Python code coverage for Lib/test/test_source_encoding.py

#	count	content
1	n/a	# -- coding: koi8-r --
2	n/a
3	n/a	import unittest
4	n/a	from test.support import TESTFN, unlink, unload, rmtree, script_helper, captured_stdout
5	n/a	import importlib
6	n/a	import os
7	n/a	import sys
8	n/a	import subprocess
9	n/a	import tempfile
10	n/a
11	n/a	class MiscSourceEncodingTest(unittest.TestCase):
12	n/a
13	n/a	def test_pep263(self):
14	n/a	self.assertEqual(
15	n/a	"ðÉÔÏÎ".encode("utf-8"),
16	n/a	b'\xd0\x9f\xd0\xb8\xd1\x82\xd0\xbe\xd0\xbd'
17	n/a	)
18	n/a	self.assertEqual(
19	n/a	"\ð".encode("utf-8"),
20	n/a	b'\\\xd0\x9f'
21	n/a	)
22	n/a
23	n/a	def test_compilestring(self):
24	n/a	# see #1882
25	n/a	c = compile(b"\n# coding: utf-8\nu = '\xc3\xb3'\n", "dummy", "exec")
26	n/a	d = {}
27	n/a	exec(c, d)
28	n/a	self.assertEqual(d['u'], '\xf3')
29	n/a
30	n/a	def test_issue2301(self):
31	n/a	try:
32	n/a	compile(b"# coding: cp932\nprint '\x94\x4e'", "dummy", "exec")
33	n/a	except SyntaxError as v:
34	n/a	self.assertEqual(v.text, "print '\u5e74'\n")
35	n/a	else:
36	n/a	self.fail()
37	n/a
38	n/a	def test_issue4626(self):
39	n/a	c = compile("# coding=latin-1\n\u00c6 = '\u00c6'", "dummy", "exec")
40	n/a	d = {}
41	n/a	exec(c, d)
42	n/a	self.assertEqual(d['\xc6'], '\xc6')
43	n/a
44	n/a	def test_issue3297(self):
45	n/a	c = compile("a, b = '\U0001010F', '\\U0001010F'", "dummy", "exec")
46	n/a	d = {}
47	n/a	exec(c, d)
48	n/a	self.assertEqual(d['a'], d['b'])
49	n/a	self.assertEqual(len(d['a']), len(d['b']))
50	n/a	self.assertEqual(ascii(d['a']), ascii(d['b']))
51	n/a
52	n/a	def test_issue7820(self):
53	n/a	# Ensure that check_bom() restores all bytes in the right order if
54	n/a	# check_bom() fails in pydebug mode: a buffer starts with the first
55	n/a	# byte of a valid BOM, but next bytes are different
56	n/a
57	n/a	# one byte in common with the UTF-16-LE BOM
58	n/a	self.assertRaises(SyntaxError, eval, b'\xff\x20')
59	n/a
60	n/a	# two bytes in common with the UTF-8 BOM
61	n/a	self.assertRaises(SyntaxError, eval, b'\xef\xbb\x20')
62	n/a
63	n/a	def test_20731(self):
64	n/a	sub = subprocess.Popen([sys.executable,
65	n/a	os.path.join(os.path.dirname(__file__),
66	n/a	'coding20731.py')],
67	n/a	stderr=subprocess.PIPE)
68	n/a	err = sub.communicate()[1]
69	n/a	self.assertEqual(sub.returncode, 0)
70	n/a	self.assertNotIn(b'SyntaxError', err)
71	n/a
72	n/a	def test_error_message(self):
73	n/a	compile(b'# -- coding: iso-8859-15 --\n', 'dummy', 'exec')
74	n/a	compile(b'\xef\xbb\xbf\n', 'dummy', 'exec')
75	n/a	compile(b'\xef\xbb\xbf# -- coding: utf-8 --\n', 'dummy', 'exec')
76	n/a	with self.assertRaisesRegex(SyntaxError, 'fake'):
77	n/a	compile(b'# -- coding: fake --\n', 'dummy', 'exec')
78	n/a	with self.assertRaisesRegex(SyntaxError, 'iso-8859-15'):
79	n/a	compile(b'\xef\xbb\xbf# -- coding: iso-8859-15 --\n',
80	n/a	'dummy', 'exec')
81	n/a	with self.assertRaisesRegex(SyntaxError, 'BOM'):
82	n/a	compile(b'\xef\xbb\xbf# -- coding: iso-8859-15 --\n',
