axyseo 2.1.11 → 2.1.13

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

@@ -0,0 +1,103 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _lodash = require("lodash");
+var _countWords = _interopRequireDefault(require("../helpers/word/countWords"));
+var _determineProminentWords = require("../helpers/prominentWords/determineProminentWords");
+var _getSubheadings = require("../helpers/html/getSubheadings");
+var _baseStemmer = _interopRequireDefault(require("../helpers/morphology/baseStemmer"));
+var _removeURLs = _interopRequireDefault(require("../helpers/sanitize/removeURLs.js"));
+var _removeEmailAddresses = _interopRequireDefault(require("../helpers/sanitize/removeEmailAddresses"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Removes URLs and email addresses from the text.
+ *
+ * @param {string}	text	The text to sanitize.
+ *
+ * @returns {string} The text without URLs and email addresses.
+ */
+const sanitizeText = function (text) {
+  text = (0, _removeURLs.default)(text);
+  return (0, _removeEmailAddresses.default)(text);
+};
+
+/**
+ * Retrieves the prominent words from the given paper.
+ *
+ * @param {Paper}       paper       The paper to determine the prominent words of.
+ * @param {Researcher}  researcher  The researcher to use for analysis.
+ *
+ * @returns {Object}          result                    A compound result object.
+ * @returns {ProminentWord[]} result.prominentWords     Prominent words for this paper, filtered and sorted.
+ * @returns {boolean}         result.hasMetaDescription Whether the metadescription is available in the input paper.
+ * @returns {boolean}         result.hasTitle           Whether the title is available in the input paper.
+ */
+function getProminentWordsForInternalLinking(paper, researcher) {
+  const functionWords = researcher.getConfig("functionWords");
+  // An optional custom helper to return custom function to return the stem of a word.
+  const customStemmer = researcher.getHelper("customGetStemmer");
+  const stemmer = customStemmer ? customStemmer(researcher) : researcher.getHelper("getStemmer")(researcher);
+  // An optional custom helper to get words from the text.
+  const getWordsCustomHelper = researcher.getHelper("getWordsCustomHelper");
+  // An optional custom helper to count length to use instead of countWords.
+  const customCountLength = researcher.getHelper("customCountLength");
+  const text = sanitizeText(paper.getText());
+  const metadescription = sanitizeText(paper.getDescription());
+  const title = sanitizeText(paper.getTitle());
+  const result = {};
+  result.hasMetaDescription = metadescription !== "";
+  result.hasTitle = title !== "";
+  result.prominentWords = [];
+
+  /**
+   * We only want to return suggestions (and spend time calculating prominent words) if the text is at least 100 words.
+   * And when a customCountLength is available, we only want to return the suggestions if the text has at least 200 characters.
+  	 */
+  if (customCountLength) {
+    if (customCountLength(text) < 200) {
+      return result;
+    }
+  } else if ((0, _countWords.default)(text) < 100) {
+    return result;
+  }
+  const subheadings = (0, _getSubheadings.getSubheadingsTopLevel)(text).map(subheading => subheading[2]);
+  const attributes = [paper.getKeyword(), paper.getSynonyms(), title, metadescription, subheadings.join(" ")];
+
+  // If the language has a custom helper to get words from the text, we don't retrieve the abbreviation.
+  const abbreviations = getWordsCustomHelper ? [] : (0, _determineProminentWords.retrieveAbbreviations)(text.concat(attributes.join(" ")));
+  const removedSubheadingText = (0, _getSubheadings.removeSubheadingsTopLevel)(text);
+  const prominentWordsFromText = (0, _determineProminentWords.getProminentWords)(removedSubheadingText, abbreviations, stemmer, functionWords, getWordsCustomHelper);
+  const prominentWordsFromPaperAttributes = (0, _determineProminentWords.getProminentWordsFromPaperAttributes)(attributes, abbreviations, stemmer, functionWords, getWordsCustomHelper);
+
+  /*
+   * If a word is used in any of the attributes, its weight is automatically high.
+   * To make sure the word survives weight filters and gets saved in the database, make the number of occurrences times-3.
+   */
+  prominentWordsFromPaperAttributes.forEach(relevantWord => relevantWord.setOccurrences(relevantWord.getOccurrences() * 3));
+  const collapsedWords = (0, _determineProminentWords.collapseProminentWordsOnStem)(prominentWordsFromPaperAttributes.concat(prominentWordsFromText));
+  (0, _determineProminentWords.sortProminentWords)(collapsedWords);
+
+  /*
+   * If morphology data are available for a language, the minimum number of occurrences to consider a word to be prominent is 4.
+   * This minimum number was chosen in order to avoid premature suggestions of words from the paper attributes.
+   * These get a times-3 boost and would therefore be prominent with just 1 occurrence.
+   *
+   * If morphology data are not available, and therefore word forms are not recognized, the minimum threshold is lowered to 2.
+   */
+  let minimumNumberOfOccurrences = 4;
+  if (stemmer === _baseStemmer.default) {
+    minimumNumberOfOccurrences = 2;
+  }
+
+  /*
+   * Return the 100 top items from the collapsed and sorted list. The number is picked deliberately to prevent larger
+   * articles from getting too long of lists.
+   */
+  result.prominentWords = (0, _lodash.take)((0, _determineProminentWords.filterProminentWords)(collapsedWords, minimumNumberOfOccurrences), 100);
+  return result;
+}
+var _default = exports.default = getProminentWordsForInternalLinking;
+//# sourceMappingURL=getProminentWordsForInternalLinking.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"getProminentWordsForInternalLinking.js","names":["_lodash","require","_countWords","_interopRequireDefault","_determineProminentWords","_getSubheadings","_baseStemmer","_removeURLs","_removeEmailAddresses","e","__esModule","default","sanitizeText","text","removeURLs","removeEmailAddresses","getProminentWordsForInternalLinking","paper","researcher","functionWords","getConfig","customStemmer","getHelper","stemmer","getWordsCustomHelper","customCountLength","getText","metadescription","getDescription","title","getTitle","result","hasMetaDescription","hasTitle","prominentWords","countWords","subheadings","getSubheadingsTopLevel","map","subheading","attributes","getKeyword","getSynonyms","join","abbreviations","retrieveAbbreviations","concat","removedSubheadingText","removeSubheadingsTopLevel","prominentWordsFromText","getProminentWords","prominentWordsFromPaperAttributes","getProminentWordsFromPaperAttributes","forEach","relevantWord","setOccurrences","getOccurrences","collapsedWords","collapseProminentWordsOnStem","sortProminentWords","minimumNumberOfOccurrences","baseStemmer","take","filterProminentWords","_default","exports"],"sources":["../../../../src/languageProcessing/researches/getProminentWordsForInternalLinking.js"],"sourcesContent":["import { take } from \"lodash\";\nimport countWords from \"../helpers/word/countWords\";\nimport {\n\tcollapseProminentWordsOnStem,\n\tfilterProminentWords,\n\tgetProminentWords,\n\tgetProminentWordsFromPaperAttributes,\n\tretrieveAbbreviations,\n\tsortProminentWords,\n} from \"../helpers/prominentWords/determineProminentWords\";\nimport { getSubheadingsTopLevel, removeSubheadingsTopLevel } from \"../helpers/html/getSubheadings\";\nimport baseStemmer from \"../helpers/morphology/baseStemmer\";\nimport removeURLs from \"../helpers/sanitize/removeURLs.js\";\nimport removeEmailAddresses from \"../helpers/sanitize/removeEmailAddresses\";\n\n/**\n * Removes URLs and email addresses from the text.\n *\n * @param {string}\ttext\tThe text to sanitize.\n *\n * @returns {string} The text without URLs and email addresses.\n */\nconst sanitizeText = function( text ) {\n\ttext = removeURLs( text );\n\treturn removeEmailAddresses( text );\n};\n\n/**\n * Retrieves the prominent words from the given paper.\n *\n * @param {Paper}       paper       The paper to determine the prominent words of.\n * @param {Researcher}  researcher  The researcher to use for analysis.\n *\n * @returns {Object}          result                    A compound result object.\n * @returns {ProminentWord[]} result.prominentWords     Prominent words for this paper, filtered and sorted.\n * @returns {boolean}         result.hasMetaDescription Whether the metadescription is available in the input paper.\n * @returns {boolean}         result.hasTitle           Whether the title is available in the input paper.\n */\nfunction getProminentWordsForInternalLinking( paper, researcher ) {\n\tconst functionWords = researcher.getConfig( \"functionWords\" );\n\t// An optional custom helper to return custom function to return the stem of a word.\n\tconst customStemmer = researcher.getHelper( \"customGetStemmer\" );\n\tconst stemmer = customStemmer ? customStemmer( researcher ) : researcher.getHelper( \"getStemmer\" )( researcher );\n\t// An optional custom helper to get words from the text.\n\tconst getWordsCustomHelper = researcher.getHelper( \"getWordsCustomHelper\" );\n\t// An optional custom helper to count length to use instead of countWords.\n\tconst customCountLength = researcher.getHelper( \"customCountLength\" );\n\n\tconst text = sanitizeText( paper.getText() );\n\tconst metadescription = sanitizeText( paper.getDescription() );\n\tconst title = sanitizeText( paper.getTitle() );\n\n\tconst result = {};\n\tresult.hasMetaDescription = metadescription !== \"\";\n\tresult.hasTitle = title !== \"\";\n\tresult.prominentWords = [];\n\n\t/**\n\t * We only want to return suggestions (and spend time calculating prominent words) if the text is at least 100 words.\n\t * And when a customCountLength is available, we only want to return the suggestions if the text has at least 200 characters.\n \t */\n\tif ( customCountLength ) {\n\t\tif ( customCountLength( text ) < 200 ) {\n\t\t\treturn result;\n\t\t}\n\t} else if ( countWords( text ) < 100 ) {\n\t\treturn result;\n\t}\n\n\tconst subheadings = getSubheadingsTopLevel( text ).map( subheading => subheading[ 2 ] );\n\tconst attributes = [\n\t\tpaper.getKeyword(),\n\t\tpaper.getSynonyms(),\n\t\ttitle,\n\t\tmetadescription,\n\t\tsubheadings.join( \" \" ),\n\t];\n\n\t// If the language has a custom helper to get words from the text, we don't retrieve the abbreviation.\n\tconst abbreviations = getWordsCustomHelper ? [] : retrieveAbbreviations( text.concat( attributes.join( \" \" ) ) );\n\n\tconst removedSubheadingText = removeSubheadingsTopLevel( text );\n\tconst prominentWordsFromText = getProminentWords( removedSubheadingText, abbreviations, stemmer, functionWords, getWordsCustomHelper );\n\n\tconst prominentWordsFromPaperAttributes = getProminentWordsFromPaperAttributes(\n\t\tattributes, abbreviations, stemmer, functionWords, getWordsCustomHelper );\n\n\t/*\n\t * If a word is used in any of the attributes, its weight is automatically high.\n\t * To make sure the word survives weight filters and gets saved in the database, make the number of occurrences times-3.\n\t */\n\tprominentWordsFromPaperAttributes.forEach( relevantWord => relevantWord.setOccurrences( relevantWord.getOccurrences() * 3 ) );\n\n\tconst collapsedWords = collapseProminentWordsOnStem( prominentWordsFromPaperAttributes.concat( prominentWordsFromText ) );\n\tsortProminentWords( collapsedWords );\n\n\t/*\n\t * If morphology data are available for a language, the minimum number of occurrences to consider a word to be prominent is 4.\n\t * This minimum number was chosen in order to avoid premature suggestions of words from the paper attributes.\n\t * These get a times-3 boost and would therefore be prominent with just 1 occurrence.\n\t *\n\t * If morphology data are not available, and therefore word forms are not recognized, the minimum threshold is lowered to 2.\n\t */\n\tlet minimumNumberOfOccurrences = 4;\n\n\tif ( stemmer === baseStemmer ) {\n\t\tminimumNumberOfOccurrences = 2;\n\t}\n\n\t/*\n\t * Return the 100 top items from the collapsed and sorted list. The number is picked deliberately to prevent larger\n\t * articles from getting too long of lists.\n\t */\n\tresult.prominentWords = take( filterProminentWords( collapsedWords, minimumNumberOfOccurrences ), 100 );\n\n\treturn result;\n}\n\nexport default getProminentWordsForInternalLinking;\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AACA,IAAAC,WAAA,GAAAC,sBAAA,CAAAF,OAAA;AACA,IAAAG,wBAAA,GAAAH,OAAA;AAQA,IAAAI,eAAA,GAAAJ,OAAA;AACA,IAAAK,YAAA,GAAAH,sBAAA,CAAAF,OAAA;AACA,IAAAM,WAAA,GAAAJ,sBAAA,CAAAF,OAAA;AACA,IAAAO,qBAAA,GAAAL,sBAAA,CAAAF,OAAA;AAA4E,SAAAE,uBAAAM,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAE5E;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,YAAY,GAAG,SAAAA,CAAUC,IAAI,EAAG;EACrCA,IAAI,GAAG,IAAAC,mBAAU,EAAED,IAAK,CAAC;EACzB,OAAO,IAAAE,6BAAoB,EAAEF,IAAK,CAAC;AACpC,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASG,mCAAmCA,CAAEC,KAAK,EAAEC,UAAU,EAAG;EACjE,MAAMC,aAAa,GAAGD,UAAU,CAACE,SAAS,CAAE,eAAgB,CAAC;EAC7D;EACA,MAAMC,aAAa,GAAGH,UAAU,CAACI,SAAS,CAAE,kBAAmB,CAAC;EAChE,MAAMC,OAAO,GAAGF,aAAa,GAAGA,aAAa,CAAEH,UAAW,CAAC,GAAGA,UAAU,CAACI,SAAS,CAAE,YAAa,CAAC,CAAEJ,UAAW,CAAC;EAChH;EACA,MAAMM,oBAAoB,GAAGN,UAAU,CAACI,SAAS,CAAE,sBAAuB,CAAC;EAC3E;EACA,MAAMG,iBAAiB,GAAGP,UAAU,CAACI,SAAS,CAAE,mBAAoB,CAAC;EAErE,MAAMT,IAAI,GAAGD,YAAY,CAAEK,KAAK,CAACS,OAAO,CAAC,CAAE,CAAC;EAC5C,MAAMC,eAAe,GAAGf,YAAY,CAAEK,KAAK,CAACW,cAAc,CAAC,CAAE,CAAC;EAC9D,MAAMC,KAAK,GAAGjB,YAAY,CAAEK,KAAK,CAACa,QAAQ,CAAC,CAAE,CAAC;EAE9C,MAAMC,MAAM,GAAG,CAAC,CAAC;EACjBA,MAAM,CAACC,kBAAkB,GAAGL,eAAe,KAAK,EAAE;EAClDI,MAAM,CAACE,QAAQ,GAAGJ,KAAK,KAAK,EAAE;EAC9BE,MAAM,CAACG,cAAc,GAAG,EAAE;;EAE1B;AACD;AACA;AACA;EACC,IAAKT,iBAAiB,EAAG;IACxB,IAAKA,iBAAiB,CAAEZ,IAAK,CAAC,GAAG,GAAG,EAAG;MACtC,OAAOkB,MAAM;IACd;EACD,CAAC,MAAM,IAAK,IAAAI,mBAAU,EAAEtB,IAAK,CAAC,GAAG,GAAG,EAAG;IACtC,OAAOkB,MAAM;EACd;EAEA,MAAMK,WAAW,GAAG,IAAAC,sCAAsB,EAAExB,IAAK,CAAC,CAACyB,GAAG,CAAEC,UAAU,IAAIA,UAAU,CAAE,CAAC,CAAG,CAAC;EACvF,MAAMC,UAAU,GAAG,CAClBvB,KAAK,CAACwB,UAAU,CAAC,CAAC,EAClBxB,KAAK,CAACyB,WAAW,CAAC,CAAC,EACnBb,KAAK,EACLF,eAAe,EACfS,WAAW,CAACO,IAAI,CAAE,GAAI,CAAC,CACvB;;EAED;EACA,MAAMC,aAAa,GAAGpB,oBAAoB,GAAG,EAAE,GAAG,IAAAqB,8CAAqB,EAAEhC,IAAI,CAACiC,MAAM,CAAEN,UAAU,CAACG,IAAI,CAAE,GAAI,CAAE,CAAE,CAAC;EAEhH,MAAMI,qBAAqB,GAAG,IAAAC,yCAAyB,EAAEnC,IAAK,CAAC;EAC/D,MAAMoC,sBAAsB,GAAG,IAAAC,0CAAiB,EAAEH,qBAAqB,EAAEH,aAAa,EAAErB,OAAO,EAAEJ,aAAa,EAAEK,oBAAqB,CAAC;EAEtI,MAAM2B,iCAAiC,GAAG,IAAAC,6DAAoC,EAC7EZ,UAAU,EAAEI,aAAa,EAAErB,OAAO,EAAEJ,aAAa,EAAEK,oBAAqB,CAAC;;EAE1E;AACD;AACA;AACA;EACC2B,iCAAiC,CAACE,OAAO,CAAEC,YAAY,IAAIA,YAAY,CAACC,cAAc,CAAED,YAAY,CAACE,cAAc,CAAC,CAAC,GAAG,CAAE,CAAE,CAAC;EAE7H,MAAMC,cAAc,GAAG,IAAAC,qDAA4B,EAAEP,iCAAiC,CAACL,MAAM,CAAEG,sBAAuB,CAAE,CAAC;EACzH,IAAAU,2CAAkB,EAAEF,cAAe,CAAC;;EAEpC;AACD;AACA;AACA;AACA;AACA;AACA;EACC,IAAIG,0BAA0B,GAAG,CAAC;EAElC,IAAKrC,OAAO,KAAKsC,oBAAW,EAAG;IAC9BD,0BAA0B,GAAG,CAAC;EAC/B;;EAEA;AACD;AACA;AACA;EACC7B,MAAM,CAACG,cAAc,GAAG,IAAA4B,YAAI,EAAE,IAAAC,6CAAoB,EAAEN,cAAc,EAAEG,0BAA2B,CAAC,EAAE,GAAI,CAAC;EAEvG,OAAO7B,MAAM;AACd;AAAC,IAAAiC,QAAA,GAAAC,OAAA,CAAAtD,OAAA,GAEcK,mCAAmC","ignoreList":[]}

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

@@ -0,0 +1,122 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _getWords = _interopRequireDefault(require("../helpers/word/getWords.js"));
+var _getSentences = _interopRequireDefault(require("../helpers/sentence/getSentences"));
+var _stripSpaces = _interopRequireDefault(require("../helpers/sanitize/stripSpaces.js"));
+var _stripHTMLTags = require("../helpers/sanitize/stripHTMLTags.js");
+var _lodash = require("lodash");
+var _htmlParser = _interopRequireDefault(require("../helpers/html/htmlParser"));
+var _helpers = require("../helpers");
+var _stripNonTextTags = _interopRequireDefault(require("../helpers/sanitize/stripNonTextTags"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Compares the first word of each sentence with the first word of the following sentence.
+ *
+ * @param {string} currentSentenceBeginning The first word of the current sentence.
+ * @param {string} nextSentenceBeginning The first word of the next sentence.
+ * @returns {boolean} Returns true if sentence beginnings match.
+ */
+const startsWithSameWord = function (currentSentenceBeginning, nextSentenceBeginning) {
+  return !(0, _lodash.isEmpty)(currentSentenceBeginning) && currentSentenceBeginning === nextSentenceBeginning;
+};
+
+/**
+ * Counts the number of similar sentence beginnings.
+ *
+ * @param {Array} sentenceBeginnings The array containing the first word of each sentence.
+ * @param {Array} sentences The array containing all sentences.
+ * @returns {Array} The array containing the objects containing the first words and the corresponding counts.
+ */
+const compareFirstWords = function (sentenceBeginnings, sentences) {
+  const consecutiveFirstWords = [];
+  let foundSentences = [];
+  let sameBeginnings = 1;
+  (0, _lodash.forEach)(sentenceBeginnings, function (beginning, i) {
+    const currentSentenceBeginning = beginning;
+    const nextSentenceBeginning = sentenceBeginnings[i + 1];
+    foundSentences.push(sentences[i]);
+    if (startsWithSameWord(currentSentenceBeginning, nextSentenceBeginning)) {
+      sameBeginnings++;
+    } else {
+      consecutiveFirstWords.push({
+        word: currentSentenceBeginning,
+        count: sameBeginnings,
+        sentences: foundSentences
+      });
+      sameBeginnings = 1;
+      foundSentences = [];
+    }
+  });
+  return consecutiveFirstWords;
+};
+
+/**
+ * Retrieves the first word from the sentence. If the first or second word is on an exception list of words that should not be considered as sentence
+ * beginnings, the following word is also retrieved.
+ *
+ * @param {string}  sentence                The sentence to retrieve the first word from.
+ * @param {Array}   firstWordExceptions     First word exceptions to match against.
+ * @param {Array}   secondWordExceptions    Second word exceptions to match against.
+ * @param {function}	getWordsCustomHelper   The language-specific helper function to retrieve words from text.
+ *
+ * @returns {string} The first word of the sentence.
+ */
+function getSentenceBeginning(sentence, firstWordExceptions, secondWordExceptions, getWordsCustomHelper) {
+  const stripped = (0, _stripHTMLTags.stripFullTags)((0, _stripSpaces.default)(sentence));
+  let words = getWordsCustomHelper ? getWordsCustomHelper(stripped) : (0, _getWords.default)(stripped);
+  words = words.filter(word => /^\p{L}/u.test(word));
+  if (words.length === 0) {
+    return '';
+  }
+  let firstWord = words[0].toLocaleLowerCase();
+  if (firstWordExceptions.indexOf(firstWord) > -1 && words.length > 1) {
+    firstWord = firstWord + ' ' + words[1];
+    if (secondWordExceptions) {
+      if (secondWordExceptions.includes(words[1])) {
+        firstWord = firstWord + ' ' + words[2];
+      }
+    }
+  }
+  return firstWord;
+}
+
+/**
+ * Gets the first word of each sentence from the text, and returns an object containing the first word of each sentence and the corresponding counts.
+ *
+ * @param {Paper}       paper       The Paper object to get the text from.
+ * @param {Researcher}  researcher  The researcher this research is a part of.
+ *
+ * @returns {Object} The object containing the first word of each sentence and the corresponding counts.
+ */
+function _default(paper, researcher) {
+  const firstWordExceptions = researcher.getConfig('firstWordExceptions');
+  const secondWordExceptions = researcher.getConfig('secondWordExceptions');
+  const getWordsCustomHelper = researcher.getHelper('getWordsCustomHelper');
+  const memoizedTokenizer = researcher.getHelper('memoizedTokenizer');
+  let text = paper.getText();
+  text = (0, _htmlParser.default)(text);
+  text = (0, _stripNonTextTags.default)(text);
+  text = (0, _helpers.filterShortcodesFromHTML)(text, paper._attributes && paper._attributes.shortcodes);
+
+  // Remove any HTML whitespace padding and replace it with a single whitespace.
+  text = text.replace(/[\s\n]+/g, ' ');
+
+  // Exclude text inside tables.
+  text = text.replace(/<figure class='wp-block-table'>.*<\/figure>/gs, '');
+  let sentences = (0, _getSentences.default)(text, memoizedTokenizer);
+  let sentenceBeginnings = sentences.map(function (sentence) {
+    return getSentenceBeginning(sentence, firstWordExceptions, secondWordExceptions, getWordsCustomHelper);
+  });
+  sentences = sentences.filter(function (sentence) {
+    const stripped = (0, _stripSpaces.default)(sentence);
+    const words = getWordsCustomHelper ? getWordsCustomHelper(stripped) : (0, _getWords.default)(stripped);
+    return words.length > 0;
+  });
+  sentenceBeginnings = (0, _lodash.filter)(sentenceBeginnings);
+  return compareFirstWords(sentenceBeginnings, sentences);
+}
+//# sourceMappingURL=getSentenceBeginnings.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"getSentenceBeginnings.js","names":["_getWords","_interopRequireDefault","require","_getSentences","_stripSpaces","_stripHTMLTags","_lodash","_htmlParser","_helpers","_stripNonTextTags","e","__esModule","default","startsWithSameWord","currentSentenceBeginning","nextSentenceBeginning","isEmpty","compareFirstWords","sentenceBeginnings","sentences","consecutiveFirstWords","foundSentences","sameBeginnings","forEach","beginning","i","push","word","count","getSentenceBeginning","sentence","firstWordExceptions","secondWordExceptions","getWordsCustomHelper","stripped","stripTags","stripSpaces","words","getWords","filter","test","length","firstWord","toLocaleLowerCase","indexOf","includes","_default","paper","researcher","getConfig","getHelper","memoizedTokenizer","text","getText","removeHtmlBlocks","stripNonTextTags","filterShortcodesFromHTML","_attributes","shortcodes","replace","getSentences","map"],"sources":["../../../../src/languageProcessing/researches/getSentenceBeginnings.js"],"sourcesContent":["import getWords from '../helpers/word/getWords.js';\nimport getSentences from '../helpers/sentence/getSentences';\nimport stripSpaces from '../helpers/sanitize/stripSpaces.js';\nimport {stripFullTags as stripTags} from '../helpers/sanitize/stripHTMLTags.js';\n\nimport {filter, forEach, isEmpty} from 'lodash';\nimport removeHtmlBlocks from '../helpers/html/htmlParser';\nimport {filterShortcodesFromHTML} from '../helpers';\nimport stripNonTextTags from '@axyseo/languageProcessing/helpers/sanitize/stripNonTextTags';\n\n/**\n * Compares the first word of each sentence with the first word of the following sentence.\n *\n * @param {string} currentSentenceBeginning The first word of the current sentence.\n * @param {string} nextSentenceBeginning The first word of the next sentence.\n * @returns {boolean} Returns true if sentence beginnings match.\n */\nconst startsWithSameWord = function(currentSentenceBeginning, nextSentenceBeginning) {\n  return !isEmpty(currentSentenceBeginning) && currentSentenceBeginning === nextSentenceBeginning;\n};\n\n/**\n * Counts the number of similar sentence beginnings.\n *\n * @param {Array} sentenceBeginnings The array containing the first word of each sentence.\n * @param {Array} sentences The array containing all sentences.\n * @returns {Array} The array containing the objects containing the first words and the corresponding counts.\n */\nconst compareFirstWords = function(sentenceBeginnings, sentences) {\n  const consecutiveFirstWords = [];\n  let foundSentences = [];\n  let sameBeginnings = 1;\n\n  forEach(sentenceBeginnings, function(beginning, i) {\n    const currentSentenceBeginning = beginning;\n    const nextSentenceBeginning = sentenceBeginnings[i + 1];\n    foundSentences.push(sentences[i]);\n\n    if (startsWithSameWord(currentSentenceBeginning, nextSentenceBeginning)) {\n      sameBeginnings++;\n    } else {\n      consecutiveFirstWords.push({\n        word: currentSentenceBeginning,\n        count: sameBeginnings,\n        sentences: foundSentences\n      });\n      sameBeginnings = 1;\n      foundSentences = [];\n    }\n  });\n\n  return consecutiveFirstWords;\n};\n\n/**\n * Retrieves the first word from the sentence. If the first or second word is on an exception list of words that should not be considered as sentence\n * beginnings, the following word is also retrieved.\n *\n * @param {string}  sentence                The sentence to retrieve the first word from.\n * @param {Array}   firstWordExceptions     First word exceptions to match against.\n * @param {Array}   secondWordExceptions    Second word exceptions to match against.\n * @param {function}\tgetWordsCustomHelper   The language-specific helper function to retrieve words from text.\n *\n * @returns {string} The first word of the sentence.\n */\nfunction getSentenceBeginning(\n  sentence,\n  firstWordExceptions,\n  secondWordExceptions,\n  getWordsCustomHelper\n) {\n  const stripped = stripTags(stripSpaces(sentence));\n  let words = getWordsCustomHelper ? getWordsCustomHelper(stripped) : getWords(stripped);\n\n  words = words.filter(word => /^\\p{L}/u.test(word));\n\n  if (words.length === 0) {\n    return '';\n  }\n\n  let firstWord = words[0].toLocaleLowerCase();\n\n  if (firstWordExceptions.indexOf(firstWord) > -1 && words.length > 1) {\n    firstWord = firstWord + ' ' + words[1];\n    if (secondWordExceptions) {\n      if (secondWordExceptions.includes(words[1])) {\n        firstWord = firstWord + ' ' + words[2];\n      }\n    }\n  }\n\n  return firstWord;\n}\n\n/**\n * Gets the first word of each sentence from the text, and returns an object containing the first word of each sentence and the corresponding counts.\n *\n * @param {Paper}       paper       The Paper object to get the text from.\n * @param {Researcher}  researcher  The researcher this research is a part of.\n *\n * @returns {Object} The object containing the first word of each sentence and the corresponding counts.\n */\nexport default function(paper, researcher) {\n  const firstWordExceptions = researcher.getConfig('firstWordExceptions');\n  const secondWordExceptions = researcher.getConfig('secondWordExceptions');\n  const getWordsCustomHelper = researcher.getHelper('getWordsCustomHelper');\n  const memoizedTokenizer = researcher.getHelper('memoizedTokenizer');\n\n  let text = paper.getText();\n  text = removeHtmlBlocks(text);\n  text = stripNonTextTags(text);\n  text = filterShortcodesFromHTML(text, paper._attributes && paper._attributes.shortcodes);\n\n  // Remove any HTML whitespace padding and replace it with a single whitespace.\n  text = text.replace(/[\\s\\n]+/g, ' ');\n\n  // Exclude text inside tables.\n  text = text.replace(/<figure class='wp-block-table'>.*<\\/figure>/gs, '');\n\n  let sentences = getSentences(text, memoizedTokenizer);\n\n  let sentenceBeginnings = sentences.map(function(sentence) {\n    return getSentenceBeginning(\n      sentence,\n      firstWordExceptions,\n      secondWordExceptions,\n      getWordsCustomHelper\n    );\n  });\n\n  sentences = sentences.filter(function(sentence) {\n    const stripped = stripSpaces(sentence);\n    const words = getWordsCustomHelper ? getWordsCustomHelper(stripped) : getWords(stripped);\n    return words.length > 0;\n  });\n  sentenceBeginnings = filter(sentenceBeginnings);\n\n  return compareFirstWords(sentenceBeginnings, sentences);\n}\n"],"mappings":";;;;;;AAAA,IAAAA,SAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,aAAA,GAAAF,sBAAA,CAAAC,OAAA;AACA,IAAAE,YAAA,GAAAH,sBAAA,CAAAC,OAAA;AACA,IAAAG,cAAA,GAAAH,OAAA;AAEA,IAAAI,OAAA,GAAAJ,OAAA;AACA,IAAAK,WAAA,GAAAN,sBAAA,CAAAC,OAAA;AACA,IAAAM,QAAA,GAAAN,OAAA;AACA,IAAAO,iBAAA,GAAAR,sBAAA,CAAAC,OAAA;AAA4F,SAAAD,uBAAAS,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAE5F;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,kBAAkB,GAAG,SAAAA,CAASC,wBAAwB,EAAEC,qBAAqB,EAAE;EACnF,OAAO,CAAC,IAAAC,eAAO,EAACF,wBAAwB,CAAC,IAAIA,wBAAwB,KAAKC,qBAAqB;AACjG,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,iBAAiB,GAAG,SAAAA,CAASC,kBAAkB,EAAEC,SAAS,EAAE;EAChE,MAAMC,qBAAqB,GAAG,EAAE;EAChC,IAAIC,cAAc,GAAG,EAAE;EACvB,IAAIC,cAAc,GAAG,CAAC;EAEtB,IAAAC,eAAO,EAACL,kBAAkB,EAAE,UAASM,SAAS,EAAEC,CAAC,EAAE;IACjD,MAAMX,wBAAwB,GAAGU,SAAS;IAC1C,MAAMT,qBAAqB,GAAGG,kBAAkB,CAACO,CAAC,GAAG,CAAC,CAAC;IACvDJ,cAAc,CAACK,IAAI,CAACP,SAAS,CAACM,CAAC,CAAC,CAAC;IAEjC,IAAIZ,kBAAkB,CAACC,wBAAwB,EAAEC,qBAAqB,CAAC,EAAE;MACvEO,cAAc,EAAE;IAClB,CAAC,MAAM;MACLF,qBAAqB,CAACM,IAAI,CAAC;QACzBC,IAAI,EAAEb,wBAAwB;QAC9Bc,KAAK,EAAEN,cAAc;QACrBH,SAAS,EAAEE;MACb,CAAC,CAAC;MACFC,cAAc,GAAG,CAAC;MAClBD,cAAc,GAAG,EAAE;IACrB;EACF,CAAC,CAAC;EAEF,OAAOD,qBAAqB;AAC9B,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASS,oBAAoBA,CAC3BC,QAAQ,EACRC,mBAAmB,EACnBC,oBAAoB,EACpBC,oBAAoB,EACpB;EACA,MAAMC,QAAQ,GAAG,IAAAC,4BAAS,EAAC,IAAAC,oBAAW,EAACN,QAAQ,CAAC,CAAC;EACjD,IAAIO,KAAK,GAAGJ,oBAAoB,GAAGA,oBAAoB,CAACC,QAAQ,CAAC,GAAG,IAAAI,iBAAQ,EAACJ,QAAQ,CAAC;EAEtFG,KAAK,GAAGA,KAAK,CAACE,MAAM,CAACZ,IAAI,IAAI,SAAS,CAACa,IAAI,CAACb,IAAI,CAAC,CAAC;EAElD,IAAIU,KAAK,CAACI,MAAM,KAAK,CAAC,EAAE;IACtB,OAAO,EAAE;EACX;EAEA,IAAIC,SAAS,GAAGL,KAAK,CAAC,CAAC,CAAC,CAACM,iBAAiB,CAAC,CAAC;EAE5C,IAAIZ,mBAAmB,CAACa,OAAO,CAACF,SAAS,CAAC,GAAG,CAAC,CAAC,IAAIL,KAAK,CAACI,MAAM,GAAG,CAAC,EAAE;IACnEC,SAAS,GAAGA,SAAS,GAAG,GAAG,GAAGL,KAAK,CAAC,CAAC,CAAC;IACtC,IAAIL,oBAAoB,EAAE;MACxB,IAAIA,oBAAoB,CAACa,QAAQ,CAACR,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE;QAC3CK,SAAS,GAAGA,SAAS,GAAG,GAAG,GAAGL,KAAK,CAAC,CAAC,CAAC;MACxC;IACF;EACF;EAEA,OAAOK,SAAS;AAClB;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAI,SAASC,KAAK,EAAEC,UAAU,EAAE;EACzC,MAAMjB,mBAAmB,GAAGiB,UAAU,CAACC,SAAS,CAAC,qBAAqB,CAAC;EACvE,MAAMjB,oBAAoB,GAAGgB,UAAU,CAACC,SAAS,CAAC,sBAAsB,CAAC;EACzE,MAAMhB,oBAAoB,GAAGe,UAAU,CAACE,SAAS,CAAC,sBAAsB,CAAC;EACzE,MAAMC,iBAAiB,GAAGH,UAAU,CAACE,SAAS,CAAC,mBAAmB,CAAC;EAEnE,IAAIE,IAAI,GAAGL,KAAK,CAACM,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAG,IAAAE,mBAAgB,EAACF,IAAI,CAAC;EAC7BA,IAAI,GAAG,IAAAG,yBAAgB,EAACH,IAAI,CAAC;EAC7BA,IAAI,GAAG,IAAAI,iCAAwB,EAACJ,IAAI,EAAEL,KAAK,CAACU,WAAW,IAAIV,KAAK,CAACU,WAAW,CAACC,UAAU,CAAC;;EAExF;EACAN,IAAI,GAAGA,IAAI,CAACO,OAAO,CAAC,UAAU,EAAE,GAAG,CAAC;;EAEpC;EACAP,IAAI,GAAGA,IAAI,CAACO,OAAO,CAAC,+CAA+C,EAAE,EAAE,CAAC;EAExE,IAAIxC,SAAS,GAAG,IAAAyC,qBAAY,EAACR,IAAI,EAAED,iBAAiB,CAAC;EAErD,IAAIjC,kBAAkB,GAAGC,SAAS,CAAC0C,GAAG,CAAC,UAAS/B,QAAQ,EAAE;IACxD,OAAOD,oBAAoB,CACzBC,QAAQ,EACRC,mBAAmB,EACnBC,oBAAoB,EACpBC,oBACF,CAAC;EACH,CAAC,CAAC;EAEFd,SAAS,GAAGA,SAAS,CAACoB,MAAM,CAAC,UAAST,QAAQ,EAAE;IAC9C,MAAMI,QAAQ,GAAG,IAAAE,oBAAW,EAACN,QAAQ,CAAC;IACtC,MAAMO,KAAK,GAAGJ,oBAAoB,GAAGA,oBAAoB,CAACC,QAAQ,CAAC,GAAG,IAAAI,iBAAQ,EAACJ,QAAQ,CAAC;IACxF,OAAOG,KAAK,CAACI,MAAM,GAAG,CAAC;EACzB,CAAC,CAAC;EACFvB,kBAAkB,GAAG,IAAAqB,cAAM,EAACrB,kBAAkB,CAAC;EAE/C,OAAOD,iBAAiB,CAACC,kBAAkB,EAAEC,SAAS,CAAC;AACzD","ignoreList":[]}

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

@@ -0,0 +1,60 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _getSubheadingTexts = _interopRequireDefault(require("../helpers/html/getSubheadingTexts"));
+var _countWords = _interopRequireDefault(require("../helpers/word/countWords"));
+var _lodash = require("lodash");
+var _htmlParser = _interopRequireDefault(require("../helpers/html/htmlParser"));
+var _helpers = require("../helpers");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Gets the subheadings from the text and returns the length of these subheading in an array.
+ *
+ * @param {Paper}       paper       The Paper object to get the text from.
+ * @param {Researcher}  researcher  The researcher to use for analysis.
+ *
+ * @returns {Object} The object containing the array of found subheadings and the length of the text before the first subheading.
+ */
+function _default(paper, researcher) {
+  let text = paper.getText();
+  text = (0, _htmlParser.default)(text);
+  text = (0, _helpers.filterShortcodesFromHTML)(text, paper._attributes && paper._attributes.shortcodes);
+  const matches = (0, _getSubheadingTexts.default)(text);
+
+  // An optional custom helper to count length to use instead of countWords.
+  const customCountLength = researcher.getHelper("customCountLength");
+  const foundSubheadings = [];
+  (0, _lodash.forEach)(matches, function (match) {
+    foundSubheadings.push({
+      subheading: match.subheading,
+      text: match.text,
+      countLength: customCountLength ? customCountLength(match.text) : (0, _countWords.default)(match.text),
+      index: match.index
+    });
+  });
+  let textBeforeFirstSubheadingLength = 0;
+  let textBeforeFirstSubheading = "";
+  if (foundSubheadings.length > 0) {
+    // Find first subheading.
+    const firstSubheading = foundSubheadings[0];
+    // Retrieve text preceding first subheading.
+    textBeforeFirstSubheading = text.slice(0, firstSubheading.index);
+    textBeforeFirstSubheadingLength = customCountLength ? customCountLength(textBeforeFirstSubheading) : (0, _countWords.default)(textBeforeFirstSubheading);
+  }
+
+  // Check if there is a text before the first subheading.
+  if (textBeforeFirstSubheadingLength > 0 && textBeforeFirstSubheading !== "") {
+    // Also add the text before the first subheading to the array.
+    foundSubheadings.unshift({
+      // Assign an empty string for the subheading for text that comes before the first subheading.
+      subheading: "",
+      text: textBeforeFirstSubheading,
+      countLength: textBeforeFirstSubheadingLength
+    });
+  }
+  return foundSubheadings;
+}
+//# sourceMappingURL=getSubheadingTextLengths.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"getSubheadingTextLengths.js","names":["_getSubheadingTexts","_interopRequireDefault","require","_countWords","_lodash","_htmlParser","_helpers","e","__esModule","default","_default","paper","researcher","text","getText","removeHtmlBlocks","filterShortcodesFromHTML","_attributes","shortcodes","matches","getSubheadingTexts","customCountLength","getHelper","foundSubheadings","forEach","match","push","subheading","countLength","countWords","index","textBeforeFirstSubheadingLength","textBeforeFirstSubheading","length","firstSubheading","slice","unshift"],"sources":["../../../../src/languageProcessing/researches/getSubheadingTextLengths.js"],"sourcesContent":["import getSubheadingTexts from \"../helpers/html/getSubheadingTexts\";\nimport countWords from \"../helpers/word/countWords\";\nimport { forEach } from \"lodash\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\n\n/**\n * Gets the subheadings from the text and returns the length of these subheading in an array.\n *\n * @param {Paper}       paper       The Paper object to get the text from.\n * @param {Researcher}  researcher  The researcher to use for analysis.\n *\n * @returns {Object} The object containing the array of found subheadings and the length of the text before the first subheading.\n */\nexport default function( paper, researcher ) {\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\tconst matches = getSubheadingTexts( text );\n\n\t// An optional custom helper to count length to use instead of countWords.\n\tconst customCountLength = researcher.getHelper( \"customCountLength\" );\n\n\tconst foundSubheadings = [];\n\n\tforEach( matches, function( match ) {\n\t\tfoundSubheadings.push( {\n\t\t\tsubheading: match.subheading,\n\t\t\ttext: match.text,\n\t\t\tcountLength: customCountLength ? customCountLength( match.text ) : countWords( match.text ),\n\t\t\tindex: match.index,\n\t\t} );\n\t} );\n\n\tlet textBeforeFirstSubheadingLength = 0;\n\tlet textBeforeFirstSubheading = \"\";\n\tif ( foundSubheadings.length > 0 ) {\n\t\t// Find first subheading.\n\t\tconst firstSubheading =  foundSubheadings[ 0 ];\n\t\t// Retrieve text preceding first subheading.\n\t\ttextBeforeFirstSubheading = text.slice( 0, firstSubheading.index );\n\t\ttextBeforeFirstSubheadingLength = customCountLength\n\t\t\t? customCountLength( textBeforeFirstSubheading )\n\t\t\t: countWords( textBeforeFirstSubheading );\n\t}\n\n\t// Check if there is a text before the first subheading.\n\tif ( textBeforeFirstSubheadingLength > 0 && textBeforeFirstSubheading !== \"\" ) {\n\t\t// Also add the text before the first subheading to the array.\n\t\tfoundSubheadings.unshift( {\n\t\t\t// Assign an empty string for the subheading for text that comes before the first subheading.\n\t\t\tsubheading: \"\",\n\t\t\ttext: textBeforeFirstSubheading,\n\t\t\tcountLength: textBeforeFirstSubheadingLength,\n\t\t} );\n\t}\n\n\treturn foundSubheadings;\n}\n"],"mappings":";;;;;;AAAA,IAAAA,mBAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,WAAA,GAAAF,sBAAA,CAAAC,OAAA;AACA,IAAAE,OAAA,GAAAF,OAAA;AACA,IAAAG,WAAA,GAAAJ,sBAAA,CAAAC,OAAA;AACA,IAAAI,QAAA,GAAAJ,OAAA;AAAsD,SAAAD,uBAAAM,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,IAAIC,IAAI,GAAGF,KAAK,CAACG,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAG,IAAAE,mBAAgB,EAAEF,IAAK,CAAC;EAC/BA,IAAI,GAAG,IAAAG,iCAAwB,EAAEH,IAAI,EAAEF,KAAK,CAACM,WAAW,IAAIN,KAAK,CAACM,WAAW,CAACC,UAAW,CAAC;EAC1F,MAAMC,OAAO,GAAG,IAAAC,2BAAkB,EAAEP,IAAK,CAAC;;EAE1C;EACA,MAAMQ,iBAAiB,GAAGT,UAAU,CAACU,SAAS,CAAE,mBAAoB,CAAC;EAErE,MAAMC,gBAAgB,GAAG,EAAE;EAE3B,IAAAC,eAAO,EAAEL,OAAO,EAAE,UAAUM,KAAK,EAAG;IACnCF,gBAAgB,CAACG,IAAI,CAAE;MACtBC,UAAU,EAAEF,KAAK,CAACE,UAAU;MAC5Bd,IAAI,EAAEY,KAAK,CAACZ,IAAI;MAChBe,WAAW,EAAEP,iBAAiB,GAAGA,iBAAiB,CAAEI,KAAK,CAACZ,IAAK,CAAC,GAAG,IAAAgB,mBAAU,EAAEJ,KAAK,CAACZ,IAAK,CAAC;MAC3FiB,KAAK,EAAEL,KAAK,CAACK;IACd,CAAE,CAAC;EACJ,CAAE,CAAC;EAEH,IAAIC,+BAA+B,GAAG,CAAC;EACvC,IAAIC,yBAAyB,GAAG,EAAE;EAClC,IAAKT,gBAAgB,CAACU,MAAM,GAAG,CAAC,EAAG;IAClC;IACA,MAAMC,eAAe,GAAIX,gBAAgB,CAAE,CAAC,CAAE;IAC9C;IACAS,yBAAyB,GAAGnB,IAAI,CAACsB,KAAK,CAAE,CAAC,EAAED,eAAe,CAACJ,KAAM,CAAC;IAClEC,+BAA+B,GAAGV,iBAAiB,GAChDA,iBAAiB,CAAEW,yBAA0B,CAAC,GAC9C,IAAAH,mBAAU,EAAEG,yBAA0B,CAAC;EAC3C;;EAEA;EACA,IAAKD,+BAA+B,GAAG,CAAC,IAAIC,yBAAyB,KAAK,EAAE,EAAG;IAC9E;IACAT,gBAAgB,CAACa,OAAO,CAAE;MACzB;MACAT,UAAU,EAAE,EAAE;MACdd,IAAI,EAAEmB,yBAAyB;MAC/BJ,WAAW,EAAEG;IACd,CAAE,CAAC;EACJ;EAEA,OAAOR,gBAAgB;AACxB","ignoreList":[]}

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

@@ -0,0 +1,183 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _quotes = require("../helpers/sanitize/quotes");
+var _buildTopicStems = require("../helpers/morphology/buildTopicStems");
+var _lodash = require("lodash");
+var _getAllWordsFromPaper = _interopRequireDefault(require("../helpers/morphology/getAllWordsFromPaper"));
+var _parseSynonyms = _interopRequireDefault(require("../helpers/sanitize/parseSynonyms"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * A stem with accompanying forms.
+ *
+ * @param {string}      stem    The word stem.
+ * @param {string[]}    forms   The word forms for the stem.
+ *
+ * @constructor
+ */
+function StemWithForms(stem, forms) {
+  this.stem = stem;
+  this.forms = forms;
+}
+
+/**
+ * A result for all topic forms.
+ *
+ * @param {Array[]} keyphraseForms  All keyphrase forms.
+ * @param {Array[]} synonymsForms   All synonym forms.
+ * @constructor
+ */
+function Result(keyphraseForms = [], synonymsForms = []) {
+  this.keyphraseForms = keyphraseForms;
+  this.synonymsForms = synonymsForms;
+}
+
+/**
+ * Takes a stem-original pair and returns the accompanying forms for the stem that were found in the paper. Additionally
+ * adds a sanitized version of the original word and (for specific languages) creates basic word forms.
+ *
+ * @param {StemOriginalPair}    stemOriginalPair            The stem-original pair for which to get forms.
+ * @param {StemWithForms[]}     paperWordsGroupedByStems    All word forms in the paper grouped by stem.
+ * @param {Function|null}       createBasicWordForms        A function to create basic word forms (if available).
+ *
+ * @returns {string[]} All forms found in the paper for the given stem, plus a sanitized version of the original word.
+ */
+function replaceStemWithForms(stemOriginalPair, paperWordsGroupedByStems, createBasicWordForms) {
+  const matchingStemFormPair = paperWordsGroupedByStems.find(element => element.stem === stemOriginalPair.stem);
+  const originalSanitized = (0, _quotes.normalizeSingle)((0, _lodash.escapeRegExp)(stemOriginalPair.original));
+  const forms = matchingStemFormPair ? [originalSanitized, ...matchingStemFormPair.forms] : [originalSanitized];
+
+  // Add extra forms for languages for which we have basic word form support.
+  if (createBasicWordForms) {
+    forms.push(...createBasicWordForms(stemOriginalPair.original));
+  }
+
+  /*
+   * Return original and found or created forms.
+   * Only return original if no matching forms were found in the text and no forms could be created.
+   */
+  return [...new Set(forms)];
+}
+
+/**
+ * Extracts the stems from all keyphrase and synonym stems.
+ *
+ * @param {TopicPhrase}   keyphrase  A topic phrase.
+ * @param {TopicPhrase[]} synonyms   An array of topic phrases.
+ *
+ * @returns {string[]} All word stems of they keyphrase and synonyms.
+ */
+function extractStems(keyphrase, synonyms) {
+  const keyphraseStemsOnly = keyphrase.stemOriginalPairs.length === 0 ? [] : keyphrase.getStems();
+  const synonymsStemsOnly = synonyms.length === 0 ? [] : synonyms.map(topicPhrase => topicPhrase.getStems());
+  return [...keyphraseStemsOnly, ...(0, _lodash.flattenDeep)(synonymsStemsOnly)];
+}
+
+/**
+ * Constructs the result with forms for a topic phrase (i.e., a keyphrase or a synonym).
+ *
+ * @param {TopicPhrase}     topicPhrase              The topic phrase for which to construct the result.
+ * @param {StemWithForms[]} paperWordsGroupedByStems All word forms in the paper grouped by stem.
+ * @param {Function|null}   createBasicWordForms     A function to create basic word forms (if available).
+ *
+ * @returns {Array.<string[]>} The word forms for a given topic phrase, grouped by original topic phrase word.
+ */
+function constructTopicPhraseResult(topicPhrase, paperWordsGroupedByStems, createBasicWordForms) {
+  // Empty result for an empty topic phrase.
+  if (topicPhrase.stemOriginalPairs.length === 0) {
+    return [];
+  }
+  if (topicPhrase.exactMatch) {
+    return [[topicPhrase.stemOriginalPairs[0].stem]];
+  }
+  return topicPhrase.stemOriginalPairs.map(function (stemOriginalPair) {
+    return replaceStemWithForms(stemOriginalPair, paperWordsGroupedByStems, createBasicWordForms);
+  });
+}
+
+/**
+ * Gets all matching word forms for the keyphrase and synonyms. Stems are either collected from
+ * the paper or, for specific languages, directly created.
+ *
+ * @param {string}          keyphrase               	The keyphrase.
+ * @param {string[]}        synonyms                	The synonyms.
+ * @param {string[]}        allWordsFromPaper       	All words found in the paper.
+ * @param {string[]}        functionWords           	The function words for a given language (if available).
+ * @param {Function|null}   stemmer                 	A stemmer (if available).
+ * @param {Function|null}   createBasicWordForms    	A function to create basic word forms (if available).
+ * @param {boolean}   		areHyphensWordBoundaries	Whether hyphens should be treated as word boundaries.
+
+ * @returns {Object} Object with an array of keyphrase forms and an array of arrays of synonyms forms, based on the forms
+ * found in the text or created forms.
+ */
+function getWordForms(keyphrase, synonyms, allWordsFromPaper, functionWords, stemmer, createBasicWordForms, areHyphensWordBoundaries) {
+  const topicPhrases = (0, _buildTopicStems.collectStems)(keyphrase, synonyms, stemmer, functionWords, areHyphensWordBoundaries);
+  const keyphraseStemmed = topicPhrases.keyphraseStems;
+  const synonymsStemmed = topicPhrases.synonymsStems;
+
+  // Return an empty result when no keyphrase and synonyms have been set.
+  if (keyphraseStemmed.stemOriginalPairs.length === 0 && synonymsStemmed.length === 0) {
+    return new Result();
+  }
+
+  // Return exact match if all topic phrases contain exact match. Forms don't need to be built in that case.
+  const allTopicPhrases = [keyphraseStemmed, ...synonymsStemmed];
+  if (allTopicPhrases.every(topicPhrase => topicPhrase.exactMatch === true)) {
+    return new Result([[keyphraseStemmed.stemOriginalPairs[0].stem]], synonymsStemmed.map(synonym => [[synonym.stemOriginalPairs[0].stem]]));
+  }
+
+  // Get all stems from the keyphrase and synonyms.
+  const topicStemsFlat = [...new Set(extractStems(keyphraseStemmed, synonymsStemmed))];
+
+  /*
+   * Get all words from the paper text, title, meta description and slug.
+   * Filter duplicates and function words.
+   */
+  const paperWords = [...new Set(allWordsFromPaper.filter(word => !functionWords.includes(word)))];
+
+  // Add stems to words from the paper, filter out all forms that aren't in the keyphrase or synonyms and order alphabetically.
+  const paperWordsWithStems = paperWords.map(word => new _buildTopicStems.StemOriginalPair(stemmer(word), word)).filter(stemOriginalPair => topicStemsFlat.includes(stemOriginalPair.stem)).sort((a, b) => a.stem.localeCompare(b.stem));
+
+  // Group word-stem pairs from the paper by stems.
+  const paperWordsGroupedByStems = paperWordsWithStems.reduce(function (accumulator, stemOriginalPair) {
+    const lastItem = accumulator[accumulator.length - 1];
+    if (accumulator.length === 0 || lastItem.stem !== stemOriginalPair.stem) {
+      accumulator.push(new StemWithForms(stemOriginalPair.stem, [stemOriginalPair.original]));
+    } else {
+      lastItem.forms.push(stemOriginalPair.original);
+    }
+    return accumulator;
+  }, []);
+  return new Result(constructTopicPhraseResult(keyphraseStemmed, paperWordsGroupedByStems, createBasicWordForms), synonymsStemmed.map(synonym => constructTopicPhraseResult(synonym, paperWordsGroupedByStems, createBasicWordForms)));
+}
+
+/**
+ * Gets all matching word forms for the keyphrase and synonyms.
+ *
+ * @param {Paper}       paper       	The paper.
+ * @param {Researcher}  researcher  	The researcher.
+ *
+ * @returns {Object} Object with an array of keyphrase forms and an array of arrays of synonyms forms, based on the forms
+ * found in the text or created forms.
+ */
+function _default(paper, researcher) {
+  const functionWords = researcher.getConfig("functionWords");
+  const stemmer = researcher.getHelper("getStemmer")(researcher);
+  const createBasicWordForms = researcher.getHelper("createBasicWordForms");
+  const language = researcher.getConfig("language");
+  /*
+   * Whether we want to split words on hyphens depends on the language.
+   * In all languages apart from Indonesian, we consider hyphens as word boundaries. But in Indonesian, hyphens are used
+   * to form plural forms of nouns, e.g. 'buku' is the singular form for 'book' and 'buku-buku' is the plural form.
+   * This is why we don't split words on hyphens in Indonesian and we consider 'buku-buku' as one word rather than two.
+   */
+  const areHyphensWordBoundaries = researcher.getConfig("areHyphensWordBoundaries");
+  const allWordsFromPaper = (0, _getAllWordsFromPaper.default)(paper, areHyphensWordBoundaries).map(word => word.toLocaleLowerCase(language));
+  const keyphrase = paper.getKeyword().toLocaleLowerCase(language).trim();
+  const synonyms = (0, _parseSynonyms.default)(paper.getSynonyms().toLocaleLowerCase(language).trim());
+  return getWordForms(keyphrase, synonyms, allWordsFromPaper, functionWords, stemmer, createBasicWordForms, areHyphensWordBoundaries);
+}
+//# sourceMappingURL=getWordForms.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"getWordForms.js","names":["_quotes","require","_buildTopicStems","_lodash","_getAllWordsFromPaper","_interopRequireDefault","_parseSynonyms","e","__esModule","default","StemWithForms","stem","forms","Result","keyphraseForms","synonymsForms","replaceStemWithForms","stemOriginalPair","paperWordsGroupedByStems","createBasicWordForms","matchingStemFormPair","find","element","originalSanitized","normalizeSingle","escapeRegExp","original","push","Set","extractStems","keyphrase","synonyms","keyphraseStemsOnly","stemOriginalPairs","length","getStems","synonymsStemsOnly","map","topicPhrase","flattenDeep","constructTopicPhraseResult","exactMatch","getWordForms","allWordsFromPaper","functionWords","stemmer","areHyphensWordBoundaries","topicPhrases","collectStems","keyphraseStemmed","keyphraseStems","synonymsStemmed","synonymsStems","allTopicPhrases","every","synonym","topicStemsFlat","paperWords","filter","word","includes","paperWordsWithStems","StemOriginalPair","sort","a","b","localeCompare","reduce","accumulator","lastItem","_default","paper","researcher","getConfig","getHelper","language","getAllWordsFromPaper","toLocaleLowerCase","getKeyword","trim","parseSynonyms","getSynonyms"],"sources":["../../../../src/languageProcessing/researches/getWordForms.js"],"sourcesContent":["import { normalizeSingle } from \"../helpers/sanitize/quotes\";\nimport { collectStems, StemOriginalPair } from \"../helpers/morphology/buildTopicStems\";\n\nimport { escapeRegExp, flattenDeep } from \"lodash\";\nimport getAllWordsFromPaper from \"../helpers/morphology/getAllWordsFromPaper\";\nimport parseSynonyms from \"../helpers/sanitize/parseSynonyms\";\n\n/**\n * A stem with accompanying forms.\n *\n * @param {string}      stem    The word stem.\n * @param {string[]}    forms   The word forms for the stem.\n *\n * @constructor\n */\nfunction StemWithForms( stem, forms ) {\n\tthis.stem = stem;\n\tthis.forms = forms;\n}\n\n/**\n * A result for all topic forms.\n *\n * @param {Array[]} keyphraseForms  All keyphrase forms.\n * @param {Array[]} synonymsForms   All synonym forms.\n * @constructor\n */\nfunction Result( keyphraseForms = [], synonymsForms = [] ) {\n\tthis.keyphraseForms = keyphraseForms;\n\tthis.synonymsForms = synonymsForms;\n}\n\n/**\n * Takes a stem-original pair and returns the accompanying forms for the stem that were found in the paper. Additionally\n * adds a sanitized version of the original word and (for specific languages) creates basic word forms.\n *\n * @param {StemOriginalPair}    stemOriginalPair            The stem-original pair for which to get forms.\n * @param {StemWithForms[]}     paperWordsGroupedByStems    All word forms in the paper grouped by stem.\n * @param {Function|null}       createBasicWordForms        A function to create basic word forms (if available).