在Python中，用空格分隔字符串——保留带引号的子字符串

我有一个这样的字符串:

this is "a test"

我试图在Python中写一些东西，通过空格分割它，同时忽略引号中的空格。我想要的结果是:

['this', 'is', 'a test']

PS，我知道你会问“如果引号中有引号会发生什么，在我的应用程序中，这永远不会发生。

当前回答

被接受的shlex方法的主要问题是它不会忽略带引号的子字符串外的转义字符，并且在某些极端情况下会给出稍微出乎意料的结果。

我有下面的用例，其中我需要一个split函数来分割输入字符串，以便保留单引号或双引号子字符串，并能够在这样的子字符串中转义引号。未加引号的字符串中的引号不应与任何其他字符区别对待。一些带有预期输出的示例测试用例:

 input string        | expected output
===============================================
 'abc def'           | ['abc', 'def']
 "abc \\s def"       | ['abc', '\\s', 'def']
 '"abc def" ghi'     | ['abc def', 'ghi']
 "'abc def' ghi"     | ['abc def', 'ghi']
 '"abc \\" def" ghi' | ['abc " def', 'ghi']
 "'abc \\' def' ghi" | ["abc ' def", 'ghi']
 "'abc \\s def' ghi" | ['abc \\s def', 'ghi']
 '"abc \\s def" ghi' | ['abc \\s def', 'ghi']
 '"" test'           | ['', 'test']
 "'' test"           | ['', 'test']
 "abc'def"           | ["abc'def"]
 "abc'def'"          | ["abc'def'"]
 "abc'def' ghi"      | ["abc'def'", 'ghi']
 "abc'def'ghi"       | ["abc'def'ghi"]
 'abc"def'           | ['abc"def']
 'abc"def"'          | ['abc"def"']
 'abc"def" ghi'      | ['abc"def"', 'ghi']
 'abc"def"ghi'       | ['abc"def"ghi']
 "r'AA' r'.*_xyz$'"  | ["r'AA'", "r'.*_xyz$'"]
 'abc"def ghi"'      | ['abc"def ghi"']
 'abc"def ghi""jkl"' | ['abc"def ghi""jkl"']
 'a"b c"d"e"f"g h"'  | ['a"b c"d"e"f"g h"']
 'c="ls /" type key' | ['c="ls /"', 'type', 'key']
 "abc'def ghi'"      | ["abc'def ghi'"]
 "c='ls /' type key" | ["c='ls /'", 'type', 'key']

我最终使用以下函数来分割字符串，以便所有输入字符串的预期输出结果:

import re

def quoted_split(s):
    def strip_quotes(s):
        if s and (s[0] == '"' or s[0] == "'") and s[0] == s[-1]:
            return s[1:-1]
        return s
    return [strip_quotes(p).replace('\\"', '"').replace("\\'", "'") \
            for p in re.findall(r'(?:[^"\s]*"(?:\\.|[^"])*"[^"\s]*)+|(?:[^\'\s]*\'(?:\\.|[^\'])*\'[^\'\s]*)+|[^\s]+', s)]

这可不漂亮;但它确实有效。下面的测试应用程序检查其他方法(目前是shlex和csv)和自定义分割实现的结果:

#!/bin/python2.7

import csv
import re
import shlex

from timeit import timeit

def test_case(fn, s, expected):
    try:
        if fn(s) == expected:
            print '[ OK ] %s -> %s' % (s, fn(s))
        else:
            print '[FAIL] %s -> %s' % (s, fn(s))
    except Exception as e:
        print '[FAIL] %s -> exception: %s' % (s, e)

def test_case_no_output(fn, s, expected):
    try:
        fn(s)
    except:
        pass

