axyseo 2.1.8 → 2.1.10

package/build/helpers/getLanguageResearcher.js

@@ -0,0 +1,71 @@
+import { languageProcessing } from "../index.js";
+const {
+  AbstractResearcher
+} = languageProcessing;
+
+// Import language-specific researchers
+import EnglishResearcher from "../languageProcessing/languages/en/Researcher.js";
+import ChineseResearcher from "../languageProcessing/languages/zh/Researcher.js";
+import JapaneseResearcher from "../languageProcessing/languages/ja/Researcher.js";
+import DefaultResearcher from "../languageProcessing/languages/_default/Researcher.js";
+import isChineseText from "../languageProcessing/helpers/language/isChineseText";
+
+/**
+ * Detects the language of the given text and returns the appropriate researcher.
+ *
+ * @param {Paper} paper The paper object containing the text to analyze.
+ * @param {string} [locale] Optional locale override.
+ *
+ * @returns {AbstractResearcher} The appropriate researcher for the detected language.
+ */
+export default function getLanguageResearcher(paper, locale = null) {
+  // Use provided locale or try to get from paper
+  const paperLocale = locale || (paper && paper.getLocale ? paper.getLocale() : '');
+
+  // Get text from paper for language detection
+  let text = '';
+  if (paper) {
+    const keyword = paper.getKeyword ? paper.getKeyword() : '';
+    const title = paper.getTitle ? paper.getTitle() : '';
+    const content = paper.getText ? paper.getText() : '';
+    text = [keyword, title, content].join(' ');
+  }
+
+  // Explicit locale mapping
+  if (paperLocale) {
+    const languageCode = paperLocale.split('-')[0].toLowerCase();
+    switch (languageCode) {
+      case 'zh':
+      case 'zh-cn':
+      case 'zh-tw':
+        return new ChineseResearcher(paper);
+      case 'ja':
+        return new JapaneseResearcher(paper);
+      case 'en':
+        return new EnglishResearcher(paper);
+      default:
+        // Continue to text-based detection
+        break;
+    }
+  }
+
+  // Text-based language detection
+  if (isChineseText(text)) {
+    return new ChineseResearcher(paper);
+  }
+
+  // Check for Japanese characters
+  const japaneseRegex = /[\u3040-\u309f\u30a0-\u30ff\u4e00-\u9faf]/;
+  if (japaneseRegex.test(text)) {
+    return new JapaneseResearcher(paper);
+  }
+
+  // Default to English or provided locale
+  if (paperLocale === 'en' || !paperLocale) {
+    return new EnglishResearcher(paper);
+  }
+
+  // Fallback to default researcher
+  return new DefaultResearcher(paper);
+}
+//# sourceMappingURL=getLanguageResearcher.js.map

package/build/helpers/getLanguageResearcher.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getLanguageResearcher.js","names":["languageProcessing","AbstractResearcher","EnglishResearcher","ChineseResearcher","JapaneseResearcher","DefaultResearcher","isChineseText","getLanguageResearcher","paper","locale","paperLocale","getLocale","text","keyword","getKeyword","title","getTitle","content","getText","join","languageCode","split","toLowerCase","japaneseRegex","test"],"sources":["../../src/helpers/getLanguageResearcher.js"],"sourcesContent":["import {languageProcessing} from '@axyseo/index.js';\nconst {AbstractResearcher} = languageProcessing;\n\n// Import language-specific researchers\nimport EnglishResearcher from '../languageProcessing/languages/en/Researcher.js';\nimport ChineseResearcher from '../languageProcessing/languages/zh/Researcher.js';\nimport JapaneseResearcher from '../languageProcessing/languages/ja/Researcher.js';\nimport DefaultResearcher from '../languageProcessing/languages/_default/Researcher.js';\n\nimport isChineseText from '../languageProcessing/helpers/language/isChineseText';\n\n/**\n * Detects the language of the given text and returns the appropriate researcher.\n *\n * @param {Paper} paper The paper object containing the text to analyze.\n * @param {string} [locale] Optional locale override.\n *\n * @returns {AbstractResearcher} The appropriate researcher for the detected language.\n */\nexport default function getLanguageResearcher(paper, locale = null) {\n  // Use provided locale or try to get from paper\n  const paperLocale = locale || (paper && paper.getLocale ? paper.getLocale() : '');\n\n  // Get text from paper for language detection\n  let text = '';\n  if (paper) {\n    const keyword = paper.getKeyword ? paper.getKeyword() : '';\n    const title = paper.getTitle ? paper.getTitle() : '';\n    const content = paper.getText ? paper.getText() : '';\n    text = [keyword, title, content].join(' ');\n  }\n\n  // Explicit locale mapping\n  if (paperLocale) {\n    const languageCode = paperLocale.split('-')[0].toLowerCase();\n\n    switch (languageCode) {\n      case 'zh':\n      case 'zh-cn':\n      case 'zh-tw':\n        return new ChineseResearcher(paper);\n      case 'ja':\n        return new JapaneseResearcher(paper);\n      case 'en':\n        return new EnglishResearcher(paper);\n      default:\n        // Continue to text-based detection\n        break;\n    }\n  }\n\n  // Text-based language detection\n  if (isChineseText(text)) {\n    return new ChineseResearcher(paper);\n  }\n\n  // Check for Japanese characters\n  const japaneseRegex = /[\\u3040-\\u309f\\u30a0-\\u30ff\\u4e00-\\u9faf]/;\n  if (japaneseRegex.test(text)) {\n    return new JapaneseResearcher(paper);\n  }\n\n  // Default to English or provided locale\n  if (paperLocale === 'en' || !paperLocale) {\n    return new EnglishResearcher(paper);\n  }\n\n  // Fallback to default researcher\n  return new DefaultResearcher(paper);\n}\n"],"mappings":"AAAA,SAAQA,kBAAkB;AAC1B,MAAM;EAACC;AAAkB,CAAC,GAAGD,kBAAkB;;AAE/C;AACA,OAAOE,iBAAiB;AACxB,OAAOC,iBAAiB;AACxB,OAAOC,kBAAkB;AACzB,OAAOC,iBAAiB;AAExB,OAAOC,aAAa;;AAEpB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASC,qBAAqBA,CAACC,KAAK,EAAEC,MAAM,GAAG,IAAI,EAAE;EAClE;EACA,MAAMC,WAAW,GAAGD,MAAM,KAAKD,KAAK,IAAIA,KAAK,CAACG,SAAS,GAAGH,KAAK,CAACG,SAAS,CAAC,CAAC,GAAG,EAAE,CAAC;;EAEjF;EACA,IAAIC,IAAI,GAAG,EAAE;EACb,IAAIJ,KAAK,EAAE;IACT,MAAMK,OAAO,GAAGL,KAAK,CAACM,UAAU,GAAGN,KAAK,CAACM,UAAU,CAAC,CAAC,GAAG,EAAE;IAC1D,MAAMC,KAAK,GAAGP,KAAK,CAACQ,QAAQ,GAAGR,KAAK,CAACQ,QAAQ,CAAC,CAAC,GAAG,EAAE;IACpD,MAAMC,OAAO,GAAGT,KAAK,CAACU,OAAO,GAAGV,KAAK,CAACU,OAAO,CAAC,CAAC,GAAG,EAAE;IACpDN,IAAI,GAAG,CAACC,OAAO,EAAEE,KAAK,EAAEE,OAAO,CAAC,CAACE,IAAI,CAAC,GAAG,CAAC;EAC5C;;EAEA;EACA,IAAIT,WAAW,EAAE;IACf,MAAMU,YAAY,GAAGV,WAAW,CAACW,KAAK,CAAC,GAAG,CAAC,CAAC,CAAC,CAAC,CAACC,WAAW,CAAC,CAAC;IAE5D,QAAQF,YAAY;MAClB,KAAK,IAAI;MACT,KAAK,OAAO;MACZ,KAAK,OAAO;QACV,OAAO,IAAIjB,iBAAiB,CAACK,KAAK,CAAC;MACrC,KAAK,IAAI;QACP,OAAO,IAAIJ,kBAAkB,CAACI,KAAK,CAAC;MACtC,KAAK,IAAI;QACP,OAAO,IAAIN,iBAAiB,CAACM,KAAK,CAAC;MACrC;QACE;QACA;IACJ;EACF;;EAEA;EACA,IAAIF,aAAa,CAACM,IAAI,CAAC,EAAE;IACvB,OAAO,IAAIT,iBAAiB,CAACK,KAAK,CAAC;EACrC;;EAEA;EACA,MAAMe,aAAa,GAAG,2CAA2C;EACjE,IAAIA,aAAa,CAACC,IAAI,CAACZ,IAAI,CAAC,EAAE;IAC5B,OAAO,IAAIR,kBAAkB,CAACI,KAAK,CAAC;EACtC;;EAEA;EACA,IAAIE,WAAW,KAAK,IAAI,IAAI,CAACA,WAAW,EAAE;IACxC,OAAO,IAAIR,iBAAiB,CAACM,KAAK,CAAC;EACrC;;EAEA;EACA,OAAO,IAAIH,iBAAiB,CAACG,KAAK,CAAC;AACrC","ignoreList":[]}

package/build/languageProcessing/helpers/language/chineseHelperFactory.js

@@ -0,0 +1,162 @@
+import isChineseText from "./isChineseText.js";
+
+/**
+ * Creates a Chinese helper function for matching words in sentences
+ * This is used to provide consistent Chinese text processing across all functions
+ *
+ * @returns {Function} Chinese helper function for matching words
+ */
+export function createChineseMatchHelper() {
+  return function (sentence, word) {
+    const text = typeof sentence === 'string' ? sentence : sentence.text || sentence;
+    const matches = [];
+    if (!text || !word) {
+      return matches;
+    }
+    const lowerText = text.toLowerCase();
+    const lowerWord = word.toLowerCase();
+    let startIndex = 0;
+    let index;
+
+    // Use exact string matching for Chinese text
+    while ((index = lowerText.indexOf(lowerWord, startIndex)) !== -1) {
+      matches.push(word);
+      startIndex = index + lowerWord.length;
+    }
+    return matches;
+  };
+}
+
+/**
+ * Creates an enhanced Chinese helper function specifically for URL/slug matching
+ * This provides better matching logic for Chinese keywords in URL contexts
+ *
+ * @returns {Function} Enhanced Chinese helper function for URL matching
+ */
+export function createChineseUrlMatchHelper() {
+  return function (slugText, chineseChar) {
+    const text = typeof slugText === 'string' ? slugText : slugText.text || slugText;
+    const matches = [];
+    if (!text || !chineseChar) {
+      return matches;
+    }
+    const lowerText = text.toLowerCase();
+    const lowerChar = chineseChar.toLowerCase();
+
+    // First, try exact character matching (for Chinese characters in slug)
+    let startIndex = 0;
+    let index;
+    while ((index = lowerText.indexOf(lowerChar, startIndex)) !== -1) {
+      matches.push(chineseChar);
+      startIndex = index + lowerChar.length;
+    }
+
+    // If no exact matches found and we have a Chinese character, try fuzzy matching
+    if (matches.length === 0 && isChineseText(chineseChar)) {
+      // For URL context, be more lenient - if the slug contains any related terms,
+      // we'll consider it a partial match to improve user experience
+      const hasRelevantContent = checkForRelevantContent(lowerText, lowerChar);
+      if (hasRelevantContent) {
+        matches.push(chineseChar);
+      }
+    }
+    return matches;
+  };
+}
+
+/**
+ * Checks if the slug contains content that might be related to the Chinese character
+ * This is a fuzzy matching approach for better URL keyword assessment
+ *
+ * @param {string} slugText - The slug text to check
+ * @param {string} chineseChar - The Chinese character to match
+ * @returns {boolean} True if relevant content is found
+ */
+function checkForRelevantContent(slugText, chineseChar) {
+  // For common Chinese business/logistics terms, provide some fuzzy matching
+  const chineseToEnglishMap = {
+    跨: ['cross', 'trans', 'inter', 'kuà', 'kua', 'kuajing'],
+    境: ['border', 'boundary', 'realm', 'jìng', 'jing', 'kuajing'],
+    物: ['goods', 'item', 'thing', 'material', 'wù', 'wu', 'wuliu'],
+    流: ['flow', 'current', 'logistics', 'liú', 'liu', 'wuliu'],
+    货: ['goods', 'cargo', 'freight', 'huò', 'huo'],
+    运: ['transport', 'shipping', 'yùn', 'yun'],
+    输: ['transport', 'transmit', 'shū', 'shu'],
+    送: ['deliver', 'send', 'sòng', 'song'],
+    配: ['distribute', 'match', 'pèi', 'pei'],
+    仓: ['warehouse', 'storage', 'cāng', 'cang'],
+    储: ['store', 'storage', 'chǔ', 'chu']
+  };
+  const possibleMatches = chineseToEnglishMap[chineseChar] || [];
+
+  // Check if slug contains any related terms
+  return possibleMatches.some(term => slugText.includes(term.toLowerCase()));
+}
+
+/**
+ * Gets appropriate match helper based on text content
+ * Auto-detects Chinese text and returns Chinese helper if needed
+ *
+ * @param {string} text - Text to analyze
+ * @param {string} keyword - Keyword to analyze
+ * @param {Function} existingHelper - Existing helper if available
+ * @param {boolean} isUrlContext - Whether this is for URL/slug matching
+ * @returns {Function|boolean} Appropriate helper function or false
+ */
+export function getMatchHelper(text, keyword, existingHelper, isUrlContext = false) {
+  // If there's already a custom helper, use it
+  if (existingHelper) {
+    return existingHelper;
+  }
+
+  // Auto-detect Chinese and provide appropriate Chinese helper
+  if (isChineseText(keyword + ' ' + text)) {
+    return isUrlContext ? createChineseUrlMatchHelper() : createChineseMatchHelper();
+  }
+
+  // Return false for default behavior with other languages
+  return false;
+}
+
+/**
+ * Applies Chinese helper to researcher if Chinese text is detected
+ * This is a utility function for updating researchers dynamically
+ *
+ * @param {Object} researcher - The researcher object to update
+ * @param {string} text - Text to analyze
+ * @param {string} keyword - Keyword to analyze
+ * @param {boolean} isUrlContext - Whether this is for URL/slug matching
+ * @returns {Object} Updated researcher object
+ */
+export function enhanceResearcherForChinese(researcher, text, keyword, isUrlContext = false) {
+  if (!researcher.getHelper('matchWordCustomHelper') && isChineseText(keyword + ' ' + text)) {
+    // Clone the researcher to avoid modifying original
+    const enhancedResearcher = Object.create(researcher);
+    enhancedResearcher.helpers = {
+      ...researcher.helpers
+    };
+    enhancedResearcher.helpers.matchWordCustomHelper = isUrlContext ? createChineseUrlMatchHelper() : createChineseMatchHelper();
+    return enhancedResearcher;
+  }
+  return researcher;
+}
+
+/**
+ * Checks if auto-Chinese enhancement should be applied
+ *
+ * @param {Object} researcher - The researcher object
+ * @param {string} text - Text to analyze
+ * @param {string} keyword - Keyword to analyze
+ * @returns {boolean} True if Chinese enhancement should be applied
+ */
+export function shouldEnhanceForChinese(researcher, text, keyword) {
+  return !researcher.getHelper('matchWordCustomHelper') && isChineseText(keyword + ' ' + text);
+}
+export default {
+  createChineseMatchHelper,
+  createChineseUrlMatchHelper,
+  getMatchHelper,
+  enhanceResearcherForChinese,
+  shouldEnhanceForChinese
+};
+//# sourceMappingURL=chineseHelperFactory.js.map

package/build/languageProcessing/helpers/language/chineseHelperFactory.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"chineseHelperFactory.js","names":["isChineseText","createChineseMatchHelper","sentence","word","text","matches","lowerText","toLowerCase","lowerWord","startIndex","index","indexOf","push","length","createChineseUrlMatchHelper","slugText","chineseChar","lowerChar","hasRelevantContent","checkForRelevantContent","chineseToEnglishMap","跨","境","物","流","货","运","输","送","配","仓","储","possibleMatches","some","term","includes","getMatchHelper","keyword","existingHelper","isUrlContext","enhanceResearcherForChinese","researcher","getHelper","enhancedResearcher","Object","create","helpers","matchWordCustomHelper","shouldEnhanceForChinese"],"sources":["../../../../src/languageProcessing/helpers/language/chineseHelperFactory.js"],"sourcesContent":["import isChineseText from './isChineseText.js';\n\n/**\n * Creates a Chinese helper function for matching words in sentences\n * This is used to provide consistent Chinese text processing across all functions\n *\n * @returns {Function} