axyseo 2.1.12 → 2.1.13

package/build/cjs/languageProcessing/researches/findKeywordInFirstParagraph.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"findKeywordInFirstParagraph.js","names":["_lodash","require","_findKeywordFormsInString","_getSentencesFromTree","_helpers","_isChineseText","_interopRequireDefault","e","__esModule","default","_default","paper","researcher","paragraphs","getResearch","filter","paragraph","parentNode","getParentNode","isImplicit","name","childNodes","createShortcodeTagsRegex","test","value","firstParagraph","topicForms","matchWordCustomHelper","getHelper","locale","getLocale","isChineseText","getKeyword","innerText","text","word","textToSearch","matches","lowerText","toLowerCase","lowerWord","startIndex","index","indexOf","push","length","startOffset","sourceCodeLocation","mappedBlocks","_attributes","wpBlocks","filteredIntroductionBlock","block","inRange","endOffset","result","foundInOneSentence","foundInParagraph","keyphraseOrSynonym","introduction","parentBlock","isEmpty","sentences","map","sentence","useSynonyms","firstResultSentence","findTopicFormsInString","find","resultSentence","percentWordMatches","resultParagraph"],"sources":["../../../../src/languageProcessing/researches/findKeywordInFirstParagraph.js"],"sourcesContent":["/** @module analyses/findKeywordInFirstParagraph */\nimport {inRange, isEmpty} from 'lodash';\n\nimport {findTopicFormsInString} from '../helpers/match/findKeywordFormsInString.js';\nimport {getParentNode} from '../helpers/sentence/getSentencesFromTree';\nimport {createShortcodeTagsRegex} from '../helpers';\nimport isChineseText from '../helpers/language/isChineseText';\n\n/**\n * Checks if the introductory paragraph contains keyphrase or synonyms.\n * First splits the first paragraph by sentences. Finds the first paragraph which contains sentences e.g., not an image).\n * (1) Tries to find all (content) words from the keyphrase or a synonym phrase within one sentence.\n * If found all words within one sentence, returns an object with foundInOneSentence = true and keyphraseOrSynonym = \"keyphrase\"\n * or \"synonym\".\n * If it did not find all words within one sentence, goes ahead with matching the keyphrase with the entire first paragraph.\n * (2) Tries to find all (content) words from the keyphrase or a synonym phrase within the paragraph.\n * If found all words within the paragraph, returns an object with foundInOneSentence = false, foundInParagraph = true,\n * and keyphraseOrSynonym = \"keyphrase\" or \"synonym\".\n * If found not all words within the paragraph of nothing at all, returns an object with foundInOneSentence = false,\n * foundInParagraph = false, and keyphraseOrSynonym = \"\".\n *\n * @param {Paper} paper The text to check for paragraphs.\n * @param {Researcher} researcher The researcher to use for analysis.\n *\n * @returns {Object} Whether the keyphrase words were found in one sentence, whether the keyphrase words were found in\n * the paragraph, whether a keyphrase or a synonym phrase was matched.\n */\nexport default function(paper, researcher) {\n  let paragraphs = researcher.getResearch('getParagraphs');\n  // Filter captions from non-Classic editors.\n  paragraphs = paragraphs.filter(paragraph => {\n    const parentNode = getParentNode(paper, paragraph);\n    return !(paragraph.isImplicit && parentNode && parentNode.name === 'figcaption');\n  });\n  // Filter captions from Classic editor and from classic block inside Block editor.\n  paragraphs = paragraphs.filter(paragraph => {\n    return !(\n      paragraph.childNodes &&\n      paragraph.childNodes[0] &&\n      createShortcodeTagsRegex(['caption']).test(paragraph.childNodes[0].value)\n    );\n  });\n  const firstParagraph = paragraphs[0];\n\n  const topicForms = researcher.getResearch('morphology');\n  let matchWordCustomHelper = researcher.getHelper('matchWordCustomHelper');\n  const locale = paper.getLocale();\n\n  // Auto-detect Chinese and use Chinese helper if not already available\n  if (\n    !matchWordCustomHelper &&\n    isChineseText(paper.getKeyword() + ' ' + (firstParagraph ? firstParagraph.innerText() : ''))\n  ) {\n    // Use Chinese word matching for Chinese text\n    matchWordCustomHelper = function(text, word) {\n      const textToSearch = typeof text === 'string' ? text : text.text || text;\n      const matches = [];\n\n      if (!textToSearch || !word) {\n        return matches;\n      }\n\n      const lowerText = textToSearch.toLowerCase();\n      const lowerWord = word.toLowerCase();\n\n      let startIndex = 0;\n      let index;\n\n      while ((index = lowerText.indexOf(lowerWord, startIndex)) !== -1) {\n        matches.push(word);\n        startIndex = index + lowerWord.length;\n      }\n\n      return matches;\n    };\n  }\n  const startOffset = firstParagraph && firstParagraph.sourceCodeLocation.startOffset;\n\n  const mappedBlocks = paper._attributes.wpBlocks;\n  const filteredIntroductionBlock =\n    mappedBlocks &&\n    mappedBlocks.filter(block => inRange(startOffset, block.startOffset, block.endOffset))[0];\n  const result = {\n    foundInOneSentence: false,\n    foundInParagraph: false,\n    keyphraseOrSynonym: '',\n    introduction: firstParagraph,\n    parentBlock: filteredIntroductionBlock || null\n  };\n\n  if (isEmpty(firstParagraph)) {\n    return result;\n  }\n\n  const sentences = firstParagraph.sentences.map(sentence => sentence.text);\n  // Use both keyphrase and synonyms to match topic words in the first paragraph.\n  const useSynonyms = true;\n\n  if (!isEmpty(sentences)) {\n    const firstResultSentence = sentences\n      .map(sentence =>\n        findTopicFormsInString(topicForms, sentence, useSynonyms, locale, matchWordCustomHelper)\n      )\n      .find(resultSentence => resultSentence.percentWordMatches === 100);\n\n    if (firstResultSentence) {\n      result.foundInOneSentence = true;\n      result.foundInParagraph = true;\n      result.keyphraseOrSynonym = firstResultSentence.keyphraseOrSynonym;\n      return result;\n    }\n\n    const resultParagraph = findTopicFormsInString(\n      topicForms,\n      firstParagraph.innerText(),\n      useSynonyms,\n      locale,\n      matchWordCustomHelper\n    );\n    if (resultParagraph.percentWordMatches === 100) {\n      result.foundInParagraph = true;\n      result.keyphraseOrSynonym = resultParagraph.keyphraseOrSynonym;\n      return result;\n    }\n  }\n\n  return result;\n}\n"],"mappings":";;;;;;AACA,IAAAA,OAAA,GAAAC,OAAA;AAEA,IAAAC,yBAAA,GAAAD,OAAA;AACA,IAAAE,qBAAA,GAAAF,OAAA;AACA,IAAAG,QAAA,GAAAH,OAAA;AACA,IAAAI,cAAA,GAAAC,sBAAA,CAAAL,OAAA;AAA8D,SAAAK,uBAAAC,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAN9D;;AAQA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAASC,KAAK,EAAEC,UAAU,EAAE;EACzC,IAAIC,UAAU,GAAGD,UAAU,CAACE,WAAW,CAAC,eAAe,CAAC;EACxD;EACAD,UAAU,GAAGA,UAAU,CAACE,MAAM,CAACC,SAAS,IAAI;IAC1C,MAAMC,UAAU,GAAG,IAAAC,mCAAa,EAACP,KAAK,EAAEK,SAAS,CAAC;IAClD,OAAO,EAAEA,SAAS,CAACG,UAAU,IAAIF,UAAU,IAAIA,UAAU,CAACG,IAAI,KAAK,YAAY,CAAC;EAClF,CAAC,CAAC;EACF;EACAP,UAAU,GAAGA,UAAU,CAACE,MAAM,CAACC,SAAS,IAAI;IAC1C,OAAO,EACLA,SAAS,CAACK,UAAU,IACpBL,SAAS,CAACK,UAAU,CAAC,CAAC,CAAC,IACvB,IAAAC,iCAAwB,EAAC,CAAC,SAAS,CAAC,CAAC,CAACC,IAAI,CAACP,SAAS,CAACK,UAAU,CAAC,CAAC,CAAC,CAACG,KAAK,CAAC,CAC1E;EACH,CAAC,CAAC;EACF,MAAMC,cAAc,GAAGZ,UAAU,CAAC,CAAC,CAAC;EAEpC,MAAMa,UAAU,GAAGd,UAAU,CAACE,WAAW,CAAC,YAAY,CAAC;EACvD,IAAIa,qBAAqB,GAAGf,UAAU,CAACgB,SAAS,CAAC,uBAAuB,CAAC;EACzE,MAAMC,MAAM,GAAGlB,KAAK,CAACmB,SAAS,CAAC,CAAC;;EAEhC;EACA,IACE,CAACH,qBAAqB,IACtB,IAAAI,sBAAa,EAACpB,KAAK,CAACqB,UAAU,CAAC,CAAC,GAAG,GAAG,IAAIP,cAAc,GAAGA,cAAc,CAACQ,SAAS,CAAC,CAAC,GAAG,EAAE,CAAC,CAAC,EAC5F;IACA;IACAN,qBAAqB,GAAG,SAAAA,CAASO,IAAI,EAAEC,IAAI,EAAE;MAC3C,MAAMC,YAAY,GAAG,OAAOF,IAAI,KAAK,QAAQ,GAAGA,IAAI,GAAGA,IAAI,CAACA,IAAI,IAAIA,IAAI;MACxE,MAAMG,OAAO,GAAG,EAAE;MAElB,IAAI,CAACD,YAAY,IAAI,CAACD,IAAI,EAAE;QAC1B,OAAOE,OAAO;MAChB;MAEA,MAAMC,SAAS,GAAGF,YAAY,CAACG,WAAW,CAAC,CAAC;MAC5C,MAAMC,SAAS,GAAGL,IAAI,CAACI,WAAW,CAAC,CAAC;MAEpC,IAAIE,UAAU,GAAG,CAAC;MAClB,IAAIC,KAAK;MAET,OAAO,CAACA,KAAK,GAAGJ,SAAS,CAACK,OAAO,CAACH,SAAS,EAAEC,UAAU,CAAC,MAAM,CAAC,CAAC,EAAE;QAChEJ,OAAO,CAACO,IAAI,CAACT,IAAI,CAAC;QAClBM,UAAU,GAAGC,KAAK,GAAGF,SAAS,CAACK,MAAM;MACvC;MAEA,OAAOR,OAAO;IAChB,CAAC;EACH;EACA,MAAMS,WAAW,GAAGrB,cAAc,IAAIA,cAAc,CAACsB,kBAAkB,CAACD,WAAW;EAEnF,MAAME,YAAY,GAAGrC,KAAK,CAACsC,WAAW,CAACC,QAAQ;EAC/C,MAAMC,yBAAyB,GAC7BH,YAAY,IACZA,YAAY,CAACjC,MAAM,CAACqC,KAAK,IAAI,IAAAC,eAAO,EAACP,WAAW,EAAEM,KAAK,CAACN,WAAW,EAAEM,KAAK,CAACE,SAAS,CAAC,CAAC,CAAC,CAAC,CAAC;EAC3F,MAAMC,MAAM,GAAG;IACbC,kBAAkB,EAAE,KAAK;IACzBC,gBAAgB,EAAE,KAAK;IACvBC,kBAAkB,EAAE,EAAE;IACtBC,YAAY,EAAElC,cAAc;IAC5BmC,WAAW,EAAET,yBAAyB,IAAI;EAC5C,CAAC;EAED,IAAI,IAAAU,eAAO,EAACpC,cAAc,CAAC,EAAE;IAC3B,OAAO8B,MAAM;EACf;EAEA,MAAMO,SAAS,GAAGrC,cAAc,CAACqC,SAAS,CAACC,GAAG,CAACC,QAAQ,IAAIA,QAAQ,CAAC9B,IAAI,CAAC;EACzE;EACA,MAAM+B,WAAW,GAAG,IAAI;EAExB,IAAI,CAAC,IAAAJ,eAAO,EAACC,SAAS,CAAC,EAAE;IACvB,MAAMI,mBAAmB,GAAGJ,SAAS,CAClCC,GAAG,CAACC,QAAQ,IACX,IAAAG,gDAAsB,EAACzC,UAAU,EAAEsC,QAAQ,EAAEC,WAAW,EAAEpC,MAAM,EAAEF,qBAAqB,CACzF,CAAC,CACAyC,IAAI,CAACC,cAAc,IAAIA,cAAc,CAACC,kBAAkB,KAAK,GAAG,CAAC;IAEpE,IAAIJ,mBAAmB,EAAE;MACvBX,MAAM,CAACC,kBAAkB,GAAG,IAAI;MAChCD,MAAM,CAACE,gBAAgB,GAAG,IAAI;MAC9BF,MAAM,CAACG,kBAAkB,GAAGQ,mBAAmB,CAACR,kBAAkB;MAClE,OAAOH,MAAM;IACf;IAEA,MAAMgB,eAAe,GAAG,IAAAJ,gDAAsB,EAC5CzC,UAAU,EACVD,cAAc,CAACQ,SAAS,CAAC,CAAC,EAC1BgC,WAAW,EACXpC,MAAM,EACNF,qBACF,CAAC;IACD,IAAI4C,eAAe,CAACD,kBAAkB,KAAK,GAAG,EAAE;MAC9Cf,MAAM,CAACE,gBAAgB,GAAG,IAAI;MAC9BF,MAAM,CAACG,kBAAkB,GAAGa,eAAe,CAACb,kBAAkB;MAC9D,OAAOH,MAAM;IACf;EACF;EAEA,OAAOA,MAAM;AACf","ignoreList":[]}

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

@@ -0,0 +1,119 @@
+"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 }; }
+let regexFromDoubleArray = null;
+let regexFromDoubleArrayCacheKey = "";
+
+/**
+ * Memoizes the createRegexFromDoubleArray with the twoPartTransitionWords.
+ *
+ * @param {Array} twoPartTransitionWords The array containing two-part transition words.
+ *
+ * @returns {RegExp} The RegExp to match text with a double array.
+ */
+function getRegexFromDoubleArray(twoPartTransitionWords) {
+  const cacheKey = (0, _lodash.flattenDeep)(twoPartTransitionWords).join("");
+  if (regexFromDoubleArrayCacheKey !== cacheKey || regexFromDoubleArray === null) {
+    regexFromDoubleArrayCacheKey = cacheKey;
+    regexFromDoubleArray = (0, _createRegexFromDoubleArray.default)(twoPartTransitionWords);
+  }
+  return regexFromDoubleArray;
+}
+
+/**
+ * Matches the sentence against two part transition words.
+ *
+ * @param {string} sentence The sentence to match against.
+ * @param {Array} twoPartTransitionWords The array containing two-part transition words.
+ * @returns {Array} The found transitional words.
+ */
+const matchTwoPartTransitionWords = function (sentence, twoPartTransitionWords) {
+  sentence = (0, _quotes.normalizeSingle)(sentence);
+  const twoPartTransitionWordsRegex = getRegexFromDoubleArray(twoPartTransitionWords);
+  return sentence.match(twoPartTransitionWordsRegex);
+};
+
+/**
+ * Matches the sentence against transition words.
+ *
+ * @param {string} sentence The sentence to match against.
+ * @param {Array} transitionWords The array containing transition words.
+ * @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));
+};
+
+/**
+ * Checks the passed sentences to see if they contain transition words.
+ *
+ * @param {Array} sentences The sentences to match against.
+ * @param {Array} transitionWords The array containing transition words.
+ * @param {Array} twoPartTransitionWords The array containing two part transition words.
+ * @param {function} matchTransitionWordsHelper The language-specific helper function to match transition words in a sentence.
+ *
+ * @returns {Array} Array of sentence objects containing the complete sentence and the transition words.
+ */
+const checkSentencesForTransitionWords = function (sentences, transitionWords, twoPartTransitionWords, matchTransitionWordsHelper) {
+  const results = [];
+  sentences.forEach(sentence => {
+    if (twoPartTransitionWords) {
+      const twoPartMatches = matchTwoPartTransitionWords(sentence, twoPartTransitionWords);
+      if (twoPartMatches !== null) {
+        results.push({
+          sentence: sentence,
+          transitionWords: twoPartMatches
+        });
+        return;
+      }
+    }
+    const transitionWordMatches = matchTransitionWordsHelper ? matchTransitionWordsHelper(sentence, transitionWords) : matchTransitionWords(sentence, transitionWords);
+    if (transitionWordMatches.length !== 0) {
+      results.push({
+        sentence: sentence,
+        transitionWords: transitionWordMatches
+      });
+    }
+  });
+  return results;
+};
+
+/**
+ * Checks how many sentences from a text contain at least one transition word or two-part transition word
+ * that are defined in the transition words config and two part transition words config.
+ *
+ * @param {Paper} paper The Paper object to get text from.
+ * @param {Researcher} researcher The researcher.
+ *
+ * @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) {
+  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);
+  const sentenceResults = checkSentencesForTransitionWords(sentences, transitionWords, twoPartTransitionWords, matchTransitionWordsHelper);
+  return {
+    totalSentences: sentences.length,
+    sentenceResults: sentenceResults,
+    transitionWordSentences: sentenceResults.length
+  };
+}
+//# sourceMappingURL=findTransitionWords.js.map

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

@@ -0,0 +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":[]}

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

@@ -0,0 +1,48 @@
+"use strict";
+
+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.
+ *
+ * @param {object} paper The paper containing the keyword.
+ * @param {Researcher} researcher The researcher.
+ *
+ * @returns {boolean} Whether the keyphrase contains of content words only.
+ */
+function _default(paper, researcher) {
+  const functionWords = researcher.getConfig("functionWords");
+
+  // A helper to get words from the keyphrase for languages that don't use the default way.
+  const getWordsCustomHelper = researcher.getHelper("getWordsCustomHelper");
+  const keyphrase = paper.getKeyword();
+
+  // Return false if there are double quotes around the keyphrase.
+  if ((0, _processExactMatchRequest.default)(keyphrase).exactMatchRequested) {
+    return false;
+  }
+
+  /*
+      * We use a word boundary regex that includes whitespaces, en-dashes, and hyphens for all languages.
+      * This means that we also consider keyphrases that consist of function words separated by hyphens (e.g. 'two-year-old')
+      * as containing only function words. Since many hyphenated phrases can also be written without hyphens, this way the
+      * behavior for hyphenated phrases matches the behavior for unhyphenated phrases.
+      * In Indonesian we normally don't want to treat hyphens as word boundaries, but in this case it makes sense because
+      * in Indonesian you can also have function words seperated by hyphens (e.g. 'dua-lima').
+      * 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());
+  });
+  return (0, _lodash.isEmpty)(keyphraseWords);
+}
+//# sourceMappingURL=functionWordsInKeyphrase.js.map

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

@@ -0,0 +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":[]}

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

@@ -0,0 +1,227 @@
+"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");
+var _chineseHelperFactory = require("../helpers/language/chineseHelperFactory.js");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+let functionWords = [];
+
+/**
+ * Checks whether the anchor's link is a relative fragment or the same as the site url/domain.
+ * Relative fragment links always point to the page itself.
+ *
+ * @param {String} anchorLink       The link anchor.
+ * @param {String} siteUrlOrDomain  The site URL or domain of the paper.
+ *
+ * @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));
+}
+
+/**
+ * Gets the anchors whose url is not linking at the current site url/domain.
+ *
+ * @param {Array}   anchors         An array with all anchors from the paper.
+ * @param {String}  siteUrlOrDomain The site URL or domain of the paper.
+ *
+ * @returns {Array} The array of all anchors whose url is not linking at the current site url/domain.
+ */
+function getAnchorsLinkingToSelf(anchors, siteUrlOrDomain) {
+  const anchorsLinkingToSelf = anchors.map(function (anchor) {
+    const anchorLink = anchor.attributes.href;
+    // Return false if there is no href attribute.
+    return anchorLink ? isLinkingToSelf(anchorLink, siteUrlOrDomain) : false;
+  });
+  return anchors.filter((anchor, index) => !anchorsLinkingToSelf[index]);
+}
+
+/**
+ * Gets the anchors with text that contains all content words of the topic (i.e. keyphrase or synonyms).
+ *
+ * @param {Array}       anchors         An array with all anchors from the paper
+ * @param {Object}      topicForms      The object with topicForms. It contains all forms of the keyphrase and synonyms.
+ * @param {String}      locale          The locale of the paper.
+ * @param {Function}    matchWordCustomHelper The helper function to match word in text.
+ *
+ * @returns {String[]} The array of all anchors with text that contains all content words of the keyphrase or synonyms.
+ */
+function getAnchorsContainingTopic(anchors, topicForms, locale, matchWordCustomHelper) {
+  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 anchors.filter((anchor, index) => anchorsContainingTopic[index]);
+}
+
+/**
+ * Gets the anchors with text that has the same content words as the keyphrase or synonyms.
+ *
+ * @param {Array}       anchors             		An array with all anchors from the paper.
+ * @param {Object}      topicForms          		The object with topicForms. It contains all forms of the keyphrase and synonyms.
+ * @param {string}      locale              		The locale of the paper.
+ * @param {Object}      customHelpers       		An object containing custom helpers.
+ * @param {Object[]}    exactMatchRequest   		An array of objects containing the keyphrase and information on whether
+ * 													the exact match has been requested.
+ * @param {boolean}	 	areHyphensWordBoundaries	Whether hyphens should be treated as word boundaries.
+ *
+ * @returns {Array} The array of all anchors with text that has the same content words as the keyphrase/synonyms.
+ */
+function getAnchorsWithSameTextAsTopic(anchors, topicForms, locale, customHelpers, exactMatchRequest, areHyphensWordBoundaries) {
+  const matchWordCustomHelper = customHelpers.matchWordCustomHelper;
+  const getWordsCustomHelper = customHelpers.getWordsCustomHelper;
+
+  // Prepare keyphrase and synonym forms for comparison with anchors.
+  const keyphraseAndSynonymsWords = [(0, _lodash.flatten)(topicForms.keyphraseForms)];
+  const synonymsForms = topicForms.synonymsForms;
+  synonymsForms.forEach(form => keyphraseAndSynonymsWords.push((0, _lodash.flatten)(form)));
+
+  // The variable that will save all the anchors with text that has the same content words as the keyphrase/synonyms.
+  const anchorsContainedInTopic = [];
+  anchors.forEach(function (currentAnchor) {
+    const currentAnchorText = currentAnchor.innerText();
+
+    /*
+     * For keyphrase matching, we want to split words on hyphens and en-dashes, except for languages where hyphens shouldn't
+     * be treated as word boundaries. Currently, the latter only applies to Indonesian, where hyphens are used to create plural forms of nouns,
+     * 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
+     * split words on hyphens in Indonesian.
+     * For languages where hyphens are treated as word boundaries we pass a custom word boundary regex string to the getWords helper
+     * that includes whitespaces, hyphens (u002d), and en-dashes (u2013). Otherwise, we pass a word boundary regex that only includes
+     * whitespaces and en-dashes.
+     */
+    let anchorWords;
+    if (getWordsCustomHelper) {
+      anchorWords = (0, _lodash.uniq)(getWordsCustomHelper(currentAnchorText));
+    } else if (areHyphensWordBoundaries) {
+      anchorWords = (0, _lodash.uniq)((0, _getWords.default)(currentAnchorText, _wordBoundariesWithoutPunctuation.WORD_BOUNDARY_WITH_HYPHEN));
+    } else {
+      anchorWords = (0, _lodash.uniq)((0, _getWords.default)(currentAnchorText, _wordBoundariesWithoutPunctuation.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);
+    if (filteredAnchorWords.length > 0) {
+      anchorWords = filteredAnchorWords;
+    }
+    exactMatchRequest.forEach(request => {
+      /*
+       * Check a) if the exact match is requested for the keyphrase, and
+       * b) if every content word in the anchor text is included in the keyphrase or synonym.
+       */
+      if (request.exactMatchRequested && anchorWords.every(anchorWord => request.keyphrase.includes(anchorWord))) {
+        anchorsContainedInTopic.push(true);
+      }
+    });
+
+    // 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)) {
+        anchorsContainedInTopic.push(true);
+        break;
+      }
+    }
+  });
+  return anchors.filter((anchor, index) => anchorsContainedInTopic[index]);
+}
+
+/**
+ * Checks whether the content words of the anchor text are the same as the content words of the keyphrase or synonym.
+ * Also includes different word forms if the morphology is available.
+ *
+ * @param {Paper}       paper       The paper to research.
+ * @param {Researcher}  researcher  The researcher to use.
+ *
+ * @returns {Object} The amount of anchor texts whose content words are the same as the keyphrase or synonyms' content words.
+ */
+function _default(paper, researcher) {
+  functionWords = researcher.getConfig('functionWords');
+  const areHyphensWordBoundaries = researcher.getConfig('areHyphensWordBoundaries');
+  const result = {
+    anchorsWithKeyphrase: [],
+    anchorsWithKeyphraseCount: 0
+  };
+  // STEP 1.
