Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commit0b23e0f

Browse files
committed
gh-104972: Ensure that line attributes in tokens in the tokenize module are correct
Signed-off-by: Pablo Galindo <pablogsal@gmail.com>
1 parent2b7027d commit0b23e0f

File tree

4 files changed

+21
-9
lines changed

4 files changed

+21
-9
lines changed

‎Lib/idlelib/idle_test/test_editor.py

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -201,8 +201,8 @@ def test_searcher(self):
201201
test_info= (# text, (block, indent))
202202
("", (None,None)),
203203
("[1,", (None,None)),# TokenError
204-
("if 1:\n", ('if 1:',None)),
205-
("if 1:\n 2\n 3\n", ('if 1:',' 2')),
204+
("if 1:\n", ('if 1:\n',None)),
205+
("if 1:\n 2\n 3\n", ('if 1:\n',' 2\n')),
206206
)
207207
forcode,expected_pairintest_info:
208208
withself.subTest(code=code):

‎Lib/test/test_tokenize.py

Lines changed: 13 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1174,7 +1174,7 @@ def readline():
11741174

11751175
# skip the initial encoding token and the end tokens
11761176
tokens=list(_tokenize(readline(),encoding='utf-8'))[:-2]
1177-
expected_tokens= [TokenInfo(3,'"ЉЊЈЁЂ"', (1,0), (1,7),'"ЉЊЈЁЂ"')]
1177+
expected_tokens= [TokenInfo(3,'"ЉЊЈЁЂ"', (1,0), (1,7),'"ЉЊЈЁЂ"\n')]
11781178
self.assertEqual(tokens,expected_tokens,
11791179
"bytes not decoded with encoding")
11801180

@@ -1657,7 +1657,6 @@ def check_roundtrip(self, f):
16571657
code=f.encode('utf-8')
16581658
else:
16591659
code=f.read()
1660-
f.close()
16611660
readline=iter(code.splitlines(keepends=True)).__next__
16621661
tokens5=list(tokenize(readline))
16631662
tokens2= [tok[:2]fortokintokens5]
@@ -1671,6 +1670,17 @@ def check_roundtrip(self, f):
16711670
readline5=iter(bytes_from5.splitlines(keepends=True)).__next__
16721671
tokens2_from5= [tok[:2]fortokintokenize(readline5)]
16731672
self.assertEqual(tokens2_from5,tokens2)
1673+
1674+
defcheck_line_extraction(self,f):
1675+
ifisinstance(f,str):
1676+
code=f.encode('utf-8')
1677+
else:
1678+
code=f.read()
1679+
readline=iter(code.splitlines(keepends=True)).__next__
1680+
fortokintokenize(readline):
1681+
iftok.typein {ENCODING,ENDMARKER}:
1682+
continue
1683+
self.assertEqual(tok.string,tok.line[tok.start[1]:tok.end[1]])
16741684

16751685
deftest_roundtrip(self):
16761686
# There are some standard formatting practices that are easy to get right.
@@ -1768,6 +1778,7 @@ def test_random_files(self):
17681778
withopen(testfile,'rb')asf:
17691779
# with self.subTest(file=testfile):
17701780
self.check_roundtrip(f)
1781+
self.check_line_extraction(f)
17711782

17721783

17731784
defroundtrip(self,code):
Lines changed: 2 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,2 @@
1+
Ensure that the ``line`` attribute in:class:`tokenize.TokenInfo` objects in
2+
the:mod:`tokenize` module are always correct. Patch by Pablo Galindo

‎Python/Python-tokenize.c

Lines changed: 4 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -194,15 +194,14 @@ tokenizeriter_next(tokenizeriterobject *it)
194194
gotoexit;
195195
}
196196

197-
Py_ssize_tsize=it->tok->inp-it->tok->buf;
198-
assert(it->tok->buf[size-1]=='\n');
199-
size-=1;// Remove the newline character from the end of the line
200-
PyObject*line=PyUnicode_DecodeUTF8(it->tok->buf,size,"replace");
197+
constchar*line_start=ISSTRINGLIT(type) ?it->tok->multi_line_start :it->tok->line_start;
198+
Py_ssize_tsize=it->tok->inp-line_start;
199+
PyObject*line=PyUnicode_DecodeUTF8(line_start,size,"replace");
201200
if (line==NULL) {
202201
Py_DECREF(str);
203202
gotoexit;
204203
}
205-
constchar*line_start=ISSTRINGLIT(type) ?it->tok->multi_line_start :it->tok->line_start;
204+
206205
Py_ssize_tlineno=ISSTRINGLIT(type) ?it->tok->first_lineno :it->tok->lineno;
207206
Py_ssize_tend_lineno=it->tok->lineno;
208207
Py_ssize_tcol_offset=-1;

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp