05-树9 Huffman Codes

05-树9 Huffman Codes

来自：PTA_数据结构_Huffman Codes

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≤N≤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 (≤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

程序代码：

方法1：

//Huffman编码不唯一
//Huffman编码是最优编码，但最优编码不一定是Huffman编码
 
//需要满足的条件
//1最优：wpl最小  建立Huffman树计算最小wpl判断学生的提交是否正确
//2无歧义：前缀码  建树过程中检查是否满足前缀码要求
 
#include <stdio.h>
#include <stdlib.h>
#include <ctype.h>
#include <string.h>
#define MinData -1
#define N 64
typedef struct HuTreeNode *HuffmanTree;
typedef struct HNode *Heap;
typedef struct BiTreeNode *BinTree;
struct HuTreeNode {
	int Weight;
	HuffmanTree Left, Right;
};
struct HNode {
	HuffmanTree* Data;
	int Size;
};
struct BiTreeNode {
	int flag;
	BinTree Left, Right;
};
 
HuffmanTree BuiltHuffman(Heap H);
HuffmanTree DeleteMinHeap(Heap H);
void InsertMinHeap(Heap H, HuffmanTree HT);
int Wpl(HuffmanTree HT, int depth);
void CheckPrefixcode(BinTree BT, char *str, int *flag);
BinTree Delete(BinTree BT);
 
int main(void) {
	int i, n, m, wpl, flag, frequency[N], w;
	char ch, str[N];
	Heap H = (Heap)malloc(sizeof(struct HNode));
	HuffmanTree HT;
	BinTree BT;
 
	scanf("%d\n", &n);
	H->Data = (HuffmanTree*)malloc((n + 1)*sizeof(HuffmanTree));
	H->Data[0] = (HuffmanTree)malloc(sizeof(struct HuTreeNode));
	H->Data[0]->Weight = MinData;
	H->Size = 0;
	for (i = 1;i <= n;i++) {
		ch = getchar();
		if(!isalpha(ch))
			ch = getchar();
		scanf(" %d", &frequency[i]);
		HT = (HuffmanTree)malloc(sizeof(struct HuTreeNode));
		HT->Weight = frequency[i];
		HT->Left = HT->Right = NULL;
		InsertMinHeap(H, HT);
	}
	HT = BuiltHuffman(H);
	w = Wpl(HT, 0);
 
	ch = getchar();
	scanf("%d\n", &m);
	while (m--) {
		wpl = 0;
		flag = 0;
		BT = (BinTree)malloc(sizeof(struct BiTreeNode));
		BT->flag = 0;
		BT->Left = BT->Right = NULL;
		for (i = 0;i < n;i++) {
			scanf("%c %s\n", &ch, str);
			wpl += strlen(str) * frequency[i+1];	
			/*其实可以先检测一下wpl是否相同，不同的话也就不用检测是否前缀码了*/
			if(!flag)	//这一行其实不需要也行，反正肯定也要执行，PTA已经试过
				CheckPrefixcode(BT, str, &flag);
		}
		if (flag || wpl > w)
			printf("No\n");
		else printf("Yes\n");
		BT = Delete(BT);
	}
}
 
//建立Huffman树
HuffmanTree BuiltHuffman(Heap H) {
	int i, k = H->Size - 1;
	HuffmanTree HT;
	for (i = 0;i < k;i++) {
		HT = (HuffmanTree)malloc(sizeof(struct HuTreeNode));
		HT->Left = DeleteMinHeap(H);
		HT->Right = DeleteMinHeap(H);
		HT->Weight = HT->Left->Weight + HT->Right->Weight;
		InsertMinHeap(H, HT);
	}
	return DeleteMinHeap(H);
}
//从最小堆中删除元素
HuffmanTree DeleteMinHeap(Heap H) {
	int i, child;
	HuffmanTree MinItem, LastItem;
	MinItem = H->Data[1];
	LastItem = H->Data[H->Size--];
	for (i = 1;i * 2 <= H->Size;i = child) {
		child = i * 2;
		if (child < H->Size && H->Data[child + 1]->Weight < H->Data[child]->Weight)
			child++;
		if(LastItem->Weight > H->Data[child]->Weight)
			H->Data[i] = H->Data[child];
		else break;
	}
	H->Data[i] = LastItem;
	return MinItem;
}

//向最小堆中插入元素
void InsertMinHeap(Heap H, HuffmanTree HT) {
	int i;
	for (i = ++H->Size; H->Data[i / 2]->Weight > HT->Weight; i /= 2)
		H->Data[i] = H->Data[i / 2];
	H->Data[i] = HT;
}

//计算最优编码长度
/*这里如果出现一种情况，HT只有左子树没有右子树怎么办？ NULL->Left会报错吗？ 
根据题意是不会，NULL-Left结果还是NULL*/
int Wpl(HuffmanTree HT, int depth) {
	if (!HT->Left && !HT->Right)    
		return depth*HT->Weight;
	else
		return Wpl(HT->Left, depth + 1) + Wpl(HT->Right, depth + 1);
}

//检查是否为前缀码
void CheckPrefixcode(BinTree BT, char *str, int *flag) {
	size_t i;
	for (i = 0;i < strlen(str);i++) {
		if (BT->flag) //非叶子节点存在元素
		{
			*flag = 1;
			return;
		}
		if (str[i] == '0') {
			if (!BT->Left) {
				BinTree T = (BinTree)malloc(sizeof(struct BiTreeNode));
				T->flag = 0;
				T->Left = T->Right = NULL;
				BT->Left = T;
			}
			BT = BT->Left;
		}
		else {
			if (!BT->Right) {
				BinTree T = (BinTree)malloc(sizeof(struct BiTreeNode));
				T->flag = 0;
				T->Left = T->Right = NULL;
				BT->Right = T;
			}
			BT = BT->Right;
		}
	}
	//该节点将写入元素，如果已经存在元素（重合）或者非叶节点（存在子树），则不是前缀码
	if (BT->flag || BT->Left || BT->Right) {
		*flag = 1;
		return;
	}
	BT->flag = 1;
}

//删除树
BinTree Delete(BinTree BT) {
	if (!BT->Left && !BT->Right) {
		free(BT);
		BT = NULL;	
	}
	else {
		if (BT->Left)
			BT->Left = Delete(BT->Left);
		if (BT->Right)
			BT->Right = Delete(BT->Right);
	}
	return BT;
}

方法2：

#include <stdio.h>
#include <stdlib.h>
#include <string>
#include <string.h>
#include <malloc.h>
#include <iostream>
using namespace std;
typedef struct LNode{
    char name;
    int weight;
    int parent;
}LNode;
void Select_2min(LNode *hf,int i,int &min1,int &min2);
int GetWeight(LNode *hf, char c, int n);
int main()
{
    int n; scanf("%d",&n);
    LNode *hf = (LNode*)malloc(sizeof(LNode)*(2*n));
    for(int i=0; i<n; i++){
        getchar();
        scanf("%c %d",&hf[i].name,&hf[i].weight);
        hf[i].parent=-1;
    }
    int min1, min2, WPL=0;
    for(int i=n; i<2*n-1; i++){
        Select_2min(hf, i, min1, min2);
        hf[i].weight = hf[min1].weight+hf[min2].weight;
        hf[min1].parent = i;
        hf[min2].parent = i;
        WPL += hf[i].weight;
        hf[i].parent = -1;
    }
    int m; scanf("%d",&m);
    while(m--){
        string code[1005];
        int sum=0;
        char c;
        for(int i=0; i<n; i++){
            getchar();
            cin>>c>>code[i];
            sum += GetWeight(hf,c,n)*code[i].length();
        }
        if(sum!=WPL) printf("No\n");
        else{
            int flag=0;
            for(int i=0; i<n; i++){
                int len=code[i].length();
                for(int j=0;j<n;j++){
                    if(i==j) continue;
                        int len_other=code[j].length();
                        if(len<=len_other&&code[i]==code[j].substr(0,len)){
                            flag=1;
                            break;
                        }
                }
                if(flag) break;
            }
            if(flag) printf("No\n");
            else printf("Yes\n");
        }
    }
}
int GetWeight(LNode *hf, char c, int n){
    for(int i=0; i<n; i++)
        if(hf[i].name == c)
            return hf[i].weight;
}
void Select_2min(LNode *hf,int n,int &min1,int &min2){
    int flag=0;
    for(int i=0;i<n;i++)
        if(!flag && hf[i].parent==-1){min1=i;flag=1;}
        else if(flag && hf[i].parent==-1){min2=i;break;}
    if(hf[min1].weight > hf[min2].weight){
        int t=min1; min1=min2; min2=t;
    }
    for(int i=0; i<n; i++){
        if(hf[i].parent!=-1 || i==min1 || i==min2) continue;
        else if(hf[i].weight < hf[min1].weight){
            min2=min1; min1=i;
        }
        else if(hf[i].weight < hf[min2].weight)
            min2=i;
    }
}

方法3：

#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#define MINH -1
#define MAXCODESIZE 63

typedef struct TreeNode *HuffmanTree;
struct TreeNode {
    int weight;
    HuffmanTree Left, Right;
};

typedef struct TreeNode *ElementType;
typedef struct HeapStruct *MinHeap;
struct HeapStruct {
    ElementType *Elements;
    int Size;
    int Capacity;
};

/* 堆的相关操作：开始 */
MinHeap CreateHeap( int MaxSize )
{
    MinHeap H = (MinHeap)malloc(sizeof(struct HeapStruct));
    H->Elements = malloc((MaxSize + 1) * sizeof(ElementType));
    H->Size = 0;
    H->Capacity = MaxSize;
    H->Elements[0] = (ElementType)malloc(sizeof(struct TreeNode));
    H->Elements[0]->weight = MINH;

    return H;
}

void DestoryHeap(MinHeap H)
{
    int i;
    if (!H) return;
    if (H->Elements) {
        for (i = 0; i < H->Size; ++i)
            free(H->Elements[i]);
        free(H->Elements);
    }
    free(H);
}

int IsFull(MinHeap H)
{
    return (H->Size == H->Capacity);
}

int IsEmpty(MinHeap H)
{
    return (H->Size == 0);
}

void Insert(MinHeap H, ElementType X)
{
    int i;
    if (IsFull(H)) return;
    i = ++H->Size;
    for (; H->Elements[i / 2]->weight > X->weight; i /= 2)
        H->Elements[i] = H->Elements[i / 2];
    H->Elements[i] = X;
}

ElementType DeleteMin(MinHeap H)
{
    int Parent, Child;
    ElementType MinItem, X;
    if (IsEmpty(H)) return 0;

    MinItem = H->Elements[1];
    X = H->Elements[H->Size--];
    for (Parent = 1; Parent * 2 <= H->Size; Parent = Child) {
        Child = Parent * 2;
        if ((Child != H->Size) && (H->Elements[Child]->weight > H->Elements[Child + 1]->weight))
            Child++;
        if (X->weight <= H->Elements[Child]->weight) break;
        else
            H->Elements[Parent] = H->Elements[Child];
    }
    H->Elements[Parent] = X;
    return MinItem;
}

MinHeap BuildMinHeap(int *freq_arr,int n)
{
    int i;
    ElementType data;
    MinHeap H;
    H = CreateHeap(n);

    for (i = 0; i < H->Capacity; ++i) {
        data = (ElementType)malloc(sizeof(struct TreeNode));
        data->weight = freq_arr[i];
        data->Left = 0; data->Right = 0;
        Insert(H, data);
    }
    return H;
}
/* 堆的相关操作：结束 */

void DestoryCharFreq(int *freq_arr)
{
    if (!freq_arr) return;
    free(freq_arr);
}

void DestoryHuffmanTree(HuffmanTree HT)
{
    if (!HT) return;
    DestoryHuffmanTree(HT->Left);
    DestoryHuffmanTree(HT->Right);
    free(HT);
}

int *readPair(int n)
{
    int i; char c;
    int *freq_arr;
    freq_arr = malloc(n * sizeof(int));
    for (i = 0; i < n; ++i) {
        scanf(" %c %d", &c, &freq_arr[i]);
    }
    return freq_arr;
}

int HuffmanTreeWPL(int *freq_arr, int n)
{
    int i, wpl = 0;
    MinHeap H;
    HuffmanTree T;
    H = BuildMinHeap(freq_arr, n);  // 根据读入数据建立小顶堆
    for (i = 1; i < H->Capacity; ++i) {
        T = (HuffmanTree)malloc(sizeof(struct TreeNode));
        T->Left = DeleteMin(H);
        T->Right = DeleteMin(H);
        T->weight = T->Left->weight + T->Right->weight;
        Insert(H, T);
        wpl += T->weight;
    }
    T = DeleteMin(H);
    DestoryHeap(H);
    DestoryHuffmanTree(T);    // 销毁Huffman树所占空间
    return wpl;
}

void init_codeArr(char *code)   // 初始化code数组每个元素为\0
{
    int i;
    for (i = 0; i < MAXCODESIZE && code[i] != '\0'; ++i)
        code[i] = '\0';
}

HuffmanTree createTreeNode()
{
    HuffmanTree HT;
    HT = (HuffmanTree)malloc(sizeof(struct TreeNode));
    HT->weight = 1; HT->Left = 0; HT->Right = 0;
    return HT;
}

// 这里使用struct TreeNode结构体，其中的weight用来表示是否为本次code新添加结点，若是则为1，否则为0
HuffmanTree RecoverHFTreeByCode(HuffmanTree HT, char *code, int *flag, int *counter)
{
    int i;  HuffmanTree node;
    if (!HT) {
        HT = createTreeNode();
        ++(*counter);
    }
    for (i = 0, node = HT; code[i] != '\0';  ++i) {
        // 第一种情况：该结点不是新添加结点，并且没有左右孩子，即之前字符对应的子节点
        // 说明之前某字符编码是该编码的前缀码
        if (node->weight == 0 && !node->Left && !node->Right) {
            (*flag) = 0;
            break;
        }
        node->weight = 0;
        if (code[i] == '0') {   // 读到0向左孩子走一位
            if (!node->Left) {
                node->Left = createTreeNode();
                ++(*counter);
            }
            node = node->Left;
        } else {
            if (!node->Right) {
                node->Right = createTreeNode();
                ++(*counter);
            }
            node = node->Right;
        }
    }
    // 第二种情况：读完所有code后，该位置有孩子结点，说明该编码是之前某字符编码的前缀码
    if (node->Left || node->Right)
        (*flag) = 0;
    return HT;
}

void check_code(int *freq_arr, int n, int wpl)
{
    int i, sum_wpl, flag, counter; char c;
    HuffmanTree HT;
    char code[MAXCODESIZE] = "\0";
    sum_wpl = 0; flag = 1; counter = 0; HT = 0;
    for (i = 0; i < n; ++i) {
        init_codeArr(code);
        scanf("\n%c %s", &c, code);
        if (flag) { // 判断该次提交是否已经不正确了，如果还正确则继续处理
            sum_wpl += strlen(code) * freq_arr[i];
            HT = RecoverHFTreeByCode(HT, code, &flag, &counter);
        }
    }
    // 这里有三个判断条件
    // 1. 提交的总wpl与预设的完全相同
    // 2. 没有前缀码情况出现，此处用flag标识
    // 3. 没有度为1的结点，此处的counter表示生成的Huffman树结点数，如果正确应该等于2*n-1，n为叶节点个数，即所有字符数
    if (sum_wpl == wpl && flag && counter == 2 * n - 1)
        printf("Yes\n");
    else
        printf("No\n");
    DestoryHuffmanTree(HT);
}

int main()
{
    int n, m, i, wpl;
    int *freq_arr;
    scanf("%d\n", &n);

    freq_arr = readPair(n);     // 读入所有字符及其对应频率
    wpl = HuffmanTreeWPL(freq_arr, n);    // 根据读入字符及频率使用小顶堆建立Huffman树求得WPL值

    scanf("%d", &m);
    for (i = 0; i < m; ++i) {
        check_code(freq_arr, n, wpl);
    }

    DestoryCharFreq(freq_arr);

    return 0;
}