\n *\n * @returns {string[]} All forms found in the paper for the given stem, plus a sanitized version of the original word.\n */\nfunction replaceStemWithForms( stemOriginalPair, paperWordsGroupedByStems, createBasicWordForms ) {\n\tconst matchingStemFormPair = paperWordsGroupedByStems.find( element => element.stem === stemOriginalPair.stem );\n\tconst originalSanitized = normalizeSingle( escapeRegExp( stemOriginalPair.original ) );\n\n\tconst forms = matchingStemFormPair\n\t\t? [ originalSanitized, ...matchingStemFormPair.forms ]\n\t\t: [ originalSanitized ];\n\n\t// Add extra forms for languages for which we have basic word form support.\n\tif ( createBasicWordForms ) {\n\t\tforms.push( ...createBasicWordForms( stemOriginalPair.original ) );\n\t}\n\n\t/*\n\t * Return original and found or created forms.\n\t * Only return original if no matching forms were found in the text and no forms could be created.\n\t */\n\treturn [ ... new Set( forms ) ];\n}\n\n/**\n * Extracts the stems from all keyphrase and synonym stems.\n *\n * @param {TopicPhrase}   keyphrase  A topic phrase.\n * @param {TopicPhrase[]} synonyms   An array of topic phrases.\n *\n * @returns {string[]} All word stems of they keyphrase and synonyms.\n */\nfunction extractStems( keyphrase, synonyms ) {\n\tconst keyphraseStemsOnly = keyphrase.stemOriginalPairs.length === 0\n\t\t? []\n\t\t: keyphrase.getStems();\n\n\tconst synonymsStemsOnly = synonyms.length === 0\n\t\t? []\n\t\t: synonyms.map( topicPhrase => topicPhrase.getStems() );\n\n\treturn ( [ ...keyphraseStemsOnly, ...flattenDeep( synonymsStemsOnly ) ] );\n}\n\n/**\n * Constructs the result with forms for a topic phrase (i.e., a keyphrase or a synonym).\n *\n * @param {TopicPhrase}     topicPhrase              The topic phrase for which to construct the result.\n * @param {StemWithForms[]} paperWordsGroupedByStems All word forms in the paper grouped by stem.\n * @param {Function|null}   createBasicWordForms     A function to create basic word forms (if available).\n *\n * @returns {Array.<string[]>} The word forms for a given topic phrase, grouped by original topic phrase word.\n */\nfunction constructTopicPhraseResult( topicPhrase, paperWordsGroupedByStems, createBasicWordForms ) {\n\t// Empty result for an empty topic phrase.\n\tif ( topicPhrase.stemOriginalPairs.length === 0 ) {\n\t\treturn [];\n\t}\n\n\tif ( topicPhrase.exactMatch ) {\n\t\treturn [ [ topicPhrase.stemOriginalPairs[ 0 ].stem ] ];\n\t}\n\n\treturn topicPhrase.stemOriginalPairs.map( function( stemOriginalPair ) {\n\t\treturn replaceStemWithForms( stemOriginalPair, paperWordsGroupedByStems, createBasicWordForms );\n\t} );\n}\n\n/**\n * Gets all matching word forms for the keyphrase and synonyms. Stems are either collected from\n * the paper or, for specific languages, directly created.\n *\n * @param {string}          keyphrase               \tThe keyphrase.\n * @param {string[]}        synonyms                \tThe synonyms.\n * @param {string[]}        allWordsFromPaper       \tAll words found in the paper.\n * @param {string[]}        functionWords           \tThe function words for a given language (if available).\n * @param {Function|null}   stemmer                 \tA stemmer (if available).\n * @param {Function|null}   createBasicWordForms    \tA function to create basic word forms (if available).\n * @param {boolean}   \t\tareHyphensWordBoundaries\tWhether hyphens should be treated as word boundaries.\n\n * @returns {Object} Object with an array of keyphrase forms and an array of arrays of synonyms forms, based on the forms\n * found in the text or created forms.\n */\nfunction getWordForms( keyphrase, synonyms, allWordsFromPaper, functionWords, stemmer, createBasicWordForms, areHyphensWordBoundaries ) {\n\tconst topicPhrases     = collectStems( keyphrase, synonyms, stemmer, functionWords, areHyphensWordBoundaries );\n\tconst keyphraseStemmed = topicPhrases.keyphraseStems;\n\tconst synonymsStemmed  = topicPhrases.synonymsStems;\n\n\t// Return an empty result when no keyphrase and synonyms have been set.\n\tif ( keyphraseStemmed.stemOriginalPairs.length === 0 && synonymsStemmed.length === 0 ) {\n\t\treturn new Result();\n\t}\n\n\t// Return exact match if all topic phrases contain exact match. Forms don't need to be built in that case.\n\tconst allTopicPhrases = [ keyphraseStemmed, ...synonymsStemmed ];\n\n\tif ( allTopicPhrases.every( topicPhrase => topicPhrase.exactMatch === true ) ) {\n\t\treturn new Result(\n\t\t\t[ [ keyphraseStemmed.stemOriginalPairs[ 0 ].stem ] ],\n\t\t\tsynonymsStemmed.map( synonym => [ [ synonym.stemOriginalPairs[ 0 ].stem ] ]\n\t\t\t)\n\t\t);\n\t}\n\n\t// Get all stems from the keyphrase and synonyms.\n\tconst topicStemsFlat = [ ... new Set( extractStems( keyphraseStemmed, synonymsStemmed ) ) ];\n\n\t/*\n\t * Get all words from the paper text, title, meta description and slug.\n\t * Filter duplicates and function words.\n\t */\n\tconst paperWords = [ ... new Set( allWordsFromPaper.filter( word => ! functionWords.includes( word ) ) ) ];\n\n\t// Add stems to words from the paper, filter out all forms that aren't in the keyphrase or synonyms and order alphabetically.\n\tconst paperWordsWithStems = paperWords\n\t\t.map( word => new StemOriginalPair( stemmer( word ), word ) )\n\t\t.filter( stemOriginalPair => topicStemsFlat.includes( stemOriginalPair.stem ) )\n\t\t.sort( ( a, b ) => a.stem.localeCompare( b.stem ) );\n\n\t// Group word-stem pairs from the paper by stems.\n\tconst paperWordsGroupedByStems = paperWordsWithStems.reduce( function( accumulator, stemOriginalPair ) {\n\t\tconst lastItem = accumulator[ accumulator.length - 1 ];\n\n\t\tif ( accumulator.length === 0 || lastItem.stem !== stemOriginalPair.stem ) {\n\t\t\taccumulator.push( new StemWithForms( stemOriginalPair.stem, [ stemOriginalPair.original ] ) );\n\t\t} else {\n\t\t\tlastItem.forms.push( stemOriginalPair.original );\n\t\t}\n\n\t\treturn accumulator;\n\t}, [] );\n\n\treturn new Result(\n\t\tconstructTopicPhraseResult( keyphraseStemmed, paperWordsGroupedByStems, createBasicWordForms ),\n\t\tsynonymsStemmed.map( synonym => constructTopicPhraseResult( synonym, paperWordsGroupedByStems, createBasicWordForms ) )\n\t);\n}\n\n/**\n * Gets all matching word forms for the keyphrase and synonyms.\n *\n * @param {Paper}       paper       \tThe paper.\n * @param {Researcher}  researcher  \tThe researcher.\n *\n * @returns {Object} Object with an array of keyphrase forms and an array of arrays of synonyms forms, based on the forms\n * found in the text or created forms.\n */\nexport default function( paper, researcher ) {\n\tconst functionWords = researcher.getConfig( \"functionWords\" );\n\tconst stemmer = researcher.getHelper( \"getStemmer\" )( researcher );\n\tconst createBasicWordForms = researcher.getHelper( \"createBasicWordForms\" );\n\tconst language = researcher.getConfig( \"language\" );\n\t/*\n\t * Whether we want to split words on hyphens depends on the language.\n\t * In all languages apart from Indonesian, we consider hyphens as word boundaries. But in Indonesian, hyphens are used\n\t * to form plural forms of nouns, e.g. 'buku' is the singular form for 'book' and 'buku-buku' is the plural form.\n\t * This is why we don't split words on hyphens in Indonesian and we consider 'buku-buku' as one word rather than two.\n\t */\n\tconst areHyphensWordBoundaries = researcher.getConfig( \"areHyphensWordBoundaries\" );\n\n\tconst allWordsFromPaper = getAllWordsFromPaper( paper, areHyphensWordBoundaries ).map( word => word.toLocaleLowerCase( language ) );\n\tconst keyphrase = paper.getKeyword().toLocaleLowerCase( language ).trim();\n\tconst synonyms = parseSynonyms( paper.getSynonyms().toLocaleLowerCase( language ).trim() );\n\n\treturn getWordForms( keyphrase, synonyms, allWordsFromPaper, functionWords, stemmer, createBasicWordForms, areHyphensWordBoundaries );\n}\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AACA,IAAAC,gBAAA,GAAAD,OAAA;AAEA,IAAAE,OAAA,GAAAF,OAAA;AACA,IAAAG,qBAAA,GAAAC,sBAAA,CAAAJ,OAAA;AACA,IAAAK,cAAA,GAAAD,sBAAA,CAAAJ,OAAA;AAA8D,SAAAI,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAE9D;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASG,aAAaA,CAAEC,IAAI,EAAEC,KAAK,EAAG;EACrC,IAAI,CAACD,IAAI,GAAGA,IAAI;EAChB,IAAI,CAACC,KAAK,GAAGA,KAAK;AACnB;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,MAAMA,CAAEC,cAAc,GAAG,EAAE,EAAEC,aAAa,GAAG,EAAE,EAAG;EAC1D,IAAI,CAACD,cAAc,GAAGA,cAAc;EACpC,IAAI,CAACC,aAAa,GAAGA,aAAa;AACnC;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,oBAAoBA,CAAEC,gBAAgB,EAAEC,wBAAwB,EAAEC,oBAAoB,EAAG;EACjG,MAAMC,oBAAoB,GAAGF,wBAAwB,CAACG,IAAI,CAAEC,OAAO,IAAIA,OAAO,CAACX,IAAI,KAAKM,gBAAgB,CAACN,IAAK,CAAC;EAC/G,MAAMY,iBAAiB,GAAG,IAAAC,uBAAe,EAAE,IAAAC,oBAAY,EAAER,gBAAgB,CAACS,QAAS,CAAE,CAAC;EAEtF,MAAMd,KAAK,GAAGQ,oBAAoB,GAC/B,CAAEG,iBAAiB,EAAE,GAAGH,oBAAoB,CAACR,KAAK,CAAE,GACpD,CAAEW,iBAAiB,CAAE;;EAExB;EACA,IAAKJ,oBAAoB,EAAG;IAC3BP,KAAK,CAACe,IAAI,CAAE,GAAGR,oBAAoB,CAAEF,gBAAgB,CAACS,QAAS,CAAE,CAAC;EACnE;;EAEA;AACD;AACA;AACA;EACC,OAAO,CAAE,GAAI,IAAIE,GAAG,CAAEhB,KAAM,CAAC,CAAE;AAChC;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASiB,YAAYA,CAAEC,SAAS,EAAEC,QAAQ,EAAG;EAC5C,MAAMC,kBAAkB,GAAGF,SAAS,CAACG,iBAAiB,CAACC,MAAM,KAAK,CAAC,GAChE,EAAE,GACFJ,SAAS,CAACK,QAAQ,CAAC,CAAC;EAEvB,MAAMC,iBAAiB,GAAGL,QAAQ,CAACG,MAAM,KAAK,CAAC,GAC5C,EAAE,GACFH,QAAQ,CAACM,GAAG,CAAEC,WAAW,IAAIA,WAAW,CAACH,QAAQ,CAAC,CAAE,CAAC;EAExD,OAAS,CAAE,GAAGH,kBAAkB,EAAE,GAAG,IAAAO,mBAAW,EAAEH,iBAAkB,CAAC,CAAE;AACxE;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASI,0BAA0BA,CAAEF,WAAW,EAAEpB,wBAAwB,EAAEC,oBAAoB,EAAG;EAClG;EACA,IAAKmB,WAAW,CAACL,iBAAiB,CAACC,MAAM,KAAK,CAAC,EAAG;IACjD,OAAO,EAAE;EACV;EAEA,IAAKI,WAAW,CAACG,UAAU,EAAG;IAC7B,OAAO,CAAE,CAAEH,WAAW,CAACL,iBAAiB,CAAE,CAAC,CAAE,CAACtB,IAAI,CAAE,CAAE;EACvD;EAEA,OAAO2B,WAAW,CAACL,iBAAiB,CAACI,GAAG,CAAE,UAAUpB,gBAAgB,EAAG;IACtE,OAAOD,oBAAoB,CAAEC,gBAAgB,EAAEC,wBAAwB,EAAEC,oBAAqB,CAAC;EAChG,CAAE,CAAC;AACJ;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASuB,YAAYA,CAAEZ,SAAS,EAAEC,QAAQ,EAAEY,iBAAiB,EAAEC,aAAa,EAAEC,OAAO,EAAE1B,oBAAoB,EAAE2B,wBAAwB,EAAG;EACvI,MAAMC,YAAY,GAAO,IAAAC,6BAAY,EAAElB,SAAS,EAAEC,QAAQ,EAAEc,OAAO,EAAED,aAAa,EAAEE,wBAAyB,CAAC;EAC9G,MAAMG,gBAAgB,GAAGF,YAAY,CAACG,cAAc;EACpD,MAAMC,eAAe,GAAIJ,YAAY,CAACK,aAAa;;EAEnD;EACA,IAAKH,gBAAgB,CAAChB,iBAAiB,CAACC,MAAM,KAAK,CAAC,IAAIiB,eAAe,CAACjB,MAAM,KAAK,CAAC,EAAG;IACtF,OAAO,IAAIrB,MAAM,CAAC,CAAC;EACpB;;EAEA;EACA,MAAMwC,eAAe,GAAG,CAAEJ,gBAAgB,EAAE,GAAGE,eAAe,CAAE;EAEhE,IAAKE,eAAe,CAACC,KAAK,CAAEhB,WAAW,IAAIA,WAAW,CAACG,UAAU,KAAK,IAAK,CAAC,EAAG;IAC9E,OAAO,IAAI5B,MAAM,CAChB,CAAE,CAAEoC,gBAAgB,CAAChB,iBAAiB,CAAE,CAAC,CAAE,CAACtB,IAAI,CAAE,CAAE,EACpDwC,eAAe,CAACd,GAAG,CAAEkB,OAAO,IAAI,CAAE,CAAEA,OAAO,CAACtB,iBAAiB,CAAE,CAAC,CAAE,CAACtB,IAAI,CAAE,CACzE,CACD,CAAC;EACF;;EAEA;EACA,MAAM6C,cAAc,GAAG,CAAE,GAAI,IAAI5B,GAAG,CAAEC,YAAY,CAAEoB,gBAAgB,EAAEE,eAAgB,CAAE,CAAC,CAAE;;EAE3F;AACD;AACA;AACA;EACC,MAAMM,UAAU,GAAG,CAAE,GAAI,IAAI7B,GAAG,CAAEe,iBAAiB,CAACe,MAAM,CAAEC,IAAI,IAAI,CAAEf,aAAa,CAACgB,QAAQ,CAAED,IAAK,CAAE,CAAE,CAAC,CAAE;;EAE1G;EACA,MAAME,mBAAmB,GAAGJ,UAAU,CACpCpB,GAAG,CAAEsB,IAAI,IAAI,IAAIG,iCAAgB,CAAEjB,OAAO,CAAEc,IAAK,CAAC,EAAEA,IAAK,CAAE,CAAC,CAC5DD,MAAM,CAAEzC,gBAAgB,IAAIuC,cAAc,CAACI,QAAQ,CAAE3C,gBAAgB,CAACN,IAAK,CAAE,CAAC,CAC9EoD,IAAI,CAAE,CAAEC,CAAC,EAAEC,CAAC,KAAMD,CAAC,CAACrD,IAAI,CAACuD,aAAa,CAAED,CAAC,CAACtD,IAAK,CAAE,CAAC;;EAEpD;EACA,MAAMO,wBAAwB,GAAG2C,mBAAmB,CAACM,MAAM,CAAE,UAAUC,WAAW,EAAEnD,gBAAgB,EAAG;IACtG,MAAMoD,QAAQ,GAAGD,WAAW,CAAEA,WAAW,CAAClC,MAAM,GAAG,CAAC,CAAE;IAEtD,IAAKkC,WAAW,CAAClC,MAAM,KAAK,CAAC,IAAImC,QAAQ,CAAC1D,IAAI,KAAKM,gBAAgB,CAACN,IAAI,EAAG;MAC1EyD,WAAW,CAACzC,IAAI,CAAE,IAAIjB,aAAa,CAAEO,gBAAgB,CAACN,IAAI,EAAE,CAAEM,gBAAgB,CAACS,QAAQ,CAAG,CAAE,CAAC;IAC9F,CAAC,MAAM;MACN2C,QAAQ,CAACzD,KAAK,CAACe,IAAI,CAAEV,gBAAgB,CAACS,QAAS,CAAC;IACjD;IAEA,OAAO0C,WAAW;EACnB,CAAC,EAAE,EAAG,CAAC;EAEP,OAAO,IAAIvD,MAAM,CAChB2B,0BAA0B,CAAES,gBAAgB,EAAE/B,wBAAwB,EAAEC,oBAAqB,CAAC,EAC9FgC,eAAe,CAACd,GAAG,CAAEkB,OAAO,IAAIf,0BAA0B,CAAEe,OAAO,EAAErC,wBAAwB,EAAEC,oBAAqB,CAAE,CACvH,CAAC;AACF;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAmD,SAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C,MAAM5B,aAAa,GAAG4B,UAAU,CAACC,SAAS,CAAE,eAAgB,CAAC;EAC7D,MAAM5B,OAAO,GAAG2B,UAAU,CAACE,SAAS,CAAE,YAAa,CAAC,CAAEF,UAAW,CAAC;EAClE,MAAMrD,oBAAoB,GAAGqD,UAAU,CAACE,SAAS,CAAE,sBAAuB,CAAC;EAC3E,MAAMC,QAAQ,GAAGH,UAAU,CAACC,SAAS,CAAE,UAAW,CAAC;EACnD;AACD;AACA;AACA;AACA;AACA;EACC,MAAM3B,wBAAwB,GAAG0B,UAAU,CAACC,SAAS,CAAE,0BAA2B,CAAC;EAEnF,MAAM9B,iBAAiB,GAAG,IAAAiC,6BAAoB,EAAEL,KAAK,EAAEzB,wBAAyB,CAAC,CAACT,GAAG,CAAEsB,IAAI,IAAIA,IAAI,CAACkB,iBAAiB,CAAEF,QAAS,CAAE,CAAC;EACnI,MAAM7C,SAAS,GAAGyC,KAAK,CAACO,UAAU,CAAC,CAAC,CAACD,iBAAiB,CAAEF,QAAS,CAAC,CAACI,IAAI,CAAC,CAAC;EACzE,MAAMhD,QAAQ,GAAG,IAAAiD,sBAAa,EAAET,KAAK,CAACU,WAAW,CAAC,CAAC,CAACJ,iBAAiB,CAAEF,QAAS,CAAC,CAACI,IAAI,CAAC,CAAE,CAAC;EAE1F,OAAOrC,YAAY,CAAEZ,SAAS,EAAEC,QAAQ,EAAEY,iBAAiB,EAAEC,aAAa,EAAEC,OAAO,EAAE1B,oBAAoB,EAAE2B,wBAAyB,CAAC;AACtI","ignoreList":[]}

package/build/cjs/languageProcessing/researches/h1s.js

@@ -0,0 +1,17 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+/**
+ * Gets all H1s in a text, including their content and their position information.
+ *
+ * @param {Paper} paper The paper for which to get the H1s.
+ *
+ * @returns {number | null} An array with all H1s, their content and position.
+ */
+function _default(paper) {
+  return paper.getH1Count();
+}
+//# sourceMappingURL=h1s.js.map

package/build/cjs/languageProcessing/researches/h1s.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"h1s.js","names":["_default","paper","getH1Count"],"sources":["../../../../src/languageProcessing/researches/h1s.js"],"sourcesContent":["/**\n * Gets all H1s in a text, including their content and their position information.\n *\n * @param {Paper} paper The paper for which to get the H1s.\n *\n * @returns {number | null} An array with all H1s, their content and position.\n */\nexport default function(paper) {\n  return paper.getH1Count();\n}\n"],"mappings":";;;;;;AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAA,SAASC,KAAK,EAAE;EAC7B,OAAOA,KAAK,CAACC,UAAU,CAAC,CAAC;AAC3B","ignoreList":[]}

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

@@ -0,0 +1,22 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = imageCount;
+var _getImagesInTree = _interopRequireDefault(require("../helpers/image/getImagesInTree"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/** @module researches/imageInText */
+
+/**
+ * Checks the amount of images in the text.
+ *
+ * @param {Paper} paper The paper to check for images.
+ *
+ * @returns {number} The amount of found images.
+ */
+function imageCount(paper) {
+  const images = (0, _getImagesInTree.default)(paper);
+  return images.length;
+}
+//# sourceMappingURL=imageCount.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"imageCount.js","names":["_getImagesInTree","_interopRequireDefault","require","e","__esModule","default","imageCount","paper","images","getImagesInTree","length"],"sources":["../../../../src/languageProcessing/researches/imageCount.js"],"sourcesContent":["/** @module researches/imageInText */\n\nimport getImagesInTree from \"../helpers/image/getImagesInTree\";\n\n/**\n * Checks the amount of images in the text.\n *\n * @param {Paper} paper The paper to check for images.\n *\n * @returns {number} The amount of found images.\n */\nexport default function imageCount( paper ) {\n\tconst images = getImagesInTree( paper );\n\n\treturn images.length;\n}\n"],"mappings":";;;;;;AAEA,IAAAA,gBAAA,GAAAC,sBAAA,CAAAC,OAAA;AAA+D,SAAAD,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAF/D;;AAIA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAASG,UAAUA,CAAEC,KAAK,EAAG;EAC3C,MAAMC,MAAM,GAAG,IAAAC,wBAAe,EAAEF,KAAM,CAAC;EAEvC,OAAOC,MAAM,CAACE,MAAM;AACrB","ignoreList":[]}