In this code, the string is split by the difference of the space. I could do that through strtok but I didn't. I just want to know that how can split the strings by assigning tokens to them, like if I want to print the first token then it should print the first word from the string. Similarly, if I want to print the second word then it should print the second word after the first space occurred and so on.
int main(){
char inputString[100], words[10][10];
int indexCtr = 0, wordIndex = 0, totalWords = 0;
printf("Input a string: ");
fgets(inputString, sizeof(inputString), stdin);
for(indexCtr = 0; indexCtr <= strlen(inputString); indexCtr++){
if(inputString[indexCtr] == ' ' || inputString[indexCtr] == '\0'){
words[totalWords][wordIndex] = '\0';
totalWords++;
wordIndex = 0;
}
else{
words[totalWords][wordIndex] = inputString[indexCtr];
wordIndex++;
}
}
printf("\nWords from the string are:\n");
for(indexCtr = 0; indexCtr < totalWords; indexCtr++){
printf("%s\n", words[indexCtr]);
}
return 0;
}
as an idea with strncpy(...):
char input[100] = " 1 2 3 4 5 "
"one two three four five";
char words[10][10] = { 0 };
size_t w_counter = 0;
for (size_t i = 0; i < strlen (input); i++) {
while (input[i] != '\0' && isspace (input[i])) {
i++;
}
char* start = &input[i];
while (input[i] != '\0' && !isspace (input[i])) {
i++;
}
strncpy (words[w_counter++],
start,
&input[i] - start);
}
//output
for (size_t i = 0; i < w_counter; i++){
puts (words[i]);
}
Related
Using the code below it only reads one char and does not convert morse to letter. My idea was to create a string of one morse "letter" and put it in the convert function, however only 1 char is being read since I am only seeing a single 1 printed on the screen after the string itself is printed. The string only consists of '-' , '.' , ' '. I was wondering if anyone knows what the solution might be.
char convertToLetter(M* data, char word[10]) {
int size = 0;
char correct;
while (size < 60)
{
int compare = strcmp(word, data->morse);
if (compare == 0) {
correct = data->letter;
}
data++;
size++;
}
correct = '\0';
return correct;
}
int main(){
//some code here for opening a file.
char curSent[200];
char letter[6] = "";
int i = 0;
char* fullString = (char*)malloc(1000 * sizeof(char));
fullString[0] = '\0';
while (fgets(curSent, 200, inFile) != NULL) {
if (curSent[0] != '\n') {
curSent[strlen(curSent) - 1] = '\0';
strcat_s(fullString,1000, curSent);
}
else {
printf("%s", fullString);
printf("\n\n");
int j = 0;
while (i < strlen(fullString)) {
if (fullString[i] != ' ') {
fullString[i] = letter[j];
i++;
j++;
printf("%d \n", 1);
}else if (fullString[i + 1] == ' ' && fullString[i] == ' ') {
printf("%d", 2);
printf(" %c", convertToLetter(dictionary, letter));
memset(letter, 0, strlen(letter));
j = 0;
i = i + 2;
}else if (fullString[i] == ' ') {
printf("%d", 3);
printf("%c", convertToLetter(dictionary, letter));
memset(letter, 0, strlen(letter));
j = 0;
i = i++;
}
}
memset(fullString, 0, strlen(fullString));
i = 0;
}
}
//printf("%s", fullString);
getchar();
return 0;
}
I basically have a sentence in a string and want to break it down word per word. Every word should go into an array of strings. I am not allowed to use strtok. I have this code but it doesn't work. Can someone help?
There is for sure something similar in the internet but I couldn't find anything...
int main(){
char s[10000]; // sentence
char array[100][100]; // array where I put every word
printf("Insert sentence: "); // receive the sentence
gets(s);
int i = 0;
int j = 0;
for(j = 0; s[j] != '\0'; j++){ // loop until I reach the end
for(i = 0; s[i] != ' '; i++){ // loop until the word is over
array[j][i] = s[i]; // put every char in the array
}
}
return 0;
}
Every word should go into an array of strings. I am not allowed to use
strtok.
Interesting problem which could be resolved in a compact algorithm.
It handles multiple spaces and punctuation marks specified in check(char c).
The most difficult part of the problem is to properly handle corner cases. We may have situation when words are longer more than WORD_LEN length or the number of words exceeds the capacity of the array.
Both cases are properly handled. The algorithm truncates the excessive words and parses only to the capacity of the array.
(BTW. Do not use gets: Why is the gets function so dangerous that it should not be used?)
Edit: The fully tested find_tokens function has been presented.
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define WORD_LEN 3 // 100 // MAX WORD LEN
#define NR_OF_WORDS 3 // 100 // MAX NUMBER OF WORDS
#define INPUT_SIZE 10000
int is_delimiter(const char * delimiters, char c) // check for a delimiter
{
char *p = strchr (delimiters, c); // if not NULL c is separator
if (p) return 1; // delimeter
else return 0; // not a delimeter
}
int skip(int *i, char *str, int skip_delimiters, const char *delimiters)
{
while(1){
if(skip_delimiters) {
if( (str[(*i)+1] =='\0') || (!is_delimiter(delimiters, str[(*i)+1])) )
break; // break on nondelimeter or '\0'
else (*i)++; // advance to next character
}
else{ // skip excess characters in the token
if( is_delimiter(delimiters, str[(*i)]) )
{
if( (str[(*i)+1] =='\0') || !is_delimiter(delimiters, str[(*i)+1]) )
break; // break on non delimiter or '\0'
else (*i)++; // skip delimiters
}
else (*i)++; // skip non delimiters
}
}
if ( str[(*i)+1] =='\0') return 0;
else return 1;
}
int find_tokens(int max_tokens, int token_len, char *str, char array[][token_len+1], const char *delimiters, int *nr_of_tokens)
{
int i = 0;
int j = 0;
int l = 0;
*nr_of_tokens = 0;
int status = 0; // all OK!
int skip_leading_delimiters = 1;
int token = 0;
int more;
for(i = 0; str[i] != '\0'; i++){ // loop until I reach the end
// skip leading delimiters
if( skip_leading_delimiters )
{
if( is_delimiter( delimiters, str[i]) ) continue;
skip_leading_delimiters = 0;
}
if( !is_delimiter(delimiters,str[i]) && (j < token_len) )
{
array[l][j] = str[i]; // put char in the array
//printf("%c!\n", array[l][j] );
j++;
array[l][j] = 0;
token = 1;
}
else
{
//printf("%c?\n", str[i] );
array[l][j] = '\0'; // token terminations
if (j < token_len) {
more = skip(&i, str, 1, delimiters); // skip delimiters
}
else{
more = skip(&i, str, 0, delimiters); // skip excess of the characters in token
status = status | 0x01; // token has been truncated
}
j = 0;
//printf("more %d\n",more);
if(token){
if (more) l++;
}
if(l >= max_tokens){
status = status | 0x02; // more tokens than expected
break;
}
}
}
if(l>=max_tokens)
*nr_of_tokens = max_tokens;
else{
if(l<=0 && token)
*nr_of_tokens = 1;
else
{
if(token)
*nr_of_tokens = l+1;
else
*nr_of_tokens = l;
}
}
return status;
}
int main(void){
char input[INPUT_SIZE+1]; // sentence
char array[NR_OF_WORDS][WORD_LEN+1]; // array where I put every word, remeber to include null terminator!!!
int number_of_words;
const char * delimiters = " .,;:\t"; // word delimiters
char *p;
printf("Insert sentence: "); // receive the sentence
fgets(input, INPUT_SIZE, stdin);
if ( (p = strchr(input, '\n')) != NULL) *p = '\0'; // remove '\n'
int ret = find_tokens(NR_OF_WORDS, WORD_LEN, input, array, delimiters, &number_of_words);
printf("tokens= %d ret= %d\n", number_of_words, ret);
for (int i=0; i < number_of_words; i++)
printf("%d: %s\n", i, array[i]);
printf("End\n");
return 0;
}
Test:
Insert sentence: ..........1234567,,,,,,abcdefgh....123::::::::::::
tokens= 3 ret= 1
0: 123
1: abc
2: 123
End
You are not '\0'-terminating the strings and you are scanning the source from
the beginning every time you've found a empty character.
You only need one loop and, the inner loop and the condition must be s[i] != 0:
int j = 0; // index for array
int k = 0; // index for array[j]
for(i = 0; s[i] != '\0'; ++i)
{
if(k == 99)
{
// word longer than array[j] can hold, aborting
array[j][99] = 0; // 0-terminating string
break;
}
if(j == 99)
{
// more words than array can hold, aborting
break;
}
if(s[i] == ' ')
{
array[j][k] = 0; // 0-terminating string
j++; // for the next entry in array
k = 0;
} else
array[j][k++] = s[i];
}
Note that this algorithm doesn't handle multiple spaces and punctuation marks.
