directory.c

对文件夹中的各文件的内容分词后按照词的内容进行统计和组织。

#include <direct.h>
#include <io.h>
#include <stdio.h>
#include <string.h>
#include "malloc.h"

 
/*词结构链表*/
struct ForwardNode
{
	int frenqucy;
	int filenum;
	char *sWord;
	struct WordName *next;
};
typedef struct ForwardNode ForwardNode;

/*文件结构链表*/
struct FileNode
{
	int FileID;	
	char *pfilename;
	struct FileNode *next;
    struct ForwardNode *pWordName;
	int wordnum;
};
struct FileNode *ptem1=NULL;


/*类别结构*/
struct ClassNode
{
	int ClassID;
	char *pclassname;
	int filenum;
	struct FileNode *pfileNode;
	struct ClassNode *next;
};
 struct ClassNode *pctem1=NULL,*head=NULL;



 /*创建词链表*/
   struct ForwardNode *CWordNode()
{
	struct WordNode *p;
	p=(struct ForwardNode *)malloc(sizeof(struct ForwardNode));
	if(p==NULL)
	{
		printf("No enough memory to alloc");
	}	
	p->sWord=(char *)malloc(sizeof(char));
    p->next=NULL;
	return(p);
}

   /*创建文件链表*/
   struct FileNode *CFileNode()
{
	struct FileName *p;
	p=(struct FileNode *)malloc(sizeof(struct FileNode));
	if(p==NULL)
	{
		printf("No enough memory to alloc");
	}	
	p->pfilename=(char *)malloc(sizeof(char));
    p->next=NULL;
	return(p);
}

    /*创建类别链表*/
   struct ClassNode *CreateNode()
   {
    	struct ClassNode *p;
        p=(struct ClassNode *)malloc(sizeof(struct ClassNode));
	    p->next=NULL;
	    p->pclassname=(char *)malloc(sizeof(char));
	    p->pfileNode=NULL;	
	    return(p);
   }

 
/*文件路径拷贝*/
char *ChangeDir(char path[])
{ 
    char *Newpath=NULL; 
	int i=2;
	strcpy(Newpath,"");
    Newpath[0]='e';
    Newpath[1]=':';  
    while(path[i]!='\0')
    {
	   Newpath[i]=path[i];
	   i++;
    }
     Newpath[i]='\0';   
     return(Newpath);   
}


/*统计文件词频*/


/*从文件中读出正向表*/
int ForwardRead(char *cfilename, ForwardNode **fNode, int *DocCount)
{
   
	int malloccount = 0;
	char cTemp;
	unsigned char sTemp[SHORTSIZE];
	unsigned char sShortTemp[SHORTSIZE];
	int iStringPos = 0;
	int iComaCount = 0;
	int flagWord = 0;
	long DCount = 0;
	int poscount = 0;
	int i,j;
	ForwardNode *ptempFNode;
	WordNode *pcurWordNode;
    FILE *pTxtFile, *pFileTemp;
	*fNode = (ForwardNode *) malloc((iMallocSize + (malloccount++) * iReallocSize) * sizeof(ForwardNode));
	
	/*打开文档*/
	if( (pTxtFile  = fopen( cfilename, "r" )) == NULL )
	{
		return EFILEOPEN;
	}

	pFileTemp = pTxtFile;
	ptempFNode = *fNode;

	/*开始读字节*/
    cTemp = fgetc(pTxtFile);
	while(cTemp != EOF)
	{
		/*读文档编号*/
		if(cTemp == '@')
		{
			iStringPos = 0;
		    cTemp = fgetc(pTxtFile);
			while(cTemp != '#')
			{
				sTemp[iStringPos++] = cTemp;
			    cTemp = fgetc(pTxtFile);
			}
			/*处理文档编号的内容*/
			sTemp[iStringPos] = '\0';
			/*分配的内存够用*/
			
				strcpy(ptempFNode->sDocID, sTemp);
			
			/*分配的内存不够用???????????*/			
		}

		/*读词内容*/
		else if((cTemp == '#')||(flagWord == 1))
		{
			/*如果是新文档的第一个词,分配第一个词节点*/
			if(cTemp == '#')    
			{
				cTemp = fgetc(pTxtFile);
				ptempFNode->wFWordNode = (WordNode *)malloc(sizeof(WordNode));
				ptempFNode->wFWordNode->pnext = NULL;
				pcurWordNode = ptempFNode->wFWordNode;
			}
			/*如果是同一个文档中的下一个词,分配下一个词节点*/
			else if(flagWord == 1)
			{
				flagWord = 0; 
				pcurWordNode->pnext = (WordNode *) malloc(1 * sizeof(WordNode));
				pcurWordNode = pcurWordNode->pnext;
				pcurWordNode->pnext = NULL;
			}
			iStringPos = 0;
			while(cTemp != ',')
			{
				sTemp[iStringPos++] = cTemp;
			    cTemp = fgetc(pTxtFile);
			}
			sTemp[iStringPos] = '\0';
			/* 处理词的内容*/
			pcurWordNode->sWords = (unsigned char *) malloc (iStringPos * sizeof(unsigned char));
			strcpy(pcurWordNode->sWords,sTemp);
		}

		/*读权重*/
		else if((cTemp == ',') && (iComaCount == 0))
		{
			iComaCount++;
			iStringPos = 0;
			cTemp = fgetc(pTxtFile);
			while(cTemp != ',')
			{
				sTemp[iStringPos++] = cTemp;
			    cTemp = fgetc(pTxtFile);
			}
			/* 处理权重的内容*/
			sTemp[iStringPos] = '\0';
			pcurWordNode->fWeight = atof(sTemp);
		}
		/*读词频*/
		else if ((cTemp == ',') && (iComaCount == 1))
		{
			iComaCount++;
			iStringPos = 0;
			cTemp = fgetc(pTxtFile);
			while(cTemp != ',')
			{
				sTemp[iStringPos++] = cTemp;
			    cTemp = fgetc(pTxtFile);
			}
			/* 处理词频的内容*/
			sTemp[iStringPos] = '\0';
			pcurWordNode->iFreq = atol(sTemp);
		}
		/*读位置*/
		else if ((cTemp == ',') && (iComaCount == 2))
		{
			iComaCount++;
			iStringPos = 0;
			cTemp = fgetc(pTxtFile);
			while(cTemp != ';')
			{
				sTemp[iStringPos++] = cTemp;
			    cTemp = fgetc(pTxtFile);
			}
			sTemp[iStringPos] = '\0';
			/* 处理位置的内容*/
			pcurWordNode->iPos = (int *) malloc((int)(pcurWordNode->iFreq) * sizeof(int));
			poscount = 0;
			i = 0;
			while( sTemp[i] != '\0')
			{
				j = 0;
				while((sTemp[i] != '+') && (sTemp[i] != '\0'))
				{
					sShortTemp[j++] = sTemp[i++];
				}
				if((sTemp[i] == '+') ) 
				{
					sShortTemp[j] = '\0';
					pcurWordNode->iPos[poscount++] = atoi(sShortTemp);
					i++;
				}
				else if(sTemp[i] == '\0')
				{
					sShortTemp[j] = '\0';
					pcurWordNode->iPos[poscount++] = atoi(sShortTemp);
				}
			}
		}
		/*下一个词或文档开始*/
		else if (cTemp == ';')
		{
			cTemp = fgetc(pTxtFile);
			/*读下一篇文档*/
			if(cTemp == '\n')
			{
				iComaCount = 0;
				DCount++;
				ptempFNode = *fNode + DCount;
				cTemp = fgetc(pTxtFile);
				continue;
			}
			/*文档读完，返回*/
			else if(cTemp == EOF)
			{
				return 0;
			}
			/*一个词结点读完，读下一个词*/
			else
			{
				iComaCount = 0;
				flagWord = 1;
				continue;
			}
		}
		else
		{
			printf("file format is error!");
			return EFILEFORMAT;
		}/* */
	}
	*DocCount = DCount;
	printf("The ForwardRead Function is over!");
	return 0;
}




  

struct FileName *FiletoWord(char *path,long wordnum)
{
    struct FileName pQuery=NULL,pQueryT=NULL;
	if((fp=fopen(path,"r"))==NULL)
	printf("open error");
    while(!feof(fp))
    { 
       cht=fgetc(fp1);
  	   while(*cht==' ') cht=fgetc(fp1);
       p2=strchr(p1,' ');

	   if(cht!='\n')
  	   {   		
       if(cht==44)  /*如果是逗号*/ 
             printf("g");
	   else if(cht==34) /*如果是引号*/  
	   {
		   cht='\n';
		   fputc(cht,fp2);
		  
	   }
       
	   else	   
    	   fputc(cht,fp2);
		
    /*  cht=fgetc(fp1);
	  fputc(cht,fp2);*/

	 /* fputc(fgetc(fp1),fp2);*/
				
			    fclose(fp);  

}

/*遍历文件夹*/
int i=0;
void ProcessFileFromDir(char *spath)
{
	long numWordNum=0;
	struct FileName *ptem2=NULL;
	struct _finddata_t file;/*定义结构体变量*/
    struct ClassName *pctem2=NULL;	
	char path[128],*Newpath;/*路径*/	
	long handle;
    FILE *fp;
  	handle=(long)_findfirst("*",&file);/*查找所有文件*/
	if(handle==-1)/*如果handle为－1,表示当前目录为空,则结束查找而返回*/
		return;	
	while(!(_findnext(handle,&file)))
	{/*继续对当前目录中的下一个子目录或文件进行与上面同样的查找*/
		
		if(file.attrib&_A_SUBDIR)
		{  
			if(file.name[0]!='.')
			{ 
				  _chdir(file.name);/*进入该目录*/
				  _getcwd(path,256);/*获得目录路径*/				
				/* 建立类别节点*/
				  pctem2=CreateNode();  
                /* 定义类别节点的文件链表头指针*/
				  ptem1=pctem2->pfileNode;
				   /*拷贝文件名*/
                  strcpy(pctem2->pclassname,path); 
			      i++;
				  printf("%d",i);
				 /*类别编码 */
				  pctem2->ClassID=i;
				  /*初始化类别的文件数目为0*/
				  pctem2->filenum=0;
				  /*类别节点连接到链表*/

				  if(pctem1==NULL)
					  pctem1=pctem2;
				  else
				  {
					  pctem1->next=pctem2;
					  pctem1=pctem1->next;
                      pctem1->next=NULL;
				  }
                  /*定义类别节点头指针*/

				  if(head==NULL)				  
					  head=pctem1; 			  
				  Newpath=ChangeDir(path);
				  mkdir(Newpath);				 
			      ProcessFileFromDir(path);					
				  _chdir(".."); /*查找完毕之后,返回上一级目录*/
				
			}			
		}
		else
		{/*如果第一个实体不是目录,显示该文件*/
			
			_getcwd(path,256);/* 获得文件的完整的路径名包含文件的名称*/  				
			if(strcmp(strchr(file.name,'.'),".txt")==0)
			{				
                /*建立文件节点并赋值*/
			    ptem2=CFileNode();
                /*文件名拷贝到节点*/
				strcat(path,"\\");
			    strcat(path,file.name);
                strcpy(ptem2->pfilename,path);
                /*文件计数*/
                pctem1->filenum++;
                ptem2->FileID=pctem1->filenum;
                /*打开文件，统计词*/ 
				ptem2->pWordName=FiletoWord(path,wordnum);				
              	/*文件节点连接到链表*/
				if(ptem1==NULL)
					ptem1=ptem2;
				else
				{   ptem1->next=ptem2;
                    ptem1=ptem1->next;
                    ptem1->next=NULL;		       	
				}
				if(pctem1->pfileNode==NULL)
                    pctem1->pfileNode=ptem2;
			  				
              /*  printf("     %ld   %s\n",ptem2->FileID,ptem2->pfilename);	*/			
				
			 /*  Newpath=ChangeDir(path);		*/	
			   

			
			}
			
		}
            
	}
	/*printf("j%d",head->filenum);*/
		
	_findclose(handle);//关闭控制台
	
}



main()
{
  struct ClassName *pr; 
  char filename[128];  
  printf("input path\n"); 
  gets(filename); 
  _chdir(filename); 
  ProcessFileFromDir(filename);
  pr=head;  
  while(pr!=NULL)
  {	  
	  printf("class%d  %s %d\n",pr->ClassID,pr->pclassname,pr->filenum);
      
	   while(pr->pfileNode!=NULL)
	  {
		  printf("file%d,%s \n",pr->pfileNode->FileID,pr->pfileNode->pfilename);
		  pr->pfileNode=pr->pfileNode->next;         
	  }
      pr=pr->next;
  }
  getchar();
}