lisp/soundex.el

   1 ;;; soundex.el --- implement Soundex algorithm
   2
   3 ;; Copyright (C) 1993, 2001, 2002, 2003, 2004, 2005,
   4 ;;   2006, 2007, 2008, 2009, 2010, 2011 Free Software Foundation, Inc.
   5
   6 ;; Author: Christian Plaunt <chris@bliss.berkeley.edu>
   7 ;; Maintainer: FSF
   8 ;; Keywords: matching
   9 ;; Created: Sat May 15 14:48:18 1993
  10
  11 ;; This file is part of GNU Emacs.
  12
  13 ;; GNU Emacs is free software: you can redistribute it and/or modify
  14 ;; it under the terms of the GNU General Public License as published by
  15 ;; the Free Software Foundation, either version 3 of the License, or
  16 ;; (at your option) any later version.
  17
  18 ;; GNU Emacs is distributed in the hope that it will be useful,
  19 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  20 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  21 ;; GNU General Public License for more details.
  22
  23 ;; You should have received a copy of the GNU General Public License
  24 ;; along with GNU Emacs.  If not, see <http://www.gnu.org/licenses/>.
  25
  26 ;;; Commentary:
  27
  28 ;; The Soundex algorithm maps English words into representations of
  29 ;; how they sound.  Words with vaguely similar sound map to the same string.
  30
  31 ;;; Code:
  32
  33 (defvar soundex-alist
  34   '((?B . "1") (?F . "1") (?P . "1") (?V . "1")
  35     (?C . "2") (?G . "2") (?J . "2") (?K . "2") (?Q . "2") (?S . "2")
  36     (?X . "2") (?Z . "2") (?D . "3") (?T . "3") (?L . "4") (?M . "5")
  37     (?N . "5") (?R . "6"))
  38   "Alist of chars-to-key-code for building Soundex keys.")
  39
  40 (defun soundex (word)
  41   "Return a Soundex key for WORD.
  42 Implemented as described in:
  43 Knuth, Donald E. \"The Art of Computer Programming, Vol. 3: Sorting
  44 and Searching\", Addison-Wesley (1973), pp. 391-392."
  45   (let* ((word (upcase word)) (length (length word))
  46          (code (cdr (assq (aref word 0) soundex-alist)))
  47          (key (substring word 0 1)) (index 1) (prev-code code))
  48     ;; once we have a four char key, we're done
  49     (while (and (> 4 (length key)) (< index length))
  50       ;; look up the code for each letter in word at index
  51       (setq code (cdr (assq (aref word index) soundex-alist))
  52             index (1+ index)
  53             ;; append code to key unless the same codes belong to
  54             ;; adjacent letters in the original string
  55             key (concat key (if (or (null code) (string= code prev-code))
  56                                 ()
  57                               code))
  58             prev-code code))
  59     ;; return a key that is 4 chars long and padded by "0"s if needed
  60     (if (> 4 (length key))
  61         (substring (concat key "000") 0 4)
  62       key)))
  63
  64 ;(defvar soundex-test
  65 ;  '("Euler" "Gauss" "Hilbert" "Knuth" "Lloyd" "Lukasiewicz"
  66 ;    "Ellery" "Ghosh" "Heilbronn" "Kant" "Ladd" "Lissajous")
  67 ;  "\n  Knuth's names to demonstrate the Soundex algorithm.")
  68 ;
  69 ;(mapcar 'soundex soundex-test)
  70 ;("E460" "G200" "H416" "K530" "L300" "L222"
  71 ; "E460" "G200" "H416" "K530" "L300" "L222")
  72
  73 (provide 'soundex)
  74
  75 ;;; soundex.el ends here