-
-
Save troelskn/5676916 to your computer and use it in GitHub Desktop.
Fixed to build on mac + 64 bit
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# C implementation of Levenshtein text distance algorithm, uses RubyInline to call from within Ruby | |
# Wildly faster than the Text gem's Text::Levenshtein | |
# Example: | |
# l = Levenshtein.new | |
# l.distance 'hello', ' hello' | |
# => 1 | |
# Taken from http://www.benallfree.com/2008/10/05/finding-duplicate-text-with-ruby/ | |
require 'inline' | |
class Levenshtein | |
inline do |builder| | |
builder.c " | |
#include <stdlib.h> | |
#if !defined(__APPLE__) | |
#include <malloc.h> | |
#endif | |
#include <string.h> | |
static long distance(char *s,char*t) | |
/*Compute levenshtein distance between s and t*/ | |
{ | |
//Step 1 | |
long min, k,i,j,n,m,cost,*d,distance; | |
n=strlen(s); | |
m=strlen(t); | |
if (n==0) return m; | |
if (m==0) return n; | |
d=malloc((sizeof(long))*(m+1)*(n+1)); | |
m++; | |
n++; | |
//Step 2 | |
for(k=0;k<n;k++) | |
{ | |
d[k]=k; | |
} | |
for(k=0;k<m;k++) | |
{ | |
d[k*n]=k; | |
} | |
//Step 3 and 4 | |
for(i=1;i<n;i++) | |
{ | |
for(j=1;j<m;j++) | |
{ | |
//Step 5 | |
if(s[i-1]==t[j-1]) | |
{ | |
cost=0; | |
} else { | |
cost=1; | |
} | |
//Step 6 | |
min = d[(j-1)*n+i]+1; | |
if (d[j*n+i-1]+1 < min) min=d[j*n+i-1]+1; | |
if (d[(j-1)*n+i-1]+cost < min) min=d[(j-1)*n+i-1]+cost; | |
d[j*n+i]=min; | |
} | |
} | |
distance=d[n*m-1]; | |
free(d); | |
return distance; | |
} | |
" | |
end | |
end |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment