I'm trying to split this string:
this is a text file
looking for the word cat
the program should print also cats
and crat and lcat but it shouldn’t
print the word caats
into a two dimensional arrays such that every line in the text is a line in the array.
For example:
lines[0][0] = 't'
lines[0][1] = 'h'
and so on. For now, this is my code:
void print_lines(char txt[]){
char lines[SIZE][SIZE];
int num_of_lines = fill_lines(txt, lines);
printf("lines: %d\n",num_of_lines );
int i;
for (i = 0; i < num_of_lines; i++)
{
printf("%s\n", lines[i]);
}
}
int fill_lines(char txt[], char lines[][]){
char copy[strlen(txt)];
memcpy(copy, txt, strlen(txt));
char *line = strtok(copy, "\n");
int i = 0;
while(line != NULL){
strcpy(lines[i][0], line);
line = strtok(NULL, "\n");
i++
}
return i + 1;
}
The problem I'm currently dealing with is an error in strcpy(lines[i], line) that reads:
expression must be a pointer to a complete object type
I have also tried memcpy(lines[i], line, strlen(line)).
Any help would be much appreciated.
I think this should work for you
Here I used '\n' as a delimiter
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
#include <assert.h>
char **str_split(char *a_str, const char a_delim)
{
char **result = 0;
size_t count = 0;
char *tmp = a_str;
char *last_comma = 0;
char delim[2];
delim[0] = a_delim;
delim[1] = 0;
/* Count how many elements will be extracted. */
while (*tmp)
{
if (a_delim == *tmp)
{
count++;
last_comma = tmp;
}
tmp++;
}
/* Add space for trailing token. */
count += last_comma < (a_str + strlen(a_str) - 1);
/* Add space for terminating null string so caller
knows where the list of returned strings ends. */
count++;
result = malloc(sizeof(char *) * count);
if (result)
{
size_t idx = 0;
char *token = strtok(a_str, delim);
while (token)
{
assert(idx < count);
*(result + idx++) = strdup(token);
token = strtok(0, delim);
}
assert(idx == count - 1);
*(result + idx) = 0;
}
return result;
}
int main()
{
char text[] = "this is a text file\nlooking for the word cat\nthe program should print also cats\nand crat and lcat but it shouldn’t\nprint the word caats";
char **tokens;
printf("ORIGINAL TEXT:\n%s\n\n", text);
tokens = str_split(text, ',');
if (tokens)
{
int i;
for (i = 0; *(tokens + i); i++)
{
printf("%s\n", *(tokens + i));
free(*(tokens + i));
}
printf("\n");
free(tokens);
}
return 0;
}
Related
I need to write code that reads a string of characters such as jasf#fjaf#afsj to a single dimension string and then ask for a separation character (eg: #) so it will get an output in two dimensions and for every line, it will be the words between the separation character like:
jasf
fjaf
afsj
I tried:
#include <stdio.h>
#include <string.h>
void main {
int s, k, b;
printf("please enter a long string\n");
gets(longstring);
s = strlen(longstring);
printf("please choose seperationg charcter\n");
scanf("%c", &ch);
if ((ch < 'A') || ((ch > 'Z') && (ch < 'a')) || (ch > 'z')) {
for (k = 0; k < s; k++) {
for (b = 0; longstring[k] == ch; ++b) {
strcpy(mat[b], longstring);
}
}
puts(mat[b]);
}
Your code is incomplete: the function definition for main lacks its argument list, which is not optional in C, longstring is not defined, etc.
Futhermore, your method is too complicated: you do not need to test for letters if the goal is just to output one line for each part of the string between separators.
