我如何才能读取长度未知的行中的每个单词？

Question

我试图使用链接列表来保存包含一段文本的文本文件中的每个单词。因此，每一行都有未知数量的单词，每个单词之间用空格分隔。我想我可以使用 strtok() 和 getline() 来阅读每个单词。但是，该程序仅读取每行的第一个单词，因此我认为可以使用循环来检测文件每行的末尾，以便读取所有单词。

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

struct node{
    char *word;
    struct node *next;
};

//refers to the struct for linked list 
typedef struct node link;

//a function to add word to front of linked list
link *addName(char[] word, link *head){
    link *temp1;

    temp1 = (link*)malloc(sizeof(link));
    //add char type word to linked list
    temp1->word = strdup(word);
    temp1->next = word;
    head = temp1;
    return head;
}

int main(){
    FILE *fO; 
    fO = fopen("paragraph.data", "r");
    int size = 0;
    int len = 0;

    //initialize it for the getline() and strtok()
    char *line = 0;

    
    //use malloc
    line = (char*)malloc(sizeof(int));

    //loop through the file
    while(getline(&line, &size, fO) != -1){
        char *word = strtok(line, " ");
        printf("the word: %s\n", word);

        //while(there is no "\n" detected?){}
        word = strtok(NULL, " ");
        printf("the word: %s\n", word);
        //addName()
    }

}

该文件是这样的（例如缩写）：

lorem ipsum
dolor
sit amet con sec
euter orci

它可以有任意数量的单词，这让我感到困惑。有谁知道如何让 while 循环检测每行的结尾？ 现在它只打印出每行的第一个单词。

the name: lorem
the name: dolor
the name: sit
the name: euter 

Answer 1

许多问题...

1. char[] word 不是有效的 C，并且无法编译
2. temp1->next = word; 成功不编译 - word 是一个 char * 指针，而不是指向
3. 您想要的节点的指针：temp1->next = head; 到链表中
4. 将新节点链接 在 strtok 上循环，因此，当然，您只会获得一个[或两个]令牌。
5. 在 main 中，size 必须是 size_t 而不是 int —— getline 调用甚至无法编译。
6. getline 确实不去除换行符
7. line 必须在循环结束时释放
8. 您的代码不调用 < main 中的 code>addName
9. 不要强制转换 malloc 的返回值：我是否强制转换 malloc 的结果？

---

在下面的代码中，我使用 < code>cpp 条件来表示旧代码与新代码：

#if 0
// old code
#else
// new code
#endif

#if 1
// new code
#endif

这是重构的代码。我已将 link 更改为 node 以更具描述性。它带有错误和修复注释：

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

typedef struct node node;
struct node {
    char *word;
    node *next;
};

//a function to add word to front of linked list
// NOTE/BUG: char[] isn't valid C and won't compile
#if 0
node *
addName(char[] word, node *head)
#else
node *
addName(const char *word, node *head)
#endif
{
    node *temp1;

    temp1 = malloc(sizeof(*temp1));

    // add char type word to linked list
    temp1->word = strdup(word);
// NOTE/BUG: word [corrected] is a char* and can't be assigned to next
#if 0
    temp1->next = word;
#else
    temp1->next = head;
#endif
    head = temp1;

    return head;
}

int
main()
{
    FILE *fO;

    fO = fopen("paragraph.data", "r");
// NOTE: bug size must be size_t or the getline won't compile
#if 0
    int size = 0;
#else
    size_t size = 0;
#endif
    int len = 0;

    // initialize it for the getline() and strtok()
#if 0
    char *line = 0;
#else
    char *line = NULL;
#endif

    // use malloc
// NOTE/BUG: getline expects a null pointer if size is 0
#if 0
    line = (char *) malloc(sizeof(int));
#endif

    // loop through the file
#if 0
    while (getline(&line, &size, fO) != -1) {
        char *word = strtok(line, " ");

        printf("the word: %s\n", word);

        // while(there is no "\n" detected?){}
        word = strtok(NULL, " ");
        printf("the word: %s\n", word);
        // addName()
    }
#else
    node *head = NULL;

    while (getline(&line, &size, fO) != -1) {
        // strip newline
        line[strcspn(line,"\n")] = 0;

        char *word = strtok(line," ");

        while (word != NULL) {
            printf("DEBUG: %s\n", word);
            head = addName(word,head);
            word = strtok(NULL," ");
        }
    }

    // must be freed at end
    free(line);

    // print linked list
    for (node *cur = head;  cur != NULL;  cur = cur->next)
        printf("Final: %s\n",cur->word);
#endif

    return 0;
}

---

这是完全清理的代码：

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

typedef struct node node;
struct node {
    char *word;
    node *next;
};

//a function to add word to front of linked list
node *
addName(const char *word, node *head)
{
    node *temp1;

    temp1 = malloc(sizeof(*temp1));

    // add char type word to linked list
    temp1->word = strdup(word);
    temp1->next = head;
    head = temp1;

    return head;
}

int
main()
{
    FILE *fO;

    fO = fopen("paragraph.data", "r");
    size_t size = 0;
    int len = 0;

    // initialize it for the getline() and strtok()
    char *line = NULL;

    // loop through the file
    node *head = NULL;

    while (getline(&line, &size, fO) != -1) {
        // strip newline
        line[strcspn(line,"\n")] = 0;

        char *word = strtok(line," ");

        while (word != NULL) {
            printf("DEBUG: %s\n", word);
            head = addName(word,head);
            word = strtok(NULL," ");
        }
    }

    // must be freed at end
    free(line);

    // print linked list
    for (node *cur = head;  cur != NULL;  cur = cur->next)
        printf("Final: %s\n",cur->word);

    return 0;
}

---

对于您的示例输入，这里是程序输出：

DEBUG: lorem
DEBUG: ipsum
DEBUG: dolor
DEBUG: sit
DEBUG: amet
DEBUG: con
DEBUG: sec
DEBUG: euter
DEBUG: orci
Final: orci
Final: euter
Final: sec
Final: con
Final: amet
Final: sit
Final: dolor
Final: ipsum
Final: lorem

Answer 2

您的主要问题是 line 已分配且 size 为零。如果您打算让 getline 为该行分配空间，则 size 必须为零且 line 必须为 null。另外，您应该在循环结束时释放分配的内存。

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

typedef struct node {
    char *word;
    struct node *next;
} link;

//a function to add word to front of linked list
link *addWord(char *word, link *head){
    link *temp1 = malloc(sizeof(link));

    //add string word to linked list
    temp1->word = strdup(word);
    temp1->next = head;
    return temp1;
}

int main(){
    FILE *fO; 
    fO = fopen("paragraph.data", "r");
    int size = 0;
    int len = 0;
    char *line;

    //loop through the file
    while(getline(&line, &size, fO) != EOF){
        char *word = strtok(line, " \n");

// addWord(词,头);
printf("单词：%s\n", word);

        while(word) {
            word = strtok(NULL, " \n");
            printf("the word: %s\n", word);

// addWord(词,头);
}
免费（线路）；
}
}