+  // If the paper's text is empty, return empty result.
+  if (paper.getText() === '') {
+    return result;
+  }
+
+  // STEP 2.
+  const keyphrase = paper.getKeyword();
+  /*
+   * If no keyphrase is set, return empty result.
+   * This is a conscious decision where we won't assess the paper if the keyphrase is not set.
+   * This includes a case where only the synonym is set but not the keyphrase.
+   */
+  if (keyphrase === '') {
+    return result;
+  }
+  /*
+   * 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());
+  originalTopics.push(keyphrase);
+
+  // Retrieve the anchors.
+  let anchors = paper.getTree().findAll(treeNode => treeNode.name === 'a');
+  /*
+   * We get the site's URL (e.g., https://yoast.com) or domain (e.g., yoast.com) from the paper.
+   * In case of WordPress, the variable is a URL. In case of Shopify, it is a domain.
+   */
+  const siteUrlOrDomain = paper.getPermalink();
+
+  // STEP 3.
+  // Get the anchors with urls that are not linking to the current site url/domain.
+  anchors = getAnchorsLinkingToSelf(anchors, siteUrlOrDomain);
+  // If all anchor urls are linking to the current site url/domain, return empty result.
+  if (anchors.length === 0) {
+    return result;
+  }
+  const locale = paper.getLocale();
+  const topicForms = researcher.getResearch('morphology');
+
+  // Auto-detect Chinese and enhance helper if needed
+  const text = paper.getText();
+  const enhancedMatchHelper = (0, _chineseHelperFactory.getMatchHelper)(text, keyphrase, researcher.getHelper('matchWordCustomHelper'));
+  const customHelpers = {
+    matchWordCustomHelper: enhancedMatchHelper,
+    getWordsCustomHelper: researcher.getHelper('getWordsCustomHelper')
+  };
+
+  // STEP 4.
+  // Get the anchors with text that contains the keyphrase/synonyms' content words.
+  anchors = getAnchorsContainingTopic(anchors, topicForms, locale, customHelpers.matchWordCustomHelper);
+  // If all anchor texts do not contain the keyphrase/synonyms' content words, return empty result.
+  if (anchors.length === 0) {
+    return result;
+  }
+
+  // STEP 5.
+  // Check if exact match is requested for every topic (keyphrase or synonym).
+  const isExactMatchRequested = originalTopics.map(originalTopic => (0, _processExactMatchRequest.default)(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 {
+    anchorsWithKeyphrase: anchors,
+    anchorsWithKeyphraseCount: anchors.length
+  };
+}
+//# sourceMappingURL=getAnchorsWithKeyphrase.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"getAnchorsWithKeyphrase.js","names":["_lodash","require","_filterWordsFromArray","_interopRequireDefault","_findKeywordFormsInString","_getWords","_matchTextWithArray","_parseSynonyms","_processExactMatchRequest","_url","_wordBoundariesWithoutPunctuation","_chineseHelperFactory","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","text","enhancedMatchHelper","getMatchHelper","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 {\n  WORD_BOUNDARY_WITH_HYPHEN,\n  WORD_BOUNDARY_WITHOUT_HYPHEN\n} from '../../config/wordBoundariesWithoutPunctuation';\nimport {getMatchHelper} from '../helpers/language/chineseHelperFactory.js';\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  return Boolean(\n    urlHelper.areEqual(anchorLink, siteUrlOrDomain) || urlHelper.isRelativeFragmentURL(anchorLink)\n  );\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  const anchorsLinkingToSelf = anchors.map(function(anchor) {\n    const anchorLink = anchor.attributes.href;\n    // Return false if there is no href attribute.\n    return anchorLink ? isLinkingToSelf(anchorLink, siteUrlOrDomain) : false;\n  });\n\n  return 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  const anchorsContainingTopic = anchors.map(function(anchor) {\n    // Only retrieve the anchor's text. This is because we only use the anchor text for the following check.\n    const anchorText = anchor.innerText();\n    return (\n      findTopicFormsInString(topicForms, anchorText, true, locale, matchWordCustomHelper)\n        .percentWordMatches === 100\n    );\n  });\n\n  return 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(\n  anchors,\n  topicForms,\n  locale,\n  customHelpers,\n  exactMatchRequest,\n  areHyphensWordBoundaries\n) {\n  const matchWordCustomHelper = customHelpers.matchWordCustomHelper;\n  const getWordsCustomHelper = customHelpers.getWordsCustomHelper;\n\n  // Prepare keyphrase and synonym forms for comparison with anchors.\n  const keyphraseAndSynonymsWords = [flatten(topicForms.keyphraseForms)];\n  const synonymsForms = topicForms.synonymsForms;\n  synonymsForms.forEach(form => keyphraseAndSynonymsWords.push(flatten(form)));\n\n  // The variable that will save all the anchors with text that has the same content words as the keyphrase/synonyms.\n  const anchorsContainedInTopic = [];\n\n  anchors.forEach(function(currentAnchor) {\n    const currentAnchorText = currentAnchor.innerText();\n\n    /*\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    let anchorWords;\n    if (getWordsCustomHelper) {\n      anchorWords = uniq(getWordsCustomHelper(currentAnchorText));\n    } else if (areHyphensWordBoundaries) {\n      anchorWords = uniq(getWords(currentAnchorText, WORD_BOUNDARY_WITH_HYPHEN));\n    } else {\n      anchorWords = uniq(getWords(currentAnchorText, WORD_BOUNDARY_WITHOUT_HYPHEN));\n    }\n\n    /*\n     * Filter function words out of the anchor text.\n     * If the anchor text contains only function words, we keep them.\n     */\n    const filteredAnchorWords = filterWordsFromArray(anchorWords, functionWords);\n    if (filteredAnchorWords.length > 0) {\n      anchorWords = filteredAnchorWords;\n    }\n\n    exactMatchRequest.forEach(request => {\n      /*\n       * Check a) if the exact match is requested for the keyphrase, and\n       * b) if every content word in the anchor text is included in the keyphrase or synonym.\n       */\n      if (\n        request.exactMatchRequested &&\n        anchorWords.every(anchorWord => request.keyphrase.includes(anchorWord))\n      ) {\n        anchorsContainedInTopic.push(true);\n      }\n    });\n\n    // Check if every word in the anchor text is also present in the keyphrase/synonym.\n    for (let i = 0; i < keyphraseAndSynonymsWords.length; i++) {\n      const topicForm = keyphraseAndSynonymsWords[i];\n\n      if (\n        anchorWords.every(\n          anchorWord =>\n            matchTextWithArray(anchorWord, topicForm, locale, matchWordCustomHelper).count > 0\n        )\n      ) {\n        anchorsContainedInTopic.push(true);\n        break;\n      }\n    }\n  });\n\n  return 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  functionWords = researcher.getConfig('functionWords');\n\n  const areHyphensWordBoundaries = researcher.getConfig('areHyphensWordBoundaries');\n\n  const result = {\n    anchorsWithKeyphrase: [],\n    anchorsWithKeyphraseCount: 0\n  };\n  // STEP 1.\n  // If the paper's text is empty, return empty result.\n  if (paper.getText() === '') {\n    return result;\n  }\n\n  // STEP 2.\n  const keyphrase = paper.getKeyword();\n  /*\n   * If no keyphrase is set, return empty result.\n   * This is a conscious decision where we won't assess the paper if the keyphrase is not set.\n   * This includes a case where only the synonym is set but not the keyphrase.\n   */\n  if (keyphrase === '') {\n    return result;\n  }\n  /*\n   * When the keyphrase is set, also retrieve the synonyms and save them in \"topics\" array.\n   * Eventually, the term topics here refers to either keyphrase or synonyms.\n   */\n  const originalTopics = parseSynonyms(paper.getSynonyms());\n  originalTopics.push(keyphrase);\n\n  // Retrieve the anchors.\n  let anchors = paper.getTree().findAll(treeNode => treeNode.name === 'a');\n  /*\n   * We get the site's URL (e.g., https://yoast.com) or domain (e.g., yoast.com) from the paper.\n   * In case of WordPress, the variable is a URL. In case of Shopify, it is a domain.\n   */\n  const siteUrlOrDomain = paper.getPermalink();\n\n  // STEP 3.\n  // Get the anchors with urls that are not linking to the current site url/domain.\n  anchors = getAnchorsLinkingToSelf(anchors, siteUrlOrDomain);\n  // If all anchor urls are linking to the current site url/domain, return empty result.\n  if (anchors.length === 0) {\n    return result;\n  }\n\n  const locale = paper.getLocale();\n  const topicForms = researcher.getResearch('morphology');\n\n  // Auto-detect Chinese and enhance helper if needed\n  const text = paper.getText();\n  const enhancedMatchHelper = getMatchHelper(\n    text,\n    keyphrase,\n    researcher.getHelper('matchWordCustomHelper')\n  );\n\n  const customHelpers = {\n    matchWordCustomHelper: enhancedMatchHelper,\n    getWordsCustomHelper: researcher.getHelper('getWordsCustomHelper')\n  };\n\n  // STEP 4.\n  // Get the anchors with text that contains the keyphrase/synonyms' content words.\n  anchors = getAnchorsContainingTopic(\n    anchors,\n    topicForms,\n    locale,\n    customHelpers.matchWordCustomHelper\n  );\n  // If all anchor texts do not contain the keyphrase/synonyms' content words, return empty result.\n  if (anchors.length === 0) {\n    return result;\n  }\n\n  // STEP 5.\n  // Check if exact match is requested for every topic (keyphrase or synonym).\n  const isExactMatchRequested = originalTopics.map(originalTopic =>\n    processExactMatchRequest(originalTopic)\n  );\n  // Get the anchors with text that has the same content words as the keyphrase/synonyms.\n  anchors = getAnchorsWithSameTextAsTopic(\n    anchors,\n    topicForms,\n    locale,\n    customHelpers,\n    isExactMatchRequested,\n    areHyphensWordBoundaries\n  );\n\n  return {\n    anchorsWithKeyphrase: anchors,\n    anchorsWithKeyphraseCount: anchors.length\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;AAIA,IAAAU,qBAAA,GAAAV,OAAA;AAA2E,SAAAE,uBAAAS,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAE3E,IAAIG,aAAa,GAAG,EAAE;;AAEtB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,eAAeA,CAACC,UAAU,EAAEC,eAAe,EAAE;EACpD,OAAOC,OAAO,CACZC,YAAS,CAACC,QAAQ,CAACJ,UAAU,EAAEC,eAAe,CAAC,IAAIE,YAAS,CAACE,qBAAqB,CAACL,UAAU,CAC/F,CAAC;AACH;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASM,uBAAuBA,CAACC,OAAO,EAAEN,eAAe,EAAE;EACzD,MAAMO,oBAAoB,GAAGD,OAAO,CAACE,GAAG,CAAC,UAASC,MAAM,EAAE;IACxD,MAAMV,UAAU,GAAGU,MAAM,CAACC,UAAU,CAACC,IAAI;IACzC;IACA,OAAOZ,UAAU,GAAGD,eAAe,CAACC,UAAU,EAAEC,eAAe,CAAC,GAAG,KAAK;EAC1E,CAAC,CAAC;EAEF,OAAOM,OAAO,CAACM,MAAM,CAAC,CAACH,MAAM,EAAEI,KAAK,KAAK,CAACN,oBAAoB,CAACM,KAAK,CAAC,CAAC;AACxE;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,yBAAyBA,CAACR,OAAO,EAAES,UAAU,EAAEC,MAAM,EAAEC,qBAAqB,EAAE;EACrF,MAAMC,sBAAsB,GAAGZ,OAAO,CAACE,GAAG,CAAC,UAASC,MAAM,EAAE;IAC1D;IACA,MAAMU,UAAU,GAAGV,MAAM,CAACW,SAAS,CAAC,CAAC;IACrC,OACE,IAAAC,gDAAsB,EAACN,UAAU,EAAEI,UAAU,EAAE,IAAI,EAAEH,MAAM,EAAEC,qBAAqB,CAAC,CAChFK,kBAAkB,KAAK,GAAG;EAEjC,CAAC,CAAC;EAEF,OAAOhB,OAAO,CAACM,MAAM,CAAC,CAACH,MAAM,EAAEI,KAAK,KAAKK,sBAAsB,CAACL,KAAK,CAAC,CAAC;AACzE;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASU,6BAA6BA,CACpCjB,OAAO,EACPS,UAAU,EACVC,MAAM,EACNQ,aAAa,EACbC,iBAAiB,EACjBC,wBAAwB,EACxB;EACA,MAAMT,qBAAqB,GAAGO,aAAa,CAACP,qBAAqB;EACjE,MAAMU,oBAAoB,GAAGH,aAAa,CAACG,oBAAoB;;EAE/D;EACA,MAAMC,yBAAyB,GAAG,CAAC,IAAAC,eAAO,EAACd,UAAU,CAACe,cAAc,CAAC,CAAC;EACtE,MAAMC,aAAa,GAAGhB,UAAU,CAACgB,aAAa;EAC9CA,aAAa,CAACC,OAAO,CAACC,IAAI,IAAIL,yBAAyB,CAACM,IAAI,CAAC,IAAAL,eAAO,EAACI,IAAI,CAAC,CAAC,CAAC;;EAE5E;EACA,MAAME,uBAAuB,GAAG,EAAE;EAElC7B,OAAO,CAAC0B,OAAO,CAAC,UAASI,aAAa,EAAE;IACtC,MAAMC,iBAAiB,GAAGD,aAAa,CAAChB,SAAS,CAAC,CAAC;;IAEnD;AACJ;AACA;AACA;AACA;AACA;AACA;AACA;AACA;IACI,IAAIkB,WAAW;IACf,IAAIX,oBAAoB,EAAE;MACxBW,WAAW,GAAG,IAAAC,YAAI,EAACZ,oBAAoB,CAACU,iBAAiB,CAAC,CAAC;IAC7D,CAAC,MAAM,IAAIX,wBAAwB,EAAE;MACnCY,WAAW,GAAG,IAAAC,YAAI,EAAC,IAAAC,iBAAQ,EAACH,iBAAiB,EAAEI,2DAAyB,CAAC,CAAC;IAC5E,CAAC,MAAM;MACLH,WAAW,GAAG,IAAAC,YAAI,EAAC,IAAAC,iBAAQ,EAACH,iBAAiB,EAAEK,8DAA4B,CAAC,CAAC;IAC/E;;IAEA;AACJ;AACA;AACA;IACI,MAAMC,mBAAmB,GAAG,IAAAC,6BAAoB,EAACN,WAAW,EAAEzC,aAAa,CAAC;IAC5E,IAAI8C,mBAAmB,CAACE,MAAM,GAAG,CAAC,EAAE;MAClCP,WAAW,GAAGK,mBAAmB;IACnC;IAEAlB,iBAAiB,CAACO,OAAO,CAACc,OAAO,IAAI;MACnC;AACN;AACA;AACA;MACM,IACEA,OAAO,CAACC,mBAAmB,IAC3BT,WAAW,CAACU,KAAK,CAACC,UAAU,IAAIH,OAAO,CAACI,SAAS,CAACC,QAAQ,CAACF,UAAU,CAAC,CAAC,EACvE;QACAd,uBAAuB,CAACD,IAAI,CAAC,IAAI,CAAC;MACpC;IACF,CAAC,CAAC;;IAEF;IACA,KAAK,IAAIkB,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGxB,yBAAyB,CAACiB,MAAM,EAAEO,CAAC,EAAE,EAAE;MACzD,MAAMC,SAAS,GAAGzB,yBAAyB,CAACwB,CAAC,CAAC;MAE9C,IACEd,WAAW,CAACU,KAAK,CACfC,UAAU,IACR,IAAAK,2BAAkB,EAACL,UAAU,EAAEI,SAAS,EAAErC,MAAM,EAAEC,qBAAqB,CAAC,CAACsC,KAAK,GAAG,CACrF,CAAC,EACD;QACApB,uBAAuB,CAACD,IAAI,CAAC,IAAI,CAAC;QAClC;MACF;IACF;EACF,CAAC,CAAC;EAEF,OAAO5B,OAAO,CAACM,MAAM,CAAC,CAACH,MAAM,EAAEI,KAAK,KAAKsB,uBAAuB,CAACtB,KAAK,CAAC,CAAC;AAC1E;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAA2C,SAASC,KAAK,EAAEC,UAAU,EAAE;EACzC7D,aAAa,GAAG6D,UAAU,CAACC,SAAS,CAAC,eAAe,CAAC;EAErD,MAAMjC,wBAAwB,GAAGgC,UAAU,CAACC,SAAS,CAAC,0BAA0B,CAAC;EAEjF,MAAMC,MAAM,GAAG;IACbC,oBAAoB,EAAE,EAAE;IACxBC,yBAAyB,EAAE;EAC7B,CAAC;EACD;EACA;EACA,IAAIL,KAAK,CAACM,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE;IAC1B,OAAOH,MAAM;EACf;;EAEA;EACA,MAAMV,SAAS,GAAGO,KAAK,CAACO,UAAU,CAAC,CAAC;EACpC;AACF;AACA;AACA;AACA;EACE,IAAId,SAAS,KAAK,EAAE,EAAE;IACpB,OAAOU,MAAM;EACf;EACA;AACF;AACA;AACA;EACE,MAAMK,cAAc,GAAG,IAAAC,sBAAa,EAACT,KAAK,CAACU,WAAW,CAAC,CAAC,CAAC;EACzDF,cAAc,CAAC/B,IAAI,CAACgB,SAAS,CAAC;;EAE9B;EACA,IAAI5C,OAAO,GAAGmD,KAAK,CAACW,OAAO,CAAC,CAAC,CAACC,OAAO,CAACC,QAAQ,IAAIA,QAAQ,CAACC,IAAI,KAAK,GAAG,CAAC;EACxE;AACF;AACA;AACA;EACE,MAAMvE,eAAe,GAAGyD,KAAK,CAACe,YAAY,CAAC,CAAC;;EAE5C;EACA;EACAlE,OAAO,GAAGD,uBAAuB,CAACC,OAAO,EAAEN,eAAe,CAAC;EAC3D;EACA,IAAIM,OAAO,CAACuC,MAAM,KAAK,CAAC,EAAE;IACxB,OAAOe,MAAM;EACf;EAEA,MAAM5C,MAAM,GAAGyC,KAAK,CAACgB,SAAS,CAAC,CAAC;EAChC,MAAM1D,UAAU,GAAG2C,UAAU,CAACgB,WAAW,CAAC,YAAY,CAAC;;EAEvD;EACA,MAAMC,IAAI,GAAGlB,KAAK,CAACM,OAAO,CAAC,CAAC;EAC5B,MAAMa,mBAAmB,GAAG,IAAAC,oCAAc,EACxCF,IAAI,EACJzB,SAAS,EACTQ,UAAU,CAACoB,SAAS,CAAC,uBAAuB,CAC9C,CAAC;EAED,MAAMtD,aAAa,GAAG;IACpBP,qBAAqB,EAAE2D,mBAAmB;IAC1CjD,oBAAoB,EAAE+B,UAAU,CAACoB,SAAS,CAAC,sBAAsB;EACnE,CAAC;;EAED;EACA;EACAxE,OAAO,GAAGQ,yBAAyB,CACjCR,OAAO,EACPS,UAAU,EACVC,MAAM,EACNQ,aAAa,CAACP,qBAChB,CAAC;EACD;EACA,IAAIX,OAAO,CAACuC,MAAM,KAAK,CAAC,EAAE;IACxB,OAAOe,MAAM;EACf;;EAEA;EACA;EACA,MAAMmB,qBAAqB,GAAGd,cAAc,CAACzD,GAAG,CAACwE,aAAa,IAC5D,IAAAC,iCAAwB,EAACD,aAAa,CACxC,CAAC;EACD;EACA1E,OAAO,GAAGiB,6BAA6B,CACrCjB,OAAO,EACPS,UAAU,EACVC,MAAM,EACNQ,aAAa,EACbuD,qBAAqB,EACrBrD,wBACF,CAAC;EAED,OAAO;IACLmC,oBAAoB,EAAEvD,OAAO;IAC7BwD,yBAAyB,EAAExD,OAAO,CAACuC;EACrC,CAAC;AACH","ignoreList":[]}

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

@@ -0,0 +1,152 @@
+"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 */
+
+/**
+ * Calculates an average from a total and an amount
+ *
+ * @param {number} total The total.
