count how many word in sentence- what's wrong - c

I wrote a code that counts how many words are there in a sentence, but it does not work in cases like this for example:
"hello world."
It needs to return that there are 2 words, but it returns 4 because of the spaces. It's only good for the case of one space between each word. This is my code:
int counthowmanywordsinasentence(char sentence[])// help forfunc7
{
int count = 0, i;
for (i = 0;sentence[i] != '\0';i++)
{
if (sentence[i] == ' ')
count++;
}
return (count+1);
}

Use a flag. If you encounter a space & flag is not set, set the flag and increment count. If space is encountered & flag is set , just ignore that case. And if flag is set & char(i.e. sentence[i]) is not space, reset flag.

This is the simplest of all answers, just add 2 lines
#include <stdio.h>
int counthowmanywordsinasentence(char sentence[])// help forfunc7
{
int count = 0, i;
for (i = 0;sentence[i] != '\0';i++)
{
if (sentence[i] == ' ')
count++;
while (sentence[i] == ' ')
i++;
}
return (count+1);
}

You can safely replace your if by this new version:
if (sentence[i] == ' ' && sentence[i+1] != ' ')
Which means you will be only counting the last space in each space sequence. So in your case of 4 contiguous spaces, you will count only the last one.
You will still need to decide what to do in these two cases:
" hello world."
"hello world "
As you need to know if these should count as 2 or 3 words in both cases.

So sscanf already does what you need it will eat any number of whitespaces before a string including tabs. This algorithm is safe with leading or trailing spaces.
int countHowManyWordsInASentence(char* sentence){
int result = 0;
int i = 0;
while(sscanf(sentence, "%*s%n", &i) != EOF){
sentence += i;
result++;
}
return result;
}
sscanf is extremely versatile you can easily read out each word as follows:
int countHowManyWordsInASentence(char* sentence){
int result = 0;
int size = strlen(sentence);
if(size > 0){
char* word = (char*)malloc((size + 1) * sizeof(char));
for(int i = 0; sscanf(sentence, "%s%n", word, &i) > 0; sentence += i){
result++;
}
free(word);
}
return result;
}

int counthowmanywordsinasentence(char sentence[])
{
int count = 0, i;
char ch, pre = ' ';
for (i = 0; (ch=sentence[i]) != '\0'; i++, pre = ch)
{
if (pre == ' ' && ch != ' ')//reckon the rise
count++;
}
return count;
}

You'll have to decide what is a word first :) let's assume a word is any sequence of characters with at least one alphabetic character (A-Za-z). then you can follow #Abhilash's suggestion to complete your code.
int wordcount(char *sentence) {
int count = 0;
int is_word = 0;
int i;
for(i=0; sentence[i]!='\0'; i++) {
if(isalpha(sentence[i])) {
is_word = 1;
}
if(sentence[i] == ' ' && is_word) {
count++;
is_word = 0;
}
}
return count + is_word;
}

Related

How to print a string based on the postion in c?

I am working on a question which requires me to print a string given a field-number at that position. The strings should be read from a file.
file.txt
C is a language.
lex lexical analyser
(blank line)
gcc is good
If the field-number is 2 (i.e the second word in the sentence). The program should output
is
lexical
(NULL)
is
I wrote a function but don't think its the correct way and that it would work for all cases. It should handle extra blanks or newlines.
while (fgets(buffer, MAX, file) != NULL) {
for (int i = 1; i < strlen(buffer); i++) {
if (count == field_number - 1) {
int j = i;
while (j < strlen(buffer) && buffer[j] != ' ') {
printf("%c", buffer[j++]);
}
printf("\n");
count = 0;
break;
}
if (buffer[i] == ' ' && buffer[i - 1] != ' ') {
count++;
}
}
}
I am a beginner. This code should be easy to understand.
This should work for all the cases,
int main() {
//FILE* file = fopen(__FILE__, "r");
//int field_number = 2;
int new_line = 0; // var to keep track of new line came or not
int word = 0;
int count = 0;
char c, prev_c;
while ((c = fgetc(file)) != EOF) {
// printf("[%c]", c);
// if a new line char comes it means you entered a new line
if(c == '\n') {
// you have to print the new line here on the output to handle
// empty line cases
printf("\n");
new_line = 1; // when line changes
word = 0; // no word has come in this new line so far
count = 0; // count becomes 0
} else if( c == ' ' && prev_c != ' ') {
if(word)
count++;
if(count == field_number) // if count exceeds field_number
new_line = 0; // wait till next line comes
} else if (new_line && count == field_number - 1) {
printf("%c", c);
} else {
word = 1; // fi a not new line or non space char comes, a word has come
}
prev_c = c;
}
return 0;
}

Function and strings

I'm new to C and have started learning about strings. I want to create a function called
void SpaceRemover(char *input )
It should remove the spaced from a given string array that has lots of space
The code that I've produced so far removes all the spaces and doesn't provide the output I'm looking for. Can anyone help me with this?
char* SpaceRemover(char *input){
char *output=input;
for (int i = 0, j = 0; i<strlen(input); i++,j++)
{
if (input[i]!=' ')
output[j]=input[i];
else
j--;
}
return output;
}
I made this but I know its wrong and does not do what i want it to but honestly this is all i could this of -_-
You could just do as below
void SpaceRemover(char *name)
{
int i=0,j=0;
for (i = 0;i<strlen(name);i++)
{
if (name[i] != ' ' || (name[i] == ' ' && name[i+1] != ' ' && j!= 0))
{
name[j++] = name[i];
}
}
name[j]='\0'; //Terminate the string to avoid junk chars
}
Where
if (name[i] != ' ' || (name[i] == ' ' && name[i+1] != ' ' && j != 0))
will let you copy only if current char is not space or current char is space and next char is not space(to include single space apart in the beginning).
Also don't forget to terminate the string.
name[j]='\0';
The problem is that you remove all spaces.
char *SpaceRemover(char *name){
char *output = name;
int j = 0;
for (int i = 0; i < strlen(name); i++) {
if (name[i] != ' ' || (name[i] == ' ' && name[i + 1] != ' ') {
output[j] = name[i];
j += 1;
}
}
output[j] = '\0'
return output;
}
This condition should let one space through.
You might notice I replaced the void return type with a char * so t o use the function you will need to use:
name = SpaceRemover(name);
I would be using a flag to activate when a space is met.
This might need to be tweaked if you want to remove leading and trailing spaces too.
A space will be added to output and the flag will be used to avoid the next ones to be added. The flag will be deactivated when something else than a space is met.
As stated Alex in comments, decrementing j in loop while it's incremented in the for statement isn't recommended.
I would copy each characters in the for loop instead of filtering a pre-copied output.
char space_found = 0;
char *output = malloc(sizeof(char) * (strlen(name) + 1));
int j = 0;
for (int i = 0; i < strlen(name); ++i)
{
if (name[i] == ' ' and space_found == 0)
{
space_found = 1;
output[j++] = name[i];
}
if (name[i] != ' ')
{
space_found = 0;
output[j++] = name[i];
}
}
output[j] = '\0';
void spaceRemover(char* str)
{
char temp[50] = {0};
int j = 0;
strncpy(temp, str, strlen(str) + 1);
for(int i = 0; i < strlen(str); i++)
{
if(temp[i] != ' ')
{
str[j] = temp[i];
j++;
}
}
str[j] = 0;
}
if you have any questions, feel free to ask, Good Luck
#include <stdio.h>
char *rem(char *str)
{
char *cur=str;
char *nex=str;
while(*nex)
{
if(*nex == ' ') nex++;
else *cur++ = *nex++;
}
*cur=0;
return str;
}
int main(void) {
char z[]=" etc def etc def ";
printf("%s\n", rem(z));
return 0;
}

