C语言打印链表时字符串出现垃圾值问题求助

问题概述 #

从文本文件读取数据填充如下NODE结构体链表时，初始化节点阶段打印字符串正常，但调用printList()函数时，line字段始终显示垃圾值。

typedef struct node {
    int data;
    char* line;
    struct node* next;
} NODE;

运行示例 #

./a.out linkedlisttext.txt

data in readFile(): 4
string in readFile():  Hello world
address in readFile(): 0x1326067a0


data in readFile(): 28
string in readFile():  What is up world???
address in readFile(): 0x1326067c0


data in readFile(): 2124
string in readFile():  your mother
address in readFile(): 0x1326067e0


data in readFile(): 85
string in readFile():  more data
address in readFile(): 0x132606800


data in readFile(): 9421
string in readFile():  just a little more data
address in readFile(): 0x132606820


data in readFile(): 992
string in readFile():  are we almost there?
address in readFile(): 0x132606840


data in readFile(): 301
string in readFile():  we did it!
address in readFile(): 0x132606860

DATA:    4 | STRING �g`2
address in printList(): 0x1326067a0
DATA:   28 | STRING �g`2
address in printList(): 0x1326067c0
DATA: 2124 | STRING �g`2
address in printList(): 0x1326067e0
DATA:   85 | STRING h`2
address in printList(): 0x132606800
DATA: 9421 | STRING 0h`2
address in printList(): 0x132606820
DATA:  992 | STRING Ph`2
address in printList(): 0x132606840
DATA:  301 | STRING 
address in printList(): 0x132606860

输入文件内容（linkedlisttext.txt） #

4, Hello world
28, What is up world???
2124, your mother
85, more data
9421, just a little more data
992, are we almost there?
301, we did it!

完整错误代码 #

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

typedef struct node {
    int data;
    char* line;
    struct node* next;
} NODE;


struct node* readFile(FILE* fp, NODE* root) {
    char line[100];
    char* token;
    NODE* curr;
    NODE* prev;

    while(fgets(line, 100, fp) != NULL) {   
        curr = malloc(sizeof(struct node*));
        token = strtok(line, ",");
        curr->data = atoi(token);
        printf("\ndata in readFile(): %d\n", curr->data);
        token = strtok(NULL, "");
        curr->line = (char*) malloc(sizeof(token)  + 1);
        strcpy(curr->line, token);
        printf("string in readFile(): %s", curr->line);
        printf("address in readFile(): %p\n\n", curr->line);
        curr->next = NULL;  
        if(root == NULL) {
            root = curr;
        } else {
            NODE* travel = root;
            while(travel->next != NULL) {
                travel = travel->next;
            }
            travel->next = curr;
        }
    }
    return root;    
}

void printList(NODE* root) {
    struct node* temp = root;
    while(temp->next != NULL) {
        printf("DATA: %4d | STRING %s\n", temp->data, temp->line);
        printf("address in printList(): %p\n", temp->line);
        temp = temp->next;
    }
    printf("DATA: %4d | STRING %s\n", temp->data, temp->line);
    printf("address in printList(): %p\n", temp->line);
}

int main(int argc, char** argv) {
    FILE* fp = fopen(argv[1], "r");
    NODE* root = NULL;  
    if(fp == NULL) {
        return 0;
    }   
    root = readFile(fp, root);
    printList(root);
}

问题原因 #

1. 节点内存分配错误：curr = malloc(sizeof(struct node*))仅分配了指针大小的内存（通常4或8字节），但NODE结构体的实际大小远大于指针，导致内存越界，后续操作会覆盖节点的line指针或其他字段，引发未定义行为。
2. 字符串内存分配错误：curr->line = (char*) malloc(sizeof(token) + 1)中，sizeof(token)是指针的大小，不是字符串的实际长度。分配的内存空间不足以存储完整字符串，导致strcpy操作越界，破坏内存中的其他数据。

修复方案 #

• 将节点内存分配改为malloc(sizeof(struct node))，确保分配足够空间存储整个结构体。
• 将字符串内存分配改为malloc(strlen(token) + 1)，根据字符串实际长度分配空间，加1是为了存储终止符\0。
• 可选优化：在链表插入时维护尾节点，避免每次遍历整个链表提升效率。

修复后的代码 #

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

typedef struct node {
    int data;
    char* line;
    struct node* next;
} NODE;


struct node* readFile(FILE* fp, NODE* root) {
    char line[100];
    char* token;
    NODE* curr;
    NODE* tail = NULL; // 维护尾节点优化插入

    while(fgets(line, 100, fp) != NULL) {   
        // 修复节点内存分配
        curr = malloc(sizeof(struct node));
        if (!curr) { // 增加内存分配失败检查
            perror("malloc failed");
            exit(EXIT_FAILURE);
        }
        token = strtok(line, ",");
        curr->data = atoi(token);
        printf("\ndata in readFile(): %d\n", curr->data);
        token = strtok(NULL, "");
        // 修复字符串内存分配
        curr->line = malloc(strlen(token) + 1);
        if (!curr->line) { // 增加内存分配失败检查
            perror("malloc failed");
            free(curr);
            exit(EXIT_FAILURE);
        }
        strcpy(curr->line, token);
        printf("string in readFile(): %s", curr->line);
        printf("address in readFile(): %p\n\n", curr->line);
        curr->next = NULL;  
        if(root == NULL) {
            root = curr;
            tail = curr;
        } else {
            // 尾节点直接插入，无需遍历
            tail->next = curr;
            tail = curr;
        }
    }
    return root;    
}

void printList(NODE* root) {
    struct node* temp = root;
    while(temp != NULL) { // 简化循环条件
        printf("DATA: %4d | STRING %s", temp->data, temp->line);
        printf("address in printList(): %p\n", temp->line);
        temp = temp->next;
    }
}

int main(int argc, char** argv) {
    if (argc < 2) { // 增加参数检查
        fprintf(stderr, "Usage: %s <filename>\n", argv[0]);
        return EXIT_FAILURE;
    }
    FILE* fp = fopen(argv[1], "r");
    NODE* root = NULL;  
    if(fp == NULL) {
        perror("fopen failed");
        return EXIT_FAILURE;
    }   
    root = readFile(fp, root);
    printList(root);
    // 可选：添加链表内存释放逻辑，避免内存泄漏
    fclose(fp);
    return EXIT_SUCCESS;
}

内容的提问来源于stack exchange，提问作者Vesot