Skip to content
Projeler
Gruplar
Parçacıklar
Yardım
Yükleniyor...
Oturum aç / Kaydol
Gezinmeyi değiştir
C
cpython
Proje
Proje
Ayrıntılar
Etkinlik
Cycle Analytics
Depo (repository)
Depo (repository)
Dosyalar
Kayıtlar (commit)
Dallar (branch)
Etiketler
Katkıda bulunanlar
Grafik
Karşılaştır
Grafikler
Konular (issue)
0
Konular (issue)
0
Liste
Pano
Etiketler
Kilometre Taşları
Birleştirme (merge) Talepleri
0
Birleştirme (merge) Talepleri
0
CI / CD
CI / CD
İş akışları (pipeline)
İşler
Zamanlamalar
Grafikler
Paketler
Paketler
Wiki
Wiki
Parçacıklar
Parçacıklar
Üyeler
Üyeler
Collapse sidebar
Close sidebar
Etkinlik
Grafik
Grafikler
Yeni bir konu (issue) oluştur
İşler
Kayıtlar (commit)
Konu (issue) Panoları
Kenar çubuğunu aç
Batuhan Osman TASKAYA
cpython
Commits
1c5aa690
Kaydet (Commit)
1c5aa690
authored
Ock 16, 2001
tarafından
Fredrik Lundh
Dosyalara gözat
Seçenekler
Dosyalara Gözat
İndir
Eposta Yamaları
Sade Fark
bumped SRE version number to 2.1. cleaned up and added 1.5.2
compatibility patches.
üst
dfb673b4
Hide whitespace changes
Inline
Side-by-side
Showing
4 changed files
with
76 additions
and
44 deletions
+76
-44
sre.py
Lib/sre.py
+1
-1
sre_parse.py
Lib/sre_parse.py
+17
-11
test_sre.py
Lib/test/test_sre.py
+17
-7
_sre.c
Modules/_sre.c
+41
-25
No files found.
Lib/sre.py
Dosyayı görüntüle @
1c5aa690
...
...
@@ -181,7 +181,7 @@ def _split(pattern, string, maxsplit=0):
continue
append
(
string
[
i
:
b
])
if
g
and
b
!=
e
:
extend
(
m
.
groups
(
))
extend
(
list
(
m
.
groups
()
))
i
=
e
n
=
n
+
1
append
(
string
[
i
:])
...
...
Lib/sre_parse.py
Dosyayı görüntüle @
1c5aa690
...
...
@@ -60,6 +60,12 @@ FLAGS = {
"u"
:
SRE_FLAG_UNICODE
,
}
try
:
int
(
"10"
,
8
)
atoi
=
int
except
TypeError
:
atoi
=
string
.
atoi
class
Pattern
:
# master pattern object. keeps track of global attributes
def
__init__
(
self
):
...
...
@@ -216,7 +222,7 @@ def isname(name):
def
_group
(
escape
,
groups
):
# check if the escape string represents a valid group
try
:
gid
=
int
(
escape
[
1
:])
gid
=
atoi
(
escape
[
1
:])
if
gid
and
gid
<
groups
:
return
gid
except
ValueError
:
...
...
@@ -239,13 +245,13 @@ def _class_escape(source, escape):
escape
=
escape
[
2
:]
if
len
(
escape
)
!=
2
:
raise
error
,
"bogus escape:
%
s"
%
repr
(
"
\\
"
+
escape
)
return
LITERAL
,
int
(
escape
,
16
)
&
0xff
return
LITERAL
,
atoi
(
escape
,
16
)
&
0xff
elif
str
(
escape
[
1
:
2
])
in
OCTDIGITS
:
# octal escape (up to three digits)
while
source
.
next
in
OCTDIGITS
and
len
(
escape
)
<
5
:
escape
=
escape
+
source
.
get
()
escape
=
escape
[
1
:]
return
LITERAL
,
int
(
escape
,
8
)
&
0xff
return
LITERAL
,
atoi
(
escape
,
8
)
&
0xff
if
len
(
escape
)
==
2
:
return
LITERAL
,
ord
(
escape
[
1
])
except
ValueError
:
...
