Rip out all the u"..." literals and calls to unicode().
diff --git a/Lib/email/charset.py b/Lib/email/charset.py
index 9bebf6f..5b5e95d 100644
--- a/Lib/email/charset.py
+++ b/Lib/email/charset.py
@@ -202,10 +202,10 @@
# is already a unicode, we leave it at that, but ensure that the
# charset is ASCII, as the standard (RFC XXX) requires.
try:
- if isinstance(input_charset, unicode):
+ if isinstance(input_charset, str):
input_charset.encode('ascii')
else:
- input_charset = unicode(input_charset, 'ascii')
+ input_charset = str(input_charset, 'ascii')
except UnicodeError:
raise errors.CharsetError(input_charset)
input_charset = input_charset.lower()
@@ -264,7 +264,7 @@
def convert(self, s):
"""Convert a string from the input_codec to the output_codec."""
if self.input_codec != self.output_codec:
- return unicode(s, self.input_codec).encode(self.output_codec)
+ return str(s, self.input_codec).encode(self.output_codec)
else:
return s
@@ -281,10 +281,10 @@
Characters that could not be converted to Unicode will be replaced
with the Unicode replacement character U+FFFD.
"""
- if isinstance(s, unicode) or self.input_codec is None:
+ if isinstance(s, str) or self.input_codec is None:
return s
try:
- return unicode(s, self.input_codec, 'replace')
+ return str(s, self.input_codec, 'replace')
except LookupError:
# Input codec not installed on system, so return the original
# string unchanged.
@@ -307,7 +307,7 @@
codec = self.output_codec
else:
codec = self.input_codec
- if not isinstance(ustr, unicode) or codec is None:
+ if not isinstance(ustr, str) or codec is None:
return ustr
try:
return ustr.encode(codec, 'replace')
diff --git a/Lib/email/generator.py b/Lib/email/generator.py
index 4f3fea4..02b4495 100644
--- a/Lib/email/generator.py
+++ b/Lib/email/generator.py
@@ -23,7 +23,7 @@
def _is8bitstring(s):
if isinstance(s, str):
try:
- unicode(s, 'us-ascii')
+ str(s, 'us-ascii')
except UnicodeError:
return True
return False
diff --git a/Lib/email/header.py b/Lib/email/header.py
index ab0d3fc..675b68d 100644
--- a/Lib/email/header.py
+++ b/Lib/email/header.py
@@ -21,9 +21,9 @@
NL = '\n'
SPACE = ' '
-USPACE = u' '
+USPACE = ' '
SPACE8 = ' ' * 8
-UEMPTYSTRING = u''
+UEMPTYSTRING = ''
MAXLINELEN = 76
@@ -210,7 +210,7 @@
elif nextcs not in (None, 'us-ascii'):
uchunks.append(USPACE)
lastcs = nextcs
- uchunks.append(unicode(s, str(charset)))
+ uchunks.append(str(s, str(charset)))
return UEMPTYSTRING.join(uchunks)
# Rich comparison operators for equality only. BAW: does it make sense to
@@ -257,13 +257,13 @@
# Possibly raise UnicodeError if the byte string can't be
# converted to a unicode with the input codec of the charset.
incodec = charset.input_codec or 'us-ascii'
- ustr = unicode(s, incodec, errors)
+ ustr = str(s, incodec, errors)
# Now make sure that the unicode could be converted back to a
# byte string with the output codec, which may be different
# than the iput coded. Still, use the original byte string.
outcodec = charset.output_codec or 'us-ascii'
ustr.encode(outcodec, errors)
- elif isinstance(s, unicode):
+ elif isinstance(s, str):
# Now we have to be sure the unicode string can be converted
# to a byte string with a reasonable output codec. We want to
# use the byte string in the chunk.
diff --git a/Lib/email/message.py b/Lib/email/message.py
index 6fc3af1..1767bfb 100644
--- a/Lib/email/message.py
+++ b/Lib/email/message.py
@@ -751,13 +751,13 @@
# LookupError will be raised if the charset isn't known to
# Python. UnicodeError will be raised if the encoded text
# contains a character not in the charset.
- charset = unicode(charset[2], pcharset).encode('us-ascii')
+ charset = str(charset[2], pcharset).encode('us-ascii')
except (LookupError, UnicodeError):
charset = charset[2]
# charset character must be in us-ascii range
try:
if isinstance(charset, str):
- charset = unicode(charset, 'us-ascii')
+ charset = str(charset, 'us-ascii')
charset = charset.encode('us-ascii')
except UnicodeError:
return failobj
diff --git a/Lib/email/test/test_email.py b/Lib/email/test/test_email.py
index a2e09fa..e1d0eb7 100644
--- a/Lib/email/test/test_email.py
+++ b/Lib/email/test/test_email.py
@@ -505,7 +505,7 @@
msg = Message()
msg.set_charset('us-ascii')
self.assertEqual('us-ascii', msg.get_content_charset())
- msg.set_charset(u'us-ascii')
+ msg.set_charset('us-ascii')
self.assertEqual('us-ascii', msg.get_content_charset())
@@ -583,7 +583,7 @@
utf8 = Charset("utf-8")
g_head = "Die Mieter treten hier ein werden mit einem Foerderband komfortabel den Korridor entlang, an s\xfcdl\xfcndischen Wandgem\xe4lden vorbei, gegen die rotierenden Klingen bef\xf6rdert. "
cz_head = "Finan\xe8ni metropole se hroutily pod tlakem jejich d\xf9vtipu.. "
- utf8_head = u"\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
+ utf8_head = "\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
h = Header(g_head, g, header_name='Subject')
h.append(cz_head, cz)
h.append(utf8_head, utf8)
@@ -1514,7 +1514,7 @@
s = '=?ISO-8859-1?Q?Andr=E9?= Pirard <pirard@dom.ain>'
dh = decode_header(s)
eq(dh, [('Andr\xe9', 'iso-8859-1'), ('Pirard <pirard@dom.ain>', None)])
- hu = unicode(make_header(dh)).encode('latin-1')
+ hu = str(make_header(dh)).encode('latin-1')
eq(hu, 'Andr\xe9 Pirard <pirard@dom.ain>')
def test_whitespace_eater_unicode_2(self):
@@ -1524,7 +1524,7 @@
eq(dh, [('The', None), ('quick brown fox', 'iso-8859-1'),
('jumped over the', None), ('lazy dog', 'iso-8859-1')])
hu = make_header(dh).__unicode__()
- eq(hu, u'The quick brown fox jumped over the lazy dog')
+ eq(hu, 'The quick brown fox jumped over the lazy dog')
def test_rfc2047_without_whitespace(self):
s = 'Sm=?ISO-8859-1?B?9g==?=rg=?ISO-8859-1?B?5Q==?=sbord'
@@ -2770,7 +2770,7 @@
eq('hello w\xf6rld', c.body_encode('hello w\xf6rld'))
def test_unicode_charset_name(self):
- charset = Charset(u'us-ascii')
+ charset = Charset('us-ascii')
self.assertEqual(str(charset), 'us-ascii')
self.assertRaises(Errors.CharsetError, Charset, 'asc\xffii')
@@ -2809,7 +2809,7 @@
utf8 = Charset("utf-8")
g_head = "Die Mieter treten hier ein werden mit einem Foerderband komfortabel den Korridor entlang, an s\xfcdl\xfcndischen Wandgem\xe4lden vorbei, gegen die rotierenden Klingen bef\xf6rdert. "
cz_head = "Finan\xe8ni metropole se hroutily pod tlakem jejich d\xf9vtipu.. "
- utf8_head = u"\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
+ utf8_head = "\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
h = Header(g_head, g)
h.append(cz_head, cz)
h.append(utf8_head, utf8)
@@ -2829,7 +2829,7 @@
eq(decode_header(enc),
[(g_head, "iso-8859-1"), (cz_head, "iso-8859-2"),
(utf8_head, "utf-8")])
- ustr = unicode(h)
+ ustr = str(h)
eq(ustr.encode('utf-8'),
'Die Mieter treten hier ein werden mit einem Foerderband '
'komfortabel den Korridor entlang, an s\xc3\xbcdl\xc3\xbcndischen '
@@ -2897,9 +2897,9 @@
def test_utf8_shortest(self):
eq = self.assertEqual
- h = Header(u'p\xf6stal', 'utf-8')
+ h = Header('p\xf6stal', 'utf-8')
eq(h.encode(), '=?utf-8?q?p=C3=B6stal?=')
- h = Header(u'\u83ca\u5730\u6642\u592b', 'utf-8')
+ h = Header('\u83ca\u5730\u6642\u592b', 'utf-8')
eq(h.encode(), '=?utf-8?b?6I+K5Zyw5pmC5aSr?=')
def test_bad_8bit_header(self):
@@ -3152,7 +3152,7 @@
'''
msg = email.message_from_string(m)
self.assertEqual(msg.get_filename(),
- u'This is even more ***fun*** is it not.pdf\ufffd')
+ 'This is even more ***fun*** is it not.pdf\ufffd')
def test_rfc2231_unknown_encoding(self):
m = """\
diff --git a/Lib/email/test/test_email_codecs.py b/Lib/email/test/test_email_codecs.py