def test_split(fn, test_case_fn=test_case):
    test_case_fn(fn, 'abc def', ['abc', 'def'])
    test_case_fn(fn, "abc \\s def", ['abc', '\\s', 'def'])
    test_case_fn(fn, '"abc def" ghi', ['abc def', 'ghi'])
    test_case_fn(fn, "'abc def' ghi", ['abc def', 'ghi'])
    test_case_fn(fn, '"abc \\" def" ghi', ['abc " def', 'ghi'])
    test_case_fn(fn, "'abc \\' def' ghi", ["abc ' def", 'ghi'])
    test_case_fn(fn, "'abc \\s def' ghi", ['abc \\s def', 'ghi'])
    test_case_fn(fn, '"abc \\s def" ghi', ['abc \\s def', 'ghi'])
    test_case_fn(fn, '"" test', ['', 'test'])
    test_case_fn(fn, "'' test", ['', 'test'])
    test_case_fn(fn, "abc'def", ["abc'def"])
    test_case_fn(fn, "abc'def'", ["abc'def'"])
    test_case_fn(fn, "abc'def' ghi", ["abc'def'", 'ghi'])
    test_case_fn(fn, "abc'def'ghi", ["abc'def'ghi"])
    test_case_fn(fn, 'abc"def', ['abc"def'])
    test_case_fn(fn, 'abc"def"', ['abc"def"'])
    test_case_fn(fn, 'abc"def" ghi', ['abc"def"', 'ghi'])
    test_case_fn(fn, 'abc"def"ghi', ['abc"def"ghi'])
    test_case_fn(fn, "r'AA' r'.*_xyz$'", ["r'AA'", "r'.*_xyz$'"])
    test_case_fn(fn, 'abc"def ghi"', ['abc"def ghi"'])
    test_case_fn(fn, 'abc"def ghi""jkl"', ['abc"def ghi""jkl"'])
    test_case_fn(fn, 'a"b c"d"e"f"g h"', ['a"b c"d"e"f"g h"'])
    test_case_fn(fn, 'c="ls /" type key', ['c="ls /"', 'type', 'key'])
    test_case_fn(fn, "abc'def ghi'", ["abc'def ghi'"])
    test_case_fn(fn, "c='ls /' type key", ["c='ls /'", 'type', 'key'])

def csv_split(s):
    return list(csv.reader([s], delimiter=' '))[0]

def re_split(s):
    def strip_quotes(s):
        if s and (s[0] == '"' or s[0] == "'") and s[0] == s[-1]:
            return s[1:-1]
        return s
    return [strip_quotes(p).replace('\\"', '"').replace("\\'", "'") for p in re.findall(r'(?:[^"\s]*"(?:\\.|[^"])*"[^"\s]*)+|(?:[^\'\s]*\'(?:\\.|[^\'])*\'[^\'\s]*)+|[^\s]+', s)]

if __name__ == '__main__':
    print 'shlex\n'
    test_split(shlex.split)
    print

    print 'csv\n'
    test_split(csv_split)
    print

    print 're\n'
    test_split(re_split)
    print

    iterations = 100
    setup = 'from __main__ import test_split, test_case_no_output, csv_split, re_split\nimport shlex, re'
    def benchmark(method, code):
        print '%s: %.3fms per iteration' % (method, (1000 * timeit(code, setup=setup, number=iterations) / iterations))
    benchmark('shlex', 'test_split(shlex.split, test_case_no_output)')
    benchmark('csv', 'test_split(csv_split, test_case_no_output)')
    benchmark('re', 'test_split(re_split, test_case_no_output)')

输出:

shlex

[ OK ] abc def -> ['abc', 'def']
[FAIL] abc \s def -> ['abc', 's', 'def']
[ OK ] "abc def" ghi -> ['abc def', 'ghi']
[ OK ] 'abc def' ghi -> ['abc def', 'ghi']
[ OK ] "abc \" def" ghi -> ['abc " def', 'ghi']
[FAIL] 'abc \' def' ghi -> exception: No closing quotation
[ OK ] 'abc \s def' ghi -> ['abc \\s def', 'ghi']
[ OK ] "abc \s def" ghi -> ['abc \\s def', 'ghi']
[ OK ] "" test -> ['', 'test']
[ OK ] '' test -> ['', 'test']
[FAIL] abc'def -> exception: No closing quotation
[FAIL] abc'def' -> ['abcdef']
[FAIL] abc'def' ghi -> ['abcdef', 'ghi']
[FAIL] abc'def'ghi -> ['abcdefghi']
[FAIL] abc"def -> exception: No closing quotation
[FAIL] abc"def" -> ['abcdef']
[FAIL] abc"def" ghi -> ['abcdef', 'ghi']
[FAIL] abc"def"ghi -> ['abcdefghi']
[FAIL] r'AA' r'.*_xyz$' -> ['rAA', 'r.*_xyz$']
[FAIL] abc"def ghi" -> ['abcdef ghi']
[FAIL] abc"def ghi""jkl" -> ['abcdef ghijkl']
[FAIL] a"b c"d"e"f"g h" -> ['ab cdefg h']
[FAIL] c="ls /" type key -> ['c=ls /', 'type', 'key']
[FAIL] abc'def ghi' -> ['abcdef ghi']
[FAIL] c='ls /' type key -> ['c=ls /', 'type', 'key']

csv

[ OK ] abc def -> ['abc', 'def']
[ OK ] abc \s def -> ['abc', '\\s', 'def']
[ OK ] "abc def" ghi -> ['abc def', 'ghi']
[FAIL] 'abc def' ghi -> ["'abc", "def'", 'ghi']
[FAIL] "abc \" def" ghi -> ['abc \\', 'def"', 'ghi']
[FAIL] 'abc \' def' ghi -> ["'abc", "\\'", "def'", 'ghi']
[FAIL] 'abc \s def' ghi -> ["'abc", '\\s', "def'", 'ghi']
[ OK ] "abc \s def" ghi -> ['abc \\s def', 'ghi']
[ OK ] "" test -> ['', 'test']
[FAIL] '' test -> ["''", 'test']
[ OK ] abc'def -> ["abc'def"]
[ OK ] abc'def' -> ["abc'def'"]
[ OK ] abc'def' ghi -> ["abc'def'", 'ghi']
[ OK ] abc'def'ghi -> ["abc'def'ghi"]
[ OK ] abc"def -> ['abc"def']
[ OK ] abc"def" -> ['abc"def"']
[ OK ] abc"def" ghi -> ['abc"def"', 'ghi']
[ OK ] abc"def"ghi -> ['abc"def"ghi']
[ OK ] r'AA' r'.*_xyz$' -> ["r'AA'", "r'.*_xyz$'"]
[FAIL] abc"def ghi" -> ['abc"def', 'ghi"']
[FAIL] abc"def ghi""jkl" -> ['abc"def', 'ghi""jkl"']
[FAIL] a"b c"d"e"f"g h" -> ['a"b', 'c"d"e"f"g', 'h"']
[FAIL] c="ls /" type key -> ['c="ls', '/"', 'type', 'key']
[FAIL] abc'def ghi' -> ["abc'def", "ghi'"]
[FAIL] c='ls /' type key -> ["c='ls", "/'", 'type', 'key']