+ * @param {number} amount The amount.
+ * @returns {number} The average from the total and the amount.
+ */
+const getAverage = function (total, amount) {
+  return total / amount;
+};
+
+/**
+ * The Flesch reading ease difficulty.
+ * @readonly
+ * @enum {number}
+ */
+const DIFFICULTY = exports.DIFFICULTY = {
+  NO_DATA: -1,
+  VERY_EASY: 0,
+  EASY: 1,
+  FAIRLY_EASY: 2,
+  OKAY: 3,
+  FAIRLY_DIFFICULT: 4,
+  DIFFICULT: 5,
+  VERY_DIFFICULT: 6
+};
+
+/**
+ * Returns the Flesch reading ease difficulty based on the boundaries
+ * defined in the score configuration.
+ *
+ * @param {number} score The Flesch reading ease score.
+ * @param {Object} scoreConfiguration The score configuration.
+ *
+ * @returns {DIFFICULTY} The Flesch reading ease 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)) {
+    return DIFFICULTY.EASY;
+  } else if ((0, _lodash.inRange)(score, scoreConfiguration.borders.fairlyEasy, scoreConfiguration.borders.easy)) {
+    return DIFFICULTY.FAIRLY_EASY;
+  } else if ((0, _lodash.inRange)(score, scoreConfiguration.borders.okay, scoreConfiguration.borders.fairlyEasy)) {
+    return DIFFICULTY.OKAY;
+  } else if ((0, _lodash.inRange)(score, scoreConfiguration.borders.fairlyDifficult, scoreConfiguration.borders.okay)) {
+    return DIFFICULTY.FAIRLY_DIFFICULT;
+  } else if ((0, _lodash.inRange)(score, scoreConfiguration.borders.difficult, scoreConfiguration.borders.fairlyDifficult)) {
+    return DIFFICULTY.DIFFICULT;
+  }
+  return DIFFICULTY.VERY_DIFFICULT;
+}
+
+/**
+ * Retrieves the scoring configuration defining the boundaries to use to
+ * determine the Flesch reading ease difficulty.
+ *
+ * @param {Researcher} researcher The researcher.
+ *
+ * @returns {Object} The language specific scoring configuration, or the default configuration if not available.
+ */
+function getConfiguration(researcher) {
+  const languageSpecificConfig = researcher.getConfig("fleschReadingEaseScores");
+  const defaultConfig = {
+    borders: {
+      veryEasy: 90,
+      easy: 80,
+      fairlyEasy: 70,
+      okay: 60,
+      fairlyDifficult: 50,
+      difficult: 30,
+      veryDifficult: 0
+    },
+    scores: {
+      veryEasy: 9,
+      easy: 9,
+      fairlyEasy: 9,
+      okay: 9,
+      fairlyDifficult: 6,
+      difficult: 3,
+      veryDifficult: 3
+    }
+  };
+  return languageSpecificConfig ? languageSpecificConfig : defaultConfig;
+}
+
+/**
+ * This calculates the Flesch reading score for a given text.
+ *
+ * @param {Paper}       paper           The paper containing the text.
+ * @param {Researcher}  researcher      The researcher.
+ *
+ * @returns {{ score: number, difficulty: DIFFICULTY }} The Flesch reading score.
+ */
+function _default(paper, researcher) {
+  const syllables = researcher.getConfig("syllables");
+  const memoizedTokenizer = researcher.getHelper("memoizedTokenizer");
+  const languageSpecificConfiguration = getConfiguration(researcher);
+  let text = paper.getText();
+  if (text === "") {
+    // A score of -1 signals to the code down the line that no valid FRE was calculated.
+    return {
+      score: -1,
+      difficulty: DIFFICULTY.NO_DATA
+    };
+  }
+  text = (0, _stripNumbers.default)(text);
+  const numberOfSentences = (0, _countSentences.default)(text, memoizedTokenizer);
+  const numberOfWords = (0, _countWords.default)(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.
+  if (numberOfSentences < 1 || numberOfWords <= 10) {
+    return {
+      score: -1,
+      difficulty: DIFFICULTY.NO_DATA
+    };
+  }
+  const numberOfSyllables = (0, _countSyllables.default)(text, syllables);
+  const averageWordsPerSentence = getAverage(numberOfWords, numberOfSentences);
+  const syllablesPer100Words = numberOfSyllables * (100 / numberOfWords);
+  const statistics = {
+    numberOfSentences,
+    numberOfWords,
+    numberOfSyllables,
+    averageWordsPerSentence,
+    syllablesPer100Words
+  };
+  const getScore = researcher.getHelper("fleschReadingScore");
+  const score = (0, _lodash.clamp)(getScore(statistics), 0, 100);
+  const difficulty = getDifficulty(score, languageSpecificConfiguration);
+  return {
+    score,
+    difficulty
+  };
+}
+//# sourceMappingURL=getFleschReadingScore.js.map