Usenet 1993 July/InfoMagic USENET CD-ROM July 1993.ISO/sources/unix/volume11/soundslike

Internet Message Format | 1987-10-18 | 7.5 KB

Return-Path: @UUNET.UU.NET:sun!pyramid!prls![e-mail]
Message-Id: <[e-mail]>
Date: Wed, 30 Sep 87 16:51:45 pdt
From: Gordon Vickers <sun!prls![e-mail]>
To: [e-mail]
Subject: soundslike; LOOK(1) like program with soundex

This is another aid to those who can't spell .  It is similar to the basic
function of LOOK(1) but uses what I believe is the "soundex" algorithm.
The code is VERY tame so I would expect to to port easily though I am no
expert on such matters.  Comments, suggestions, etc are welcomed.


Gordon P. Vickers, [phone],             =======================
Signetics Corp.                                || Ultrix-32 ver 1.2 ||
PO Box 3409  M/S 69                            ||     VAX 11/750    ||
Sunnyvale, California,  USA  94086             =======================
{pyramid, philabs}!prls!gordon

[  I turned the formatted manpage into an unformatted one, along with
   light editing, and wrote a Makefile.  Feel free to take the latter
   as a prototype makefile for submissions...  Also, I don't know if
   this is true "soundex" or not -- and I don't care -- it works nicely.
   --r$  ]

#! /bin/sh
# This is a shell archive.  Remove anything before this line, then unpack
# it by saving it into a file and typing "sh file".  To overwrite existing
# files, type "sh file -c".  You can also feed this as standard input via
# unshar, or by typing "sh <file", e.g..  If this archive is complete, you
# will see the following message at the end:
#        "End of shell archive."
# Contents:  Makefile soundslike.1 soundslike.c
PATH=/bin:/usr/bin:/usr/ucb ; export PATH
if test -f 'Makefile' -a "${1}" != "-c" ; then
  echo shar: Will not clobber existing file \"'Makefile'\"
else
echo shar: Extracting \"'Makefile'\" \(178 characters\)
sed "s/^X//" >'Makefile' <<'END_OF_FILE'
X# Makefile for soundslike.
XCFLAGS    = -O
Xp    = soundslike
Xall:        $p $p.1
Xinstall:    all
X    @echo install $p and $p.1 according to local convention.
X
X$p:        $p.c
X    $(CC) $(CFLAGS) -o $p $p.c
END_OF_FILE
if test 178 -ne `wc -c <'Makefile'`; then
    echo shar: \"'Makefile'\" unpacked with wrong size!
fi
# end of 'Makefile'
fi
if test -f 'soundslike.1' -a "${1}" != "-c" ; then
  echo shar: Will not clobber existing file \"'soundslike.1'\"
else
echo shar: Extracting \"'soundslike.1'\" \(928 characters\)
sed "s/^X//" >'soundslike.1' <<'END_OF_FILE'
X.TH SOUNDSLIKE 1 LOCAL
X.SH NAME
Xsoundslike \- spell word based on what it sounds like
X.SH SYNOPSIS
X.B soundslike
Xword
X.br
X.B soundslike
X-filename word
X.br
X.B soundslike
Xword -filename
X.SH DESCRIPTION
X.I Soundslike
Xuses an implementation of the soundex algorithm.
XType the word in question as best as you can,
Xand the program will search a database for similar-sounding words.
XThe default database is normally
X.I /usr/dict/words
Xbut the user may specify any other file.
X.PP
XRegardless of which file is specified as the database, only the
Xfirst word of each line is tested against the users' word.
X.PP
XFor example,
X.RS
Xsoundslike butiful
X.RE
Xwill produce:
X.RS
Xbeautiful
Xbiddable
Xbotfly
X.RE
Xand
X.RS
Xsoundslike nessaccary
X.RE
Xproduces:
X.RS
Xnecessary
X.RE
X.SH RESTRICTIONS
XYou must be able to at least get the first letter correct.
X.SH AUTHOR
X.nf
XGordon P. Vickers
XSignetics Corp. , Sunnyvale, Ca.
X{pyramid, philabs}!prls!gordon
X.fi
END_OF_FILE
if test 928 -ne `wc -c <'soundslike.1'`; then
    echo shar: \"'soundslike.1'\" unpacked with wrong size!
fi
# end of 'soundslike.1'
fi
if test -f 'soundslike.c' -a "${1}" != "-c" ; then
  echo shar: Will not clobber existing file \"'soundslike.c'\"
else
echo shar: Extracting \"'soundslike.c'\" \(3557 characters\)
sed "s/^X//" >'soundslike.c' <<'END_OF_FILE'
X#include <stdio.h>
X#include <strings.h>
X
X/*******************************************************
X *  Soundex (like) filter.  Default database is DEFDB  *
X *     or user specifies with "-filename"              *
X *     syntex: soundex word                            *
X *             soundex -database word                  *
X *             soundex word -database                  *
X ******************************************************/
X
X#define DEFDB  "/usr/dict/words"   /* default database  */
X
Xmain(argc,argv)
X  int    argc;
X  char **argv;
X{
X   void mkcode(), syntex();
X   int i;
X   char c;
X   char dbname[BUFSIZ], word[BUFSIZ], s[BUFSIZ];
X   char dbword[BUFSIZ], dbcode[BUFSIZ];
X
X   sprintf(dbname,"%s",DEFDB);
X   if(argc == 1)
X      syntex(argv[0]);  /* print syntex help then exit */
X
X
X   for(i = 1; argv[i] != NULL; i++) {   /* process argument line */
X     if( argv[i][0] == '-')
X        sprintf(dbname,"%s",argv[i]);
X     else
X        sprintf(word,"%s",argv[i]);
X   }
X
X   if( !strlen(word) )
X        syntex(argv[0]);
X
X   if ( freopen(dbname,"r",stdin) == NULL ) {
X      perror(dbname);
X      exit(0);
X   }
X
X   /*  Sanity checks done.  Now, down to buisness */
X
X   c = word[0];
X   mkcode(word);
X
X   while( (gets(dbword) ) != NULL ) {
X       if( c < dbword[0] )    /* assumes database is in alphabetical order */
X           break;
X       else if (c > dbword[0])
X           continue;
X       else {
X          sscanf(dbword,"%s%*s",dbcode); /* isolate only first word     */
X          sprintf(dbword,"%s",dbcode);   /* truncate dbword to one word */
X          mkcode(dbcode);                /* convert to code             */
X           if( !strcmp(dbcode,word) )    /* check for exact code match  */
X             printf("%s\n",dbword);
X       }
X   }
X}
X
X/*********************************   MKCODE()  ****************************/
Xvoid mkcode(codeword)
X   char  *codeword;
X{
X    int i, j = 0;
X    int l;
X
X    l = strlen(codeword);
X    if(l <= 1){           /* this should probably return some snide remark */
X        codeword[l] = '\0';
X        return;
X    }
X
X    for(i = 1; codeword[i] != NULL; i++) {
X         if(codeword[i] == codeword[i - 1])
X             continue;
X         switch (codeword[i]) {
X             case 'b':
X             case 'f':
X             case 'p':
X             case 'v': codeword[j] = '1';
X                       j++;
X                       break;
X
X             case 'c':
X             case 'g':
X             case 'j':
X             case 'k':
X             case 'q':
X             case 's':
X             case 'x':
X             case 'z': codeword[j] = '2';
X                       j++;
X                       break;
X
X             case 'd':
X             case 't':  codeword[j] = '3';
X                        j++;
X                        break;
X
X             case 'l':  codeword[j] = '4';
X                        j++;
X                        break;
X
X             case 'm':
X             case 'n':  codeword[j] = '5';
X                        j++;
X                        break;
X
X             case 'r':  codeword[j] = '6';
X                        j++;
X                        break;
X
X             default :  break;
X        }
X     }
X     codeword[j] = '\0';
X     while( strlen(codeword) < 3 )  /* pad with zeroes til minimum length */
X        strcat(codeword,"0");
X
X
X}
X
X/*******************************   SYNTEX()   **************************/
Xvoid syntex(name)
X  char *name;
X{
X     printf("syntex:  %s word\n",name);
X     printf("    or   %s -database word\n",name);
X     printf("     or  %s word -database\n",name);
X     exit(0);
X}
END_OF_FILE
if test 3557 -ne `wc -c <'soundslike.c'`; then
    echo shar: \"'soundslike.c'\" unpacked with wrong size!
fi
# end of 'soundslike.c'
fi
echo shar: End of shell archive.
exit 0