C语言中从文本文件到链表的字数计算

我是C语言编程新手，在我的一个课程中，我们将编写代码，读取文本文件，将所有单词放入带有计数器的链表中，并将链表输出到文本文件中

我不确定我在下面的代码中做错了什么，它只计算了一些单词，似乎跳过了其他单词。（我添加了许多额外的打印，以尝试查看文字丢失的位置）

然后，当我把所有的单词添加到链表中时，我尝试将它们改成小写，但这似乎使它读的单词更少，我不知道为什么

如有任何帮助/建议，将不胜感激

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

typedef struct s_words {
    char *str; //word
    int count; //number of times word occurs
    struct s_words* next; //pointer to next word
} words;


words* create_words(char* word) {
    //+allocate space for the structure
    printf("%lu ", strlen(word));
    words* newWord = malloc(sizeof(words));
    if (NULL != newWord)
    {
        //+allocate space for storing the new word in "str"
        //+if str was array of fixed size, storage wud be wasted
        newWord->str = (char *)malloc((strlen(word))+1);
        strcpy(newWord->str, word); //+copy “word” into newWord->str
        newWord->str[strlen(word)]='\0';
        printf(" Create: %s ", newWord->str);
        //+initialize count to 1;
        newWord->count = 1;
        //+initialize next;
        newWord->next = NULL;                   
    }
    return newWord;
}

words* add_word(words* wordList, char* word) 
{
    int found=0;
    words *temp=wordList;
    //+ search if word exists in the list; if so, make found=1
    while (temp != NULL) 
    {

        if (strcmp(temp->str, word) == 0) 
        {  //+use strcmp command
            found=1;
            temp->count = temp->count+1; //+increment count;
            return wordList;
        }
        else 
        {
            //+update temp
            temp = temp->next;
        }
    }
    if (found==0) 
    {  //new word
        //printf("%s ", word);
        words* newWord = create_words(word);
        if (NULL != newWord) 
        {
            //+??  Insert new word at the head of the list
            newWord->next = wordList;
            printf(" NEW WORD: %s\n ", newWord->str);
        }
        return newWord;
    }
    //return wordList; //code never gets here, just added in case of error    
}




int main(int argc, char* argv[]) 
{

    words *mywords;  //+head of linked list containing words
    mywords=NULL;

    FILE *myFile;
    FILE *myOutput;

    char* filename = argv[1];
    char* outputfile = argv[2];

    myFile = fopen(filename, "r");  //+first parameter is input file
    if (myFile==0) 
    {
        printf("file not opened\n");
        return 1;
    }
    else 
    {
        printf("file opened \n");
    }

    //+start reading file character by character;
    //+when word has been detected; call the add_word function

    int ch = 0, word = 1, k = 0;
    char thisword[100];
    //ch = putchar(tolower(ch));
    //ch = fgetc(myFile);
    while ((ch = fgetc(myFile)) != EOF )
    {
        //error handling

        if (ch == '.' || ch == ' ' || ch == ',' || ch == ':' || ch == ';' || ch == '\n')  //+detect new word? Check if ch is a delimiter
        { //when above if is true, new word created in next if:
            if ( word == 1 )  //+make sure previous character was not delimiter
            {
                word = 0;
                //+make the kth character of thisword as \0
                thisword[k] = '\0';

                //+now call add_word to add thisword into the list
                printf(" Add:%s ", thisword);
                mywords = add_word(mywords, thisword);
                printf(" Added:%s\n", mywords->str);

                k=0;
            }
        }
        else
        {
            word = 1;
            //make ch lowercase
            //ch = putchar(toupper(ch));
            //+?? //make the kth character of thisword equal to ch
            thisword[k] = ch;
            thisword[k] = putchar(tolower(thisword[k]));
            k++;
        }
    }
    if (word == 1) 
    {
        thisword[k] = '\0';
        //add thisword into the list
        printf("Last Word:%s ", thisword);
        mywords = add_word(mywords, thisword);      
    }

    words *currword;
    printf("printing list\n");

    //+Traverse list and print each word and its count to outputfile
    //+output file is second parameter being passed

    myOutput = fopen(outputfile, "w+");  //+first parameter is input file
    if (myOutput == 0) 
    {
        printf("output file not opened \n");
        return 1;
    }
    else 
    {
        printf("output file opened \n");
    }

    currword = mywords;

    while (currword->next != NULL)
    {
        //add word name then word count to file, then move to next
        fprintf(myOutput, "%s %d \n", currword->str, currword->count);
        printf("%s ", currword->str);
        currword = currword->next;
    }

    return 0;

}

#包括
#包括
#包括
#包括
typedef结构s_字{
char*str；//word
int count；//单词出现的次数
struct s_words*next；//指向下一个单词的指针
}文字；
单词*创建单词（字符*单词）{
//+为结构分配空间
printf（“%lu”，strlen（word））；
words*newWord=malloc（sizeof（words））；
if（NULL！=新词）
{
//+为“str”中的新词分配存储空间
//+如果str是固定大小的数组，则可能会浪费存储空间
newWord->str=（char*）malloc（（strlen（word））+1；
strcpy（newWord->str，word）；//+将“word”复制到newWord->str
newWord->str[strlen（word）]='\0'；
printf（“创建：%s”，newWord->str）；
//+将计数初始化为1；
newWord->count=1；
//+下一步初始化；
newWord->next=NULL；
}
返回新词；
}
单词*添加单词（单词*单词列表，字符*单词）
{
int=0；
单词*temp=单词列表；
//+搜索列表中是否存在单词；如果存在，则使find=1
while（temp！=NULL）
{
如果（strcmp（temp->str，word）==0）
{//+使用strcmp命令
发现=1；
临时->计数=临时->计数+1；//+增量计数；
返回词表；
}
其他的
{
//+更新温度
温度=温度->下一步；
}
}
如果（找到==0）
{//新词
//printf（“%s”，单词）；
words*newWord=创建单词（word）；
if（NULL！=新词）
{
//+？在列表的开头插入新词
newWord->next=wordList；
printf（“新词：%s\n”，新词->str）；
}
返回新词；
}
//return wordList；//这里没有代码，只是在出错时添加
}
int main（int argc，char*argv[]）
{
words*mywords；//+包含单词的链接列表的标题
mywords=NULL；
文件*myFile；
文件*myOutput；
char*filename=argv[1]；
char*outputfile=argv[2]；
myFile=fopen（文件名，“r”）；//+第一个参数是输入文件
如果（myFile==0）
{
printf（“文件未打开\n”）；
返回1；
}
其他的
{
printf（“文件已打开”）；
}
//+开始逐字读取文件；
//+当检测到单词时，调用add_word函数
int ch=0，word=1，k=0；
字符这个词[100]；
//ch=putchar（tolower（ch））；
//ch=fgetc（myFile）；
而（（ch=fgetc（myFile））！=EOF）
{
//错误处理
如果（ch='.||ch='.|ch='.，'.|ch='.：'.| ch='.'.\n'）/+检测新词？检查ch是否是分隔符
{//如果上述if为真，则在下一个if中创建新词：
如果（word==1）/+请确保前一个字符不是分隔符
{
字=0；
//+将此单词的第k个字符设置为\0
这个词[k]='\0'；
//+现在调用add_word将该单词添加到列表中
printf（“添加：%s”，thisword）；
mywords=添加单词（mywords，ThisWords）；
printf（“添加了：%s\n”，mywords->str）；
k=0；
}
}
其他的
{
单词=1；
//使ch小写
//ch=putchar（toupper（ch））；
//+？？//使该单词的第k个字符等于ch
这个词[k]=ch；
这个词[k]=putchar（tolower（这个词[k]）；
k++；
}
}
if（word==1）
{
这个词[k]='\0'；
//将这个词添加到列表中
printf（“最后一个字：%s”，这个字）；
mywords=添加单词（mywords，ThisWords）；
}
单词*currword；
printf（“打印列表”）；
//+遍历列表并将每个单词及其计数打印到outputfile
//+输出文件是正在传递的第二个参数
myOutput=fopen（outputfile，“w+”）；//+第一个参数是输入文件
如果（myOutput==0）
{
printf（“输出文件未打开\n”）；
返回1；
}
其他的
{
printf（“输出文件已打开\n”）；
}
currword=mywords；
while（currword->next！=NULL）
{
//将单词名、单词数添加到文件中，然后移动到下一个
fprintf（myOutput，“%s%d\n”，currword->str，currword->count）；
printf（“%s”，currword->str）；
currword=currword->next；
}
返回0；
}

你肯定喜欢让事情对自己不利。。。您最大的四个问题是（1）未将

mywords

的地址传递给

add\u words

，（2）未能在

add\u words

中处理新的/空的列表案例，（3）将新节点添加到列表的开头，以及（4）每次调用

add\u word

时覆盖列表地址（例如

mywords=add\u words…

）

解决这些问题并稍微整理一下语法分析，您应该能够在列表中找到所有单词。检查/测试以下各项：

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

typedef struct s_words {
    char *str;                  //word
    int count;                  //number of times word occurs
    struct s_words *next;       //pointer to next word
} words;

