How to extract words from files

[hornet07]

I want to know how I can extract words from a text file and store them in a char array. The file will probably have to store hundreds of words.

  FILE *in;
  in = fopen("Dictionary.txt", "r"); 
	
  char[20] temp;
  while (fscanf(in, " %20s", temp) == 1) {
	gets(temp);
  }
  in.close();

That mess up there is what I've pieced together from google.

Note: I don't want to use c++ stuff, so no strings.

[tipaye]

I don't want to use c++ stuff

Ha ha, so why're you trying

in.close();

I assumed you want an array of words, not just one giant array of everything in the file. Below is an example in standard C (C89), maximum 1024 words each up to 19 characters.

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

#define MAX_WORD 20
#define MAX_WORDS 1024

int main(int argc, char *argv[])
{
	char words[MAX_WORDS][MAX_WORD];
	FILE *inf = fopen(argv[1], "r");
	int c = 0;
	int i = 0;
	int word = 0;

	memset(words, 0, MAX_WORDS * MAX_WORD);
	while (((c = fgetc(inf)) != EOF) && (word <= MAX_WORDS))
	{
		int j = 0;
		if (isspace(c)) continue; 
		while (!isspace(c))
		{
			if (j < (MAX_WORD - 1))
			{
				words[word][j] = c;
				++j;
			}
			
			c = fgetc(inf);
			if ((c == EOF) || isspace(c))
			{
				ungetc(c, inf);
				++word;
			}
		}
	}
	
	fclose(inf);
	
	for (i = 0; i < word; ++i)
	{
		fprintf(stdout, "%s\n", words[i]);
	}
	
	return 0;
}

[hornet07]

It works just as intented, thanks for that. Problem is, I was trying to integrate it into an existing program and it doesn't work. Beware, it's a big SOB lol.

The original program was a C implementation of a TRIE. I was trying to make it work by reading from a text file rather than manually inputting words. Basically a TRIE dictionary.

//--------------------------------------------------------------------------------MAIN.CPP 

#include"header.h"


int main()
{
	TrieNode *trie;
	char UserInputWord[20], cont_insert = ' ';
	int option = 0;
	trie = NULL;
label_menu:
	while (option != 5)
	{
		cout << endl << " Menu: " << endl;
		cout << "___________________________________________" << endl;
		cout << " 1. Create tree\n 2. Insert node\n 3. Search for node\n 4. Display tree\n 5. Exit\n";
		cout << "\n\n\nInput choice: ";
		cin >> option;
		switch (option)
		{
		case 1:
			while (cont_insert != 'n')
			{
				//readDictionary(trie);

				cout << endl << "Insert word :";
				cin >> UserInputWord;
				trie = Insert(trie, UserInputWord);
				cout << "\n Continue ? <y/n>";
				cont_insert = _getch();
			}
			break;
		case 2:
			cout << endl << "Insert word :";
			cin >> UserInputWord;
			Insert(trie, UserInputWord);
			break;
		case 3:
			cout << endl << "Searched word :";
			cin >> UserInputWord;
			Find(trie, UserInputWord);
			break;
		case 4:
			DisplayTrie(trie, 0);
			break;
		case 5:
			break;
		default:
			cout << "Choose from the displayed options (1-5) !!!";
			goto label_menu;
		}
	}
	system("PAUSE");
	return 0;
}


//-------------------------------------------------------------------------HEADER.H

#define MAX_WORD 20
#define MAX_WORDS 1024

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

using namespace std;



#define NR 27 

typedef struct TrieNode{
	bool NotLeaf;
	TrieNode *pChildren[NR];
	char word[20];
};

TrieNode *NewLeaf(char keyWord[20]);
TrieNode *NewIntern();
//void readDictionary(TrieNode *trie);
void Find(TrieNode *trie, char keyWord[20]);
TrieNode *Insert(TrieNode *trie, char keyWord[20]);
void DisplayTrie(TrieNode *trie, int nivel);



//---------------------------------------------------------------------FUNCTIONS.CPP

#ifdef _MSC_VER
#define _CRT_SECURE_NO_WARNINGS

#include"header.h"



TrieNode *NewLeaf(char keyWord[20])
{
	TrieNode *node;
	int count;

	node = (TrieNode *)malloc(sizeof(TrieNode));
	for (count = 0; count < 27; count++)
		node->pChildren[count] = NULL;
	node->NotLeaf = false;
	strcpy_s(node->word, keyWord);
	return node;
}

TrieNode *NewIntern()
{
	TrieNode *node;
	int count;

	node = (TrieNode *)malloc(sizeof(TrieNode));
	for (count = 0; count < 27; count++)
		node->pChildren[count] = NULL;
	node->NotLeaf = true;
	node->word[0] = 0;
	return node;
}

/*void readDictionary(TrieNode *trie)
{
	char words[MAX_WORDS][MAX_WORD];
	FILE *inf = fopen("Dictionary.txt", "r");
	int c = 0;
	int i = 0;
	int word = 0;

	memset(words, 0, MAX_WORDS * MAX_WORD);
	while (((c = fgetc(inf)) != EOF) && (word <= MAX_WORDS))
	{
		int j = 0;
		if (isspace(c)) continue;
		while (!isspace(c))
		{
			if (j < (MAX_WORD - 1))
			{
				words[word][j] = c;
				++j;
			}

			c = fgetc(inf);
			if ((c == EOF) || isspace(c))
			{
				ungetc(c, inf);
				++word;
			}
		}
	}

	fclose(inf);

	for (i = 0; i < word; ++i)
	{
		Insert(trie, words[i]);
	}
}*/

void Find(TrieNode *trie, char keyWord[20])
{
	TrieNode *next, *index, *data;
	int count;
	next = trie;
	if (next == NULL)
	{
		cout << "Word not found in trie !!!!" << endl;
		exit(1);
	}
	else
		index = next;
	count = 0;
	while ((index->NotLeaf == true) && (count < strlen(keyWord)) && (index->pChildren[keyWord[count] - 'a'] != NULL))
	{
		next = index->pChildren[keyWord[count] - 'a'];
		index = next;
		count++;
	}
	if (next == NULL)
		cout << "Word not found in trie !!!!" << endl;
	else
	{
		data = next;

		if (!strcmp(data->word, keyWord))
			cout << "Key exists --- Word found in trie !!!!" << endl;
		else
			if ((data->pChildren[26]) && !strcmp(data->pChildren[26]->word, keyWord))
				cout << "Key exists --- Word found in trie !!!!" << endl;
			else
				cout << "Word not found in trie !!!!" << endl;
	}
}

TrieNode *Insert(TrieNode *trie, char keyWord[20])
{
	TrieNode *next, *index, *parent = nullptr;
	TrieNode *new_leaf, *data, *new_index;
	TrieNode *oldChildren = nullptr, *newWord = nullptr, *intern;
	int inWordIndex, prefixLenght, lenght = strlen(keyWord);
	next = trie;
	if (next == NULL)
	{
		trie = NewIntern();
		new_leaf = NewLeaf(keyWord);
		trie->pChildren[keyWord[0] - 'a'] = new_leaf;
		return trie;
	}
	else
		index = next;
	inWordIndex = 0;
	while ((inWordIndex < lenght) && (index->NotLeaf == true) && (index->pChildren[keyWord[inWordIndex] - 'a'] != NULL))
	{
		parent = next;
		next = index->pChildren[keyWord[inWordIndex] - 'a'];
		index = next;
		inWordIndex++;
	}

