axyseo 2.0.0-alpha.0.0.2 → 2.0.0-alpha.0.0.21

package/build/languageProcessing/researches/keywordCount.js

@@ -0,0 +1,135 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.countKeyphraseInText = countKeyphraseInText;
+exports.default = getKeyphraseCount;
+exports.keywordCount = keywordCount;
+var _lodash = require("lodash");
+var _getSentencesFromTree = _interopRequireDefault(require("../helpers/sentence/getSentencesFromTree"));
+var _quotes = require("../helpers/sanitize/quotes");
+var _getMarkingsInSentence = _interopRequireDefault(require("../helpers/highlighting/getMarkingsInSentence"));
+var _matchWordFormsWithSentence = _interopRequireDefault(require("../helpers/match/matchWordFormsWithSentence"));
+var _isDoubleQuoted = _interopRequireDefault(require("../helpers/match/isDoubleQuoted"));
+var _markWordsInSentences = require("../helpers/word/markWordsInSentences");
+var _getSentences = _interopRequireDefault(require("../helpers/sentence/getSentences"));
+var _helpers = require("../helpers");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Counts the occurrences of the keyphrase in the text and creates the Mark objects for the matches.
+ *
+ * @param {(Sentence|string)[]}	sentences			The sentences to check.
+ * @param {Array}		keyphraseForms				The keyphrase forms.
+ * @param {string}		locale						The locale used in the analysis.
+ * @param {function}	matchWordCustomHelper		A custom helper to match words with a text.
+ * @param {boolean}		isExactMatchRequested		Whether the exact matching is requested.
+ * @param {function}	customSplitIntoTokensHelper	A custom helper to split sentences into tokens.
+ *
+ * @returns {{markings: Mark[], count: number}} The number of keyphrase occurrences in the text and the Mark objects of the matches.
+ */
+function countKeyphraseInText(sentences, keyphraseForms, locale, matchWordCustomHelper, isExactMatchRequested, customSplitIntoTokensHelper) {
+  const result = {
+    count: 0,
+    markings: []
+  };
+  sentences.forEach(sentence => {
+    const matchesInSentence = keyphraseForms.map(wordForms => (0, _matchWordFormsWithSentence.default)(sentence, wordForms, locale, matchWordCustomHelper, isExactMatchRequested, customSplitIntoTokensHelper));
+
+    // A sentence has at least one full-match of the keyphrase if each word occurs at least once.
+    const isEachWordFound = matchesInSentence.every(wordForms => wordForms.count > 0);
+    if (isEachWordFound) {
+      /*
+       * Retrieve all the occurrences' count of each word of the keyphrase and save it in an array.
+       * matches: [ [ { matches: ["red"], count: 1 } ], [ { matches: ["pandas"], count: 2 } ] ]
+       * counts: [ 1, 2 ]
+       */
+      const counts = matchesInSentence.map(match => match.count);
+      /*
+       * The number of the full-match count is the lowest count of the occurrences.
+       * counts: [ 1, 2 ]
+       * totalMatchCount: 1
+       *
+       * From the example above, the full-match is 1, because one of the "pandas" occurrences is not accompanied by "red"
+       * to be counted as a full-match.
+       */
+      const totalMatchCount = Math.min(...counts);
+      const foundWords = (0, _lodash.flattenDeep)(matchesInSentence.map(match => match.matches));
+      let markings = [];
+      if (matchWordCustomHelper) {
+        // Currently, this check is only applicable for Japanese.
+        markings = (0, _markWordsInSentences.markWordsInASentence)(sentence, foundWords, matchWordCustomHelper);
+      } else {
+        markings = (0, _getMarkingsInSentence.default)(sentence, foundWords);
+      }
+      result.count += totalMatchCount;
+      result.markings.push(markings);
+    }
+  });
+  return result;
+}
+
+/**
+ * Calculates the keyphrase count, takes morphology into account.
+ *
+ * @param {Paper}       paper       The paper containing keyphrase and text.
+ * @param {Researcher}  researcher  The researcher.
+ *
+ * @returns {{count: number, markings: Mark[], keyphraseLength: number}} An object containing the keyphrase count, markings and the kephrase length.
+ */
+function getKeyphraseCount(paper, researcher) {
+  const result = {
+    count: 0,
+    markings: [],
+    keyphraseLength: 0
+  };
+  const topicForms = researcher.getResearch("morphology");
+  let keyphraseForms = topicForms.keyphraseForms;
+  const keyphraseLength = keyphraseForms.length;
+
+  /*
+   * Normalize single quotes so that word form with different type of single quotes can still be matched.
+   * For example, "key‛word" should match "key'word".
+   */
+  keyphraseForms = keyphraseForms.map(word => word.map(form => (0, _quotes.normalizeSingle)(form)));
+  if (keyphraseLength === 0) {
+    return result;
+  }
+  const matchWordCustomHelper = researcher.getHelper("matchWordCustomHelper");
+  const customSentenceTokenizer = researcher.getHelper("memoizedTokenizer");
+  const customSplitIntoTokensHelper = researcher.getHelper("splitIntoTokensCustom");
+  const locale = paper.getLocale();
+  const text = matchWordCustomHelper ? (0, _helpers.filterShortcodesFromHTML)(paper.getText(), paper._attributes && paper._attributes.shortcodes) : paper.getText();
+
+  // When the custom helper is available, we're using the sentences retrieved from the text for the analysis.
+  const sentences = matchWordCustomHelper ? (0, _getSentences.default)(text, customSentenceTokenizer) : (0, _getSentencesFromTree.default)(paper);
+  // Exact matching is requested when the keyphrase is enclosed in double quotes.
+  const isExactMatchRequested = (0, _isDoubleQuoted.default)(paper.getKeyword());
+
+  /*
+  * Count the amount of keyphrase occurrences in the sentences.
+  * An occurrence is counted when all words of the keyphrase are contained within the sentence. Each sentence can contain multiple keyphrases.
+  * (e.g. "The apple potato is an apple and a potato." has two occurrences of the keyphrase "apple potato").
+  */
+  const keyphraseFound = countKeyphraseInText(sentences, keyphraseForms, locale, matchWordCustomHelper, isExactMatchRequested, customSplitIntoTokensHelper);
+  result.count = keyphraseFound.count;
+  result.markings = (0, _lodash.flatten)(keyphraseFound.markings);
+  result.keyphraseLength = keyphraseLength;
+  return result;
+}
+
+/**
+ * Calculates the keyphrase count, takes morphology into account.
+ *
+ * @deprecated Use getKeyphraseCount instead.
+ *
+ * @param {Paper}       paper       The paper containing keyphrase and text.
+ * @param {Researcher}  researcher  The researcher.
+ *
+ * @returns {Object} An array of all the matches, markings and the keyphrase count.
+ */
+function keywordCount(paper, researcher) {
+  console.warn("This function is deprecated, use getKeyphraseCount instead.");
+  return getKeyphraseCount(paper, researcher);
+}
+//# sourceMappingURL=keywordCount.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"keywordCount.js","names":["_lodash","require","_getSentencesFromTree","_interopRequireDefault","_quotes","_getMarkingsInSentence","_matchWordFormsWithSentence","_isDoubleQuoted","_markWordsInSentences","_getSentences","_helpers","e","__esModule","default","countKeyphraseInText","sentences","keyphraseForms","locale","matchWordCustomHelper","isExactMatchRequested","customSplitIntoTokensHelper","result","count","markings","forEach","sentence","matchesInSentence","map","wordForms","matchWordFormsWithSentence","isEachWordFound","every","counts","match","totalMatchCount","Math","min","foundWords","flattenDeep","matches","markWordsInASentence","getMarkingsInSentence","push","getKeyphraseCount","paper","researcher","keyphraseLength","topicForms","getResearch","length","word","form","normalizeSingle","getHelper","customSentenceTokenizer","getLocale","text","filterShortcodesFromHTML","getText","_attributes","shortcodes","getSentences","getSentencesFromTree","isDoubleQuoted","getKeyword","keyphraseFound","flatten","keywordCount","console","warn"],"sources":["../../../src/languageProcessing/researches/keywordCount.js"],"sourcesContent":["import { flatten, flattenDeep } from \"lodash\";\nimport getSentencesFromTree from \"../helpers/sentence/getSentencesFromTree\";\nimport { normalizeSingle } from \"../helpers/sanitize/quotes\";\nimport getMarkingsInSentence from \"../helpers/highlighting/getMarkingsInSentence\";\nimport matchWordFormsWithSentence from \"../helpers/match/matchWordFormsWithSentence\";\nimport isDoubleQuoted from \"../helpers/match/isDoubleQuoted\";\nimport { markWordsInASentence } from \"../helpers/word/markWordsInSentences\";\nimport getSentences from \"../helpers/sentence/getSentences\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\n\n/**\n * Counts the occurrences of the keyphrase in the text and creates the Mark objects for the matches.\n *\n * @param {(Sentence|string)[]}\tsentences\t\t\tThe sentences to check.\n * @param {Array}\t\tkeyphraseForms\t\t\t\tThe keyphrase forms.\n * @param {string}\t\tlocale\t\t\t\t\t\tThe locale used in the analysis.\n * @param {function}\tmatchWordCustomHelper\t\tA custom helper to match words with a text.\n * @param {boolean}\t\tisExactMatchRequested\t\tWhether the exact matching is requested.\n * @param {function}\tcustomSplitIntoTokensHelper\tA custom helper to split sentences into tokens.\n *\n * @returns {{markings: Mark[], count: number}} The number of keyphrase occurrences in the text and the Mark objects of the matches.\n */\nexport function countKeyphraseInText( sentences, keyphraseForms, locale, matchWordCustomHelper,\n\t\t\t\t\t\t\t\t\t  isExactMatchRequested, customSplitIntoTokensHelper ) {\n\tconst result = { count: 0, markings: [] };\n\n\tsentences.forEach( sentence => {\n\t\tconst matchesInSentence = keyphraseForms.map( wordForms => matchWordFormsWithSentence( sentence,\n\t\t\twordForms, locale, matchWordCustomHelper, isExactMatchRequested, customSplitIntoTokensHelper ) );\n\n\t\t// A sentence has at least one full-match of the keyphrase if each word occurs at least once.\n\t\tconst isEachWordFound = matchesInSentence.every( wordForms => wordForms.count > 0 );\n\n\t\tif ( isEachWordFound ) {\n\t\t\t/*\n\t\t\t * Retrieve all the occurrences' count of each word of the keyphrase and save it in an array.\n\t\t\t * matches: [ [ { matches: [\"red\"], count: 1 } ], [ { matches: [\"pandas\"], count: 2 } ] ]\n\t\t\t * counts: [ 1, 2 ]\n\t\t\t */\n\t\t\tconst counts = matchesInSentence.map( match => match.count );\n\t\t\t/*\n\t\t\t * The number of the full-match count is the lowest count of the occurrences.\n\t\t\t * counts: [ 1, 2 ]\n\t\t\t * totalMatchCount: 1\n\t\t\t *\n\t\t\t * From the example above, the full-match is 1, because one of the \"pandas\" occurrences is not accompanied by \"red\"\n\t\t\t * to be counted as a full-match.\n\t\t\t */\n\t\t\tconst totalMatchCount = Math.min( ...counts );\n\t\t\tconst foundWords = flattenDeep( matchesInSentence.map( match => match.matches ) );\n\n\t\t\tlet markings = [];\n\n\t\t\tif ( matchWordCustomHelper ) {\n\t\t\t\t// Currently, this check is only applicable for Japanese.\n\t\t\t\tmarkings = markWordsInASentence( sentence, foundWords, matchWordCustomHelper );\n\t\t\t} else {\n\t\t\t\tmarkings = getMarkingsInSentence( sentence, foundWords );\n\t\t\t}\n\n\t\t\tresult.count += totalMatchCount;\n\t\t\tresult.markings.push( markings );\n\t\t}\n\t} );\n\n\treturn result;\n}\n\n/**\n * Calculates the keyphrase count, takes morphology into account.\n *\n * @param {Paper}       paper       The paper containing keyphrase and text.\n * @param {Researcher}  researcher  The researcher.\n *\n * @returns {{count: number, markings: Mark[], keyphraseLength: number}} An object containing the keyphrase count, markings and the kephrase length.\n */\nexport default function getKeyphraseCount( paper, researcher ) {\n\tconst result = { count: 0, markings: [], keyphraseLength: 0 };\n\tconst topicForms = researcher.getResearch( \"morphology\" );\n\tlet keyphraseForms = topicForms.keyphraseForms;\n\tconst keyphraseLength = keyphraseForms.length;\n\n\t/*\n\t * Normalize single quotes so that word form with different type of single quotes can still be matched.\n\t * For example, \"key‛word\" should match \"key'word\".\n\t */\n\tkeyphraseForms = keyphraseForms.map( word => word.map( form => normalizeSingle( form ) ) );\n\n\tif ( keyphraseLength === 0 ) {\n\t\treturn result;\n\t}\n\n\tconst matchWordCustomHelper = researcher.getHelper( \"matchWordCustomHelper\" );\n\tconst customSentenceTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\tconst customSplitIntoTokensHelper = researcher.getHelper( \"splitIntoTokensCustom\" );\n\tconst locale = paper.getLocale();\n\tconst text = matchWordCustomHelper\n\t\t? filterShortcodesFromHTML( paper.getText(), paper._attributes && paper._attributes.shortcodes )\n\t\t: paper.getText();\n\n\t// When the custom helper is available, we're using the sentences retrieved from the text for the analysis.\n\tconst sentences = matchWordCustomHelper ? getSentences( text, customSentenceTokenizer ) : getSentencesFromTree( paper );\n\t// Exact matching is requested when the keyphrase is enclosed in double quotes.\n\tconst isExactMatchRequested = isDoubleQuoted( paper.getKeyword() );\n\n\t/*\n\t* Count the amount of keyphrase occurrences in the sentences.\n\t* An occurrence is counted when all words of the keyphrase are contained within the sentence. Each sentence can contain multiple keyphrases.\n\t* (e.g. \"The apple potato is an apple and a potato.\" has two occurrences of the keyphrase \"apple potato\").\n\t*/\n\tconst keyphraseFound = countKeyphraseInText( sentences, keyphraseForms, locale, matchWordCustomHelper,\n\t\tisExactMatchRequested, customSplitIntoTokensHelper );\n\n\tresult.count = keyphraseFound.count;\n\tresult.markings = flatten( keyphraseFound.markings );\n\tresult.keyphraseLength = keyphraseLength;\n\n\treturn result;\n}\n\n/**\n * Calculates the keyphrase count, takes morphology into account.\n *\n * @deprecated Use getKeyphraseCount instead.\n *\n * @param {Paper}       paper       The paper containing keyphrase and text.\n * @param {Researcher}  researcher  The researcher.\n *\n * @returns {Object} An array of all the matches, markings and the keyphrase count.\n */\nexport function keywordCount( paper, researcher ) {\n\tconsole.warn( \"This function is deprecated, use getKeyphraseCount instead.\" );\n\treturn getKeyphraseCount( paper, researcher );\n}\n"],"mappings":";;;;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AACA,IAAAC,qBAAA,GAAAC,sBAAA,CAAAF,OAAA;AACA,IAAAG,OAAA,GAAAH,OAAA;AACA,IAAAI,sBAAA,GAAAF,sBAAA,CAAAF,OAAA;AACA,IAAAK,2BAAA,GAAAH,sBAAA,CAAAF,OAAA;AACA,IAAAM,eAAA,GAAAJ,sBAAA,CAAAF,OAAA;AACA,IAAAO,qBAAA,GAAAP,OAAA;AACA,IAAAQ,aAAA,GAAAN,sBAAA,CAAAF,OAAA;AACA,IAAAS,QAAA,GAAAT,OAAA;AAAsD,SAAAE,uBAAAQ,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEtD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACO,SAASG,oBAAoBA,CAAEC,SAAS,EAAEC,cAAc,EAAEC,MAAM,EAAEC,qBAAqB,EACnFC,qBAAqB,EAAEC,2BAA2B,EAAG;EAC/D,MAAMC,MAAM,GAAG;IAAEC,KAAK,EAAE,CAAC;IAAEC,QAAQ,EAAE;EAAG,CAAC;EAEzCR,SAAS,CAACS,OAAO,CAAEC,QAAQ,IAAI;IAC9B,MAAMC,iBAAiB,GAAGV,cAAc,CAACW,GAAG,CAAEC,SAAS,IAAI,IAAAC,mCAA0B,EAAEJ,QAAQ,EAC9FG,SAAS,EAAEX,MAAM,EAAEC,qBAAqB,EAAEC,qBAAqB,EAAEC,2BAA4B,CAAE,CAAC;;IAEjG;IACA,MAAMU,eAAe,GAAGJ,iBAAiB,CAACK,KAAK,CAAEH,SAAS,IAAIA,SAAS,CAACN,KAAK,GAAG,CAAE,CAAC;IAEnF,IAAKQ,eAAe,EAAG;MACtB;AACH;AACA;AACA;AACA;MACG,MAAME,MAAM,GAAGN,iBAAiB,CAACC,GAAG,CAAEM,KAAK,IAAIA,KAAK,CAACX,KAAM,CAAC;MAC5D;AACH;AACA;AACA;AACA;AACA;AACA;AACA;MACG,MAAMY,eAAe,GAAGC,IAAI,CAACC,GAAG,CAAE,GAAGJ,MAAO,CAAC;MAC7C,MAAMK,UAAU,GAAG,IAAAC,mBAAW,EAAEZ,iBAAiB,CAACC,GAAG,CAAEM,KAAK,IAAIA,KAAK,CAACM,OAAQ,CAAE,CAAC;MAEjF,IAAIhB,QAAQ,GAAG,EAAE;MAEjB,IAAKL,qBAAqB,EAAG;QAC5B;QACAK,QAAQ,GAAG,IAAAiB,0CAAoB,EAAEf,QAAQ,EAAEY,UAAU,EAAEnB,qBAAsB,CAAC;MAC/E,CAAC,MAAM;QACNK,QAAQ,GAAG,IAAAkB,8BAAqB,EAAEhB,QAAQ,EAAEY,UAAW,CAAC;MACzD;MAEAhB,MAAM,CAACC,KAAK,IAAIY,eAAe;MAC/Bb,MAAM,CAACE,QAAQ,CAACmB,IAAI,CAAEnB,QAAS,CAAC;IACjC;EACD,CAAE,CAAC;EAEH,OAAOF,MAAM;AACd;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAASsB,iBAAiBA,CAAEC,KAAK,EAAEC,UAAU,EAAG;EAC9D,MAAMxB,MAAM,GAAG;IAAEC,KAAK,EAAE,CAAC;IAAEC,QAAQ,EAAE,EAAE;IAAEuB,eAAe,EAAE;EAAE,CAAC;EAC7D,MAAMC,UAAU,GAAGF,UAAU,CAACG,WAAW,CAAE,YAAa,CAAC;EACzD,IAAIhC,cAAc,GAAG+B,UAAU,CAAC/B,cAAc;EAC9C,MAAM8B,eAAe,GAAG9B,cAAc,CAACiC,MAAM;;EAE7C;AACD;AACA;AACA;EACCjC,cAAc,GAAGA,cAAc,CAACW,GAAG,CAAEuB,IAAI,IAAIA,IAAI,CAACvB,GAAG,CAAEwB,IAAI,IAAI,IAAAC,uBAAe,EAAED,IAAK,CAAE,CAAE,CAAC;EAE1F,IAAKL,eAAe,KAAK,CAAC,EAAG;IAC5B,OAAOzB,MAAM;EACd;EAEA,MAAMH,qBAAqB,GAAG2B,UAAU,CAACQ,SAAS,CAAE,uBAAwB,CAAC;EAC7E,MAAMC,uBAAuB,GAAGT,UAAU,CAACQ,SAAS,CAAE,mBAAoB,CAAC;EAC3E,MAAMjC,2BAA2B,GAAGyB,UAAU,CAACQ,SAAS,CAAE,uBAAwB,CAAC;EACnF,MAAMpC,MAAM,GAAG2B,KAAK,CAACW,SAAS,CAAC,CAAC;EAChC,MAAMC,IAAI,GAAGtC,qBAAqB,GAC/B,IAAAuC,iCAAwB,EAAEb,KAAK,CAACc,OAAO,CAAC,CAAC,EAAEd,KAAK,CAACe,WAAW,IAAIf,KAAK,CAACe,WAAW,CAACC,UAAW,CAAC,GAC9FhB,KAAK,CAACc,OAAO,CAAC,CAAC;;EAElB;EACA,MAAM3C,SAAS,GAAGG,qBAAqB,GAAG,IAAA2C,qBAAY,EAAEL,IAAI,EAAEF,uBAAwB,CAAC,GAAG,IAAAQ,6BAAoB,EAAElB,KAAM,CAAC;EACvH;EACA,MAAMzB,qBAAqB,GAAG,IAAA4C,uBAAc,EAAEnB,KAAK,CAACoB,UAAU,CAAC,CAAE,CAAC;;EAElE;AACD;AACA;AACA;AACA;EACC,MAAMC,cAAc,GAAGnD,oBAAoB,CAAEC,SAAS,EAAEC,cAAc,EAAEC,MAAM,EAAEC,qBAAqB,EACpGC,qBAAqB,EAAEC,2BAA4B,CAAC;EAErDC,MAAM,CAACC,KAAK,GAAG2C,cAAc,CAAC3C,KAAK;EACnCD,MAAM,CAACE,QAAQ,GAAG,IAAA2C,eAAO,EAAED,cAAc,CAAC1C,QAAS,CAAC;EACpDF,MAAM,CAACyB,eAAe,GAAGA,eAAe;EAExC,OAAOzB,MAAM;AACd;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACO,SAAS8C,YAAYA,CAAEvB,KAAK,EAAEC,UAAU,EAAG;EACjDuB,OAAO,CAACC,IAAI,CAAE,6DAA8D,CAAC;EAC7E,OAAO1B,iBAAiB,CAAEC,KAAK,EAAEC,UAAW,CAAC;AAC9C","ignoreList":[]}

package/build/languageProcessing/researches/keywordCountInUrl.js

@@ -0,0 +1,58 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+exports.keywordCountInSlug = keywordCountInSlug;
+exports.keywordCountInUrl = keywordCountInUrl;
+var _parseSlug = _interopRequireDefault(require("../helpers/url/parseSlug"));
+var _findKeywordFormsInString = require("../helpers/match/findKeywordFormsInString.js");
+var _lodash = require("lodash");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/** @module researches/keywordCountInSlug */
+
+/**
+ * Matches the keyword in the slug. Replaces all dashes and underscores with whitespaces and uses whitespace as word boundary.
+ *
+ * @param {Paper} paper the Paper object to use in this count.
+ * @param {Researcher} researcher The Researcher object containing all available researches.
+ *
+ * @returns {{keyphraseLength: int, percentWordMatches: int}} The length of the keyphrase and the percentage of keyphrase forms that has been found.
+ */
+function keywordCountInSlug(paper, researcher) {
+  /*
+   * We want to override the `areHyphensWordBoundaries` config value from the researcher so that it is `true` for all
+   * languages. This is because slugs usually use hyphens (or underscores) as word boundaries. So if only the slug is
+   * split on hyphens and not the keyphrase forms, some keyphrase forms won't be found in the slug.
+   */
+  const languageResearcher = (0, _lodash.cloneDeep)(researcher);
+  languageResearcher.addConfig("areHyphensWordBoundaries", true);
+  const topicForms = languageResearcher.getResearch("morphology");
+  const parsedSlug = (0, _parseSlug.default)(paper.getSlug());
+  const locale = paper.getLocale();
+  const keyphraseInSlug = (0, _findKeywordFormsInString.findTopicFormsInString)(topicForms, parsedSlug, false, locale, false);
+  return {
+    keyphraseLength: topicForms.keyphraseForms.length,
+    percentWordMatches: keyphraseInSlug.percentWordMatches
+  };
+}
+
+/**
+ * Matches the keyword in the slug.
+ * keywordCountInUrl was the previous name for keywordCountInSlug (hence the name of this file).
+ * We keep (and expose) this research for backwards compatibility.
+ *
+ * @deprecated Since version 18.7. Use keywordCountInSlug instead.
+ *
+ * @param {Paper} paper the Paper object to use in this count.
+ * @param {Researcher} researcher The Researcher object containing all available researches.
+ *
+ * @returns {{keyphraseLength: int, percentWordMatches: int}} The length of the keyphrase and the percentage of keyphrase forms that has been found.
+ */
+function keywordCountInUrl(paper, researcher) {
+  console.warn("This function is deprecated, use keywordCountInSlug instead.");
+  return keywordCountInSlug(paper, researcher);
+}
+var _default = exports.default = keywordCountInSlug;
+//# sourceMappingURL=keywordCountInUrl.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"keywordCountInUrl.js","names":["_parseSlug","_interopRequireDefault","require","_findKeywordFormsInString","_lodash","e","__esModule","default","keywordCountInSlug","paper","researcher","languageResearcher","cloneDeep","addConfig","topicForms","getResearch","parsedSlug","parseSlug","getSlug","locale","getLocale","keyphraseInSlug","findTopicFormsInString","keyphraseLength","keyphraseForms","length","percentWordMatches","keywordCountInUrl","console","warn","_default","exports"],"sources":["../../../src/languageProcessing/researches/keywordCountInUrl.js"],"sourcesContent":["/** @module researches/keywordCountInSlug */\nimport parseSlug from \"../helpers/url/parseSlug\";\nimport { findTopicFormsInString } from \"../helpers/match/findKeywordFormsInString.js\";\nimport { cloneDeep } from \"lodash\";\n\n/**\n * Matches the keyword in the slug. Replaces all dashes and underscores with whitespaces and uses whitespace as word boundary.\n *\n * @param {Paper} paper the Paper object to use in this count.\n * @param {Researcher} researcher The Researcher object containing all available researches.\n *\n * @returns {{keyphraseLength: int, percentWordMatches: int}} The length of the keyphrase and the percentage of keyphrase forms that has been found.\n */\nfunction keywordCountInSlug( paper, researcher ) {\n\t/*\n\t * We want to override the `areHyphensWordBoundaries` config value from the researcher so that it is `true` for all\n\t * languages. This is because slugs usually use hyphens (or underscores) as word boundaries. So if only the slug is\n\t * split on hyphens and not the keyphrase forms, some keyphrase forms won't be found in the slug.\n\t */\n\tconst languageResearcher = cloneDeep( researcher );\n\tlanguageResearcher.addConfig( \"areHyphensWordBoundaries\", true );\n\tconst topicForms = languageResearcher.getResearch( \"morphology\" );\n\n\tconst parsedSlug = parseSlug( paper.getSlug() );\n\tconst locale = paper.getLocale();\n\n\tconst keyphraseInSlug = findTopicFormsInString( topicForms, parsedSlug, false, locale, false );\n\n\treturn {\n\t\tkeyphraseLength: topicForms.keyphraseForms.length,\n\t\tpercentWordMatches: keyphraseInSlug.percentWordMatches,\n\t};\n}\n\n/**\n * Matches the keyword in the slug.\n * keywordCountInUrl was the previous name for keywordCountInSlug (hence the name of this file).\n * We keep (and expose) this research for backwards compatibility.\n *\n * @deprecated Since version 18.7. Use keywordCountInSlug instead.\n *\n * @param {Paper} paper the Paper object to use in this count.\n * @param {Researcher} researcher The Researcher object containing all available researches.\n *\n * @returns {{keyphraseLength: int, percentWordMatches: int}} The length of the keyphrase and the percentage of keyphrase forms that has been found.\n */\nfunction keywordCountInUrl( paper, researcher ) {\n\tconsole.warn( \"This function is deprecated, use keywordCountInSlug instead.\" );\n\treturn keywordCountInSlug( paper, researcher );\n}\n\nexport {\n\tkeywordCountInSlug,\n\tkeywordCountInUrl,\n};\n\nexport default keywordCountInSlug;\n"],"mappings":";;;;;;;;AACA,IAAAA,UAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,yBAAA,GAAAD,OAAA;AACA,IAAAE,OAAA,GAAAF,OAAA;AAAmC,SAAAD,uBAAAI,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAHnC;;AAKA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASG,kBAAkBA,CAAEC,KAAK,EAAEC,UAAU,EAAG;EAChD;AACD;AACA;AACA;AACA;EACC,MAAMC,kBAAkB,GAAG,IAAAC,iBAAS,EAAEF,UAAW,CAAC;EAClDC,kBAAkB,CAACE,SAAS,CAAE,0BAA0B,EAAE,IAAK,CAAC;EAChE,MAAMC,UAAU,GAAGH,kBAAkB,CAACI,WAAW,CAAE,YAAa,CAAC;EAEjE,MAAMC,UAAU,GAAG,IAAAC,kBAAS,EAAER,KAAK,CAACS,OAAO,CAAC,CAAE,CAAC;EAC/C,MAAMC,MAAM,GAAGV,KAAK,CAACW,SAAS,CAAC,CAAC;EAEhC,MAAMC,eAAe,GAAG,IAAAC,gDAAsB,EAAER,UAAU,EAAEE,UAAU,EAAE,KAAK,EAAEG,MAAM,EAAE,KAAM,CAAC;EAE9F,OAAO;IACNI,eAAe,EAAET,UAAU,CAACU,cAAc,CAACC,MAAM;IACjDC,kBAAkB,EAAEL,eAAe,CAACK;EACrC,CAAC;AACF;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,iBAAiBA,CAAElB,KAAK,EAAEC,UAAU,EAAG;EAC/CkB,OAAO,CAACC,IAAI,CAAE,8DAA+D,CAAC;EAC9E,OAAOrB,kBAAkB,CAAEC,KAAK,EAAEC,UAAW,CAAC;AAC/C;AAAC,IAAAoB,QAAA,GAAAC,OAAA,CAAAxB,OAAA,GAOcC,kBAAkB","ignoreList":[]}

package/build/languageProcessing/researches/matchKeywordInSubheadings.js

@@ -0,0 +1,68 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = matchKeywordInSubheadings;
+var _getSubheadings = require("../helpers/html/getSubheadings");
+var _stripNonTextTags = _interopRequireDefault(require("../helpers/sanitize/stripNonTextTags"));
+var _findKeywordFormsInString = require("../helpers/match/findKeywordFormsInString");
+var _htmlParser = _interopRequireDefault(require("../helpers/html/htmlParser"));
+var _helpers = require("../helpers");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Computes the amount of subheadings reflecting the topic.
+ *
+ * @param {Object}      topicForms      The main key phrase and its synonyms to check.
+ * @param {string[]}    subheadings     The subheadings to check.
+ * @param {boolean}     useSynonyms     Whether to match synonyms or only main keyphrase.
+ * @param {string}      locale          The current locale.
+ * @param {Array}       functionWords	The function words list.
+ * @param {function}    matchWordCustomHelper   The language-specific helper function to match word in text.
+ *
+ * @returns {number} The amount of subheadings reflecting the topic.
+ */
+const numberOfSubheadingsReflectingTopic = function (topicForms, subheadings, useSynonyms, locale, functionWords, matchWordCustomHelper) {
+  return subheadings.filter(subheading => {
+    const matchedTopicForms = (0, _findKeywordFormsInString.findTopicFormsInString)(topicForms, subheading, useSynonyms, locale, matchWordCustomHelper);
+    if (functionWords.length === 0) {
+      return matchedTopicForms.percentWordMatches === 100;
+    }
+    return matchedTopicForms.percentWordMatches > 50;
+  }).length;
+};
+
+/**
+ * Checks if there are any h2 or h3 subheadings in the text and if they have the keyphrase or synonyms in them.
+ *
+ * @param {Object}     paper      The paper object containing the text and keyword.
+ * @param {Researcher} researcher The researcher object.
+ *
+ * @returns {Object} The result object.
+ */
+function matchKeywordInSubheadings(paper, researcher) {
+  const functionWords = researcher.getConfig("functionWords");
+
+  // A custom helper to match word in text.
+  const matchWordCustomHelper = researcher.getHelper("matchWordCustomHelper");
+  let text = paper.getText();
+  text = (0, _htmlParser.default)(text);
+  text = (0, _helpers.filterShortcodesFromHTML)(text, paper._attributes && paper._attributes.shortcodes);
+  text = (0, _stripNonTextTags.default)(text);
+  const topicForms = researcher.getResearch("morphology");
+  const locale = paper.getLocale();
+  const result = {
+    count: 0,
+    matches: 0,
+    percentReflectingTopic: 0
+  };
+  const useSynonyms = true;
+  const subheadings = (0, _getSubheadings.getSubheadingContentsTopLevel)(text);
+  if (subheadings.length !== 0) {
+    result.count = subheadings.length;
+    result.matches = numberOfSubheadingsReflectingTopic(topicForms, subheadings, useSynonyms, locale, functionWords, matchWordCustomHelper);
+    result.percentReflectingTopic = result.matches / result.count * 100;
+  }
+  return result;
+}
+//# sourceMappingURL=matchKeywordInSubheadings.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"matchKeywordInSubheadings.js","names":["_getSubheadings","require","_stripNonTextTags","_interopRequireDefault","_findKeywordFormsInString","_htmlParser","_helpers","e","__esModule","default","numberOfSubheadingsReflectingTopic","topicForms","subheadings","useSynonyms","locale","functionWords","matchWordCustomHelper","filter","subheading","matchedTopicForms","findTopicFormsInString","length","percentWordMatches","matchKeywordInSubheadings","paper","researcher","getConfig","getHelper","text","getText","removeHtmlBlocks","filterShortcodesFromHTML","_attributes","shortcodes","stripSomeTags","getResearch","getLocale","result","count","matches","percentReflectingTopic","getSubheadingContentsTopLevel"],"sources":["../../../src/languageProcessing/researches/matchKeywordInSubheadings.js"],"sourcesContent":["import { getSubheadingContentsTopLevel } from \"../helpers/html/getSubheadings\";\nimport stripSomeTags from \"../helpers/sanitize/stripNonTextTags\";\nimport { findTopicFormsInString } from \"../helpers/match/findKeywordFormsInString\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\n\n/**\n * Computes the amount of subheadings reflecting the topic.\n *\n * @param {Object}      topicForms      The main key phrase and its synonyms to check.\n * @param {string[]}    subheadings     The subheadings to check.\n * @param {boolean}     useSynonyms     Whether to match synonyms or only main keyphrase.\n * @param {string}      locale          The current locale.\n * @param {Array}       functionWords\tThe function words list.\n * @param {function}    matchWordCustomHelper   The language-specific helper function to match word in text.\n *\n * @returns {number} The amount of subheadings reflecting the topic.\n */\nconst numberOfSubheadingsReflectingTopic = function( topicForms, subheadings, useSynonyms, locale, functionWords, matchWordCustomHelper ) {\n\treturn subheadings.filter( subheading => {\n\t\tconst matchedTopicForms = findTopicFormsInString( topicForms, subheading, useSynonyms, locale, matchWordCustomHelper );\n\n\t\tif ( functionWords.length === 0 ) {\n\t\t\treturn matchedTopicForms.percentWordMatches === 100;\n\t\t}\n\t\treturn matchedTopicForms.percentWordMatches > 50;\n\t} ).length;\n};\n\n/**\n * Checks if there are any h2 or h3 subheadings in the text and if they have the keyphrase or synonyms in them.\n *\n * @param {Object}     paper      The paper object containing the text and keyword.\n * @param {Researcher} researcher The researcher object.\n *\n * @returns {Object} The result object.\n */\nexport default function matchKeywordInSubheadings( paper, researcher ) {\n\tconst functionWords = researcher.getConfig( \"functionWords\" );\n\n\t// A custom helper to match word in text.\n\tconst matchWordCustomHelper = researcher.getHelper( \"matchWordCustomHelper\" );\n\n\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\ttext = stripSomeTags( text );\n\tconst topicForms = researcher.getResearch( \"morphology\" );\n\tconst locale = paper.getLocale();\n\tconst result = { count: 0, matches: 0, percentReflectingTopic: 0 };\n\tconst useSynonyms = true;\n\tconst subheadings = getSubheadingContentsTopLevel( text );\n\n\tif ( subheadings.length !== 0 ) {\n\t\tresult.count = subheadings.length;\n\t\tresult.matches = numberOfSubheadingsReflectingTopic( topicForms, subheadings, useSynonyms, locale, functionWords, matchWordCustomHelper );\n\t\tresult.percentReflectingTopic = result.matches / result.count * 100;\n\t}\n\n\treturn result;\n}\n"],"mappings":";;;;;;AAAA,IAAAA,eAAA,GAAAC,OAAA;AACA,IAAAC,iBAAA,GAAAC,sBAAA,CAAAF,OAAA;AACA,IAAAG,yBAAA,GAAAH,OAAA;AACA,IAAAI,WAAA,GAAAF,sBAAA,CAAAF,OAAA;AACA,IAAAK,QAAA,GAAAL,OAAA;AAAsD,SAAAE,uBAAAI,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEtD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,kCAAkC,GAAG,SAAAA,CAAUC,UAAU,EAAEC,WAAW,EAAEC,WAAW,EAAEC,MAAM,EAAEC,aAAa,EAAEC,qBAAqB,EAAG;EACzI,OAAOJ,WAAW,CAACK,MAAM,CAAEC,UAAU,IAAI;IACxC,MAAMC,iBAAiB,GAAG,IAAAC,gDAAsB,EAAET,UAAU,EAAEO,UAAU,EAAEL,WAAW,EAAEC,MAAM,EAAEE,qBAAsB,CAAC;IAEtH,IAAKD,aAAa,CAACM,MAAM,KAAK,CAAC,EAAG;MACjC,OAAOF,iBAAiB,CAACG,kBAAkB,KAAK,GAAG;IACpD;IACA,OAAOH,iBAAiB,CAACG,kBAAkB,GAAG,EAAE;EACjD,CAAE,CAAC,CAACD,MAAM;AACX,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAASE,yBAAyBA,CAAEC,KAAK,EAAEC,UAAU,EAAG;EACtE,MAAMV,aAAa,GAAGU,UAAU,CAACC,SAAS,CAAE,eAAgB,CAAC;;EAE7D;EACA,MAAMV,qBAAqB,GAAGS,UAAU,CAACE,SAAS,CAAE,uBAAwB,CAAC;EAG7E,IAAIC,IAAI,GAAGJ,KAAK,CAACK,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAG,IAAAE,mBAAgB,EAAEF,IAAK,CAAC;EAC/BA,IAAI,GAAG,IAAAG,iCAAwB,EAAEH,IAAI,EAAEJ,KAAK,CAACQ,WAAW,IAAIR,KAAK,CAACQ,WAAW,CAACC,UAAW,CAAC;EAC1FL,IAAI,GAAG,IAAAM,yBAAa,EAAEN,IAAK,CAAC;EAC5B,MAAMjB,UAAU,GAAGc,UAAU,CAACU,WAAW,CAAE,YAAa,CAAC;EACzD,MAAMrB,MAAM,GAAGU,KAAK,CAACY,SAAS,CAAC,CAAC;EAChC,MAAMC,MAAM,GAAG;IAAEC,KAAK,EAAE,CAAC;IAAEC,OAAO,EAAE,CAAC;IAAEC,sBAAsB,EAAE;EAAE,CAAC;EAClE,MAAM3B,WAAW,GAAG,IAAI;EACxB,MAAMD,WAAW,GAAG,IAAA6B,6CAA6B,EAAEb,IAAK,CAAC;EAEzD,IAAKhB,WAAW,CAACS,MAAM,KAAK,CAAC,EAAG;IAC/BgB,MAAM,CAACC,KAAK,GAAG1B,WAAW,CAACS,MAAM;IACjCgB,MAAM,CAACE,OAAO,GAAG7B,kCAAkC,CAAEC,UAAU,EAAEC,WAAW,EAAEC,WAAW,EAAEC,MAAM,EAAEC,aAAa,EAAEC,qBAAsB,CAAC;IACzIqB,MAAM,CAACG,sBAAsB,GAAGH,MAAM,CAACE,OAAO,GAAGF,MAAM,CAACC,KAAK,GAAG,GAAG;EACpE;EAEA,OAAOD,MAAM;AACd","ignoreList":[]}

package/build/languageProcessing/researches/metaDescriptionKeyword.js

@@ -0,0 +1,78 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _matchTextWithArray = _interopRequireDefault(require("../helpers/match/matchTextWithArray"));
+var _getSentences = _interopRequireDefault(require("../helpers/sentence/getSentences"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Replaces found keyword forms in the given description.
+ *
+ * @param {string}      description         The description to remove the matched keyword forms from.
+ * @param {Object[]}    matchedKeywordForms The matched keyword forms to remove from the description.
+ * @param {Number}      maxToRemove         The maximum amount of matches of each individual keyword to remove.
+ *
+ * @returns {string} The description with the keywords removed.
+ */
+const replaceFoundKeywordForms = function (description, matchedKeywordForms, maxToRemove) {
+  // Replace matches so we do not match them for synonyms.
+  matchedKeywordForms.forEach(keywordForm => keywordForm.matches.slice(0, maxToRemove).forEach(match => {
+    description = description.replace(match, "");
+  }));
+  return description;
+};
+
+/**
+ * Counts the number of full keyphrase matches in the given sentence. Takes synonyms into account.
+ * A full keyphrase is when all keywords in the keyphrase match.
+ *
+ * @param {string}      sentence        The sentence that needs to be analyzed.
+ * @param {Object}      topicForms      The keyphrase (and its optional synonyms') word forms.
+ * @param {string}      locale          The current locale.
+ * @param {function}    matchWordCustomHelper   The language-specific helper function to match word in text.
+ *
+ * @returns {Number} The number of matched keyphrases in the sentence.
+ */
+const matchPerSentence = function (sentence, topicForms, locale, matchWordCustomHelper) {
+  // Focus keyphrase matches.
+  const matchesKeyphrase = topicForms.keyphraseForms.map(keywordForms => (0, _matchTextWithArray.default)(sentence, keywordForms, locale, matchWordCustomHelper));
+  // Count the number of matches that contain every word in the entire keyphrase.
+  const fullKeyphraseMatches = Math.min(...matchesKeyphrase.map(match => match.count));
+
+  // Replace all full keyphrase matches so we do not match them for synonyms.
+  sentence = replaceFoundKeywordForms(sentence, matchesKeyphrase, fullKeyphraseMatches);
+
+  // Keyphrase synonyms matches.
+  const fullSynonymsMatches = topicForms.synonymsForms.map(synonymForms => {
+    // Synonym keyphrase matches.
+    const matches = synonymForms.map(keywordForms => (0, _matchTextWithArray.default)(sentence, keywordForms, locale, matchWordCustomHelper));
+    // Count the number of matches that contain every word in the entire synonym keyphrase.
+    const fullSynonymMatches = Math.min(...matches.map(match => match.count));
+    // Replace all full matches so we do not match them for other synonyms.
+    sentence = replaceFoundKeywordForms(sentence, matchesKeyphrase, fullSynonymMatches);
+    return fullSynonymMatches;
+  });
+  return [fullKeyphraseMatches, ...fullSynonymsMatches].reduce((sum, count) => sum + count, 0);
+};
+
+/**
+ * Counts the number of full keyphrase matches in the description.
+ *
+ * @param {Paper}       paper       The paper object containing the description.
+ * @param {Researcher}  researcher  The researcher object to gather researchers from.
+ *
+ * @returns {Number} The number of keyphrase matches for the entire description.
+ */
+function _default(paper, researcher) {
+  const description = paper.getDescription();
+  const locale = paper.getLocale();
+  const topicForms = researcher.getResearch("morphology");
+  const matchWordCustomHelper = researcher.getHelper("matchWordCustomHelper");
+  const memoizedTokenizer = researcher.getHelper("memoizedTokenizer");
+  const sentences = (0, _getSentences.default)(description, memoizedTokenizer);
+  const sentenceMatches = sentences.map(sentence => matchPerSentence(sentence, topicForms, locale, matchWordCustomHelper));
+  return sentenceMatches.reduce((sum, count) => sum + count, 0);
+}
+//# sourceMappingURL=metaDescriptionKeyword.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"metaDescriptionKeyword.js","names":["_matchTextWithArray","_interopRequireDefault","require","_getSentences","e","__esModule","default","replaceFoundKeywordForms","description","matchedKeywordForms","maxToRemove","forEach","keywordForm","matches","slice","match","replace","matchPerSentence","sentence","topicForms","locale","matchWordCustomHelper","matchesKeyphrase","keyphraseForms","map","keywordForms","matchWords","fullKeyphraseMatches","Math","min","count","fullSynonymsMatches","synonymsForms","synonymForms","fullSynonymMatches","reduce","sum","_default","paper","researcher","getDescription","getLocale","getResearch","getHelper","memoizedTokenizer","sentences","getSentences","sentenceMatches"],"sources":["../../../src/languageProcessing/researches/metaDescriptionKeyword.js"],"sourcesContent":["import matchWords from \"../helpers/match/matchTextWithArray\";\nimport getSentences from \"../helpers/sentence/getSentences\";\n\n/**\n * Replaces found keyword forms in the given description.\n *\n * @param {string}      description         The description to remove the matched keyword forms from.\n * @param {Object[]}    matchedKeywordForms The matched keyword forms to remove from the description.\n * @param {Number}      maxToRemove         The maximum amount of matches of each individual keyword to remove.\n *\n * @returns {string} The description with the keywords removed.\n */\nconst replaceFoundKeywordForms = function( description, matchedKeywordForms, maxToRemove ) {\n\t// Replace matches so we do not match them for synonyms.\n\tmatchedKeywordForms.forEach( keywordForm =>\n\t\tkeywordForm.matches.slice( 0, maxToRemove ).forEach(\n\t\t\tmatch => {\n\t\t\t\tdescription = description.replace( match, \"\" );\n\t\t\t}\n\t\t)\n\t);\n\treturn description;\n};\n\n/**\n * Counts the number of full keyphrase matches in the given sentence. Takes synonyms into account.\n * A full keyphrase is when all keywords in the keyphrase match.\n *\n * @param {string}      sentence        The sentence that needs to be analyzed.\n * @param {Object}      topicForms      The keyphrase (and its optional synonyms') word forms.\n * @param {string}      locale          The current locale.\n * @param {function}    matchWordCustomHelper   The language-specific helper function to match word in text.\n *\n * @returns {Number} The number of matched keyphrases in the sentence.\n */\nconst matchPerSentence = function( sentence, topicForms, locale, matchWordCustomHelper ) {\n\t// Focus keyphrase matches.\n\tconst matchesKeyphrase = topicForms.keyphraseForms.map( keywordForms => matchWords( sentence, keywordForms, locale, matchWordCustomHelper ) );\n\t// Count the number of matches that contain every word in the entire keyphrase.\n\tconst fullKeyphraseMatches = Math.min( ...matchesKeyphrase.map( match => match.count ) );\n\n\t// Replace all full keyphrase matches so we do not match them for synonyms.\n\tsentence = replaceFoundKeywordForms( sentence, matchesKeyphrase, fullKeyphraseMatches );\n\n\t// Keyphrase synonyms matches.\n\tconst fullSynonymsMatches = topicForms.synonymsForms.map(\n\t\tsynonymForms => {\n\t\t\t// Synonym keyphrase matches.\n\t\t\tconst matches = synonymForms.map( keywordForms => matchWords( sentence, keywordForms, locale, matchWordCustomHelper ) );\n\t\t\t// Count the number of matches that contain every word in the entire synonym keyphrase.\n\t\t\tconst fullSynonymMatches = Math.min( ...matches.map( match => match.count ) );\n\t\t\t// Replace all full matches so we do not match them for other synonyms.\n\t\t\tsentence = replaceFoundKeywordForms( sentence, matchesKeyphrase, fullSynonymMatches );\n\t\t\treturn fullSynonymMatches;\n\t\t}\n\t);\n\n\treturn [ fullKeyphraseMatches, ...fullSynonymsMatches ].reduce( ( sum, count ) => sum + count, 0 );\n};\n\n/**\n * Counts the number of full keyphrase matches in the description.\n *\n * @param {Paper}       paper       The paper object containing the description.\n * @param {Researcher}  researcher  The researcher object to gather researchers from.\n *\n * @returns {Number} The number of keyphrase matches for the entire description.\n */\nexport default function( paper, researcher ) {\n\tconst description = paper.getDescription();\n\tconst locale = paper.getLocale();\n\n\tconst topicForms = researcher.getResearch( \"morphology\" );\n\tconst matchWordCustomHelper = researcher.getHelper( \"matchWordCustomHelper\" );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\n\tconst sentences = getSentences( description, memoizedTokenizer );\n\n\tconst sentenceMatches = sentences.map(\n\t\tsentence => matchPerSentence( sentence, topicForms, locale, matchWordCustomHelper )\n\t);\n\n\treturn sentenceMatches.reduce( ( sum, count ) => sum + count, 0 );\n}\n\n"],"mappings":";;;;;;AAAA,IAAAA,mBAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,aAAA,GAAAF,sBAAA,CAAAC,OAAA;AAA4D,SAAAD,uBAAAG,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAE5D;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,wBAAwB,GAAG,SAAAA,CAAUC,WAAW,EAAEC,mBAAmB,EAAEC,WAAW,EAAG;EAC1F;EACAD,mBAAmB,CAACE,OAAO,CAAEC,WAAW,IACvCA,WAAW,CAACC,OAAO,CAACC,KAAK,CAAE,CAAC,EAAEJ,WAAY,CAAC,CAACC,OAAO,CAClDI,KAAK,IAAI;IACRP,WAAW,GAAGA,WAAW,CAACQ,OAAO,CAAED,KAAK,EAAE,EAAG,CAAC;EAC/C,CACD,CACD,CAAC;EACD,OAAOP,WAAW;AACnB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMS,gBAAgB,GAAG,SAAAA,CAAUC,QAAQ,EAAEC,UAAU,EAAEC,MAAM,EAAEC,qBAAqB,EAAG;EACxF;EACA,MAAMC,gBAAgB,GAAGH,UAAU,CAACI,cAAc,CAACC,GAAG,CAAEC,YAAY,IAAI,IAAAC,2BAAU,EAAER,QAAQ,EAAEO,YAAY,EAAEL,MAAM,EAAEC,qBAAsB,CAAE,CAAC;EAC7I;EACA,MAAMM,oBAAoB,GAAGC,IAAI,CAACC,GAAG,CAAE,GAAGP,gBAAgB,CAACE,GAAG,CAAET,KAAK,IAAIA,KAAK,CAACe,KAAM,CAAE,CAAC;;EAExF;EACAZ,QAAQ,GAAGX,wBAAwB,CAAEW,QAAQ,EAAEI,gBAAgB,EAAEK,oBAAqB,CAAC;;EAEvF;EACA,MAAMI,mBAAmB,GAAGZ,UAAU,CAACa,aAAa,CAACR,GAAG,CACvDS,YAAY,IAAI;IACf;IACA,MAAMpB,OAAO,GAAGoB,YAAY,CAACT,GAAG,CAAEC,YAAY,IAAI,IAAAC,2BAAU,EAAER,QAAQ,EAAEO,YAAY,EAAEL,MAAM,EAAEC,qBAAsB,CAAE,CAAC;IACvH;IACA,MAAMa,kBAAkB,GAAGN,IAAI,CAACC,GAAG,CAAE,GAAGhB,OAAO,CAACW,GAAG,CAAET,KAAK,IAAIA,KAAK,CAACe,KAAM,CAAE,CAAC;IAC7E;IACAZ,QAAQ,GAAGX,wBAAwB,CAAEW,QAAQ,EAAEI,gBAAgB,EAAEY,kBAAmB,CAAC;IACrF,OAAOA,kBAAkB;EAC1B,CACD,CAAC;EAED,OAAO,CAAEP,oBAAoB,EAAE,GAAGI,mBAAmB,CAAE,CAACI,MAAM,CAAE,CAAEC,GAAG,EAAEN,KAAK,KAAMM,GAAG,GAAGN,KAAK,EAAE,CAAE,CAAC;AACnG,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAO,SAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C,MAAM/B,WAAW,GAAG8B,KAAK,CAACE,cAAc,CAAC,CAAC;EAC1C,MAAMpB,MAAM,GAAGkB,KAAK,CAACG,SAAS,CAAC,CAAC;EAEhC,MAAMtB,UAAU,GAAGoB,UAAU,CAACG,WAAW,CAAE,YAAa,CAAC;EACzD,MAAMrB,qBAAqB,GAAGkB,UAAU,CAACI,SAAS,CAAE,uBAAwB,CAAC;EAC7E,MAAMC,iBAAiB,GAAGL,UAAU,CAACI,SAAS,CAAE,mBAAoB,CAAC;EAErE,MAAME,SAAS,GAAG,IAAAC,qBAAY,EAAEtC,WAAW,EAAEoC,iBAAkB,CAAC;EAEhE,MAAMG,eAAe,GAAGF,SAAS,CAACrB,GAAG,CACpCN,QAAQ,IAAID,gBAAgB,CAAEC,QAAQ,EAAEC,UAAU,EAAEC,MAAM,EAAEC,qBAAsB,CACnF,CAAC;EAED,OAAO0B,eAAe,CAACZ,MAAM,CAAE,CAAEC,GAAG,EAAEN,KAAK,KAAMM,GAAG,GAAGN,KAAK,EAAE,CAAE,CAAC;AAClE","ignoreList":[]}

package/build/languageProcessing/researches/metaDescriptionLength.js

@@ -0,0 +1,19 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = metaDescriptionLength;
+var _countMetaDescriptionLength = _interopRequireDefault(require("../helpers/word/countMetaDescriptionLength"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Count the meta description length.
+ *
+ * @param {Paper} paper The paper to check for images.
+ *
+ * @returns {number|*}  The meta description length.
+ */
+function metaDescriptionLength(paper) {
+  return (0, _countMetaDescriptionLength.default)(paper.getDate(), paper.getDescription());
+}
+//# sourceMappingURL=metaDescriptionLength.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"metaDescriptionLength.js","names":["_countMetaDescriptionLength","_interopRequireDefault","require","e","__esModule","default","metaDescriptionLength","paper","countMetaDescriptionLength","getDate","getDescription"],"sources":["../../../src/languageProcessing/researches/metaDescriptionLength.js"],"sourcesContent":["import countMetaDescriptionLength from \"../helpers/word/countMetaDescriptionLength\";\n\n/**\n * Count the meta description length.\n *\n * @param {Paper} paper The paper to check for images.\n *\n * @returns {number|*}  The meta description length.\n */\nexport default function metaDescriptionLength( paper ) {\n\treturn countMetaDescriptionLength( paper.getDate(), paper.getDescription() );\n}\n"],"mappings":";;;;;;AAAA,IAAAA,2BAAA,GAAAC,sBAAA,CAAAC,OAAA;AAAoF,SAAAD,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEpF;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAASG,qBAAqBA,CAAEC,KAAK,EAAG;EACtD,OAAO,IAAAC,mCAA0B,EAAED,KAAK,CAACE,OAAO,CAAC,CAAC,EAAEF,KAAK,CAACG,cAAc,CAAC,CAAE,CAAC;AAC7E","ignoreList":[]}

package/build/languageProcessing/researches/pageTitleWidth.js

@@ -0,0 +1,18 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+/**
+ * Check the width of the title in pixels
+ * @param {Paper} paper The paper object containing the title width in pixels.
+ * @returns {number} The width of the title in pixels
+ */
+function _default(paper) {
+  if (paper.hasTitle()) {
+    return paper.getTitleWidth();
+  }
+  return 0;
+}
+//# sourceMappingURL=pageTitleWidth.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"pageTitleWidth.js","names":["_default","paper","hasTitle","getTitleWidth"],"sources":["../../../src/languageProcessing/researches/pageTitleWidth.js"],"sourcesContent":["/**\n * Check the width of the title in pixels\n * @param {Paper} paper The paper object containing the title width in pixels.\n * @returns {number} The width of the title in pixels\n */\nexport default function( paper ) {\n\tif ( paper.hasTitle() ) {\n\t\treturn paper.getTitleWidth();\n\t}\n\treturn 0;\n}\n"],"mappings":";;;;;;AAAA;AACA;AACA;AACA;AACA;AACe,SAAAA,SAAUC,KAAK,EAAG;EAChC,IAAKA,KAAK,CAACC,QAAQ,CAAC,CAAC,EAAG;IACvB,OAAOD,KAAK,CAACE,aAAa,CAAC,CAAC;EAC7B;EACA,OAAO,CAAC;AACT","ignoreList":[]}

package/build/languageProcessing/researches/readingTime.js

@@ -0,0 +1,84 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _getLanguage = _interopRequireDefault(require("../../languageProcessing/helpers/language/getLanguage"));
+var _wordCountInText = _interopRequireDefault(require("./wordCountInText.js"));
+var _imageCount = _interopRequireDefault(require("./imageCount.js"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Calculates the expected reading time of a text.
+ *
+ * @param {Paper} paper The paper to calculate the reading time for.
+ * @param {Researcher} researcher The researcher.
+ *
+ * @returns {number} The expected reading time in minutes for a given language.
+ */
+function _default(paper, researcher) {
+  const language = (0, _getLanguage.default)(paper.getLocale());
+
+  // A helper to get words from the text for languages that don't use the default approach.
+  const customGetWords = researcher.getHelper("getWordsCustomHelper");
+  const countCharactersFromArray = researcher.getHelper("wordsCharacterCount");
+
+  /*
+   * These numbers (both in `wordsPerMinute` and `charactersPerMinute`) are based on research into average reading times:
+   * Susanne Trauzettel-Klosinski, Klaus Dietz, the IReST Study Group;
+   * Standardized Assessment of Reading Performance: The New International Reading Speed Texts IReST.
+   * Invest. Ophthalmol. Vis. Sci. 2012;53(9):5452-5461
+   */
+  const wordsPerMinute = {
+    ar: 138,
+    cn: 158,
+    de: 179,
+    en: 228,
+    es: 218,
+    fi: 161,
+    fr: 195,
+    he: 187,
+    it: 188,
+    nl: 202,
+    pl: 166,
+    pt: 181,
+    ru: 184,
+    sl: 180,
+    sv: 199,
+    tr: 166
+  };
+  const charactersPerMinute = {
+    ja: 357
+  };
+  const wordsPerMinuteScore = wordsPerMinute[language];
+  const charactersPerMinuteScore = charactersPerMinute[language];
+
+  // The default approach of calculating the text length is by counting the words in the text.
+  let textLength = (0, _wordCountInText.default)(paper).count;
+  let minutesToReadText;
+  if (charactersPerMinuteScore) {
+    /*
+     * If a language has a characters per minute score, we assume that the language also uses a character count helper
+     * for retrieving the text length and a custom helper to get words from the text.
+     */
+    textLength = countCharactersFromArray(customGetWords(paper.getText()));
+    minutesToReadText = textLength / charactersPerMinuteScore;
+  } else if (wordsPerMinuteScore) {
+    minutesToReadText = textLength / wordsPerMinuteScore;
+  } else {
+    // If the language is not on both lists, assign the average of all language-dependent reading times as the score.
+    const sumWordsPerMinute = Object.values(wordsPerMinute).reduce((a, b) => a + b);
+    const sumNumberOfLanguages = Object.keys(wordsPerMinute).length;
+    minutesToReadText = textLength / (sumWordsPerMinute / sumNumberOfLanguages);
+  }
+  const minutesPerImage = 0.2;