83	n/a	'dummy', 'exec')
84	n/a	with self.assertRaisesRegex(SyntaxError, 'fake'):
85	n/a	compile(b'\xef\xbb\xbf# -- coding: fake --\n', 'dummy', 'exec')
86	n/a	with self.assertRaisesRegex(SyntaxError, 'BOM'):
87	n/a	compile(b'\xef\xbb\xbf# -- coding: fake --\n', 'dummy', 'exec')
88	n/a
89	n/a	def test_bad_coding(self):
90	n/a	module_name = 'bad_coding'
91	n/a	self.verify_bad_module(module_name)
92	n/a
93	n/a	def test_bad_coding2(self):
94	n/a	module_name = 'bad_coding2'
95	n/a	self.verify_bad_module(module_name)
96	n/a
97	n/a	def verify_bad_module(self, module_name):
98	n/a	self.assertRaises(SyntaxError, __import__, 'test.' + module_name)
99	n/a
100	n/a	path = os.path.dirname(__file__)
101	n/a	filename = os.path.join(path, module_name + '.py')
102	n/a	with open(filename, "rb") as fp:
103	n/a	bytes = fp.read()
104	n/a	self.assertRaises(SyntaxError, compile, bytes, filename, 'exec')
105	n/a
106	n/a	def test_exec_valid_coding(self):
107	n/a	d = {}
108	n/a	exec(b'# coding: cp949\na = "\xaa\xa7"\n', d)
109	n/a	self.assertEqual(d['a'], '\u3047')
110	n/a
111	n/a	def test_file_parse(self):
112	n/a	# issue1134: all encodings outside latin-1 and utf-8 fail on
113	n/a	# multiline strings and long lines (>512 columns)
114	n/a	unload(TESTFN)
115	n/a	filename = TESTFN + ".py"
116	n/a	f = open(filename, "w", encoding="cp1252")
117	n/a	sys.path.insert(0, os.curdir)
118	n/a	try:
119	n/a	with f:
120	n/a	f.write("# -- coding: cp1252 --\n")
121	n/a	f.write("'''A short string\n")
122	n/a	f.write("'''\n")
123	n/a	f.write("'A very long string %s'\n" % ("X" * 1000))
124	n/a
125	n/a	importlib.invalidate_caches()
126	n/a	__import__(TESTFN)
127	n/a	finally:
128	n/a	del sys.path[0]
129	n/a	unlink(filename)
130	n/a	unlink(filename + "c")
131	n/a	unlink(filename + "o")
132	n/a	unload(TESTFN)
133	n/a	rmtree('__pycache__')
134	n/a
135	n/a	def test_error_from_string(self):
136	n/a	# See http://bugs.python.org/issue6289
137	n/a	input = "# coding: ascii\n\N{SNOWMAN}".encode('utf-8')
138	n/a	with self.assertRaises(SyntaxError) as c:
139	n/a	compile(input, "<string>", "exec")
140	n/a	expected = "'ascii' codec can't decode byte 0xe2 in position 16: " \
141	n/a	"ordinal not in range(128)"
142	n/a	self.assertTrue(c.exception.args[0].startswith(expected),
143	n/a	msg=c.exception.args[0])
144	n/a
145	n/a
146	n/a	class AbstractSourceEncodingTest:
147	n/a
148	n/a	def test_default_coding(self):
149	n/a	src = (b'print(ascii("\xc3\xa4"))\n')
150	n/a	self.check_script_output(src, br"'\xe4'")
151	n/a
152	n/a	def test_first_coding_line(self):
153	n/a	src = (b'#coding:iso8859-15\n'
154	n/a	b'print(ascii("\xc3\xa4"))\n')
155	n/a	self.check_script_output(src, br"'\xc3\u20ac'")
156	n/a
157	n/a	def test_second_coding_line(self):
158	n/a	src = (b'#\n'
159	n/a	b'#coding:iso8859-15\n'
160	n/a	b'print(ascii("\xc3\xa4"))\n')
161	n/a	self.check_script_output(src, br"'\xc3\u20ac'")
162	n/a
163	n/a	def test_third_coding_line(self):
164	n/a	# Only first two lines are tested for a magic comment.
165	n/a	src = (b'#\n'
166	n/a	b'#\n'
167	n/a	b'#coding:iso8859-15\n'
168	n/a	b'print(ascii("\xc3\xa4"))\n')
169	n/a	self.check_script_output(src, br"'\xe4'")
170	n/a
171	n/a	def test_double_coding_line(self):
172	n/a	# If the first line matches the second line is ignored.
173	n/a	src = (b'#coding:iso8859-15\n'
174	n/a	b'#coding:latin1\n'
175	n/a	b'print(ascii("\xc3\xa4"))\n')
176	n/a	self.check_script_output(src, br"'\xc3\u20ac'")
177	n/a
178	n/a	def test_double_coding_same_line(self):
179	n/a	src = (b'#coding:iso8859-15 coding:latin1\n'
180	n/a	b'print(ascii("\xc3\xa4"))\n')
181	n/a	self.check_script_output(src, br"'\xc3\u20ac'")
182	n/a
183	n/a	def test_first_non_utf8_coding_line(self):
184	n/a	src = (b'#coding:iso-8859-15 \xa4\n'
185	n/a	b'print(ascii("\xc3\xa4"))\n')
186	n/a	self.check_script_output(src, br"'\xc3\u20ac'")
187	n/a
188	n/a	def test_second_non_utf8_coding_line(self):
189	n/a	src = (b'\n'
190	n/a	b'#coding:iso-8859-15 \xa4\n'
191	n/a	b'print(ascii("\xc3\xa4"))\n')
192	n/a	self.check_script_output(src, br"'\xc3\u20ac'")
193	n/a
194	n/a	def test_utf8_bom(self):
195	n/a	src = (b'\xef\xbb\xbfprint(ascii("\xc3\xa4"))\n')
196	n/a	self.check_script_output(src, br"'\xe4'")
197	n/a
198	n/a	def test_utf8_bom_and_utf8_coding_line(self):
199	n/a	src = (b'\xef\xbb\xbf#coding:utf-8\n'
200	n/a	b'print(ascii("\xc3\xa4"))\n')
201	n/a	self.check_script_output(src, br"'\xe4'")
202	n/a
203	n/a
204	n/a	class BytesSourceEncodingTest(AbstractSourceEncodingTest, unittest.TestCase):
205	n/a
206	n/a	def check_script_output(self, src, expected):
207	n/a	with captured_stdout() as stdout:
208	n/a	exec(src)
209	n/a	out = stdout.getvalue().encode('latin1')
210	n/a	self.assertEqual(out.rstrip(), expected)
211	n/a
212	n/a
213	n/a	class FileSourceEncodingTest(AbstractSourceEncodingTest, unittest.TestCase):
214	n/a
215	n/a	def check_script_output(self, src, expected):
216	n/a	with tempfile.TemporaryDirectory() as tmpd:
217	n/a	fn = os.path.join(tmpd, 'test.py')
218	n/a	with open(fn, 'wb') as fp:
219	n/a	fp.write(src)
220	n/a	res = script_helper.assert_python_ok(fn)
221	n/a	self.assertEqual(res.out.rstrip(), expected)
222	n/a
223	n/a
224	n/a	if __name__ == "__main__":
225	n/a	unittest.main()