"Richard Heathfield" <
[email protected]> a écrit dans le message de (e-mail address removed)...
Except CBFalconer is no John F. Kennedy ;-)
His blunt rethoric does not bolster any one's morale, sarcasm does no good.
You are right, I should not have attributed to malice that which can be
adequately explained by plain ignorance. But I repeat: to not use strtok
anymore, check for availability of strtok_r or implement it locally from the
public domain source that has been posted above.
It's trivial to write one:
#include <string.h>
#include <limits.h>
#include <stdlib.h>
#include <ctype.h>
/* The default delimiters are chosen as some ordinary white space
characters: */
static const char default_delimiters[] =
{' ', '\n', '\t', '\r', '\f', 0};
/*
* The tokenize() function is similar to a reentrant version of
strtok().
* It parses tokens from 's', where tokens are substrings separated
by
* characters from 'delimiter_list'.
* To get the first token from 's', tokenize() is called with 's' as
its first
* parameter.
* Remaining tokens from 's' are obtained by calling tokenize() with
NULL for
* the first parameter.
* The s of delimiters, identified by 'delimiter_list', can change
from call
* to call.
* If the list of delimiters is NULL, then the standard list
'default_delimiters'
* (see above) is used.
* tokenize() modifies the memory pointed to by 's', because it writes
null
* characters into the buffer.
*/
char *tokenize(char *s, const char *delimiter_list, char
**placeholder)
{
if (delimiter_list == NULL)
delimiter_list = default_delimiters;
if (delimiter_list[0] == 0)
delimiter_list = default_delimiters;
if (s == NULL)
s = *placeholder;
if (s == NULL)
return NULL;
/*
* The strspn() function computes the length of the initial segment of
the first
* string that consists entirely of characters contained in the second
string.
*/
s += strspn(s, delimiter_list);
if (!s[0]) {
*placeholder = s;
return NULL;
} else {
char *token;
token = s;
/*
* The strpbrk() function finds the first occurrence of any character
contained in
* the second string found in the first string.
*/
s = strpbrk(token, delimiter_list);
if (s == NULL)
*placeholder = token + strlen(token);
else {
*s++ = 0;
*placeholder = s;
}
return token;
}
}
#ifdef UNIT_TEST
char ts0[] =
"This is a test. This is only a test. If it were an actual emergency,
you would"
" be dead.";
char ts1[] =
"This is a also a test. This is only a test. If it were an actual
emergency, you"
" would be dead. 12345";
char ts2[] =
"The quick brown fox jumped over the lazy dog's back 1234567890
times.";
char ts3[] =
" \t\r\n\fThe quick brown fox jumped over the lazy dog's back
1234567890 times.";
char ts4[] =
"This is a test. This is only a test. If it were an actual emergency,
you would"
" be dead.";
char ts5[] =
"This is a also a test. This is only a test. If it were an actual
emergency, you"
" would be dead. 12345";
char ts6[] =
"The quick brown fox jumped over the lazy dog's back 1234567890
times.";
char ts7[] =
" \t\r\n\fThe quick brown fox jumped over the lazy dog's back
1234567890 times.";
#include <stdio.h>
char whitespace[UCHAR_MAX + 1];
/*
This test will create token separators as any whitespace or any
punctuation
marks:
*/
void init_whitespace()
{
int i;
int index = 0;
for (i = 0; i < UCHAR_MAX; i++) {
if (isspace(i)) {
whitespace[index++] = (char) i;
}
if (ispunct(i)) {
whitespace[index++] = (char) i;
}
}
}
/*
TNX Gerd.
*/
void spin_test(char *ts, char *white)
{
char *p = NULL;
char *token;
token = tokenize(ts, white, &p);
while (token) {
puts(token);
token = tokenize(NULL, white, &p);
}
}
int main(void)
{
init_whitespace();
puts("Whitespace is whitespace+punctuation");
spin_test(ts0, whitespace);
spin_test(ts1, whitespace);
spin_test(ts2, whitespace);
spin_test(ts3, whitespace);
puts("Whitespace is simple whitespace");
spin_test(ts4, NULL);
spin_test(ts5, NULL);
spin_test(ts6, NULL);
spin_test(ts7, NULL);
return 0;
}
#endif