words *create_words (char *word)
{
    //+allocate space for the structure
    printf ("%lu ", strlen (word));
    words *newWord = malloc (sizeof (words));
    if (NULL != newWord) {
        //+allocate space for storing the new word in "str"
        //+if str was array of fixed size, storage wud be wasted
        newWord->str = (char *) malloc ((strlen (word)) + 1);
        strcpy (newWord->str, word);    //+copy “word” into newWord->str
        newWord->str[strlen (word)] = '\0';
        printf (" Create: %s ", newWord->str);
        //+initialize count to 1;
        newWord->count = 1;
        //+initialize next;
        newWord->next = NULL;
    }
    return newWord;
}

words *add_word (words **wordList, char *word)
{
    if (!*wordList) {       /* handle EMPTY list */
        printf ("NEW LIST\n");
        return *wordList = create_words (word);
    }

    words *temp = *wordList;
    //+ search if word exists in the list; if so, make found=1
    while (temp->next != NULL) {    /* iterate while temp->next != NULL */

        if (strcmp (temp->str, word) == 0) {    //+use strcmp command
            temp->count = temp->count + 1;      //+increment count;
            return *wordList;
        }
        else
            temp = temp->next;  //+update temp
    }
    words *newWord = create_words (word);
    if (NULL != newWord) {  /* insert at TAIL of list */
        temp->next = newWord; 
        printf (" NEW WORD: %s\n ", newWord->str);
    }
    return newWord;
}

int main (int argc, char *argv[]) {

    words *mywords;             //+head of linked list containing words
    mywords = NULL;
    char *delim = ". ,:;\t\n";

    FILE *myFile;
    FILE *myOutput;

    char *filename = argv[1];
    char *outputfile = argv[2];

    if (argc != 3) {
        fprintf (stderr, "error: insufficient input. usage: %s ifile ofile\n",
                argv[0]);
        return 1;
    }

    myFile = fopen (filename, "r");     //+first parameter is input file
    if (myFile == 0) {
        printf ("file not opened\n");
        return 1;
    } else {
        printf ("file opened \n");
    }

    //+start reading file character by character;
    //+when word has been detected; call the add_word function

    int ch = 0, word = 1, k = 0;
    char thisword[100];
    while ((ch = fgetc (myFile)) != EOF) {  /* for each char    */
        if (strchr (delim, ch)) {           /* check if delim   */
            if (word == 1) {    /* if so, terminate word, reset */
                word = 0;
                thisword[k] = '\0';

                printf ("\nadd_word (mywords, %s)\n", thisword);
                /* do NOT overwrite list address each time,
                 * you must send ADDRESS of list to add_word
                 * to handle EMPTY list case.
                 */
                if (add_word (&mywords, thisword))
                    printf (" added: %s\n", mywords->str);
                else
                    fprintf (stderr, "error: add_word failed.\n");

                k = 0;
            }
        }
        else {  /* if not delim, add char to string, set word 1 */
            word = 1;
            thisword[k++] = tolower (ch);   /* make ch lowercase */
        }
    }
    if (word == 1) {    /* handle non-POSIX line-end */
        thisword[k] = '\0';
        //add thisword into the list
        printf ("\nadd_word (mywords, %s) (last)\n", thisword);
        if (add_word (&mywords, thisword))  /* same comment as above */
            printf (" added: %s\n", mywords->str);
        else
            fprintf (stderr, "error: add_word failed.\n");
    }

    words *currword;
    printf ("printing list\n");

    //+Traverse list and print each word and its count to outputfile
    //+output file is second parameter being passed

    myOutput = fopen (outputfile, "w+");        //+first parameter is input file
    if (myOutput == 0) {
        printf ("output file not opened \n");
        return 1;
    } else {
        printf ("output file opened \n");
    }

    currword = mywords;

    while (currword != NULL) {  /* just test currword here */
        //add word name then word count to file, then move to next
        fprintf (myOutput, "%s %d \n", currword->str, currword->count);
        printf ("%s ", currword->str);
        currword = currword->next;
    }

    putchar ('\n');
    return 0;
}

测试使用

$ cat ../dat/captnjack.txt
This is a tale
Of Captain Jack Sparrow
A Pirate So Brave
On the Seven Seas.

$ ./bin/llwordcount ../dat/captnjack.txt dat/llout.txt

$ cat dat/llout.txt
this 1
is 1
a 2
tale 1
of 1
captain 1
jack 1
sparrow 1
pirate 1
so 1
brave 1
on 1
the 1
seven 1
seas 1

输出文件

$ cat ../dat/captnjack.txt
This is a tale
Of Captain Jack Sparrow
A Pirate So Brave
On the Seven Seas.

$ ./bin/llwordcount ../dat/captnjack.txt dat/llout.txt

$ cat dat/llout.txt
this 1
is 1
a 2
tale 1
of 1
captain 1
jack 1
sparrow 1
pirate 1
so 1
brave 1
on 1
the 1
seven 1
seas 1

注意：对于打印/输出，只需

while（currword！=NULL）

遍历列表即可

现在，你应该真正考虑使用面向线的I