axyseo 2.0.0-alpha.1

package/build/languageProcessing/languages/nl/helpers/internal/determineStem.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"determineStem.js","names":["_lodash","require","_index","_stem","_interopRequireDefault","_stemTOrDFromEndOfWord","e","__esModule","default","flattenSortLength","exceptionListHelpers","checkExceptionListWithTwoStems","languageProcessing","checkStrongVerbExceptionList","strongVerbsLists","stemmedWord","key","Object","keys","stemsSet","stems","flatten","values","includes","findStemOnVerbExceptionList","morphologyDataNL","prefixes","pastParticipleStemmer","compoundVerbsPrefixes","foundPrefix","find","prefix","startsWith","doNotStemPrefix","stemExceptions","stemmingExceptionsWithMultipleStems","strongAndIrregularVerbs","doNotStemPrefixException","exception","endsWith","stemmedWordWithoutPrefix","slice","length","strongVerbExceptions","strongVerbStems","strongVerbsExceptionLists","irregularStrongVerbs","regularStrongVerbs","bothRegularAndIrregularStrongVerbs","i","checkIfWordIsException","determineStem","word","stem","stemFromExceptionList","stemmingExceptionsWithTwoStems","ambiguousEndings","ambiguousTAndDEndings","tAndDEndings","ending","stemmedWordWithoutTOrD","stemTOrDFromEndOfWord"],"sources":["../../../../../../src/languageProcessing/languages/nl/helpers/internal/determineStem.js"],"sourcesContent":["import {flatten} from 'lodash';\nimport {languageProcessing} from '../../../index';\nconst {\n  flattenSortLength,\n  exceptionListHelpers: {checkExceptionListWithTwoStems}\n} = languageProcessing;\n\nimport stem from './stem';\nimport {stemTOrDFromEndOfWord} from './stemTOrDFromEndOfWord';\n\n/**\n * Checks if the word checked is in the list of strong verbs exceptions. If it is, only return the first stem from the stem set.\n * E.g. stems: help, hielp, geholp -> the stem returned would be \"help\".\n *\n * @param {Object} strongVerbsLists\tThe exception lists of strong verbs.\n * @param {string} stemmedWord The word to check.\n * @returns {string} The unique stem.\n */\nconst checkStrongVerbExceptionList = function(strongVerbsLists, stemmedWord) {\n  for (const key of Object.keys(strongVerbsLists)) {\n    for (const stemsSet of strongVerbsLists[key]) {\n      const stems = flatten(Object.values(stemsSet));\n      if (stems.includes(stemmedWord)) {\n        return stems[0];\n      }\n    }\n  }\n};\n\n/**\n * Checks if the word checked is in the list of strong verbs exceptions. Before checking, see if the word has a prefix and delete it if it does.\n * If the stem after prefix deletion is in the verb exception list, only return the first stem from the stem set and attach back the prefix.\n * E.g. words to check: verhielp, stem set: help, hielp, geholp -> the stem returned would be \"verhelp\".\n *\n * @param  {Object} morphologyDataNL \tThe Dutch morphology data file.\n * @param  {string} stemmedWord \t\tThe word to check.\n *\n * @returns {string} The unique stem.\n */\nconst findStemOnVerbExceptionList = function(morphologyDataNL, stemmedWord) {\n  const prefixes = flattenSortLength(morphologyDataNL.pastParticipleStemmer.compoundVerbsPrefixes);\n  // Check whether the inputted stem is started with one of the separable compound prefixes\n  let foundPrefix = prefixes.find(prefix => stemmedWord.startsWith(prefix));\n  const doNotStemPrefix =\n    morphologyDataNL.stemExceptions.stemmingExceptionsWithMultipleStems.strongAndIrregularVerbs\n      .doNotStemPrefix;\n  const doNotStemPrefixException = doNotStemPrefix.find(exception =>\n    stemmedWord.endsWith(exception)\n  );\n  let stemmedWordWithoutPrefix = '';\n\n  // Check whether the stemmedWord is in the list of strong verbs starting with be-, ont- or ver- that do not need to be stemmed.\n  if (doNotStemPrefixException) {\n    // Reset foundPrefix so that it won't be attached when the stem is found in the verb exception list.\n    foundPrefix = null;\n    // If the inputted stem is started with one of the separable compound prefixes, the prefix needs to be deleted for now.\n  } else if (foundPrefix) {\n    // Delete the prefix for now.\n    stemmedWordWithoutPrefix = stemmedWord.slice(foundPrefix.length, stemmedWord.length);\n    // At least 3 characters left after prefix deletion so that e.g. \"be\" is not found in the stem \"berg\".\n    if (stemmedWordWithoutPrefix.length > 2) {\n      stemmedWord = stemmedWordWithoutPrefix;\n    } else {\n      // Reset foundPrefix so that it won't be attached when the stem is found in the verb exception list.\n      foundPrefix = null;\n    }\n  }\n\n  const strongVerbExceptions =\n    morphologyDataNL.stemExceptions.stemmingExceptionsWithMultipleStems.strongAndIrregularVerbs\n      .strongVerbStems;\n  // Find stem strong verbs lists.\n  const strongVerbsExceptionLists = [\n    strongVerbExceptions.irregularStrongVerbs,\n    strongVerbExceptions.regularStrongVerbs,\n    strongVerbExceptions.bothRegularAndIrregularStrongVerbs\n  ];\n  for (let i = 0; i < strongVerbsExceptionLists.length; i++) {\n    const checkIfWordIsException = checkStrongVerbExceptionList(\n      strongVerbsExceptionLists[i],\n      stemmedWord\n    );\n    if (checkIfWordIsException) {\n      // If the word checked had a prefix previously, attach it back.\n      if (foundPrefix) {\n        return (\n          foundPrefix + checkStrongVerbExceptionList(strongVerbsExceptionLists[i], stemmedWord)\n        );\n      }\n      // If the word checked did not have a prefix previously, only return the first stem.\n      return checkStrongVerbExceptionList(strongVerbsExceptionLists[i], stemmedWord);\n    }\n  }\n};\n\n/**\n * Return the unique stem for a given Dutch input word.\n *\n * @param {string} word The word to be checked.\n * @param {Object} morphologyDataNL The Dutch data file.\n *\n * @returns {string} The unique stem.\n */\nexport default function determineStem(word, morphologyDataNL) {\n  const stemmedWord = stem(word, morphologyDataNL);\n\n  // Check whether the stemmed word is on an exception list of words with multiple stems. If it is, return the canonical stem.\n  let stemFromExceptionList = checkExceptionListWithTwoStems(\n    morphologyDataNL.stemExceptions.stemmingExceptionsWithMultipleStems\n      .stemmingExceptionsWithTwoStems,\n    stemmedWord\n  );\n  if (stemFromExceptionList) {\n    return stemFromExceptionList;\n  }\n  stemFromExceptionList = findStemOnVerbExceptionList(morphologyDataNL, stemmedWord);\n  if (stemFromExceptionList) {\n    return stemFromExceptionList;\n  }\n\n  // If the stemmed word ends in -t or -d, check whether it should be stemmed further, and return the stem with or without the -t/d.\n  const ambiguousEndings = morphologyDataNL.ambiguousTAndDEndings.tAndDEndings;\n  for (const ending of ambiguousEndings) {\n    if (stemmedWord.endsWith(ending)) {\n      const stemmedWordWithoutTOrD = stemTOrDFromEndOfWord(morphologyDataNL, stemmedWord, word);\n      if (stemmedWordWithoutTOrD) {\n        return stemmedWordWithoutTOrD;\n      }\n    }\n  }\n\n  return stemmedWord;\n}\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AACA,IAAAC,MAAA,GAAAD,OAAA;AAMA,IAAAE,KAAA,GAAAC,sBAAA,CAAAH,OAAA;AACA,IAAAI,sBAAA,GAAAJ,OAAA;AAA8D,SAAAG,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAN9D,MAAM;EACJG,iBAAiB;EACjBC,oBAAoB,EAAE;IAACC;EAA8B;AACvD,CAAC,GAAGC,yBAAkB;AAKtB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,4BAA4B,GAAG,SAAAA,CAASC,gBAAgB,EAAEC,WAAW,EAAE;EAC3E,KAAK,MAAMC,GAAG,IAAIC,MAAM,CAACC,IAAI,CAACJ,gBAAgB,CAAC,EAAE;IAC/C,KAAK,MAAMK,QAAQ,IAAIL,gBAAgB,CAACE,GAAG,CAAC,EAAE;MAC5C,MAAMI,KAAK,GAAG,IAAAC,eAAO,EAACJ,MAAM,CAACK,MAAM,CAACH,QAAQ,CAAC,CAAC;MAC9C,IAAIC,KAAK,CAACG,QAAQ,CAACR,WAAW,CAAC,EAAE;QAC/B,OAAOK,KAAK,CAAC,CAAC,CAAC;MACjB;IACF;EACF;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMI,2BAA2B,GAAG,SAAAA,CAASC,gBAAgB,EAAEV,WAAW,EAAE;EAC1E,MAAMW,QAAQ,GAAGjB,iBAAiB,CAACgB,gBAAgB,CAACE,qBAAqB,CAACC,qBAAqB,CAAC;EAChG;EACA,IAAIC,WAAW,GAAGH,QAAQ,CAACI,IAAI,CAACC,MAAM,IAAIhB,WAAW,CAACiB,UAAU,CAACD,MAAM,CAAC,CAAC;EACzE,MAAME,eAAe,GACnBR,gBAAgB,CAACS,cAAc,CAACC,mCAAmC,CAACC,uBAAuB,CACxFH,eAAe;EACpB,MAAMI,wBAAwB,GAAGJ,eAAe,CAACH,IAAI,CAACQ,SAAS,IAC7DvB,WAAW,CAACwB,QAAQ,CAACD,SAAS,CAChC,CAAC;EACD,IAAIE,wBAAwB,GAAG,EAAE;;EAEjC;EACA,IAAIH,wBAAwB,EAAE;IAC5B;IACAR,WAAW,GAAG,IAAI;IAClB;EACF,CAAC,MAAM,IAAIA,WAAW,EAAE;IACtB;IACAW,wBAAwB,GAAGzB,WAAW,CAAC0B,KAAK,CAACZ,WAAW,CAACa,MAAM,EAAE3B,WAAW,CAAC2B,MAAM,CAAC;IACpF;IACA,IAAIF,wBAAwB,CAACE,MAAM,GAAG,CAAC,EAAE;MACvC3B,WAAW,GAAGyB,wBAAwB;IACxC,CAAC,MAAM;MACL;MACAX,WAAW,GAAG,IAAI;IACpB;EACF;EAEA,MAAMc,oBAAoB,GACxBlB,gBAAgB,CAACS,cAAc,CAACC,mCAAmC,CAACC,uBAAuB,CACxFQ,eAAe;EACpB;EACA,MAAMC,yBAAyB,GAAG,CAChCF,oBAAoB,CAACG,oBAAoB,EACzCH,oBAAoB,CAACI,kBAAkB,EACvCJ,oBAAoB,CAACK,kCAAkC,CACxD;EACD,KAAK,IAAIC,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGJ,yBAAyB,CAACH,MAAM,EAAEO,CAAC,EAAE,EAAE;IACzD,MAAMC,sBAAsB,GAAGrC,4BAA4B,CACzDgC,yBAAyB,CAACI,CAAC,CAAC,EAC5BlC,WACF,CAAC;IACD,IAAImC,sBAAsB,EAAE;MAC1B;MACA,IAAIrB,WAAW,EAAE;QACf,OACEA,WAAW,GAAGhB,4BAA4B,CAACgC,yBAAyB,CAACI,CAAC,CAAC,EAAElC,WAAW,CAAC;MAEzF;MACA;MACA,OAAOF,4BAA4B,CAACgC,yBAAyB,CAACI,CAAC,CAAC,EAAElC,WAAW,CAAC;IAChF;EACF;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAASoC,aAAaA,CAACC,IAAI,EAAE3B,gBAAgB,EAAE;EAC5D,MAAMV,WAAW,GAAG,IAAAsC,aAAI,EAACD,IAAI,EAAE3B,gBAAgB,CAAC;;EAEhD;EACA,IAAI6B,qBAAqB,GAAG3C,8BAA8B,CACxDc,gBAAgB,CAACS,cAAc,CAACC,mCAAmC,CAChEoB,8BAA8B,EACjCxC,WACF,CAAC;EACD,IAAIuC,qBAAqB,EAAE;IACzB,OAAOA,qBAAqB;EAC9B;EACAA,qBAAqB,GAAG9B,2BAA2B,CAACC,gBAAgB,EAAEV,WAAW,CAAC;EAClF,IAAIuC,qBAAqB,EAAE;IACzB,OAAOA,qBAAqB;EAC9B;;EAEA;EACA,MAAME,gBAAgB,GAAG/B,gBAAgB,CAACgC,qBAAqB,CAACC,YAAY;EAC5E,KAAK,MAAMC,MAAM,IAAIH,gBAAgB,EAAE;IACrC,IAAIzC,WAAW,CAACwB,QAAQ,CAACoB,MAAM,CAAC,EAAE;MAChC,MAAMC,sBAAsB,GAAG,IAAAC,4CAAqB,EAACpC,gBAAgB,EAAEV,WAAW,EAAEqC,IAAI,CAAC;MACzF,IAAIQ,sBAAsB,EAAE;QAC1B,OAAOA,sBAAsB;MAC/B;IACF;EACF;EAEA,OAAO7C,WAAW;AACpB","ignoreList":[]}

package/build/languageProcessing/languages/nl/helpers/internal/getParticiples.js

@@ -0,0 +1,27 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = getParticiples;
+var _lodash = require("lodash");
+var _index = require("../../../index");
+var _passiveVoiceIrregulars = _interopRequireDefault(require("../../config/internal/passiveVoiceIrregulars"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+const {
+  getWords,
+  matchRegularParticiples
+} = _index.languageProcessing;
+/**
+ * Creates an array of participle for the participles found in a clause.
+ *
+ * @param {string} clauseText The clause text to find participles in.
+ *
+ * @returns {Array} The list with participle.
+ */
+function getParticiples(clauseText) {
+  const words = getWords(clauseText);
+  const regexes = [/^(ge|be|ont|ver|her|er)\S+([dt])($|[ \n\r\t.,'()"+\-;!?:/»«‹›<>])/gi, /^(aan|af|bij|binnen|los|mee|na|neer|om|onder|samen|terug|tegen|toe|uit|vast)(ge)\S+([dtn])($|[ \n\r\t.,'()"+\-;!?:/»«‹›<>])/gi];
+  return words.filter(word => matchRegularParticiples(word, regexes).length !== 0 || (0, _lodash.includes)(_passiveVoiceIrregulars.default, word));
+}
+//# sourceMappingURL=getParticiples.js.map

package/build/languageProcessing/languages/nl/helpers/internal/getParticiples.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getParticiples.js","names":["_lodash","require","_index","_passiveVoiceIrregulars","_interopRequireDefault","e","__esModule","default","getWords","matchRegularParticiples","languageProcessing","getParticiples","clauseText","words","regexes","filter","word","length","includes","irregularParticiples"],"sources":["../../../../../../src/languageProcessing/languages/nl/helpers/internal/getParticiples.js"],"sourcesContent":["import {includes} from 'lodash';\nimport {languageProcessing} from '../../../index';\nconst {getWords, matchRegularParticiples} = languageProcessing;\n\nimport irregularParticiples from '../../config/internal/passiveVoiceIrregulars';\n\n/**\n * Creates an array of participle for the participles found in a clause.\n *\n * @param {string} clauseText The clause text to find participles in.\n *\n * @returns {Array} The list with participle.\n */\nexport default function getParticiples(clauseText) {\n  const words = getWords(clauseText);\n  const regexes = [\n    /^(ge|be|ont|ver|her|er)\\S+([dt])($|[ \\n\\r\\t.,'()\"+\\-;!?:/»«‹›<>])/gi,\n    /^(aan|af|bij|binnen|los|mee|na|neer|om|onder|samen|terug|tegen|toe|uit|vast)(ge)\\S+([dtn])($|[ \\n\\r\\t.,'()\"+\\-;!?:/»«‹›<>])/gi\n  ];\n\n  return words.filter(\n    word =>\n      matchRegularParticiples(word, regexes).length !== 0 || includes(irregularParticiples, word)\n  );\n}\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AACA,IAAAC,MAAA,GAAAD,OAAA;AAGA,IAAAE,uBAAA,GAAAC,sBAAA,CAAAH,OAAA;AAAgF,SAAAG,uBAAAC,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAFhF,MAAM;EAACG,QAAQ;EAAEC;AAAuB,CAAC,GAAGC,yBAAkB;AAI9D;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAASC,cAAcA,CAACC,UAAU,EAAE;EACjD,MAAMC,KAAK,GAAGL,QAAQ,CAACI,UAAU,CAAC;EAClC,MAAME,OAAO,GAAG,CACd,qEAAqE,EACrE,+HAA+H,CAChI;EAED,OAAOD,KAAK,CAACE,MAAM,CACjBC,IAAI,IACFP,uBAAuB,CAACO,IAAI,EAAEF,OAAO,CAAC,CAACG,MAAM,KAAK,CAAC,IAAI,IAAAC,gBAAQ,EAACC,+BAAoB,EAAEH,IAAI,CAC9F,CAAC;AACH","ignoreList":[]}

package/build/languageProcessing/languages/nl/helpers/internal/getStemWordsWithTAndDEnding.js

@@ -0,0 +1,152 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.generateCorrectStemWithTAndDEnding = generateCorrectStemWithTAndDEnding;
+var _index = require("../../../index");
+var _stemModificationHelpers = require("./stemModificationHelpers");
+const {
+  regexHelpers: {
+    searchAndReplaceWithRegex,
+    doesWordMatchRegex
+  },
+  exceptionListHelpers: {
+    checkIfWordEndingIsOnExceptionList,
+    checkIfWordIsOnListThatCanHavePrefix
+  }
+} = _index.languageProcessing;
+/**
+ * Checks whether the word ends in suffixes -e or -en which are preceded by -t or -d, and the -t/-d is part of the stem.
+ * If it does, stem the -e/-en. Also checks if after suffix deletion the stemmed word needs modification, and applies it if
+ * needed. e.g. doden -> dod -> dood
+ *
+ * @param {Object} 		morphologyDataNL			 	The Dutch morphology data file.
+ * @param {string[]} 	regexAndReplacement				The regex to check and the string replacement that should be made.
+ * @param {string} 		word							The word to be checked.
+ *
+ * @returns {?string}							The stem created or null.
+ */
+const stemWordsWithEOrEnSuffix = function (morphologyDataNL, regexAndReplacement, word) {
+  if (doesWordMatchRegex(word, regexAndReplacement[0])) {
+    const stemmedWord = word.replace(new RegExp(regexAndReplacement[0]), regexAndReplacement[1]);
+    if ((0, _stemModificationHelpers.isVowelDoublingAllowed)(stemmedWord, morphologyDataNL.regularStemmer.stemModifications.exceptionsStemModifications, morphologyDataNL.pastParticipleStemmer.compoundVerbsPrefixes)) {
+      const replacement = searchAndReplaceWithRegex(stemmedWord, morphologyDataNL.regularStemmer.stemModifications.doubleVowel);
+      return replacement ? replacement : stemmedWord;
+    }
+    return stemmedWord;
+  }
+  return null;
+};
+
+/**
+ * Stems words for which we know that -t/-d is the ending of the stem (so the -t/-d is not stemmed). This is done through
+ * checking lists of words and matching the word with regexes.
+ *
+ * @param {string}	word								The word to check.
+ * @param {Object} 	morphologyDataNL 					The Dutch morphology data.
+ *
+ * @returns {?string} 							The stemmed word, if matched in one of the checks, or null if not matched.
+ */
+const checkWhetherTOrDIsPartOfStem = function (word, morphologyDataNL) {
+  const tAndDPartOfStemData = morphologyDataNL.ambiguousTAndDEndings.tOrDArePartOfStem;
+  /*
+   * Step 1:
+   * - If the stem ends in -tte, -tten, -dde or -dden leave the first -t/-d and stem the remaining ending.
+   * - Example: "katten" (-ten should be stemmed, leaving "kat").
+   */
+  let stemmedWord = searchAndReplaceWithRegex(word, tAndDPartOfStemData.firstTOrDPartOfStem);
+  if (stemmedWord) {
+    return stemmedWord;
+  }
+
+  /*
+   * Step 2:
+   * 2a)
+   * - Checks whether the word is in the exception list of verbal forms ending in long vowel + -fden/sden. If so, stems -den off.
+   * - Example: "hoefden" (-den should be stemmed, leaving "hoef").
+   * 2b)
+   * - Check whether the word has the suffix -en preceded by -d, where the -d is part of the stem. If it is, stem only -en.
+   * - Example: "eenden" (-en should be stemmed, leaving "eend").
+   */
+  if (tAndDPartOfStemData.verbsDenShouldBeStemmed.includes(word)) {
+    return word.slice(0, -3);
+  }
+  if (checkIfWordEndingIsOnExceptionList(word, tAndDPartOfStemData.wordsStemOnlyEnEnding.endingMatch) || checkIfWordIsOnListThatCanHavePrefix(word, tAndDPartOfStemData.wordsStemOnlyEnEnding.verbs, morphologyDataNL.pastParticipleStemmer.compoundVerbsPrefixes) || doesWordMatchRegex(word, tAndDPartOfStemData.denEnding)) {
+    stemmedWord = word.slice(0, -2);
+    //	Check if the vowel needs to be doubled after deleting suffix -en.
+    if ((0, _stemModificationHelpers.isVowelDoublingAllowed)(stemmedWord, morphologyDataNL.regularStemmer.stemModifications.exceptionsStemModifications, morphologyDataNL.pastParticipleStemmer.compoundVerbsPrefixes)) {
+      const replacement = searchAndReplaceWithRegex(stemmedWord, morphologyDataNL.regularStemmer.stemModifications.doubleVowel);
+      return replacement ? replacement : stemmedWord;
+    }
+    return stemmedWord;
+  }
+
+  /*
+   * Step 3:
+   * - Checks whether the word matches the regex for words ending in -de with -d being part of the stem. If it is matched,
+   * only stem the -e.
+   * - Example: "beenharde" (-e should be stemmed, leaving "beenhard")
+   */
+  const dIsPartOfStemRegex = tAndDPartOfStemData.deEnding;
+  stemmedWord = stemWordsWithEOrEnSuffix(morphologyDataNL, dIsPartOfStemRegex, word);
+  if (stemmedWord) {
+    return stemmedWord;
+  }
+
+  /*
+   * Step 4:
+   * - Checks whether the word matches the regex for words ending in -te or -ten with -t being part of the stem. If it is
+   * matched, only stem the -e/-en.
+   * - Example: "castraten" (-en should be stemmed, leaving "castraat")
+   */
+  const tIsPartOfStemRegex = tAndDPartOfStemData.teAndTenEndings;
+  stemmedWord = stemWordsWithEOrEnSuffix(morphologyDataNL, tIsPartOfStemRegex, word);
+  if (stemmedWord) {
+    return stemmedWord;
+  }
+  return null;
+};
+
+/**
+ * Creates the correct stem for words which end in ambiguous endings -t, -te, -ten, -de, or -den.
+ *
+ * @param {Object} 		morphologyDataNL 					The Dutch morphology data.
+ * @param {string} 		word								The word to be checked.
+ *
+ * @returns {?string} 	The stemmed word or null.
+ */
+function generateCorrectStemWithTAndDEnding(morphologyDataNL, word) {
+  /*
+   * Step 1:
+   * - Check whether the word is in the exception list of words in which -t ending needs to be stemmed. If it is, stem -t.
+   * - Example: "squasht".
+   * - This is an exception to one of the rule in step 2.
+   */
+  if (checkIfWordEndingIsOnExceptionList(word, morphologyDataNL.ambiguousTAndDEndings.wordsTShouldBeStemmed)) {
+    return word.slice(0, -1);
+  }
+
+  /*
+   * Step 2:
+   * - Check if word is matched by a regex for a t that shouldn't be stemmed.
+   * - Example: "boot".
+   */
+  if (doesWordMatchRegex(word, morphologyDataNL.ambiguousTAndDEndings.tOrDArePartOfStem.tEnding)) {
+    return word;
+  }
+
+  /*
+   * Step 3:
+   * - Check whether the word has another suffix that should be stemmed (e.g. -en) preceded by -t or -d which is part of the stem.
+   *  If yes, stem the suffix that should be stemmed and return the stem which ends in -t/-d.
+   * - Example: "tijden" (only -en should be removed, not -den).
+   */
+
+  const stemmedWord = checkWhetherTOrDIsPartOfStem(word, morphologyDataNL);
+  if (stemmedWord) {
+    return stemmedWord;
+  }
+  return null;
+}
+//# sourceMappingURL=getStemWordsWithTAndDEnding.js.map

