How to read and print a random word from a text file in C

Question

I have a file named

"grwords.txt"

How can I assign the file to an array and print a random word from it? My text file contains around 540000 words. This is my code:

int main(int argc, char *argv[]) {
    FILE *file;
    int i, random;
    char words[540000][25];
    file = fopen("grwords.txt", "r");
    if (file == NULL){
        printf("The file cannot be opened.\n");
        return 1;
    }
    random = rand();
    fprintf(file, "%lf\n", random);
    fclose(file);
    return 0;
}

Answer 1

void ReadFile(char *name)
{
    FILE *file;
    char *buffer;
    unsigned long fileLen;

    //Open file
    file = fopen(name, "rb");
    if (!file)
    {
        fprintf(stderr, "Unable to open file %s", name);
        return;
    }

    //Get file length
    fseek(file, 0, SEEK_END);
    fileLen=ftell(file);
    fseek(file, 0, SEEK_SET);

    //Allocate memory
    buffer=(char *)malloc(fileLen+1);
    if (!buffer)
    {
        fprintf(stderr, "Memory error!");
                                fclose(file);
        return;
    }

    //Read file contents into buffer
    fread(buffer, fileLen, 1, file);
    fclose(file);

    //Do what ever with buffer

    free(buffer);
}

Answer 2

Open the file. Determine its size. Find a random file offset between 0 and size and fseek to it. Scan a word and discard it, because we might have jumped into the middle of a word and would then printing only part of it. Scan the next word and print it. Close the file.

Of course we may have jumped to a position close to the end of the file, so we need to take care of reaching the end of the file when reading the word by rewinding the file. As a corner case, the file may not have any words in it.

If your file size ig greater than RAND_MAX, you must find a way to compose a random number greater than that, e.g.:

int pos = (rand() * RAND_MAX + rand()) % size

File seeking is oviously not a good method if you need to print random words from the file repeatedly.

Answer 3

How can I assign the file to an array and print a random word from it?

A) read the file once to get parameters: 1: number of words, 2: length of longest word (used for memory alloc later)
B) Allocate memory for an array of strings (eg: char **strings;) to read file into.
(note: you have choosen to use char words[540000][25];, which will also work, but is not flexible)
C) Using fopen() and fgets() read each word into array strings.
D) Use srand() and rand() to produce pseudo random number from 0 to numWords.
(Note: rand() by itself only produces numbers from 0 to RAND_MAX (32767). If bigger number needed, adapt to that by using combinations of rand() to produce a bigger number.
E) Use printf("Random word is %s", strings[randNum]); to print random number.

Your code segment is a start, but you are missing a few key elements. One of which is shown here:

At this point in your code:

random = rand();
fprintf(file, "%lf\n", random);
fclose(file);  

You still have not read the words from the opened file into a string array words, as you stated you wanted to. That should be done before this last section. Something like this should work:

    #define DELIM "- .,:;//_*&\n"  //or use char DELIM[]="- .,:;//_*&\n"

    //...other code

    char *buf;
    char line[260];
    int cnt=0;

   while(fgets(line, 260, file))
    {
        buf = strtok(line, DELIM);
        while(buf)
        {
            if((strlen(buf) > 0) && (buf[0] != '\t') && (buf[0] != '\n') && (buf[0] != '\0')&& (buf[0] > 0))
            {
                strcpy(words[cnt++], buf);
            }
            buf = strtok(NULL, DELIM);
        }
    }
    //... other code

Answer 4

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

int main(int argc, char *argv[]) {
    static char words[540000][25];
    FILE *file;
    int i, j;
    size_t cnt, n;
    char word[25];

    srand(time(NULL));
    file = fopen("grwords.txt", "r");
    if (file == NULL){
        printf("The file cannot be opened.\n");
        return 1;
    }
    cnt = 0;
    while(1==fscanf(file, "%24s", word)){
        if(cnt == 540000)
            break;
        strcpy(words[cnt++], word);
    }
    fclose(file);
    n = cnt;
    if(n > RAND_MAX){
        int part;
        size_t random = 0;
        i = n / RAND_MAX;
        part = rand() % (i+1);
        if(part == i){
            j = n % RAND_MAX;
            if(j != 0)
                random = random + RAND_MAX*part + rand() % j;
            else
                random = random + RAND_MAX*(part-1) + rand();
        } else {
            random = random + RAND_MAX*part + rand();
        }
        printf("%s\n", words[random]);
    } else {
        int random = rand() % n;
        printf("%s\n", words[random]);
    }
    return 0;
}