Coverage for tests / test_phystokens.py: 100.000%

1# Licensed under the Apache License: http://www.apache.org/licenses/LICENSE-2.0 

2# For details: https://github.com/coveragepy/coveragepy/blob/main/NOTICE.txt 

3 

4"""Tests for coverage.py's improved tokenizer.""" 

5 

6from __future__ import annotations 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

7 

8import os.path 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

9import re 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

10import sys 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

11import textwrap 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

12import warnings 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

13 

14import pytest 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

15 

16from coverage import env 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

17from coverage.phystokens import source_token_lines, source_encoding 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

18from coverage.python import get_python_source 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

19 

20from tests.coveragetest import CoverageTest, TESTS_DIR 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

21 

22 

23# A simple program and its token stream. 

24SIMPLE = """\ 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

25# yay! 

26def foo(): 

27 say('two = %d' % 2) 

28""" 

29 

30SIMPLE_TOKENS = [ 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

31 [("com", "# yay!")], 

32 [("key", "def"), ("ws", " "), ("nam", "foo"), ("op", "("), ("op", ")"), ("op", ":")], 

33 [ 

34 ("ws", " "), 

35 ("nam", "say"), 

36 ("op", "("), 

37 ("str", "'two = %d'"), 

38 ("ws", " "), 

39 ("op", "%"), 

40 ("ws", " "), 

41 ("num", "2"), 

42 ("op", ")"), 

43 ], 

44] 

45 

46# Mixed-white-space program, and its token stream. 

47MIXED_WS = """\ 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

48def hello(): 

49 a="Hello world!" 

50\tb="indented" 

51""" 

52 

53MIXED_WS_TOKENS = [ 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

54 [("key", "def"), ("ws", " "), ("nam", "hello"), ("op", "("), ("op", ")"), ("op", ":")], 

55 [("ws", " "), ("nam", "a"), ("op", "="), ("str", '"Hello world!"')], 

56 [("ws", " "), ("nam", "b"), ("op", "="), ("str", '"indented"')], 

57] 

58 

59# https://github.com/coveragepy/coveragepy/issues/822 

60BUG_822 = """\ 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

61print( "Message 1" ) 

62array = [ 1,2,3,4, # 4 numbers \\ 

63 5,6,7 ] # 3 numbers 

64print( "Message 2" ) 

65""" 

66 

67 

68class PhysTokensTest(CoverageTest): 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

69 """Tests for coverage.py's improved tokenizer.""" 

70 

71 run_in_temp_dir = False 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

72 

73 def check_tokenization(self, source: str) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

74 """Tokenize `source`, then put it back together, should be the same.""" 

75 tokenized = "" 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

76 for line in source_token_lines(source): 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

77 text = "".join(t for _, t in line) 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

78 tokenized += text + "\n" 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

79 # source_token_lines doesn't preserve trailing spaces, so trim all that 

80 # before comparing. 

81 source = source.replace("\r\n", "\n") 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

82 source = re.sub(r"(?m)[ \t]+$", "", source) 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

83 tokenized = re.sub(r"(?m)[ \t]+$", "", tokenized) 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

84 assert source == tokenized 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

85 

86 def check_file_tokenization(self, fname: str) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

87 """Use the contents of `fname` for `check_tokenization`.""" 

88 self.check_tokenization(get_python_source(fname)) 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

89 

90 def test_simple(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

91 assert list(source_token_lines(SIMPLE)) == SIMPLE_TOKENS 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

92 self.check_tokenization(SIMPLE) 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

93 

94 def test_missing_final_newline(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

95 # We can tokenize source that is missing the final newline. 

96 assert list(source_token_lines(SIMPLE.rstrip())) == SIMPLE_TOKENS 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

97 

98 def test_tab_indentation(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

99 # Mixed tabs and spaces... 