re

[ OK ] abc def -> ['abc', 'def']
[ OK ] abc \s def -> ['abc', '\\s', 'def']
[ OK ] "abc def" ghi -> ['abc def', 'ghi']
[ OK ] 'abc def' ghi -> ['abc def', 'ghi']
[ OK ] "abc \" def" ghi -> ['abc " def', 'ghi']
[ OK ] 'abc \' def' ghi -> ["abc ' def", 'ghi']
[ OK ] 'abc \s def' ghi -> ['abc \\s def', 'ghi']
[ OK ] "abc \s def" ghi -> ['abc \\s def', 'ghi']
[ OK ] "" test -> ['', 'test']
[ OK ] '' test -> ['', 'test']
[ OK ] abc'def -> ["abc'def"]
[ OK ] abc'def' -> ["abc'def'"]
[ OK ] abc'def' ghi -> ["abc'def'", 'ghi']
[ OK ] abc'def'ghi -> ["abc'def'ghi"]
[ OK ] abc"def -> ['abc"def']
[ OK ] abc"def" -> ['abc"def"']
[ OK ] abc"def" ghi -> ['abc"def"', 'ghi']
[ OK ] abc"def"ghi -> ['abc"def"ghi']
[ OK ] r'AA' r'.*_xyz$' -> ["r'AA'", "r'.*_xyz$'"]
[ OK ] abc"def ghi" -> ['abc"def ghi"']
[ OK ] abc"def ghi""jkl" -> ['abc"def ghi""jkl"']
[ OK ] a"b c"d"e"f"g h" -> ['a"b c"d"e"f"g h"']
[ OK ] c="ls /" type key -> ['c="ls /"', 'type', 'key']
[ OK ] abc'def ghi' -> ["abc'def ghi'"]
[ OK ] c='ls /' type key -> ["c='ls /'", 'type', 'key']

shlex: 0.335ms per iteration
csv: 0.036ms per iteration
re: 0.068ms per iteration

因此，性能比shlex好得多，并且可以通过预编译正则表达式进一步提高，在这种情况下，它将优于csv方法。

2018-07-27 14:53:46

其他回答

嗯，好像找不到“回复”按钮了…不管怎样，这个答案是基于Kate的方法，但正确地分割了包含转义引号的子字符串，并删除了子字符串的开始和结束引号:

  [i.strip('"').strip("'") for i in re.split(r'(\s+|(?<!\\)".*?(?<!\\)"|(?<!\\)\'.*?(?<!\\)\')', string) if i.strip()]

这适用于'这是' a \\\"test\\\"\\\'s子字符串' '这样的字符串(不幸的是，为了防止Python删除转义，这个疯狂的标记是必要的)。

如果返回列表中的字符串不需要转义，您可以使用稍微修改过的函数版本:

[i.strip('"').strip("'").decode('string_escape') for i in re.split(r'(\s+|(?<!\\)".*?(?<!\\)"|(?<!\\)\'.*?(?<!\\)\')', string) if i.strip()]

2010-01-29 01:36:23

由于性能原因，re似乎更快。下面是我的解决方案，使用最小贪婪操作符，保留外部引号:

re.findall("(?:\".*?\"|\S)+", s)

结果:

['this', 'is', '"a test"']

它将像aaa“bla blub”bbb这样的结构放在一起，因为这些标记没有被空格分隔。如果字符串包含转义字符，你可以这样匹配:

>>> a = "She said \"He said, \\\"My name is Mark.\\\"\""
>>> a
'She said "He said, \\"My name is Mark.\\""'
>>> for i in re.findall("(?:\".*?[^\\\\]\"|\S)+", a): print(i)
...
She
said
"He said, \"My name is Mark.\""

请注意，这也通过模式的\S部分来匹配空字符串“”。

2018-11-08 15:21:24

试试这个:

  def adamsplit(s):
    result = []
    inquotes = False
    for substring in s.split('"'):
      if not inquotes:
        result.extend(substring.split())
      else:
        result.append(substring)
      inquotes = not inquotes
    return result

一些测试字符串:

'This is "a test"' -> ['This', 'is', 'a test']
'"This is \'a test\'"' -> ["This is 'a test'"]

2008-09-17 04:31:38

我用shlex。拆分来处理七千万行鱿鱼日志，太慢了。所以我换成了re。

请尝试这个，如果你有性能问题与shlex。

import re

def line_split(line):
    return re.findall(r'[^"\s]\S*|".+?"', line)

2014-04-18 13:29:10