Folding input lines every nth column (K&R 1-22) in C

Write a program to "fold" long input lines into two or more shorter lines after the last non-blank character that occurs before the n-th column of input. Make sure your program does something intelligent with very long lines, and if there are no blanks or tabs before the specified column.
The algorithm I decided to follow for this was as follows:
If length of input line < maxcol (the column after which one would have to fold), then print the line as it is.
If not, from maxcol, I check towards it's left, and it's right to find the closest non-space character, and save them as 'first' and 'last'. I then print the character array from line[0] to line[first] and then the rest of the array, from line[last] to line[len] becomes the new line array.
Here's my code:
#include <stdio.h>
#define MAXCOL 5
int getline1(char line[]);
int main()
{
char line[1000];
int len, i, j, first, last;
len = getline1(line);
while (len > 0) {
if (len < MAXCOL) {
printf("%s\n", line);
break;
}
else {
for (i = MAXCOL - 1; i >= 0; i--) {
if (line[i] != ' ') {
first = i;
break;
}
}
for (j = MAXCOL - 1; j <= len; j++) {
if (line[j] != ' ') {
last = j;
break;
}
}
//printf("first %d last %d\n", first, last);
for (i = 0; i <= first; i++)
putchar(line[i]);
putchar('\n');
for (i = 0; i < len - last; i++) {
line[i] = line[last + i];
}
len -= last;
first = last = 0;
}
}
return 0;
}
int getline1(char line[])
{
int c, i = 0;
while ((c = getchar()) != EOF && c != '\n')
line[i++] = c;
if (c == '\n')
line[i++] = '\n';
line[i] = '\0';
return i;
}
Here are the problems:
It does not do something intelligent with very long lines (this is fine, as I can add it as an edge case).
It does not do anything for tabs.
I cannot understand a part of the output.
For example, with the input:
asd de def deffff
I get the output:
asd
de
def
defff //Expected until here
//Unexpected lines below
ff
fff
deffff
deffff
deffff
Question 1 - Why do the unexpected lines print? How do I make my program/algorithm better?
Eventually, after spending quite some time with this question, I gave up and decided to check the clc-wiki for solutions. Every program here did NOT work, save one (The others didn't work because they did not cover certain edge cases). The one that worked was the largest one, and it did not make any sense to me. It did not have any comments, and neither could I properly understand the variable names, and what they represented. But it was the ONLY program in the wiki that worked.
#include <stdio.h>
#define YES 1
#define NO 0
int main(void)
{
int TCOL = 8, ch, co[3], i, COL = 19, tabs[COL - 1];
char bls[COL - 1], bonly = YES;
co[0] = co[1] = co[2] = 0;
while ((ch = getchar()) != EOF)
{
if (ch != '\t') {
++co[0];
++co[2];
}
else {
co[0] = co[0] + (TCOL * (1 + (co[2] / TCOL)) - co[2]);
i = co[2];
co[2] = TCOL + (co[2] / TCOL) * TCOL;
}
if (ch != '\n' && ch != ' ' && ch != '\t')
{
if (co[0] >= COL) {
putchar('\n');
co[0] = 1;
co[1] = 0;
}
else
for (i = co[1]; co[1] > 0; --co[1])
{
if (bls[i - co[1]] == ' ')
putchar(bls[i - co[1]]);
else
for (; tabs[i - co[1]] != 0;)
if (tabs[i - co[1]] > 0) {
putchar(' ');
--tabs[i - co[1]];
}
else {
tabs[i - co[1]] = 0;
putchar(bls[i - co[1]]);
}
}
putchar(ch);
if (bonly == YES)
bonly = NO;
}
else if (ch != '\n')
{
if (co[0] >= COL)
{
if (bonly == NO) {
putchar('\n');
bonly = YES;
}
co[0] = co[1] = 0;
}
else if (bonly == NO) {
bls[co[1]] = ch;
if (ch == '\t') {
if (TCOL * (1 + ((co[0] - (co[2] - i)) / TCOL)) -
(co[0] - (co[2] - i)) == co[2] - i)
tabs[co[1]] = -1;
else
tabs[co[1]] = co[2] - i;
}
++co[1];
}
else
co[0] = co[1] = 0;
}
else {
putchar(ch);
if (bonly == NO)
bonly = YES;
co[0] = co[1] = co[2] = 0;
}
}
return 0;
}
Question 2 - Can you help me make sense of this code and how it works?
It fixes all the problems with my solution, and also works by reading character to character, and therefore seems more efficient.
Question 1 - Why do the unexpected lines print? How do I make my program/algorithm better?
You are getting the unexpected lines in the output because after printing the array, you are not terminating the new line array with null character \0 -
Here you are copying character from starting from last till len - last, creating a new line array:
for (i = 0; i < len - last; i++) {
line[i] = line[last + i];
}
You have copied the characters but the null terminating character is still at its original position. Assume the input string is:
asd de def deffff
So, initially the content of line array will be:
"asd de def deffff\n"
^
|
null character is here
Now after printing asd, you are copying characters from last index of line till len - last index to line array itself starting from 0 index. So, after copying the content of line array will be:
"de def deffff\n deffff\n"
|____ _____|
\/
This is causing the unexpected output
(null character is still at the previous location)
So, after for loop you should add the null character just after the last character copied, like this:
line [len - last] = '\0';
With this the content of line array that will be processed in the next iteration of while loop will be:
"de def deffff\n"
One more thing, in the line array you can see the \n (newline) character at the end. May you want to remove it before processing the input, you can do:
line[strcspn(line, "\n")] = 0;
Improvements that you can do in your program:
1. One very obvious improvement that you can do is to use pointer to the input string while processing it. With the help of pointer you don't need to copy the rest of the array, apart from processed part, again to the same array till the program process the whole input. Initialize the pointer to the start of the input string and in every iteration just move the pointer to appropriate location and start processing from that location where pointer is pointing to.
2. Since you are taking the whole input first in a buffer and then processing it. You may consider fgets() for taking input. It will give better control over the input from user.
3. Add a check for line array overflow, in case of very long input. With fgets() you can specify the maximum number of character to be copied to line array from input stream.
Question 2 - Can you help me make sense of this code and how it works?
The program is very simple, try to understand it at least once by yourself. Either use a debugger or take a pen and paper, dry run it once for small size input and check the output. Increase the input size and add some variations like multiple space characters and check the program code path and output. This way you can understand it very easily.
Here's another (and I think better) solution to this exercise :
#include <stdio.h>
#define MAXCOL 10
void my_flush(char buf[]);
int main()
{
int c, prev_char, i, j, ctr, spaceleft, first_non_space_buf;
char buf[MAXCOL+2];
prev_char = -1;
i = first_non_space_buf = ctr = 0;
spaceleft = MAXCOL;
printf("Just keep typing once the output has been printed");
while ((c = getchar()) != EOF) {
if (buf[0] == '\n') {
i = 0;
my_flush(buf);
}
//printf("Prev char = %c and Current char = %c and i = %d and fnsb = %d and spaceleft = %d and j = %d and buf = %s \n", prev_char, c, i, first_non_space_buf, spaceleft, j, buf);
if ((((prev_char != ' ') && (prev_char != '\t') && (prev_char != '\n')) &&
((c == ' ') || (c == '\t') || (c == '\n'))) ||
(i == MAXCOL)) {
if (i <= spaceleft) {
printf("%s", buf);
spaceleft -= i;
}
else {
putchar('\n');
spaceleft = MAXCOL;
for (j = first_non_space_buf; buf[j] != '\0'; ++j) {
putchar(buf[j]);
++ctr;
}
spaceleft -= ctr;
}
i = 0;
my_flush(buf);
buf[i++] = c;
first_non_space_buf = j = ctr = 0;
}
else {
if (((prev_char == ' ') || (prev_char == '\t') || (prev_char == '\n')) &&
((c != ' ') && (c != '\t') && (c != '\n'))) {
first_non_space_buf = i;
}
buf[i++] = c;
buf[i] = '\0';
}
prev_char = c;
}
printf("%s", buf);
return 0;
}
void my_flush(char buf[])
{
int i;
for (i = 0; i < MAXCOL; ++i)
buf[i] = '\0';
}
Below is my solution, I know the thread is no longer active but my code might help someone who's facing issues to grasp the already presented code snippets.
*EDIT
explaination
Keep reading input unless the input contains '\n', '\t' or there've been
atleast MAXCOl chars.
Incase of '\t', use expandTab to replace with required spaces and use printLine if it doesn't exceed MAXCOl.
Incase of '\n', directly use printLine and reset the index.
If index is 10:
find the last blank using findBlank ad get a new index.
use printLine to print the current line.
get new index as 0 or index of newly copied char array using the newIndex function.
code
/* fold long lines after last non-blank char */
#include <stdio.h>
#define MAXCOL 10 /* maximum column of input */
#define TABSIZE 8 /* tab size */
char line[MAXCOL]; /* input line */
int expandTab(int index);
int findBlank(int index);
int newIndex(int index);
void printLine(int index);
void main() {
int c, index;
index = 0;
while((c = getchar()) != EOF) {
line[index] = c; /* store current char */
if (c == '\t')
index = expandTab(index);
else if (c == '\n') {
printLine(index); /* print current input line */
index = 0;
} else if (++index == MAXCOL) {
index = findBlank(index);
printLine(index);
index = newIndex(index);
}
}
}
/* expand tab into blanks */
int expandTab(int index) {
line[index] = ' '; /* tab is atleast one blank */
for (++index; index < MAXCOL && index % TABSIZE != 0; ++index)
line[index] = ' ';
if (index > MAXCOL)
return index;
else {
printLine(index);
return 0;
}
}
/* find last blank position */
int findBlank(int index) {
while( index > 0 && line[index] != ' ')
--index;
if (index == 0)
return MAXCOL;
else
return index - 1;
}
/* re-arrange line with new position */
int newIndex(int index) {
int i, j;
if (index <= 0 || index >= MAXCOL)
return 0;
else {
i = 0;
for (j = index; j < MAXCOL; ++j) {
line[i] = line[j];
++i;
}
return i;
}
}
/* print line until passed index */
void printLine(int index) {
int i;
for(i = 0; i < index; ++i)
putchar(line[i]);
if (index > 0)
putchar('\n');
}

