Python解析括号内的块

Question

Python 中解析匹配括号中包含的文本块的最佳方法是什么？

"{ { a } { b } { { { c } } } }"

最初应该返回：

[ "{ a } { b } { { { c } } }" ]

将其作为输入应该返回：

[ "a", "b", "{ { c } }" ]

应该返回：

[ "{ c }" ]

[ "c" ]

[]

Answer 1

或者这个 pyparsing 版本：

>>> from pyparsing import nestedExpr
>>> txt = "{ { a } { b } { { { c } } } }"
>>>
>>> nestedExpr('{','}').parseString(txt).asList()
[[['a'], ['b'], [[['c']]]]]
>>>

Answer 2

伪代码：

For each string in the array:
    Find the first '{'. If there is none, leave that string alone.
    Init a counter to 0. 
    For each character in the string:  
        If you see a '{', increment the counter.
        If you see a '}', decrement the counter.
        If the counter reaches 0, break.
    Here, if your counter is not 0, you have invalid input (unbalanced brackets)
    If it is, then take the string from the first '{' up to the '}' that put the
     counter at 0, and that is a new element in your array.

Answer 3

我对 Python 有点陌生，所以请放轻松，但这里有一个有效的实现：

def balanced_braces(args):
    parts = []
    for arg in args:
        if '{' not in arg:
            continue
        chars = []
        n = 0
        for c in arg:
            if c == '{':
                if n > 0:
                    chars.append(c)
                n += 1
            elif c == '}':
                n -= 1
                if n > 0:
                    chars.append(c)
                elif n == 0:
                    parts.append(''.join(chars).lstrip().rstrip())
                    chars = []
            elif n > 0:
                chars.append(c)
    return parts

t1 = balanced_braces(["{{ a } { b } { { { c } } } }"]);
print t1
t2 = balanced_braces(t1)
print t2
t3 = balanced_braces(t2)
print t3
t4 = balanced_braces(t3)
print t4

输出：

['{ a } { b } { { { c } } }']
['a', 'b', '{ { c } }']
['{ c }']
['c']

Answer 4

使用 lepl 进行解析（可通过 $ easy_install lepl 安装):

from lepl import Any, Delayed, Node, Space

expr = Delayed()
expr += '{' / (Any() | expr[1:,Space()[:]]) / '}' > Node

print expr.parse("{{a}{b}{{{c}}}}")[0]

输出:

Node
 +- '{'
 +- Node
 |   +- '{'
 |   +- 'a'
 |   `- '}'
 +- Node
 |   +- '{'
 |   +- 'b'
 |   `- '}'
 +- Node
 |   +- '{'
 |   +- Node
 |   |   +- '{'
 |   |   +- Node
 |   |   |   +- '{'
 |   |   |   +- 'c'
 |   |   |   `- '}'
 |   |   `- '}'
 |   `- '}'
 `- '}'

Answer 5

更清洁的解决方案。这将返回最外层括号中包含的字符串。如果返回 None，则表示没有匹配项。

def findBrackets( aString ):
   if '{' in aString:
      match = aString.split('{',1)[1]
      open = 1
      for index in xrange(len(match)):
         if match[index] in '{}':
            open = (open + 1) if match[index] == '{' else (open - 1)
         if not open:
            return match[:index]

Answer 6

您也可以一次解析它们，尽管我发现 {a} 的意思是 "a" 而不是 ["a"] 稍微诡异的。如果我正确理解了格式：

import re
import sys


_mbrack_rb = re.compile("([^{}]*)}") # re.match doesn't have a pos parameter
def mbrack(s):
  """Parse matching brackets.

  >>> mbrack("{a}")
  'a'
  >>> mbrack("{{a}{b}}")
  ['a', 'b']
  >>> mbrack("{{a}{b}{{{c}}}}")
  ['a', 'b', [['c']]]

  >>> mbrack("a")
  Traceback (most recent call last):
  ValueError: expected left bracket
  >>> mbrack("{a}{b}")
  Traceback (most recent call last):
  ValueError: more than one root
  >>> mbrack("{a")
  Traceback (most recent call last):
  ValueError: expected value then right bracket
  >>> mbrack("{a{}}")
  Traceback (most recent call last):
  ValueError: expected value then right bracket
  >>> mbrack("{a}}")
  Traceback (most recent call last):
  ValueError: unbalanced brackets (found right bracket)
  >>> mbrack("{{a}")
  Traceback (most recent call last):
  ValueError: unbalanced brackets (not enough right brackets)
  """
  stack = [[]]
  i, end = 0, len(s)
  while i < end:
    if s[i] != "{":
      raise ValueError("expected left bracket")
    elif i != 0 and len(stack) == 1:
      raise ValueError("more than one root")
    while i < end and s[i] == "{":
      L = []
      stack[-1].append(L)
      stack.append(L)
      i += 1
    stack.pop()
    stack[-1].pop()
    m = _mbrack_rb.match(s, i)
    if m is None:
      raise ValueError("expected value then right bracket")
    stack[-1].append(m.group(1))
    i = m.end(0)
    while i < end and s[i] == "}":
      if len(stack) == 1:
        raise ValueError("unbalanced brackets (found right bracket)")
      stack.pop()
      i += 1
  if len(stack) != 1:
    raise ValueError("unbalanced brackets (not enough right brackets)")
  return stack[0][0]


def main(args):
  if args:
    print >>sys.stderr, "unexpected arguments: %r" % args
  import doctest
  r = doctest.testmod()
  print r
  return r[0]

if __name__ == "__main__":
  sys.exit(main(sys.argv[1:]))

Answer 7

如果您想使用解析器（在本例中为 lepl），但仍然想要中间结果而不是最终解析列表，那么我认为这就是您正在寻找的东西：

>>> nested = Delayed()
>>> nested += "{" + (nested[1:,...]|Any()) + "}"
>>> split = (Drop("{") & (nested[:,...]|Any()) & Drop("}"))[:].parse
>>> split("{{a}{b}{{{c}}}}")
['{a}{b}{{{c}}}']
>>> split("{a}{b}{{{c}}}")
['a', 'b', '{{c}}']
>>> split("{{c}}")
['{c}']
>>> split("{c}")
['c']

一开始可能看起来不透明，但它是确实相当简单:o)

nested 是嵌套括号匹配器的递归定义（定义中的“+”和 [...] 在匹配后将所有内容保留为单个字符串） 。然后 split 表示尽可能多地匹配由“{”...“}”（我们用“Drop”丢弃）包围的内容（“[:]”），并且包含嵌套表达式或任何字母。

最后，这是“一体式”解析器的 lepl 版本，它给出的结果格式与上面的 pyparsing 示例相同，但（我相信）对于空格在输入中的显示方式更加灵活：

>>> with Separator(~Space()[:]):
...     nested = Delayed()
...     nested += Drop("{") & (nested[1:] | Any()) & Drop("}") > list
...
>>> nested.parse("{{ a }{ b}{{{c}}}}")
[[['a'], ['b'], [[['c']]]]]

Answer 8

使用 Grako（语法编译器）：

#!/usr/bin/env python
import json
import grako # $ pip install grako

grammar_ebnf = """
    bracketed = '{' @:( { bracketed }+ | any ) '}' ;
    any = /[^{}]+?/ ;
"""
model = grako.genmodel("Bracketed", grammar_ebnf)
ast = model.parse("{ { a } { b } { { { c } } } }", "bracketed")
print(json.dumps(ast, indent=4))

输出

[
    "a", 
    "b", 
    [
        [
            "c"
        ]
    ]
]

Answer 9

这是我针对类似用例提出的解决方案。这大致基于已接受的伪代码答案。我不想为外部库添加任何依赖项：

def parse_segments(source, recurse=False):
    """
    extract any substring enclosed in parenthesis
    source should be a string
    """
    unmatched_count = 0
    start_pos = 0
    opened = False
    open_pos = 0
    cur_pos = 0

    finished = []
    segments = []

    for character in source:
        #scan for mismatched parenthesis:
        if character == '(':
            unmatched_count += 1
            if not opened:
                open_pos = cur_pos
            opened = True

        if character == ')':
            unmatched_count -= 1

        if opened and unmatched_count == 0:
            segment = source[open_pos:cur_pos+1]
            segments.append(segment)
            clean = source[start_pos:open_pos]
            if clean:
                finished.append(clean)
            opened = False
            start_pos = cur_pos+1

        cur_pos += 1

    assert unmatched_count == 0

    if start_pos != cur_pos:
        #get anything that was left over here
        finished.append(source[start_pos:cur_pos])

    #now check on recursion:
    for item in segments:
        #get rid of bounding parentheses:
        pruned = item[1:-1]
        if recurse:
            results = parse_tags(pruned, recurse)
            finished.expand(results)
        else:
            finished.append(pruned)

    return finished