[单链表]统计文本中英文单词出现次数，并输出前200个单词及其出现次数

不知道该说些什么，直接上代码吧(　･ัω･ั )

 

                                                                                                   ——已优化单链表排序WordsSort()

#define _CRT_SECURE_NO_WARNINGS
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <ctype.h>

#define SIZE 50    //设置单词最长长度

//储存单词，数量，以及构成链表的指针
typedef struct words
{
	char str[SIZE];	//单词最长100个
	int count;
	struct words *next;
}Words;


//初始化链表
Words* InitWord()
{
	Words *headWord = (Words*)malloc(sizeof(Words));
	strcpy(headWord->str,"");
	headWord->count = 0;
	headWord->next = NULL;
	return headWord;
}

//头插入的方式插入新数据
void AddWord(Words *headWord,const char *str)//头插入
{
	Words *pos = headWord->next;	//储存当前第一个结构体的指针
	Words *newWord = (Words*)malloc(sizeof(Words));
	strcpy(newWord->str,str);
	headWord->next = newWord;
	if(pos == NULL)	newWord->next = NULL;//第一个单词，储存在链表尾部，next指向空
	else			newWord->next = pos;
	newWord->count=1;
}


int CheckStr(Words *headWord,const char *str)//检查单词是否出现过，若出现单词数量加一，返回1，没出现返回0
{
	Words *p = headWord->next;
	if(headWord->next == NULL)	
		{
			AddWord(headWord,str);
			return 1;
		}
	while(strcmp(p->str,str) != 0)
	{
		p = p->next;
		if(p == NULL)	break;
	}
	if(p == NULL)	return 0;//没有该单词，返回0标记
	else
	{
		++(p->count);	//已有单词，数量加一
		return 1;
	}
	return -1;			//异常出错
}

//读单词操作——过滤标点与空格
int ReadWord(FILE *fp,int *plen,char *str)
{
	fseek(fp, *plen, SEEK_SET);
	unsigned char ch;
	int flg_eof = 0;	//标记 判断是否文件结束，如果再没有读入的内容了，即文件结束
	int i=0;
	while(fread(&ch,sizeof(char),1,fp) != 0)	//注：isalpha(unsigned(ch))，需要强制转换
	{
		if(!isalpha(unsigned(ch)) && i == 0)	continue;//排除单词是个字母无法读取问题
		if(isalpha(unsigned(ch)) || ch == '\'')//类似I'm中的 ' 符号，有且只能有一个
		{
			flg_eof = 1;
			str[i++] = ch;
		}
		else
		{
			break;
		}
	}
	if(flg_eof == 0)	return 0;	//没有读文件，文件结尾了
	str[i] = '\0';
	*plen = ftell(fp);
	return *plen;
}

//读文件操作
void ReadFile(Words *headWord,char *name)//文件操作，从文件中读取单词
{
	FILE *fp ;
	int len = 0;		//标记文件指针在文件中的位置
	if((fp= fopen(name,"r")) == NULL)
	{
		fp = fopen(name, "w+");/* 如果创建失败，新建一个文件  w+:可读写
					文件存在则文件长度清为零，文件不存在时创建一个   */
	}

	char str[SIZE];
	while(ReadWord(fp,&len,str) != 0)//fscanf(fp,"%s",str) != EOF
	{
		if(CheckStr(headWord,str) == 0)	//没有该单词，新增一个
		{
			AddWord(headWord,str);
		}	

	}

	fclose(fp);
}

//交换数据——单词/出现次数
void SwapWord(Words *posWord,Words *posNext)
{
	char tmpWord[SIZE]="";
	strcpy(tmpWord ,posWord->str);  
	strcpy(posWord->str, posNext->str);
	strcpy(posNext->str, tmpWord);

	int tmpCount;
	tmpCount	   = posWord->count;
	posWord->count = posNext->count;
	posNext->count = tmpCount;

}

//单词排序
void WordsSort(Words *headWord)
{
	if(headWord->next == NULL)	return;
	Words *pos = headWord->next;
	Words *pos_next = pos->next;
	int flag;
	while(pos_next != NULL)
	{
		flag = 0;

		/*-- _pos 表示内循环的遍历 --*//* ps:本来想通过这种方式优化，然后写的有点复杂了，已优化，链接见文章首行*/
		Words *_pos = pos;           
		Words *_pos_next = pos_next;

		while(_pos_next != NULL)
		{
			Words *tmp = _pos_next->next;
			if(_pos->count < _pos_next->count)
			{
				SwapWord(_pos,_pos_next);
				flag = 1;
			}
			_pos = _pos->next;
			_pos_next = _pos_next->next;

		}
		if(flag == 0)	break;
	}

}


void PrintWords(Words *headWord,const char *name)
{
	Words *pMove = headWord->next;
	if(headWord->next == NULL)	return;
	int count = 0;
	printf("\t<<%s>>中出现的最高频率的单词:\n",name);
	printf("\t单词：\t\t\t\t\t\t出现次数：\n");
	while(pMove != NULL && count<200)
	{
		printf("\t%-50s%d\n",pMove->str,pMove->count);
		pMove = pMove->next;
		count++;
	}
	printf("\n");
}

//释放链表
void free_Word(Words* headNode)
{
	Words *point = NULL;
	while(headNode != NULL)
	{
		point = headNode;//指向所释放的空间
		headNode = headNode->next;//指针后移
		free(point);
	}
}



int main()
{
	Words *headWord = InitWord();		//初始化链表,创建表头
	char bookName[] = "输入文件地址及文件名";
	ReadFile(headWord,bookName);		//文件操作
	WordsSort(headWord);
	PrintWords(headWord,bookName);
	free_Word(headWord);
	return 0;
}

说明：程序中没有加入大小写判断机制，也就是说 My 和 my 是两个单词，因为懒也没有想过再去修改，就这样吧(*-ω-)