Last active
September 21, 2018 08:22
-
-
Save kreeben/13faea4b3e68dad6c9a50006a3b4675a to your computer and use it in GitHub Desktop.
Comparing text with Resin
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
using System; | |
using Sir.Store; | |
namespace Sir.StringCompare | |
{ | |
class Program | |
{ | |
static void Main(string[] args) | |
{ | |
var document1 = args[0]; | |
var document2 = args[1]; | |
var docNode1 = new VectorNode(document1); | |
var docNode2 = new VectorNode(document2); | |
var docAngle = docNode1.TermVector.CosAngle(docNode2.TermVector); | |
if (docAngle >= VectorNode.IdenticalAngle) | |
{ | |
Console.Write("{0} is very similar to {1} ({2}%)", document1, document2, docAngle*100); | |
} | |
else | |
{ | |
var tokenizer = new LatinTokenizer(); | |
var index1 = new VectorNode(); | |
foreach (var token in tokenizer.Tokenize(document1)) | |
{ | |
index1.Add(new VectorNode(token)); | |
} | |
float score = 0; | |
var count = 0; | |
foreach (var token in tokenizer.Tokenize(document2)) | |
{ | |
var node = index1.ClosestMatch(token, skipDirtyNodes:false); | |
score += node.Highscore; | |
count++; | |
} | |
var similarity = (score / count) * 100; | |
Console.WriteLine("{0} is {1}% similar to {2}", document1, similarity, document2); | |
Console.Read(); | |
} | |
} | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment