~amirouche/dwmt

9bdc2f04ee768cbbbbff4a08b8275b14ba9b0a1f — Amirouche 1 year, 11 months ago 65e5082 master
cosmit
2 files changed, 15 insertions(+), 21 deletions(-)

M dwmt.scm
M dwmt/aho-corasick.scm
M dwmt.scm => dwmt.scm +15 -17
@@ 183,21 183,19 @@

(pk 'searching2)


(time
 (let loop ()
   (call-with-values warc-record-reader
     (lambda (h body)
       (let ((matches (delete-duplicates
                       (aho-corasick-match ac body))))
         ;; (unless #f ;; (null? matches)
         ;;   (display total*) (display " ")
         ;;   (display (headers-ref h (string-downcase "WARC-Target-URI")))
         ;;   (display " ") (display matches) (newline)))))
         (when (fx<? 4 (length matches))
           (display (headers-ref h (string-downcase "WARC-Target-URI")))
           (newline)
           (set! count* (fx+ count* 1))))))
   (pk total* count*)
   (set! total* (fx+ total* 1))
   (loop)))
 (guard (ex (else (pk count*)))
   (let loop ()
     (call-with-values warc-record-reader
       (lambda (h body)
         (let ((matches (delete-duplicates
                         (aho-corasick-match ac body))))
           ;; (unless #f ;; (null? matches)
           ;;   (display total*) (display " ")
           ;;   (display (headers-ref h (string-downcase "WARC-Target-URI")))
           ;;   (display " ") (display matches) (newline)))))
           (when (fx<? 4 (length matches))
             (display ".")
             (set! count* (fx+ count* 1))))))
     (set! total* (fx+ total* 1))
     (loop))))

M dwmt/aho-corasick.scm => dwmt/aho-corasick.scm +0 -4
@@ 296,10 296,6 @@

    (define fallback (state-next root))

    (define (dg o)
      (unless (fx=? o 0)
        (pk o)))
    
    (unless (aho-corasick-finalized? aho-corasick)
      (error 'aho-corasick "aho-corasick is not finalized"))