mirrors/cpython
1
0
Fork 0
mirror of https://github.com/python/cpython.git synced 2025-08-24 10:45:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8

gh-105564: Don't include artificial newlines in the line attribute of tokens (#105565)

Browse source
This commit is contained in:
Pablo Galindo Salgado 2023-06-09 17:01:26 +01:00 • committed by GitHub
parent 1dd267af64
commit d7f46bcd98
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
4 changed files with 30 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

34
Lib/test/test_peg_generator/test_pegen.py
View file

@ -552,14 +552,14 @@ class TestPegen(unittest.TestCase):
string="D", string="D",
start=(1, 0), start=(1, 0),
end=(1, 1), end=(1, 1),
line="D A C A E\n", line="D A C A E",
), ),
TokenInfo( TokenInfo(
type=NAME, type=NAME,
string="A", string="A",
start=(1, 2), start=(1, 2),
end=(1, 3), end=(1, 3),
line="D A C A E\n", line="D A C A E",
), ),
], ],
TokenInfo( TokenInfo(
@ -567,7 +567,7 @@ class TestPegen(unittest.TestCase):
string="C", string="C",
start=(1, 4), start=(1, 4),
end=(1, 5), end=(1, 5),
line="D A C A E\n", line="D A C A E",
), ),
], ],
TokenInfo( TokenInfo(
@ -575,11 +575,11 @@ class TestPegen(unittest.TestCase):
string="A", string="A",
start=(1, 6), start=(1, 6),
end=(1, 7), end=(1, 7),
line="D A C A E\n", line="D A C A E",
), ),
], ],
TokenInfo( TokenInfo(
type=NAME, string="E", start=(1, 8), end=(1, 9), line="D A C A E\n" type=NAME, string="E", start=(1, 8), end=(1, 9), line="D A C A E"
), ),
], ],
) )
@ -594,22 +594,22 @@ class TestPegen(unittest.TestCase):
string="B", string="B",
start=(1, 0), start=(1, 0),
end=(1, 1), end=(1, 1),
line="B C A E\n", line="B C A E",
), ),
TokenInfo( TokenInfo(
type=NAME, type=NAME,
string="C", string="C",
start=(1, 2), start=(1, 2),
end=(1, 3), end=(1, 3),
line="B C A E\n", line="B C A E",
), ),
], ],
TokenInfo( TokenInfo(
type=NAME, string="A", start=(1, 4), end=(1, 5), line="B C A E\n" type=NAME, string="A", start=(1, 4), end=(1, 5), line="B C A E"
), ),
], ],
TokenInfo( TokenInfo(
type=NAME, string="E", start=(1, 6), end=(1, 7), line="B C A E\n" type=NAME, string="E", start=(1, 6), end=(1, 7), line="B C A E"
), ),
], ],
) )
@ -655,10 +655,10 @@ class TestPegen(unittest.TestCase):
node, node,
[ [
TokenInfo( TokenInfo(
NAME, string="foo", start=(1, 0), end=(1, 3), line="foo = 12 + 12 .\n" NAME, string="foo", start=(1, 0), end=(1, 3), line="foo = 12 + 12 ."
), ),
TokenInfo( TokenInfo(
OP, string="=", start=(1, 4), end=(1, 5), line="foo = 12 + 12 .\n" OP, string="=", start=(1, 4), end=(1, 5), line="foo = 12 + 12 ."
), ),
[ [
TokenInfo( TokenInfo(
@ -666,7 +666,7 @@ class TestPegen(unittest.TestCase):
string="12", string="12",
start=(1, 6), start=(1, 6),
end=(1, 8), end=(1, 8),
line="foo = 12 + 12 .\n", line="foo = 12 + 12 .",
), ),
[ [
[ [
@ -675,14 +675,14 @@ class TestPegen(unittest.TestCase):
string="+", string="+",
start=(1, 9), start=(1, 9),
end=(1, 10), end=(1, 10),
line="foo = 12 + 12 .\n", line="foo = 12 + 12 .",
), ),
TokenInfo( TokenInfo(
NUMBER, NUMBER,
string="12", string="12",
start=(1, 11), start=(1, 11),
end=(1, 13), end=(1, 13),
line="foo = 12 + 12 .\n", line="foo = 12 + 12 .",
), ),
] ]
], ],
@ -734,9 +734,9 @@ class TestPegen(unittest.TestCase):
self.assertEqual( self.assertEqual(
node, node,
[ [
TokenInfo(OP, string="(", start=(1, 0), end=(1, 1), line="(1)\n"), TokenInfo(OP, string="(", start=(1, 0), end=(1, 1), line="(1)"),
TokenInfo(NUMBER, string="1", start=(1, 1), end=(1, 2), line="(1)\n"), TokenInfo(NUMBER, string="1", start=(1, 1), end=(1, 2), line="(1)"),
TokenInfo(OP, string=")", start=(1, 2), end=(1, 3), line="(1)\n"), TokenInfo(OP, string=")", start=(1, 2), end=(1, 3), line="(1)"),
], ],
) )

