Skip to content

Commit 0e04987

Browse files
GallaecioGallaecio
committed
Remove the u prefix from literal strings
1 parent 9922b17 commit 0e04987

File tree

10 files changed

+264
-264
lines changed

10 files changed

+264
-264
lines changed

‎docs/conf.py‎

Lines changed: 8 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -47,8 +47,8 @@
4747
master_doc = 'index'
4848

4949
# General information about the project.
50-
project = u'w3lib'
51-
copyright = u'2014, w3lib developers'
50+
project = 'w3lib'
51+
copyright = '2014, w3lib developers'
5252

5353
# The version info for the project you're documenting, acts as replacement for
5454
# |version| and |release|, also used in various other places throughout the
@@ -190,8 +190,8 @@
190190
# Grouping the document tree into LaTeX files. List of tuples
191191
# (source start file, target name, title, author, documentclass [howto/manual]).
192192
latex_documents = [
193-
('index', 'w3lib.tex', u'w3lib Documentation',
194-
u'w3lib developers', 'manual'),
193+
('index', 'w3lib.tex', 'w3lib Documentation',
194+
'w3lib developers', 'manual'),
195195
]
196196

197197
# The name of an image file (relative to this directory) to place at the top of
@@ -220,8 +220,8 @@
220220
# One entry per manual page. List of tuples
221221
# (source start file, name, description, authors, manual section).
222222
man_pages = [
223-
('index', 'w3lib', u'w3lib Documentation',
224-
[u'w3lib developers'], 1)
223+
('index', 'w3lib', 'w3lib Documentation',
224+
['w3lib developers'], 1)
225225
]
226226

227227
# If true, show URL addresses after external links.
@@ -234,8 +234,8 @@
234234
# (source start file, target name, title, author,
235235
# dir menu entry, description, category)
236236
texinfo_documents = [
237-
('index', 'w3lib', u'w3lib Documentation',
238-
u'w3lib developers', 'w3lib', 'One line description of project.',
237+
('index', 'w3lib', 'w3lib Documentation',
238+
'w3lib developers', 'w3lib', 'One line description of project.',
239239
'Miscellaneous'),
240240
]
241241

‎tests/test_encoding.py‎

Lines changed: 42 additions & 42 deletions
Original file line numberDiff line numberDiff line change
@@ -29,7 +29,7 @@ class RequestEncodingTests(unittest.TestCase):
2929

3030
def test_bom(self):
3131
# cjk water character in unicode
32-
water_unicode = u'\u6C34'
32+
water_unicode = '\u6C34'
3333
# BOM + water character encoded
3434
utf16be = b'\xfe\xff\x6c\x34'
3535
utf16le = b'\xff\xfe\x34\x6c'
@@ -69,19 +69,19 @@ def test_html_body_declared_encoding(self):
6969

7070
def test_html_body_declared_encoding_unicode(self):
7171
# html_body_declared_encoding should work when unicode body is passed
72-
self.assertEqual(None, html_body_declared_encoding(u"something else"))
72+
self.assertEqual(None, html_body_declared_encoding("something else"))
7373

7474
for fragment in self.utf8_fragments:
7575
encoding = html_body_declared_encoding(fragment.decode('utf8'))
7676
self.assertEqual(encoding, 'utf-8', fragment)
7777

78-
self.assertEqual(None, html_body_declared_encoding(u"""
78+
self.assertEqual(None, html_body_declared_encoding("""
7979
<head></head><body>
8080
this isn't searched
8181
<meta charset="utf-8">
8282
"""))
8383
self.assertEqual(None, html_body_declared_encoding(
84-
u"""<meta http-equiv="Fake-Content-Type-Header" content="text/html; charset=utf-8">"""))
84+
"""<meta http-equiv="Fake-Content-Type-Header" content="text/html; charset=utf-8">"""))
8585

8686

8787
class CodecsEncodingTestCase(unittest.TestCase):
@@ -95,10 +95,10 @@ def test_resolve_encoding(self):
9595
class UnicodeDecodingTestCase(unittest.TestCase):
9696

9797
def test_utf8(self):
98-
self.assertEqual(to_unicode(b'\xc2\xa3', 'utf-8'), u'\xa3')
98+
self.assertEqual(to_unicode(b'\xc2\xa3', 'utf-8'), '\xa3')
9999

100100
def test_invalid_utf8(self):
101-
self.assertEqual(to_unicode(b'\xc2\xc2\xa3', 'utf-8'), u'\ufffd\xa3')
101+
self.assertEqual(to_unicode(b'\xc2\xc2\xa3', 'utf-8'), '\ufffd\xa3')
102102

103103

104104
def ct(charset):
@@ -110,7 +110,7 @@ def norm_encoding(enc):
110110
class HtmlConversionTests(unittest.TestCase):
111111

112112
def test_unicode_body(self):
113-
unicode_string = u'\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0447\u0435\u0441\u043a\u0438\u0439 \u0442\u0435\u043a\u0441\u0442'
113+
unicode_string = '\u043a\u0438\u0440\u0438\u043b\u043b\u0438\u0447\u0435\u0441\u043a\u0438\u0439 \u0442\u0435\u043a\u0441\u0442'
114114
original_string = unicode_string.encode('cp1251')
115115
encoding, body_unicode = html_to_unicode(ct('cp1251'), original_string)
116116
# check body_as_unicode
@@ -137,23 +137,23 @@ def test_content_type_and_conversion(self):
137137
"""Test content type header is interpreted and text converted as
138138
expected
139139
"""
140-
self._assert_encoding('utf-8', b"\xc2\xa3", 'utf-8', u"\xa3")
140+
self._assert_encoding('utf-8', b"\xc2\xa3", 'utf-8', "\xa3")
141141
# something like this in the scrapy tests - but that's invalid?
142-
# self._assert_encoding('', "\xa3", 'utf-8', u"\xa3")
142+
# self._assert_encoding('', "\xa3", 'utf-8', "\xa3")
143143
# iso-8859-1 is overridden to cp1252
144-
self._assert_encoding('iso-8859-1', b"\xa3", 'cp1252', u"\xa3")
145-
self._assert_encoding('', b"\xc2\xa3", 'utf-8', u"\xa3")
146-
self._assert_encoding('none', b"\xc2\xa3", 'utf-8', u"\xa3")
147-
self._assert_encoding('gb2312', b"\xa8D", 'gb18030', u"\u2015")
148-
self._assert_encoding('gbk', b"\xa8D", 'gb18030', u"\u2015")
149-
self._assert_encoding('big5', b"\xf9\xda", 'big5hkscs', u"\u6052")
144+
self._assert_encoding('iso-8859-1', b"\xa3", 'cp1252', "\xa3")
145+
self._assert_encoding('', b"\xc2\xa3", 'utf-8', "\xa3")
146+
self._assert_encoding('none', b"\xc2\xa3", 'utf-8', "\xa3")
147+
self._assert_encoding('gb2312', b"\xa8D", 'gb18030', "\u2015")
148+
self._assert_encoding('gbk', b"\xa8D", 'gb18030', "\u2015")
149+
self._assert_encoding('big5', b"\xf9\xda", 'big5hkscs', "\u6052")
150150

151151
def test_invalid_utf8_encoded_body_with_valid_utf8_BOM(self):
152152
# unlike scrapy, the BOM is stripped
153153
self._assert_encoding('utf-8', b"\xef\xbb\xbfWORD\xe3\xabWORD2",
154-
'utf-8', u'WORD\ufffdWORD2')
154+
'utf-8', 'WORD\ufffdWORD2')
155155
self._assert_encoding(None, b"\xef\xbb\xbfWORD\xe3\xabWORD2",
156-
'utf-8', u'WORD\ufffdWORD2')
156+
'utf-8', 'WORD\ufffdWORD2')
157157

158158
def test_utf8_unexpected_end_of_data_with_valid_utf8_BOM(self):
159159
# Python implementations handle unexpected end of UTF8 data
@@ -163,24 +163,24 @@ def test_utf8_unexpected_end_of_data_with_valid_utf8_BOM(self):
163163

164164
# unlike scrapy, the BOM is stripped
165165
self._assert_encoding('utf-8', b"\xef\xbb\xbfWORD\xe3\xab",
166-
'utf-8', [u'WORD\ufffd\ufffd', u'WORD\ufffd'])
166+
'utf-8', ['WORD\ufffd\ufffd', 'WORD\ufffd'])
167167
self._assert_encoding(None, b"\xef\xbb\xbfWORD\xe3\xab",
168-
'utf-8', [u'WORD\ufffd\ufffd', u'WORD\ufffd'])
168+
'utf-8', ['WORD\ufffd\ufffd', 'WORD\ufffd'])
169169

170170
def test_replace_wrong_encoding(self):
171171
"""Test invalid chars are replaced properly"""
172172
encoding, body_unicode = html_to_unicode(ct('utf-8'),
173173
b'PREFIX\xe3\xabSUFFIX')
174174
# XXX: Policy for replacing invalid chars may suffer minor variations
175-
# but it should always contain the unicode replacement char (u'\ufffd')
176-
assert u'\ufffd' in body_unicode, repr(body_unicode)
177-
assert u'PREFIX' in body_unicode, repr(body_unicode)
178-
assert u'SUFFIX' in body_unicode, repr(body_unicode)
175+
# but it should always contain the unicode replacement char ('\ufffd')
176+
assert '\ufffd' in body_unicode, repr(body_unicode)
177+
assert 'PREFIX' in body_unicode, repr(body_unicode)
178+
assert 'SUFFIX' in body_unicode, repr(body_unicode)
179179

180180
# Do not destroy html tags due to encoding bugs
181181
encoding, body_unicode = html_to_unicode(ct('utf-8'),
182182
b'\xf0<span>value</span>')
183-
assert u'<span>value</span>' in body_unicode, repr(body_unicode)
183+
assert '<span>value</span>' in body_unicode, repr(body_unicode)
184184

185185
def _assert_encoding_detected(self, content_type, expected_encoding, body,
186186
**kwargs):
@@ -193,39 +193,39 @@ def test_BOM(self):
193193
# utf-16 cases already tested, as is the BOM detection function
194194

195195
# http header takes precedence, irrespective of BOM
196-
bom_be_str = codecs.BOM_UTF16_BE + u"hi".encode('utf-16-be')
197-
expected = u'\ufffd\ufffd\x00h\x00i'
196+
bom_be_str = codecs.BOM_UTF16_BE + "hi".encode('utf-16-be')
197+
expected = '\ufffd\ufffd\x00h\x00i'
198198
self._assert_encoding('utf-8', bom_be_str, 'utf-8', expected)
199199

200200
# BOM is stripped when it agrees with the encoding, or used to
201201
# determine encoding
202202
bom_utf8_str = codecs.BOM_UTF8 + b'hi'
203-
self._assert_encoding('utf-8', bom_utf8_str, 'utf-8', u"hi")
204-
self._assert_encoding(None, bom_utf8_str, 'utf-8', u"hi")
203+
self._assert_encoding('utf-8', bom_utf8_str, 'utf-8', "hi")
204+
self._assert_encoding(None, bom_utf8_str, 'utf-8', "hi")
205205

206206
def test_utf16_32(self):
207207
# tools.ietf.org/html/rfc2781 section 4.3
208208

209209
# USE BOM and strip it
210-
bom_be_str = codecs.BOM_UTF16_BE + u"hi".encode('utf-16-be')
211-
self._assert_encoding('utf-16', bom_be_str, 'utf-16-be', u"hi")
212-
self._assert_encoding(None, bom_be_str, 'utf-16-be', u"hi")
210+
bom_be_str = codecs.BOM_UTF16_BE + "hi".encode('utf-16-be')
211+
self._assert_encoding('utf-16', bom_be_str, 'utf-16-be', "hi")
212+
self._assert_encoding(None, bom_be_str, 'utf-16-be', "hi")
213213

