axyseo 2.0.0-alpha.3 → 2.1.1

package/build/languageProcessing/researches/findTransitionWords.js

@@ -1,17 +1,10 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
-var _createRegexFromDoubleArray = _interopRequireDefault(require("../helpers/regex/createRegexFromDoubleArray.js"));
-var _getSentences = _interopRequireDefault(require("../helpers/sentence/getSentences.js"));
-var _quotes = require("../helpers/sanitize/quotes.js");
-var _matchWordInSentence = require("../helpers/word/matchWordInSentence.js");
-var _htmlParser = _interopRequireDefault(require("../helpers/html/htmlParser"));
-var _lodash = require("lodash");
-var _helpers = require("../helpers");
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+import createRegexFromDoubleArray from "../helpers/regex/createRegexFromDoubleArray.js";
+import getSentences from "../helpers/sentence/getSentences.js";
+import { normalizeSingle as normalizeSingleQuotes } from "../helpers/sanitize/quotes.js";
+import { isWordInSentence as matchWordInSentence } from "../helpers/word/matchWordInSentence.js";
+import removeHtmlBlocks from "../helpers/html/htmlParser";
+import { flattenDeep } from "lodash";
+import { filterShortcodesFromHTML } from "../helpers";
 let regexFromDoubleArray = null;
 let regexFromDoubleArrayCacheKey = "";
 
@@ -23,10 +16,10 @@ let regexFromDoubleArrayCacheKey = "";
  * @returns {RegExp} The RegExp to match text with a double array.
  */
 function getRegexFromDoubleArray(twoPartTransitionWords) {
-  const cacheKey = (0, _lodash.flattenDeep)(twoPartTransitionWords).join("");
+  const cacheKey = flattenDeep(twoPartTransitionWords).join("");
   if (regexFromDoubleArrayCacheKey !== cacheKey || regexFromDoubleArray === null) {
     regexFromDoubleArrayCacheKey = cacheKey;
-    regexFromDoubleArray = (0, _createRegexFromDoubleArray.default)(twoPartTransitionWords);
+    regexFromDoubleArray = createRegexFromDoubleArray(twoPartTransitionWords);
   }
   return regexFromDoubleArray;
 }
@@ -39,7 +32,7 @@ function getRegexFromDoubleArray(twoPartTransitionWords) {
  * @returns {Array} The found transitional words.
  */
 const matchTwoPartTransitionWords = function (sentence, twoPartTransitionWords) {
-  sentence = (0, _quotes.normalizeSingle)(sentence);
+  sentence = normalizeSingleQuotes(sentence);
   const twoPartTransitionWordsRegex = getRegexFromDoubleArray(twoPartTransitionWords);
   return sentence.match(twoPartTransitionWordsRegex);
 };
@@ -52,8 +45,8 @@ const matchTwoPartTransitionWords = function (sentence, twoPartTransitionWords)
  * @returns {Array} The found transitional words.
  */
 const matchTransitionWords = function (sentence, transitionWords) {
-  sentence = (0, _quotes.normalizeSingle)(sentence);
-  return transitionWords.filter(word => (0, _matchWordInSentence.isWordInSentence)(word, sentence));
+  sentence = normalizeSingleQuotes(sentence);
+  return transitionWords.filter(word => matchWordInSentence(word, sentence));
 };
 
 /**
@@ -100,15 +93,15 @@ const checkSentencesForTransitionWords = function (sentences, transitionWords, t
  * @returns {object} An object with the total number of sentences in the text
  *                   and the total number of sentences containing one or more transition words.
  */
-function _default(paper, researcher) {
+export default function (paper, researcher) {
   const matchTransitionWordsHelper = researcher.getHelper("matchTransitionWordsHelper");
   const transitionWords = researcher.getConfig("transitionWords");
   const twoPartTransitionWords = researcher.getConfig("twoPartTransitionWords");
   const memoizedTokenizer = researcher.getHelper("memoizedTokenizer");
   let text = paper.getText();
-  text = (0, _htmlParser.default)(text);
-  text = (0, _helpers.filterShortcodesFromHTML)(text, paper._attributes && paper._attributes.shortcodes);
-  const sentences = (0, _getSentences.default)(text, memoizedTokenizer);
+  text = removeHtmlBlocks(text);
+  text = filterShortcodesFromHTML(text, paper._attributes && paper._attributes.shortcodes);
+  const sentences = getSentences(text, memoizedTokenizer);
   const sentenceResults = checkSentencesForTransitionWords(sentences, transitionWords, twoPartTransitionWords, matchTransitionWordsHelper);
   return {
     totalSentences: sentences.length,

package/build/languageProcessing/researches/findTransitionWords.js.map

@@ -1 +1 @@
-{"version":3,"file":"findTransitionWords.js","names":["_createRegexFromDoubleArray","_interopRequireDefault","require","_getSentences","_quotes","_matchWordInSentence","_htmlParser","_lodash","_helpers","e","__esModule","default","regexFromDoubleArray","regexFromDoubleArrayCacheKey","getRegexFromDoubleArray","twoPartTransitionWords","cacheKey","flattenDeep","join","createRegexFromDoubleArray","matchTwoPartTransitionWords","sentence","normalizeSingleQuotes","twoPartTransitionWordsRegex","match","matchTransitionWords","transitionWords","filter","word","matchWordInSentence","checkSentencesForTransitionWords","sentences","matchTransitionWordsHelper","results","forEach","twoPartMatches","push","transitionWordMatches","length","_default","paper","researcher","getHelper","getConfig","memoizedTokenizer","text","getText","removeHtmlBlocks","filterShortcodesFromHTML","_attributes","shortcodes","getSentences","sentenceResults","totalSentences","transitionWordSentences"],"sources":["../../../src/languageProcessing/researches/findTransitionWords.js"],"sourcesContent":["import createRegexFromDoubleArray from \"../helpers/regex/createRegexFromDoubleArray.js\";\nimport getSentences from \"../helpers/sentence/getSentences.js\";\nimport { normalizeSingle as normalizeSingleQuotes } from \"../helpers/sanitize/quotes.js\";\nimport { isWordInSentence as matchWordInSentence } from \"../helpers/word/matchWordInSentence.js\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\n\nimport { flattenDeep } from \"lodash\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\n\nlet regexFromDoubleArray = null;\nlet regexFromDoubleArrayCacheKey = \"\";\n\n/**\n * Memoizes the createRegexFromDoubleArray with the twoPartTransitionWords.\n *\n * @param {Array} twoPartTransitionWords The array containing two-part transition words.\n *\n * @returns {RegExp} The RegExp to match text with a double array.\n */\nfunction getRegexFromDoubleArray( twoPartTransitionWords ) {\n\tconst cacheKey = flattenDeep( twoPartTransitionWords ).join( \"\" );\n\tif ( regexFromDoubleArrayCacheKey !== cacheKey || regexFromDoubleArray === null ) {\n\t\tregexFromDoubleArrayCacheKey = cacheKey;\n\t\tregexFromDoubleArray = createRegexFromDoubleArray( twoPartTransitionWords );\n\t}\n\treturn regexFromDoubleArray;\n}\n\n/**\n * Matches the sentence against two part transition words.\n *\n * @param {string} sentence The sentence to match against.\n * @param {Array} twoPartTransitionWords The array containing two-part transition words.\n * @returns {Array} The found transitional words.\n */\nconst matchTwoPartTransitionWords = function( sentence, twoPartTransitionWords ) {\n\tsentence = normalizeSingleQuotes( sentence );\n\tconst twoPartTransitionWordsRegex = getRegexFromDoubleArray( twoPartTransitionWords );\n\treturn sentence.match( twoPartTransitionWordsRegex );\n};\n\n/**\n * Matches the sentence against transition words.\n *\n * @param {string} sentence The sentence to match against.\n * @param {Array} transitionWords The array containing transition words.\n * @returns {Array} The found transitional words.\n */\nconst matchTransitionWords = function( sentence, transitionWords ) {\n\tsentence = normalizeSingleQuotes( sentence );\n\treturn transitionWords.filter( word => matchWordInSentence( word, sentence ) );\n};\n\n/**\n * Checks the passed sentences to see if they contain transition words.\n *\n * @param {Array} sentences The sentences to match against.\n * @param {Array} transitionWords The array containing transition words.\n * @param {Array} twoPartTransitionWords The array containing two part transition words.\n * @param {function} matchTransitionWordsHelper The language-specific helper function to match transition words in a sentence.\n *\n * @returns {Array} Array of sentence objects containing the complete sentence and the transition words.\n */\nconst checkSentencesForTransitionWords = function( sentences, transitionWords, twoPartTransitionWords, matchTransitionWordsHelper ) {\n\tconst results = [];\n\n\tsentences.forEach( sentence => {\n\t\tif ( twoPartTransitionWords ) {\n\t\t\tconst twoPartMatches = matchTwoPartTransitionWords( sentence, twoPartTransitionWords );\n\n\t\t\tif ( twoPartMatches !== null ) {\n\t\t\t\tresults.push( {\n\t\t\t\t\tsentence: sentence,\n\t\t\t\t\ttransitionWords: twoPartMatches,\n\t\t\t\t} );\n\n\t\t\t\treturn;\n\t\t\t}\n\t\t}\n\n\t\tconst transitionWordMatches = matchTransitionWordsHelper\n\t\t\t? matchTransitionWordsHelper( sentence, transitionWords )\n\t\t\t: matchTransitionWords( sentence, transitionWords );\n\n\t\tif ( transitionWordMatches.length !== 0 ) {\n\t\t\tresults.push( {\n\t\t\t\tsentence: sentence,\n\t\t\t\ttransitionWords: transitionWordMatches,\n\t\t\t} );\n\t\t}\n\t} );\n\n\treturn results;\n};\n\n/**\n * Checks how many sentences from a text contain at least one transition word or two-part transition word\n * that are defined in the transition words config and two part transition words config.\n *\n * @param {Paper} paper The Paper object to get text from.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {object} An object with the total number of sentences in the text\n *                   and the total number of sentences containing one or more transition words.\n */\nexport default function( paper, researcher ) {\n\tconst matchTransitionWordsHelper = researcher.getHelper( \"matchTransitionWordsHelper\" );\n\tconst transitionWords = researcher.getConfig( \"transitionWords\" );\n\tconst twoPartTransitionWords = researcher.getConfig( \"twoPartTransitionWords\" );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\tconst sentences = getSentences( text, memoizedTokenizer );\n\tconst sentenceResults = checkSentencesForTransitionWords( sentences, transitionWords, twoPartTransitionWords, matchTransitionWordsHelper );\n\n\treturn {\n\t\ttotalSentences: sentences.length,\n\t\tsentenceResults: sentenceResults,\n\t\ttransitionWordSentences: sentenceResults.length,\n\t};\n}\n"],"mappings":";;;;;;AAAA,IAAAA,2BAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,aAAA,GAAAF,sBAAA,CAAAC,OAAA;AACA,IAAAE,OAAA,GAAAF,OAAA;AACA,IAAAG,oBAAA,GAAAH,OAAA;AACA,IAAAI,WAAA,GAAAL,sBAAA,CAAAC,OAAA;AAEA,IAAAK,OAAA,GAAAL,OAAA;AACA,IAAAM,QAAA,GAAAN,OAAA;AAAsD,SAAAD,uBAAAQ,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEtD,IAAIG,oBAAoB,GAAG,IAAI;AAC/B,IAAIC,4BAA4B,GAAG,EAAE;;AAErC;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,uBAAuBA,CAAEC,sBAAsB,EAAG;EAC1D,MAAMC,QAAQ,GAAG,IAAAC,mBAAW,EAAEF,sBAAuB,CAAC,CAACG,IAAI,CAAE,EAAG,CAAC;EACjE,IAAKL,4BAA4B,KAAKG,QAAQ,IAAIJ,oBAAoB,KAAK,IAAI,EAAG;IACjFC,4BAA4B,GAAGG,QAAQ;IACvCJ,oBAAoB,GAAG,IAAAO,mCAA0B,EAAEJ,sBAAuB,CAAC;EAC5E;EACA,OAAOH,oBAAoB;AAC5B;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMQ,2BAA2B,GAAG,SAAAA,CAAUC,QAAQ,EAAEN,sBAAsB,EAAG;EAChFM,QAAQ,GAAG,IAAAC,uBAAqB,EAAED,QAAS,CAAC;EAC5C,MAAME,2BAA2B,GAAGT,uBAAuB,CAAEC,sBAAuB,CAAC;EACrF,OAAOM,QAAQ,CAACG,KAAK,CAAED,2BAA4B,CAAC;AACrD,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,oBAAoB,GAAG,SAAAA,CAAUJ,QAAQ,EAAEK,eAAe,EAAG;EAClEL,QAAQ,GAAG,IAAAC,uBAAqB,EAAED,QAAS,CAAC;EAC5C,OAAOK,eAAe,CAACC,MAAM,CAAEC,IAAI,IAAI,IAAAC,qCAAmB,EAAED,IAAI,EAAEP,QAAS,CAAE,CAAC;AAC/E,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMS,gCAAgC,GAAG,SAAAA,CAAUC,SAAS,EAAEL,eAAe,EAAEX,sBAAsB,EAAEiB,0BAA0B,EAAG;EACnI,MAAMC,OAAO,GAAG,EAAE;EAElBF,SAAS,CAACG,OAAO,CAAEb,QAAQ,IAAI;IAC9B,IAAKN,sBAAsB,EAAG;MAC7B,MAAMoB,cAAc,GAAGf,2BAA2B,CAAEC,QAAQ,EAAEN,sBAAuB,CAAC;MAEtF,IAAKoB,cAAc,KAAK,IAAI,EAAG;QAC9BF,OAAO,CAACG,IAAI,CAAE;UACbf,QAAQ,EAAEA,QAAQ;UAClBK,eAAe,EAAES;QAClB,CAAE,CAAC;QAEH;MACD;IACD;IAEA,MAAME,qBAAqB,GAAGL,0BAA0B,GACrDA,0BAA0B,CAAEX,QAAQ,EAAEK,eAAgB,CAAC,GACvDD,oBAAoB,CAAEJ,QAAQ,EAAEK,eAAgB,CAAC;IAEpD,IAAKW,qBAAqB,CAACC,MAAM,KAAK,CAAC,EAAG;MACzCL,OAAO,CAACG,IAAI,CAAE;QACbf,QAAQ,EAAEA,QAAQ;QAClBK,eAAe,EAAEW;MAClB,CAAE,CAAC;IACJ;EACD,CAAE,CAAC;EAEH,OAAOJ,OAAO;AACf,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAM,SAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C,MAAMT,0BAA0B,GAAGS,UAAU,CAACC,SAAS,CAAE,4BAA6B,CAAC;EACvF,MAAMhB,eAAe,GAAGe,UAAU,CAACE,SAAS,CAAE,iBAAkB,CAAC;EACjE,MAAM5B,sBAAsB,GAAG0B,UAAU,CAACE,SAAS,CAAE,wBAAyB,CAAC;EAC/E,MAAMC,iBAAiB,GAAGH,UAAU,CAACC,SAAS,CAAE,mBAAoB,CAAC;EAErE,IAAIG,IAAI,GAAGL,KAAK,CAACM,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAG,IAAAE,mBAAgB,EAAEF,IAAK,CAAC;EAC/BA,IAAI,GAAG,IAAAG,iCAAwB,EAAEH,IAAI,EAAEL,KAAK,CAACS,WAAW,IAAIT,KAAK,CAACS,WAAW,CAACC,UAAW,CAAC;EAC1F,MAAMnB,SAAS,GAAG,IAAAoB,qBAAY,EAAEN,IAAI,EAAED,iBAAkB,CAAC;EACzD,MAAMQ,eAAe,GAAGtB,gCAAgC,CAAEC,SAAS,EAAEL,eAAe,EAAEX,sBAAsB,EAAEiB,0BAA2B,CAAC;EAE1I,OAAO;IACNqB,cAAc,EAAEtB,SAAS,CAACO,MAAM;IAChCc,eAAe,EAAEA,eAAe;IAChCE,uBAAuB,EAAEF,eAAe,CAACd;EAC1C,CAAC;AACF","ignoreList":[]}
+{"version":3,"file":"findTransitionWords.js","names":["createRegexFromDoubleArray","getSentences","normalizeSingle","normalizeSingleQuotes","isWordInSentence","matchWordInSentence","removeHtmlBlocks","flattenDeep","filterShortcodesFromHTML","regexFromDoubleArray","regexFromDoubleArrayCacheKey","getRegexFromDoubleArray","twoPartTransitionWords","cacheKey","join","matchTwoPartTransitionWords","sentence","twoPartTransitionWordsRegex","match","matchTransitionWords","transitionWords","filter","word","checkSentencesForTransitionWords","sentences","matchTransitionWordsHelper","results","forEach","twoPartMatches","push","transitionWordMatches","length","paper","researcher","getHelper","getConfig","memoizedTokenizer","text","getText","_attributes","shortcodes","sentenceResults","totalSentences","transitionWordSentences"],"sources":["../../../src/languageProcessing/researches/findTransitionWords.js"],"sourcesContent":["import createRegexFromDoubleArray from \"../helpers/regex/createRegexFromDoubleArray.js\";\nimport getSentences from \"../helpers/sentence/getSentences.js\";\nimport { normalizeSingle as normalizeSingleQuotes } from \"../helpers/sanitize/quotes.js\";\nimport { isWordInSentence as matchWordInSentence } from \"../helpers/word/matchWordInSentence.js\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\n\nimport { flattenDeep } from \"lodash\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\n\nlet regexFromDoubleArray = null;\nlet regexFromDoubleArrayCacheKey = \"\";\n\n/**\n * Memoizes the createRegexFromDoubleArray with the twoPartTransitionWords.\n *\n * @param {Array} twoPartTransitionWords The array containing two-part transition words.\n *\n * @returns {RegExp} The RegExp to match text with a double array.\n */\nfunction getRegexFromDoubleArray( twoPartTransitionWords ) {\n\tconst cacheKey = flattenDeep( twoPartTransitionWords ).join( \"\" );\n\tif ( regexFromDoubleArrayCacheKey !== cacheKey || regexFromDoubleArray === null ) {\n\t\tregexFromDoubleArrayCacheKey = cacheKey;\n\t\tregexFromDoubleArray = createRegexFromDoubleArray( twoPartTransitionWords );\n\t}\n\treturn regexFromDoubleArray;\n}\n\n/**\n * Matches the sentence against two part transition words.\n *\n * @param {string} sentence The sentence to match against.\n * @param {Array} twoPartTransitionWords The array containing two-part transition words.\n * @returns {Array} The found transitional words.\n */\nconst matchTwoPartTransitionWords = function( sentence, twoPartTransitionWords ) {\n\tsentence = normalizeSingleQuotes( sentence );\n\tconst twoPartTransitionWordsRegex = getRegexFromDoubleArray( twoPartTransitionWords );\n\treturn sentence.match( twoPartTransitionWordsRegex );\n};\n\n/**\n * Matches the sentence against transition words.\n *\n * @param {string} sentence The sentence to match against.\n * @param {Array} transitionWords The array containing transition words.\n * @returns {Array} The found transitional words.\n */\nconst matchTransitionWords = function( sentence, transitionWords ) {\n\tsentence = normalizeSingleQuotes( sentence );\n\treturn transitionWords.filter( word => matchWordInSentence( word, sentence ) );\n};\n\n/**\n * Checks the passed sentences to see if they contain transition words.\n *\n * @param {Array} sentences The sentences to match against.\n * @param {Array} transitionWords The array containing transition words.\n * @param {Array} twoPartTransitionWords The array containing two part transition words.\n * @param {function} matchTransitionWordsHelper The language-specific helper function to match transition words in a sentence.\n *\n * @returns {Array} Array of sentence objects containing the complete sentence and the transition words.\n */\nconst checkSentencesForTransitionWords = function( sentences, transitionWords, twoPartTransitionWords, matchTransitionWordsHelper ) {\n\tconst results = [];\n\n\tsentences.forEach( sentence => {\n\t\tif ( twoPartTransitionWords ) {\n\t\t\tconst twoPartMatches = matchTwoPartTransitionWords( sentence, twoPartTransitionWords );\n\n\t\t\tif ( twoPartMatches !== null ) {\n\t\t\t\tresults.push( {\n\t\t\t\t\tsentence: sentence,\n\t\t\t\t\ttransitionWords: twoPartMatches,\n\t\t\t\t} );\n\n\t\t\t\treturn;\n\t\t\t}\n\t\t}\n\n\t\tconst transitionWordMatches = matchTransitionWordsHelper\n\t\t\t? matchTransitionWordsHelper( sentence, transitionWords )\n\t\t\t: matchTransitionWords( sentence, transitionWords );\n\n\t\tif ( transitionWordMatches.length !== 0 ) {\n\t\t\tresults.push( {\n\t\t\t\tsentence: sentence,\n\t\t\t\ttransitionWords: transitionWordMatches,\n\t\t\t} );\n\t\t}\n\t} );\n\n\treturn results;\n};\n\n/**\n * Checks how many sentences from a text contain at least one transition word or two-part transition word\n * that are defined in the transition words config and two part transition words config.\n *\n * @param {Paper} paper The Paper object to get text from.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {object} An object with the total number of sentences in the text\n *                   and the total number of sentences containing one or more transition words.\n */\nexport default function( paper, researcher ) {\n\tconst matchTransitionWordsHelper = researcher.getHelper( \"matchTransitionWordsHelper\" );\n\tconst transitionWords = researcher.getConfig( \"transitionWords\" );\n\tconst twoPartTransitionWords = researcher.getConfig( \"twoPartTransitionWords\" );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\tconst sentences = getSentences( text, memoizedTokenizer );\n\tconst sentenceResults = checkSentencesForTransitionWords( sentences, transitionWords, twoPartTransitionWords, matchTransitionWordsHelper );\n\n\treturn {\n\t\ttotalSentences: sentences.length,\n\t\tsentenceResults: sentenceResults,\n\t\ttransitionWordSentences: sentenceResults.length,\n\t};\n}\n"],"mappings":"AAAA,OAAOA,0BAA0B;AACjC,OAAOC,YAAY;AACnB,SAASC,eAAe,IAAIC,qBAAqB;AACjD,SAASC,gBAAgB,IAAIC,mBAAmB;AAChD,OAAOC,gBAAgB;AAEvB,SAASC,WAAW,QAAQ,QAAQ;AACpC,SAASC,wBAAwB;AAEjC,IAAIC,oBAAoB,GAAG,IAAI;AAC/B,IAAIC,4BAA4B,GAAG,EAAE;;AAErC;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,uBAAuBA,CAAEC,sBAAsB,EAAG;EAC1D,MAAMC,QAAQ,GAAGN,WAAW,CAAEK,sBAAuB,CAAC,CAACE,IAAI,CAAE,EAAG,CAAC;EACjE,IAAKJ,4BAA4B,KAAKG,QAAQ,IAAIJ,oBAAoB,KAAK,IAAI,EAAG;IACjFC,4BAA4B,GAAGG,QAAQ;IACvCJ,oBAAoB,GAAGT,0BAA0B,CAAEY,sBAAuB,CAAC;EAC5E;EACA,OAAOH,oBAAoB;AAC5B;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMM,2BAA2B,GAAG,SAAAA,CAAUC,QAAQ,EAAEJ,sBAAsB,EAAG;EAChFI,QAAQ,GAAGb,qBAAqB,CAAEa,QAAS,CAAC;EAC5C,MAAMC,2BAA2B,GAAGN,uBAAuB,CAAEC,sBAAuB,CAAC;EACrF,OAAOI,QAAQ,CAACE,KAAK,CAAED,2BAA4B,CAAC;AACrD,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,oBAAoB,GAAG,SAAAA,CAAUH,QAAQ,EAAEI,eAAe,EAAG;EAClEJ,QAAQ,GAAGb,qBAAqB,CAAEa,QAAS,CAAC;EAC5C,OAAOI,eAAe,CAACC,MAAM,CAAEC,IAAI,IAAIjB,mBAAmB,CAAEiB,IAAI,EAAEN,QAAS,CAAE,CAAC;AAC/E,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMO,gCAAgC,GAAG,SAAAA,CAAUC,SAAS,EAAEJ,eAAe,EAAER,sBAAsB,EAAEa,0BAA0B,EAAG;EACnI,MAAMC,OAAO,GAAG,EAAE;EAElBF,SAAS,CAACG,OAAO,CAAEX,QAAQ,IAAI;IAC9B,IAAKJ,sBAAsB,EAAG;MAC7B,MAAMgB,cAAc,GAAGb,2BAA2B,CAAEC,QAAQ,EAAEJ,sBAAuB,CAAC;MAEtF,IAAKgB,cAAc,KAAK,IAAI,EAAG;QAC9BF,OAAO,CAACG,IAAI,CAAE;UACbb,QAAQ,EAAEA,QAAQ;UAClBI,eAAe,EAAEQ;QAClB,CAAE,CAAC;QAEH;MACD;IACD;IAEA,MAAME,qBAAqB,GAAGL,0BAA0B,GACrDA,0BAA0B,CAAET,QAAQ,EAAEI,eAAgB,CAAC,GACvDD,oBAAoB,CAAEH,QAAQ,EAAEI,eAAgB,CAAC;IAEpD,IAAKU,qBAAqB,CAACC,MAAM,KAAK,CAAC,EAAG;MACzCL,OAAO,CAACG,IAAI,CAAE;QACbb,QAAQ,EAAEA,QAAQ;QAClBI,eAAe,EAAEU;MAClB,CAAE,CAAC;IACJ;EACD,CAAE,CAAC;EAEH,OAAOJ,OAAO;AACf,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUM,KAAK,EAAEC,UAAU,EAAG;EAC5C,MAAMR,0BAA0B,GAAGQ,UAAU,CAACC,SAAS,CAAE,4BAA6B,CAAC;EACvF,MAAMd,eAAe,GAAGa,UAAU,CAACE,SAAS,CAAE,iBAAkB,CAAC;EACjE,MAAMvB,sBAAsB,GAAGqB,UAAU,CAACE,SAAS,CAAE,wBAAyB,CAAC;EAC/E,MAAMC,iBAAiB,GAAGH,UAAU,CAACC,SAAS,CAAE,mBAAoB,CAAC;EAErE,IAAIG,IAAI,GAAGL,KAAK,CAACM,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAG/B,gBAAgB,CAAE+B,IAAK,CAAC;EAC/BA,IAAI,GAAG7B,wBAAwB,CAAE6B,IAAI,EAAEL,KAAK,CAACO,WAAW,IAAIP,KAAK,CAACO,WAAW,CAACC,UAAW,CAAC;EAC1F,MAAMhB,SAAS,GAAGvB,YAAY,CAAEoC,IAAI,EAAED,iBAAkB,CAAC;EACzD,MAAMK,eAAe,GAAGlB,gCAAgC,CAAEC,SAAS,EAAEJ,eAAe,EAAER,sBAAsB,EAAEa,0BAA2B,CAAC;EAE1I,OAAO;IACNiB,cAAc,EAAElB,SAAS,CAACO,MAAM;IAChCU,eAAe,EAAEA,eAAe;IAChCE,uBAAuB,EAAEF,eAAe,CAACV;EAC1C,CAAC;AACF","ignoreList":[]}

package/build/languageProcessing/researches/functionWordsInKeyphrase.js

@@ -1,14 +1,8 @@
-"use strict";
+import { filter, includes, isEmpty } from "lodash";
+import getWords from "../helpers/word/getWords";
+import processExactMatchRequest from "../helpers/match/processExactMatchRequest";
+import { WORD_BOUNDARY_WITH_HYPHEN } from "../../config/wordBoundariesWithoutPunctuation";
 
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
-var _lodash = require("lodash");
-var _getWords = _interopRequireDefault(require("../helpers/word/getWords"));
-var _processExactMatchRequest = _interopRequireDefault(require("../helpers/match/processExactMatchRequest"));
-var _wordBoundariesWithoutPunctuation = require("../../config/wordBoundariesWithoutPunctuation");
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /**
  * Checks if the keyphrase contains of function words only.
  *
@@ -17,7 +11,7 @@ function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e
  *
  * @returns {boolean} Whether the keyphrase contains of content words only.
  */
-function _default(paper, researcher) {
+export default function (paper, researcher) {
   const functionWords = researcher.getConfig("functionWords");
 
   // A helper to get words from the keyphrase for languages that don't use the default way.
@@ -25,7 +19,7 @@ function _default(paper, researcher) {
   const keyphrase = paper.getKeyword();
 
   // Return false if there are double quotes around the keyphrase.
-  if ((0, _processExactMatchRequest.default)(keyphrase).exactMatchRequested) {
+  if (processExactMatchRequest(keyphrase).exactMatchRequested) {
     return false;
   }
 
@@ -39,10 +33,10 @@ function _default(paper, researcher) {
       * As a downside, single function words containing hyphens (e.g. 'vis-à-vis') won't be automatically matched, but we
       * are solving this by adding each word from such function words as separate entries in the function words lists.
       */
-  let keyphraseWords = getWordsCustomHelper ? getWordsCustomHelper(keyphrase) : (0, _getWords.default)(keyphrase, _wordBoundariesWithoutPunctuation.WORD_BOUNDARY_WITH_HYPHEN);
-  keyphraseWords = (0, _lodash.filter)(keyphraseWords, function (word) {
-    return !(0, _lodash.includes)(functionWords, word.trim().toLocaleLowerCase());
+  let keyphraseWords = getWordsCustomHelper ? getWordsCustomHelper(keyphrase) : getWords(keyphrase, WORD_BOUNDARY_WITH_HYPHEN);
+  keyphraseWords = filter(keyphraseWords, function (word) {
+    return !includes(functionWords, word.trim().toLocaleLowerCase());
   });
-  return (0, _lodash.isEmpty)(keyphraseWords);
+  return isEmpty(keyphraseWords);
 }
 //# sourceMappingURL=functionWordsInKeyphrase.js.map

package/build/languageProcessing/researches/functionWordsInKeyphrase.js.map

@@ -1 +1 @@
-{"version":3,"file":"functionWordsInKeyphrase.js","names":["_lodash","require","_getWords","_interopRequireDefault","_processExactMatchRequest","_wordBoundariesWithoutPunctuation","e","__esModule","default","_default","paper","researcher","functionWords","getConfig","getWordsCustomHelper","getHelper","keyphrase","getKeyword","processExactMatchRequest","exactMatchRequested","keyphraseWords","getWords","WORD_BOUNDARY_WITH_HYPHEN","filter","word","includes","trim","toLocaleLowerCase","isEmpty"],"sources":["../../../src/languageProcessing/researches/functionWordsInKeyphrase.js"],"sourcesContent":["import { filter, includes, isEmpty } from \"lodash\";\nimport getWords from \"../helpers/word/getWords\";\nimport processExactMatchRequest from \"../helpers/match/processExactMatchRequest\";\nimport { WORD_BOUNDARY_WITH_HYPHEN } from \"../../config/wordBoundariesWithoutPunctuation\";\n\n/**\n * Checks if the keyphrase contains of function words only.\n *\n * @param {object} paper The paper containing the keyword.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {boolean} Whether the keyphrase contains of content words only.\n */\nexport default function( paper, researcher ) {\n\tconst functionWords = researcher.getConfig( \"functionWords\" );\n\n\t// A helper to get words from the keyphrase for languages that don't use the default way.\n\tconst getWordsCustomHelper = researcher.getHelper( \"getWordsCustomHelper\" );\n\tconst keyphrase = paper.getKeyword();\n\n\t// Return false if there are double quotes around the keyphrase.\n\tif ( processExactMatchRequest( keyphrase ).exactMatchRequested ) {\n\t\treturn false;\n\t}\n\n\t/*\n     * We use a word boundary regex that includes whitespaces, en-dashes, and hyphens for all languages.\n     * This means that we also consider keyphrases that consist of function words separated by hyphens (e.g. 'two-year-old')\n     * as containing only function words. Since many hyphenated phrases can also be written without hyphens, this way the\n     * behavior for hyphenated phrases matches the behavior for unhyphenated phrases.\n     * In Indonesian we normally don't want to treat hyphens as word boundaries, but in this case it makes sense because\n     * in Indonesian you can also have function words seperated by hyphens (e.g. 'dua-lima').\n     * As a downside, single function words containing hyphens (e.g. 'vis-à-vis') won't be automatically matched, but we\n     * are solving this by adding each word from such function words as separate entries in the function words lists.\n     */\n\tlet keyphraseWords = getWordsCustomHelper ? getWordsCustomHelper( keyphrase )\n\t\t: getWords( keyphrase, WORD_BOUNDARY_WITH_HYPHEN );\n\n\tkeyphraseWords = filter( keyphraseWords, function( word ) {\n\t\treturn ( ! includes( functionWords, word.trim().toLocaleLowerCase() ) );\n\t} );\n\n\treturn isEmpty( keyphraseWords );\n}\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AACA,IAAAC,SAAA,GAAAC,sBAAA,CAAAF,OAAA;AACA,IAAAG,yBAAA,GAAAD,sBAAA,CAAAF,OAAA;AACA,IAAAI,iCAAA,GAAAJ,OAAA;AAA0F,SAAAE,uBAAAG,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAE1F;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C,MAAMC,aAAa,GAAGD,UAAU,CAACE,SAAS,CAAE,eAAgB,CAAC;;EAE7D;EACA,MAAMC,oBAAoB,GAAGH,UAAU,CAACI,SAAS,CAAE,sBAAuB,CAAC;EAC3E,MAAMC,SAAS,GAAGN,KAAK,CAACO,UAAU,CAAC,CAAC;;EAEpC;EACA,IAAK,IAAAC,iCAAwB,EAAEF,SAAU,CAAC,CAACG,mBAAmB,EAAG;IAChE,OAAO,KAAK;EACb;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACC,IAAIC,cAAc,GAAGN,oBAAoB,GAAGA,oBAAoB,CAAEE,SAAU,CAAC,GAC1E,IAAAK,iBAAQ,EAAEL,SAAS,EAAEM,2DAA0B,CAAC;EAEnDF,cAAc,GAAG,IAAAG,cAAM,EAAEH,cAAc,EAAE,UAAUI,IAAI,EAAG;IACzD,OAAS,CAAE,IAAAC,gBAAQ,EAAEb,aAAa,EAAEY,IAAI,CAACE,IAAI,CAAC,CAAC,CAACC,iBAAiB,CAAC,CAAE,CAAC;EACtE,CAAE,CAAC;EAEH,OAAO,IAAAC,eAAO,EAAER,cAAe,CAAC;AACjC","ignoreList":[]}
+{"version":3,"file":"functionWordsInKeyphrase.js","names":["filter","includes","isEmpty","getWords","processExactMatchRequest","WORD_BOUNDARY_WITH_HYPHEN","paper","researcher","functionWords","getConfig","getWordsCustomHelper","getHelper","keyphrase","getKeyword","exactMatchRequested","keyphraseWords","word","trim","toLocaleLowerCase"],"sources":["../../../src/languageProcessing/researches/functionWordsInKeyphrase.js"],"sourcesContent":["import { filter, includes, isEmpty } from \"lodash\";\nimport getWords from \"../helpers/word/getWords\";\nimport processExactMatchRequest from \"../helpers/match/processExactMatchRequest\";\nimport { WORD_BOUNDARY_WITH_HYPHEN } from \"../../config/wordBoundariesWithoutPunctuation\";\n\n/**\n * Checks if the keyphrase contains of function words only.\n *\n * @param {object} paper The paper containing the keyword.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {boolean} Whether the keyphrase contains of content words only.\n */\nexport default function( paper, researcher ) {\n\tconst functionWords = researcher.getConfig( \"functionWords\" );\n\n\t// A helper to get words from the keyphrase for languages that don't use the default way.\n\tconst getWordsCustomHelper = researcher.getHelper( \"getWordsCustomHelper\" );\n\tconst keyphrase = paper.getKeyword();\n\n\t// Return false if there are double quotes around the keyphrase.\n\tif ( processExactMatchRequest( keyphrase ).exactMatchRequested ) {\n\t\treturn false;\n\t}\n\n\t/*\n     * We use a word boundary regex that includes whitespaces, en-dashes, and hyphens for all languages.\n     * This means that we also consider keyphrases that consist of function words separated by hyphens (e.g. 'two-year-old')\n     * as containing only function words. Since many hyphenated phrases can also be written without hyphens, this way the\n     * behavior for hyphenated phrases matches the behavior for unhyphenated phrases.\n     * In Indonesian we normally don't want to treat hyphens as word boundaries, but in this case it makes sense because\n     * in Indonesian you can also have function words seperated by hyphens (e.g. 'dua-lima').\n     * As a downside, single function words containing hyphens (e.g. 'vis-à-vis') won't be automatically matched, but we\n     * are solving this by adding each word from such function words as separate entries in the function words lists.\n     */\n\tlet keyphraseWords = getWordsCustomHelper ? getWordsCustomHelper( keyphrase )\n\t\t: getWords( keyphrase, WORD_BOUNDARY_WITH_HYPHEN );\n\n\tkeyphraseWords = filter( keyphraseWords, function( word ) {\n\t\treturn ( ! includes( functionWords, word.trim().toLocaleLowerCase() ) );\n\t} );\n\n\treturn isEmpty( keyphraseWords );\n}\n"],"mappings":"AAAA,SAASA,MAAM,EAAEC,QAAQ,EAAEC,OAAO,QAAQ,QAAQ;AAClD,OAAOC,QAAQ;AACf,OAAOC,wBAAwB;AAC/B,SAASC,yBAAyB;;AAElC;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C,MAAMC,aAAa,GAAGD,UAAU,CAACE,SAAS,CAAE,eAAgB,CAAC;;EAE7D;EACA,MAAMC,oBAAoB,GAAGH,UAAU,CAACI,SAAS,CAAE,sBAAuB,CAAC;EAC3E,MAAMC,SAAS,GAAGN,KAAK,CAACO,UAAU,CAAC,CAAC;;EAEpC;EACA,IAAKT,wBAAwB,CAAEQ,SAAU,CAAC,CAACE,mBAAmB,EAAG;IAChE,OAAO,KAAK;EACb;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACC,IAAIC,cAAc,GAAGL,oBAAoB,GAAGA,oBAAoB,CAAEE,SAAU,CAAC,GAC1ET,QAAQ,CAAES,SAAS,EAAEP,yBAA0B,CAAC;EAEnDU,cAAc,GAAGf,MAAM,CAAEe,cAAc,EAAE,UAAUC,IAAI,EAAG;IACzD,OAAS,CAAEf,QAAQ,CAAEO,aAAa,EAAEQ,IAAI,CAACC,IAAI,CAAC,CAAC,CAACC,iBAAiB,CAAC,CAAE,CAAC;EACtE,CAAE,CAAC;EAEH,OAAOhB,OAAO,CAAEa,cAAe,CAAC;AACjC","ignoreList":[]}

package/build/languageProcessing/researches/getAnchorsWithKeyphrase.js

@@ -1,19 +1,12 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
-var _lodash = require("lodash");
-var _filterWordsFromArray = _interopRequireDefault(require("../helpers/word/filterWordsFromArray"));
-var _findKeywordFormsInString = require("../helpers/match/findKeywordFormsInString");
-var _getWords = _interopRequireDefault(require("../helpers/word/getWords"));
-var _matchTextWithArray = _interopRequireDefault(require("../helpers/match/matchTextWithArray"));
-var _parseSynonyms = _interopRequireDefault(require("../helpers/sanitize/parseSynonyms"));
-var _processExactMatchRequest = _interopRequireDefault(require("../helpers/match/processExactMatchRequest"));
-var _url = _interopRequireDefault(require("../helpers/url/url.js"));
-var _wordBoundariesWithoutPunctuation = require("../../config/wordBoundariesWithoutPunctuation");
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+import { flatten, uniq } from "lodash";
+import filterWordsFromArray from "../helpers/word/filterWordsFromArray";
+import { findTopicFormsInString } from "../helpers/match/findKeywordFormsInString";
+import getWords from "../helpers/word/getWords";
+import matchTextWithArray from "../helpers/match/matchTextWithArray";
+import parseSynonyms from "../helpers/sanitize/parseSynonyms";
+import processExactMatchRequest from "../helpers/match/processExactMatchRequest";
+import urlHelper from "../helpers/url/url.js";
+import { WORD_BOUNDARY_WITH_HYPHEN, WORD_BOUNDARY_WITHOUT_HYPHEN } from "../../config/wordBoundariesWithoutPunctuation";
 let functionWords = [];
 
 /**
@@ -26,7 +19,7 @@ let functionWords = [];
  * @returns {boolean} Whether the anchor's link is a relative fragment or the same as the site url/domain.
  */
 function isLinkingToSelf(anchorLink, siteUrlOrDomain) {
-  return Boolean(_url.default.areEqual(anchorLink, siteUrlOrDomain) || _url.default.isRelativeFragmentURL(anchorLink));
+  return Boolean(urlHelper.areEqual(anchorLink, siteUrlOrDomain) || urlHelper.isRelativeFragmentURL(anchorLink));
 }
 
 /**
@@ -60,7 +53,7 @@ function getAnchorsContainingTopic(anchors, topicForms, locale, matchWordCustomH
   const anchorsContainingTopic = anchors.map(function (anchor) {
     // Only retrieve the anchor's text. This is because we only use the anchor text for the following check.
     const anchorText = anchor.innerText();
-    return (0, _findKeywordFormsInString.findTopicFormsInString)(topicForms, anchorText, true, locale, matchWordCustomHelper).percentWordMatches === 100;
+    return findTopicFormsInString(topicForms, anchorText, true, locale, matchWordCustomHelper).percentWordMatches === 100;
   });
   return anchors.filter((anchor, index) => anchorsContainingTopic[index]);
 }
@@ -83,9 +76,9 @@ function getAnchorsWithSameTextAsTopic(anchors, topicForms, locale, customHelper
   const getWordsCustomHelper = customHelpers.getWordsCustomHelper;
 
   // Prepare keyphrase and synonym forms for comparison with anchors.
-  const keyphraseAndSynonymsWords = [(0, _lodash.flatten)(topicForms.keyphraseForms)];
+  const keyphraseAndSynonymsWords = [flatten(topicForms.keyphraseForms)];
   const synonymsForms = topicForms.synonymsForms;
-  synonymsForms.forEach(form => keyphraseAndSynonymsWords.push((0, _lodash.flatten)(form)));
+  synonymsForms.forEach(form => keyphraseAndSynonymsWords.push(flatten(form)));
 
   // The variable that will save all the anchors with text that has the same content words as the keyphrase/synonyms.
   const anchorsContainedInTopic = [];
@@ -103,18 +96,18 @@ function getAnchorsWithSameTextAsTopic(anchors, topicForms, locale, customHelper
           */
     let anchorWords;
     if (getWordsCustomHelper) {
-      anchorWords = (0, _lodash.uniq)(getWordsCustomHelper(currentAnchorText));
+      anchorWords = uniq(getWordsCustomHelper(currentAnchorText));
     } else if (areHyphensWordBoundaries) {
-      anchorWords = (0, _lodash.uniq)((0, _getWords.default)(currentAnchorText, _wordBoundariesWithoutPunctuation.WORD_BOUNDARY_WITH_HYPHEN));
+      anchorWords = uniq(getWords(currentAnchorText, WORD_BOUNDARY_WITH_HYPHEN));
     } else {
-      anchorWords = (0, _lodash.uniq)((0, _getWords.default)(currentAnchorText, _wordBoundariesWithoutPunctuation.WORD_BOUNDARY_WITHOUT_HYPHEN));
+      anchorWords = uniq(getWords(currentAnchorText, WORD_BOUNDARY_WITHOUT_HYPHEN));
     }
 
     /*
      * Filter function words out of the anchor text.
      * If the anchor text contains only function words, we keep them.
      */
-    const filteredAnchorWords = (0, _filterWordsFromArray.default)(anchorWords, functionWords);
+    const filteredAnchorWords = filterWordsFromArray(anchorWords, functionWords);
     if (filteredAnchorWords.length > 0) {
       anchorWords = filteredAnchorWords;
     }
@@ -131,7 +124,7 @@ function getAnchorsWithSameTextAsTopic(anchors, topicForms, locale, customHelper
     // Check if every word in the anchor text is also present in the keyphrase/synonym.
     for (let i = 0; i < keyphraseAndSynonymsWords.length; i++) {
       const topicForm = keyphraseAndSynonymsWords[i];
-      if (anchorWords.every(anchorWord => (0, _matchTextWithArray.default)(anchorWord, topicForm, locale, matchWordCustomHelper).count > 0)) {
+      if (anchorWords.every(anchorWord => matchTextWithArray(anchorWord, topicForm, locale, matchWordCustomHelper).count > 0)) {
         anchorsContainedInTopic.push(true);
         break;
       }
@@ -149,7 +142,7 @@ function getAnchorsWithSameTextAsTopic(anchors, topicForms, locale, customHelper
  *
  * @returns {Object} The amount of anchor texts whose content words are the same as the keyphrase or synonyms' content words.
  */
-function _default(paper, researcher) {
+export default function (paper, researcher) {
   functionWords = researcher.getConfig("functionWords");
   const areHyphensWordBoundaries = researcher.getConfig("areHyphensWordBoundaries");
   const result = {
@@ -176,7 +169,7 @@ function _default(paper, researcher) {
    * When the keyphrase is set, also retrieve the synonyms and save them in "topics" array.
    * Eventually, the term topics here refers to either keyphrase or synonyms.
    */
-  const originalTopics = (0, _parseSynonyms.default)(paper.getSynonyms());
+  const originalTopics = parseSynonyms(paper.getSynonyms());
   originalTopics.push(keyphrase);
 
   // Retrieve the anchors.
@@ -211,7 +204,7 @@ function _default(paper, researcher) {
 
   // STEP 5.
   // Check if exact match is requested for every topic (keyphrase or synonym).
-  const isExactMatchRequested = originalTopics.map(originalTopic => (0, _processExactMatchRequest.default)(originalTopic));
+  const isExactMatchRequested = originalTopics.map(originalTopic => processExactMatchRequest(originalTopic));
   // Get the anchors with text that has the same content words as the keyphrase/synonyms.
   anchors = getAnchorsWithSameTextAsTopic(anchors, topicForms, locale, customHelpers, isExactMatchRequested, areHyphensWordBoundaries);
   return {

package/build/languageProcessing/researches/getAnchorsWithKeyphrase.js.map

@@ -1 +1 @@
-{"version":3,"file":"getAnchorsWithKeyphrase.js","names":["_lodash","require","_filterWordsFromArray","_interopRequireDefault","_findKeywordFormsInString","_getWords","_matchTextWithArray","_parseSynonyms","_processExactMatchRequest","_url","_wordBoundariesWithoutPunctuation","e","__esModule","default","functionWords","isLinkingToSelf","anchorLink","siteUrlOrDomain","Boolean","urlHelper","areEqual","isRelativeFragmentURL","getAnchorsLinkingToSelf","anchors","anchorsLinkingToSelf","map","anchor","attributes","href","filter","index","getAnchorsContainingTopic","topicForms","locale","matchWordCustomHelper","anchorsContainingTopic","anchorText","innerText","findTopicFormsInString","percentWordMatches","getAnchorsWithSameTextAsTopic","customHelpers","exactMatchRequest","areHyphensWordBoundaries","getWordsCustomHelper","keyphraseAndSynonymsWords","flatten","keyphraseForms","synonymsForms","forEach","form","push","anchorsContainedInTopic","currentAnchor","currentAnchorText","anchorWords","uniq","getWords","WORD_BOUNDARY_WITH_HYPHEN","WORD_BOUNDARY_WITHOUT_HYPHEN","filteredAnchorWords","filterWordsFromArray","length","request","exactMatchRequested","every","anchorWord","keyphrase","includes","i","topicForm","matchTextWithArray","count","_default","paper","researcher","getConfig","result","anchorsWithKeyphrase","anchorsWithKeyphraseCount","getText","getKeyword","originalTopics","parseSynonyms","getSynonyms","getTree","findAll","treeNode","name","getPermalink","getLocale","getResearch","getHelper","isExactMatchRequested","originalTopic","processExactMatchRequest"],"sources":["../../../src/languageProcessing/researches/getAnchorsWithKeyphrase.js"],"sourcesContent":["import { flatten, uniq } from \"lodash\";\nimport filterWordsFromArray from \"../helpers/word/filterWordsFromArray\";\nimport { findTopicFormsInString } from \"../helpers/match/findKeywordFormsInString\";\nimport getWords from \"../helpers/word/getWords\";\nimport matchTextWithArray from \"../helpers/match/matchTextWithArray\";\nimport parseSynonyms from \"../helpers/sanitize/parseSynonyms\";\nimport processExactMatchRequest from \"../helpers/match/processExactMatchRequest\";\nimport urlHelper from \"../helpers/url/url.js\";\nimport { WORD_BOUNDARY_WITH_HYPHEN, WORD_BOUNDARY_WITHOUT_HYPHEN } from \"../../config/wordBoundariesWithoutPunctuation\";\n\nlet functionWords = [];\n\n/**\n * Checks whether the anchor's link is a relative fragment or the same as the site url/domain.\n * Relative fragment links always point to the page itself.\n *\n * @param {String} anchorLink       The link anchor.\n * @param {String} siteUrlOrDomain  The site URL or domain of the paper.\n *\n * @returns {boolean} Whether the anchor's link is a relative fragment or the same as the site url/domain.\n */\nfunction isLinkingToSelf( anchorLink, siteUrlOrDomain ) {\n\treturn Boolean( urlHelper.areEqual( anchorLink, siteUrlOrDomain ) || urlHelper.isRelativeFragmentURL( anchorLink ) );\n}\n\n/**\n * Gets the anchors whose url is not linking at the current site url/domain.\n *\n * @param {Array}   anchors         An array with all anchors from the paper.\n * @param {String}  siteUrlOrDomain The site URL or domain of the paper.\n *\n * @returns {Array} The array of all anchors whose url is not linking at the current site url/domain.\n */\nfunction getAnchorsLinkingToSelf( anchors, siteUrlOrDomain ) {\n\tconst anchorsLinkingToSelf = anchors.map( function( anchor ) {\n\t\tconst anchorLink = anchor.attributes.href;\n\t\t// Return false if there is no href attribute.\n\t\treturn anchorLink ? isLinkingToSelf( anchorLink, siteUrlOrDomain ) : false;\n\t} );\n\n\treturn  anchors.filter( ( anchor, index ) => ! anchorsLinkingToSelf[ index ] );\n}\n\n/**\n * Gets the anchors with text that contains all content words of the topic (i.e. keyphrase or synonyms).\n *\n * @param {Array}       anchors         An array with all anchors from the paper\n * @param {Object}      topicForms      The object with topicForms. It contains all forms of the keyphrase and synonyms.\n * @param {String}      locale          The locale of the paper.\n * @param {Function}    matchWordCustomHelper The helper function to match word in text.\n *\n * @returns {String[]} The array of all anchors with text that contains all content words of the keyphrase or synonyms.\n */\nfunction getAnchorsContainingTopic( anchors, topicForms, locale, matchWordCustomHelper ) {\n\tconst anchorsContainingTopic = anchors.map( function( anchor ) {\n\t\t// Only retrieve the anchor's text. This is because we only use the anchor text for the following check.\n\t\tconst anchorText = anchor.innerText();\n\t\treturn findTopicFormsInString( topicForms, anchorText, true, locale, matchWordCustomHelper  ).percentWordMatches === 100;\n\t} );\n\n\treturn anchors.filter( ( anchor, index ) => anchorsContainingTopic[ index ] );\n}\n\n/**\n * Gets the anchors with text that has the same content words as the keyphrase or synonyms.\n *\n * @param {Array}       anchors             \t\tAn array with all anchors from the paper.\n * @param {Object}      topicForms          \t\tThe object with topicForms. It contains all forms of the keyphrase and synonyms.\n * @param {string}      locale              \t\tThe locale of the paper.\n * @param {Object}      customHelpers       \t\tAn object containing custom helpers.\n * @param {Object[]}    exactMatchRequest   \t\tAn array of objects containing the keyphrase and information on whether\n * \t\t\t\t\t\t\t\t\t\t\t\t\tthe exact match has been requested.\n * @param {boolean}\t \tareHyphensWordBoundaries\tWhether hyphens should be treated as word boundaries.\n *\n * @returns {Array} The array of all anchors with text that has the same content words as the keyphrase/synonyms.\n */\nfunction getAnchorsWithSameTextAsTopic( anchors, topicForms, locale, customHelpers, exactMatchRequest, areHyphensWordBoundaries  ) {\n\tconst matchWordCustomHelper = customHelpers.matchWordCustomHelper;\n\tconst getWordsCustomHelper = customHelpers.getWordsCustomHelper;\n\n\t// Prepare keyphrase and synonym forms for comparison with anchors.\n\tconst keyphraseAndSynonymsWords = [ flatten( topicForms.keyphraseForms ) ];\n\tconst synonymsForms = topicForms.synonymsForms;\n\tsynonymsForms.forEach( form => keyphraseAndSynonymsWords.push( flatten( form ) ) );\n\n\t// The variable that will save all the anchors with text that has the same content words as the keyphrase/synonyms.\n\tconst anchorsContainedInTopic = [];\n\n\tanchors.forEach( function( currentAnchor ) {\n\t\tconst currentAnchorText = currentAnchor.innerText();\n\n\t\t/*\n        * For keyphrase matching, we want to split words on hyphens and en-dashes, except for languages where hyphens shouldn't\n        * be treated as word boundaries. Currently, the latter only applies to Indonesian, where hyphens are used to create plural forms of nouns,\n        * such as \"buku-buku\" being a plural form of \"buku\". We want to treat forms like \"buku-buku\" as one word, so we shouldn't\n        * split words on hyphens in Indonesian.\n        * For languages where hyphens are treated as word boundaries we pass a custom word boundary regex string to the getWords helper\n        * that includes whitespaces, hyphens (u002d), and en-dashes (u2013). Otherwise, we pass a word boundary regex that only includes\n        * whitespaces and en-dashes.\n        */\n\t\tlet anchorWords;\n\t\tif ( getWordsCustomHelper ) {\n\t\t\tanchorWords = uniq( getWordsCustomHelper( currentAnchorText ) );\n\t\t} else if ( areHyphensWordBoundaries ) {\n\t\t\tanchorWords = uniq( getWords( currentAnchorText, WORD_BOUNDARY_WITH_HYPHEN ) );\n\t\t} else {\n\t\t\tanchorWords = uniq( getWords( currentAnchorText, WORD_BOUNDARY_WITHOUT_HYPHEN ) );\n\t\t}\n\n\t\t/*\n\t\t * Filter function words out of the anchor text.\n\t\t * If the anchor text contains only function words, we keep them.\n\t\t */\n\t\tconst filteredAnchorWords = filterWordsFromArray( anchorWords, functionWords );\n\t\tif ( filteredAnchorWords.length > 0 ) {\n\t\t\tanchorWords = filteredAnchorWords;\n\t\t}\n\n\t\texactMatchRequest.forEach( request => {\n\t\t\t/*\n\t\t\t * Check a) if the exact match is requested for the keyphrase, and\n\t\t\t * b) if every content word in the anchor text is included in the keyphrase or synonym.\n\t\t\t */\n\t\t\tif ( request.exactMatchRequested &&\n\t\t\t\tanchorWords.every( anchorWord => request.keyphrase.includes( anchorWord ) ) ) {\n\t\t\t\tanchorsContainedInTopic.push( true );\n\t\t\t}\n\t\t} );\n\n\t\t// Check if every word in the anchor text is also present in the keyphrase/synonym.\n\t\tfor ( let i = 0; i < keyphraseAndSynonymsWords.length; i++ ) {\n\t\t\tconst topicForm =  keyphraseAndSynonymsWords[ i ];\n\n\t\t\tif ( anchorWords.every( anchorWord => matchTextWithArray( anchorWord, topicForm, locale, matchWordCustomHelper ).count > 0 ) ) {\n\t\t\t\tanchorsContainedInTopic.push( true );\n\t\t\t\tbreak;\n\t\t\t}\n\t\t}\n\t} );\n\n\treturn anchors.filter( ( anchor, index ) => anchorsContainedInTopic[ index ] );\n}\n\n/**\n * Checks whether the content words of the anchor text are the same as the content words of the keyphrase or synonym.\n * Also includes different word forms if the morphology is available.\n *\n * @param {Paper}       paper       The paper to research.\n * @param {Researcher}  researcher  The researcher to use.\n *\n * @returns {Object} The amount of anchor texts whose content words are the same as the keyphrase or synonyms' content words.\n */\nexport default function( paper, researcher ) {\n\tfunctionWords = researcher.getConfig( \"functionWords\" );\n\n\tconst areHyphensWordBoundaries = researcher.getConfig( \"areHyphensWordBoundaries\" );\n\n\tconst result = {\n\t\tanchorsWithKeyphrase: [],\n\t\tanchorsWithKeyphraseCount: 0,\n\t};\n\t// STEP 1.\n\t// If the paper's text is empty, return empty result.\n\tif ( paper.getText() === \"\" ) {\n\t\treturn result;\n\t}\n\n\t// STEP 2.\n\tconst keyphrase = paper.getKeyword();\n\t/*\n\t * If no keyphrase is set, return empty result.\n\t * This is a conscious decision where we won't assess the paper if the keyphrase is not set.\n\t * This includes a case where only the synonym is set but not the keyphrase.\n\t */\n\tif ( keyphrase === \"\" ) {\n\t\treturn result;\n\t}\n\t/*\n\t * When the keyphrase is set, also retrieve the synonyms and save them in \"topics\" array.\n\t * Eventually, the term topics here refers to either keyphrase or synonyms.\n\t */\n\tconst originalTopics = parseSynonyms( paper.getSynonyms() );\n\toriginalTopics.push( keyphrase );\n\n\t// Retrieve the anchors.\n\tlet anchors = paper.getTree().findAll( treeNode => treeNode.name === \"a\" );\n\t/*\n\t * We get the site's URL (e.g., https://yoast.com) or domain (e.g., yoast.com) from the paper.\n\t * In case of WordPress, the variable is a URL. In case of Shopify, it is a domain.\n\t */\n\tconst siteUrlOrDomain = paper.getPermalink();\n\n\t// STEP 3.\n\t// Get the anchors with urls that are not linking to the current site url/domain.\n\tanchors = getAnchorsLinkingToSelf( anchors, siteUrlOrDomain );\n\t// If all anchor urls are linking to the current site url/domain, return empty result.\n\tif ( anchors.length === 0 ) {\n\t\treturn result;\n\t}\n\n\tconst locale = paper.getLocale();\n\tconst topicForms = researcher.getResearch( \"morphology\" );\n\tconst customHelpers = {\n\t\tmatchWordCustomHelper: researcher.getHelper( \"matchWordCustomHelper\" ),\n\t\tgetWordsCustomHelper: researcher.getHelper( \"getWordsCustomHelper\" ),\n\t};\n\n\t// STEP 4.