index 8b97530..1c77347 100644
--- a/Lib/email/test/test_email_codecs.py
+++ b/Lib/email/test/test_email_codecs.py
@@ -13,7 +13,7 @@
# We're compatible with Python 2.3, but it doesn't have the built-in Asian
# codecs, so we have to skip all these tests.
try:
- unicode('foo', 'euc-jp')
+ str('foo', 'euc-jp')
except LookupError:
raise TestSkipped
@@ -57,7 +57,7 @@
jcode = 'euc-jp'
msg = Message()
msg.set_payload(jhello, jcode)
- ustr = unicode(msg.get_payload(), msg.get_content_charset())
+ ustr = str(msg.get_payload(), msg.get_content_charset())
self.assertEqual(jhello, ustr.encode(jcode))
diff --git a/Lib/email/test/test_email_codecs_renamed.py b/Lib/email/test/test_email_codecs_renamed.py
index 10e2065..d190de3 100644
--- a/Lib/email/test/test_email_codecs_renamed.py
+++ b/Lib/email/test/test_email_codecs_renamed.py
@@ -13,7 +13,7 @@
# We're compatible with Python 2.3, but it doesn't have the built-in Asian
# codecs, so we have to skip all these tests.
try:
- unicode('foo', 'euc-jp')
+ str('foo', 'euc-jp')
except LookupError:
raise TestSkipped
@@ -57,7 +57,7 @@
jcode = 'euc-jp'
msg = Message()
msg.set_payload(jhello, jcode)
- ustr = unicode(msg.get_payload(), msg.get_content_charset())
+ ustr = str(msg.get_payload(), msg.get_content_charset())
self.assertEqual(jhello, ustr.encode(jcode))
diff --git a/Lib/email/test/test_email_renamed.py b/Lib/email/test/test_email_renamed.py
index 7f72270..4ce2184 100644
--- a/Lib/email/test/test_email_renamed.py
+++ b/Lib/email/test/test_email_renamed.py
@@ -564,7 +564,7 @@
utf8 = Charset("utf-8")
g_head = "Die Mieter treten hier ein werden mit einem Foerderband komfortabel den Korridor entlang, an s\xfcdl\xfcndischen Wandgem\xe4lden vorbei, gegen die rotierenden Klingen bef\xf6rdert. "
cz_head = "Finan\xe8ni metropole se hroutily pod tlakem jejich d\xf9vtipu.. "
- utf8_head = u"\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
+ utf8_head = "\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
h = Header(g_head, g, header_name='Subject')
h.append(cz_head, cz)
h.append(utf8_head, utf8)
@@ -1512,7 +1512,7 @@
s = '=?ISO-8859-1?Q?Andr=E9?= Pirard <pirard@dom.ain>'
dh = decode_header(s)
eq(dh, [('Andr\xe9', 'iso-8859-1'), ('Pirard <pirard@dom.ain>', None)])
- hu = unicode(make_header(dh)).encode('latin-1')
+ hu = str(make_header(dh)).encode('latin-1')
eq(hu, 'Andr\xe9 Pirard <pirard@dom.ain>')
def test_whitespace_eater_unicode_2(self):
@@ -1522,7 +1522,7 @@
eq(dh, [('The', None), ('quick brown fox', 'iso-8859-1'),
('jumped over the', None), ('lazy dog', 'iso-8859-1')])
hu = make_header(dh).__unicode__()
- eq(hu, u'The quick brown fox jumped over the lazy dog')
+ eq(hu, 'The quick brown fox jumped over the lazy dog')
def test_rfc2047_missing_whitespace(self):