+  const numberOfImages = (0, _imageCount.default)(paper);
+
+  /*
+   * This formula is based on the average number of words a person is expected to read per minute,
+   * plus extra time for each image in the text. It returns the expected reading time in whole minutes,
+   * rounded up to the nearest minute.
+   */
+  return Math.ceil(minutesToReadText + numberOfImages * minutesPerImage);
+}
+//# sourceMappingURL=readingTime.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"readingTime.js","names":["_getLanguage","_interopRequireDefault","require","_wordCountInText","_imageCount","e","__esModule","default","_default","paper","researcher","language","getLanguage","getLocale","customGetWords","getHelper","countCharactersFromArray","wordsPerMinute","ar","cn","de","en","es","fi","fr","he","it","nl","pl","pt","ru","sl","sv","tr","charactersPerMinute","ja","wordsPerMinuteScore","charactersPerMinuteScore","textLength","wordCountInText","count","minutesToReadText","getText","sumWordsPerMinute","Object","values","reduce","a","b","sumNumberOfLanguages","keys","length","minutesPerImage","numberOfImages","imageCount","Math","ceil"],"sources":["../../../src/languageProcessing/researches/readingTime.js"],"sourcesContent":["import getLanguage from \"../../languageProcessing/helpers/language/getLanguage\";\nimport wordCountInText from \"./wordCountInText.js\";\nimport imageCount from \"./imageCount.js\";\n\n/**\n * Calculates the expected reading time of a text.\n *\n * @param {Paper} paper The paper to calculate the reading time for.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {number} The expected reading time in minutes for a given language.\n */\nexport default function( paper, researcher ) {\n\tconst language = getLanguage( paper.getLocale() );\n\n\t// A helper to get words from the text for languages that don't use the default approach.\n\tconst customGetWords = researcher.getHelper( \"getWordsCustomHelper\" );\n\tconst countCharactersFromArray = researcher.getHelper( \"wordsCharacterCount\" );\n\n\t/*\n\t * These numbers (both in `wordsPerMinute` and `charactersPerMinute`) are based on research into average reading times:\n\t * Susanne Trauzettel-Klosinski, Klaus Dietz, the IReST Study Group;\n\t * Standardized Assessment of Reading Performance: The New International Reading Speed Texts IReST.\n\t * Invest. Ophthalmol. Vis. Sci. 2012;53(9):5452-5461\n\t */\n\tconst wordsPerMinute = {\n\t\tar: 138,\n\t\tcn: 158,\n\t\tde: 179,\n\t\ten: 228,\n\t\tes: 218,\n\t\tfi: 161,\n\t\tfr: 195,\n\t\the: 187,\n\t\tit: 188,\n\t\tnl: 202,\n\t\tpl: 166,\n\t\tpt: 181,\n\t\tru: 184,\n\t\tsl: 180,\n\t\tsv: 199,\n\t\ttr: 166,\n\t};\n\n\tconst charactersPerMinute = {\n\t\tja: 357,\n\t};\n\n\n\tconst wordsPerMinuteScore = wordsPerMinute[ language ];\n\tconst charactersPerMinuteScore = charactersPerMinute[ language ];\n\n\t// The default approach of calculating the text length is by counting the words in the text.\n\tlet textLength = wordCountInText( paper ).count;\n\tlet minutesToReadText;\n\n\tif ( charactersPerMinuteScore ) {\n\t\t/*\n\t\t * If a language has a characters per minute score, we assume that the language also uses a character count helper\n\t\t * for retrieving the text length and a custom helper to get words from the text.\n\t\t */\n\t\ttextLength = countCharactersFromArray( customGetWords( paper.getText() ) );\n\t\tminutesToReadText = textLength / charactersPerMinuteScore;\n\t} else if ( wordsPerMinuteScore ) {\n\t\tminutesToReadText = textLength / wordsPerMinuteScore;\n\t} else {\n\t\t// If the language is not on both lists, assign the average of all language-dependent reading times as the score.\n\t\tconst sumWordsPerMinute = Object.values( wordsPerMinute ).reduce( ( a, b ) => a + b );\n\t\tconst sumNumberOfLanguages = Object.keys( wordsPerMinute ).length;\n\t\tminutesToReadText = textLength / ( sumWordsPerMinute / sumNumberOfLanguages );\n\t}\n\n\tconst minutesPerImage = 0.2;\n\tconst numberOfImages = imageCount( paper );\n\n\t/*\n\t * This formula is based on the average number of words a person is expected to read per minute,\n\t * plus extra time for each image in the text. It returns the expected reading time in whole minutes,\n\t * rounded up to the nearest minute.\n\t */\n\treturn Math.ceil( minutesToReadText + ( numberOfImages * minutesPerImage ) );\n}\n"],"mappings":";;;;;;AAAA,IAAAA,YAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,gBAAA,GAAAF,sBAAA,CAAAC,OAAA;AACA,IAAAE,WAAA,GAAAH,sBAAA,CAAAC,OAAA;AAAyC,SAAAD,uBAAAI,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEzC;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C,MAAMC,QAAQ,GAAG,IAAAC,oBAAW,EAAEH,KAAK,CAACI,SAAS,CAAC,CAAE,CAAC;;EAEjD;EACA,MAAMC,cAAc,GAAGJ,UAAU,CAACK,SAAS,CAAE,sBAAuB,CAAC;EACrE,MAAMC,wBAAwB,GAAGN,UAAU,CAACK,SAAS,CAAE,qBAAsB,CAAC;;EAE9E;AACD;AACA;AACA;AACA;AACA;EACC,MAAME,cAAc,GAAG;IACtBC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE;EACL,CAAC;EAED,MAAMC,mBAAmB,GAAG;IAC3BC,EAAE,EAAE;EACL,CAAC;EAGD,MAAMC,mBAAmB,GAAGnB,cAAc,CAAEN,QAAQ,CAAE;EACtD,MAAM0B,wBAAwB,GAAGH,mBAAmB,CAAEvB,QAAQ,CAAE;;EAEhE;EACA,IAAI2B,UAAU,GAAG,IAAAC,wBAAe,EAAE9B,KAAM,CAAC,CAAC+B,KAAK;EAC/C,IAAIC,iBAAiB;EAErB,IAAKJ,wBAAwB,EAAG;IAC/B;AACF;AACA;AACA;IACEC,UAAU,GAAGtB,wBAAwB,CAAEF,cAAc,CAAEL,KAAK,CAACiC,OAAO,CAAC,CAAE,CAAE,CAAC;IAC1ED,iBAAiB,GAAGH,UAAU,GAAGD,wBAAwB;EAC1D,CAAC,MAAM,IAAKD,mBAAmB,EAAG;IACjCK,iBAAiB,GAAGH,UAAU,GAAGF,mBAAmB;EACrD,CAAC,MAAM;IACN;IACA,MAAMO,iBAAiB,GAAGC,MAAM,CAACC,MAAM,CAAE5B,cAAe,CAAC,CAAC6B,MAAM,CAAE,CAAEC,CAAC,EAAEC,CAAC,KAAMD,CAAC,GAAGC,CAAE,CAAC;IACrF,MAAMC,oBAAoB,GAAGL,MAAM,CAACM,IAAI,CAAEjC,cAAe,CAAC,CAACkC,MAAM;IACjEV,iBAAiB,GAAGH,UAAU,IAAKK,iBAAiB,GAAGM,oBAAoB,CAAE;EAC9E;EAEA,MAAMG,eAAe,GAAG,GAAG;EAC3B,MAAMC,cAAc,GAAG,IAAAC,mBAAU,EAAE7C,KAAM,CAAC;;EAE1C;AACD;AACA;AACA;AACA;EACC,OAAO8C,IAAI,CAACC,IAAI,CAAEf,iBAAiB,GAAKY,cAAc,GAAGD,eAAkB,CAAC;AAC7E","ignoreList":[]}

