X-Git-Url: http://git.shadowcat.co.uk/gitweb/gitweb.cgi?a=blobdiff_plain;f=lib%2FText%2FSoundex.pm;h=64a9e6507d56fbb5ac38bafb441b75e14d33041b;hb=a646417951941146b1ea568de33ca3508b9859a2;hp=655152347c3c669c575b3cd1764e899395aadcfc;hpb=a0d0e21ea6ea90a22318550944fe6cb09ae10cda;p=p5sagit%2Fp5-mst-13.2.git

diff --git a/lib/Text/Soundex.pm b/lib/Text/Soundex.pm
index 6551523..64a9e65 100644
--- a/lib/Text/Soundex.pm
+++ b/lib/Text/Soundex.pm
@@ -5,11 +5,13 @@ require Exporter;
 @ISA = qw(Exporter);
 @EXPORT = qw(&soundex $soundex_nocode);
 
+$VERSION = '1.01';
+
 # $Id: soundex.pl,v 1.2 1994/03/24 00:30:27 mike Exp $
 #
 # Implementation of soundex algorithm as described by Knuth in volume
 # 3 of The Art of Computer Programming, with ideas stolen from Ian
-# Phillips <ian@pipex.net>.
+# Phillipps <ian@pipex.net>.
 #
 # Mike Stok <Mike.Stok@meiko.concord.ma.us>, 2 March 1994.
 #
@@ -40,22 +42,15 @@ require Exporter;
 
 $soundex_nocode = undef;
 
-# soundex
-#
-# usage:
-#
-# @codes = &soundex (@wordList);
-# $code = &soundex ($word);
-#
-# This strenuously avoids 0
-
 sub soundex
 {
   local (@s, $f, $fc, $_) = @_;
 
+  push @s, '' unless @s;	# handle no args as a single empty string
+
   foreach (@s)
   {
-    tr/a-z/A-Z/;
+    $_ = uc $_;
     tr/A-Z//cd;
 
     if ($_ eq '')
@@ -80,3 +75,76 @@ sub soundex
 
 1;
 
+__END__
+
+=head1 NAME
+
+Text::Soundex - Implementation of the Soundex Algorithm as Described by Knuth
+
+=head1 SYNOPSIS
+
+  use Text::Soundex;
+
+  $code = soundex $string;            # get soundex code for a string
+  @codes = soundex @list;             # get list of codes for list of strings
+
+  # set value to be returned for strings without soundex code
+
+  $soundex_nocode = 'Z000';
+
+=head1 DESCRIPTION
+
+This module implements the soundex algorithm as described by Donald Knuth
+in Volume 3 of B<The Art of Computer Programming>.  The algorithm is
+intended to hash words (in particular surnames) into a small space using a
+simple model which approximates the sound of the word when spoken by an English
+speaker.  Each word is reduced to a four character string, the first
+character being an upper case letter and the remaining three being digits.
+
+If there is no soundex code representation for a string then the value of
+C<$soundex_nocode> is returned.  This is initially set to C<undef>, but
+many people seem to prefer an I<unlikely> value like C<Z000>
+(how unlikely this is depends on the data set being dealt with.)  Any value
+can be assigned to C<$soundex_nocode>.
+
+In scalar context C<soundex> returns the soundex code of its first
+argument, and in list context a list is returned in which each element is the 
+soundex code for the corresponding argument passed to C<soundex> e.g.
+
+  @codes = soundex qw(Mike Stok);
+
+leaves C<@codes> containing C<('M200', 'S320')>.
+
+=head1 EXAMPLES
+
+Knuth's examples of various names and the soundex codes they map to
+are listed below:
+
+  Euler, Ellery -> E460
+  Gauss, Ghosh -> G200
+  Hilbert, Heilbronn -> H416
+  Knuth, Kant -> K530
+  Lloyd, Ladd -> L300
+  Lukasiewicz, Lissajous -> L222
+
+so:
+
+  $code = soundex 'Knuth';              # $code contains 'K530'
+  @list = soundex qw(Lloyd Gauss);	# @list contains 'L300', 'G200'
+
+=head1 LIMITATIONS
+
+As the soundex algorithm was originally used a B<long> time ago in the US
+it considers only the English alphabet and pronunciation.
+
+As it is mapping a large space (arbitrary length strings) onto a small
+space (single letter plus 3 digits) no inference can be made about the
+similarity of two strings which end up with the same soundex code.  For 
+example, both C<Hilbert> and C<Heilbronn> end up with a soundex code
+of C<H416>.
+
+=head1 AUTHOR
+
+This code was implemented by Mike Stok (C<stok@cybercom.net>) from the 
+description given by Knuth.  Ian Phillipps (C<ian@pipex.net>) and Rich Pinder 
+(C<rpinder@hsc.usc.edu>) supplied ideas and spotted mistakes.