How to get words out of a string and put them in an string array ? In C

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

C - Split a string at the whitespaces

I need to split a string where there are spaces (ex string: Hello this is an example string. into an array of words. I'm not sure what I'm missing here, I'm also curious as to what the best way to test this function is. The only library function allowed is malloc.
Any help is appreciated!
#include <stdlib.h>
char **ft_split(char *str) {
int wordlength;
int wordcount;
char **wordbank;
int i;
int current;
current = 0;
wordlength = 0;
//while sentence
while (str[wordlength] != '\0') {
//go till letters
while (str[current] == ' ')
current++;
//go till spaces
wordlength = 0;
while (str[wordlength] != ' ' && str[wordlength] != '\0')
wordlength++;
//make memory for word
wordbank[wordcount] = malloc(sizeof(char) * (wordlength - current + 1));
i = 0;
//fill wordbank current
while (i < wordlength - current) {
wordbank[wordcount][i] = str[current];
i++;
current++;
}
//end word with '\0'
wordbank[wordcount][i] = '\0';
wordcount++;
}
return wordbank;
}
There are multiple problems in your code:
You do not allocate an array for wordbank to point to, dereferencing an uninitialized pointer has undefined behavior.
Your approach to scanning the string is broken: you reset wordlength inside the loop so you keep re-scanning from the beginning of the string.
You should allocate an extra entry in the array for a trailing null pointer to indicate the end of the array to the caller.
Here is a modified version:
#include <stdlib.h>
char **ft_split(const char *str) {
size_t i, j, k, wordcount;
char **wordbank;
// count the number of words:
wordcount = 0;
for (i = 0; str[i]; i++) {
if (str[i] != ' ' && (i == 0 || str[i - 1] == ' ')) {
wordcount++;
}
}
// allocate the word array
wordbank = malloc((wordcount + 1) * sizeof(*wordbank));
if (wordbank) {
for (i = k = 0;;) {
// skip spaces
while (str[i] == ' ')
i++;
// check for end of string
if (str[i] == '\0')
break;
// scan for end of word
for (j = i++; str[i] != '\0' && str[i] != ' '; i++)
continue;
// allocate space for word copy
wordbank[k] = p = malloc(i - j + 1);
if (p == NULL) {
// allocation failed: free and return NULL
while (k-- > 0) {
free(wordbank[k]);
}
free(wordbank);
return NULL;
}
// copy string contents
memcpy(p, str + j, i - j);
p[i - j] = '\0';
}
// set a null pointer at the end of the array
wordbank[k] = NULL;
}
return wordbank;
}
You need to malloc() wordbank too. You can count the number for words, and then
wordbank = malloc((count + 1) * sizeof(*wordbank));
if (wordbank == NULL)
return NULL;
Note: sizeof(char) is 1 by definition. And sizeof *pointer is always what you want.

Resources