Разделение строк с разделителями-запятыми в python

Хотя использовать регулярное выражение невозможно, следующий простой код позволит достичь желаемого результата:

def split_at(text, delimiter, opens='<([', closes='>)]', quotes='"\''):
    result = []
    buff = ""
    level = 0
    is_quoted = False

    for char in text:
        if char in delimiter and level == 0 and not is_quoted:
            result.append(buff)
            buff = ""
        else:
            buff += char

            if char in opens:
                level += 1
            if char in closes:
                level -= 1
            if char in quotes:
                is_quoted = not is_quoted

    if not buff == "":
        result.append(buff)

    return result

Запускаем это в интерпретаторе:

>>> split_at('obj<1, 2, 3>, x(4, 5), "msg, with comma"', ',')                                                                                                                                 
#=>['obj<1, 2, 3>', ' x(4, 5)', ' "msg with comma"']

используя итераторы и генераторы:

def tokenize(txt, delim=',', pairs={'"':'"', '<':'>', '(':')'}):
    fst, snd = set(pairs.keys()), set(pairs.values())
    it = txt.__iter__()

    def loop():
        from collections import defaultdict
        cnt = defaultdict(int)

        while True:
            ch = it.__next__()
            if ch == delim and not any (cnt[x] for x in snd):
                return
            elif ch in fst:
                cnt[pairs[ch]] += 1
            elif ch in snd:
                cnt[ch] -= 1
            yield ch

    while it.__length_hint__():
        yield ''.join(loop())

и,

>>> txt = 'obj<1, sub<6, 7>, 3>,x(4, y(8, 9), 5),"msg, with comma"'
>>> [x for x in tokenize(txt)]
['obj<1, sub<6, 7>, 3>', 'x(4, y(8, 9), 5)', '"msg, with comma"']

Если у вас есть рекурсивные вложенные выражения, вы можете разделить их запятыми и проверить, что они совпадают, сделав это с помощью pyparsing. :

import pyparsing as pp

def CommaSplit(txt):
    ''' Replicate the function of str.split(',') but do not split on nested expressions or in quoted strings'''
    com_lok=[]
    comma = pp.Suppress(',')
    # note the location of each comma outside an ignored expression:
    comma.setParseAction(lambda s, lok, toks: com_lok.append(lok))
    ident = pp.Word(pp.alphas+"_", pp.alphanums+"_")  # python identifier
    ex1=(ident+pp.nestedExpr(opener='<', closer='>'))   # Ignore everthing inside nested '< >'
    ex2=(ident+pp.nestedExpr())                       # Ignore everthing inside nested '( )'
    ex3=pp.Regex(r'("|\').*?\1')                      # Ignore everything inside "'" or '"'
    atom = ex1 | ex2 | ex3 | comma
    expr = pp.OneOrMore(atom) + pp.ZeroOrMore(comma  + atom )
    try:
        result=expr.parseString(txt)
    except pp.ParseException:
        return [txt]
    else:    
        return [txt[st:end] for st,end in zip([0]+[e+1 for e in com_lok],com_lok+[len(txt)])]             


tests='''\
obj<1, 2, 3>, x(4, 5), "msg, with comma"
nesteobj<1, sub<6, 7>, 3>, nestedx(4, y(8, 9), 5), "msg, with comma"
nestedobj<1, sub<6, 7>, 3>, nestedx(4, y(8, 9), 5), 'msg, with comma', additional<1, sub<6, 7>, 3>
bare_comma<1, sub(6, 7), 3>, x(4, y(8, 9), 5),  , 'msg, with comma', obj<1, sub<6, 7>, 3>
bad_close<1, sub<6, 7>, 3), x(4, y(8, 9), 5), 'msg, with comma', obj<1, sub<6, 7>, 3)
'''

for te in tests.splitlines():
    result=CommaSplit(te)
    print(te,'==>\n\t',result)

Отпечатки:

obj<1, 2, 3>, x(4, 5), "msg, with comma" ==>
     ['obj<1, 2, 3>', ' x(4, 5)', ' "msg, with comma"']
nesteobj<1, sub<6, 7>, 3>, nestedx(4, y(8, 9), 5), "msg, with comma" ==>
     ['nesteobj<1, sub<6, 7>, 3>', ' nestedx(4, y(8, 9), 5)', ' "msg, with comma"']
nestedobj<1, sub<6, 7>, 3>, nestedx(4, y(8, 9), 5), 'msg, with comma', additional<1, sub<6, 7>, 3> ==>
     ['nestedobj<1, sub<6, 7>, 3>', ' nestedx(4, y(8, 9), 5)', " 'msg, with comma'", ' additional<1, sub<6, 7>, 3>']
bare_comma<1, sub(6, 7), 3>, x(4, y(8, 9), 5),  , 'msg, with comma', obj<1, sub<6, 7>, 3> ==>
     ['bare_comma<1, sub(6, 7), 3>', ' x(4, y(8, 9), 5)', '  ', " 'msg, with comma'", ' obj<1, sub<6, 7>, 3>']
bad_close<1, sub<6, 7>, 3), x(4, y(8, 9), 5), 'msg, with comma', obj<1, sub<6, 7>, 3) ==>
     ["bad_close<1, sub<6, 7>, 3), x(4, y(8, 9), 5), 'msg, with comma', obj<1, sub<6, 7>, 3)"]

Текущее поведение такое же, как '(something does not split), b, "in quotes", c'.split','), включая сохранение начальных пробелов и кавычек. Тривиально удалить кавычки и начальные пробелы из полей.

Измените else под try на:

else:
    rtr = [txt[st:end] for st,end in zip([0]+[e+1 for e in com_lok],com_lok+[len(txt)])]
    if strip_fields:
        rtr=[e.strip().strip('\'"') for e in rtr]
    return rtr