encoding.py :  » Content-Management-Systems » PyLucid » PyLucid_standalone » django » utils » Python Open Source

Home
Python Open Source
1.3.1.2 Python
2.Ajax
3.Aspect Oriented
4.Blog
5.Build
6.Business Application
7.Chart Report
8.Content Management Systems
9.Cryptographic
10.Database
11.Development
12.Editor
13.Email
14.ERP
15.Game 2D 3D
16.GIS
17.GUI
18.IDE
19.Installer
20.IRC
21.Issue Tracker
22.Language Interface
23.Log
24.Math
25.Media Sound Audio
26.Mobile
27.Network
28.Parser
29.PDF
30.Project Management
31.RSS
32.Search
33.Security
34.Template Engines
35.Test
36.UML
37.USB Serial
38.Web Frameworks
39.Web Server
40.Web Services
41.Web Unit
42.Wiki
43.Windows
44.XML
Python Open Source » Content Management Systems » PyLucid 
PyLucid » PyLucid_standalone » 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'
www.java2java.com | Contact Us
Copyright 2009 - 12 Demo Source and Support. All rights reserved.
All other trademarks are property of their respective owners.