Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Support
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
C
cpython
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Issues
0
Issues
0
List
Boards
Labels
Milestones
Merge Requests
0
Merge Requests
0
Analytics
Analytics
Repository
Value Stream
Wiki
Wiki
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Commits
Issue Boards
Open sidebar
Kirill Smelkov
cpython
Commits
9eabac68
Commit
9eabac68
authored
Oct 26, 2013
by
Serhiy Storchaka
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
Issue #18685: Restore re performance to pre-PEP 393 levels.
parent
ffb58e96
Changes
4
Expand all
Hide whitespace changes
Inline
Side-by-side
Showing
4 changed files
with
350 additions
and
384 deletions
+350
-384
Lib/test/test_re.py
Lib/test/test_re.py
+23
-0
Misc/NEWS
Misc/NEWS
+2
-0
Modules/_sre.c
Modules/_sre.c
+322
-378
Modules/sre.h
Modules/sre.h
+3
-6
No files found.
Lib/test/test_re.py
View file @
9eabac68
...
...
@@ -77,6 +77,8 @@ class ReTests(unittest.TestCase):
self
.
assertTypedEqual
(
re
.
sub
(
b'y'
,
B
(
b'a'
),
B
(
b'xyz'
)),
b'xaz'
)
self
.
assertTypedEqual
(
re
.
sub
(
b'y'
,
bytearray
(
b'a'
),
bytearray
(
b'xyz'
)),
b'xaz'
)
self
.
assertTypedEqual
(
re
.
sub
(
b'y'
,
memoryview
(
b'a'
),
memoryview
(
b'xyz'
)),
b'xaz'
)
for
y
in
(
"
\
xe0
"
,
"
\
u0430
"
,
"
\
U0001d49c
"
):
self
.
assertEqual
(
re
.
sub
(
y
,
'a'
,
'x%sz'
%
y
),
'xaz'
)
self
.
assertEqual
(
re
.
sub
(
"(?i)b+"
,
"x"
,
"bbbb BBBB"
),
'x x'
)
self
.
assertEqual
(
re
.
sub
(
r'\
d+
', self.bump_num, '
08.2
-
2
23
x99y
'),
...
...
@@ -250,6 +252,13 @@ class ReTests(unittest.TestCase):
[b'', b'
a
', b'b', b'
c
'])
self.assertTypedEqual(re.split(b"(:*)", string),
[b'', b'
:
', b'
a
', b'
:
', b'b', b'
::
', b'
c
'])
for a, b, c in ("
\
xe0
\
xdf
\
xe7
", "
\
u0430
\
u0431
\
u0432
",
"
\
U0001d49c
\
U0001d49e
\
U0001d4b5
"):
string = ":%s:%s::%s" % (a, b, c)
self.assertEqual(re.split(":", string), ['', a, b, '', c])
self.assertEqual(re.split(":*", string), ['', a, b, c])
self.assertEqual(re.split("(:*)", string),
['', '
:
', a, '
:
', b, '
::
', c])
self.assertEqual(re.split("(?::*)", ":a:b::c"), ['', '
a
', 'b', '
c
'])
self.assertEqual(re.split("(:)*", ":a:b::c"),
...
...
@@ -287,6 +296,14 @@ class ReTests(unittest.TestCase):
[b":", b"::", b":::"])
self.assertTypedEqual(re.findall(b"(:)(:*)", string),
[(b":", b""), (b":", b":"), (b":", b"::")])
for x in ("
\
xe0
", "
\
u0430
", "
\
U0001d49c
"):
xx = x * 2
xxx = x * 3
string = "a%sb%sc%sd" % (x, xx, xxx)
self.assertEqual(re.findall("%s+" % x, string), [x, xx, xxx])
self.assertEqual(re.findall("(%s+)" % x, string), [x, xx, xxx])
self.assertEqual(re.findall("(%s)(%s*)" % (x, x), string),
[(x, ""), (x, x), (x, xx)])
def test_bug_117612(self):
self.assertEqual(re.findall(r"(a|(b))", "aba"),
...
...
@@ -305,6 +322,12 @@ class ReTests(unittest.TestCase):
self.assertEqual(re.match(b'
(
a
)
', string).group(0), b'
a
')
self.assertEqual(re.match(b'
(
a
)
', string).group(1), b'
a
')
self.assertEqual(re.match(b'
(
a
)
', string).group(1, 1), (b'
a
', b'
a
'))
for a in ("
\
xe0
", "
\
u0430
", "
\
U0001d49c
"):
self.assertEqual(re.match(a, a).groups(), ())
self.assertEqual(re.match('
(
%
s
)
' % a, a).groups(), (a,))
self.assertEqual(re.match('
(
%
s
)
' % a, a).group(0), a)
self.assertEqual(re.match('
(
%
s
)
' % a, a).group(1), a)
self.assertEqual(re.match('
(
%
s
)
' % a, a).group(1, 1), (a, a))
pat = re.compile('
((
a
)
|
(
b
))(
c
)
?
')
self.assertEqual(pat.match('
a
').groups(), ('
a
', '
a
', None, None))
...
...
Misc/NEWS
View file @
9eabac68
...
...
@@ -21,6 +21,8 @@ Core and Builtins
Library
-------
- Issue #18685: Restore re performance to pre-PEP 393 levels.
- Issue #19339: telnetlib module is now using time.monotonic() when available
to compute timeout.
...
...
Modules/_sre.c
View file @
9eabac68
This diff is collapsed.
Click to expand it.
Modules/sre.h
View file @
9eabac68
...
...
@@ -31,9 +31,7 @@ typedef struct {
PyObject
*
pattern
;
/* pattern source (or None) */
int
flags
;
/* flags used when compiling pattern source */
PyObject
*
weakreflist
;
/* List of weak references */
int
logical_charsize
;
/* pattern charsize (or -1) */
int
charsize
;
Py_buffer
view
;
int
isbytes
;
/* pattern type (1 - bytes, 0 - string, -1 - None) */
/* pattern code */
Py_ssize_t
codesize
;
SRE_CODE
code
[
1
];
...
...
@@ -73,9 +71,8 @@ typedef struct {
/* attributes for the match object */
PyObject
*
string
;
Py_ssize_t
pos
,
endpos
;
/* character size */
int
logical_charsize
;
/* kind of thing: 1 - bytes, 2/4 - unicode */
int
charsize
;
int
isbytes
;
int
charsize
;
/* character size */
/* registers */
Py_ssize_t
lastindex
;
Py_ssize_t
lastmark
;
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment