一个字符统计的程序

//By Aba
#include <cstdlib>
#include <cstdio>
#include <cstring>
#include <map>
#define FILENAMELENGTH 256
#define TYPES 6 //手动更新
using namespace std;
typedef long long Character;
class Reader{
	public:
		virtual Character read()=0; //read a char from the file
};
	class Counter{
	public:
		virtual int sum(Character ch) const=0; //the sum of ch appeared in the file
		virtual int sum(Character ch1,Character ch2) const=0; //the sum of chars between ch1 ang ch2
		virtual int sum() const=0; //the sum of chars of the file
		virtual Character next() const=0;
};
	class Reporter{
	public:
		virtual void report(const Counter& ct,FILE* out) const=0;
};
long wcode(const char* st){
	long c=0;
	for(int i=0;st[i]!='\0';i++){
		c<<=8;
		c+=(unsigned char)st[i];
	}
	return c;
}
class UTF8Reader:public Reader{
	private:
//		char *fpath;  //save filename
		FILE *in;  //input file
		bool isava;  //is avaliable
		int eof(){
			close();
			return -1;
		}
	public:
		UTF8Reader(FILE* in){
			this->in=in;
			if(NULL!=in) isava=true;
		}
		~UTF8Reader(){
			close();
			isava=false;
		}
		void close(){
			if(isava){
				fclose(in);
				isava=false;
			}
		}
		Character read(){ //遍历文件，统计字符种类及个数
			Character UTF8ch;
			int h,buf;
			if(!isava)
				return -1; 
			if(EOF==(buf=fgetc(in))){ //the first byte
				return eof();
			}
			UTF8ch=h=buf;
			if(h&0x80)
			for(unsigned char i=0x40;i&h;i>>=1){
				UTF8ch<<=8;
				if(EOF==(buf=fgetc(in))){ //the first byte
					return eof();
				}
				UTF8ch+=buf;
			}
			return UTF8ch;
		}
};
class UTF8Reporter:public Reporter{
public:
	void report(const Counter& ct,FILE* out) const{
		Character wt;
		unsigned char buf;
		unsigned int totally=0,thistime=0;
		while((wt=ct.next())!=-1){
			if(wt<0x20)continue;
			for(int i=56;i>=0;i-=8){
				buf=(wt>>i)&0xff;
				if(buf) fputc(buf,out);
			}
			thistime=ct.sum(wt);
			fprintf(out," (%I64x): %d\n",wt,thistime);
			totally+=thistime;
		}
		fprintf(out,"totally: %u\n",totally);
	}
};
class GB18030Reader:public Reader{
	private:
//		char *fpath;  //save filename
		FILE *in;  //input file
		bool isava;  //is avaliable
		int eof(){
			close();
			return -1;
		}
	public:
		GB18030Reader(FILE* in){
			this->in=in;
			if(NULL!=in) isava=true;
		}
		~GB18030Reader(){
			close();
			isava=false;
		}
		void close(){
			if(isava){
				fclose(in);
				isava=false;
			}
		}
		Character read(){
			unsigned int GB18030ch;
			int buf;
			if(!isava)
				return -1; 
			if(EOF==(buf=fgetc(in))){ //the first byte
				return eof();
			}
			if(buf<=0x80) 
				return buf;
			GB18030ch=buf;
			buf=fgetc(in); //the second byte
			if(EOF==buf){
				return eof();
			}
			GB18030ch<<=8;
			GB18030ch+=buf;
			if(buf>=30 && buf<=0x39){
				if(EOF==(buf=fgetc(in))){ //the third byte
					return eof();
				}
				GB18030ch<<=8;
				GB18030ch+=buf;
				if(EOF==(buf=fgetc(in))){ //the forth byte
					return eof();
				}
				GB18030ch<<=8;
				GB18030ch+=buf;
			}
			return GB18030ch;
		}
};
class GB18030Reporter:public Reporter{
public:
	void report(const Counter& ct,FILE* out) const{
		Character wt;
		unsigned int hanzinum=0,hanzicount=0,totally=0,thistime=0;
		while((wt=ct.next())!=-1){
			if(wt<0x20)continue; //skip control chars
				if(wt<=0x80){
					fputc(wt&0xff,out); //one byte
				}
				else{ //two or more byte
					if(wt>=0x81308130){ //four bytes character
						fputc((wt>>24)&0xff,out);
						fputc((wt>>16)&0xff,out);
						fputc((wt>>8)&0xff,out);
						fputc(wt&0xff,out);
						++hanzinum;
						hanzicount+=ct.sum(wt);
					}else if(wt>=0x8140&&wt<=0xa0fe || wt>=0xaa40&&wt<=0xfea0){ //two bytes character
						fputc((wt>>8)&0xff,out);
						fputc(wt&0xff,out);
						++hanzinum;
						hanzicount+=ct.sum(wt);
					}
					else{ //two byte not character
						fputc((wt>>8)&0xff,out);
						fputc(wt&0xff,out);
					}		
				}
				thistime=ct.sum(wt);
				totally+=thistime;
				fprintf(out," (%I64x): %d\n",wt,thistime);
			}
		fprintf(out,"不同汉字的个数：%u\n总汉字数（不包括全角标点符号）：%u\n",hanzinum,hanzicount);
		fprintf(out,"不包括控制字符的总字数：%u\n",totally);
	}
};
class WordCounter:public Counter{
	public:
		WordCounter(Reader& in){
			Character ch;
			ch=in.read();
			while(ch!=-1){
				map<Character,int>::iterator iter=countmap.find(ch);
				if(iter!=countmap.end()){
					iter->second=iter->second+1;
				}
				else{
					countmap[ch]=1;
				}
				ch=in.read();
			}
		}
		~WordCounter(){
			countmap.clear();
		}
		int sum(Character ch) const{
			map<Character,int>::const_iterator citer=countmap.find(ch);
			if(citer==countmap.end()) return 0;
			else return citer->second;
		}
		int sum(Character ch1,Character ch2) const{
			Character i;
			int sigma=0;
			for(Character i=ch1;i<=ch2;i++){
				if(sum(i)!=0)break;
			}
			for(map<Character,int>::const_iterator citer=countmap.find(i);citer!=countmap.end() && citer->first<=ch2;++citer){
				sigma+=citer->second;
			}
			return sigma;
		}
		int sum() const{
			int sigma=0;
			map<Character,int>::const_iterator citer;
    		for(citer=countmap.begin();citer!=countmap.end();++citer){
				sigma+=citer->second;
			}
			return sigma;
		}
		Character next() const{
			static map<Character,int>::const_iterator citer=countmap.begin();
			if(citer!=countmap.end())return (citer++)->first;
			else return -1;
		};
private:
	map<Character,int> countmap;
};
const unsigned char types[TYPES][6]={
	{0} //ANSI	0
	,{3,0xef,0xbb,0xbf} //UTF-8	1
	,{2,0xfe,0xff} //UTF-16（大端序）	2
	,{2,0xff,0xfe} //UTF-16（小端序）	3
	,{4,0xfe,0xff,0,0} //UTF-32（大端序）	4
	,{4,0xff,0xfe,0,0} //UTF-32（小端序）	5
};
int putftmark(int t,FILE *out){ //添加标记
	if(NULL==out) return -1;
	for(int i=1;i<=types[t][0];++i){
		fputc(types[t][i],out);
	}
	return 0;
}
int getfiletype(FILE* in){
	int i,j;
	if(NULL==in) return -1;
	for(i=1;i<TYPES;++i){
		fseek(in,0,SEEK_SET);
		for(j=1;j<=types[i][0];++j){
			if(fgetc(in)!=types[i][j])break;
		}
		if(j>types[i][0]) return i;
	}
	fseek(in,0,SEEK_SET);
	return 0;
} 
void filenameformulize(char *str) //去掉由于文件路径带有空格系统自动加的引号 
{
	int i;
	if(str[0]=='"'){ //move "
		for(i=0;str[i+1]!=0;i++)
			str[i]=str[i+1];
		str[i-1]=0;
	}
}
int main(int argc, char *argv[]){
	char *filein,*fileout,*sstr;
	Reader *gr=NULL;
	WordCounter *wc=NULL;
	Reporter *grp=NULL;
	FILE *in=NULL,*out=NULL;
	int filetype;
	switch(argc){
		case 1:	
			filein=new char[FILENAMELENGTH];
			fileout=new char[FILENAMELENGTH];
			printf("字符统计\n输入文本文档地址：");
			gets(filein);
			printf("输出文本文档地址：");
			gets(fileout);
			break;
		case 3:
			filein=argv[1];
			fileout=argv[2];
			break;
		default:
			printf("字符统计. 参数: [输入文件 输出文件]\n");
			system("pause");
			return 0;
	}
	filenameformulize(filein);
	in=fopen(filein,"rb");
	filetype=getfiletype(in);
	switch (filetype){
	case 0: //ANSI
		gr=new GB18030Reader(in);
		break;
	case 1: //UTF-8
		gr=new UTF8Reader(in);
		break;
	case -1:
		printf("无法打开%s\n",filein);
		system("pause");
		return -1;
		break;
	default:
		printf("不支持的编码格式\n");
		system("pause");
		return filetype;
	}
	if(!(out=fopen(fileout,"w"))){
		printf("无法打开%s\n",fileout);
		system("pause");
		return -1;
	}
	wc=new WordCounter(*gr);
	putftmark(filetype,out);
	switch (filetype){
	case 0: //ANSI
		fprintf(out,"字符统计：%s\n",filein);
		grp=new GB18030Reporter();
		break;
	case 1: //UTF-8
		grp=new UTF8Reporter();
		break;
	default:
		printf("不支持的编码格式\n");
		system("pause");
		return filetype;
	}
	grp->report(*wc,out);
	fclose(out);
	if(3!=argc){ //如果带输入文件和输出文件两个参数，认作批量处理，执行完后就不打开记事本了
		sstr=new char[FILENAMELENGTH + 15];
		strcpy(sstr,"start notepad ");
		strcat(sstr,fileout);
		system(sstr);
		delete []sstr;
	}
	delete[] filein;
	delete[] fileout;
	return 0;
}

使用