Remove first few characters from a string - c

I need to remove the first 3 characters from an array without any libraries. How would I go about doing this? I know that I can use memmove but I'm working on a system without the standard library, also memmove is for pointers. With memmove I can do this:
void chopN(char *str, size_t n)
{
assert(n != 0 && str != 0);
size_t len = strlen(str);
if (n > len)
return; // Or: n = len;
memmove(str, str+n, len - n + 1);
}
But could I remove characters from an array without memmove or any other standard library functions?

As long as you know the string is at least 3 characters long, you can simply use str + 3.

Hmmm: 2 simple while loops should do it.
Some untested code to give you an idea.
void chopN(char *str, size_t n) {
char *dest = str;
// find beginning watching out for rump `str`
while (*str && n--) {
str++;
}
// Copy byte by byte
while (*src) {
*dest++ = *src++;
}
*dest = '\0';
}
Could add a if (n==0) short-cut if desired.

Here is a function that does not use standard C string functions. n can be less then or equal to strlen( s ). Otherwise the function does nothing.
#include <stdio.h>
char * chopN( char *s, size_t n )
{
char *src = s;
while ( *src && n ) --n, ++src;
if ( n == 0 && src != s )
{
for ( char *dst = s; ( *dst++ = *src++ ); );
}
return s;
}
int main(void)
{
char s[] = "Hello, World";
puts( s );
puts( chopN( s, 7 ) );
return 0;
}
The program output is
Hello, World
World
If you want that in case when n is greater than strlen( s ) all characters were removed then it is enough to substituted the if statement
if ( n == 0 && src != s )
for this one
if ( src != s )

Simply start at the new start (str+n) and copy to the old start char by char until you reach the end of the string:
char *str1;
for(str1 = str+n; *str1; *str++=*str1++)
;
*str = 0;
If you want something more powerful, you can e.g., steal a memmove implementation from http://git.musl-libc.org/cgit/musl/tree/src/string/memmove.c (it basically does the same thing, except with some performance tweaks and a decision on which way (left/right) the move goes).

You don't need to pass the "amount" of characters as a parameter, you can search for '\0':
void chopN(char *str, size_t n){
char *aux;
int i=0,j=0;
while(str[i]!='\0'){
if(i>n+1){
aux[j++]=str[i++];
}else i++;
}
aux[j]='\0';
str = aux;
}

Related

Deleting extra spaces in a string - C [duplicate]

Is there a clean, preferably standard method of trimming leading and trailing whitespace from a string in C? I'd roll my own, but I would think this is a common problem with an equally common solution.
If you can modify the string:
// Note: This function returns a pointer to a substring of the original string.
// If the given string was allocated dynamically, the caller must not overwrite
// that pointer with the returned value, since the original pointer must be
// deallocated using the same allocator with which it was allocated. The return
// value must NOT be deallocated using free() etc.
char *trimwhitespace(char *str)
{
char *end;
// Trim leading space
while(isspace((unsigned char)*str)) str++;
if(*str == 0) // All spaces?
return str;
// Trim trailing space
end = str + strlen(str) - 1;
while(end > str && isspace((unsigned char)*end)) end--;
// Write new null terminator character
end[1] = '\0';
return str;
}
If you can't modify the string, then you can use basically the same method:
// Stores the trimmed input string into the given output buffer, which must be
// large enough to store the result. If it is too small, the output is
// truncated.
size_t trimwhitespace(char *out, size_t len, const char *str)
{
if(len == 0)
return 0;
const char *end;
size_t out_size;
// Trim leading space
while(isspace((unsigned char)*str)) str++;
if(*str == 0) // All spaces?
{
*out = 0;
return 1;
}
// Trim trailing space
end = str + strlen(str) - 1;
while(end > str && isspace((unsigned char)*end)) end--;
end++;
// Set output size to minimum of trimmed string length and buffer size minus 1
out_size = (end - str) < len-1 ? (end - str) : len-1;
// Copy trimmed string and add null terminator
memcpy(out, str, out_size);
out[out_size] = 0;
return out_size;
}
Here's one that shifts the string into the first position of your buffer. You might want this behavior so that if you dynamically allocated the string, you can still free it on the same pointer that trim() returns:
char *trim(char *str)
{
size_t len = 0;
char *frontp = str;
char *endp = NULL;
if( str == NULL ) { return NULL; }
if( str[0] == '\0' ) { return str; }
len = strlen(str);
endp = str + len;
/* Move the front and back pointers to address the first non-whitespace
* characters from each end.
*/
while( isspace((unsigned char) *frontp) ) { ++frontp; }
if( endp != frontp )
{
while( isspace((unsigned char) *(--endp)) && endp != frontp ) {}
}
if( frontp != str && endp == frontp )
*str = '\0';
else if( str + len - 1 != endp )
*(endp + 1) = '\0';
/* Shift the string so that it starts at str so that if it's dynamically
* allocated, we can still free it on the returned pointer. Note the reuse
* of endp to mean the front of the string buffer now.
*/
endp = str;
if( frontp != str )
{
while( *frontp ) { *endp++ = *frontp++; }
*endp = '\0';
}
return str;
}
Test for correctness:
#include <stdio.h>
#include <string.h>
#include <ctype.h>
/* Paste function from above here. */
int main()
{
/* The test prints the following:
[nothing to trim] -> [nothing to trim]
[ trim the front] -> [trim the front]
[trim the back ] -> [trim the back]
[ trim front and back ] -> [trim front and back]
[ trim one char front and back ] -> [trim one char front and back]
[ trim one char front] -> [trim one char front]
[trim one char back ] -> [trim one char back]
[ ] -> []
[ ] -> []
[a] -> [a]
[] -> []
*/
char *sample_strings[] =
{
"nothing to trim",
" trim the front",
"trim the back ",
" trim front and back ",
" trim one char front and back ",
" trim one char front",
"trim one char back ",
" ",
" ",
"a",
"",
NULL
};
char test_buffer[64];
char comparison_buffer[64];
size_t index, compare_pos;
for( index = 0; sample_strings[index] != NULL; ++index )
{
// Fill buffer with known value to verify we do not write past the end of the string.
memset( test_buffer, 0xCC, sizeof(test_buffer) );
strcpy( test_buffer, sample_strings[index] );
memcpy( comparison_buffer, test_buffer, sizeof(comparison_buffer));
printf("[%s] -> [%s]\n", sample_strings[index],
trim(test_buffer));
for( compare_pos = strlen(comparison_buffer);
compare_pos < sizeof(comparison_buffer);
++compare_pos )
{
if( test_buffer[compare_pos] != comparison_buffer[compare_pos] )
{
printf("Unexpected change to buffer # index %u: %02x (expected %02x)\n",
compare_pos, (unsigned char) test_buffer[compare_pos], (unsigned char) comparison_buffer[compare_pos]);
}
}
}
return 0;
}
Source file was trim.c. Compiled with 'cc -Wall trim.c -o trim'.
My solution. String must be changeable. The advantage above some of the other solutions that it moves the non-space part to the beginning so you can keep using the old pointer, in case you have to free() it later.
void trim(char * s) {
char * p = s;
int l = strlen(p);
while(isspace(p[l - 1])) p[--l] = 0;
while(* p && isspace(* p)) ++p, --l;
memmove(s, p, l + 1);
}
This version creates a copy of the string with strndup() instead of editing it in place. strndup() requires _GNU_SOURCE, so maybe you need to make your own strndup() with malloc() and strncpy().
char * trim(char * s) {
int l = strlen(s);
while(isspace(s[l - 1])) --l;
while(* s && isspace(* s)) ++s, --l;
return strndup(s, l);
}
Here's my C mini library for trimming left, right, both, all, in place and separate, and trimming a set of specified characters (or white space by default).
contents of strlib.h:
#ifndef STRLIB_H_
#define STRLIB_H_ 1
enum strtrim_mode_t {
STRLIB_MODE_ALL = 0,
STRLIB_MODE_RIGHT = 0x01,
STRLIB_MODE_LEFT = 0x02,
STRLIB_MODE_BOTH = 0x03
};
char *strcpytrim(char *d, // destination
char *s, // source
int mode,
char *delim
);
char *strtriml(char *d, char *s);
char *strtrimr(char *d, char *s);
char *strtrim(char *d, char *s);
char *strkill(char *d, char *s);
char *triml(char *s);
char *trimr(char *s);
char *trim(char *s);
char *kill(char *s);
#endif
contents of strlib.c:
#include <strlib.h>
char *strcpytrim(char *d, // destination
char *s, // source
int mode,
char *delim
) {
char *o = d; // save orig
char *e = 0; // end space ptr.
char dtab[256] = {0};
if (!s || !d) return 0;
if (!delim) delim = " \t\n\f";
while (*delim)
dtab[*delim++] = 1;
while ( (*d = *s++) != 0 ) {
if (!dtab[0xFF & (unsigned int)*d]) { // Not a match char
e = 0; // Reset end pointer
} else {
if (!e) e = d; // Found first match.
if ( mode == STRLIB_MODE_ALL || ((mode != STRLIB_MODE_RIGHT) && (d == o)) )
continue;
}
d++;
}
if (mode != STRLIB_MODE_LEFT && e) { // for everything but trim_left, delete trailing matches.
*e = 0;
}
return o;
}
// perhaps these could be inlined in strlib.h
char *strtriml(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_LEFT, 0); }
char *strtrimr(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_RIGHT, 0); }
char *strtrim(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_BOTH, 0); }
char *strkill(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_ALL, 0); }
char *triml(char *s) { return strcpytrim(s, s, STRLIB_MODE_LEFT, 0); }
char *trimr(char *s) { return strcpytrim(s, s, STRLIB_MODE_RIGHT, 0); }
char *trim(char *s) { return strcpytrim(s, s, STRLIB_MODE_BOTH, 0); }
char *kill(char *s) { return strcpytrim(s, s, STRLIB_MODE_ALL, 0); }
The one main routine does it all.
It trims in place if src == dst, otherwise,
it works like the strcpy routines.
It trims a set of characters specified in the string delim, or white space if null.
It trims left, right, both, and all (like tr).
There is not much to it, and it iterates over the string only once. Some folks might complain that trim right starts on the left, however, no strlen is needed which starts on the left anyway. (One way or another you have to get to the end of the string for right trims, so you might as well do the work as you go.) There may be arguments to be made about pipelining and cache sizes and such -- who knows. Since the solution works from left to right and iterates only once, it can be expanded to work on streams as well. Limitations: it does not work on unicode strings.
Here is my attempt at a simple, yet correct in-place trim function.
void trim(char *str)
{
int i;
int begin = 0;
int end = strlen(str) - 1;
while (isspace((unsigned char) str[begin]))
begin++;
while ((end >= begin) && isspace((unsigned char) str[end]))
end--;
// Shift all characters back to the start of the string array.
for (i = begin; i <= end; i++)
str[i - begin] = str[i];
str[i - begin] = '\0'; // Null terminate string.
}
Late to the trim party
Features:
1. Trim the beginning quickly, as in a number of other answers.
2. After going to the end, trimming the right with only 1 test per loop. Like #jfm3, but works for an all white-space string)
3. To avoid undefined behavior when char is a signed char, cast *s to unsigned char.
Character handling "In all cases the argument is an int, the value of which shall be representable as an unsigned char or shall equal the value of the macro EOF. If the argument has any other value, the behavior is undefined." C11 §7.4 1
#include <ctype.h>
// Return a pointer to the trimmed string
char *string_trim_inplace(char *s) {
while (isspace((unsigned char) *s)) s++;
if (*s) {
char *p = s;
while (*p) p++;
while (isspace((unsigned char) *(--p)));
p[1] = '\0';
}
// If desired, shift the trimmed string
return s;
}
#chqrlie commented the above does not shift the trimmed string. To do so....
// Return a pointer to the (shifted) trimmed string
char *string_trim_inplace(char *s) {
char *original = s;
size_t len = 0;
while (isspace((unsigned char) *s)) {
s++;
}
if (*s) {
char *p = s;
while (*p) p++;
while (isspace((unsigned char) *(--p)));
p[1] = '\0';
// len = (size_t) (p - s); // older errant code
len = (size_t) (p - s + 1); // Thanks to #theriver
}
return (s == original) ? s : memmove(original, s, len + 1);
}
Here's a solution similar to #adam-rosenfields in-place modification routine but without needlessly resorting to strlen(). Like #jkramer, the string is left-adjusted within the buffer so you can free the same pointer. Not optimal for large strings since it does not use memmove. Includes the ++/-- operators that #jfm3 mentions. FCTX-based unit tests included.
#include <ctype.h>
void trim(char * const a)
{
char *p = a, *q = a;
while (isspace(*q)) ++q;
while (*q) *p++ = *q++;
*p = '\0';
while (p > a && isspace(*--p)) *p = '\0';
}
/* See http://fctx.wildbearsoftware.com/ */
#include "fct.h"
FCT_BGN()
{
FCT_QTEST_BGN(trim)
{
{ char s[] = ""; trim(s); fct_chk_eq_str("", s); } // Trivial
{ char s[] = " "; trim(s); fct_chk_eq_str("", s); } // Trivial
{ char s[] = "\t"; trim(s); fct_chk_eq_str("", s); } // Trivial
{ char s[] = "a"; trim(s); fct_chk_eq_str("a", s); } // NOP
{ char s[] = "abc"; trim(s); fct_chk_eq_str("abc", s); } // NOP
{ char s[] = " a"; trim(s); fct_chk_eq_str("a", s); } // Leading
{ char s[] = " a c"; trim(s); fct_chk_eq_str("a c", s); } // Leading
{ char s[] = "a "; trim(s); fct_chk_eq_str("a", s); } // Trailing
{ char s[] = "a c "; trim(s); fct_chk_eq_str("a c", s); } // Trailing
{ char s[] = " a "; trim(s); fct_chk_eq_str("a", s); } // Both
{ char s[] = " a c "; trim(s); fct_chk_eq_str("a c", s); } // Both
// Villemoes pointed out an edge case that corrupted memory. Thank you.
// http://stackoverflow.com/questions/122616/#comment23332594_4505533
{
char s[] = "a "; // Buffer with whitespace before s + 2
trim(s + 2); // Trim " " containing only whitespace
fct_chk_eq_str("", s + 2); // Ensure correct result from the trim
fct_chk_eq_str("a ", s); // Ensure preceding buffer not mutated
}
// doukremt suggested I investigate this test case but
// did not indicate the specific behavior that was objectionable.
// http://stackoverflow.com/posts/comments/33571430
{
char s[] = " foobar"; // Shifted across whitespace
trim(s); // Trim
fct_chk_eq_str("foobar", s); // Leading string is correct
// Here is what the algorithm produces:
char r[16] = { 'f', 'o', 'o', 'b', 'a', 'r', '\0', ' ',
' ', 'f', 'o', 'o', 'b', 'a', 'r', '\0'};
fct_chk_eq_int(0, memcmp(s, r, sizeof(s)));
}
}
FCT_QTEST_END();
}
FCT_END();
I'm not sure what you consider "painless."
C strings are pretty painful. We can find the first non-whitespace character position trivially:
while (isspace(* p)) p++;
We can find the last non-whitespace character position with two similar trivial moves:
while (* q) q++;
do { q--; } while (isspace(* q));
(I have spared you the pain of using the * and ++ operators at the same time.)
The question now is what do you do with this? The datatype at hand isn't really a big robust abstract String that is easy to think about, but instead really barely any more than an array of storage bytes. Lacking a robust data type, it is impossible to write a function that will do the same as PHperytonby's chomp function. What would such a function in C return?
Another one, with one line doing the real job:
#include <stdio.h>
int main()
{
const char *target = " haha ";
char buf[256];
sscanf(target, "%s", buf); // Trimming on both sides occurs here
printf("<%s>\n", buf);
}
If you're using glib, then you can use g_strstrip
I didn't like most of these answers because they did one or more of the following...
Returned a different pointer inside the original pointer's string (kind of a pain to juggle two different pointers to the same thing).
Made gratuitous use of things like strlen() that pre-iterate the entire string.
Used non-portable OS-specific lib functions.
Backscanned.
Used comparison to ' ' instead of isspace() so that TAB / CR / LF are preserved.
Wasted memory with large static buffers.
Wasted cycles with high-cost functions like sscanf/sprintf.
Here is my version:
void fnStrTrimInPlace(char *szWrite) {
const char *szWriteOrig = szWrite;
char *szLastSpace = szWrite, *szRead = szWrite;
int bNotSpace;
// SHIFT STRING, STARTING AT FIRST NON-SPACE CHAR, LEFTMOST
while( *szRead != '\0' ) {
bNotSpace = !isspace((unsigned char)(*szRead));
if( (szWrite != szWriteOrig) || bNotSpace ) {
*szWrite = *szRead;
szWrite++;
// TRACK POINTER TO LAST NON-SPACE
if( bNotSpace )
szLastSpace = szWrite;
}
szRead++;
}
// TERMINATE AFTER LAST NON-SPACE (OR BEGINNING IF THERE WAS NO NON-SPACE)
*szLastSpace = '\0';
}
Use a string library, for instance:
Ustr *s1 = USTR1(\7, " 12345 ");
ustr_sc_trim_cstr(&s1, " ");
assert(ustr_cmp_cstr_eq(s1, "12345"));
...as you say this is a "common" problem, yes you need to include a #include or so and it's not included in libc but don't go inventing your own hack job storing random pointers and size_t's that way only leads to buffer overflows.
A bit late to the game, but I'll throw my routines into the fray. They're probably not the most absolute efficient, but I believe they're correct and they're simple (with rtrim() pushing the complexity envelope):
#include <ctype.h>
#include <string.h>
/*
Public domain implementations of in-place string trim functions
Michael Burr
michael.burr#nth-element.com
2010
*/
char* ltrim(char* s)
{
char* newstart = s;
while (isspace( *newstart)) {
++newstart;
}
// newstart points to first non-whitespace char (which might be '\0')
memmove( s, newstart, strlen( newstart) + 1); // don't forget to move the '\0' terminator
return s;
}
char* rtrim( char* s)
{
char* end = s + strlen( s);
// find the last non-whitespace character
while ((end != s) && isspace( *(end-1))) {
--end;
}
// at this point either (end == s) and s is either empty or all whitespace
// so it needs to be made empty, or
// end points just past the last non-whitespace character (it might point
// at the '\0' terminator, in which case there's no problem writing
// another there).
*end = '\0';
return s;
}
char* trim( char* s)
{
return rtrim( ltrim( s));
}
Very late to the party...
Single-pass forward-scanning solution with no backtracking. Every character in the source string is tested exactly once twice. (So it should be faster than most of the other solutions here, especially if the source string has a lot of trailing spaces.)
This includes two solutions, one to copy and trim a source string into another destination string, and the other to trim the source string in place. Both functions use the same code.
The (modifiable) string is moved in-place, so the original pointer to it remains unchanged.
#include <stddef.h>
#include <ctype.h>
char * trim2(char *d, const char *s)
{
// Sanity checks
if (s == NULL || d == NULL)
return NULL;
// Skip leading spaces
const unsigned char * p = (const unsigned char *)s;
while (isspace(*p))
p++;
// Copy the string
unsigned char * dst = (unsigned char *)d; // d and s can be the same
unsigned char * end = dst;
while (*p != '\0')
{
if (!isspace(*dst++ = *p++))
end = dst;
}
// Truncate trailing spaces
*end = '\0';
return d;
}
char * trim(char *s)
{
return trim2(s, s);
}
Just to keep this growing, one more option with a modifiable string:
void trimString(char *string)
{
size_t i = 0, j = strlen(string);
while (j > 0 && isspace((unsigned char)string[j - 1])) string[--j] = '\0';
while (isspace((unsigned char)string[i])) i++;
if (i > 0) memmove(string, string + i, j - i + 1);
}
I know there have many answers, but I post my answer here to see if my solution is good enough.
// Trims leading whitespace chars in left `str`, then copy at almost `n - 1` chars
// into the `out` buffer in which copying might stop when the first '\0' occurs,
// and finally append '\0' to the position of the last non-trailing whitespace char.
// Reture the length the trimed string which '\0' is not count in like strlen().
size_t trim(char *out, size_t n, const char *str)
{
// do nothing
if(n == 0) return 0;
// ptr stop at the first non-leading space char
while(isspace(*str)) str++;
if(*str == '\0') {
out[0] = '\0';
return 0;
}
size_t i = 0;
// copy char to out until '\0' or i == n - 1
for(i = 0; i < n - 1 && *str != '\0'; i++){
out[i] = *str++;
}
// deal with the trailing space
while(isspace(out[--i]));
out[++i] = '\0';
return i;
}
The easiest way to skip leading spaces in a string is, imho,
#include <stdio.h>
int main()
{
char *foo=" teststring ";
char *bar;
sscanf(foo,"%s",bar);
printf("String is >%s<\n",bar);
return 0;
}
Ok this is my take on the question. I believe it's the most concise solution that modifies the string in place (free will work) and avoids any UB. For small strings, it's probably faster than a solution involving memmove.
void stripWS_LT(char *str)
{
char *a = str, *b = str;
while (isspace((unsigned char)*a)) a++;
while (*b = *a++) b++;
while (b > str && isspace((unsigned char)*--b)) *b = 0;
}
#include <ctype.h>
#include <string.h>
char *trim_space(char *in)
{
char *out = NULL;
int len;
if (in) {
len = strlen(in);
while(len && isspace(in[len - 1])) --len;
while(len && *in && isspace(*in)) ++in, --len;
if (len) {
out = strndup(in, len);
}
}
return out;
}
isspace helps to trim all white spaces.
Run a first loop to check from last byte for space character and reduce the length variable
Run a second loop to check from first byte for space character and reduce the length variable and increment char pointer.
Finally if length variable is more than 0, then use strndup to create new string buffer by excluding spaces.
This one is short and simple, uses for-loops and doesn't overwrite the string boundaries.
You can replace the test with isspace() if needed.
void trim (char *s) // trim leading and trailing spaces+tabs
{
int i,j,k, len;
j=k=0;
len = strlen(s);
// find start of string
for (i=0; i<len; i++) if ((s[i]!=32) && (s[i]!=9)) { j=i; break; }
// find end of string+1
for (i=len-1; i>=j; i--) if ((s[i]!=32) && (s[i]!=9)) { k=i+1; break;}
if (k<=j) {s[0]=0; return;} // all whitespace (j==k==0)
len=k-j;
for (i=0; i<len; i++) s[i] = s[j++]; // shift result to start of string
s[i]=0; // end the string
}//_trim
If, and ONLY IF there's only one contiguous block of text between whitespace, you can use a single call to strtok(3), like so:
char *trimmed = strtok(input, "\r\t\n ");
This works for strings like the following:
" +1.123.456.7890 "
" 01-01-2020\n"
"\t2.523"
This will not work for strings that contain whitespace between blocks of non-whitespace, like " hi there ". It's probably better to avoid this approach, but now it's here in your toolbox if you need it.
Personally, I'd roll my own. You can use strtok, but you need to take care with doing so (particularly if you're removing leading characters) that you know what memory is what.
Getting rid of trailing spaces is easy, and pretty safe, as you can just put a 0 in over the top of the last space, counting back from the end. Getting rid of leading spaces means moving things around. If you want to do it in place (probably sensible) you can just keep shifting everything back one character until there's no leading space. Or, to be more efficient, you could find the index of the first non-space character, and shift everything back by that number. Or, you could just use a pointer to the first non-space character (but then you need to be careful in the same way as you do with strtok).
#include "stdafx.h"
#include "malloc.h"
#include "string.h"
int main(int argc, char* argv[])
{
char *ptr = (char*)malloc(sizeof(char)*30);
strcpy(ptr," Hel lo wo rl d G eo rocks!!! by shahil sucks b i g tim e");
int i = 0, j = 0;
while(ptr[j]!='\0')
{
if(ptr[j] == ' ' )
{
j++;
ptr[i] = ptr[j];
}
else
{
i++;
j++;
ptr[i] = ptr[j];
}
}
printf("\noutput-%s\n",ptr);
return 0;
}
Most of the answers so far do one of the following:
Backtrack at the end of the string (i.e. find the end of the string and then seek backwards until a non-space character is found,) or
Call strlen() first, making a second pass through the whole string.
This version makes only one pass and does not backtrack. Hence it may perform better than the others, though only if it is common to have hundreds of trailing spaces (which is not unusual when dealing with the output of a SQL query.)
static char const WHITESPACE[] = " \t\n\r";
static void get_trim_bounds(char const *s,
char const **firstWord,
char const **trailingSpace)
{
char const *lastWord;
*firstWord = lastWord = s + strspn(s, WHITESPACE);
do
{
*trailingSpace = lastWord + strcspn(lastWord, WHITESPACE);
lastWord = *trailingSpace + strspn(*trailingSpace, WHITESPACE);
}
while (*lastWord != '\0');
}
char *copy_trim(char const *s)
{
char const *firstWord, *trailingSpace;
char *result;
size_t newLength;
get_trim_bounds(s, &firstWord, &trailingSpace);
newLength = trailingSpace - firstWord;
result = malloc(newLength + 1);
memcpy(result, firstWord, newLength);
result[newLength] = '\0';
return result;
}
void inplace_trim(char *s)
{
char const *firstWord, *trailingSpace;
size_t newLength;
get_trim_bounds(s, &firstWord, &trailingSpace);
newLength = trailingSpace - firstWord;
memmove(s, firstWord, newLength);
s[newLength] = '\0';
}
This is the shortest possible implementation I can think of:
static const char *WhiteSpace=" \n\r\t";
char* trim(char *t)
{
char *e=t+(t!=NULL?strlen(t):0); // *e initially points to end of string
if (t==NULL) return;
do --e; while (strchr(WhiteSpace, *e) && e>=t); // Find last char that is not \r\n\t
*(++e)=0; // Null-terminate
e=t+strspn (t,WhiteSpace); // Find first char that is not \t
return e>t?memmove(t,e,strlen(e)+1):t; // memmove string contents and terminator
}
These functions will modify the original buffer, so if dynamically allocated, the original
pointer can be freed.
#include <string.h>
void rstrip(char *string)
{
int l;
if (!string)
return;
l = strlen(string) - 1;
while (isspace(string[l]) && l >= 0)
string[l--] = 0;
}
void lstrip(char *string)
{
int i, l;
if (!string)
return;
l = strlen(string);
while (isspace(string[(i = 0)]))
while(i++ < l)
string[i-1] = string[i];
}
void strip(char *string)
{
lstrip(string);
rstrip(string);
}
What do you think about using StrTrim function defined in header Shlwapi.h.? It is straight forward rather defining on your own.
Details can be found on:
http://msdn.microsoft.com/en-us/library/windows/desktop/bb773454(v=vs.85).aspx
If you have
char ausCaptain[]="GeorgeBailey ";
StrTrim(ausCaptain," ");
This will give ausCaptain as "GeorgeBailey" not "GeorgeBailey ".
To trim my strings from the both sides I use the oldie but the gooody ;)
It can trim anything with ascii less than a space, meaning that the control chars will be trimmed also !
char *trimAll(char *strData)
{
unsigned int L = strlen(strData);
if(L > 0){ L--; }else{ return strData; }
size_t S = 0, E = L;
while((!(strData[S] > ' ') || !(strData[E] > ' ')) && (S >= 0) && (S <= L) && (E >= 0) && (E <= L))
{
if(strData[S] <= ' '){ S++; }
if(strData[E] <= ' '){ E--; }
}
if(S == 0 && E == L){ return strData; } // Nothing to be done
if((S >= 0) && (S <= L) && (E >= 0) && (E <= L)){
L = E - S + 1;
memmove(strData,&strData[S],L); strData[L] = '\0';
}else{ strData[0] = '\0'; }
return strData;
}
I'm only including code because the code posted so far seems suboptimal (and I don't have the rep to comment yet.)
void inplace_trim(char* s)
{
int start, end = strlen(s);
for (start = 0; isspace(s[start]); ++start) {}
if (s[start]) {
while (end > 0 && isspace(s[end-1]))
--end;
memmove(s, &s[start], end - start);
}
s[end - start] = '\0';
}
char* copy_trim(const char* s)
{
int start, end;
for (start = 0; isspace(s[start]); ++start) {}
for (end = strlen(s); end > 0 && isspace(s[end-1]); --end) {}
return strndup(s + start, end - start);
}
strndup() is a GNU extension. If you don't have it or something equivalent, roll your own. For example:
r = strdup(s + start);
r[end-start] = '\0';
Here i use the dynamic memory allocation to trim the input string to the function trimStr. First, we find how many non-empty characters exist in the input string. Then, we allocate a character array with that size and taking care of the null terminated character. When we use this function, we need to free the memory inside of main function.
#include<stdio.h>
#include<stdlib.h>
char *trimStr(char *str){
char *tmp = str;
printf("input string %s\n",str);
int nc = 0;
while(*tmp!='\0'){
if (*tmp != ' '){
nc++;
}
tmp++;
}
printf("total nonempty characters are %d\n",nc);
char *trim = NULL;
trim = malloc(sizeof(char)*(nc+1));
if (trim == NULL) return NULL;
tmp = str;
int ne = 0;
while(*tmp!='\0'){
if (*tmp != ' '){
trim[ne] = *tmp;
ne++;
}
tmp++;
}
trim[nc] = '\0';
printf("trimmed string is %s\n",trim);
return trim;
}
int main(void){
char str[] = " s ta ck ove r fl o w ";
char *trim = trimStr(str);
if (trim != NULL )free(trim);
return 0;
}

How to count how many word in string?

I want to know how to count how many words are in a string.
I use strstr to compare and it works but only works for one time
like this
char buff = "This is a real-life, or this is just fantasy";
char op = "is";
if (strstr(buff,op)){
count++;
}
printf("%d",count);
and the output is 1 but there are two "is" in the sentence, please tell me.
For starters you have to write the declarations at least like
char buff[] = "This is a real-life, or this is just fantasy";
const char *op = "is";
Also if you need to count words you have to check whether words are separated by white spaces.
You can do the task the following way
#include <string.h>
#include <stdio.h>
#include <ctype.h>
//...
size_t n = strlen( op );
for ( const char *p = buff; ( p = strstr( p, op ) ) != NULL; p += n )
{
if ( p == buff || isblank( ( unsigned char )p[-1] ) )
{
if ( p[n] == '\0' || isblank( ( unsigned char )p[n] ) )
{
count++;
}
}
}
printf("%d",count);
Here is a demonstration program.
#include <stdio.h>
#include <string.h>
#include <ctype.h>
int main(void)
{
char buff[] = "This is a real-life, or this is just fantasy";
const char *op = "is";
size_t n = strlen( op );
size_t count = 0;
for ( const char *p = buff; ( p = strstr( p, op ) ) != NULL; p += n )
{
if ( p == buff || isblank( ( unsigned char )p[-1] ) )
{
if ( p[n] == '\0' || isblank( ( unsigned char )p[n] ) )
{
count++;
}
}
}
printf( "The word \"%s\" is encountered %zu time(s).\n", op, count );
return 0;
}
The program output is
The word "is" is encountered 2 time(s).
Parse the string, in a loop.
As OP has "but there are two "is" in the sentence", it is not enough just to look for "is" as that occurs 4x, twice in "This". Code needs to parse the string for the idea of a "word".
Case sensitively is also a concern.
char buff = "This is a real-life, or this is just fantasy";
char op = "is";
char *p = buff;
char *candidate;
while ((candidate = strstr(p, op)) {
// Add code to test if candidate is a stand-alone word
// Test if candidate is beginning of buff or prior character is a white-space.
// Test if candidate is end of buff or next character is a white-space/punctuation.
p += strlen(op); // advance
}
For me, I would not use strstr(), but look for "words" with isalpha().
// Concept code
size_t n = strlen(op);
while (*p) {
if (isalpha(*p)) { // Start of word
// some limited case insensitive compare
if (strnicmp(p, op, n) == 0 && !isalpha(p[n]) {
count++;
}
while (isalpha(*p)) p++; // Find end of word
} else {
p++;
}
}

