Question

我有像这样的维基文字

data = """
{{hello}}

{{hello world}}
{{hello much { }}
{{a {{b}}}}

{{a

td {

}
{{inner}}
}}

“”“

我想在其中提取宏 macro是{{和}}

之间的文字

所以我尝试使用nestedExpr

from pyparsing import *
import pprint

def getMacroCandidates(txt):

    candidates = []

    def nestedExpr(opener="(", closer=")", content=None, ignoreExpr=quotedString.copy()):
        if opener == closer:
            raise ValueError("opening and closing strings cannot be the same")
        if content is None:
            if isinstance(opener,str) and isinstance(closer,str):
                if ignoreExpr is not None:
                    content = (Combine(OneOrMore(~ignoreExpr + 
                                    ~Literal(opener) + ~Literal(closer) +
                                    CharsNotIn(ParserElement.DEFAULT_WHITE_CHARS,exact=1))
                                ).setParseAction(lambda t:t[0]))
        ret = Forward()
        ret <<= Group( opener + ZeroOrMore( ignoreExpr | ret | content ) + closer )

        ret.setName('nested %s%s expression' % (opener,closer))
        return ret

    # use {}'s for nested lists
    macro = nestedExpr("{{", "}}")
    # print(( (nestedItems+stringEnd).parseString(data).asList() ))
    for toks, preloc, nextloc in macro.scanString(data):
        print(toks)
    return candidates

data = """
{{hello}}

{{hello world}}
{{hello much { }}
{{a {{b}}}}

{{a

td {

}
{{inner}}
}}
"""

getMacroCandidates(data)

这让我删除了令牌和空格

[['{{', 'hello', '}}']]
[['{{', 'hello', 'world', '}}']]
[['{{', 'hello', 'much', '{', '}}']]
[['{{', 'a', ['{{', 'b', '}}'], '}}']]
[['{{', 'a', 'td', '{', '}', ['{{', 'inner', '}}'], '}}']]

提前谢谢

Answer 1

你可以替换

data = """
{{hello}}

{{hello world}}
{{hello much { }}
{{a {{b}}}}

{{a

td {

}
{{inner}}
}}
"""

import shlex
data1= data.replace("{{",'"')
data2 = data1.replace("}}",'"')
data3=   data2.replace("}"," ")
data4=   data3.replace("{"," ")
data5= ' '.join(data4.split())
print(shlex.split(data5.replace("\n"," ")))

输出

这将返回所有带有大括号和空格的标记，并删除额外的行空间

 ['hello', 'hello world', 'hello much ', 'a b', 'a td inner ']

PS：这可以用于单个表达式，多个表达式用于可读性

如何在nestedExpr pyparsing中留下空格

1 个答案: