我正在编写一些需要读取fasta 文件的代码,所以我的部分代码(包括在下面)是一个 fasta 解析器。由于单个序列可以跨越 fasta 格式的多行,因此我需要将从文件中读取的多个连续行连接成一个字符串。我这样做,通过在读取每一行后重新分配字符串缓冲区,使其成为序列的当前长度加上读入的行的长度。我做了一些其他的事情,比如剥离空白等。一切顺利第一个序列,但 fasta 文件可以包含多个序列。同样,我有一个动态结构数组,其中包含两个字符串(标题和实际序列),即“char *”。同样,当我遇到一个新标题(由以“>”开头的行引入)时,我增加了序列的数量,并重新分配了序列列表缓冲区。realloc 段错误为第二个序列分配空间
*** glibc detected *** ./stackoverflow: malloc(): memory corruption: 0x09fd9210 ***
Aborted
对于我的生活,我不明白为什么。我已经通过 gdb 运行它,一切似乎都在工作(即一切都已初始化,值看起来很正常)......这是代码:
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <ctype.h>
#include <math.h>
#include <errno.h>
//a struture to keep a record of sequences read in from file, and their titles
typedef struct {
char *title;
char *sequence;
} sequence_rec;
//string convenience functions
//checks whether a string consists entirely of white space
int empty(const char *s) {
int i;
i = 0;
while (s[i] != 0) {
if (!isspace(s[i])) return 0;
i++;
}
return 1;
}
//substr allocates and returns a new string which is a substring of s from i to
//j exclusive, where i < j; If i or j are negative they refer to distance from
//the end of the s
char *substr(const char *s, int i, int j) {
char *ret;
if (i < 0) i = strlen(s)-i;
if (j < 0) j = strlen(s)-j;
ret = malloc(j-i+1);
strncpy(ret,s,j-i);
return ret;
}
//strips white space from either end of the string
void strip(char **s) {
int i, j, len;
char *tmp = *s;
len = strlen(*s);
i = 0;
while ((isspace(*(*s+i)))&&(i < len)) {
i++;
}
j = strlen(*s)-1;
while ((isspace(*(*s+j)))&&(j > 0)) {
j--;
}
*s = strndup(*s+i, j-i);
free(tmp);
}
int main(int argc, char**argv) {
sequence_rec *sequences = NULL;
FILE *f = NULL;
char *line = NULL;
size_t linelen;
int rcount;
int numsequences = 0;
f = fopen(argv[1], "r");
if (f == NULL) {
fprintf(stderr, "Error opening %s: %s\n", argv[1], strerror(errno));
return EXIT_FAILURE;
}
rcount = getline(&line, &linelen, f);
while (rcount != -1) {
while (empty(line)) rcount = getline(&line, &linelen, f);
if (line[0] != '>') {
fprintf(stderr,"Sequence input not in valid fasta format\n");
return EXIT_FAILURE;
}
numsequences++;
sequences = realloc(sequences,sizeof(sequence_rec)*numsequences);
sequences[numsequences-1].title = strdup(line+1); strip(&sequences[numsequences-1].title);
rcount = getline(&line, &linelen, f);
sequences[numsequences-1].sequence = malloc(1); sequences[numsequences-1].sequence[0] = 0;
while ((!empty(line))&&(line[0] != '>')) {
strip(&line);
sequences[numsequences-1].sequence = realloc(sequences[numsequences-1].sequence, strlen(sequences[numsequences-1].sequence)+strlen(line)+1);
strcat(sequences[numsequences-1].sequence,line);
rcount = getline(&line, &linelen, f);
}
}
return EXIT_SUCCESS;
}