/
opt
/
alt
/
python34
/
lib64
/
python3.4
/
/opt/alt/python34/lib64/python3.4
mkdir
upload
Name
Size
Mode
Actions
asyncio/
-
0755
rm
collections/
-
0755
rm
concurrent/
-
0755
rm
config-3.4m/
-
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
plat-linux/
-
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
8624
0644
edit
dl
rm
aifc.py
31578
0644
edit
dl
rm
antigravity.py
475
0644
edit
dl
rm
argparse.py
90027
0644
edit
dl
rm
ast.py
12034
0644
edit
dl
rm
asynchat.py
11825
0644
edit
dl
rm
asyncore.py
20998
0644
edit
dl
rm
base64.py
20180
0755
edit
dl
rm
bdb.py
23354
0644
edit
dl
rm
binhex.py
13928
0644
edit
dl
rm
bisect.py
2595
0644
edit
dl
rm
bz2.py
18860
0644
edit
dl
rm
calendar.py
22941
0644
edit
dl
rm
cgi.py
35941
0755
edit
dl
rm
cgitb.py
12041
0644
edit
dl
rm
chunk.py
5425
0644
edit
dl
rm
cmd.py
14860
0644
edit
dl
rm
code.py
10037
0644
edit
dl
rm
codecs.py
35910
0644
edit
dl
rm
codeop.py
5994
0644
edit
dl
rm
colorsys.py
4064
0644
edit
dl
rm
compileall.py
9618
0644
edit
dl
rm
configparser.py
49698
0644
edit
dl
rm
contextlib.py
11639
0644
edit
dl
rm
copy.py
9005
0644
edit
dl
rm
copyreg.py
6833
0644
edit
dl
rm
cProfile.py
5324
0755
edit
dl
rm
crypt.py
1879
0644
edit
dl
rm
csv.py
16185
0644
edit
dl
rm
datetime.py
75804
0644
edit
dl
rm
decimal.py
228688
0644
edit
dl
rm
difflib.py
81684
0644
edit
dl
rm
dis.py
17160
0644
edit
dl
rm
doctest.py
104492
0644
edit
dl
rm
dummy_threading.py
2815
0644
edit
dl
rm
enum.py
21538
0644
edit
dl
rm
filecmp.py
9830
0644
edit
dl
rm
fileinput.py
14865
0644
edit
dl
rm
fnmatch.py
3163
0644
edit
dl
rm
formatter.py
15173
0644
edit
dl
rm
fractions.py
23203
0644
edit
dl
rm
ftplib.py
38532
0644
edit
dl
rm
functools.py
28511
0644
edit
dl
rm
genericpath.py
3882
0644
edit
dl
rm
getopt.py
7489
0644
edit
dl
rm
getpass.py
6069
0644
edit
dl
rm
gettext.py
20767
0644
edit
dl
rm
glob.py
3461
0644
edit
dl
rm
gzip.py
24314
0644
edit
dl
rm
hashlib.py
9850
0644
edit
dl
rm
heapq.py
17997
0644
edit
dl
rm
hmac.py
5063
0644
edit
dl
rm
imaplib.py
50267
0644
edit
dl
rm
imghdr.py
3528
0644
edit
dl
rm
imp.py
9984
0644
edit
dl
rm
inspect.py
104640
0644
edit
dl
rm
io.py
3396
0644
edit
dl
rm
ipaddress.py
71598
0644
edit
dl
rm
keyword.py
2222
0755
edit
dl
rm
linecache.py
3953
0644
edit
dl
rm
locale.py
74530
0644
edit
dl
rm
lzma.py
19371
0644
edit
dl
rm
macpath.py
5619
0644
edit
dl
rm
macurl2path.py
2732
0644
edit
dl
rm
mailbox.py
78382
0644
edit
dl
rm
mailcap.py
7437
0644
edit
dl
rm
mimetypes.py
20781
0644
edit
dl
rm
modulefinder.py
23421
0644
edit
dl
rm
netrc.py
5748
0644
edit
dl
rm
nntplib.py
43082
0644
edit
dl
rm
ntpath.py
20477
0644
edit
dl
rm
nturl2path.py
2444
0644
edit
dl
rm
numbers.py
10243
0644
edit
dl
rm
opcode.py
5442
0644
edit
dl
rm
operator.py
9195
0644
edit
dl
rm
optparse.py
60346
0644
edit
dl
rm
os.py
33882
0644
edit
dl
rm
pathlib.py
42467
0644
edit
dl
rm
pdb.py
60992
0755
edit
dl
rm
pickle.py
55989
0644
edit
dl
rm
pickletools.py
91762
0644
edit
dl
rm
pipes.py
8916
0644
edit
dl
rm
pkgutil.py
21215
0644
edit
dl
rm
platform.py
46761
0755
edit
dl
rm
plistlib.py
31791
0644
edit
dl
rm
poplib.py
14319
0644
edit
dl
rm
posixpath.py
13448
0644
edit
dl
rm
pprint.py
14919
0644
edit
dl
rm
profile.py
22032
0755
edit
dl
rm
pstats.py
26316
0644
edit
dl
rm
pty.py
4763
0644
edit
dl
rm
pyclbr.py
13520
0644
edit
dl
rm
pydoc.py
103011
0755
edit
dl
rm
py_compile.py
7103
0644
edit
dl
rm
queue.py
8835
0644
edit
dl
rm
quopri.py
7265
0755
edit
dl
rm
random.py
26084
0644
edit
dl
rm
re.py
15604
0644
edit
dl
rm
reprlib.py
5110
0644
edit
dl
rm
rlcompleter.py
6069
0644
edit
dl
rm
runpy.py
10816
0644
edit
dl
rm
sched.py
6354
0644
edit
dl
rm
selectors.py
17097
0644
edit
dl
rm
shelve.py
8528
0644
edit
dl
rm
shlex.py
11548
0644
edit
dl
rm
shutil.py
39902
0644
edit
dl
rm
site.py
21553
0644
edit
dl
rm
smtpd.py
29991
0755
edit
dl
rm
smtplib.py
38971
0755
edit
dl
rm
sndhdr.py
6256
0644
edit
dl
rm
socket.py
19067
0644
edit
dl
rm
socketserver.py
24372
0644
edit
dl
rm
sre_compile.py
19903
0644
edit
dl
rm
sre_constants.py
7267
0644
edit
dl
rm
sre_parse.py
31429
0644
edit
dl
rm
ssl.py
34747
0644
edit
dl
rm
stat.py
4400
0644
edit
dl
rm
statistics.py
19556
0644
edit
dl
rm
string.py
11445
0644
edit
dl
rm
stringprep.py
12917
0644
edit
dl
rm
struct.py
257
0644
edit
dl
rm
subprocess.py
64549
0644
edit
dl
rm
sunau.py
18095
0644
edit
dl
rm
symbol.py
2053
0755
edit
dl
rm
symtable.py
7404
0644
edit
dl
rm
sysconfig.py
24632
0644
edit
dl
rm
tabnanny.py
11410
0755
edit
dl
rm
tarfile.py
91557
0755
edit
dl
rm
telnetlib.py
23074
0644
edit
dl
rm
tempfile.py
22525
0644
edit
dl
rm
textwrap.py
19282
0644
edit
dl
rm
this.py
1003
0644
edit
dl
rm
threading.py
48802
0644
edit
dl
rm
timeit.py
11972
0755
edit
dl
rm
token.py
3034
0644
edit
dl
rm
tokenize.py
25596
0644
edit
dl
rm
trace.py
31487
0755
edit
dl
rm
traceback.py
11167
0644
edit
dl
rm
tracemalloc.py
15651
0644
edit
dl
rm
tty.py
879
0644
edit
dl
rm
types.py
5411
0644
edit
dl
rm
uu.py
6766
0755
edit
dl
rm
uuid.py
23724
0644
edit
dl
rm
warnings.py
14303
0644
edit
dl
rm
wave.py
17682
0644
edit
dl
rm
weakref.py
19384
0644
edit
dl
rm
webbrowser.py
21432
0755
edit
dl
rm
xdrlib.py
5913
0644
edit
dl
rm
zipfile.py
68547
0644
edit
dl
rm
_bootlocale.py
1301
0644
edit
dl
rm
_collections_abc.py
19898
0644
edit
dl
rm
_compat_pickle.py
8318
0644
edit
dl
rm
_dummy_thread.py
4872
0644
edit
dl
rm
_markupbase.py
14598
0644
edit
dl
rm
_osx_support.py
19101
0644
edit
dl
rm
_pyio.py
73893
0644
edit
dl
rm
_sitebuiltins.py
3115
0644
edit
dl
rm
_strptime.py
22053
0644
edit
dl
rm
_sysconfigdata.py
24480
0644
edit
dl
rm
_threading_local.py
7410
0644
edit
dl
rm
_weakrefset.py
5705
0644
edit
dl
rm
__future__.py
4584
0644
edit
dl
rm
__phello__.foo.py
64
0644
edit
dl
rm
Edit:
/opt/alt/python34/lib64/python3.4/sre_parse.py
(31429B)
# # Secret Labs' Regular Expression Engine # # convert re-style regular expression to sre pattern # # Copyright (c) 1998-2001 by Secret Labs AB. All rights reserved. # # See the sre.py file for information on usage and redistribution. # """Internal support module for sre""" # XXX: show string offset and offending character for all errors from sre_constants import * from _sre import MAXREPEAT SPECIAL_CHARS = ".\\[{()*+?^$|" REPEAT_CHARS = "*+?{" DIGITS = set("0123456789") OCTDIGITS = set("01234567") HEXDIGITS = set("0123456789abcdefABCDEF") WHITESPACE = set(" \t\n\r\v\f") ESCAPES = { r"\a": (LITERAL, ord("\a")), r"\b": (LITERAL, ord("\b")), r"\f": (LITERAL, ord("\f")), r"\n": (LITERAL, ord("\n")), r"\r": (LITERAL, ord("\r")), r"\t": (LITERAL, ord("\t")), r"\v": (LITERAL, ord("\v")), r"\\": (LITERAL, ord("\\")) } CATEGORIES = { r"\A": (AT, AT_BEGINNING_STRING), # start of string r"\b": (AT, AT_BOUNDARY), r"\B": (AT, AT_NON_BOUNDARY), r"\d": (IN, [(CATEGORY, CATEGORY_DIGIT)]), r"\D": (IN, [(CATEGORY, CATEGORY_NOT_DIGIT)]), r"\s": (IN, [(CATEGORY, CATEGORY_SPACE)]), r"\S": (IN, [(CATEGORY, CATEGORY_NOT_SPACE)]), r"\w": (IN, [(CATEGORY, CATEGORY_WORD)]), r"\W": (IN, [(CATEGORY, CATEGORY_NOT_WORD)]), r"\Z": (AT, AT_END_STRING), # end of string } FLAGS = { # standard flags "i": SRE_FLAG_IGNORECASE, "L": SRE_FLAG_LOCALE, "m": SRE_FLAG_MULTILINE, "s": SRE_FLAG_DOTALL, "x": SRE_FLAG_VERBOSE, # extensions "a": SRE_FLAG_ASCII, "t": SRE_FLAG_TEMPLATE, "u": SRE_FLAG_UNICODE, } class Pattern: # master pattern object. keeps track of global attributes def __init__(self): self.flags = 0 self.open = [] self.groups = 1 self.groupdict = {} self.lookbehind = 0 def opengroup(self, name=None): gid = self.groups self.groups = gid + 1 if name is not None: ogid = self.groupdict.get(name, None) if ogid is not None: raise error("redefinition of group name %s as group %d; " "was group %d" % (repr(name), gid, ogid)) self.groupdict[name] = gid self.open.append(gid) return gid def closegroup(self, gid): self.open.remove(gid) def checkgroup(self, gid): return gid < self.groups and gid not in self.open class SubPattern: # a subpattern, in intermediate form def __init__(self, pattern, data=None): self.pattern = pattern if data is None: data = [] self.data = data self.width = None def dump(self, level=0): nl = True seqtypes = (tuple, list) for op, av in self.data: print(level*" " + op, end='') if op == IN: # member sublanguage print() for op, a in av: print((level+1)*" " + op, a) elif op == BRANCH: print() for i, a in enumerate(av[1]): if i: print(level*" " + "or") a.dump(level+1) elif op == GROUPREF_EXISTS: condgroup, item_yes, item_no = av print('', condgroup) item_yes.dump(level+1) if item_no: print(level*" " + "else") item_no.dump(level+1) elif isinstance(av, seqtypes): nl = False for a in av: if isinstance(a, SubPattern): if not nl: print() a.dump(level+1) nl = True else: if not nl: print(' ', end='') print(a, end='') nl = False if not nl: print() else: print('', av) def __repr__(self): return repr(self.data) def __len__(self): return len(self.data) def __delitem__(self, index): del self.data[index] def __getitem__(self, index): if isinstance(index, slice): return SubPattern(self.pattern, self.data[index]) return self.data[index] def __setitem__(self, index, code): self.data[index] = code def insert(self, index, code): self.data.insert(index, code) def append(self, code): self.data.append(code) def getwidth(self): # determine the width (min, max) for this subpattern if self.width: return self.width lo = hi = 0 UNITCODES = (ANY, RANGE, IN, LITERAL, NOT_LITERAL, CATEGORY) REPEATCODES = (MIN_REPEAT, MAX_REPEAT) for op, av in self.data: if op is BRANCH: i = MAXREPEAT - 1 j = 0 for av in av[1]: l, h = av.getwidth() i = min(i, l) j = max(j, h) lo = lo + i hi = hi + j elif op is CALL: i, j = av.getwidth() lo = lo + i hi = hi + j elif op is SUBPATTERN: i, j = av[1].getwidth() lo = lo + i hi = hi + j elif op in REPEATCODES: i, j = av[2].getwidth() lo = lo + i * av[0] hi = hi + j * av[1] elif op in UNITCODES: lo = lo + 1 hi = hi + 1 elif op == SUCCESS: break self.width = min(lo, MAXREPEAT - 1), min(hi, MAXREPEAT) return self.width class Tokenizer: def __init__(self, string): self.istext = isinstance(string, str) self.string = string self.index = 0 self.__next() def __next(self): if self.index >= len(self.string): self.next = None return char = self.string[self.index:self.index+1] # Special case for the str8, since indexing returns a integer # XXX This is only needed for test_bug_926075 in test_re.py if char and not self.istext: char = chr(char[0]) if char == "\\": try: c = self.string[self.index + 1] except IndexError: raise error("bogus escape (end of line)") if not self.istext: c = chr(c) char = char + c self.index = self.index + len(char) self.next = char def match(self, char, skip=1): if char == self.next: if skip: self.__next() return 1 return 0 def get(self): this = self.next self.__next() return this def getwhile(self, n, charset): result = '' for _ in range(n): c = self.next if c not in charset: break result += c self.__next() return result def tell(self): return self.index, self.next def seek(self, index): self.index, self.next = index # The following three functions are not used in this module anymore, but we keep # them here (with DeprecationWarnings) for backwards compatibility. def isident(char): import warnings warnings.warn('sre_parse.isident() will be removed in 3.5', DeprecationWarning, stacklevel=2) return "a" <= char <= "z" or "A" <= char <= "Z" or char == "_" def isdigit(char): import warnings warnings.warn('sre_parse.isdigit() will be removed in 3.5', DeprecationWarning, stacklevel=2) return "0" <= char <= "9" def isname(name): import warnings warnings.warn('sre_parse.isname() will be removed in 3.5', DeprecationWarning, stacklevel=2) # check that group name is a valid string if not isident(name[0]): return False for char in name[1:]: if not isident(char) and not isdigit(char): return False return True def _class_escape(source, escape): # handle escape code inside character class code = ESCAPES.get(escape) if code: return code code = CATEGORIES.get(escape) if code and code[0] == IN: return code try: c = escape[1:2] if c == "x": # hexadecimal escape (exactly two digits) escape += source.getwhile(2, HEXDIGITS) if len(escape) != 4: raise ValueError return LITERAL, int(escape[2:], 16) & 0xff elif c == "u" and source.istext: # unicode escape (exactly four digits) escape += source.getwhile(4, HEXDIGITS) if len(escape) != 6: raise ValueError return LITERAL, int(escape[2:], 16) elif c == "U" and source.istext: # unicode escape (exactly eight digits) escape += source.getwhile(8, HEXDIGITS) if len(escape) != 10: raise ValueError c = int(escape[2:], 16) chr(c) # raise ValueError for invalid code return LITERAL, c elif c in OCTDIGITS: # octal escape (up to three digits) escape += source.getwhile(2, OCTDIGITS) return LITERAL, int(escape[1:], 8) & 0xff elif c in DIGITS: raise ValueError if len(escape) == 2: return LITERAL, ord(escape[1]) except ValueError: pass raise error("bogus escape: %s" % repr(escape)) def _escape(source, escape, state): # handle escape code in expression code = CATEGORIES.get(escape) if code: return code code = ESCAPES.get(escape) if code: return code try: c = escape[1:2] if c == "x": # hexadecimal escape escape += source.getwhile(2, HEXDIGITS) if len(escape) != 4: raise ValueError return LITERAL, int(escape[2:], 16) & 0xff elif c == "u" and source.istext: # unicode escape (exactly four digits) escape += source.getwhile(4, HEXDIGITS) if len(escape) != 6: raise ValueError return LITERAL, int(escape[2:], 16) elif c == "U" and source.istext: # unicode escape (exactly eight digits) escape += source.getwhile(8, HEXDIGITS) if len(escape) != 10: raise ValueError c = int(escape[2:], 16) chr(c) # raise ValueError for invalid code return LITERAL, c elif c == "0": # octal escape escape += source.getwhile(2, OCTDIGITS) return LITERAL, int(escape[1:], 8) & 0xff elif c in DIGITS: # octal escape *or* decimal group reference (sigh) if source.next in DIGITS: escape = escape + source.get() if (escape[1] in OCTDIGITS and escape[2] in OCTDIGITS and source.next in OCTDIGITS): # got three octal digits; this is an octal escape escape = escape + source.get() return LITERAL, int(escape[1:], 8) & 0xff # not an octal escape, so this is a group reference group = int(escape[1:]) if group < state.groups: if not state.checkgroup(group): raise error("cannot refer to open group") if state.lookbehind: import warnings warnings.warn('group references in lookbehind ' 'assertions are not supported', RuntimeWarning) return GROUPREF, group raise ValueError if len(escape) == 2: return LITERAL, ord(escape[1]) except ValueError: pass raise error("bogus escape: %s" % repr(escape)) def _parse_sub(source, state, nested=1): # parse an alternation: a|b|c items = [] itemsappend = items.append sourcematch = source.match while 1: itemsappend(_parse(source, state)) if sourcematch("|"): continue if not nested: break if not source.next or sourcematch(")", 0): break else: raise error("pattern not properly closed") if len(items) == 1: return items[0] subpattern = SubPattern(state) subpatternappend = subpattern.append # check if all items share a common prefix while 1: prefix = None for