16
Lib/test/test_tokenize.py
View file

@ -1229,7 +1229,7 @@ class Test_Tokenize(TestCase):
# skip the initial encoding token and the end tokens # skip the initial encoding token and the end tokens
tokens = list(_generate_tokens_from_c_tokenizer(readline().__next__, encoding='utf-8', tokens = list(_generate_tokens_from_c_tokenizer(readline().__next__, encoding='utf-8',
extra_tokens=True))[:-2] extra_tokens=True))[:-2]
expected_tokens = [TokenInfo(3, '"ЉЊЈЁЂ"', (1, 0), (1, 7), '"ЉЊЈЁЂ"\n')] expected_tokens = [TokenInfo(3, '"ЉЊЈЁЂ"', (1, 0), (1, 7), '"ЉЊЈЁЂ"')]
self.assertEqual(tokens, expected_tokens, self.assertEqual(tokens, expected_tokens,
"bytes not decoded with encoding") "bytes not decoded with encoding")
@ -1638,8 +1638,8 @@ class TestTokenize(TestCase):
TokenInfo(type=token.NUMBER, string='1', start=(1, 4), end=(1, 5), line='b = 1\n'), TokenInfo(type=token.NUMBER, string='1', start=(1, 4), end=(1, 5), line='b = 1\n'),
TokenInfo(type=token.NEWLINE, string='\n', start=(1, 5), end=(1, 6), line='b = 1\n'), TokenInfo(type=token.NEWLINE, string='\n', start=(1, 5), end=(1, 6), line='b = 1\n'),
TokenInfo(type=token.NL, string='\n', start=(2, 0), end=(2, 1), line='\n'), TokenInfo(type=token.NL, string='\n', start=(2, 0), end=(2, 1), line='\n'),
TokenInfo(type=token.COMMENT, string='#test', start=(3, 0), end=(3, 5), line='#test\n'), TokenInfo(type=token.COMMENT, string='#test', start=(3, 0), end=(3, 5), line='#test'),
TokenInfo(type=token.NL, string='', start=(3, 5), end=(3, 6), line='#test\n'), TokenInfo(type=token.NL, string='', start=(3, 5), end=(3, 6), line='#test'),
TokenInfo(type=token.ENDMARKER, string='', start=(4, 0), end=(4, 0), line='') TokenInfo(type=token.ENDMARKER, string='', start=(4, 0), end=(4, 0), line='')
] ]
@ -1653,7 +1653,7 @@ class TestTokenize(TestCase):
TokenInfo(token.ENCODING, string='utf-8', start=(0, 0), end=(0, 0), line=''), TokenInfo(token.ENCODING, string='utf-8', start=(0, 0), end=(0, 0), line=''),
TokenInfo(token.NAME, string='a', start=(1, 0), end=(1, 1), line='a\n'), TokenInfo(token.NAME, string='a', start=(1, 0), end=(1, 1), line='a\n'),
TokenInfo(token.NEWLINE, string='\n', start=(1, 1), end=(1, 2), line='a\n'), TokenInfo(token.NEWLINE, string='\n', start=(1, 1), end=(1, 2), line='a\n'),
TokenInfo(token.NL, string='', start=(2, 1), end=(2, 2), line=' \n'), TokenInfo(token.NL, string='', start=(2, 1), end=(2, 2), line=' '),
TokenInfo(token.ENDMARKER, string='', start=(3, 0), end=(3, 0), line='') TokenInfo(token.ENDMARKER, string='', start=(3, 0), end=(3, 0), line='')
] ]
@ -1889,10 +1889,10 @@ class CTokenizeTest(TestCase):
yield "1+1".encode(encoding) yield "1+1".encode(encoding)
expected = [ expected = [
TokenInfo(type=NUMBER, string='1', start=(1, 0), end=(1, 1), line='1+1\n'), TokenInfo(type=NUMBER, string='1', start=(1, 0), end=(1, 1), line='1+1'),
TokenInfo(type=OP, string='+', start=(1, 1), end=(1, 2), line='1+1\n'), TokenInfo(type=OP, string='+', start=(1, 1), end=(1, 2), line='1+1'),
TokenInfo(type=NUMBER, string='1', start=(1, 2), end=(1, 3), line='1+1\n'), TokenInfo(type=NUMBER, string='1', start=(1, 2), end=(1, 3), line='1+1'),
TokenInfo(type=NEWLINE, string='', start=(1, 3), end=(1, 4), line='1+1\n'), TokenInfo(type=NEWLINE, string='', start=(1, 3), end=(1, 4), line='1+1'),
TokenInfo(type=ENDMARKER, string='', start=(2, 0), end=(2, 0), line='') TokenInfo(type=ENDMARKER, string='', start=(2, 0), end=(2, 0), line='')
] ]
for encoding in ["utf-8", "latin-1", "utf-16"]: for encoding in ["utf-8", "latin-1", "utf-16"]:

2
Misc/NEWS.d/next/Core and Builtins/2023-06-09-15-25-12.gh-issue-105564.sFdUu4.rst Normal file
View file

@ -0,0 +1,2 @@
Don't include artificil newlines in the ``line`` attribute of tokens in the
APIs of the :mod:`tokenize` module. Patch by Pablo Galindo

3
Python/Python-tokenize.c
View file

@ -206,6 +206,9 @@ tokenizeriter_next(tokenizeriterobject *it)
line = PyUnicode_FromString(""); line = PyUnicode_FromString("");
} else { } else {
Py_ssize_t size = it->tok->inp - line_start; Py_ssize_t size = it->tok->inp - line_start;
if (size >= 1 && it->tok->implicit_newline) {
size -= 1;
}
line = PyUnicode_DecodeUTF8(line_start, size, "replace"); line = PyUnicode_DecodeUTF8(line_start, size, "replace");
} }
if (line == NULL) { if (line == NULL) {