214-
bom_le_str = codecs.BOM_UTF16_LE + u"hi".encode('utf-16-le')
215-
self._assert_encoding('utf-16', bom_le_str, 'utf-16-le', u"hi")
216-
self._assert_encoding(None, bom_le_str, 'utf-16-le', u"hi")
214+
bom_le_str = codecs.BOM_UTF16_LE + "hi".encode('utf-16-le')
215+
self._assert_encoding('utf-16', bom_le_str, 'utf-16-le', "hi")
216+
self._assert_encoding(None, bom_le_str, 'utf-16-le', "hi")
217217

218-
bom_be_str = codecs.BOM_UTF32_BE + u"hi".encode('utf-32-be')
219-
self._assert_encoding('utf-32', bom_be_str, 'utf-32-be', u"hi")
220-
self._assert_encoding(None, bom_be_str, 'utf-32-be', u"hi")
218+
bom_be_str = codecs.BOM_UTF32_BE + "hi".encode('utf-32-be')
219+
self._assert_encoding('utf-32', bom_be_str, 'utf-32-be', "hi")
220+
self._assert_encoding(None, bom_be_str, 'utf-32-be', "hi")
221221

222-
bom_le_str = codecs.BOM_UTF32_LE + u"hi".encode('utf-32-le')
223-
self._assert_encoding('utf-32', bom_le_str, 'utf-32-le', u"hi")
224-
self._assert_encoding(None, bom_le_str, 'utf-32-le', u"hi")
222+
bom_le_str = codecs.BOM_UTF32_LE + "hi".encode('utf-32-le')
223+
self._assert_encoding('utf-32', bom_le_str, 'utf-32-le', "hi")
224+
self._assert_encoding(None, bom_le_str, 'utf-32-le', "hi")
225225

226226
# if there is no BOM, big endian should be chosen
227-
self._assert_encoding('utf-16', u"hi".encode('utf-16-be'), 'utf-16-be', u"hi")
228-
self._assert_encoding('utf-32', u"hi".encode('utf-32-be'), 'utf-32-be', u"hi")
227+
self._assert_encoding('utf-16', "hi".encode('utf-16-be'), 'utf-16-be', "hi")
228+
self._assert_encoding('utf-32', "hi".encode('utf-32-be'), 'utf-32-be', "hi")
229229

230230
def test_python_crash(self):
231231
import random

‎tests/test_form.py‎

Lines changed: 10 additions & 10 deletions
Original file line numberDiff line numberDiff line change
@@ -23,20 +23,20 @@ def test_encode_multipart(self):
2323

2424
def test_encode_multipart_unicode(self):
2525
data = OrderedDict([
26-
(u'ключ1', u'значение1'.encode('utf8')),
27-
(u'ключ2', u'значение2'),
26+
('ключ1', 'значение1'.encode('utf8')),
27+
('ключ2', 'значение2'),
2828
])
2929
with warnings.catch_warnings(record=True):
3030
body, boundary = encode_multipart(data)
3131
expected_body = (
32-
u'\r\n--{boundary}'
33-
u'\r\nContent-Disposition: form-data; name="ключ1"\r\n'
34-
u'\r\nзначение1'
35-
u'\r\n--{boundary}'
36-
u'\r\nContent-Disposition: form-data; name="ключ2"\r\n'
37-
u'\r\nзначение2'
38-
u'\r\n--{boundary}--'
39-
u'\r\n'.format(boundary=boundary).encode('utf8')
32+
'\r\n--{boundary}'
33+
'\r\nContent-Disposition: form-data; name="ключ1"\r\n'
34+
'\r\nзначение1'
35+
'\r\n--{boundary}'
36+
'\r\nContent-Disposition: form-data; name="ключ2"\r\n'
37+
'\r\nзначение2'
38+
'\r\n--{boundary}--'
39+
'\r\n'.format(boundary=boundary).encode('utf8')
4040
)
4141
self.assertEqual(body, expected_body)
4242

0 commit comments

Comments
 (0)