s = 'Sm=?ISO-8859-1?B?9g==?=rg=?ISO-8859-1?B?5Q==?=sbord'
@@ -2769,7 +2769,7 @@
eq('hello w\xf6rld', c.body_encode('hello w\xf6rld'))
def test_unicode_charset_name(self):
- charset = Charset(u'us-ascii')
+ charset = Charset('us-ascii')
self.assertEqual(str(charset), 'us-ascii')
self.assertRaises(errors.CharsetError, Charset, 'asc\xffii')
@@ -2808,7 +2808,7 @@
utf8 = Charset("utf-8")
g_head = "Die Mieter treten hier ein werden mit einem Foerderband komfortabel den Korridor entlang, an s\xfcdl\xfcndischen Wandgem\xe4lden vorbei, gegen die rotierenden Klingen bef\xf6rdert. "
cz_head = "Finan\xe8ni metropole se hroutily pod tlakem jejich d\xf9vtipu.. "
- utf8_head = u"\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
+ utf8_head = "\u6b63\u78ba\u306b\u8a00\u3046\u3068\u7ffb\u8a33\u306f\u3055\u308c\u3066\u3044\u307e\u305b\u3093\u3002\u4e00\u90e8\u306f\u30c9\u30a4\u30c4\u8a9e\u3067\u3059\u304c\u3001\u3042\u3068\u306f\u3067\u305f\u3089\u3081\u3067\u3059\u3002\u5b9f\u969b\u306b\u306f\u300cWenn ist das Nunstuck git und Slotermeyer? Ja! Beiherhund das Oder die Flipperwaldt gersput.\u300d\u3068\u8a00\u3063\u3066\u3044\u307e\u3059\u3002".encode("utf-8")
h = Header(g_head, g)
h.append(cz_head, cz)
h.append(utf8_head, utf8)
@@ -2828,7 +2828,7 @@
eq(decode_header(enc),
[(g_head, "iso-8859-1"), (cz_head, "iso-8859-2"),
(utf8_head, "utf-8")])
- ustr = unicode(h)
+ ustr = str(h)
eq(ustr.encode('utf-8'),
'Die Mieter treten hier ein werden mit einem Foerderband '
'komfortabel den Korridor entlang, an s\xc3\xbcdl\xc3\xbcndischen '
@@ -2896,9 +2896,9 @@
def test_utf8_shortest(self):
eq = self.assertEqual
- h = Header(u'p\xf6stal', 'utf-8')
+ h = Header('p\xf6stal', 'utf-8')
eq(h.encode(), '=?utf-8?q?p=C3=B6stal?=')
- h = Header(u'\u83ca\u5730\u6642\u592b', 'utf-8')
+ h = Header('\u83ca\u5730\u6642\u592b', 'utf-8')
eq(h.encode(), '=?utf-8?b?6I+K5Zyw5pmC5aSr?=')
def test_bad_8bit_header(self):
@@ -3151,7 +3151,7 @@
'''
msg = email.message_from_string(m)
self.assertEqual(msg.get_filename(),
- u'This is even more ***fun*** is it not.pdf\ufffd')
+ 'This is even more ***fun*** is it not.pdf\ufffd')
def test_rfc2231_unknown_encoding(self):
m = """\
diff --git a/Lib/email/utils.py b/Lib/email/utils.py
index ee952d3..de9fbf8 100644
--- a/Lib/email/utils.py
+++ b/Lib/email/utils.py
@@ -44,7 +44,7 @@
COMMASPACE = ', '
EMPTYSTRING = ''
-UEMPTYSTRING = u''
+UEMPTYSTRING = ''
CRLF = '\r\n'
TICK = "'"
@@ -315,9 +315,9 @@
rawval = unquote(value[2])
charset = value[0] or 'us-ascii'
try:
- return unicode(rawval, charset, errors)
+ return str(rawval, charset, errors)
except LookupError:
# XXX charset is unknown to Python.
- return unicode(rawval, fallback_charset, errors)
+ return str(rawval, fallback_charset, errors)
else:
return unquote(value)