package/build/languageProcessing/languages/nl/helpers/internal/getStemWordsWithTAndDEnding.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getStemWordsWithTAndDEnding.js","names":["_index","require","_stemModificationHelpers","regexHelpers","searchAndReplaceWithRegex","doesWordMatchRegex","exceptionListHelpers","checkIfWordEndingIsOnExceptionList","checkIfWordIsOnListThatCanHavePrefix","languageProcessing","stemWordsWithEOrEnSuffix","morphologyDataNL","regexAndReplacement","word","stemmedWord","replace","RegExp","isVowelDoublingAllowed","regularStemmer","stemModifications","exceptionsStemModifications","pastParticipleStemmer","compoundVerbsPrefixes","replacement","doubleVowel","checkWhetherTOrDIsPartOfStem","tAndDPartOfStemData","ambiguousTAndDEndings","tOrDArePartOfStem","firstTOrDPartOfStem","verbsDenShouldBeStemmed","includes","slice","wordsStemOnlyEnEnding","endingMatch","verbs","denEnding","dIsPartOfStemRegex","deEnding","tIsPartOfStemRegex","teAndTenEndings","generateCorrectStemWithTAndDEnding","wordsTShouldBeStemmed","tEnding"],"sources":["../../../../../../src/languageProcessing/languages/nl/helpers/internal/getStemWordsWithTAndDEnding.js"],"sourcesContent":["import {languageProcessing} from '../../../index';\nconst {\n  regexHelpers: {searchAndReplaceWithRegex, doesWordMatchRegex},\n  exceptionListHelpers: {checkIfWordEndingIsOnExceptionList, checkIfWordIsOnListThatCanHavePrefix}\n} = languageProcessing;\n\nimport {isVowelDoublingAllowed} from './stemModificationHelpers';\n\n/**\n * Checks whether the word ends in suffixes -e or -en which are preceded by -t or -d, and the -t/-d is part of the stem.\n * If it does, stem the -e/-en. Also checks if after suffix deletion the stemmed word needs modification, and applies it if\n * needed. e.g. doden -> dod -> dood\n *\n * @param {Object} \t\tmorphologyDataNL\t\t\t \tThe Dutch morphology data file.\n * @param {string[]} \tregexAndReplacement\t\t\t\tThe regex to check and the string replacement that should be made.\n * @param {string} \t\tword\t\t\t\t\t\t\tThe word to be checked.\n *\n * @returns {?string}\t\t\t\t\t\t\tThe stem created or null.\n */\nconst stemWordsWithEOrEnSuffix = function(morphologyDataNL, regexAndReplacement, word) {\n  if (doesWordMatchRegex(word, regexAndReplacement[0])) {\n    const stemmedWord = word.replace(new RegExp(regexAndReplacement[0]), regexAndReplacement[1]);\n    if (\n      isVowelDoublingAllowed(\n        stemmedWord,\n        morphologyDataNL.regularStemmer.stemModifications.exceptionsStemModifications,\n        morphologyDataNL.pastParticipleStemmer.compoundVerbsPrefixes\n      )\n    ) {\n      const replacement = searchAndReplaceWithRegex(\n        stemmedWord,\n        morphologyDataNL.regularStemmer.stemModifications.doubleVowel\n      );\n      return replacement ? replacement : stemmedWord;\n    }\n    return stemmedWord;\n  }\n\n  return null;\n};\n\n/**\n * Stems words for which we know that -t/-d is the ending of the stem (so the -t/-d is not stemmed). This is done through\n * checking lists of words and matching the word with regexes.\n *\n * @param {string}\tword\t\t\t\t\t\t\t\tThe word to check.\n * @param {Object} \tmorphologyDataNL \t\t\t\t\tThe Dutch morphology data.\n *\n * @returns {?string} \t\t\t\t\t\t\tThe stemmed word, if matched in one of the checks, or null if not matched.\n */\nconst checkWhetherTOrDIsPartOfStem = function(word, morphologyDataNL) {\n  const tAndDPartOfStemData = morphologyDataNL.ambiguousTAndDEndings.tOrDArePartOfStem;\n  /*\n   * Step 1:\n   * - If the stem ends in -tte, -tten, -dde or -dden leave the first -t/-d and stem the remaining ending.\n   * - Example: \"katten\" (-ten should be stemmed, leaving \"kat\").\n   */\n  let stemmedWord = searchAndReplaceWithRegex(word, tAndDPartOfStemData.firstTOrDPartOfStem);\n\n  if (stemmedWord) {\n    return stemmedWord;\n  }\n\n  /*\n   * Step 2:\n   * 2a)\n   * - Checks whether the word is in the exception list of verbal forms ending in long vowel + -fden/sden. If so, stems -den off.\n   * - Example: \"hoefden\" (-den should be stemmed, leaving \"hoef\").\n   * 2b)\n   * - Check whether the word has the suffix -en preceded by -d, where the -d is part of the stem. If it is, stem only -en.\n   * - Example: \"eenden\" (-en should be stemmed, leaving \"eend\").\n   */\n  if (tAndDPartOfStemData.verbsDenShouldBeStemmed.includes(word)) {\n    return word.slice(0, -3);\n  }\n\n  if (\n    checkIfWordEndingIsOnExceptionList(\n      word,\n      tAndDPartOfStemData.wordsStemOnlyEnEnding.endingMatch\n    ) ||\n    checkIfWordIsOnListThatCanHavePrefix(\n      word,\n      tAndDPartOfStemData.wordsStemOnlyEnEnding.verbs,\n      morphologyDataNL.pastParticipleStemmer.compoundVerbsPrefixes\n    ) ||\n    doesWordMatchRegex(word, tAndDPartOfStemData.denEnding)\n  ) {\n    stemmedWord = word.slice(0, -2);\n    //\tCheck if the vowel needs to be doubled after deleting suffix -en.\n    if (\n      isVowelDoublingAllowed(\n        stemmedWord,\n        morphologyDataNL.regularStemmer.stemModifications.exceptionsStemModifications,\n        morphologyDataNL.pastParticipleStemmer.compoundVerbsPrefixes\n      )\n    ) {\n      const replacement = searchAndReplaceWithRegex(\n        stemmedWord,\n        morphologyDataNL.regularStemmer.stemModifications.doubleVowel\n      );\n      return replacement ? replacement : stemmedWord;\n    }\n    return stemmedWord;\n  }\n\n  /*\n   * Step 3:\n   * - Checks whether the word matches the regex for words ending in -de with -d being part of the stem. If it is matched,\n   * only stem the -e.\n   * - Example: \"beenharde\" (-e should be stemmed, leaving \"beenhard\")\n   */\n  const dIsPartOfStemRegex = tAndDPartOfStemData.deEnding;\n  stemmedWord = stemWordsWithEOrEnSuffix(morphologyDataNL, dIsPartOfStemRegex, word);\n\n  if (stemmedWord) {\n    return stemmedWord;\n  }\n\n  /*\n   * Step 4:\n   * - Checks whether the word matches the regex for words ending in -te or -ten with -t being part of the stem. If it is\n   * matched, only stem the -e/-en.\n   * - Example: \"castraten\" (-en should be stemmed, leaving \"castraat\")\n   */\n  const tIsPartOfStemRegex = tAndDPartOfStemData.teAndTenEndings;\n  stemmedWord = stemWordsWithEOrEnSuffix(morphologyDataNL, tIsPartOfStemRegex, word);\n\n  if (stemmedWord) {\n    return stemmedWord;\n  }\n\n  return null;\n};\n\n/**\n * Creates the correct stem for words which end in ambiguous endings -t, -te, -ten, -de, or -den.\n *\n * @param {Object} \t\tmorphologyDataNL \t\t\t\t\tThe Dutch morphology data.\n * @param {string} \t\tword\t\t\t\t\t\t\t\tThe word to be checked.\n *\n * @returns {?string} \tThe stemmed word or null.\n */\nexport function generateCorrectStemWithTAndDEnding(morphologyDataNL, word) {\n  /*\n   * Step 1:\n   * - Check whether the word is in the exception list of words in which -t ending needs to be stemmed. If it is, stem -t.\n   * - Example: \"squasht\".\n   * - This is an exception to one of the rule in step 2.\n   */\n  if (\n    checkIfWordEndingIsOnExceptionList(\n      word,\n      morphologyDataNL.ambiguousTAndDEndings.wordsTShouldBeStemmed\n    )\n  ) {\n    return word.slice(0, -1);\n  }\n\n  /*\n   * Step 2:\n   * - Check if word is matched by a regex for a t that shouldn't be stemmed.\n   * - Example: \"boot\".\n   */\n  if (doesWordMatchRegex(word, morphologyDataNL.ambiguousTAndDEndings.tOrDArePartOfStem.tEnding)) {\n    return word;\n  }\n\n  /*\n   * Step 3:\n   * - Check whether the word has another suffix that should be stemmed (e.g. -en) preceded by -t or -d which is part of the stem.\n   *  If yes, stem the suffix that should be stemmed and return the stem which ends in -t/-d.\n   * - Example: \"tijden\" (only -en should be removed, not -den).\n   */\n\n  const stemmedWord = checkWhetherTOrDIsPartOfStem(word, morphologyDataNL);\n\n  if (stemmedWord) {\n    return stemmedWord;\n  }\n\n  return null;\n}\n"],"mappings":";;;;;;AAAA,IAAAA,MAAA,GAAAC,OAAA;AAMA,IAAAC,wBAAA,GAAAD,OAAA;AALA,MAAM;EACJE,YAAY,EAAE;IAACC,yBAAyB;IAAEC;EAAkB,CAAC;EAC7DC,oBAAoB,EAAE;IAACC,kCAAkC;IAAEC;EAAoC;AACjG,CAAC,GAAGC,yBAAkB;AAItB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,wBAAwB,GAAG,SAAAA,CAASC,gBAAgB,EAAEC,mBAAmB,EAAEC,IAAI,EAAE;EACrF,IAAIR,kBAAkB,CAACQ,IAAI,EAAED,mBAAmB,CAAC,CAAC,CAAC,CAAC,EAAE;IACpD,MAAME,WAAW,GAAGD,IAAI,CAACE,OAAO,CAAC,IAAIC,MAAM,CAACJ,mBAAmB,CAAC,CAAC,CAAC,CAAC,EAAEA,mBAAmB,CAAC,CAAC,CAAC,CAAC;IAC5F,IACE,IAAAK,+CAAsB,EACpBH,WAAW,EACXH,gBAAgB,CAACO,cAAc,CAACC,iBAAiB,CAACC,2BAA2B,EAC7ET,gBAAgB,CAACU,qBAAqB,CAACC,qBACzC,CAAC,EACD;MACA,MAAMC,WAAW,GAAGnB,yBAAyB,CAC3CU,WAAW,EACXH,gBAAgB,CAACO,cAAc,CAACC,iBAAiB,CAACK,WACpD,CAAC;MACD,OAAOD,WAAW,GAAGA,WAAW,GAAGT,WAAW;IAChD;IACA,OAAOA,WAAW;EACpB;EAEA,OAAO,IAAI;AACb,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMW,4BAA4B,GAAG,SAAAA,CAASZ,IAAI,EAAEF,gBAAgB,EAAE;EACpE,MAAMe,mBAAmB,GAAGf,gBAAgB,CAACgB,qBAAqB,CAACC,iBAAiB;EACpF;AACF;AACA;AACA;AACA;EACE,IAAId,WAAW,GAAGV,yBAAyB,CAACS,IAAI,EAAEa,mBAAmB,CAACG,mBAAmB,CAAC;EAE1F,IAAIf,WAAW,EAAE;IACf,OAAOA,WAAW;EACpB;;EAEA;AACF;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACE,IAAIY,mBAAmB,CAACI,uBAAuB,CAACC,QAAQ,CAAClB,IAAI,CAAC,EAAE;IAC9D,OAAOA,IAAI,CAACmB,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC;EAC1B;EAEA,IACEzB,kCAAkC,CAChCM,IAAI,EACJa,mBAAmB,CAACO,qBAAqB,CAACC,WAC5C,CAAC,IACD1B,oCAAoC,CAClCK,IAAI,EACJa,mBAAmB,CAACO,qBAAqB,CAACE,KAAK,EAC/CxB,gBAAgB,CAACU,qBAAqB,CAACC,qBACzC,CAAC,IACDjB,kBAAkB,CAACQ,IAAI,EAAEa,mBAAmB,CAACU,SAAS,CAAC,EACvD;IACAtB,WAAW,GAAGD,IAAI,CAACmB,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC;IAC/B;IACA,IACE,IAAAf,+CAAsB,EACpBH,WAAW,EACXH,gBAAgB,CAACO,cAAc,CAACC,iBAAiB,CAACC,2BAA2B,EAC7ET,gBAAgB,CAACU,qBAAqB,CAACC,qBACzC,CAAC,EACD;MACA,MAAMC,WAAW,GAAGnB,yBAAyB,CAC3CU,WAAW,EACXH,gBAAgB,CAACO,cAAc,CAACC,iBAAiB,CAACK,WACpD,CAAC;MACD,OAAOD,WAAW,GAAGA,WAAW,GAAGT,WAAW;IAChD;IACA,OAAOA,WAAW;EACpB;;EAEA;AACF;AACA;AACA;AACA;AACA;EACE,MAAMuB,kBAAkB,GAAGX,mBAAmB,CAACY,QAAQ;EACvDxB,WAAW,GAAGJ,wBAAwB,CAACC,gBAAgB,EAAE0B,kBAAkB,EAAExB,IAAI,CAAC;EAElF,IAAIC,WAAW,EAAE;IACf,OAAOA,WAAW;EACpB;;EAEA;AACF;AACA;AACA;AACA;AACA;EACE,MAAMyB,kBAAkB,GAAGb,mBAAmB,CAACc,eAAe;EAC9D1B,WAAW,GAAGJ,wBAAwB,CAACC,gBAAgB,EAAE4B,kBAAkB,EAAE1B,IAAI,CAAC;EAElF,IAAIC,WAAW,EAAE;IACf,OAAOA,WAAW;EACpB;EAEA,OAAO,IAAI;AACb,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACO,SAAS2B,kCAAkCA,CAAC9B,gBAAgB,EAAEE,IAAI,EAAE;EACzE;AACF;AACA;AACA;AACA;AACA;EACE,IACEN,kCAAkC,CAChCM,IAAI,EACJF,gBAAgB,CAACgB,qBAAqB,CAACe,qBACzC,CAAC,EACD;IACA,OAAO7B,IAAI,CAACmB,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC;EAC1B;;EAEA;AACF;AACA;AACA;AACA;EACE,IAAI3B,kBAAkB,CAACQ,IAAI,EAAEF,gBAAgB,CAACgB,qBAAqB,CAACC,iBAAiB,CAACe,OAAO,CAAC,EAAE;IAC9F,OAAO9B,IAAI;EACb;;EAEA;AACF;AACA;AACA;AACA;AACA;;EAEE,MAAMC,WAAW,GAAGW,4BAA4B,CAACZ,IAAI,EAAEF,gBAAgB,CAAC;EAExE,IAAIG,WAAW,EAAE;IACf,OAAOA,WAAW;EACpB;EAEA,OAAO,IAAI;AACb","ignoreList":[]}

