如何扫描单词并存储从C扫描的哪一行?

时间:2017-06-17 12:06:16

标签: c file

我试图制作一个程序,从文件中读取单词并将每个单词及其出现的行存储在一个列表中,然后打印出按字母顺序排列的单词,任何有关如何操作的指导? 到目前为止,我已经放了两个数组,单词和行来测试我的代码..但是我很困惑如何让它从文件中读取每个单词和它出现的行...

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

#define LEN  7


/* Struct for word and lines that appears in */
struct wordStruct {
char *word;
char *lines;
struct wordStruct *next;
};

static int compare_words(const struct wordStruct *a, const struct wordStruct *b) {
 return strcmp(a->word, b->word);
}

static struct wordStruct *insert_sorted(struct wordStruct *headptr, char *word, char *lines) {
/* Struct head */
struct wordStruct **pp = &headptr;
/* Allocate heap space for a record */
struct wordStruct *ptr = malloc(sizeof(struct wordStruct));
if (ptr == NULL) {
    abort();
}

/* Assign to structure fields */
ptr->word = word;
ptr->lines = lines;
ptr->next = NULL;

/* Store words in alphabetic order */
while (*pp != NULL && compare_words(ptr, *pp) >= 0) {
    pp = &(*pp)->next;
}
ptr->next = *pp;
*pp = ptr;

return headptr;
}


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

char *Arr[LEN] = { "jack", "and", "jill", "went", "up", "the", "hill" };
char *Arr2[LEN] = { "22,1,5", "24,7,3", "50", "26,66", "18,23", "32,22", "24,8" };


int i;

/* Snitialize empty list */
struct wordStruct *headptr = NULL;
/* Snitialize current */
struct wordStruct *current;

/* Insert words in list */
for (i = 0; i < LEN; i++) {
    headptr = insert_sorted(headptr, Arr[i], Arr2[i]);
}

current = headptr;
while (current != NULL) {
    printf("%s appears in lines %s.\n", current->word, current->lines);
    current = current->next;
}
return 0;
}

我也对此有所了解,但我不知道如何将其与我的代码合并,以使其获得找到该单词的位置,并在wordStruct中对行进行更改。

    void read_words (FILE *f) {
char x[1024];
/* assumes no word exceeds length of 1023 */
while (fscanf(f, " %1023s", x) == 1) {
    puts(x);
}
}

1 个答案:

答案 0 :(得分:1)

  

我很困惑如何从文件中读取每个单词及其出现的行...

让我们定义:所有字符,包括潜在的终止'\n'。第一行是 line 1.最后一行可能会也可能不会以'\n'结尾。

让我们定义一个单词:一个由非空白字符组成的字符串。出于实际和安全考虑,请限制其大小。

使用fscanf(..., "%1023s", ...)工作来阅读单词,但由于"%s"消耗了前导空格,因此计算行时会丢失任何'\n'。简单地预先fscanf,一次一个角色寻找'\n'

char *GetWord1024(FILE *ifile, char *dest, uintmax_t *linefeed_count) {
  // test for bad parameters
  assert(ifile && dest && linefeed_count);

  // consume leading white space and update count of leading line-feeds
  int ch;
  while (isspace(ch = fgetc(ifile))) {
    if (ch == '\n') {
      (*linefeed_count)++;
    }
  }
  ungetc(ch, ifile);  // put back non-whitespace character or EOF

  if (fscanf(ifile, "%1023s", dest) == 1) {
    return dest;
  }

  return NULL;  // No word
}

样本用法

int main(void) {
  uintmax_t linefeed_count = 0;
  char word[1024];
  while (GetWord1024(stdin, word, &linefeed_count)) {
    printf("Line:%ju <%s>\n", linefeed_count + 1, word);
  }
  return 0;
}