OXIESEC PANEL
- Current Dir:
/
/
snap
/
core
/
17210
/
usr
/
lib
/
python3.5
Server IP: 139.59.38.164
Upload:
Create Dir:
Name
Size
Modified
Perms
π
..
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
LICENSE.txt
12.47 KB
09/30/2024 02:20:08 PM
rw-r--r--
π
__future__.py
4.73 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
__phello__.foo.py
64 bytes
09/30/2024 02:20:03 PM
rw-r--r--
π
__pycache__
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
_bootlocale.py
1.27 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
_collections_abc.py
24.13 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
_compat_pickle.py
8.36 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
_compression.py
5.21 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
_dummy_thread.py
5 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
_markupbase.py
14.26 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
_osx_support.py
18.66 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
_pydecimal.py
222.46 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
_pyio.py
85.91 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
_sitebuiltins.py
3.04 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
_strptime.py
21.67 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
_sysconfigdata.py
126 bytes
11/23/2013 12:09:48 PM
rw-r--r--
π
_threading_local.py
7.24 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
_weakrefset.py
5.57 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
abc.py
8.43 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
aifc.py
30.84 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
antigravity.py
475 bytes
09/30/2024 02:20:03 PM
rw-r--r--
π
argparse.py
88.21 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
ast.py
11.72 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
asynchat.py
11.69 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
asyncio
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
asyncore.py
19.63 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
base64.py
19.96 KB
09/30/2024 02:20:44 PM
rwxr-xr-x
π
bdb.py
22.81 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
binhex.py
13.63 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
bisect.py
2.53 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
bz2.py
12.13 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
cProfile.py
5.19 KB
09/30/2024 02:20:29 PM
rwxr-xr-x
π
calendar.py
22.4 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
cgi.py
35.19 KB
09/30/2024 02:20:31 PM
rwxr-xr-x
π
cgitb.py
11.74 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
chunk.py
5.3 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
cmd.py
14.51 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
code.py
9.88 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
codecs.py
35.38 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
codeop.py
5.85 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
collections
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
colorsys.py
3.97 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
compileall.py
11.42 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
concurrent
-
10/02/2024 07:52:54 PM
rwxr-xr-x
π
configparser.py
52.2 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
contextlib.py
11.97 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
copy.py
8.74 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
copyreg.py
6.67 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
crypt.py
1.83 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
csv.py
15.75 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
ctypes
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
curses
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
datetime.py
74.12 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
dbm
-
10/02/2024 07:52:54 PM
rwxr-xr-x
π
decimal.py
320 bytes
09/30/2024 02:20:03 PM
rw-r--r--
π
difflib.py
82.23 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
dis.py
16.94 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
distutils
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
doctest.py
101.6 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
dummy_threading.py
2.75 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
email
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
encodings
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
enum.py
21.71 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
filecmp.py
9.6 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
fileinput.py
13.92 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
fnmatch.py
3.09 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
formatter.py
14.79 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
fractions.py
23.82 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
ftplib.py
34.36 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
functools.py
28.1 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
genericpath.py
4.26 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
getopt.py
7.31 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
getpass.py
5.91 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
gettext.py
18.18 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
glob.py
4.95 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
gzip.py
19.79 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
hashlib.py
7.79 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
heapq.py
22.39 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
hmac.py
4.94 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
html
-
10/02/2024 07:52:54 PM
rwxr-xr-x
π
http
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
idlelib
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
imaplib.py
50.75 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
imghdr.py
3.67 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
imp.py
10.38 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
importlib
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
inspect.py
110.66 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
io.py
3.32 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
ipaddress.py
73.83 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
json
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
keyword.py
2.16 KB
09/30/2024 02:20:45 PM
rwxr-xr-x
π
lib-dynload
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
lib2to3
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
linecache.py
5.19 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
locale.py
72.97 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
logging
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
lzma.py
12.62 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
macpath.py
5.77 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
macurl2path.py
2.67 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
mailbox.py
76.58 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
mailcap.py
8.21 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
mimetypes.py
20.36 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
modulefinder.py
22.54 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
multiprocessing
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
netrc.py
5.61 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
nntplib.py
42.07 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
ntpath.py
22.26 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
nturl2path.py
2.39 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
numbers.py
10 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
opcode.py
5.75 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
operator.py
10.61 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
optparse.py
58.93 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
os.py
36.1 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
pathlib.py
45.89 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
pdb.py
59.56 KB
09/30/2024 02:20:36 PM
rwxr-xr-x
π
pickle.py
54.54 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
pickletools.py
89.61 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
pipes.py
8.71 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
pkgutil.py
20.71 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
plat-x86_64-linux-gnu
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
platform.py
47.91 KB
09/30/2024 02:20:45 PM
rwxr-xr-x
π
plistlib.py
32 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
poplib.py
14.17 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
posixpath.py
14.53 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
pprint.py
20.37 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
profile.py
21.5 KB
09/30/2024 02:20:30 PM
rwxr-xr-x
π
pstats.py
25.7 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
pty.py
4.65 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
py_compile.py
7.01 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
pyclbr.py
13.25 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
pydoc.py
100.38 KB
09/30/2024 02:20:36 PM
rwxr-xr-x
π
pydoc_data
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
queue.py
8.57 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
quopri.py
7.08 KB
09/30/2024 02:20:29 PM
rwxr-xr-x
π
random.py
25.48 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
re.py
15.14 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
reprlib.py
5.21 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
rlcompleter.py
6.16 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
runpy.py
11.13 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
sched.py
6.07 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
selectors.py
18.72 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
shelve.py
8.33 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
shlex.py
11.15 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
shutil.py
38.93 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
signal.py
2.07 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
site.py
21.74 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
sitecustomize.py
0 bytes
01/01/1970 12:00:00 AM
---------
π
smtpd.py
34.53 KB
09/30/2024 02:20:31 PM
rwxr-xr-x
π
smtplib.py
42.57 KB
09/30/2024 02:20:30 PM
rwxr-xr-x
π
sndhdr.py
6.27 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
socket.py
26.46 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
socketserver.py
24.09 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
sqlite3
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
sre_compile.py
17.98 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
sre_constants.py
6.3 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
sre_parse.py
34.14 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
ssl.py
42.54 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
stat.py
4.92 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
statistics.py
19.08 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
string.py
11.58 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
stringprep.py
12.61 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
struct.py
257 bytes
09/30/2024 02:20:03 PM
rw-r--r--
π
subprocess.py
66.8 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
sunau.py
17.67 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
symbol.py
2.04 KB
09/30/2024 02:20:40 PM
rwxr-xr-x
π
symtable.py
7.02 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
sysconfig.py
24.07 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
tabnanny.py
11.13 KB
09/30/2024 02:20:29 PM
rwxr-xr-x
π
tarfile.py
92.34 KB
09/30/2024 02:20:36 PM
rwxr-xr-x
π
telnetlib.py
22.48 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
tempfile.py
30.98 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
test
-
10/02/2024 07:52:54 PM
rwxr-xr-x
π
textwrap.py
19.19 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
this.py
1003 bytes
09/30/2024 02:20:03 PM
rw-r--r--
π
threading.py
47.77 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
timeit.py
12.1 KB
09/30/2024 02:20:29 PM
rwxr-xr-x
π
tkinter
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
token.py
3 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
tokenize.py
27.14 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
trace.py
30.8 KB
09/30/2024 02:20:29 PM
rwxr-xr-x
π
traceback.py
21.67 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
tracemalloc.py
15.27 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
tty.py
879 bytes
09/30/2024 02:20:03 PM
rw-r--r--
π
turtle.py
140.14 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
types.py
8.59 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
typing.py
58.12 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
unittest
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
urllib
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
uu.py
6.59 KB
09/30/2024 02:20:29 PM
rwxr-xr-x
π
uuid.py
22.72 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
venv
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
warnings.py
15.48 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
wave.py
17.27 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
weakref.py
18.95 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
webbrowser.py
20.92 KB
09/30/2024 02:20:38 PM
rwxr-xr-x
π
wsgiref
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
xdrlib.py
5.77 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
xml
-
10/02/2024 07:52:54 PM
rwxr-xr-x
π
xmlrpc
-
10/02/2024 07:52:55 PM
rwxr-xr-x
π
zipapp.py
6.99 KB
09/30/2024 02:20:03 PM
rw-r--r--
π
zipfile.py
72.61 KB
09/30/2024 02:20:03 PM
rw-r--r--
Editing: sre_compile.py
Close
# # Secret Labs' Regular Expression Engine # # convert template to internal format # # Copyright (c) 1997-2001 by Secret Labs AB. All rights reserved. # # See the sre.py file for information on usage and redistribution. # """Internal support module for sre""" import _sre import sre_parse from sre_constants import * assert _sre.MAGIC == MAGIC, "SRE module mismatch" _LITERAL_CODES = {LITERAL, NOT_LITERAL} _REPEATING_CODES = {REPEAT, MIN_REPEAT, MAX_REPEAT} _SUCCESS_CODES = {SUCCESS, FAILURE} _ASSERT_CODES = {ASSERT, ASSERT_NOT} # Sets of lowercase characters which have the same uppercase. _equivalences = ( # LATIN SMALL LETTER I, LATIN SMALL LETTER DOTLESS I (0x69, 0x131), # iΔ± # LATIN SMALL LETTER S, LATIN SMALL LETTER LONG S (0x73, 0x17f), # sΕΏ # MICRO SIGN, GREEK SMALL LETTER MU (0xb5, 0x3bc), # ¡μ # COMBINING GREEK YPOGEGRAMMENI, GREEK SMALL LETTER IOTA, GREEK PROSGEGRAMMENI (0x345, 0x3b9, 0x1fbe), # \u0345ΞΉαΎΎ # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS, GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA (0x390, 0x1fd3), # ΞαΏ # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS, GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA (0x3b0, 0x1fe3), # Ξ°αΏ£ # GREEK SMALL LETTER BETA, GREEK BETA SYMBOL (0x3b2, 0x3d0), # Ξ²Ο # GREEK SMALL LETTER EPSILON, GREEK LUNATE EPSILON SYMBOL (0x3b5, 0x3f5), # Ρϡ # GREEK SMALL LETTER THETA, GREEK THETA SYMBOL (0x3b8, 0x3d1), # ΞΈΟ # GREEK SMALL LETTER KAPPA, GREEK KAPPA SYMBOL (0x3ba, 0x3f0), # ΞΊΟ° # GREEK SMALL LETTER PI, GREEK PI SYMBOL (0x3c0, 0x3d6), # ΟΟ # GREEK SMALL LETTER RHO, GREEK RHO SYMBOL (0x3c1, 0x3f1), # ΟΟ± # GREEK SMALL LETTER FINAL SIGMA, GREEK SMALL LETTER SIGMA (0x3c2, 0x3c3), # ΟΟ # GREEK SMALL LETTER PHI, GREEK PHI SYMBOL (0x3c6, 0x3d5), # ΟΟ # LATIN SMALL LETTER S WITH DOT ABOVE, LATIN SMALL LETTER LONG S WITH DOT ABOVE (0x1e61, 0x1e9b), # αΉ‘αΊ # LATIN SMALL LIGATURE LONG S T, LATIN SMALL LIGATURE ST (0xfb05, 0xfb06), # ο¬ ο¬ ) # Maps the lowercase code to lowercase codes which have the same uppercase. _ignorecase_fixes = {i: tuple(j for j in t if i != j) for t in _equivalences for i in t} def _compile(code, pattern, flags): # internal: compile a (sub)pattern emit = code.append _len = len LITERAL_CODES = _LITERAL_CODES REPEATING_CODES = _REPEATING_CODES SUCCESS_CODES = _SUCCESS_CODES ASSERT_CODES = _ASSERT_CODES if (flags & SRE_FLAG_IGNORECASE and not (flags & SRE_FLAG_LOCALE) and flags & SRE_FLAG_UNICODE): fixes = _ignorecase_fixes else: fixes = None for op, av in pattern: if op in LITERAL_CODES: if flags & SRE_FLAG_IGNORECASE: lo = _sre.getlower(av, flags) if fixes and lo in fixes: emit(IN_IGNORE) skip = _len(code); emit(0) if op is NOT_LITERAL: emit(NEGATE) for k in (lo,) + fixes[lo]: emit(LITERAL) emit(k) emit(FAILURE) code[skip] = _len(code) - skip else: emit(OP_IGNORE[op]) emit(lo) else: emit(op) emit(av) elif op is IN: if flags & SRE_FLAG_IGNORECASE: emit(OP_IGNORE[op]) def fixup(literal, flags=flags): return _sre.getlower(literal, flags) else: emit(op) fixup = None skip = _len(code); emit(0) _compile_charset(av, flags, code, fixup, fixes) code[skip] = _len(code) - skip elif op is ANY: if flags & SRE_FLAG_DOTALL: emit(ANY_ALL) else: emit(ANY) elif op in REPEATING_CODES: if flags & SRE_FLAG_TEMPLATE: raise error("internal: unsupported template operator %r" % (op,)) elif _simple(av) and op is not REPEAT: if op is MAX_REPEAT: emit(REPEAT_ONE) else: emit(MIN_REPEAT_ONE) skip = _len(code); emit(0) emit(av[0]) emit(av[1]) _compile(code, av[2], flags) emit(SUCCESS) code[skip] = _len(code) - skip else: emit(REPEAT) skip = _len(code); emit(0) emit(av[0]) emit(av[1]) _compile(code, av[2], flags) code[skip] = _len(code) - skip if op is MAX_REPEAT: emit(MAX_UNTIL) else: emit(MIN_UNTIL) elif op is SUBPATTERN: if av[0]: emit(MARK) emit((av[0]-1)*2) # _compile_info(code, av[1], flags) _compile(code, av[1], flags) if av[0]: emit(MARK) emit((av[0]-1)*2+1) elif op in SUCCESS_CODES: emit(op) elif op in ASSERT_CODES: emit(op) skip = _len(code); emit(0) if av[0] >= 0: emit(0) # look ahead else: lo, hi = av[1].getwidth() if lo != hi: raise error("look-behind requires fixed-width pattern") emit(lo) # look behind _compile(code, av[1], flags) emit(SUCCESS) code[skip] = _len(code) - skip elif op is CALL: emit(op) skip = _len(code); emit(0) _compile(code, av, flags) emit(SUCCESS) code[skip] = _len(code) - skip elif op is AT: emit(op) if flags & SRE_FLAG_MULTILINE: av = AT_MULTILINE.get(av, av) if flags & SRE_FLAG_LOCALE: av = AT_LOCALE.get(av, av) elif flags & SRE_FLAG_UNICODE: av = AT_UNICODE.get(av, av) emit(av) elif op is BRANCH: emit(op) tail = [] tailappend = tail.append for av in av[1]: skip = _len(code); emit(0) # _compile_info(code, av, flags) _compile(code, av, flags) emit(JUMP) tailappend(_len(code)); emit(0) code[skip] = _len(code) - skip emit(FAILURE) # end of branch for tail in tail: code[tail] = _len(code) - tail elif op is CATEGORY: emit(op) if flags & SRE_FLAG_LOCALE: av = CH_LOCALE[av] elif flags & SRE_FLAG_UNICODE: av = CH_UNICODE[av] emit(av) elif op is GROUPREF: if flags & SRE_FLAG_IGNORECASE: emit(OP_IGNORE[op]) else: emit(op) emit(av-1) elif op is GROUPREF_EXISTS: emit(op) emit(av[0]-1) skipyes = _len(code); emit(0) _compile(code, av[1], flags) if av[2]: emit(JUMP) skipno = _len(code); emit(0) code[skipyes] = _len(code) - skipyes + 1 _compile(code, av[2], flags) code[skipno] = _len(code) - skipno else: code[skipyes] = _len(code) - skipyes + 1 else: raise error("internal: unsupported operand type %r" % (op,)) def _compile_charset(charset, flags, code, fixup=None, fixes=None): # compile charset subprogram emit = code.append for op, av in _optimize_charset(charset, fixup, fixes): emit(op) if op is NEGATE: pass elif op is LITERAL: emit(av) elif op is RANGE or op is RANGE_IGNORE: emit(av[0]) emit(av[1]) elif op is CHARSET: code.extend(av) elif op is BIGCHARSET: code.extend(av) elif op is CATEGORY: if flags & SRE_FLAG_LOCALE: emit(CH_LOCALE[av]) elif flags & SRE_FLAG_UNICODE: emit(CH_UNICODE[av]) else: emit(av) else: raise error("internal: unsupported set operator %r" % (op,)) emit(FAILURE) def _optimize_charset(charset, fixup, fixes): # internal: optimize character set out = [] tail = [] charmap = bytearray(256) for op, av in charset: while True: try: if op is LITERAL: if fixup: lo = fixup(av) charmap[lo] = 1 if fixes and lo in fixes: for k in fixes[lo]: charmap[k] = 1 else: charmap[av] = 1 elif op is RANGE: r = range(av[0], av[1]+1) if fixup: r = map(fixup, r) if fixup and fixes: for i in r: charmap[i] = 1 if i in fixes: for k in fixes[i]: charmap[k] = 1 else: for i in r: charmap[i] = 1 elif op is NEGATE: out.append((op, av)) else: tail.append((op, av)) except IndexError: if len(charmap) == 256: # character set contains non-UCS1 character codes charmap += b'\0' * 0xff00 continue # Character set contains non-BMP character codes. # There are only two ranges of cased non-BMP characters: # 10400-1044F (Deseret) and 118A0-118DF (Warang Citi), # and for both ranges RANGE_IGNORE works. if fixup and op is RANGE: op = RANGE_IGNORE tail.append((op, av)) break # compress character map runs = [] q = 0 while True: p = charmap.find(1, q) if p < 0: break if len(runs) >= 2: runs = None break q = charmap.find(0, p) if q < 0: runs.append((p, len(charmap))) break runs.append((p, q)) if runs is not None: # use literal/range for p, q in runs: if q - p == 1: out.append((LITERAL, p)) else: out.append((RANGE, (p, q - 1))) out += tail # if the case was changed or new representation is more compact if fixup or len(out) < len(charset): return out # else original character set is good enough return charset # use bitmap if len(charmap) == 256: data = _mk_bitmap(charmap) out.append((CHARSET, data)) out += tail return out # To represent a big charset, first a bitmap of all characters in the # set is constructed. Then, this bitmap is sliced into chunks of 256 # characters, duplicate chunks are eliminated, and each chunk is # given a number. In the compiled expression, the charset is # represented by a 32-bit word sequence, consisting of one word for # the number of different chunks, a sequence of 256 bytes (64 words) # of chunk numbers indexed by their original chunk position, and a # sequence of 256-bit chunks (8 words each). # Compression is normally good: in a typical charset, large ranges of # Unicode will be either completely excluded (e.g. if only cyrillic # letters are to be matched), or completely included (e.g. if large # subranges of Kanji match). These ranges will be represented by # chunks of all one-bits or all zero-bits. # Matching can be also done efficiently: the more significant byte of # the Unicode character is an index into the chunk number, and the # less significant byte is a bit index in the chunk (just like the # CHARSET matching). charmap = bytes(charmap) # should be hashable comps = {} mapping = bytearray(256) block = 0 data = bytearray() for i in range(0, 65536, 256): chunk = charmap[i: i + 256] if chunk in comps: mapping[i // 256] = comps[chunk] else: mapping[i // 256] = comps[chunk] = block block += 1 data += chunk data = _mk_bitmap(data) data[0:0] = [block] + _bytes_to_codes(mapping) out.append((BIGCHARSET, data)) out += tail return out _CODEBITS = _sre.CODESIZE * 8 MAXCODE = (1 << _CODEBITS) - 1 _BITS_TRANS = b'0' + b'1' * 255 def _mk_bitmap(bits, _CODEBITS=_CODEBITS, _int=int): s = bits.translate(_BITS_TRANS)[::-1] return [_int(s[i - _CODEBITS: i], 2) for i in range(len(s), 0, -_CODEBITS)] def _bytes_to_codes(b): # Convert block indices to word array a = memoryview(b).cast('I') assert a.itemsize == _sre.CODESIZE assert len(a) * a.itemsize == len(b) return a.tolist() def _simple(av): # check if av is a "simple" operator lo, hi = av[2].getwidth() return lo == hi == 1 and av[2][0][0] != SUBPATTERN def _generate_overlap_table(prefix): """ Generate an overlap table for the following prefix. An overlap table is a table of the same size as the prefix which informs about the potential self-overlap for each index in the prefix: - if overlap[i] == 0, prefix[i:] can't overlap prefix[0:...] - if overlap[i] == k with 0 < k <= i, prefix[i-k+1:i+1] overlaps with prefix[0:k] """ table = [0] * len(prefix) for i in range(1, len(prefix)): idx = table[i - 1] while prefix[i] != prefix[idx]: if idx == 0: table[i] = 0 break idx = table[idx - 1] else: table[i] = idx + 1 return table def _compile_info(code, pattern, flags): # internal: compile an info block. in the current version, # this contains min/max pattern width, and an optional literal # prefix or a character map lo, hi = pattern.getwidth() if hi > MAXCODE: hi = MAXCODE if lo == 0: code.extend([INFO, 4, 0, lo, hi]) return # look for a literal prefix prefix = [] prefixappend = prefix.append prefix_skip = 0 charset = [] # not used charsetappend = charset.append if not (flags & SRE_FLAG_IGNORECASE): # look for literal prefix for op, av in pattern.data: if op is LITERAL: if len(prefix) == prefix_skip: prefix_skip = prefix_skip + 1 prefixappend(av) elif op is SUBPATTERN and len(av[1]) == 1: op, av = av[1][0] if op is LITERAL: prefixappend(av) else: break else: break # if no prefix, look for charset prefix if not prefix and pattern.data: op, av = pattern.data[0] if op is SUBPATTERN and av[1]: op, av = av[1][0] if op is LITERAL: charsetappend((op, av)) elif op is BRANCH: c = [] cappend = c.append for p in av[1]: if not p: break op, av = p[0] if op is LITERAL: cappend((op, av)) else: break else: charset = c elif op is BRANCH: c = [] cappend = c.append for p in av[1]: if not p: break op, av = p[0] if op is LITERAL: cappend((op, av)) else: break else: charset = c elif op is IN: charset = av ## if prefix: ## print("*** PREFIX", prefix, prefix_skip) ## if charset: ## print("*** CHARSET", charset) # add an info block emit = code.append emit(INFO) skip = len(code); emit(0) # literal flag mask = 0 if prefix: mask = SRE_INFO_PREFIX if len(prefix) == prefix_skip == len(pattern.data): mask = mask | SRE_INFO_LITERAL elif charset: mask = mask | SRE_INFO_CHARSET emit(mask) # pattern length if lo < MAXCODE: emit(lo) else: emit(MAXCODE) prefix = prefix[:MAXCODE] emit(min(hi, MAXCODE)) # add literal prefix if prefix: emit(len(prefix)) # length emit(prefix_skip) # skip code.extend(prefix) # generate overlap table code.extend(_generate_overlap_table(prefix)) elif charset: _compile_charset(charset, flags, code) code[skip] = len(code) - skip def isstring(obj): return isinstance(obj, (str, bytes)) def _code(p, flags): flags = p.pattern.flags | flags code = [] # compile info block _compile_info(code, p, flags) # compile the pattern _compile(code, p.data, flags) code.append(SUCCESS) return code def compile(p, flags=0): # internal: convert pattern list to internal format if isstring(p): pattern = p p = sre_parse.parse(p, flags) else: pattern = None code = _code(p, flags) # print(code) # map in either direction groupindex = p.pattern.groupdict indexgroup = [None] * p.pattern.groups for k, i in groupindex.items(): indexgroup[i] = k return _sre.compile( pattern, flags | p.pattern.flags, code, p.pattern.groups-1, groupindex, indexgroup )