package/build/languageProcessing/languages/nl/helpers/internal/stem.js

@@ -0,0 +1,131 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = stem;
+var _index = require("../../../index");
+var _detectAndStemSuffixes = _interopRequireDefault(require("./detectAndStemSuffixes"));
+var _getStemWordsWithTAndDEnding = require("./getStemWordsWithTAndDEnding.js");
+var _checkExceptionsWithFullForms = _interopRequireDefault(require("./checkExceptionsWithFullForms"));
+var _detectAndStemRegularParticiple = require("./detectAndStemRegularParticiple");
+var _stemModificationHelpers = require("./stemModificationHelpers");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+const {
+  exceptionListHelpers: {
+    checkIfWordEndingIsOnExceptionList,
+    checkIfWordIsOnListThatCanHavePrefix
+  },
+  stemHelpers: {
+    removeSuffixFromFullForm,
+    removeSuffixesFromFullForm
+  }
+} = _index.languageProcessing;
+/**
+ * Get the stem from noun diminutives and plurals exceptions.
+ *
+ * @param {Object}    morphologyDataNL The data for stemming exception.
+ * @param {string}      word                                The word to check.
+ *
+ * @returns {string} The stemmed word.
+ */
+const removeSuffixFromFullForms = function (morphologyDataNL, word) {
+  /*
+   * Checks whether the word is in the exception list of words ending in -er and gets either -e or -s suffix
+   * If it is, remove the corresponding suffix.
+   * e.g. lekkere -> lekker, bitters -> bitter
+   */
+  for (const exceptionClass of morphologyDataNL.stemExceptions.removeSuffixesFromFullForms) {
+    const stemmedWord = removeSuffixesFromFullForm(exceptionClass.forms, exceptionClass.suffixes, word);
+    if (stemmedWord) {
+      return stemmedWord;
+    }
+  }
+  /*
+   * Checks whether the word is in one of the exception lists of nouns
+   * for which a specific suffix needs to be stemmed (e.g. -s, -es, -eren, -er etc.)
+   * e.g. kuddes -> kud, modes -> mod, revenuen -> revenu
+   */
+  for (const exceptionClass of morphologyDataNL.stemExceptions.removeSuffixFromFullForms) {
+    const stemmedWord = removeSuffixFromFullForm(exceptionClass.forms, exceptionClass.suffix, word);
+    if (stemmedWord) {
+      return stemmedWord;
+    }
+  }
+};
+
+/**
+ * Checks if the word is on a stemming exception list.
+ *
+ * @param {string} word The word to check.
+ * @param {Object} morphologyDataNL The Dutch morphology data file.
+ * @returns {string|null} The stem or null if the word was not matched by any of the exception checks.
+ */
+const checkOtherStemmingExceptions = function (word, morphologyDataNL) {
+  /*
+   * Checks whether the word is in the exception list of nouns or adjectives with specific suffixes that needs to be stemmed.
+   * If it is return the stem here and run possible stem modification if it is required. e.g. modes -> mod -> mood
+   */
+  let stemFromFullForm = removeSuffixFromFullForms(morphologyDataNL, word);
+  if (stemFromFullForm) {
+    if ((0, _stemModificationHelpers.isVowelDoublingAllowed)(stemFromFullForm, morphologyDataNL.regularStemmer.stemModifications.exceptionsStemModifications, morphologyDataNL.pastParticipleStemmer.compoundVerbsPrefixes)) {
+      stemFromFullForm = (0, _stemModificationHelpers.modifyStem)(stemFromFullForm, morphologyDataNL.regularStemmer.stemModifications.doubleVowel);
+      return (0, _stemModificationHelpers.modifyStem)(stemFromFullForm, morphologyDataNL.regularStemmer.stemModifications.finalChanges);
+    }
+    return (0, _stemModificationHelpers.modifyStem)(stemFromFullForm, morphologyDataNL.regularStemmer.stemModifications.finalChanges);
+  }
+  return null;
+};
+
+/**
+ * Stems Dutch words.
+ *
+ * @param {string} word  The word to stem.
+ * @param {Object} morphologyDataNL The Dutch morphology data file.
+ *
+ * @returns {string} The stemmed word.
+ */
+function stem(word, morphologyDataNL) {
+  // Check whether the word is in the list of words with full forms for which we define the stem. If it is, return the canonical stem.
+  let stemmedWord = (0, _checkExceptionsWithFullForms.default)(morphologyDataNL, word);
+  if (stemmedWord) {
+    return stemmedWord;
+  }
+
+  // Check whether the word is a participle, and if yes, stem it and return the stem.
+  stemmedWord = (0, _detectAndStemRegularParticiple.detectAndStemRegularParticiple)(morphologyDataNL, word);
+  if (stemmedWord) {
+    return stemmedWord;
+  }
+
+  // Check whether the word is on the list of words that should not be stemmed, and if yes, return the word. Example: gans -> gans
+  const wordsNotToBeStemmed = morphologyDataNL.stemExceptions.wordsNotToBeStemmedExceptions;
+  if (checkIfWordIsOnListThatCanHavePrefix(word, wordsNotToBeStemmed.verbs, morphologyDataNL.pastParticipleStemmer.compoundVerbsPrefixes) || checkIfWordEndingIsOnExceptionList(word, wordsNotToBeStemmed.endingMatch) || wordsNotToBeStemmed.exactMatch.includes(word)) {
+    return word;
+  }
+
+  /*
+   * Check whether the word ends in -t/-te/-ten/-tend/-de/-den/-dend. If it does, run through a series of checks aimed at
+   * predicting whether the -t/d is part of the stem or the suffix. If the word was matched in one of the checks, stem it
+   * accordingly and return the stem. Example: boot -> boot, squasht -> squash
+   */
+  const tAndDEndings = morphologyDataNL.ambiguousTAndDEndings.otherTAndDEndings;
+  for (const ending of tAndDEndings) {
+    if (word.endsWith(ending)) {
+      stemmedWord = (0, _getStemWordsWithTAndDEnding.generateCorrectStemWithTAndDEnding)(morphologyDataNL, word);
+      if (stemmedWord) {
+        return stemmedWord;
+      }
+    }
+  }
+
+  // Check if the word is on any other stemming exception list, and if yes, return the correct stem.
+  stemmedWord = checkOtherStemmingExceptions(word, morphologyDataNL);
+  if (stemmedWord) {
+    return stemmedWord;
+  }
+
+  // If the word was not stemmed in any of the previous steps, run through the stemming algorithm which detects and stems suffixes.
+  return (0, _detectAndStemSuffixes.default)(word, morphologyDataNL);
+}
+//# sourceMappingURL=stem.js.map

package/build/languageProcessing/languages/nl/helpers/internal/stem.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"stem.js","names":["_index","require","_detectAndStemSuffixes","_interopRequireDefault","_getStemWordsWithTAndDEnding","_checkExceptionsWithFullForms","_detectAndStemRegularParticiple","_stemModificationHelpers","e","__esModule","default","exceptionListHelpers","checkIfWordEndingIsOnExceptionList","checkIfWordIsOnListThatCanHavePrefix","stemHelpers","removeSuffixFromFullForm","removeSuffixesFromFullForm","languageProcessing","removeSuffixFromFullForms","morphologyDataNL","word","exceptionClass","stemExceptions","removeSuffixesFromFullForms","stemmedWord","forms","suffixes","suffix","checkOtherStemmingExceptions","stemFromFullForm","isVowelDoublingAllowed","regularStemmer","stemModifications","exceptionsStemModifications","pastParticipleStemmer","compoundVerbsPrefixes","modifyStem","doubleVowel","finalChanges","stem","checkExceptionsWithFullForms","detectAndStemRegularParticiple","wordsNotToBeStemmed","wordsNotToBeStemmedExceptions","verbs","endingMatch","exactMatch","includes","tAndDEndings","ambiguousTAndDEndings","otherTAndDEndings","ending","endsWith","generateCorrectStemWithTAndDEnding","detectAndStemSuffixes"],"sources":["../../../../../../src/languageProcessing/languages/nl/helpers/internal/stem.js"],"sourcesContent":["import {languageProcessing} from '../../../index';\nconst {\n  exceptionListHelpers: {checkIfWordEndingIsOnExceptionList, checkIfWordIsOnListThatCanHavePrefix},\n  stemHelpers: {removeSuffixFromFullForm, removeSuffixesFromFullForm}\n} = languageProcessing;\n\nimport detectAndStemSuffixes from './detectAndStemSuffixes';\nimport {generateCorrectStemWithTAndDEnding} from './getStemWordsWithTAndDEnding.js';\nimport checkExceptionsWithFullForms from './checkExceptionsWithFullForms';\nimport {detectAndStemRegularParticiple} from './detectAndStemRegularParticiple';\nimport {modifyStem, isVowelDoublingAllowed} from './stemModificationHelpers';\n\n/**\n * Get the stem from noun diminutives and plurals exceptions.\n *\n * @param {Object}    morphologyDataNL The data for stemming exception.\n * @param {string}      word                                The word to check.\n *\n * @returns {string} The stemmed word.\n */\nconst removeSuffixFromFullForms = function(morphologyDataNL, word) {\n  /*\n   * Checks whether the word is in the exception list of words ending in -er and gets either -e or -s suffix\n   * If it is, remove the corresponding suffix.\n   * e.g. lekkere -> lekker, bitters -> bitter\n   */\n  for (const exceptionClass of morphologyDataNL.stemExceptions.removeSuffixesFromFullForms) {\n    const stemmedWord = removeSuffixesFromFullForm(\n      exceptionClass.forms,\n      exceptionClass.suffixes,\n      word\n    );\n    if (stemmedWord) {\n      return stemmedWord;\n    }\n  }\n  /*\n   * Checks whether the word is in one of the exception lists of nouns\n   * for which a specific suffix needs to be stemmed (e.g. -s, -es, -eren, -er etc.)\n   * e.g. kuddes -> kud, modes -> mod, revenuen -> revenu\n   */\n  for (const exceptionClass of morphologyDataNL.stemExceptions.removeSuffixFromFullForms) {\n    const stemmedWord = removeSuffixFromFullForm(exceptionClass.forms, exceptionClass.suffix, word);\n    if (stemmedWord) {\n      return stemmedWord;\n    }\n  }\n};\n\n/**\n * Checks if the word is on a stemming exception list.\n *\n * @param {string} word The word to check.\n * @param {Object} morphologyDataNL The Dutch morphology data file.\n * @returns {string|null} The stem or null if the word was not matched by any of the exception checks.\n */\nconst checkOtherStemmingExceptions = function(word, morphologyDataNL) {\n  /*\n   * Checks whether the word is in the exception list of nouns or adjectives with specific suffixes that needs to be stemmed.\n   * If it is return the stem here and run possible stem modification if it is required. e.g. modes -> mod -> mood\n   */\n  let stemFromFullForm = removeSuffixFromFullForms(morphologyDataNL, word);\n  if (stemFromFullForm) {\n    if (\n      isVowelDoublingAllowed(\n        stemFromFullForm,\n        morphologyDataNL.regularStemmer.stemModifications.exceptionsStemModifications,\n        morphologyDataNL.pastParticipleStemmer.compoundVerbsPrefixes\n      )\n    ) {\n      stemFromFullForm = modifyStem(\n        stemFromFullForm,\n        morphologyDataNL.regularStemmer.stemModifications.doubleVowel\n      );\n      return modifyStem(\n        stemFromFullForm,\n        morphologyDataNL.regularStemmer.stemModifications.finalChanges\n      );\n    }\n    return modifyStem(\n      stemFromFullForm,\n      morphologyDataNL.regularStemmer.stemModifications.finalChanges\n    );\n  }\n  return null;\n};\n\n/**\n * Stems Dutch words.\n *\n * @param {string} word  The word to stem.\n * @param {Object} morphologyDataNL The Dutch morphology data file.\n *\n * @returns {string} The stemmed word.\n */\nexport default function stem(word, morphologyDataNL) {\n  // Check whether the word is in the list of words with full forms for which we define the stem. If it is, return the canonical stem.\n  let stemmedWord = checkExceptionsWithFullForms(morphologyDataNL, word);\n  if (stemmedWord) {\n    return stemmedWord;\n  }\n\n  // Check whether the word is a participle, and if yes, stem it and return the stem.\n  stemmedWord = detectAndStemRegularParticiple(morphologyDataNL, word);\n  if (stemmedWord) {\n    return stemmedWord;\n  }\n\n  // Check whether the word is on the list of words that should not be stemmed, and if yes, return the word. Example: gans -> gans\n  const wordsNotToBeStemmed = morphologyDataNL.stemExceptions.wordsNotToBeStemmedExceptions;\n  if (\n    checkIfWordIsOnListThatCanHavePrefix(\n      word,\n      wordsNotToBeStemmed.verbs,\n      morphologyDataNL.pastParticipleStemmer.compoundVerbsPrefixes\n    ) ||\n    checkIfWordEndingIsOnExceptionList(word, wordsNotToBeStemmed.endingMatch) ||\n    wordsNotToBeStemmed.exactMatch.includes(word)\n  ) {\n    return word;\n  }\n\n  /*\n   * Check whether the word ends in -t/-te/-ten/-tend/-de/-den/-dend. If it does, run through a series of checks aimed at\n   * predicting whether the -t/d is part of the stem or the suffix. If the word was matched in one of the checks, stem it\n   * accordingly and return the stem. Example: boot -> boot, squasht -> squash\n   */\n  const tAndDEndings = morphologyDataNL.ambiguousTAndDEndings.otherTAndDEndings;\n  for (const ending of tAndDEndings) {\n    if (word.endsWith(ending)) {\n      stemmedWord = generateCorrectStemWithTAndDEnding(morphologyDataNL, word);\n      if (stemmedWord) {\n        return stemmedWord;\n      }\n    }\n  }\n\n  // Check if the word is on any other stemming exception list, and if yes, return the correct stem.\n  stemmedWord = checkOtherStemmingExceptions(word, morphologyDataNL);\n  if (stemmedWord) {\n    return stemmedWord;\n  }\n\n  // If the word was not stemmed in any of the previous steps, run through the stemming algorithm which detects and stems suffixes.\n  return detectAndStemSuffixes(word, morphologyDataNL);\n}\n"],"mappings":";;;;;;AAAA,IAAAA,MAAA,GAAAC,OAAA;AAMA,IAAAC,sBAAA,GAAAC,sBAAA,CAAAF,OAAA;AACA,IAAAG,4BAAA,GAAAH,OAAA;AACA,IAAAI,6BAAA,GAAAF,sBAAA,CAAAF,OAAA;AACA,IAAAK,+BAAA,GAAAL,OAAA;AACA,IAAAM,wBAAA,GAAAN,OAAA;AAA6E,SAAAE,uBAAAK,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAT7E,MAAM;EACJG,oBAAoB,EAAE;IAACC,kCAAkC;IAAEC;EAAoC,CAAC;EAChGC,WAAW,EAAE;IAACC,wBAAwB;IAAEC;EAA0B;AACpE,CAAC,GAAGC,yBAAkB;AAQtB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,yBAAyB,GAAG,SAAAA,CAASC,gBAAgB,EAAEC,IAAI,EAAE;EACjE;AACF;AACA;AACA;AACA;EACE,KAAK,MAAMC,cAAc,IAAIF,gBAAgB,CAACG,cAAc,CAACC,2BAA2B,EAAE;IACxF,MAAMC,WAAW,GAAGR,0BAA0B,CAC5CK,cAAc,CAACI,KAAK,EACpBJ,cAAc,CAACK,QAAQ,EACvBN,IACF,CAAC;IACD,IAAII,WAAW,EAAE;MACf,OAAOA,WAAW;IACpB;EACF;EACA;AACF;AACA;AACA;AACA;EACE,KAAK,MAAMH,cAAc,IAAIF,gBAAgB,CAACG,cAAc,CAACJ,yBAAyB,EAAE;IACtF,MAAMM,WAAW,GAAGT,wBAAwB,CAACM,cAAc,CAACI,KAAK,EAAEJ,cAAc,CAACM,MAAM,EAAEP,IAAI,CAAC;IAC/F,IAAII,WAAW,EAAE;MACf,OAAOA,WAAW;IACpB;EACF;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMI,4BAA4B,GAAG,SAAAA,CAASR,IAAI,EAAED,gBAAgB,EAAE;EACpE;AACF;AACA;AACA;EACE,IAAIU,gBAAgB,GAAGX,yBAAyB,CAACC,gBAAgB,EAAEC,IAAI,CAAC;EACxE,IAAIS,gBAAgB,EAAE;IACpB,IACE,IAAAC,+CAAsB,EACpBD,gBAAgB,EAChBV,gBAAgB,CAACY,cAAc,CAACC,iBAAiB,CAACC,2BAA2B,EAC7Ed,gBAAgB,CAACe,qBAAqB,CAACC,qBACzC,CAAC,EACD;MACAN,gBAAgB,GAAG,IAAAO,mCAAU,EAC3BP,gBAAgB,EAChBV,gBAAgB,CAACY,cAAc,CAACC,iBAAiB,CAACK,WACpD,CAAC;MACD,OAAO,IAAAD,mCAAU,EACfP,gBAAgB,EAChBV,gBAAgB,CAACY,cAAc,CAACC,iBAAiB,CAACM,YACpD,CAAC;IACH;IACA,OAAO,IAAAF,mCAAU,EACfP,gBAAgB,EAChBV,gBAAgB,CAACY,cAAc,CAACC,iBAAiB,CAACM,YACpD,CAAC;EACH;EACA,OAAO,IAAI;AACb,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAASC,IAAIA,CAACnB,IAAI,EAAED,gBAAgB,EAAE;EACnD;EACA,IAAIK,WAAW,GAAG,IAAAgB,qCAA4B,EAACrB,gBAAgB,EAAEC,IAAI,CAAC;EACtE,IAAII,WAAW,EAAE;IACf,OAAOA,WAAW;EACpB;;EAEA;EACAA,WAAW,GAAG,IAAAiB,8DAA8B,EAACtB,gBAAgB,EAAEC,IAAI,CAAC;EACpE,IAAII,WAAW,EAAE;IACf,OAAOA,WAAW;EACpB;;EAEA;EACA,MAAMkB,mBAAmB,GAAGvB,gBAAgB,CAACG,cAAc,CAACqB,6BAA6B;EACzF,IACE9B,oCAAoC,CAClCO,IAAI,EACJsB,mBAAmB,CAACE,KAAK,EACzBzB,gBAAgB,CAACe,qBAAqB,CAACC,qBACzC,CAAC,IACDvB,kCAAkC,CAACQ,IAAI,EAAEsB,mBAAmB,CAACG,WAAW,CAAC,IACzEH,mBAAmB,CAACI,UAAU,CAACC,QAAQ,CAAC3B,IAAI,CAAC,EAC7C;IACA,OAAOA,IAAI;EACb;;EAEA;AACF;AACA;AACA;AACA;EACE,MAAM4B,YAAY,GAAG7B,gBAAgB,CAAC8B,qBAAqB,CAACC,iBAAiB;EAC7E,KAAK,MAAMC,MAAM,IAAIH,YAAY,EAAE;IACjC,IAAI5B,IAAI,CAACgC,QAAQ,CAACD,MAAM,CAAC,EAAE;MACzB3B,WAAW,GAAG,IAAA6B,+DAAkC,EAAClC,gBAAgB,EAAEC,IAAI,CAAC;MACxE,IAAII,WAAW,EAAE;QACf,OAAOA,WAAW;MACpB;IACF;EACF;;EAEA;EACAA,WAAW,GAAGI,4BAA4B,CAACR,IAAI,EAAED,gBAAgB,CAAC;EAClE,IAAIK,WAAW,EAAE;IACf,OAAOA,WAAW;EACpB;;EAEA;EACA,OAAO,IAAA8B,8BAAqB,EAAClC,IAAI,EAAED,gBAAgB,CAAC;AACtD","ignoreList":[]}

package/build/languageProcessing/languages/nl/helpers/internal/stemModificationHelpers.js

@@ -0,0 +1,94 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.isVowelDoublingAllowed = isVowelDoublingAllowed;
+exports.modifyStem = modifyStem;
+var _index = require("../../../index");
+const {
+  exceptionListHelpers: {
+    checkIfWordEndingIsOnExceptionList,
+    checkIfWordIsOnListThatCanHavePrefix
+  }
+} = _index.languageProcessing;
+
+/**
+ * Checks whether the word is on any of the sub-lists of the noVowelDoublingList (ending match, exact match,
+ * and verbs) and returns true if it is.
+ *
+ * @param {string}	word							The word to check.
+ * @param {Object}	noVowelDoublingList	The list of stems that should not have the vowel doubled.
+ * @param {Object}	compoundVerbPrefixes			The list of inseparable and separable verb prefixes.
+ *
+ * @returns {boolean} Whether the word was found on one of the lists
+ */
+const checkIfWordIsOnNoVowelDoublingList = function (word, noVowelDoublingList, compoundVerbPrefixes) {
+  if (checkIfWordEndingIsOnExceptionList(word, noVowelDoublingList.endingMatch) || checkIfWordIsOnListThatCanHavePrefix(word, noVowelDoublingList.verbs, compoundVerbPrefixes) || noVowelDoublingList.exactMatch.includes(word)) {
+    return true;
+  }
+};
+
+/**
+ * Checks whether the third to last and fourth to last characters of the stem are the same. This, in principle, checks
+ * whether the last vowel of the stem is preceded by a double consonant (as only consonants can precede the vowel).
+ * If the third and fourth to last characters are the same, it means that vowel doubling is allowed. For example, in the
+ * word 'luttel', the third and fourth to last characters are both t's so it should not become 'lutteel'.
+ *
+ * @param {string} word The stemmed word to check.
+ *
+ * @returns {boolean} Whether the vowel should be doubled or not.
+ */
+const isVowelPrecededByDoubleConsonant = function (word) {
+  const fourthToLastLetter = word.charAt(word.length - 4);
+  const thirdToLastLetter = word.charAt(word.length - 3);
+  return fourthToLastLetter !== thirdToLastLetter;
+};
+
+/**
+ * Checks whether the second to last syllable contains a diphthong. If it does, the vowel in the last syllable should
+ * not be doubled.
+ *
+ * @param {string} word                 The stemmed word to check.
+ * @param {string} noVowelDoublingRegex The regex to match a word with.
+ *
+ * @returns {boolean} Whether the vowel should be doubled or not.
+ */
+const doesPrecedingSyllableContainDiphthong = function (word, noVowelDoublingRegex) {
+  return word.search(new RegExp(noVowelDoublingRegex)) === -1;
+};
+
+/**
+ * Modifies the stem of the word according to the specified modification type.
+ *
+ * @param {string} word The stem that needs to be modified.
+ * @param {string[]} modificationGroup The type of modification that needs to be done.
+ * @returns {string} The modified stem, or the same stem if no modification was made.
+ */
+function modifyStem(word, modificationGroup) {
+  const neededReplacement = modificationGroup.find(replacement => word.search(new RegExp(replacement[0])) !== -1);
+  if (typeof neededReplacement !== 'undefined') {
+    word = word.replace(new RegExp(neededReplacement[0]), neededReplacement[1]);
+  }
+  return word;
+}
+
+/**
+ * Checks whether the final vowel of the stem should be doubled by going through four checks.
+ *
+ * @param {string}  word                               The stemmed word that the check should be executed on.
+ * @param {Object}  morphologyDataNLStemmingExceptions The Dutch morphology data for stemming exceptions.
+ * @param {Object}  morphologyDataNLVerbPrefixes	   The separable and inseparable verb prefixes.
+ *
+ * @returns {boolean} Whether the vowel should be doubled or not.
+ */
+function isVowelDoublingAllowed(word, morphologyDataNLStemmingExceptions, morphologyDataNLVerbPrefixes) {
+  // Check whether the word is on the list of verbs which should have the vowel doubled (exception to third check)
+  const firstCheck = checkIfWordIsOnListThatCanHavePrefix(word, morphologyDataNLStemmingExceptions.getVowelDoubling, morphologyDataNLVerbPrefixes);
+  // Check whether the word is on the list of words which should NOT have the vowel doubled
+  const secondCheck = checkIfWordIsOnNoVowelDoublingList(word, morphologyDataNLStemmingExceptions.noVowelDoubling, morphologyDataNLVerbPrefixes);
+  const thirdCheck = isVowelPrecededByDoubleConsonant(word);
+  const fourthCheck = doesPrecedingSyllableContainDiphthong(word, morphologyDataNLStemmingExceptions.noVowelDoubling.rule);
+  return firstCheck || !secondCheck && thirdCheck && fourthCheck;
+}
+//# sourceMappingURL=stemModificationHelpers.js.map

package/build/languageProcessing/languages/nl/helpers/internal/stemModificationHelpers.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"stemModificationHelpers.js","names":["_index","require","exceptionListHelpers","checkIfWordEndingIsOnExceptionList","checkIfWordIsOnListThatCanHavePrefix","languageProcessing","checkIfWordIsOnNoVowelDoublingList","word","noVowelDoublingList","compoundVerbPrefixes","endingMatch","verbs","exactMatch","includes","isVowelPrecededByDoubleConsonant","fourthToLastLetter","charAt","length","thirdToLastLetter","doesPrecedingSyllableContainDiphthong","noVowelDoublingRegex","search","RegExp","modifyStem","modificationGroup","neededReplacement","find","replacement","replace","isVowelDoublingAllowed","morphologyDataNLStemmingExceptions","morphologyDataNLVerbPrefixes","firstCheck","getVowelDoubling","secondCheck","noVowelDoubling","thirdCheck","fourthCheck","rule"],"sources":["../../../../../../src/languageProcessing/languages/nl/helpers/internal/stemModificationHelpers.js"],"sourcesContent":["import {languageProcessing} from '../../../index';\nconst {\n  exceptionListHelpers: {checkIfWordEndingIsOnExceptionList, checkIfWordIsOnListThatCanHavePrefix}\n} = languageProcessing;\n\n/**\n * Checks whether the word is on any of the sub-lists of the noVowelDoublingList (ending match, exact match,\n * and verbs) and returns true if it is.\n *\n * @param {string}\tword\t\t\t\t\t\t\tThe word to check.\n * @param {Object}\tnoVowelDoublingList\tThe list of stems that should not have the vowel doubled.\n * @param {Object}\tcompoundVerbPrefixes\t\t\tThe list of inseparable and separable verb prefixes.\n *\n * @returns {boolean} Whether the word was found on one of the lists\n */\nconst checkIfWordIsOnNoVowelDoublingList = function(\n  word,\n  noVowelDoublingList,\n  compoundVerbPrefixes\n) {\n  if (\n    checkIfWordEndingIsOnExceptionList(word, noVowelDoublingList.endingMatch) ||\n    checkIfWordIsOnListThatCanHavePrefix(word, noVowelDoublingList.verbs, compoundVerbPrefixes) ||\n    noVowelDoublingList.exactMatch.includes(word)\n  ) {\n    return true;\n  }\n};\n\n/**\n * Checks whether the third to last and fourth to last characters of the stem are the same. This, in principle, checks\n * whether the last vowel of the stem is preceded by a double consonant (as only consonants can precede the vowel).\n * If the third and fourth to last characters are the same, it means that vowel doubling is allowed. For example, in the\n * word 'luttel', the third and fourth to last characters are both t's so it should not become 'lutteel'.\n *\n * @param {string} word The stemmed word to check.\n *\n * @returns {boolean} Whether the vowel should be doubled or not.\n */\nconst isVowelPrecededByDoubleConsonant = function(word) {\n  const fourthToLastLetter = word.charAt(word.length - 4);\n  const thirdToLastLetter = word.charAt(word.length - 3);\n  return fourthToLastLetter !== thirdToLastLetter;\n};\n\n/**\n * Checks whether the second to last syllable contains a diphthong. If it does, the vowel in the last syllable should\n * not be doubled.\n *\n * @param {string} word                 The stemmed word to check.\n * @param {string} noVowelDoublingRegex The regex to match a word with.\n *\n * @returns {boolean} Whether the vowel should be doubled or not.\n */\nconst doesPrecedingSyllableContainDiphthong = function(word, noVowelDoublingRegex) {\n  return word.search(new RegExp(noVowelDoublingRegex)) === -1;\n};\n\n/**\n * Modifies the stem of the word according to the specified modification type.\n *\n * @param {string} word The stem that needs to be modified.\n * @param {string[]} modificationGroup The type of modification that needs to be done.\n * @returns {string} The modified stem, or the same stem if no modification was made.\n */\nexport function modifyStem(word, modificationGroup) {\n  const neededReplacement = modificationGroup.find(\n    replacement => word.search(new RegExp(replacement[0])) !== -1\n  );\n  if (typeof neededReplacement !== 'undefined') {\n    word = word.replace(new RegExp(neededReplacement[0]), neededReplacement[1]);\n  }\n  return word;\n}\n\n/**\n * Checks whether the final vowel of the stem should be doubled by going through four checks.\n *\n * @param {string}  word                               The stemmed word that the check should be executed on.\n * @param {Object}  morphologyDataNLStemmingExceptions The Dutch morphology data for stemming exceptions.\n * @param {Object}  morphologyDataNLVerbPrefixes\t   The separable and inseparable verb prefixes.\n *\n * @returns {boolean} Whether the vowel should be doubled or not.\n */\nexport function isVowelDoublingAllowed(\n  word,\n  morphologyDataNLStemmingExceptions,\n  morphologyDataNLVerbPrefixes\n) {\n  // Check whether the word is on the list of verbs which should have the vowel doubled (exception to third check)\n  const firstCheck = checkIfWordIsOnListThatCanHavePrefix(\n    word,\n    morphologyDataNLStemmingExceptions.getVowelDoubling,\n    morphologyDataNLVerbPrefixes\n  );\n  // Check whether the word is on the list of words which should NOT have the vowel doubled\n  const secondCheck = checkIfWordIsOnNoVowelDoublingList(\n    word,\n    morphologyDataNLStemmingExceptions.noVowelDoubling,\n    morphologyDataNLVerbPrefixes\n  );\n  const thirdCheck = isVowelPrecededByDoubleConsonant(word);\n  const fourthCheck = doesPrecedingSyllableContainDiphthong(\n    word,\n    morphologyDataNLStemmingExceptions.noVowelDoubling.rule\n  );\n\n  return firstCheck || (!secondCheck && thirdCheck && fourthCheck);\n}\n"],"mappings":";;;;;;;AAAA,IAAAA,MAAA,GAAAC,OAAA;AACA,MAAM;EACJC,oBAAoB,EAAE;IAACC,kCAAkC;IAAEC;EAAoC;AACjG,CAAC,GAAGC,yBAAkB;;AAEtB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,kCAAkC,GAAG,SAAAA,CACzCC,IAAI,EACJC,mBAAmB,EACnBC,oBAAoB,EACpB;EACA,IACEN,kCAAkC,CAACI,IAAI,EAAEC,mBAAmB,CAACE,WAAW,CAAC,IACzEN,oCAAoC,CAACG,IAAI,EAAEC,mBAAmB,CAACG,KAAK,EAAEF,oBAAoB,CAAC,IAC3FD,mBAAmB,CAACI,UAAU,CAACC,QAAQ,CAACN,IAAI,CAAC,EAC7C;IACA,OAAO,IAAI;EACb;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMO,gCAAgC,GAAG,SAAAA,CAASP,IAAI,EAAE;EACtD,MAAMQ,kBAAkB,GAAGR,IAAI,CAACS,MAAM,CAACT,IAAI,CAACU,MAAM,GAAG,CAAC,CAAC;EACvD,MAAMC,iBAAiB,GAAGX,IAAI,CAACS,MAAM,CAACT,IAAI,CAACU,MAAM,GAAG,CAAC,CAAC;EACtD,OAAOF,kBAAkB,KAAKG,iBAAiB;AACjD,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,qCAAqC,GAAG,SAAAA,CAASZ,IAAI,EAAEa,oBAAoB,EAAE;EACjF,OAAOb,IAAI,CAACc,MAAM,CAAC,IAAIC,MAAM,CAACF,oBAAoB,CAAC,CAAC,KAAK,CAAC,CAAC;AAC7D,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACO,SAASG,UAAUA,CAAChB,IAAI,EAAEiB,iBAAiB,EAAE;EAClD,MAAMC,iBAAiB,GAAGD,iBAAiB,CAACE,IAAI,CAC9CC,WAAW,IAAIpB,IAAI,CAACc,MAAM,CAAC,IAAIC,MAAM,CAACK,WAAW,CAAC,CAAC,CAAC,CAAC,CAAC,KAAK,CAAC,CAC9D,CAAC;EACD,IAAI,OAAOF,iBAAiB,KAAK,WAAW,EAAE;IAC5ClB,IAAI,GAAGA,IAAI,CAACqB,OAAO,CAAC,IAAIN,MAAM,CAACG,iBAAiB,CAAC,CAAC,CAAC,CAAC,EAAEA,iBAAiB,CAAC,CAAC,CAAC,CAAC;EAC7E;EACA,OAAOlB,IAAI;AACb;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACO,SAASsB,sBAAsBA,CACpCtB,IAAI,EACJuB,kCAAkC,EAClCC,4BAA4B,EAC5B;EACA;EACA,MAAMC,UAAU,GAAG5B,oCAAoC,CACrDG,IAAI,EACJuB,kCAAkC,CAACG,gBAAgB,EACnDF,4BACF,CAAC;EACD;EACA,MAAMG,WAAW,GAAG5B,kCAAkC,CACpDC,IAAI,EACJuB,kCAAkC,CAACK,eAAe,EAClDJ,4BACF,CAAC;EACD,MAAMK,UAAU,GAAGtB,gCAAgC,CAACP,IAAI,CAAC;EACzD,MAAM8B,WAAW,GAAGlB,qCAAqC,CACvDZ,IAAI,EACJuB,kCAAkC,CAACK,eAAe,CAACG,IACrD,CAAC;EAED,OAAON,UAAU,IAAK,CAACE,WAAW,IAAIE,UAAU,IAAIC,WAAY;AAClE","ignoreList":[]}

package/build/languageProcessing/languages/nl/helpers/internal/stemTOrDFromEndOfWord.js

@@ -0,0 +1,59 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.stemTOrDFromEndOfWord = stemTOrDFromEndOfWord;
+var _index = require("../../../index");
+var _detectAndStemRegularParticiple = require("./detectAndStemRegularParticiple");
+var _getStemWordsWithTAndDEnding = require("./getStemWordsWithTAndDEnding");
+var _checkExceptionsWithFullForms = _interopRequireDefault(require("./checkExceptionsWithFullForms"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+const {
+  exceptionListHelpers: {
+    checkIfWordEndingIsOnExceptionList,
+    checkIfWordIsOnListThatCanHavePrefix
+  }
+} = _index.languageProcessing;
+/**
+ * If the word ending in -t/-d was not matched in any of the checks for whether -t/-d should be stemmed or not, other checks still need
+ * to be done in order to be sure whether we need to stem the word further or not.
+ * If one of these checks returns true, we do not need to stem the word further.
+ *
+ * @param {Object}  morphologyDataNL	The Dutch morphology data.
+ * @param {string}	stemmedWord			The stemmed word.
+ * @param {string}	word				The unstemmed word.
+ * @returns {boolean}	Whether one of the conditions returns true or not.
+ */
+const checkIfTorDIsUnambiguous = function (morphologyDataNL, stemmedWord, word) {
+  const wordsNotToBeStemmed = morphologyDataNL.stemExceptions.wordsNotToBeStemmedExceptions;
+  const adjectivesEndingInRd = morphologyDataNL.stemExceptions.removeSuffixesFromFullForms[1].forms;
+  const wordsEndingInTOrDExceptionList = morphologyDataNL.ambiguousTAndDEndings.tOrDArePartOfStem.doNotStemTOrD;
+
+  // Run the checks below. If one of the conditions returns true, return the stem.
+  if ((0, _detectAndStemRegularParticiple.detectAndStemRegularParticiple)(morphologyDataNL, word) || (0, _getStemWordsWithTAndDEnding.generateCorrectStemWithTAndDEnding)(morphologyDataNL, word) || checkIfWordIsOnListThatCanHavePrefix(word, wordsNotToBeStemmed.verbs, morphologyDataNL.pastParticipleStemmer.compoundVerbsPrefixes) || checkIfWordEndingIsOnExceptionList(word, wordsNotToBeStemmed.endingMatch) || wordsNotToBeStemmed.exactMatch.includes(word) || adjectivesEndingInRd.includes(stemmedWord) || (0, _checkExceptionsWithFullForms.default)(morphologyDataNL, word) || stemmedWord.endsWith('heid') || checkIfWordEndingIsOnExceptionList(stemmedWord, wordsEndingInTOrDExceptionList)) {
+    return true;
+  }
+};
+
+/**
+ * If the word ending in -t/-d was not matched in any of the checks for whether -t/-d should be stemmed or not, and if it
+ * is not a participle (which has its separate check), then it is still ambiguous whether -t/-d is part of the stem or a suffix.
+ * Therefore, a second stem should be created with the -t/-d removed in case it was a suffix. For example, in the verb 'poolt',
+ * -t is a suffix, but we could not predict in any of the previous checks that -t should be stemmed. To account for such cases,
+ * we stem the -t here.
+ *
+ * @param {Object}  morphologyDataNL	The Dutch morphology data.
+ * @param {string}	stemmedWord			The stemmed word.
+ * @param {string}	word				The unstemmed word.
+ *
+ * @returns {?string}				    The stemmed word or null if the -t/-d should not be stemmed.
+ */
+function stemTOrDFromEndOfWord(morphologyDataNL, stemmedWord, word) {
+  if (checkIfTorDIsUnambiguous(morphologyDataNL, stemmedWord, word)) {
+    return null;
+  }
+  // If none of the conditions above is true, stem the t/d from the word.
+  return stemmedWord.slice(0, -1);
+}
+//# sourceMappingURL=stemTOrDFromEndOfWord.js.map

package/build/languageProcessing/languages/nl/helpers/internal/stemTOrDFromEndOfWord.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"stemTOrDFromEndOfWord.js","names":["_index","require","_detectAndStemRegularParticiple","_getStemWordsWithTAndDEnding","_checkExceptionsWithFullForms","_interopRequireDefault","e","__esModule","default","exceptionListHelpers","checkIfWordEndingIsOnExceptionList","checkIfWordIsOnListThatCanHavePrefix","languageProcessing","checkIfTorDIsUnambiguous","morphologyDataNL","stemmedWord","word","wordsNotToBeStemmed","stemExceptions","wordsNotToBeStemmedExceptions","adjectivesEndingInRd","removeSuffixesFromFullForms","forms","wordsEndingInTOrDExceptionList","ambiguousTAndDEndings","tOrDArePartOfStem","doNotStemTOrD","detectAndStemRegularParticiple","generateCorrectStemWithTAndDEnding","verbs","pastParticipleStemmer","compoundVerbsPrefixes","endingMatch","exactMatch","includes","checkExceptionsWithFullForms","endsWith","stemTOrDFromEndOfWord","slice"],"sources":["../../../../../../src/languageProcessing/languages/nl/helpers/internal/stemTOrDFromEndOfWord.js"],"sourcesContent":["import {languageProcessing} from '../../../index';\nconst {\n  exceptionListHelpers: {checkIfWordEndingIsOnExceptionList, checkIfWordIsOnListThatCanHavePrefix}\n} = languageProcessing;\n\nimport {detectAndStemRegularParticiple} from './detectAndStemRegularParticiple';\nimport {generateCorrectStemWithTAndDEnding} from './getStemWordsWithTAndDEnding';\nimport checkExceptionsWithFullForms from './checkExceptionsWithFullForms';\n\n/**\n * If the word ending in -t/-d was not matched in any of the checks for whether -t/-d should be stemmed or not, other checks still need\n * to be done in order to be sure whether we need to stem the word further or not.\n * If one of these checks returns true, we do not need to stem the word further.\n *\n * @param {Object}  morphologyDataNL\tThe Dutch morphology data.\n * @param {string}\tstemmedWord\t\t\tThe stemmed word.\n * @param {string}\tword\t\t\t\tThe unstemmed word.\n * @returns {boolean}\tWhether one of the conditions returns true or not.\n */\nconst checkIfTorDIsUnambiguous = function(morphologyDataNL, stemmedWord, word) {\n  const wordsNotToBeStemmed = morphologyDataNL.stemExceptions.wordsNotToBeStemmedExceptions;\n  const adjectivesEndingInRd = morphologyDataNL.stemExceptions.removeSuffixesFromFullForms[1].forms;\n  const wordsEndingInTOrDExceptionList =\n    morphologyDataNL.ambiguousTAndDEndings.tOrDArePartOfStem.doNotStemTOrD;\n\n  // Run the checks below. If one of the conditions returns true, return the stem.\n  if (\n    detectAndStemRegularParticiple(morphologyDataNL, word) ||\n    generateCorrectStemWithTAndDEnding(morphologyDataNL, word) ||\n    checkIfWordIsOnListThatCanHavePrefix(\n      word,\n      wordsNotToBeStemmed.verbs,\n      morphologyDataNL.pastParticipleStemmer.compoundVerbsPrefixes\n    ) ||\n    checkIfWordEndingIsOnExceptionList(word, wordsNotToBeStemmed.endingMatch) ||\n    wordsNotToBeStemmed.exactMatch.includes(word) ||\n    adjectivesEndingInRd.includes(stemmedWord) ||\n    checkExceptionsWithFullForms(morphologyDataNL, word) ||\n    stemmedWord.endsWith('heid') ||\n    checkIfWordEndingIsOnExceptionList(stemmedWord, wordsEndingInTOrDExceptionList)\n  ) {\n    return true;\n  }\n};\n\n/**\n * If the word ending in -t/-d was not matched in any of the checks for whether -t/-d should be stemmed or not, and if it\n * is not a participle (which has its separate check), then it is still ambiguous whether -t/-d is part of the stem or a suffix.\n * Therefore, a second stem should be created with the -t/-d removed in case it was a suffix. For example, in the verb 'poolt',\n * -t is a suffix, but we could not predict in any of the previous checks that -t should be stemmed. To account for such cases,\n * we stem the -t here.\n *\n * @param {Object}  morphologyDataNL\tThe Dutch morphology data.\n * @param {string}\tstemmedWord\t\t\tThe stemmed word.\n * @param {string}\tword\t\t\t\tThe unstemmed word.\n *\n * @returns {?string}\t\t\t\t    The stemmed word or null if the -t/-d should not be stemmed.\n */\nexport function stemTOrDFromEndOfWord(morphologyDataNL, stemmedWord, word) {\n  if (checkIfTorDIsUnambiguous(morphologyDataNL, stemmedWord, word)) {\n    return null;\n  }\n  // If none of the conditions above is true, stem the t/d from the word.\n  return stemmedWord.slice(0, -1);\n}\n"],"mappings":";;;;;;AAAA,IAAAA,MAAA,GAAAC,OAAA;AAKA,IAAAC,+BAAA,GAAAD,OAAA;AACA,IAAAE,4BAAA,GAAAF,OAAA;AACA,IAAAG,6BAAA,GAAAC,sBAAA,CAAAJ,OAAA;AAA0E,SAAAI,uBAAAC,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAN1E,MAAM;EACJG,oBAAoB,EAAE;IAACC,kCAAkC;IAAEC;EAAoC;AACjG,CAAC,GAAGC,yBAAkB;AAMtB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,wBAAwB,GAAG,SAAAA,CAASC,gBAAgB,EAAEC,WAAW,EAAEC,IAAI,EAAE;EAC7E,MAAMC,mBAAmB,GAAGH,gBAAgB,CAACI,cAAc,CAACC,6BAA6B;EACzF,MAAMC,oBAAoB,GAAGN,gBAAgB,CAACI,cAAc,CAACG,2BAA2B,CAAC,CAAC,CAAC,CAACC,KAAK;EACjG,MAAMC,8BAA8B,GAClCT,gBAAgB,CAACU,qBAAqB,CAACC,iBAAiB,CAACC,aAAa;;EAExE;EACA,IACE,IAAAC,8DAA8B,EAACb,gBAAgB,EAAEE,IAAI,CAAC,IACtD,IAAAY,+DAAkC,EAACd,gBAAgB,EAAEE,IAAI,CAAC,IAC1DL,oCAAoC,CAClCK,IAAI,EACJC,mBAAmB,CAACY,KAAK,EACzBf,gBAAgB,CAACgB,qBAAqB,CAACC,qBACzC,CAAC,IACDrB,kCAAkC,CAACM,IAAI,EAAEC,mBAAmB,CAACe,WAAW,CAAC,IACzEf,mBAAmB,CAACgB,UAAU,CAACC,QAAQ,CAAClB,IAAI,CAAC,IAC7CI,oBAAoB,CAACc,QAAQ,CAACnB,WAAW,CAAC,IAC1C,IAAAoB,qCAA4B,EAACrB,gBAAgB,EAAEE,IAAI,CAAC,IACpDD,WAAW,CAACqB,QAAQ,CAAC,MAAM,CAAC,IAC5B1B,kCAAkC,CAACK,WAAW,EAAEQ,8BAA8B,CAAC,EAC/E;IACA,OAAO,IAAI;EACb;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACO,SAASc,qBAAqBA,CAACvB,gBAAgB,EAAEC,WAAW,EAAEC,IAAI,EAAE;EACzE,IAAIH,wBAAwB,CAACC,gBAAgB,EAAEC,WAAW,EAAEC,IAAI,CAAC,EAAE;IACjE,OAAO,IAAI;EACb;EACA;EACA,OAAOD,WAAW,CAACuB,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC;AACjC","ignoreList":[]}