mirror of
https://github.com/python/cpython.git
synced 2025-10-24 10:23:58 +00:00
[3.13] gh-63161: Add more tests for source encoding (GH-139440) (#139443)
(cherry picked from commit b2f5ad0c6d)
Co-authored-by: Serhiy Storchaka <storchaka@gmail.com>
This commit is contained in:
Miss Islington (bot)
GitHub
parent
7bb51bd5be
commit
4216ea7c81
2 changed files with 179 additions and 22 deletions
|
|
@ -173,6 +173,8 @@ def test_tokenizer_fstring_warning_in_first_line(self):
|
|||
os.unlink(TESTFN)
|
||||
|
||||
|
||||
BUFSIZ = 2**13
|
||||
|
||||
class AbstractSourceEncodingTest:
|
||||
|
||||
def test_default_coding(self):
|
||||
|
|
@ -185,14 +187,20 @@ def test_first_coding_line(self):
|
|||
self.check_script_output(src, br"'\xc3\u20ac'")
|
||||
|
||||
def test_second_coding_line(self):
|
||||
src = (b'#\n'
|
||||
src = (b'#!/usr/bin/python\n'
|
||||
b'#coding:iso8859-15\n'
|
||||
b'print(ascii("\xc3\xa4"))\n')
|
||||
self.check_script_output(src, br"'\xc3\u20ac'")
|
||||
|
||||
def test_second_coding_line_empty_first_line(self):
|
||||
src = (b'\n'
|
||||
b'#coding:iso8859-15\n'
|
||||
b'print(ascii("\xc3\xa4"))\n')
|
||||
self.check_script_output(src, br"'\xc3\u20ac'")
|
||||
|
||||
def test_third_coding_line(self):
|
||||
# Only first two lines are tested for a magic comment.
|
||||
src = (b'#\n'
|
||||
src = (b'#!/usr/bin/python\n'
|
||||
b'#\n'
|
||||
b'#coding:iso8859-15\n'
|
||||
b'print(ascii("\xc3\xa4"))\n')
|
||||
|
|
@ -210,13 +218,52 @@ def test_double_coding_same_line(self):
|
|||
b'print(ascii("\xc3\xa4"))\n')
|
||||
self.check_script_output(src, br"'\xc3\u20ac'")
|
||||
|
||||
def test_double_coding_utf8(self):
|
||||
src = (b'#coding:utf-8\n'
|
||||
b'#coding:latin1\n'
|
||||
b'print(ascii("\xc3\xa4"))\n')
|
||||
self.check_script_output(src, br"'\xe4'")
|
||||
|
||||
def test_long_first_coding_line(self):
|
||||
src = (b'#' + b' '*BUFSIZ + b'coding:iso8859-15\n'
|
||||
b'print(ascii("\xc3\xa4"))\n')
|
||||
self.check_script_output(src, br"'\xc3\u20ac'")
|
||||
|
||||
def test_long_second_coding_line(self):
|
||||
src = (b'#!/usr/bin/python\n'
|
||||
b'#' + b' '*BUFSIZ + b'coding:iso8859-15\n'
|
||||
b'print(ascii("\xc3\xa4"))\n')
|
||||
self.check_script_output(src, br"'\xc3\u20ac'")
|
||||
|
||||
def test_long_coding_line(self):
|
||||
src = (b'#coding:iso-8859-15' + b' '*BUFSIZ + b'\n'
|
||||
b'print(ascii("\xc3\xa4"))\n')
|
||||
self.check_script_output(src, br"'\xc3\u20ac'")
|
||||
|
||||
def test_long_coding_name(self):
|
||||
src = (b'#coding:iso-8859-1-' + b'x'*BUFSIZ + b'\n'
|
||||
b'print(ascii("\xc3\xa4"))\n')
|
||||
self.check_script_output(src, br"'\xc3\xa4'")
|
||||
|
||||
def test_long_first_utf8_line(self):
|
||||
src = b'#' + b'\xc3\xa4'*(BUFSIZ//2) + b'\n'
|
||||
self.check_script_output(src, b'')
|
||||
src = b'# ' + b'\xc3\xa4'*(BUFSIZ//2) + b'\n'
|
||||
self.check_script_output(src, b'')
|
||||
|
||||
def test_long_second_utf8_line(self):
|
||||
src = b'\n#' + b'\xc3\xa4'*(BUFSIZ//2) + b'\n'
|
||||
self.check_script_output(src, b'')
|
||||
src = b'\n# ' + b'\xc3\xa4'*(BUFSIZ//2) + b'\n'
|
||||
self.check_script_output(src, b'')
|
||||
|
||||
def test_first_non_utf8_coding_line(self):
|
||||
src = (b'#coding:iso-8859-15 \xa4\n'
|
||||
b'print(ascii("\xc3\xa4"))\n')
|
||||
self.check_script_output(src, br"'\xc3\u20ac'")
|
||||
|
||||
def test_second_non_utf8_coding_line(self):
|
||||
src = (b'\n'
|
||||
src = (b'#!/usr/bin/python\n'