...
@@ -267,12 +273,12 @@ def _escape(source, escape, state):
escape
=
escape
+
source
.
get
()
if
len
(
escape
)
!=
4
:
raise
ValueError
return
LITERAL
,
int
(
escape
[
2
:],
16
)
&
0xff
return
LITERAL
,
atoi
(
escape
[
2
:],
16
)
&
0xff
elif
escape
[
1
:
2
]
==
"0"
:
# octal escape
while
source
.
next
in
OCTDIGITS
and
len
(
escape
)
<
4
:
escape
=
escape
+
source
.
get
()
return
LITERAL
,
int
(
escape
[
1
:],
8
)
&
0xff
return
LITERAL
,
atoi
(
escape
[
1
:],
8
)
&
0xff
elif
escape
[
1
:
2
]
in
DIGITS
:
# octal escape *or* decimal group reference (sigh)
here
=
source
.
tell
()
...
...
@@ -282,7 +288,7 @@ def _escape(source, escape, state):
source
.
next
in
OCTDIGITS
):
# got three octal digits; this is an octal escape
escape
=
escape
+
source
.
get
()
return
LITERAL
,
int
(
escape
[
1
:],
8
)
&
0xff
return
LITERAL
,
atoi
(
escape
[
1
:],
8
)
&
0xff
# got at least one decimal digit; this is a group reference
group
=
_group
(
escape
,
state
.
groups
)
if
group
:
...
...
@@ -456,9 +462,9 @@ def _parse(source, state):
source
.
seek
(
here
)
continue
if
lo
:
min
=
int
(
lo
)
min
=
atoi
(
lo
)
if
hi
:
max
=
int
(
hi
)
max
=
atoi
(
hi
)
if
max
<
min
:
raise
error
,
"bad repeat interval"
else
:
...
...
@@ -646,7 +652,7 @@ def parse_template(source, pattern):
if
not
name
:
raise
error
,
"bad group name"
try
:
index
=
int
(
name
)
index
=
atoi
(
name
)
except
ValueError
:
if
not
isname
(
name
):
raise
error
,
"bad character in group name"
...
...
@@ -662,7 +668,7 @@ def parse_template(source, pattern):
if
group
:
if
(
s
.
next
not
in
DIGITS
or
not
_group
(
this
+
s
.
next
,
pattern
.
groups
+
1
)):
code
=
MARK
,
int
(
group
)
code
=
MARK
,
group
break
elif
s
.
next
in
OCTDIGITS
:
this
=
this
+
s
.
get
()
...
...
@@ -670,7 +676,7 @@ def parse_template(source, pattern):
break
if
not
code
:
this
=
this
[
1
:]
code
=
LITERAL
,
int
(
this
[
-
6
:],
8
)
&
0xff
code
=
LITERAL
,
atoi
(
this
[
-
6
:],
8
)
&
0xff
a
(
code
)
else
:
try
:
...
...
Lib/test/test_sre.py
Dosyayı görüntüle @
1c5aa690
...
...
@@ -325,16 +325,26 @@ for t in tests:
# Try the match on a unicode string, and check that it
# still succeeds.
result
=
obj
.
search
(
unicode
(
s
,
"latin-1"
))
if
result
==
None
:
print
'=== Fails on unicode match'
,
t
try
:
u
=
unicode
(
s
,
"latin-1"
)
except
NameError
:
pass
else
:
result
=
obj
.
search
(
u
)
if
result
==
None
:
print
'=== Fails on unicode match'
,
t
# Try the match on a unicode pattern, and check that it
# still succeeds.
obj
=
sre
.
compile
(
unicode
(
pattern
,
"latin-1"
))
result
=
obj
.
search
(
s
)
if
result
==
None
:
print
'=== Fails on unicode pattern match'
,
t
try
:
u
=
unicode
(
pattern
,
"latin-1"
)
except
NameError
:
pass
else
:
obj
=
sre
.
compile
(
u
)
result
=
obj
.
search
(
s
)
if
result
==
None
:
print
'=== Fails on unicode pattern match'
,
t
# Try the match with the search area limited to the extent
# of the match and see if it still succeeds. \B will
...
...
Modules/_sre.c
Dosyayı görüntüle @
1c5aa690
...
...
@@ -24,7 +24,7 @@
* 2000-10-24 fl really fixed assert_not; reset groups in findall
* 2000-12-21 fl fixed memory leak in groupdict
* 2001-01-02 fl properly reset pointer after failed assertion in MIN_UNTIL
* 2001-01-15 fl
don't use recursion for unbounded MIN_UTIL; fixed
* 2001-01-15 fl
avoid recursion for MIN_UTIL; fixed uppercase literal bug
* 2001-01-16 fl fixed memory leak in pattern destructor
*
* Copyright (c) 1997-2001 by Secret Labs AB. All rights reserved.
...
...
@@ -40,7 +40,7 @@
#ifndef SRE_RECURSIVE
char
copyright
[]
=
" SRE
0.9.9
Copyright (c) 1997-2001 by Secret Labs AB "
;
char
copyright
[]
=
" SRE
2.1
Copyright (c) 1997-2001 by Secret Labs AB "
;
#include "Python.h"
...
...
@@ -49,7 +49,9 @@ char copyright[] = " SRE 0.9.9 Copyright (c) 1997-2001 by Secret Labs AB ";
#include <ctype.h>
/* name of this module, minus the leading underscore */
#define MODULE "sre"
#if !defined(SRE_MODULE)
#define SRE_MODULE "sre"
#endif
/* defining this one enables tracing */
#undef VERBOSE
...
...
@@ -81,6 +83,10 @@ char copyright[] = " SRE 0.9.9 Copyright (c) 1997-2001 by Secret Labs AB ";
/* enables aggressive inlining (always on for Visual C) */
#undef USE_INLINE
#if PY_VERSION_HEX < 0x01060000
#define PyObject_DEL(op) PyMem_DEL((op))
#endif
/* -------------------------------------------------------------------- */
#if defined(_MSC_VER)
...
...
@@ -221,6 +227,23 @@ sre_category(SRE_CODE category, unsigned int ch)
return
SRE_UNI_IS_LINEBREAK
(
ch
);
case
SRE_CATEGORY_UNI_NOT_LINEBREAK
:
return
!
SRE_UNI_IS_LINEBREAK
(
ch
);
#else
case
SRE_CATEGORY_UNI_DIGIT
:
return
SRE_IS_DIGIT
(
ch
);
case
SRE_CATEGORY_UNI_NOT_DIGIT
:
return
!
SRE_IS_DIGIT
(
ch
);
case
SRE_CATEGORY_UNI_SPACE
:
return
SRE_IS_SPACE
(
ch
);
case
SRE_CATEGORY_UNI_NOT_SPACE
:
return
!
SRE_IS_SPACE
(
ch
);
case
SRE_CATEGORY_UNI_WORD
:
return
SRE_LOC_IS_WORD
(
ch
);
case
SRE_CATEGORY_UNI_NOT_WORD
:
return
!
SRE_LOC_IS_WORD
(
ch
);
case
SRE_CATEGORY_UNI_LINEBREAK
:
return
SRE_IS_LINEBREAK
(
ch
);
case
SRE_CATEGORY_UNI_NOT_LINEBREAK
:
return
!
SRE_IS_LINEBREAK
(
ch
);
#endif
}
return
0
;
...
...
@@ -1208,33 +1231,22 @@ _compile(PyObject* self_, PyObject* args)
int
groups
=
0
;
PyObject
*
groupindex
=
NULL
;
PyObject
*
indexgroup
=
NULL
;
if
(
!
