是否可以用另一个正则表达式检测一个有效的正则表达式?如果是这样，请给出下面的示例代码。
当前回答
下面的例子由Paul McGuire编写，最初来自pyparsing wiki，但现在只能通过Wayback Machine获得，给出了用于解析某些正则表达式的语法，目的是返回一组匹配的字符串。因此，它拒绝那些包含无限重复项的re，如'+'和'*'。但是它应该让您了解如何构造处理re的解析器。
#
# invRegex.py
#
# Copyright 2008, Paul McGuire
#
# pyparsing script to expand a regular expression into all possible matching strings
# Supports:
# - {n} and {m,n} repetition, but not unbounded + or * repetition
# - ? optional elements
# - [] character ranges
# - () grouping
# - | alternation
#
__all__ = ["count","invert"]
from pyparsing import (Literal, oneOf, printables, ParserElement, Combine,
SkipTo, operatorPrecedence, ParseFatalException, Word, nums, opAssoc,
Suppress, ParseResults, srange)
class CharacterRangeEmitter(object):
def __init__(self,chars):
# remove duplicate chars in character range, but preserve original order
seen = set()
self.charset = "".join( seen.add(c) or c for c in chars if c not in seen )
def __str__(self):
return '['+self.charset+']'
def __repr__(self):
return '['+self.charset+']'
def makeGenerator(self):
def genChars():
for s in self.charset:
yield s
return genChars
class OptionalEmitter(object):
def __init__(self,expr):
self.expr = expr
def makeGenerator(self):
def optionalGen():
yield ""
for s in self.expr.makeGenerator()():
yield s
return optionalGen
class DotEmitter(object):
def makeGenerator(self):
def dotGen():
for c in printables:
yield c
return dotGen
class GroupEmitter(object):
def __init__(self,exprs):
self.exprs = ParseResults(exprs)
def makeGenerator(self):
def groupGen():
def recurseList(elist):
if len(elist)==1:
for s in elist[0].makeGenerator()():
yield s
else:
for s in elist[0].makeGenerator()():
for s2 in recurseList(elist[1:]):
yield s + s2
if self.exprs:
for s in recurseList(self.exprs):
yield s
return groupGen
class AlternativeEmitter(object):
def __init__(self,exprs):
self.exprs = exprs
def makeGenerator(self):
def altGen():
for e in self.exprs:
for s in e.makeGenerator()():
yield s
return altGen
class LiteralEmitter(object):
def __init__(self,lit):
self.lit = lit
def __str__(self):
return "Lit:"+self.lit
def __repr__(self):
return "Lit:"+self.lit
def makeGenerator(self):
def litGen():
yield self.lit
return litGen
def handleRange(toks):
return CharacterRangeEmitter(srange(toks[0]))
def handleRepetition(toks):
toks=toks[0]
if toks[1] in "*+":
raise ParseFatalException("",0,"unbounded repetition operators not supported")
if toks[1] == "?":
return OptionalEmitter(toks[0])
if "count" in toks:
return GroupEmitter([toks[0]] * int(toks.count))
if "minCount" in toks:
mincount = int(toks.minCount)
maxcount = int(toks.maxCount)
optcount = maxcount - mincount
if optcount:
opt = OptionalEmitter(toks[0])
for i in range(1,optcount):
opt = OptionalEmitter(GroupEmitter([toks[0],opt]))
return GroupEmitter([toks[0]] * mincount + [opt])
else:
return [toks[0]] * mincount
def handleLiteral(toks):
lit = ""
for t in toks:
if t[0] == "\\":
if t[1] == "t":
lit += '\t'
else:
lit += t[1]
else:
lit += t
return LiteralEmitter(lit)
def handleMacro(toks):
macroChar = toks[0][1]
if macroChar == "d":
return CharacterRangeEmitter("0123456789")
elif macroChar == "w":
return CharacterRangeEmitter(srange("[A-Za-z0-9_]"))
elif macroChar == "s":
return LiteralEmitter(" ")
else:
raise ParseFatalException("",0,"unsupported macro character (" + macroChar + ")")
def handleSequence(toks):
return GroupEmitter(toks[0])
def handleDot():
return CharacterRangeEmitter(printables)
def handleAlternative(toks):
return AlternativeEmitter(toks[0])
_parser = None
def parser():
global _parser
if _parser is None:
ParserElement.setDefaultWhitespaceChars("")
lbrack,rbrack,lbrace,rbrace,lparen,rparen = map(Literal,"[]{}()")
reMacro = Combine("\\" + oneOf(list("dws")))
escapedChar = ~reMacro + Combine("\\" + oneOf(list(printables)))
reLiteralChar = "".join(c for c in printables if c not in r"\[]{}().*?+|") + " \t"
reRange = Combine(lbrack + SkipTo(rbrack,ignore=escapedChar) + rbrack)
reLiteral = ( escapedChar | oneOf(list(reLiteralChar)) )
reDot = Literal(".")
repetition = (
( lbrace + Word(nums).setResultsName("count") + rbrace ) |
( lbrace + Word(nums).setResultsName("minCount")+","+ Word(nums).setResultsName("maxCount") + rbrace ) |
oneOf(list("*+?"))
)
reRange.setParseAction(handleRange)
reLiteral.setParseAction(handleLiteral)
reMacro.setParseAction(handleMacro)
reDot.setParseAction(handleDot)
reTerm = ( reLiteral | reRange | reMacro | reDot )
reExpr = operatorPrecedence( reTerm,
[
(repetition, 1, opAssoc.LEFT, handleRepetition),
(None, 2, opAssoc.LEFT, handleSequence),
(Suppress('|'), 2, opAssoc.LEFT, handleAlternative),
]
)
_parser = reExpr
return _parser
def count(gen):
"""Simple function to count the number of elements returned by a generator."""
i = 0
for s in gen:
i += 1
return i
def invert(regex):
"""Call this routine as a generator to return all the strings that
match the input regular expression.
for s in invert("[A-Z]{3}\d{3}"):
print s
"""
invReGenerator = GroupEmitter(parser().parseString(regex)).makeGenerator()
return invReGenerator()
def main():
tests = r"""
[A-EA]
[A-D]*
[A-D]{3}
X[A-C]{3}Y
X[A-C]{3}\(
X\d
foobar\d\d
foobar{2}
foobar{2,9}
fooba[rz]{2}
(foobar){2}
([01]\d)|(2[0-5])
([01]\d\d)|(2[0-4]\d)|(25[0-5])
[A-C]{1,2}
[A-C]{0,3}
[A-C]\s[A-C]\s[A-C]
[A-C]\s?[A-C][A-C]
[A-C]\s([A-C][A-C])
[A-C]\s([A-C][A-C])?
[A-C]{2}\d{2}
@|TH[12]
@(@|TH[12])?
@(@|TH[12]|AL[12]|SP[123]|TB(1[0-9]?|20?|[3-9]))?
@(@|TH[12]|AL[12]|SP[123]|TB(1[0-9]?|20?|[3-9])|OH(1[0-9]?|2[0-9]?|30?|[4-9]))?
(([ECMP]|HA|AK)[SD]|HS)T
[A-CV]{2}
A[cglmrstu]|B[aehikr]?|C[adeflmorsu]?|D[bsy]|E[rsu]|F[emr]?|G[ade]|H[efgos]?|I[nr]?|Kr?|L[airu]|M[dgnot]|N[abdeiop]?|Os?|P[abdmortu]?|R[abefghnu]|S[bcegimnr]?|T[abcehilm]|Uu[bhopqst]|U|V|W|Xe|Yb?|Z[nr]
(a|b)|(x|y)
(a|b) (x|y)
""".split('\n')
for t in tests:
t = t.strip()
if not t: continue
print '-'*50
print t
try:
print count(invert(t))
for s in invert(t):
print s
except ParseFatalException,pfe:
print pfe.msg
print
continue
print
if __name__ == "__main__":
main()
其他回答
下面的例子由Paul McGuire编写，最初来自pyparsing wiki，但现在只能通过Wayback Machine获得，给出了用于解析某些正则表达式的语法，目的是返回一组匹配的字符串。因此，它拒绝那些包含无限重复项的re，如'+'和'*'。但是它应该让您了解如何构造处理re的解析器。
#
# invRegex.py
#
# Copyright 2008, Paul McGuire
#
# pyparsing script to expand a regular expression into all possible matching strings
# Supports:
# - {n} and {m,n} repetition, but not unbounded + or * repetition
# - ? optional elements
# - [] character ranges
# - () grouping
# - | alternation
#
__all__ = ["count","invert"]
from pyparsing import (Literal, oneOf, printables, ParserElement, Combine,
SkipTo, operatorPrecedence, ParseFatalException, Word, nums, opAssoc,
Suppress, ParseResults, srange)
class CharacterRangeEmitter(object):
def __init__(self,chars):
# remove duplicate chars in character range, but preserve original order
seen = set()
self.charset = "".join( seen.add(c) or c for c in chars if c not in seen )
def __str__(self):
return '['+self.charset+']'
def __repr__(self):
return '['+self.charset+']'
def makeGenerator(self):
def genChars():
for s in self.charset:
yield s
return genChars
class OptionalEmitter(object):
def __init__(self,expr):
self.expr = expr
def makeGenerator(self):
def optionalGen():
yield ""
