Question

How do you create a function to get the word after “class” only if it is not a quoted (by single or double, or any triple quotations) and if its spelled correctly (cannot get class d() )

"class hi()"  > hi

"class hi(dff)"  > hi

"class hi   (  dff  )  :"  > hi 

"  class        hi       (  dff  )  :"  > hi 

"class hi"  > hi

"classf hi"  > Nothing

"fclass hi"  > Nothing

"'class hi(dd)'"  > Nothing

'"class hi(dd)"'  > Nothing

"'''class hi(dd)'''"  > Nothing

'"""class hi(dd)"""'  > Nothing

'"""\n\n\n\nclass hi(dd)\n\n\n\n"""'  > Nothing    

"'class' hi()"  > Nothing

It is too hard to create using loops. If anyone can help that would be nice, thanks. This is pretty challenging,

Answer 1

import re

def remove(reg, s, multiline=False):
    flags = [re.M, re.M | re.DOTALL][multiline]
    s,num = re.subn(reg, "", s, flags=flags)
    return s

def classname(s):
    s = remove("\"\"\".*?\"\"\"", s, multiline=True)
    s = remove("\'\'\'.*?\'\'\'", s, multiline=True)
    s = remove("\".*?\"", s)
    s = remove("\'.*?\'", s)

    res = re.search("(^|\s)class\s+(\w+)", s, flags=re.M)
    # print "*** {} -> {}".format(s, res.groups() if res else None)
    if res is None:
        return None
    else:
        return res.group(2)

I wanted to use \b instead of (^|\s) but it didn’t seem to want to work?

I also put together the following test code:

tests = [
    ("class hi()", "hi"),
    ("class hi(dff)", "hi"),
    ("class hi   (  dff  )  :", "hi"),
    ("  class        hi       (  dff  )  :", "hi"),
    ("class hi", "hi"),
    ("classf hi", None),
    ("fclass hi", None),
    ("'class hi(dd)'", None),
    ('"class hi(dd)"', None),
    ("'''class hi(dd)'''", None),
    ('"""class hi(dd)"""', None),
    ('"""\n\n\n\nclass hi(dd)\n\n\n\n"""', None),   
    ("'class' hi()", None),
    ("a = ''; class hi(object): pass", "hi")
]

def run_tests(fn, tests=tests):
    for inp,outp in tests:
        res = fn(inp)
        if res == outp:
            print("passed")
        else:
            print("FAILED on {} (gave '{}', should be '{}')".format(inp, repr(res), repr(outp)))