lucene-tokenizers

Online Demo

Install:

npm install lucene-tokenizers

Example:

var lt = require('lucene-tokenizers');

var ts = new lt.StandardTokenizer();
ts.setReader(new lt.StringReader("Hello World!"));
var res = [], token = null;
while ((token = ts.incrementToken()) !== null) {
  var pretty_token = {};
  for (var prop in token) {
    if(token.hasOwnProperty(prop)) {
      pretty_token[prop.substring('_$esjava$'.length)] = token[prop];
    } 
  }
  res.push(pretty_token);
}

console.log(JSON.stringify(res, null, 2));

Output:

[
  {
    "text": "Hello",
    "type": "<ALPHANUM>",
    "start": 0,
    "positionIncrement": 1
  },
  {
    "text": "World",
    "type": "<ALPHANUM>",
    "start": 6,
    "positionIncrement": 1
  }
]

More about ESJava