garbage output after whitespace removing

i've this code:
int i =0;
char * str = "ar bitrary whitespace";
int whitespace=0,index;
for(index = 0;index < strlen(str);index++)
{
if(isspace(str[index]) != 0)
{
whitespace++;
}
}
char * tmp = (char *)calloc(strlen(str)-whitespace +1,sizeof(char));
memset(tmp,'\0',strlen(tmp)+1);
while(i < strlen(str))
{
if(isspace(str[i]) != 0)
{
i++;
continue;
}else if(isspace(str[i]) == 0)
{
strcat(tmp,&str[i]);
i++;
}
}
printf("\nnew string is: %s \n",tmp);
the problem is that the output is a string without the whitespace removed + some garbage character.
I've used memset to null terminate tmp,is there the problem?
The length of the source string could be calculated before this loop
for(index = 0;index < strlen(str);index++)
Otherwise if the code will not be optimized the function strlen will be called for each iteration of the loop. In fact using of the function is redundant for such a task.
This statement
memset(tmp,'\0',strlen(tmp)+1);
does not make sense because the call of calloc already initialized the memory with zeroes.
This statement
strcat(tmp,&str[i]);
also copies blanks from the source string after the position i. So it can write beyond the memory allocated for the array pointed to by the pointer tmp.
You can write a separate function that can look as it is shown in this demonstrative program
#include <stdlib.h>
#include <stdio.h>
#include <ctype.h>
char * remove_blanks( const char *s )
{
size_t n = 0;
const char *p = s;
do
{
if ( !isspace( ( unsigned char )*p ) ) ++n;
} while ( *p++ );
char *t = malloc( n );
if ( t )
{
char *q = t;
p = s;
do
{
if ( !isspace( ( unsigned char )*p ) ) *q++ = *p;
} while ( *p++ );
}
return t;
}
int main(void)
{
char * str = "ar bitrary whitespace";
printf( "\"%s\"\n", str );
char *t = remove_blanks( str );
printf( "\"%s\"\n", t );
free( t );
}
The program output is
"ar bitrary whitespace"
"arbitrarywhitespace"
this is your problem
memset(tmp,'\0',strlen(tmp)+1);
strlen(tmp) works by looking for '\0' in tmp, you have a chicken and egg situation here.
You should not be doing a memset any way, just tack on a '\0' when you fnish copying
And dont use strcat, instead maintain a pointer to tmp and just do *p = str[i] then increment p
I will not read your question, you overwrite the '\0' terminator for sure.
Now that I read your question, it looks like you need to understand strings and arrays better,
Don't ever write while (i < strlen(str))
Don't use strcat() for adding a single character, you apparently did overwrite the '\0' there. Furthermore, don't ever use strcat() for concatenating more than to pieces of a string.
Also notable,
You memset() after calloc() which already initialized to 0. That means that you are enforcing something that is not necessary, and trying it twice as if it failed the first time which I can guarantee it didn't.
In fact, since you have used calloc() and all bytes pointed to by tmp are 0 then strlen(tmp) will return 0, thus your memset() is equivalent to
tmp[0] = '\0';
and you REALLY don't need initialize tmp except when you finally copy the actual bytes from str.
I always advice against calloc() for strings, because
You don't really need to initialize something twice.
You should be sure your code does take the terminating '\0' into account and not simply assume that it's there because you calloc()ed. That is a bug that you just hide with calloc() but it shows up at some point.
Try this and see if you can understand the reasons for my changes
#include <stdio.h>
#include <ctype.h>
#include <stdlib.h>
int main(void)
{
int whitespace;
int length;
char *str = "ar bitrary whitespace";
char *tmp;
whitespace = 0;
for (length = 0; str[length] != '\0'; ++length) {
if (isspace(str[length]) != 0) {
whitespace++;
}
}
tmp = malloc(length - whitespace + 1);
if (tmp == NULL)
return -1;
for (int i = 0, j = 0; str[i] != '\0'; ++i) {
if (isspace(str[i]) != 0)
continue;
tmp[j++] = str[i];
}
tmp[length - whitespace] = '\0';
printf("new string is: %s\n",tmp);
free(tmp);
return 0;
}

Copying characters from a source string to a buffer - C

I am currently working on a computer science project and have gotten it totally working bar a very specific case which I cannot seem to fix. The goal of the code is to write a function int tokenCopy(char* dest, const char* src, int destSize) which copies characters from the given source string src into the given destination buffer dest, which is of size destSize, until either:
the end of the source string occurs, or
the destination buffer is full (allowing for the terminator that will be needed), or a space character is found in the input string
whichever comes first. If the copying finishes because a space is found, the space is not copied. The destination string must always be correctly terminated. If there is insufficient space in the destination for the source string, the destination string must be a correctly terminated leading substring of the source string.
The return value is the number of characters copied, not including the terminating null byte.
Where testing in done in the form of:
char buff[3];
int n = tokenCopy(buff, "This is a string", 3);
printf("%d '%s'\n", n, buff);
This is my code so far:
#include <stdio.h>
int tokenCopy(char* dest, const char* src, int destSize){
int new_value = 0;
int i=0;
for (;*src != ' '; new_value++){
destSize = 1;
return new_value;
}
for (; *src != '\0' && *src!= ' '; new_value++)
{
while (i < destSize-1 && *src!= '\0'){
*dest = *src;
dest++;
src++;
new_value++;
i++;
*dest = '\0';
}
return new_value;
}
return new_value;
}
However in the case of the following test:
char buff[10];
int n = tokenCopy(buff, " ", 10);
printf("%d '%s'\n", n, buff);
The output should be:
0 ''
However my code is outputting the zero, followed by the speech marks containing a different letter followed a question mark in a diamond per each change I try to make to the code. For reference I am using linux with the Geany IDE.
Any help with this problem would be much appreciated.
You need to assign to dest inside the function
int tokenCopy(char *dest, const char *src, int destSize) {
*dest = 0;
// rest of the code
}
After getting rid of the first for loop, you can modify the second for loop to something like
for ( i = 0; *src != '\0' && *src!= ' ' && (i < destSize-1) ; i++)
{
*dest++ = *src++;
}
*dest = '\0';
return new_value;
to get what you want. The modification includes
getting rid of the redundant check on empty string.
combining the copying of value and the pointer increment
adding the destination length check as a terminating condition for the loop itself
Even the very first loop of your function implementation
for (;*src != ' '; new_value++){
destSize = 1;
return new_value;
}
does not make sense.
The function can be written the following way
#include <stdio.h>
size_t tokenCopy( char *dest, const char *src, size_t destSize )
{
size_t n = 0;
if ( destSize != 0 )
{
while ( n < destSize && *src && *src != ' ' ) dest[n++] = *src++;
dest[n == destSize ? --n : n] = '\0';
}
return n;
}
int main( void )
{
char buff[10];
size_t n;
n = tokenCopy( buff, " ", 10 );
printf("%zu \"%s\"\n", n, buff );
n = tokenCopy( buff, "0123456789", 10 );
printf("%zu \"%s\"\n", n, buff );
}
The program output is
0 ""
9 "012345678"
#include<stdio.h>
int tokenCopy(char* dest, const char* src, int destSize){
while(*src && destSize>1 && *src!=' ') {
*dest = *src;
dest++;
src++;
destSize--;
}
*dest = '\0';
}
main(int argc, char **argv)
{
char buff[6];
tokenCopy(buff,"Th",6);
printf("%s\n",buff);
}

How do I trim leading/trailing whitespace in a standard way?

Is there a clean, preferably standard method of trimming leading and trailing whitespace from a string in C? I'd roll my own, but I would think this is a common problem with an equally common solution.
If you can modify the string:
// Note: This function returns a pointer to a substring of the original string.
// If the given string was allocated dynamically, the caller must not overwrite
// that pointer with the returned value, since the original pointer must be
// deallocated using the same allocator with which it was allocated. The return
// value must NOT be deallocated using free() etc.
char *trimwhitespace(char *str)
{
char *end;
// Trim leading space
while(isspace((unsigned char)*str)) str++;
if(*str == 0) // All spaces?
return str;
// Trim trailing space
end = str + strlen(str) - 1;
while(end > str && isspace((unsigned char)*end)) end--;
// Write new null terminator character
end[1] = '\0';
return str;
}
If you can't modify the string, then you can use basically the same method:
// Stores the trimmed input string into the given output buffer, which must be
// large enough to store the result. If it is too small, the output is
// truncated.
size_t trimwhitespace(char *out, size_t len, const char *str)
{
if(len == 0)
return 0;
const char *end;
size_t out_size;
// Trim leading space
while(isspace((unsigned char)*str)) str++;
if(*str == 0) // All spaces?
{
*out = 0;
return 1;
}
// Trim trailing space
end = str + strlen(str) - 1;
while(end > str && isspace((unsigned char)*end)) end--;
end++;
// Set output size to minimum of trimmed string length and buffer size minus 1
out_size = (end - str) < len-1 ? (end - str) : len-1;
// Copy trimmed string and add null terminator
memcpy(out, str, out_size);
out[out_size] = 0;
return out_size;
}
Here's one that shifts the string into the first position of your buffer. You might want this behavior so that if you dynamically allocated the string, you can still free it on the same pointer that trim() returns:
char *trim(char *str)
{
size_t len = 0;
char *frontp = str;
char *endp = NULL;
if( str == NULL ) { return NULL; }
if( str[0] == '\0' ) { return str; }
len = strlen(str);
endp = str + len;
/* Move the front and back pointers to address the first non-whitespace
* characters from each end.
*/
while( isspace((unsigned char) *frontp) ) { ++frontp; }
if( endp != frontp )
{
while( isspace((unsigned char) *(--endp)) && endp != frontp ) {}
}
if( frontp != str && endp == frontp )
*str = '\0';
else if( str + len - 1 != endp )
*(endp + 1) = '\0';
/* Shift the string so that it starts at str so that if it's dynamically
* allocated, we can still free it on the returned pointer. Note the reuse
* of endp to mean the front of the string buffer now.
*/
endp = str;
if( frontp != str )
{
while( *frontp ) { *endp++ = *frontp++; }
*endp = '\0';
}
return str;
}
Test for correctness:
#include <stdio.h>
#include <string.h>
#include <ctype.h>
/* Paste function from above here. */
int main()
{
/* The test prints the following:
[nothing to trim] -> [nothing to trim]
[ trim the front] -> [trim the front]
[trim the back ] -> [trim the back]
[ trim front and back ] -> [trim front and back]
[ trim one char front and back ] -> [trim one char front and back]
[ trim one char front] -> [trim one char front]
[trim one char back ] -> [trim one char back]
[ ] -> []
[ ] -> []
[a] -> [a]
[] -> []
*/
char *sample_strings[] =
{
"nothing to trim",
" trim the front",
"trim the back ",
" trim front and back ",
" trim one char front and back ",
" trim one char front",
"trim one char back ",
" ",
" ",
"a",
"",
NULL
};
char test_buffer[64];
char comparison_buffer[64];
size_t index, compare_pos;
for( index = 0; sample_strings[index] != NULL; ++index )
{
// Fill buffer with known value to verify we do not write past the end of the string.
memset( test_buffer, 0xCC, sizeof(test_buffer) );
strcpy( test_buffer, sample_strings[index] );
memcpy( comparison_buffer, test_buffer, sizeof(comparison_buffer));
printf("[%s] -> [%s]\n", sample_strings[index],
trim(test_buffer));
for( compare_pos = strlen(comparison_buffer);
compare_pos < sizeof(comparison_buffer);
++compare_pos )
{
if( test_buffer[compare_pos] != comparison_buffer[compare_pos] )
{
printf("Unexpected change to buffer # index %u: %02x (expected %02x)\n",
compare_pos, (unsigned char) test_buffer[compare_pos], (unsigned char) comparison_buffer[compare_pos]);
}
}
}
return 0;
}
Source file was trim.c. Compiled with 'cc -Wall trim.c -o trim'.
My solution. String must be changeable. The advantage above some of the other solutions that it moves the non-space part to the beginning so you can keep using the old pointer, in case you have to free() it later.
void trim(char * s) {
char * p = s;
int l = strlen(p);
while(isspace(p[l - 1])) p[--l] = 0;
while(* p && isspace(* p)) ++p, --l;
memmove(s, p, l + 1);
}
This version creates a copy of the string with strndup() instead of editing it in place. strndup() requires _GNU_SOURCE, so maybe you need to make your own strndup() with malloc() and strncpy().
char * trim(char * s) {
int l = strlen(s);
while(isspace(s[l - 1])) --l;
while(* s && isspace(* s)) ++s, --l;
return strndup(s, l);
}
Here's my C mini library for trimming left, right, both, all, in place and separate, and trimming a set of specified characters (or white space by default).
contents of strlib.h:
#ifndef STRLIB_H_
#define STRLIB_H_ 1
enum strtrim_mode_t {
STRLIB_MODE_ALL = 0,
STRLIB_MODE_RIGHT = 0x01,
STRLIB_MODE_LEFT = 0x02,
STRLIB_MODE_BOTH = 0x03
};
char *strcpytrim(char *d, // destination
char *s, // source
int mode,
char *delim
);
char *strtriml(char *d, char *s);
char *strtrimr(char *d, char *s);
char *strtrim(char *d, char *s);
char *strkill(char *d, char *s);
char *triml(char *s);
char *trimr(char *s);
char *trim(char *s);
char *kill(char *s);
#endif
contents of strlib.c:
#include <strlib.h>
char *strcpytrim(char *d, // destination
char *s, // source
int mode,
char *delim
) {
char *o = d; // save orig
char *e = 0; // end space ptr.
char dtab[256] = {0};
if (!s || !d) return 0;
if (!delim) delim = " \t\n\f";
while (*delim)
dtab[*delim++] = 1;
while ( (*d = *s++) != 0 ) {
if (!dtab[0xFF & (unsigned int)*d]) { // Not a match char
e = 0; // Reset end pointer
} else {
if (!e) e = d; // Found first match.
if ( mode == STRLIB_MODE_ALL || ((mode != STRLIB_MODE_RIGHT) && (d == o)) )
continue;
}
d++;
}
if (mode != STRLIB_MODE_LEFT && e) { // for everything but trim_left, delete trailing matches.
*e = 0;
}
return o;
}
// perhaps these could be inlined in strlib.h
char *strtriml(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_LEFT, 0); }
char *strtrimr(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_RIGHT, 0); }
char *strtrim(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_BOTH, 0); }
char *strkill(char *d, char *s) { return strcpytrim(d, s, STRLIB_MODE_ALL, 0); }
char *triml(char *s) { return strcpytrim(s, s, STRLIB_MODE_LEFT, 0); }
char *trimr(char *s) { return strcpytrim(s, s, STRLIB_MODE_RIGHT, 0); }
char *trim(char *s) { return strcpytrim(s, s, STRLIB_MODE_BOTH, 0); }
char *kill(char *s) { return strcpytrim(s, s, STRLIB_MODE_ALL, 0); }
The one main routine does it all.
It trims in place if src == dst, otherwise,
it works like the strcpy routines.
It trims a set of characters specified in the string delim, or white space if null.
It trims left, right, both, and all (like tr).
There is not much to it, and it iterates over the string only once. Some folks might complain that trim right starts on the left, however, no strlen is needed which starts on the left anyway. (One way or another you have to get to the end of the string for right trims, so you might as well do the work as you go.) There may be arguments to be made about pipelining and cache sizes and such -- who knows. Since the solution works from left to right and iterates only once, it can be expanded to work on streams as well. Limitations: it does not work on unicode strings.
Here is my attempt at a simple, yet correct in-place trim function.
void trim(char *str)
{
int i;
int begin = 0;
int end = strlen(str) - 1;
while (isspace((unsigned char) str[begin]))
begin++;
while ((end >= begin) && isspace((unsigned char) str[end]))
end--;
// Shift all characters back to the start of the string array.
for (i = begin; i <= end; i++)
str[i - begin] = str[i];
str[i - begin] = '\0'; // Null terminate string.
}
Late to the trim party
Features:
1. Trim the beginning quickly, as in a number of other answers.
2. After going to the end, trimming the right with only 1 test per loop. Like #jfm3, but works for an all white-space string)
3. To avoid undefined behavior when char is a signed char, cast *s to unsigned char.
Character handling "In all cases the argument is an int, the value of which shall be representable as an unsigned char or shall equal the value of the macro EOF. If the argument has any other value, the behavior is undefined." C11 §7.4 1
#include <ctype.h>
// Return a pointer to the trimmed string
char *string_trim_inplace(char *s) {
while (isspace((unsigned char) *s)) s++;
if (*s) {
char *p = s;
while (*p) p++;
while (isspace((unsigned char) *(--p)));
p[1] = '\0';
}
// If desired, shift the trimmed string
return s;
}
#chqrlie commented the above does not shift the trimmed string. To do so....
// Return a pointer to the (shifted) trimmed string
char *string_trim_inplace(char *s) {
char *original = s;
size_t len = 0;
while (isspace((unsigned char) *s)) {
s++;
}
if (*s) {
char *p = s;
while (*p) p++;
while (isspace((unsigned char) *(--p)));
p[1] = '\0';
// len = (size_t) (p - s); // older errant code
len = (size_t) (p - s + 1); // Thanks to #theriver
}
return (s == original) ? s : memmove(original, s, len + 1);
}
Here's a solution similar to #adam-rosenfields in-place modification routine but without needlessly resorting to strlen(). Like #jkramer, the string is left-adjusted within the buffer so you can free the same pointer. Not optimal for large strings since it does not use memmove. Includes the ++/-- operators that #jfm3 mentions. FCTX-based unit tests included.
#include <ctype.h>
void trim(char * const a)
{
char *p = a, *q = a;
while (isspace(*q)) ++q;
while (*q) *p++ = *q++;
*p = '\0';
while (p > a && isspace(*--p)) *p = '\0';
}
/* See http://fctx.wildbearsoftware.com/ */
#include "fct.h"
FCT_BGN()
{
FCT_QTEST_BGN(trim)
{
{ char s[] = ""; trim(s); fct_chk_eq_str("", s); } // Trivial
{ char s[] = " "; trim(s); fct_chk_eq_str("", s); } // Trivial
{ char s[] = "\t"; trim(s); fct_chk_eq_str("", s); } // Trivial
{ char s[] = "a"; trim(s); fct_chk_eq_str("a", s); } // NOP
{ char s[] = "abc"; trim(s); fct_chk_eq_str("abc", s); } // NOP
{ char s[] = " a"; trim(s); fct_chk_eq_str("a", s); } // Leading
{ char s[] = " a c"; trim(s); fct_chk_eq_str("a c", s); } // Leading
{ char s[] = "a "; trim(s); fct_chk_eq_str("a", s); } // Trailing
{ char s[] = "a c "; trim(s); fct_chk_eq_str("a c", s); } // Trailing
{ char s[] = " a "; trim(s); fct_chk_eq_str("a", s); } // Both
{ char s[] = " a c "; trim(s); fct_chk_eq_str("a c", s); } // Both
// Villemoes pointed out an edge case that corrupted memory. Thank you.
// http://stackoverflow.com/questions/122616/#comment23332594_4505533
{
char s[] = "a "; // Buffer with whitespace before s + 2
trim(s + 2); // Trim " " containing only whitespace
fct_chk_eq_str("", s + 2); // Ensure correct result from the trim
fct_chk_eq_str("a ", s); // Ensure preceding buffer not mutated
}
// doukremt suggested I investigate this test case but
// did not indicate the specific behavior that was objectionable.
// http://stackoverflow.com/posts/comments/33571430
{
char s[] = " foobar"; // Shifted across whitespace
trim(s); // Trim
fct_chk_eq_str("foobar", s); // Leading string is correct
// Here is what the algorithm produces:
char r[16] = { 'f', 'o', 'o', 'b', 'a', 'r', '\0', ' ',
' ', 'f', 'o', 'o', 'b', 'a', 'r', '\0'};
fct_chk_eq_int(0, memcmp(s, r, sizeof(s)));
}
}
FCT_QTEST_END();
}
FCT_END();
I'm not sure what you consider "painless."
C strings are pretty painful. We can find the first non-whitespace character position trivially:
while (isspace(* p)) p++;
We can find the last non-whitespace character position with two similar trivial moves:
while (* q) q++;
do { q--; } while (isspace(* q));
(I have spared you the pain of using the * and ++ operators at the same time.)
The question now is what do you do with this? The datatype at hand isn't really a big robust abstract String that is easy to think about, but instead really barely any more than an array of storage bytes. Lacking a robust data type, it is impossible to write a function that will do the same as PHperytonby's chomp function. What would such a function in C return?
Another one, with one line doing the real job:
#include <stdio.h>
int main()
{
const char *target = " haha ";
char buf[256];
sscanf(target, "%s", buf); // Trimming on both sides occurs here
printf("<%s>\n", buf);
}
If you're using glib, then you can use g_strstrip
I didn't like most of these answers because they did one or more of the following...
Returned a different pointer inside the original pointer's string (kind of a pain to juggle two different pointers to the same thing).
Made gratuitous use of things like strlen() that pre-iterate the entire string.
Used non-portable OS-specific lib functions.
Backscanned.
Used comparison to ' ' instead of isspace() so that TAB / CR / LF are preserved.
Wasted memory with large static buffers.
Wasted cycles with high-cost functions like sscanf/sprintf.
Here is my version:
void fnStrTrimInPlace(char *szWrite) {
const char *szWriteOrig = szWrite;
char *szLastSpace = szWrite, *szRead = szWrite;
int bNotSpace;
// SHIFT STRING, STARTING AT FIRST NON-SPACE CHAR, LEFTMOST
while( *szRead != '\0' ) {
bNotSpace = !isspace((unsigned char)(*szRead));
if( (szWrite != szWriteOrig) || bNotSpace ) {
*szWrite = *szRead;
szWrite++;
// TRACK POINTER TO LAST NON-SPACE
if( bNotSpace )
szLastSpace = szWrite;
}
szRead++;
}
// TERMINATE AFTER LAST NON-SPACE (OR BEGINNING IF THERE WAS NO NON-SPACE)
*szLastSpace = '\0';
}
Use a string library, for instance:
Ustr *s1 = USTR1(\7, " 12345 ");
ustr_sc_trim_cstr(&s1, " ");
assert(ustr_cmp_cstr_eq(s1, "12345"));
...as you say this is a "common" problem, yes you need to include a #include or so and it's not included in libc but don't go inventing your own hack job storing random pointers and size_t's that way only leads to buffer overflows.
A bit late to the game, but I'll throw my routines into the fray. They're probably not the most absolute efficient, but I believe they're correct and they're simple (with rtrim() pushing the complexity envelope):
#include <ctype.h>
#include <string.h>
/*
Public domain implementations of in-place string trim functions
Michael Burr
michael.burr#nth-element.com
2010
*/
char* ltrim(char* s)
{
char* newstart = s;
while (isspace( *newstart)) {
++newstart;
}
// newstart points to first non-whitespace char (which might be '\0')
memmove( s, newstart, strlen( newstart) + 1); // don't forget to move the '\0' terminator
return s;
}
char* rtrim( char* s)
{
char* end = s + strlen( s);
// find the last non-whitespace character
while ((end != s) && isspace( *(end-1))) {
--end;
}
// at this point either (end == s) and s is either empty or all whitespace
// so it needs to be made empty, or
// end points just past the last non-whitespace character (it might point
// at the '\0' terminator, in which case there's no problem writing
// another there).
*end = '\0';
return s;
}
char* trim( char* s)
{
return rtrim( ltrim( s));
}
Very late to the party...
Single-pass forward-scanning solution with no backtracking. Every character in the source string is tested exactly once twice. (So it should be faster than most of the other solutions here, especially if the source string has a lot of trailing spaces.)
This includes two solutions, one to copy and trim a source string into another destination string, and the other to trim the source string in place. Both functions use the same code.
The (modifiable) string is moved in-place, so the original pointer to it remains unchanged.
#include <stddef.h>
#include <ctype.h>
char * trim2(char *d, const char *s)
{
// Sanity checks
if (s == NULL || d == NULL)
return NULL;
// Skip leading spaces
const unsigned char * p = (const unsigned char *)s;
while (isspace(*p))
p++;
// Copy the string
unsigned char * dst = (unsigned char *)d; // d and s can be the same
unsigned char * end = dst;
while (*p != '\0')
{
if (!isspace(*dst++ = *p++))
end = dst;
}
// Truncate trailing spaces
*end = '\0';
return d;
}
char * trim(char *s)
{
return trim2(s, s);
}
Just to keep this growing, one more option with a modifiable string:
void trimString(char *string)
{
size_t i = 0, j = strlen(string);
while (j > 0 && isspace((unsigned char)string[j - 1])) string[--j] = '\0';
while (isspace((unsigned char)string[i])) i++;
if (i > 0) memmove(string, string + i, j - i + 1);
}
I know there have many answers, but I post my answer here to see if my solution is good enough.
// Trims leading whitespace chars in left `str`, then copy at almost `n - 1` chars
// into the `out` buffer in which copying might stop when the first '\0' occurs,
// and finally append '\0' to the position of the last non-trailing whitespace char.
// Reture the length the trimed string which '\0' is not count in like strlen().
size_t trim(char *out, size_t n, const char *str)
{
// do nothing
if(n == 0) return 0;
// ptr stop at the first non-leading space char
while(isspace(*str)) str++;
if(*str == '\0') {
out[0] = '\0';
return 0;
}
size_t i = 0;
// copy char to out until '\0' or i == n - 1
for(i = 0; i < n - 1 && *str != '\0'; i++){
out[i] = *str++;
}
// deal with the trailing space
while(isspace(out[--i]));
out[++i] = '\0';
return i;
}
The easiest way to skip leading spaces in a string is, imho,
#include <stdio.h>
int main()
{
char *foo=" teststring ";
char *bar;
sscanf(foo,"%s",bar);
printf("String is >%s<\n",bar);
return 0;
}
Ok this is my take on the question. I believe it's the most concise solution that modifies the string in place (free will work) and avoids any UB. For small strings, it's probably faster than a solution involving memmove.
void stripWS_LT(char *str)
{
char *a = str, *b = str;
while (isspace((unsigned char)*a)) a++;
while (*b = *a++) b++;
while (b > str && isspace((unsigned char)*--b)) *b = 0;
}
#include <ctype.h>
#include <string.h>
char *trim_space(char *in)
{
char *out = NULL;
int len;
if (in) {
len = strlen(in);
while(len && isspace(in[len - 1])) --len;
while(len && *in && isspace(*in)) ++in, --len;
if (len) {
out = strndup(in, len);
}
}
return out;
}
isspace helps to trim all white spaces.
Run a first loop to check from last byte for space character and reduce the length variable
Run a second loop to check from first byte for space character and reduce the length variable and increment char pointer.
Finally if length variable is more than 0, then use strndup to create new string buffer by excluding spaces.
This one is short and simple, uses for-loops and doesn't overwrite the string boundaries.
You can replace the test with isspace() if needed.
void trim (char *s) // trim leading and trailing spaces+tabs
{
int i,j,k, len;
j=k=0;
len = strlen(s);
// find start of string
for (i=0; i<len; i++) if ((s[i]!=32) && (s[i]!=9)) { j=i; break; }
// find end of string+1
for (i=len-1; i>=j; i--) if ((s[i]!=32) && (s[i]!=9)) { k=i+1; break;}
if (k<=j) {s[0]=0; return;} // all whitespace (j==k==0)
len=k-j;
for (i=0; i<len; i++) s[i] = s[j++]; // shift result to start of string
s[i]=0; // end the string
}//_trim
If, and ONLY IF there's only one contiguous block of text between whitespace, you can use a single call to strtok(3), like so:
char *trimmed = strtok(input, "\r\t\n ");
This works for strings like the following:
" +1.123.456.7890 "
" 01-01-2020\n"
"\t2.523"
This will not work for strings that contain whitespace between blocks of non-whitespace, like " hi there ". It's probably better to avoid this approach, but now it's here in your toolbox if you need it.
Personally, I'd roll my own. You can use strtok, but you need to take care with doing so (particularly if you're removing leading characters) that you know what memory is what.
Getting rid of trailing spaces is easy, and pretty safe, as you can just put a 0 in over the top of the last space, counting back from the end. Getting rid of leading spaces means moving things around. If you want to do it in place (probably sensible) you can just keep shifting everything back one character until there's no leading space. Or, to be more efficient, you could find the index of the first non-space character, and shift everything back by that number. Or, you could just use a pointer to the first non-space character (but then you need to be careful in the same way as you do with strtok).
#include "stdafx.h"
#include "malloc.h"
#include "string.h"
int main(int argc, char* argv[])
{
char *ptr = (char*)malloc(sizeof(char)*30);
strcpy(ptr," Hel lo wo rl d G eo rocks!!! by shahil sucks b i g tim e");
int i = 0, j = 0;
while(ptr[j]!='\0')
{
if(ptr[j] == ' ' )
{
j++;
ptr[i] = ptr[j];
}
else
{
i++;
j++;
ptr[i] = ptr[j];
}
}
printf("\noutput-%s\n",ptr);
return 0;
}
Most of the answers so far do one of the following:
Backtrack at the end of the string (i.e. find the end of the string and then seek backwards until a non-space character is found,) or
Call strlen() first, making a second pass through the whole string.
This version makes only one pass and does not backtrack. Hence it may perform better than the others, though only if it is common to have hundreds of trailing spaces (which is not unusual when dealing with the output of a SQL query.)
static char const WHITESPACE[] = " \t\n\r";
static void get_trim_bounds(char const *s,
char const **firstWord,
char const **trailingSpace)
{
char const *lastWord;
*firstWord = lastWord = s + strspn(s, WHITESPACE);
do
{
*trailingSpace = lastWord + strcspn(lastWord, WHITESPACE);
lastWord = *trailingSpace + strspn(*trailingSpace, WHITESPACE);
}
while (*lastWord != '\0');
}
char *copy_trim(char const *s)
{
char const *firstWord, *trailingSpace;
char *result;
size_t newLength;
get_trim_bounds(s, &firstWord, &trailingSpace);
newLength = trailingSpace - firstWord;
result = malloc(newLength + 1);
memcpy(result, firstWord, newLength);
result[newLength] = '\0';
return result;
}
void inplace_trim(char *s)
{
char const *firstWord, *trailingSpace;
size_t newLength;
get_trim_bounds(s, &firstWord, &trailingSpace);
newLength = trailingSpace - firstWord;
memmove(s, firstWord, newLength);
s[newLength] = '\0';
}
This is the shortest possible implementation I can think of:
static const char *WhiteSpace=" \n\r\t";
char* trim(char *t)
{
char *e=t+(t!=NULL?strlen(t):0); // *e initially points to end of string
if (t==NULL) return;
do --e; while (strchr(WhiteSpace, *e) && e>=t); // Find last char that is not \r\n\t
*(++e)=0; // Null-terminate
e=t+strspn (t,WhiteSpace); // Find first char that is not \t
return e>t?memmove(t,e,strlen(e)+1):t; // memmove string contents and terminator
}
These functions will modify the original buffer, so if dynamically allocated, the original
pointer can be freed.
#include <string.h>
void rstrip(char *string)
{
int l;
if (!string)
return;
l = strlen(string) - 1;
while (isspace(string[l]) && l >= 0)
string[l--] = 0;
}
void lstrip(char *string)
{
int i, l;
if (!string)
return;
l = strlen(string);
while (isspace(string[(i = 0)]))
while(i++ < l)
string[i-1] = string[i];
}
void strip(char *string)
{
lstrip(string);
rstrip(string);
}
What do you think about using StrTrim function defined in header Shlwapi.h.? It is straight forward rather defining on your own.
Details can be found on:
http://msdn.microsoft.com/en-us/library/windows/desktop/bb773454(v=vs.85).aspx
If you have
char ausCaptain[]="GeorgeBailey ";
StrTrim(ausCaptain," ");
This will give ausCaptain as "GeorgeBailey" not "GeorgeBailey ".
To trim my strings from the both sides I use the oldie but the gooody ;)
It can trim anything with ascii less than a space, meaning that the control chars will be trimmed also !
char *trimAll(char *strData)
{
unsigned int L = strlen(strData);
if(L > 0){ L--; }else{ return strData; }
size_t S = 0, E = L;
while((!(strData[S] > ' ') || !(strData[E] > ' ')) && (S >= 0) && (S <= L) && (E >= 0) && (E <= L))
{
if(strData[S] <= ' '){ S++; }
if(strData[E] <= ' '){ E--; }
}
if(S == 0 && E == L){ return strData; } // Nothing to be done
if((S >= 0) && (S <= L) && (E >= 0) && (E <= L)){
L = E - S + 1;
memmove(strData,&strData[S],L); strData[L] = '\0';
}else{ strData[0] = '\0'; }
return strData;
}
I'm only including code because the code posted so far seems suboptimal (and I don't have the rep to comment yet.)
void inplace_trim(char* s)
{
int start, end = strlen(s);
for (start = 0; isspace(s[start]); ++start) {}
if (s[start]) {
while (end > 0 && isspace(s[end-1]))
--end;
memmove(s, &s[start], end - start);
}
s[end - start] = '\0';
}
char* copy_trim(const char* s)
{
int start, end;
for (start = 0; isspace(s[start]); ++start) {}
for (end = strlen(s); end > 0 && isspace(s[end-1]); --end) {}
return strndup(s + start, end - start);
}
strndup() is a GNU extension. If you don't have it or something equivalent, roll your own. For example:
r = strdup(s + start);
r[end-start] = '\0';
Here i use the dynamic memory allocation to trim the input string to the function trimStr. First, we find how many non-empty characters exist in the input string. Then, we allocate a character array with that size and taking care of the null terminated character. When we use this function, we need to free the memory inside of main function.
#include<stdio.h>
#include<stdlib.h>
char *trimStr(char *str){
char *tmp = str;
printf("input string %s\n",str);
int nc = 0;
while(*tmp!='\0'){
if (*tmp != ' '){
nc++;
}
tmp++;
}
printf("total nonempty characters are %d\n",nc);
char *trim = NULL;
trim = malloc(sizeof(char)*(nc+1));
if (trim == NULL) return NULL;
tmp = str;
int ne = 0;
while(*tmp!='\0'){
if (*tmp != ' '){
trim[ne] = *tmp;
ne++;
}
tmp++;
}
trim[nc] = '\0';
printf("trimmed string is %s\n",trim);
return trim;
}
int main(void){
char str[] = " s ta ck ove r fl o w ";
char *trim = trimStr(str);
if (trim != NULL )free(trim);
return 0;
}

Resources