django1/django/utils/encoding.py

import types
import urllib
import datetime
from django.utils.functional import Promise

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 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 isinstance(s, (types.NoneType, int, long, datetime.datetime, datetime.date, datetime.time, float)):
        return s
    if not isinstance(s, basestring,):
        if hasattr(s, '__unicode__'):
            s = unicode(s)
        else:
            s = unicode(str(s), encoding, errors)
    elif not isinstance(s, unicode):
        s = unicode(s, encoding, errors)
    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:
            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 printable ASCII
    # characters that are not explicitly excluded by the list at the end of
    # section 3.1 of RFC 3987.
    if iri is None:
        return iri
    return urllib.quote(smart_str(iri), safe='/#%[]=:;$&()+,!?')