所以我正在用c语言编写一个多线程单词计数程序,我的代码遇到了一些问题,在这里搜索时发现了一个与我自己的项目相似的老问题。我决定不尝试重新编写充满问题的代码,而是尝试使其他代码正常工作,然后对其进行修改以实现所需。
该代码将txt文件作为输入。问题是,当您运行该程序时,出现了分段错误。
这是代码:
#include <stdio.h>
#include <pthread.h>
#include <stdlib.h>
struct thread_data{
FILE *fp;
long int offset;
int start;
int blockSize;
};
int words=0;
void *countFrequency(void* data){
struct thread_data* td=data;
char *buffer = malloc(td->blockSize);
int i,c;
i=0;c=0;
enum states { WHITESPACE, WORD };
int state = WHITESPACE;
fseek(td->fp, td->offset, td->start);
char last = ' ';
while ((fread(buffer, td->blockSize, 1, td->fp))==1){
if ( buffer[0]== ' ' || buffer[0] == '\t' ){
state = WHITESPACE;
}
else if (buffer[0]=='\n'){
state = WHITESPACE;
}
else {
if ( state == WHITESPACE ){
words++;
}
state = WORD;
}
last = buffer[0];
}
free(buffer);
pthread_exit(NULL);
return NULL;
}
int main(int argc, char **argv){
int nthreads, id, blockSize,len;
FILE *fp;
pthread_t *threads;
if (argc < 2){
fprintf(stderr, "Usage: ./a.out <file_path>");
exit(-1);
}
if((fp=fopen(argv[1],"r"))==NULL){
printf("Error opening file");
exit(-1);
}
printf("Enter the number of threads: ");
scanf("%d",&nthreads);
struct thread_data data[nthreads];
threads = malloc(nthreads*sizeof(pthread_t));
fseek(fp, 0, SEEK_END);
len = ftell(fp);
printf("len= %d\n",len);
blockSize=(len+nthreads-1)/nthreads;
printf("size= %d\n",blockSize);
for(id = 0; id < nthreads; id++){
data[id].fp=fp;
data[id].offset = blockSize;
data[id].start = id*blockSize+1;
}
data[nthreads-1].start=(nthreads-1)*blockSize+1;
for(id = 0; id < nthreads; id++)
pthread_create(&threads[id], NULL, &countFrequency,&data[id]);
for(id = 0; id < nthreads; id++)
pthread_join(threads[id],NULL);
fclose(fp);
printf("%d\n",words);
return 0;
}
这是原始帖子的链接:original
最佳答案
通过使用在nthreads
中具有自动存储持续时间struct thread_data data[nthreads];
的未初始化变量的不确定值来调用未定义行为。
尝试在scanf("%d",&nthreads);
之后移动该行。