[Programmers] 카카오 코테 기출 - Lv2. 뉴스 클러스터링

import math

def solution(str1, str2):
    answer = 0
    # 필터링
    str1=str1.lower()
    str2=str2.lower()
    #print(str1, str2)
    
    # 다중집합 만들기
    l1=[''.join(str1[i:i+2]) for i in range(len(str1)-1) if str1[i:i+2].isalpha()]
    l2=[''.join(str2[i:i+2]) for i in range(len(str2)-1) if str2[i:i+2].isalpha()]
        
    print(l1, l2)
    
    # 다중집합 원소들 숫자로 변환
    ids=dict([(i,a) for a,i in enumerate(set(l1+l2))])
    print(ids)
    l1=sorted([ids[item] for item in l1])
    l2=sorted([ids[item] for item in l2])
    print(l1,l2)

    p1=p2=0
    both=[]
    merge=[]
    
    while p1<len(l1) and p2<len(l2):
        if l1[p1]==l2[p2]:
            both.append(l1[p1])
            merge.append(l1[p1])
            p1+=1
            p2+=1
        elif l1[p1]<l2[p2]:
            merge.append(l1[p1])
            p1+=1
        else:
            merge.append(l2[p2])
            p2+=1
    
    if p1<len(l1): merge+=l1[p1:]
    if p2<len(l2): merge+=l2[p2:]
    
    print(both, merge)

    if not merge: return 65536

    return math.floor(len(both)/len(merge)*65536)