Text Analyzer Source

/*
 * words.c
 *
 *  Created on: October 6, 2013
 *      Author: Chris Cirefice
 */

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

int getNumUniqueWords(char text[], int size);

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

    setvbuf(stdout, NULL, 4, _IONBF); // For Eclipse... stupid bug. --> does NOT affect the program, just the output to console!

    int nbr_words;

    char text[] = "Some - \"text, a stdin\". We'll have! also repeat? We'll also have a repeat!";
    int length = sizeof(text);
    nbr_words = getNumUniqueWords(text, length);

    return 0;
}

void free_memory(char **list, int size) {

    for (int i = 0; i < size; i ++) {
        // You can see that printing the values is fine, as long as free is not called.
        // When free is called, the program will crash if (size > strlen(list[i]))
        //printf("Wanna free value %d w/len of %d: %s\n", i, strlen(list[i]), list[i]);
        free(list[i]);
    }
    free(list);
}

int getNumUniqueWords(char text[], int length) {
    int numTotalWords = 0;
    char *word;

    printf("Length: %d characters\n", length);

    char totalWords[length];
    strcpy(totalWords, text);

    word = strtok(totalWords, " ,.-!?()\"0123456789");

    while (word != NULL) {
        numTotalWords ++;
        printf("%s\n", word);
        word = strtok(NULL, " ,.-!?()\"0123456789");
    }

    printf("Looks like we counted %d total words\n\n", numTotalWords);

    char *uniqueWords[numTotalWords];
    char *tempWord;
    int wordAlreadyExists = 0;
    int numUniqueWords = 0;

    char totalWordsCopy[length];
    strcpy(totalWordsCopy, text);

    for (int i = 0; i < numTotalWords; i++) {
        uniqueWords[i] = NULL;
    }

    // Tokenize until all the text is consumed.
    word = strtok(totalWordsCopy, " ,.-!?()\"0123456789");
    while (word != NULL) {

        // Look through the word list for the current token.
        for (int j = 0; j < numTotalWords; j ++) {
            // Just for clarity, no real meaning.
            tempWord = uniqueWords[j];

            // The word list is either empty or the current token is not in the list.
            if (tempWord == NULL) {
                break;
            }

            //printf("Comparing (%s) with (%s)\n", tempWord, word);

            // If the current token is the same as the current element in the word list, mark and break
            if (strcmp(tempWord, word) == 0) {
                printf("\nDuplicate: (%s)\n\n", word);
                wordAlreadyExists = 1;
                break;
            }
        }

        // Word does not exist, add it to the array.
        if (!wordAlreadyExists) {
            uniqueWords[numUniqueWords] = malloc(strlen(word));
            uniqueWords[numUniqueWords] = word;
            numUniqueWords ++;
            printf("Unique: %s\n", word);
        }

        // Reset flags and continue.
        wordAlreadyExists = 0;
        word = strtok(NULL, " ,.-!?()\"0123456789");
    }

    // Print out the array just for funsies - make sure it's working properly.
    for (int x = 0; x <numUniqueWords; x++) {
        printf("Unique list %d: %s\n", x, uniqueWords[x]);
    }

    printf("\nNumber of unique words: %d\n\n", numUniqueWords);

    // Right below is where things start to suck.
    free_memory(uniqueWords, numUniqueWords);

    return numUniqueWords;
}