Strip unicode (why was this tricky in php?)

findunicode.c

#include <stdio.h>

#define BUF_SZ (1 << 16)

size_t
find_unicode(char *p, size_t n)
{
	size_t i;
	for (i = 0; i < n; ++i) {
		if (p[i] & 128)
			return i;
	}
	return i;
}

int
main(void)
{
	char buf[BUF_SZ];
	size_t len_in, len_out;

	do {
		len_in = fread(buf, 1, BUF_SZ, stdin);
		len_out = find_unicode(buf, len_in);
		fwrite(buf, 1, len_out, stdout);
	} while (len_out == BUF_SZ);

	return len_in != len_out;
}

stripunicode.c

#include <stdio.h>

#define BUF_SZ (1 << 16)

size_t
strip_unicode(char *p, size_t n)
{
	size_t i, j;
	for (i = 0, j = 0; j < n; ++j) {
		p[i] = p[j];
		if (!(p[i] & 128))
			++i;
	}
	return i;
}

int
main(void)
{
	char buf[BUF_SZ];
	size_t len_in, len_out;

	do {
		len_in = fread(buf, 1, BUF_SZ, stdin);
		len_out = strip_unicode(buf, len_in);
		fwrite(buf, 1, len_out, stdout);
	} while (len_in == BUF_SZ);

	return 0;
}