item in items: if not item: break if prefix is None: prefix = item[0] elif item[0] != prefix: break else: # all subitems start with a common "prefix". # move it out of the branch for item in items: del item[0] subpatternappend(prefix) continue # check next one break # check if the branch can be replaced by a character set for item in items: if len(item) != 1 or item[0][0] != LITERAL: break else: # we can store this as a character set instead of a # branch (the compiler may optimize this even more) set = [] setappend = set.append for item in items: setappend(item[0]) subpatternappend((IN, set)) return subpattern subpattern.append((BRANCH, (None, items))) return subpattern def _parse_sub_cond(source, state, condgroup): item_yes = _parse(source, state) if source.match("|"): item_no = _parse(source, state) if source.match("|"): raise error("conditional backref with more than two branches") else: item_no = None if source.next and not source.match(")", 0): raise error("pattern not properly closed") subpattern = SubPattern(state) subpattern.append((GROUPREF_EXISTS, (condgroup, item_yes, item_no))) return subpattern _PATTERNENDERS = set("|)") _ASSERTCHARS = set("=!<") _LOOKBEHINDASSERTCHARS = set("=!") _REPEATCODES = set([MIN_REPEAT, MAX_REPEAT]) def _parse(source, state): # parse a simple pattern subpattern = SubPattern(state) # precompute constants into local variables subpatternappend = subpattern.append sourceget = source.get sourcematch = source.match _len = len PATTERNENDERS = _PATTERNENDERS ASSERTCHARS = _ASSERTCHARS LOOKBEHINDASSERTCHARS = _LOOKBEHINDASSERTCHARS REPEATCODES = _REPEATCODES while 1: if source.next in PATTERNENDERS: break # end of subpattern this = sourceget() if this is None: break # end of pattern if state.flags & SRE_FLAG_VERBOSE: # skip whitespace and comments if this in WHITESPACE: continue if this == "#": while 1: this = sourceget() if this in (None, "\n"): break continue if this and this[0] not in SPECIAL_CHARS: subpatternappend((LITERAL, ord(this))) elif this == "[": # character set set = [] setappend = set.append ## if sourcematch(":"): ## pass # handle character classes if sourcematch("^"): setappend((NEGATE, None)) # check remaining characters start = set[:] while 1: this = sourceget() if this == "]" and set != start: break elif this and this[0] == "\\": code1 = _class_escape(source, this) elif this: code1 = LITERAL, ord(this) else: raise error("unexpected end of regular expression") if sourcematch("-"): # potential range this = sourceget() if this == "]": if code1[0] is IN: code1 = code1[1][0] setappend(code1) setappend((LITERAL, ord("-"))) break elif this: if this[0] == "\\": code2 = _class_escape(source, this) else: code2 = LITERAL, ord(this) if code1[0] != LITERAL or code2[0] != LITERAL: raise error("bad character range") lo = code1[1] hi = code2[1] if hi < lo: raise error("bad character range") setappend((RANGE, (lo, hi))) else: raise error("unexpected end of regular expression") else: if code1[0] is IN: code1 = code1[1][0] setappend(code1) # XXX: <fl> should move set optimization to compiler! if _len(set)==1 and set[0][0] is LITERAL: subpatternappend(set[0]) # optimization elif _len(set)==2 and set[0][0] is NEGATE and set[1][0] is LITERAL: subpatternappend((NOT_LITERAL, set[1][1])) # optimization else: # XXX: <fl> should add charmap optimization here subpatternappend((IN, set)) elif this and this[0] in REPEAT_CHARS: # repeat previous item if this == "?": min, max = 0, 1 elif this == "*": min, max = 0, MAXREPEAT elif this == "+": min, max = 1, MAXREPEAT elif this == "{": if source.next == "}": subpatternappend((LITERAL, ord(this))) continue here = source.tell() min, max = 0, MAXREPEAT lo = hi = "" while source.next in DIGITS: lo = lo + source.get() if sourcematch(","): while source.next in DIGITS: hi = hi + sourceget() else: hi = lo if not sourcematch("}"): subpatternappend((LITERAL, ord(this))) source.seek(here) continue if lo: min = int(lo) if min >= MAXREPEAT: raise OverflowError("the repetition number is too large") if hi: max = int(hi) if max >= MAXREPEAT: raise OverflowError("the repetition number is too large") if max < min: raise error("bad repeat interval") else: raise error("not supported") # figure out which item to repeat if subpattern: item = subpattern[-1:] else: item = None if not item or (_len(item) == 1 and item[0][0] == AT): raise error("nothing to repeat") if item[0][0] in REPEATCODES: raise error("multiple repeat") if sourcematch("?"): subpattern[-1] = (MIN_REPEAT, (min, max, item)) else: subpattern[-1] = (MAX_REPEAT, (min, max, item)) elif this == ".": subpatternappend((ANY, None)) elif this == "(": group = 1 name = None condgroup = None if sourcematch("?"): group = 0 # options if sourcematch("P"): # python extensions if sourcematch("<"): # named group: skip forward to end of name name = "" while 1: char = sourceget() if char is None: raise error("unterminated name") if char == ">": break name = name + char group = 1 if not name: raise error("missing group name") if not name.isidentifier(): raise error("bad character in group name %r" % name) elif sourcematch("="): # named backreference name = "" while 1: char = sourceget() if char is None: raise error("unterminated name") if char == ")": break name = name + char if not name: raise error("missing group name") if not name.isidentifier(): raise error("bad character in backref group name " "%r" % name) gid = state.groupdict.get(name) if gid is None: msg = "unknown group name: {0!r}".format(name) raise error(msg) if state.lookbehind: import warnings warnings.warn('group references in lookbehind ' 'assertions are not supported', RuntimeWarning) subpatternappend((GROUPREF, gid)) continue else: char = sourceget() if char is None: raise error("unexpected end of pattern") raise error("unknown specifier: ?P%s" % char) elif sourcematch(":"): # non-capturing group group = 2 elif sourcematch("#"): # comment while 1: if source.next is None or source.next == ")": break sourceget() if not sourcematch(")"): raise error("unbalanced parenthesis") continue elif source.next in ASSERTCHARS: # lookahead assertions char = sourceget() dir = 1 if char == "<": if source.next not in LOOKBEHINDASSERTCHARS: raise error("syntax error") dir = -1 # lookbehind char = sourceget() state.lookbehind += 1 p = _parse_sub(source, state) if dir < 0: state.lookbehind -= 1 if not sourcematch(")"): raise error("unbalanced parenthesis") if char == "=": subpatternappend((ASSERT, (dir, p))) else: subpatternappend((ASSERT_NOT, (dir, p))) continue elif sourcematch("("): # conditional backreference group condname = "" while 1: char = sourceget() if char is None: raise error("unterminated name") if char == ")": break condname = condname + char group = 2 if not condname: raise error("missing group name") if condname.isidentifier(): condgroup = state.groupdict.get(condname) if condgroup is None: msg = "unknown group name: {0!r}".format(condname) raise error(msg) else: try: condgroup = int(condname) except ValueError: raise error("bad character in group name") if state.lookbehind: import warnings warnings.warn('group references in lookbehind ' 'assertions are not supported', RuntimeWarning) else: # flags if not source.next in FLAGS: raise error("unexpected end of pattern") while source.next in FLAGS: state.flags = state.flags | FLAGS[sourceget()] if group: # parse group contents if group == 2: # anonymous group group = None else: group = state.opengroup(name) if condgroup: p = _parse_sub_cond(source, state, condgroup) else: p = _parse_sub(source, state) if not sourcematch(")"): raise error("unbalanced parenthesis") if group is not None: state.closegroup(group) subpatternappend((SUBPATTERN, (group, p))) else: while 1: char = sourceget() if char is None: raise error("unexpected end of pattern") if char == ")": break raise error("unknown extension") elif this == "^": subpatternappend((AT, AT_BEGINNING)) elif this == "$": subpattern.append((AT, AT_END)) elif this and this[0] == "\\": code = _escape(source, this, state) subpatternappend(code) else: raise error("parser error") return subpattern def fix_flags(src, flags): # Check and fix flags according to the type of pattern (str or bytes) if isinstance(src, str): if not flags & SRE_FLAG_ASCII: flags |= SRE_FLAG_UNICODE elif flags & SRE_FLAG_UNICODE: raise ValueError("ASCII and UNICODE flags are incompatible") else: if flags & SRE_FLAG_UNICODE: raise ValueError("can't use UNICODE flag with a bytes pattern") return flags def parse(str, flags=0, pattern=None): # parse 're' pattern into list of (opcode, argument) tuples source = Tokenizer(str) if pattern is None: pattern = Pattern() pattern.flags = flags pattern.str = str p = _parse_sub(source, pattern, 0) p.pattern.flags = fix_flags(str, p.pattern.flags) tail = source.get() if tail == ")": raise error("unbalanced parenthesis") elif tail: raise error("bogus characters at end of regular expression") if flags & SRE_FLAG_DEBUG: p.dump() if not (flags & SRE_FLAG_VERBOSE) and p.pattern.flags & SRE_FLAG_VERBOSE: # the VERBOSE flag was switched on inside the pattern. to be # on the safe side, we'll parse the whole thing again... return parse(str, p.pattern.flags) return p def parse_template(source, pattern): # parse 're' replacement string into list of literals and # group references s = Tokenizer(source) sget = s.get groups = [] literals = [] literal = [] lappend = literal.append def addgroup(index): if literal: literals.append(''.join(literal)) del literal[:] groups.append((len(literals), index)) literals.append(None) while True: this = sget() if this is None: break # end of replacement string if this[0] == "\\": # group c = this[1] if c == "g": name = "" if s.match("<"): while True: char = sget() if char is None: raise error("unterminated group name") if char == ">": break name += char if not name: raise error("missing group name") try: index = int(name) if index < 0: raise error("negative group number") except ValueError: if not name.isidentifier(): raise error("bad character in group name") try: index = pattern.groupindex[name] except KeyError: msg = "unknown group name: {0!r}".format(name) raise IndexError(msg) addgroup(index) elif c == "0": if s.next in OCTDIGITS: this += sget() if s.next in OCTDIGITS: this += sget() lappend(chr(int(this[1:], 8) & 0xff)) elif c in DIGITS: isoctal = False if s.next in DIGITS: this += sget() if (c in OCTDIGITS and this[2] in OCTDIGITS and s.next in OCTDIGITS): this += sget() isoctal = True lappend(chr(int(this[1:], 8) & 0xff)) if not isoctal: addgroup(int(this[1:])) else: try: this = chr(ESCAPES[this][1]) except KeyError: pass lappend(this) else: lappend(this) if literal: literals.append(''.join(literal)) if not isinstance(source, str): # The tokenizer implicitly decodes bytes objects as latin-1, we must # therefore re-encode the final representation. literals = [None if s is None else s.encode('latin-1') for s in literals] return groups, literals def expand_template(template, match): g = match.group sep = match.string[:0] groups, literals = template literals = literals[:] try: for index, group in groups: literals[index] = s = g(group) if s is None: raise error("unmatched group") except IndexError: raise error("invalid group reference") return sep.join(literals)
Save
cmd:
run