Python code coverage for Lib/test/test_importlib/source/test_source_encoding.py

#	count	content
1	n/a	from .. import util
2	n/a
3	n/a	machinery = util.import_importlib('importlib.machinery')
4	n/a
5	n/a	import codecs
6	n/a	import importlib.util
7	n/a	import re
8	n/a	import types
9	n/a	# Because sys.path gets essentially blanked, need to have unicodedata already
10	n/a	# imported for the parser to use.
11	n/a	import unicodedata
12	n/a	import unittest
13	n/a	import warnings
14	n/a
15	n/a
16	n/a	CODING_RE = re.compile(r'^[ \t\f]#.?coding[:=][ \t]*([-\w.]+)', re.ASCII)
17	n/a
18	n/a
19	n/a	class EncodingTest:
20	n/a
21	n/a	"""PEP 3120 makes UTF-8 the default encoding for source code
22	n/a	[default encoding].
23	n/a
24	n/a	PEP 263 specifies how that can change on a per-file basis. Either the first
25	n/a	or second line can contain the encoding line [encoding first line]
26	n/a	encoding second line]. If the file has the BOM marker it is considered UTF-8
27	n/a	implicitly [BOM]. If any encoding is specified it must be UTF-8, else it is
28	n/a	an error [BOM and utf-8][BOM conflict].
29	n/a
30	n/a	"""
31	n/a
32	n/a	variable = '\u00fc'
33	n/a	character = '\u00c9'
34	n/a	source_line = "{0} = '{1}'\n".format(variable, character)
35	n/a	module_name = '_temp'
36	n/a
37	n/a	def run_test(self, source):
38	n/a	with util.create_modules(self.module_name) as mapping:
39	n/a	with open(mapping[self.module_name], 'wb') as file:
40	n/a	file.write(source)
41	n/a	loader = self.machinery.SourceFileLoader(self.module_name,
42	n/a	mapping[self.module_name])
43	n/a	return self.load(loader)
44	n/a
45	n/a	def create_source(self, encoding):
46	n/a	encoding_line = "# coding={0}".format(encoding)
47	n/a	assert CODING_RE.match(encoding_line)
48	n/a	source_lines = [encoding_line.encode('utf-8')]
49	n/a	source_lines.append(self.source_line.encode(encoding))
50	n/a	return b'\n'.join(source_lines)
51	n/a
52	n/a	def test_non_obvious_encoding(self):
53	n/a	# Make sure that an encoding that has never been a standard one for
54	n/a	# Python works.
55	n/a	encoding_line = "# coding=koi8-r"
56	n/a	assert CODING_RE.match(encoding_line)
57	n/a	source = "{0}\na=42\n".format(encoding_line).encode("koi8-r")
58	n/a	self.run_test(source)
59	n/a
60	n/a	# [default encoding]
61	n/a	def test_default_encoding(self):
62	n/a	self.run_test(self.source_line.encode('utf-8'))
63	n/a
64	n/a	# [encoding first line]
65	n/a	def test_encoding_on_first_line(self):
66	n/a	encoding = 'Latin-1'
67	n/a	source = self.create_source(encoding)
68	n/a	self.run_test(source)
69	n/a
70	n/a	# [encoding second line]
71	n/a	def test_encoding_on_second_line(self):
72	n/a	source = b"#/usr/bin/python\n" + self.create_source('Latin-1')
73	n/a	self.run_test(source)
74	n/a
75	n/a	# [BOM]
76	n/a	def test_bom(self):
77	n/a	self.run_test(codecs.BOM_UTF8 + self.source_line.encode('utf-8'))
78	n/a
79	n/a	# [BOM and utf-8]
80	n/a	def test_bom_and_utf_8(self):
81	n/a	source = codecs.BOM_UTF8 + self.create_source('utf-8')
82	n/a	self.run_test(source)
83	n/a
84	n/a	# [BOM conflict]
85	n/a	def test_bom_conflict(self):
86	n/a	source = codecs.BOM_UTF8 + self.create_source('latin-1')
87	n/a	with self.assertRaises(SyntaxError):
88	n/a	self.run_test(source)
89	n/a
90	n/a
91	n/a	class EncodingTestPEP451(EncodingTest):
92	n/a
93	n/a	def load(self, loader):
94	n/a	module = types.ModuleType(self.module_name)
95	n/a	module.__spec__ = importlib.util.spec_from_loader(self.module_name, loader)
96	n/a	loader.exec_module(module)
97	n/a	return module
98	n/a
99	n/a
100	n/a	(Frozen_EncodingTestPEP451,
101	n/a	Source_EncodingTestPEP451
102	n/a	) = util.test_both(EncodingTestPEP451, machinery=machinery)
103	n/a
104	n/a
105	n/a	class EncodingTestPEP302(EncodingTest):
106	n/a
107	n/a	def load(self, loader):
108	n/a	with warnings.catch_warnings():
109	n/a	warnings.simplefilter('ignore', DeprecationWarning)
110	n/a	return loader.load_module(self.module_name)
111	n/a
112	n/a
113	n/a	(Frozen_EncodingTestPEP302,
114	n/a	Source_EncodingTestPEP302
115	n/a	) = util.test_both(EncodingTestPEP302, machinery=machinery)
116	n/a
117	n/a
118	n/a	class LineEndingTest:
119	n/a
120	n/a	r"""Source written with the three types of line endings (\n, \r\n, \r)
121	n/a	need to be readable [cr][crlf][lf]."""
122	n/a
123	n/a	def run_test(self, line_ending):
124	n/a	module_name = '_temp'
125	n/a	source_lines = [b"a = 42", b"b = -13", b'']
126	n/a	source = line_ending.join(source_lines)
127	n/a	with util.create_modules(module_name) as mapping:
128	n/a	with open(mapping[module_name], 'wb') as file:
129	n/a	file.write(source)
130	n/a	loader = self.machinery.SourceFileLoader(module_name,
131	n/a	mapping[module_name])
132	n/a	return self.load(loader, module_name)
133	n/a
134	n/a	# [cr]
135	n/a	def test_cr(self):
136	n/a	self.run_test(b'\r')
137	n/a
138	n/a	# [crlf]
139	n/a	def test_crlf(self):
140	n/a	self.run_test(b'\r\n')
141	n/a
142	n/a	# [lf]
143	n/a	def test_lf(self):
144	n/a	self.run_test(b'\n')
145	n/a
146	n/a
147	n/a	class LineEndingTestPEP451(LineEndingTest):
148	n/a
149	n/a	def load(self, loader, module_name):
150	n/a	module = types.ModuleType(module_name)
151	n/a	module.__spec__ = importlib.util.spec_from_loader(module_name, loader)
152	n/a	loader.exec_module(module)
153	n/a	return module
154	n/a
155	n/a
156	n/a	(Frozen_LineEndingTestPEP451,
157	n/a	Source_LineEndingTestPEP451
158	n/a	) = util.test_both(LineEndingTestPEP451, machinery=machinery)
159	n/a
160	n/a
161	n/a	class LineEndingTestPEP302(LineEndingTest):
162	n/a
163	n/a	def load(self, loader, module_name):
164	n/a	with warnings.catch_warnings():
165	n/a	warnings.simplefilter('ignore', DeprecationWarning)
166	n/a	return loader.load_module(module_name)
167	n/a
168	n/a
169	n/a	(Frozen_LineEndingTestPEP302,
170	n/a	Source_LineEndingTestPEP302
171	n/a	) = util.test_both(LineEndingTestPEP302, machinery=machinery)
172	n/a
173	n/a
174	n/a	if __name__ == '__main__':
175	n/a	unittest.main()