Split string in C every white space - c

I want to write a program in C that displays each word of a whole sentence (taken as input) at a seperate line. This is what I have done so far:
void manipulate(char *buffer);
int get_words(char *buffer);
int main(){
char buff[100];
printf("sizeof %d\nstrlen %d\n", sizeof(buff), strlen(buff)); // Debugging reasons
bzero(buff, sizeof(buff));
printf("Give me the text:\n");
fgets(buff, sizeof(buff), stdin);
manipulate(buff);
return 0;
}
int get_words(char *buffer){ // Function that gets the word count, by counting the spaces.
int count;
int wordcount = 0;
char ch;
for (count = 0; count < strlen(buffer); count ++){
ch = buffer[count];
if((isblank(ch)) || (buffer[count] == '\0')){ // if the character is blank, or null byte add 1 to the wordcounter
wordcount += 1;
}
}
printf("%d\n\n", wordcount);
return wordcount;
}
void manipulate(char *buffer){
int words = get_words(buffer);
char *newbuff[words];
char *ptr;
int count = 0;
int count2 = 0;
char ch = '\n';
ptr = buffer;
bzero(newbuff, sizeof(newbuff));
for (count = 0; count < 100; count ++){
ch = buffer[count];
if (isblank(ch) || buffer[count] == '\0'){
buffer[count] = '\0';
if((newbuff[count2] = (char *)malloc(strlen(buffer))) == NULL) {
printf("MALLOC ERROR!\n");
exit(-1);
}
strcpy(newbuff[count2], ptr);
printf("\n%s\n",newbuff[count2]);
ptr = &buffer[count + 1];
count2 ++;
}
}
}
Although the output is what I want, I have really many black spaces after the final word displayed, and the malloc() returns NULL so the MALLOC ERROR! is displayed in the end.
I can understand that there is a mistake at my malloc() implementation, but I do not know what it is.
Is there another more elegant or generally better way to do it?

http://www.cplusplus.com/reference/clibrary/cstring/strtok/
Take a look at this, and use whitespace characters as the delimiter. If you need more hints let me know.
From the website:
char * strtok ( char * str, const char * delimiters );
On a first call, the function expects a C string as argument for str, whose first character is used as the starting location to scan for tokens. In subsequent calls, the function expects a null pointer and uses the position right after the end of last token as the new starting location for scanning.
Once the terminating null character of str is found in a call to strtok, all subsequent calls to this function (with a null pointer as the first argument) return a null pointer.
Parameters
str
C string to truncate.
Notice that this string is modified by being broken into smaller strings (tokens).
Alternativelly [sic], a null pointer may be specified, in which case the function continues scanning where a previous successful call to the function ended.
delimiters
C string containing the delimiter characters.
These may vary from one call to another.
Return Value
A pointer to the last token found in string.
A null pointer is returned if there are no tokens left to retrieve.
Example
/* strtok example */
#include <stdio.h>
#include <string.h>
int main ()
{
char str[] ="- This, a sample string.";
char * pch;
printf ("Splitting string \"%s\" into tokens:\n",str);
pch = strtok (str," ,.-");
while (pch != NULL)
{
printf ("%s\n",pch);
pch = strtok (NULL, " ,.-");
}
return 0;
}

For the fun of it here's an implementation based on the callback approach:
const char* find(const char* s,
const char* e,
int (*pred)(char))
{
while( s != e && !pred(*s) ) ++s;
return s;
}
void split_on_ws(const char* s,
const char* e,
void (*callback)(const char*, const char*))
{
const char* p = s;
while( s != e ) {
s = find(s, e, isspace);
callback(p, s);
p = s = find(s, e, isnotspace);
}
}
void handle_word(const char* s, const char* e)
{
// handle the word that starts at s and ends at e
}
int main()
{
split_on_ws(some_str, some_str + strlen(some_str), handle_word);
}

malloc(0) may (optionally) return NULL, depending on the implementation. Do you realize why you may be calling malloc(0)? Or more precisely, do you see where you are reading and writing beyond the size of your arrays?

Consider using strtok_r, as others have suggested, or something like:
void printWords(const char *string) {
// Make a local copy of the string that we can manipulate.
char * const copy = strdup(string);
char *space = copy;
// Find the next space in the string, and replace it with a newline.
while (space = strchr(space,' ')) *space = '\n';
// There are no more spaces in the string; print out our modified copy.
printf("%s\n", copy);
// Free our local copy
free(copy);
}

Something going wrong is get_words() always returning one less than the actual word count, so eventually you attempt to:
char *newbuff[words]; /* Words is one less than the actual number,
so this is declared to be too small. */
newbuff[count2] = (char *)malloc(strlen(buffer))
count2, eventually, is always one more than the number of elements you've declared for newbuff[]. Why malloc() isn't returning a valid ptr, though, I don't know.

You should be malloc'ing strlen(ptr), not strlen(buf). Also, your count2 should be limited to the number of words. When you get to the end of your string, you continue going over the zeros in your buffer and adding zero size strings to your array.

Just as an idea of a different style of string manipulation in C, here's an example which does not modify the source string, and does not use malloc. To find spaces I use the libc function strpbrk.
int print_words(const char *string, FILE *f)
{
static const char space_characters[] = " \t";
const char *next_space;
// Find the next space in the string
//
while ((next_space = strpbrk(string, space_characters)))
{
const char *p;
// If there are non-space characters between what we found
// and what we started from, print them.
//
if (next_space != string)
{
for (p=string; p<next_space; p++)
{
if(fputc(*p, f) == EOF)
{
return -1;
}
}
// Print a newline
//
if (fputc('\n', f) == EOF)
{
return -1;
}
}
// Advance next_space until we hit a non-space character
//
while (*next_space && strchr(space_characters, *next_space))
{
next_space++;
}
// Advance the string
//
string = next_space;
}
// Handle the case where there are no spaces left in the string
//
if (*string)
{
if (fprintf(f, "%s\n", string) < 0)
{
return -1;
}
}
return 0;
}

you can scan the char array looking for the token if you found it just print new line else print the char.
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int main()
{
char *s;
s = malloc(1024 * sizeof(char));
scanf("%[^\n]", s);
s = realloc(s, strlen(s) + 1);
int len = strlen(s);
char delim =' ';
for(int i = 0; i < len; i++) {
if(s[i] == delim) {
printf("\n");
}
else {
printf("%c", s[i]);
}
}
free(s);
return 0;
}

char arr[50];
gets(arr);
int c=0,i,l;
l=strlen(arr);
for(i=0;i<l;i++){
if(arr[i]==32){
printf("\n");
}
else
printf("%c",arr[i]);
}

Related

How to replace characters by strtok function - C?

I really want to change all spaces ' ' in my char array for NULL -
#include <string.h>
void ReplaceCharactersInString(char *pcString, char *cOldChar, char *cNewChar) {
char *p = strtok(pcString, cOldChar);
strcpy(pcString, p);
while (p != NULL) {
strcat(pcString, p);
p = strtok(cNewChar, cOldChar);
}
}
int main() {
char pcString[] = "I am testing";
ReplaceCharactersInString(pcString, " ", NULL);
printf(pcString);
}
OUTPUT: Iamtesting
If I simply put the printf(p) function before:
p = strtok(cNewChar, cOldChar);
In the result I have what I need - but the problem is how to store it in pcString (directly)?
Or there is maybe a better solution to simply do it?
While some functions expect a [single] string to be pre-parsed to: I\0am\0testing, that is rare.
And, if you have multiple spaces/delimiters, you'll get (e.g.) foo\0\0bar, which you probably don't want.
And, your printf in main will only print the first token in the string because it will stop on the first EOS (i.e. '\0').
(i.e.) You probably don't want strcpy/strcat.
More likely, you want to fill an array of char * pointers to the tokens you parse.
So, you'd want to pass down char **argv, then do: argv[argc++] = strtok(...); and then do: return argc
Here's how I would refactor your code:
#include <stdio.h>
#include <string.h>
#define ARGMAX 100
int
ReplaceCharactersInString(int argmax,char **argv,char *pcString,
const char *delim)
{
char *p;
int argc;
// allow space for NULL termination
--argmax;
for (argc = 0; argc < argmax; ++argc, ++argv) {
// get next token
p = strtok(pcString,delim);
if (p == NULL)
break;
// zap the buffer pointer
pcString = NULL;
// store the token in the [returned] array
*argv = p;
}
*argv = NULL;
return argc;
}
int
main(void)
{
char pcString[] = "I am testing";
int argc;
char **av;
char *argv[ARGMAX];
argc = ReplaceCharactersInString(ARGMAX,argv,pcString," ");
printf("argc: %d\n",argc);
for (av = argv; *av != NULL; ++av)
printf("'%s'\n",*av);
return 0;
}
Here's the output:
argc: 3
'I'
'am'
'testing'
strcat strcpy should not be used when the source and destination overlap in memory.
Iterate through the array and replace the matching character with the desired character.
Since zeros are part of the string, printf will stop at the first zero and strlen can't be used for the length to print. sizeof can be used as pcString is defined in the same scope.
Note that ReplaceCharactersInString would not work a second time as it would stop at the first zero. The function could be written to accept a length parameter and loop using the length.
#include <stdio.h>
#include <stdlib.h>
void ReplaceCharactersInString(char *pcString, char cOldChar,char cNewChar){
while ( pcString && *pcString) {//not NULL and not zero
if ( *pcString == cOldChar) {//match
*pcString = cNewChar;//replace
}
++pcString;//advance to next character
}
}
int main ( void) {
char pcString[] = "I am testing";
ReplaceCharactersInString ( pcString, ' ', '\0');
for ( int each = 0; each < sizeof pcString; ++each) {
printf ( "pcString[%02d] = int:%-4d char:%c\n", each, pcString[each], pcString[each]);
}
return 0;
}
You want to split the string into individual tokens separated by spaces such as "I\0am\0testing\0". You can use strtok() for this but this function is error prone. I suggest you allocate an array of pointers and make them point to the words. Note that splitting the source string is sloppy and does not allow for tokens to be adjacent such as in 1+1. You could allocate the strings instead.
Here is an example:
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
char **split_string(const char *str, char *delim) {
size_t i, len, count;
const char *p;
/* count tokens */
p = str;
p += strspn(p, delim); // skip initial delimiters
count = 0;
while (*p) {
count++;
p += strcspn(p, delim); // skip token
p += strspn(p, delim); // skip delimiters
}
/* allocate token array */
char **array = calloc(sizeof(*array, count + 1);
p = str;
p += strspn(p, delim); // skip initial delimiters
for (i = 0; i < count; i++) {
len = strcspn(p, delim); // token length
array[i] = strndup(p, len); // allocate a copy of the token
p += len; // skip token
p += strspn(p, delim); // skip delimiters
}
/* array ends with a null pointer */
array[count] = NULL;
return array;
}
int main() {
const char *pcString = "I am testing";
char **array = split_string(pcString, " \t\r\n");
for (size_t i = 0; array[i] != NULL; i++) {
printf("%zu: %s\n", i, array[i]);
}
return 0;
}
The strtok function pretty much does exactly what you want. It basically replaces the next delimiter with a '\0' character and returns the pointer to the current token. The next time you call strtok, you should pass a NULL argument (see the documentation for strtok) and it will point to the next token, which will again be delimited by '\0'. Read some more examples of correct strtok usage.

Searching an array for a specific character [duplicate]

I want to write a program in C that displays each word of a whole sentence (taken as input) at a seperate line. This is what I have done so far:
void manipulate(char *buffer);
int get_words(char *buffer);
int main(){
char buff[100];
printf("sizeof %d\nstrlen %d\n", sizeof(buff), strlen(buff)); // Debugging reasons
bzero(buff, sizeof(buff));
printf("Give me the text:\n");
fgets(buff, sizeof(buff), stdin);
manipulate(buff);
return 0;
}
int get_words(char *buffer){ // Function that gets the word count, by counting the spaces.
int count;
int wordcount = 0;
char ch;
for (count = 0; count < strlen(buffer); count ++){
ch = buffer[count];
if((isblank(ch)) || (buffer[count] == '\0')){ // if the character is blank, or null byte add 1 to the wordcounter
wordcount += 1;
}
}
printf("%d\n\n", wordcount);
return wordcount;
}
void manipulate(char *buffer){
int words = get_words(buffer);
char *newbuff[words];
char *ptr;
int count = 0;
int count2 = 0;
char ch = '\n';
ptr = buffer;
bzero(newbuff, sizeof(newbuff));
for (count = 0; count < 100; count ++){
ch = buffer[count];
if (isblank(ch) || buffer[count] == '\0'){
buffer[count] = '\0';
if((newbuff[count2] = (char *)malloc(strlen(buffer))) == NULL) {
printf("MALLOC ERROR!\n");
exit(-1);
}
strcpy(newbuff[count2], ptr);
printf("\n%s\n",newbuff[count2]);
ptr = &buffer[count + 1];
count2 ++;
}
}
}
Although the output is what I want, I have really many black spaces after the final word displayed, and the malloc() returns NULL so the MALLOC ERROR! is displayed in the end.
I can understand that there is a mistake at my malloc() implementation, but I do not know what it is.
Is there another more elegant or generally better way to do it?
http://www.cplusplus.com/reference/clibrary/cstring/strtok/
Take a look at this, and use whitespace characters as the delimiter. If you need more hints let me know.
From the website:
char * strtok ( char * str, const char * delimiters );
On a first call, the function expects a C string as argument for str, whose first character is used as the starting location to scan for tokens. In subsequent calls, the function expects a null pointer and uses the position right after the end of last token as the new starting location for scanning.
Once the terminating null character of str is found in a call to strtok, all subsequent calls to this function (with a null pointer as the first argument) return a null pointer.
Parameters
str
C string to truncate.
Notice that this string is modified by being broken into smaller strings (tokens).
Alternativelly [sic], a null pointer may be specified, in which case the function continues scanning where a previous successful call to the function ended.
delimiters
C string containing the delimiter characters.
These may vary from one call to another.
Return Value
A pointer to the last token found in string.
A null pointer is returned if there are no tokens left to retrieve.
Example
/* strtok example */
#include <stdio.h>
#include <string.h>
int main ()
{
char str[] ="- This, a sample string.";
char * pch;
printf ("Splitting string \"%s\" into tokens:\n",str);
pch = strtok (str," ,.-");
while (pch != NULL)
{
printf ("%s\n",pch);
pch = strtok (NULL, " ,.-");
}
return 0;
}
For the fun of it here's an implementation based on the callback approach:
const char* find(const char* s,
const char* e,
int (*pred)(char))
{
while( s != e && !pred(*s) ) ++s;
return s;
}
