Common String Components #python

common_string_components.py

from itertools import zip_longest


def common_string_components(strings, separator=None):
    def split_string(string):
        if type(string) == str:
            # if separator is '', split by character
            if separator == '':
                string = list(string)
            else:
                string = string.split(separator)
        return string

    strings = map(split_string, strings)
    strings = zip_longest(*strings)
    strings = map(lambda c: list(set(c)), strings)
    return list(strings)
  
# it is possible to later use this for producing canonical names
# from a set of possible names, you just have to replace `None` with `'None'`
# each component can be separated by spaces
# so "A B C" and "A B D" can turn into "A B (C or D)"

def canonical_name(names, separator=None):
    name_components = common_string_components(names, separator)
    name_components_rendered = []
    for component in name_components:
        component = ['None' if c is None else c for c in component]
        if len(component) > 1:
            component = '(' + ' or '.join(component) + ')'
        else:
            component = ''.join(component)
        name_components_rendered.append(component)
    name_components_rendered = ' '.join(name_components_rendered)
    return name_components_rendered