How to use the stopword.getStopwords function in stopword

To help you get started, we’ve selected a few stopword examples, based on popular ways it is used in public projects.

Secure your code as it's written. Use Snyk Code to scan source code in minutes - no build needed - and fix issues immediately.

github fergiemcdowall / term-vector / lib / term-vector.js View on Github external
exports.getVector = function(text, options) {
  if (typeof text != "string")
    throw new Error("error: input must be a string");
  var defaults = {
    nGramLength: 1,
    separator: /[\|' \.,\-|(\n)]+/,
    stopwords: sw.getStopwords()
  }
  options = _.defaults(options || {}, defaults)
  if (options.nGramLength == 0)
    throw new Error("error: nGramLength must be greater than 0");
  //tokenise string, remove stopwords
  var tokens = sw.removeStopwords(text, {
    inputSeparator: options.separator,
    stopwords: options.stopwords
  }).split(' ');
  var vec = []
  if (!isNaN(options.nGramLength)) {
    return getTermVectorForNgramLength(tokens, options.nGramLength);
  }
  else if (options.nGramLength.constructor === Array) {
    for (var i = 0; i < options.nGramLength.length; i++)
      vec = vec.concat(getTermVectorForNgramLength(tokens, options.nGramLength[i]))
github fergiemcdowall / term-vector / lib / term-vector.js View on Github external
exports.getStopwords = function(lang) {
  return sw.getStopwords(lang);
}

stopword

A module for node.js and the browser that takes in text and returns text that is stripped of stopwords. Has pre-defined stopword lists for 62 languages and also takes lists with custom stopwords as input.

MIT
Latest version published 3 months ago

Package Health Score

84 / 100
Full package analysis