要求:从一文件中读取字符,统计该文件中各个字符(如abc…等26个字符)出现的概率,根据各自的概率为权值,为这些字符建立一颗哈夫曼树,并对每个字符进行哈夫曼编码和哈夫曼解码。要求具有较好的变量命名和较好人机交互处理过程。
代码:
#include <stdio.h>
#include <stdlib.h>
#include <malloc.h>
#include <string.h>
struct Data
{
char capital;
char small;
int count;
};
typedef struct
{
double weight;
int parent,lchild,rchild;
}HTNode,*HuffmanTree;
typedef char **HuffmanCode;
void Select(HuffmanTree &HT,int n,int &s1,int &s2)//找出其中权值最小的两个并记下其位置s1,s2
{
int i=1;
double min, secondmin;
min=secondmin=1;
for(i=1;i<=n;i++)
{
if(HT[i].weight<min&&HT[i].parent==0)
{
min=HT[i].weight;
s1=i;
}
}
HT[s1].parent=1; //将s1的parent变为1,避免与下面找s2冲突
for(i=1;i<=n;i++)
{
if(HT[i].weight<secondmin&&HT[i].parent==0)
{
secondmin=HT[i].weight;
s2=i;
}
}
//printf("%d ",s1); //调试输出
//printf("%d\n",s2);
}
void HuffmanCoding(HuffmanTree &HT,HuffmanCode &HC,double *w,int n)
{
if(n<=1) return;
int m=2*n-1;
HT=(HuffmanTree)malloc((m+1)*sizeof(HTNode));
if(HT==NULL)
{
printf("no enough money");
exit(1);
}
int i;
HuffmanTree p;
for(p=HT+1,i=1;i<=n;++i,++p)
{
p->weight=w[i-1];
p->lchild=0;
p->parent=0;
p->rchild=0;
}
for(;i<=m;++i,++p)
{
p->weight=0;
p->lchild=0;
p->parent=0;
p->rchild=0;
}
for(i=n+1;i<=m;++i)
{
int s1=0,s2=0;
Select(HT,i-1,s1,s2);
HT[s1].parent=i;
HT[s2].parent=i;
HT[i].lchild=s1;
HT[i].rchild=s2;
HT[i].weight=HT[s1].weight+HT[s2].weight;
}
HC = (HuffmanCode)malloc((n+1)*sizeof(char*));
if(HC==NULL)
{
printf("no enough money");
exit(1);
}
char* cd;
cd = (char*)malloc(n*sizeof(char));
cd[n-1]='\0';
for(i=1;i<=n;++i)
{
int start;
start=n-1;
int c,f;
for(c=i,f=HT[i].parent;f!=0;c=f,f=HT[f].parent)
{
if(HT[f].lchild==c)
{
cd[--start]='0';
}
else cd[--start]='1';
}
HC[i]=(char*)malloc((n-start)*sizeof(char));
strcpy(HC[i],&cd[start]);
}
free(cd);
}
void decode(HuffmanTree &HT,int n,char *Letter)
{
int root=2*n-1;
char code [100];
printf("请输入哈夫曼密码(0或1):");
int i=0,j=root;
gets(code);
int length=0;
for(i=0;i<100;i++)
{
if(code[i]=='0'||code[i]=='1')
{
length++;
}
else
{
break;
}
}
printf("%d\n",length);
printf("解码结果如下:\n");
for(i=0;i<length;i++)
{
if(code[i]=='0')
{
j=HT[j].lchild;
}
else if(code[i]=='1')
{
j=HT[j].rchild;
}
if(HT[j].lchild==0&&HT[j].rchild==0)
{
printf("%c",Letter[j-1]);
j=root;
}
}
}
int main()
{
struct Data letter[26];
int num,figure;
for(num=0,figure=65;num<26;num++,figure++)
{
letter[num].capital=figure;
letter[num].small=figure+32;
letter[num].count=0;
}
FILE *fp=NULL;
if((fp=fopen("D:/HUFFMAN/Huffman.txt","r"))==NULL)
{
printf("打开文件失败!");
system("pause");
exit(0);
}
char ch;
int i,j;
while((ch=fgetc(fp))!=EOF)
{
for(i=0;i<26;i++)
{
if(ch==letter[i].capital||ch==letter[i].small)
{
letter[i].count++;
}
}
}
/*for(i=0;i<26;i++)
{
printf("%d ",letter[i].count); //调试输出
}*/
int sum=0;
for(i=0;i<26;i++)
{
sum +=letter[i].count; //所有字母个数,便于计算概率
}
//printf("\n%d\n",sum); //调试输出
int n=0; //n是文本中出现的字母种数(0<=n<=26)
for(i=0;i<26;i++)
{
if(letter[i].count!=0)
{
n++;
}
}
//printf("%d\n",n); //调试输出
char Letter[n];
for(i=0,j=0;i<26&&j<n;i++)
{
if(letter[i].count!=0)
{
Letter[j]=letter[i].small;
j++;
}
}
double weight[n];
for(i=0,j=0;i<26&&j<n;i++)
{
if(letter[i].count!=0)
{
weight[j]=letter[i].count*1.0/sum*1.0;
j++;
}
}
/*for(i=0;i<n;i++)
{
printf("%lf ",weight[i]); //调试输出
}
printf("\n");*/
HuffmanTree letterTree;
HuffmanCode letterCode;
HuffmanCoding(letterTree,letterCode,weight,n);
printf("文本中出现的字母的哈夫曼编码如下:\n");
for(i=1;i<=n;i++)
{
printf("%c:",Letter[i-1]);
puts(letterCode[i]);
}
decode(letterTree,n,Letter);
free(letterTree);
free(letterCode);
fclose(fp);
return 0;
}
运行截图:
说明:代码使用的都是最基础的C语言,编译器用的DevC++5.11,本人较菜,如有错误,欢迎指正。