sumTools.c

#include <stdlib.h>
#include <stdio.h>
#include "sumTools.h"
#include <string.h>
#include "trees.h"
#include "linkedList.h"
#include "strs.h"
// this used to insert ngrams of words 
void insertEach(cell **root,  char *nframe, int gram) {
    if (root == NULL || nframe == NULL || gram <= 0) {
        return;
    }

    char frame[256];
    int len = strlen(nframe);
    if (len >= sizeof(frame)) {
        len = sizeof(frame) - 1;
    }

    memcpy(frame, nframe, len);
    frame[len] = '\0';

    if (len > 0 && frame[len - 1] == ' ') {
        frame[len - 1] = '\0';
    }

    char *word = malloc(256);
    word[0] = '\0';
   
    for(int i = 0 ;  i < len ; i++){
      if(frame[i] != ' ' && frame[i] != '\0'){
            word[i] = frame[i];
      }else{
        insert(root, word);
        strcat(word, " ");

      }

    }
  
}

// this doesn't took words individual but it took n-grams of the words 
//it's helpful to gard the main idea of the paragraph and to make the intersection and the difference more accurate
void popStructNgram(node ** listHead , char * fileLocation , int gram){
	node *paragraph = NULL;
	cell *paragraphTree = NULL;
	FILE *file = fopen(fileLocation, "r");
	char line[10000];
	char copy[10000];        
	int numberOfParagraphs = 0 ;
	if (file == NULL) {
		printf("Failed to open file");
		return;
	}

    while(fgets(line, sizeof(line), file) != NULL) {
		
		if (isBlankLine(line)) {
			continue;
		}
		numberOfParagraphs++;
		paragraph = NULL;
		paragraphTree = NULL;
		
            strcpy(copy, line);
            
            char *word = strtok(copy, " \t\r\n,.?!;:\"()");
            char accumulator[256] = "";
            int count = 0;

            while (word != NULL) {
                toLowerCase(word);
                count++;
                size_t acc_len = strlen(accumulator);
                size_t word_len = strlen(word);
                if (acc_len + word_len + 2 >= sizeof(accumulator)) {
                    break;
                }
                strcat(accumulator, word);
                strcat(accumulator, " ");
                if(count == gram){
                    insertEach(&paragraphTree, accumulator , gram);    
                    int i = 0;
                    while(accumulator[i] != ' ' && accumulator[i] != '\0'){
                        i++;
                    }
                    remove_substring(accumulator, 0, i+1);
                    count -- ;
                }
                 
                word = strtok(NULL, " \t\r\n,.?!;:\"()");
            }

            if(paragraphTree != NULL && paragraphTree->word != NULL){
            insertNewParagraph(listHead , paragraph , paragraphTree);
            }
		}
	if(numberOfParagraphs == 0){
		node * vide = malloc(sizeof(node));
		cell * emptyParagraph = malloc(sizeof(cell));
		emptyParagraph->word = malloc(sizeof(char) * 20);
		vide->pragraph = emptyParagraph ;
		
		strcpy(vide->pragraph->word, "empty file");
		vide->next = NULL ;
        insertNewParagraph(listHead, vide , vide->pragraph);
	}
   
	fclose(file);
	
}

//populate the tree with sentences not words 

void populSentences(char *fileLocation, node **listHead) {
	node *paragraph = NULL;
	cell *paragraphTree = NULL;
	FILE *file = fopen(fileLocation, "r");
	char line[10000];
	char copy[10000];        
	int numberOfParagraphs = 0 ;
	if (file == NULL) {
		printf("Failed to open file");
		return;
	}

    while(fgets(line, sizeof(line), file) != NULL) {
		
		if (isBlankLine(line)) {
			continue;
		}
		numberOfParagraphs++;
		paragraph = NULL;
		paragraphTree = NULL;
		
			strcpy(copy, line);                         
			
			char *word = strtok(copy, "\t\r\n,.?!;:");
			while (word != NULL) {
				toLowerCase(word);
				insert(&paragraphTree, word);
				word = strtok(NULL, "\t\r\n,.?!;:");
			}
			if(paragraphTree != NULL && paragraphTree->word != NULL){
			insertNewParagraph(listHead , paragraph , paragraphTree);
			}
		}
	if(numberOfParagraphs == 0){
		node * vide = malloc(sizeof(node));
		cell * emptyParagraph = malloc(sizeof(cell));
		emptyParagraph->word = malloc(sizeof(char) * 20);
		vide->pragraph = emptyParagraph ;
		
		strcpy(vide->pragraph->word, "empty file");
		vide->next = NULL ;
		insertNewParagraph(listHead, vide , vide->pragraph);
	}
	fclose(file);
	
}
// sums up the frequencies of the words in the sentences 

void scoringSentence(cell **sentenecs, cell *words) {
    if (sentenecs == NULL || *sentenecs == NULL || words == NULL) {
        return;
    }

    scoringSentence(&(*sentenecs)->leftC, words);

    if ((*sentenecs)->word != NULL) {
        char tmp[256];
        strcpy(tmp, (*sentenecs)->word);
      
        char *word = strtok(tmp, " ");
        while (word != NULL) {
            cell *hit = getCell(words, word);
            if (hit != NULL) {
                (*sentenecs)->freq += hit->freq ;
            }
            word = strtok(NULL, " ");
        }
    }

    scoringSentence(&(*sentenecs)->rightC, words);
}
//extract the most repeated token in the tree 
cell * mostRepeated(cell * root){
    if(root == NULL){
        return NULL ;
    }
    cell * leftMost = mostRepeated(root->leftC);
    cell * rightMost = mostRepeated(root->rightC);
    cell * maxCell = root;

    if (leftMost != NULL && leftMost->freq > maxCell->freq) {
        maxCell = leftMost;
    }
    if (rightMost != NULL && rightMost->freq > maxCell->freq) {
        maxCell = rightMost;
    }
    return maxCell;
}