axyseo 2.0.0-alpha.1

package/build/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/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/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/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/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/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/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":[]}

package/build/languageProcessing/researches/index.js

@@ -0,0 +1,28 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+Object.defineProperty(exports, "getLongCenterAlignedTexts", {
+  enumerable: true,
+  get: function () {
+    return _getLongCenterAlignedTexts.default;
+  }
+});
+Object.defineProperty(exports, "keyphraseDistribution", {
+  enumerable: true,
+  get: function () {
+    return _keyphraseDistribution.default;
+  }
+});
+Object.defineProperty(exports, "wordComplexity", {
+  enumerable: true,
+  get: function () {
+    return _wordComplexity.default;
+  }
+});
+var _getLongCenterAlignedTexts = _interopRequireDefault(require("./getLongCenterAlignedTexts"));
+var _wordComplexity = _interopRequireDefault(require("./wordComplexity"));
+var _keyphraseDistribution = _interopRequireDefault(require("./keyphraseDistribution"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+//# sourceMappingURL=index.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","names":["_getLongCenterAlignedTexts","_interopRequireDefault","require","_wordComplexity","_keyphraseDistribution","e","__esModule","default"],"sources":["../../../src/languageProcessing/researches/index.js"],"sourcesContent":["import getLongCenterAlignedTexts from './getLongCenterAlignedTexts';\nimport wordComplexity from './wordComplexity';\nimport keyphraseDistribution from './keyphraseDistribution';\n\nexport {getLongCenterAlignedTexts, keyphraseDistribution, wordComplexity};\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;AAAA,IAAAA,0BAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,eAAA,GAAAF,sBAAA,CAAAC,OAAA;AACA,IAAAE,sBAAA,GAAAH,sBAAA,CAAAC,OAAA;AAA4D,SAAAD,uBAAAI,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA","ignoreList":[]}

package/build/languageProcessing/researches/keyphraseDistribution.js

@@ -0,0 +1,233 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.maximizeSentenceScores = exports.keyphraseDistributionResearcher = exports.getDistraction = exports.default = exports.computeScoresPerSentenceShortTopic = exports.computeScoresPerSentenceLongTopic = void 0;
+var _lodash = require("lodash");
+var _findKeywordFormsInString = require("../helpers/match/findKeywordFormsInString");
+var _markWordsInSentences = require("../helpers/word/markWordsInSentences");
+var _getSentences = _interopRequireDefault(require("../helpers/sentence/getSentences"));
+var _parseSynonyms = _interopRequireDefault(require("../helpers/sanitize/parseSynonyms"));
+var _mergeListItems = require("../helpers/sanitize/mergeListItems");
+var _htmlParser = _interopRequireDefault(require("../helpers/html/htmlParser"));
+var _filterShortcodesFromTree = require("../helpers/sanitize/filterShortcodesFromTree");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Checks whether at least half of the content words from the topic are found within the sentence.
+ * Assigns a score to every sentence following the following schema:
+ * 9 if at least half of the content words from the topic are in the sentence,
+ * 3 otherwise.
+ *
+ * @param {Array}  topic     The word forms of all content words in a keyphrase or a synonym.
+ * @param {Array}  sentences An array of all sentences in the text.
+ * @param {string} locale    The locale of the paper to analyse.
+ * @param {function}    matchWordCustomHelper 	The language-specific helper function to match word in text.
+ *
+ * @returns {Array} The scores per sentence.
+ */
+const computeScoresPerSentenceLongTopic = function (topic, sentences, locale, matchWordCustomHelper) {
+  const sentenceScores = Array(sentences.length);
+  for (let i = 0; i < sentences.length; i++) {
+    const foundInCurrentSentence = (0, _findKeywordFormsInString.findWordFormsInString)(topic, sentences[i], locale, matchWordCustomHelper);
+    if (foundInCurrentSentence.percentWordMatches >= 50) {
+      sentenceScores[i] = 9;
+    } else {
+      sentenceScores[i] = 3;
+    }
+  }
+  return sentenceScores;
+};
+
+/**
+ * Checks whether all content words from the topic are found within one sentence.
+ * Assigns a score to every sentence following the following schema:
+ * 9 if all content words from the topic are in the sentence,
+ * 3 if not all content words from the topic were found in the sentence.
+ *
+ * @param {Array}  topic     The word forms of all content words in a keyphrase or a synonym.
+ * @param {Array}  sentences An array of all sentences in the text.
+ * @param {string} locale    The locale of the paper to analyse.
+ * @param {function}    matchWordCustomHelper 	The language-specific helper function to match word in text.
+ *
+ * @returns {Array} The scores per sentence.
+ */
+exports.computeScoresPerSentenceLongTopic = computeScoresPerSentenceLongTopic;
+const computeScoresPerSentenceShortTopic = function (topic, sentences, locale, matchWordCustomHelper) {
+  const sentenceScores = Array(sentences.length);
+  for (let i = 0; i < sentences.length; i++) {
+    const currentSentence = sentences[i];
+    const foundInCurrentSentence = (0, _findKeywordFormsInString.findWordFormsInString)(topic, currentSentence, locale, matchWordCustomHelper);
+    if (foundInCurrentSentence.percentWordMatches === 100) {
+      sentenceScores[i] = 9;
+    } else {
+      sentenceScores[i] = 3;
+    }
+  }
+  return sentenceScores;
+};
+
+/**
+ * Maximizes scores: Give every sentence a maximal score that it got from analysis of all topics
+ *
+ * @param {Array} sentenceScores The scores for every sentence, as assessed per keyphrase and every synonym.
