lisp/soundex.el

   1 ;;; soundex.el --- implement Soundex algorithm
   2
   3 ;; Copyright (C) 1993, 2002, 2003, 2004, 2005 Free Software Foundation, Inc.
   4
   5 ;; Author: Christian Plaunt <chris@bliss.berkeley.edu>
   6 ;; Maintainer: FSF
   7 ;; Keywords: matching
   8 ;; Created: Sat May 15 14:48:18 1993
   9
  10 ;; This file is part of GNU Emacs.
  11
  12 ;; GNU Emacs is free software; you can redistribute it and/or modify
  13 ;; it under the terms of the GNU General Public License as published by
  14 ;; the Free Software Foundation; either version 2, or (at your option)
  15 ;; any later version.
  16
  17 ;; GNU Emacs is distributed in the hope that it will be useful,
  18 ;; but WITHOUT ANY WARRANTY; without even the implied warranty of
  19 ;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  20 ;; GNU General Public License for more details.
  21
  22 ;; You should have received a copy of the GNU General Public License
  23 ;; along with GNU Emacs; see the file COPYING.  If not, write to the
  24 ;; Free Software Foundation, Inc., 51 Franklin Street, Fifth Floor,
  25 ;; Boston, MA 02110-1301, USA.
  26
  27 ;;; Commentary:
  28
  29 ;; The Soundex algorithm maps English words into representations of
  30 ;; how they sound.  Words with vaguely similar sound map to the same string.
  31
  32 ;;; Code:
  33
  34 (defvar soundex-alist
  35   '((?B . "1") (?F . "1") (?P . "1") (?V . "1")
  36     (?C . "2") (?G . "2") (?J . "2") (?K . "2") (?Q . "2") (?S . "2")
  37     (?X . "2") (?Z . "2") (?D . "3") (?T . "3") (?L . "4") (?M . "5")
  38     (?N . "5") (?R . "6"))
  39   "Alist of chars-to-key-code for building Soundex keys.")
  40
  41 (defun soundex (word)
  42   "Return a Soundex key for WORD.
  43 Implemented as described in:
  44 Knuth, Donald E. \"The Art of Computer Programming, Vol. 3: Sorting
  45 and Searching\", Addison-Wesley (1973), pp. 391-392."
  46   (let* ((word (upcase word)) (length (length word))
  47          (code (cdr (assq (aref word 0) soundex-alist)))
  48          (key (substring word 0 1)) (index 1) (prev-code code))
  49     ;; once we have a four char key, we're done
  50     (while (and (> 4 (length key)) (< index length))
  51       ;; look up the code for each letter in word at index
  52       (setq code (cdr (assq (aref word index) soundex-alist))
  53             index (1+ index)
  54             ;; append code to key unless the same codes belong to
  55             ;; adjacent letters in the original string
  56             key (concat key (if (or (null code) (string= code prev-code))
  57                                 ()
  58                               code))
  59             prev-code code))
  60     ;; return a key that is 4 chars long and padded by "0"s if needed
  61     (if (> 4 (length key))
  62         (substring (concat key "000") 0 4)
  63       key)))
  64
  65 ;(defvar soundex-test
  66 ;  '("Euler" "Gauss" "Hilbert" "Knuth" "Lloyd" "Lukasiewicz"
  67 ;    "Ellery" "Ghosh" "Heilbronn" "Kant" "Ladd" "Lissajous")
  68 ;  "\n  Knuth's names to demonstrate the Soundex algorithm.")
  69 ;
  70 ;(mapcar 'soundex soundex-test)
  71 ;("E460" "G200" "H416" "K530" "L300" "L222"
  72 ; "E460" "G200" "H416" "K530" "L300" "L222")
  73
  74 (provide 'soundex)
  75
  76 ;;; arch-tag: b2615a98-feb7-430e-a717-171086738953
  77 ;;; soundex.el ends here