from functions_cluster import *

def create_df_algorithm(raw_aff_string):
    aff_no_symbols_d =  substrings_dict(clean_string(remove_outer_parentheses(remove_leading_numbers(raw_aff_string))))
    substring_list = list(aff_no_symbols_d.values())

    i = 0

    while i < len(substring_list) - 1:
        if is_contained('progr', substring_list[i]) and is_contained('dep', substring_list[i+1]):
            substring_list.pop(i)

            
        elif (is_contained('assistant', substring_list[i]) or is_contained('researcher', substring_list[i]) or is_contained('phd', substring_list[i]) or is_contained('student', substring_list[i]) or is_contained('section', substring_list[i]) or is_contained('prof', substring_list[i]) or is_contained('director', substring_list[i])) and (not is_contained('school', substring_list[i+1]) or is_contained('univ', substring_list[i+1]) or is_contained('inst', substring_list[i+1]) or is_contained('lab', substring_list[i+1]) or is_contained('fac', substring_list[i+1])):
            substring_list.pop(i)

        elif (is_contained('engineer', substring_list[i]) or is_contained('progr', substring_list[i]) or is_contained('unit', substring_list[i]) or is_contained('lab', substring_list[i]) or is_contained('dep', substring_list[i]) or  is_contained('school', substring_list[i])  or is_contained('inst', substring_list[i]) #or is_contained('hosp', substring_list[i]) 
            or is_contained('fac', substring_list[i])) and is_contained('univ', substring_list[i+1]):
            if not is_contained('univ', substring_list[i]):
                substring_list.pop(i)
            else:
                i = i+1
                continue

        elif is_contained('lab', substring_list[i]) and (is_contained('colege', substring_list[i+1]) or is_contained('inst', substring_list[i+1]) or is_contained('dep', substring_list[i+1]) or is_contained('school', substring_list[i+1])):
            if not is_contained('univ', substring_list[i]):
                substring_list.pop(i)
            else:
                i = i+1
                continue

        elif is_contained('dep', substring_list[i]) and (is_contained('tech', substring_list[i+1]) or is_contained('colege', substring_list[i+1]) or is_contained('inst', substring_list[i+1]) or  is_contained('hosp', substring_list[i+1]) or  is_contained('school', substring_list[i+1]) or  is_contained('fac', substring_list[i+1])):
            if not is_contained('univ', substring_list[i]):
                substring_list.pop(i)
            else:
                i = i+1
                continue

        elif is_contained('inst',substring_list[i]) and (is_contained('school', substring_list[i+1]) or is_contained('dep', substring_list[i+1]) or is_contained('acad', substring_list[i+1]) or is_contained('hosp', substring_list[i+1]) or is_contained('clin', substring_list[i+1]) or is_contained('klin', substring_list[i+1])  or is_contained('fak', substring_list[i+1]) or is_contained('fac', substring_list[i+1]) or is_contained('cent', substring_list[i+1]) or is_contained('div', substring_list[i+1])):
            if not is_contained('univ', substring_list[i]):
                substring_list.pop(i)
            else:
                i = i+1
                continue


        elif is_contained('school',substring_list[i]) and is_contained('colege', substring_list[i+1]):
            if not is_contained('univ', substring_list[i]):
                substring_list.pop(i)
            else:
                i = i+1
                continue

        else:
            i += 1

    light_aff = (', '.join((substring_list)))
    for x in substring_list:
        if x in city_names+remove_list:
            substring_list.remove(x)
    
    substring_list = [shorten_keywords_spark([x])[0] for x in substring_list] 


    def valueToCategory(value):
        flag = 0

        for k in categ_dicts:
            if k in value: 
                flag = 1
        return flag
    
    aff_list = [{"index": i, "keywords": substring_list[i], "category": valueToCategory(substring_list[i])} for i in range(len(substring_list))]

    filtered_list = [entry for entry in aff_list if entry.get("category") == 1]

    return   [light_aff, filtered_list]