C从文件中读取以空格分隔的值

时间:2013-08-03 19:51:09

标签: c file fgets scanf

我需要从文件中读取文本,并根据读取的信息为结构赋值。

以下是文本文件的格式:

First Middle Last   Address          city     state zip age sex tenure salary  
\--------------------------------------------------------------  
ADA     A AGUSTA    33 BABBAGE ROAD  LOVELACE    GB 19569 28 F 2 350.50  
ISSAC   A ASIMOV    99 FICTION WAY   AMHERST     MA 63948 58 M 6 423.88  
HUMPHRY R BOGART    71 SAM STREET    HOLLYWOOD   CA 48482 56 M 5 366.00  

结构我必须把它读成:

typedef struct  
{  
char first[8], initial, last[10],  
street[17], city[12], state[3];  
int age, tenure, zip;  
float salary;  
char sex;  
}Employee;  

到目前为止,我使用的代码是:

void inputLine(Employee* e)  
{  
fscanf(pay, "%s %s %s %s %s %s %s %s %d %d %s %d %f",  
           e->first, &e->initial, e->last, e->street,  
           e->street, e->city, e->city, e->state,  
           &e->zip, &e->age, &e->sex, &e->tenure,  
           &e->salary);  
}  

但是当我打印每一行时,前几行很好,然后事情开始变得混乱:

TED L KOPPEL ABC WASHINGTON DC 37376 48 M 9 909.44  
DAVID T LETTERMAN WNBC NEW YORK 0 0   
NY 1 47 5 STEVIE R 0 0   
NICKS 3 MUSIC CHICAGO 23459 38 0 0   
F 8 460.88 P 76 SILLY 0 89   
STREET L GB 44 2 320.50 0 12341   

我也尝试过:

void inputLine(Employee* e)  
{  
char line[53];  
fgets(line, 52, pay);  
printf("%s\n", line);  
fflush(stdout);  
sscanf(line, "%s %s %s %s %s %s %s %s %d %d %s %d %f",  
e->first, &e->initial, e->last, e->street,  
e->street, e->city, e->city, e->state,  
&e->zip, &e->age, &e->sex, &e->tenure,  
&e->salary);  
}  

但是这会得到相同的结果。

代码不能在C ++中。 我正在使用Linux GNU GCC 4.8.1编译器,但我也在Mac的编译器上对它进行了测试,但它没有用。

1 个答案:

答案 0 :(得分:5)

pay等全局变量 - 明确定义为FILE *pay; - 是一个坏主意,在示例代码中完全没有必要。始终测试fscanf()及其亲属的返回值,以确保获得预期的所有数据。

但是,您的问题是%s在第一个空格处停止,因此您在阅读地址字段时遇到了巨大的问题。您的输入也不受约束。您还尝试多次使用e->street获取街道地址的多个字词;这是行不通的,因为第三个单词会覆盖第一个单词。

您需要以下内容:

int inputLine(FILE *fp, Employee* e)  
{  
    if (fscanf(fp, "%7s %c %9s %16c %11c %2s %d %d %c %d %f",  
               e->first, &e->initial, e->last, e->street, e->city, e->state,  
               &e->zip, &e->age, &e->sex, &e->tenure, &e->salary) != 11)
        return -1;
    e->street[16] = '\0';
    e->city[11] = '\0';
    return 0;
}

这使用%c来读取单个字符;它使用%16c来读取多字街道地址,使用%11c来读取(可能是多字)城市。它使用%7s%9s%2s来防止其他字符串溢出。 fscanf()调用后的分配可确保计数的%c字符串为空终止; %16c本身不会添加空终止符。

inputLine()函数现在会在出现问题时返回错误指示(-1已选中),0表示成功。这是Unix系统调用的常见模式,但与基础scanf() - 函数族的行为不同,如comment chux中所述。

工作代码1

此代码使用问题中的fscanf()读取标准输入。它确保emp数组也没有溢出。

#include <stdio.h>

typedef struct  
{  
    char first[8], initial, last[10],  
         street[17], city[12], state[3];  
    int age, tenure, zip;  
    float salary;  
    char sex;  
} Employee; 

void dump_employee(FILE *fp, const char *tag, const Employee *e);
int inputLine(FILE *fp, Employee *e);

enum { MAXEMP = 10 };

int main(void)
{
    char line[4096];
    Employee emp[MAXEMP];

    if (fgets(line, sizeof(line), stdin) == 0 ||
        fgets(line, sizeof(line), stdin) == 0)
        return 1;
    for (int i = 0; i < MAXEMP && inputLine(stdin, &emp[i]) != 0; i++)
        dump_employee(stdout, "Employee", &emp[i]);
    return 0;
}

int inputLine(FILE *fp, Employee *e)  
{  
    if (fscanf(fp, "%7s %c %9s %16c %11c %2s %d %d %c %d %f",  
               e->first, &e->initial, e->last, e->street, e->city, e->state,  
               &e->zip, &e->age, &e->sex, &e->tenure, &e->salary) != 11)
        return -1;
    e->street[16] = '\0';
    e->city[11] = '\0';
    return 0;
}

void dump_employee(FILE *fp, const char *tag, const Employee *e)  
{  
    fprintf(fp, "%s: %-7s %c %-9s %-16s %-11s %-2s %.5d %3d %c %d %6.2f\n",  
               tag, e->first, e->initial, e->last, e->street, e->city, e->state,  
               e->zip, e->age, e->sex, e->tenure, e->salary);
}

示例输出

Employee: ADA     A AGUSTA    33 BABBAGE ROAD  LOVELACE    GB 19569  28 F 2 350.50
Employee: ISSAC   A ASIMOV    99 FICTION WAY   AMHERST     MA 63948  58 M 6 423.88
Employee: HUMPHRY R BOGART    71 SAM STREET    HOLLYWOOD   CA 48482  56 M 5 366.00

工作代码2

此代码使用fgets()来读取行,使用sscanf()来转换数据。使用此版本的代码可以更容易地报告错误。

#include <stdio.h>

typedef struct  
{  
    char first[8], initial, last[10],  
         street[17], city[12], state[3];  
    int age, tenure, zip;  
    float salary;  
    char sex;  
} Employee; 

void dump_employee(FILE *fp, const char *tag, const Employee *e);
int scan_employee(Employee *e, const char *line);

enum { MAXEMP = 10 };

int main(void)
{
    char line[4096];
    Employee emp[MAXEMP];

    if (fgets(line, sizeof(line), stdin) == 0 ||
        fgets(line, sizeof(line), stdin) == 0)
        return 1;
    for (int i = 0; i < MAXEMP && fgets(line, sizeof(line), stdin) != 0; i++)
    {
        if (scan_employee(&emp[i], line) == 0)
            dump_employee(stdout, "Employee", &emp[i]);
    }
    return 0;
}

int scan_employee(Employee *e, const char *line)  
{  
    if (sscanf(line, "%7s %c %9s %16c %11c %2s %d %d %c %d %f",  
               e->first, &e->initial, e->last, e->street, e->city, e->state,  
               &e->zip, &e->age, &e->sex, &e->tenure, &e->salary) != 11)
        return -1;
    e->street[16] = '\0';
    e->city[11] = '\0';
    return 0;
}

void dump_employee(FILE *fp, const char *tag, const Employee *e)  
{  
    fprintf(fp, "%s: %-7s %c %-9s %-16s %-11s %-2s %.5d %3d %c %d %6.2f\n",  
               tag, e->first, e->initial, e->last, e->street, e->city, e->state,  
               e->zip, e->age, e->sex, e->tenure, e->salary);
}

此输出与问题中的样本数据的输出相同。