使用inverse_regex:
"""
http://www.mail-archive.com/[email protected]/msg125198.html
"""
import itertools as IT
import sre_constants as sc
import sre_parse
import string
# Generate strings that match a given regex
category_chars = {
sc.CATEGORY_DIGIT : string.digits,
sc.CATEGORY_SPACE : string.whitespace,
sc.CATEGORY_WORD : string.digits + string.letters + '_'
}
def unique_extend(res_list, list):
for item in list:
if item not in res_list:
res_list.append(item)
def handle_any(val):
"""
This is different from normal regexp matching. It only matches
printable ASCII characters.
"""
return string.printable
def handle_branch((tok, val)):
all_opts = []
for toks in val:
opts = permute_toks(toks)
unique_extend(all_opts, opts)
return all_opts
def handle_category(val):
return list(category_chars[val])
def handle_in(val):
out = []
for tok, val in val:
out += handle_tok(tok, val)
return out
def handle_literal(val):
return [chr(val)]
def handle_max_repeat((min, max, val)):
"""
Handle a repeat token such as {x,y} or ?.
"""
subtok, subval = val[0]
if max > 5000:
# max is the number of cartesian join operations needed to be
# carried out. More than 5000 consumes way to much memory.
# raise ValueError("To many repetitions requested (%d)" % max)
max = 5000
optlist = handle_tok(subtok, subval)
iterlist = []
for x in range(min, max + 1):
joined = IT.product(*[optlist]*x)
iterlist.append(joined)
return (''.join(it) for it in IT.chain(*iterlist))
def handle_range(val):
lo, hi = val
return (chr(x) for x in range(lo, hi + 1))
def handle_subpattern(val):
return list(permute_toks(val[1]))
def handle_tok(tok, val):
"""
Returns a list of strings of possible permutations for this regexp
token.
"""
handlers = {
sc.ANY : handle_any,
sc.BRANCH : handle_branch,
sc.CATEGORY : handle_category,
sc.LITERAL : handle_literal,
sc.IN : handle_in,
sc.MAX_REPEAT : handle_max_repeat,
sc.RANGE : handle_range,
sc.SUBPATTERN : handle_subpattern}
try:
return handlers[tok](val)
except KeyError, e:
fmt = "Unsupported regular expression construct: %s"
raise ValueError(fmt % tok)
def permute_toks(toks):
"""
Returns a generator of strings of possible permutations for this
regexp token list.
"""
lists = [handle_tok(tok, val) for tok, val in toks]
return (''.join(it) for it in IT.product(*lists))
########## PUBLIC API ####################
def ipermute(p):
return permute_toks(sre_parse.parse(p))
您可以應用給rex
和data
,然後替換使用inverse_regex.ipermute
生成匹配原始正則表達式的字符串:
import re
import itertools as IT
import inverse_regex as ire
rex = r"(?:at (?P<hour>[0-2][0-9])|today) send email to (?P<name>\w*):? (?P<message>.+)"
match = re.match(rex, "at 10 send email to bob: hi bob!")
data = match.groupdict()
del match
new_regex = re.sub(r'[(][?]P<([^>]+)>[^)]*[)]', lambda m: data.get(m.group(1)), rex)
for s in IT.islice(ire.ipermute(new_regex), 10):
print(s)
產生
today send email to bob hi bob!
today send email to bob: hi bob!
at 10 send email to bob hi bob!
at 10 send email to bob: hi bob!
注:我修改了原來inverse_regex到不引發ValueError時,正則表達式中包含*
秒。相反,*
更改爲有效像{,5000}
,所以你至少會得到一些排列。
它真的是無限的嗎?除了可選的':'之外,其他的東西都是固定的? –
使用'match.group()'(a.k.a.'match.group(0)'),沒有。您丟棄了信息(特別是原始字符串是否包含冒號),因此無法從捕獲的組的內容中明確重構原始字符串。唯一的方法是爲冒號添加一個捕獲組,然後可以使用它來確定輸入文本是否包含冒號。 – Mac
我給了一個不正確的答案...的一點是,正則表達式失去一些數據,因此,如果你想恢復需要捕獲整個數據(在不同的令牌)輸入 – Emilien