axyseo 2.1.12 → 2.1.19

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

@@ -0,0 +1 @@
+{"version":3,"file":"findTransitionWords.js","names":["createRegexFromDoubleArray","getSentences","normalizeSingle","normalizeSingleQuotes","isWordInSentence","matchWordInSentence","removeHtmlBlocks","flattenDeep","filterShortcodesFromHTML","regexFromDoubleArray","regexFromDoubleArrayCacheKey","getRegexFromDoubleArray","twoPartTransitionWords","cacheKey","join","matchTwoPartTransitionWords","sentence","twoPartTransitionWordsRegex","match","matchTransitionWords","transitionWords","filter","word","checkSentencesForTransitionWords","sentences","matchTransitionWordsHelper","results","forEach","twoPartMatches","push","transitionWordMatches","length","paper","researcher","getHelper","getConfig","memoizedTokenizer","text","getText","_attributes","shortcodes","sentenceResults","totalSentences","transitionWordSentences"],"sources":["../../../../src/languageProcessing/researches/findTransitionWords.js"],"sourcesContent":["import createRegexFromDoubleArray from \"../helpers/regex/createRegexFromDoubleArray.js\";\nimport getSentences from \"../helpers/sentence/getSentences.js\";\nimport { normalizeSingle as normalizeSingleQuotes } from \"../helpers/sanitize/quotes.js\";\nimport { isWordInSentence as matchWordInSentence } from \"../helpers/word/matchWordInSentence.js\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\n\nimport { flattenDeep } from \"lodash\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\n\nlet regexFromDoubleArray = null;\nlet regexFromDoubleArrayCacheKey = \"\";\n\n/**\n * Memoizes the createRegexFromDoubleArray with the twoPartTransitionWords.\n *\n * @param {Array} twoPartTransitionWords The array containing two-part transition words.\n *\n * @returns {RegExp} The RegExp to match text with a double array.\n */\nfunction getRegexFromDoubleArray( twoPartTransitionWords ) {\n\tconst cacheKey = flattenDeep( twoPartTransitionWords ).join( \"\" );\n\tif ( regexFromDoubleArrayCacheKey !== cacheKey || regexFromDoubleArray === null ) {\n\t\tregexFromDoubleArrayCacheKey = cacheKey;\n\t\tregexFromDoubleArray = createRegexFromDoubleArray( twoPartTransitionWords );\n\t}\n\treturn regexFromDoubleArray;\n}\n\n/**\n * Matches the sentence against two part transition words.\n *\n * @param {string} sentence The sentence to match against.\n * @param {Array} twoPartTransitionWords The array containing two-part transition words.\n * @returns {Array} The found transitional words.\n */\nconst matchTwoPartTransitionWords = function( sentence, twoPartTransitionWords ) {\n\tsentence = normalizeSingleQuotes( sentence );\n\tconst twoPartTransitionWordsRegex = getRegexFromDoubleArray( twoPartTransitionWords );\n\treturn sentence.match( twoPartTransitionWordsRegex );\n};\n\n/**\n * Matches the sentence against transition words.\n *\n * @param {string} sentence The sentence to match against.\n * @param {Array} transitionWords The array containing transition words.\n * @returns {Array} The found transitional words.\n */\nconst matchTransitionWords = function( sentence, transitionWords ) {\n\tsentence = normalizeSingleQuotes( sentence );\n\treturn transitionWords.filter( word => matchWordInSentence( word, sentence ) );\n};\n\n/**\n * Checks the passed sentences to see if they contain transition words.\n *\n * @param {Array} sentences The sentences to match against.\n * @param {Array} transitionWords The array containing transition words.\n * @param {Array} twoPartTransitionWords The array containing two part transition words.\n * @param {function} matchTransitionWordsHelper The language-specific helper function to match transition words in a sentence.\n *\n * @returns {Array} Array of sentence objects containing the complete sentence and the transition words.\n */\nconst checkSentencesForTransitionWords = function( sentences, transitionWords, twoPartTransitionWords, matchTransitionWordsHelper ) {\n\tconst results = [];\n\n\tsentences.forEach( sentence => {\n\t\tif ( twoPartTransitionWords ) {\n\t\t\tconst twoPartMatches = matchTwoPartTransitionWords( sentence, twoPartTransitionWords );\n\n\t\t\tif ( twoPartMatches !== null ) {\n\t\t\t\tresults.push( {\n\t\t\t\t\tsentence: sentence,\n\t\t\t\t\ttransitionWords: twoPartMatches,\n\t\t\t\t} );\n\n\t\t\t\treturn;\n\t\t\t}\n\t\t}\n\n\t\tconst transitionWordMatches = matchTransitionWordsHelper\n\t\t\t? matchTransitionWordsHelper( sentence, transitionWords )\n\t\t\t: matchTransitionWords( sentence, transitionWords );\n\n\t\tif ( transitionWordMatches.length !== 0 ) {\n\t\t\tresults.push( {\n\t\t\t\tsentence: sentence,\n\t\t\t\ttransitionWords: transitionWordMatches,\n\t\t\t} );\n\t\t}\n\t} );\n\n\treturn results;\n};\n\n/**\n * Checks how many sentences from a text contain at least one transition word or two-part transition word\n * that are defined in the transition words config and two part transition words config.\n *\n * @param {Paper} paper The Paper object to get text from.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {object} An object with the total number of sentences in the text\n *                   and the total number of sentences containing one or more transition words.\n */\nexport default function( paper, researcher ) {\n\tconst matchTransitionWordsHelper = researcher.getHelper( \"matchTransitionWordsHelper\" );\n\tconst transitionWords = researcher.getConfig( \"transitionWords\" );\n\tconst twoPartTransitionWords = researcher.getConfig( \"twoPartTransitionWords\" );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\tconst sentences = getSentences( text, memoizedTokenizer );\n\tconst sentenceResults = checkSentencesForTransitionWords( sentences, transitionWords, twoPartTransitionWords, matchTransitionWordsHelper );\n\n\treturn {\n\t\ttotalSentences: sentences.length,\n\t\tsentenceResults: sentenceResults,\n\t\ttransitionWordSentences: sentenceResults.length,\n\t};\n}\n"],"mappings":"AAAA,OAAOA,0BAA0B;AACjC,OAAOC,YAAY;AACnB,SAASC,eAAe,IAAIC,qBAAqB;AACjD,SAASC,gBAAgB,IAAIC,mBAAmB;AAChD,OAAOC,gBAAgB;AAEvB,SAASC,WAAW,QAAQ,QAAQ;AACpC,SAASC,wBAAwB;AAEjC,IAAIC,oBAAoB,GAAG,IAAI;AAC/B,IAAIC,4BAA4B,GAAG,EAAE;;AAErC;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,uBAAuBA,CAAEC,sBAAsB,EAAG;EAC1D,MAAMC,QAAQ,GAAGN,WAAW,CAAEK,sBAAuB,CAAC,CAACE,IAAI,CAAE,EAAG,CAAC;EACjE,IAAKJ,4BAA4B,KAAKG,QAAQ,IAAIJ,oBAAoB,KAAK,IAAI,EAAG;IACjFC,4BAA4B,GAAGG,QAAQ;IACvCJ,oBAAoB,GAAGT,0BAA0B,CAAEY,sBAAuB,CAAC;EAC5E;EACA,OAAOH,oBAAoB;AAC5B;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMM,2BAA2B,GAAG,SAAAA,CAAUC,QAAQ,EAAEJ,sBAAsB,EAAG;EAChFI,QAAQ,GAAGb,qBAAqB,CAAEa,QAAS,CAAC;EAC5C,MAAMC,2BAA2B,GAAGN,uBAAuB,CAAEC,sBAAuB,CAAC;EACrF,OAAOI,QAAQ,CAACE,KAAK,CAAED,2BAA4B,CAAC;AACrD,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,oBAAoB,GAAG,SAAAA,CAAUH,QAAQ,EAAEI,eAAe,EAAG;EAClEJ,QAAQ,GAAGb,qBAAqB,CAAEa,QAAS,CAAC;EAC5C,OAAOI,eAAe,CAACC,MAAM,CAAEC,IAAI,IAAIjB,mBAAmB,CAAEiB,IAAI,EAAEN,QAAS,CAAE,CAAC;AAC/E,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMO,gCAAgC,GAAG,SAAAA,CAAUC,SAAS,EAAEJ,eAAe,EAAER,sBAAsB,EAAEa,0BAA0B,EAAG;EACnI,MAAMC,OAAO,GAAG,EAAE;EAElBF,SAAS,CAACG,OAAO,CAAEX,QAAQ,IAAI;IAC9B,IAAKJ,sBAAsB,EAAG;MAC7B,MAAMgB,cAAc,GAAGb,2BAA2B,CAAEC,QAAQ,EAAEJ,sBAAuB,CAAC;MAEtF,IAAKgB,cAAc,KAAK,IAAI,EAAG;QAC9BF,OAAO,CAACG,IAAI,CAAE;UACbb,QAAQ,EAAEA,QAAQ;UAClBI,eAAe,EAAEQ;QAClB,CAAE,CAAC;QAEH;MACD;IACD;IAEA,MAAME,qBAAqB,GAAGL,0BAA0B,GACrDA,0BAA0B,CAAET,QAAQ,EAAEI,eAAgB,CAAC,GACvDD,oBAAoB,CAAEH,QAAQ,EAAEI,eAAgB,CAAC;IAEpD,IAAKU,qBAAqB,CAACC,MAAM,KAAK,CAAC,EAAG;MACzCL,OAAO,CAACG,IAAI,CAAE;QACbb,QAAQ,EAAEA,QAAQ;QAClBI,eAAe,EAAEU;MAClB,CAAE,CAAC;IACJ;EACD,CAAE,CAAC;EAEH,OAAOJ,OAAO;AACf,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUM,KAAK,EAAEC,UAAU,EAAG;EAC5C,MAAMR,0BAA0B,GAAGQ,UAAU,CAACC,SAAS,CAAE,4BAA6B,CAAC;EACvF,MAAMd,eAAe,GAAGa,UAAU,CAACE,SAAS,CAAE,iBAAkB,CAAC;EACjE,MAAMvB,sBAAsB,GAAGqB,UAAU,CAACE,SAAS,CAAE,wBAAyB,CAAC;EAC/E,MAAMC,iBAAiB,GAAGH,UAAU,CAACC,SAAS,CAAE,mBAAoB,CAAC;EAErE,IAAIG,IAAI,GAAGL,KAAK,CAACM,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAG/B,gBAAgB,CAAE+B,IAAK,CAAC;EAC/BA,IAAI,GAAG7B,wBAAwB,CAAE6B,IAAI,EAAEL,KAAK,CAACO,WAAW,IAAIP,KAAK,CAACO,WAAW,CAACC,UAAW,CAAC;EAC1F,MAAMhB,SAAS,GAAGvB,YAAY,CAAEoC,IAAI,EAAED,iBAAkB,CAAC;EACzD,MAAMK,eAAe,GAAGlB,gCAAgC,CAAEC,SAAS,EAAEJ,eAAe,EAAER,sBAAsB,EAAEa,0BAA2B,CAAC;EAE1I,OAAO;IACNiB,cAAc,EAAElB,SAAS,CAACO,MAAM;IAChCU,eAAe,EAAEA,eAAe;IAChCE,uBAAuB,EAAEF,eAAe,CAACV;EAC1C,CAAC;AACF","ignoreList":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"functionWordsInKeyphrase.js","names":["filter","includes","isEmpty","getWords","processExactMatchRequest","WORD_BOUNDARY_WITH_HYPHEN","paper","researcher","functionWords","getConfig","getWordsCustomHelper","getHelper","keyphrase","getKeyword","exactMatchRequested","keyphraseWords","word","trim","toLocaleLowerCase"],"sources":["../../../../src/languageProcessing/researches/functionWordsInKeyphrase.js"],"sourcesContent":["import { filter, includes, isEmpty } from \"lodash\";\nimport getWords from \"../helpers/word/getWords\";\nimport processExactMatchRequest from \"../helpers/match/processExactMatchRequest\";\nimport { WORD_BOUNDARY_WITH_HYPHEN } from \"../../config/wordBoundariesWithoutPunctuation\";\n\n/**\n * Checks if the keyphrase contains of function words only.\n *\n * @param {object} paper The paper containing the keyword.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {boolean} Whether the keyphrase contains of content words only.\n */\nexport default function( paper, researcher ) {\n\tconst functionWords = researcher.getConfig( \"functionWords\" );\n\n\t// A helper to get words from the keyphrase for languages that don't use the default way.\n\tconst getWordsCustomHelper = researcher.getHelper( \"getWordsCustomHelper\" );\n\tconst keyphrase = paper.getKeyword();\n\n\t// Return false if there are double quotes around the keyphrase.\n\tif ( processExactMatchRequest( keyphrase ).exactMatchRequested ) {\n\t\treturn false;\n\t}\n\n\t/*\n     * We use a word boundary regex that includes whitespaces, en-dashes, and hyphens for all languages.\n     * This means that we also consider keyphrases that consist of function words separated by hyphens (e.g. 'two-year-old')\n     * as containing only function words. Since many hyphenated phrases can also be written without hyphens, this way the\n     * behavior for hyphenated phrases matches the behavior for unhyphenated phrases.\n     * In Indonesian we normally don't want to treat hyphens as word boundaries, but in this case it makes sense because\n     * in Indonesian you can also have function words seperated by hyphens (e.g. 'dua-lima').\n     * As a downside, single function words containing hyphens (e.g. 'vis-à-vis') won't be automatically matched, but we\n     * are solving this by adding each word from such function words as separate entries in the function words lists.\n     */\n\tlet keyphraseWords = getWordsCustomHelper ? getWordsCustomHelper( keyphrase )\n\t\t: getWords( keyphrase, WORD_BOUNDARY_WITH_HYPHEN );\n\n\tkeyphraseWords = filter( keyphraseWords, function( word ) {\n\t\treturn ( ! includes( functionWords, word.trim().toLocaleLowerCase() ) );\n\t} );\n\n\treturn isEmpty( keyphraseWords );\n}\n"],"mappings":"AAAA,SAASA,MAAM,EAAEC,QAAQ,EAAEC,OAAO,QAAQ,QAAQ;AAClD,OAAOC,QAAQ;AACf,OAAOC,wBAAwB;AAC/B,SAASC,yBAAyB;;AAElC;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C,MAAMC,aAAa,GAAGD,UAAU,CAACE,SAAS,CAAE,eAAgB,CAAC;;EAE7D;EACA,MAAMC,oBAAoB,GAAGH,UAAU,CAACI,SAAS,CAAE,sBAAuB,CAAC;EAC3E,MAAMC,SAAS,GAAGN,KAAK,CAACO,UAAU,CAAC,CAAC;;EAEpC;EACA,IAAKT,wBAAwB,CAAEQ,SAAU,CAAC,CAACE,mBAAmB,EAAG;IAChE,OAAO,KAAK;EACb;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACC,IAAIC,cAAc,GAAGL,oBAAoB,GAAGA,oBAAoB,CAAEE,SAAU,CAAC,GAC1ET,QAAQ,CAAES,SAAS,EAAEP,yBAA0B,CAAC;EAEnDU,cAAc,GAAGf,MAAM,CAAEe,cAAc,EAAE,UAAUC,IAAI,EAAG;IACzD,OAAS,CAAEf,QAAQ,CAAEO,aAAa,EAAEQ,IAAI,CAACC,IAAI,CAAC,CAAC,CAACC,iBAAiB,CAAC,CAAE,CAAC;EACtE,CAAE,CAAC;EAEH,OAAOhB,OAAO,CAAEa,cAAe,CAAC;AACjC","ignoreList":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"getAnchorsWithKeyphrase.js","names":["flatten","uniq","filterWordsFromArray","findTopicFormsInString","getWords","matchTextWithArray","parseSynonyms","processExactMatchRequest","urlHelper","WORD_BOUNDARY_WITH_HYPHEN","WORD_BOUNDARY_WITHOUT_HYPHEN","getMatchHelper","functionWords","isLinkingToSelf","anchorLink","siteUrlOrDomain","Boolean","areEqual","isRelativeFragmentURL","getAnchorsLinkingToSelf","anchors","anchorsLinkingToSelf","map","anchor","attributes","href","filter","index","getAnchorsContainingTopic","topicForms","locale","matchWordCustomHelper","anchorsContainingTopic","anchorText","innerText","percentWordMatches","getAnchorsWithSameTextAsTopic","customHelpers","exactMatchRequest","areHyphensWordBoundaries","getWordsCustomHelper","keyphraseAndSynonymsWords","keyphraseForms","synonymsForms","forEach","form","push","anchorsContainedInTopic","currentAnchor","currentAnchorText","anchorWords","filteredAnchorWords","length","request","exactMatchRequested","every","anchorWord","keyphrase","includes","i","topicForm","count","paper","researcher","getConfig","result","anchorsWithKeyphrase","anchorsWithKeyphraseCount","getText","getKeyword","originalTopics","getSynonyms","getTree","findAll","treeNode","name","getPermalink","getLocale","getResearch","text","enhancedMatchHelper","getHelper","isExactMatchRequested","originalTopic"],"sources":["../../../../src/languageProcessing/researches/getAnchorsWithKeyphrase.js"],"sourcesContent":["import {flatten, uniq} from 'lodash';\nimport filterWordsFromArray from '../helpers/word/filterWordsFromArray';\nimport {findTopicFormsInString} from '../helpers/match/findKeywordFormsInString';\nimport getWords from '../helpers/word/getWords';\nimport matchTextWithArray from '../helpers/match/matchTextWithArray';\nimport parseSynonyms from '../helpers/sanitize/parseSynonyms';\nimport processExactMatchRequest from '../helpers/match/processExactMatchRequest';\nimport urlHelper from '../helpers/url/url.js';\nimport {\n  WORD_BOUNDARY_WITH_HYPHEN,\n  WORD_BOUNDARY_WITHOUT_HYPHEN\n} from '../../config/wordBoundariesWithoutPunctuation';\nimport {getMatchHelper} from '../helpers/language/chineseHelperFactory.js';\n\nlet functionWords = [];\n\n/**\n * Checks whether the anchor's link is a relative fragment or the same as the site url/domain.\n * Relative fragment links always point to the page itself.\n *\n * @param {String} anchorLink       The link anchor.\n * @param {String} siteUrlOrDomain  The site URL or domain of the paper.\n *\n * @returns {boolean} Whether the anchor's link is a relative fragment or the same as the site url/domain.\n */\nfunction isLinkingToSelf(anchorLink, siteUrlOrDomain) {\n  return Boolean(\n    urlHelper.areEqual(anchorLink, siteUrlOrDomain) || urlHelper.isRelativeFragmentURL(anchorLink)\n  );\n}\n\n/**\n * Gets the anchors whose url is not linking at the current site url/domain.\n *\n * @param {Array}   anchors         An array with all anchors from the paper.\n * @param {String}  siteUrlOrDomain The site URL or domain of the paper.\n *\n * @returns {Array} The array of all anchors whose url is not linking at the current site url/domain.\n */\nfunction getAnchorsLinkingToSelf(anchors, siteUrlOrDomain) {\n  const anchorsLinkingToSelf = anchors.map(function(anchor) {\n    const anchorLink = anchor.attributes.href;\n    // Return false if there is no href attribute.\n    return anchorLink ? isLinkingToSelf(anchorLink, siteUrlOrDomain) : false;\n  });\n\n  return anchors.filter((anchor, index) => !anchorsLinkingToSelf[index]);\n}\n\n/**\n * Gets the anchors with text that contains all content words of the topic (i.e. keyphrase or synonyms).\n *\n * @param {Array}       anchors         An array with all anchors from the paper\n * @param {Object}      topicForms      The object with topicForms. It contains all forms of the keyphrase and synonyms.\n * @param {String}      locale          The locale of the paper.\n * @param {Function}    matchWordCustomHelper The helper function to match word in text.\n *\n * @returns {String[]} The array of all anchors with text that contains all content words of the keyphrase or synonyms.\n */\nfunction getAnchorsContainingTopic(anchors, topicForms, locale, matchWordCustomHelper) {\n  const anchorsContainingTopic = anchors.map(function(anchor) {\n    // Only retrieve the anchor's text. This is because we only use the anchor text for the following check.\n    const anchorText = anchor.innerText();\n    return (\n      findTopicFormsInString(topicForms, anchorText, true, locale, matchWordCustomHelper)\n        .percentWordMatches === 100\n    );\n  });\n\n  return anchors.filter((anchor, index) => anchorsContainingTopic[index]);\n}\n\n/**\n * Gets the anchors with text that has the same content words as the keyphrase or synonyms.\n *\n * @param {Array}       anchors             \t\tAn array with all anchors from the paper.\n * @param {Object}      topicForms          \t\tThe object with topicForms. It contains all forms of the keyphrase and synonyms.\n * @param {string}      locale              \t\tThe locale of the paper.\n * @param {Object}      customHelpers       \t\tAn object containing custom helpers.\n * @param {Object[]}    exactMatchRequest   \t\tAn array of objects containing the keyphrase and information on whether\n * \t\t\t\t\t\t\t\t\t\t\t\t\tthe exact match has been requested.\n * @param {boolean}\t \tareHyphensWordBoundaries\tWhether hyphens should be treated as word boundaries.\n *\n * @returns {Array} The array of all anchors with text that has the same content words as the keyphrase/synonyms.\n */\nfunction getAnchorsWithSameTextAsTopic(\n  anchors,\n  topicForms,\n  locale,\n  customHelpers,\n  exactMatchRequest,\n  areHyphensWordBoundaries\n) {\n  const matchWordCustomHelper = customHelpers.matchWordCustomHelper;\n  const getWordsCustomHelper = customHelpers.getWordsCustomHelper;\n\n  // Prepare keyphrase and synonym forms for comparison with anchors.\n  const keyphraseAndSynonymsWords = [flatten(topicForms.keyphraseForms)];\n  const synonymsForms = topicForms.synonymsForms;\n  synonymsForms.forEach(form => keyphraseAndSynonymsWords.push(flatten(form)));\n\n  // The variable that will save all the anchors with text that has the same content words as the keyphrase/synonyms.\n  const anchorsContainedInTopic = [];\n\n  anchors.forEach(function(currentAnchor) {\n    const currentAnchorText = currentAnchor.innerText();\n\n    /*\n     * For keyphrase matching, we want to split words on hyphens and en-dashes, except for languages where hyphens shouldn't\n     * be treated as word boundaries. Currently, the latter only applies to Indonesian, where hyphens are used to create plural forms of nouns,\n     * such as \"buku-buku\" being a plural form of \"buku\". We want to treat forms like \"buku-buku\" as one word, so we shouldn't\n     * split words on hyphens in Indonesian.\n     * For languages where hyphens are treated as word boundaries we pass a custom word boundary regex string to the getWords helper\n     * that includes whitespaces, hyphens (u002d), and en-dashes (u2013). Otherwise, we pass a word boundary regex that only includes\n     * whitespaces and en-dashes.\n     */\n    let anchorWords;\n    if (getWordsCustomHelper) {\n      anchorWords = uniq(getWordsCustomHelper(currentAnchorText));\n    } else if (areHyphensWordBoundaries) {\n      anchorWords = uniq(getWords(currentAnchorText, WORD_BOUNDARY_WITH_HYPHEN));\n    } else {\n      anchorWords = uniq(getWords(currentAnchorText, WORD_BOUNDARY_WITHOUT_HYPHEN));\n    }\n\n    /*\n     * Filter function words out of the anchor text.\n     * If the anchor text contains only function words, we keep them.\n     */\n    const filteredAnchorWords = filterWordsFromArray(anchorWords, functionWords);\n    if (filteredAnchorWords.length > 0) {\n      anchorWords = filteredAnchorWords;\n    }\n\n    exactMatchRequest.forEach(request => {\n      /*\n       * Check a) if the exact match is requested for the keyphrase, and\n       * b) if every content word in the anchor text is included in the keyphrase or synonym.\n       */\n      if (\n        request.exactMatchRequested &&\n        anchorWords.every(anchorWord => request.keyphrase.includes(anchorWord))\n      ) {\n        anchorsContainedInTopic.push(true);\n      }\n    });\n\n    // Check if every word in the anchor text is also present in the keyphrase/synonym.\n    for (let i = 0; i < keyphraseAndSynonymsWords.length; i++) {\n      const topicForm = keyphraseAndSynonymsWords[i];\n\n      if (\n        anchorWords.every(\n          anchorWord =>\n            matchTextWithArray(anchorWord, topicForm, locale, matchWordCustomHelper).count > 0\n        )\n      ) {\n        anchorsContainedInTopic.push(true);\n        break;\n      }\n    }\n  });\n\n  return anchors.filter((anchor, index) => anchorsContainedInTopic[index]);\n}\n\n/**\n * Checks whether the content words of the anchor text are the same as the content words of the keyphrase or synonym.\n * Also includes different word forms if the morphology is available.\n *\n * @param {Paper}       paper       The paper to research.\n * @param {Researcher}  researcher  The researcher to use.\n *\n * @returns {Object} The amount of anchor texts whose content words are the same as the keyphrase or synonyms' content words.\n */\nexport default function(paper, researcher) {\n  functionWords = researcher.getConfig('functionWords');\n\n  const areHyphensWordBoundaries = researcher.getConfig('areHyphensWordBoundaries');\n\n  const result = {\n    anchorsWithKeyphrase: [],\n    anchorsWithKeyphraseCount: 0\n  };\n  // STEP 1.\n  // If the paper's text is empty, return empty result.\n  if (paper.getText() === '') {\n    return result;\n  }\n\n  // STEP 2.\n  const keyphrase = paper.getKeyword();\n  /*\n   * If no keyphrase is set, return empty result.\n   * This is a conscious decision where we won't assess the paper if the keyphrase is not set.\n   * This includes a case where only the synonym is set but not the keyphrase.\n   */\n  if (keyphrase === '') {\n    return result;\n  }\n  /*\n   * When the keyphrase is set, also retrieve the synonyms and save them in \"topics\" array.\n   * Eventually, the term topics here refers to either keyphrase or synonyms.\n   */\n  const originalTopics = parseSynonyms(paper.getSynonyms());\n  originalTopics.push(keyphrase);\n\n  // Retrieve the anchors.\n  let anchors = paper.getTree().findAll(treeNode => treeNode.name === 'a');\n  /*\n   * We get the site's URL (e.g., https://yoast.com) or domain (e.g., yoast.com) from the paper.\n   * In case of WordPress, the variable is a URL. In case of Shopify, it is a domain.\n   */\n  const siteUrlOrDomain = paper.getPermalink();\n\n  // STEP 3.\n  // Get the anchors with urls that are not linking to the current site url/domain.\n  anchors = getAnchorsLinkingToSelf(anchors, siteUrlOrDomain);\n  // If all anchor urls are linking to the current site url/domain, return empty result.\n  if (anchors.length === 0) {\n    return result;\n  }\n\n  const locale = paper.getLocale();\n  const topicForms = researcher.getResearch('morphology');\n\n  // Auto-detect Chinese and enhance helper if needed\n  const text = paper.getText();\n  const enhancedMatchHelper = getMatchHelper(\n    text,\n    keyphrase,\n    researcher.getHelper('matchWordCustomHelper')\n  );\n\n  const customHelpers = {\n    matchWordCustomHelper: enhancedMatchHelper,\n    getWordsCustomHelper: researcher.getHelper('getWordsCustomHelper')\n  };\n\n  // STEP 4.\n  // Get the anchors with text that contains the keyphrase/synonyms' content words.\n  anchors = getAnchorsContainingTopic(\n    anchors,\n    topicForms,\n    locale,\n    customHelpers.matchWordCustomHelper\n  );\n  // If all anchor texts do not contain the keyphrase/synonyms' content words, return empty result.\n  if (anchors.length === 0) {\n    return result;\n  }\n\n  // STEP 5.\n  // Check if exact match is requested for every topic (keyphrase or synonym).\n  const isExactMatchRequested = originalTopics.map(originalTopic =>\n    processExactMatchRequest(originalTopic)\n  );\n  // Get the anchors with text that has the same content words as the keyphrase/synonyms.\n  anchors = getAnchorsWithSameTextAsTopic(\n    anchors,\n    topicForms,\n    locale,\n    customHelpers,\n    isExactMatchRequested,\n    areHyphensWordBoundaries\n  );\n\n  return {\n    anchorsWithKeyphrase: anchors,\n    anchorsWithKeyphraseCount: anchors.length\n  };\n}\n"],"mappings":"AAAA,SAAQA,OAAO,EAAEC,IAAI,QAAO,QAAQ;AACpC,OAAOC,oBAAoB;AAC3B,SAAQC,sBAAsB;AAC9B,OAAOC,QAAQ;AACf,OAAOC,kBAAkB;AACzB,OAAOC,aAAa;AACpB,OAAOC,wBAAwB;AAC/B,OAAOC,SAAS;AAChB,SACEC,yBAAyB,EACzBC,4BAA4B;AAE9B,SAAQC,cAAc;AAEtB,IAAIC,aAAa,GAAG,EAAE;;AAEtB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,eAAeA,CAACC,UAAU,EAAEC,eAAe,EAAE;EACpD,OAAOC,OAAO,CACZR,SAAS,CAACS,QAAQ,CAACH,UAAU,EAAEC,eAAe,CAAC,IAAIP,SAAS,CAACU,qBAAqB,CAACJ,UAAU,CAC/F,CAAC;AACH;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASK,uBAAuBA,CAACC,OAAO,EAAEL,eAAe,EAAE;EACzD,MAAMM,oBAAoB,GAAGD,OAAO,CAACE,GAAG,CAAC,UAASC,MAAM,EAAE;IACxD,MAAMT,UAAU,GAAGS,MAAM,CAACC,UAAU,CAACC,IAAI;IACzC;IACA,OAAOX,UAAU,GAAGD,eAAe,CAACC,UAAU,EAAEC,eAAe,CAAC,GAAG,KAAK;EAC1E,CAAC,CAAC;EAEF,OAAOK,OAAO,CAACM,MAAM,CAAC,CAACH,MAAM,EAAEI,KAAK,KAAK,CAACN,oBAAoB,CAACM,KAAK,CAAC,CAAC;AACxE;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,yBAAyBA,CAACR,OAAO,EAAES,UAAU,EAAEC,MAAM,EAAEC,qBAAqB,EAAE;EACrF,MAAMC,sBAAsB,GAAGZ,OAAO,CAACE,GAAG,CAAC,UAASC,MAAM,EAAE;IAC1D;IACA,MAAMU,UAAU,GAAGV,MAAM,CAACW,SAAS,CAAC,CAAC;IACrC,OACE/B,sBAAsB,CAAC0B,UAAU,EAAEI,UAAU,EAAE,IAAI,EAAEH,MAAM,EAAEC,qBAAqB,CAAC,CAChFI,kBAAkB,KAAK,GAAG;EAEjC,CAAC,CAAC;EAEF,OAAOf,OAAO,CAACM,MAAM,CAAC,CAACH,MAAM,EAAEI,KAAK,KAAKK,sBAAsB,CAACL,KAAK,CAAC,CAAC;AACzE;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASS,6BAA6BA,CACpChB,OAAO,EACPS,UAAU,EACVC,MAAM,EACNO,aAAa,EACbC,iBAAiB,EACjBC,wBAAwB,EACxB;EACA,MAAMR,qBAAqB,GAAGM,aAAa,CAACN,qBAAqB;EACjE,MAAMS,oBAAoB,GAAGH,aAAa,CAACG,oBAAoB;;EAE/D;EACA,MAAMC,yBAAyB,GAAG,CAACzC,OAAO,CAAC6B,UAAU,CAACa,cAAc,CAAC,CAAC;EACtE,MAAMC,aAAa,GAAGd,UAAU,CAACc,aAAa;EAC9CA,aAAa,CAACC,OAAO,CAACC,IAAI,IAAIJ,yBAAyB,CAACK,IAAI,CAAC9C,OAAO,CAAC6C,IAAI,CAAC,CAAC,CAAC;;EAE5E;EACA,MAAME,uBAAuB,GAAG,EAAE;EAElC3B,OAAO,CAACwB,OAAO,CAAC,UAASI,aAAa,EAAE;IACtC,MAAMC,iBAAiB,GAAGD,aAAa,CAACd,SAAS,CAAC,CAAC;;IAEnD;AACJ;AACA;AACA;AACA;AACA;AACA;AACA;AACA;IACI,IAAIgB,WAAW;IACf,IAAIV,oBAAoB,EAAE;MACxBU,WAAW,GAAGjD,IAAI,CAACuC,oBAAoB,CAACS,iBAAiB,CAAC,CAAC;IAC7D,CAAC,MAAM,IAAIV,wBAAwB,EAAE;MACnCW,WAAW,GAAGjD,IAAI,CAACG,QAAQ,CAAC6C,iBAAiB,EAAExC,yBAAyB,CAAC,CAAC;IAC5E,CAAC,MAAM;MACLyC,WAAW,GAAGjD,IAAI,CAACG,QAAQ,CAAC6C,iBAAiB,EAAEvC,4BAA4B,CAAC,CAAC;IAC/E;;IAEA;AACJ;AACA;AACA;IACI,MAAMyC,mBAAmB,GAAGjD,oBAAoB,CAACgD,WAAW,EAAEtC,aAAa,CAAC;IAC5E,IAAIuC,mBAAmB,CAACC,MAAM,GAAG,CAAC,EAAE;MAClCF,WAAW,GAAGC,mBAAmB;IACnC;IAEAb,iBAAiB,CAACM,OAAO,CAACS,OAAO,IAAI;MACnC;AACN;AACA;AACA;MACM,IACEA,OAAO,CAACC,mBAAmB,IAC3BJ,WAAW,CAACK,KAAK,CAACC,UAAU,IAAIH,OAAO,CAACI,SAAS,CAACC,QAAQ,CAACF,UAAU,CAAC,CAAC,EACvE;QACAT,uBAAuB,CAACD,IAAI,CAAC,IAAI,CAAC;MACpC;IACF,CAAC,CAAC;;IAEF;IACA,KAAK,IAAIa,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGlB,yBAAyB,CAACW,MAAM,EAAEO,CAAC,EAAE,EAAE;MACzD,MAAMC,SAAS,GAAGnB,yBAAyB,CAACkB,CAAC,CAAC;MAE9C,IACET,WAAW,CAACK,KAAK,CACfC,UAAU,IACRnD,kBAAkB,CAACmD,UAAU,EAAEI,SAAS,EAAE9B,MAAM,EAAEC,qBAAqB,CAAC,CAAC8B,KAAK,GAAG,CACrF,CAAC,EACD;QACAd,uBAAuB,CAACD,IAAI,CAAC,IAAI,CAAC;QAClC;MACF;IACF;EACF,CAAC,CAAC;EAEF,OAAO1B,OAAO,CAACM,MAAM,CAAC,CAACH,MAAM,EAAEI,KAAK,KAAKoB,uBAAuB,CAACpB,KAAK,CAAC,CAAC;AAC1E;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAASmC,KAAK,EAAEC,UAAU,EAAE;EACzCnD,aAAa,GAAGmD,UAAU,CAACC,SAAS,CAAC,eAAe,CAAC;EAErD,MAAMzB,wBAAwB,GAAGwB,UAAU,CAACC,SAAS,CAAC,0BAA0B,CAAC;EAEjF,MAAMC,MAAM,GAAG;IACbC,oBAAoB,EAAE,EAAE;IACxBC,yBAAyB,EAAE;EAC7B,CAAC;EACD;EACA;EACA,IAAIL,KAAK,CAACM,OAAO,CAAC,CAAC,KAAK,EAAE,EAAE;IAC1B,OAAOH,MAAM;EACf;;EAEA;EACA,MAAMR,SAAS,GAAGK,KAAK,CAACO,UAAU,CAAC,CAAC;EACpC;AACF;AACA;AACA;AACA;EACE,IAAIZ,SAAS,KAAK,EAAE,EAAE;IACpB,OAAOQ,MAAM;EACf;EACA;AACF;AACA;AACA;EACE,MAAMK,cAAc,GAAGhE,aAAa,CAACwD,KAAK,CAACS,WAAW,CAAC,CAAC,CAAC;EACzDD,cAAc,CAACxB,IAAI,CAACW,SAAS,CAAC;;EAE9B;EACA,IAAIrC,OAAO,GAAG0C,KAAK,CAACU,OAAO,CAAC,CAAC,CAACC,OAAO,CAACC,QAAQ,IAAIA,QAAQ,CAACC,IAAI,KAAK,GAAG,CAAC;EACxE;AACF;AACA;AACA;EACE,MAAM5D,eAAe,GAAG+C,KAAK,CAACc,YAAY,CAAC,CAAC;;EAE5C;EACA;EACAxD,OAAO,GAAGD,uBAAuB,CAACC,OAAO,EAAEL,eAAe,CAAC;EAC3D;EACA,IAAIK,OAAO,CAACgC,MAAM,KAAK,CAAC,EAAE;IACxB,OAAOa,MAAM;EACf;EAEA,MAAMnC,MAAM,GAAGgC,KAAK,CAACe,SAAS,CAAC,CAAC;EAChC,MAAMhD,UAAU,GAAGkC,UAAU,CAACe,WAAW,CAAC,YAAY,CAAC;;EAEvD;EACA,MAAMC,IAAI,GAAGjB,KAAK,CAACM,OAAO,CAAC,CAAC;EAC5B,MAAMY,mBAAmB,GAAGrE,cAAc,CACxCoE,IAAI,EACJtB,SAAS,EACTM,UAAU,CAACkB,SAAS,CAAC,uBAAuB,CAC9C,CAAC;EAED,MAAM5C,aAAa,GAAG;IACpBN,qBAAqB,EAAEiD,mBAAmB;IAC1CxC,oBAAoB,EAAEuB,UAAU,CAACkB,SAAS,CAAC,sBAAsB;EACnE,CAAC;;EAED;EACA;EACA7D,OAAO,GAAGQ,yBAAyB,CACjCR,OAAO,EACPS,UAAU,EACVC,MAAM,EACNO,aAAa,CAACN,qBAChB,CAAC;EACD;EACA,IAAIX,OAAO,CAACgC,MAAM,KAAK,CAAC,EAAE;IACxB,OAAOa,MAAM;EACf;;EAEA;EACA;EACA,MAAMiB,qBAAqB,GAAGZ,cAAc,CAAChD,GAAG,CAAC6D,aAAa,IAC5D5E,wBAAwB,CAAC4E,aAAa,CACxC,CAAC;EACD;EACA/D,OAAO,GAAGgB,6BAA6B,CACrChB,OAAO,EACPS,UAAU,EACVC,MAAM,EACNO,aAAa,EACb6C,qBAAqB,EACrB3C,wBACF,CAAC;EAED,OAAO;IACL2B,oBAAoB,EAAE9C,OAAO;IAC7B+C,yBAAyB,EAAE/C,OAAO,CAACgC;EACrC,CAAC;AACH","ignoreList":[]}

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

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

package/build/esm/languageProcessing/researches/getKeywordDensity.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getKeywordDensity.js","names":["countWords","getKeyphraseDensity","paper","researcher","getWordsCustomHelper","getHelper","wordCount","getText","length","keyphraseCount","getResearch","count","getKeywordDensity","console","warn"],"sources":["../../../../src/languageProcessing/researches/getKeywordDensity.js"],"sourcesContent":["import countWords from '@axyseo/languageProcessing/helpers/word/countWords';\n\n/**\n * Calculates the keyphrase density.\n *\n * @param {Paper} paper The paper containing keyphrase and text.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {number} The keyphrase density.\n */\nexport default function getKeyphraseDensity(paper, researcher) {\n  const getWordsCustomHelper = researcher.getHelper('getWordsCustomHelper');\n  let wordCount = 0;\n\n  // If there is a custom getWords helper, use its output for countWords.\n  if (getWordsCustomHelper) {\n    wordCount = getWordsCustomHelper(paper.getText()).length;\n  } else {\n    wordCount = countWords(paper.getText());\n  }\n\n  if (wordCount === 0) {\n    return 0;\n  }\n  const keyphraseCount = researcher.getResearch('getKeyphraseCount');\n  return (keyphraseCount.count / wordCount) * 100;\n}\n\n/**\n * Calculates the keyphrase density.\n *\n * @deprecated Use getKeyphraseDensity instead.\n *\n * @param {Paper} paper The paper containing keyphrase and text.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {number} The keyphrase density.\n */\nexport function getKeywordDensity(paper, researcher) {\n  console.warn('This function is deprecated, use getKeyphraseDensity instead.');\n  return getKeyphraseDensity(paper, researcher);\n}\n"],"mappings":"AAAA,OAAOA,UAAU;;AAEjB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASC,mBAAmBA,CAACC,KAAK,EAAEC,UAAU,EAAE;EAC7D,MAAMC,oBAAoB,GAAGD,UAAU,CAACE,SAAS,CAAC,sBAAsB,CAAC;EACzE,IAAIC,SAAS,GAAG,CAAC;;EAEjB;EACA,IAAIF,oBAAoB,EAAE;IACxBE,SAAS,GAAGF,oBAAoB,CAACF,KAAK,CAACK,OAAO,CAAC,CAAC,CAAC,CAACC,MAAM;EAC1D,CAAC,MAAM;IACLF,SAAS,GAAGN,UAAU,CAACE,KAAK,CAACK,OAAO,CAAC,CAAC,CAAC;EACzC;EAEA,IAAID,SAAS,KAAK,CAAC,EAAE;IACnB,OAAO,CAAC;EACV;EACA,MAAMG,cAAc,GAAGN,UAAU,CAACO,WAAW,CAAC,mBAAmB,CAAC;EAClE,OAAQD,cAAc,CAACE,KAAK,GAAGL,SAAS,GAAI,GAAG;AACjD;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,SAASM,iBAAiBA,CAACV,KAAK,EAAEC,UAAU,EAAE;EACnDU,OAAO,CAACC,IAAI,CAAC,+DAA+D,CAAC;EAC7E,OAAOb,mBAAmB,CAACC,KAAK,EAAEC,UAAU,CAAC;AAC/C","ignoreList":[]}

package/build/esm/languageProcessing/researches/getLinkStatistics.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getLinkStatistics.js","names":["checkNofollow","getAnchors","getLinkType","paper","anchors","getText","siteUrlOrDomain","getPermalink","linkCount","total","length","internalTotal","internalDofollow","internalNofollow","externalTotal","externalDofollow","externalNofollow","otherTotal","otherDofollow","otherNofollow","i","currentAnchor","linkType","linkFollow"],"sources":["../../../../src/languageProcessing/researches/getLinkStatistics.js"],"sourcesContent":["import checkNofollow from \"../helpers/link/checkNofollow.js\";\nimport getAnchors from \"../helpers/link/getAnchorsFromText.js\";\nimport getLinkType from \"../helpers/link/getLinkType.js\";\n\n/**\n * Counts the links found in the text.\n *\n * @param {Paper} paper The paper object containing text, keyword and url.\n *\n * @returns {object} The object containing all linktypes.\n * total: the total number of links found.\n * internalTotal: the total number of links that are internal.\n * internalDofollow: the internal links without a nofollow attribute.\n * internalNofollow: the internal links with a nofollow attribute.\n * externalTotal: the total number of links that are external.\n * externalDofollow: the external links without a nofollow attribute.\n * externalNofollow: the internal links with a dofollow attribute.\n * otherTotal: all links that are not HTTP or HTTPS.\n * otherDofollow: other links without a nofollow attribute.\n * otherNofollow: other links with a nofollow attribute.\n */\nexport default function( paper ) {\n\tconst anchors = getAnchors( paper.getText() );\n\t/*\n\t * We get the site's URL (e.g., https://yoast.com) or domain (e.g., yoast.com) from the paper.\n\t * In case of WordPress, the variable is a URL. In case of Shopify, it is a domain.\n\t */\n\tconst siteUrlOrDomain = paper.getPermalink();\n\n\tconst linkCount = {\n\t\ttotal: anchors.length,\n\t\tinternalTotal: 0,\n\t\tinternalDofollow: 0,\n\t\tinternalNofollow: 0,\n\t\texternalTotal: 0,\n\t\texternalDofollow: 0,\n\t\texternalNofollow: 0,\n\t\totherTotal: 0,\n\t\totherDofollow: 0,\n\t\totherNofollow: 0,\n\t};\n\n\tfor ( let i = 0; i < anchors.length; i++ ) {\n\t\tconst currentAnchor = anchors[ i ];\n\n\t\tconst linkType = getLinkType( currentAnchor, siteUrlOrDomain );\n\t\tconst linkFollow = checkNofollow( currentAnchor );\n\n\t\tlinkCount[ linkType + \"Total\" ]++;\n\t\tlinkCount[ linkType + linkFollow ]++;\n\t}\n\n\treturn linkCount;\n}\n"],"mappings":"AAAA,OAAOA,aAAa;AACpB,OAAOC,UAAU;AACjB,OAAOC,WAAW;;AAElB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,KAAK,EAAG;EAChC,MAAMC,OAAO,GAAGH,UAAU,CAAEE,KAAK,CAACE,OAAO,CAAC,CAAE,CAAC;EAC7C;AACD;AACA;AACA;EACC,MAAMC,eAAe,GAAGH,KAAK,CAACI,YAAY,CAAC,CAAC;EAE5C,MAAMC,SAAS,GAAG;IACjBC,KAAK,EAAEL,OAAO,CAACM,MAAM;IACrBC,aAAa,EAAE,CAAC;IAChBC,gBAAgB,EAAE,CAAC;IACnBC,gBAAgB,EAAE,CAAC;IACnBC,aAAa,EAAE,CAAC;IAChBC,gBAAgB,EAAE,CAAC;IACnBC,gBAAgB,EAAE,CAAC;IACnBC,UAAU,EAAE,CAAC;IACbC,aAAa,EAAE,CAAC;IAChBC,aAAa,EAAE;EAChB,CAAC;EAED,KAAM,IAAIC,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGhB,OAAO,CAACM,MAAM,EAAEU,CAAC,EAAE,EAAG;IAC1C,MAAMC,aAAa,GAAGjB,OAAO,CAAEgB,CAAC,CAAE;IAElC,MAAME,QAAQ,GAAGpB,WAAW,CAAEmB,aAAa,EAAEf,eAAgB,CAAC;IAC9D,MAAMiB,UAAU,GAAGvB,aAAa,CAAEqB,aAAc,CAAC;IAEjDb,SAAS,CAAEc,QAAQ,GAAG,OAAO,CAAE,EAAE;IACjCd,SAAS,CAAEc,QAAQ,GAAGC,UAAU,CAAE,EAAE;EACrC;EAEA,OAAOf,SAAS;AACjB","ignoreList":[]}

package/build/esm/languageProcessing/researches/getLinks.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getLinks.js","names":["getAnchors","map","url","paper","anchors","getText","getFromAnchorTag"],"sources":["../../../../src/languageProcessing/researches/getLinks.js"],"sourcesContent":["/** @module analyses/getLinkStatistics */\n\nimport getAnchors from \"../helpers/link/getAnchorsFromText.js\";\n\nimport { map } from \"lodash\";\nimport url from \"../helpers/url/url.js\";\n\n/**\n * Checks a text for anchors and returns the number found.\n *\n * @param {Object} paper The paper to get the text from.\n * @returns {Array} An array with the anchors\n */\nexport default function( paper ) {\n\tconst anchors = getAnchors( paper.getText() );\n\n\treturn map( anchors, url.getFromAnchorTag );\n}\n"],"mappings":"AAAA;;AAEA,OAAOA,UAAU;AAEjB,SAASC,GAAG,QAAQ,QAAQ;AAC5B,OAAOC,GAAG;;AAEV;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,KAAK,EAAG;EAChC,MAAMC,OAAO,GAAGJ,UAAU,CAAEG,KAAK,CAACE,OAAO,CAAC,CAAE,CAAC;EAE7C,OAAOJ,GAAG,CAAEG,OAAO,EAAEF,GAAG,CAACI,gBAAiB,CAAC;AAC5C","ignoreList":[]}

package/build/esm/languageProcessing/researches/getLongCenterAlignedTexts.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getLongCenterAlignedTexts.js","names":["MAX_CENTER_ALIGNED_LENGTH","HEADING_TAGS_REGEX","getLongCenterAlignedElements","nodes","filter","node","isCenterAligned","attributes","class","Set","has","innerText","length","paper","tree","getTree","paragraphs","findAll","name","headings","test","concat"],"sources":["../../../../src/languageProcessing/researches/getLongCenterAlignedTexts.js"],"sourcesContent":["/**\n * The maximum allowed length of a center-aligned paragraph or heading in characters.\n * @type {number}\n */\nconst MAX_CENTER_ALIGNED_LENGTH = 50;\n\n/**\n * A regular expression to match heading tags.\n * @type {RegExp}\n */\nconst HEADING_TAGS_REGEX = /^h[1-6]$/;\n\n/**\n * Filters out all nodes that are center-aligned and longer than 50 characters (as defined in `MAX_CENTER_ALIGNED_LENGTH`).\n * @param {Node[]} nodes An array of nodes.\n * @returns {Node[]} An array containing all center-aligned nodes that are longer than 50 characters.\n */\nfunction getLongCenterAlignedElements( nodes ) {\n\treturn nodes.filter( node => {\n\t\tconst isCenterAligned = node.attributes.class instanceof Set && node.attributes.class.has( \"has-text-align-center\" );\n\t\treturn isCenterAligned && node.innerText().length > MAX_CENTER_ALIGNED_LENGTH;\n\t} );\n}\n\n/**\n * Finds all paragraphs and headings that are center-aligned and longer than 50 characters (after stripping HTML tags).\n * @param {Paper} paper The paper to analyze.\n * @returns {Node[]} An array of nodes containing too long center-aligned paragraphs/headings.\n */\nexport default function( paper ) {\n\tconst tree = paper.getTree();\n\n\tconst paragraphs = tree.findAll( node => node.name === \"p\" );\n\tconst headings = tree.findAll( node => HEADING_TAGS_REGEX.test( node.name ) );\n\n\treturn getLongCenterAlignedElements( paragraphs.concat( headings ) );\n}\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA,MAAMA,yBAAyB,GAAG,EAAE;;AAEpC;AACA;AACA;AACA;AACA,MAAMC,kBAAkB,GAAG,UAAU;;AAErC;AACA;AACA;AACA;AACA;AACA,SAASC,4BAA4BA,CAAEC,KAAK,EAAG;EAC9C,OAAOA,KAAK,CAACC,MAAM,CAAEC,IAAI,IAAI;IAC5B,MAAMC,eAAe,GAAGD,IAAI,CAACE,UAAU,CAACC,KAAK,YAAYC,GAAG,IAAIJ,IAAI,CAACE,UAAU,CAACC,KAAK,CAACE,GAAG,CAAE,uBAAwB,CAAC;IACpH,OAAOJ,eAAe,IAAID,IAAI,CAACM,SAAS,CAAC,CAAC,CAACC,MAAM,GAAGZ,yBAAyB;EAC9E,CAAE,CAAC;AACJ;;AAEA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUa,KAAK,EAAG;EAChC,MAAMC,IAAI,GAAGD,KAAK,CAACE,OAAO,CAAC,CAAC;EAE5B,MAAMC,UAAU,GAAGF,IAAI,CAACG,OAAO,CAAEZ,IAAI,IAAIA,IAAI,CAACa,IAAI,KAAK,GAAI,CAAC;EAC5D,MAAMC,QAAQ,GAAGL,IAAI,CAACG,OAAO,CAAEZ,IAAI,IAAIJ,kBAAkB,CAACmB,IAAI,CAAEf,IAAI,CAACa,IAAK,CAAE,CAAC;EAE7E,OAAOhB,4BAA4B,CAAEc,UAAU,CAACK,MAAM,CAAEF,QAAS,CAAE,CAAC;AACrE","ignoreList":[]}

package/build/esm/languageProcessing/researches/getParagraphLength.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getParagraphLength.js","names":["imageRegex","sanitizeLineBreakTag","countWords","matchParagraphs","filter","removeHtmlBlocks","filterShortcodesFromHTML","paper","researcher","text","getText","_attributes","shortcodes","replace","paragraphs","paragraphsLength","customCountLength","getHelper","map","paragraph","push","countLength","paragraphLength"],"sources":["../../../../src/languageProcessing/researches/getParagraphLength.js"],"sourcesContent":["import { imageRegex } from \"../helpers/image/imageInText\";\nimport sanitizeLineBreakTag from \"../helpers/sanitize/sanitizeLineBreakTag\";\nimport countWords from \"../helpers/word/countWords.js\";\nimport matchParagraphs from \"../helpers/html/matchParagraphs.js\";\nimport { filter } from \"lodash\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\n\n/**\n * Gets all paragraphs and their word counts or character counts from the text.\n *\n * @param {Paper} \t\tpaper \t\tThe paper object to get the text from.\n * @param {Researcher} \tresearcher \tThe researcher to use for analysis.\n *\n * @returns {Array} The array containing an object with the paragraph word or character count and paragraph text.\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\n\t// Remove images from text before retrieving the paragraphs.\n\t// This step is done here so that applying highlight in captions is possible for ParagraphTooLongAssessment.\n\ttext = text.replace( imageRegex, \"\" );\n\n\t// Replace line break tags containing attribute(s) with paragraph tag.\n\ttext = sanitizeLineBreakTag( text );\n\tconst paragraphs = matchParagraphs( text );\n\tconst paragraphsLength = [];\n\n\t// An optional custom helper to count length to use instead of countWords.\n\tconst customCountLength = researcher.getHelper( \"customCountLength\" );\n\n\tparagraphs.map( function( paragraph ) {\n\t\tparagraphsLength.push( {\n\t\t\tcountLength: customCountLength ? customCountLength( paragraph ) : countWords( paragraph ),\n\t\t\ttext: paragraph,\n\t\t} );\n\t} );\n\n\treturn filter( paragraphsLength, function( paragraphLength ) {\n\t\treturn ( paragraphLength.countLength > 0 );\n\t} );\n}\n"],"mappings":"AAAA,SAASA,UAAU;AACnB,OAAOC,oBAAoB;AAC3B,OAAOC,UAAU;AACjB,OAAOC,eAAe;AACtB,SAASC,MAAM,QAAQ,QAAQ;AAC/B,OAAOC,gBAAgB;AACvB,SAASC,wBAAwB;;AAEjC;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C,IAAIC,IAAI,GAAGF,KAAK,CAACG,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAGJ,gBAAgB,CAAEI,IAAK,CAAC;EAC/BA,IAAI,GAAGH,wBAAwB,CAAEG,IAAI,EAAEF,KAAK,CAACI,WAAW,IAAIJ,KAAK,CAACI,WAAW,CAACC,UAAW,CAAC;;EAE1F;EACA;EACAH,IAAI,GAAGA,IAAI,CAACI,OAAO,CAAEb,UAAU,EAAE,EAAG,CAAC;;EAErC;EACAS,IAAI,GAAGR,oBAAoB,CAAEQ,IAAK,CAAC;EACnC,MAAMK,UAAU,GAAGX,eAAe,CAAEM,IAAK,CAAC;EAC1C,MAAMM,gBAAgB,GAAG,EAAE;;EAE3B;EACA,MAAMC,iBAAiB,GAAGR,UAAU,CAACS,SAAS,CAAE,mBAAoB,CAAC;EAErEH,UAAU,CAACI,GAAG,CAAE,UAAUC,SAAS,EAAG;IACrCJ,gBAAgB,CAACK,IAAI,CAAE;MACtBC,WAAW,EAAEL,iBAAiB,GAAGA,iBAAiB,CAAEG,SAAU,CAAC,GAAGjB,UAAU,CAAEiB,SAAU,CAAC;MACzFV,IAAI,EAAEU;IACP,CAAE,CAAC;EACJ,CAAE,CAAC;EAEH,OAAOf,MAAM,CAAEW,gBAAgB,EAAE,UAAUO,eAAe,EAAG;IAC5D,OAASA,eAAe,CAACD,WAAW,GAAG,CAAC;EACzC,CAAE,CAAC;AACJ","ignoreList":[]}

package/build/esm/languageProcessing/researches/getParagraphs.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getParagraphs.js","names":["reject","paper","paragraphs","getTree","findAll","node","name","paragraph","sentences","length","allLinks","childNodes","every","textContent","innerText","trim"],"sources":["../../../../src/languageProcessing/researches/getParagraphs.js"],"sourcesContent":["import {reject} from 'lodash';\n\n/**\n * Returns all paragraphs in a given Paper.\n * Remove paragraphs that do not contain sentences or only consist of links.\n *\n * @param {Paper} paper The current paper.\n * @returns {Paragraph[]} All paragraphs in the paper.\n */\nexport default function(paper) {\n  let paragraphs = paper.getTree().findAll(node => node.name === 'p');\n\n  // Remove empty paragraphs without sentences and paragraphs only consisting of empty links.\n  paragraphs = reject(paragraphs, paragraph => paragraph.sentences.length === 0);\n  // Don't remove paragraphs with links that contain meaningful text\n  paragraphs = reject(paragraphs, paragraph => {\n    // Only reject if ALL children are links AND those links are empty/meaningless\n    const allLinks = paragraph.childNodes.every(node => node.name === 'a');\n    if (!allLinks) return false;\n\n    // Check if the paragraph has meaningful text content\n    const textContent = paragraph.innerText().trim();\n    return textContent.length === 0; // Only reject if completely empty\n  });\n\n  return paragraphs;\n}\n"],"mappings":"AAAA,SAAQA,MAAM,QAAO,QAAQ;;AAE7B;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAASC,KAAK,EAAE;EAC7B,IAAIC,UAAU,GAAGD,KAAK,CAACE,OAAO,CAAC,CAAC,CAACC,OAAO,CAACC,IAAI,IAAIA,IAAI,CAACC,IAAI,KAAK,GAAG,CAAC;;EAEnE;EACAJ,UAAU,GAAGF,MAAM,CAACE,UAAU,EAAEK,SAAS,IAAIA,SAAS,CAACC,SAAS,CAACC,MAAM,KAAK,CAAC,CAAC;EAC9E;EACAP,UAAU,GAAGF,MAAM,CAACE,UAAU,EAAEK,SAAS,IAAI;IAC3C;IACA,MAAMG,QAAQ,GAAGH,SAAS,CAACI,UAAU,CAACC,KAAK,CAACP,IAAI,IAAIA,IAAI,CAACC,IAAI,KAAK,GAAG,CAAC;IACtE,IAAI,CAACI,QAAQ,EAAE,OAAO,KAAK;;IAE3B;IACA,MAAMG,WAAW,GAAGN,SAAS,CAACO,SAAS,CAAC,CAAC,CAACC,IAAI,CAAC,CAAC;IAChD,OAAOF,WAAW,CAACJ,MAAM,KAAK,CAAC,CAAC,CAAC;EACnC,CAAC,CAAC;EAEF,OAAOP,UAAU;AACnB","ignoreList":[]}

package/build/esm/languageProcessing/researches/getPassiveVoiceResult.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getPassiveVoiceResult.js","names":["getSentences","stripFullTags","stripHTMLTags","Sentence","forEach","removeHtmlBlocks","filterShortcodesFromHTML","getMorphologicalPassives","paper","researcher","isPassiveSentence","getHelper","text","getText","_attributes","shortcodes","memoizedTokenizer","sentences","map","sentence","totalNumberSentences","length","passiveSentences","strippedSentence","getSentenceText","toLocaleLowerCase","setPassive","isPassive","push","total","passives","getPeriphrasticPassives","getClauses","clauses","setClauses","getMorphologicalAndPeriphrasticPassive","morphologicalPassives","periphrasticPassives","concat","getPassiveVoice","passiveType","getConfig"],"sources":["../../../../src/languageProcessing/researches/getPassiveVoiceResult.js"],"sourcesContent":["import getSentences from \"../helpers/sentence/getSentences.js\";\nimport { stripFullTags as stripHTMLTags } from \"../helpers/sanitize/stripHTMLTags.js\";\nimport Sentence from \"../../languageProcessing/values/Sentence.js\";\n\nimport { forEach } from \"lodash\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\n\n/**\n * Looks for morphological passive voice.\n * Supported morphological languages: \"ru\", \"sv\", \"id\", \"ar\", \"he\", \"tr\", \"fa\".\n * Farsi is implemented as morphological because the periphrastic passives are used as compound verbs (among other compound passives).\n * @param {Paper}      paper      The paper object.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The found passive sentences.\n */\nexport const getMorphologicalPassives = function( paper, researcher ) {\n\tconst isPassiveSentence = researcher.getHelper( \"isPassiveSentence\" );\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\tconst sentences = getSentences( text, memoizedTokenizer )\n\t\t.map( function( sentence ) {\n\t\t\treturn new Sentence( sentence );\n\t\t} );\n\tconst totalNumberSentences = sentences.length;\n\tconst passiveSentences = [];\n\n\tforEach( sentences, function( sentence ) {\n\t\tconst strippedSentence = stripHTMLTags( sentence.getSentenceText() ).toLocaleLowerCase();\n\n\t\tsentence.setPassive( isPassiveSentence( strippedSentence ) );\n\n\t\tif ( sentence.isPassive() === true ) {\n\t\t\tpassiveSentences.push( sentence.getSentenceText() );\n\t\t}\n\t} );\n\n\treturn {\n\t\ttotal: totalNumberSentences,\n\t\tpassives: passiveSentences,\n\t};\n};\n\n/**\n * Looks for periphrastic passive voice.\n * Supported periphrastic languages: \"en\", \"de\", \"nl\", \"fr\", \"es\", \"it\", \"pt\", \"pl\", \"sk\".\n *\n * @param {Paper}      paper      The paper object.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The found passive sentences.\n */\nexport const getPeriphrasticPassives = function( paper, researcher ) {\n\tconst getClauses = researcher.getHelper( \"getClauses\" );\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\tconst sentences = getSentences( text, memoizedTokenizer )\n\t\t.map( function( sentence ) {\n\t\t\treturn new Sentence( sentence );\n\t\t} );\n\tconst totalNumberSentences = sentences.length;\n\tconst passiveSentences = [];\n\n\tforEach( sentences, function( sentence ) {\n\t\tconst strippedSentence = stripHTMLTags( sentence.getSentenceText() ).toLocaleLowerCase();\n\n\t\t// The functionality based on sentencePart objects should be rewritten using array indices of stopwords and auxiliaries.\n\n\t\t// Divide a sentence into clauses and return an array of clause objects that have been checked for passiveness.\n\t\tconst clauses = getClauses( strippedSentence );\n\t\tsentence.setClauses( clauses );\n\n\t\t// Check sentence passiveness based on its clause passiveness.\n\t\tif ( sentence.isPassive() ) {\n\t\t\tpassiveSentences.push( sentence.getSentenceText() );\n\t\t}\n\t} );\n\n\treturn {\n\t\ttotal: totalNumberSentences,\n\t\tpassives: passiveSentences,\n\t};\n};\n\n/**\n * Looks for both morphological and periphrastic passive voice\n * Supported languages with both morphological and periphrastic passives: \"hu\", \"nb\".\n * Due to technical difficulties \"nb\" is only implemented as periphrastic at the moment. Languages that have not been implemented yet: \"da\".\n *\n * @param {Paper}      paper      The paper object.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The found passive sentences.\n */\nconst getMorphologicalAndPeriphrasticPassive = function( paper, researcher ) {\n\tconst morphologicalPassives = getMorphologicalPassives( paper, researcher );\n\tconst periphrasticPassives = getPeriphrasticPassives( paper, researcher ).passives;\n\n\treturn {\n\t\ttotal: morphologicalPassives.total,\n\t\tpassives: periphrasticPassives.concat( morphologicalPassives.passives ),\n\t};\n};\n\n/**\n * Looks for passive voice.\n *\n * @param {Paper}      paper      The paper object.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The found passive sentences.\n */\nexport default function getPassiveVoice( paper, researcher ) {\n\tconst passiveType = researcher.getConfig( \"passiveConstructionType\" );\n\n\tif ( passiveType === \"periphrastic\" ) {\n\t\treturn getPeriphrasticPassives( paper, researcher );\n\t}\n\tif ( passiveType === \"morphological\" ) {\n\t\treturn getMorphologicalPassives( paper, researcher );\n\t}\n\n\treturn getMorphologicalAndPeriphrasticPassive( paper, researcher );\n}\n"],"mappings":"AAAA,OAAOA,YAAY;AACnB,SAASC,aAAa,IAAIC,aAAa;AACvC,OAAOC,QAAQ;AAEf,SAASC,OAAO,QAAQ,QAAQ;AAChC,OAAOC,gBAAgB;AACvB,SAASC,wBAAwB;;AAEjC;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,MAAMC,wBAAwB,GAAG,SAAAA,CAAUC,KAAK,EAAEC,UAAU,EAAG;EACrE,MAAMC,iBAAiB,GAAGD,UAAU,CAACE,SAAS,CAAE,mBAAoB,CAAC;EACrE,IAAIC,IAAI,GAAGJ,KAAK,CAACK,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAGP,gBAAgB,CAAEO,IAAK,CAAC;EAC/BA,IAAI,GAAGN,wBAAwB,CAAEM,IAAI,EAAEJ,KAAK,CAACM,WAAW,IAAIN,KAAK,CAACM,WAAW,CAACC,UAAW,CAAC;EAC1F,MAAMC,iBAAiB,GAAGP,UAAU,CAACE,SAAS,CAAE,mBAAoB,CAAC;EACrE,MAAMM,SAAS,GAAGjB,YAAY,CAAEY,IAAI,EAAEI,iBAAkB,CAAC,CACvDE,GAAG,CAAE,UAAUC,QAAQ,EAAG;IAC1B,OAAO,IAAIhB,QAAQ,CAAEgB,QAAS,CAAC;EAChC,CAAE,CAAC;EACJ,MAAMC,oBAAoB,GAAGH,SAAS,CAACI,MAAM;EAC7C,MAAMC,gBAAgB,GAAG,EAAE;EAE3BlB,OAAO,CAAEa,SAAS,EAAE,UAAUE,QAAQ,EAAG;IACxC,MAAMI,gBAAgB,GAAGrB,aAAa,CAAEiB,QAAQ,CAACK,eAAe,CAAC,CAAE,CAAC,CAACC,iBAAiB,CAAC,CAAC;IAExFN,QAAQ,CAACO,UAAU,CAAEhB,iBAAiB,CAAEa,gBAAiB,CAAE,CAAC;IAE5D,IAAKJ,QAAQ,CAACQ,SAAS,CAAC,CAAC,KAAK,IAAI,EAAG;MACpCL,gBAAgB,CAACM,IAAI,CAAET,QAAQ,CAACK,eAAe,CAAC,CAAE,CAAC;IACpD;EACD,CAAE,CAAC;EAEH,OAAO;IACNK,KAAK,EAAET,oBAAoB;IAC3BU,QAAQ,EAAER;EACX,CAAC;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,MAAMS,uBAAuB,GAAG,SAAAA,CAAUvB,KAAK,EAAEC,UAAU,EAAG;EACpE,MAAMuB,UAAU,GAAGvB,UAAU,CAACE,SAAS,CAAE,YAAa,CAAC;EACvD,IAAIC,IAAI,GAAGJ,KAAK,CAACK,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAGP,gBAAgB,CAAEO,IAAK,CAAC;EAC/BA,IAAI,GAAGN,wBAAwB,CAAEM,IAAI,EAAEJ,KAAK,CAACM,WAAW,IAAIN,KAAK,CAACM,WAAW,CAACC,UAAW,CAAC;EAC1F,MAAMC,iBAAiB,GAAGP,UAAU,CAACE,SAAS,CAAE,mBAAoB,CAAC;EACrE,MAAMM,SAAS,GAAGjB,YAAY,CAAEY,IAAI,EAAEI,iBAAkB,CAAC,CACvDE,GAAG,CAAE,UAAUC,QAAQ,EAAG;IAC1B,OAAO,IAAIhB,QAAQ,CAAEgB,QAAS,CAAC;EAChC,CAAE,CAAC;EACJ,MAAMC,oBAAoB,GAAGH,SAAS,CAACI,MAAM;EAC7C,MAAMC,gBAAgB,GAAG,EAAE;EAE3BlB,OAAO,CAAEa,SAAS,EAAE,UAAUE,QAAQ,EAAG;IACxC,MAAMI,gBAAgB,GAAGrB,aAAa,CAAEiB,QAAQ,CAACK,eAAe,CAAC,CAAE,CAAC,CAACC,iBAAiB,CAAC,CAAC;;IAExF;;IAEA;IACA,MAAMQ,OAAO,GAAGD,UAAU,CAAET,gBAAiB,CAAC;IAC9CJ,QAAQ,CAACe,UAAU,CAAED,OAAQ,CAAC;;IAE9B;IACA,IAAKd,QAAQ,CAACQ,SAAS,CAAC,CAAC,EAAG;MAC3BL,gBAAgB,CAACM,IAAI,CAAET,QAAQ,CAACK,eAAe,CAAC,CAAE,CAAC;IACpD;EACD,CAAE,CAAC;EAEH,OAAO;IACNK,KAAK,EAAET,oBAAoB;IAC3BU,QAAQ,EAAER;EACX,CAAC;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMa,sCAAsC,GAAG,SAAAA,CAAU3B,KAAK,EAAEC,UAAU,EAAG;EAC5E,MAAM2B,qBAAqB,GAAG7B,wBAAwB,CAAEC,KAAK,EAAEC,UAAW,CAAC;EAC3E,MAAM4B,oBAAoB,GAAGN,uBAAuB,CAAEvB,KAAK,EAAEC,UAAW,CAAC,CAACqB,QAAQ;EAElF,OAAO;IACND,KAAK,EAAEO,qBAAqB,CAACP,KAAK;IAClCC,QAAQ,EAAEO,oBAAoB,CAACC,MAAM,CAAEF,qBAAqB,CAACN,QAAS;EACvE,CAAC;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASS,eAAeA,CAAE/B,KAAK,EAAEC,UAAU,EAAG;EAC5D,MAAM+B,WAAW,GAAG/B,UAAU,CAACgC,SAAS,CAAE,yBAA0B,CAAC;EAErE,IAAKD,WAAW,KAAK,cAAc,EAAG;IACrC,OAAOT,uBAAuB,CAAEvB,KAAK,EAAEC,UAAW,CAAC;EACpD;EACA,IAAK+B,WAAW,KAAK,eAAe,EAAG;IACtC,OAAOjC,wBAAwB,CAAEC,KAAK,EAAEC,UAAW,CAAC;EACrD;EAEA,OAAO0B,sCAAsC,CAAE3B,KAAK,EAAEC,UAAW,CAAC;AACnE","ignoreList":[]}

package/build/esm/languageProcessing/researches/getProminentWordsForInsights.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getProminentWordsForInsights.js","names":["take","collapseProminentWordsOnStem","filterProminentWords","getProminentWords","retrieveAbbreviations","sortProminentWords","removeURLs","removeEmailAddresses","getProminentWordsForInsights","paper","researcher","functionWords","getConfig","customStemmer","getHelper","stemmer","getWordsCustomHelper","text","getText","abbreviations","prominentWordsFromText","collapsedWords"],"sources":["../../../../src/languageProcessing/researches/getProminentWordsForInsights.js"],"sourcesContent":["import { take } from \"lodash\";\nimport {\n\tcollapseProminentWordsOnStem,\n\tfilterProminentWords,\n\tgetProminentWords,\n\tretrieveAbbreviations,\n\tsortProminentWords,\n} from \"../helpers/prominentWords/determineProminentWords\";\nimport removeURLs from \"../helpers/sanitize/removeURLs.js\";\nimport removeEmailAddresses from \"../helpers/sanitize/removeEmailAddresses\";\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 {WordCombination[]} Prominent words for this paper, filtered and sorted.\n */\nfunction getProminentWordsForInsights( 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\n\tlet text = paper.getText();\n\t// We don't want to include URLs or email addresses in prominent words.\n\ttext = removeURLs( text );\n\ttext = removeEmailAddresses( text );\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 );\n\n\tconst prominentWordsFromText = getProminentWords( text, abbreviations, stemmer, functionWords, getWordsCustomHelper );\n\n\tconst collapsedWords = collapseProminentWordsOnStem( prominentWordsFromText );\n\tsortProminentWords( collapsedWords );\n\n\t/*\n\t * Collapse the list of prominent words on stems, sort it, filter out all words that occur less than\n\t * 5 times in the text. Return the 20 top items from this list.\n\t */\n\treturn take( filterProminentWords( collapsedWords, 5 ), 20 );\n}\n\nexport default getProminentWordsForInsights;\n"],"mappings":"AAAA,SAASA,IAAI,QAAQ,QAAQ;AAC7B,SACCC,4BAA4B,EAC5BC,oBAAoB,EACpBC,iBAAiB,EACjBC,qBAAqB,EACrBC,kBAAkB;AAEnB,OAAOC,UAAU;AACjB,OAAOC,oBAAoB;;AAE3B;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,4BAA4BA,CAAEC,KAAK,EAAEC,UAAU,EAAG;EAC1D,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;EAE3E,IAAIG,IAAI,GAAGR,KAAK,CAACS,OAAO,CAAC,CAAC;EAC1B;EACAD,IAAI,GAAGX,UAAU,CAAEW,IAAK,CAAC;EACzBA,IAAI,GAAGV,oBAAoB,CAAEU,IAAK,CAAC;;EAEnC;EACA,MAAME,aAAa,GAAGH,oBAAoB,GAAG,EAAE,GAAGZ,qBAAqB,CAAEa,IAAK,CAAC;EAE/E,MAAMG,sBAAsB,GAAGjB,iBAAiB,CAAEc,IAAI,EAAEE,aAAa,EAAEJ,OAAO,EAAEJ,aAAa,EAAEK,oBAAqB,CAAC;EAErH,MAAMK,cAAc,GAAGpB,4BAA4B,CAAEmB,sBAAuB,CAAC;EAC7Ef,kBAAkB,CAAEgB,cAAe,CAAC;;EAEpC;AACD;AACA;AACA;EACC,OAAOrB,IAAI,CAAEE,oBAAoB,CAAEmB,cAAc,EAAE,CAAE,CAAC,EAAE,EAAG,CAAC;AAC7D;AAEA,eAAeb,4BAA4B","ignoreList":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"getProminentWordsForInternalLinking.js","names":["take","countWords","collapseProminentWordsOnStem","filterProminentWords","getProminentWords","getProminentWordsFromPaperAttributes","retrieveAbbreviations","sortProminentWords","getSubheadingsTopLevel","removeSubheadingsTopLevel","baseStemmer","removeURLs","removeEmailAddresses","sanitizeText","text","getProminentWordsForInternalLinking","paper","researcher","functionWords","getConfig","customStemmer","getHelper","stemmer","getWordsCustomHelper","customCountLength","getText","metadescription","getDescription","title","getTitle","result","hasMetaDescription","hasTitle","prominentWords","subheadings","map","subheading","attributes","getKeyword","getSynonyms","join","abbreviations","concat","removedSubheadingText","prominentWordsFromText","prominentWordsFromPaperAttributes","forEach","relevantWord","setOccurrences","getOccurrences","collapsedWords","minimumNumberOfOccurrences"],"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,SAASA,IAAI,QAAQ,QAAQ;AAC7B,OAAOC,UAAU;AACjB,SACCC,4BAA4B,EAC5BC,oBAAoB,EACpBC,iBAAiB,EACjBC,oCAAoC,EACpCC,qBAAqB,EACrBC,kBAAkB;AAEnB,SAASC,sBAAsB,EAAEC,yBAAyB;AAC1D,OAAOC,WAAW;AAClB,OAAOC,UAAU;AACjB,OAAOC,oBAAoB;;AAE3B;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,YAAY,GAAG,SAAAA,CAAUC,IAAI,EAAG;EACrCA,IAAI,GAAGH,UAAU,CAAEG,IAAK,CAAC;EACzB,OAAOF,oBAAoB,CAAEE,IAAK,CAAC;AACpC,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,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,MAAMP,IAAI,GAAGD,YAAY,CAAEG,KAAK,CAACS,OAAO,CAAC,CAAE,CAAC;EAC5C,MAAMC,eAAe,GAAGb,YAAY,CAAEG,KAAK,CAACW,cAAc,CAAC,CAAE,CAAC;EAC9D,MAAMC,KAAK,GAAGf,YAAY,CAAEG,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,CAAEV,IAAK,CAAC,GAAG,GAAG,EAAG;MACtC,OAAOgB,MAAM;IACd;EACD,CAAC,MAAM,IAAK7B,UAAU,CAAEa,IAAK,CAAC,GAAG,GAAG,EAAG;IACtC,OAAOgB,MAAM;EACd;EAEA,MAAMI,WAAW,GAAG1B,sBAAsB,CAAEM,IAAK,CAAC,CAACqB,GAAG,CAAEC,UAAU,IAAIA,UAAU,CAAE,CAAC,CAAG,CAAC;EACvF,MAAMC,UAAU,GAAG,CAClBrB,KAAK,CAACsB,UAAU,CAAC,CAAC,EAClBtB,KAAK,CAACuB,WAAW,CAAC,CAAC,EACnBX,KAAK,EACLF,eAAe,EACfQ,WAAW,CAACM,IAAI,CAAE,GAAI,CAAC,CACvB;;EAED;EACA,MAAMC,aAAa,GAAGlB,oBAAoB,GAAG,EAAE,GAAGjB,qBAAqB,CAAEQ,IAAI,CAAC4B,MAAM,CAAEL,UAAU,CAACG,IAAI,CAAE,GAAI,CAAE,CAAE,CAAC;EAEhH,MAAMG,qBAAqB,GAAGlC,yBAAyB,CAAEK,IAAK,CAAC;EAC/D,MAAM8B,sBAAsB,GAAGxC,iBAAiB,CAAEuC,qBAAqB,EAAEF,aAAa,EAAEnB,OAAO,EAAEJ,aAAa,EAAEK,oBAAqB,CAAC;EAEtI,MAAMsB,iCAAiC,GAAGxC,oCAAoC,CAC7EgC,UAAU,EAAEI,aAAa,EAAEnB,OAAO,EAAEJ,aAAa,EAAEK,oBAAqB,CAAC;;EAE1E;AACD;AACA;AACA;EACCsB,iCAAiC,CAACC,OAAO,CAAEC,YAAY,IAAIA,YAAY,CAACC,cAAc,CAAED,YAAY,CAACE,cAAc,CAAC,CAAC,GAAG,CAAE,CAAE,CAAC;EAE7H,MAAMC,cAAc,GAAGhD,4BAA4B,CAAE2C,iCAAiC,CAACH,MAAM,CAAEE,sBAAuB,CAAE,CAAC;EACzHrC,kBAAkB,CAAE2C,cAAe,CAAC;;EAEpC;AACD;AACA;AACA;AACA;AACA;AACA;EACC,IAAIC,0BAA0B,GAAG,CAAC;EAElC,IAAK7B,OAAO,KAAKZ,WAAW,EAAG;IAC9ByC,0BAA0B,GAAG,CAAC;EAC/B;;EAEA;AACD;AACA;AACA;EACCrB,MAAM,CAACG,cAAc,GAAGjC,IAAI,CAAEG,oBAAoB,CAAE+C,cAAc,EAAEC,0BAA2B,CAAC,EAAE,GAAI,CAAC;EAEvG,OAAOrB,MAAM;AACd;AAEA,eAAef,mCAAmC","ignoreList":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"getSentenceBeginnings.js","names":["getWords","getSentences","stripSpaces","stripFullTags","stripTags","filter","forEach","isEmpty","removeHtmlBlocks","filterShortcodesFromHTML","stripNonTextTags","startsWithSameWord","currentSentenceBeginning","nextSentenceBeginning","compareFirstWords","sentenceBeginnings","sentences","consecutiveFirstWords","foundSentences","sameBeginnings","beginning","i","push","word","count","getSentenceBeginning","sentence","firstWordExceptions","secondWordExceptions","getWordsCustomHelper","stripped","words","test","length","firstWord","toLocaleLowerCase","indexOf","includes","paper","researcher","getConfig","getHelper","memoizedTokenizer","text","getText","_attributes","shortcodes","replace","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,OAAOA,QAAQ;AACf,OAAOC,YAAY;AACnB,OAAOC,WAAW;AAClB,SAAQC,aAAa,IAAIC,SAAS;AAElC,SAAQC,MAAM,EAAEC,OAAO,EAAEC,OAAO,QAAO,QAAQ;AAC/C,OAAOC,gBAAgB;AACvB,SAAQC,wBAAwB;AAChC,OAAOC,gBAAgB;;AAEvB;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,kBAAkB,GAAG,SAAAA,CAASC,wBAAwB,EAAEC,qBAAqB,EAAE;EACnF,OAAO,CAACN,OAAO,CAACK,wBAAwB,CAAC,IAAIA,wBAAwB,KAAKC,qBAAqB;AACjG,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,iBAAiB,GAAG,SAAAA,CAASC,kBAAkB,EAAEC,SAAS,EAAE;EAChE,MAAMC,qBAAqB,GAAG,EAAE;EAChC,IAAIC,cAAc,GAAG,EAAE;EACvB,IAAIC,cAAc,GAAG,CAAC;EAEtBb,OAAO,CAACS,kBAAkB,EAAE,UAASK,SAAS,EAAEC,CAAC,EAAE;IACjD,MAAMT,wBAAwB,GAAGQ,SAAS;IAC1C,MAAMP,qBAAqB,GAAGE,kBAAkB,CAACM,CAAC,GAAG,CAAC,CAAC;IACvDH,cAAc,CAACI,IAAI,CAACN,SAAS,CAACK,CAAC,CAAC,CAAC;IAEjC,IAAIV,kBAAkB,CAACC,wBAAwB,EAAEC,qBAAqB,CAAC,EAAE;MACvEM,cAAc,EAAE;IAClB,CAAC,MAAM;MACLF,qBAAqB,CAACK,IAAI,CAAC;QACzBC,IAAI,EAAEX,wBAAwB;QAC9BY,KAAK,EAAEL,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,SAASQ,oBAAoBA,CAC3BC,QAAQ,EACRC,mBAAmB,EACnBC,oBAAoB,EACpBC,oBAAoB,EACpB;EACA,MAAMC,QAAQ,GAAG1B,SAAS,CAACF,WAAW,CAACwB,QAAQ,CAAC,CAAC;EACjD,IAAIK,KAAK,GAAGF,oBAAoB,GAAGA,oBAAoB,CAACC,QAAQ,CAAC,GAAG9B,QAAQ,CAAC8B,QAAQ,CAAC;EAEtFC,KAAK,GAAGA,KAAK,CAAC1B,MAAM,CAACkB,IAAI,IAAI,SAAS,CAACS,IAAI,CAACT,IAAI,CAAC,CAAC;EAElD,IAAIQ,KAAK,CAACE,MAAM,KAAK,CAAC,EAAE;IACtB,OAAO,EAAE;EACX;EAEA,IAAIC,SAAS,GAAGH,KAAK,CAAC,CAAC,CAAC,CAACI,iBAAiB,CAAC,CAAC;EAE5C,IAAIR,mBAAmB,CAACS,OAAO,CAACF,SAAS,CAAC,GAAG,CAAC,CAAC,IAAIH,KAAK,CAACE,MAAM,GAAG,CAAC,EAAE;IACnEC,SAAS,GAAGA,SAAS,GAAG,GAAG,GAAGH,KAAK,CAAC,CAAC,CAAC;IACtC,IAAIH,oBAAoB,EAAE;MACxB,IAAIA,oBAAoB,CAACS,QAAQ,CAACN,KAAK,CAAC,CAAC,CAAC,CAAC,EAAE;QAC3CG,SAAS,GAAGA,SAAS,GAAG,GAAG,GAAGH,KAAK,CAAC,CAAC,CAAC;MACxC;IACF;EACF;EAEA,OAAOG,SAAS;AAClB;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAASI,KAAK,EAAEC,UAAU,EAAE;EACzC,MAAMZ,mBAAmB,GAAGY,UAAU,CAACC,SAAS,CAAC,qBAAqB,CAAC;EACvE,MAAMZ,oBAAoB,GAAGW,UAAU,CAACC,SAAS,CAAC,sBAAsB,CAAC;EACzE,MAAMX,oBAAoB,GAAGU,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,GAAGnC,gBAAgB,CAACmC,IAAI,CAAC;EAC7BA,IAAI,GAAGjC,gBAAgB,CAACiC,IAAI,CAAC;EAC7BA,IAAI,GAAGlC,wBAAwB,CAACkC,IAAI,EAAEL,KAAK,CAACO,WAAW,IAAIP,KAAK,CAACO,WAAW,CAACC,UAAU,CAAC;;EAExF;EACAH,IAAI,GAAGA,IAAI,CAACI,OAAO,CAAC,UAAU,EAAE,GAAG,CAAC;;EAEpC;EACAJ,IAAI,GAAGA,IAAI,CAACI,OAAO,CAAC,+CAA+C,EAAE,EAAE,CAAC;EAExE,IAAI/B,SAAS,GAAGf,YAAY,CAAC0C,IAAI,EAAED,iBAAiB,CAAC;EAErD,IAAI3B,kBAAkB,GAAGC,SAAS,CAACgC,GAAG,CAAC,UAAStB,QAAQ,EAAE;IACxD,OAAOD,oBAAoB,CACzBC,QAAQ,EACRC,mBAAmB,EACnBC,oBAAoB,EACpBC,oBACF,CAAC;EACH,CAAC,CAAC;EAEFb,SAAS,GAAGA,SAAS,CAACX,MAAM,CAAC,UAASqB,QAAQ,EAAE;IAC9C,MAAMI,QAAQ,GAAG5B,WAAW,CAACwB,QAAQ,CAAC;IACtC,MAAMK,KAAK,GAAGF,oBAAoB,GAAGA,oBAAoB,CAACC,QAAQ,CAAC,GAAG9B,QAAQ,CAAC8B,QAAQ,CAAC;IACxF,OAAOC,KAAK,CAACE,MAAM,GAAG,CAAC;EACzB,CAAC,CAAC;EACFlB,kBAAkB,GAAGV,MAAM,CAACU,kBAAkB,CAAC;EAE/C,OAAOD,iBAAiB,CAACC,kBAAkB,EAAEC,SAAS,CAAC;AACzD","ignoreList":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"getSubheadingTextLengths.js","names":["getSubheadingTexts","countWords","forEach","removeHtmlBlocks","filterShortcodesFromHTML","paper","researcher","text","getText","_attributes","shortcodes","matches","customCountLength","getHelper","foundSubheadings","match","push","subheading","countLength","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,OAAOA,kBAAkB;AACzB,OAAOC,UAAU;AACjB,SAASC,OAAO,QAAQ,QAAQ;AAChC,OAAOC,gBAAgB;AACvB,SAASC,wBAAwB;;AAEjC;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C,IAAIC,IAAI,GAAGF,KAAK,CAACG,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAGJ,gBAAgB,CAAEI,IAAK,CAAC;EAC/BA,IAAI,GAAGH,wBAAwB,CAAEG,IAAI,EAAEF,KAAK,CAACI,WAAW,IAAIJ,KAAK,CAACI,WAAW,CAACC,UAAW,CAAC;EAC1F,MAAMC,OAAO,GAAGX,kBAAkB,CAAEO,IAAK,CAAC;;EAE1C;EACA,MAAMK,iBAAiB,GAAGN,UAAU,CAACO,SAAS,CAAE,mBAAoB,CAAC;EAErE,MAAMC,gBAAgB,GAAG,EAAE;EAE3BZ,OAAO,CAAES,OAAO,EAAE,UAAUI,KAAK,EAAG;IACnCD,gBAAgB,CAACE,IAAI,CAAE;MACtBC,UAAU,EAAEF,KAAK,CAACE,UAAU;MAC5BV,IAAI,EAAEQ,KAAK,CAACR,IAAI;MAChBW,WAAW,EAAEN,iBAAiB,GAAGA,iBAAiB,CAAEG,KAAK,CAACR,IAAK,CAAC,GAAGN,UAAU,CAAEc,KAAK,CAACR,IAAK,CAAC;MAC3FY,KAAK,EAAEJ,KAAK,CAACI;IACd,CAAE,CAAC;EACJ,CAAE,CAAC;EAEH,IAAIC,+BAA+B,GAAG,CAAC;EACvC,IAAIC,yBAAyB,GAAG,EAAE;EAClC,IAAKP,gBAAgB,CAACQ,MAAM,GAAG,CAAC,EAAG;IAClC;IACA,MAAMC,eAAe,GAAIT,gBAAgB,CAAE,CAAC,CAAE;IAC9C;IACAO,yBAAyB,GAAGd,IAAI,CAACiB,KAAK,CAAE,CAAC,EAAED,eAAe,CAACJ,KAAM,CAAC;IAClEC,+BAA+B,GAAGR,iBAAiB,GAChDA,iBAAiB,CAAES,yBAA0B,CAAC,GAC9CpB,UAAU,CAAEoB,yBAA0B,CAAC;EAC3C;;EAEA;EACA,IAAKD,+BAA+B,GAAG,CAAC,IAAIC,yBAAyB,KAAK,EAAE,EAAG;IAC9E;IACAP,gBAAgB,CAACW,OAAO,CAAE;MACzB;MACAR,UAAU,EAAE,EAAE;MACdV,IAAI,EAAEc,yBAAyB;MAC/BH,WAAW,EAAEE;IACd,CAAE,CAAC;EACJ;EAEA,OAAON,gBAAgB;AACxB","ignoreList":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"getWordForms.js","names":["normalizeSingle","collectStems","StemOriginalPair","escapeRegExp","flattenDeep","getAllWordsFromPaper","parseSynonyms","StemWithForms","stem","forms","Result","keyphraseForms","synonymsForms","replaceStemWithForms","stemOriginalPair","paperWordsGroupedByStems","createBasicWordForms","matchingStemFormPair","find","element","originalSanitized","original","push","Set","extractStems","keyphrase","synonyms","keyphraseStemsOnly","stemOriginalPairs","length","getStems","synonymsStemsOnly","map","topicPhrase","constructTopicPhraseResult","exactMatch","getWordForms","allWordsFromPaper","functionWords","stemmer","areHyphensWordBoundaries","topicPhrases","keyphraseStemmed","keyphraseStems","synonymsStemmed","synonymsStems","allTopicPhrases","every","synonym","topicStemsFlat","paperWords","filter","word","includes","paperWordsWithStems","sort","a","b","localeCompare","reduce","accumulator","lastItem","paper","researcher","getConfig","getHelper","language","toLocaleLowerCase","getKeyword","trim","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,SAASA,eAAe;AACxB,SAASC,YAAY,EAAEC,gBAAgB;AAEvC,SAASC,YAAY,EAAEC,WAAW,QAAQ,QAAQ;AAClD,OAAOC,oBAAoB;AAC3B,OAAOC,aAAa;;AAEpB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,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,GAAGpB,eAAe,CAAEG,YAAY,CAAEW,gBAAgB,CAACO,QAAS,CAAE,CAAC;EAEtF,MAAMZ,KAAK,GAAGQ,oBAAoB,GAC/B,CAAEG,iBAAiB,EAAE,GAAGH,oBAAoB,CAACR,KAAK,CAAE,GACpD,CAAEW,iBAAiB,CAAE;;EAExB;EACA,IAAKJ,oBAAoB,EAAG;IAC3BP,KAAK,CAACa,IAAI,CAAE,GAAGN,oBAAoB,CAAEF,gBAAgB,CAACO,QAAS,CAAE,CAAC;EACnE;;EAEA;AACD;AACA;AACA;EACC,OAAO,CAAE,GAAI,IAAIE,GAAG,CAAEd,KAAM,CAAC,CAAE;AAChC;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASe,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,GAAGvB,WAAW,CAAE2B,iBAAkB,CAAC,CAAE;AACxE;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASG,0BAA0BA,CAAED,WAAW,EAAElB,wBAAwB,EAAEC,oBAAoB,EAAG;EAClG;EACA,IAAKiB,WAAW,CAACL,iBAAiB,CAACC,MAAM,KAAK,CAAC,EAAG;IACjD,OAAO,EAAE;EACV;EAEA,IAAKI,WAAW,CAACE,UAAU,EAAG;IAC7B,OAAO,CAAE,CAAEF,WAAW,CAACL,iBAAiB,CAAE,CAAC,CAAE,CAACpB,IAAI,CAAE,CAAE;EACvD;EAEA,OAAOyB,WAAW,CAACL,iBAAiB,CAACI,GAAG,CAAE,UAAUlB,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,SAASoB,YAAYA,CAAEX,SAAS,EAAEC,QAAQ,EAAEW,iBAAiB,EAAEC,aAAa,EAAEC,OAAO,EAAEvB,oBAAoB,EAAEwB,wBAAwB,EAAG;EACvI,MAAMC,YAAY,GAAOxC,YAAY,CAAEwB,SAAS,EAAEC,QAAQ,EAAEa,OAAO,EAAED,aAAa,EAAEE,wBAAyB,CAAC;EAC9G,MAAME,gBAAgB,GAAGD,YAAY,CAACE,cAAc;EACpD,MAAMC,eAAe,GAAIH,YAAY,CAACI,aAAa;;EAEnD;EACA,IAAKH,gBAAgB,CAACd,iBAAiB,CAACC,MAAM,KAAK,CAAC,IAAIe,eAAe,CAACf,MAAM,KAAK,CAAC,EAAG;IACtF,OAAO,IAAInB,MAAM,CAAC,CAAC;EACpB;;EAEA;EACA,MAAMoC,eAAe,GAAG,CAAEJ,gBAAgB,EAAE,GAAGE,eAAe,CAAE;EAEhE,IAAKE,eAAe,CAACC,KAAK,CAAEd,WAAW,IAAIA,WAAW,CAACE,UAAU,KAAK,IAAK,CAAC,EAAG;IAC9E,OAAO,IAAIzB,MAAM,CAChB,CAAE,CAAEgC,gBAAgB,CAACd,iBAAiB,CAAE,CAAC,CAAE,CAACpB,IAAI,CAAE,CAAE,EACpDoC,eAAe,CAACZ,GAAG,CAAEgB,OAAO,IAAI,CAAE,CAAEA,OAAO,CAACpB,iBAAiB,CAAE,CAAC,CAAE,CAACpB,IAAI,CAAE,CACzE,CACD,CAAC;EACF;;EAEA;EACA,MAAMyC,cAAc,GAAG,CAAE,GAAI,IAAI1B,GAAG,CAAEC,YAAY,CAAEkB,gBAAgB,EAAEE,eAAgB,CAAE,CAAC,CAAE;;EAE3F;AACD;AACA;AACA;EACC,MAAMM,UAAU,GAAG,CAAE,GAAI,IAAI3B,GAAG,CAAEc,iBAAiB,CAACc,MAAM,CAAEC,IAAI,IAAI,CAAEd,aAAa,CAACe,QAAQ,CAAED,IAAK,CAAE,CAAE,CAAC,CAAE;;EAE1G;EACA,MAAME,mBAAmB,GAAGJ,UAAU,CACpClB,GAAG,CAAEoB,IAAI,IAAI,IAAIlD,gBAAgB,CAAEqC,OAAO,CAAEa,IAAK,CAAC,EAAEA,IAAK,CAAE,CAAC,CAC5DD,MAAM,CAAErC,gBAAgB,IAAImC,cAAc,CAACI,QAAQ,CAAEvC,gBAAgB,CAACN,IAAK,CAAE,CAAC,CAC9E+C,IAAI,CAAE,CAAEC,CAAC,EAAEC,CAAC,KAAMD,CAAC,CAAChD,IAAI,CAACkD,aAAa,CAAED,CAAC,CAACjD,IAAK,CAAE,CAAC;;EAEpD;EACA,MAAMO,wBAAwB,GAAGuC,mBAAmB,CAACK,MAAM,CAAE,UAAUC,WAAW,EAAE9C,gBAAgB,EAAG;IACtG,MAAM+C,QAAQ,GAAGD,WAAW,CAAEA,WAAW,CAAC/B,MAAM,GAAG,CAAC,CAAE;IAEtD,IAAK+B,WAAW,CAAC/B,MAAM,KAAK,CAAC,IAAIgC,QAAQ,CAACrD,IAAI,KAAKM,gBAAgB,CAACN,IAAI,EAAG;MAC1EoD,WAAW,CAACtC,IAAI,CAAE,IAAIf,aAAa,CAAEO,gBAAgB,CAACN,IAAI,EAAE,CAAEM,gBAAgB,CAACO,QAAQ,CAAG,CAAE,CAAC;IAC9F,CAAC,MAAM;MACNwC,QAAQ,CAACpD,KAAK,CAACa,IAAI,CAAER,gBAAgB,CAACO,QAAS,CAAC;IACjD;IAEA,OAAOuC,WAAW;EACnB,CAAC,EAAE,EAAG,CAAC;EAEP,OAAO,IAAIlD,MAAM,CAChBwB,0BAA0B,CAAEQ,gBAAgB,EAAE3B,wBAAwB,EAAEC,oBAAqB,CAAC,EAC9F4B,eAAe,CAACZ,GAAG,CAAEgB,OAAO,IAAId,0BAA0B,CAAEc,OAAO,EAAEjC,wBAAwB,EAAEC,oBAAqB,CAAE,CACvH,CAAC;AACF;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAU8C,KAAK,EAAEC,UAAU,EAAG;EAC5C,MAAMzB,aAAa,GAAGyB,UAAU,CAACC,SAAS,CAAE,eAAgB,CAAC;EAC7D,MAAMzB,OAAO,GAAGwB,UAAU,CAACE,SAAS,CAAE,YAAa,CAAC,CAAEF,UAAW,CAAC;EAClE,MAAM/C,oBAAoB,GAAG+C,UAAU,CAACE,SAAS,CAAE,sBAAuB,CAAC;EAC3E,MAAMC,QAAQ,GAAGH,UAAU,CAACC,SAAS,CAAE,UAAW,CAAC;EACnD;AACD;AACA;AACA;AACA;AACA;EACC,MAAMxB,wBAAwB,GAAGuB,UAAU,CAACC,SAAS,CAAE,0BAA2B,CAAC;EAEnF,MAAM3B,iBAAiB,GAAGhC,oBAAoB,CAAEyD,KAAK,EAAEtB,wBAAyB,CAAC,CAACR,GAAG,CAAEoB,IAAI,IAAIA,IAAI,CAACe,iBAAiB,CAAED,QAAS,CAAE,CAAC;EACnI,MAAMzC,SAAS,GAAGqC,KAAK,CAACM,UAAU,CAAC,CAAC,CAACD,iBAAiB,CAAED,QAAS,CAAC,CAACG,IAAI,CAAC,CAAC;EACzE,MAAM3C,QAAQ,GAAGpB,aAAa,CAAEwD,KAAK,CAACQ,WAAW,CAAC,CAAC,CAACH,iBAAiB,CAAED,QAAS,CAAC,CAACG,IAAI,CAAC,CAAE,CAAC;EAE1F,OAAOjC,YAAY,CAAEX,SAAS,EAAEC,QAAQ,EAAEW,iBAAiB,