django1/django/utils/encoding.py

import types
import urllib
import locale
import datetime
import codecs

from django.utils.functional import Promise

try:
    from decimal import Decimal
except ImportError:
    from django.utils._decimal import Decimal # Python 2.3 fallback


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))

class StrAndUnicode(object):
    """
    A class whose __str__ returns its __unicode__ as a UTF-8 bytestring.

    Useful as a mix-in.
    """
    def __str__(self):
        return self.__unicode__().encode('utf-8')

def smart_unicode(s, encoding='utf-8', strings_only=False, errors='strict'):
    """
    Returns a unicode object representing 's'. 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)

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, (
        types.NoneType,
        int, long,
        datetime.datetime, datetime.date, datetime.time,
        float, Decimal)
    )

def force_unicode(s, encoding='utf-8', strings_only=False, errors='strict'):
    """
    Similar to smart_unicode, 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 strings_only and is_protected_type(s):
        return s
    try:
        if not isinstance(s, basestring,):
            if hasattr(s, '__unicode__'):
                s = unicode(s)
            else:
                try:
                    s = unicode(str(s), encoding, errors)
                except UnicodeEncodeError:
                    if not isinstance(s, Exception):
                        raise
                    # If we get to here, the caller has passed in an Exception
                    # subclass populated with non-ASCII data without special
                    # handling to display as a string. We need to handle this
                    # 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,
                            errors) for arg in s])
        elif not isinstance(s, unicode):
            # Note: We use .decode() here, instead of unicode(s, encoding,
            # errors), so that if s is a SafeString, it ends up being a
            # SafeUnicode at the end.
            s = s.decode(encoding, errors)
    except UnicodeDecodeError, 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_unicode(arg, encoding, strings_only,
                    errors) for arg in s])
    return s

def smart_str(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 strings_only and isinstance(s, (types.NoneType, int)):
        return s
    if isinstance(s, Promise):
        return unicode(s).encode(encoding, errors)
    elif not isinstance(s, basestring):
        try:
            return str(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 ' '.join([smart_str(arg, encoding, strings_only,
                        errors) for arg in s])
            return unicode(s).encode(encoding, errors)
    elif isinstance(s, unicode):
        return s.encode(encoding, errors)
    elif s and encoding != 'utf-8':
        return s.decode('utf-8', errors).encode(encoding, errors)
    else:
        return s

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  = "!" / "$" / "&" / "'" / "(" / ")"
    #                   / "*" / "+" / "," / ";" / "="
    #     unreserved  = ALPHA / DIGIT / "-" / "." / "_" / "~"
    # Of the unreserved characters, urllib.quote already considers all but
    # the ~ safe.
    # The % character is also added to the list of safe characters here, as the
    # end of section 3.1 of RFC 3987 specifically mentions that % must not be
    # converted.
    if iri is None:
        return iri
    return urllib.quote(smart_str(iri), safe="/#%[]=:;$&()+,!?*@'~")


# 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:
    DEFAULT_LOCALE_ENCODING = locale.getdefaultlocale()[1] or 'ascii'
    codecs.lookup(DEFAULT_LOCALE_ENCODING)
except:
    DEFAULT_LOCALE_ENCODING = 'ascii'