c - 将 CSV 解析为动态分配的结构数组 (ANSI 89)

Question

我正在尝试将 csv 解析为动态分配的结构数组，但是我的尝试因段错误而崩溃。

这是我的数据结构:

SO02773202,5087001,0
SO02773203,5087001,0
SO02773204,5087001,0
SO02773205,5087001,0
SO02773206,5087001,14

这是我将数据解析成的结构:

typedef struct saleslines{
  char* salesid;
  char* smmcampaignid;
  int numberofbottles;
} saleslines_t;

这是我解析文件的尝试:

int read_saleslines(saleslines_t* saleslines, int number_of_lines){
  char c;

  FILE* fp; 
  fp = fopen(FILENAME, "r");             /* Open the saleslines file */

  if(fp == NULL){                              /* Crash if file not found */
  printf("Error - file not found\n");
    return 0;
  }

  c = getc(fp);
  while (c != EOF){
    if (c == '\n'){
    number_of_lines += 1;
    }
    c = getc(fp);
  }

  printf("Number of lines is %d\n", number_of_lines);

  saleslines = (saleslines_t*) malloc((number_of_lines * 2) * sizeof(saleslines_t));

  /* allocation of the buffer for every line in the File */
  char *buf = (char*) malloc(1000);
  char *tmp; 

  if ( ( fp = fopen(FILENAME, "r" ) ) == NULL )
  {
    printf( "File could not be opened.\n" );
  }
  int i = 0;
  while (fgets(buf, 255, fp) != NULL){
    if ((strlen(buf)>0) && (buf[strlen (buf) - 1] == '\n'))
      buf[strlen (buf) - 1] = '\0';       

    tmp = strtok(buf, ",");
    saleslines[i].salesid = strdup(tmp);

    tmp = strtok(NULL, ",");
    saleslines[i].smmcampaignid = strdup(tmp);

    tmp = strtok(NULL, ",");
    saleslines[i].numberofbottles = atoi(tmp);

    printf("Salesid: %s\nCampaign: %s\nBottles: %i\n\n", saleslines[i].salesid , saleslines[i].smmcampaignid, saleslines[i].numberofbottles);

    i++;
  }
  free(buf);
  fclose(fp);
  printf("Number of lines is %i\n", number_of_lines);
  return number_of_lines;
}

出于某种原因，它解析文件并打印结果结构数组，但是当我之后立即调用此函数时，它因段错误而崩溃:

void print_saleslines_struct(saleslines_t* saleslines, int number_of_lines{
  int i;
  printf("Number of lines is %i", number_of_lines);
  for(i = 0; i < number_of_lines; i++){
    printf("Salesid:\t %s\n", saleslines[i].salesid);
    printf("Campaign:\t %s\n", saleslines[i].smmcampaignid);
    printf("# of Bottles:\t %d\n", saleslines[i].numberofbottles);
  }
}

我似乎找不到这个内存错误在哪里。

这里是初始化和main:

saleslines_t* saleslines;
saleslines_summary_t* saleslines_summary;
saleslines_grouped_t* saleslines_grouped;
int number_of_lines = 0;
int* number_of_linesp = &number_of_lines;

/* Main */

int main(){

  int chosen_option;

  while(1){

    printf("What would you like to do?\n");
    printf("1. Read saleslines.txt\n");
    printf("2. Print saleslines\n");
    printf("3. Summarise saleslines\n");
    printf("4. Exit the program\n");

    scanf("%d", &chosen_option);

    switch(chosen_option){

    /*  case 1 : number_of_lines = read_saleslines_file(saleslines, number_of_lines); break; */

      case 1 : number_of_lines = read_saleslines(saleslines, number_of_lines); break;

      case 2 : printf("Number of lines is %i", number_of_lines);  print_saleslines_struct(saleslines, number_of_lines); break;

      case 3 : summarise_saleslines(saleslines, number_of_linesp, saleslines_summary, saleslines_grouped); break;

      case 4 : free(saleslines); free(saleslines_summary); free(saleslines_grouped); return 0;   

    }

  }

  return 0;

}

更新

问题似乎出在我对结构数组的初始化上。

当我像这样初始化它时:saleslines_t* saleslines;然后像这样进行 malloc:saleslines = malloc(number_of_lines + 1 * sizeof(saleslines_t);

我遇到段错误。

但如果我这样初始化:saleslines[600];(分配的行数超过文件中的行数)，一切正常。

我该如何解决这个问题？我希望能够动态分配结构数组中的条目数。

编辑 2

以下是建议的更改:

int read_saleslines(saleslines_t** saleslines, int number_of_lines);

saleslines_t* saleslines;
int number_of_lines = 0;

int main(){

  while(1){

    printf("What would you like to do?\n");
    printf("1. Read saleslines.txt\n");
    printf("2. Print saleslines\n");
    printf("3. Summarise saleslines\n");
    printf("4. Exit the program\n");

    printf("Number of saleslines = %i\n", number_of_lines);

    scanf("%d", &chosen_option);

    switch(chosen_option){

    /*  case 1 : number_of_lines = read_saleslines_file(saleslines, number_of_lines); break; */

      case 1 : number_of_lines = read_saleslines(&saleslines, number_of_lines); break;

      case 2 : printf("Number of lines is %i", number_of_lines);  print_saleslines_struct(saleslines, number_of_lines); break;

      case 3 : summarise_saleslines(saleslines, number_of_linesp, saleslines_summary, saleslines_grouped); break;

      case 4 : free(saleslines); free(saleslines_summary); free(saleslines_grouped); return 0;   

    }

  }

  return 0;

}

int read_saleslines(saleslines_t** saleslines, int number_of_lines)
{

  char c;

  FILE* fp; 
  fp = fopen(FILENAME, "r");             /* Open the saleslines file */

  if(fp == NULL){                              /* Crash if file not found */
  printf("Error - file not found\n");
    return 0;
  }

  c = getc(fp);
  while (c != EOF){
    if (c == '\n'){
    number_of_lines += 1;
    }
    c = getc(fp);
  }

  fclose(fp);

  printf("Number of lines is %d\n", number_of_lines);

  *saleslines = (saleslines_t*) malloc((number_of_lines + 1) * sizeof(saleslines_t));

  /* allocation of the buffer for every line in the File */
  char *buf = malloc(25);
  char *tmp; 

  if ( ( fp = fopen(FILENAME, "r" ) ) == NULL )
  {
    printf( "File could not be opened.\n" );
  }
  int i = 0;
  while (fgets(buf, 25, fp) != NULL){
    if ((strlen(buf)>0) && (buf[strlen (buf) - 1] == '\n'))
      buf[strlen (buf) - 1] = '\0';       

    tmp = strtok(buf, ",");
    (*saleslines)[i].salesid = strdup(tmp);

    tmp = strtok(NULL, ",");
    (*saleslines)[i].smmcampaignid = strdup(tmp);

    tmp = strtok(NULL, ",");
    (*saleslines)[i].numberofbottles = atoi(tmp);

    printf("Salesid: %s\nCampaign: %s\nBottles: %i\n\n", saleslines[i]->salesid , saleslines[i]->smmcampaignid, saleslines[i]->numberofbottles);

    i++;
  }
  free(buf);
  fclose(fp);
  printf("Number of lines is %i\n", number_of_lines);
  return number_of_lines;
}

程序现在在读取结构数组中的第一个元素后出现段错误。

Answer 1

read_saleslines() 的参数有问题。第一个参数应该是指向结构数组的指针，即双指针。

在

int read_saleslines(saleslines_t* saleslines, int number_of_lines){

您想修改 saleslines 指向的位置。 saleslines是函数的局部变量，作用域就是那个函数。一旦退出 read_saleslines()，该变量就会被“销毁”，这意味着它所持有的值将无法再访问。添加另一个间接级别，一个指针，您可以修改定义在函数外部 的变量，无论是(丑陋的)全局变量还是其他变量。因此，更改该参数以使函数原型(prototype)匹配

int read_saleslines(saleslines_t** saleslines, int *);

并更改您在函数内部访问它的地方(添加一个*来访问它，例如:

saleslines = (saleslines_t*) malloc((number_of_lines * ...

到

*saleslines = (saleslines_t*) malloc((number_of_lines * ...

和

saleslines[i].salesid = strdup(tmp);

到

(*saleslines)[i].salesid = strdup(tmp);

然后在函数外使用变量的地方添加&:

number_of_lines = read_saleslines(saleslines, number_of_lines);

更改为

some_var = read_saleslines(&saleslines, &number_of_lines);

这将使您的代码工作。