关于对哈夫曼树解码的最后一个字节的处理

由韩顺平老师的网课代码,其对哈夫曼树解码的最后一个字节可能会出现bug

在此提出解决方法,在压缩过程中多开辟一个空间用于存储最后一个字节的长度

这是全部代码

class HuffmanCode {
    //哈夫曼编码对应map
    private static Map<Byte, String> huffmanCodes = new HashMap<Byte, String>();
    //stringBuilder用于拼接路径
    private static StringBuilder stringBuilder = new StringBuilder();

    public static List<Node> getNodes(String s) {
        return getNodes(s.getBytes());
    }

    //根据数据生成一个列表
    private static List<Node> getNodes(byte[] bytes) {
        List<Node> list = new ArrayList<>();
        Map<Byte, Integer> map = new HashMap<>();
        for (int i = 0; i < bytes.length; i++) {
            if (map.get(bytes[i]) == null) {
                map.put(bytes[i], 1);
            } else {
                map.put(bytes[i], map.get(bytes[i]) + 1);
            }
        }
        for (Map.Entry<Byte, Integer> byteIntegerEntry : map.entrySet()) {
            list.add(new Node(byteIntegerEntry.getKey(), byteIntegerEntry.getValue()));
        }
        return list;
    }

    //根据列表生成一个哈夫曼树
    public static Node createHuffmanTree(List<Node> list) {
        while (list.size() > 1) {
            Collections.sort(list);
            Node node1 = list.remove(0);
            Node node2 = list.remove(0);
            Node node = new Node(null, node1.weight + node2.weight);
            node.left = node1;
            node.right = node2;
            list.add(node);
        }
        return list.remove(0);
    }

    //获取编码
    private static void getCodes(Node node, String code, StringBuilder stringBuilder) {
        StringBuilder stringBuilder1 = new StringBuilder(stringBuilder);
        stringBuilder1.append(code);
        if (node != null) {
            if (node.data == null) {
                getCodes(node.left, "0", stringBuilder1);
                getCodes(node.right, "1", stringBuilder1);
            } else {
                huffmanCodes.put(node.data, stringBuilder1.toString());
            }
        }
    }

    //重载一下
    public static Map getCodes(Node root) {
        if (root == null) {
            return null;
        }
        getCodes(root.left, "0", stringBuilder);
        getCodes(root.right, "1", stringBuilder);
        return huffmanCodes;
    }

    //获取编码表【最终】
    public static Map<Byte, String> get(String s) {
        return getCodes(createHuffmanTree(getNodes(s)));
    }

    //压缩
    public static byte[] zip(byte[] bytes, Map<Byte, String> huffmanCodes) {
        StringBuilder stringBuilder1 = new StringBuilder();
        for (int i = 0; i < bytes.length; i++) {
            stringBuilder1.append(huffmanCodes.get(bytes[i]));
        }
        int len;
        if (stringBuilder1.length() % 8 == 0) {
            len = stringBuilder1.length() / 8;
        } else {
            len = stringBuilder1.length() / 8 + 1;
        }
        byte[] huffmanCodeBytes = new byte[len + 1];
        int index = 0;
        int length = 0;
        for (int i = 0; i < stringBuilder1.length(); i += 8) {
            String str;
            if (i + 8 > stringBuilder1.length()) {
                str = stringBuilder1.substring(i);
                //huffmanCodeBytes最后一个空间存储 最后一个字符串的长度

                length = str.length();
            } else {
                str = stringBuilder1.substring(i, i + 8);
            }
            huffmanCodeBytes[index] = (byte) Integer.parseInt(str, 2);
            index++;
        }
        huffmanCodeBytes[index] = (byte) length;
        //倒数第二个一定为正数,因为其的位数最多为七位
        return huffmanCodeBytes;
    }

    //重载一下
    public static byte[] zip(String s) {
        return zip(s.getBytes(), huffmanCodes);
    }

    //解压
    //生成对应的字符串
    public static String byteToBitString(boolean flag, byte b) {
        int tmp = b;
        if (flag) {
            tmp |= 256;
        }
        String str = Integer.toBinaryString(tmp);
        return str.substring(str.length() - 8);
    }

    //正式解压
    public static byte[] decode(byte[] huffmanCodeBytes) {
        boolean flag = false;
        StringBuilder stringBuilder1 = new StringBuilder();
        for (int i = 0; i < huffmanCodeBytes.length - 1; i++) {
            if (i == huffmanCodeBytes.length - 2) {
                String string = new String();
                string += Integer.toBinaryString(huffmanCodeBytes[i]);
                while ((int) huffmanCodeBytes[i + 1] > string.length()) {
                    string = "0" + string;
                }
                stringBuilder1.append(string);
            } else {
                if (huffmanCodeBytes[i] >= 0) {
                    stringBuilder1.append(byteToBitString(true, huffmanCodeBytes[i]));
                } else {
                    stringBuilder1.append(byteToBitString(false, huffmanCodeBytes[i]));
                }
            }
        }
        //把huffmanCodes倒置
        Map<String, Byte> map = new HashMap<>();
        for (Map.Entry<Byte, String> entry : huffmanCodes.entrySet()) {
            map.put(entry.getValue(), entry.getKey());
        }

        List list = new ArrayList();
        Byte b = null;
        int count;
        boolean loop = true;
        String key;
        int i = 0;
        while (i < stringBuilder1.length()) {
            count = 1;
            loop = true;
            while (loop) {
                key = stringBuilder1.substring(i, i + count);
                b = map.get(key);
                if (b == null) {
                    count++;
                } else {
                    loop = false;
                }
            }
            list.add(b);
            i = i + count;
        }

        byte[] bytes = new byte[list.size()];
        for (int j = 0; j < bytes.length; j++) {
            bytes[j] = (Byte) list.get(j);
        }
        return bytes;
    }
}

class Node implements Comparable {
    Byte data;
    int weight;
    Node left;
    Node right;


    public Node(Byte data, int weight) {
        this.data = data;
        this.weight = weight;
    }

    @Override
    public int compareTo(Object o) {
        return this.weight - ((Node) o).weight;
    }
}

  • 0
    点赞
  • 0
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
#include #include #include #include using namespace std; # define MaxN 100//初始设定的最大结点数 # define MaxC 1000//最大编码长度 # define ImpossibleWeight 10000//结点不可能达到的权值 # define n 26//字符集的个数 //-----------哈夫曼树的结点结构类型定义----------- typedef struct //定义哈夫曼树各结点 { int weight;//权值 int parent;//双亲结点下标 int lchild;//左孩子结点下标 int rchild;//右孩子结点下标 }HTNode,*HuffmanTree;//动态分配数组存储哈夫曼树 typedef char**HuffmanCode;//动态分配数组存储哈夫曼编码表 //-------全局变量-------- HuffmanTree HT; HuffmanCode HC; int *w;//权值数组 //const int n=26;//字符集的个数 char *info;//字符值数组 int flag=0;//初始化标记 //********************************************************************** //初始化函数 //函数功能: 从终端读入字符集大小n , 以及n个字符和n个权值,建立哈夫曼树,并将它存于文件hfmTree中 //函数参数: //向量HT的前n个分量表示叶子结点,最后一个分量表示根结点,各字符的编码长度不等,所以按实际长度动态分配空间 void Select(HuffmanTree t,int i,int &s1,int &s2) { //s1为最小的两个值中序号最小的那个 int j; int k=ImpossibleWeight;//k的初值为不可能达到的最大权值 for(j=1;j<=i;j++) { if(t[j].weight<k&&t[j].parent==0) {k=t[j].weight; s1=j;} } t[s1].parent=1; k=ImpossibleWeight; for(j=1;j<=i;j++) { if(t[j].weight0),构造哈夫曼树HT,并求出n个字符的哈弗曼编码HC { int i,m,c,s1,s2,start,f; HuffmanTree p; char* cd; if(num<=1) return; m=2*num-1;//m为结点数,一棵有n个叶子结点的哈夫曼树共有2n-1个结点,可以存储在一个大小为2n-1的一维数组中 HT=(HuffmanTree)malloc((m+1)*sizeof(HTNode));//0号单元未用 //--------初始化哈弗曼树------- for(p=HT+1,i=1;iweight=*w; p->parent=0; p->lchild=0; p->rchild=0; } for(i=num+1;iweight=0; p->parent=0; p->lchild=0; p->rchild=0; } //--------建哈夫曼树------------- for(i=num+1;i<=m;i++) { Select(HT,i-1,s1,s2);//在HT[1...i-1]选择parent为0且weight最小的两个结点,其序号分别为s1和s2 HT[s1].parent=i; HT[s2].parent=i; HT[i].lchild=s1; HT[i].rchild=s2;//左孩子权值小,右孩子权值大 HT[i].weight=HT[s1].weight+HT[s2].weight; } //-------从叶子到根逆向求每个字符的哈弗曼编码-------- HC=(HuffmanCode)malloc((num+1)*sizeof(char *));//指针数组:分配n个字符编码的头指针向量 cd=(char*)malloc(n*sizeof(char*));//分配求编码的工作空间 cd[n-1]='\0';//编码结束符 for(i=1;i<=n;i++)//逐个字符求哈弗曼编码 { start=n-1;//编码结束符位置 for(c=i,f=HT[i].parent;f!=0;c=f,f=HT[f].parent)//从叶子到跟逆向求哈弗曼编码 if(HT[f].lchild==c) cd[--start]='0';//判断是左孩子还是右孩子(左为0右为1) else cd[--start]='1'; HC[i]=(char*)malloc((num-start)*sizeof(char*));//按所需长度分配空间 int j,h; strcpy(HC[i],&cd[start]); } free(cd); } //****************初始化函数****************** void Initialization() { flag=1;//标记为已初始化 int i; w=(int*)malloc(n*sizeof(int));//为26个字符权值分配空间 info=(char*)malloc(n*sizeof(char));//为26个字符分配空间 ifstream infile("ABC.txt",ios::in); if(!infile) { cerr<<"打开失败"<<endl; exit(1); } for(i=0;i>info[i]; infile>>w[i]; } infile.close(); cout<<"读入字符成功!"<<endl; HuffmanCoding(HT,HC,w,n); //------------打印编码----------- cout<<"依次显示各个字符的值,权值或频度,编码如下"<<endl; cout<<"字符"<<setw(6)<<"权值"<<setw(11)<<"编码"<<endl; for(i=0;i<n;i++) { cout<<setw(3)<<info[i]; cout<<setw(6)<<w[i]<<setw(12)<<HC[i+1]<<endl; } //---------将建好的哈夫曼树写入文件------------ cout<<"下面将哈夫曼树写入文件"<<endl; ofstream outfile("hfmTree.txt",ios::out); if(!outfile) { cerr<<"打开失败"<<endl; exit(1); } for(i=0;i<n;i++,w++) { outfile<<info[i]<<" "; outfile<<w[i]<<" "; outfile<<HC[i+1]<<" "; } outfile.close(); cout<<"已经将字符与对应的权值,编码写入根目录下文件hfmTree.txt"<<endl; } //*****************输入待编码字符函数************************* void Input() { char string[100]; ofstream outfile("ToBeTran.txt",ios::out); if(!outfile) { cerr<<"打开失败"<<endl; exit(1); } cout<<"请输入你想要编码的字符串(字符个数应小于100),以#结束"<>string; for(int i=0;string[i]!='\0';i++) { if(string[i]=='\0') break; outfile<<string[i]; } cout<<"获取报文成功"<<endl; outfile.close(); cout<<"------"<<"已经将报文存入根目录下的ToBeTran.txt文件"<<endl; } //******************编码函数**************** void Encoding() { int i,j; char*string; string=(char*)malloc(MaxN*sizeof(char)); cout<<"下面对根目录下的ToBeTran.txt文件中的字符进行编码"<<endl; ifstream infile("ToBeTran.txt",ios::in); if(!infile) { cerr<<"打开失败"<<endl; exit(1); } for(i=0;i>string[i]; } for(i=0;i<100;i++) if(string[i]!='#') cout<<string[i]; else break; infile.close(); ofstream outfile("CodeFile.txt",ios::out); if(!outfile) { cerr<<"打开失败"<<endl; exit(1); } for(i=0;string[i]!='#';i++) { for(j=0;j<n;j++) { if(string[i]==info[j]) outfile<<HC[j+1]; } } outfile<<'#'; outfile.close(); free(string); cout<<"编码完成------"; cout<<"编码已写入根目录下的文件CodeFile.txt中"<<endl; } //******************译码函数**************** void Decoding() { int j=0,i; char *code; code=(char*)malloc(MaxC*sizeof(char)); char*string; string=(char*)malloc(MaxN*sizeof(char)); cout<<"下面对根目录下的CodeFile.txt文件中的代码进行译码"<<endl; ifstream infile("CodeFile.txt",ios::in); if(!infile) { cerr<<"打开失败"<<endl; exit(1); } for( i=0;i>code[i]; if(code[i]!='#') { cout<<code[i]; } else break; } infile.close(); int m=2*n-1; for(i=0;code[i-1]!='#';i++) { if(HT[m].lchild==0) { string[j]=info[m-1]; j++; m=2*n-1; i--; } else if(code[i]=='1') m=HT[m].rchild; else if(code[i]=='0') m=HT[m].lchild; } string[j]='#'; ofstream outfile("TextFile.txt",ios::out); if(!outfile) { cerr<<"打开失败"<<endl; exit(1); } cout<<"的译码为------"<<endl; for( i=0;string[i]!='#';i++) { outfile<<string[i]; cout<<string[i]; } outfile<<'#'; outfile.close(); cout<<"------译码完成------"<<endl; cout<<"译码结果已写入根目录下的文件TextFile.txt中"<<endl; free(code); free(string); } //*************打印编码函数**************** void Code_printing() { int i; char *code; code=(char*)malloc(MaxC*sizeof(char)); cout<<"下面打印根目录下文件CodeFile.txt中的编码"<<endl; ifstream infile("CodeFile.txt",ios::in); if(!infile) { cerr<<"打开失败"<<endl; exit(1); } for( i=0;i>code[i]; if(code[i]!='#') cout<<code[i]; else break; } infile.close(); cout<<endl; ofstream outfile("CodePrin.txt",ios::out); if(!outfile) { cerr<<"打开失败"<<endl; exit(1); } for(i=0;code[i]!='#';i++) { outfile<<code[i]; } outfile.close(); free(code); cout<<"------打印结束------"<<endl; cout<<"该字符形式的编码文件已写入文件CodePrin.txt中"<<endl; } //*************打印哈夫曼树函数**************** int numb=0; void coprint(HuffmanTree start,HuffmanTree HT) //start=ht+26这是一个递归算法 { if(start!=HT) { ofstream outfile("TreePrint.txt",ios::out); if(!outfile) { cerr<<"打开失败"<rchild,HT); //递归先序遍历 cout<<setw(5*numb)<weight<rchild==0) cout<<info[start-HT-1]<<endl; outfile<weight; coprint(HT+start->lchild,HT); numb--; outfile.close(); } } void Tree_printing(HuffmanTree HT,int num) { HuffmanTree p; p=HT+2*num-1; //p=HT+26 cout<<"下面打印赫夫曼树"<<endl; coprint(p,HT); //p=HT+26 cout<<"打印工作结束"<<endl; } //*************主函数************************** int main() { char choice; do{ cout<<"************哈弗曼编/译码器系统***************"<<endl; cout<<"请选择您所需功能:"<<endl; cout<<":初始化哈弗曼树"<<endl; cout<<":输入待编码字符串"<<endl; cout<<":利用已建好的哈夫曼树进行编码"<<endl; cout<<":利用已建好的哈夫曼树进行译码"<<endl; cout<<":打印代码文件"<<endl; cout<<":打印哈夫曼树"<<endl; cout<<":退出"<<endl; if(flag==0) { cout<<"请先初始化哈夫曼树,输入I"<<endl; cout<<""<>choice; switch(choice) { case 'I':Initialization();break; case 'W':Input();break; case 'E':Encoding();break; case 'D':Decoding();break; case 'P':Code_printing();break; case 'T':Tree_printing(HT,n);break; case 'Q':;break; default:cout<<"输入的命令出错,请重新输入!"<<endl; } }while(choice!='Q'); free(w); free(info); free(HT); free(HC); system("pause"); return 0; }

“相关推荐”对你有帮助么?

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值