爲什麼我的程序不能輸出正確的字數？

Question

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

struct thread_data { 
    FILE *fp; 
    long int offset; 
    int start; 
    int blockSize; 
    //struct word maybe? 
}; 

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') { 
     //newLine++; 
     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, x, id, blockSize, len; 
    //void *state; 
    FILE *fp; 
    pthread_t *threads; 

    fp = fopen("file1.txt", "r"); 

    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; 
    //maybe data[id]. word struct 
    } 
    //LAST THREAD 
    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; 
} 

我有一個分段故障，我在這個程序中修復，但現在當我運行它時，我得到0個字，這是不正確的，因爲在文本文件中有大約一百萬字。

誰能告訴我爲什麼它給我一個不正確的字數？

Answer 1

您遇到的一個問題是您在每個countFrequency線程中使用相同的文件描述符，每個線程執行一次fseek，然後嘗試循環讀取。最後的fseek獲勝。

這個設計缺陷必須首先解決。