for s in self.expr.makeGenerator()():
yield s
return optionalGen
class DotEmitter(object):
def makeGenerator(self):
def dotGen():
for c in printables:
yield c
return dotGen
class GroupEmitter(object):
def __init__(self,exprs):
self.exprs = ParseResults(exprs)
def makeGenerator(self):
def groupGen():
def recurseList(elist):
if len(elist)==1:
for s in elist[0].makeGenerator()():
yield s
else:
for s in elist[0].makeGenerator()():
for s2 in recurseList(elist[1:]):
yield s + s2
if self.exprs:
for s in recurseList(self.exprs):
yield s
return groupGen
class AlternativeEmitter(object):
def __init__(self,exprs):
self.exprs = exprs
def makeGenerator(self):
def altGen():
for e in self.exprs:
for s in e.makeGenerator()():
yield s
return altGen
class LiteralEmitter(object):
def __init__(self,lit):
self.lit = lit
def __str__(self):
return "Lit:"+self.lit
def __repr__(self):
return "Lit:"+self.lit
def makeGenerator(self):
def litGen():
yield self.lit
return litGen
def handleRange(toks):
return CharacterRangeEmitter(srange(toks[0]))
def handleRepetition(toks):
toks=toks[0]
if toks[1] in "*+":
raise ParseFatalException("",0,"unbounded repetition operators not supported")
if toks[1] == "?":
return OptionalEmitter(toks[0])
if "count" in toks:
return GroupEmitter([toks[0]] * int(toks.count))
if "minCount" in toks:
mincount = int(toks.minCount)
maxcount = int(toks.maxCount)
optcount = maxcount - mincount
if optcount:
opt = OptionalEmitter(toks[0])
for i in range(1,optcount):
opt = OptionalEmitter(GroupEmitter([toks[0],opt]))
return GroupEmitter([toks[0]] * mincount + [opt])
else:
return [toks[0]] * mincount
def handleLiteral(toks):
lit = ""
for t in toks:
if t[0] == "\\":
if t[1] == "t":
lit += '\t'
else:
lit += t[1]
else:
lit += t
return LiteralEmitter(lit)
def handleMacro(toks):
macroChar = toks[0][1]
if macroChar == "d":
return CharacterRangeEmitter("0123456789")
elif macroChar == "w":
return CharacterRangeEmitter(srange("[A-Za-z0-9_]"))
elif macroChar == "s":
return LiteralEmitter(" ")
else:
raise ParseFatalException("",0,"unsupported macro character (" + macroChar + ")")
def handleSequence(toks):
return GroupEmitter(toks[0])
def handleDot():
return CharacterRangeEmitter(printables)
def handleAlternative(toks):
return AlternativeEmitter(toks[0])
_parser = None
def parser():
global _parser
if _parser is None:
ParserElement.setDefaultWhitespaceChars("")
lbrack,rbrack,lbrace,rbrace,lparen,rparen = map(Literal,"[]{}()")
reMacro = Combine("\\" + oneOf(list("dws")))
escapedChar = ~reMacro + Combine("\\" + oneOf(list(printables)))
reLiteralChar = "".join(c for c in printables if c not in r"\[]{}().*?+|") + " \t"
reRange = Combine(lbrack + SkipTo(rbrack,ignore=escapedChar) + rbrack)
reLiteral = ( escapedChar | oneOf(list(reLiteralChar)) )
reDot = Literal(".")
repetition = (
( lbrace + Word(nums).setResultsName("count") + rbrace ) |
( lbrace + Word(nums).setResultsName("minCount")+","+ Word(nums).setResultsName("maxCount") + rbrace ) |
oneOf(list("*+?"))
)
reRange.setParseAction(handleRange)
reLiteral.setParseAction(handleLiteral)
reMacro.setParseAction(handleMacro)
reDot.setParseAction(handleDot)
reTerm = ( reLiteral | reRange | reMacro | reDot )
reExpr = operatorPrecedence( reTerm,
[
(repetition, 1, opAssoc.LEFT, handleRepetition),
(None, 2, opAssoc.LEFT, handleSequence),
(Suppress('|'), 2, opAssoc.LEFT, handleAlternative),
]
)
_parser = reExpr
return _parser
def count(gen):
"""Simple function to count the number of elements returned by a generator."""
i = 0
for s in gen:
i += 1
return i
def invert(regex):
"""Call this routine as a generator to return all the strings that
match the input regular expression.
for s in invert("[A-Z]{3}\d{3}"):
print s
"""
invReGenerator = GroupEmitter(parser().parseString(regex)).makeGenerator()
return invReGenerator()
def main():
tests = r"""
[A-EA]
[A-D]*
[A-D]{3}
X[A-C]{3}Y
X[A-C]{3}\(
X\d
foobar\d\d
foobar{2}
foobar{2,9}
fooba[rz]{2}
(foobar){2}
([01]\d)|(2[0-5])
([01]\d\d)|(2[0-4]\d)|(25[0-5])
[A-C]{1,2}
[A-C]{0,3}
[A-C]\s[A-C]\s[A-C]
[A-C]\s?[A-C][A-C]
[A-C]\s([A-C][A-C])
[A-C]\s([A-C][A-C])?
[A-C]{2}\d{2}
@|TH[12]
@(@|TH[12])?
@(@|TH[12]|AL[12]|SP[123]|TB(1[0-9]?|20?|[3-9]))?
@(@|TH[12]|AL[12]|SP[123]|TB(1[0-9]?|20?|[3-9])|OH(1[0-9]?|2[0-9]?|30?|[4-9]))?
(([ECMP]|HA|AK)[SD]|HS)T
[A-CV]{2}
A[cglmrstu]|B[aehikr]?|C[adeflmorsu]?|D[bsy]|E[rsu]|F[emr]?|G[ade]|H[efgos]?|I[nr]?|Kr?|L[airu]|M[dgnot]|N[abdeiop]?|Os?|P[abdmortu]?|R[abefghnu]|S[bcegimnr]?|T[abcehilm]|Uu[bhopqst]|U|V|W|Xe|Yb?|Z[nr]
(a|b)|(x|y)
(a|b) (x|y)
""".split('\n')
for t in tests:
t = t.strip()
if not t: continue
print '-'*50
print t
try:
print count(invert(t))
for s in invert(t):
print s
except ParseFatalException,pfe:
print pfe.msg
print
continue
print
if __name__ == "__main__":
main()
不，如果你使用标准正则表达式。
原因是您不能满足常规语言的抽运引理。抽吸引理指出，属于语言“L”的字符串是正则的，如果存在一个数字“N”，使得将字符串分为三个子字符串x, y, z，使得|x|>=1 && |xy|<=N，你可以重复y多次，而整个字符串仍然属于L。
抽运引理的一个结果是，你不能有A ^Nb^Mc^N这样的正则字符串，也就是说，两个相同长度的子字符串被另一个字符串隔开。无论你以何种方式将这些字符串分割成x、y和z，你都不能在不获得“a”和“c”数量不同的字符串的情况下“抽取”y，从而保留原始语言。例如，正则表达式中的圆括号就是这种情况。
好问题。
真正的规则语言不能任意地决定嵌套良好的圆括号。如果你的字母表中包含'('和')'，目标是判断这些字符串是否有格式良好的匹配圆括号。因为这是正则表达式的必要要求，所以答案是否定的。
但是，如果您放宽要求并添加递归，您可能就可以做到这一点。原因是递归可以作为一个堆栈，让您通过推入这个堆栈来“计算”当前嵌套深度。
Russ Cox写了“正则表达式匹配可以简单而快速”，这是一篇关于正则表达式引擎实现的精彩论文。
/
^ # start of string
( # first group start
(?:
(?:[^?+*{}()[\]\\|]+ # literals and ^, $
| \\. # escaped characters
| \[ (?: \^?\\. | \^[^\\] | [^\\^] ) # character classes
(?: [^\]\\]+ | \\. )* \]
| \( (?:\?[:=!]|\?<[=!]|\?>)? (?1)?? \) # parenthesis, with recursive content
| \(\? (?:R|[+-]?\d+) \) # recursive matching
)
(?: (?:[?+*]|\{\d+(?:,\d*)?\}) [?+]? )? # quantifiers
| \| # alternative
)* # repeat content
) # end first group
$ # end of string
/
这是一个递归正则表达式，许多正则表达式引擎都不支持。基于PCRE的程序应该支持它。
没有空格和注释:
/^((?:(?:[^?+*{}()[\]\\|]+|\\.|\[(?:\^?\\.|\^[^\\]|[^\\^])(?:[^\]\\]+|\\.)*\]|\((?:\?[:=!]|\?<[=!]|\?>)?(?1)??\)|\(\?(?:R|[+-]?\d+)\))(?:(?:[?+*]|\{\d+(?:,\d*)?\})[?+]?)?|\|)*)$/
. net不直接支持递归。(?1)和(?R)结构。)递归必须转换为计算平衡的组:
^ # start of string
(?:
(?: [^?+*{}()[\]\\|]+ # literals and ^, $
| \\. # escaped characters
| \[ (?: \^?\\. | \^[^\\] | [^\\^] ) # character classes
(?: [^\]\\]+ | \\. )* \]
| \( (?:\?[:=!]