void split_on_ws(const char* s,
const char* e,
void (*callback)(const char*, const char*))
{
const char* p = s;
while( s != e ) {
s = find(s, e, isspace);
callback(p, s);
p = s = find(s, e, isnotspace);
}
}
void handle_word(const char* s, const char* e)
{
// handle the word that starts at s and ends at e
}
int main()
{
split_on_ws(some_str, some_str + strlen(some_str), handle_word);
}
malloc(0) may (optionally) return NULL, depending on the implementation. Do you realize why you may be calling malloc(0)? Or more precisely, do you see where you are reading and writing beyond the size of your arrays?
Consider using strtok_r, as others have suggested, or something like:
void printWords(const char *string) {
// Make a local copy of the string that we can manipulate.
char * const copy = strdup(string);
char *space = copy;
// Find the next space in the string, and replace it with a newline.
while (space = strchr(space,' ')) *space = '\n';
// There are no more spaces in the string; print out our modified copy.
printf("%s\n", copy);
// Free our local copy
free(copy);
}
Something going wrong is get_words() always returning one less than the actual word count, so eventually you attempt to:
char *newbuff[words]; /* Words is one less than the actual number,
so this is declared to be too small. */
newbuff[count2] = (char *)malloc(strlen(buffer))
count2, eventually, is always one more than the number of elements you've declared for newbuff[]. Why malloc() isn't returning a valid ptr, though, I don't know.
You should be malloc'ing strlen(ptr), not strlen(buf). Also, your count2 should be limited to the number of words. When you get to the end of your string, you continue going over the zeros in your buffer and adding zero size strings to your array.
Just as an idea of a different style of string manipulation in C, here's an example which does not modify the source string, and does not use malloc. To find spaces I use the libc function strpbrk.
int print_words(const char *string, FILE *f)
{
static const char space_characters[] = " \t";
const char *next_space;
// Find the next space in the string
//
while ((next_space = strpbrk(string, space_characters)))
{
const char *p;
// If there are non-space characters between what we found
// and what we started from, print them.
//
if (next_space != string)
{
for (p=string; p<next_space; p++)
{
if(fputc(*p, f) == EOF)
{
return -1;
}
}
// Print a newline
//
if (fputc('\n', f) == EOF)
{
return -1;
}
}
// Advance next_space until we hit a non-space character
//
while (*next_space && strchr(space_characters, *next_space))
{
next_space++;
}
// Advance the string
//
string = next_space;
}
// Handle the case where there are no spaces left in the string
//
if (*string)
{
if (fprintf(f, "%s\n", string) < 0)
{
return -1;
}
}
return 0;
}
you can scan the char array looking for the token if you found it just print new line else print the char.
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
int main()
{
char *s;
s = malloc(1024 * sizeof(char));
scanf("%[^\n]", s);
s = realloc(s, strlen(s) + 1);
int len = strlen(s);
char delim =' ';
for(int i = 0; i < len; i++) {
if(s[i] == delim) {
printf("\n");
}
else {
printf("%c", s[i]);
}
}
free(s);
return 0;
}
char arr[50];
gets(arr);
int c=0,i,l;
l=strlen(arr);
for(i=0;i<l;i++){
if(arr[i]==32){
printf("\n");
}
else
printf("%c",arr[i]);
}

In the C language, how do I divide a string up into substrings separated by a space character. [duplicate]

I have been trying to tokenize a string using SPACE as delimiter but it doesn't work. Does any one have suggestion on why it doesn't work?
Edit: tokenizing using:
strtok(string, " ");
The code is like the following
pch = strtok (str," ");
while (pch != NULL)
{
printf ("%s\n",pch);
pch = strtok (NULL, " ");
}
Do it like this:
char s[256];
strcpy(s, "one two three");
char* token = strtok(s, " ");
while (token) {
printf("token: %s\n", token);
token = strtok(NULL, " ");
}
Note: strtok modifies the string its tokenising, so it cannot be a const char*.
Here's an example of strtok usage, keep in mind that strtok is destructive of its input string (and therefore can't ever be used on a string constant
char *p = strtok(str, " ");
while(p != NULL) {
printf("%s\n", p);
p = strtok(NULL, " ");
}
Basically the thing to note is that passing a NULL as the first parameter to strtok tells it to get the next token from the string it was previously tokenizing.
strtok can be very dangerous. It is not thread safe. Its intended use is to be called over and over in a loop, passing in the output from the previous call. The strtok function has an internal variable that stores the state of the strtok call. This state is not unique to each thread - it is global. If any other code uses strtok in another thread, you get problems. Not the kind of problems you want to track down either!
I'd recommend looking for a regex implementation, or using sscanf to pull apart the string.
Try this:
char strprint[256];
char text[256];
strcpy(text, "My string to test");
while ( sscanf( text, "%s %s", strprint, text) > 0 ) {
printf("token: %s\n", strprint);
}
Note: The 'text' string is destroyed as it's separated. This may not be the preferred behaviour =)
You can simplify the code by introducing an extra variable.
#include <string.h>
#include <stdio.h>
int main()
{
char str[100], *s = str, *t = NULL;
strcpy(str, "a space delimited string");
while ((t = strtok(s, " ")) != NULL) {
s = NULL;
printf(":%s:\n", t);
}
return 0;
}
I've made some string functions in order to split values, by using less pointers as I could because this code is intended to run on PIC18F processors. Those processors does not handle really good with pointers when you have few free RAM available:
#include <stdio.h>
#include <string.h>
char POSTREQ[255] = "pwd=123456&apply=Apply&d1=88&d2=100&pwr=1&mpx=Internal&stmo=Stereo&proc=Processor&cmp=Compressor&ip1=192&ip2=168&ip3=10&ip4=131&gw1=192&gw2=168&gw3=10&gw4=192&pt=80&lic=&A=A";
int findchar(char *string, int Start, char C) {
while((string[Start] != 0)) { Start++; if(string[Start] == C) return Start; }
return -1;
}
int findcharn(char *string, int Times, char C) {
int i = 0, pos = 0, fnd = 0;
while(i < Times) {
fnd = findchar(string, pos, C);
if(fnd < 0) return -1;
if(fnd > 0) pos = fnd;
i++;
}
return fnd;
}
void mid(char *in, char *out, int start, int end) {
int i = 0;
int size = end - start;
for(i = 0; i < size; i++){
out[i] = in[start + i + 1];
}
out[size] = 0;
}
void getvalue(char *out, int index) {
mid(POSTREQ, out, findcharn(POSTREQ, index, '='), (findcharn(POSTREQ, index, '&') - 1));
}
void main() {
char n_pwd[7];
char n_d1[7];
getvalue(n_d1, 1);
printf("Value: %s\n", n_d1);
}
When reading the strtok documentation, I see you need to pass in a NULL pointer after the first "initializing" call. Maybe you didn't do that. Just a guess of course.
Here is another strtok() implementation, which has the ability to recognize consecutive delimiters (standard library's strtok() does not have this)
The function is a part of BSD licensed string library, called zString. You are more than welcome to contribute :)
https://github.com/fnoyanisi/zString
char *zstring_strtok(char *str, const char *delim) {
static char *static_str=0; /* var to store last address */
int index=0, strlength=0; /* integers for indexes */
int found = 0; /* check if delim is found */
/* delimiter cannot be NULL
* if no more char left, return NULL as well
*/
if (delim==0 || (str == 0 && static_str == 0))
return 0;
if (str == 0)
str = static_str;
/* get length of string */
while(str[strlength])
strlength++;
/* find the first occurance of delim */
for (index=0;index<strlength;index++)
if (str[index]==delim[0]) {
found=1;
break;
}
/* if delim is not contained in str, return str */
if (!found) {
static_str = 0;
return str;
}
/* check for consecutive delimiters
*if first char is delim, return delim
*/
if (str[0]==delim[0]) {
static_str = (str + 1);
return (char *)delim;
}
/* terminate the string
* this assignmetn requires char[], so str has to
* be char[] rather than *char
*/
str[index] = '\0';
/* save the rest of the string */
if ((str + index + 1)!=0)
static_str = (str + index + 1);
else
static_str = 0;
return str;
}
As mentioned in previous posts, since strtok(), or the one I implmented above, relies on a static *char variable to preserve the location of last delimiter between consecutive calls, extra care should be taken while dealing with multi-threaded aplications.
int not_in_delimiter(char c, char *delim){
while(*delim != '\0'){
if(c == *delim) return 0;
delim++;
}
return 1;
}
char *token_separater(char *source, char *delimiter, char **last){
char *begin, *next_token;
char *sbegin;
/*Get the start of the token */
if(source)
begin = source;
else
begin = *last;
sbegin = begin;
/*Scan through the string till we find character in delimiter. */
while(*begin != '\0' && not_in_delimiter(*begin, delimiter)){
begin++;
}
/* Check if we have reached at of the string */
if(*begin == '\0') {
/* We dont need to come further, hence return NULL*/
*last = NULL;
return sbegin;
}
/* Scan the string till we find a character which is not in delimiter */
next_token = begin;
while(next_token != '\0' && !not_in_delimiter(*next_token, delimiter)) {
next_token++;
}
/* If we have not reached at the end of the string */
if(*next_token != '\0'){
*last = next_token--;
*next_token = '\0';
return sbegin;
}
}
void main(){
char string[10] = "abcb_dccc";
char delim[10] = "_";
char *token = NULL;
char *last = "" ;
token = token_separater(string, delim, &last);
printf("%s\n", token);
while(last){
token = token_separater(NULL, delim, &last);
printf("%s\n", token);
}
}
You can read detail analysis at blog mentioned in my profile :)

Parsing input in C [duplicate]

I have been trying to tokenize a string using SPACE as delimiter but it doesn't work. Does any one have suggestion on why it doesn't work?
Edit: tokenizing using:
strtok(string, " ");
The code is like the following
pch = strtok (str," ");
while (pch != NULL)
{
printf ("%s\n",pch);
pch = strtok (NULL, " ");
}
Do it like this:
char s[256];
strcpy(s, "one two three");
char* token = strtok(s, " ");
while (token) {
printf("token: %s\n", token);
token = strtok(NULL, " ");
}
Note: strtok modifies the string its tokenising, so it cannot be a const char*.
Here's an example of strtok usage, keep in mind that strtok is destructive of its input string (and therefore can't ever be used on a string constant
char *p = strtok(str, " ");
while(p != NULL) {
printf("%s\n", p);
p = strtok(NULL, " ");
}
Basically the thing to note is that passing a NULL as the first parameter to strtok tells it to get the next token from the string it was previously tokenizing.
strtok can be very dangerous. It is not thread safe. Its intended use is to be called over and over in a loop, passing in the output from the previous call. The strtok function has an internal variable that stores the state of the strtok call. This state is not unique to each thread - it is global. If any other code uses strtok in another thread, you get problems. Not the kind of problems you want to track down either!
I'd recommend looking for a regex implementation, or using sscanf to pull apart the string.
Try this:
char strprint[256];
char text[256];
strcpy(text, "My string to test");
while ( sscanf( text, "%s %s", strprint, text) > 0 ) {
printf("token: %s\n", strprint);
}
Note: The 'text' string is destroyed as it's separated. This may not be the preferred behaviour =)
You can simplify the code by introducing an extra variable.
#include <string.h>
#include <stdio.h>
int main()
{
char str[100], *s = str, *t = NULL;
strcpy(str, "a space delimited string");
while ((t = strtok(s, " ")) != NULL) {
s = NULL;
printf(":%s:\n", t);
}
return 0;
}
I've made some string functions in order to split values, by using less pointers as I could because this code is intended to run on PIC18F processors. Those processors does not handle really good with pointers when you have few free RAM available:
#include <stdio.h>
#include <string.h>
char POSTREQ[255] = "pwd=123456&apply=Apply&d1=88&d2=100&pwr=1&mpx=Internal&stmo=Stereo&proc=Processor&cmp=Compressor&ip1=192&ip2=168&ip3=10&ip4=131&gw1=192&gw2=168&gw3=10&gw4=192&pt=80&lic=&A=A";
int findchar(char *string, int Start, char C) {
while((string[Start] != 0)) { Start++; if(string[Start] == C) return Start; }
return -1;
}
int findcharn(char *string, int Times, char C) {
int i = 0, pos = 0, fnd = 0;
while(i < Times) {
fnd = findchar(string, pos, C);
if(fnd < 0) return -1;
if(fnd > 0) pos = fnd;
i++;
}
return fnd;
}
void mid(char *in, char *out, int start, int end) {
int i = 0;
int size = end - start;
for(i = 0; i < size; i++){
out[i] = in[start + i + 1];
}
out[size] = 0;
}
void getvalue(char *out, int index) {
mid(POSTREQ, out, findcharn(POSTREQ, index, '='), (findcharn(POSTREQ, index, '&') - 1));
}
void main() {
char n_pwd[7];
char n_d1[7];
getvalue(n_d1, 1);
printf("Value: %s\n", n_d1);
}
When reading the strtok documentation, I see you need to pass in a NULL pointer after the first "initializing" call. Maybe you didn't do that. Just a guess of course.
Here is another strtok() implementation, which has the ability to recognize consecutive delimiters (standard library's strtok() does not have this)
The function is a part of BSD licensed string library, called zString. You are more than welcome to contribute :)
https://github.com/fnoyanisi/zString
char *zstring_strtok(char *str, const char *delim) {
static char *static_str=0; /* var to store last address */
int index=0, strlength=0; /* integers for indexes */
int found = 0; /* check if delim is found */
/* delimiter cannot be NULL
* if no more char left, return NULL as well
*/
if (delim==0 || (str == 0 && static_str == 0))
return 0;
if (str == 0)
str = static_str;
/* get length of string */
while(str[strlength])
strlength++;
/* find the first occurance of delim */
for (index=0;index<strlength;index++)
if (str[index]==delim[0]) {
found=1;
break;
}
/* if delim is not contained in str, return str */
if (!found) {
static_str = 0;
return str;
}
/* check for consecutive delimiters
*if first char is delim, return delim
*/
if (str[0]==delim[0]) {
static_str = (str + 1);
return (char *)delim;
}
/* terminate the string
* this assignmetn requires char[], so str has to
* be char[] rather than *char
*/
str[index] = '\0';
/* save the rest of the string */
if ((str + index + 1)!=0)
static_str = (str + index + 1);
else
static_str = 0;
return str;
}
As mentioned in previous posts, since strtok(), or the one I implmented above, relies on a static *char variable to preserve the location of last delimiter between consecutive calls, extra care should be taken while dealing with multi-threaded aplications.
int not_in_delimiter(char c, char *delim){
while(*delim != '\0'){
if(c == *delim) return 0;
delim++;
}
return 1;
}
char *token_separater(char *source, char *delimiter, char **last){
char *begin, *next_token;
char *sbegin;
/*Get the start of the token */
if(source)
begin = source;
else
begin = *last;
sbegin = begin;
/*Scan through the string till we find character in delimiter. */
while(*begin != '\0' && not_in_delimiter(*begin, delimiter)){
begin++;
}
/* Check if we have reached at of the string */
if(*begin == '\0') {
/* We dont need to come further, hence return NULL*/
*last = NULL;
return sbegin;
}
/* Scan the string till we find a character which is not in delimiter */
next_token = begin;
while(next_token != '\0' && !not_in_delimiter(*next_token, delimiter)) {
next_token++;
}
/* If we have not reached at the end of the string */
if(*next_token != '\0'){
*last = next_token--;
*next_token = '\0';
return sbegin;
}
}
void main(){
char string[10] = "abcb_dccc";
char delim[10] = "_";
char *token = NULL;
char *last = "" ;
token = token_separater(string, delim, &last);
printf("%s\n", token);
while(last){
token = token_separater(NULL, delim, &last);
printf("%s\n", token);
}
}
You can read detail analysis at blog mentioned in my profile :)

