Data update

This commit is contained in:
Ingy döt Net 2026-02-01 16:33:20 -08:00
parent 5150844a7d
commit 4bb20c9b71
7735 changed files with 38060 additions and 199180 deletions

View file

@ -9,46 +9,46 @@
int ordered(char *s, char **end)
{
int r = 1;
while (*++s != '\n' && *s != '\r' && *s != '\0')
if (s[0] < s[-1]) r = 0;
int r = 1;
while (*++s != '\n' && *s != '\r' && *s != '\0')
if (s[0] < s[-1]) r = 0;
*end = s;
return r;
*end = s;
return r;
}
int main()
{
char *buf, *word, *end, *tail;
struct stat st;
int longest = 0, len, fd;
char *buf, *word, *end, *tail;
struct stat st;
int longest = 0, len, fd;
if ((fd = open("unixdict.txt", O_RDONLY)) == -1) err(1, "read error");
if ((fd = open("unixdict.txt", O_RDONLY)) == -1) err(1, "read error");
fstat(fd, &st);
if (!(buf = mmap(0, st.st_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0)))
err(1, "mmap");
fstat(fd, &st);
if (!(buf = mmap(0, st.st_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0)))
err(1, "mmap");
for (word = end = buf; end < buf + st.st_size; word = end) {
while (*word == '\r' || *word == '\n') word++;
if (!ordered(word, &end)) continue;
if ((len = end - word + 1) < longest) continue;
if (len > longest) {
tail = buf; /* longer words found; reset out buffer */
longest = len;
}
/* use the same mmap'd region to store output. because of MAP_PRIVATE,
* change will not go back to file. mmap is copy on write, and we are using
* only the head space to store output, so kernel doesn't need to copy more
* than the words we saved--in this case, one page tops.
*/
memcpy(tail, word, len);
tail += len;
*tail = '\0';
}
printf(buf);
for (word = end = buf; end < buf + st.st_size; word = end) {
while (*word == '\r' || *word == '\n') word++;
if (!ordered(word, &end)) continue;
if ((len = end - word + 1) < longest) continue;
if (len > longest) {
tail = buf; /* longer words found; reset out buffer */
longest = len;
}
/* use the same mmap'd region to store output. because of MAP_PRIVATE,
* change will not go back to file. mmap is copy on write, and we are using
* only the head space to store output, so kernel doesn't need to copy more
* than the words we saved--in this case, one page tops.
*/
memcpy(tail, word, len);
tail += len;
*tail = '\0';
}
printf(buf);
munmap(buf, st.st_size);
close(fd);
return 0;
munmap(buf, st.st_size);
close(fd);
return 0;
}