axyseo 2.1.11 → 2.1.13

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

@@ -0,0 +1,203 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+exports.keywordCountInSlug = keywordCountInSlug;
+exports.keywordCountInUrl = keywordCountInUrl;
+var _parseSlug = _interopRequireDefault(require("../helpers/url/parseSlug"));
+var _findKeywordFormsInString = require("../helpers/match/findKeywordFormsInString.js");
+var _lodash = require("lodash");
+var _chineseHelperFactory = require("../helpers/language/chineseHelperFactory.js");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/** @module researches/keywordCountInSlug */
+
+/**
+ * Enhanced pinyin mapping for Chinese keywords commonly used in URLs
+ */
+const CHINESE_PINYIN_URL_MAP = {
+  跨境: ['kuajing', 'kua-jing', 'cross-border'],
+  物流: ['wuliu', 'wu-liu', 'logistics'],
+  人工智能: ['renqingzhinen', 'ai', 'artificial-intelligence'],
+  机器学习: ['jiqixuexi', 'machine-learning', 'ml'],
+  数据: ['shuju', 'data'],
+  分析: ['fenxi', 'analysis'],
+  技术: ['jishu', 'technology', 'tech'],
+  服务: ['fuwu', 'service'],
+  平台: ['pingtai', 'platform'],
+  系统: ['xitong', 'system'],
+  解决方案: ['jiejuefangan', 'solution'],
+  管理: ['guanli', 'management'],
+  企业: ['qiye', 'enterprise'],
+  商务: ['shangwu', 'business'],
+  电商: ['dianshang', 'ecommerce', 'e-commerce'],
+  网站: ['wangzhan', 'website'],
+  应用: ['yingyong', 'application', 'app'],
+  软件: ['ruanjian', 'software'],
+  开发: ['kaifa', 'development', 'dev'],
+  设计: ['sheji', 'design'],
+  营销: ['yingxiao', 'marketing'],
+  推广: ['tuiguang', 'promotion'],
+  优化: ['youhua', 'optimization', 'seo'],
+  搜索: ['sousuo', 'search'],
+  引擎: ['yinqing', 'engine'],
+  网络: ['wangluo', 'network'],
+  互联网: ['hulianwang', 'internet'],
+  数字: ['shuzi', 'digital'],
+  在线: ['zaixian', 'online'],
+  云: ['yun', 'cloud'],
+  大数据: ['dashuju', 'big-data'],
+  区块链: ['qukuailian', 'blockchain'],
+  金融: ['jinrong', 'finance', 'financial'],
+  科技: ['keji', 'technology', 'tech'],
+  创新: ['chuangxin', 'innovation'],
+  智能: ['zhineng', 'intelligent', 'smart'],
+  自动: ['zidong', 'automatic', 'auto'],
+  专业: ['zhuanye', 'professional'],
+  高效: ['gaoxiao', 'efficient'],
+  安全: ['anquan', 'security', 'safe'],
+  可靠: ['kekao', 'reliable'],
+  快速: ['kuaisu', 'fast', 'quick'],
+  便捷: ['bianjie', 'convenient'],
+  移动: ['yidong', 'mobile'],
+  社交: ['shejiao', 'social'],
+  媒体: ['meiti', 'media'],
+  内容: ['neirong', 'content'],
+  用户: ['yonghu', 'user'],
+  客户: ['kehu', 'customer', 'client'],
+  产品: ['chanpin', 'product'],
+  品牌: ['pinpai', 'brand'],
+  市场: ['shichang', 'market'],
+  销售: ['xiaoshou', 'sales'],
+  教育: ['jiaoyu', 'education'],
+  培训: ['peixun', 'training'],
+  学习: ['xuexi', 'learning'],
+  知识: ['zhishi', 'knowledge'],
+  信息: ['xinxi', 'information', 'info'],
+  新闻: ['xinwen', 'news'],
+  资讯: ['zixun', 'information', 'info'],
+  咨询: ['zixun', 'consulting'],
+  顾问: ['guwen', 'consultant', 'advisor']
+};
+
+/**
+ * Creates enhanced keyphrase forms for Chinese keywords in URL context
+ * @param {Object} originalTopicForms - Original morphology forms
+ * @param {string} keyword - The Chinese keyword
+ * @param {string} parsedSlug - The parsed URL slug
+ * @returns {Object} Enhanced topic forms with pinyin variations
+ */
+function createEnhancedChineseUrlForms(originalTopicForms, keyword, parsedSlug) {
+  const enhancedForms = [...originalTopicForms.keyphraseForms];
+
+  // Check if keyword contains any Chinese characters
+  const chineseMatches = keyword.match(/[\u4e00-\u9fff]+/g) || [];
+
+  // Add pinyin mappings for each Chinese phrase found
+  chineseMatches.forEach(chinesePhrase => {
+    // Check for exact matches in our mapping
+    if (CHINESE_PINYIN_URL_MAP[chinesePhrase]) {
+      CHINESE_PINYIN_URL_MAP[chinesePhrase].forEach(pinyin => {
+        enhancedForms.push([pinyin]);
+      });
+    }
+
+    // Check for partial matches (useful for compound words)
+    Object.entries(CHINESE_PINYIN_URL_MAP).forEach(([chinese, pinyins]) => {
+      if (chinesePhrase.includes(chinese)) {
+        pinyins.forEach(pinyin => {
+          enhancedForms.push([pinyin]);
+        });
+      }
+    });
+  });
+
+  // Extract potential meaningful words from slug for additional matching
+  const slugWords = parsedSlug.toLowerCase().split(/\s+/).filter(word => word.length > 2 && !/^(and|or|the|of|in|on|at|to|for|with|by)$/i.test(word));
+  slugWords.forEach(word => {
+    enhancedForms.push([word]);
+  });
+  return {
+    keyphraseForms: enhancedForms,
+    synonymsForms: originalTopicForms.synonymsForms || []
+  };
+}
+
+/**
+ * Matches the keyword in the slug. Replaces all dashes and underscores with whitespaces and uses whitespace as word boundary.
+ * Enhanced with Chinese URL slug support.
+ *
+ * @param {Paper} paper the Paper object to use in this count.
+ * @param {Researcher} researcher The Researcher object containing all available researches.
+ *
+ * @returns {{keyphraseLength: int, percentWordMatches: int}} The length of the keyphrase and the percentage of keyphrase forms that has been found.
+ */
+function keywordCountInSlug(paper, researcher) {
+  /*
+   * We want to override the `areHyphensWordBoundaries` config value from the researcher so that it is `true` for all
+   * languages. This is because slugs usually use hyphens (or underscores) as word boundaries. So if only the slug is
+   * split on hyphens and not the keyphrase forms, some keyphrase forms won't be found in the slug.
+   */
+  const languageResearcher = (0, _lodash.cloneDeep)(researcher);
+  languageResearcher.addConfig('areHyphensWordBoundaries', true);
+  const originalTopicForms = languageResearcher.getResearch('morphology');
+  const parsedSlug = (0, _parseSlug.default)(paper.getSlug());
+  const locale = paper.getLocale();
+  const keyword = paper.getKeyword();
+
+  // Enhanced Chinese URL handling
+  const isChineseKeyword = /[\u4e00-\u9fff]/.test(keyword);
+  const isPinyinSlug = /^[a-zA-Z0-9\s\-_]+$/.test(parsedSlug) && !/[\u4e00-\u9fff]/.test(parsedSlug);
+  let topicForms = originalTopicForms;
+  if (isChineseKeyword && isPinyinSlug) {
+    topicForms = createEnhancedChineseUrlForms(originalTopicForms, keyword, parsedSlug);
+
+    // For Chinese URL context, use enhanced calculation
+    const pinyinMatches = topicForms.keyphraseForms.filter(([form]) => {
+      return parsedSlug.toLowerCase().includes(form.toLowerCase()) && !/[\u4e00-\u9fff]/.test(form); // Only count non-Chinese forms
+    }).length;
+    const chineseComponents = keyword.match(/[\u4e00-\u9fff]+/g) || [];
+    const expectedMatches = chineseComponents.length;
+    if (pinyinMatches >= expectedMatches) {
+      return {
+        keyphraseLength: expectedMatches,
+        percentWordMatches: 100
+      };
+    } else if (pinyinMatches > 0) {
+      const enhancedPercent = Math.round(pinyinMatches / expectedMatches * 100);
+      return {
+        keyphraseLength: expectedMatches,
+        percentWordMatches: enhancedPercent >= 50 ? enhancedPercent : Math.max(enhancedPercent, 67)
+      };
+    }
+  }
+
+  // Auto-detect Chinese and use appropriate helper - specifically for URL context
+  const matchHelper = (0, _chineseHelperFactory.getMatchHelper)(parsedSlug, keyword, researcher.getHelper('matchWordCustomHelper'), true // isUrlContext = true for enhanced Chinese URL matching
+  );
+  const keyphraseInSlug = (0, _findKeywordFormsInString.findTopicFormsInString)(topicForms, parsedSlug, false, locale, matchHelper);
+  return {
+    keyphraseLength: topicForms.keyphraseForms.length,
+    percentWordMatches: keyphraseInSlug.percentWordMatches
+  };
+}
+
+/**
+ * Matches the keyword in the slug.
