Last active
November 17, 2021 16:04
-
-
Save weirddan455/530cc599ea0f1e268a27be8ac2061cec to your computer and use it in GitHub Desktop.
Program to extract Arena Ids from MTGJson dataset
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include <fcntl.h> | |
#include <stdbool.h> | |
#include <stdio.h> | |
#include <stdlib.h> | |
#include <string.h> | |
#include <sys/stat.h> | |
#include <unistd.h> | |
typedef struct Card | |
{ | |
int id; | |
char name[128]; | |
} Card; | |
Card cards[10000]; | |
int main() | |
{ | |
int fd = open("AllPrintings.json", O_RDONLY); | |
if (fd == -1) | |
{ | |
puts("Failed to open file"); | |
return 1; | |
} | |
struct stat fileInfo; | |
if (fstat(fd, &fileInfo) != 0) | |
{ | |
puts("fstat failed"); | |
close(fd); | |
return 1; | |
} | |
char *log = malloc(fileInfo.st_size); | |
if (log == NULL) | |
{ | |
puts("malloc failed"); | |
close(fd); | |
return 1; | |
} | |
if (read(fd, log, fileInfo.st_size) != fileInfo.st_size) | |
{ | |
puts("read failed"); | |
close(fd); | |
return 1; | |
} | |
close(fd); | |
const char *arenaId = "mtgArenaId"; | |
const char *name = "name"; | |
int numCards = 0; | |
for (int i = 0; i < fileInfo.st_size - 9; i++) | |
{ | |
if (memcmp(arenaId, &log[i], 10) == 0) | |
{ | |
i += 14; | |
char id[8]; | |
int j = 0; | |
while (log[i] > 47 && log[i] < 58) | |
{ | |
id[j] = log[i]; | |
i++; | |
j++; | |
} | |
id[j] = 0; | |
cards[numCards].id = atoi(id); | |
while (memcmp(name, &log[i], 4) != 0) | |
{ | |
i++; | |
} | |
i += 8; | |
j = 0; | |
while (log[i] != '"') | |
{ | |
cards[numCards].name[j] = log[i]; | |
i++; | |
j++; | |
} | |
cards[numCards].name[j] = 0; | |
numCards++; | |
} | |
} | |
free(log); | |
// Bubble sort by id | |
for (int i = 0; i < numCards - 1; i++) | |
{ | |
bool sorted = true; | |
for (int j = 0; j < numCards - 1; j++) | |
{ | |
if (cards[j].id > cards[j + 1].id) | |
{ | |
Card temp = cards[j]; | |
cards[j] = cards[j + 1]; | |
cards[j + 1] = temp; | |
sorted = false; | |
} | |
} | |
if (sorted) | |
{ | |
break; | |
} | |
} | |
// Remove true duplicates | |
for (int i = 0; i < numCards - 1; i++) | |
{ | |
if (cards[i].id == cards[i + 1].id && strcmp(cards[i].name, cards[i + 1].name) == 0) | |
{ | |
for (int j = i + 1; j < numCards - 1; j++) | |
{ | |
cards[j] = cards[j + 1]; | |
} | |
numCards--; | |
} | |
printf("%d %s\n", cards[i].id, cards[i].name); | |
} | |
printf("%d %s\n", cards[numCards - 1].id, cards[numCards - 1].name); | |
// Print duplicate ids with different cards names (not sure why these exist, maybe an error in mtgjson dataset?) | |
puts("\nDuplicates with different card names:\n"); | |
for (int i = 0; i < numCards - 1; i++) | |
{ | |
if (cards[i].id == cards[i + 1].id) | |
{ | |
printf("%d %s\n%d %s\n", cards[i].id, cards[i].name, cards[i + 1].id, cards[i + 1].name); | |
} | |
} | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment