How to use wink-nlp-utils - 10 common examples

it( 'should throw error if config is not defined', function () {
    expect( bts.definePrepTasks.bind( null, [ prepare.string.lowerCase ] ) ).to.throw( 'winkBM25S: Config must be defined before defining prepTasks.' );
    // Config must be defined first to test remaining cases.
    bts.defineConfig( { fldWeights: { title: 4, body: 1, tags: 2 } } );
  } );
  var prepTasks = [

/* eslint no-console: 0 */
// Load wink-bm25-text-search
var bm25 = require( 'wink-bm25-text-search' );
// Create search engine's instance
var engine = bm25();
// Load NLP utilities
var nlp = require( 'wink-nlp-utils' );
// Load sample data (load any other JSON data instead of sample)
var docs = require( 'wink-bm25-text-search/sample-data/demo-data-for-wink-bm25.json' );

// Define preparatory task pipe!
var pipe = [
  nlp.string.lowerCase,
  nlp.string.tokenize0,
  nlp.tokens.removeWords,
  nlp.tokens.stem,
  nlp.tokens.propagateNegations
];
// Contains search query.
var query;

// Step I: Define config
// Only field weights are required in this example.
engine.defineConfig( { fldWeights: { title: 1, body: 2 } } );
// Step II: Define PrepTasks pipe.
// Set up 'default' preparatory tasks i.e. for everything else
engine.definePrepTasks( pipe );

// Step III: Add Docs
// Add documents now...

/* eslint no-console: 0 */
// Load wink-bm25-text-search
var bm25 = require( 'wink-bm25-text-search' );
// Create search engine's instance
var engine = bm25();
// Load NLP utilities
var nlp = require( 'wink-nlp-utils' );
// Load sample data (load any other JSON data instead of sample)
var docs = require( 'wink-bm25-text-search/sample-data/demo-data-for-wink-bm25.json' );

// Define preparatory task pipe!
var pipe = [
  nlp.string.lowerCase,
  nlp.string.tokenize0,
  nlp.tokens.removeWords,
  nlp.tokens.stem,
  nlp.tokens.propagateNegations
];
// Contains search query.
var query;

// Step I: Define config
// Only field weights are required in this example.
engine.defineConfig( { fldWeights: { title: 1, body: 2 } } );
// Step II: Define PrepTasks pipe.
// Set up 'default' preparatory tasks i.e. for everything else
engine.definePrepTasks( pipe );

// Step III: Add Docs

/* eslint no-console: 0 */
// Load wink-bm25-text-search
var bm25 = require( 'wink-bm25-text-search' );
// Create search engine's instance
var engine = bm25();
// Load NLP utilities
var nlp = require( 'wink-nlp-utils' );
// Load sample data (load any other JSON data instead of sample)
var docs = require( 'wink-bm25-text-search/sample-data/demo-data-for-wink-bm25.json' );

// Define preparatory task pipe!
var pipe = [
  nlp.string.lowerCase,
  nlp.string.tokenize0,
  nlp.tokens.removeWords,
  nlp.tokens.stem,
  nlp.tokens.propagateNegations
];
// Contains search query.
var query;

// Step I: Define config
// Only field weights are required in this example.
engine.defineConfig( { fldWeights: { title: 1, body: 2 } } );
// Step II: Define PrepTasks pipe.
// Set up 'default' preparatory tasks i.e. for everything else
engine.definePrepTasks( pipe );

// Step III: Add Docs
// Add documents now...
docs.forEach( function ( doc, i ) {

// Load wink-bm25-text-search
var bm25 = require( 'wink-bm25-text-search' );
// Create search engine's instance
var engine = bm25();
// Load NLP utilities
var nlp = require( 'wink-nlp-utils' );
// Load sample data (load any other JSON data instead of sample)
var docs = require( 'wink-bm25-text-search/sample-data/demo-data-for-wink-bm25.json' );

// Define preparatory task pipe!
var pipe = [
  nlp.string.lowerCase,
  nlp.string.tokenize0,
  nlp.tokens.removeWords,
  nlp.tokens.stem,
  nlp.tokens.propagateNegations
];
// Contains search query.
var query;

// Step I: Define config
// Only field weights are required in this example.
engine.defineConfig( { fldWeights: { title: 1, body: 2 } } );
// Step II: Define PrepTasks pipe.
// Set up 'default' preparatory tasks i.e. for everything else
engine.definePrepTasks( pipe );

// Step III: Add Docs
// Add documents now...
docs.forEach( function ( doc, i ) {
  // Note, 'i' becomes the unique id for 'doc'
  engine.addDoc( doc, i );

describe( 'definePrepTasks() Proper Cases', function () {
  var bts = bm25();
  bts.defineConfig( { fldWeights: { title: 4, body: 1, tags: 2 } } );
  var prepTasks = [
    { whenInputIs: [ prepare.string.tokenize0, prepare.string.stem ], expectedOutputIs: 2 },
    { whenInputIs: [ ], expectedOutputIs: 0 }
  ];

  prepTasks.forEach( function ( ptask ) {
    it( 'should return "' + ptask.expectedOutputIs + '" if the input is ' + JSON.stringify( ptask.whenInputIs ), function () {
      expect( bts.definePrepTasks( ptask.whenInputIs ) ).to.equal( ptask.expectedOutputIs );
    } );
  } );
} );

describe( 'definePrepTasks() Error Cases', function () {
  var prepTNBC = tnbc();
  var prepTasks = [
    { whenInputIs: [ prepare.string.incorrect, prepare.string.lowerCase ], expectedOutputIs: 'winkNBTC: each task should be a function, instead found: undefined' },
    { whenInputIs: null, expectedOutputIs: 'winkNBTC: tasks should be an array, instead found: null' },
    { whenInputIs: undefined, expectedOutputIs: 'winkNBTC: tasks should be an array, instead found: undefined' },
    { whenInputIs: 1, expectedOutputIs: 'winkNBTC: tasks should be an array, instead found: 1' },
    { whenInputIs: { a: 3 }, expectedOutputIs: 'winkNBTC: tasks should be an array, instead found: {"a":3}' }
  ];

  prepTasks.forEach( function ( ptask ) {
    it( 'should throw "' + ptask.expectedOutputIs + '" if the input is ' + JSON.stringify( ptask.whenInputIs ), function () {
      expect( prepTNBC.definePrepTasks.bind( null, ptask.whenInputIs ) ).to.throw( ptask.expectedOutputIs );
    } );
  } );
}
);

it( 'definePrepTasks should return 1', function () {
    expect( learnTNBC.definePrepTasks( [ prepare.string.tokenize0 ] ) ).to.equal( 1 );
  } );
  it( 'defineConfig should return true', function () {

describe( 'complete clean workflow test', function () {
  var bts = bm25();
  var prepTasks = [
    {
      whenInputIs: [ [
      prepare.string.lowerCase,
      prepare.string.removeExtraSpaces,
      prepare.string.tokenize0,
      prepare.tokens.stem,
      prepare.tokens.propagateNegations ] ],
      expectedOutputIs: 5
    },
    {
      whenInputIs: [ [
      prepare.string.lowerCase,
      prepare.string.removeExtraSpaces,
      prepare.string.tokenize0,
      prepare.tokens.propagateNegations,
      prepare.tokens.removeWords,
      prepare.tokens.stem ], 'body' ],
      expectedOutputIs: 6
    }
  ];

  it( 'defineConfig should return true when proper config is passed', function () {

{
      whenInputIs: [ [
      prepare.string.lowerCase,
      prepare.string.removeExtraSpaces,
      prepare.string.tokenize0,
      prepare.tokens.stem,
      prepare.tokens.propagateNegations ] ],
      expectedOutputIs: 5
    },
    {
      whenInputIs: [ [
      prepare.string.lowerCase,
      prepare.string.removeExtraSpaces,
      prepare.string.tokenize0,
      prepare.tokens.propagateNegations,
      prepare.tokens.removeWords,
      prepare.tokens.stem ], 'body' ],
      expectedOutputIs: 6
    }
  ];

  it( 'defineConfig should return true when proper config is passed', function () {
    var config = {
      fldWeights: {
         title: 4,
         body: 1,
         tags: 2
       },
       bm25Params: {
          k1: 1.2,
          k: 1,
          b: 0.75