+ *
+ * @returns {Array} Maximal scores of topic relevance per sentence.
+ */
+exports.computeScoresPerSentenceShortTopic = computeScoresPerSentenceShortTopic;
+const maximizeSentenceScores = function (sentenceScores) {
+  const sentenceScoresTransposed = sentenceScores[0].map(function (col, i) {
+    return sentenceScores.map(function (row) {
+      return row[i];
+    });
+  });
+  return sentenceScoresTransposed.map(function (scoresForOneSentence) {
+    return (0, _lodash.max)(scoresForOneSentence);
+  });
+};
+
+/**
+ * Computes the maximally long piece of text that does not include the topic.
+ *
+ * @param {Array} sentenceScores The array of scores per sentence.
+ *
+ * @returns {number} The maximum number of sentences that do not include the topic.
+ */
+exports.maximizeSentenceScores = maximizeSentenceScores;
+const getDistraction = function (sentenceScores) {
+  const numberOfSentences = sentenceScores.length;
+  const allTopicSentencesIndices = [];
+  for (let i = 0; i < numberOfSentences; i++) {
+    if (sentenceScores[i] > 3) {
+      allTopicSentencesIndices.push(i);
+    }
+  }
+  const numberOfTopicSentences = allTopicSentencesIndices.length;
+  if (numberOfTopicSentences === 0) {
+    return numberOfSentences;
+  }
+
+  /**
+   * Add fake topic sentences at the very beginning and at the very end
+   * to account for cases when the text starts or ends with a train of distraction.
+   */
+  allTopicSentencesIndices.unshift(-1);
+  allTopicSentencesIndices.push(numberOfSentences);
+  const distances = [];
+  for (let i = 1; i < numberOfTopicSentences + 2; i++) {
+    distances.push(allTopicSentencesIndices[i] - allTopicSentencesIndices[i - 1] - 1);
+  }
+  return (0, _lodash.max)(distances);
+};
+
+/**
+ * Computes the per-sentence scores depending on the length of the topic phrase and maximizes them over all topic phrases.
+ *
+ * @param {Array}       sentences              The sentences to get scores for.
+ * @param {Array}       topicFormsInOneArray   The topic phrases forms to search for in the sentences.
+ * @param {string}      locale                 The locale to work in.
+ * @param {Array}       functionWords           The function words list.
+ * @param {function}    matchWordCustomHelper 	The language-specific helper function to match word in text.
+ * @param {int}         topicLengthCriteria     The topic length criteria. The default value is 4, where a topic is considered short
+ *                                              if it's less than 4 word long, and otherwise long.
+ * @param {Array}       originalTopic           The array of the original form of the topic with function words filtered out.
+ * @param {function}    wordsCharacterCount     The helper to calculate the characters length of all the words in the array.
+ *
+ * @returns {Object} An array with maximized score per sentence and an array with all sentences that do not contain the topic.
+ */
+exports.getDistraction = getDistraction;
+const getSentenceScores = function (sentences, topicFormsInOneArray, locale, functionWords, matchWordCustomHelper, topicLengthCriteria = 4, originalTopic, wordsCharacterCount) {
+  // Compute per-sentence scores of topic-relatedness.
+  const topicNumber = topicFormsInOneArray.length;
+  const sentenceScores = Array(topicNumber);
+
+  // For languages with function words apply either full match or partial match depending on topic length
+  if (functionWords.length > 0) {
+    for (let i = 0; i < topicNumber; i++) {
+      const topic = topicFormsInOneArray[i];
+      /*
+       * If the helper to calculate the characters length of all the words in the array is available,
+       * we use this helper to calculate the characters length of the original topic form.
+       * We then use the result and compare it with the topicLengthCriteria.
+       */
+      const topicLength = wordsCharacterCount ? wordsCharacterCount(originalTopic[i]) : topic.length;
+      if (topicLength < topicLengthCriteria) {
+        sentenceScores[i] = computeScoresPerSentenceShortTopic(topic, sentences, locale, matchWordCustomHelper);
+      } else {
+        sentenceScores[i] = computeScoresPerSentenceLongTopic(topic, sentences, locale, matchWordCustomHelper);
+      }
+    }
+  } else {
+    // For languages without function words apply the full match always
+    for (let i = 0; i < topicNumber; i++) {
+      const topic = topicFormsInOneArray[i];
+      sentenceScores[i] = computeScoresPerSentenceShortTopic(topic, sentences, locale, matchWordCustomHelper);
+    }
+  }
+
+  // Maximize scores: Give every sentence a maximal score that it got from analysis of all topics
+  const maximizedSentenceScores = maximizeSentenceScores(sentenceScores);
+
+  // Zip an array combining each sentence with the associated maximized score.
+  const sentencesWithMaximizedScores = (0, _lodash.zipWith)(sentences, maximizedSentenceScores, (sentence, score) => {
+    return {
+      sentence,
+      score
+    };
+  });
+
+  // Filter sentences that contain topic words for future highlights.
+  const sentencesWithTopic = sentencesWithMaximizedScores.filter(sentenceObject => sentenceObject.score > 3);
+  return {
+    maximizedSentenceScores: maximizedSentenceScores,
+    sentencesWithTopic: sentencesWithTopic.map(sentenceObject => sentenceObject.sentence)
+  };
+};
+
+/**
+ * Determines which portions of the text did not receive a lot of content words from keyphrase and synonyms.
+ *
+ * @param {Paper}       paper               The paper to check the keyphrase distribution for.
+ * @param {Researcher}  researcher          The researcher to use for analysis.
+ *
+ * @returns {Object} The scores of topic relevance per portion of text and an array of all word forms to highlight.
+ */
+const keyphraseDistributionResearcher = function (paper, researcher) {
+  const functionWords = researcher.getConfig("functionWords");
+  const matchWordCustomHelper = researcher.getHelper("matchWordCustomHelper");
+  const getContentWordsHelper = researcher.getHelper("getContentWords");
+  const wordsCharacterCount = researcher.getResearch("wordsCharacterCount");
+  const memoizedTokenizer = researcher.getHelper("memoizedTokenizer");
+
+  // Custom topic length criteria for languages that don't use the default value to determine whether a topic is long or short.
+  const topicLengthCriteria = researcher.getConfig("topicLength").lengthCriteria;
+  let text = paper.getText();
+  text = (0, _htmlParser.default)(text);
+  text = (0, _filterShortcodesFromTree.filterShortcodesFromHTML)(text, paper._attributes && paper._attributes.shortcodes);
+  text = (0, _mergeListItems.mergeListItems)(text);
+  const sentences = (0, _getSentences.default)(text, memoizedTokenizer);
+  const topicForms = researcher.getResearch("morphology");
+  const originalTopic = [];
+  if (getContentWordsHelper) {
+    originalTopic.push(getContentWordsHelper(paper.getKeyword()));
+    (0, _parseSynonyms.default)(paper.getSynonyms()).forEach(synonym => originalTopic.push(getContentWordsHelper(synonym)));
+  }
+  const locale = paper.getLocale();
+  const topicFormsInOneArray = [topicForms.keyphraseForms];
+  topicForms.synonymsForms.forEach(function (synonym) {
+    topicFormsInOneArray.push(synonym);
+  });
+  const allTopicWords = (0, _lodash.uniq)((0, _lodash.flattenDeep)(topicFormsInOneArray)).sort((a, b) => b.length - a.length);
+
+  // Get per-sentence scores and sentences that have topic.
+  const sentenceScores = getSentenceScores(sentences, topicFormsInOneArray, locale, functionWords, matchWordCustomHelper, topicLengthCriteria, originalTopic, wordsCharacterCount);
+  const maximizedSentenceScores = sentenceScores.maximizedSentenceScores;
+  const maxLengthDistraction = getDistraction(maximizedSentenceScores);
+  return {
+    sentencesToHighlight: (0, _markWordsInSentences.markWordsInSentences)(allTopicWords, sentenceScores.sentencesWithTopic, locale, matchWordCustomHelper),
+    keyphraseDistributionScore: maxLengthDistraction / sentences.length * 100
+  };
+};
+exports.keyphraseDistributionResearcher = keyphraseDistributionResearcher;
+var _default = exports.default = keyphraseDistributionResearcher;
+//# sourceMappingURL=keyphraseDistribution.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"keyphraseDistribution.js","names":["_lodash","require","_findKeywordFormsInString","_markWordsInSentences","_getSentences","_interopRequireDefault","_parseSynonyms","_mergeListItems","_htmlParser","_filterShortcodesFromTree","e","__esModule","default","computeScoresPerSentenceLongTopic","topic","sentences","locale","matchWordCustomHelper","sentenceScores","Array","length","i","foundInCurrentSentence","findWordFormsInString","percentWordMatches","exports","computeScoresPerSentenceShortTopic","currentSentence","maximizeSentenceScores","sentenceScoresTransposed","map","col","row","scoresForOneSentence","max","getDistraction","numberOfSentences","allTopicSentencesIndices","push","numberOfTopicSentences","unshift","distances","getSentenceScores","topicFormsInOneArray","functionWords","topicLengthCriteria","originalTopic","wordsCharacterCount","topicNumber","topicLength","maximizedSentenceScores","sentencesWithMaximizedScores","zipWith","sentence","score","sentencesWithTopic","filter","sentenceObject","keyphraseDistributionResearcher","paper","researcher","getConfig","getHelper","getContentWordsHelper","getResearch","memoizedTokenizer","lengthCriteria","text","getText","removeHtmlBlocks","filterShortcodesFromHTML","_attributes","shortcodes","mergeListItems","getSentences","topicForms","getKeyword","parseSynonyms","getSynonyms","forEach","synonym","getLocale","keyphraseForms","synonymsForms","allTopicWords","unique","flattenDeep","sort","a","b","maxLengthDistraction","sentencesToHighlight","markWordsInSentences","keyphraseDistributionScore","_default"],"sources":["../../../src/languageProcessing/researches/keyphraseDistribution.js"],"sourcesContent":["import { flattenDeep, max, uniq as unique, zipWith } from \"lodash\";\nimport { findWordFormsInString } from \"../helpers/match/findKeywordFormsInString\";\nimport { markWordsInSentences } from \"../helpers/word/markWordsInSentences\";\nimport getSentences from \"../helpers/sentence/getSentences\";\nimport parseSynonyms from \"../helpers/sanitize/parseSynonyms\";\nimport { mergeListItems } from \"../helpers/sanitize/mergeListItems\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\nimport { filterShortcodesFromHTML } from \"../helpers/sanitize/filterShortcodesFromTree\";\n\n/**\n * Checks whether at least half of the content words from the topic are found within the sentence.\n * Assigns a score to every sentence following the following schema:\n * 9 if at least half of the content words from the topic are in the sentence,\n * 3 otherwise.\n *\n * @param {Array}  topic     The word forms of all content words in a keyphrase or a synonym.\n * @param {Array}  sentences An array of all sentences in the text.\n * @param {string} locale    The locale of the paper to analyse.\n * @param {function}    matchWordCustomHelper \tThe language-specific helper function to match word in text.\n *\n * @returns {Array} The scores per sentence.\n */\nconst computeScoresPerSentenceLongTopic = function( topic, sentences, locale, matchWordCustomHelper ) {\n\tconst sentenceScores = Array( sentences.length );\n\n\tfor ( let i = 0; i < sentences.length; i++ ) {\n\t\tconst foundInCurrentSentence = findWordFormsInString( topic, sentences[ i ], locale, matchWordCustomHelper );\n\n\t\tif ( foundInCurrentSentence.percentWordMatches >= 50 ) {\n\t\t\tsentenceScores[ i ] = 9;\n\t\t} else {\n\t\t\tsentenceScores[ i ] = 3;\n\t\t}\n\t}\n\n\treturn sentenceScores;\n};\n\n\n/**\n * Checks whether all content words from the topic are found within one sentence.\n * Assigns a score to every sentence following the following schema:\n * 9 if all content words from the topic are in the sentence,\n * 3 if not all content words from the topic were found in the sentence.\n *\n * @param {Array}  topic     The word forms of all content words in a keyphrase or a synonym.\n * @param {Array}  sentences An array of all sentences in the text.\n * @param {string} locale    The locale of the paper to analyse.\n * @param {function}    matchWordCustomHelper \tThe language-specific helper function to match word in text.\n *\n * @returns {Array} The scores per sentence.\n */\nconst computeScoresPerSentenceShortTopic = function( topic, sentences, locale, matchWordCustomHelper ) {\n\tconst sentenceScores = Array( sentences.length );\n\n\tfor ( let i = 0; i < sentences.length; i++ ) {\n\t\tconst currentSentence = sentences[ i ];\n\t\tconst foundInCurrentSentence = findWordFormsInString( topic, currentSentence, locale, matchWordCustomHelper );\n\t\tif ( foundInCurrentSentence.percentWordMatches === 100 ) {\n\t\t\tsentenceScores[ i ] = 9;\n\t\t} else {\n\t\t\tsentenceScores[ i ] = 3;\n\t\t}\n\t}\n\treturn sentenceScores;\n};\n\n/**\n * Maximizes scores: Give every sentence a maximal score that it got from analysis of all topics\n *\n * @param {Array} sentenceScores The scores for every sentence, as assessed per keyphrase and every synonym.\n *\n * @returns {Array} Maximal scores of topic relevance per sentence.\n */\nconst maximizeSentenceScores = function( sentenceScores ) {\n\tconst sentenceScoresTransposed = sentenceScores[ 0 ].map( function( col, i ) {\n\t\treturn sentenceScores.map( function( row ) {\n\t\t\treturn row[ i ];\n\t\t} );\n\t} );\n\n\treturn sentenceScoresTransposed.map( function( scoresForOneSentence ) {\n\t\treturn max( scoresForOneSentence );\n\t} );\n};\n\n\n/**\n * Computes the maximally long piece of text that does not include the topic.\n *\n * @param {Array} sentenceScores The array of scores per sentence.\n *\n * @returns {number} The maximum number of sentences that do not include the topic.\n */\nconst getDistraction = function( sentenceScores ) {\n\tconst numberOfSentences = sentenceScores.length;\n\tconst allTopicSentencesIndices = [];\n\n\tfor ( let i = 0; i < numberOfSentences; i++ ) {\n\t\tif ( sentenceScores[ i ] > 3 ) {\n\t\t\tallTopicSentencesIndices.push( i );\n\t\t}\n\t}\n\n\tconst numberOfTopicSentences = allTopicSentencesIndices.length;\n\n\tif ( numberOfTopicSentences === 0 ) {\n\t\treturn numberOfSentences;\n\t}\n\n\t/**\n\t * Add fake topic sentences at the very beginning and at the very end\n\t * to account for cases when the text starts or ends with a train of distraction.\n\t */\n\tallTopicSentencesIndices.unshift( -1 );\n\tallTopicSentencesIndices.push( numberOfSentences );\n\n\tconst distances = [];\n\n\tfor ( let i = 1; i < numberOfTopicSentences + 2; i++ ) {\n\t\tdistances.push( allTopicSentencesIndices[ i ] - allTopicSentencesIndices[ i - 1 ] - 1 );\n\t}\n\n\treturn max( distances );\n};\n\n/**\n * Computes the per-sentence scores depending on the length of the topic phrase and maximizes them over all topic phrases.\n *\n * @param {Array}       sentences              The sentences to get scores for.\n * @param {Array}       topicFormsInOneArray   The topic phrases forms to search for in the sentences.\n * @param {string}      locale                 The locale to work in.\n * @param {Array}       functionWords           The function words list.\n * @param {function}    matchWordCustomHelper \tThe language-specific helper function to match word in text.\n * @param {int}         topicLengthCriteria     The topic length criteria. The default value is 4, where a topic is considered short\n *                                              if it's less than 4 word long, and otherwise long.\n * @param {Array}       originalTopic           The array of the original form of the topic with function words filtered out.\n * @param {function}    wordsCharacterCount     The helper to calculate the characters length of all the words in the array.\n *\n * @returns {Object} An array with maximized score per sentence and an array with all sentences that do not contain the topic.\n */\nconst getSentenceScores = function( sentences, topicFormsInOneArray, locale, functionWords, matchWordCustomHelper,\n\ttopicLengthCriteria = 4, originalTopic, wordsCharacterCount ) {\n\t// Compute per-sentence scores of topic-relatedness.\n\tconst topicNumber = topicFormsInOneArray.length;\n\n\tconst sentenceScores = Array( topicNumber );\n\n\t// For languages with function words apply either full match or partial match depending on topic length\n\tif ( functionWords.length > 0 ) {\n\t\tfor ( let i = 0; i < topicNumber; i++ ) {\n\t\t\tconst topic = topicFormsInOneArray[ i ];\n\t\t\t/*\n\t\t\t * If the helper to calculate the characters length of all the words in the array is available,\n\t\t\t * we use this helper to calculate the characters length of the original topic form.\n\t\t\t * We then use the result and compare it with the topicLengthCriteria.\n\t\t\t */\n\t\t\tconst topicLength = wordsCharacterCount ? wordsCharacterCount( originalTopic[ i ] ) : topic.length;\n\t\t\tif ( topicLength < topicLengthCriteria ) {\n\t\t\t\tsentenceScores[ i ] = computeScoresPerSentenceShortTopic( topic, sentences, locale, matchWordCustomHelper );\n\t\t\t} else {\n\t\t\t\tsentenceScores[ i ] = computeScoresPerSentenceLongTopic( topic, sentences, locale, matchWordCustomHelper );\n\t\t\t}\n\t\t}\n\t} else {\n\t\t// For languages without function words apply the full match always\n\t\tfor ( let i = 0; i < topicNumber; i++ ) {\n\t\t\tconst topic = topicFormsInOneArray[ i ];\n\t\t\tsentenceScores[ i ] = computeScoresPerSentenceShortTopic( topic, sentences, locale, matchWordCustomHelper );\n\t\t}\n\t}\n\n\t// Maximize scores: Give every sentence a maximal score that it got from analysis of all topics\n\tconst maximizedSentenceScores = maximizeSentenceScores( sentenceScores );\n\n\t// Zip an array combining each sentence with the associated maximized score.\n\tconst sentencesWithMaximizedScores =  zipWith( sentences, maximizedSentenceScores, ( sentence, score ) => {\n\t\treturn { sentence, score };\n\t} );\n\n\t// Filter sentences that contain topic words for future highlights.\n\tconst sentencesWithTopic = sentencesWithMaximizedScores.filter( sentenceObject => sentenceObject.score > 3 );\n\n\treturn {\n\t\tmaximizedSentenceScores: maximizedSentenceScores,\n\t\tsentencesWithTopic: sentencesWithTopic.map( sentenceObject => sentenceObject.sentence ),\n\t};\n};\n\n\n/**\n * Determines which portions of the text did not receive a lot of content words from keyphrase and synonyms.\n *\n * @param {Paper}       paper               The paper to check the keyphrase distribution for.\n * @param {Researcher}  researcher          The researcher to use for analysis.\n *\n * @returns {Object} The scores of topic relevance per portion of text and an array of all word forms to highlight.\n */\nconst keyphraseDistributionResearcher = function( paper, researcher ) {\n\tconst functionWords = researcher.getConfig( \"functionWords\" );\n\tconst matchWordCustomHelper = researcher.getHelper( \"matchWordCustomHelper\" );\n\tconst getContentWordsHelper = researcher.getHelper( \"getContentWords\" );\n\tconst wordsCharacterCount = researcher.getResearch( \"wordsCharacterCount\" );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\n\t// Custom topic length criteria for languages that don't use the default value to determine whether a topic is long or short.\n\tconst topicLengthCriteria = researcher.getConfig( \"topicLength\" ).lengthCriteria;\n\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\ttext = mergeListItems( text );\n\tconst sentences = getSentences( text, memoizedTokenizer );\n\tconst topicForms = researcher.getResearch( \"morphology\" );\n\n\tconst originalTopic = [];\n\tif ( getContentWordsHelper ) {\n\t\toriginalTopic.push( getContentWordsHelper( paper.getKeyword() ) );\n\t\tparseSynonyms( paper.getSynonyms() ).forEach( synonym => originalTopic.push( getContentWordsHelper( synonym ) ) );\n\t}\n\tconst locale = paper.getLocale();\n\tconst topicFormsInOneArray = [ topicForms.keyphraseForms ];\n\ttopicForms.synonymsForms.forEach( function( synonym ) {\n\t\ttopicFormsInOneArray.push( synonym );\n\t} );\n\n\tconst allTopicWords = unique( flattenDeep( topicFormsInOneArray ) ).sort( ( a, b ) => b.length - a.length );\n\n\t// Get per-sentence scores and sentences that have topic.\n\tconst sentenceScores = getSentenceScores( sentences, topicFormsInOneArray, locale, functionWords, matchWordCustomHelper,\n\t\ttopicLengthCriteria, originalTopic, wordsCharacterCount );\n\tconst maximizedSentenceScores = sentenceScores.maximizedSentenceScores;\n\tconst maxLengthDistraction = getDistraction( maximizedSentenceScores );\n\n\treturn {\n\t\tsentencesToHighlight: markWordsInSentences( allTopicWords, sentenceScores.sentencesWithTopic, locale, matchWordCustomHelper ),\n\t\tkeyphraseDistributionScore: maxLengthDistraction / sentences.length * 100,\n\t};\n};\n\nexport {\n\tcomputeScoresPerSentenceShortTopic,\n\tcomputeScoresPerSentenceLongTopic,\n\tmaximizeSentenceScores,\n\tkeyphraseDistributionResearcher,\n\tgetDistraction,\n};\n\nexport default keyphraseDistributionResearcher;\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AACA,IAAAC,yBAAA,GAAAD,OAAA;AACA,IAAAE,qBAAA,GAAAF,OAAA;AACA,IAAAG,aAAA,GAAAC,sBAAA,CAAAJ,OAAA;AACA,IAAAK,cAAA,GAAAD,sBAAA,CAAAJ,OAAA;AACA,IAAAM,eAAA,GAAAN,OAAA;AACA,IAAAO,WAAA,GAAAH,sBAAA,CAAAJ,OAAA;AACA,IAAAQ,yBAAA,GAAAR,OAAA;AAAwF,SAAAI,uBAAAK,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAExF;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,iCAAiC,GAAG,SAAAA,CAAUC,KAAK,EAAEC,SAAS,EAAEC,MAAM,EAAEC,qBAAqB,EAAG;EACrG,MAAMC,cAAc,GAAGC,KAAK,CAAEJ,SAAS,CAACK,MAAO,CAAC;EAEhD,KAAM,IAAIC,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGN,SAAS,CAACK,MAAM,EAAEC,CAAC,EAAE,EAAG;IAC5C,MAAMC,sBAAsB,GAAG,IAAAC,+CAAqB,EAAET,KAAK,EAAEC,SAAS,CAAEM,CAAC,CAAE,EAAEL,MAAM,EAAEC,qBAAsB,CAAC;IAE5G,IAAKK,sBAAsB,CAACE,kBAAkB,IAAI,EAAE,EAAG;MACtDN,cAAc,CAAEG,CAAC,CAAE,GAAG,CAAC;IACxB,CAAC,MAAM;MACNH,cAAc,CAAEG,CAAC,CAAE,GAAG,CAAC;IACxB;EACD;EAEA,OAAOH,cAAc;AACtB,CAAC;;AAGD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AAZAO,OAAA,CAAAZ,iCAAA,GAAAA,iCAAA;AAaA,MAAMa,kCAAkC,GAAG,SAAAA,CAAUZ,KAAK,EAAEC,SAAS,EAAEC,MAAM,EAAEC,qBAAqB,EAAG;EACtG,MAAMC,cAAc,GAAGC,KAAK,CAAEJ,SAAS,CAACK,MAAO,CAAC;EAEhD,KAAM,IAAIC,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGN,SAAS,CAACK,MAAM,EAAEC,CAAC,EAAE,EAAG;IAC5C,MAAMM,eAAe,GAAGZ,SAAS,CAAEM,CAAC,CAAE;IACtC,MAAMC,sBAAsB,GAAG,IAAAC,+CAAqB,EAAET,KAAK,EAAEa,eAAe,EAAEX,MAAM,EAAEC,qBAAsB,CAAC;IAC7G,IAAKK,sBAAsB,CAACE,kBAAkB,KAAK,GAAG,EAAG;MACxDN,cAAc,CAAEG,CAAC,CAAE,GAAG,CAAC;IACxB,CAAC,MAAM;MACNH,cAAc,CAAEG,CAAC,CAAE,GAAG,CAAC;IACxB;EACD;EACA,OAAOH,cAAc;AACtB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AANAO,OAAA,CAAAC,kCAAA,GAAAA,kCAAA;AAOA,MAAME,sBAAsB,GAAG,SAAAA,CAAUV,cAAc,EAAG;EACzD,MAAMW,wBAAwB,GAAGX,cAAc,CAAE,CAAC,CAAE,CAACY,GAAG,CAAE,UAAUC,GAAG,EAAEV,CAAC,EAAG;IAC5E,OAAOH,cAAc,CAACY,GAAG,CAAE,UAAUE,GAAG,EAAG;MAC1C,OAAOA,GAAG,CAAEX,CAAC,CAAE;IAChB,CAAE,CAAC;EACJ,CAAE,CAAC;EAEH,OAAOQ,wBAAwB,CAACC,GAAG,CAAE,UAAUG,oBAAoB,EAAG;IACrE,OAAO,IAAAC,WAAG,EAAED,oBAAqB,CAAC;EACnC,CAAE,CAAC;AACJ,CAAC;;AAGD;AACA;AACA;AACA;AACA;AACA;AACA;AANAR,OAAA,CAAAG,sBAAA,GAAAA,sBAAA;AAOA,MAAMO,cAAc,GAAG,SAAAA,CAAUjB,cAAc,EAAG;EACjD,MAAMkB,iBAAiB,GAAGlB,cAAc,CAACE,MAAM;EAC/C,MAAMiB,wBAAwB,GAAG,EAAE;EAEnC,KAAM,IAAIhB,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGe,iBAAiB,EAAEf,CAAC,EAAE,EAAG;IAC7C,IAAKH,cAAc,CAAEG,CAAC,CAAE,GAAG,CAAC,EAAG;MAC9BgB,wBAAwB,CAACC,IAAI,CAAEjB,CAAE,CAAC;IACnC;EACD;EAEA,MAAMkB,sBAAsB,GAAGF,wBAAwB,CAACjB,MAAM;EAE9D,IAAKmB,sBAAsB,KAAK,CAAC,EAAG;IACnC,OAAOH,iBAAiB;EACzB;;EAEA;AACD;AACA;AACA;EACCC,wBAAwB,CAACG,OAAO,CAAE,CAAC,CAAE,CAAC;EACtCH,wBAAwB,CAACC,IAAI,CAAEF,iBAAkB,CAAC;EAElD,MAAMK,SAAS,GAAG,EAAE;EAEpB,KAAM,IAAIpB,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGkB,sBAAsB,GAAG,CAAC,EAAElB,CAAC,EAAE,EAAG;IACtDoB,SAAS,CAACH,IAAI,CAAED,wBAAwB,CAAEhB,CAAC,CAAE,GAAGgB,wBAAwB,CAAEhB,CAAC,GAAG,CAAC,CAAE,GAAG,CAAE,CAAC;EACxF;EAEA,OAAO,IAAAa,WAAG,EAAEO,SAAU,CAAC;AACxB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AAdAhB,OAAA,CAAAU,cAAA,GAAAA,cAAA;AAeA,MAAMO,iBAAiB,GAAG,SAAAA,CAAU3B,SAAS,EAAE4B,oBAAoB,EAAE3B,MAAM,EAAE4B,aAAa,EAAE3B,qBAAqB,EAChH4B,mBAAmB,GAAG,CAAC,EAAEC,aAAa,EAAEC,mBAAmB,EAAG;EAC9D;EACA,MAAMC,WAAW,GAAGL,oBAAoB,CAACvB,MAAM;EAE/C,MAAMF,cAAc,GAAGC,KAAK,CAAE6B,WAAY,CAAC;;EAE3C;EACA,IAAKJ,aAAa,CAACxB,MAAM,GAAG,CAAC,EAAG;IAC/B,KAAM,IAAIC,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAG2B,WAAW,EAAE3B,CAAC,EAAE,EAAG;MACvC,MAAMP,KAAK,GAAG6B,oBAAoB,CAAEtB,CAAC,CAAE;MACvC;AACH;AACA;AACA;AACA;MACG,MAAM4B,WAAW,GAAGF,mBAAmB,GAAGA,mBAAmB,CAAED,aAAa,CAAEzB,CAAC,CAAG,CAAC,GAAGP,KAAK,CAACM,MAAM;MAClG,IAAK6B,WAAW,GAAGJ,mBAAmB,EAAG;QACxC3B,cAAc,CAAEG,CAAC,CAAE,GAAGK,kCAAkC,CAAEZ,KAAK,EAAEC,SAAS,EAAEC,MAAM,EAAEC,qBAAsB,CAAC;MAC5G,CAAC,MAAM;QACNC,cAAc,CAAEG,CAAC,CAAE,GAAGR,iCAAiC,CAAEC,KAAK,EAAEC,SAAS,EAAEC,MAAM,EAAEC,qBAAsB,CAAC;MAC3G;IACD;EACD,CAAC,MAAM;IACN;IACA,KAAM,IAAII,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAG2B,WAAW,EAAE3B,CAAC,EAAE,EAAG;MACvC,MAAMP,KAAK,GAAG6B,oBAAoB,CAAEtB,CAAC,CAAE;MACvCH,cAAc,CAAEG,CAAC,CAAE,GAAGK,kCAAkC,CAAEZ,KAAK,EAAEC,SAAS,EAAEC,MAAM,EAAEC,qBAAsB,CAAC;IAC5G;EACD;;EAEA;EACA,MAAMiC,uBAAuB,GAAGtB,sBAAsB,CAAEV,cAAe,CAAC;;EAExE;EACA,MAAMiC,4BAA4B,GAAI,IAAAC,eAAO,EAAErC,SAAS,EAAEmC,uBAAuB,EAAE,CAAEG,QAAQ,EAAEC,KAAK,KAAM;IACzG,OAAO;MAAED,QAAQ;MAAEC;IAAM,CAAC;EAC3B,CAAE,CAAC;;EAEH;EACA,MAAMC,kBAAkB,GAAGJ,4BAA4B,CAACK,MAAM,CAAEC,cAAc,IAAIA,cAAc,CAACH,KAAK,GAAG,CAAE,CAAC;EAE5G,OAAO;IACNJ,uBAAuB,EAAEA,uBAAuB;IAChDK,kBAAkB,EAAEA,kBAAkB,CAACzB,GAAG,CAAE2B,cAAc,IAAIA,cAAc,CAACJ,QAAS;EACvF,CAAC;AACF,CAAC;;AAGD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMK,+BAA+B,GAAG,SAAAA,CAAUC,KAAK,EAAEC,UAAU,EAAG;EACrE,MAAMhB,aAAa,GAAGgB,UAAU,CAACC,SAAS,CAAE,eAAgB,CAAC;EAC7D,MAAM5C,qBAAqB,GAAG2C,UAAU,CAACE,SAAS,CAAE,uBAAwB,CAAC;EAC7E,MAAMC,qBAAqB,GAAGH,UAAU,CAACE,SAAS,CAAE,iBAAkB,CAAC;EACvE,MAAMf,mBAAmB,GAAGa,UAAU,CAACI,WAAW,CAAE,qBAAsB,CAAC;EAC3E,MAAMC,iBAAiB,GAAGL,UAAU,CAACE,SAAS,CAAE,mBAAoB,CAAC;;EAErE;EACA,MAAMjB,mBAAmB,GAAGe,UAAU,CAACC,SAAS,CAAE,aAAc,CAAC,CAACK,cAAc;EAEhF,IAAIC,IAAI,GAAGR,KAAK,CAACS,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAG,IAAAE,mBAAgB,EAAEF,IAAK,CAAC;EAC/BA,IAAI,GAAG,IAAAG,kDAAwB,EAAEH,IAAI,EAAER,KAAK,CAACY,WAAW,IAAIZ,KAAK,CAACY,WAAW,CAACC,UAAW,CAAC;EAC1FL,IAAI,GAAG,IAAAM,8BAAc,EAAEN,IAAK,CAAC;EAC7B,MAAMpD,SAAS,GAAG,IAAA2D,qBAAY,EAAEP,IAAI,EAAEF,iBAAkB,CAAC;EACzD,MAAMU,UAAU,GAAGf,UAAU,CAACI,WAAW,CAAE,YAAa,CAAC;EAEzD,MAAMlB,aAAa,GAAG,EAAE;EACxB,IAAKiB,qBAAqB,EAAG;IAC5BjB,aAAa,CAACR,IAAI,CAAEyB,qBAAqB,CAAEJ,KAAK,CAACiB,UAAU,CAAC,CAAE,CAAE,CAAC;IACjE,IAAAC,sBAAa,EAAElB,KAAK,CAACmB,WAAW,CAAC,CAAE,CAAC,CAACC,OAAO,CAAEC,OAAO,IAAIlC,aAAa,CAACR,IAAI,CAAEyB,qBAAqB,CAAEiB,OAAQ,CAAE,CAAE,CAAC;EAClH;EACA,MAAMhE,MAAM,GAAG2C,KAAK,CAACsB,SAAS,CAAC,CAAC;EAChC,MAAMtC,oBAAoB,GAAG,CAAEgC,UAAU,CAACO,cAAc,CAAE;EAC1DP,UAAU,CAACQ,aAAa,CAACJ,OAAO,CAAE,UAAUC,OAAO,EAAG;IACrDrC,oBAAoB,CAACL,IAAI,CAAE0C,OAAQ,CAAC;EACrC,CAAE,CAAC;EAEH,MAAMI,aAAa,GAAG,IAAAC,YAAM,EAAE,IAAAC,mBAAW,EAAE3C,oBAAqB,CAAE,CAAC,CAAC4C,IAAI,CAAE,CAAEC,CAAC,EAAEC,CAAC,KAAMA,CAAC,CAACrE,MAAM,GAAGoE,CAAC,CAACpE,MAAO,CAAC;;EAE3G;EACA,MAAMF,cAAc,GAAGwB,iBAAiB,CAAE3B,SAAS,EAAE4B,oBAAoB,EAAE3B,MAAM,EAAE4B,aAAa,EAAE3B,qBAAqB,EACtH4B,mBAAmB,EAAEC,aAAa,EAAEC,mBAAoB,CAAC;EAC1D,MAAMG,uBAAuB,GAAGhC,cAAc,CAACgC,uBAAuB;EACtE,MAAMwC,oBAAoB,GAAGvD,cAAc,CAAEe,uBAAwB,CAAC;EAEtE,OAAO;IACNyC,oBAAoB,EAAE,IAAAC,0CAAoB,EAAER,aAAa,EAAElE,cAAc,CAACqC,kBAAkB,EAAEvC,MAAM,EAAEC,qBAAsB,CAAC;IAC7H4E,0BAA0B,EAAEH,oBAAoB,GAAG3E,SAAS,CAACK,MAAM,GAAG;EACvE,CAAC;AACF,CAAC;AAACK,OAAA,CAAAiC,+BAAA,GAAAA,+BAAA;AAAA,IAAAoC,QAAA,GAAArE,OAAA,CAAAb,OAAA,GAUa8C,+BAA+B","ignoreList":[]}

package/build/languageProcessing/researches/keyphraseLength.js

@@ -0,0 +1,23 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+/**
+ * Determines the length in words of the keyphrase.
+ *
+ * @param {Paper} paper 			The paper to research
+ * @param {Researcher} researcher 	The researcher to use for analysis
+ *
+ * @returns {Object} The length of the keyphrase and the function words list.
+ */
+function _default(paper, researcher) {
+  const topicForms = researcher.getResearch("morphology");
+  const functionWords = researcher.getConfig("functionWords");
+  return {
+    keyphraseLength: topicForms.keyphraseForms.length,
+    functionWords: functionWords
+  };
+}
+//# sourceMappingURL=keyphraseLength.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"keyphraseLength.js","names":["_default","paper","researcher","topicForms","getResearch","functionWords","getConfig","keyphraseLength","keyphraseForms","length"],"sources":["../../../src/languageProcessing/researches/keyphraseLength.js"],"sourcesContent":["/**\n * Determines the length in words of the keyphrase.\n *\n * @param {Paper} paper \t\t\tThe paper to research\n * @param {Researcher} researcher \tThe researcher to use for analysis\n *\n * @returns {Object} The length of the keyphrase and the function words list.\n */\nexport default function( paper, researcher ) {\n\tconst topicForms = researcher.getResearch( \"morphology\" );\n\tconst functionWords = researcher.getConfig( \"functionWords\" );\n\n\treturn {\n\t\tkeyphraseLength: topicForms.keyphraseForms.length,\n\t\tfunctionWords: functionWords,\n\t};\n}\n"],"mappings":";;;;;;AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAA,SAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C,MAAMC,UAAU,GAAGD,UAAU,CAACE,WAAW,CAAE,YAAa,CAAC;EACzD,MAAMC,aAAa,GAAGH,UAAU,CAACI,SAAS,CAAE,eAAgB,CAAC;EAE7D,OAAO;IACNC,eAAe,EAAEJ,UAAU,CAACK,cAAc,CAACC,MAAM;IACjDJ,aAAa,EAAEA;EAChB,CAAC;AACF","ignoreList":[]}