Subj : Re: Detecting if 2 names are probably the same
To   : comp.lang.smalltalk,comp.programming
From : Chris McDonald
Date : Wed Jul 20 2005 11:30 pm

"Rob Thorpe" <robert.thorpe@antenova.com> writes:

>Yes it would.  But after you've figured that out it would be useful to
>be able to detect things that are caused by minor typos and
>mispellings, since they would also be a problem.


Minor typos detected by the appended code.

______________________________________________________________________________ 
Dr Chris McDonald                          E: chris@csse.uwa.edu.au
Computer Science & Software Engineering    W: http://www.csse.uwa.edu.au/~chris
The University of Western Australia, M002  T: +618 6488 2533
Crawley, Western Australia, 6009           F: +618 6488 1089



#define	streq(s,t)	(strcmp(s,t)==0)

enum howbad	{EXACT,TRANSPOSE,MISMATCH,EXTRACHAR,MISSINGCHAR,HOPELESS} ;

enum howbad similar(s,t) char *s, *t;
{
    while(*s++ == *t)
	if(!*t++) return(EXACT);	/* exact match */
    if(*--s) {
	if(*t) {
	    if(s[1] && t[1] && *s == t[1] && *t == s[1] && streq(s+2,t+2))
		return(TRANSPOSE);	/* transposition */
	    if(streq(s+1,t+1))
		return(MISMATCH);	/* one char mismatch */
	}
	if(streq(s+1,t))
	    return(EXTRACHAR);		/* extra character */
    }
    if(*t && streq(s,t+1))
	return(MISSINGCHAR);		/* missing character */
    return(HOPELESS);			/* hopeless */
}

.