PyArg_ParseTuple
(
args
,
"OiO|iOO"
,
&
pattern
,
&
flags
,
&
code
,
&
groups
,
&
groupindex
,
&
indexgroup
))
if
(
!
PyArg_ParseTuple
(
args
,
"OiO!|iOO"
,
&
pattern
,
&
flags
,
&
PyList_Type
,
&
code
,
&
groups
,
&
groupindex
,
&
indexgroup
))
return
NULL
;
code
=
PySequence_Fast
(
code
,
"code argument must be a sequence"
);
if
(
!
code
)
return
NULL
;
#if PY_VERSION_HEX >= 0x01060000
n
=
PySequence_Size
(
code
);
#else
n
=
PySequence_Length
(
code
);
#endif
n
=
PyList_GET_SIZE
(
code
);
self
=
PyObject_NEW_VAR
(
PatternObject
,
&
Pattern_Type
,
n
);
if
(
!
self
)
{
Py_DECREF
(
code
);
if
(
!
self
)
return
NULL
;
}
for
(
i
=
0
;
i
<
n
;
i
++
)
{
PyObject
*
o
=
Py
Sequence_Fa
st_GET_ITEM
(
code
,
i
);
PyObject
*
o
=
Py
Li
st_GET_ITEM
(
code
,
i
);
self
->
code
[
i
]
=
(
SRE_CODE
)
PyInt_AsLong
(
o
);
}
Py_DECREF
(
code
);
if
(
PyErr_Occurred
())
{
PyObject_DEL
(
self
);
return
NULL
;
...
...
@@ -1270,9 +1282,11 @@ sre_getlower(PyObject* self, PyObject* args)
return
NULL
;
if
(
flags
&
SRE_FLAG_LOCALE
)
return
Py_BuildValue
(
"i"
,
sre_lower_locale
(
character
));
#if defined(HAVE_UNICODE)
if
(
flags
&
SRE_FLAG_UNICODE
)
#if defined(HAVE_UNICODE)
return
Py_BuildValue
(
"i"
,
sre_lower_unicode
(
character
));
#else
return
Py_BuildValue
(
"i"
,
sre_lower_locale
(
character
));
#endif
return
Py_BuildValue
(
"i"
,
sre_lower
(
character
));
}
...
...
@@ -1380,9 +1394,11 @@ state_init(SRE_STATE* state, PatternObject* pattern, PyObject* string,
if
(
pattern
->
flags
&
SRE_FLAG_LOCALE
)
state
->
lower
=
sre_lower_locale
;
#if defined(HAVE_UNICODE)
else
if
(
pattern
->
flags
&
SRE_FLAG_UNICODE
)
#if defined(HAVE_UNICODE)
state
->
lower
=
sre_lower_unicode
;
#else
state
->
lower
=
sre_lower_locale
;
#endif
else
state
->
lower
=
sre_lower
;
...
...
@@ -1520,7 +1536,7 @@ pattern_scanner(PatternObject* pattern, PyObject* args)
string
=
state_init
(
&
self
->
state
,
pattern
,
string
,
start
,
end
);
if
(
!
string
)
{
PyObject_D
el
(
self
);
PyObject_D
EL
(
self
);
return
NULL
;
}
...
...
@@ -1619,7 +1635,7 @@ call(char* function, PyObject* args)
PyObject
*
func
;
PyObject
*
result
;
name
=
PyString_FromString
(
MODULE
);
name
=
PyString_FromString
(
SRE_
MODULE
);
if
(
!
name
)
return
NULL
;
module
=
PyImport_Import
(
name
);
...
...
@@ -2366,7 +2382,7 @@ init_sre(void)
Pattern_Type
.
ob_type
=
Match_Type
.
ob_type
=
Scanner_Type
.
ob_type
=
&
PyType_Type
;
m
=
Py_InitModule
(
"_"
MODULE
,
_functions
);
m
=
Py_InitModule
(
"_"
SRE_
MODULE
,
_functions
);
d
=
PyModule_GetDict
(
m
);
PyDict_SetItemString
(
...
...
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