package/build/languageProcessing/researches/sentences.js

@@ -0,0 +1,26 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _getSentences = _interopRequireDefault(require("../helpers/sentence/getSentences"));
+var _htmlParser = _interopRequireDefault(require("../helpers/html/htmlParser"));
+var _helpers = require("../helpers");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Returns the sentences from a paper.
+ *
+ * @param {Paper}   paper       The paper to analyze.
+ * @param {object}  researcher  The researcher.
+ *
+ * @returns {Array} Sentences found in the paper.
+ */
+function _default(paper, researcher) {
+  const memoizedTokenizer = researcher.getHelper("memoizedTokenizer");
+  let text = paper.getText();
+  text = (0, _htmlParser.default)(text);
+  text = (0, _helpers.filterShortcodesFromHTML)(text, paper._attributes && paper._attributes.shortcodes);
+  return (0, _getSentences.default)(text, memoizedTokenizer);
+}
+//# sourceMappingURL=sentences.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"sentences.js","names":["_getSentences","_interopRequireDefault","require","_htmlParser","_helpers","e","__esModule","default","_default","paper","researcher","memoizedTokenizer","getHelper","text","getText","removeHtmlBlocks","filterShortcodesFromHTML","_attributes","shortcodes","getSentences"],"sources":["../../../src/languageProcessing/researches/sentences.js"],"sourcesContent":["import getSentences from \"../helpers/sentence/getSentences\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\n\n/**\n * Returns the sentences from a paper.\n *\n * @param {Paper}   paper       The paper to analyze.\n * @param {object}  researcher  The researcher.\n *\n * @returns {Array} Sentences found in the paper.\n */\nexport default function( paper, researcher ) {\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\treturn getSentences( text, memoizedTokenizer );\n}\n"],"mappings":";;;;;;AAAA,IAAAA,aAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,WAAA,GAAAF,sBAAA,CAAAC,OAAA;AACA,IAAAE,QAAA,GAAAF,OAAA;AAAsD,SAAAD,uBAAAI,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEtD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C,MAAMC,iBAAiB,GAAGD,UAAU,CAACE,SAAS,CAAE,mBAAoB,CAAC;EAErE,IAAIC,IAAI,GAAGJ,KAAK,CAACK,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAG,IAAAE,mBAAgB,EAAEF,IAAK,CAAC;EAC/BA,IAAI,GAAG,IAAAG,iCAAwB,EAAEH,IAAI,EAAEJ,KAAK,CAACQ,WAAW,IAAIR,KAAK,CAACQ,WAAW,CAACC,UAAW,CAAC;EAC1F,OAAO,IAAAC,qBAAY,EAAEN,IAAI,EAAEF,iBAAkB,CAAC;AAC/C","ignoreList":[]}

package/build/languageProcessing/researches/videoCount.js

@@ -0,0 +1,39 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = countVideoInText;
+/**
+ * Checks the amount of videos in the text, including embedded video iframes and specific video sources.
+ *
+ * @param {Paper} paper The paper to check for videos.
+ *
+ * @returns {number} The amount of found videos.
+ */
+function countVideoInText(paper) {
+  // Regular expression to match <video> tags.
+  const videoTag = /<video.*?<\/video>/gis;
+
+  // Regular expression to match <iframe> tags with video sources (YouTube, Vimeo, Shopify CDN, etc.).
+  const iframeVideoTag = /<iframe[^>]*src=["']https?:\/\/(?:www\.)?(youtube\.com|youtu\.be|vimeo\.com|cdn\.shopify\.com)[^"']*["'][^>]*>/gis;
+
+  // Regular expression to match any src attributes with common video file extensions.
+  const videoSrcTag = /src=["'].*?\.(mp4|webm|ogg|mov|m4v|avi|mkv|flv|wmv)(\?.*?)?["']/gis;
+
+  // Match occurrences of <video> tags in the text.
+  const videoMatches = paper.getText().match(videoTag) || [];
+
+  // Match occurrences of <iframe> tags with video sources in the text.
+  const iframeVideoMatches = paper.getText().match(iframeVideoTag) || [];
+
+  // Match occurrences of src attributes pointing to video files in the text.
+  const videoSrcMatches = paper.getText().match(videoSrcTag) || [];
+
+  // Combine all matches into a single set to remove duplicates.
+  const allMatches = new Set([...videoMatches, ...iframeVideoMatches, ...videoSrcMatches]);
+
+  // Return the unique count of all found matches.
+  return allMatches.size;
+}
+//# sourceMappingURL=videoCount.js.map