npp_settings/plugins/config/PythonScript/scripts/regex_pp.py

import re
paren = re.compile(r"\([^\(\)]*\)")

def whiteout(s,start,end):
    return s[:start] + (' '*(end-start)) + s[end:]

def endparen(s,start):
    end = None
    while end == None:
        span = paren.search(s,start).span()
        if span[0] == start:
            end = span[1]
        else:
            s = whiteout(s,*span)
    return end

def find_named_groups(regex):
    start = 0
    while start < len(regex)-1:
        try:
            start = regex.index('(?P',start)
            yield start
            start += 1
        except ValueError:
            break

def named_group_split(regex):
    named_groups = list(find_named_groups(regex))
    for index in range(len(named_groups)):
        s0 = named_groups[index]
        e0 = endparen(regex,s0)
        s1 = e0
        try:
            if not e0 == named_groups[index+1]:
                e1 = named_groups[index+1]
            else:
                e1 = s1
        except IndexError:
            s1 = e0
            e1 = len(regex)+1
        yield [regex[s0:e0],regex[s1:e1]]

def wrap(s):
    if s:
        return 'r"{}"'.format(s)
    else:
        return ''


def sep_row(row,lengths,add_sep = 0):
    ret = ''
    for col in range(len(row)-1):
        if row[col+1]:
            ret += row[col].ljust(lengths[col]+add_sep,' ')
        else:
            ret += row[col]
    return ret + row[-1]


def list2dstring(list2d,space=1):
    col_length = []
    for col in range(len(list2d[0])-1):
        col_length.append(
            max(
                map(
                    len,(row[col] for row in list2d)
                    )
                )
            )
    col_length.append(0)
    ret = []
    for row in list2d:
        ret.append(sep_row(list(map(wrap,row)),col_length,add_sep = 4))
    return '\n'.join(ret)

def pformat_regex(regex):
    return '\n'+list2dstring(list(named_group_split(regex)))+'\n'

if __name__ == "__main__":
    from Npp import editor
    start = editor.getSelectionStart()
    content = editor.getSelText()
    prev_content = content
    content = re.sub(r'^\(?r?[\"\']|[\"\']\)?','',content)
    result = pformat_regex(content)
    if prev_content[0] == '(':
        result = '(' + result
    if prev_content[-1] == ')':
        result = result + ')'
    editor.replaceSel(result)
 
    editor.setSelectionStart(start)
    editor.setSelectionEnd(start + len(result))