Here is a simple solution:
#include <stdio.h>
#include <string.h>
int main() {
char longstring[256];
int i, len;
char sep;
printf("please enter a long string\n");
if (fgets(longstring, sizeof longstring, stdin)) {
len = strlen(longstring);
printf("please choose a separationg character: ");
if (scanf("%c", &sep) != 1)
return 1;
for (i = 0; i < len; i++) {
if (longstring[i] == sep)
putchar('\n');
else
putchar(longstring[i]);
}
}
return 0;
}
since your code is not complete , let me add what is missing to achieve the task :
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <assert.h>
char** str_split(char* a_str, const char a_delim)
{
char** result = 0;
size_t count = 0;
char* tmp = a_str;
char* last_comma = 0;
char delim[2];
delim[0] = a_delim;
delim[1] = 0;
/* Count how many elements will be extracted. */
while (*tmp)
{
if (a_delim == *tmp)
{
count++;
last_comma = tmp;
}
tmp++;
}
/* Add space for trailing token. */
count += last_comma < (a_str + strlen(a_str) - 1);
/* Add space for terminating null string so caller
knows where the list of returned strings ends. */
count++;
result = (char**) malloc(sizeof(char*) * count);
if (result)
{
size_t idx = 0;
char* token = strtok(a_str, delim);
while (token)
{
assert(idx < count);
*(result + idx++) = strdup(token);
token = strtok(0, delim);
}
assert(idx == count - 1);
*(result + idx) = 0;
}
return result;
}
int main()
{
char longstring[1024];
char** tokens;
char ch;
unsigned long s;
printf("please enter a long string\n");
gets(longstring);
s = strlen(longstring);
printf("please choose seperationg charcter\n");
scanf("%c", &ch);
if ((ch<'A') || ((ch>'Z') && (ch<'a')) || (ch>'z'))
{
tokens = str_split(longstring, ch);
if (tokens)
{
int i;
for (i = 0; *(tokens + i); i++)
{
printf("%s\n", *(tokens + i));
free(*(tokens + i));
}
printf("\n");
free(tokens);
}
}
return 0;
}
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 want to return nothing when the string is number
here is my code,
#include <string.h>
#include <ctype.h>
int num = 0;
char* findWord(char* subString) {
char* word = malloc(sizeof(char) * (strlen(subString) + 1));
int i = 0;
int Position = 0;
num = 0;
while (ispunct(subString[i]) != 0 || isspace(subString[i]) != 0) {
i++;
}
num = i;
while (ispunct(subString[i]) == 0 && isspace(subString[i]) == 0) {
word[Position] = subString[i];
i++;
Position++;
}
word[Position] = '\0';
return word;
}
char** wordList(const char* s) {
int len = strlen(s);
int i = 0;
char* Copyword = malloc(sizeof(char) * len);
strncpy(Copyword, s, len);
char** result = (char**) malloc(sizeof(char*) * (len + 1));
char* word = NULL;
word = findWord(Copyword);
char* wordEnd = Copyword;
while (*word != 0) {
result[i] = word;
wordEnd = wordEnd + strlen(word) + num;
word = findWord(wordEnd);
i++;
}
result[i] = '\0';
free(Copyword);
return result;
}
int main(void) {
char** words = wordList("1 23 456 789");
int i = 0;
while (words[i] != NULL) {
printf("%s\n", words[i]);
free(words[i]); // We're done with that word
i++;
}
free(words); // We're done with the list
return 0;
}
my code is ok when the string is sentence.
however, in this case, I want to print nothing(just like a space) when the string is number.
but what I go is
1
23
456
789
I expect to get
nothing shows here! just a space
For starters: You pass a non 0-terminated C-"string" (Copyword) to findWord() and in there call strlen() on it. This just doesn't crash your app by bad luck.
I wrote a simple code to split string in C with delimiter. When I remove all my frees, code works great but gives memory leaks. When I dont remove free, it does not show memory leaks but gives segmentation fault .. What is wring and how to solve it?