Tokenizing strings in C

I have been trying to tokenize a string using SPACE as delimiter but it doesn't work. Does any one have suggestion on why it doesn't work?
Edit: tokenizing using:
strtok(string, " ");
The code is like the following
pch = strtok (str," ");
while (pch != NULL)
{
printf ("%s\n",pch);
pch = strtok (NULL, " ");
}
Do it like this:
char s[256];
strcpy(s, "one two three");
char* token = strtok(s, " ");
while (token) {
printf("token: %s\n", token);
token = strtok(NULL, " ");
}
Note: strtok modifies the string its tokenising, so it cannot be a const char*.
Here's an example of strtok usage, keep in mind that strtok is destructive of its input string (and therefore can't ever be used on a string constant
char *p = strtok(str, " ");
while(p != NULL) {
printf("%s\n", p);
p = strtok(NULL, " ");
}
Basically the thing to note is that passing a NULL as the first parameter to strtok tells it to get the next token from the string it was previously tokenizing.
strtok can be very dangerous. It is not thread safe. Its intended use is to be called over and over in a loop, passing in the output from the previous call. The strtok function has an internal variable that stores the state of the strtok call. This state is not unique to each thread - it is global. If any other code uses strtok in another thread, you get problems. Not the kind of problems you want to track down either!
I'd recommend looking for a regex implementation, or using sscanf to pull apart the string.
Try this:
char strprint[256];
char text[256];
strcpy(text, "My string to test");
while ( sscanf( text, "%s %s", strprint, text) > 0 ) {
printf("token: %s\n", strprint);
}
Note: The 'text' string is destroyed as it's separated. This may not be the preferred behaviour =)
You can simplify the code by introducing an extra variable.
#include <string.h>
#include <stdio.h>
int main()
{
char str[100], *s = str, *t = NULL;
strcpy(str, "a space delimited string");
while ((t = strtok(s, " ")) != NULL) {
s = NULL;
printf(":%s:\n", t);
}
return 0;
}
I've made some string functions in order to split values, by using less pointers as I could because this code is intended to run on PIC18F processors. Those processors does not handle really good with pointers when you have few free RAM available:
#include <stdio.h>
#include <string.h>
char POSTREQ[255] = "pwd=123456&apply=Apply&d1=88&d2=100&pwr=1&mpx=Internal&stmo=Stereo&proc=Processor&cmp=Compressor&ip1=192&ip2=168&ip3=10&ip4=131&gw1=192&gw2=168&gw3=10&gw4=192&pt=80&lic=&A=A";
int findchar(char *string, int Start, char C) {
while((string[Start] != 0)) { Start++; if(string[Start] == C) return Start; }
return -1;
}
int findcharn(char *string, int Times, char C) {
int i = 0, pos = 0, fnd = 0;
while(i < Times) {
fnd = findchar(string, pos, C);
if(fnd < 0) return -1;
if(fnd > 0) pos = fnd;
i++;
}
return fnd;
}
void mid(char *in, char *out, int start, int end) {
int i = 0;
int size = end - start;
for(i = 0; i < size; i++){
out[i] = in[start + i + 1];
}
out[size] = 0;
}
void getvalue(char *out, int index) {
mid(POSTREQ, out, findcharn(POSTREQ, index, '='), (findcharn(POSTREQ, index, '&') - 1));
}
void main() {
char n_pwd[7];
char n_d1[7];
getvalue(n_d1, 1);
printf("Value: %s\n", n_d1);
}
When reading the strtok documentation, I see you need to pass in a NULL pointer after the first "initializing" call. Maybe you didn't do that. Just a guess of course.
Here is another strtok() implementation, which has the ability to recognize consecutive delimiters (standard library's strtok() does not have this)
The function is a part of BSD licensed string library, called zString. You are more than welcome to contribute :)
https://github.com/fnoyanisi/zString
char *zstring_strtok(char *str, const char *delim) {
static char *static_str=0; /* var to store last address */
int index=0, strlength=0; /* integers for indexes */
int found = 0; /* check if delim is found */
/* delimiter cannot be NULL
* if no more char left, return NULL as well
*/
if (delim==0 || (str == 0 && static_str == 0))
return 0;
if (str == 0)
str = static_str;
/* get length of string */
while(str[strlength])
strlength++;
/* find the first occurance of delim */
for (index=0;index<strlength;index++)
if (str[index]==delim[0]) {
found=1;
break;
}
/* if delim is not contained in str, return str */
if (!found) {
static_str = 0;
return str;
}
/* check for consecutive delimiters
*if first char is delim, return delim
*/
if (str[0]==delim[0]) {
static_str = (str + 1);
return (char *)delim;
}
/* terminate the string
* this assignmetn requires char[], so str has to
* be char[] rather than *char
*/
str[index] = '\0';
/* save the rest of the string */
if ((str + index + 1)!=0)
static_str = (str + index + 1);
else
static_str = 0;
return str;
}
As mentioned in previous posts, since strtok(), or the one I implmented above, relies on a static *char variable to preserve the location of last delimiter between consecutive calls, extra care should be taken while dealing with multi-threaded aplications.
int not_in_delimiter(char c, char *delim){
while(*delim != '\0'){
if(c == *delim) return 0;
delim++;
}
return 1;
}
char *token_separater(char *source, char *delimiter, char **last){
char *begin, *next_token;
char *sbegin;
/*Get the start of the token */
if(source)
begin = source;
else
begin = *last;
sbegin = begin;
/*Scan through the string till we find character in delimiter. */
while(*begin != '\0' && not_in_delimiter(*begin, delimiter)){
begin++;
}
/* Check if we have reached at of the string */
if(*begin == '\0') {
/* We dont need to come further, hence return NULL*/
*last = NULL;
return sbegin;
}
/* Scan the string till we find a character which is not in delimiter */
next_token = begin;
while(next_token != '\0' && !not_in_delimiter(*next_token, delimiter)) {
next_token++;
}
/* If we have not reached at the end of the string */
if(*next_token != '\0'){
*last = next_token--;
*next_token = '\0';
return sbegin;
}
}
void main(){
char string[10] = "abcb_dccc";
char delim[10] = "_";
char *token = NULL;
char *last = "" ;
token = token_separater(string, delim, &last);
printf("%s\n", token);
while(last){
token = token_separater(NULL, delim, &last);
printf("%s\n", token);
}
}
You can read detail analysis at blog mentioned in my profile :)

Resources