EAAEC,aAAa,EAAEC,OAAO,EAAEvB,oBAAoB,EAAEwB,wBAAyB,CAAC;AACtI","ignoreList":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"h1s.js","names":["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;AACA,eAAe,UAASA,KAAK,EAAE;EAC7B,OAAOA,KAAK,CAACC,UAAU,CAAC,CAAC;AAC3B","ignoreList":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"imageCount.js","names":["getImagesInTree","imageCount","paper","images","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":"AAAA;;AAEA,OAAOA,eAAe;;AAEtB;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASC,UAAUA,CAAEC,KAAK,EAAG;EAC3C,MAAMC,MAAM,GAAGH,eAAe,CAAEE,KAAM,CAAC;EAEvC,OAAOC,MAAM,CAACC,MAAM;AACrB","ignoreList":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","names":["getLongCenterAlignedTexts","wordComplexity","keyphraseDistribution"],"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,OAAOA,yBAAyB;AAChC,OAAOC,cAAc;AACrB,OAAOC,qBAAqB;AAE5B,SAAQF,yBAAyB,EAAEE,qBAAqB,EAAED,cAAc","ignoreList":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"keyphraseDistribution.js","names":["flattenDeep","max","uniq","unique","zipWith","findWordFormsInString","markWordsInSentences","getSentences","parseSynonyms","mergeListItems","removeHtmlBlocks","filterShortcodesFromHTML","computeScoresPerSentenceLongTopic","topic","sentences","locale","matchWordCustomHelper","sentenceScores","Array","length","i","foundInCurrentSentence","percentWordMatches","computeScoresPerSentenceShortTopic","currentSentence","maximizeSentenceScores","sentenceScoresTransposed","map","col","row","scoresForOneSentence","getDistraction","numberOfSentences","allTopicSentencesIndices","push","numberOfTopicSentences","unshift","distances","getSentenceScores","topicFormsInOneArray","functionWords","topicLengthCriteria","originalTopic","wordsCharacterCount","topicNumber","topicLength","maximizedSentenceScores","sentencesWithMaximizedScores","sentence","score","sentencesWithTopic","filter","sentenceObject","keyphraseDistributionResearcher","paper","researcher","getConfig","getHelper","getContentWordsHelper","getResearch","memoizedTokenizer","lengthCriteria","text","getText","_attributes","shortcodes","topicForms","getKeyword","getSynonyms","forEach","synonym","getLocale","keyphraseForms","synonymsForms","allTopicWords","sort","a","b","maxLengthDistraction","sentencesToHighlight","keyphraseDistributionScore"],"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,SAASA,WAAW,EAAEC,GAAG,EAAEC,IAAI,IAAIC,MAAM,EAAEC,OAAO,QAAQ,QAAQ;AAClE,SAASC,qBAAqB;AAC9B,SAASC,oBAAoB;AAC7B,OAAOC,YAAY;AACnB,OAAOC,aAAa;AACpB,SAASC,cAAc;AACvB,OAAOC,gBAAgB;AACvB,SAASC,wBAAwB;;AAEjC;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,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,GAAGhB,qBAAqB,CAAEQ,KAAK,EAAEC,SAAS,CAAEM,CAAC,CAAE,EAAEL,MAAM,EAAEC,qBAAsB,CAAC;IAE5G,IAAKK,sBAAsB,CAACC,kBAAkB,IAAI,EAAE,EAAG;MACtDL,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;AACA,MAAMM,kCAAkC,GAAG,SAAAA,CAAUV,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,MAAMI,eAAe,GAAGV,SAAS,CAAEM,CAAC,CAAE;IACtC,MAAMC,sBAAsB,GAAGhB,qBAAqB,CAAEQ,KAAK,EAAEW,eAAe,EAAET,MAAM,EAAEC,qBAAsB,CAAC;IAC7G,IAAKK,sBAAsB,CAACC,kBAAkB,KAAK,GAAG,EAAG;MACxDL,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;AACA,MAAMQ,sBAAsB,GAAG,SAAAA,CAAUR,cAAc,EAAG;EACzD,MAAMS,wBAAwB,GAAGT,cAAc,CAAE,CAAC,CAAE,CAACU,GAAG,CAAE,UAAUC,GAAG,EAAER,CAAC,EAAG;IAC5E,OAAOH,cAAc,CAACU,GAAG,CAAE,UAAUE,GAAG,EAAG;MAC1C,OAAOA,GAAG,CAAET,CAAC,CAAE;IAChB,CAAE,CAAC;EACJ,CAAE,CAAC;EAEH,OAAOM,wBAAwB,CAACC,GAAG,CAAE,UAAUG,oBAAoB,EAAG;IACrE,OAAO7B,GAAG,CAAE6B,oBAAqB,CAAC;EACnC,CAAE,CAAC;AACJ,CAAC;;AAGD;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,cAAc,GAAG,SAAAA,CAAUd,cAAc,EAAG;EACjD,MAAMe,iBAAiB,GAAGf,cAAc,CAACE,MAAM;EAC/C,MAAMc,wBAAwB,GAAG,EAAE;EAEnC,KAAM,IAAIb,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGY,iBAAiB,EAAEZ,CAAC,EAAE,EAAG;IAC7C,IAAKH,cAAc,CAAEG,CAAC,CAAE,GAAG,CAAC,EAAG;MAC9Ba,wBAAwB,CAACC,IAAI,CAAEd,CAAE,CAAC;IACnC;EACD;EAEA,MAAMe,sBAAsB,GAAGF,wBAAwB,CAACd,MAAM;EAE9D,IAAKgB,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,IAAIjB,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGe,sBAAsB,GAAG,CAAC,EAAEf,CAAC,EAAE,EAAG;IACtDiB,SAAS,CAACH,IAAI,CAAED,wBAAwB,CAAEb,CAAC,CAAE,GAAGa,wBAAwB,CAAEb,CAAC,GAAG,CAAC,CAAE,GAAG,CAAE,CAAC;EACxF;EAEA,OAAOnB,GAAG,CAAEoC,SAAU,CAAC;AACxB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,iBAAiB,GAAG,SAAAA,CAAUxB,SAAS,EAAEyB,oBAAoB,EAAExB,MAAM,EAAEyB,aAAa,EAAExB,qBAAqB,EAChHyB,mBAAmB,GAAG,CAAC,EAAEC,aAAa,EAAEC,mBAAmB,EAAG;EAC9D;EACA,MAAMC,WAAW,GAAGL,oBAAoB,CAACpB,MAAM;EAE/C,MAAMF,cAAc,GAAGC,KAAK,CAAE0B,WAAY,CAAC;;EAE3C;EACA,IAAKJ,aAAa,CAACrB,MAAM,GAAG,CAAC,EAAG;IAC/B,KAAM,IAAIC,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGwB,WAAW,EAAExB,CAAC,EAAE,EAAG;MACvC,MAAMP,KAAK,GAAG0B,oBAAoB,CAAEnB,CAAC,CAAE;MACvC;AACH;AACA;AACA;AACA;MACG,MAAMyB,WAAW,GAAGF,mBAAmB,GAAGA,mBAAmB,CAAED,aAAa,CAAEtB,CAAC,CAAG,CAAC,GAAGP,KAAK,CAACM,MAAM;MAClG,IAAK0B,WAAW,GAAGJ,mBAAmB,EAAG;QACxCxB,cAAc,CAAEG,CAAC,CAAE,GAAGG,kCAAkC,CAAEV,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,GAAGwB,WAAW,EAAExB,CAAC,EAAE,EAAG;MACvC,MAAMP,KAAK,GAAG0B,oBAAoB,CAAEnB,CAAC,CAAE;MACvCH,cAAc,CAAEG,CAAC,CAAE,GAAGG,kCAAkC,CAAEV,KAAK,EAAEC,SAAS,EAAEC,MAAM,EAAEC,qBAAsB,CAAC;IAC5G;EACD;;EAEA;EACA,MAAM8B,uBAAuB,GAAGrB,sBAAsB,CAAER,cAAe,CAAC;;EAExE;EACA,MAAM8B,4BAA4B,GAAI3C,OAAO,CAAEU,SAAS,EAAEgC,uBAAuB,EAAE,CAAEE,QAAQ,EAAEC,KAAK,KAAM;IACzG,OAAO;MAAED,QAAQ;MAAEC;IAAM,CAAC;EAC3B,CAAE,CAAC;;EAEH;EACA,MAAMC,kBAAkB,GAAGH,4BAA4B,CAACI,MAAM,CAAEC,cAAc,IAAIA,cAAc,CAACH,KAAK,GAAG,CAAE,CAAC;EAE5G,OAAO;IACNH,uBAAuB,EAAEA,uBAAuB;IAChDI,kBAAkB,EAAEA,kBAAkB,CAACvB,GAAG,CAAEyB,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,MAAMf,aAAa,GAAGe,UAAU,CAACC,SAAS,CAAE,eAAgB,CAAC;EAC7D,MAAMxC,qBAAqB,GAAGuC,UAAU,CAACE,SAAS,CAAE,uBAAwB,CAAC;EAC7E,MAAMC,qBAAqB,GAAGH,UAAU,CAACE,SAAS,CAAE,iBAAkB,CAAC;EACvE,MAAMd,mBAAmB,GAAGY,UAAU,CAACI,WAAW,CAAE,qBAAsB,CAAC;EAC3E,MAAMC,iBAAiB,GAAGL,UAAU,CAACE,SAAS,CAAE,mBAAoB,CAAC;;EAErE;EACA,MAAMhB,mBAAmB,GAAGc,UAAU,CAACC,SAAS,CAAE,aAAc,CAAC,CAACK,cAAc;EAEhF,IAAIC,IAAI,GAAGR,KAAK,CAACS,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAGpD,gBAAgB,CAAEoD,IAAK,CAAC;EAC/BA,IAAI,GAAGnD,wBAAwB,CAAEmD,IAAI,EAAER,KAAK,CAACU,WAAW,IAAIV,KAAK,CAACU,WAAW,CAACC,UAAW,CAAC;EAC1FH,IAAI,GAAGrD,cAAc,CAAEqD,IAAK,CAAC;EAC7B,MAAMhD,SAAS,GAAGP,YAAY,CAAEuD,IAAI,EAAEF,iBAAkB,CAAC;EACzD,MAAMM,UAAU,GAAGX,UAAU,CAACI,WAAW,CAAE,YAAa,CAAC;EAEzD,MAAMjB,aAAa,GAAG,EAAE;EACxB,IAAKgB,qBAAqB,EAAG;IAC5BhB,aAAa,CAACR,IAAI,CAAEwB,qBAAqB,CAAEJ,KAAK,CAACa,UAAU,CAAC,CAAE,CAAE,CAAC;IACjE3D,aAAa,CAAE8C,KAAK,CAACc,WAAW,CAAC,CAAE,CAAC,CAACC,OAAO,CAAEC,OAAO,IAAI5B,aAAa,CAACR,IAAI,CAAEwB,qBAAqB,CAAEY,OAAQ,CAAE,CAAE,CAAC;EAClH;EACA,MAAMvD,MAAM,GAAGuC,KAAK,CAACiB,SAAS,CAAC,CAAC;EAChC,MAAMhC,oBAAoB,GAAG,CAAE2B,UAAU,CAACM,cAAc,CAAE;EAC1DN,UAAU,CAACO,aAAa,CAACJ,OAAO,CAAE,UAAUC,OAAO,EAAG;IACrD/B,oBAAoB,CAACL,IAAI,CAAEoC,OAAQ,CAAC;EACrC,CAAE,CAAC;EAEH,MAAMI,aAAa,GAAGvE,MAAM,CAAEH,WAAW,CAAEuC,oBAAqB,CAAE,CAAC,CAACoC,IAAI,CAAE,CAAEC,CAAC,EAAEC,CAAC,KAAMA,CAAC,CAAC1D,MAAM,GAAGyD,CAAC,CAACzD,MAAO,CAAC;;EAE3G;EACA,MAAMF,cAAc,GAAGqB,iBAAiB,CAAExB,SAAS,EAAEyB,oBAAoB,EAAExB,MAAM,EAAEyB,aAAa,EAAExB,qBAAqB,EACtHyB,mBAAmB,EAAEC,aAAa,EAAEC,mBAAoB,CAAC;EAC1D,MAAMG,uBAAuB,GAAG7B,cAAc,CAAC6B,uBAAuB;EACtE,MAAMgC,oBAAoB,GAAG/C,cAAc,CAAEe,uBAAwB,CAAC;EAEtE,OAAO;IACNiC,oBAAoB,EAAEzE,oBAAoB,CAAEoE,aAAa,EAAEzD,cAAc,CAACiC,kBAAkB,EAAEnC,MAAM,EAAEC,qBAAsB,CAAC;IAC7HgE,0BAA0B,EAAEF,oBAAoB,GAAGhE,SAAS,CAACK,MAAM,GAAG;EACvE,CAAC;AACF,CAAC;AAED,SACCI,kCAAkC,EAClCX,iCAAiC,EACjCa,sBAAsB,EACtB4B,+BAA+B,EAC/BtB,cAAc;AAGf,eAAesB,+BAA+B","ignoreList":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"keyphraseLength.js","names":["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;AACA,eAAe,UAAUA,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":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"keywordCount.js","names":["flatten","flattenDeep","getSentencesFromTree","normalizeSingle","getMarkingsInSentence","matchWordFormsWithSentence","isDoubleQuoted","markWordsInASentence","getSentences","filterShortcodesFromHTML","isChineseText","countKeyphraseInText","sentences","keyphraseForms","locale","matchWordCustomHelper","isExactMatchRequested","customSplitIntoTokensHelper","result","count","markings","forEach","sentence","matchesInSentence","map","wordForms","isEachWordFound","every","counts","match","totalMatchCount","Math","min","foundWords","matches","push","getKeyphraseCount","paper","researcher","keyphraseLength","topicForms","getResearch","length","word","form","getHelper","customSentenceTokenizer","getLocale","text","getText","_attributes","shortcodes","getKeyword","lowerText","toLowerCase","lowerWord","startIndex","index","indexOf","error","console","warn","message","keyphraseFound","keywordCount"],"sources":["../../../../src/languageProcessing/researches/keywordCount.js"],"sourcesContent":["import {flatten, flattenDeep} from 'lodash';\nimport getSentencesFromTree from '../helpers/sentence/getSentencesFromTree';\nimport {normalizeSingle} from '../helpers/sanitize/quotes';\nimport getMarkingsInSentence from '../helpers/highlighting/getMarkingsInSentence';\nimport matchWordFormsWithSentence from '../helpers/match/matchWordFormsWithSentence';\nimport isDoubleQuoted from '../helpers/match/isDoubleQuoted';\nimport {markWordsInASentence} from '../helpers/word/markWordsInSentences';\nimport getSentences from '../helpers/sentence/getSentences';\nimport {filterShortcodesFromHTML} from '../helpers';\nimport isChineseText from '../helpers/language/isChineseText';\n\n/**\n * Counts the occurrences of the keyphrase in the text and creates the Mark objects for the matches.\n *\n * @param {(Sentence|string)[]}\tsentences\t\t\tThe sentences to check.\n * @param {Array}\t\tkeyphraseForms\t\t\t\tThe keyphrase forms.\n * @param {string}\t\tlocale\t\t\t\t\t\tThe locale used in the analysis.\n * @param {function}\tmatchWordCustomHelper\t\tA custom helper to match words with a text.\n * @param {boolean}\t\tisExactMatchRequested\t\tWhether the exact matching is requested.\n * @param {function}\tcustomSplitIntoTokensHelper\tA custom helper to split sentences into tokens.\n *\n * @returns {{markings: Mark[], count: number}} The number of keyphrase occurrences in the text and the Mark objects of the matches.\n */\nexport function countKeyphraseInText(\n  sentences,\n  keyphraseForms,\n  locale,\n  matchWordCustomHelper,\n  isExactMatchRequested,\n  customSplitIntoTokensHelper\n) {\n  const result = {count: 0, markings: []};\n\n  sentences.forEach(sentence => {\n    const matchesInSentence = keyphraseForms.map(wordForms =>\n      matchWordFormsWithSentence(\n        sentence,\n        wordForms,\n        locale,\n        matchWordCustomHelper,\n        isExactMatchRequested,\n        customSplitIntoTokensHelper\n      )\n    );\n    // A sentence has at least one full-match of the keyphrase if each word occurs at least once.\n    const isEachWordFound = matchesInSentence.every(wordForms => wordForms.count > 0);\n\n    if (isEachWordFound) {\n      /*\n       * Retrieve all the occurrences' count of each word of the keyphrase and save it in an array.\n       * matches: [ [ { matches: [\"red\"], count: 1 } ], [ { matches: [\"pandas\"], count: 2 } ] ]\n       * counts: [ 1, 2 ]\n       */\n      const counts = matchesInSentence.map(match => match.count);\n      /*\n       * The number of the full-match count is the lowest count of the occurrences.\n       * counts: [ 1, 2 ]\n       * totalMatchCount: 1\n       *\n       * From the example above, the full-match is 1, because one of the \"pandas\" occurrences is not accompanied by \"red\"\n       * to be counted as a full-match.\n       */\n      const totalMatchCount = Math.min(...counts);\n      const foundWords = flattenDeep(matchesInSentence.map(match => match.matches));\n\n      let markings = [];\n\n      if (matchWordCustomHelper) {\n        // Currently, this check is only applicable for Japanese.\n        markings = markWordsInASentence(sentence, foundWords, matchWordCustomHelper);\n      } else {\n        markings = getMarkingsInSentence(sentence, foundWords);\n      }\n\n      result.count += totalMatchCount;\n      result.markings.push(markings);\n    }\n  });\n\n  return result;\n}\n\n/**\n * Calculates the keyphrase count, takes morphology into account.\n *\n * @param {Paper}       paper       The paper containing keyphrase and text.\n * @param {Researcher}  researcher  The researcher.\n *\n * @returns {{count: number, markings: Mark[], keyphraseLength: number}} An object containing the keyphrase count, markings and the kephrase length.\n */\nexport default function getKeyphraseCount(paper, researcher) {\n  const result = {count: 0, markings: [], keyphraseLength: 0};\n  const topicForms = researcher.getResearch('morphology');\n  let keyphraseForms = topicForms.keyphraseForms;\n  const keyphraseLength = keyphraseForms.length;\n\n  /*\n   * Normalize single quotes so that word form with different type of single quotes can still be matched.\n   * For example, \"key‛word\" should match \"key'word\".\n   */\n  keyphraseForms = keyphraseForms.map(word => word.map(form => normalizeSingle(form)));\n\n  if (keyphraseLength === 0) {\n    return result;\n  }\n\n  let matchWordCustomHelper = researcher.getHelper('matchWordCustomHelper');\n  const customSentenceTokenizer = researcher.getHelper('memoizedTokenizer');\n  const customSplitIntoTokensHelper = researcher.getHelper('splitIntoTokensCustom');\n  const locale = paper.getLocale();\n  const text = matchWordCustomHelper\n    ? filterShortcodesFromHTML(paper.getText(), paper._attributes && paper._attributes.shortcodes)\n    : paper.getText();\n\n  // Auto-detect Chinese and use Chinese helper if not already available\n  if (!matchWordCustomHelper && isChineseText(paper.getKeyword() + ' ' + text)) {\n    // Import Chinese helper for Chinese text\n    try {\n      // Use simple Chinese word matching for Chinese text\n      matchWordCustomHelper = function(sentence, word) {\n        const text = typeof sentence === 'string' ? sentence : sentence.text || sentence;\n        const matches = [];\n\n        if (!text || !word) {\n          return matches;\n        }\n\n        const lowerText = text.toLowerCase();\n        const lowerWord = word.toLowerCase();\n\n        let startIndex = 0;\n        let index;\n\n        while ((index = lowerText.indexOf(lowerWord, startIndex)) !== -1) {\n          matches.push(word);\n          startIndex = index + lowerWord.length;\n        }\n\n        return matches;\n      };\n    } catch (error) {\n      // If there's any issue, continue with default behavior\n      console.warn('Error setting up Chinese matching, using default:', error.message);\n    }\n  }\n\n  // When the custom helper is available, we're using the sentences retrieved from the text for the analysis.\n  const sentences = matchWordCustomHelper\n    ? getSentences(text, customSentenceTokenizer)\n    : getSentencesFromTree(paper);\n  // Exact matching is requested when the keyphrase is enclosed in double quotes.\n  const isExactMatchRequested = isDoubleQuoted(paper.getKeyword());\n\n  /*\n   * Count the amount of keyphrase occurrences in the sentences.\n   * An occurrence is counted when all words of the keyphrase are contained within the sentence. Each sentence can contain multiple keyphrases.\n   * (e.g. \"The apple potato is an apple and a potato.\" has two occurrences of the keyphrase \"apple potato\").\n   */\n  const keyphraseFound = countKeyphraseInText(\n    sentences,\n    keyphraseForms,\n    locale,\n    matchWordCustomHelper,\n    isExactMatchRequested,\n    customSplitIntoTokensHelper\n  );\n\n  result.count = keyphraseFound.count;\n  result.markings = flatten(keyphraseFound.markings);\n  result.keyphraseLength = keyphraseLength;\n\n  return result;\n}\n\n/**\n * Calculates the keyphrase count, takes morphology into account.\n *\n * @deprecated Use getKeyphraseCount instead.\n *\n * @param {Paper}       paper       The paper containing keyphrase and text.\n * @param {Researcher}  researcher  The researcher.\n *\n * @returns {Object} An array of all the matches, markings and the keyphrase count.\n */\nexport function keywordCount(paper, researcher) {\n  console.warn('This function is deprecated, use getKeyphraseCount instead.');\n  return getKeyphraseCount(paper, researcher);\n}\n"],"mappings":"AAAA,SAAQA,OAAO,EAAEC,WAAW,QAAO,QAAQ;AAC3C,OAAOC,oBAAoB;AAC3B,SAAQC,eAAe;AACvB,OAAOC,qBAAqB;AAC5B,OAAOC,0BAA0B;AACjC,OAAOC,cAAc;AACrB,SAAQC,oBAAoB;AAC5B,OAAOC,YAAY;AACnB,SAAQC,wBAAwB;AAChC,OAAOC,aAAa;;AAEpB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,SAASC,oBAAoBA,CAClCC,SAAS,EACTC,cAAc,EACdC,MAAM,EACNC,qBAAqB,EACrBC,qBAAqB,EACrBC,2BAA2B,EAC3B;EACA,MAAMC,MAAM,GAAG;IAACC,KAAK,EAAE,CAAC;IAAEC,QAAQ,EAAE;EAAE,CAAC;EAEvCR,SAAS,CAACS,OAAO,CAACC,QAAQ,IAAI;IAC5B,MAAMC,iBAAiB,GAAGV,cAAc,CAACW,GAAG,CAACC,SAAS,IACpDpB,0BAA0B,CACxBiB,QAAQ,EACRG,SAAS,EACTX,MAAM,EACNC,qBAAqB,EACrBC,qBAAqB,EACrBC,2BACF,CACF,CAAC;IACD;IACA,MAAMS,eAAe,GAAGH,iBAAiB,CAACI,KAAK,CAACF,SAAS,IAAIA,SAAS,CAACN,KAAK,GAAG,CAAC,CAAC;IAEjF,IAAIO,eAAe,EAAE;MACnB;AACN;AACA;AACA;AACA;MACM,MAAME,MAAM,GAAGL,iBAAiB,CAACC,GAAG,CAACK,KAAK,IAAIA,KAAK,CAACV,KAAK,CAAC;MAC1D;AACN;AACA;AACA;AACA;AACA;AACA;AACA;MACM,MAAMW,eAAe,GAAGC,IAAI,CAACC,GAAG,CAAC,GAAGJ,MAAM,CAAC;MAC3C,MAAMK,UAAU,GAAGhC,WAAW,CAACsB,iBAAiB,CAACC,GAAG,CAACK,KAAK,IAAIA,KAAK,CAACK,OAAO,CAAC,CAAC;MAE7E,IAAId,QAAQ,GAAG,EAAE;MAEjB,IAAIL,qBAAqB,EAAE;QACzB;QACAK,QAAQ,GAAGb,oBAAoB,CAACe,QAAQ,EAAEW,UAAU,EAAElB,qBAAqB,CAAC;MAC9E,CAAC,MAAM;QACLK,QAAQ,GAAGhB,qBAAqB,CAACkB,QAAQ,EAAEW,UAAU,CAAC;MACxD;MAEAf,MAAM,CAACC,KAAK,IAAIW,eAAe;MAC/BZ,MAAM,CAACE,QAAQ,CAACe,IAAI,CAACf,QAAQ,CAAC;IAChC;EACF,CAAC,CAAC;EAEF,OAAOF,MAAM;AACf;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASkB,iBAAiBA,CAACC,KAAK,EAAEC,UAAU,EAAE;EAC3D,MAAMpB,MAAM,GAAG;IAACC,KAAK,EAAE,CAAC;IAAEC,QAAQ,EAAE,EAAE;IAAEmB,eAAe,EAAE;EAAC,CAAC;EAC3D,MAAMC,UAAU,GAAGF,UAAU,CAACG,WAAW,CAAC,YAAY,CAAC;EACvD,IAAI5B,cAAc,GAAG2B,UAAU,CAAC3B,cAAc;EAC9C,MAAM0B,eAAe,GAAG1B,cAAc,CAAC6B,MAAM;;EAE7C;AACF;AACA;AACA;EACE7B,cAAc,GAAGA,cAAc,CAACW,GAAG,CAACmB,IAAI,IAAIA,IAAI,CAACnB,GAAG,CAACoB,IAAI,IAAIzC,eAAe,CAACyC,IAAI,CAAC,CAAC,CAAC;EAEpF,IAAIL,eAAe,KAAK,CAAC,EAAE;IACzB,OAAOrB,MAAM;EACf;EAEA,IAAIH,qBAAqB,GAAGuB,UAAU,CAACO,SAAS,CAAC,uBAAuB,CAAC;EACzE,MAAMC,uBAAuB,GAAGR,UAAU,CAACO,SAAS,CAAC,mBAAmB,CAAC;EACzE,MAAM5B,2BAA2B,GAAGqB,UAAU,CAACO,SAAS,CAAC,uBAAuB,CAAC;EACjF,MAAM/B,MAAM,GAAGuB,KAAK,CAACU,SAAS,CAAC,CAAC;EAChC,MAAMC,IAAI,GAAGjC,qBAAqB,GAC9BN,wBAAwB,CAAC4B,KAAK,CAACY,OAAO,CAAC,CAAC,EAAEZ,KAAK,CAACa,WAAW,IAAIb,KAAK,CAACa,WAAW,CAACC,UAAU,CAAC,GAC5Fd,KAAK,CAACY,OAAO,CAAC,CAAC;;EAEnB;EACA,IAAI,CAAClC,qBAAqB,IAAIL,aAAa,CAAC2B,KAAK,CAACe,UAAU,CAAC,CAAC,GAAG,GAAG,GAAGJ,IAAI,CAAC,EAAE;IAC5E;IACA,IAAI;MACF;MACAjC,qBAAqB,GAAG,SAAAA,CAASO,QAAQ,EAAEqB,IAAI,EAAE;QAC/C,MAAMK,IAAI,GAAG,OAAO1B,QAAQ,KAAK,QAAQ,GAAGA,QAAQ,GAAGA,QAAQ,CAAC0B,IAAI,IAAI1B,QAAQ;QAChF,MAAMY,OAAO,GAAG,EAAE;QAElB,IAAI,CAACc,IAAI,IAAI,CAACL,IAAI,EAAE;UAClB,OAAOT,OAAO;QAChB;QAEA,MAAMmB,SAAS,GAAGL,IAAI,CAACM,WAAW,CAAC,CAAC;QACpC,MAAMC,SAAS,GAAGZ,IAAI,CAACW,WAAW,CAAC,CAAC;QAEpC,IAAIE,UAAU,GAAG,CAAC;QAClB,IAAIC,KAAK;QAET,OAAO,CAACA,KAAK,GAAGJ,SAAS,CAACK,OAAO,CAACH,SAAS,EAAEC,UAAU,CAAC,MAAM,CAAC,CAAC,EAAE;UAChEtB,OAAO,CAACC,IAAI,CAACQ,IAAI,CAAC;UAClBa,UAAU,GAAGC,KAAK,GAAGF,SAAS,CAACb,MAAM;QACvC;QAEA,OAAOR,OAAO;MAChB,CAAC;IACH,CAAC,CAAC,OAAOyB,KAAK,EAAE;MACd;MACAC,OAAO,CAACC,IAAI,CAAC,mDAAmD,EAAEF,KAAK,CAACG,OAAO,CAAC;IAClF;EACF;;EAEA;EACA,MAAMlD,SAAS,GAAGG,qBAAqB,GACnCP,YAAY,CAACwC,IAAI,EAAEF,uBAAuB,CAAC,GAC3C5C,oBAAoB,CAACmC,KAAK,CAAC;EAC/B;EACA,MAAMrB,qBAAqB,GAAGV,cAAc,CAAC+B,KAAK,CAACe,UAAU,CAAC,CAAC,CAAC;;EAEhE;AACF;AACA;AACA;AACA;EACE,MAAMW,cAAc,GAAGpD,oBAAoB,CACzCC,SAAS,EACTC,cAAc,EACdC,MAAM,EACNC,qBAAqB,EACrBC,qBAAqB,EACrBC,2BACF,CAAC;EAEDC,MAAM,CAACC,KAAK,GAAG4C,cAAc,CAAC5C,KAAK;EACnCD,MAAM,CAACE,QAAQ,GAAGpB,OAAO,CAAC+D,cAAc,CAAC3C,QAAQ,CAAC;EAClDF,MAAM,CAACqB,eAAe,GAAGA,eAAe;EAExC,OAAOrB,MAAM;AACf;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,SAAS8C,YAAYA,CAAC3B,KAAK,EAAEC,UAAU,EAAE;EAC9CsB,OAAO,CAACC,IAAI,CAAC,6DAA6D,CAAC;EAC3E,OAAOzB,iBAAiB,CAACC,KAAK,EAAEC,UAAU,CAAC;AAC7C","ignoreList":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"keywordCountInUrl.js","names":["parseSlug","findTopicFormsInString","cloneDeep","getMatchHelper","CHINESE_PINYIN_URL_MAP","跨境","物流","人工智能","机器学习","数据","分析","技术","服务","平台","系统","解决方案","管理","企业","商务","电商","网站","应用","软件","开发","设计","营销","推广","优化","搜索","引擎","网络","互联网","数字","在线","云","大数据","区块链","金融","科技","创新","智能","自动","专业","高效","安全","可靠","快速","便捷","移动","社交","媒体","内容","用户","客户","产品","品牌","市场","销售","教育","培训","学习","知识","信息","新闻","资讯","咨询","顾问","createEnhancedChineseUrlForms","originalTopicForms","keyword","parsedSlug","enhancedForms","keyphraseForms","chineseMatches","match","forEach","chinesePhrase","pinyin","push","Object","entries","chinese","pinyins","includes","slugWords","toLowerCase","split","filter","word","length","test","synonymsForms","keywordCountInSlug","paper","researcher","languageResearcher","addConfig","getResearch","getSlug","locale","getLocale","getKeyword","isChineseKeyword","isPinyinSlug","topicForms","pinyinMatches","form","chineseComponents","expectedMatches","keyphraseLength","percentWordMatches","enhancedPercent","Math","round","max","matchHelper","getHelper","keyphraseInSlug","keywordCountInUrl","console","warn"],"sources":["../../../../src/languageProcessing/researches/keywordCountInUrl.js"],"sourcesContent":["/** @module researches/keywordCountInSlug */\nimport parseSlug from '../helpers/url/parseSlug';\nimport {findTopicFormsInString} from '../helpers/match/findKeywordFormsInString.js';\nimport {cloneDeep} from 'lodash';\nimport {getMatchHelper} from '../helpers/language/chineseHelperFactory.js';\n\n/**\n * Enhanced pinyin mapping for Chinese keywords commonly used in URLs\n */\nconst CHINESE_PINYIN_URL_MAP = {\n  跨境: ['kuajing', 'kua-jing', 'cross-border'],\n  物流: ['wuliu', 'wu-liu', 'logistics'],\n  人工智能: ['renqingzhinen', 'ai', 'artificial-intelligence'],\n  机器学习: ['jiqixuexi', 'machine-learning', 'ml'],\n  数据: ['shuju', 'data'],\n  分析: ['fenxi', 'analysis'],\n  技术: ['jishu', 'technology', 'tech'],\n  服务: ['fuwu', 'service'],\n  平台: ['pingtai', 'platform'],\n  系统: ['xitong', 'system'],\n  解决方案: ['jiejuefangan', 'solution'],\n  管理: ['guanli', 'management'],\n  企业: ['qiye', 'enterprise'],\n  商务: ['shangwu', 'business'],\n  电商: ['dianshang', 'ecommerce', 'e-commerce'],\n  网站: ['wangzhan', 'website'],\n  应用: ['yingyong', 'application', 'app'],\n  软件: ['ruanjian', 'software'],\n  开发: ['kaifa', 'development', 'dev'],\n  设计: ['sheji', 'design'],\n  营销: ['yingxiao', 'marketing'],\n  推广: ['tuiguang', 'promotion'],\n  优化: ['youhua', 'optimization', 'seo'],\n  搜索: ['sousuo', 'search'],\n  引擎: ['yinqing', 'engine'],\n  网络: ['wangluo', 'network'],\n  互联网: ['hulianwang', 'internet'],\n  数字: ['shuzi', 'digital'],\n  在线: ['zaixian', 'online'],\n  云: ['yun', 'cloud'],\n  大数据: ['dashuju', 'big-data'],\n  区块链: ['qukuailian', 'blockchain'],\n  金融: ['jinrong', 'finance', 'financial'],\n  科技: ['keji', 'technology', 'tech'],\n  创新: ['chuangxin', 'innovation'],\n  智能: ['zhineng', 'intelligent', 'smart'],\n  自动: ['zidong', 'automatic', 'auto'],\n  专业: ['zhuanye', 'professional'],\n  高效: ['gaoxiao', 'efficient'],\n  安全: ['anquan', 'security', 'safe'],\n  可靠: ['kekao', 'reliable'],\n  快速: ['kuaisu', 'fast', 'quick'],\n  便捷: ['bianjie', 'convenient'],\n  移动: ['yidong', 'mobile'],\n  社交: ['shejiao', 'social'],\n  媒体: ['meiti', 'media'],\n  内容: ['neirong', 'content'],\n  用户: ['yonghu', 'user'],\n  客户: ['kehu', 'customer', 'client'],\n  产品: ['chanpin', 'product'],\n  品牌: ['pinpai', 'brand'],\n  市场: ['shichang', 'market'],\n  销售: ['xiaoshou', 'sales'],\n  教育: ['jiaoyu', 'education'],\n  培训: ['peixun', 'training'],\n  学习: ['xuexi', 'learning'],\n  知识: ['zhishi', 'knowledge'],\n  信息: ['xinxi', 'information', 'info'],\n  新闻: ['xinwen', 'news'],\n  资讯: ['zixun', 'information', 'info'],\n  咨询: ['zixun', 'consulting'],\n  顾问: ['guwen', 'consultant', 'advisor']\n};\n\n/**\n * Creates enhanced keyphrase forms for Chinese keywords in URL context\n * @param {Object} originalTopicForms - Original morphology forms\n * @param {string} keyword - The Chinese keyword\n * @param {string} parsedSlug - The parsed URL slug\n * @returns {Object} Enhanced topic forms with pinyin variations\n */\nfunction createEnhancedChineseUrlForms(originalTopicForms, keyword, parsedSlug) {\n  const enhancedForms = [...originalTopicForms.keyphraseForms];\n\n  // Check if keyword contains any Chinese characters\n  const chineseMatches = keyword.match(/[\\u4e00-\\u9fff]+/g) || [];\n\n  // Add pinyin mappings for each Chinese phrase found\n  chineseMatches.forEach(chinesePhrase => {\n    // Check for exact matches in our mapping\n    if (CHINESE_PINYIN_URL_MAP[chinesePhrase]) {\n      CHINESE_PINYIN_URL_MAP[chinesePhrase].forEach(pinyin => {\n        enhancedForms.push([pinyin]);\n      });\n    }\n\n    // Check for partial matches (useful for compound words)\n    Object.entries(CHINESE_PINYIN_URL_MAP).forEach(([chinese, pinyins]) => {\n      if (chinesePhrase.includes(chinese)) {\n        pinyins.forEach(pinyin => {\n          enhancedForms.push([pinyin]);\n        });\n      }\n    });\n  });\n\n  // Extract potential meaningful words from slug for additional matching\n  const slugWords = parsedSlug\n    .toLowerCase()\n    .split(/\\s+/)\n    .filter(word => word.length > 2 && !/^(and|or|the|of|in|on|at|to|for|with|by)$/i.test(word));\n\n  slugWords.forEach(word => {\n    enhancedForms.push([word]);\n  });\n\n  return {\n    keyphraseForms: enhancedForms,\n    synonymsForms: originalTopicForms.synonymsForms || []\n  };\n}\n\n/**\n * Matches the keyword in the slug. Replaces all dashes and underscores with whitespaces and uses whitespace as word boundary.\n * Enhanced with Chinese URL slug support.\n *\n * @param {Paper} paper the Paper object to use in this count.\n * @param {Researcher} researcher The Researcher object containing all available researches.\n *\n * @returns {{keyphraseLength: int, percentWordMatches: int}} The length of the keyphrase and the percentage of keyphrase forms that has been found.\n */\nfunction keywordCountInSlug(paper, researcher) {\n  /*\n   * We want to override the `areHyphensWordBoundaries` config value from the researcher so that it is `true` for all\n   * languages. This is because slugs usually use hyphens (or underscores) as word boundaries. So if only the slug is\n   * split on hyphens and not the keyphrase forms, some keyphrase forms won't be found in the slug.\n   */\n  const languageResearcher = cloneDeep(researcher);\n  languageResearcher.addConfig('areHyphensWordBoundaries', true);\n  const originalTopicForms = languageResearcher.getResearch('morphology');\n\n  const parsedSlug = parseSlug(paper.getSlug());\n  const locale = paper.getLocale();\n  const keyword = paper.getKeyword();\n\n  // Enhanced Chinese URL handling\n  const isChineseKeyword = /[\\u4e00-\\u9fff]/.test(keyword);\n  const isPinyinSlug =\n    /^[a-zA-Z0-9\\s\\-_]+$/.test(parsedSlug) && !/[\\u4e00-\\u9fff]/.test(parsedSlug);\n\n  let topicForms = originalTopicForms;\n\n  if (isChineseKeyword && isPinyinSlug) {\n    topicForms = createEnhancedChineseUrlForms(originalTopicForms, keyword, parsedSlug);\n\n    // For Chinese URL context, use enhanced calculation\n    const pinyinMatches = topicForms.keyphraseForms.filter(([form]) => {\n      return parsedSlug.toLowerCase().includes(form.toLowerCase()) && !/[\\u4e00-\\u9fff]/.test(form); // Only count non-Chinese forms\n    }).length;\n\n    const chineseComponents = keyword.match(/[\\u4e00-\\u9fff]+/g) || [];\n    const expectedMatches = chineseComponents.length;\n\n    if (pinyinMatches >= expectedMatches) {\n      return {\n        keyphraseLength: expectedMatches,\n        percentWordMatches: 100\n      };\n    } else if (pinyinMatches > 0) {\n      const enhancedPercent = Math.round((pinyinMatches / expectedMatches) * 100);\n      return {\n        keyphraseLength: expectedMatches,\n        percentWordMatches: enhancedPercent >= 50 ? enhancedPercent : Math.max(enhancedPercent, 67)\n      };\n    }\n  }\n\n  // Auto-detect Chinese and use appropriate helper - specifically for URL context\n  const matchHelper = getMatchHelper(\n    parsedSlug,\n    keyword,\n    researcher.getHelper('matchWordCustomHelper'),\n    true // isUrlContext = true for enhanced Chinese URL matching\n  );\n\n  const keyphraseInSlug = findTopicFormsInString(\n    topicForms,\n    parsedSlug,\n    false,\n    locale,\n    matchHelper\n  );\n\n  return {\n    keyphraseLength: topicForms.keyphraseForms.length,\n    percentWordMatches: keyphraseInSlug.percentWordMatches\n  };\n}\n\n/**\n * Matches the keyword in the slug.\n * keywordCountInUrl was the previous name for keywordCountInSlug (hence the name of this file).\n * We keep (and expose) this research for backwards compatibility.\n *\n * @deprecated Since version 18.7. Use keywordCountInSlug instead.\n *\n * @param {Paper} paper the Paper object to use in this count.\n * @param {Researcher} researcher The Researcher object containing all available researches.\n *\n * @returns {{keyphraseLength: int, percentWordMatches: int}} The length of the keyphrase and the percentage of keyphrase forms that has been found.\n */\nfunction keywordCountInUrl(paper, researcher) {\n  console.warn('This function is deprecated, use keywordCountInSlug instead.');\n  return keywordCountInSlug(paper, researcher);\n}\n\nexport {keywordCountInSlug, keywordCountInUrl};\n\nexport default keywordCountInSlug;\n"],"mappings":"AAAA;AACA,OAAOA,SAAS;AAChB,SAAQC,sBAAsB;AAC9B,SAAQC,SAAS,QAAO,QAAQ;AAChC,SAAQC,cAAc;;AAEtB;AACA;AACA;AACA,MAAMC,sBAAsB,GAAG;EAC7BC,EAAE,EAAE,CAAC,SAAS,EAAE,UAAU,EAAE,cAAc,CAAC;EAC3CC,EAAE,EAAE,CAAC,OAAO,EAAE,QAAQ,EAAE,WAAW,CAAC;EACpCC,IAAI,EAAE,CAAC,eAAe,EAAE,IAAI,EAAE,yBAAyB,CAAC;EACxDC,IAAI,EAAE,CAAC,WAAW,EAAE,kBAAkB,EAAE,IAAI,CAAC;EAC7CC,EAAE,EAAE,CAAC,OAAO,EAAE,MAAM,CAAC;EACrBC,EAAE,EAAE,CAAC,OAAO,EAAE,UAAU,CAAC;EACzBC,EAAE,EAAE,CAAC,OAAO,EAAE,YAAY,EAAE,MAAM,CAAC;EACnCC,EAAE,EAAE,CAAC,MAAM,EAAE,SAAS,CAAC;EACvBC,EAAE,EAAE,CAAC,SAAS,EAAE,UAAU,CAAC;EAC3BC,EAAE,EAAE,CAAC,QAAQ,EAAE,QAAQ,CAAC;EACxBC,IAAI,EAAE,CAAC,cAAc,EAAE,UAAU,CAAC;EAClCC,EAAE,EAAE,CAAC,QAAQ,EAAE,YAAY,CAAC;EAC5BC,EAAE,EAAE,CAAC,MAAM,EAAE,YAAY,CAAC;EAC1BC,EAAE,EAAE,CAAC,SAAS,EAAE,UAAU,CAAC;EAC3BC,EAAE,EAAE,CAAC,WAAW,EAAE,WAAW,EAAE,YAAY,CAAC;EAC5CC,EAAE,EAAE,CAAC,UAAU,EAAE,SAAS,CAAC;EAC3BC,EAAE,EAAE,CAAC,UAAU,EAAE,aAAa,EAAE,KAAK,CAAC;EACtCC,EAAE,EAAE,CAAC,UAAU,EAAE,UAAU,CAAC;EAC5BC,EAAE,EAAE,CAAC,OAAO,EAAE,aAAa,EAAE,KAAK,CAAC;EACnCC,EAAE,EAAE,CAAC,OAAO,EAAE,QAAQ,CAAC;EACvBC,EAAE,EAAE,CAAC,UAAU,EAAE,WAAW,CAAC;EAC7BC,EAAE,EAAE,CAAC,UAAU,EAAE,WAAW,CAAC;EAC7BC,EAAE,EAAE,CAAC,QAAQ,EAAE,cAAc,EAAE,KAAK,CAAC;EACrCC,EAAE,EAAE,CAAC,QAAQ,EAAE,QAAQ,CAAC;EACxBC,EAAE,EAAE,CAAC,SAAS,EAAE,QAAQ,CAAC;EACzBC,EAAE,EAAE,CAAC,SAAS,EAAE,SAAS,CAAC;EAC1BC,GAAG,EAAE,CAAC,YAAY,EAAE,UAAU,CAAC;EAC/BC,EAAE,EAAE,CAAC,OAAO,EAAE,SAAS,CAAC;EACxBC,EAAE,EAAE,CAAC,SAAS,EAAE,QAAQ,CAAC;EACzBC,CAAC,EAAE,CAAC,KAAK,EAAE,OAAO,CAAC;EACnBC,GAAG,EAAE,CAAC,SAAS,EAAE,UAAU,CAAC;EAC5BC,GAAG,EAAE,CAAC,YAAY,EAAE,YAAY,CAAC;EACjCC,EAAE,EAAE,CAAC,SAAS,EAAE,SAAS,EAAE,WAAW,CAAC;EACvCC,EAAE,EAAE,CAAC,MAAM,EAAE,YAAY,EAAE,MAAM,CAAC;EAClCC,EAAE,EAAE,CAAC,WAAW,EAAE,YAAY,CAAC;EAC/BC,EAAE,EAAE,CAAC,SAAS,EAAE,aAAa,EAAE,OAAO,CAAC;EACvCC,EAAE,EAAE,CAAC,QAAQ,EAAE,WAAW,EAAE,MAAM,CAAC;EACnCC,EAAE,EAAE,CAAC,SAAS,EAAE,cAAc,CAAC;EAC/BC,EAAE,EAAE,CAAC,SAAS,EAAE,WAAW,CAAC;EAC5BC,EAAE,EAAE,CAAC,QAAQ,EAAE,UAAU,EAAE,MAAM,CAAC;EAClCC,EAAE,EAAE,CAAC,OAAO,EAAE,UAAU,CAAC;EACzBC,EAAE,EAAE,CAAC,QAAQ,EAAE,MAAM,EAAE,OAAO,CAAC;EAC/BC,EAAE,EAAE,CAAC,SAAS,EAAE,YAAY,CAAC;EAC7BC,EAAE,EAAE,CAAC,QAAQ,EAAE,QAAQ,CAAC;EACxBC,EAAE,EAAE,CAAC,SAAS,EAAE,QAAQ,CAAC;EACzBC,EAAE,EAAE,CAAC,OAAO,EAAE,OAAO,CAAC;EACtBC,EAAE,EAAE,CAAC,SAAS,EAAE,SAAS,CAAC;EAC1BC,EAAE,EAAE,CAAC,QAAQ,EAAE,MAAM,CAAC;EACtBC,EAAE,EAAE,CAAC,MAAM,EAAE,UAAU,EAAE,QAAQ,CAAC;EAClCC,EAAE,EAAE,CAAC,SAAS,EAAE,SAAS,CAAC;EAC1BC,EAAE,EAAE,CAAC,QAAQ,EAAE,OAAO,CAAC;EACvBC,EAAE,EAAE,CAAC,UAAU,EAAE,QAAQ,CAAC;EAC1BC,EAAE,EAAE,CAAC,UAAU,EAAE,OAAO,CAAC;EACzBC,EAAE,EAAE,CAAC,QAAQ,EAAE,WAAW,CAAC;EAC3BC,EAAE,EAAE,CAAC,QAAQ,EAAE,UAAU,CAAC;EAC1BC,EAAE,EAAE,CAAC,OAAO,EAAE,UAAU,CAAC;EACzBC,EAAE,EAAE,CAAC,QAAQ,EAAE,WAAW,CAAC;EAC3BC,EAAE,EAAE,CAAC,OAAO,EAAE,aAAa,EAAE,MAAM,CAAC;EACpCC,EAAE,EAAE,CAAC,QAAQ,EAAE,MAAM,CAAC;EACtBC,EAAE,EAAE,CAAC,OAAO,EAAE,aAAa,EAAE,MAAM,CAAC;EACpCC,EAAE,EAAE,CAAC,OAAO,EAAE,YAAY,CAAC;EAC3BC,EAAE,EAAE,CAAC,OAAO,EAAE,YAAY,EAAE,SAAS;AACvC,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,6BAA6BA,CAACC,kBAAkB,EAAEC,OAAO,EAAEC,UAAU,EAAE;EAC9E,MAAMC,aAAa,GAAG,CAAC,GAAGH,kBAAkB,CAACI,cAAc,CAAC;;EAE5D;EACA,MAAMC,cAAc,GAAGJ,OAAO,CAACK,KAAK,CAAC,mBAAmB,CAAC,IAAI,EAAE;;EAE/D;EACAD,cAAc,CAACE,OAAO,CAACC,aAAa,IAAI;IACtC;IACA,IAAIxE,sBAAsB,CAACwE,aAAa,CAAC,EAAE;MACzCxE,sBAAsB,CAACwE,aAAa,CAAC,CAACD,OAAO,CAACE,MAAM,IAAI;QACtDN,aAAa,CAACO,IAAI,CAAC,CAACD,MAAM,CAAC,CAAC;MAC9B,CAAC,CAAC;IACJ;;IAEA;IACAE,MAAM,CAACC,OAAO,CAAC5E,sBAAsB,CAAC,CAACuE,OAAO,CAAC,CAAC,CAACM,OAAO,EAAEC,OAAO,CAAC,KAAK;MACrE,IAAIN,aAAa,CAACO,QAAQ,CAACF,OAAO,CAAC,EAAE;QACnCC,OAAO,CAACP,OAAO,CAACE,MAAM,IAAI;UACxBN,aAAa,CAACO,IAAI,CAAC,CAACD,MAAM,CAAC,CAAC;QAC9B,CAAC,CAAC;MACJ;IACF,CAAC,CAAC;EACJ,CAAC,CAAC;;EAEF;EACA,MAAMO,SAAS,GAAGd,UAAU,CACzBe,WAAW,CAAC,CAAC,CACbC,KAAK,CAAC,KAAK,CAAC,CACZC,MAAM,CAACC,IAAI,IAAIA,IAAI,CAACC,MAAM,GAAG,CAAC,IAAI,CAAC,4CAA4C,CAACC,IAAI,CAACF,IAAI,CAAC,CAAC;EAE9FJ,SAAS,CAACT,OAAO,CAACa,IAAI,IAAI;IACxBjB,aAAa,CAACO,IAAI,CAAC,CAACU,IAAI,CAAC,CAAC;EAC5B,CAAC,CAAC;EAEF,OAAO;IACLhB,cAAc,EAAED,aAAa;IAC7BoB,aAAa,EAAEvB,kBAAkB,CAACuB,aAAa,IAAI;EACrD,CAAC;AACH;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,kBAAkBA,CAACC,KAAK,EAAEC,UAAU,EAAE;EAC7C;AACF;AACA;AACA;AACA;EACE,MAAMC,kBAAkB,GAAG7F,SAAS,CAAC4F,UAAU,CAAC;EAChDC,kBAAkB,CAACC,SAAS,CAAC,0BAA0B,EAAE,IAAI,CAAC;EAC9D,MAAM5B,kBAAkB,GAAG2B,kBAAkB,CAACE,WAAW,CAAC,YAAY,CAAC;EAEvE,MAAM3B,UAAU,GAAGtE,SAAS,CAAC6F,KAAK,CAACK,OAAO,CAAC,CAAC,CAAC;EAC7C,MAAMC,MAAM,GAAGN,KAAK,CAACO,SAAS,CAAC,CAAC;EAChC,MAAM/B,OAAO,GAAGwB,KAAK,CAACQ,UAAU,CAAC,CAAC;;EAElC;EACA,MAAMC,gBAAgB,GAAG,iBAAiB,CAACZ,IAAI,CAACrB,OAAO,CAAC;EACxD,MAAMkC,YAAY,GAChB,qBAAqB,CAACb,IAAI,CAACpB,UAAU,CAAC,IAAI,CAAC,iBAAiB,CAACoB,IAAI,CAACpB,UAAU,CAAC;EAE/E,IAAIkC,UAAU,GAAGpC,kBAAkB;EAEnC,IAAIkC,gBAAgB,IAAIC,YAAY,EAAE;IACpCC,UAAU,GAAGrC,6BAA6B,CAACC,kBAAkB,EAAEC,OAAO,EAAEC,UAAU,CAAC;;IAEnF;IACA,MAAMmC,aAAa,GAAGD,UAAU,CAAChC,cAAc,CAACe,MAAM,CAAC,CAAC,CAACmB,IAAI,CAAC,KAAK;MACjE,OAAOpC,UAAU,CAACe,WAAW,CAAC,CAAC,CAACF,QAAQ,CAACuB,IAAI,CAACrB,WAAW,CAAC,CAAC,CAAC,IAAI,CAAC,iBAAiB,CAACK,IAAI,CAACgB,IAAI,CAAC,CAAC,CAAC;IACjG,CAAC,CAAC,CAACjB,MAAM;IAET,MAAMkB,iBAAiB,GAAGtC,OAAO,CAACK,KAAK,CAAC,mBAAmB,CAAC,IAAI,EAAE;IAClE,MAAMkC,eAAe,GAAGD,iBAAiB,CAAClB,MAAM;IAEhD,IAAIgB,aAAa,IAAIG,eAAe,EAAE;MACpC,OAAO;QACLC,eAAe,EAAED,eAAe;QAChCE,kBAAkB,EAAE;MACtB,CAAC;IACH,CAAC,MAAM,IAAIL,aAAa,GAAG,CAAC,EAAE;MAC5B,MAAMM,eAAe,GAAGC,IAAI,CAACC,KAAK,CAAER,aAAa,GAAGG,eAAe,GAAI,GAAG,CAAC;MAC3E,OAAO;QACLC,eAAe,EAAED,eAAe;QAChCE,kBAAkB,EAAEC,eAAe,IAAI,EAAE,GAAGA,eAAe,GAAGC,IAAI,CAACE,GAAG,CAACH,eAAe,EAAE,EAAE;MAC5F,CAAC;IACH;EACF;;EAEA;EACA,MAAMI,WAAW,GAAGhH,cAAc,CAChCmE,UAAU,EACVD,OAAO,EACPyB,UAAU,CAACsB,SAAS,CAAC,uBAAuB,CAAC,EAC7C,IAAI,CAAC;EACP,CAAC;EAED,MAAMC,eAAe,GAAGpH,sBAAsB,CAC5CuG,UAAU,EACVlC,UAAU,EACV,KAAK,EACL6B,MAAM,EACNgB,WACF,CAAC;EAED,OAAO;IACLN,eAAe,EAAEL,UAAU,CAAChC,cAAc,CAACiB,MAAM;IACjDqB,kBAAkB,EAAEO,eAAe,CAACP;EACtC,CAAC;AACH;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASQ,iBAAiBA,CAACzB,KAAK,EAAEC,UAAU,EAAE;EAC5CyB,OAAO,CAACC,IAAI,CAAC,8DAA8D,CAAC;EAC5E,OAAO5B,kBAAkB,CAACC,KAAK,EAAEC,UAAU,CAAC;AAC9C;AAEA,SAAQF,kBAAkB,EAAE0B,iBAAiB;AAE7C,eAAe1B,kBAAkB","ignoreList":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"matchKeywordInSubheadings.js","names":["getSubheadingContentsTopLevel","stripSomeTags","findTopicFormsInString","removeHtmlBlocks","filterShortcodesFromHTML","numberOfSubheadingsReflectingTopic","topicForms","subheadings","useSynonyms","locale","functionWords","matchWordCustomHelper","filter","subheading","matchedTopicForms","length","percentWordMatches","matchKeywordInSubheadings","paper","researcher","getConfig","getHelper","text","getText","_attributes","shortcodes","replace","trim","getResearch","getLocale","result","count","matches","percentReflectingTopic"],"sources":["../../../../src/languageProcessing/researches/matchKeywordInSubheadings.js"],"sourcesContent":["import {getSubheadingContentsTopLevel} from '../helpers/html/getSubheadings';\nimport stripSomeTags from '../helpers/sanitize/stripNonTextTags';\nimport {findTopicFormsInString} from '../helpers/match/findKeywordFormsInString';\nimport removeHtmlBlocks from '../helpers/html/htmlParser';\nimport {filterShortcodesFromHTML} from '../helpers';\n\n/**\n * Computes the amount of subheadings reflecting the topic.\n *\n * @param {Object}      topicForms      The main key phrase and its synonyms to check.\n * @param {string[]}    subheadings     The subheadings to check.\n * @param {boolean}     useSynonyms     Whether to match synonyms or only main keyphrase.\n * @param {string}      locale          The current locale.\n * @param {Array}       functionWords\tThe function words list.\n * @param {function}    matchWordCustomHelper   The language-specific helper function to match word in text.\n *\n * @returns {number} The amount of subheadings reflecting the topic.\n */\nconst numberOfSubheadingsReflectingTopic = function(\n  topicForms,\n  subheadings,\n  useSynonyms,\n  locale,\n  functionWords,\n  matchWordCustomHelper\n) {\n  return subheadings.filter(subheading => {\n    const matchedTopicForms = findTopicFormsInString(\n      topicForms,\n      subheading,\n      useSynonyms,\n      locale,\n      matchWordCustomHelper\n    );\n\n    if (functionWords.length === 0) {\n      return matchedTopicForms.percentWordMatches === 100;\n    }\n    return matchedTopicForms.percentWordMatches > 50;\n  }).length;\n};\n\n/**\n * Checks if there are any h2 or h3 subheadings in the text and if they have the keyphrase or synonyms in them.\n *\n * @param {Object}     paper      The paper object containing the text and keyword.\n * @param {Researcher} researcher The researcher object.\n *\n * @returns {Object} The result object.\n */\nexport default function matchKeywordInSubheadings(paper, researcher) {\n  const functionWords = researcher.getConfig('functionWords');\n\n  // A custom helper to match word in text.\n  const matchWordCustomHelper = researcher.getHelper('matchWordCustomHelper');\n\n  let text = paper.getText();\n  text = removeHtmlBlocks(text);\n  text = filterShortcodesFromHTML(text, paper._attributes && paper._attributes.shortcodes);\n  text = stripSomeTags(text);\n  text = text.replace(/\\s+/g, ' ').trim();\n\n  const topicForms = researcher.getResearch('morphology');\n  const locale = paper.getLocale();\n  const result = {count: 0, matches: 0, percentReflectingTopic: 0};\n  const useSynonyms = true;\n  const subheadings = getSubheadingContentsTopLevel(text);\n\n  if (subheadings.length !== 0) {\n    result.count = subheadings.length;\n    result.matches = numberOfSubheadingsReflectingTopic(\n      topicForms,\n      subheadings,\n      useSynonyms,\n      locale,\n      functionWords,\n      matchWordCustomHelper\n    );\n    result.percentReflectingTopic = (result.matches / result.count) * 100;\n  }\n\n  return result;\n}\n"],"mappings":"AAAA,SAAQA,6BAA6B;AACrC,OAAOC,aAAa;AACpB,SAAQC,sBAAsB;AAC9B,OAAOC,gBAAgB;AACvB,SAAQC,wBAAwB;;AAEhC;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,kCAAkC,GAAG,SAAAA,CACzCC,UAAU,EACVC,WAAW,EACXC,WAAW,EACXC,MAAM,EACNC,aAAa,EACbC,qBAAqB,EACrB;EACA,OAAOJ,WAAW,CAACK,MAAM,CAACC,UAAU,IAAI;IACtC,MAAMC,iBAAiB,GAAGZ,sBAAsB,CAC9CI,UAAU,EACVO,UAAU,EACVL,WAAW,EACXC,MAAM,EACNE,qBACF,CAAC;IAED,IAAID,aAAa,CAACK,MAAM,KAAK,CAAC,EAAE;MAC9B,OAAOD,iBAAiB,CAACE,kBAAkB,KAAK,GAAG;IACrD;IACA,OAAOF,iBAAiB,CAACE,kBAAkB,GAAG,EAAE;EAClD,CAAC,CAAC,CAACD,MAAM;AACX,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASE,yBAAyBA,CAACC,KAAK,EAAEC,UAAU,EAAE;EACnE,MAAMT,aAAa,GAAGS,UAAU,CAACC,SAAS,CAAC,eAAe,CAAC;;EAE3D;EACA,MAAMT,qBAAqB,GAAGQ,UAAU,CAACE,SAAS,CAAC,uBAAuB,CAAC;EAE3E,IAAIC,IAAI,GAAGJ,KAAK,CAACK,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAGnB,gBAAgB,CAACmB,IAAI,CAAC;EAC7BA,IAAI,GAAGlB,wBAAwB,CAACkB,IAAI,EAAEJ,KAAK,CAACM,WAAW,IAAIN,KAAK,CAACM,WAAW,CAACC,UAAU,CAAC;EACxFH,IAAI,GAAGrB,aAAa,CAACqB,IAAI,CAAC;EAC1BA,IAAI,GAAGA,IAAI,CAACI,OAAO,CAAC,MAAM,EAAE,GAAG,CAAC,CAACC,IAAI,CAAC,CAAC;EAEvC,MAAMrB,UAAU,GAAGa,UAAU,CAACS,WAAW,CAAC,YAAY,CAAC;EACvD,MAAMnB,MAAM,GAAGS,KAAK,CAACW,SAAS,CAAC,CAAC;EAChC,MAAMC,MAAM,GAAG;IAACC,KAAK,EAAE,CAAC;IAAEC,OAAO,EAAE,CAAC;IAAEC,sBAAsB,EAAE;EAAC,CAAC;EAChE,MAAMzB,WAAW,GAAG,IAAI;EACxB,MAAMD,WAAW,GAAGP,6BAA6B,CAACsB,IAAI,CAAC;EAEvD,IAAIf,WAAW,CAACQ,MAAM,KAAK,CAAC,EAAE;IAC5Be,MAAM,CAACC,KAAK,GAAGxB,WAAW,CAACQ,MAAM;IACjCe,MAAM,CAACE,OAAO,GAAG3B,kCAAkC,CACjDC,UAAU,EACVC,WAAW,EACXC,WAAW,EACXC,MAAM,EACNC,aAAa,EACbC,qBACF,CAAC;IACDmB,MAAM,CAACG,sBAAsB,GAAIH,MAAM,CAACE,OAAO,GAAGF,MAAM,CAACC,KAAK,GAAI,GAAG;EACvE;EAEA,OAAOD,MAAM;AACf","ignoreList":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"metaDescriptionKeyword.js","names":["matchWords","getSentences","replaceFoundKeywordForms","description","matchedKeywordForms","maxToRemove","forEach","keywordForm","matches","slice","match","replace","matchPerSentence","sentence","topicForms","locale","matchWordCustomHelper","matchesKeyphrase","keyphraseForms","map","keywordForms","fullKeyphraseMatches","Math","min","count","fullSynonymsMatches","synonymsForms","synonymForms","fullSynonymMatches","reduce","sum","paper","researcher","getDescription","getLocale","getResearch","getHelper","memoizedTokenizer","keyphrase","getKeyword","isChinese","test","pos","indexOf","length","sentences","sentenceMatches"],"sources":["../../../../src/languageProcessing/researches/metaDescriptionKeyword.js"],"sourcesContent":["import matchWords from '../helpers/match/matchTextWithArray';\nimport getSentences from '../helpers/sentence/getSentences';\n\n/**\n * Replaces found keyword forms in the given description.\n *\n * @param {string}      description         The description to remove the matched keyword forms from.\n * @param {Object[]}    matchedKeywordForms The matched keyword forms to remove from the description.\n * @param {Number}      maxToRemove         The maximum amount of matches of each individual keyword to remove.\n *\n * @returns {string} The description with the keywords removed.\n */\nconst replaceFoundKeywordForms = function(description, matchedKeywordForms, maxToRemove) {\n  // Replace matches so we do not match them for synonyms.\n  matchedKeywordForms.forEach(keywordForm =>\n    keywordForm.matches.slice(0, maxToRemove).forEach(match => {\n      description = description.replace(match, '');\n    })\n  );\n  return description;\n};\n\n/**\n * Counts the number of full keyphrase matches in the given sentence. Takes synonyms into account.\n * A full keyphrase is when all keywords in the keyphrase match.\n *\n * @param {string}      sentence        The sentence that needs to be analyzed.\n * @param {Object}      topicForms      The keyphrase (and its optional synonyms') word forms.\n * @param {string}      locale          The current locale.\n * @param {function}    matchWordCustomHelper   The language-specific helper function to match word in text.\n *\n * @returns {Number} The number of matched keyphrases in the sentence.\n */\nconst matchPerSentence = function(sentence, topicForms, locale, matchWordCustomHelper) {\n  // Focus keyphrase matches.\n  const matchesKeyphrase = topicForms.keyphraseForms.map(keywordForms =>\n    matchWords(sentence, keywordForms, locale, matchWordCustomHelper)\n  );\n  // Count the number of matches that contain every word in the entire keyphrase.\n  const fullKeyphraseMatches = Math.min(...matchesKeyphrase.map(match => match.count));\n\n  // Replace all full keyphrase matches so we do not match them for synonyms.\n  sentence = replaceFoundKeywordForms(sentence, matchesKeyphrase, fullKeyphraseMatches);\n\n  // Keyphrase synonyms matches.\n  const fullSynonymsMatches = topicForms.synonymsForms.map(synonymForms => {\n    // Synonym keyphrase matches.\n    const matches = synonymForms.map(keywordForms =>\n      matchWords(sentence, keywordForms, locale, matchWordCustomHelper)\n    );\n    // Count the number of matches that contain every word in the entire synonym keyphrase.\n    const fullSynonymMatches = Math.min(...matches.map(match => match.count));\n    // Replace all full matches so we do not match them for other synonyms.\n    sentence = replaceFoundKeywordForms(sentence, matchesKeyphrase, fullSynonymMatches);\n    return fullSynonymMatches;\n  });\n\n  return [fullKeyphraseMatches, ...fullSynonymsMatches].reduce((sum, count) => sum + count, 0);\n};\n\n/**\n * Counts the number of full keyphrase matches in the description.\n *\n * @param {Paper}       paper       The paper object containing the description.\n * @param {Researcher}  researcher  The researcher object to gather researchers from.\n *\n * @returns {Number} The number of keyphrase matches for the entire description.\n */\nexport default function(paper, researcher) {\n  const description = paper.getDescription();\n  const locale = paper.getLocale();\n\n  const topicForms = researcher.getResearch('morphology');\n  const matchWordCustomHelper = researcher.getHelper('matchWordCustomHelper');\n  const memoizedTokenizer = researcher.getHelper('memoizedTokenizer');\n\n  const keyphrase = paper.getKeyword && paper.getKeyword();\n  const isChinese = keyphrase && /[\\u4e00-\\u9fff]/.test(keyphrase);\n\n  if (isChinese) {\n    if (!keyphrase) return 0;\n    let count = 0;\n    let pos = description.indexOf(keyphrase);\n    while (pos !== -1) {\n      count++;\n      pos = description.indexOf(keyphrase, pos + keyphrase.length);\n    }\n    return count;\n  }\n\n  const sentences = getSentences(description, memoizedTokenizer);\n\n  const sentenceMatches = sentences.map(sentence =>\n    matchPerSentence(sentence, topicForms, locale, matchWordCustomHelper)\n  );\n\n  return sentenceMatches.reduce((sum, count) => sum + count, 0);\n}\n"],"mappings":"AAAA,OAAOA,UAAU;AACjB,OAAOC,YAAY;;AAEnB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,wBAAwB,GAAG,SAAAA,CAASC,WAAW,EAAEC,mBAAmB,EAAEC,WAAW,EAAE;EACvF;EACAD,mBAAmB,CAACE,OAAO,CAACC,WAAW,IACrCA,WAAW,CAACC,OAAO,CAACC,KAAK,CAAC,CAAC,EAAEJ,WAAW,CAAC,CAACC,OAAO,CAACI,KAAK,IAAI;IACzDP,WAAW,GAAGA,WAAW,CAACQ,OAAO,CAACD,KAAK,EAAE,EAAE,CAAC;EAC9C,CAAC,CACH,CAAC;EACD,OAAOP,WAAW;AACpB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMS,gBAAgB,GAAG,SAAAA,CAASC,QAAQ,EAAEC,UAAU,EAAEC,MAAM,EAAEC,qBAAqB,EAAE;EACrF;EACA,MAAMC,gBAAgB,GAAGH,UAAU,CAACI,cAAc,CAACC,GAAG,CAACC,YAAY,IACjEpB,UAAU,CAACa,QAAQ,EAAEO,YAAY,EAAEL,MAAM,EAAEC,qBAAqB,CAClE,CAAC;EACD;EACA,MAAMK,oBAAoB,GAAGC,IAAI,CAACC,GAAG,CAAC,GAAGN,gBAAgB,CAACE,GAAG,CAACT,KAAK,IAAIA,KAAK,CAACc,KAAK,CAAC,CAAC;;EAEpF;EACAX,QAAQ,GAAGX,wBAAwB,CAACW,QAAQ,EAAEI,gBAAgB,EAAEI,oBAAoB,CAAC;;EAErF;EACA,MAAMI,mBAAmB,GAAGX,UAAU,CAACY,aAAa,CAACP,GAAG,CAACQ,YAAY,IAAI;IACvE;IACA,MAAMnB,OAAO,GAAGmB,YAAY,CAACR,GAAG,CAACC,YAAY,IAC3CpB,UAAU,CAACa,QAAQ,EAAEO,YAAY,EAAEL,MAAM,EAAEC,qBAAqB,CAClE,CAAC;IACD;IACA,MAAMY,kBAAkB,GAAGN,IAAI,CAACC,GAAG,CAAC,GAAGf,OAAO,CAACW,GAAG,CAACT,KAAK,IAAIA,KAAK,CAACc,KAAK,CAAC,CAAC;IACzE;IACAX,QAAQ,GAAGX,wBAAwB,CAACW,QAAQ,EAAEI,gBAAgB,EAAEW,kBAAkB,CAAC;IACnF,OAAOA,kBAAkB;EAC3B,CAAC,CAAC;EAEF,OAAO,CAACP,oBAAoB,EAAE,GAAGI,mBAAmB,CAAC,CAACI,MAAM,CAAC,CAACC,GAAG,EAAEN,KAAK,KAAKM,GAAG,GAAGN,KAAK,EAAE,CAAC,CAAC;AAC9F,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAASO,KAAK,EAAEC,UAAU,EAAE;EACzC,MAAM7B,WAAW,GAAG4B,KAAK,CAACE,cAAc,CAAC,CAAC;EAC1C,MAAMlB,MAAM,GAAGgB,KAAK,CAACG,SAAS,CAAC,CAAC;EAEhC,MAAMpB,UAAU,GAAGkB,UAAU,CAACG,WAAW,CAAC,YAAY,CAAC;EACvD,MAAMnB,qBAAqB,GAAGgB,UAAU,CAACI,SAAS,CAAC,uBAAuB,CAAC;EAC3E,MAAMC,iBAAiB,GAAGL,UAAU,CAACI,SAAS,CAAC,mBAAmB,CAAC;EAEnE,MAAME,SAAS,GAAGP,KAAK,CAACQ,UAAU,IAAIR,KAAK,CAACQ,UAAU,CAAC,CAAC;EACxD,MAAMC,SAAS,GAAGF,SAAS,IAAI,iBAAiB,CAACG,IAAI,CAACH,SAAS,CAAC;EAEhE,IAAIE,SAAS,EAAE;IACb,IAAI,CAACF,SAAS,EAAE,OAAO,CAAC;IACxB,IAAId,KAAK,GAAG,CAAC;IACb,IAAIkB,GAAG,GAAGvC,WAAW,CAACwC,OAAO,CAACL,SAAS,CAAC;IACxC,OAAOI,GAAG,KAAK,CAAC,CAAC,EAAE;MACjBlB,KAAK,EAAE;MACPkB,GAAG,GAAGvC,WAAW,CAACwC,OAAO,CAACL,SAAS,EAAEI,GAAG,GAAGJ,SAAS,CAACM,MAAM,CAAC;IAC9D;IACA,OAAOpB,KAAK;EACd;EAEA,MAAMqB,SAAS,GAAG5C,YAAY,CAACE,WAAW,EAAEkC,iBAAiB,CAAC;EAE9D,MAAMS,eAAe,GAAGD,SAAS,CAAC1B,GAAG,CAACN,QAAQ,IAC5CD,gBAAgB,CAACC,QAAQ,EAAEC,UAAU,EAAEC,MAAM,EAAEC,qBAAqB,CACtE,CAAC;EAED,OAAO8B,eAAe,CAACjB,MAAM,CAAC,CAACC,GAAG,EAAEN,KAAK,KAAKM,GAAG,GAAGN,KAAK,EAAE,CAAC,CAAC;AAC/D","ignoreList":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"metaDescriptionLength.js","names":["countMetaDescriptionLength","metaDescriptionLength","paper","getDate","getDescription"],"sources":["../../../../src/languageProcessing/researches/metaDescriptionLength.js"],"sourcesContent":["import countMetaDescriptionLength from \"../helpers/word/countMetaDescriptionLength\";\n\n/**\n * Count the meta description length.\n *\n * @param {Paper} paper The paper to check for images.\n *\n * @returns {number|*}  The meta description length.\n */\nexport default function metaDescriptionLength( paper ) {\n\treturn countMetaDescriptionLength( paper.getDate(), paper.getDescription() );\n}\n"],"mappings":"AAAA,OAAOA,0BAA0B;;AAEjC;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASC,qBAAqBA,CAAEC,KAAK,EAAG;EACtD,OAAOF,0BAA0B,CAAEE,KAAK,CAACC,OAAO,CAAC,CAAC,EAAED,KAAK,CAACE,cAAc,CAAC,CAAE,CAAC;AAC7E","ignoreList":[]}

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

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

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

@@ -0,0 +1 @@
+{"version":3,"file":"readingTime.js","names":["getLanguage","wordCountInText","imageCount","paper","researcher","language","getLocale","customGetWords","getHelper","countCharactersFromArray","wordsPerMinute","ar","cn","de","en","es","fi","fr","he","it","nl","pl","pt","ru","sl","sv","tr","charactersPerMinute","ja","wordsPerMinuteScore","charactersPerMinuteScore","textLength","count","minutesToReadText","getText","sumWordsPerMinute","Object","values","reduce","a","b","sumNumberOfLanguages","keys","length","minutesPerImage","numberOfImages","Math","ceil"],"sources":["../../../../src/languageProcessing/researches/readingTime.js"],"sourcesContent":["import getLanguage from \"../../languageProcessing/helpers/language/getLanguage\";\nimport wordCountInText from \"./wordCountInText.js\";\nimport imageCount from \"./imageCount.js\";\n\n/**\n * Calculates the expected reading time of a text.\n *\n * @param {Paper} paper The paper to calculate the reading time for.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {number} The expected reading time in minutes for a given language.\n */\nexport default function( paper, researcher ) {\n\tconst language = getLanguage( paper.getLocale() );\n\n\t// A helper to get words from the text for languages that don't use the default approach.\n\tconst customGetWords = researcher.getHelper( \"getWordsCustomHelper\" );\n\tconst countCharactersFromArray = researcher.getHelper( \"wordsCharacterCount\" );\n\n\t/*\n\t * These numbers (both in `wordsPerMinute` and `charactersPerMinute`) are based on research into average reading times:\n\t * Susanne Trauzettel-Klosinski, Klaus Dietz, the IReST Study Group;\n\t * Standardized Assessment of Reading Performance: The New International Reading Speed Texts IReST.\n\t * Invest. Ophthalmol. Vis. Sci. 2012;53(9):5452-5461\n\t */\n\tconst wordsPerMinute = {\n\t\tar: 138,\n\t\tcn: 158,\n\t\tde: 179,\n\t\ten: 228,\n\t\tes: 218,\n\t\tfi: 161,\n\t\tfr: 195,\n\t\the: 187,\n\t\tit: 188,\n\t\tnl: 202,\n\t\tpl: 166,\n\t\tpt: 181,\n\t\tru: 184,\n\t\tsl: 180,\n\t\tsv: 199,\n\t\ttr: 166,\n\t};\n\n\tconst charactersPerMinute = {\n\t\tja: 357,\n\t};\n\n\n\tconst wordsPerMinuteScore = wordsPerMinute[ language ];\n\tconst charactersPerMinuteScore = charactersPerMinute[ language ];\n\n\t// The default approach of calculating the text length is by counting the words in the text.\n\tlet textLength = wordCountInText( paper ).count;\n\tlet minutesToReadText;\n\n\tif ( charactersPerMinuteScore ) {\n\t\t/*\n\t\t * If a language has a characters per minute score, we assume that the language also uses a character count helper\n\t\t * for retrieving the text length and a custom helper to get words from the text.\n\t\t */\n\t\ttextLength = countCharactersFromArray( customGetWords( paper.getText() ) );\n\t\tminutesToReadText = textLength / charactersPerMinuteScore;\n\t} else if ( wordsPerMinuteScore ) {\n\t\tminutesToReadText = textLength / wordsPerMinuteScore;\n\t} else {\n\t\t// If the language is not on both lists, assign the average of all language-dependent reading times as the score.\n\t\tconst sumWordsPerMinute = Object.values( wordsPerMinute ).reduce( ( a, b ) => a + b );\n\t\tconst sumNumberOfLanguages = Object.keys( wordsPerMinute ).length;\n\t\tminutesToReadText = textLength / ( sumWordsPerMinute / sumNumberOfLanguages );\n\t}\n\n\tconst minutesPerImage = 0.2;\n\tconst numberOfImages = imageCount( paper );\n\n\t/*\n\t * This formula is based on the average number of words a person is expected to read per minute,\n\t * plus extra time for each image in the text. It returns the expected reading time in whole minutes,\n\t * rounded up to the nearest minute.\n\t */\n\treturn Math.ceil( minutesToReadText + ( numberOfImages * minutesPerImage ) );\n}\n"],"mappings":"AAAA,OAAOA,WAAW;AAClB,OAAOC,eAAe;AACtB,OAAOC,UAAU;;AAEjB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C,MAAMC,QAAQ,GAAGL,WAAW,CAAEG,KAAK,CAACG,SAAS,CAAC,CAAE,CAAC;;EAEjD;EACA,MAAMC,cAAc,GAAGH,UAAU,CAACI,SAAS,CAAE,sBAAuB,CAAC;EACrE,MAAMC,wBAAwB,GAAGL,UAAU,CAACI,SAAS,CAAE,qBAAsB,CAAC;;EAE9E;AACD;AACA;AACA;AACA;AACA;EACC,MAAME,cAAc,GAAG;IACtBC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE,GAAG;IACPC,EAAE,EAAE;EACL,CAAC;EAED,MAAMC,mBAAmB,GAAG;IAC3BC,EAAE,EAAE;EACL,CAAC;EAGD,MAAMC,mBAAmB,GAAGnB,cAAc,CAAEL,QAAQ,CAAE;EACtD,MAAMyB,wBAAwB,GAAGH,mBAAmB,CAAEtB,QAAQ,CAAE;;EAEhE;EACA,IAAI0B,UAAU,GAAG9B,eAAe,CAAEE,KAAM,CAAC,CAAC6B,KAAK;EAC/C,IAAIC,iBAAiB;EAErB,IAAKH,wBAAwB,EAAG;IAC/B;AACF;AACA;AACA;IACEC,UAAU,GAAGtB,wBAAwB,CAAEF,cAAc,CAAEJ,KAAK,CAAC+B,OAAO,CAAC,CAAE,CAAE,CAAC;IAC1ED,iBAAiB,GAAGF,UAAU,GAAGD,wBAAwB;EAC1D,CAAC,MAAM,IAAKD,mBAAmB,EAAG;IACjCI,iBAAiB,GAAGF,UAAU,GAAGF,mBAAmB;EACrD,CAAC,MAAM;IACN;IACA,MAAMM,iBAAiB,GAAGC,MAAM,CAACC,MAAM,CAAE3B,cAAe,CAAC,CAAC4B,MAAM,CAAE,CAAEC,CAAC,EAAEC,CAAC,KAAMD,CAAC,GAAGC,CAAE,CAAC;IACrF,MAAMC,oBAAoB,GAAGL,MAAM,CAACM,IAAI,CAAEhC,cAAe,CAAC,CAACiC,MAAM;IACjEV,iBAAiB,GAAGF,UAAU,IAAKI,iBAAiB,GAAGM,oBAAoB,CAAE;EAC9E;EAEA,MAAMG,eAAe,GAAG,GAAG;EAC3B,MAAMC,cAAc,GAAG3C,UAAU,CAAEC,KAAM,CAAC;;EAE1C;AACD;AACA;AACA;AACA;EACC,OAAO2C,IAAI,CAACC,IAAI,CAAEd,iBAAiB,GAAKY,cAAc,GAAGD,eAAkB,CAAC;AAC7E","ignoreList":[]}

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

@@ -0,0 +1 @@
+{"version":3,"file":"sentences.js","names":["getSentences","removeHtmlBlocks","filterShortcodesFromHTML","paper","researcher","memoizedTokenizer","getHelper","text","getText","_attributes","shortcodes"],"sources":["../../../../src/languageProcessing/researches/sentences.js"],"sourcesContent":["import getSentences from \"../helpers/sentence/getSentences\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\n\n/**\n * Returns the sentences from a paper.\n *\n * @param {Paper}   paper       The paper to analyze.\n * @param {object}  researcher  The researcher.\n *\n * @returns {Array} Sentences found in the paper.\n */\nexport default function( paper, researcher ) {\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\treturn getSentences( text, memoizedTokenizer );\n}\n"],"mappings":"AAAA,OAAOA,YAAY;AACnB,OAAOC,gBAAgB;AACvB,SAASC,wBAAwB;;AAEjC;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C,MAAMC,iBAAiB,GAAGD,UAAU,CAACE,SAAS,CAAE,mBAAoB,CAAC;EAErE,IAAIC,IAAI,GAAGJ,KAAK,CAACK,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAGN,gBAAgB,CAAEM,IAAK,CAAC;EAC/BA,IAAI,GAAGL,wBAAwB,CAAEK,IAAI,EAAEJ,KAAK,CAACM,WAAW,IAAIN,KAAK,CAACM,WAAW,CAACC,UAAW,CAAC;EAC1F,OAAOV,YAAY,CAAEO,IAAI,EAAEF,iBAAkB,CAAC;AAC/C","ignoreList":[]}

package/build/esm/languageProcessing/researches/videoCount.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"videoCount.js","names":["countVideoInText","paper","videoTag","iframeVideoTag","videoSrcTag","videoMatches","getText","match","iframeVideoMatches","videoSrcMatches","allMatches","Set","size"],"sources":["../../../../src/languageProcessing/researches/videoCount.js"],"sourcesContent":["/**\n * Checks the amount of videos in the text, including embedded video iframes and specific video sources.\n *\n * @param {Paper} paper The paper to check for videos.\n *\n * @returns {number} The amount of found videos.\n */\nexport default function countVideoInText(paper) {\n  // Regular expression to match <video> tags.\n  const videoTag = /<video.*?<\\/video>/gis;\n\n  // Regular expression to match <iframe> tags with video sources (YouTube, Vimeo, Shopify CDN, etc.).\n  const iframeVideoTag = /<iframe[^>]*src=[\"']https?:\\/\\/(?:www\\.)?(youtube\\.com|youtu\\.be|vimeo\\.com|cdn\\.shopify\\.com)[^\"']*[\"'][^>]*>/gis;\n\n  // Regular expression to match any src attributes with common video file extensions.\n  const videoSrcTag = /src=[\"'].*?\\.(mp4|webm|ogg|mov|m4v|avi|mkv|flv|wmv)(\\?.*?)?[\"']/gis;\n\n  // Match occurrences of <video> tags in the text.\n  const videoMatches = paper.getText().match(videoTag) || [];\n\n  // Match occurrences of <iframe> tags with video sources in the text.\n  const iframeVideoMatches = paper.getText().match(iframeVideoTag) || [];\n\n  // Match occurrences of src attributes pointing to video files in the text.\n  const videoSrcMatches = paper.getText().match(videoSrcTag) || [];\n\n  // Combine all matches into a single set to remove duplicates.\n  const allMatches = new Set([...videoMatches, ...iframeVideoMatches, ...videoSrcMatches]);\n\n  // Return the unique count of all found matches.\n  return allMatches.size;\n}\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASA,gBAAgBA,CAACC,KAAK,EAAE;EAC9C;EACA,MAAMC,QAAQ,GAAG,uBAAuB;;EAExC;EACA,MAAMC,cAAc,GAAG,mHAAmH;;EAE1I;EACA,MAAMC,WAAW,GAAG,oEAAoE;;EAExF;EACA,MAAMC,YAAY,GAAGJ,KAAK,CAACK,OAAO,CAAC,CAAC,CAACC,KAAK,CAACL,QAAQ,CAAC,IAAI,EAAE;;EAE1D;EACA,MAAMM,kBAAkB,GAAGP,KAAK,CAACK,OAAO,CAAC,CAAC,CAACC,KAAK,CAACJ,cAAc,CAAC,IAAI,EAAE;;EAEtE;EACA,MAAMM,eAAe,GAAGR,KAAK,CAACK,OAAO,CAAC,CAAC,CAACC,KAAK,CAACH,WAAW,CAAC,IAAI,EAAE;;EAEhE;EACA,MAAMM,UAAU,GAAG,IAAIC,GAAG,CAAC,CAAC,GAAGN,YAAY,EAAE,GAAGG,kBAAkB,EAAE,GAAGC,eAAe,CAAC,CAAC;;EAExF;EACA,OAAOC,UAAU,CAACE,IAAI;AACxB","ignoreList":[]}

package/build/esm/languageProcessing/researches/wordComplexity.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"wordComplexity.js","names":["flatMap","get","getSentences","getWords","removeHtmlBlocks","filterShortcodesFromHTML","findTopicFormsInString","getComplexWords","currentSentence","researcher","topicForms","language","getConfig","checkIfWordIsComplex","getHelper","functionWords","wordComplexityConfig","checkIfWordIsFunction","premiumData","getData","words","matchWordCustomHelper","foundTopicForms","paper","getLocale","filter","word","matches","includes","result","complexWords","sentence","forEach","push","calculateComplexWordsPercentage","complexWordsResults","totalComplexWords","percentage","length","toFixed","wordComplexity","memoizedTokenizer","text","getText","_attributes","shortcodes","sentences","getResearch","results","map"],"sources":["../../../../src/languageProcessing/researches/wordComplexity.js"],"sourcesContent":["import { flatMap, get } from \"lodash\";\n\nimport getSentences from \"../helpers/sentence/getSentences\";\nimport getWords from \"../helpers/word/getWords\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\nimport { findTopicFormsInString } from \"../helpers/match/findKeywordFormsInString\";\n\n/**\n * An object containing the results of the complex words research for a single sentence.\n *\n * The structure of the data is:\n * @example\n * {\n * complexWords: [\"word1\", \"word2\", \"word3\" ],\n * sentence: \"the sentence\"\n * }\n *\n * @typedef {Object} \tComplexWordsResult\n * @property {string[]}\tcomplexWords\tThe complex words in the sentence.\n * @property {string}\tsentence\t\tThe sentence.\n */\n\n/**\n * Retrieves all complex words in a sentence.\n *\n * @param {string} \t\tcurrentSentence\tThe current sentence.\n * @param {Researcher} \tresearcher\t\tThe researcher object.\n * @param {Object}      topicForms       The object with word forms of all (content) words from the keyphrase and eventually synonyms,\n * comes in a shape {\n *                     keyphraseForms: [[ form1, form2, ... ], [ form1, form2, ... ]],\n *                     synonymsForms: [\n *                          [[ form1, form2, ... ], [ form1, form2, ... ]],\n *                          [[ form1, form2, ... ], [ form1, form2, ... ]],\n *                          [[ form1, form2, ... ], [ form1, form2, ... ]],\n *                     ],\n *                  }\n *\n * @returns {ComplexWordsResult} An object containing all complex words in a given sentence.\n */\nconst getComplexWords = function( currentSentence, researcher, topicForms ) {\n\tconst language = researcher.getConfig( \"language\" );\n\tconst checkIfWordIsComplex = researcher.getHelper( \"checkIfWordIsComplex\" );\n\tconst functionWords = researcher.getConfig( \"functionWords\" );\n\tconst wordComplexityConfig = researcher.getConfig( \"wordComplexity\" );\n\tconst checkIfWordIsFunction = researcher.getHelper( \"checkIfWordIsFunction\" );\n\tconst premiumData = get( researcher.getData( \"morphology\" ), language, false );\n\n\t// Retrieve all words from the sentence.\n\tlet words = getWords( currentSentence );\n\n\t// Filters out keyphrase forms (but not synonyms) because we consider them not to be complex.\n\tconst matchWordCustomHelper = researcher.getHelper( \"matchWordCustomHelper\" );\n\tconst foundTopicForms = findTopicFormsInString( topicForms, currentSentence, false, researcher.paper.getLocale(), matchWordCustomHelper );\n\twords = words.filter( word => ! foundTopicForms.matches.includes( word ) );\n\n\t// Filters out function words because function words are not complex.\n\t// Words are converted to lowercase before processing to avoid excluding function words that start with a capital letter.\n\twords = words.filter( word => ! ( checkIfWordIsFunction ? checkIfWordIsFunction( word ) : functionWords.includes( word ) ) );\n\n\tconst result = {\n\t\tcomplexWords: [],\n\t\tsentence: currentSentence,\n\t};\n\n\tif ( ! premiumData ) {\n\t\treturn result;\n\t}\n\n\twords.forEach( word => {\n\t\tif ( checkIfWordIsComplex( wordComplexityConfig, word, premiumData ) ) {\n\t\t\tresult.complexWords.push( word );\n\t\t}\n\t} );\n\n\treturn result;\n};\n\n/**\n * Calculates the percentage of the complex words compared to the total words in the text.\n *\n * @param {ComplexWordsResult[]}\tcomplexWordsResults\tThe array of complex words results.\n * @param {string[]} \t\t\t\twords    \t\t\tThe array of words retrieved from the text.\n *\n * @returns {number} The percentage of the complex words compared to the total words in the text.\n */\nconst calculateComplexWordsPercentage = function( complexWordsResults, words ) {\n\tconst totalComplexWords = flatMap( complexWordsResults, result => result.complexWords );\n\tconst percentage = ( totalComplexWords.length / words.length ) * 100;\n\n\t// If the number is a decimal, round it to two numbers after the period, e.g. 5.12345 -> 5.12.\n\t// This approach is inspired from this thread: https://stackoverflow.com/questions/11832914/how-to-round-to-at-most-2-decimal-places-if-necessary.\n\treturn +percentage.toFixed( 2 );\n};\n\n/**\n * Gets the complex words from the sentences and calculates the percentage of complex words compared to the total words in the text.\n * This is a research for the Word Complexity assessment. As such, this research is not part of the AbstractResearcher, and not bundled in Yoast SEO.\n *\n * @param {Paper}       paper       The Paper object to get the text from.\n * @param {Researcher}  researcher  The researcher object.\n *\n * @returns {{complexWords: ComplexWordsResult[], percentage: number}}\n * The complex words found and their percentage compared to the total words in the text.\n */\nexport default function wordComplexity( paper, researcher ) {\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\tconst sentences = getSentences( text, memoizedTokenizer );\n\n\tconst topicForms = researcher.getResearch( \"morphology\" );\n\t// Find the complex words in each sentence.\n\tlet results = sentences.map( sentence => getComplexWords( sentence, researcher, topicForms ) );\n\n\t// Remove sentences without complex words.\n\tresults = results.filter( result => result.complexWords.length !== 0 );\n\n\t// Calculate the percentage of complex words in the text as a whole.\n\tconst words = getWords( text );\n\tconst percentage = calculateComplexWordsPercentage( results, words );\n\n\treturn {\n\t\tcomplexWords: results,\n\t\tpercentage: percentage,\n\t};\n}\n\n"],"mappings":"AAAA,SAASA,OAAO,EAAEC,GAAG,QAAQ,QAAQ;AAErC,OAAOC,YAAY;AACnB,OAAOC,QAAQ;AACf,OAAOC,gBAAgB;AACvB,SAASC,wBAAwB;AACjC,SAASC,sBAAsB;;AAE/B;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,eAAe,GAAG,SAAAA,CAAUC,eAAe,EAAEC,UAAU,EAAEC,UAAU,EAAG;EAC3E,MAAMC,QAAQ,GAAGF,UAAU,CAACG,SAAS,CAAE,UAAW,CAAC;EACnD,MAAMC,oBAAoB,GAAGJ,UAAU,CAACK,SAAS,CAAE,sBAAuB,CAAC;EAC3E,MAAMC,aAAa,GAAGN,UAAU,CAACG,SAAS,CAAE,eAAgB,CAAC;EAC7D,MAAMI,oBAAoB,GAAGP,UAAU,CAACG,SAAS,CAAE,gBAAiB,CAAC;EACrE,MAAMK,qBAAqB,GAAGR,UAAU,CAACK,SAAS,CAAE,uBAAwB,CAAC;EAC7E,MAAMI,WAAW,GAAGjB,GAAG,CAAEQ,UAAU,CAACU,OAAO,CAAE,YAAa,CAAC,EAAER,QAAQ,EAAE,KAAM,CAAC;;EAE9E;EACA,IAAIS,KAAK,GAAGjB,QAAQ,CAAEK,eAAgB,CAAC;;EAEvC;EACA,MAAMa,qBAAqB,GAAGZ,UAAU,CAACK,SAAS,CAAE,uBAAwB,CAAC;EAC7E,MAAMQ,eAAe,GAAGhB,sBAAsB,CAAEI,UAAU,EAAEF,eAAe,EAAE,KAAK,EAAEC,UAAU,CAACc,KAAK,CAACC,SAAS,CAAC,CAAC,EAAEH,qBAAsB,CAAC;EACzID,KAAK,GAAGA,KAAK,CAACK,MAAM,CAAEC,IAAI,IAAI,CAAEJ,eAAe,CAACK,OAAO,CAACC,QAAQ,CAAEF,IAAK,CAAE,CAAC;;EAE1E;EACA;EACAN,KAAK,GAAGA,KAAK,CAACK,MAAM,CAAEC,IAAI,IAAI,EAAIT,qBAAqB,GAAGA,qBAAqB,CAAES,IAAK,CAAC,GAAGX,aAAa,CAACa,QAAQ,CAAEF,IAAK,CAAC,CAAG,CAAC;EAE5H,MAAMG,MAAM,GAAG;IACdC,YAAY,EAAE,EAAE;IAChBC,QAAQ,EAAEvB;EACX,CAAC;EAED,IAAK,CAAEU,WAAW,EAAG;IACpB,OAAOW,MAAM;EACd;EAEAT,KAAK,CAACY,OAAO,CAAEN,IAAI,IAAI;IACtB,IAAKb,oBAAoB,CAAEG,oBAAoB,EAAEU,IAAI,EAAER,WAAY,CAAC,EAAG;MACtEW,MAAM,CAACC,YAAY,CAACG,IAAI,CAAEP,IAAK,CAAC;IACjC;EACD,CAAE,CAAC;EAEH,OAAOG,MAAM;AACd,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMK,+BAA+B,GAAG,SAAAA,CAAUC,mBAAmB,EAAEf,KAAK,EAAG;EAC9E,MAAMgB,iBAAiB,GAAGpC,OAAO,CAAEmC,mBAAmB,EAAEN,MAAM,IAAIA,MAAM,CAACC,YAAa,CAAC;EACvF,MAAMO,UAAU,GAAKD,iBAAiB,CAACE,MAAM,GAAGlB,KAAK,CAACkB,MAAM,GAAK,GAAG;;EAEpE;EACA;EACA,OAAO,CAACD,UAAU,CAACE,OAAO,CAAE,CAAE,CAAC;AAChC,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASC,cAAcA,CAAEjB,KAAK,EAAEd,UAAU,EAAG;EAC3D,MAAMgC,iBAAiB,GAAGhC,UAAU,CAACK,SAAS,CAAE,mBAAoB,CAAC;EACrE,IAAI4B,IAAI,GAAGnB,KAAK,CAACoB,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAGtC,gBAAgB,CAAEsC,IAAK,CAAC;EAC/BA,IAAI,GAAGrC,wBAAwB,CAAEqC,IAAI,EAAEnB,KAAK,CAACqB,WAAW,IAAIrB,KAAK,CAACqB,WAAW,CAACC,UAAW,CAAC;EAC1F,MAAMC,SAAS,GAAG5C,YAAY,CAAEwC,IAAI,EAAED,iBAAkB,CAAC;EAEzD,MAAM/B,UAAU,GAAGD,UAAU,CAACsC,WAAW,CAAE,YAAa,CAAC;EACzD;EACA,IAAIC,OAAO,GAAGF,SAAS,CAACG,GAAG,CAAElB,QAAQ,IAAIxB,eAAe,CAAEwB,QAAQ,EAAEtB,UAAU,EAAEC,UAAW,CAAE,CAAC;;EAE9F;EACAsC,OAAO,GAAGA,OAAO,CAACvB,MAAM,CAAEI,MAAM,IAAIA,MAAM,CAACC,YAAY,CAACQ,MAAM,KAAK,CAAE,CAAC;;EAEtE;EACA,MAAMlB,KAAK,GAAGjB,QAAQ,CAAEuC,IAAK,CAAC;EAC9B,MAAML,UAAU,GAAGH,+BAA+B,CAAEc,OAAO,EAAE5B,KAAM,CAAC;EAEpE,OAAO;IACNU,YAAY,EAAEkB,OAAO;IACrBX,UAAU,EAAEA;EACb,CAAC;AACF","ignoreList":[]}