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
unsigned int countWords(char *stringLine)
{
unsigned int count = 0;
char* tmp = stringLine;
char* last = 0;
const char delim = '/';
while (*tmp)
{
if (delim == *tmp)
{
count++;
last = tmp;
}
tmp++;
}
return count;
}
char **getWordsFromString(char *stringLine)
{
char** sizeNames = 0;
unsigned int count = 0;
const char *delim = "/";
count = countWords(stringLine);
sizeNames = malloc(sizeof(char*) * count);
if(sizeNames == NULL)
{
return NULL;
}
if (sizeNames)
{
size_t idx = 0;
char* token = strtok(stringLine, delim);
while (token)
{
if(idx > count)
{
exit(-1);
}
*(sizeNames + idx++) = strdup(token);
token = strtok(0, delim);
}
if(idx == count - 1)
{
exit(-1);
}
*(sizeNames + idx) = 0;
}
return sizeNames;
}
void showWords(char *stringLine)
{
unsigned int size = countWords(stringLine), i = 0;
char** sizeNames = getWordsFromString(stringLine);
for (i = 0; *(sizeNames + i); i++)
{
printf("word=[%s]\n", *(sizeNames + i));
free(*(sizeNames + i));
}
printf("\n");
free(sizeNames);
}
int main()
{
char words[] = "hello/world/!/its/me/";
showWords(words);
return 0;
}
Variable sizeNames is an array of pointers, not a string (array of characters) that you need to terminate with a null-character.
So remove this:
*(sizeNames + idx) = 0;
And change this:
for (i=0; *(sizeNames+i); i++)
To this:
for (i=0; i<size; i++)
In getWordsFromString,
*(sizeNames + idx) = 0;
Writes one past the end of your allocated memory, and when you try to free it, you get a segfault. Try count+1 in the malloc:
sizeNames = malloc(sizeof(char*) * (count+1) );
*Can someone please help me with this function. I'm trying to separate the string input into tokens and also shift each token some by some specified amount. *
char *tokenize(char *f, int shift){
const char delim[] = " .;\n\t";
char *pa = f; //points to the beginning of *f
//size of *f
int i;
int stringSize = 0;
for(i = 0; f[i] != '\0'; i++)
{
stringSize++;
}
//put string in array to pass to strtok function
char newString[stringSize];
int j;
for(j = 0; j < stringSize; j++)
{
newString[j] = *f;
f++;
}
//break the words up into sub-strings without the delimiters
char *word = strtok(newString, delim);
while(word != NULL)
{
word = strtok(NULL, delim);
word = stringShift(word, shift);
//printf("After being shifted %d = %s\n", shift, word);
}
return pa;
}
/*Shift Function*/
char *stringShift(char *s, int k){
int i;
for(i = 0; s[i] != '\0'; i++)
{
s[i] += k;
}
return s;
}
I think this should serve the purpose ok, as far as I understand it
char* addWordToArr(char *arr,char *word)
{
int i;
for(i =0;i<strlen(word);i++)
{
*arr++ = word[i];
}
*arr++ = ' ';
return arr;
}
char *tokenize(char *f, int shift){
const char delim[] = " .;\n\t";
int stringSize = strlen(f);
//put string in array to pass to strtok function
char newString[stringSize+1];
int j;
for(j = 0; j < stringSize; j++)
{
newString[j] = *f;
f++;
}
newString[stringSize] = '\0'; //null terminate
char *rVal = malloc(sizeof(char) * (stringSize +1)); //The total length of the tokenized string must be <= the original string
char *writePtr = rVal;
//break the words up into sub-strings without the delimiters
char *word = strtok(newString, delim);
word = stringShift(word, shift);
writePtr = addWordToArr(writePtr,word);
while(word != NULL)
{
word = strtok(NULL, delim);
if(word)
{
word = stringShift(word, shift);
writePtr = addWordToArr(writePtr,word);
}
}
writePtr = '\0';
return rVal;
}
which produces:
string before shift bish;bash;bosh hyena trout llama exquisite underwater dinosaur
string after shift dkuj dcuj dquj j{gpc vtqwv nncoc gzswkukvg wpfgtycvgt fkpqucwt
The stringShift function is unchanged