codeforce D. Innokenty and a Football League 贪心,模拟

题目：

Innokenty is a president of a new football league in Byteland. The first task he should do is to assign short names to all clubs to be shown on TV next to the score. Of course, the short names should be distinct, and Innokenty wants that all short names consist of three letters.

Each club's full name consist of two words: the team's name and the hometown's name, for example, "DINAMO BYTECITY". Innokenty doesn't want to assign strange short names, so he wants to choose such short names for each club that:

1. the short name is the same as three first letters of the team's name, for example, for the mentioned club it is "DIN",
2. or, the first two letters of the short name should be the same as the first two letters of the team's name, while the third letter is the same as the first letter in the hometown's name. For the mentioned club it is "DIB".

Apart from this, there is a rule that if for some club x the second option of short name is chosen, then there should be no club, for which the first option is chosen which is the same as the first option for the club x. For example, if the above mentioned club has short name "DIB", then no club for which the first option is chosen can have short name equal to "DIN". However, it is possible that some club have short name "DIN", where "DI" are the first two letters of the team's name, and "N" is the first letter of hometown's name. Of course, no two teams can have the same short name.

Help Innokenty to choose a short name for each of the teams. If this is impossible, report that. If there are multiple answer, any of them will suit Innokenty. If for some team the two options of short name are equal, then Innokenty will formally think that only one of these options is chosen.

Input

The first line contains a single integer n (1 ≤ n ≤ 1000) — the number of clubs in the league.

Each of the next n lines contains two words — the team's name and the hometown's name for some club. Both team's name and hometown's name consist of uppercase English letters and have length at least 3 and at most 20.

Output

It it is not possible to choose short names and satisfy all constraints, print a single line "NO".

Otherwise, in the first line print "YES". Then print n lines, in each line print the chosen short name for the corresponding club. Print the clubs in the same order as they appeared in input.

If there are multiple answers, print any of them.

Examples

input

2
DINAMO BYTECITY
FOOTBALL MOSCOW

output

YES
DIN
FOO

input

2
DINAMO BYTECITY
DINAMO BITECITY

output

NO

input

3
PLAYFOOTBALL MOSCOW
PLAYVOLLEYBALL SPB
GOGO TECHNOCUP

output

YES
PLM
PLS
GOG

input

3
ABC DEF
ABC EFG
ABD OOO

output

YES
ABD
ABE
ABO

这个题，哎~纠结了好几天，一直不知道那错了，我开始采用的策略是这样：首先考虑前面的名字相同的，那么这些只能选后面的，如果后面的有重复就无解，然后再跑一圈，

考虑前面的，看是不是被占，如果被占就往后摞一摞，如果还被占也无解。这个是错的,感谢ZJ学姐的样例：

 4
abc def
abc ghi
abo xyz
abg opq

仔细分析，原因是对于不确定的元素，不能贸然决定，直到把所有没有争议的选完后，才能瞎选，你在前面瞎选会对后面产生影响。

code：

#include<cstring>
#include<cstdio>
#include<map>
#include<string>
using namespace std;
char name[25],home[25];
char op0[1005][5],op2[1005][5];
char ans[1005][5];
int main(){
    int N;
    while(scanf("%d",&N)==1){
        for(int i=0;i<N;++i){
            scanf("%s%s",name,home);
            op0[i][0]=name[0];op0[i][1]=name[1];
            op0[i][2]=name[2];op0[i][3]='\0';
            op2[i][0]=name[0];op2[i][1]=name[1];
            op2[i][2]=home[0];op2[i][3]='\0';
        }
        map<string,int>cnt;
        for(int i=0;i<N;++i){
            cnt[op0[i]]++;
        }
        map<string,bool>visit;
        bool noAns=false;
        for(int i=0;i<N;++i){
            if(cnt[op0[i]]>=2){
                if(!visit[op2[i]]){
                    strcpy(ans[i],op2[i]);
                    visit[op2[i]]=true;
                }else{
                    noAns=true;
                }
            }
            //printf("%d\n",noAns);
        }
        for(int j=0;j<N;++j){//最差情况下的循环次数
            bool update=false;//标记更新了没
            for(int i=0;i<N;++i){
                if(!strlen(ans[i])){
                    if(!visit[op0[i]]&&!visit[op2[i]])continue;
                    if(visit[op0[i]]&&!visit[op2[i]]){
                        strcpy(ans[i],op2[i]);
                        visit[op2[i]]=true;update=true;
                    }else if(visit[op2[i]]&&!visit[op0[i]]){
                        strcpy(ans[i],op0[i]);
                        visit[op0[i]]=true;update=true;
                    }else noAns=true;
                }
            }
            if(!update)break;
        }
        for(int i=0;i<N;++i){
            if(!strlen(ans[i]))strcpy(ans[i],op0[i]);
        }
        if(noAns)printf("NO\n");
        else{
            printf("YES\n");
            for(int i=0;i<N;++i)
                printf("%s\n",ans[i]);
        }
    }
}

另外贴一下看的别人的代码，思路大体上差不多，但写得挺漂亮的：

#include <bits/stdc++.h>
using namespace std;
const int maxn = 1000+5;
string a[maxn], b[maxn],ans[maxn];
bool hasAns[maxn];
set<string> used;
void f(string s){
    if(used.count(s)){cout << "NO"<<endl; exit(0);}
}
int main(){
    int n;
    cin >> n;
    for(int i = 0; i < n; i++){
        string s1,s2;
        cin >> s1 >> s2;
        a[i] = s1.substr(0, 3);
        b[i] = s1.substr(0, 2) + s2.substr(0, 1);
    }


    for(int i = 0; i < n; i++)
        for(int j = 0; j < i; j++)
            if(a[i] == a[j])
                hasAns[i] = hasAns[j] = 1;//具有相同第一个名字的
    for(int i = 0; i < n; i++){
        if(hasAns[i]){
            f(b[i]);
            ans[i] = b[i];
            used.insert(b[i]);
        }
    }
    
    for(int j = 0; j < n; j++){//j代表最差情况，需要循环次数
        for(int i = 0; i < n; i++){
            if(hasAns[i]) continue;//已经有答案了
            if(used.count(a[i])){//a[i]已经被用
                f(b[i]);
                ans[i] = b[i];
                used.insert(b[i]);
                hasAns[i] = 1;
            }
        }
    }
    for(int i = 0; i < n; i++)
        if(!hasAns[i])
            ans[i] = a[i];
    cout << "YES\n";
    for(int i = 0; i < n; i++) cout << ans[i] << endl;
    return 0;
}

另外，据说此题与2_SAT有关，看来有必要学一波了~