| \?<[=!]
| \?>
| \?<[^\W\d]\w*>
| \?'[^\W\d]\w*'
)? # opening of group
(?<N>) # increment counter
| \) # closing of group
(?<-N>) # decrement counter
)
(?: (?:[?+*]|\{\d+(?:,\d*)?\}) [?+]? )? # quantifiers
| \| # alternative
)* # repeat content
$ # end of string
(?(N)(?!)) # fail if counter is non-zero.
压实:
^(?:(?:[^?+*{}()[\]\\|]+|\\.|\[(?:\^?\\.|\^[^\\]|[^\\^])(?:[^\]\\]+|\\.)*\]|\((?:\?[:=!]|\?<[=!]|\?>|\?<[^\W\d]\w*>|\?'[^\W\d]\w*')?(?<N>)|\)(?<-N>))(?:(?:[?+*]|\{\d+(?:,\d*)?\})[?+]?)?|\|)*$(?(N)(?!))
评论如下:
这将验证替换和转换吗?
它将只验证替换和转换的正则表达式部分。s / < >这一部分/…/
理论上不可能将所有有效的正则表达式语法与一个正则表达式匹配。
如果正则表达式引擎支持递归，比如PCRE，这是可能的，但它不能再被真正地称为正则表达式了。
实际上，“递归正则表达式”不是正则表达式。但这是一个经常被接受的正则表达式引擎的扩展…具有讽刺意味的是，这个扩展的正则表达式并不匹配扩展的正则表达式。
“在理论上，理论和实践是一样的。但实际上并非如此。”几乎所有了解正则表达式的人都知道正则表达式不支持递归。但是PCRE和大多数其他实现支持的不仅仅是基本的正则表达式。
在grep命令中使用这个shell脚本，它向我显示了一些错误。grep:{}的无效内容。我正在制作一个脚本，可以grep代码库找到所有包含正则表达式的文件
这个模式利用了一个名为递归正则表达式的扩展。正则表达式的POSIX风格不支持这一点。您可以尝试使用-P开关来启用PCRE正则表达式风格。
Regex本身“不是正则语言，因此不能用正则表达式来解析……”
这对于经典正则表达式是正确的。一些现代实现允许递归，这使得它成为一种上下文自由语言，尽管对于这个任务来说有点冗长。
我看到你匹配[]()/\。和其他特殊的正则表达式字符。哪里允许非特殊字符?它似乎可以匹配^(?:[\.]+)$，但不能匹配^abcdefg$。这是一个有效的正则表达式。
[^?+*{}()[\]\\|]将匹配任何单个字符，而不是任何其他结构的一部分。这包括文字(a - z)和某些特殊字符(^，$，.)。
你可以将regex提交给preg_match，如果regex无效，preg_match将返回false。不要忘记使用@来抑制错误消息:
@preg_match($regexToTest, '');
如果正则表达式为//，则返回1。 如果正则表达式没问题，将返回0。 否则将返回false。
推荐文章
- 使用String.split()和多个分隔符
- 从数字中移除无关紧要的尾随零?
- 最终的邮政编码和邮政正则表达式是什么?
- 删除多个空白空间
- 正则表达式不是运算符
- 如何通过正则表达式过滤熊猫行
- 我如何在JavaScript中使用unicode感知的正则表达式?
- RE错误:在Mac OS X上的非法字节序列
- Regex验证日期格式dd/mm/YYYY, dd-mm-YYYY, dd.mm。YYYY, dd mmm, dd-mmm-YYYY, dd/mmm/YYYY, dd.mmm.YYYY与闰年支持
- jQuery验证:如何为正则表达式验证添加规则?
- 正则表达式在Javascript中获得括号之间的字符串
- 如何检查有效的电子邮件地址?
- Regex邮件验证
- 如何在bash脚本中使用正则表达式否定测试?
- 如何提取位于圆括号(圆括号)之间的文本?