|
||||
b'#coding:iso-8859-15 \xa4\n'
|
||||
b'print(ascii("\xc3\xa4"))\n')
|
||||
self.check_script_output(src, br"'\xc3\u20ac'")
|
||||
|
|
@ -225,27 +272,56 @@ def test_utf8_bom(self):
|
|||
src = (b'\xef\xbb\xbfprint(ascii("\xc3\xa4"))\n')
|
||||
self.check_script_output(src, br"'\xe4'")
|
||||
|
||||
def test_utf8_bom_utf8_comments(self):
|
||||
src = (b'\xef\xbb\xbf#\xc3\xa4\n'
|
||||
b'#\xc3\xa4\n'
|
||||
b'print(ascii("\xc3\xa4"))\n')
|
||||
self.check_script_output(src, br"'\xe4'")
|
||||
|
||||
def test_utf8_bom_and_utf8_coding_line(self):
|
||||
src = (b'\xef\xbb\xbf#coding:utf-8\n'
|
||||
b'print(ascii("\xc3\xa4"))\n')
|
||||
self.check_script_output(src, br"'\xe4'")
|
||||
|
||||
def test_utf8_non_utf8_comment_line_error(self):
|
||||
src = (b'#coding: utf8\n'
|
||||
b'#\n'
|
||||
b'#\xa4\n'
|
||||
b'raise RuntimeError\n')
|
||||
self.check_script_error(src,
|
||||
br"'utf-8' codec can't decode byte|"
|
||||
br"encoding problem: utf8")
|
||||
|
||||
def test_crlf(self):
|
||||
src = (b'print(ascii("""\r\n"""))\n')
|
||||
out = self.check_script_output(src, br"'\n'")
|
||||
self.check_script_output(src, br"'\n'")
|
||||
|
||||
def test_crcrlf(self):
|
||||
src = (b'print(ascii("""\r\r\n"""))\n')
|
||||
out = self.check_script_output(src, br"'\n\n'")
|
||||
self.check_script_output(src, br"'\n\n'")
|
||||
|
||||
def test_crcrcrlf(self):
|
||||
src = (b'print(ascii("""\r\r\r\n"""))\n')
|
||||
out = self.check_script_output(src, br"'\n\n\n'")
|
||||
self.check_script_output(src, br"'\n\n\n'")
|
||||
|
||||
def test_crcrcrlf2(self):
|
||||
src = (b'#coding:iso-8859-1\n'
|
||||
b'print(ascii("""\r\r\r\n"""))\n')
|
||||
out = self.check_script_output(src, br"'\n\n\n'")
|
||||
self.check_script_output(src, br"'\n\n\n'")
|
||||
|
||||
def test_nul_in_first_coding_line(self):
|
||||
src = (b'#coding:iso8859-15\x00\n'
|
||||
b'\n'
|
||||
b'\n'
|
||||
b'raise RuntimeError\n')
|
||||
self.check_script_error(src, br"source code (string )?cannot contain null bytes")
|
||||
|
||||
def test_nul_in_second_coding_line(self):
|
||||
src = (b'#!/usr/bin/python\n'
|
||||
b'#coding:iso8859-15\x00\n'
|
||||
b'\n'
|
||||
b'raise RuntimeError\n')
|
||||
self.check_script_error(src, br"source code (string )?cannot contain null bytes")
|
||||
|
||||
|
||||
class UTF8ValidatorTest(unittest.TestCase):
|
||||
|
|
@ -325,6 +401,10 @@ def check_script_output(self, src, expected):
|
|||
out = stdout.getvalue().encode('latin1')
|
||||
self.assertEqual(out.rstrip(), expected)
|
||||
|
||||
def check_script_error(self, src, expected):
|
||||
with self.assertRaisesRegex(SyntaxError, expected.decode()) as cm:
|
||||
exec(src)
|
||||
|
||||
|
||||
class FileSourceEncodingTest(AbstractSourceEncodingTest, unittest.TestCase):
|
||||
|
||||
|
|
@ -336,6 +416,14 @@ def check_script_output(self, src, expected):
|
|||
res = script_helper.assert_python_ok(fn)
|
||||
self.assertEqual(res.out.rstrip(), expected)
|
||||
|
||||
def check_script_error(self, src, expected):
|
||||
with tempfile.TemporaryDirectory() as tmpd:
|
||||
fn = os.path.join(tmpd, 'test.py')
|
||||
with open(fn, 'wb') as fp:
|
||||
fp.write(src)
|
||||
res = script_helper.assert_python_failure(fn)
|
||||
self.assertRegex(res.err.rstrip().splitlines()[-1], b'SyntaxError.*?' + expected)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
unittest.main()
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue