/
opt
/
alt
/
python37
/
lib64
/
python3.7
/
/opt/alt/python37/lib64/python3.7
mkdir
upload
Name
Size
Mode
Actions
asyncio/
-
0755
rm
collections/
-
0755
rm
concurrent/
-
0755
rm
config-3.7m/
-
0755
rm
ctypes/
-
0755
rm
curses/
-
0755
rm
dbm/
-
0755
rm
distutils/
-
0755
rm
email/
-
0755
rm
encodings/
-
0755
rm
ensurepip/
-
0755
rm
html/
-
0755
rm
http/
-
0755
rm
idlelib/
-
0755
rm
importlib/
-
0755
rm
json/
-
0755
rm
lib-dynload/
-
0755
rm
lib2to3/
-
0755
rm
logging/
-
0755
rm
multiprocessing/
-
0755
rm
pydoc_data/
-
0755
rm
site-packages/
-
0755
rm
sqlite3/
-
0755
rm
test/
-
0755
rm
unittest/
-
0755
rm
urllib/
-
0755
rm
venv/
-
0755
rm
wsgiref/
-
0755
rm
xml/
-
0755
rm
xmlrpc/
-
0755
rm
__pycache__/
-
0755
rm
abc.py
5580
0644
edit
dl
rm
aifc.py
32814
0644
edit
dl
rm
antigravity.py
477
0644
edit
dl
rm
argparse.py
95372
0644
edit
dl
rm
ast.py
12842
0644
edit
dl
rm
asynchat.py
11328
0644
edit
dl
rm
asyncore.py
20118
0644
edit
dl
rm
base64.py
20393
0755
edit
dl
rm
bdb.py
31730
0644
edit
dl
rm
binhex.py
13954
0644
edit
dl
rm
bisect.py
2557
0644
edit
dl
rm
bz2.py
12410
0644
edit
dl
rm
calendar.py
24826
0644
edit
dl
rm
cgi.py
35050
0755
edit
dl
rm
cgitb.py
12018
0644
edit
dl
rm
chunk.py
5435
0644
edit
dl
rm
cmd.py
14860
0644
edit
dl
rm
code.py
10622
0644
edit
dl
rm
codecs.py
36615
0644
edit
dl
rm
codeop.py
6275
0644
edit
dl
rm
colorsys.py
4064
0644
edit
dl
rm
compileall.py
13788
0644
edit
dl
rm
configparser.py
54283
0644
edit
dl
rm
contextlib.py
24763
0644
edit
dl
rm
contextvars.py
129
0644
edit
dl
rm
copy.py
8856
0644
edit
dl
rm
copyreg.py
7017
0644
edit
dl
rm
cProfile.py
6253
0755
edit
dl
rm
crypt.py
3346
0644
edit
dl
rm
csv.py
16180
0644
edit
dl
rm
dataclasses.py
49520
0644
edit
dl
rm
datetime.py
86544
0644
edit
dl
rm
decimal.py
320
0644
edit
dl
rm
difflib.py
84393
0644
edit
dl
rm
dis.py
19888
0644
edit
dl
rm
doctest.py
104560
0644
edit
dl
rm
dummy_threading.py
2815
0644
edit
dl
rm
enum.py
35043
0644
edit
dl
rm
filecmp.py
9830
0644
edit
dl
rm
fileinput.py
14625
0644
edit
dl
rm
fnmatch.py
4056
0644
edit
dl
rm
formatter.py
15143
0644
edit
dl
rm
fractions.py
23752
0644
edit
dl
rm
ftplib.py
35618
0644
edit
dl
rm
functools.py
32932
0644
edit
dl
rm
genericpath.py
4912
0644
edit
dl
rm
getopt.py
7489
0644
edit
dl
rm
getpass.py
5994
0644
edit
dl
rm
gettext.py
21967
0644
edit
dl
rm
glob.py
5638
0644
edit
dl
rm
gzip.py
20637
0644
edit
dl
rm
hashlib.py
9534
0644
edit
dl
rm
heapq.py
23017
0644
edit
dl
rm
hmac.py
6517
0644
edit
dl
rm
imaplib.py
53292
0644
edit
dl
rm
imghdr.py
3795
0644
edit
dl
rm
imp.py
10536
0644
edit
dl
rm
inspect.py
117635
0644
edit
dl
rm
io.py
3517
0644
edit
dl
rm
ipaddress.py
73578
0644
edit
dl
rm
keyword.py
2256
0755
edit
dl
rm
linecache.py
5330
0644
edit
dl
rm
locale.py
78191
0644
edit
dl
rm
lzma.py
12983
0644
edit
dl
rm
macpath.py
6123
0644
edit
dl
rm
mailbox.py
78654
0644
edit
dl
rm
mailcap.py
9067
0644
edit
dl
rm
mimetypes.py
21496
0644
edit
dl
rm
modulefinder.py
23035
0644
edit
dl
rm
netrc.py
5566
0644
edit
dl
rm
nntplib.py
43087
0644
edit
dl
rm
ntpath.py
22340
0644
edit
dl
rm
nturl2path.py
2584
0644
edit
dl
rm
numbers.py
10244
0644
edit
dl
rm
opcode.py
5824
0644
edit
dl
rm
operator.py
10863
0644
edit
dl
rm
optparse.py
60371
0644
edit
dl
rm
os.py
37901
0644
edit
dl
rm
pathlib.py
50329
0644
edit
dl
rm
pdb.py
62505
0755
edit
dl
rm
pickle.py
57994
0644
edit
dl
rm
pickletools.py
91220
0644
edit
dl
rm
pipes.py
8916
0644
edit
dl
rm
pkgutil.py
21461
0644
edit
dl
rm
platform.py
46994
0755
edit
dl
rm
plistlib.py
30709
0644
edit
dl
rm
poplib.py
14964
0644
edit
dl
rm
posixpath.py
15771
0644
edit
dl
rm
pprint.py
20884
0644
edit
dl
rm
profile.py
22494
0755
edit
dl
rm
pstats.py
27315
0644
edit
dl
rm
pty.py
4763
0644
edit
dl
rm
pyclbr.py
15137
0644
edit
dl
rm
pydoc.py
105876
0644
edit
dl
rm
py_compile.py
8001
0644
edit
dl
rm
queue.py
11359
0644
edit
dl
rm
quopri.py
7265
0755
edit
dl
rm
random.py
27557
0644
edit
dl
rm
re.py
15306
0644
edit
dl
rm
reprlib.py
5267
0644
edit
dl
rm
rlcompleter.py
7097
0644
edit
dl
rm
runpy.py
11959
0644
edit
dl
rm
sched.py
6442
0644
edit
dl
rm
secrets.py
2038
0644
edit
dl
rm
selectors.py
18561
0644
edit
dl
rm
shelve.py
8527
0644
edit
dl
rm
shlex.py
13100
0644
edit
dl
rm
shutil.py
41950
0644
edit
dl
rm
signal.py
2123
0644
edit
dl
rm
site.py
21575
0644
edit
dl
rm
smtpd.py
34722
0755
edit
dl
rm
smtplib.py
44443
0755
edit
dl
rm
sndhdr.py
7086
0644
edit
dl
rm
socket.py
27469
0644
edit
dl
rm
socketserver.py
26923
0644
edit
dl
rm
sre_compile.py
26872
0644
edit
dl
rm
sre_constants.py
7177
0644
edit
dl
rm
sre_parse.py
39156
0644
edit
dl
rm
ssl.py
45495
0644
edit
dl
rm
stat.py
5391
0644
edit
dl
rm
statistics.py
20651
0644
edit
dl
rm
string.py
11564
0644
edit
dl
rm
stringprep.py
12917
0644
edit
dl
rm
struct.py
257
0644
edit
dl
rm
subprocess.py
72649
0644
edit
dl
rm
sunau.py
18375
0644
edit
dl
rm
symbol.py
2142
0755
edit
dl
rm
symtable.py
7279
0644
edit
dl
rm
sysconfig.py
24440
0644
edit
dl
rm
tabnanny.py
11419
0755
edit
dl
rm
tarfile.py
92675
0755
edit
dl
rm
telnetlib.py
23135
0644
edit
dl
rm
tempfile.py
26730
0644
edit
dl
rm
textwrap.py
19407
0644
edit
dl
rm
this.py
1003
0644
edit
dl
rm
threading.py
49284
0644
edit
dl
rm
timeit.py
13493
0755
edit
dl
rm
token.py
3763
0644
edit
dl
rm
tokenize.py
27031
0644
edit
dl
rm
trace.py
28903
0755
edit
dl
rm
traceback.py
23437
0644
edit
dl
rm
tracemalloc.py
17076
0644
edit
dl
rm
tty.py
879
0644
edit
dl
rm
types.py
9897
0644
edit
dl
rm
typing.py
56438
0644
edit
dl
rm
uu.py
7277
0644
edit
dl
rm
uuid.py
29518
0644
edit
dl
rm
warnings.py
20080
0644
edit
dl
rm
wave.py
18230
0644
edit
dl
rm
weakref.py
21508
0644
edit
dl
rm
webbrowser.py
23715
0755
edit
dl
rm
xdrlib.py
5913
0644
edit
dl
rm
zipapp.py
7535
0644
edit
dl
rm
zipfile.py
81094
0644
edit
dl
rm
_bootlocale.py
1801
0644
edit
dl
rm
_collections_abc.py
26424
0644
edit
dl
rm
_compat_pickle.py
8749
0644
edit
dl
rm
_compression.py
5340
0644
edit
dl
rm
_dummy_thread.py
6027
0644
edit
dl
rm
_markupbase.py
14598
0644
edit
dl
rm
_osx_support.py
19600
0644
edit
dl
rm
_pydecimal.py
228690
0644
edit
dl
rm
_pyio.py
91616
0644
edit
dl
rm
_py_abc.py
6186
0644
edit
dl
rm
_sitebuiltins.py
3115
0644
edit
dl
rm
_strptime.py
25504
0644
edit
dl
rm
_sysconfigdata_dm_linux_x86_64-linux-gnu.py
29786
0644
edit
dl
rm
_sysconfigdata_m_linux_x86_64-linux-gnu.py
28651
0644
edit
dl
rm
_threading_local.py
7214
0644
edit
dl
rm
_weakrefset.py
5679
0644
edit
dl
rm
__future__.py
5101
0644
edit
dl
rm
__phello__.foo.py
64
0644
edit
dl
rm
Edit:
/opt/alt/python37/lib64/python3.7/sre_compile.py
(26872B)
# # 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} _UNIT_CODES = _LITERAL_CODES | {ANY, IN} # Sets of lowercase characters which have the same uppercase. _equivalences = ( # LATIN SMALL LETTER I, LATIN SMALL LETTER DOTLESS I (0x69, 0x131), # iı # LATIN SMALL LETTER S, LATIN SMALL LETTER LONG S (0x73, 0x17f), # sſ # MICRO SIGN, GREEK SMALL LETTER MU (0xb5, 0x3bc), # µμ # COMBINING GREEK YPOGEGRAMMENI, GREEK SMALL LETTER IOTA, GREEK PROSGEGRAMMENI (0x345, 0x3b9, 0x1fbe), # \u0345ιι # GREEK SMALL LETTER IOTA WITH DIALYTIKA AND TONOS, GREEK SMALL LETTER IOTA WITH DIALYTIKA AND OXIA (0x390, 0x1fd3), # ΐΐ # GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND TONOS, GREEK SMALL LETTER UPSILON WITH DIALYTIKA AND OXIA (0x3b0, 0x1fe3), # ΰΰ # GREEK SMALL LETTER BETA, GREEK BETA SYMBOL (0x3b2, 0x3d0), # βϐ # GREEK SMALL LETTER EPSILON, GREEK LUNATE EPSILON SYMBOL (0x3b5, 0x3f5), # εϵ # GREEK SMALL LETTER THETA, GREEK THETA SYMBOL (0x3b8, 0x3d1), # θϑ # GREEK SMALL LETTER KAPPA, GREEK KAPPA SYMBOL (0x3ba, 0x3f0), # κϰ # GREEK SMALL LETTER PI, GREEK PI SYMBOL (0x3c0, 0x3d6), # πϖ # GREEK SMALL LETTER RHO, GREEK RHO SYMBOL (0x3c1, 0x3f1), # ρϱ # GREEK SMALL LETTER FINAL SIGMA, GREEK SMALL LETTER SIGMA (0x3c2, 0x3c3), # ςσ # GREEK SMALL LETTER PHI, GREEK PHI SYMBOL (0x3c6, 0x3d5), # φϕ # LATIN SMALL LETTER S WITH DOT ABOVE, LATIN SMALL LETTER LONG S WITH DOT ABOVE (0x1e61, 0x1e9b), # ṡẛ # LATIN SMALL LIGATURE LONG S T, LATIN SMALL LIGATURE ST (0xfb05, 0xfb06), # ſtst ) # 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 _combine_flags(flags, add_flags, del_flags, TYPE_FLAGS=sre_parse.TYPE_FLAGS): if add_flags & TYPE_FLAGS: flags &= ~TYPE_FLAGS return (flags | add_flags) & ~del_flags 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 iscased = None tolower = None fixes = None if flags & SRE_FLAG_IGNORECASE and not flags & SRE_FLAG_LOCALE: if flags & SRE_FLAG_UNICODE and not flags & SRE_FLAG_ASCII: iscased = _sre.unicode_iscased tolower = _sre.unicode_tolower fixes = _ignorecase_fixes else: iscased = _sre.ascii_iscased tolower = _sre.ascii_tolower for op, av in pattern: if op in LITERAL_CODES: if not flags & SRE_FLAG_IGNORECASE: emit(op) emit(av) elif flags & SRE_FLAG_LOCALE: emit(OP_LOCALE_IGNORE[op]) emit(av) elif not iscased(av): emit(op) emit(av) else: lo = tolower(av) if not fixes: # ascii emit(OP_IGNORE[op]) emit(lo) elif lo not in fixes: emit(OP_UNICODE_IGNORE[op]) emit(lo) else: emit(IN_UNI_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 elif op is IN: charset, hascased = _optimize_charset(av, iscased, tolower, fixes) if flags & SRE_FLAG_IGNORECASE and flags & SRE_FLAG_LOCALE: emit(IN_LOC_IGNORE) elif not hascased: emit(IN) elif not fixes: # ascii emit(IN_IGNORE) else: emit(IN_UNI_IGNORE) skip = _len(code); emit(0) _compile_charset(charset, flags, code) 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,)) if _simple(av[2]): 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: group, add_flags, del_flags, p = av if group: emit(MARK) emit((group-1)*2) # _compile_info(code, p, _combine_flags(flags, add_flags, del_flags)) _compile(code, p, _combine_flags(flags, add_flags, del_flags)) if group: emit(MARK) emit((group-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) and not (flags & SRE_FLAG_ASCII): 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) and not (flags & SRE_FLAG_ASCII): av = CH_UNICODE[av] emit(av) elif op is GROUPREF: if not flags & SRE_FLAG_IGNORECASE: emit(op) elif flags & SRE_FLAG_LOCALE: emit(GROUPREF_LOC_IGNORE) elif not fixes: # ascii emit(GROUPREF_IGNORE) else: emit(GROUPREF_UNI_IGNORE) 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): # compile charset subprogram emit = code.append for op, av in charset: emit(op) if op is NEGATE: pass elif op is LITERAL: emit(av) elif op is RANGE or op is RANGE_UNI_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) and not (flags & SRE_FLAG_ASCII): emit(CH_UNICODE[av]) else: emit(av) else: raise error("internal: unsupported set operator %r" % (op,)) emit(FAILURE) def _optimize_charset(charset, iscased=None, fixup=None, fixes=None): # internal: optimize character set out = [] tail = [] charmap = bytearray(256) hascased = False 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 if not hascased and iscased(av): hascased = True else: charmap[av] = 1 elif op is RANGE: r = range(av[0], av[1]+1) if fixup: if fixes: for i in map(fixup, r): charmap[i] = 1 if i in fixes: for k in fixes[i]: charmap[k] = 1 else: for i in map(fixup, r): charmap[i] = 1 if not hascased: hascased = any(map(iscased, r)) 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. if fixup: hascased = True # There are only two ranges of cased non-BMP characters: # 10400-1044F (Deseret) and 118A0-118DF (Warang Citi), # and for both ranges RANGE_UNI_IGNORE works. if op is RANGE: op = RANGE_UNI_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 hascased or len(out) < len(charset): return out, hascased # else original character set is good enough return charset, hascased # use bitmap if len(charmap) == 256: data = _mk_bitmap(charmap) out.append((CHARSET, data)) out += tail return out, hascased # 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, hascased _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(p): # check if this subpattern is a "simple" operator if len(p) != 1: return False op, av = p[0] if op is SUBPATTERN: return av[0] is None and _simple(av[-1]) return op in _UNIT_CODES 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 _get_iscased(flags): if not flags & SRE_FLAG_IGNORECASE: return None elif flags & SRE_FLAG_UNICODE and not flags & SRE_FLAG_ASCII: return _sre.unicode_iscased else: return _sre.ascii_iscased def _get_literal_prefix(pattern, flags): # look for literal prefix prefix = [] prefixappend = prefix.append prefix_skip = None iscased = _get_iscased(flags) for op, av in pattern.data: if op is LITERAL: if iscased and iscased(av): break prefixappend(av) elif op is SUBPATTERN: group, add_flags, del_flags, p = av flags1 = _combine_flags(flags, add_flags, del_flags) if flags1 & SRE_FLAG_IGNORECASE and flags1 & SRE_FLAG_LOCALE: break prefix1, prefix_skip1, got_all = _get_literal_prefix(p, flags1) if prefix_skip is None: if group is not None: prefix_skip = len(prefix) elif prefix_skip1 is not None: prefix_skip = len(prefix) + prefix_skip1 prefix.extend(prefix1) if not got_all: break else: break else: return prefix, prefix_skip, True return prefix, prefix_skip, False def _get_charset_prefix(pattern, flags): while True: if not pattern.data: return None op, av = pattern.data[0] if op is not SUBPATTERN: break group, add_flags, del_flags, pattern = av flags = _combine_flags(flags, add_flags, del_flags) if flags & SRE_FLAG_IGNORECASE and flags & SRE_FLAG_LOCALE: return None iscased = _get_iscased(flags) if op is LITERAL: if iscased and iscased(av): return None return [(op, av)] elif op is BRANCH: charset = [] charsetappend = charset.append for p in av[1]: if not p: return None op, av = p[0] if op is LITERAL and not (iscased and iscased(av)): charsetappend((op, av)) else: return None return charset elif op is IN: charset = av if iscased: for op, av in charset: if op is LITERAL: if iscased(av): return None elif op is RANGE: if av[1] > 0xffff: return None if any(map(iscased, range(av[0], av[1]+1))): return None return charset return None 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 = [] prefix_skip = 0 charset = [] # not used if not (flags & SRE_FLAG_IGNORECASE and flags & SRE_FLAG_LOCALE): # look for literal prefix prefix, prefix_skip, got_all = _get_literal_prefix(pattern, flags) # if no prefix, look for charset prefix if not prefix: charset = _get_charset_prefix(pattern, flags) ## 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 prefix_skip is None and got_all: 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 if prefix_skip is None: prefix_skip = len(prefix) emit(prefix_skip) # skip code.extend(prefix) # generate overlap table code.extend(_generate_overlap_table(prefix)) elif charset: charset, hascased = _optimize_charset(charset) assert not hascased _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 _hex_code(code): return '[%s]' % ', '.join('%#0*x' % (_sre.CODESIZE*2+2, x) for x in code) def dis(code): import sys labels = set() level = 0 offset_width = len(str(len(code) - 1)) def dis_(start, end): def print_(*args, to=None): if to is not None: labels.add(to) args += ('(to %d)' % (to,),) print('%*d%s ' % (offset_width, start, ':' if start in labels else '.'), end=' '*(level-1)) print(*args) def print_2(*args): print(end=' '*(offset_width + 2*level)) print(*args) nonlocal level level += 1 i = start while i < end: start = i op = code[i] i += 1 op = OPCODES[op] if op in (SUCCESS, FAILURE, ANY, ANY_ALL, MAX_UNTIL, MIN_UNTIL, NEGATE): print_(op) elif op in (LITERAL, NOT_LITERAL, LITERAL_IGNORE, NOT_LITERAL_IGNORE, LITERAL_UNI_IGNORE, NOT_LITERAL_UNI_IGNORE, LITERAL_LOC_IGNORE, NOT_LITERAL_LOC_IGNORE): arg = code[i] i += 1 print_(op, '%#02x (%r)' % (arg, chr(arg))) elif op is AT: arg = code[i] i += 1 arg = str(ATCODES[arg]) assert arg[:3] == 'AT_' print_(op, arg[3:]) elif op is CATEGORY: arg = code[i] i += 1 arg = str(CHCODES[arg]) assert arg[:9] == 'CATEGORY_' print_(op, arg[9:]) elif op in (IN, IN_IGNORE, IN_UNI_IGNORE, IN_LOC_IGNORE): skip = code[i] print_(op, skip, to=i+skip) dis_(i+1, i+skip) i += skip elif op in (RANGE, RANGE_UNI_IGNORE): lo, hi = code[i: i+2] i += 2 print_(op, '%#02x %#02x (%r-%r)' % (lo, hi, chr(lo), chr(hi))) elif op is CHARSET: print_(op, _hex_code(code[i: i + 256//_CODEBITS])) i += 256//_CODEBITS elif op is BIGCHARSET: arg = code[i] i += 1 mapping = list(b''.join(x.to_bytes(_sre.CODESIZE, sys.byteorder) for x in code[i: i + 256//_sre.CODESIZE])) print_(op, arg, mapping) i += 256//_sre.CODESIZE level += 1 for j in range(arg): print_2(_hex_code(code[i: i + 256//_CODEBITS])) i += 256//_CODEBITS level -= 1 elif op in (MARK, GROUPREF, GROUPREF_IGNORE, GROUPREF_UNI_IGNORE, GROUPREF_LOC_IGNORE): arg = code[i] i += 1 print_(op, arg) elif op is JUMP: skip = code[i] print_(op, skip, to=i+skip) i += 1 elif op is BRANCH: skip = code[i] print_(op, skip, to=i+skip) while skip: dis_(i+1, i+skip) i += skip start = i skip = code[i] if skip: print_('branch', skip, to=i+skip) else: print_(FAILURE) i += 1 elif op in (REPEAT, REPEAT_ONE, MIN_REPEAT_ONE): skip, min, max = code[i: i+3] if max == MAXREPEAT: max = 'MAXREPEAT' print_(op, skip, min, max, to=i+skip) dis_(i+3, i+skip) i += skip elif op is GROUPREF_EXISTS: arg, skip = code[i: i+2] print_(op, arg, skip, to=i+skip) i += 2 elif op in (ASSERT, ASSERT_NOT): skip, arg = code[i: i+2] print_(op, skip, arg, to=i+skip) dis_(i+2, i+skip) i += skip elif op is INFO: skip, flags, min, max = code[i: i+4] if max == MAXREPEAT: max = 'MAXREPEAT' print_(op, skip, bin(flags), min, max, to=i+skip) start = i+4 if flags & SRE_INFO_PREFIX: prefix_len, prefix_skip = code[i+4: i+6] print_2(' prefix_skip', prefix_skip) start = i + 6 prefix = code[start: start+prefix_len] print_2(' prefix', '[%s]' % ', '.join('%#02x' % x for x in prefix), '(%r)' % ''.join(map(chr, prefix))) start += prefix_len print_2(' overlap', code[start: start+prefix_len]) start += prefix_len if flags & SRE_INFO_CHARSET: level += 1 print_2('in') dis_(start, i+skip) level -= 1 i += skip else: raise ValueError(op) level -= 1 dis_(0, len(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) if flags & SRE_FLAG_DEBUG: print() dis(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, tuple(indexgroup) )
Save
cmd:
run