This can be solved by using a variable that stores the last state.
int j = 0; // index for array
int k = 0; // index for array[j]
int sep_state = 0; // 0 normal mode, 1 separation mode
for(i = 0; s[i] != '\0'; ++i)
{
if(k == 99)
{
// word longer than array[j] can hold, aborting
array[j][99] = 0; // 0-terminating string
break;
}
if(j == 99)
{
// more words than array can hold, aborting
break;
}
// check for usual word separators
if(s[i] == ' ' || s[i] == '.' || s[i] == ',' || s[i] == ';' || s[i] == ':')
{
if(sep_state == 1)
continue; // skip multiple separators
array[j][k] = 0; // 0-terminating string
j++; // for the next entry in array
k = 0;
sep_state = 1; // enter separation mode
} else {
array[j][k++] = s[i];
sep_state = 0; // leave separation mode
}
}
As you can see, using the sep_state variable I'm able to check if multiple
separators come one after the other and skips subsequent separators. I also
check for common punctuation marks.
#include <stdio.h>
int main()
{
char s[10000]; // sentence
char array[100][100]; // array where i put every word
printf("Insert sentence: "); // receive the sentece
gets(s);
printf("%s",s);
int i = 0;
int j = 0;
int k = 0;
for(j = 0; s[j] != '\0'; j++){ // loop until i reach the end
if ( s[j] != ' ' || s[j] == '\0' )
{
array[i][k] = s[j];
k++;
}
else {
i++;
k = 0;
}
}
return 0;
}
please note that the gets function is very unsafe and shouldn't in any case be used, use scanf or fgets instead
I'm trying to split a sentence the user inputs to an array of words so I can later manipulate the words separately as strings.
The code is compiling but prints only garbage after the user input.
I tried debugging but don't see the problem. Can someone help me fix it?
#include <stdio.h>
#include <string.h>
int main() {
char str[1000];
int i = 0;
char rev[1000][1000];
int r = 0;
puts("Enter text:");
gets(str);
int k, length = 0;
printf_s("So the words are:\n");
while (str[i] != '\0') {
if (str[i] == ' ') {
k = i - length;
do {
rev[r][k] = (str[k]);
k++;
} while (str[k] != ' ');
printf(" ");
length = (-1);
r++;
} else
if (str[i + 1] == '\0') {
k = i - length;
do {
rev[r][k] = (str[k]);
k++;
} while (str[k] != '\0');
length = 0;
r++;
}
length++;
i++;
}
for (int r = 0; r < 1000; r++)
printf("%s ", rev[r]);
return 0;
}
fix like this
#include <stdio.h>
int main(void) {
char str[1000];
char rev[1000][1000];
puts("Enter text:");
fgets(str, sizeof str, stdin);//Use fgets instead of gets. It has already been abolished.
int r = 0;
int k = 0;
for(int i = 0; str[i] != '\0'; ++i){
if (str[i] == ' ' || str[i] == '\n'){//is delimiter
if(k != 0){
rev[r++][k] = '\0';//add null-terminator and increment rows
k = 0;//reset store position
}
} else {
rev[r][k++] = str[i];
}
}
if(k != 0)//Lastly there was no delimiter
rev[r++][k] = '\0';
puts("So the words are:");
for (int i = 0; i < r; i++){
printf("%s", rev[i]);
if(i < r - 2)
printf(", ");
else if(i == r - 2)
printf(" and ");
}
return 0;
}
Replace you declaration
char rev[1000][1000];
with
char * rev[1000]; // We will need pointers only
int i = 0; // Index to previous array
and all your code after
puts( "Enter text:" );
with this:
fgets( str, 998, stdin ); // Safe way; don't use gets(str)
const char delim[] = ",; "; // Possible delimiters - comma, semicolon, space
char *word;
/* Get the first word */
word = strtok( str, delim );
rev[i++] = word;
/* Get the next words */
while( word != NULL )
{
word = strtok( NULL, delim );
rev[i++] = word;
}
/* Testing */
for (int r = 0; r < i - 1; r++)
printf( "%s\n", rev[r] );
return 0
}
As you can see, all dirty work is done with the strtok() function ("string to tokens") which walks through other and other words ("tokens"), recognizing them as delimited by one or more characters from the string delim.
