Hacking_in_C_Assignments/Assignment 1/excercise2/parsegenome.c

84 lines
2.0 KiB
C

#include <stdio.h>
#include <stdlib.h>
int main ( int argc, char** args ){
/*
* About this program:
* Reads a genome file and checks if its contents is valid.
* If the content is invalid the program exits with -1 otherwise the program exits with 0
*/
if( argc != 2){
printf("Program use: ./a.out <filePath>");
} else {
printf("Argument 1 : %s\n", args[1]);
FILE* genomeFile = fopen(args[1], "r" );
/*
* File specification/requirements
* The file must contain:
* - 500 lines of 100 character plus the newline character
* - each line of 100 character only contains characters A, C, G or T
*/
// PSUEDO Code
// Step 1: Read the amount of bytes 101 characters take.
// step 2: for the first 100 characters check if equal to A, C, G or T
// step 3: If not okay close file and program exits (-1)
// step 4: if okay check if the last byte is a newline
// step 5: if not okay close file and program exits (-1)
// step 6: if okay close file and program exits (0)
const int LINESIZE = 101;
unsigned int A = 0, G = 0, C = 0, T = 0;
printf("start count: %i , %i , %i , %i\n" , A, C, G, T);
for ( int i = 0; i < 500 ; i++){
char line[LINESIZE];
int bytesRead = fread(line, sizeof *line, LINESIZE, genomeFile);
if( bytesRead != LINESIZE ){
printf("Could only read %i bytes", bytesRead);
goto FAILURE;
}
for ( int j = 0; j < 100; j++ ) {
if( line[j] == 'A') {
A ++;
continue;
}
if( line[j] == 'C' ) {
C ++;
continue;
}
if( line[j] == 'G' ){
G ++;
continue;
}
if( line[j] == 'T' ) {
T ++;
continue;
}
printf("line %i character %i: %s is not valid.",i,j,line[j]);
goto FAILURE;
}
if( line[100] != '\n') {
printf("Read %c instead of newline ", line[100]);
goto FAILURE;
}
}
fclose (genomeFile);
printf("Counted A's %i\nCounted C's %i\nCounted G's %i\nCounted T's %i\n" ,A ,C ,G ,T);
exit(0);
FAILURE:
fclose(genomeFile);
exit(-1);
}
}