如何根据C中的匹配词解析和排列csv文件的行?

Question

>我有以下格式的csv文件：

name,birthmonth,country,hobby
jack,jan,england,soccer
roben,july,germany,soccer
emma,dec,china,tennis
yannick,sep,france,music
alex,nov,england,cricket
thomas,apr,germany,tennis
mike,oct,netherlands,cycling
michelle,feb,france,poetry
yui,mar,japan,coding
feng,jun,china,reading

我想使用 C 解析此文件，并以连续的方式放置所有具有相同国家/地区名称的行，如下所示：

name,birthmonth,country,hobby
jack,jan,england,soccer
alex,nov,england,cricket
roben,july,germany,soccer
thomas,apr,germany,tennis
emma,dec,china,tennis
feng,jun,china,reading
yannick,sep,france,music
michelle,feb,france,poetry
mike,oct,netherlands,cycling
yui,mar,japan,coding

到目前为止，我已经在下面尝试了这段代码，但是无法正确匹配并继续：

#include<stdio.h>
#include<stdlib.h>
#include<ctype.h>
#include<fcntl.h>
#include<string.h>
int main (int argc, char **argv) {
//int line;
char line[200];
char *inputFile =  argv[1];
FILE *input_csv_file;
char a,b,c,d,e;
input_csv_file = fopen(inputFile, "rt");
if(input_csv_file ==0) {
printf("Can not open input file n");
} 
else {    
//while((line = fgetc(input_csv_file)) != EOF) {
while(fgets(line, sizeof line, input_csv_file) != NULL) {
printf ("line = %sn", line);
if(sscanf(line, "%s,%s,%s,%s,%s", a,b,c,d,e)) {
//if(sscanf(line, "%[^,], %[^,], %[^,], %[^,], %[^,]", a,b,c,d,e)) {
printf("d=%sn",d);
}         
}
} 
return 0;
}

我是 C/C++ 的新手。任何帮助将不胜感激 谢谢。

Answer 1

我可以编写代码来获得所需的输出。下面是代码：

#include<stdio.h>
#include<stdlib.h>
#include<ctype.h>
#include<fcntl.h>
#include<string.h>
int main(int argc, char ** argv) 
{
struct filedata {
char nation[8];
char content[50];
};
char line[100];
char *inputFile = argv[1];
FILE *input_csv_file;
int iter = 0, c;
char * tok;
int count = 0;
char ch;
char country[] = "country";
char header_line[50];
input_csv_file = fopen(inputFile, "rt");
//count line numbers of the input csv
for(ch = getc(input_csv_file); ch!= EOF; ch=getc(input_csv_file))
if(ch == 'n')
count = count + 1;

fclose(input_csv_file);

count =  count -1;
struct filedata * record[count];
input_csv_file = fopen(inputFile, "rt");
if(input_csv_file == 0) 
{
printf("Can not open input filen");
} else 
{
while(fgets(line, sizeof line, input_csv_file) != NULL) 
{
//printf("-- line = %sn", line);
int s_line = sizeof line;
char dup_line[s_line];
strcpy(dup_line, line);
int h = 0;
int s_token;
tok = strtok(line, ",");
while(tok != NULL) 
{
h++;
if(h == 3)
{
s_token = sizeof tok;
break;
}
tok = strtok(NULL, ",");
}

// skipping the line having column headers
if(compare_col(tok, country) == 0) {
strcpy(header_line, dup_line);
continue;
}
iter++;
c = iter - 1;
record[c] = (struct filedata*)malloc(sizeof(struct filedata));
strcpy(record[c]->nation, tok);
strcpy(record[c]->content, dup_line);
} //while
struct filedata * temp;
FILE * fptr;
fptr = fopen("nation_csv.txt", "w");
if(fptr == NULL)
{
printf("Error in opening the file to writen");
exit(1);
}
// sorting the arr of struct nation wise
for(iter=1; iter < count; iter++)
for(c =0 ; c < count -1; c++) {
if(strcmp(record[c]->nation, record[c+1]->nation) > 0) {
temp = record[c];
record[c] = record[c+1];
record[c+1] = temp;
}
} 
for(iter=0; iter < count; ++iter) 
{
if(iter == 0) {
fprintf(fptr, "%s", header_line);
continue;
}
fprintf(fptr, "%s", record[iter]->content);
}
fclose(fptr);
}
fclose(input_csv_file);
}
int compare_col(char a[], char b[] )
{
int c = 0;
while(a[c] == b[c]) {
if(a[c] == '' || b[c] == '')
break;
c++;
}
if(a[c] == '' && b[c] == '')
return 0;
else 
return -1;
}   

感谢您的所有意见。非常感谢任何进一步的投入，以使其更好。

谢谢