100 assert list(source_token_lines(MIXED_WS)) == MIXED_WS_TOKENS 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

101 

102 def test_bug_822(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

103 self.check_tokenization(BUG_822) 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

104 

105 def test_tokenize_real_file(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

106 # Check the tokenization of a real file (large, btw). 

107 real_file = os.path.join(TESTS_DIR, "test_coverage.py") 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

108 self.check_file_tokenization(real_file) 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

109 

110 def test_1828(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

111 # https://github.com/coveragepy/coveragepy/pull/1828 

112 tokens = list( 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

113 source_token_lines( 

114 textwrap.dedent(""" 

115 x = \ 

116 1 

117 a = ["aaa",\\ 

118 "bbb \\ 

119 ccc"] 

120 """) 

121 ) 

122 ) 

123 assert tokens == [ 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

124 [], 

125 [("nam", "x"), ("ws", " "), ("op", "="), ("ws", " "), ("num", "1")], 

126 [ 

127 ("nam", "a"), 

128 ("ws", " "), 

129 ("op", "="), 

130 ("ws", " "), 

131 ("op", "["), 

132 ("str", '"aaa"'), 

133 ("op", ","), 

134 ("xx", "\\"), 

135 ], 

136 [("ws", " "), ("str", '"bbb \\')], 

137 [("str", ' ccc"'), ("op", "]")], 

138 ] 

139 

140 @pytest.mark.parametrize( 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

141 "fname", 

142 [ 

143 "stress_phystoken.tok", 

144 "stress_phystoken_dos.tok", 

145 ], 

146 ) 

147 def test_stress(self, fname: str) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

148 # Check the tokenization of the stress-test files. 

149 # And check that those files haven't been incorrectly "fixed". 

150 with warnings.catch_warnings(): 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

151 warnings.filterwarnings("ignore", message=r".*invalid escape sequence") 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

152 

153 stress = os.path.join(TESTS_DIR, fname) 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

154 self.check_file_tokenization(stress) 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

155 with open(stress, encoding="utf-8") as fstress: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

156 assert re.search(r"(?m) $", fstress.read()), f"{stress} needs a trailing space." 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

157 

158 def test_fstring_middle(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

159 tokens = list( 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

160 source_token_lines( 

161 textwrap.dedent("""\ 

162 f'Look: {x} {{x}}!' 

163 """) 

164 ) 

165 ) 

166 if env.PYBEHAVIOR.fstring_syntax: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

167 assert tokens == [ 54 ctx1abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01

168 [ 

169 ("fst", "f'"), 

170 ("fst", "Look: "), 

171 ("op", "{"), 

172 ("nam", "x"), 

173 ("op", "}"), 

174 ("fst", " {{"), 

175 ("fst", "x}}"), 

176 ("fst", "!"), 

177 ("fst", "'"), 

178 ], 

179 ] 

180 else: 

181 assert tokens == [[("str", "f'Look: {x} {{x}}!'")]] 15 ctx123456789!#$%'()

182 

183 

184class SoftKeywordTest(CoverageTest): 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

185 """Tests the tokenizer handling soft keywords.""" 

186 

187 run_in_temp_dir = False 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

188 

189 def test_soft_keywords_match_case(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

190 source = textwrap.dedent("""\ 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

191 match re.match(something): 

192 case ["what"]: 

193 match = case("hello") 

194 case [_]: 

195 match("hello") 

196 match another.thing: 

197 case 1: 

198 pass 

199 

200 class case(): pass 

201 def match(): 

202 global case 

203 """) 

204 tokens = list(source_token_lines(source)) 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

205 assert tokens[0][0] == ("key", "match") 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

206 assert tokens[0][4] == ("nam", "match") 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

207 assert tokens[1][1] == ("key", "case") 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

208 assert tokens[2][1] == ("nam", "match") 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

209 assert tokens[2][5] == ("nam", "case") 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

210 assert tokens[3][1] == ("key", "case") 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

211 assert tokens[4][1] == ("nam", "match") 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

212 assert tokens[5][1] == ("key", "match") 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

213 assert tokens[6][1] == ("key", "case") 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

214 assert tokens[9][2] == ("nam", "case") 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

215 assert tokens[10][2] == ("nam", "match") 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

216 assert tokens[11][3] == ("nam", "case") 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

217 

218 @pytest.mark.skipif(sys.version_info < (3, 12), reason="type isn't a soft keyword until 3.12") 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

219 def test_soft_keyword_type(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

220 source = textwrap.dedent("""\ 54 ctx1abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01

221 type Point = tuple[float, float] 

222 type(int) 

223 """) 

224 tokens = list(source_token_lines(source)) 54 ctx1abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01

225 assert tokens[0][0] == ("key", "type") 54 ctx1abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01

226 assert tokens[1][0] == ("nam", "type") 54 ctx1abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01

227 

228 

229# The default source file encoding. 

230DEF_ENCODING = "utf-8" 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

231 

232 

233ENCODING_DECLARATION_SOURCES = [ 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

234 # Various forms from http://www.python.org/dev/peps/pep-0263/ 

235 (1, b"# coding=cp850\n\n", "cp850"), 

236 (1, b"# coding=latin-1\n", "iso-8859-1"), 

237 (1, b"# coding=iso-latin-1\n", "iso-8859-1"), 

238 (1, b"#!/usr/bin/python\n# -*- coding: cp850 -*-\n", "cp850"), 

239 (1, b"#!/usr/bin/python\n# vim: set fileencoding=cp850:\n", "cp850"), 

240 (1, b"# This Python file uses this encoding: cp850\n", "cp850"), 

241 (1, b"# This file uses a different encoding:\n# coding: cp850\n", "cp850"), 

242 (1, b"\n# coding=cp850\n\n", "cp850"), 

243 (2, b"# -*- coding:cp850 -*-\n# vim: fileencoding=cp850\n", "cp850"), 

244] 

245 

246 

247class SourceEncodingTest(CoverageTest): 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

248 """Tests of source_encoding() for detecting encodings.""" 

249 

250 run_in_temp_dir = False 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

251 

252 def test_detect_source_encoding(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

253 for _, source, expected in ENCODING_DECLARATION_SOURCES: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

254 assert source_encoding(source) == expected, f"Wrong encoding in {source!r}" 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

255 

256 def test_detect_source_encoding_not_in_comment(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

257 # Should not detect anything here 

258 source = b"def parse(src, encoding=None):\n pass" 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

259 assert source_encoding(source) == DEF_ENCODING 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

260 

261 def test_dont_detect_source_encoding_on_third_line(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

262 # A coding declaration doesn't count on the third line. 

263 source = b"\n\n# coding=cp850\n\n" 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

264 assert source_encoding(source) == DEF_ENCODING 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

265 

266 def test_detect_source_encoding_of_empty_file(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

267 # An important edge case. 

268 assert source_encoding(b"") == DEF_ENCODING 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

269 

270 def test_bom(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

271 # A BOM means utf-8. 

272 source = b"\xef\xbb\xbftext = 'hello'\n" 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

273 assert source_encoding(source) == "utf-8-sig" 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

274 

275 def test_bom_with_encoding(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

276 source = b"\xef\xbb\xbf# coding: utf-8\ntext = 'hello'\n" 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

277 assert source_encoding(source) == "utf-8-sig" 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

278 

279 def test_bom_is_wrong(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

280 # A BOM with an explicit non-utf8 encoding is an error. 

281 source = b"\xef\xbb\xbf# coding: cp850\n" 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

282 with pytest.raises(SyntaxError, match="encoding problem: utf-8"): 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

283 source_encoding(source) 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

284 

285 def test_unknown_encoding(self) -> None: 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

286 source = b"# coding: klingon\n" 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

287 with pytest.raises(SyntaxError, match="unknown encoding: klingon"): 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()

288 source_encoding(source) 69 ctx123456789!#$%abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ01'()