Related
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;
}
This is the requirement for my code:
This function appends the src string to the dest string, overwriting the terminating null byte ('\0') at the end of dest, and then adds a terminating null byte.
Returns a pointer to the resulting string dest.
This is the output I am getting:
Hello
World!
Hello World!
Hello
Here is my code:
char *_strcat(char *dest, char *src) {
int lengthd = 0;
int lengths = 0;
int i = 0;
int j = 0;
int k = 0;
char tmp[10];
while (dest[i] != '\0') {
lengthd++;
i++;
}
while (src[k] != '\0') {
tmp[lengths] = src[k];
lengths++;
k++;
}
for (; j < lengths - 1; j++) {
dest[lengthd + 1] = tmp[j];
}
dest[lengthd + 1] = '\0';
return (dest);
}
int main(void) {
char s1[98] = "Hello ";
char s2[] = "World!\n";
char *ptr;
printf("%s\\n", s1);
printf("%s", s2);
ptr = _strcat(s1, s2);
printf("%s", s1);
printf("%s", s2);
printf("%s", ptr);
return (0);
}
Your code fails for multiple reasons:
you use a temporary array to make a copy of the source string: this array tmp has a fixed length of 10 bytes, which is too small if the source string is longer than 10 bytes. Otherwise you will have undefined behavior when you write beyond the end of this array.
there is really no need for this temporary array anyway.
the final loop stops at lengths - 1, hence you stop before the last byte of the copy.
you copy all bytes to the same position dest[lengthd + 1].
you finally set the null terminator at the same position again.
you never changed the null terminator at dest[lengthd] so the function appears to have no effect on dest.
the tests in main() cannot produce the output you posted, probably because of a typo in "%s\\n".
avoid using identifiers starting with an _.
Here is a modified version:
#include <stdio.h>
#include <string.h>
char *my_strcat(char *dest, char *src) {
int i = 0;
int k = 0;
/* find the offset of the null terminator in dest */
while (dest[i] != '\0') {
i++;
}
/* copy the bytes from the src string there */
while (src[k] != '\0') {
dest[i] = src[k];
i++;
k++;
}
/* set the null terminator */
dest[i] = '\0';
/* return the pointer to the destination array */
return dest;
}
int main(void) {
char s1[98] = "Hello ";
char s2[] = "World!";
char *ptr;
printf("%s\n", s1);
printf("%s", s2);
ptr = my_strcat(s1, s2);
printf("%s", s1);
printf("%s", s2);
printf("%s", ptr);
return 0;
}
Note that the source string is not modified and the offsets should have type size_t and can be incremented as a side effect of the assignment:
char *my_strcat(char *dest, const char *src) {
size_t i = 0;
size_t k = 0;
/* find the offset of the null terminator in dest */
while (dest[i] != '\0') {
i++;
}
/* copy the bytes from the src string there */
while (src[k] != '\0') {
dest[i++] = src[k++];
}
/* set the null terminator */
dest[i] = '\0';
/* return the pointer to the destination array */
return dest;
}
You can also use pointers instead of offsets:
char *my_strcat(char *dest, const char *src) {
/* use a working pointer to preserve dest for the return value */
char *p = dest;
/* find the offset of the null terminator in dest */
while (*p != '\0') {
p++;
}
/* copy the bytes from the src string there */
while (*src != '\0') {
*p++ = *src++;
}
/* set the null terminator */
*p = '\0';
/* return the pointer to the destination array */
return dest;
}
One final change: you can combine reading the source byte, copying to the destination and testing for the null terminator, which will have been copied already:
char *my_strcat(char *dest, const char *src) {
/* use a working pointer to preserve dest for the return value */
char *p = dest;
/* find the offset of the null terminator in dest */
while (*p != '\0') {
p++;
}
/* copy the bytes from the src string there */
while ((p++ = *src++) != '\0') {
/* nothing */
}
/* the null terminator was copied from the source string */
/* return the pointer to the destination array */
return dest;
}
At least due to the declaration of the character array tmp with the magic number 10
char tmp[10];
the function does not make a sense.
Moreover in this while loop
while (src[k] != '\0')
{
lengths++;
k++;
tmp[lengths] = src[k];
}
the first element of the array tmp is skipped.
Also in this for loop
for (; j < lengths-1; j++)
{
dest[lengthd + 1] = tmp[j];
}
the condition of the loop is incorrect. Also the expression dest[lengthd + 1] skips the terminating zero character of the string pointed to by the pointer dest. And all characters are written at the same position lengthd + 1.
Apart from this the names s1, s2 and ptr used in main were not declared.
The function can be declared and defined the following way
char * my_strcat( char *dest, const char *src )
{
char *p = dest;
while ( *p ) ++p;
while ( ( *p++ = *src++ ) != '\0' );
return dest;
}
and can be called like
char s1[13] = "Hello ";
const char *s2 = "World!";
puts( my_strcat( s1, s2 ) );
Another way to define the function using an approach similar to yours is the following
char * my_strcat( char *dest, const char *src )
{
size_t i = 0;
while ( dest[i] != '\0' ) ++i;
for ( size_t j = 0; src[j] != '\0'; j++ )
{
dest[i++] = src[j];
}
dest[i] '\0';
return dest;
}
I'm attempting to remove a character from a string in C. The problem I am having with my code is that it removes the first instance of the character from the string but also wipes everything after that character in the string too. For example, removing 'l' from 'hello' prints 'he' rather than 'heo'
int i;
char str1[30] = "Hello", *ptr1, c = 'l';
ptr1 = str1;
for (i=0; i<strlen(str1); i++)
{
if (*ptr1 == c) *ptr1 = 0;
printf("%c\n", *ptr1);
ptr1++;
}
I need to use pointers for this and would like to keep it as simple as possible since I'm a beginner in C.
Thanks
You can do it like this:
void remove_all_chars(char* str, char c) {
char *pr = str, *pw = str;
while (*pr) {
*pw = *pr++;
pw += (*pw != c);
}
*pw = '\0';
}
int main() {
char str[] = "llHello, world!ll";
remove_all_chars(str, 'l');
printf("'%s'\n", str);
return 0;
}
The idea is to keep a separate read and write pointers (pr for reading and pw for writing), always advance the reading pointer, and advance the writing pointer only when it's not pointing to a given character.
If you remove the characters in place you will have to shift the rest of the string one place to the left every time you remove a character, this is not very efficient. The best way is to have a second array that takes the filtered string. For example you can change your code like this.
int i;
char str1[30] = "Hello", *ptr1, c = 'l';
char str2[30] = {0}, *ptr2;
ptr1 = str1;
ptr2 = str2;
for (i=0; i<strlen(str1); i++)
{
if (*ptr1 != c) *ptr2++=*ptr1;
ptr1++;
}
printf("%s\n", str2);
The problem is that when you encounter the first character that matches c, you insert a null character right there. That means you're essentially cutting off the rest of the string.
What you need to do is when you find a matching character, move the following characters back one position. Then you need to insert the null character at the very end depending on how many characters you have removed.
char str1[30] = "Hello", *prt1, c = 'l';
char str2[30], *prt2;
prt1 = str1;
prt2 = str2;
while(*prt1 != 0)
{
if(*prt1 != c)
{
*prt2 = *prt1;
prt2++;
}
prt1++;
}
*prt2 = '\0';
i know that it is a type of duplicate answer, but this code is function's version for solving the problem. I thought that as the questioner was a beginner, he might learn much from decomposed version of problem.
int del_x_char(char *p, int x)
{
char *q;
x=first_occurance(p, 'i')/*you can replace any character that you want delete with 'i'*/
q=p+x;
while(*q=*(q+1))
q++;
*q='\0';
return 0;
}
int first_occurance(char *q, char phar)
{
int i=0;
while(*q)
{
if(*q++==phar)
return i;
i++;
}
return -1;
}
just change
if (*ptr1 == c) *ptr1 = 0;
to
if (*ptr1 == c) continue;
as #ouah said, it breaks at the first NULL character..
C defines a string as "a contiguous sequence of characters terminated by and including the first null character"
How can I strip a string with all \n and \t in C?
This works in my quick and dirty tests. Does it in place:
#include <stdio.h>
void strip(char *s) {
char *p2 = s;
while(*s != '\0') {
if(*s != '\t' && *s != '\n') {
*p2++ = *s++;
} else {
++s;
}
}
*p2 = '\0';
}
int main() {
char buf[] = "this\t is\n a\t test\n test";
strip(buf);
printf("%s\n", buf);
}
And to appease Chris, here is a version which will make a place the result in a newly malloced buffer and return it (thus it'll work on literals). You will need to free the result.
char *strip_copy(const char *s) {
char *p = malloc(strlen(s) + 1);
if(p) {
char *p2 = p;
while(*s != '\0') {
if(*s != '\t' && *s != '\n') {
*p2++ = *s++;
} else {
++s;
}
}
*p2 = '\0';
}
return p;
}
If you want to replace \n or \t with something else, you can use the function strstr(). It returns a pointer to the first place in a function that has a certain string. For example:
// Find the first "\n".
char new_char = 't';
char* pFirstN = strstr(szMyString, "\n");
*pFirstN = new_char;
You can run that in a loop to find all \n's and \t's.
If you want to "strip" them, i.e. remove them from the string, you'll need to actually use the same method as above, but copy the contents of the string "back" every time you find a \n or \t, so that "this i\ns a test" becomes: "this is a test".
You can do that with memmove (not memcpy, since the src and dst are pointing to overlapping memory), like so:
char* temp = strstr(str, "\t");
// Remove \n.
while ((temp = strstr(str, "\n")) != NULL) {
// Len is the length of the string, from the ampersand \n, including the \n.
int len = strlen(str);
memmove(temp, temp + 1, len);
}
You'll need to repeat this loop again to remove the \t's.
Note: Both of these methods work in-place. This might not be safe! (read Evan Teran's comments for details.. Also, these methods are not very efficient, although they do utilize a library function for some of the code instead of rolling your own.
Basically, you have two ways to do this: you can create a copy of the original string, minus all '\t' and '\n' characters, or you can strip the string "in-place." However, I bet money that the first option will be faster, and I promise you it will be safer.
So we'll make a function:
char *strip(const char *str, const char *d);
We want to use strlen() and malloc() to allocate a new char * buffer the same size as our str buffer. Then we go through str character by character. If the character is not contained in d, we copy it into our new buffer. We can use something like strchr() to see if each character is in the string d. Once we're done, we have a new buffer, with the contents of our old buffer minus characters in the string d, so we just return that. I won't give you sample code, because this might be homework, but here's the sample usage to show you how it solves your problem:
char *string = "some\n text\t to strip";
char *stripped = strip(string, "\t\n");
This is a c string function that will find any character in accept and return a pointer to that position or NULL if it is not found.
#include <string.h>
char *strpbrk(const char *s, const char *accept);
Example:
char search[] = "a string with \t and \n";
char *first_occ = strpbrk( search, "\t\n" );
first_occ will point to the \t, or the 15 character in search. You can replace then call again to loop through until all have been replaced.
I like to make the standard library do as much of the work as possible, so I would use something similar to Evan's solution but with strspn() and strcspn().
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#define SPACE " \t\r\n"
static void strip(char *s);
static char *strip_copy(char const *s);
int main(int ac, char **av)
{
char s[] = "this\t is\n a\t test\n test";
char *s1 = strip_copy(s);
strip(s);
printf("%s\n%s\n", s, s1);
return 0;
}
static void strip(char *s)
{
char *p = s;
int n;
while (*s)
{
n = strcspn(s, SPACE);
strncpy(p, s, n);
p += n;
s += n + strspn(s+n, SPACE);
}
*p = 0;
}
static char *strip_copy(char const *s)
{
char *buf = malloc(1 + strlen(s));
if (buf)
{
char *p = buf;
char const *q;
int n;
for (q = s; *q; q += n + strspn(q+n, SPACE))
{
n = strcspn(q, SPACE);
strncpy(p, q, n);
p += n;
}
*p++ = '\0';
buf = realloc(buf, p - buf);
}
return buf;
}
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;
}