我正在尝试使用C将csv文件中的内容插入到链接列表中。但是,我得到了很多垃圾输出。源代码如下。
#include<stdio.h>
#include<stdlib.h>
#include<string.h>
struct product *customer_head;
struct customer
{
long long int c_id;//first 6 characters=date & next 6 characters=time & next characters=counter no & city code
/*Compulsory Fields (Cannot be Skipped)*/
char name[57];
long long int ph_no;//10 digit phone number
/*Non Compulsory Fields (Can be Skipped)*/
char address[58];
char city[25];
char state_code[2];
char pin[6];
char email[60];
struct customer *next;
};
struct customer * load()
{
FILE * cust=fopen("customer_db.csv","r");
struct customer *temp,*ptr;
customer_head=NULL;
char str[208];
char *token,*eptr1,*eptr2;
int line_cnt=0,i=0;
while(fgets(str,234,cust)!=NULL)
{
line_cnt=0;
i=0;
ptr=(struct customer *)malloc(sizeof(struct customer));
for(;str[i];i++)
{
if(str[i]=='\n')
{
str[i]='\0';
i=0;
break;
}
}
token=strtok(str,",");
while(token!=NULL)
{
if(line_cnt==0)
ptr->c_id=strtoll(token,&eptr1,10);
else if(line_cnt==1)
ptr->ph_no=strtoll(token,&eptr2,10);
else if(line_cnt==2)
sprintf(ptr->name,"%s",token);
else if(line_cnt==3)
sprintf(ptr->address,"%s",token);
else if(line_cnt==4)
sprintf(ptr->city,"%s",token);
else if(line_cnt==5)
sprintf(ptr->state_code,"%s",token);
else if(line_cnt==6)
sprintf(ptr->pin,"%s",token);
else
sprintf(ptr->email,"%s",token);
line_cnt++;
token=strtok(NULL,",");
}
if(customer_head==NULL)
customer_head=ptr;
else
temp->next=ptr;
temp=ptr;
}
}
int print(struct customer *h)
{
while(h->next!=NULL)
{
printf("\nCustomer ID: ");
printf("%lld",h->c_id);
printf("\nName: ");
puts(h->name);
printf("Phone Number: ");
printf("%lld",h->ph_no);
printf("\nAddress: ");
puts(h->address);
printf("City: ");
puts(h->city);
printf("State Code: ");
puts(h->state_code);
printf("PIN: ");
puts(h->pin);
printf("Email: ");
puts(h->email);
h=h->next;
}
printf("\nCustomer ID: ");
printf("%lld",h->c_id);
printf("\nName: ");
puts(h->name);
printf("Phone Number: ");
printf("%ld",h->ph_no);
printf("\nAddress: ");
puts(h->address);
printf("City: ");
puts(h->city);
printf("State Code: ");
puts(h->state_code);
printf("PIN: ");
puts(h->pin);
printf("Email: ");
puts(h->email);
return 1;
}
int main()
{
load();
print(customer_head);
}
我也在这里附加了csv文件。为了使程序更简单,我从csv文件中删除了标题。他们按顺序
客户编号,电话号码,姓名,地址,城市,州代码,PIN码,电子邮件
1403201156540201,2226179183,Katherine_Hamilton,87_Thompson_St.,Fremont,IA,502645,[email protected]
2204201532220103,8023631298,Marc_Knight,-,-,-,-,-
0305201423120305,8025595163,Albie_Rowland,-,Hamburg,NY,140752,-
0607201232220901,4055218053,Grant_Phelps,-,-,-,-,-
破折号(-)表示这些字段应保持为空。
输出如下:
Customer ID: 1403201156540201
Name: Katherine_Hamilton
Phone Number: 2226179183
Address: 87_Thompson_St.
City: Fremont
State Code: [email protected]
PIN: [email protected]
Email: [email protected]
Customer ID: 2204201532220103
Name: Marc_Knight
Phone Number: 8023631298
Address: -
City: -
State Code: -
PIN: -
Email: -
Customer ID: 305201423120305
Name: Albie_Rowland
Phone Number: 8025595163
Address: -
City: Hamburg
State Code: NY140752-
PIN: 140752-
Email: -
Customer ID: 607201232220901
Name: Grant_Phelps
Phone Number: 4055218053
Address: -
City: -
State Code: -
PIN: -
Email: -
如您所见,内容在很多地方都已合并。我不明白为什么。
由于从注释中您知道字符数组的声明受字符太少的影响,至少在char state_code[2];
使数组不包含导致未定义行为的n终止字符的情况下,应确保对您所有的输入。(不要跳过缓冲区大小)
通常,您会使自己的工作变得比实际需要的要难。您没有固定的输入字段,而没有尝试使用strtok()
和计算字段并处理的8部分链中的每个if, else if ...
字段,因此只需解析数据sscanf()
并验证转换次数以确认解析成功即可,例如
/** fill list from csv file */
list_t *list_from_csv (list_t *list, FILE *fp)
{
char buf[MAXC];
node_t data = { .c_id = 0, .next = NULL };
while (fgets (buf, MAXC, fp)) { /* read each line in file */
/* parse and VALIDATE values from line */
if (sscanf (buf, "%lld,%lld,%63[^,],%63[^,],%31[^,],%7[^,],%7[^,],%63[^,\n]",
&data.c_id, &data.ph_no, data.name, data.address, data.city,
data.state_code, data.pin, data.email) == 8) {
if (!add (list, &data)) /* validate add to list or break */
break;
}
}
return list;
}
在这里,list_t
只是一个附加的“包装器”结构,该结构为链接列表保留head
和tail
指针。这使您可以在所需范围内声明多个列表,并通过使tail
指针始终指向列表中的最后一个节点(your temp
)来允许相同的O(1)插入。在这里,head
和tail
只是包装器的一部分,并作为参数传递,而不必将列表指针声明为全局(不好的做法)。列表中的每个节点和包装器结构均可编写为:
#define BYTE8 8 /* if you need a constant, #define one (or more) */
#define BYTE32 32
#define BYTE64 64
#define MAXC 1024
typedef struct node_t { /* list node */
/* 6 characters=date & 6 characters=time & counter no & city code */
long long int c_id;
/*Compulsory Fields (Cannot be Skipped)*/
char name[BYTE64];
long long int ph_no; //10 digit phone number
/*Non Compulsory Fields (Can be Skipped)*/
char address[BYTE64];
char city[BYTE32];
char state_code[BYTE8];
char pin[BYTE8];
char email[BYTE64];
struct node_t *next;
} node_t;
typedef struct { /* list wrapper with head & tail pointers */
node_t *head, *tail;
} list_t;
然后,不要将您的列表写成load()
同时包含FILE
和列表操作,而是将列表操作分开。只需创建一个add()
函数即可将节点添加到列表中,例如
/** add node at end of list, update tail to end */
node_t *add (list_t *l, node_t *data)
{
node_t *node = malloc (sizeof *node); /* allocate node */
if (!node) { /* validate allocation */
perror ("malloc-node");
return NULL;
}
*node = *data; /* initialize members values */
if (!l->head) /* if 1st node, node is head/tail */
l->head = l->tail = node;
else { /* otherwise */
l->tail->next = node; /* add at end, update tail pointer */
l->tail = node;
}
return node; /* return new node */
}
现在,您的加载函数只需要从文件中读取每一行并解析该行,然后调用add()
传递指向数据结构的指针以及列表指针作为参数即可。您的load()
功能减少为:
/** fill list from csv file */
list_t *list_from_csv (list_t *list, FILE *fp)
{
char buf[MAXC];
node_t data = { .c_id = 0, .next = NULL };
while (fgets (buf, MAXC, fp)) { /* read each line in file */
/* parse and VALIDATE values from line */
if (sscanf (buf, "%lld,%lld,%63[^,],%63[^,],%31[^,],%7[^,],%7[^,],%63[^,\n]",
&data.c_id, &data.ph_no, data.name, data.address, data.city,
data.state_code, data.pin, data.email) == 8) {
if (!add (list, &data)) /* validate add to list or break */
break;
}
}
return list;
}
(注意:使用strtok()
或时sscanf()
,无需'\n'
从输入字符串中删除尾随-只需将其作为定界符包含在内即可,strtok()
或使用排除在转换之外sscanf()
)
此外,您无需多次调用puts()
,并printf()
在你的清单打印数据的每个节点的价值。查看您进行了多少次函数调用以打印数据。您只需打一个电话printf()
,例如
/** print all nodes in list */
void prn_list (list_t *l)
{
if (!l->head) {
puts ("list-empty");
return;
}
for (node_t *n = l->head; n; n = n->next)
printf ("\nCustomer ID: %lld\n"
"Name: %s\n"
"Phone Number: %lld\n"
"Address: %s\n"
"City: %s\n"
"State Code: %s\n"
"PIN: %s\n"
"Email: %s\n", n->c_id, n->name, n->ph_no, n->address, n->city,
n->state_code, n->pin, n->email);
}
在main()
简单地声明list_t
包装器的实例中,打开/验证您的包装器,FILE
然后将指针传递到列表,并将文件流传递到您的list_from_csv()
(您的load()
),然后打印该列表,最后释放所有您已分配的内存,然后完成。(是的,内存将在退出时被释放,但是会提早养成良好的习惯-不久之后,您将在函数中使用分配内存,否则在释放之前会return
导致内存泄漏)
int main (int argc, char **argv) {
list_t list = { .head = NULL, .tail = NULL };
/* use filename provided as 1st argument (stdin by default) */
FILE *fp = argc > 1 ? fopen (argv[1], "r") : stdin;
if (!fp) { /* validate file open for reading */
perror ("file open failed");
return 1;
}
if (!list_from_csv (&list, fp))
return 1;
if (fp != stdin) /* close file if not stdin */
fclose (fp);
prn_list (&list);
del_list (&list);
}
综上所述,您将获得类似于以下内容的内容:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define BYTE8 8 /* if you need a constant, #define one (or more) */
#define BYTE32 32
#define BYTE64 64
#define MAXC 1024
typedef struct node_t { /* list node */
/* 6 characters=date & 6 characters=time & counter no & city code */
long long int c_id;
/*Compulsory Fields (Cannot be Skipped)*/
char name[BYTE64];
long long int ph_no; //10 digit phone number
/*Non Compulsory Fields (Can be Skipped)*/
char address[BYTE64];
char city[BYTE32];
char state_code[BYTE8];
char pin[BYTE8];
char email[BYTE64];
struct node_t *next;
} node_t;
typedef struct { /* list wrapper with head & tail pointers */
node_t *head, *tail;
} list_t;
/** add node at end of list, update tail to end */
node_t *add (list_t *l, node_t *data)
{
node_t *node = malloc (sizeof *node); /* allocate node */
if (!node) { /* validate allocation */
perror ("malloc-node");
return NULL;
}
*node = *data; /* initialize members values */
if (!l->head) /* if 1st node, node is head/tail */
l->head = l->tail = node;
else { /* otherwise */
l->tail->next = node; /* add at end, update tail pointer */
l->tail = node;
}
return node; /* return new node */
}
/** print all nodes in list */
void prn_list (list_t *l)
{
if (!l->head) {
puts ("list-empty");
return;
}
for (node_t *n = l->head; n; n = n->next)
printf ("\nCustomer ID: %lld\n"
"Name: %s\n"
"Phone Number: %lld\n"
"Address: %s\n"
"City: %s\n"
"State Code: %s\n"
"PIN: %s\n"
"Email: %s\n", n->c_id, n->name, n->ph_no, n->address, n->city,
n->state_code, n->pin, n->email);
}
/** delete all nodes in list */
void del_list (list_t *l)
{
node_t *n = l->head;
while (n) {
node_t *victim = n;
n = n->next;
free (victim);
}
}
/** fill list from csv file */
list_t *list_from_csv (list_t *list, FILE *fp)
{
char buf[MAXC];
node_t data = { .c_id = 0, .next = NULL };
while (fgets (buf, MAXC, fp)) { /* read each line in file */
/* parse and VALIDATE values from line */
if (sscanf (buf, "%lld,%lld,%63[^,],%63[^,],%31[^,],%7[^,],%7[^,],%63[^,\n]",
&data.c_id, &data.ph_no, data.name, data.address, data.city,
data.state_code, data.pin, data.email) == 8) {
if (!add (list, &data)) /* validate add to list or break */
break;
}
}
return list;
}
int main (int argc, char **argv) {
list_t list = { .head = NULL, .tail = NULL };
/* use filename provided as 1st argument (stdin by default) */
FILE *fp = argc > 1 ? fopen (argv[1], "r") : stdin;
if (!fp) { /* validate file open for reading */
perror ("file open failed");
return 1;
}
if (!list_from_csv (&list, fp))
return 1;
if (fp != stdin) /* close file if not stdin */
fclose (fp);
prn_list (&list);
del_list (&list);
}
使用/输出示例
将输入文件放在中dat/customer_list.txt
,运行该程序,您将收到:
$ ./bin/customer_list dat/customer_list.txt
Customer ID: 1403201156540201
Name: Katherine_Hamilton
Phone Number: 2226179183
Address: 87_Thompson_St.