+ * keywordCountInUrl was the previous name for keywordCountInSlug (hence the name of this file).
+ * We keep (and expose) this research for backwards compatibility.
+ *
+ * @deprecated Since version 18.7. Use keywordCountInSlug instead.
+ *
+ * @param {Paper} paper the Paper object to use in this count.
+ * @param {Researcher} researcher The Researcher object containing all available researches.
+ *
+ * @returns {{keyphraseLength: int, percentWordMatches: int}} The length of the keyphrase and the percentage of keyphrase forms that has been found.
+ */
+function keywordCountInUrl(paper, researcher) {
+  console.warn('This function is deprecated, use keywordCountInSlug instead.');
+  return keywordCountInSlug(paper, researcher);
+}
+var _default = exports.default = keywordCountInSlug;
+//# sourceMappingURL=keywordCountInUrl.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"keywordCountInUrl.js","names":["_parseSlug","_interopRequireDefault","require","_findKeywordFormsInString","_lodash","_chineseHelperFactory","e","__esModule","default","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","cloneDeep","addConfig","getResearch","parseSlug","getSlug","locale","getLocale","getKeyword","isChineseKeyword","isPinyinSlug","topicForms","pinyinMatches","form","chineseComponents","expectedMatches","keyphraseLength","percentWordMatches","enhancedPercent","Math","round","max","matchHelper","getMatchHelper","getHelper","keyphraseInSlug","findTopicFormsInString","keywordCountInUrl","console","warn","_default","exports"],"sources":["../../../../src/languageProcessing/researches/keywordCountInUrl.js"],"sourcesContent":["/** @module researches/keywordCountInSlug */\nimport parseSlug from '../helpers/url/parseSlug';\nimport {findTopicFormsInString} from '../helpers/match/findKeywordFormsInString.js';\nimport {cloneDeep} from 'lodash';\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":";;;;;;;;AACA,IAAAA,UAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,yBAAA,GAAAD,OAAA;AACA,IAAAE,OAAA,GAAAF,OAAA;AACA,IAAAG,qBAAA,GAAAH,OAAA;AAA2E,SAAAD,uBAAAK,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAJ3E;;AAMA;AACA;AACA;AACA,MAAMG,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,GAAG,IAAAC,iBAAS,EAACF,UAAU,CAAC;EAChDC,kBAAkB,CAACE,SAAS,CAAC,0BAA0B,EAAE,IAAI,CAAC;EAC9D,MAAM7B,kBAAkB,GAAG2B,kBAAkB,CAACG,WAAW,CAAC,YAAY,CAAC;EAEvE,MAAM5B,UAAU,GAAG,IAAA6B,kBAAS,EAACN,KAAK,CAACO,OAAO,CAAC,CAAC,CAAC;EAC7C,MAAMC,MAAM,GAAGR,KAAK,CAACS,SAAS,CAAC,CAAC;EAChC,MAAMjC,OAAO,GAAGwB,KAAK,CAACU,UAAU,CAAC,CAAC;;EAElC;EACA,MAAMC,gBAAgB,GAAG,iBAAiB,CAACd,IAAI,CAACrB,OAAO,CAAC;EACxD,MAAMoC,YAAY,GAChB,qBAAqB,CAACf,IAAI,CAACpB,UAAU,CAAC,IAAI,CAAC,iBAAiB,CAACoB,IAAI,CAACpB,UAAU,CAAC;EAE/E,IAAIoC,UAAU,GAAGtC,kBAAkB;EAEnC,IAAIoC,gBAAgB,IAAIC,YAAY,EAAE;IACpCC,UAAU,GAAGvC,6BAA6B,CAACC,kBAAkB,EAAEC,OAAO,EAAEC,UAAU,CAAC;;IAEnF;IACA,MAAMqC,aAAa,GAAGD,UAAU,CAAClC,cAAc,CAACe,MAAM,CAAC,CAAC,CAACqB,IAAI,CAAC,KAAK;MACjE,OAAOtC,UAAU,CAACe,WAAW,CAAC,CAAC,CAACF,QAAQ,CAACyB,IAAI,CAACvB,WAAW,CAAC,CAAC,CAAC,IAAI,CAAC,iBAAiB,CAACK,IAAI,CAACkB,IAAI,CAAC,CAAC,CAAC;IACjG,CAAC,CAAC,CAACnB,MAAM;IAET,MAAMoB,iBAAiB,GAAGxC,OAAO,CAACK,KAAK,CAAC,mBAAmB,CAAC,IAAI,EAAE;IAClE,MAAMoC,eAAe,GAAGD,iBAAiB,CAACpB,MAAM;IAEhD,IAAIkB,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,GAAG,IAAAC,oCAAc,EAChChD,UAAU,EACVD,OAAO,EACPyB,UAAU,CAACyB,SAAS,CAAC,uBAAuB,CAAC,EAC7C,IAAI,CAAC;EACP,CAAC;EAED,MAAMC,eAAe,GAAG,IAAAC,gDAAsB,EAC5Cf,UAAU,EACVpC,UAAU,EACV,KAAK,EACL+B,MAAM,EACNgB,WACF,CAAC;EAED,OAAO;IACLN,eAAe,EAAEL,UAAU,CAAClC,cAAc,CAACiB,MAAM;IACjDuB,kBAAkB,EAAEQ,eAAe,CAACR;EACtC,CAAC;AACH;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASU,iBAAiBA,CAAC7B,KAAK,EAAEC,UAAU,EAAE;EAC5C6B,OAAO,CAACC,IAAI,CAAC,8DAA8D,CAAC;EAC5E,OAAOhC,kBAAkB,CAACC,KAAK,EAAEC,UAAU,CAAC;AAC9C;AAAC,IAAA+B,QAAA,GAAAC,OAAA,CAAA3H,OAAA,GAIcyF,kBAAkB","ignoreList":[]}

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

@@ -0,0 +1,69 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = matchKeywordInSubheadings;
+var _getSubheadings = require("../helpers/html/getSubheadings");
+var _stripNonTextTags = _interopRequireDefault(require("../helpers/sanitize/stripNonTextTags"));
+var _findKeywordFormsInString = require("../helpers/match/findKeywordFormsInString");
+var _htmlParser = _interopRequireDefault(require("../helpers/html/htmlParser"));
+var _helpers = require("../helpers");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Computes the amount of subheadings reflecting the topic.
+ *
+ * @param {Object}      topicForms      The main key phrase and its synonyms to check.
+ * @param {string[]}    subheadings     The subheadings to check.
+ * @param {boolean}     useSynonyms     Whether to match synonyms or only main keyphrase.
+ * @param {string}      locale          The current locale.
+ * @param {Array}       functionWords	The function words list.
+ * @param {function}    matchWordCustomHelper   The language-specific helper function to match word in text.
+ *
+ * @returns {number} The amount of subheadings reflecting the topic.
+ */
+const numberOfSubheadingsReflectingTopic = function (topicForms, subheadings, useSynonyms, locale, functionWords, matchWordCustomHelper) {
+  return subheadings.filter(subheading => {
+    const matchedTopicForms = (0, _findKeywordFormsInString.findTopicFormsInString)(topicForms, subheading, useSynonyms, locale, matchWordCustomHelper);
+    if (functionWords.length === 0) {
+      return matchedTopicForms.percentWordMatches === 100;
+    }
+    return matchedTopicForms.percentWordMatches > 50;
+  }).length;
+};
+
+/**
+ * Checks if there are any h2 or h3 subheadings in the text and if they have the keyphrase or synonyms in them.
+ *
+ * @param {Object}     paper      The paper object containing the text and keyword.
+ * @param {Researcher} researcher The researcher object.
+ *
+ * @returns {Object} The result object.
+ */
+function matchKeywordInSubheadings(paper, researcher) {
+  const functionWords = researcher.getConfig('functionWords');
+
+  // A custom helper to match word in text.
+  const matchWordCustomHelper = researcher.getHelper('matchWordCustomHelper');
+  let text = paper.getText();
+  text = (0, _htmlParser.default)(text);
+  text = (0, _helpers.filterShortcodesFromHTML)(text, paper._attributes && paper._attributes.shortcodes);
+  text = (0, _stripNonTextTags.default)(text);
+  text = text.replace(/\s+/g, ' ').trim();
+  const topicForms = researcher.getResearch('morphology');
+  const locale = paper.getLocale();
+  const result = {
+    count: 0,
+    matches: 0,
+    percentReflectingTopic: 0
+  };
+  const useSynonyms = true;
+  const subheadings = (0, _getSubheadings.getSubheadingContentsTopLevel)(text);
+  if (subheadings.length !== 0) {
+    result.count = subheadings.length;
+    result.matches = numberOfSubheadingsReflectingTopic(topicForms, subheadings, useSynonyms, locale, functionWords, matchWordCustomHelper);
+    result.percentReflectingTopic = result.matches / result.count * 100;
+  }
+  return result;
+}
+//# sourceMappingURL=matchKeywordInSubheadings.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"matchKeywordInSubheadings.js","names":["_getSubheadings","require","_stripNonTextTags","_interopRequireDefault","_findKeywordFormsInString","_htmlParser","_helpers","e","__esModule","default","numberOfSubheadingsReflectingTopic","topicForms","subheadings","useSynonyms","locale","functionWords","matchWordCustomHelper","filter","subheading","matchedTopicForms","findTopicFormsInString","length","percentWordMatches","matchKeywordInSubheadings","paper","researcher","getConfig","getHelper","text","getText","removeHtmlBlocks","filterShortcodesFromHTML","_attributes","shortcodes","stripSomeTags","replace","trim","getResearch","getLocale","result","count","matches","percentReflectingTopic","getSubheadingContentsTopLevel"],"sources":["../../../../src/languageProcessing/researches/matchKeywordInSubheadings.js"],"sourcesContent":["import {getSubheadingContentsTopLevel} from '../helpers/html/getSubheadings';\nimport stripSomeTags from '../helpers/sanitize/stripNonTextTags';\nimport {findTopicFormsInString} from '../helpers/match/findKeywordFormsInString';\nimport removeHtmlBlocks from '../helpers/html/htmlParser';\nimport {filterShortcodesFromHTML} from '../helpers';\n\n/**\n * Computes the amount of subheadings reflecting the topic.\n *\n * @param {Object}      topicForms      The main key phrase and its synonyms to check.\n * @param {string[]}    subheadings     The subheadings to check.\n * @param {boolean}     useSynonyms     Whether to match synonyms or only main keyphrase.\n * @param {string}      locale          The current locale.\n * @param {Array}       functionWords\tThe function words list.\n * @param {function}    matchWordCustomHelper   The language-specific helper function to match word in text.\n *\n * @returns {number} The amount of subheadings reflecting the topic.\n */\nconst numberOfSubheadingsReflectingTopic = function(\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,IAAAA,eAAA,GAAAC,OAAA;AACA,IAAAC,iBAAA,GAAAC,sBAAA,CAAAF,OAAA;AACA,IAAAG,yBAAA,GAAAH,OAAA;AACA,IAAAI,WAAA,GAAAF,sBAAA,CAAAF,OAAA;AACA,IAAAK,QAAA,GAAAL,OAAA;AAAoD,SAAAE,uBAAAI,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEpD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,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,GAAG,IAAAC,gDAAsB,EAC9CT,UAAU,EACVO,UAAU,EACVL,WAAW,EACXC,MAAM,EACNE,qBACF,CAAC;IAED,IAAID,aAAa,CAACM,MAAM,KAAK,CAAC,EAAE;MAC9B,OAAOF,iBAAiB,CAACG,kBAAkB,KAAK,GAAG;IACrD;IACA,OAAOH,iBAAiB,CAACG,kBAAkB,GAAG,EAAE;EAClD,CAAC,CAAC,CAACD,MAAM;AACX,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAASE,yBAAyBA,CAACC,KAAK,EAAEC,UAAU,EAAE;EACnE,MAAMV,aAAa,GAAGU,UAAU,CAACC,SAAS,CAAC,eAAe,CAAC;;EAE3D;EACA,MAAMV,qBAAqB,GAAGS,UAAU,CAACE,SAAS,CAAC,uBAAuB,CAAC;EAE3E,IAAIC,IAAI,GAAGJ,KAAK,CAACK,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAG,IAAAE,mBAAgB,EAACF,IAAI,CAAC;EAC7BA,IAAI,GAAG,IAAAG,iCAAwB,EAACH,IAAI,EAAEJ,KAAK,CAACQ,WAAW,IAAIR,KAAK,CAACQ,WAAW,CAACC,UAAU,CAAC;EACxFL,IAAI,GAAG,IAAAM,yBAAa,EAACN,IAAI,CAAC;EAC1BA,IAAI,GAAGA,IAAI,CAACO,OAAO,CAAC,MAAM,EAAE,GAAG,CAAC,CAACC,IAAI,CAAC,CAAC;EAEvC,MAAMzB,UAAU,GAAGc,UAAU,CAACY,WAAW,CAAC,YAAY,CAAC;EACvD,MAAMvB,MAAM,GAAGU,KAAK,CAACc,SAAS,CAAC,CAAC;EAChC,MAAMC,MAAM,GAAG;IAACC,KAAK,EAAE,CAAC;IAAEC,OAAO,EAAE,CAAC;IAAEC,sBAAsB,EAAE;EAAC,CAAC;EAChE,MAAM7B,WAAW,GAAG,IAAI;EACxB,MAAMD,WAAW,GAAG,IAAA+B,6CAA6B,EAACf,IAAI,CAAC;EAEvD,IAAIhB,WAAW,CAACS,MAAM,KAAK,CAAC,EAAE;IAC5BkB,MAAM,CAACC,KAAK,GAAG5B,WAAW,CAACS,MAAM;IACjCkB,MAAM,CAACE,OAAO,GAAG/B,kCAAkC,CACjDC,UAAU,EACVC,WAAW,EACXC,WAAW,EACXC,MAAM,EACNC,aAAa,EACbC,qBACF,CAAC;IACDuB,MAAM,CAACG,sBAAsB,GAAIH,MAAM,CAACE,OAAO,GAAGF,MAAM,CAACC,KAAK,GAAI,GAAG;EACvE;EAEA,OAAOD,MAAM;AACf","ignoreList":[]}

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

@@ -0,0 +1,90 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _matchTextWithArray = _interopRequireDefault(require("../helpers/match/matchTextWithArray"));
+var _getSentences = _interopRequireDefault(require("../helpers/sentence/getSentences"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Replaces found keyword forms in the given description.
+ *
+ * @param {string}      description         The description to remove the matched keyword forms from.
+ * @param {Object[]}    matchedKeywordForms The matched keyword forms to remove from the description.
+ * @param {Number}      maxToRemove         The maximum amount of matches of each individual keyword to remove.
+ *
+ * @returns {string} The description with the keywords removed.
+ */
+const replaceFoundKeywordForms = function (description, matchedKeywordForms, maxToRemove) {
+  // Replace matches so we do not match them for synonyms.
+  matchedKeywordForms.forEach(keywordForm => keywordForm.matches.slice(0, maxToRemove).forEach(match => {
+    description = description.replace(match, '');
+  }));
+  return description;
+};
+
+/**
+ * Counts the number of full keyphrase matches in the given sentence. Takes synonyms into account.
+ * A full keyphrase is when all keywords in the keyphrase match.
+ *
+ * @param {string}      sentence        The sentence that needs to be analyzed.
+ * @param {Object}      topicForms      The keyphrase (and its optional synonyms') word forms.
+ * @param {string}      locale          The current locale.
+ * @param {function}    matchWordCustomHelper   The language-specific helper function to match word in text.
+ *
+ * @returns {Number} The number of matched keyphrases in the sentence.
+ */
+const matchPerSentence = function (sentence, topicForms, locale, matchWordCustomHelper) {
+  // Focus keyphrase matches.
+  const matchesKeyphrase = topicForms.keyphraseForms.map(keywordForms => (0, _matchTextWithArray.default)(sentence, keywordForms, locale, matchWordCustomHelper));
+  // Count the number of matches that contain every word in the entire keyphrase.
+  const fullKeyphraseMatches = Math.min(...matchesKeyphrase.map(match => match.count));
+
+  // Replace all full keyphrase matches so we do not match them for synonyms.
+  sentence = replaceFoundKeywordForms(sentence, matchesKeyphrase, fullKeyphraseMatches);
+
+  // Keyphrase synonyms matches.
+  const fullSynonymsMatches = topicForms.synonymsForms.map(synonymForms => {
+    // Synonym keyphrase matches.
+    const matches = synonymForms.map(keywordForms => (0, _matchTextWithArray.default)(sentence, keywordForms, locale, matchWordCustomHelper));
+    // Count the number of matches that contain every word in the entire synonym keyphrase.
+    const fullSynonymMatches = Math.min(...matches.map(match => match.count));
+    // Replace all full matches so we do not match them for other synonyms.
+    sentence = replaceFoundKeywordForms(sentence, matchesKeyphrase, fullSynonymMatches);
+    return fullSynonymMatches;
+  });
+  return [fullKeyphraseMatches, ...fullSynonymsMatches].reduce((sum, count) => sum + count, 0);
+};
+
+/**
+ * Counts the number of full keyphrase matches in the description.
+ *
+ * @param {Paper}       paper       The paper object containing the description.
+ * @param {Researcher}  researcher  The researcher object to gather researchers from.
+ *
+ * @returns {Number} The number of keyphrase matches for the entire description.
+ */
+function _default(paper, researcher) {
+  const description = paper.getDescription();
+  const locale = paper.getLocale();
+  const topicForms = researcher.getResearch('morphology');
+  const matchWordCustomHelper = researcher.getHelper('matchWordCustomHelper');
+  const memoizedTokenizer = researcher.getHelper('memoizedTokenizer');
+  const keyphrase = paper.getKeyword && paper.getKeyword();
+  const isChinese = keyphrase && /[\u4e00-\u9fff]/.test(keyphrase);
+  if (isChinese) {
+    if (!keyphrase) return 0;
+    let count = 0;
+    let pos = description.indexOf(keyphrase);
+    while (pos !== -1) {
+      count++;
+      pos = description.indexOf(keyphrase, pos + keyphrase.length);
+    }
+    return count;
+  }
+  const sentences = (0, _getSentences.default)(description, memoizedTokenizer);
+  const sentenceMatches = sentences.map(sentence => matchPerSentence(sentence, topicForms, locale, matchWordCustomHelper));
+  return sentenceMatches.reduce((sum, count) => sum + count, 0);
+}
+//# sourceMappingURL=metaDescriptionKeyword.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"metaDescriptionKeyword.js","names":["_matchTextWithArray","_interopRequireDefault","require","_getSentences","e","__esModule","default","replaceFoundKeywordForms","description","matchedKeywordForms","maxToRemove","forEach","keywordForm","matches","slice","match","replace","matchPerSentence","sentence","topicForms","locale","matchWordCustomHelper","matchesKeyphrase","keyphraseForms","map","keywordForms","matchWords","fullKeyphraseMatches","Math","min","count","fullSynonymsMatches","synonymsForms","synonymForms","fullSynonymMatches","reduce","sum","_default","paper","researcher","getDescription","getLocale","getResearch","getHelper","memoizedTokenizer","keyphrase","getKeyword","isChinese","test","pos","indexOf","length","sentences","getSentences","sentenceMatches"],"sources":["../../../../src/languageProcessing/researches/metaDescriptionKeyword.js"],"sourcesContent":["import matchWords from '../helpers/match/matchTextWithArray';\nimport getSentences from '../helpers/sentence/getSentences';\n\n/**\n * Replaces found keyword forms in the given description.\n *\n * @param {string}      description         The description to remove the matched keyword forms from.\n * @param {Object[]}    matchedKeywordForms The matched keyword forms to remove from the description.\n * @param {Number}      maxToRemove         The maximum amount of matches of each individual keyword to remove.\n *\n * @returns {string} The description with the keywords removed.\n */\nconst replaceFoundKeywordForms = function(description, matchedKeywordForms, maxToRemove) {\n  // 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,IAAAA,mBAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,aAAA,GAAAF,sBAAA,CAAAC,OAAA;AAA4D,SAAAD,uBAAAG,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAE5D;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,wBAAwB,GAAG,SAAAA,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,IACjE,IAAAC,2BAAU,EAACR,QAAQ,EAAEO,YAAY,EAAEL,MAAM,EAAEC,qBAAqB,CAClE,CAAC;EACD;EACA,MAAMM,oBAAoB,GAAGC,IAAI,CAACC,GAAG,CAAC,GAAGP,gBAAgB,CAACE,GAAG,CAACT,KAAK,IAAIA,KAAK,CAACe,KAAK,CAAC,CAAC;;EAEpF;EACAZ,QAAQ,GAAGX,wBAAwB,CAACW,QAAQ,EAAEI,gBAAgB,EAAEK,oBAAoB,CAAC;;EAErF;EACA,MAAMI,mBAAmB,GAAGZ,UAAU,CAACa,aAAa,CAACR,GAAG,CAACS,YAAY,IAAI;IACvE;IACA,MAAMpB,OAAO,GAAGoB,YAAY,CAACT,GAAG,CAACC,YAAY,IAC3C,IAAAC,2BAAU,EAACR,QAAQ,EAAEO,YAAY,EAAEL,MAAM,EAAEC,qBAAqB,CAClE,CAAC;IACD;IACA,MAAMa,kBAAkB,GAAGN,IAAI,CAACC,GAAG,CAAC,GAAGhB,OAAO,CAACW,GAAG,CAACT,KAAK,IAAIA,KAAK,CAACe,KAAK,CAAC,CAAC;IACzE;IACAZ,QAAQ,GAAGX,wBAAwB,CAACW,QAAQ,EAAEI,gBAAgB,EAAEY,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;AACe,SAAAO,SAASC,KAAK,EAAEC,UAAU,EAAE;EACzC,MAAM/B,WAAW,GAAG8B,KAAK,CAACE,cAAc,CAAC,CAAC;EAC1C,MAAMpB,MAAM,GAAGkB,KAAK,CAACG,SAAS,CAAC,CAAC;EAEhC,MAAMtB,UAAU,GAAGoB,UAAU,CAACG,WAAW,CAAC,YAAY,CAAC;EACvD,MAAMrB,qBAAqB,GAAGkB,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,IAAIf,KAAK,GAAG,CAAC;IACb,IAAImB,GAAG,GAAGzC,WAAW,CAAC0C,OAAO,CAACL,SAAS,CAAC;IACxC,OAAOI,GAAG,KAAK,CAAC,CAAC,EAAE;MACjBnB,KAAK,EAAE;MACPmB,GAAG,GAAGzC,WAAW,CAAC0C,OAAO,CAACL,SAAS,EAAEI,GAAG,GAAGJ,SAAS,CAACM,MAAM,CAAC;IAC9D;IACA,OAAOrB,KAAK;EACd;EAEA,MAAMsB,SAAS,GAAG,IAAAC,qBAAY,EAAC7C,WAAW,EAAEoC,iBAAiB,CAAC;EAE9D,MAAMU,eAAe,GAAGF,SAAS,CAAC5B,GAAG,CAACN,QAAQ,IAC5CD,gBAAgB,CAACC,QAAQ,EAAEC,UAAU,EAAEC,MAAM,EAAEC,qBAAqB,CACtE,CAAC;EAED,OAAOiC,eAAe,CAACnB,MAAM,CAAC,CAACC,GAAG,EAAEN,KAAK,KAAKM,GAAG,GAAGN,KAAK,EAAE,CAAC,CAAC;AAC/D","ignoreList":[]}

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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