2016/11/10 1004. Huffman Coding V1

// Problem#: 19625
// Submission#: 4906423
// The source code is licensed under Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License
// URI: http://creativecommons.org/licenses/by-nc-sa/3.0/ // All Copyright reserved by Informatic Lab of Sun Yat-sen University
// Problem#: 19625
// Submission#: 4906106
// The source code is licensed under Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Unported License
// URI: http://creativecommons.org/licenses/by-nc-sa/3.0/ // All Copyright reserved by Informatic Lab of Sun Yat-sen University
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#define MAX  27
#define MAX_INT  99999

//哈夫曼树和哈夫曼编码的存储表示
typedef struct
{
int weight;
int parent,lchild,rchild;
} HTNode,*HuffmanTree; // 动态分配数组存储哈夫曼树

typedef char **HuffmanCode;

typedef struct Charnode
{
char c;
int weight;
}CharNode,*CharNodePtr;//不要定义为Char

CharNode *b;

int Chat_get()
{
char c;
int j=0;
int m;
int i;
scanf("%d",&m);
getchar();
b=(CharNodePtr)malloc(sizeof(CharNode)*MAX);
int a[MAX];
for(i=0;i<MAX;i++)
{
a[i]=0;
}
for(i=0;i<m;i++)
{
scanf("%c",&c);
getchar();
a[c-'A']++;
}
for(i=0;i<26;i++)
{
if(a[i]!=0)
{
b[j].c=char(i+'A');
b[j].weight=a[i];
j++;
}
}
return j;
}//得到不同字符的个数和数组

int min(HuffmanTree t,int i)
{
int j,flag;
int k=MAX_INT; // 取k为不小于可能的值
for(j=1; j<=i; j++)
if(t[j].weight<k&&t[j].parent==0)
k=t[j].weight,flag=j;
t[flag].parent=1;
return flag;
}

//本实习题中右子树是最小值对应序号，左子树是次小值对应序号
void select(HuffmanTree t,int i,int &s1,int &s2)
{
s2=min(t,i);
s1=min(t,i);
}

void PrintHuffmanTree(HuffmanTree &HT,HuffmanCode &HC, int n)
{
int i, c, cdlen;
char *cd;
HC=(HuffmanCode)malloc((n+1)*sizeof(char*));
// 分配n个字符编码的头指针向量([0]不用)
cd=(char*)malloc(n*sizeof(char)); // 分配求编码的工作空间
c=2*n-1;
cdlen=0;
for(i=0; i<=c; ++i) HT[i].weight=0; // 遍历赫夫曼树时用作结点状态标志
while(c)
{
if(HT[c].weight==0)   // 向左
{
HT[c].weight=1;
if(HT[c].lchild==0 && HT[c].rchild==0)  // 登记叶子结点字符编码
{
HC[c]=(char *)malloc((cdlen+1)*sizeof(char));
cd[cdlen]='\0';
strcpy(HC[c],cd); // 复制编码(串)
}
if(HT[c].lchild!=0)
{
c=HT[c].lchild;
cd[cdlen++]='1';
}
}
else if(HT[c].weight==1)   // 向右
{
HT[c].weight=2;
if(HT[c].rchild!=0)
{
c=HT[c].rchild;
cd[cdlen++]='0';
}
}
else
{
HT[c].weight=0;
c=HT[c].parent;
--cdlen; //
4000
退到父结点,编码长度减1
}
}
free(cd);
}

// w存放n个字符的权值(均>0),构造哈夫曼树HT,并求出n个字符的哈夫曼编码HC
void HuffmanCoding(HuffmanTree &HT,HuffmanCode &HC,int *w,int n)
{
int m,i,s1,s2;

HuffmanTree p;

if(n<=1)   exit(0);
m=2*n-1;
HT=(HuffmanTree)malloc((m+1)*sizeof(HTNode)); // 0号单元未用
//因为0号单元未用，处理数据时候从1号单元开始
for(p=HT+1,i=1; i<=n; ++i,++p,++w)
{
(*p).weight=*w;
(*p).parent=0;
(*p).lchild=0;
(*p).rchild=0;
}
for(; i<=m; ++i,++p)  (*p).parent=0;
// 在HT[1~i-1]中选择parent为0且weight最小的两个结点,其序号分别为s1和s2
for(i=n+1; i<=m; ++i)   // 建哈夫曼树
{
select(HT,i-1,s1,s2);
HT[s1].parent=HT[s2].parent=i;
HT[i].lchild=s1;
HT[i].rchild=s2;
HT[i].weight=HT[s1].weight+HT[s2].weight;
}
//顺序输出哈夫曼树
PrintHuffmanTree(HT, HC, n);
}

void sort_b(int k)
{
int n;
char c;
int i,j;
for(i=0;i<k;i++)
{
for(j=k-1;j>=i;j--)
{
if(b[j].weight>b[j-1].weight)
{
n=b[j].weight; b[j].weight=b[j-1].weight;b[j-1].weight=n;
c=b[j].c; b[j].c=b[j-1].c; b[j-1].c=c;
}
}
}
}

int main()
{
int k;
int j;
int i;
HuffmanTree HT;
HuffmanCode HC;
k=Chat_get();
int *w;
w=(int *)malloc(sizeof(int)*k);
sort_b(k);
for(i=0;i<k;i++)
{
w[i]=b[i].weight;
}
HuffmanCoding(HT,HC,w,k);
for(i=0,j=1;i<k;j++,i++)
{
printf("%c %d %s\n",b[i].c,b[i].weight,HC[j]);
}
return 0;
}