	if ((inWordIndex < lenght) && (index->pChildren[keyWord[inWordIndex] - 'a'] == NULL) && (index->NotLeaf == true))
	{
		new_index = NewLeaf(keyWord);
		index->pChildren[keyWord[inWordIndex] - 'a'] = new_index;
		return trie;
	}
	else
		data = next;
	if (!strcmp(data->word, keyWord))
		cout << "Word already exists in trie !!!" << endl;
	else
	{
		oldChildren = parent->pChildren[keyWord[inWordIndex - 1] - 'a'];
		newWord = NewLeaf(keyWord);
		prefixLenght = strlen(keyWord);
		if (data->word[0] != '\0')
			if (strlen(data->word) < prefixLenght)
				prefixLenght = strlen(data->word);
	}
	bool createIntern = false;

	while ((inWordIndex <= prefixLenght) && (((data->word[0] != '\0') && (data->word[inWordIndex - 1] == keyWord[inWordIndex - 1])) || (data->word[0] == '\0')))
	{
		intern = NewIntern();
		parent->pChildren[keyWord[inWordIndex - 1] - 'a'] = intern;
		parent->NotLeaf = true;
		parent = intern;
		inWordIndex++;
		createIntern = true;
	}
	if (createIntern)
		inWordIndex--;

	if ((inWordIndex != prefixLenght) || ((inWordIndex == prefixLenght) && (strlen(keyWord) == strlen(data->word))))
	{
		parent->pChildren[data->word[inWordIndex] - 'a'] = oldChildren;
		parent->pChildren[keyWord[inWordIndex] - 'a'] = newWord;
	}
	else
		if (data->word[0] != '\0')
			if (strlen(data->word) <= prefixLenght)
			{
				parent->pChildren[26] = oldChildren;
				parent->pChildren[keyWord[prefixLenght] - 'a'] = newWord;
			}
			else
			{
				parent->pChildren[26] = newWord;
				parent->pChildren[data->word[prefixLenght] - 'a'] = oldChildren;
			}
		else
		{
			for (int count = 0; count < 27; count++)
				parent->pChildren[count] = oldChildren->pChildren[count];
			parent->pChildren[26] = newWord;
		}
	return trie;
}

void DisplayTrie(TrieNode *trie, int nivel)
{
	int count;
	if (trie)
	{
		if (trie->NotLeaf != true)
		{
			for (count = 0; count <= nivel; count++)
				cout << " ";
			cout << trie->word << endl;
		}
		for (count = 26; count >= 0; count--)
			DisplayTrie(trie->pChildren[count], nivel + 4);
	}
}

#endif 

I didn't write this implementation, but I HAVE to use it, that's why I said no C++. The implementation works manually. I just need it to work by reading from a text file instead of inserting words on the keyboard.

The commented parts are what I was trying with your input. The "1. Create tree" option works. But when I try searching for the words, the console window instantly closes, even with system pause and cin.get. I don't get it...

[hornet07]

I realize this looks big, but most of it doesn't need to change. Just the part that reads from the file. I would appreciate it if someone told me what's wrong with it.

[tipaye]

Hi Hornet, I'm not sure I understand:
Do you mean that you're still having problems reading from the file?
Can you narrow it down to the sequence of function calls and arguments and the error message you get?
Are you sure your program can find the file? If you're running from an ide, like eclipse or visual studio, the binary you're executing may not be where you think it is, relative to the file you're trying to open - have you tried using an absolute path name?
Also, if you start a command prompt yourself and execute the program, then there'll be no disappearing console, so any diagnostic messages will still be available.

[hornet07]

Okay so I did it eventually with a simple function. Just this:

TrieNode *readDictionary(TrieNode *trie)
{
	char words[MAX_WORDS];
	FILE *inf = fopen("Dictionary.txt", "r");
	while (!feof(inf))
	{
		fgets(words, MAX_WORDS, inf);
		words[strlen(words) - 1] = NULL;
		trie = Insert(trie, words);
	}
	fclose(inf);

	return trie;
}

As for the exe, that also closed immediately. Don't know why.