gistfile1.lisp

(defun get-file (filename)
  (with-open-file (stream filename)
    (loop for line = (read-line stream nil)
          while line
          collect line)))

(defvar *filename*
  "/Users/jacobsen/Programming/Lisp/commonlisp/word-pairs.txt")

(defun hash-keys (hash-table)
  (loop for key being the hash-keys of hash-table collect key))

(defun take (n s) (subseq s 0 n))

(defun split (string)
  ;; http://stackoverflow.com/questions/6152055/
  ;; common-lisp-the-fastest-way-to-read-the-stream
  (let ((space-position (position #\, string)))
    (list
     (subseq string 0 space-position)
     (subseq string (+ space-position 1)))))

(defun hash-keys (hash-table)
  (loop for key being the hash-keys of hash-table collect key))

(defun group-by (f s)
  (let ((h (make-hash-table :test 'equal)))
    (loop for el in s do
	 (let ((cur (gethash (funcall f el) h)))
	   (setf (gethash (car el) h) (cons el cur))))
    h))

(defun hash-pairs (h)
  (mapcar #'(lambda (k) (list k (gethash k h)))	(hash-keys h)))

;; (let* ((h (group-by #'car '((1 1) (0 2) (1 1) (2 5) (0 6)))))
;;   (hash-pairs h))
;;=> ((1 ((1 1) (1 1))) (0 ((0 6) (0 2))) (2 ((2 5))))

;; (let* ((s (take 10 (mapcar #'split (get-file *filename*))))
;;        (h (group-by #'car s)))
;;   (hash-keys h))
;;=> ("it" "was" "the" "best" "of" "times" "worst")

;; (length (hash-keys (group-by #'car (mapcar #'split (get-file *filename*)))))
;;=> 11707

(time
 (loop for i upto 9 do
      (setq result (group-by #'car (mapcar #'split (get-file *filename*))))))
;; 1.290 seconds