It is way too slow to read numbers from a file simply by using `read'
for example a txt file contains 10,000,000 line of numbers:
(define (gen-sample max k file)
(with-output-to-file
file
(lambda ()
(let lp ((k k))
(when (> k 0)
(display (random max)) (newline)
(lp (- k 1) ))))))
(gen-sample 999999999 10000000 "rnd.txt")
And read the numbers in
(define (read-test1)
(with-input-from-file
"rnd.txt"
(lambda ()
(let lp ((i (read)))
(if (not (eof-object? i))
(lp (read)))))))
scheme@(guile-user)> ,time (read-test1)
;; 37.348000s real time, 37.340000s run time. 0.450000s spent in GC.
with rdelim's read-line, it's better but still slow.
(import (ice-9 rdelim))
(define (read-test2)
(with-input-from-file
"rnd.txt"
(lambda ()
(let lp ((i (read-line)))
(if (not (eof-object? i))
(begin
(string->number i)
(lp (read-line))))))))
scheme@(guile-user)> ,time (read-test2)
;; 11.943000s real time, 11.930000s run time. 0.890000s spent in GC.
it only takes 1.8 seconds by using fscanf
FILE *f = fopen("rnd.txt", "r");
if (f == NULL) {
printf("open failed!");
exit(1);
}
long long i;
while (fscanf(f, "%lld", &i) != EOF) {
}
$ time ./read
real 0m1.844s
user 0m1.803s
sys 0m0.032s
Are there any primitives in Guile that is equivalent to C's scanf?