\n\t// Get the anchors with text that contains the keyphrase/synonyms' content words.\n\tanchors = getAnchorsContainingTopic( anchors, topicForms, locale, customHelpers.matchWordCustomHelper );\n\t// If all anchor texts do not contain the keyphrase/synonyms' content words, return empty result.\n\tif ( anchors.length === 0 ) {\n\t\treturn result;\n\t}\n\n\t// STEP 5.\n\t// Check if exact match is requested for every topic (keyphrase or synonym).\n\tconst isExactMatchRequested = originalTopics.map( originalTopic => processExactMatchRequest( originalTopic ) );\n\t// Get the anchors with text that has the same content words as the keyphrase/synonyms.\n\tanchors = getAnchorsWithSameTextAsTopic( anchors, topicForms, locale, customHelpers, isExactMatchRequested, areHyphensWordBoundaries );\n\n\treturn {\n\t\tanchorsWithKeyphrase: anchors,\n\t\tanchorsWithKeyphraseCount: anchors.length,\n\t};\n}\n\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AACA,IAAAC,qBAAA,GAAAC,sBAAA,CAAAF,OAAA;AACA,IAAAG,yBAAA,GAAAH,OAAA;AACA,IAAAI,SAAA,GAAAF,sBAAA,CAAAF,OAAA;AACA,IAAAK,mBAAA,GAAAH,sBAAA,CAAAF,OAAA;AACA,IAAAM,cAAA,GAAAJ,sBAAA,CAAAF,OAAA;AACA,IAAAO,yBAAA,GAAAL,sBAAA,CAAAF,OAAA;AACA,IAAAQ,IAAA,GAAAN,sBAAA,CAAAF,OAAA;AACA,IAAAS,iCAAA,GAAAT,OAAA;AAAwH,SAAAE,uBAAAQ,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAExH,IAAIG,aAAa,GAAG,EAAE;;AAEtB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,eAAeA,CAAEC,UAAU,EAAEC,eAAe,EAAG;EACvD,OAAOC,OAAO,CAAEC,YAAS,CAACC,QAAQ,CAAEJ,UAAU,EAAEC,eAAgB,CAAC,IAAIE,YAAS,CAACE,qBAAqB,CAAEL,UAAW,CAAE,CAAC;AACrH;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASM,uBAAuBA,CAAEC,OAAO,EAAEN,eAAe,EAAG;EAC5D,MAAMO,oBAAoB,GAAGD,OAAO,CAACE,GAAG,CAAE,UAAUC,MAAM,EAAG;IAC5D,MAAMV,UAAU,GAAGU,MAAM,CAACC,UAAU,CAACC,IAAI;IACzC;IACA,OAAOZ,UAAU,GAAGD,eAAe,CAAEC,UAAU,EAAEC,eAAgB,CAAC,GAAG,KAAK;EAC3E,CAAE,CAAC;EAEH,OAAQM,OAAO,CAACM,MAAM,CAAE,CAAEH,MAAM,EAAEI,KAAK,KAAM,CAAEN,oBAAoB,CAAEM,KAAK,CAAG,CAAC;AAC/E;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,yBAAyBA,CAAER,OAAO,EAAES,UAAU,EAAEC,MAAM,EAAEC,qBAAqB,EAAG;EACxF,MAAMC,sBAAsB,GAAGZ,OAAO,CAACE,GAAG,CAAE,UAAUC,MAAM,EAAG;IAC9D;IACA,MAAMU,UAAU,GAAGV,MAAM,CAACW,SAAS,CAAC,CAAC;IACrC,OAAO,IAAAC,gDAAsB,EAAEN,UAAU,EAAEI,UAAU,EAAE,IAAI,EAAEH,MAAM,EAAEC,qBAAuB,CAAC,CAACK,kBAAkB,KAAK,GAAG;EACzH,CAAE,CAAC;EAEH,OAAOhB,OAAO,CAACM,MAAM,CAAE,CAAEH,MAAM,EAAEI,KAAK,KAAMK,sBAAsB,CAAEL,KAAK,CAAG,CAAC;AAC9E;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASU,6BAA6BA,CAAEjB,OAAO,EAAES,UAAU,EAAEC,MAAM,EAAEQ,aAAa,EAAEC,iBAAiB,EAAEC,wBAAwB,EAAI;EAClI,MAAMT,qBAAqB,GAAGO,aAAa,CAACP,qBAAqB;EACjE,MAAMU,oBAAoB,GAAGH,aAAa,CAACG,oBAAoB;;EAE/D;EACA,MAAMC,yBAAyB,GAAG,CAAE,IAAAC,eAAO,EAAEd,UAAU,CAACe,cAAe,CAAC,CAAE;EAC1E,MAAMC,aAAa,GAAGhB,UAAU,CAACgB,aAAa;EAC9CA,aAAa,CAACC,OAAO,CAAEC,IAAI,IAAIL,yBAAyB,CAACM,IAAI,CAAE,IAAAL,eAAO,EAAEI,IAAK,CAAE,CAAE,CAAC;;EAElF;EACA,MAAME,uBAAuB,GAAG,EAAE;EAElC7B,OAAO,CAAC0B,OAAO,CAAE,UAAUI,aAAa,EAAG;IAC1C,MAAMC,iBAAiB,GAAGD,aAAa,CAAChB,SAAS,CAAC,CAAC;;IAEnD;AACF;AACA;AACA;AACA;AACA;AACA;AACA;AACA;IACE,IAAIkB,WAAW;IACf,IAAKX,oBAAoB,EAAG;MAC3BW,WAAW,GAAG,IAAAC,YAAI,EAAEZ,oBAAoB,CAAEU,iBAAkB,CAAE,CAAC;IAChE,CAAC,MAAM,IAAKX,wBAAwB,EAAG;MACtCY,WAAW,GAAG,IAAAC,YAAI,EAAE,IAAAC,iBAAQ,EAAEH,iBAAiB,EAAEI,2DAA0B,CAAE,CAAC;IAC/E,CAAC,MAAM;MACNH,WAAW,GAAG,IAAAC,YAAI,EAAE,IAAAC,iBAAQ,EAAEH,iBAAiB,EAAEK,8DAA6B,CAAE,CAAC;IAClF;;IAEA;AACF;AACA;AACA;IACE,MAAMC,mBAAmB,GAAG,IAAAC,6BAAoB,EAAEN,WAAW,EAAEzC,aAAc,CAAC;IAC9E,IAAK8C,mBAAmB,CAACE,MAAM,GAAG,CAAC,EAAG;MACrCP,WAAW,GAAGK,mBAAmB;IAClC;IAEAlB,iBAAiB,CAACO,OAAO,CAAEc,OAAO,IAAI;MACrC;AACH;AACA;AACA;MACG,IAAKA,OAAO,CAACC,mBAAmB,IAC/BT,WAAW,CAACU,KAAK,CAAEC,UAAU,IAAIH,OAAO,CAACI,SAAS,CAACC,QAAQ,CAAEF,UAAW,CAAE,CAAC,EAAG;QAC9Ed,uBAAuB,CAACD,IAAI,CAAE,IAAK,CAAC;MACrC;IACD,CAAE,CAAC;;IAEH;IACA,KAAM,IAAIkB,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGxB,yBAAyB,CAACiB,MAAM,EAAEO,CAAC,EAAE,EAAG;MAC5D,MAAMC,SAAS,GAAIzB,yBAAyB,CAAEwB,CAAC,CAAE;MAEjD,IAAKd,WAAW,CAACU,KAAK,CAAEC,UAAU,IAAI,IAAAK,2BAAkB,EAAEL,UAAU,EAAEI,SAAS,EAAErC,MAAM,EAAEC,qBAAsB,CAAC,CAACsC,KAAK,GAAG,CAAE,CAAC,EAAG;QAC9HpB,uBAAuB,CAACD,IAAI,CAAE,IAAK,CAAC;QACpC;MACD;IACD;EACD,CAAE,CAAC;EAEH,OAAO5B,OAAO,CAACM,MAAM,CAAE,CAAEH,MAAM,EAAEI,KAAK,KAAMsB,uBAAuB,CAAEtB,KAAK,CAAG,CAAC;AAC/E;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAA2C,SAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C7D,aAAa,GAAG6D,UAAU,CAACC,SAAS,CAAE,eAAgB,CAAC;EAEvD,MAAMjC,wBAAwB,GAAGgC,UAAU,CAACC,SAAS,CAAE,0BAA2B,CAAC;EAEnF,MAAMC,MAAM,GAAG;IACdC,oBAAoB,EAAE,EAAE;IACxBC,yBAAyB,EAAE;EAC5B,CAAC;EACD;EACA;EACA,IAAKL,KAAK,CAACM,OAAO,CAAC,CAAC,KAAK,EAAE,EAAG;IAC7B,OAAOH,MAAM;EACd;;EAEA;EACA,MAAMV,SAAS,GAAGO,KAAK,CAACO,UAAU,CAAC,CAAC;EACpC;AACD;AACA;AACA;AACA;EACC,IAAKd,SAAS,KAAK,EAAE,EAAG;IACvB,OAAOU,MAAM;EACd;EACA;AACD;AACA;AACA;EACC,MAAMK,cAAc,GAAG,IAAAC,sBAAa,EAAET,KAAK,CAACU,WAAW,CAAC,CAAE,CAAC;EAC3DF,cAAc,CAAC/B,IAAI,CAAEgB,SAAU,CAAC;;EAEhC;EACA,IAAI5C,OAAO,GAAGmD,KAAK,CAACW,OAAO,CAAC,CAAC,CAACC,OAAO,CAAEC,QAAQ,IAAIA,QAAQ,CAACC,IAAI,KAAK,GAAI,CAAC;EAC1E;AACD;AACA;AACA;EACC,MAAMvE,eAAe,GAAGyD,KAAK,CAACe,YAAY,CAAC,CAAC;;EAE5C;EACA;EACAlE,OAAO,GAAGD,uBAAuB,CAAEC,OAAO,EAAEN,eAAgB,CAAC;EAC7D;EACA,IAAKM,OAAO,CAACuC,MAAM,KAAK,CAAC,EAAG;IAC3B,OAAOe,MAAM;EACd;EAEA,MAAM5C,MAAM,GAAGyC,KAAK,CAACgB,SAAS,CAAC,CAAC;EAChC,MAAM1D,UAAU,GAAG2C,UAAU,CAACgB,WAAW,CAAE,YAAa,CAAC;EACzD,MAAMlD,aAAa,GAAG;IACrBP,qBAAqB,EAAEyC,UAAU,CAACiB,SAAS,CAAE,uBAAwB,CAAC;IACtEhD,oBAAoB,EAAE+B,UAAU,CAACiB,SAAS,CAAE,sBAAuB;EACpE,CAAC;;EAED;EACA;EACArE,OAAO,GAAGQ,yBAAyB,CAAER,OAAO,EAAES,UAAU,EAAEC,MAAM,EAAEQ,aAAa,CAACP,qBAAsB,CAAC;EACvG;EACA,IAAKX,OAAO,CAACuC,MAAM,KAAK,CAAC,EAAG;IAC3B,OAAOe,MAAM;EACd;;EAEA;EACA;EACA,MAAMgB,qBAAqB,GAAGX,cAAc,CAACzD,GAAG,CAAEqE,aAAa,IAAI,IAAAC,iCAAwB,EAAED,aAAc,CAAE,CAAC;EAC9G;EACAvE,OAAO,GAAGiB,6BAA6B,CAAEjB,OAAO,EAAES,UAAU,EAAEC,MAAM,EAAEQ,aAAa,EAAEoD,qBAAqB,EAAElD,wBAAyB,CAAC;EAEtI,OAAO;IACNmC,oBAAoB,EAAEvD,OAAO;IAC7BwD,yBAAyB,EAAExD,OAAO,CAACuC;EACpC,CAAC;AACF","ignoreList":[]}
+{"version":3,"file":"getAnchorsWithKeyphrase.js","names":["flatten","uniq","filterWordsFromArray","findTopicFormsInString","getWords","matchTextWithArray","parseSynonyms","processExactMatchRequest","urlHelper","WORD_BOUNDARY_WITH_HYPHEN","WORD_BOUNDARY_WITHOUT_HYPHEN","functionWords","isLinkingToSelf","anchorLink","siteUrlOrDomain","Boolean","areEqual","isRelativeFragmentURL","getAnchorsLinkingToSelf","anchors","anchorsLinkingToSelf","map","anchor","attributes","href","filter","index","getAnchorsContainingTopic","topicForms","locale","matchWordCustomHelper","anchorsContainingTopic","anchorText","innerText","percentWordMatches","getAnchorsWithSameTextAsTopic","customHelpers","exactMatchRequest","areHyphensWordBoundaries","getWordsCustomHelper","keyphraseAndSynonymsWords","keyphraseForms","synonymsForms","forEach","form","push","anchorsContainedInTopic","currentAnchor","currentAnchorText","anchorWords","filteredAnchorWords","length","request","exactMatchRequested","every","anchorWord","keyphrase","includes","i","topicForm","count","paper","researcher","getConfig","result","anchorsWithKeyphrase","anchorsWithKeyphraseCount","getText","getKeyword","originalTopics","getSynonyms","getTree","findAll","treeNode","name","getPermalink","getLocale","getResearch","getHelper","isExactMatchRequested","originalTopic"],"sources":["../../../src/languageProcessing/researches/getAnchorsWithKeyphrase.js"],"sourcesContent":["import { flatten, uniq } from \"lodash\";\nimport filterWordsFromArray from \"../helpers/word/filterWordsFromArray\";\nimport { findTopicFormsInString } from \"../helpers/match/findKeywordFormsInString\";\nimport getWords from \"../helpers/word/getWords\";\nimport matchTextWithArray from \"../helpers/match/matchTextWithArray\";\nimport parseSynonyms from \"../helpers/sanitize/parseSynonyms\";\nimport processExactMatchRequest from \"../helpers/match/processExactMatchRequest\";\nimport urlHelper from \"../helpers/url/url.js\";\nimport { WORD_BOUNDARY_WITH_HYPHEN, WORD_BOUNDARY_WITHOUT_HYPHEN } from \"../../config/wordBoundariesWithoutPunctuation\";\n\nlet functionWords = [];\n\n/**\n * Checks whether the anchor's link is a relative fragment or the same as the site url/domain.\n * Relative fragment links always point to the page itself.\n *\n * @param {String} anchorLink       The link anchor.\n * @param {String} siteUrlOrDomain  The site URL or domain of the paper.\n *\n * @returns {boolean} Whether the anchor's link is a relative fragment or the same as the site url/domain.\n */\nfunction isLinkingToSelf( anchorLink, siteUrlOrDomain ) {\n\treturn Boolean( urlHelper.areEqual( anchorLink, siteUrlOrDomain ) || urlHelper.isRelativeFragmentURL( anchorLink ) );\n}\n\n/**\n * Gets the anchors whose url is not linking at the current site url/domain.\n *\n * @param {Array}   anchors         An array with all anchors from the paper.\n * @param {String}  siteUrlOrDomain The site URL or domain of the paper.\n *\n * @returns {Array} The array of all anchors whose url is not linking at the current site url/domain.\n */\nfunction getAnchorsLinkingToSelf( anchors, siteUrlOrDomain ) {\n\tconst anchorsLinkingToSelf = anchors.map( function( anchor ) {\n\t\tconst anchorLink = anchor.attributes.href;\n\t\t// Return false if there is no href attribute.\n\t\treturn anchorLink ? isLinkingToSelf( anchorLink, siteUrlOrDomain ) : false;\n\t} );\n\n\treturn  anchors.filter( ( anchor, index ) => ! anchorsLinkingToSelf[ index ] );\n}\n\n/**\n * Gets the anchors with text that contains all content words of the topic (i.e. keyphrase or synonyms).\n *\n * @param {Array}       anchors         An array with all anchors from the paper\n * @param {Object}      topicForms      The object with topicForms. It contains all forms of the keyphrase and synonyms.\n * @param {String}      locale          The locale of the paper.\n * @param {Function}    matchWordCustomHelper The helper function to match word in text.\n *\n * @returns {String[]} The array of all anchors with text that contains all content words of the keyphrase or synonyms.\n */\nfunction getAnchorsContainingTopic( anchors, topicForms, locale, matchWordCustomHelper ) {\n\tconst anchorsContainingTopic = anchors.map( function( anchor ) {\n\t\t// Only retrieve the anchor's text. This is because we only use the anchor text for the following check.\n\t\tconst anchorText = anchor.innerText();\n\t\treturn findTopicFormsInString( topicForms, anchorText, true, locale, matchWordCustomHelper  ).percentWordMatches === 100;\n\t} );\n\n\treturn anchors.filter( ( anchor, index ) => anchorsContainingTopic[ index ] );\n}\n\n/**\n * Gets the anchors with text that has the same content words as the keyphrase or synonyms.\n *\n * @param {Array}       anchors             \t\tAn array with all anchors from the paper.\n * @param {Object}      topicForms          \t\tThe object with topicForms. It contains all forms of the keyphrase and synonyms.\n * @param {string}      locale              \t\tThe locale of the paper.\n * @param {Object}      customHelpers       \t\tAn object containing custom helpers.\n * @param {Object[]}    exactMatchRequest   \t\tAn array of objects containing the keyphrase and information on whether\n * \t\t\t\t\t\t\t\t\t\t\t\t\tthe exact match has been requested.\n * @param {boolean}\t \tareHyphensWordBoundaries\tWhether hyphens should be treated as word boundaries.\n *\n * @returns {Array} The array of all anchors with text that has the same content words as the keyphrase/synonyms.\n */\nfunction getAnchorsWithSameTextAsTopic( anchors, topicForms, locale, customHelpers, exactMatchRequest, areHyphensWordBoundaries  ) {\n\tconst matchWordCustomHelper = customHelpers.matchWordCustomHelper;\n\tconst getWordsCustomHelper = customHelpers.getWordsCustomHelper;\n\n\t// Prepare keyphrase and synonym forms for comparison with anchors.\n\tconst keyphraseAndSynonymsWords = [ flatten( topicForms.keyphraseForms ) ];\n\tconst synonymsForms = topicForms.synonymsForms;\n\tsynonymsForms.forEach( form => keyphraseAndSynonymsWords.push( flatten( form ) ) );\n\n\t// The variable that will save all the anchors with text that has the same content words as the keyphrase/synonyms.\n\tconst anchorsContainedInTopic = [];\n\n\tanchors.forEach( function( currentAnchor ) {\n\t\tconst currentAnchorText = currentAnchor.innerText();\n\n\t\t/*\n        * For keyphrase matching, we want to split words on hyphens and en-dashes, except for languages where hyphens shouldn't\n        * be treated as word boundaries. Currently, the latter only applies to Indonesian, where hyphens are used to create plural forms of nouns,\n        * such as \"buku-buku\" being a plural form of \"buku\". We want to treat forms like \"buku-buku\" as one word, so we shouldn't\n        * split words on hyphens in Indonesian.\n        * For languages where hyphens are treated as word boundaries we pass a custom word boundary regex string to the getWords helper\n        * that includes whitespaces, hyphens (u002d), and en-dashes (u2013). Otherwise, we pass a word boundary regex that only includes\n        * whitespaces and en-dashes.\n        */\n\t\tlet anchorWords;\n\t\tif ( getWordsCustomHelper ) {\n\t\t\tanchorWords = uniq( getWordsCustomHelper( currentAnchorText ) );\n\t\t} else if ( areHyphensWordBoundaries ) {\n\t\t\tanchorWords = uniq( getWords( currentAnchorText, WORD_BOUNDARY_WITH_HYPHEN ) );\n\t\t} else {\n\t\t\tanchorWords = uniq( getWords( currentAnchorText, WORD_BOUNDARY_WITHOUT_HYPHEN ) );\n\t\t}\n\n\t\t/*\n\t\t * Filter function words out of the anchor text.\n\t\t * If the anchor text contains only function words, we keep them.\n\t\t */\n\t\tconst filteredAnchorWords = filterWordsFromArray( anchorWords, functionWords );\n\t\tif ( filteredAnchorWords.length > 0 ) {\n\t\t\tanchorWords = filteredAnchorWords;\n\t\t}\n\n\t\texactMatchRequest.forEach( request => {\n\t\t\t/*\n\t\t\t * Check a) if the exact match is requested for the keyphrase, and\n\t\t\t * b) if every content word in the anchor text is included in the keyphrase or synonym.\n\t\t\t */\n\t\t\tif ( request.exactMatchRequested &&\n\t\t\t\tanchorWords.every( anchorWord => request.keyphrase.includes( anchorWord ) ) ) {\n\t\t\t\tanchorsContainedInTopic.push( true );\n\t\t\t}\n\t\t} );\n\n\t\t// Check if every word in the anchor text is also present in the keyphrase/synonym.\n\t\tfor ( let i = 0; i < keyphraseAndSynonymsWords.length; i++ ) {\n\t\t\tconst topicForm =  keyphraseAndSynonymsWords[ i ];\n\n\t\t\tif ( anchorWords.every( anchorWord => matchTextWithArray( anchorWord, topicForm, locale, matchWordCustomHelper ).count > 0 ) ) {\n\t\t\t\tanchorsContainedInTopic.push( true );\n\t\t\t\tbreak;\n\t\t\t}\n\t\t}\n\t} );\n\n\treturn anchors.filter( ( anchor, index ) => anchorsContainedInTopic[ index ] );\n}\n\n/**\n * Checks whether the content words of the anchor text are the same as the content words of the keyphrase or synonym.\n * Also includes different word forms if the morphology is available.\n *\n * @param {Paper}       paper       The paper to research.\n * @param {Researcher}  researcher  The researcher to use.\n *\n * @returns {Object} The amount of anchor texts whose content words are the same as the keyphrase or synonyms' content words.\n */\nexport default function( paper, researcher ) {\n\tfunctionWords = researcher.getConfig( \"functionWords\" );\n\n\tconst areHyphensWordBoundaries = researcher.getConfig( \"areHyphensWordBoundaries\" );\n\n\tconst result = {\n\t\tanchorsWithKeyphrase: [],\n\t\tanchorsWithKeyphraseCount: 0,\n\t};\n\t// STEP 1.\n\t// If the paper's text is empty, return empty result.\n\tif ( paper.getText() === \"\" ) {\n\t\treturn result;\n\t}\n\n\t// STEP 2.\n\tconst keyphrase = paper.getKeyword();\n\t/*\n\t * If no keyphrase is set, return empty result.\n\t * This is a conscious decision where we won't assess the paper if the keyphrase is not set.\n\t * This includes a case where only the synonym is set but not the keyphrase.\n\t */\n\tif ( keyphrase === \"\" ) {\n\t\treturn result;\n\t}\n\t/*\n\t * When the keyphrase is set, also retrieve the synonyms and save them in \"topics\" array.\n\t * Eventually, the term topics here refers to either keyphrase or synonyms.\n\t */\n\tconst originalTopics = parseSynonyms( paper.getSynonyms() );\n\toriginalTopics.push( keyphrase );\n\n\t// Retrieve the anchors.\n\tlet anchors = paper.getTree().findAll( treeNode => treeNode.name === \"a\" );\n\t/*\n\t * We get the site's URL (e.g., https://yoast.com) or domain (e.g., yoast.com) from the paper.\n\t * In case of WordPress, the variable is a URL. In case of Shopify, it is a domain.\n\t */\n\tconst siteUrlOrDomain = paper.getPermalink();\n\n\t// STEP 3.\n\t// Get the anchors with urls that are not linking to the current site url/domain.\n\tanchors = getAnchorsLinkingToSelf( anchors, siteUrlOrDomain );\n\t// If all anchor urls are linking to the current site url/domain, return empty result.\n\tif ( anchors.length === 0 ) {\n\t\treturn result;\n\t}\n\n\tconst locale = paper.getLocale();\n\tconst topicForms = researcher.getResearch( \"morphology\" );\n\tconst customHelpers = {\n\t\tmatchWordCustomHelper: researcher.getHelper( \"matchWordCustomHelper\" ),\n\t\tgetWordsCustomHelper: researcher.getHelper( \"getWordsCustomHelper\" ),\n\t};\n\n\t// STEP 4.\n\t// Get the anchors with text that contains the keyphrase/synonyms' content words.\n\tanchors = getAnchorsContainingTopic( anchors, topicForms, locale, customHelpers.matchWordCustomHelper );\n\t// If all anchor texts do not contain the keyphrase/synonyms' content words, return empty result.\n\tif ( anchors.length === 0 ) {\n\t\treturn result;\n\t}\n\n\t// STEP 5.\n\t// Check if exact match is requested for every topic (keyphrase or synonym).\n\tconst isExactMatchRequested = originalTopics.map( originalTopic => processExactMatchRequest( originalTopic ) );\n\t// Get the anchors with text that has the same content words as the keyphrase/synonyms.\n\tanchors = getAnchorsWithSameTextAsTopic( anchors, topicForms, locale, customHelpers, isExactMatchRequested, areHyphensWordBoundaries );\n\n\treturn {\n\t\tanchorsWithKeyphrase: anchors,\n\t\tanchorsWithKeyphraseCount: anchors.length,\n\t};\n}\n\n"],"mappings":"AAAA,SAASA,OAAO,EAAEC,IAAI,QAAQ,QAAQ;AACtC,OAAOC,oBAAoB;AAC3B,SAASC,sBAAsB;AAC/B,OAAOC,QAAQ;AACf,OAAOC,kBAAkB;AACzB,OAAOC,aAAa;AACpB,OAAOC,wBAAwB;AAC/B,OAAOC,SAAS;AAChB,SAASC,yBAAyB,EAAEC,4BAA4B;AAEhE,IAAIC,aAAa,GAAG,EAAE;;AAEtB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,eAAeA,CAAEC,UAAU,EAAEC,eAAe,EAAG;EACvD,OAAOC,OAAO,CAAEP,SAAS,CAACQ,QAAQ,CAAEH,UAAU,EAAEC,eAAgB,CAAC,IAAIN,SAAS,CAACS,qBAAqB,CAAEJ,UAAW,CAAE,CAAC;AACrH;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASK,uBAAuBA,CAAEC,OAAO,EAAEL,eAAe,EAAG;EAC5D,MAAMM,oBAAoB,GAAGD,OAAO,CAACE,GAAG,CAAE,UAAUC,MAAM,EAAG;IAC5D,MAAMT,UAAU,GAAGS,MAAM,CAACC,UAAU,CAACC,IAAI;IACzC;IACA,OAAOX,UAAU,GAAGD,eAAe,CAAEC,UAAU,EAAEC,eAAgB,CAAC,GAAG,KAAK;EAC3E,CAAE,CAAC;EAEH,OAAQK,OAAO,CAACM,MAAM,CAAE,CAAEH,MAAM,EAAEI,KAAK,KAAM,CAAEN,oBAAoB,CAAEM,KAAK,CAAG,CAAC;AAC/E;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,yBAAyBA,CAAER,OAAO,EAAES,UAAU,EAAEC,MAAM,EAAEC,qBAAqB,EAAG;EACxF,MAAMC,sBAAsB,GAAGZ,OAAO,CAACE,GAAG,CAAE,UAAUC,MAAM,EAAG;IAC9D;IACA,MAAMU,UAAU,GAAGV,MAAM,CAACW,SAAS,CAAC,CAAC;IACrC,OAAO9B,sBAAsB,CAAEyB,UAAU,EAAEI,UAAU,EAAE,IAAI,EAAEH,MAAM,EAAEC,qBAAuB,CAAC,CAACI,kBAAkB,KAAK,GAAG;EACzH,CAAE,CAAC;EAEH,OAAOf,OAAO,CAACM,MAAM,CAAE,CAAEH,MAAM,EAAEI,KAAK,KAAMK,sBAAsB,CAAEL,KAAK,CAAG,CAAC;AAC9E;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASS,6BAA6BA,CAAEhB,OAAO,EAAES,UAAU,EAAEC,MAAM,EAAEO,aAAa,EAAEC,iBAAiB,EAAEC,wBAAwB,EAAI;EAClI,MAAMR,qBAAqB,GAAGM,aAAa,CAACN,qBAAqB;EACjE,MAAMS,oBAAoB,GAAGH,aAAa,CAACG,oBAAoB;;EAE/D;EACA,MAAMC,yBAAyB,GAAG,CAAExC,OAAO,CAAE4B,UAAU,CAACa,cAAe,CAAC,CAAE;EAC1E,MAAMC,aAAa,GAAGd,UAAU,CAACc,aAAa;EAC9CA,aAAa,CAACC,OAAO,CAAEC,IAAI,IAAIJ,yBAAyB,CAACK,IAAI,CAAE7C,OAAO,CAAE4C,IAAK,CAAE,CAAE,CAAC;;EAElF;EACA,MAAME,uBAAuB,GAAG,EAAE;EAElC3B,OAAO,CAACwB,OAAO,CAAE,UAAUI,aAAa,EAAG;IAC1C,MAAMC,iBAAiB,GAAGD,aAAa,CAACd,SAAS,CAAC,CAAC;;IAEnD;AACF;AACA;AACA;AACA;AACA;AACA;AACA;AACA;IACE,IAAIgB,WAAW;IACf,IAAKV,oBAAoB,EAAG;MAC3BU,WAAW,GAAGhD,IAAI,CAAEsC,oBAAoB,CAAES,iBAAkB,CAAE,CAAC;IAChE,CAAC,MAAM,IAAKV,wBAAwB,EAAG;MACtCW,WAAW,GAAGhD,IAAI,CAAEG,QAAQ,CAAE4C,iBAAiB,EAAEvC,yBAA0B,CAAE,CAAC;IAC/E,CAAC,MAAM;MACNwC,WAAW,GAAGhD,IAAI,CAAEG,QAAQ,CAAE4C,iBAAiB,EAAEtC,4BAA6B,CAAE,CAAC;IAClF;;IAEA;AACF;AACA;AACA;IACE,MAAMwC,mBAAmB,GAAGhD,oBAAoB,CAAE+C,WAAW,EAAEtC,aAAc,CAAC;IAC9E,IAAKuC,mBAAmB,CAACC,MAAM,GAAG,CAAC,EAAG;MACrCF,WAAW,GAAGC,mBAAmB;IAClC;IAEAb,iBAAiB,CAACM,OAAO,CAAES,OAAO,IAAI;MACrC;AACH;AACA;AACA;MACG,IAAKA,OAAO,CAACC,mBAAmB,IAC/BJ,WAAW,CAACK,KAAK,CAAEC,UAAU,IAAIH,OAAO,CAACI,SAAS,CAACC,QAAQ,CAAEF,UAAW,CAAE,CAAC,EAAG;QAC9ET,uBAAuB,CAACD,IAAI,CAAE,IAAK,CAAC;MACrC;IACD,CAAE,CAAC;;IAEH;IACA,KAAM,IAAIa,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGlB,yBAAyB,CAACW,MAAM,EAAEO,CAAC,EAAE,EAAG;MAC5D,MAAMC,SAAS,GAAInB,yBAAyB,CAAEkB,CAAC,CAAE;MAEjD,IAAKT,WAAW,CAACK,KAAK,CAAEC,UAAU,IAAIlD,kBAAkB,CAAEkD,UAAU,EAAEI,SAAS,EAAE9B,MAAM,EAAEC,qBAAsB,CAAC,CAAC8B,KAAK,GAAG,CAAE,CAAC,EAAG;QAC9Hd,uBAAuB,CAACD,IAAI,CAAE,IAAK,CAAC;QACpC;MACD;IACD;EACD,CAAE,CAAC;EAEH,OAAO1B,OAAO,CAACM,MAAM,CAAE,CAAEH,MAAM,EAAEI,KAAK,KAAMoB,uBAAuB,CAAEpB,KAAK,CAAG,CAAC;AAC/E;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUmC,KAAK,EAAEC,UAAU,EAAG;EAC5CnD,aAAa,GAAGmD,UAAU,CAACC,SAAS,CAAE,eAAgB,CAAC;EAEvD,MAAMzB,wBAAwB,GAAGwB,UAAU,CAACC,SAAS,CAAE,0BAA2B,CAAC;EAEnF,MAAMC,MAAM,GAAG;IACdC,oBAAoB,EAAE,EAAE;IACxBC,yBAAyB,EAAE;EAC5B,CAAC;EACD;EACA;EACA,IAAKL,KAAK,CAACM,OAAO,CAAC,CAAC,KAAK,EAAE,EAAG;IAC7B,OAAOH,MAAM;EACd;;EAEA;EACA,MAAMR,SAAS,GAAGK,KAAK,CAACO,UAAU,CAAC,CAAC;EACpC;AACD;AACA;AACA;AACA;EACC,IAAKZ,SAAS,KAAK,EAAE,EAAG;IACvB,OAAOQ,MAAM;EACd;EACA;AACD;AACA;AACA;EACC,MAAMK,cAAc,GAAG/D,aAAa,CAAEuD,KAAK,CAACS,WAAW,CAAC,CAAE,CAAC;EAC3DD,cAAc,CAACxB,IAAI,CAAEW,SAAU,CAAC;;EAEhC;EACA,IAAIrC,OAAO,GAAG0C,KAAK,CAACU,OAAO,CAAC,CAAC,CAACC,OAAO,CAAEC,QAAQ,IAAIA,QAAQ,CAACC,IAAI,KAAK,GAAI,CAAC;EAC1E;AACD;AACA;AACA;EACC,MAAM5D,eAAe,GAAG+C,KAAK,CAACc,YAAY,CAAC,CAAC;;EAE5C;EACA;EACAxD,OAAO,GAAGD,uBAAuB,CAAEC,OAAO,EAAEL,eAAgB,CAAC;EAC7D;EACA,IAAKK,OAAO,CAACgC,MAAM,KAAK,CAAC,EAAG;IAC3B,OAAOa,MAAM;EACd;EAEA,MAAMnC,MAAM,GAAGgC,KAAK,CAACe,SAAS,CAAC,CAAC;EAChC,MAAMhD,UAAU,GAAGkC,UAAU,CAACe,WAAW,CAAE,YAAa,CAAC;EACzD,MAAMzC,aAAa,GAAG;IACrBN,qBAAqB,EAAEgC,UAAU,CAACgB,SAAS,CAAE,uBAAwB,CAAC;IACtEvC,oBAAoB,EAAEuB,UAAU,CAACgB,SAAS,CAAE,sBAAuB;EACpE,CAAC;;EAED;EACA;EACA3D,OAAO,GAAGQ,yBAAyB,CAAER,OAAO,EAAES,UAAU,EAAEC,MAAM,EAAEO,aAAa,CAACN,qBAAsB,CAAC;EACvG;EACA,IAAKX,OAAO,CAACgC,MAAM,KAAK,CAAC,EAAG;IAC3B,OAAOa,MAAM;EACd;;EAEA;EACA;EACA,MAAMe,qBAAqB,GAAGV,cAAc,CAAChD,GAAG,CAAE2D,aAAa,IAAIzE,wBAAwB,CAAEyE,aAAc,CAAE,CAAC;EAC9G;EACA7D,OAAO,GAAGgB,6BAA6B,CAAEhB,OAAO,EAAES,UAAU,EAAEC,MAAM,EAAEO,aAAa,EAAE2C,qBAAqB,EAAEzC,wBAAyB,CAAC;EAEtI,OAAO;IACN2B,oBAAoB,EAAE9C,OAAO;IAC7B+C,yBAAyB,EAAE/C,OAAO,CAACgC;EACpC,CAAC;AACF","ignoreList":[]}

package/build/languageProcessing/researches/getFleschReadingScore.js

@@ -1,18 +1,11 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.DIFFICULTY = void 0;
-exports.default = _default;
-var _stripNumbers = _interopRequireDefault(require("../helpers/sanitize/stripNumbers.js"));
-var _countSentences = _interopRequireDefault(require("../helpers/sentence/countSentences.js"));
-var _countWords = _interopRequireDefault(require("../helpers/word/countWords.js"));
-var _countSyllables = _interopRequireDefault(require("../helpers/syllables/countSyllables.js"));
-var _lodash = require("lodash");
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /** @module analyses/calculateFleschReading */
 
+import stripNumbers from "../helpers/sanitize/stripNumbers.js";
+import countSentences from "../helpers/sentence/countSentences.js";
+import countWords from "../helpers/word/countWords.js";
+import countSyllables from "../helpers/syllables/countSyllables.js";
+import { clamp, inRange } from "lodash";
+
 /**
  * Calculates an average from a total and an amount
  *
@@ -29,7 +22,7 @@ const getAverage = function (total, amount) {
  * @readonly
  * @enum {number}
  */
-const DIFFICULTY = exports.DIFFICULTY = {
+export const DIFFICULTY = {
   NO_DATA: -1,
   VERY_EASY: 0,
   EASY: 1,
@@ -52,15 +45,15 @@ const DIFFICULTY = exports.DIFFICULTY = {
 function getDifficulty(score, scoreConfiguration) {
   if (score >= scoreConfiguration.borders.veryEasy) {
     return DIFFICULTY.VERY_EASY;
-  } else if ((0, _lodash.inRange)(score, scoreConfiguration.borders.easy, scoreConfiguration.borders.veryEasy)) {
+  } else if (inRange(score, scoreConfiguration.borders.easy, scoreConfiguration.borders.veryEasy)) {
     return DIFFICULTY.EASY;
-  } else if ((0, _lodash.inRange)(score, scoreConfiguration.borders.fairlyEasy, scoreConfiguration.borders.easy)) {
+  } else if (inRange(score, scoreConfiguration.borders.fairlyEasy, scoreConfiguration.borders.easy)) {
     return DIFFICULTY.FAIRLY_EASY;
-  } else if ((0, _lodash.inRange)(score, scoreConfiguration.borders.okay, scoreConfiguration.borders.fairlyEasy)) {
+  } else if (inRange(score, scoreConfiguration.borders.okay, scoreConfiguration.borders.fairlyEasy)) {
     return DIFFICULTY.OKAY;
-  } else if ((0, _lodash.inRange)(score, scoreConfiguration.borders.fairlyDifficult, scoreConfiguration.borders.okay)) {
+  } else if (inRange(score, scoreConfiguration.borders.fairlyDifficult, scoreConfiguration.borders.okay)) {
     return DIFFICULTY.FAIRLY_DIFFICULT;
-  } else if ((0, _lodash.inRange)(score, scoreConfiguration.borders.difficult, scoreConfiguration.borders.fairlyDifficult)) {
+  } else if (inRange(score, scoreConfiguration.borders.difficult, scoreConfiguration.borders.fairlyDifficult)) {
     return DIFFICULTY.DIFFICULT;
   }
   return DIFFICULTY.VERY_DIFFICULT;
@@ -107,7 +100,7 @@ function getConfiguration(researcher) {
  *
  * @returns {{ score: number, difficulty: DIFFICULTY }} The Flesch reading score.
  */
-function _default(paper, researcher) {
+export default function (paper, researcher) {
   const syllables = researcher.getConfig("syllables");
   const memoizedTokenizer = researcher.getHelper("memoizedTokenizer");
   const languageSpecificConfiguration = getConfiguration(researcher);
@@ -119,9 +112,9 @@ function _default(paper, researcher) {
       difficulty: DIFFICULTY.NO_DATA
     };
   }
-  text = (0, _stripNumbers.default)(text);
-  const numberOfSentences = (0, _countSentences.default)(text, memoizedTokenizer);
-  const numberOfWords = (0, _countWords.default)(text);
+  text = stripNumbers(text);
+  const numberOfSentences = countSentences(text, memoizedTokenizer);
+  const numberOfWords = countWords(text);
 
   // Do not show the Flesch reading ease when there is not enough data for the FRE to make sense. Also used to prevent division by zero errors.
   // A score of -1 signals to the code down the line that no valid FRE was calculated.
@@ -131,7 +124,7 @@ function _default(paper, researcher) {
       difficulty: DIFFICULTY.NO_DATA
     };
   }
-  const numberOfSyllables = (0, _countSyllables.default)(text, syllables);
+  const numberOfSyllables = countSyllables(text, syllables);
   const averageWordsPerSentence = getAverage(numberOfWords, numberOfSentences);
   const syllablesPer100Words = numberOfSyllables * (100 / numberOfWords);
   const statistics = {
@@ -142,7 +135,7 @@ function _default(paper, researcher) {
     syllablesPer100Words
   };
   const getScore = researcher.getHelper("fleschReadingScore");
-  const score = (0, _lodash.clamp)(getScore(statistics), 0, 100);
+  const score = clamp(getScore(statistics), 0, 100);
   const difficulty = getDifficulty(score, languageSpecificConfiguration);
   return {
     score,

package/build/languageProcessing/researches/getFleschReadingScore.js.map

@@ -1 +1 @@
-{"version":3,"file":"getFleschReadingScore.js","names":["_stripNumbers","_interopRequireDefault","require","_countSentences","_countWords","_countSyllables","_lodash","e","__esModule","default","getAverage","total","amount","DIFFICULTY","exports","NO_DATA","VERY_EASY","EASY","FAIRLY_EASY","OKAY","FAIRLY_DIFFICULT","DIFFICULT","VERY_DIFFICULT","getDifficulty","score","scoreConfiguration","borders","veryEasy","inRange","easy","fairlyEasy","okay","fairlyDifficult","difficult","getConfiguration","researcher","languageSpecificConfig","getConfig","defaultConfig","veryDifficult","scores","_default","paper","syllables","memoizedTokenizer","getHelper","languageSpecificConfiguration","text","getText","difficulty","stripNumbers","numberOfSentences","countSentences","numberOfWords","countWords","numberOfSyllables","countSyllables","averageWordsPerSentence","syllablesPer100Words","statistics","getScore","clamp"],"sources":["../../../src/languageProcessing/researches/getFleschReadingScore.js"],"sourcesContent":["/** @module analyses/calculateFleschReading */\n\nimport stripNumbers from \"../helpers/sanitize/stripNumbers.js\";\nimport countSentences from \"../helpers/sentence/countSentences.js\";\nimport countWords from \"../helpers/word/countWords.js\";\nimport countSyllables from \"../helpers/syllables/countSyllables.js\";\nimport { clamp, inRange } from \"lodash\";\n\n/**\n * Calculates an average from a total and an amount\n *\n * @param {number} total The total.\n * @param {number} amount The amount.\n * @returns {number} The average from the total and the amount.\n */\nconst getAverage = function( total, amount ) {\n\treturn total / amount;\n};\n\n/**\n * The Flesch reading ease difficulty.\n * @readonly\n * @enum {number}\n */\nexport const DIFFICULTY = {\n\tNO_DATA: -1,\n\tVERY_EASY: 0,\n\tEASY: 1,\n\tFAIRLY_EASY: 2,\n\tOKAY: 3,\n\tFAIRLY_DIFFICULT: 4,\n\tDIFFICULT: 5,\n\tVERY_DIFFICULT: 6,\n};\n\n/**\n * Returns the Flesch reading ease difficulty based on the boundaries\n * defined in the score configuration.\n *\n * @param {number} score The Flesch reading ease score.\n * @param {Object} scoreConfiguration The score configuration.\n *\n * @returns {DIFFICULTY} The Flesch reading ease difficulty.\n */\nfunction getDifficulty( score, scoreConfiguration ) {\n\tif ( score >= scoreConfiguration.borders.veryEasy ) {\n\t\treturn DIFFICULTY.VERY_EASY;\n\t} else if ( inRange( score, scoreConfiguration.borders.easy, scoreConfiguration.borders.veryEasy ) ) {\n\t\treturn DIFFICULTY.EASY;\n\t} else if ( inRange( score, scoreConfiguration.borders.fairlyEasy, scoreConfiguration.borders.easy ) ) {\n\t\treturn DIFFICULTY.FAIRLY_EASY;\n\t} else if ( inRange( score, scoreConfiguration.borders.okay, scoreConfiguration.borders.fairlyEasy ) ) {\n\t\treturn DIFFICULTY.OKAY;\n\t} else if ( inRange( score, scoreConfiguration.borders.fairlyDifficult, scoreConfiguration.borders.okay ) ) {\n\t\treturn DIFFICULTY.FAIRLY_DIFFICULT;\n\t} else if ( inRange( score, scoreConfiguration.borders.difficult, scoreConfiguration.borders.fairlyDifficult ) ) {\n\t\treturn DIFFICULTY.DIFFICULT;\n\t}\n\n\treturn DIFFICULTY.VERY_DIFFICULT;\n}\n\n/**\n * Retrieves the scoring configuration defining the boundaries to use to\n * determine the Flesch reading ease difficulty.\n *\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The language specific scoring configuration, or the default configuration if not available.\n */\nfunction getConfiguration( researcher ) {\n\tconst languageSpecificConfig = researcher.getConfig( \"fleschReadingEaseScores\" );\n\tconst defaultConfig = {\n\t\tborders: {\n\t\t\tveryEasy: 90,\n\t\t\teasy: 80,\n\t\t\tfairlyEasy: 70,\n\t\t\tokay: 60,\n\t\t\tfairlyDifficult: 50,\n\t\t\tdifficult: 30,\n\t\t\tveryDifficult: 0,\n\t\t},\n\t\tscores: {\n\t\t\tveryEasy: 9,\n\t\t\teasy: 9,\n\t\t\tfairlyEasy: 9,\n\t\t\tokay: 9,\n\t\t\tfairlyDifficult: 6,\n\t\t\tdifficult: 3,\n\t\t\tveryDifficult: 3,\n\t\t},\n\t};\n\treturn languageSpecificConfig ? languageSpecificConfig : defaultConfig;\n}\n\n/**\n * This calculates the Flesch reading score for a given text.\n *\n * @param {Paper}       paper           The paper containing the text.\n * @param {Researcher}  researcher      The researcher.\n *\n * @returns {{ score: number, difficulty: DIFFICULTY }} The Flesch reading score.\n */\nexport default function( paper, researcher ) {\n\tconst syllables = researcher.getConfig( \"syllables\" );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\tconst languageSpecificConfiguration = getConfiguration( researcher );\n\n\tlet text = paper.getText();\n\tif ( text === \"\" ) {\n\t\t// A score of -1 signals to the code down the line that no valid FRE was calculated.\n\t\treturn {\n\t\t\tscore: -1,\n\t\t\tdifficulty: DIFFICULTY.NO_DATA,\n\t\t};\n\t}\n\n\ttext = stripNumbers( text );\n\n\tconst numberOfSentences = countSentences( text, memoizedTokenizer );\n\tconst numberOfWords = countWords( text );\n\n\t// Do not show the Flesch reading ease when there is not enough data for the FRE to make sense. Also used to prevent division by zero errors.\n\t// A score of -1 signals to the code down the line that no valid FRE was calculated.\n\tif ( numberOfSentences < 1 || numberOfWords <= 10 ) {\n\t\treturn {\n\t\t\tscore: -1,\n\t\t\tdifficulty: DIFFICULTY.NO_DATA,\n\t\t};\n\t}\n\n\tconst numberOfSyllables = countSyllables( text, syllables );\n\tconst averageWordsPerSentence = getAverage( numberOfWords, numberOfSentences );\n\tconst syllablesPer100Words = numberOfSyllables * ( 100 / numberOfWords );\n\tconst statistics = {\n\t\tnumberOfSentences,\n\t\tnumberOfWords,\n\t\tnumberOfSyllables,\n\t\taverageWordsPerSentence,\n\t\tsyllablesPer100Words,\n\t};\n\n\tconst getScore = researcher.getHelper( \"fleschReadingScore\" );\n\n\tconst score = clamp( getScore( statistics ), 0, 100 );\n\n\tconst difficulty = getDifficulty( score, languageSpecificConfiguration );\n\n\treturn { score, difficulty };\n}\n"],"mappings":";;;;;;;AAEA,IAAAA,aAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,eAAA,GAAAF,sBAAA,CAAAC,OAAA;AACA,IAAAE,WAAA,GAAAH,sBAAA,CAAAC,OAAA;AACA,IAAAG,eAAA,GAAAJ,sBAAA,CAAAC,OAAA;AACA,IAAAI,OAAA,GAAAJ,OAAA;AAAwC,SAAAD,uBAAAM,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AANxC;;AAQA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,UAAU,GAAG,SAAAA,CAAUC,KAAK,EAAEC,MAAM,EAAG;EAC5C,OAAOD,KAAK,GAAGC,MAAM;AACtB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACO,MAAMC,UAAU,GAAAC,OAAA,CAAAD,UAAA,GAAG;EACzBE,OAAO,EAAE,CAAC,CAAC;EACXC,SAAS,EAAE,CAAC;EACZC,IAAI,EAAE,CAAC;EACPC,WAAW,EAAE,CAAC;EACdC,IAAI,EAAE,CAAC;EACPC,gBAAgB,EAAE,CAAC;EACnBC,SAAS,EAAE,CAAC;EACZC,cAAc,EAAE;AACjB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,aAAaA,CAAEC,KAAK,EAAEC,kBAAkB,EAAG;EACnD,IAAKD,KAAK,IAAIC,kBAAkB,CAACC,OAAO,CAACC,QAAQ,EAAG;IACnD,OAAOd,UAAU,CAACG,SAAS;EAC5B,CAAC,MAAM,IAAK,IAAAY,eAAO,EAAEJ,KAAK,EAAEC,kBAAkB,CAACC,OAAO,CAACG,IAAI,EAAEJ,kBAAkB,CAACC,OAAO,CAACC,QAAS,CAAC,EAAG;IACpG,OAAOd,UAAU,CAACI,IAAI;EACvB,CAAC,MAAM,IAAK,IAAAW,eAAO,EAAEJ,KAAK,EAAEC,kBAAkB,CAACC,OAAO,CAACI,UAAU,EAAEL,kBAAkB,CAACC,OAAO,CAACG,IAAK,CAAC,EAAG;IACtG,OAAOhB,UAAU,CAACK,WAAW;EAC9B,CAAC,MAAM,IAAK,IAAAU,eAAO,EAAEJ,KAAK,EAAEC,kBAAkB,CAACC,OAAO,CAACK,IAAI,EAAEN,kBAAkB,CAACC,OAAO,CAACI,UAAW,CAAC,EAAG;IACtG,OAAOjB,UAAU,CAACM,IAAI;EACvB,CAAC,MAAM,IAAK,IAAAS,eAAO,EAAEJ,KAAK,EAAEC,kBAAkB,CAACC,OAAO,CAACM,eAAe,EAAEP,kBAAkB,CAACC,OAAO,CAACK,IAAK,CAAC,EAAG;IAC3G,OAAOlB,UAAU,CAACO,gBAAgB;EACnC,CAAC,MAAM,IAAK,IAAAQ,eAAO,EAAEJ,KAAK,EAAEC,kBAAkB,CAACC,OAAO,CAACO,SAAS,EAAER,kBAAkB,CAACC,OAAO,CAACM,eAAgB,CAAC,EAAG;IAChH,OAAOnB,UAAU,CAACQ,SAAS;EAC5B;EAEA,OAAOR,UAAU,CAACS,cAAc;AACjC;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASY,gBAAgBA,CAAEC,UAAU,EAAG;EACvC,MAAMC,sBAAsB,GAAGD,UAAU,CAACE,SAAS,CAAE,yBAA0B,CAAC;EAChF,MAAMC,aAAa,GAAG;IACrBZ,OAAO,EAAE;MACRC,QAAQ,EAAE,EAAE;MACZE,IAAI,EAAE,EAAE;MACRC,UAAU,EAAE,EAAE;MACdC,IAAI,EAAE,EAAE;MACRC,eAAe,EAAE,EAAE;MACnBC,SAAS,EAAE,EAAE;MACbM,aAAa,EAAE;IAChB,CAAC;IACDC,MAAM,EAAE;MACPb,QAAQ,EAAE,CAAC;MACXE,IAAI,EAAE,CAAC;MACPC,UAAU,EAAE,CAAC;MACbC,IAAI,EAAE,CAAC;MACPC,eAAe,EAAE,CAAC;MAClBC,SAAS,EAAE,CAAC;MACZM,aAAa,EAAE;IAChB;EACD,CAAC;EACD,OAAOH,sBAAsB,GAAGA,sBAAsB,GAAGE,aAAa;AACvE;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAAUC,KAAK,EAAEP,UAAU,EAAG;EAC5C,MAAMQ,SAAS,GAAGR,UAAU,CAACE,SAAS,CAAE,WAAY,CAAC;EACrD,MAAMO,iBAAiB,GAAGT,UAAU,CAACU,SAAS,CAAE,mBAAoB,CAAC;EACrE,MAAMC,6BAA6B,GAAGZ,gBAAgB,CAAEC,UAAW,CAAC;EAEpE,IAAIY,IAAI,GAAGL,KAAK,CAACM,OAAO,CAAC,CAAC;EAC1B,IAAKD,IAAI,KAAK,EAAE,EAAG;IAClB;IACA,OAAO;MACNvB,KAAK,EAAE,CAAC,CAAC;MACTyB,UAAU,EAAEpC,UAAU,CAACE;IACxB,CAAC;EACF;EAEAgC,IAAI,GAAG,IAAAG,qBAAY,EAAEH,IAAK,CAAC;EAE3B,MAAMI,iBAAiB,GAAG,IAAAC,uBAAc,EAAEL,IAAI,EAAEH,iBAAkB,CAAC;EACnE,MAAMS,aAAa,GAAG,IAAAC,mBAAU,EAAEP,IAAK,CAAC;;EAExC;EACA;EACA,IAAKI,iBAAiB,GAAG,CAAC,IAAIE,aAAa,IAAI,EAAE,EAAG;IACnD,OAAO;MACN7B,KAAK,EAAE,CAAC,CAAC;MACTyB,UAAU,EAAEpC,UAAU,CAACE;IACxB,CAAC;EACF;EAEA,MAAMwC,iBAAiB,GAAG,IAAAC,uBAAc,EAAET,IAAI,EAAEJ,SAAU,CAAC;EAC3D,MAAMc,uBAAuB,GAAG/C,UAAU,CAAE2C,aAAa,EAAEF,iBAAkB,CAAC;EAC9E,MAAMO,oBAAoB,GAAGH,iBAAiB,IAAK,GAAG,GAAGF,aAAa,CAAE;EACxE,MAAMM,UAAU,GAAG;IAClBR,iBAAiB;IACjBE,aAAa;IACbE,iBAAiB;IACjBE,uBAAuB;IACvBC;EACD,CAAC;EAED,MAAME,QAAQ,GAAGzB,UAAU,CAACU,SAAS,CAAE,oBAAqB,CAAC;EAE7D,MAAMrB,KAAK,GAAG,IAAAqC,aAAK,EAAED,QAAQ,CAAED,UAAW,CAAC,EAAE,CAAC,EAAE,GAAI,CAAC;EAErD,MAAMV,UAAU,GAAG1B,aAAa,CAAEC,KAAK,EAAEsB,6BAA8B,CAAC;EAExE,OAAO;IAAEtB,KAAK;IAAEyB;EAAW,CAAC;AAC7B","ignoreList":[]}
+{"version":3,"file":"getFleschReadingScore.js","names":["stripNumbers","countSentences","countWords","countSyllables","clamp","inRange","getAverage","total","amount","DIFFICULTY","NO_DATA","VERY_EASY","EASY","FAIRLY_EASY","OKAY","FAIRLY_DIFFICULT","DIFFICULT","VERY_DIFFICULT","getDifficulty","score","scoreConfiguration","borders","veryEasy","easy","fairlyEasy","okay","fairlyDifficult","difficult","getConfiguration","researcher","languageSpecificConfig","getConfig","defaultConfig","veryDifficult","scores","paper","syllables","memoizedTokenizer","getHelper","languageSpecificConfiguration","text","getText","difficulty","numberOfSentences","numberOfWords","numberOfSyllables","averageWordsPerSentence","syllablesPer100Words","statistics","getScore"],"sources":["../../../src/languageProcessing/researches/getFleschReadingScore.js"],"sourcesContent":["/** @module analyses/calculateFleschReading */\n\nimport stripNumbers from \"../helpers/sanitize/stripNumbers.js\";\nimport countSentences from \"../helpers/sentence/countSentences.js\";\nimport countWords from \"../helpers/word/countWords.js\";\nimport countSyllables from \"../helpers/syllables/countSyllables.js\";\nimport { clamp, inRange } from \"lodash\";\n\n/**\n * Calculates an average from a total and an amount\n *\n * @param {number} total The total.\n * @param {number} amount The amount.\n * @returns {number} The average from the total and the amount.\n */\nconst getAverage = function( total, amount ) {\n\treturn total / amount;\n};\n\n/**\n * The Flesch reading ease difficulty.\n * @readonly\n * @enum {number}\n */\nexport const DIFFICULTY = {\n\tNO_DATA: -1,\n\tVERY_EASY: 0,\n\tEASY: 1,\n\tFAIRLY_EASY: 2,\n\tOKAY: 3,\n\tFAIRLY_DIFFICULT: 4,\n\tDIFFICULT: 5,\n\tVERY_DIFFICULT: 6,\n};\n\n/**\n * Returns the Flesch reading ease difficulty based on the boundaries\n * defined in the score configuration.\n *\n * @param {number} score The Flesch reading ease score.\n * @param {Object} scoreConfiguration The score configuration.\n *\n * @returns {DIFFICULTY} The Flesch reading ease difficulty.\n */\nfunction getDifficulty( score, scoreConfiguration ) {\n\tif ( score >= scoreConfiguration.borders.veryEasy ) {\n\t\treturn DIFFICULTY.VERY_EASY;\n\t} else if ( inRange( score, scoreConfiguration.borders.easy, scoreConfiguration.borders.veryEasy ) ) {\n\t\treturn DIFFICULTY.EASY;\n\t} else if ( inRange( score, scoreConfiguration.borders.fairlyEasy, scoreConfiguration.borders.easy ) ) {\n\t\treturn DIFFICULTY.FAIRLY_EASY;\n\t} else if ( inRange( score, scoreConfiguration.borders.okay, scoreConfiguration.borders.fairlyEasy ) ) {\n\t\treturn DIFFICULTY.OKAY;\n\t} else if ( inRange( score, scoreConfiguration.borders.fairlyDifficult, scoreConfiguration.borders.okay ) ) {\n\t\treturn DIFFICULTY.FAIRLY_DIFFICULT;\n\t} else if ( inRange( score, scoreConfiguration.borders.difficult, scoreConfiguration.borders.fairlyDifficult ) ) {\n\t\treturn DIFFICULTY.DIFFICULT;\n\t}\n\n\treturn DIFFICULTY.VERY_DIFFICULT;\n}\n\n/**\n * Retrieves the scoring configuration defining the boundaries to use to\n * determine the Flesch reading ease difficulty.\n *\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The language specific scoring configuration, or the default configuration if not available.\n */\nfunction getConfiguration( researcher ) {\n\tconst languageSpecificConfig = researcher.getConfig( \"fleschReadingEaseScores\" );\n\tconst defaultConfig = {\n\t\tborders: {\n\t\t\tveryEasy: 90,\n\t\t\teasy: 80,\n\t\t\tfairlyEasy: 70,\n\t\t\tokay: 60,\n\t\t\tfairlyDifficult: 50,\n\t\t\tdifficult: 30,\n\t\t\tveryDifficult: 0,\n\t\t},\n\t\tscores: {\n\t\t\tveryEasy: 9,\n\t\t\teasy: 9,\n\t\t\tfairlyEasy: 9,\n\t\t\tokay: 9,\n\t\t\tfairlyDifficult: 6,\n\t\t\tdifficult: 3,\n\t\t\tveryDifficult: 3,\n\t\t},\n\t};\n\treturn languageSpecificConfig ? languageSpecificConfig : defaultConfig;\n}\n\n/**\n * This calculates the Flesch reading score for a given text.\n *\n * @param {Paper}       paper           The paper containing the text.\n * @param {Researcher}  researcher      The researcher.\n *\n * @returns {{ score: number, difficulty: DIFFICULTY }} The Flesch reading score.\n */\nexport default function( paper, researcher ) {\n\tconst syllables = researcher.getConfig( \"syllables\" );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\tconst languageSpecificConfiguration = getConfiguration( researcher );\n\n\tlet text = paper.getText();\n\tif ( text === \"\" ) {\n\t\t// A score of -1 signals to the code down the line that no valid FRE was calculated.\n\t\treturn {\n\t\t\tscore: -1,\n\t\t\tdifficulty: DIFFICULTY.NO_DATA,\n\t\t};\n\t}\n\n\ttext = stripNumbers( text );\n\n\tconst numberOfSentences = countSentences( text, memoizedTokenizer );\n\tconst numberOfWords = countWords( text );\n\n\t// Do not show the Flesch reading ease when there is not enough data for the FRE to make sense. Also used to prevent division by zero errors.\n\t// A score of -1 signals to the code down the line that no valid FRE was calculated.\n\tif ( numberOfSentences < 1 || numberOfWords <= 10 ) {\n\t\treturn {\n\t\t\tscore: -1,\n\t\t\tdifficulty: DIFFICULTY.NO_DATA,\n\t\t};\n\t}\n\n\tconst numberOfSyllables = countSyllables( text, syllables );\n\tconst averageWordsPerSentence = getAverage( numberOfWords, numberOfSentences );\n\tconst syllablesPer100Words = numberOfSyllables * ( 100 / numberOfWords );\n\tconst statistics = {\n\t\tnumberOfSentences,\n\t\tnumberOfWords,\n\t\tnumberOfSyllables,\n\t\taverageWordsPerSentence,\n\t\tsyllablesPer100Words,\n\t};\n\n\tconst getScore = researcher.getHelper( \"fleschReadingScore\" );\n\n\tconst score = clamp( getScore( statistics ), 0, 100 );\n\n\tconst difficulty = getDifficulty( score, languageSpecificConfiguration );\n\n\treturn { score, difficulty };\n}\n"],"mappings":"AAAA;;AAEA,OAAOA,YAAY;AACnB,OAAOC,cAAc;AACrB,OAAOC,UAAU;AACjB,OAAOC,cAAc;AACrB,SAASC,KAAK,EAAEC,OAAO,QAAQ,QAAQ;;AAEvC;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,UAAU,GAAG,SAAAA,CAAUC,KAAK,EAAEC,MAAM,EAAG;EAC5C,OAAOD,KAAK,GAAGC,MAAM;AACtB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA,OAAO,MAAMC,UAAU,GAAG;EACzBC,OAAO,EAAE,CAAC,CAAC;EACXC,SAAS,EAAE,CAAC;EACZC,IAAI,EAAE,CAAC;EACPC,WAAW,EAAE,CAAC;EACdC,IAAI,EAAE,CAAC;EACPC,gBAAgB,EAAE,CAAC;EACnBC,SAAS,EAAE,CAAC;EACZC,cAAc,EAAE;AACjB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,aAAaA,CAAEC,KAAK,EAAEC,kBAAkB,EAAG;EACnD,IAAKD,KAAK,IAAIC,kBAAkB,CAACC,OAAO,CAACC,QAAQ,EAAG;IACnD,OAAOb,UAAU,CAACE,SAAS;EAC5B,CAAC,MAAM,IAAKN,OAAO,CAAEc,KAAK,EAAEC,kBAAkB,CAACC,OAAO,CAACE,IAAI,EAAEH,kBAAkB,CAACC,OAAO,CAACC,QAAS,CAAC,EAAG;IACpG,OAAOb,UAAU,CAACG,IAAI;EACvB,CAAC,MAAM,IAAKP,OAAO,CAAEc,KAAK,EAAEC,kBAAkB,CAACC,OAAO,CAACG,UAAU,EAAEJ,kBAAkB,CAACC,OAAO,CAACE,IAAK,CAAC,EAAG;IACtG,OAAOd,UAAU,CAACI,WAAW;EAC9B,CAAC,MAAM,IAAKR,OAAO,CAAEc,KAAK,EAAEC,kBAAkB,CAACC,OAAO,CAACI,IAAI,EAAEL,kBAAkB,CAACC,OAAO,CAACG,UAAW,CAAC,EAAG;IACtG,OAAOf,UAAU,CAACK,IAAI;EACvB,CAAC,MAAM,IAAKT,OAAO,CAAEc,KAAK,EAAEC,kBAAkB,CAACC,OAAO,CAACK,eAAe,EAAEN,kBAAkB,CAACC,OAAO,CAACI,IAAK,CAAC,EAAG;IAC3G,OAAOhB,UAAU,CAACM,gBAAgB;EACnC,CAAC,MAAM,IAAKV,OAAO,CAAEc,KAAK,EAAEC,kBAAkB,CAACC,OAAO,CAACM,SAAS,EAAEP,kBAAkB,CAACC,OAAO,CAACK,eAAgB,CAAC,EAAG;IAChH,OAAOjB,UAAU,CAACO,SAAS;EAC5B;EAEA,OAAOP,UAAU,CAACQ,cAAc;AACjC;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASW,gBAAgBA,CAAEC,UAAU,EAAG;EACvC,MAAMC,sBAAsB,GAAGD,UAAU,CAACE,SAAS,CAAE,yBAA0B,CAAC;EAChF,MAAMC,aAAa,GAAG;IACrBX,OAAO,EAAE;MACRC,QAAQ,EAAE,EAAE;MACZC,IAAI,EAAE,EAAE;MACRC,UAAU,EAAE,EAAE;MACdC,IAAI,EAAE,EAAE;MACRC,eAAe,EAAE,EAAE;MACnBC,SAAS,EAAE,EAAE;MACbM,aAAa,EAAE;IAChB,CAAC;IACDC,MAAM,EAAE;MACPZ,QAAQ,EAAE,CAAC;MACXC,IAAI,EAAE,CAAC;MACPC,UAAU,EAAE,CAAC;MACbC,IAAI,EAAE,CAAC;MACPC,eAAe,EAAE,CAAC;MAClBC,SAAS,EAAE,CAAC;MACZM,aAAa,EAAE;IAChB;EACD,CAAC;EACD,OAAOH,sBAAsB,GAAGA,sBAAsB,GAAGE,aAAa;AACvE;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUG,KAAK,EAAEN,UAAU,EAAG;EAC5C,MAAMO,SAAS,GAAGP,UAAU,CAACE,SAAS,CAAE,WAAY,CAAC;EACrD,MAAMM,iBAAiB,GAAGR,UAAU,CAACS,SAAS,CAAE,mBAAoB,CAAC;EACrE,MAAMC,6BAA6B,GAAGX,gBAAgB,CAAEC,UAAW,CAAC;EAEpE,IAAIW,IAAI,GAAGL,KAAK,CAACM,OAAO,CAAC,CAAC;EAC1B,IAAKD,IAAI,KAAK,EAAE,EAAG;IAClB;IACA,OAAO;MACNrB,KAAK,EAAE,CAAC,CAAC;MACTuB,UAAU,EAAEjC,UAAU,CAACC;IACxB,CAAC;EACF;EAEA8B,IAAI,GAAGxC,YAAY,CAAEwC,IAAK,CAAC;EAE3B,MAAMG,iBAAiB,GAAG1C,cAAc,CAAEuC,IAAI,EAAEH,iBAAkB,CAAC;EACnE,MAAMO,aAAa,GAAG1C,UAAU,CAAEsC,IAAK,CAAC;;EAExC;EACA;EACA,IAAKG,iBAAiB,GAAG,CAAC,IAAIC,aAAa,IAAI,EAAE,EAAG;IACnD,OAAO;MACNzB,KAAK,EAAE,CAAC,CAAC;MACTuB,UAAU,EAAEjC,UAAU,CAACC;IACxB,CAAC;EACF;EAEA,MAAMmC,iBAAiB,GAAG1C,cAAc,CAAEqC,IAAI,EAAEJ,SAAU,CAAC;EAC3D,MAAMU,uBAAuB,GAAGxC,UAAU,CAAEsC,aAAa,EAAED,iBAAkB,CAAC;EAC9E,MAAMI,oBAAoB,GAAGF,iBAAiB,IAAK,GAAG,GAAGD,aAAa,CAAE;EACxE,MAAMI,UAAU,GAAG;IAClBL,iBAAiB;IACjBC,aAAa;IACbC,iBAAiB;IACjBC,uBAAuB;IACvBC;EACD,CAAC;EAED,MAAME,QAAQ,GAAGpB,UAAU,CAACS,SAAS,CAAE,oBAAqB,CAAC;EAE7D,MAAMnB,KAAK,GAAGf,KAAK,CAAE6C,QAAQ,CAAED,UAAW,CAAC,EAAE,CAAC,EAAE,GAAI,CAAC;EAErD,MAAMN,UAAU,GAAGxB,aAAa,CAAEC,KAAK,EAAEoB,6BAA8B,CAAC;EAExE,OAAO;IAAEpB,KAAK;IAAEuB;EAAW,CAAC;AAC7B","ignoreList":[]}

package/build/languageProcessing/researches/getKeywordDensity.js

@@ -1,12 +1,5 @@
-"use strict";
+import countWords from "../helpers/word/countWords";
 
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = getKeyphraseDensity;
-exports.getKeywordDensity = getKeywordDensity;
-var _getAllWordsFromTree = _interopRequireDefault(require("../helpers/word/getAllWordsFromTree"));
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /**
  * Calculates the keyphrase density.
  *
@@ -15,20 +8,20 @@ function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e
  *
  * @returns {number} The keyphrase density.
  */
-function getKeyphraseDensity(paper, researcher) {
-  const getWordsCustomHelper = researcher.getHelper("getWordsCustomHelper");
+export default function getKeyphraseDensity(paper, researcher) {
+  const getWordsCustomHelper = researcher.getHelper('getWordsCustomHelper');
   let wordCount = 0;
 
   // If there is a custom getWords helper, use its output for countWords.
   if (getWordsCustomHelper) {
     wordCount = getWordsCustomHelper(paper.getText()).length;
   } else {
-    wordCount = (0, _getAllWordsFromTree.default)(paper).length;
+    wordCount = countWords(paper.getText());
   }
   if (wordCount === 0) {
     return 0;
   }
-  const keyphraseCount = researcher.getResearch("getKeyphraseCount");
+  const keyphraseCount = researcher.getResearch('getKeyphraseCount');
   return keyphraseCount.count / wordCount * 100;
 }
 
@@ -42,8 +35,8 @@ function getKeyphraseDensity(paper, researcher) {
  *
  * @returns {number} The keyphrase density.
  */
-function getKeywordDensity(paper, researcher) {
-  console.warn("This function is deprecated, use getKeyphraseDensity instead.");
+export function getKeywordDensity(paper, researcher) {
+  console.warn('This function is deprecated, use getKeyphraseDensity instead.');
   return getKeyphraseDensity(paper, researcher);
 }
 //# sourceMappingURL=getKeywordDensity.js.map