Python charset.Charset方法代码示例

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import Charset [as 别名]
def addr_header_encode(text, header_name=None):
    """Encode and line-wrap the value of an email header field containing
    email addresses."""

    # Convert to unicode, if required.
    if not isinstance(text, unicode):
        text = unicode(text, "utf-8")

    text = ", ".join(
        formataddr((header_encode(name), emailaddr))
        for name, emailaddr in getaddresses([text])
    )

    if is_ascii(text):
        charset = "ascii"
    else:
        charset = "utf-8"

    return Header(
        text, header_name=header_name, charset=Charset(charset)
    ).encode() 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import Charset [as 别名]
def make_header(decoded_seq, maxlinelen=None, header_name=None,
                continuation_ws=' '):
    """Create a Header from a sequence of pairs as returned by decode_header()

    decode_header() takes a header value string and returns a sequence of
    pairs of the format (decoded_string, charset) where charset is the string
    name of the character set.

    This function takes one of those sequence of pairs and returns a Header
    instance.  Optional maxlinelen, header_name, and continuation_ws are as in
    the Header constructor.
    """
    h = Header(maxlinelen=maxlinelen, header_name=header_name,
               continuation_ws=continuation_ws)
    for s, charset in decoded_seq:
        # None means us-ascii but we can simply pass it on to h.append()
        if charset is not None and not isinstance(charset, Charset):
            charset = Charset(charset)
        h.append(s, charset)
    return h 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import Charset [as 别名]
def test_getset_charset(self):
        eq = self.assertEqual
        msg = Message()
        eq(msg.get_charset(), None)
        charset = Charset('iso-8859-1')
        msg.set_charset(charset)
        eq(msg['mime-version'], '1.0')
        eq(msg.get_content_type(), 'text/plain')
        eq(msg['content-type'], 'text/plain; charset="iso-8859-1"')
        eq(msg.get_param('charset'), 'iso-8859-1')
        eq(msg['content-transfer-encoding'], 'quoted-printable')
        eq(msg.get_charset().input_charset, 'iso-8859-1')
        # Remove the charset
        msg.set_charset(None)
        eq(msg.get_charset(), None)
        eq(msg['content-type'], 'text/plain')
        # Try adding a charset when there's already MIME headers present
        msg = Message()
        msg['MIME-Version'] = '2.0'
        msg['Content-Type'] = 'text/x-weird'
        msg['Content-Transfer-Encoding'] = 'quinted-puntable'
        msg.set_charset(charset)
        eq(msg['mime-version'], '2.0')
        eq(msg['content-type'], 'text/x-weird; charset="iso-8859-1"')
        eq(msg['content-transfer-encoding'], 'quinted-puntable') 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import Charset [as 别名]
def test__all__(self):
        module = __import__('email')
        # Can't use sorted() here due to Python 2.3 compatibility
        all = module.__all__[:]
        all.sort()
        self.assertEqual(all, [
            # Old names
            'Charset', 'Encoders', 'Errors', 'Generator',
            'Header', 'Iterators', 'MIMEAudio', 'MIMEBase',
            'MIMEImage', 'MIMEMessage', 'MIMEMultipart',
            'MIMENonMultipart', 'MIMEText', 'Message',
            'Parser', 'Utils', 'base64MIME',
            # new names
            'base64mime', 'charset', 'encoders', 'errors', 'generator',
            'header', 'iterators', 'message', 'message_from_file',
            'message_from_string', 'mime', 'parser',
            'quopriMIME', 'quoprimime', 'utils',
            ]) 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import Charset [as 别名]
def test_charset_richcomparisons(self):
        eq = self.assertEqual
        ne = self.assertNotEqual
        cset1 = Charset()
        cset2 = Charset()
        eq(cset1, 'us-ascii')
        eq(cset1, 'US-ASCII')
        eq(cset1, 'Us-AsCiI')
        eq('us-ascii', cset1)
        eq('US-ASCII', cset1)
        eq('Us-AsCiI', cset1)
        ne(cset1, 'usascii')
        ne(cset1, 'USASCII')
        ne(cset1, 'UsAsCiI')
        ne('usascii', cset1)
        ne('USASCII', cset1)
        ne('UsAsCiI', cset1)
        eq(cset1, cset2)
        eq(cset2, cset1) 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import Charset [as 别名]
def test_get_body_encoding_with_uppercase_charset(self):
        eq = self.assertEqual
        msg = Message()
        msg['Content-Type'] = 'text/plain; charset=UTF-8'
        eq(msg['content-type'], 'text/plain; charset=UTF-8')
        charsets = msg.get_charsets()
        eq(len(charsets), 1)
        eq(charsets[0], 'utf-8')
        charset = Charset(charsets[0])
        eq(charset.get_body_encoding(), 'base64')
        msg.set_payload('hello world', charset=charset)
        eq(msg.get_payload(), 'aGVsbG8gd29ybGQ=\n')
        eq(msg.get_payload(decode=True), 'hello world')
        eq(msg['content-transfer-encoding'], 'base64')
        # Try another one
        msg = Message()
        msg['Content-Type'] = 'text/plain; charset="US-ASCII"'
        charsets = msg.get_charsets()
        eq(len(charsets), 1)
        eq(charsets[0], 'us-ascii')
        charset = Charset(charsets[0])
        eq(charset.get_body_encoding(), encoders.encode_7or8bit)
        msg.set_payload('hello world', charset=charset)
        eq(msg.get_payload(), 'hello world')
        eq(msg['content-transfer-encoding'], '7bit') 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import Charset [as 别名]
def set_payload(self, payload, charset=None):
        """Set the payload to the given value.

        Optional charset sets the message's default character set.  See
        set_charset() for details.
        """
        if hasattr(payload, 'encode'):
            if charset is None:
                self._payload = payload
                return
            if not isinstance(charset, Charset):
                charset = Charset(charset)
            payload = payload.encode(charset.output_charset)
        if hasattr(payload, 'decode'):
            self._payload = payload.decode('ascii', 'surrogateescape')
        else:
            self._payload = payload
        if charset is not None:
            self.set_charset(charset) 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import Charset [as 别名]
def header_encode(text, header_name=None):
    """Encode and line-wrap the value of an email header field."""

    # Convert to unicode, if required.
    if not isinstance(text, unicode):
        text = unicode(text, "utf-8")

    if is_ascii(text):
        charset = "ascii"
    else:
        charset = "utf-8"

    return Header(
        text, header_name=header_name, charset=Charset(charset)
    ).encode() 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import Charset [as 别名]
def test_get_body_encoding_with_bogus_charset(self):
        charset = Charset('not a charset')
        self.assertEqual(charset.get_body_encoding(), 'base64') 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import Charset [as 别名]
def test_encode(self):
        eq = self.assertEqual
        eq(quoprimime.encode(''), '')
        eq(quoprimime.encode('hello'), 'hello')
        # Test the binary flag
        eq(quoprimime.encode('hello\r\nworld'), 'hello\nworld')
        eq(quoprimime.encode('hello\r\nworld', 0), 'hello\nworld')
        # Test the maxlinelen arg
        eq(quoprimime.encode('xxxx ' * 20, maxlinelen=40), """\
xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxxx=
 xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxx=
x xxxx xxxx xxxx xxxx=20""")
        # Test the eol argument
        eq(quoprimime.encode('xxxx ' * 20, maxlinelen=40, eol='\r\n'), """\
xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxxx=\r
 xxxx xxxx xxxx xxxx xxxx xxxx xxxx xxx=\r
x xxxx xxxx xxxx xxxx=20""")
        eq(quoprimime.encode("""\
one line

two line"""), """\
one line

two line""")



# Test the Charset class 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import Charset [as 别名]
def test_idempotent(self):
        eq = self.assertEqual
        # Make sure us-ascii = no Unicode conversion
        c = Charset('us-ascii')
        s = 'Hello World!'
        sp = c.to_splittable(s)
        eq(s, c.from_splittable(sp))
        # test 8-bit idempotency with us-ascii
        s = '\xa4\xa2\xa4\xa4\xa4\xa6\xa4\xa8\xa4\xaa'
        sp = c.to_splittable(s)
        eq(s, c.from_splittable(sp)) 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import Charset [as 别名]
def test_body_encode(self):
        eq = self.assertEqual
        # Try a charset with QP body encoding
        c = Charset('iso-8859-1')
        eq('hello w=F6rld', c.body_encode('hello w\xf6rld'))
        # Try a charset with Base64 body encoding
        c = Charset('utf-8')
        eq('aGVsbG8gd29ybGQ=\n', c.body_encode('hello world'))
        # Try a charset with None body encoding
        c = Charset('us-ascii')
        eq('hello world', c.body_encode('hello world'))
        # Try the convert argument, where input codec != output codec
        c = Charset('euc-jp')
        # With apologies to Tokio Kikuchi ;)
        try:
            eq('\x1b$B5FCO;~IW\x1b(B',
               c.body_encode('\xb5\xc6\xc3\xcf\xbb\xfe\xc9\xd7'))
            eq('\xb5\xc6\xc3\xcf\xbb\xfe\xc9\xd7',
               c.body_encode('\xb5\xc6\xc3\xcf\xbb\xfe\xc9\xd7', False))
        except LookupError:
            # We probably don't have the Japanese codecs installed
            pass
        # Testing SF bug #625509, which we have to fake, since there are no
        # built-in encodings where the header encoding is QP but the body
        # encoding is not.
        from email import charset as CharsetModule
        CharsetModule.add_charset('fake', CharsetModule.QP, None)
        c = Charset('fake')
        eq('hello w\xf6rld', c.body_encode('hello w\xf6rld')) 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import Charset [as 别名]
def test_unicode_charset_name(self):
        charset = Charset(u'us-ascii')
        self.assertEqual(str(charset), 'us-ascii')
        self.assertRaises(errors.CharsetError, Charset, 'asc\xffii')



# Test multilingual MIME headers. 

# 需要导入模块: from email import charset [as 别名]
# 或者: from email.charset import Charset [as 别名]
def test_japanese_codecs(self):
        eq = self.ndiffAssertEqual
        j = Charset("euc-jp")
        g = Charset("iso-8859-1")
        h = Header("Hello World!")
        jhello = '\xa5\xcf\xa5\xed\xa1\xbc\xa5\xef\xa1\xbc\xa5\xeb\xa5\xc9\xa1\xaa'
        ghello = 'Gr\xfc\xdf Gott!'
        h.append(jhello, j)
        h.append(ghello, g)
        # BAW: This used to -- and maybe should -- fold the two iso-8859-1
        # chunks into a single encoded word.  However it doesn't violate the
        # standard to have them as two encoded chunks and maybe it's
        # reasonable <wink> for each .append() call to result in a separate
        # encoded word.
        eq(h.encode(), """\
Hello World! =?iso-2022-jp?b?GyRCJU8lbSE8JW8hPCVrJUkhKhsoQg==?=
 =?iso-8859-1?q?Gr=FC=DF?= =?iso-8859-1?q?_Gott!?=""")
        eq(decode_header(h.encode()),
           [('Hello World!', None),
            ('\x1b$B%O%m!<%o!<%k%I!*\x1b(B', 'iso-2022-jp'),
            ('Gr\xfc\xdf Gott!', 'iso-8859-1')])
        long = 'test-ja \xa4\xd8\xc5\xea\xb9\xc6\xa4\xb5\xa4\xec\xa4\xbf\xa5\xe1\xa1\xbc\xa5\xeb\xa4\xcf\xbb\xca\xb2\xf1\xbc\xd4\xa4\xce\xbe\xb5\xc7\xa7\xa4\xf2\xc2\xd4\xa4\xc3\xa4\xc6\xa4\xa4\xa4\xde\xa4\xb9'
        h = Header(long, j, header_name="Subject")
        # test a very long header
        enc = h.encode()
        # TK: splitting point may differ by codec design and/or Header encoding
        eq(enc , """\
=?iso-2022-jp?b?dGVzdC1qYSAbJEIkWEVqOUYkNSRsJD8lYSE8JWskTztKGyhC?=
 =?iso-2022-jp?b?GyRCMnE8VCROPjVHJyRyQlQkQyRGJCQkXiQ5GyhC?=""")
        # TK: full decode comparison
        eq(h.__unicode__().encode('euc-jp'), long)