding if the encoding is unsupported by python or could not be determined. See tickets #10335 and #5846 """ try: encoding = locale.getdefaultlocale()[1] or 'ascii' codecs.lookup(encoding) except Exception: encoding = 'ascii' return encoding DEFAULT_LOCALE_ENCODING = get_system_encoding()