Huffman压缩和解压txt

Huffman的原理大家都应该很清楚，今天尝试用它来压缩txt文件和解压，txt中只含有英文，中文的编码我不清楚，所以遇到后就会吃掉

#define _CRT_SECURE_NO_WARNINGS
#include<iostream>
#include<string>
#include<fstream>
#include<vector>
#include<algorithm>
#include<queue>
#include<time.h>
#include<map>
using namespace std;
/***********************************                  Hufman                        **********************************************************/
const int BIGSIZE = 260;
long long cpcount[BIGSIZE] = { 0 };
struct Node//hufman 的节点
{
	char charcter;
	long long power;
	Node * left = NULL;
	Node * right = NULL;
	Node * parent = NULL;
	char code[20];
	bool is_left;
};
bool cmp(const Node*  it1, const Node*  it2)
{
	if (it1->power > it2->power)
		return true;
	else
		return false;
}
class Hufman
{
private:
	Node * root;
	long compress_time;
	long decompress_time;
	double B_bit = 0;
	double C_bit = 0;
	string compress_filename;
public:
	Hufman();
	void Build_hufmanTree();//建树
	void code_hufmanTree();//确定各个字符的编码
	void Hufman_code(char ch, char code[20]);
	void compress();//压缩
	void decompress();//解压
	void Hufman_action();//接口
};
int flag;
class Cache
	//缓存类      将0 1每七个形成一个一个ancll码对应的字符，然后把这个字符写到文件中，解压的时候将文件中的每个字符再变成7个01码
{
public:
	Cache();
	void add(string s);
	char getCH();
	bool have_tail();
	bool cache_is_ok = false;
private:
	int binary[100];
	int position = 0;
};
Cache::Cache()
{
	for (int i = 0; i < 100; i++)
		binary[i] = 0;
}
void Cache::add(string s)
{
	for (int i = 0; i < s.size(); i++)
	{
		binary[position] = s[i] - 48;
		position++;
	}
	if (position>7)
		cache_is_ok = true;
}
char Cache::getCH()
{
	int num = 0;
	for (int i = 0; i < 7; i++)
	{
		int two = binary[i];
		for (int j = 5 - i; j >= 0; j--)
			two = 2 * two;
		num += two;
	}
	for (int i = 7; i < position; i++)
		binary[i - 7] = binary[i];
	position -= 7;
	if (position < 7)
		cache_is_ok = false;
	char out;
	out = char((num - 48) + '0');
	return out;
}
bool Cache::have_tail()
{
	if (position != 0)
	{
		cache_is_ok = true;
		for (int i = position; i < 7; i++)
			binary[i] = 0;
		flag = position;
		return true;
	}
	return false;
}
Hufman::Hufman()
{
	cout << "Hufman压缩" << endl;
	cout << "请输入要压缩的文件名:";
	getline(cin, compress_filename);
	fstream fin;
	fin.open(compress_filename);
	if (!fin.is_open())
	{
		cerr << "cannot open " << compress_filename << endl;
		return;
	}
	char c;
	while (fin.get(c))  //计算各个字符出现的频率
	{
		cpcount[(int)c]++;
	}
	fin.close();
}
void Hufman::Build_hufmanTree()
{
	vector<Node *>hufman_heap;
	for (int i = 0; i < BIGSIZE; i++)
	{
		if (cpcount[i] != 0)
		{
			Node * p = new Node;
			p->power = cpcount[i];
			p->charcter = (char)i;
			p->code[0] = '\0';
			hufman_heap.push_back(p);
		}
	}
	vector<Node *>::iterator it;
	make_heap(hufman_heap.begin(), hufman_heap.end(), cmp);//建立最小堆
	while (hufman_heap.size() != 1)
	{
		Node * p = new Node;
		p->code[0] = '\0';
		it = hufman_heap.begin();
		p->left = *it;
		(*it)->parent = p;
		(*it)->is_left = true;
		hufman_heap.erase(hufman_heap.begin());
		make_heap(hufman_heap.begin(), hufman_heap.end(), cmp);
		it = hufman_heap.begin();
		p->right = *it;
		(*it)->parent = p;
		(*it)->is_left = false;
		hufman_heap.erase(hufman_heap.begin());
		make_heap(hufman_heap.begin(), hufman_heap.end(), cmp);
		p->power = p->left->power + p->right->power;
		hufman_heap.push_back(p);
		make_heap(hufman_heap.begin(), hufman_heap.end(), cmp);
	}
	root = *hufman_heap.begin(); //建立哈夫曼树
}
void Hufman::code_hufmanTree()//给每个哈夫曼树上的节点编码
{
	queue<Node*>hufman_queue;
	hufman_queue.push(root);
	Node * p;
	while (hufman_queue.empty() == false)
	{
		p = hufman_queue.front();
		hufman_queue.pop();
		if (p->parent != NULL)
		{
			strcpy(p->code, p->parent->code);
			for (int i = 0; i < 20; i++)
			{
				if (p->code[i] == '\0')
				{
					if (p->is_left)
						p->code[i] = '0';
					else
						p->code[i] = '1';
					p->code[++i] = '\0';
					break;
				}
			}
		}
		else
		{
			p->code[0] = 0;
			p->code[1] = '\0';
		}
		if (p->left == NULL&&p->right == NULL)
		{
			Hufman_code(p->charcter, p->code);//将字符的编码写入哈夫曼的编码表中
			continue;
		}
		hufman_queue.push(p->left);
		hufman_queue.push(p->right);
	}
}
void Hufman::Hufman_code(char ch, char code[20])//将字符的编码写入哈夫曼的编码表中
{
	ofstream fout("Hufman code form.txt", ios::app);
	if (fout.is_open() == false)
	{
		cerr << "cannot open the Hufman code form.txt" << endl;
		return;
	}
	fout << ch << "	" << code << endl;
	fout.close();
}
void Hufman::compress()
{
	time_t start, end;
	time(&start);
	string form[BIGSIZE];//哈夫曼编码表 数组序号是字符的ascil序号
	fstream fin;
	fin.open("Hufman code form.txt");
	if (fin.is_open() == false)
	{
		cerr << "cannot open the hufman code form";
		return;
	}
	char ch;
	string code;
	while (fin.get(ch))
	{
		fin >> code;
		form[(int)ch] = code;
		fin.get();
	}
	fin.close();
	fin.open(compress_filename);
	if (fin.is_open() == false)
	{
		cerr << "cannot open the " << compress_filename;
		return;
	}
	ofstream fout("Huf.bin", ios::binary);
	if (fout.is_open() == false)
	{
		cerr << "cannot open the Huf.bin" << endl;
		return;
	}
	Cache cache;
	char c;
	string temp;
	while (fin.get(c))
	{
		if ((int)c<0 || (int)c>250)
			continue;
		temp = form[(int)c];//压缩文件
		cache.add(temp);
		while (cache.cache_is_ok == true)
		{
			c = cache.getCH();
			fout.write((char*)&c, sizeof(char));
		}
		B_bit++;
	}
	if (cache.have_tail())
	{
		c = cache.getCH();
		fout.write((char*)&c, sizeof(char));
	}
	fin.close();
	fout.close();
	B_bit *= 8;
	time(&end);
	compress_time = end - start;
}
void Hufman::decompress()
{
	time_t start, end;
	time(&start);
	ifstream fin("Huf.bin", ios::binary);
	if (fin.is_open() == false)
	{
		cerr << "cannot open the Huf.bin";
		return;
	}
	char c;
	string target;
	char char_to_int[8] = { '0', '0', '0', '0', '0', '0', '0', '\0' };
	int cc;
	while (fin.read((char*)&c, sizeof(char)))
	{
		cc = int(c);
		for (int i = 6; i >= 0; i--)
		{
			if (cc & 1)
				char_to_int[i] = '1';
			else
				char_to_int[i] = '0';
			cc >>= 1;
		}
		target += char_to_int;
	}
	C_bit = target.size() - 7 + flag;
	fin.close();
	ofstream fout("Hufman decompress.txt", ios::app);
	if (fout.is_open() == false)
	{
		cerr << "cannot open the decompress.txt" << endl;
		return;
	}
	Node * p = root;
	for (int i = 0; i < target.size() - 7 + flag; i++)//对0 1 压缩码经行解压
	{
		if (target[i] == '0')
			p = p->left;
		else
			p = p->right;
		if (p->left == NULL&p->right == NULL)
		{
			fout << p->charcter;
			p = root;
		}
	}
	time(&end);
	decompress_time = end - start;
}
void Hufman::Hufman_action()
{
	Build_hufmanTree();
	code_hufmanTree();
	compress();
	decompress();
	double answer = C_bit / B_bit;
	answer /= 0.01;
	cout << "hufman压缩时间:" << compress_time << "s" << endl << "hufman解压时间:" << decompress_time << "s" << endl << "压缩比:" << answer << "%" << endl;
}
int main()
{
    Hufman h;
    h.Hufman_action();
    system("pause");
    return 0;
}