1# -*- coding: koi8-r -*- 2 3import unittest 4from test.test_support import run_unittest, rmtree, captured_stdout 5import script_helper 6import os 7import tempfile 8 9class MiscSourceEncodingTest(unittest.TestCase): 10 11 def test_pep263(self): 12 self.assertEqual( 13 u"�����".encode("utf-8"), 14 '\xd0\x9f\xd0\xb8\xd1\x82\xd0\xbe\xd0\xbd' 15 ) 16 self.assertEqual( 17 u"\�".encode("utf-8"), 18 '\\\xd0\x9f' 19 ) 20 21 def test_compilestring(self): 22 # see #1882 23 c = compile("\n# coding: utf-8\nu = u'\xc3\xb3'\n", "dummy", "exec") 24 d = {} 25 exec c in d 26 self.assertEqual(d['u'], u'\xf3') 27 28 def test_issue3297(self): 29 c = compile("a, b = '\U0001010F', '\\U0001010F'", "dummy", "exec") 30 d = {} 31 exec(c, d) 32 self.assertEqual(d['a'], d['b']) 33 self.assertEqual(len(d['a']), len(d['b'])) 34 35 def test_issue7820(self): 36 # Ensure that check_bom() restores all bytes in the right order if 37 # check_bom() fails in pydebug mode: a buffer starts with the first 38 # byte of a valid BOM, but next bytes are different 39 40 # one byte in common with the UTF-16-LE BOM 41 self.assertRaises(SyntaxError, eval, '\xff\x20') 42 43 # two bytes in common with the UTF-8 BOM 44 self.assertRaises(SyntaxError, eval, '\xef\xbb\x20') 45 46 def test_error_message(self): 47 compile('# -*- coding: iso-8859-15 -*-\n', 'dummy', 'exec') 48 compile('\xef\xbb\xbf\n', 'dummy', 'exec') 49 compile('\xef\xbb\xbf# -*- coding: utf-8 -*-\n', 'dummy', 'exec') 50 with self.assertRaisesRegexp(SyntaxError, 'fake'): 51 compile('# -*- coding: fake -*-\n', 'dummy', 'exec') 52 with self.assertRaisesRegexp(SyntaxError, 'iso-8859-15'): 53 compile('\xef\xbb\xbf# -*- coding: iso-8859-15 -*-\n', 54 'dummy', 'exec') 55 with self.assertRaisesRegexp(SyntaxError, 'BOM'): 56 compile('\xef\xbb\xbf# -*- coding: iso-8859-15 -*-\n', 57 'dummy', 'exec') 58 with self.assertRaisesRegexp(SyntaxError, 'fake'): 59 compile('\xef\xbb\xbf# -*- coding: fake -*-\n', 'dummy', 'exec') 60 with self.assertRaisesRegexp(SyntaxError, 'BOM'): 61 compile('\xef\xbb\xbf# -*- coding: fake -*-\n', 'dummy', 'exec') 62 63 def test_non_unicode_codec(self): 64 with self.assertRaisesRegexp(SyntaxError, 65 'codec did not return a unicode'): 66 from test import bad_coding3 67 68 69 def test_bad_coding(self): 70 module_name = 'bad_coding' 71 self.verify_bad_module(module_name) 72 73 def test_bad_coding2(self): 74 module_name = 'bad_coding2' 75 self.verify_bad_module(module_name) 76 77 def verify_bad_module(self, module_name): 78 self.assertRaises(SyntaxError, __import__, 'test.' + module_name) 79 80 path = os.path.dirname(__file__) 81 filename = os.path.join(path, module_name + '.py') 82 with open(filename) as fp: 83 text = fp.read() 84 self.assertRaises(SyntaxError, compile, text, filename, 'exec') 85 86 def test_error_from_string(self): 87 # See http://bugs.python.org/issue6289 88 input = u"# coding: ascii\n\N{SNOWMAN}".encode('utf-8') 89 with self.assertRaises(SyntaxError) as c: 90 compile(input, "<string>", "exec") 91 expected = "'ascii' codec can't decode byte 0xe2 in position 16: " \ 92 "ordinal not in range(128)" 93 self.assertTrue(c.exception.args[0].startswith(expected)) 94 95 96class AbstractSourceEncodingTest: 97 98 def test_first_coding_line(self): 99 src = ('#coding:iso8859-15\n' 100 'print(repr(u"\xc3\xa4"))\n') 101 self.check_script_output(src, r"u'\xc3\u20ac'") 102 103 def test_second_coding_line(self): 104 src = ('#\n' 105 '#coding:iso8859-15\n' 106 'print(repr(u"\xc3\xa4"))\n') 107 self.check_script_output(src, r"u'\xc3\u20ac'") 108 109 def test_double_coding_line(self): 110 # If the first line matches the second line is ignored. 111 src = ('#coding:iso8859-15\n' 112 '#coding:latin1\n' 113 'print(repr(u"\xc3\xa4"))\n') 114 self.check_script_output(src, r"u'\xc3\u20ac'") 115 116 def test_double_coding_same_line(self): 117 src = ('#coding:iso8859-15 coding:latin1\n' 118 'print(repr(u"\xc3\xa4"))\n') 119 self.check_script_output(src, r"u'\xc3\u20ac'") 120 121 def test_first_non_utf8_coding_line(self): 122 src = ('#coding:iso-8859-15 \xa4\n' 123 'print(repr(u"\xc3\xa4"))\n') 124 self.check_script_output(src, r"u'\xc3\u20ac'") 125 126 def test_second_non_utf8_coding_line(self): 127 src = ('\n' 128 '#coding:iso-8859-15 \xa4\n' 129 'print(repr(u"\xc3\xa4"))\n') 130 self.check_script_output(src, r"u'\xc3\u20ac'") 131 132 def test_utf8_bom(self): 133 src = ('\xef\xbb\xbfprint(repr(u"\xc3\xa4"))\n') 134 self.check_script_output(src, r"u'\xe4'") 135 136 def test_utf8_bom_and_utf8_coding_line(self): 137 src = ('\xef\xbb\xbf#coding:utf-8\n' 138 'print(repr(u"\xc3\xa4"))\n') 139 self.check_script_output(src, r"u'\xe4'") 140 141 142class BytesSourceEncodingTest(AbstractSourceEncodingTest, unittest.TestCase): 143 144 def check_script_output(self, src, expected): 145 with captured_stdout() as stdout: 146 exec(src) 147 out = stdout.getvalue().encode('latin1') 148 self.assertEqual(out.rstrip(), expected) 149 150 151class FileSourceEncodingTest(AbstractSourceEncodingTest, unittest.TestCase): 152 153 def check_script_output(self, src, expected): 154 tmpd = tempfile.mkdtemp() 155 try: 156 fn = os.path.join(tmpd, 'test.py') 157 with open(fn, 'wb') as fp: 158 fp.write(src) 159 rc, out, err = script_helper.assert_python_ok(fn) 160 finally: 161 rmtree(tmpd) 162 self.assertEqual(out.rstrip(), expected) 163 164 165def test_main(): 166 run_unittest(MiscSourceEncodingTest, BytesSourceEncodingTest, FileSourceEncodingTest) 167 168if __name__ == "__main__": 169 test_main() 170