2021-04-22

05-树9 Huffman Codes (30 分)

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

#define _CRT_SECURE_NO_WARNINGS
#include<stdio.h>
#include<stdlib.h>
#include<stdio.h>
#include<stdlib.h>
#include<stdbool.h>
#include<string.h>
typedef int ElementType2;
typedef struct HNode* Heap;
#define MinSize 0
typedef struct Haffman_Node_ {
	bool Flag;//是否为字符的标识1的话是
	int Depth;
	ElementType2 weight;
	struct Haffman_Node_* left;
	struct Haffman_Node_* right;
}HaffmanNode;
typedef struct Haffman_Node_* HaffmanTree;

typedef HaffmanNode ElementType;
struct HNode {
	ElementType* Data;
	int Capacity;
	int Size;//当前大小
};

typedef Heap MinHeap;
Heap CreateHeap(int n);
void Get_Num(MinHeap a, int n, int* Weight);
void Arrange_MinHeap(MinHeap a);//创建最小堆
ElementType Delete_MinHeap(MinHeap a);
int IsEmpty(Heap a);
HaffmanTree CreateHaffmanTree(Heap a);
void PreTraverseTree(HaffmanTree a);
bool Prefix_Judge(char* a, char* b);
void GetDepth(HaffmanTree a);//获取树节点深度
int BestLength=0;
int main()
{
	int N;//生成堆的大小
	int M;//判断几组
	char c;
	scanf("%d", &N);
	Heap a = CreateHeap(N + 10);
	int* Weight = (int*)malloc(sizeof(int) * N+1);
	Get_Num(a, N, Weight);
	Arrange_MinHeap(a);
	ElementType* Tree1 = CreateHaffmanTree(a);
	Tree1->Depth = 1;
	GetDepth(Tree1);
	PreTraverseTree(Tree1);
	scanf("%d", &M);
	char*** S = (char***)malloc(sizeof(char**) * M);
	for (int i = 0; i < M; i++)
	{
		S[i] = (char**)malloc(sizeof(char*) * N);
		for (int j = 0; j < N; j++)
		{
			S[i][j] = (char*)malloc(sizeof(char) * 65);
		}
	}

	for (int i = 0; i < M; i++)
	{
		for (int j = 0; j < N; j++)
		{
			scanf(" %c", &c);
			scanf("%s", S[i][j]);
		}
	}
	for (int k = 0; k < M; k++)
	{
		int PrefixJudge = 0;
		int CodeLength = 0;
		for (int i = 0; i < N; i++)
		{
			for (int j = 0; j < N; j++)
			{
				if (i == j)
				{
					continue;
				}
				if (Prefix_Judge(S[k][i], S[k][j]) == 1)
				{
					PrefixJudge = 1;
					break;
				}
			}
			if (PrefixJudge == 1)
			{
				break;
			}


		}
		if (PrefixJudge == 1)
		{
			printf("No\n");

		}
		else
		{
			for (int i = 0; i < N; i++)
				CodeLength = CodeLength + Weight[i+1] * strlen(S[k][i]);
			if (CodeLength == BestLength)

			{
				printf("Yes\n");
			}
			
			else
			{
				
					printf("No\n");
			}
		}
	}
	
}
Heap CreateHeap(int n)//创建一个最大承载n个节点的堆
{
	Heap a = (Heap)malloc(sizeof(struct HNode));
	a->Data = (ElementType*)malloc((n + 1) * sizeof(ElementType));//Data是一个指向ElementType的指针
	a->Capacity = n;
	a->Size = 0;
	a->Data[0].weight = MinSize;
	return a;
}
void Get_Num(MinHeap a, int n,int*Weight)//对堆进行初始化
{
	char c;
	if (a->Size <= n)
	{
		for (int i = 1; i <= n; i++)
		{
			scanf(" %c", &c);
			scanf("%d", &((a->Data) + i)->weight);
			Weight[i] = ((a->Data) + i)->weight;
		}
		for (int i = 0; i <= n; i++)
		{
			a->Data[i].left = NULL;
			a->Data[i].right = NULL;
			a->Data[i].Flag = 1;
		}
		a->Size = n;
	}

}
/**/

void Arrange_MinHeap(MinHeap a)/*创建最小堆在测试过程中我发现了我的思维误区:Parent
							   节点下移后应该和子节点判断是否是最小的,此函数就是从最后一个子节点的父节点处开始
							   子节点有比它小的就把这个父节点拽下来*/
{
	int Parent, Child;
	ElementType2 t;
	for (int i = a->Size / 2; i > 0; i--)
	{
		t = a->Data[i].weight;
		for (Parent = i; Parent * 2 <= a->Size; Parent = Child)
		{
			Child = 2 * Parent;
			if (Child + 1 <= a->Size && a->Data[Child + 1].weight < a->Data[Child].weight)
				Child = Child + 1;
			if (a->Data[Child].weight > t)
				break;
			else
				a->Data[Parent].weight = a->Data[Child].weight;

		}
		a->Data[Parent].weight = t;
	}
}
ElementType Delete_MinHeap(MinHeap a)//返回被删除的节点
{
	if (!IsEmpty(a))
	{
		int Parent, Child;
		ElementType t;
		ElementType MinElement;
		MinElement = a->Data[1];
		a->Data[1] = a->Data[a->Size];
		a->Size -= 1;
		t = a->Data[1];

		for (Parent = 1; Parent * 2 <= a->Size; Parent = Child)
		{
			Child = 2 * Parent;
			if (Child + 1 <= a->Size && a->Data[Child].weight >= a->Data[Child + 1].weight)
				Child++;
			if (t.weight < a->Data[Child].weight)
				break;
			else
				a->Data[Parent] = a->Data[Child];

		}
		a->Data[Parent] = t;
		return MinElement;//返回被删除的节点
	}

}
int Insert_MinHeap(MinHeap a, ElementType k)/*如果父节点比它大,父节点下移*/
{
	int  Child;
	if (a->Size == a->Capacity)
		return 0;
	else
		Child = ++a->Size;
	for (; a->Data[Child / 2].weight > k.weight; Child = Child / 2)//这样就不需要额外声名parent
	{

		a->Data[Child] = a->Data[Child / 2];
	}
	a->Data[Child] = k;
	return 1;

}
int IsEmpty(Heap a)
{
	if (a->Size == 0)
		return 1;
	else
		return 0;
}
/*哈夫曼树:要查找的元素必须在叶结点上,从所有节点中找两个最小的,合成一个二叉树
根节点是两个节点值的和,然后用新的根节点和之前的叶节点比较,最小的两个合并....这
符合上面的权重大,下面的权重小的趋势,但为什么这个是最优的方法呢*/
/*和最小堆之间的关系:我把节点放在最小堆里面,找出最小的两个节点(delete)删除然后插
入新合成的节点*/
HaffmanTree CreateHaffmanTree(Heap a)
{
	if (a->Size == 0)
		return NULL;

	else
	{
		while (a->Size != 1)
		{
			ElementType* Ptr1 = (ElementType*)malloc(sizeof(ElementType));
			ElementType* Ptr2 = (ElementType*)malloc(sizeof(ElementType));
			*Ptr1 = Delete_MinHeap(a);
			*Ptr2 = Delete_MinHeap(a);
			HaffmanNode NewNode;
			NewNode.weight = Ptr1->weight + Ptr2->weight;
			NewNode.left = Ptr1;
			NewNode.right = Ptr2;
			NewNode.Flag = 0;
			Insert_MinHeap(a, NewNode);
		}

		return &a->Data[1];
	}


}
void PreTraverseTree(HaffmanTree a)
{
	if (a)
	{
		BestLength = BestLength+ a->Flag * (a->Depth - 1) * (a->weight);
		PreTraverseTree(a->left);
		PreTraverseTree(a->right);
	}
}
bool Prefix_Judge(char* a, char* b)//判断a是否是b的前缀
{
	int k = strlen(a);
	if (k > strlen(b))
		return false;//不是
	else
	{
		for (int i = 0; i < k; i++)
		{
			if (*(a + i) != *(b + i))
				return false;
		}
	}
	return true;//是前缀
}
void GetDepth(HaffmanTree a)//获取树节点高度
{
	if (a->left)
	{
		a->left->Depth = a->Depth + 1;
		GetDepth(a->left);
	}
	if (a->right)
	{
		a->right->Depth = a->Depth + 1;
		GetDepth(a->right);
	}

}

有趣,只需知道huffman可以找到BestLength以及一个字符的编码不能是另一个字符的前缀就OK了