05-树9 Huffman Codes（30 point(s)） 最小堆、哈夫曼树、dfs

05-树9 Huffman Codes（30 point(s)）

In 1953, David A. Huffman published his paper "A Method for the Construction of Minimum-Redundancy Codes", and hence printed his name in the history of computer science. As a professor who gives the final exam problem on Huffman codes, I am encountering a big problem: the Huffman codes are NOT unique. For example, given a string "aaaxuaxz", we can observe that the frequencies of the characters 'a', 'x', 'u' and 'z' are 4, 2, 1 and 1, respectively. We may either encode the symbols as {'a'=0, 'x'=10, 'u'=110, 'z'=111}, or in another way as {'a'=1, 'x'=01, 'u'=001, 'z'=000}, both compress the string into 14 bits. Another set of code can be given as {'a'=0, 'x'=11, 'u'=100, 'z'=101}, but {'a'=0, 'x'=01, 'u'=011, 'z'=001} is NOT correct since "aaaxuaxz" and "aazuaxax" can both be decoded from the code 00001011001001. The students are submitting all kinds of codes, and I need a computer program to help me determine which ones are correct and which ones are not.

Input Specification:

Each input file contains one test case. For each case, the first line gives an integer $N$ ($2\le N\le 63$), then followed by a line that contains all the $N$distinct characters and their frequencies in the following format:

c[1] f[1] c[2] f[2] ... c[N] f[N]

where c[i] is a character chosen from {'0' - '9', 'a' - 'z', 'A' - 'Z', '_'}, and f[i]is the frequency of c[i] and is an integer no more than 1000. The next line gives a positive integer $M$ ($\le 1000$), then followed by $M$ student submissions. Each student submission consists of $N$ lines, each in the format:

c[i] code[i]

where c[i] is the i-th character and code[i] is an non-empty string of no more than 63 '0's and '1's.

Output Specification:

For each test case, print in each line either "Yes" if the student's submission is correct, or "No" if not.

Note: The optimal solution is not necessarily generated by Huffman algorithm. Any prefix code with code length being optimal is considered correct.

Sample Input:

7
A 1 B 1 C 1 D 3 E 3 F 6 G 6
4
A 00000
B 00001
C 0001
D 001
E 01
F 10
G 11
A 01010
B 01011
C 0100
D 011
E 10
F 11
G 00
A 000
B 001
C 010
D 011
E 100
F 101
G 110
A 00000
B 00001
C 0001
D 001
E 00
F 10
G 11

Sample Output:

Yes
Yes
No
No

思路：先建立最小堆，用最小堆生成哈夫曼树，计算出编码占用的最小空间。输入学生的编码时先看长度是否超过n-1，然后计算占用空间，最后检查任意两个编码是否相同，某个是否是另一个的前缀

#include<cstdio>
#include<cstdlib>
#include<cstring>
using namespace std;

int n,wt,m,sz[520];

typedef struct hnod *HNOD;
typedef struct hfm *HFM;

typedef struct hfm{    //节点结构体 
	char c;
	int f;
	HFM l,r;
}hfm;

typedef struct hnod{    //堆结构体，nods为节点地址数组，下标从1开始存储，curn为当前元素个数，maxn为最大元素个数（没有用到 
	HFM *nods;
	int curn;
	int maxn;
}hnod;

HNOD minheap;
HFM T;

void buildmh(){    //建立最小堆 
	minheap=(HNOD)malloc(sizeof(struct hnod));
	minheap->nods=(HFM*)malloc((n+1)*sizeof(HFM));    //从1开始存储，所以申请n+1空间 
	minheap->curn=0;
	minheap->maxn=n;
}

void insmh(HFM h){    //插入最小堆 
	minheap->curn++;    //元素个数+1 
	minheap->nods[minheap->curn]=h;    //把要插入的元素放到最后 
	int cld=minheap->curn;    //初始化孩子节点位置 
	int par=cld/2;    //初始化父节点位置 
	while(par>0&&h->f<minheap->nods[par]->f){     //从最后位置往上遍历 
		minheap->nods[cld]=minheap->nods[par];
		cld=par;
		par=cld/2;
	}
	minheap->nods[cld]=h;
}

HFM del(){    //从堆中返回并删除最小元素 
	HFM tnod=minheap->nods[1];    //取出最小元素 
	minheap->nods[1]=minheap->nods[minheap->curn--];    //将最后位置的元素拿到根节点 
	HFM tnod2=minheap->nods[1];
	if(minheap->curn>1){    //如果取出之后堆只剩一个或者没有元素，则不需要整理 
		int par=1,cld=2;
		if(cld<minheap->curn&&minheap->nods[cld+1]->f<minheap->nods[cld]->f) cld++;
		while(cld<=minheap->curn&&tnod2->f>minheap->nods[cld]->f){    //从根节点往下遍历 
			minheap->nods[par]=minheap->nods[cld];
			par=cld;
			cld=par*2;
			if(cld<minheap->curn&&minheap->nods[cld+1]->f<minheap->nods[cld]->f) cld++;
		}
		minheap->nods[par]=tnod2;
	}
	return tnod;
}

HFM buildhfm(){    //建立哈夫曼树 
	while(minheap->curn>1){    //当堆中只剩一个元素的时候表示只剩一颗树，退出循环 
		HFM h1=del();    //取出两个最小元素 
		HFM h2=del();
		HFM h3=(HFM)malloc(sizeof(struct hfm));
		h3->f=h1->f+h2->f;
		h3->l=h1;
		h3->r=h2;
		insmh(h3);    //将用两个最小元素合成的新节点插入最小堆 
	}
	return minheap->nods[1];
}

int dfs(HFM h,int w){
	if(!h->l)return h->f*w;
	return dfs(h->l,w+1)+dfs(h->r,w+1);
}

int min(int a,int b){
	return a<b?a:b;
}

bool ck(char a[],char b[]){
	int i;
	for(i=0;i<strlen(a)&&i<strlen(b);i++){
		if(a[i]!=b[i])break;     
	}
	return i!=min(strlen(a),strlen(b));
}

int main(){
	scanf("%d",&n);
	buildmh();    //建立最小堆，堆元素为节点的地址 
	int i,j,k,tf;
	char tc;
	for(i=0;i<n;i++){
		scanf("%c",&tc);
		scanf("%c %d",&tc,&tf);
		sz[tc]=tf;
		HFM h=(HFM)malloc(sizeof(struct hfm));    //读取建立节点 
		h->c=tc;
		h->f=tf;
		h->l=NULL;
		h->r=NULL;
		insmh(h);   //把节点地址插入最小堆 
	}
	int t=minheap->curn;
	T=buildhfm();    //建立哈夫曼树 
	wt=dfs(T,0);    //获得最小的占用空间 
	
	scanf("%d",&m);
	for(i=0;i<m;i++){
		bool f=true;
		int tw=0;
		char cs[63][64];
		for(j=0;j<n;j++){
			scanf("%c",&tc);
			scanf("%c %s",&tc,cs[j]);
			if(strlen(cs[j])>n-1){    //单个编码最长可能为n-1，如果超过则肯定不是哈夫曼编码 
				f=false;
			}
			if(f){
				tw+=strlen(cs[j])*sz[tc];    //统计占用空间 
			}
		}
		if(tw>wt)f=false;    //检查占用空间 
		if(f)    
			for(j=0;j<n;j++)
				for(k=j+1;k<n;k++)
					if(f) f=ck(cs[j],cs[k]);    //两两检查是否相同，一个是否是另一个的前缀 
		printf("%s\n",f?"Yes":"No");
	}
	return 0;
}