axyseo 2.0.0-alpha.0.0.19 → 2.0.0-alpha.0.0.2

package/src/languageProcessing/languages/nb/config/internal/passiveVoiceAuxiliaries.js

@@ -0,0 +1,15 @@
+/**
+ * Returns a list with auxiliaries for the Spanish passive voice assessment.
+ * @returns {Array} The list with auxiliaries.
+ */
+export default [
+	"bli",
+	"blir",
+	"ble ",
+	"blei",
+	"blitt",
+	"bli",
+	"blivende",
+	"blis",
+	"er",
+];

package/src/languageProcessing/languages/nb/config/stopWords.js

@@ -0,0 +1,39 @@
+/**
+ * Returns a list with stopwords for the Norwegian passive voice assessment.
+ *
+ * @returns {Array}                 The list with stopwords.
+ */
+export default [
+	"dette",
+	"at",
+	"disse",
+	"på",
+	"unntatt",
+	"for",
+	"fra",
+	"i",
+	"om",
+	"ovenfor",
+	"på tvers",
+	"etter",
+	"mot",
+	"blant",
+	"rundt",
+	"som",
+	"på",
+	"før",
+	"bak",
+	"nedenfor",
+	"under",
+	"siden",
+	"mellom",
+	"utover",
+	"men",
+	"av",
+	"når",
+	"da",
+	"som",
+	"fordi ",
+	"ikke",
+	"og",
+];

package/src/languageProcessing/languages/nb/config/transitionWords.js

@@ -0,0 +1,21 @@
+/** @module config/transitionWords */
+
+export const singleWords = [ "også", "fortsatt", "derimot", "derfor", "faktisk", "endelig", "likevel", "følgelig", "likeså", "dessuten", "selvsagt",
+	"deretter", "men", "for", "fordi", "mens", "bare", "da", "dog", "enn", "ettersom", "før", "hvorpå", "inntil", "når", "omennskjønt", "samt",
+	"som", "uaktet", "pga.", "uansett", "foruten", "siden", "m.a.o", "attpåtil", "derved", "følgelig", "forøvrig", "iallfall", "imidlertid",
+	"især", "likefullt", "likeledes", "likeså", "likevel", "omsider", "samstundes", "samtidig", "sikkert", "således", "såleis", "særs", "ellers",
+	"enda", "dersom", "skjønt", "samme", "eansett", "etterpå", "generelt", "herav", "imens" ];
+
+export const multipleWords = [ "på den andre siden", "for øyeblikket", "i stedet", "i mellomtiden", "til slutt", "i tillegg", "i tilfelle",
+	"med mindre", "om enn", "om to strakser", "selv om", "på grunn av", "med hensyn til", "for eksempel", "en gang", "fremfor alt", "i alle fall",
+	"i et nøtteskall", "i hvert fall", "i mellomtiden", "med andre ord", "til dømes", "for øvrig", "i ettertid", "så langt", "på tross av",
+	"til tross for", "til tross for at ", "for at", "slik at", "i løpet av", "så at", "slik som", "så lenge", "så ofte", "så snart",
+	"etter hvert som", "så fremt", "så sant", "i fall", "for så vidt som", "fordi om", "enda om", "trass i at", "hvor så", "hva enn", "hvor enn",
+	"sånn at", "som om", "så som", "rett og slett ", "på samme måte", "etter hvert", "av dette følger", "i mellomtiden", "i dette tilfellet",
+	"i motsetning til", "som et resultat", "like viktig", "på grunn av det", "på den positive siden", "på den negative siden", "tvert imot",
+	"kort oppsummert", "i begge tilfeller" ];
+
+export const allWords = singleWords.concat( multipleWords );
+
+export default allWords;
+

package/src/languageProcessing/languages/nb/config/twoPartTransitionWords.js

@@ -0,0 +1,10 @@
+/** @module config/twoPartTransitionWords */
+
+/**
+ * Returns an array with two-part transition words to be used by the assessments.
+ * @type {Array} The array filled with two-part transition words.
+ */
+export default [ [ "både", "og" ], [ "enten", "eller" ], [ "verken", "eller" ], [ "jo", "dess" ], [ "dess", "dess" ], [ "jo", "desto" ],
+	[ "ikke bare", "men" ], [ "ikke bare", "også" ],
+];
+

package/src/languageProcessing/languages/nb/helpers/getClauses.js

@@ -0,0 +1,28 @@
+import {languageProcessing} from '../../../index';
+const {createRegexFromArray, getClauses} = languageProcessing;
+
+import NorwegianClause from '../values/Clause';
+import auxiliaries from '../config/internal/passiveVoiceAuxiliaries.js';
+import stopwords from '../config/stopWords.js';
+
+const options = {
+  Clause: NorwegianClause,
+  stopwords,
+  auxiliaries,
+  regexes: {
+    auxiliaryRegex: createRegexFromArray(auxiliaries),
+    stopwordRegex: createRegexFromArray(stopwords),
+    stopCharacterRegex: /([:,])(?=[ \n\r\t'"+\-»«‹›<>])/gi
+  }
+};
+
+/**
+ * Gets the clauses from a sentence by determining sentence breakers.
+ *
+ * @param {string} sentence The sentence to split up in clauses.
+ *
+ * @returns {Array} The array with all clauses that have an auxiliary.
+ */
+export default function getNorwegianClauses(sentence) {
+  return getClauses(sentence, options);
+}

package/src/languageProcessing/languages/nb/helpers/getStemmer.js

@@ -0,0 +1,22 @@
+import {get} from 'lodash';
+import {languageProcessing} from '../../../index';
+const {baseStemmer} = languageProcessing;
+
+import determineStem from './internal/stem';
+
+/**
+ * Returns the stemmer for a researcher.
+ *
+ * @param {Researcher} researcher The researcher.
+ *
+ * @returns {Function} The stemmer.
+ */
+export default function getStemmer(researcher) {
+  const morphologyData = get(researcher.getData('morphology'), 'nb', false);
+
+  if (morphologyData) {
+    return word => determineStem(word, morphologyData);
+  }
+
+  return baseStemmer;
+}

package/src/languageProcessing/languages/nb/helpers/internal/getParticiples.js

@@ -0,0 +1,24 @@
+import {languageProcessing} from '../../../index';
+const {getWords} = languageProcessing;
+
+import participles from '../../config/internal/participles.js';
+import {forEach, includes} from 'lodash';
+
+/**
+ * Creates an array of participles found in a clause.
+ *
+ * @param {string} clauseText   The clause to finds participles in.
+ *
+ * @returns {Array} The array with the participles.
+ */
+export default function(clauseText) {
+  const words = getWords(clauseText);
+  const foundParticiples = [];
+
+  forEach(words, function(word) {
+    if (includes(participles, word)) {
+      foundParticiples.push(word);
+    }
+  });
+  return foundParticiples;
+}

package/src/languageProcessing/languages/nb/helpers/internal/stem.js

@@ -0,0 +1,133 @@
+/*
+ * Copyright (c) 2001, Dr Martin Porter
+ * Copyright (c) 2002, Richard Boulton.
+ * All rights reserved.
+ *
+ *
+ * Redistribution and use in source and binary forms, with or without modification, are permitted provided that
+ * the following conditions are met:
+ *
+ * 1. Redistributions of source code must retain the above copyright notice, this list of conditions and
+ * the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright notice, this list of conditions and
+ * the following disclaimer in the documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of the copyright holder nor the names of its contributors may be used to endorse
+ * or promote products derived from this software without specific prior written permission.
+ *
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES,
+ * INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
+ * IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY,
+ * OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA,
+ * OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
+ * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE,
+ * EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+ */
+
+/**
+ * Determines the start index of the R1 region.
+ * R1 is the region after the first non-vowel following a vowel. It should include at least 3 letters.
+ *
+ * @param {string} word The word for which to determine the R1 region.
+ *
+ * @returns {number} The start index of the R1 region.
+ */
+const determineR1 = function( word ) {
+	// Start with matching first vowel and non-vowel.
+	let r1Index = word.search( /[aeiouyøåæ][^aeiouyøåæ]/ );
+	// Then add 2 since the R1 index is the index after the first vowel & non-vowel matched with the regex.
+	if ( r1Index !== -1 ) {
+		r1Index += 2;
+	}
+
+	// Adjust R1 so that the region preceding it includes at least 3 letters.
+	if ( r1Index !== -1 && r1Index < 3 ) {
+		r1Index = 3;
+	}
+
+	return r1Index;
+};
+
+/**
+ *  Searches and stems these suffixes if in R1: hetene, hetens, hetens, heten, heter, endes, ande, ende, edes, enes, ede,
+ *  ane, ene, ens, ers, ets, het, ast, en, ar, er, as, es, et, a, e. After stemming the suffix, it checks if the word
+ *  ends in -ert, if it is stem -t.
+ *  Searches and stems suffix -s if in R1 and if preceded by a valid precedence: b, c, d, f, g, h, j, l, m, n, o, p, r, t, v, y, z,
+ *  or k not preceded by a vowel.
+ *
+ * @param {string} word             The word to check.
+ * @param {number} r1Index          The start index of the R1.
+ * @param {Object} morphologyData   The morphology data file.
+ *
+ * @returns {string}    The stemmed word.
+ */
+const removeSuffixesStep1 = function( word, r1Index, morphologyData ) {
+	const suffixes1aIndex = word.search( new RegExp( morphologyData.externalStemmer.regexSuffixes1a ) );
+	if ( suffixes1aIndex >= r1Index && r1Index !== -1 ) {
+		let wordAfterStemming = word.substring( 0, suffixes1aIndex );
+		if ( /ert$/i.test( wordAfterStemming ) ) {
+			wordAfterStemming = wordAfterStemming.slice( 0, -1 );
+		}
+		return wordAfterStemming;
+	}
+
+	const suffixSIndex = word.search( /s$/ );
+	const suffixes1bIndex = word.search( new RegExp( morphologyData.externalStemmer.regexSuffixes1b ) );
+	if ( suffixSIndex >= r1Index && suffixes1bIndex !== -1 && r1Index !== -1 ) {
+		return word.slice( 0, -1 );
+	}
+
+
+	return word;
+};
+
+/**
+ * Searches for suffixes -ert/-dt/-vt and stems -t if the suffix is in R1.
+ *
+ * @param {string} word             The word to check.
+ * @param {number} r1Index          The start index of the R1.
+ * @param {Object} morphologyData   The morphology data file.
+ *
+ * @returns {string}    The stemmed word.
+ */
+const removeSuffixesStep2 = function( word, r1Index, morphologyData ) {
+	const suffixes2Index = word.search( new RegExp( morphologyData.externalStemmer.regexSuffixes2 ) );
+	if ( suffixes2Index >= r1Index && r1Index !== -1 ) {
+		word = word.slice( 0, -1 );
+	}
+	return word;
+};
+
+/**
+ * Searches and stems these suffixes if in R1: hetslov, eleg, elig, elov, slov, leg, eig, lig, els, lov, ig.
+ *
+ * @param {string} word             The word to check.
+ * @param {number} r1Index          The start index of the R1.
+ * @param {Object} morphologyData   The morphology data file.
+ *
+ * @returns {string}    The stemmed word.
+ */
+const removeSuffixesStep3 = function( word, r1Index, morphologyData ) {
+	const suffixes3Index = word.search( new RegExp( morphologyData.externalStemmer.regexSuffixes3 ) );
+	if ( suffixes3Index >= r1Index && r1Index !== -1 ) {
+		word = word.substring( 0, suffixes3Index );
+	}
+	return word;
+};
+
+/**
+ * Stems Norwegian words.
+ *
+ * @param {string} word             The word to check.
+ * @param {Object} morphologyData   The morphology data file.
+ *
+ * @returns {string}    The stemmed word.
+ */
+export default function stem( word, morphologyData ) {
+	let r1Index = -1;
+	for ( const step of [ removeSuffixesStep1, removeSuffixesStep2, removeSuffixesStep3 ] ) {
+		r1Index = determineR1( word );
+		word = step( word, r1Index, morphologyData );
+	}
+
+	return word;
+}

package/src/languageProcessing/languages/nb/values/Clause.js

@@ -0,0 +1,43 @@
+import {languageProcessing} from '../../../index';
+const {precedenceException, values} = languageProcessing;
+const {Clause} = values;
+
+import getParticiples from '../helpers/internal/getParticiples';
+import {cannotBeBetweenPassiveAuxiliaryAndParticiple} from '../../nb/config/functionWords';
+
+/**
+ * Creates a Clause object for the Norwegian language.
+ */
+class NorwegianClause extends Clause {
+  /**
+   * Constructor.
+   *
+   * @param {string} clauseText   The text of the clause.
+   * @param {Array} auxiliaries   The auxiliaries.
+   *
+   * @constructor
+   */
+  constructor(clauseText, auxiliaries) {
+    super(clauseText, auxiliaries);
+    this._participles = getParticiples(this.getClauseText());
+    this.checkParticiples();
+  }
+
+  /**
+   * Checks if any exceptions are applicable to this participle that would result in the clause not being passive.
+   * If no exceptions are found, the clause is passive.
+   *
+   * @returns { void }
+   */
+  checkParticiples() {
+    const clause = this.getClauseText();
+    const passiveParticiples = this.getParticiples().filter(
+      participle =>
+        !precedenceException(clause, participle, cannotBeBetweenPassiveAuxiliaryAndParticiple)
+    );
+
+    this.setPassive(passiveParticiples.length > 0);
+  }
+}
+
+export default NorwegianClause;

package/src/languageProcessing/languages/nl/Researcher.js

@@ -0,0 +1,48 @@
+import {languageProcessing} from '../../../index';
+const {AbstractResearcher} = languageProcessing;
+
+// All config
+import firstWordExceptions from './config/firstWordExceptions';
+import {all as functionWords} from './config/functionWords';
+import stopWords from './config/stopWords';
+import transitionWords from './config/transitionWords';
+import twoPartTransitionWords from './config/twoPartTransitionWords';
+import syllables from './config/syllables.json';
+import keyphraseLength from './config/keyphraseLength';
+
+// All helpers
+import getClauses from './helpers/getClauses';
+import getStemmer from './helpers/getStemmer';
+import fleschReadingScore from './helpers/calculateFleschReadingScore';
+
+/**
+ * The researcher contains all the researches, helpers, data, and config.
+ */
+export default class Researcher extends AbstractResearcher {
+  /**
+   * Constructor
+   * @param {Paper} paper The Paper object that is needed within the researches.
+   * @constructor
+   */
+  constructor(paper) {
+    super(paper);
+
+    Object.assign(this.config, {
+      language: 'nl',
+      passiveConstructionType: 'periphrastic',
+      firstWordExceptions,
+      functionWords,
+      stopWords,
+      transitionWords,
+      twoPartTransitionWords,
+      syllables,
+      keyphraseLength
+    });
+
+    Object.assign(this.helpers, {
+      getClauses,
+      getStemmer,
+      fleschReadingScore
+    });
+  }
+}

package/src/languageProcessing/languages/nl/config/firstWordExceptions.js

@@ -0,0 +1,15 @@
+/**
+ * Returns an array with exceptions for the sentence beginning researcher.
+ * @returns {Array} The array filled with exceptions.
+ */
+export default [
+	// Definite articles:
+	"de", "het",
+	// Indefinite articles:
+	"een",
+	// Numbers 1-10:
+	"één", "eén", "twee", "drie", "vier", "vijf", "zes", "zeven", "acht", "negen", "tien",
+	// Demonstrative pronouns:
+	"dit", "dat", "die", "deze",
+];
+

package/src/languageProcessing/languages/nl/config/functionWords.js

@@ -0,0 +1,233 @@
+import { singleWords as transitionWords } from "./transitionWords";
+import transformWordsWithHyphens from "../../../helpers/transform/transformWordsWithHyphens";
+
+/**
+ * Returns an array with exceptions for the prominent words researcher.
+ * @returns {Array} The array filled with exceptions.
+ */
+
+const articles = [ "de", "het", "een", "der", "des", "den" ];
+
+const cardinalNumerals = [
+	"eén", "één", "twee", "drie", "vier", "vijf", "zes", "zeven", "acht", "negen", "tien", "elf", "twaalf", "dertien",
+	"veertien", "vijftien", "zestien", "zeventien", "achttien", "negentien", "twintig", "honderd", "honderden", "duizend", "duizenden", "miljoen",
+	"miljoenen", "biljoen", "biljoenen",
+];
+
+const ordinalNumerals = [
+	"eerste", "tweede", "derde", "vierde", "vijfde", "zesde", "zevende", "achtste", "negende",
+	"tiende", "elfde", "twaalfde", "dertiende", "veertiende", "vijftiende", "zestiende", "zeventiende",
+	"achttiende", "negentiende", "twinstigste",
+];
+
+// 'Het' is already included in the list of articles.
+const personalPronounsNominative = [ "ik", "je", "jij", "hij", "ze", "we", "wij", "jullie", "zij", "u", "ge", "gij", "men" ];
+const personalPronounsAccusative = [ "mij", "jou", "hem", "haar", "hen", "hun", "uw" ];
+const demonstrativePronouns = [ "dit", "dat", "deze", "die", "zelf" ];
+
+// What to do with 'zijn', since it is also a verb?
+const possessivePronouns = [ "mijn", "mijne", "jouw", "jouwe", "zijne", "hare", "ons", "onze", "hunne", "uwe", "elkaars", "elkanders" ];
+const quantifiers = [
+	"alle", "sommige", "sommigen", "weinig", "weinige", "weinigen", "veel", "vele", "velen", "geen", "beetje",
+	"elke", "elk", "genoeg", "meer", "meest", "meeste", "meesten", "paar", "zoveel", "enkele", "enkelen", "zoveelste", "hoeveelste",
+	"laatste", "laatsten", "iedere", "allemaal", "zekere", "ander", "andere", "gene", "enig", "enige", "verscheidene",
+	"verschillende", "voldoende", "allerlei", "allerhande", "enerlei", "enerhande", "beiderlei", "beiderhande", "tweeërlei", "tweeërhande",
+	"drieërlei", "drieërhande", "velerlei", "velerhande", "menigerlei", "menigerhande", "enigerlei", "enigerhande", "generlei", "generhande",
+];
+
+const reflexivePronouns = [
+	"mezelf", "mijzelf", "jezelf", "jouzelf", "zichzelf", "haarzelf", "hemzelf", "onszelf", "julliezelf",
+	"henzelf", "hunzelf", "uzelf", "zich",
+];
+
+const reciprocalPronouns = [ "mekaar", "elkaar", "elkander", "mekander" ];
+
+const indefinitePronouns = [ "iedereen", "ieder", "eenieder", "alleman", "allen", "alles", "iemand", "niemand", "iets", "niets", "menigeen" ];
+
+const indefinitePronounsPossessive = [ "ieders", "aller", "iedereens", "eenieders" ];
+
+const relativePronouns = [ "welke", "welk", "wat", "wie", "wiens", "wier" ];
+
+const interrogativeProAdverbs = [ "hoe", "waarom", "waar", "hoezo", "hoeveel" ];
+
+const pronominalAdverbs = [
+	"daaraan", "daarachter", "daaraf", "daarbij", "daarbinnen", "daarboven", "daarbuiten", "daardoorheen",
+	"daarheen", "daarin", "daarjegens", "daarmede", "daarnaar", "daarnaartoe", "daaromtrent", "daaronder", "daarop", "daarover",
+	"daaroverheen", "daarrond", "daartegen", "daartussen", "daartussenuit", "daaruit", "daarvan", "daarvandaan", "eraan", "erachter",
+	"erachteraan", "eraf", "erbij", "erbinnen", "erboven", "erbuiten", "erdoor", "erdoorheen", "erheen", "erin", "erjegens", "ermede",
+	"ermee", "erna", "ernaar", "ernaartoe", "ernaast", "erom", "eromtrent", "eronder", "eronderdoor", "erop", "eropaf", "eropuit", "erover",
+	"eroverheen", "errond", "ertegen", "ertegenaan", "ertoe", "ertussen", "ertussenuit", "eruit", "ervan", "ervandaan", "ervandoor", "ervoor",
