Split a string by spaces — preserving quoted substrings — in Python

Question

I have a string which is like this:

this is \"a test\"

I\'m trying to write something in Python to split it up by space while ignoring spac

Answer 1

To get around the unicode issues in some Python 2 versions, I suggest:

from shlex import split as _split
split = lambda a: [b.decode('utf-8') for b in _split(a.encode('utf-8'))]

Answer 2

The main problem with the accepted shlex approach is that it does not ignore escape characters outside quoted substrings, and gives slightly unexpected results in some corner cases.

I have the following use case, where I need a split function that splits input strings such that either single-quoted or double-quoted substrings are preserved, with the ability to escape quotes within such a substring. Quotes within an unquoted string should not be treated differently from any other character. Some example test cases with the expected output:

 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$'"  | ["r'AA'", "r'.*_xyz$'"]

I ended up with the following function to split a string such that the expected output results for all input strings:

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)]

The following test application checks the results of other approaches (shlex and csv for now) and the custom split implementation:

#!/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$'", ["r'AA'", "r'.*_xyz$'"])

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)]

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)')

Output:

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$' -> ['rAA', 'r.*_xyz$']

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$' -> ["r'AA'", "r'.*_xyz$'"]

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$' -> ["r'AA'", "r'.*_xyz$'"]

shlex: 0.281ms per iteration
csv: 0.030ms per iteration
re: 0.049ms per iteration

So performance is much better than shlex, and can be improved further by precompiling the regular expression, in which case it will outperform the csv approach.

Answer 3

Try this:

  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

Some test strings:

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

Answer 4

You want split, from the built-in shlex module.

>>> import shlex
>>> shlex.split('this is "a test"')
['this', 'is', 'a test']

This should do exactly what you want.

Answer 5

I use shlex.split to process 70,000,000 lines of squid log, it's so slow. So I switched to re.

Please try this, if you have performance problem with shlex.

import re

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

Answer 6

As an option try tssplit:

In [1]: from tssplit import tssplit
In [2]: tssplit('this is "a test"', quote='"', delimiter='')
Out[2]: ['this', 'is', 'a test']