City: Fremont
State Code: IA
PIN: 502645
Email: [email protected]
Customer ID: 2204201532220103
Name: Marc_Knight
Phone Number: 8023631298
Address: -
City: -
State Code: -
PIN: -
Email: -
Customer ID: 305201423120305
Name: Albie_Rowland
Phone Number: 8025595163
Address: -
City: Hamburg
State Code: NY
PIN: 140752
Email: -
Customer ID: 607201232220901
Name: Grant_Phelps
Phone Number: 4055218053
Address: -
City: -
State Code: -
PIN: -
Email: -
内存使用/错误检查
在您编写的任何动态分配内存的代码中,对于任何分配的内存块,您都有2个责任:(1)始终保留指向该内存块的起始地址的指针,因此,(2)在没有内存块时可以将其释放需要更长的时间。
必须使用一个内存错误检查程序来确保您不尝试访问内存或不要在已分配的块的边界之外/之外写,尝试读取或基于未初始化的值进行条件跳转,最后确认您可以释放已分配的所有内存。
对于Linuxvalgrind
是正常的选择。每个平台都有类似的内存检查器。它们都很容易使用,只需通过它运行程序即可。
$ valgrind ./bin/customer_list dat/customer_list.txt
==14823== Memcheck, a memory error detector
==14823== Copyright (C) 2002-2017, and GNU GPL'd, by Julian Seward et al.
==14823== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==14823== Command: ./bin/customer_list dat/customer_list.txt
==14823==
Customer ID: 1403201156540201
Name: Katherine_Hamilton
Phone Number: 2226179183
Address: 87_Thompson_St.
City: Fremont
State Code: IA
PIN: 502645
Email: [email protected]
<snipped rest>
==14823==
==14823== HEAP SUMMARY:
==14823== in use at exit: 0 bytes in 0 blocks
==14823== total heap usage: 7 allocs, 7 frees, 6,728 bytes allocated
==14823==
==14823== All heap blocks were freed -- no leaks are possible
==14823==
==14823== For counts of detected and suppressed errors, rerun with: -v
==14823== ERROR SUMMARY: 0 errors from 0 contexts (suppressed: 0 from 0)
始终确认已释放已分配的所有内存,并且没有内存错误。
尽管仅通过确保每个字符串都有足够的存储空间就可以解决问题的很大一部分,但是请花一些时间思考使用sscanf()
和进行值解析的方法,并且由于您控制了转换,因此无需删除路径中的尾部'\n'
。行从文件中读取。(只是不要在从输入字符串解析的值中包含换行符)如果您确实想'\n'
从头开始解析,则应使用,例如
str[strcspn (str, "\n")] = 0;
最后,使用sscanf()
和一起使用的格式字符串strcspn()
,请确保您完全了解它们的工作原理,请参见man 3 scanf和man 3 strspn
如果您还有其他问题,请告诉我。
本文收集自互联网,转载请注明来源。
如有侵权,请联系 [email protected] 删除。
我来说两句