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
int count_spaces(char *str)
{
if (str == NULL || strlen(str) <= 0)
return (0);
int i = 0, count = 0;
while (str[i])
{
if (str[i] == ' ')
count++;
i++;
}
return (count);
}
int count_char_from_pos(char *str, int pos)
{
if (str == NULL || strlen(str) <= 0)
return 0;
int i = pos, count = 0;
while (str[i] && str[i] != ' ')
{
count++;
i++;
}
return count;
}
char **get_words(char *str)
{
if (str == NULL || strlen(str) <= 0)
{
printf("Bad string inputed");
return NULL;
}
int i = 0, j = 0, k = 0;
char **dest;
if ((dest = malloc(sizeof(char*) * (count_spaces(str) + 1))) == NULL
|| (dest[0] = malloc(sizeof(char) * (count_char_from_pos(str, 0) + 1))) == NULL)
{
printf("Malloc failed\n");
return NULL;
}
while (str[i])
{
if (str[i] == ' ') {
dest[j++][k] = '\0';
if ((dest[j] = malloc(sizeof(char) * (count_char_from_pos(str, i) + 1))) == NULL)
{
printf("Malloc failed\n");
return NULL;
}
k = 0;
}
else {
dest[j][k++] = str[i];
}
i++;
}
dest[j][k] = 0;
dest[j + 1] = NULL;
return dest;
}
int main(void) {
char *line = NULL;
size_t n = 0;
getline(&line, &n, stdin);
printf("%s\n", line);
line[strlen(line) - 1] = 0;
printf("%s\n", line);
char **tab = get_words(line);
int i = 0;
while (tab[i])
{
printf("%s\n", tab[i++]);
}
}
here is a long but fully working example
get the user input
then send it to get_words function. It will get the number of words, the number of characters for each words, allocate everything in memory and writes chars then return it. You get a char ** and prints it just tested it it works
If you wish to split a string into an array of strings, you should consider the strtok function from #include <string.h>. The strtok function will the split the string on the given delimiter(s). For your case, it would the " ".
Using the strtok example from Tutorials Point:
#include <string.h>
#include <stdio.h>
int main(){
char str[80] = "This is - www.tutorialspoint.com - website";//The string you wish to split
const char s[] = "-";//The thing you want it to split from. But there is no need to this.
char *token;//Storing the string
/* get the first token */
token = strtok(str, s);//Split str one time using the delimiter s
/* walk through other tokens */
while( token != NULL )
{
printf( " %s\n", token );//Print the string
token = strtok(NULL, s);//Split the string again using the delimiter
}
return(0);
}
I have been stuck on this for a while now. I wrote my program to count word occurrence in an inputted string by the user as well to sort the words alphabetically. My issue is my program runs perfectly only if there are spaces in between the words inputted. For example, if I input "to to," my program will count those two words as two different words due to the comma rather than counting it as one word in "to" as I would like it to. It is that issue for all of my delimiters in the array const char delim[]. How can I fix this issue in my program? I really appreciate any help! My code is down below:
Edit: I took Bob's suggestion to use strchr() and it worked! My only issue is my program outputs the count for delimiters now. I was thinking of possibly writing an if statement when comparing words[i] with words[j] to see if they have the same value. Is that the best approach to it?
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <ctype.h>
const char delim[] = ", . - !*()&^%$##<> ? []{}\\ / \"";
#define SIZE 1000
int main(){
char string[SIZE], words[SIZE][SIZE], temp[SIZE];
int a = 0, i = 0, j = 0, k = 0, n = 0, count;
int c = 0, cnt[26] = { 0 };
int word = 0;
int x;
printf("Enter your input string:");
fgets(string, SIZE, stdin);
string[strlen(string) - 1] = '\0';
lower(string);
/*extracting each and every string and copying to a different place */
while (string[i] != '\0'){
if (strchr(", . - !*()&^%$##<> ? []{}\\ / \"", string[i]) != NULL){
words[j][k] = '\0';
k = 0;
j++;
}else {
words[j][k++] = string[i];
}
i++;
}
words[j][k] = '\0';
n = j;
printf("Number of occurences of each word unsorted:\n");
i = 0;
/* find the frequency of each word and print the results */
while (i <= n) {
count = 1;
if (i != n) {
for (j = i + 1; j <= n; j++) {
if (strcmp(words[i], words[j]) == 0) {
count++;
for (a = j; a <= n; a++)
strcpy(words[a], words[a + 1]);
n--;
}
}//for
}
//word == strtok(string, delim);
/* count - indicates the frequecy of word[i] */
printf("%s\t%d\n", words[i], count);
i = i + 1;
}//while
printf("Alphabetical Order:\n");
/* sort the words in the given string */
for (i = 0; i < n; i++){
strcpy(temp, words[i]);
for (j = i + 1; j <= n; j++){
if (strcmp(words[i], words[j]) > 0){
strcpy(temp, words[j]);
strcpy(words[j], words[i]);
strcpy(words[i], temp);
}
} //inner for
} //outer for
i = 0;
while (i <= n) {
count = 1;
if (i != n) {
for (j = i + 1; j <= n; j++) {
if (strcmp(words[i], words[j]) == 0) {
count++;
}
}
}
printf("%s\n", words[i]);
i = i + count;
}
}
Strip every word of that delimeter before comparing. Actually you don't even need a list of delimeters because words are 'alpha' other than that it's a delimeter.
Please try this, it works, it is an extract of your own code, a little bit modified, it will give you the count, then you have to write the rest, have fun.
#include <string.h>
#define YES 1
#define NO 0
int main( )
{
char string[1000];
int i = 0;
int j = 0;
int is_this_a_word = 0;
strcpy( string, " to or not ,tobe" );
while ( string[i++] != '\0' )
{
if ( strchr( ", . - !*()&^%$##<> ? []{}\\ / \"", string[i] ) != NULL )
{
is_this_a_word = NO;
}
else
{
if ( ! is_this_a_word )
{
is_this_a_word = YES;
j++;
}
}
}
printf( "I counted %d words", j );
getchar( );
}
I have another problem concerning C :( what I want to do with this function is check for numbers in a token and if there are none I put that token in a string, which I later print to file. My function looks like this:
const char *tarpas = " ";
{
const char *space = " ";
char *token, B[255];
int i, length, found = 0, x = 0;
token = strtok(A, space);
while(token != NULL){
for(i = 0; i < strlen(token); i++){
if((token[i] >= '0') && (token[i] <= '9')) found++; //If found a number
} //increase found
if(found == 0){ //if found = 0 means the word is clean
for(i = 0; i < strlen(token); i++){
B[x] = token[i];
x++;
}
B[x] = ' '; //adds a space after the token is in string
x++;
}
rado = 0;
token = strtok(NULL, tarpas); // get another token
}
print(B);
memset(B, 0, strlen(B)); //clear B string
}
My data file:
ta5iip r345ytas suraitytas o rytoj gimimo rytas
asdasdasd
asdasd
My result file:
asdasd \
rytoj gimimo rytas
(
What it should be:
suraitytas o rytoj gimimo rytas
asdasdasd
asdasd
Thank you for any kind of input!!!
You have to reset found in each iteration of the while loop.
Also you have to exit loop
for(i = 0; i < strlen(token); i++){
if((token[i] >= '0') && (token[i] <= '9')) found++; //If found a number
}
if a digit was found in the string.
This loop could be rewritten the following way
size_t n = strlen(token);
i = 0;
while ( i < n && ( token[i] < '0' || token[i] > '9' ) ++i;
found = i != n;
It seems also that you read strings with function fgets that includes the new line character. You should remove this character from the string.
ANd place statement
memset(B, 0, strlen(B));
before the while loop or initially initialize array B to zeroes
You never reset found to zero inside the loop.
Since you find a digit in the first token, that means that you never execute the if(found == 0) code.
This, in turn, means that when you print B, it's still uninitialised and you're printing some random data.
You should initialise B:
char B[255] = {0};
and add
found = 0;
as the first line of the loop.
Or, since you have no use of found outside the loop, move it inside the loop.
while(token != NULL){
int found = 0;
/* ... */
You forgot to initialize found variable inside the while loop. Also as #BLUEPIXY mentioned, B array needs to be ended with '\0'.
So the code would be as following
{
const char *space = " ";
char *token, B[255];
int i, length, found = 0, x = 0;
token = strtok(A, space);
while(token != NULL){
found = 0;
for(i = 0; i < strlen(token); i++){
if((token[i] >= '0') && (token[i] <= '9')) found++; //If found a number
} //increase found
if(found == 0){ //if found = 0 means the word is clean
for(i = 0; i < strlen(token); i++){
B[x] = token[i];
x++;
}
B[x] = ' '; //adds a space after the token is in string
x++;
}
rado = 0;
token = strtok(NULL, tarpas); // get another token
}
B[x] = '\0';
print(B);
memset(B, 0, strlen(B)); //clear B string
}