+	"hieraan", "hierachter", "hieraf", "hierbij", "hierbinnen", "hierboven", "hierbuiten", "hierdoor", "hierdoorheen", "hierheen", "hierin",
+	"hierjegens", "hierlangs", "hiermede", "hiermee", "hierna", "hiernaar", "hiernaartoe", "hiernaast", "hieromheen", "hieromtrent",
+	"hieronder", "hierop", "hierover", "hieroverheen", "hierrond", "hiertegen", "hiertoe", "hiertussen", "hiertussenuit", "hieruit", "hiervan",
+	"hiervandaan", "hiervoor", "vandaan", "waaraan", "waarachter", "waaraf", "waarbij", "waarboven", "waarbuiten", "waardoorheen",
+	"waarheen", "waarin", "waarjegens", "waarmede", "waarna", "waarnaar", "waarnaartoe", "waarnaast", "waarop", "waarover", "waaroverheen",
+	"waarrond", "waartegen", "waartegenin", "waartoe", "waartussen", "waartussenuit", "waaruit", "waarvan", "waarvandaan", "waarvoor",
+];
+
+const locativeAdverbs = [
+	"daar", "hier", "ginder", "daarginds", "ginds", "ver", "veraf", "ergens", "nergens", "overal", "dichtbij",
+	"kortbij",
+];
+
+const filteredPassiveAuxiliaries = [ "word", "wordt", "werd", "werden", "ben", "bent", "is", "was", "waren" ];
+
+const passiveAuxiliariesInfinitive = [ "worden", "zijn" ];
+
+const otherAuxiliaries = [
+	"heb", "hebt", "heeft", "hadden", "had", "kun", "kan", "kunt", "kon", "konden", "mag",
+	"mocht", "mochten", "dien", "dient", "diende", "dienden", "moet", "moest", "moesten", "ga", "gaat",
+	"ging", "gingen",
+];
+
+const otherAuxiliariesInfinitive = [ "hebben", "kunnen", "mogen", "dienen", "moeten", "gaan" ];
+
+// 'Vóórkomen' (appear) is not included, because we don't want to filter out 'voorkómen' (prevent).
+const copula = [
+	"blijkt", "blijk", "bleek", "bleken", "gebleken", "dunkt", "dunk", "dunkte", "dunkten",
+	"gedunkt", "heet", "heette", "heetten", "geheten", "lijkt", "lijk", "geleken", "leek", "leken",
+	"schijn", "schijnt", "scheen", "schenen", "toescheen", "toeschijnt", "toeschijn", "toeschenen",
+];
+
+const copulaInfinitive = [ "blijken", "dunken", "heten", "lijken", "schijnen", "toeschijnen" ];
+
+const prepositions = [
+	"à", "aan", "aangaande", "achter", "behalve", "behoudens", "beneden", "benevens", "benoorden", "benoordoosten", "benoordwesten",
+	"beoosten", "betreffende", "bewesten", "bezijden", "bezuiden", "bezuidoosten", "bezuidwesten", "bij", "binnen", "blijkens", "boven", "bovenaan",
+	"buiten", "circa", "conform", "contra", "cum", "dankzij", "door", "gedurende", "gezien", "in", "ingevolge", "inzake", "jegens", "krachtens",
+	"langs", "luidens", "met", "middels", "na", "naar", "naast", "nabij", "namens", "nevens", "niettegenstaande", "nopens", "om",
+	"omstreeks", "omtrent", "onder", "onderaan", "ongeacht", "onverminderd", "op", "over", "overeenkomstig", "per", "plus", "post",
+	"richting", "rond", "rondom", "spijts", "staande", "te", "tegen", "tegenover", "ten", "ter", "tijdens", "tot", "tussen",
+	"uit", "van", "vanaf", "vanuit", "versus", "via", "vis-à-vis", "volgens", "voor", "voorbij", "wegens", "zijdens",
+	"zonder",
+];
+
+// Many prepositional adverbs are already listed as preposition.
+const prepositionalAdverbs = [
+	"af", "heen", "mee", "toe", "achterop", "onderin", "voorin", "bovenop",
+	"buitenop", "achteraan", "onderop", "binnenin", "tevoren",
+];
+
+const coordinatingConjunctions = [ "en", "alsmede", "of", "ofwel", "en/of" ];
+
+/* 'Zowel' and 'als' are part of 'zowel...als', 'evenmin' is part of 'evenmin...als', 'zomin' is part of 'zomin...als',
+ 'hetzij' is part of 'hetzij...hetzij'. */
+const correlativeConjunctions = [ "zowel", "evenmin", "zomin", "hetzij" ];
+
+const subordinatingConjunctions = [
+	"vermits", "dewijl", "dorodien", "naardien", "nademaal", "overmits", "wijl", "eer",
+	"eerdat", "aleer", "vooraleer", "alvorens", "totdat", "zolang", "sinds", "sedert", "ingeval", "tenware", "alhoewel",
+	"hoezeer", "uitgezonderd", "zoverre", "zover", "naargelang", "naarmate", "alsof",
+];
+
+// These verbs are frequently used in interviews to indicate questions and answers.
+const interviewVerbs = [ "zegt", "zei", "vraagt", "vroeg", "denkt", "dacht", "stelt", "pleit", "pleitte" ];
+
+// These transition words were not included in the list for the transition word assessment for various reasons.
+const additionalTransitionWords = [
+	"absoluut", "zeker", "ongetwijfeld", "sowieso", "onmiddelijk", "meteen", "inclusief",
+	"direct", "ogenblikkelijk", "terstond", "natuurlijk", "vanzelfsprekend", "gewoonlijk", "normaliter",
+	"doorgaans", "werkelijk", "daadwerkelijk", "inderdaad", "waarachtig", "oprecht", "bijna", "meestal", "misschien",
+	"waarschijnlijk", "wellicht", "mogelijk", "vermoedelijk", "allicht", "aannemelijk", "oorspronkelijk", "aanvankelijk",
+	"initieel", "eigenlijk", "feitelijk", "wezenlijk", "juist", "reeds", "alvast", "bijv.", "vaak", "dikwijls", "veelal",
+	"geregeld", "menigmaal", "regelmatig", "veelvuldig", "eenvoudigweg", "simpelweg", "louter", "kortweg", "stomweg", "domweg", "zomaar",
+	"eventueel", "mogelijkerwijs", "eens", "weleens", "nooit", "ooit", "anders", "momenteel", "thans", "incidenteel", "trouwens", "elders",
+	"volgend", "recent", "onlangs", "recentelijk", "laatst", "zojuist", "relatief", "duidelijk", "overduidelijk", "klaarblijkelijk",
+	"nadrukkelijk", "ogenschijnlijk", "kennelijk", "schijnbaar", "alweer", "continu", "herhaaldelijk", "nog", "steeds", "nu",
+];
+
+// 'vrij' is not included because it also means 'free'.
+const intensifiers = [
+	"zeer", "erg", "redelijk", "flink", "tikkeltje", "bijzonder", "ernstig", "enigszins",
+	"zo", "tamelijk", "nogal", "behoorlijk", "zwaar", "heel", "hele", "reuze", "buitengewoon",
+	"ontzettend", "vreselijk",
+];
+
+// These verbs convey little meaning.
+const delexicalizedVerbs = [
+	"laat", "liet", "lieten", "kom", "komt", "kwam", "kwamen", "maakt",
+	"maak", "maakte", "maakten", "doe", "doet", "deed", "deden", "vindt", "vind", "vond", "vonden",
+];
+
+const delexicalizedVerbsInfinitive = [ "laten", "komen", "maken", "doen", "vinden" ];
+
+/* These adjectives and adverbs are so general, they should never be suggested as a (single) keyword.
+Keyword combinations containing these adjectives/adverbs are fine. */
+const generalAdjectivesAdverbs = [
+	"nieuw", "nieuwe", "nieuwer", "nieuwere", "nieuwst", "nieuwste", "oud", "oude", "ouder", "oudere",
+	"oudst", "oudste", "vorig", "vorige", "goed", "goede", "beter", "betere", "best", "beste", "groot", "grote", "groter", "grotere",
+	"grootst", "grootste", "makkelijk", "makkelijke", "makkelijker", "makkelijkere", "makkelijkst", "makkelijste", "gemakkelijk",
+	"gemakkelijke", "gemakkelijker", "gemakkelijkere", "gemakkelijkst", "gemakkelijste", "simpel", "simpele", "simpeler", "simpelere",
+	"simpelst", "simpelste", "snel", "snelle", "sneller", "snellere", "snelst", "snelste", "verre", "verder", "verdere", "verst",
+	"verste", "lang", "lange", "langer", "langere", "langst", "langste", "hard", "harde", "harder", "hardere", "hardst", "hardste",
+	"minder", "mindere", "minst", "minste", "eigen", "laag", "lage", "lager", "lagere", "laagst", "laagste", "hoog", "hoge", "hoger",
+	"hogere", "hoogst", "hoogste", "klein", "kleine", "kleiner", "kleinere", "kleinst", "kleinste", "kort", "korte", "korter", "kortere",
+	"kortst", "kortste", "herhaaldelijke", "directe", "ongeveer", "slecht", "slechte", "slechter", "slechtere", "slechtst",
+	"slechtste", "zulke", "zulk", "zo'n", "zulks", "er", "extreem", "extreme", "bijbehorende", "bijbehorend", "niet",
+];
+
+const interjections = [
+	"oh", "wauw", "hèhè", "hè", "hé", "au", "ai", "jaja", "welja", "jawel", "ssst", "heremijntijd", "hemeltjelief", "aha",
+	"foei", "hmm", "nou", "nee", "tja", "nja", "okido", "ho", "halt", "komaan", "komop", "verrek", "nietwaar", "brr", "oef",
+	"ach", "och", "bah", "enfin", "afijn", "haha", "hihi", "hatsjie", "hatsjoe", "hm", "tring", "vroem", "boem", "hopla",
+];
+
+// These words and abbreviations are frequently used in recipes in lists of ingredients.
+const recipeWords = [ "ml", "cl", "dl", "l", "tl", "el", "mg", "g", "gr", "kg", "ca", "theel", "min", "sec", "uur" ];
+
+const timeWords = [
+	"seconde", "secondes", "seconden", "minuut", "minuten", "uur", "uren", "dag", "dagen", "week", "weken",
+	"maand", "maanden", "jaar", "jaren", "vandaag", "morgen", "overmorgen", "gisteren", "eergisteren",
+	"'s", "morgens", "avonds", "middags", "nachts",
+];
+
+const vagueNouns = [
+	"ding", "dingen", "manier", "manieren", "item", "items", "keer", "maal", "procent", "geval", "aspect", "persoon",
+	"personen", "deel",
+];
+
+const miscellaneous = [ "wel", "ja", "neen", "oké", "oke", "okee", "ok", "zoiets", "€", "euro" ];
+
+const titlesPreceding = [ "mevr", "dhr", "mr", "dr", "prof" ];
+
+const titlesFollowing = [ "jr", "sr" ];
+
+
+// These word categories are filtered at the ending of word combinations.
+export const filteredAtBeginning = transformWordsWithHyphens( [].concat( passiveAuxiliariesInfinitive, otherAuxiliariesInfinitive, copulaInfinitive,
+	delexicalizedVerbsInfinitive ) );
+
+// These word categories are filtered at the ending of word combinations.
+export const filteredAtEnding = transformWordsWithHyphens( [].concat( ordinalNumerals, generalAdjectivesAdverbs ) );
+
+// These word categories are filtered at the beginning and ending of word combinations.
+export const filteredAtBeginningAndEnding = transformWordsWithHyphens( [].concat( articles, prepositions, coordinatingConjunctions,
+	demonstrativePronouns, intensifiers, quantifiers ) );
+
+// These word categories are filtered everywhere within word combinations.
+export const filteredAnywhere = transformWordsWithHyphens( [].concat( transitionWords, personalPronounsNominative, personalPronounsAccusative,
+	reflexivePronouns, interjections, cardinalNumerals, filteredPassiveAuxiliaries, otherAuxiliaries, copula, interviewVerbs,
+	delexicalizedVerbs, indefinitePronouns, correlativeConjunctions, subordinatingConjunctions, interrogativeProAdverbs, relativePronouns,
+	locativeAdverbs, miscellaneous, prepositionalAdverbs, pronominalAdverbs, recipeWords, timeWords, vagueNouns,
+	reciprocalPronouns, possessivePronouns ) );
+
+export const cannotDirectlyPrecedePassiveParticiple = transformWordsWithHyphens( [].concat( articles, interrogativeProAdverbs,
+	cardinalNumerals, possessivePronouns, reflexivePronouns, indefinitePronounsPossessive, copula, copulaInfinitive, prepositions ) );
+
+// This export contains all of the above words.
+export const all = transformWordsWithHyphens( [].concat( articles, cardinalNumerals, ordinalNumerals, demonstrativePronouns, possessivePronouns,
+	reflexivePronouns, reciprocalPronouns, personalPronounsNominative, personalPronounsAccusative, quantifiers, indefinitePronouns,
+	indefinitePronounsPossessive, relativePronouns, interrogativeProAdverbs,
+	pronominalAdverbs, locativeAdverbs, prepositionalAdverbs, filteredPassiveAuxiliaries, passiveAuxiliariesInfinitive,
+	otherAuxiliaries, otherAuxiliariesInfinitive, copula, copulaInfinitive, prepositions, coordinatingConjunctions,
+	correlativeConjunctions, subordinatingConjunctions, interviewVerbs,
+	transitionWords, additionalTransitionWords, intensifiers, delexicalizedVerbs, delexicalizedVerbsInfinitive,
+	interjections, generalAdjectivesAdverbs, recipeWords, vagueNouns, miscellaneous, timeWords, titlesPreceding, titlesFollowing ) );
+
+export default {
+	filteredAtEnding,
+	filteredAtBeginningAndEnding,
+	filteredAnywhere,
+	cannotDirectlyPrecedePassiveParticiple,
+	all,
+};