;;; Nani Project website

;;; Copyright © 2019 Julien Lepiller <julien@lepiller.eu>

;;;

;;; This file is part of the Nani Project website.

;;;

;;; The Nani Project website is free software; you can redistribute it and/or modify it

;;; under the terms of the GNU Affero General Public License as published by

;;; the Free Software Foundation; either version 3 of the License, or (at

;;; your option) any later version.

;;;

;;; The Nani Project website is distributed in the hope that it will be useful, but

;;; WITHOUT ANY WARRANTY; without even the implied warranty of

;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the

;;; GNU Affero General Public License for more details.

;;;

;;; You should have received a copy of the GNU Affero General Public License

;;; along with the Nani Project website.  If not, see <http://www.gnu.org/licenses/>.

(use-modules (nani jmdict trie))

(use-modules (nani jmdict serialize))

(use-modules (nani jmdict xml))

(use-modules (nani frequency))

(use-modules (nani trie))

(use-modules (nani result))

(use-modules (ice-9 match))

(use-modules (ice-9 binary-ports))

(define (convert input output)

  (let ((sxml (load-dic input)))

    (call-with-output-file output

      (lambda (port)

        (write sxml port)))))

(define (compile input sense-filter output)

  (let* ((frq (load-frequency "dictionaries/frequency.tsv"))

         (sxml (if (equal? (substring input (- (string-length input) 4)) ".xml")

                 (load-dic input)

                 (call-with-input-file input read)))

         (results (sxml->results sxml frq))

         (results (map (lambda (result)

                         (update-result

                           result

                           #:senses (filter sense-filter

                                            (result-senses result))))

                       results))

         (results (filter (lambda (result) (not (null? (result-senses result))))

                          results))

         (kanji-trie (compress-trie (make-kanji-trie results)))

         (reading-trie (compress-trie (make-reading-trie results)))

         (meaning-trie (compress-trie (make-meaning-trie results))))

    (format #t "Number of entries in ~a: ~a~%" output (length results))

    (call-with-output-file output

      (lambda (port)

        (put-bytevector port

          (serialize-jmdict results kanji-trie reading-trie meaning-trie))))))

(match (command-line)

  ((_ cmd input lang output)

   (cond

    ((equal? cmd "build")

     (if (equal? lang "e")

       (compile input (const #t) output)

       (compile input (lambda (sense) (equal? (sense-language sense) lang)) output)))

    ((equal? cmd "convert")

     (convert input output))

    (else (format #t "Unknown cmd ~a.~%" cmd)))))