Mercurial > emacs
annotate lisp/soundex.el @ 108319:c3a1d1b47790 EMACS_PRETEST_23_1_96
Bump version to 23.1.96.
author | Chong Yidong <cyd@stupidchicken.com> |
---|---|
date | Mon, 19 Apr 2010 21:29:37 -0400 |
parents | 1d1d5d9bd884 |
children | 376148b31b5e |
rev | line source |
---|---|
15261 | 1 ;;; soundex.el --- implement Soundex algorithm |
5995 | 2 |
74442 | 3 ;; Copyright (C) 1993, 2001, 2002, 2003, 2004, 2005, |
106815 | 4 ;; 2006, 2007, 2008, 2009, 2010 Free Software Foundation, Inc. |
5995 | 5 |
6 ;; Author: Christian Plaunt <chris@bliss.berkeley.edu> | |
49597
e88404e8f2cf
Trailing whitespace deleted.
Juanma Barranquero <lekktu@gmail.com>
parents:
38412
diff
changeset
|
7 ;; Maintainer: FSF |
5995 | 8 ;; Keywords: matching |
9 ;; Created: Sat May 15 14:48:18 1993 | |
10 | |
11 ;; This file is part of GNU Emacs. | |
12 | |
94678
ee5932bf781d
Switch to recommended form of GPLv3 permissions notice.
Glenn Morris <rgm@gnu.org>
parents:
93975
diff
changeset
|
13 ;; GNU Emacs is free software: you can redistribute it and/or modify |
5995 | 14 ;; it under the terms of the GNU General Public License as published by |
94678
ee5932bf781d
Switch to recommended form of GPLv3 permissions notice.
Glenn Morris <rgm@gnu.org>
parents:
93975
diff
changeset
|
15 ;; the Free Software Foundation, either version 3 of the License, or |
ee5932bf781d
Switch to recommended form of GPLv3 permissions notice.
Glenn Morris <rgm@gnu.org>
parents:
93975
diff
changeset
|
16 ;; (at your option) any later version. |
5995 | 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 | |
94678
ee5932bf781d
Switch to recommended form of GPLv3 permissions notice.
Glenn Morris <rgm@gnu.org>
parents:
93975
diff
changeset
|
24 ;; along with GNU Emacs. If not, see <http://www.gnu.org/licenses/>. |
5995 | 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 | |
38412
253f761ad37b
Some fixes to follow coding conventions in files maintained by FSF.
Pavel Janík <Pavel@Janik.cz>
parents:
18383
diff
changeset
|
31 ;;; Code: |
5995 | 32 |
7534
9b82dae27c01
(soundex-alist): Put variable before fn that uses it.
Richard M. Stallman <rms@gnu.org>
parents:
5995
diff
changeset
|
33 (defvar soundex-alist |
8028
ba1bbdb8595e
(soundex-alist): Delete the elements that mapped into nil.
Richard M. Stallman <rms@gnu.org>
parents:
7534
diff
changeset
|
34 '((?B . "1") (?F . "1") (?P . "1") (?V . "1") |
7534
9b82dae27c01
(soundex-alist): Put variable before fn that uses it.
Richard M. Stallman <rms@gnu.org>
parents:
5995
diff
changeset
|
35 (?C . "2") (?G . "2") (?J . "2") (?K . "2") (?Q . "2") (?S . "2") |
9b82dae27c01
(soundex-alist): Put variable before fn that uses it.
Richard M. Stallman <rms@gnu.org>
parents:
5995
diff
changeset
|
36 (?X . "2") (?Z . "2") (?D . "3") (?T . "3") (?L . "4") (?M . "5") |
9b82dae27c01
(soundex-alist): Put variable before fn that uses it.
Richard M. Stallman <rms@gnu.org>
parents:
5995
diff
changeset
|
37 (?N . "5") (?R . "6")) |
9b82dae27c01
(soundex-alist): Put variable before fn that uses it.
Richard M. Stallman <rms@gnu.org>
parents:
5995
diff
changeset
|
38 "Alist of chars-to-key-code for building Soundex keys.") |
9b82dae27c01
(soundex-alist): Put variable before fn that uses it.
Richard M. Stallman <rms@gnu.org>
parents:
5995
diff
changeset
|
39 |
5995 | 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)) | |
8028
ba1bbdb8595e
(soundex-alist): Delete the elements that mapped into nil.
Richard M. Stallman <rms@gnu.org>
parents:
7534
diff
changeset
|
48 ;; once we have a four char key, we're done |
5995 | 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 | |
18383 | 73 (provide 'soundex) |
74 | |
93975
1e3a407766b9
Fix up comment convention on the arch-tag lines.
Stefan Monnier <monnier@iro.umontreal.ca>
parents:
79721
diff
changeset
|
75 ;; arch-tag: b2615a98-feb7-430e-a717-171086738953 |
38412
253f761ad37b
Some fixes to follow coding conventions in files maintained by FSF.
Pavel Janík <Pavel@Janik.cz>
parents:
18383
diff
changeset
|
76 ;;; soundex.el ends here |