程序从文件中读取单词并计算它们在文件中的出现次数

Question

我目前正在尝试制作一个读取文件的程序，以查找每个唯一单词并计算该单词在文件中出现的次数。我目前向用户询问一个单词并在文件中搜索该单词出现的次数。但是我需要程序自己读取文件，而不是向用户询问单个单词。

这是我目前拥有的：

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

int main(int argc, char const *argv[])
{   
int num =0;
char word[2000];
char *string;

FILE *in_file = fopen("words.txt", "r");

if (in_file == NULL)
{
    printf("Error file missing\n");
    exit(-1);
}

scanf("%s",word);

printf("%s\n", word);

while(!feof(in_file))//this loop searches the for the current word
{
    fscanf(in_file,"%s",string);
    if(!strcmp(string,word))//if match found increment num
    num++;
}
printf("we found the word %s in the file %d times\n",word,num );
return 0;
}

我只需要一些帮助来弄清楚如何读取文件中的唯一单词（尚未检查的单词），尽管对我的程序有任何其他建议将不胜感激。

Answer 1

如果您只想将文件中包含的每一行打印一次，则必须将已读取的字符串保存在给定的数据结构中。例如，排序数组可以解决问题。代码可能如下所示：

#include <stddef.h>

size_t numberOfLine = getNumberOfLine (file);
char **previousStrings = allocArray (numberOfLine, maxStringSize);
size_t i;

for (i = 0; i < numberOfLine; i++)
{
    char *currentString = readNextLine (file);

    if (!containString (previousStrings, currentString))
    {
        printString (currentString);
        insertString (previousStrings, currentString);
    }
}

您可以使用二进制搜索以有效的方式对函数containString 和insertString 进行编码。请参阅here 了解更多信息。

Answer 2

您必须将代码拆分为函数（子例程）。

一个函数会读取文件并记录所有单词；另一个会计算每个单词的出现次数。

int main(int argc, char const *argv[])
{
    char *words[2000];

    // Read the file; store all words in the list
    int number_of_words = ReadWords("words.txt", words, 2000);

    // Now count and print the number of occurrences for each word
    for (int i = 0; i < number_of_words; i++)
    {
        int n = CountOccurrences(words[i], "words.txt");
        printf("we found the word %s in the file %d times\n", words[i], n);
    }

    // Deallocate dynamically allocated memory
    Cleanup(words, number_of_words);
}

注意main 函数相对较短。所有细节都在函数ReadWords和CountOccurrences中。

实现从文件中读取所有单词：

int ReadWords(const char *filename, char *words[], int max_number_of_words)
{
    FILE *f = fopen(filename, "rt"); // checking for NULL is boring; i omit it
    int i;
    char temp[100]; // assuming the words cannot be too long

    for (i = 0; i < max_number_of_words; ++i)
    {
        // Read a word from the file
        if (fscanf(f, "%s", temp) != 1)
            break;
        // note: "!=1" checks for end-of-file; using feof for that is usually a bug

        // Allocate memory for the word, because temp is too temporary
        words[i] = strdup(temp);
    }
    fclose(f);

    // The result of this function is the number of words in the file
    return i;
}

Answer 3

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

int main(int argc, char*argv[])
{   
int num =0;
char word[2000];
char string[30];

FILE *in_file = fopen(argv[1], "r");

if (in_file == NULL)
{
    printf("Error file missing\n");
    exit(-1);
}

scanf("%s",word);

printf("%s\n", word);

while(!feof(in_file))//this loop searches the for the current word
{
    fscanf(in_file,"%s",string);
    if(!strcmp(string,word))//if match found increment num
    num++;
}
printf("we found the word %s in the file %d times\n",word,num );
return 0;
}`

if any suggestion plz..most welcome

Blockquote