3

So I have chains of DNA letters (A,G,T,C) in linked list, and am supposed to read in from a file that looks like this:

I[tab]  ATT\n
I[tab]  ATC\n (etc)
L   CTA
L   CTG
V   GTA
V   GTG
F   TTT
F   TTC
..

where the single letters is what you get from the 3 a,t,g,c combination. I figured out how to start where I need to start (at the AGT), but can't formulate how to read the string and compare with the file to see what matches. This is what I have so far:

#include<stdio.h>
#include<stdlib.h>
#include<string.h>

typedef struct node{
    char seq[300];
    struct node* next;
    } NODE;


int
main(int argc, char* argv[]){

    int i, j=0;
    FILE *fin, *fout, *fop;
    char code1[300], code2[300], prot;
    NODE *current, *first, *prev;

    fin = fopen( argv[1], "r");
    fout = fopen( argv[2], "w");
    fop = fopen("codeoflife.txt", "r");

    current = first = malloc (sizeof (NODE));

    while( fscanf( fin, "%s", current -> seq) != EOF) {

        for (i = 0; i < 300; i++){
            if (current->seq[i] == 'a')
                current->seq[i] = 'A';
            else if (current->seq[i] == 't')
                current->seq[i] = 'T';
            else if(current->seq[i] == 'g')
                current->seq[i] = 'G';
            else if(current->seq[i] == 'c')
                current->seq[i] = 'C';
        }

        if ( (current -> next = malloc ( sizeof(NODE) ) ) == NULL){
            fprintf(fout, "Out of memory\nCan't add more DNA sequences\n");
            return EXIT_FAILURE;
        }
        prev = current;
        current = current -> next;

    }

    free(current)
    prev->next = NULL;

    current = first;

    while(current->next != NULL){
        for( i = 0; i < 300; i++){
            if( current->seq[i] == 'A')
                if( current->seq[i+1] == 'G')
                    if( current->seq[i+2] =='T'){
                        code1[j] = 'M';
                        while(fscanf(fop, "%c", &prot)) != EOF){

                        break;
        }
        if (i == 299)
            strcpy ( current->seq, "None");

        current = current->next;
    }

    return 0;
}
4

1 回答 1

0

该函数fscanf()往往会产生正确读取单个字段的问题,因为它有时对“%s”是什么有一个奇怪的想法。

特别是因为这是一个面向行的文件,使用fgets()然后用 sscanf 解析字符串,或者甚至只是一次查看一个字符。您的代码没有这样做,因此简化版本是:

while (fgets (current->seq, sizeof (current->seq), fin))
{
    char *cp = strchr (current->seq, '\n');   // fgets usually adds \n
    if (cp)                                   // if \n present
         *cp  = '\000';                       // remove \n
    strupr (current->seq);   // make all upper case (unifies mixed case input)

    ...
}

这替换了 12 行代码,但没有出现奇怪的故障

于 2011-06-02T23:57:12.997 回答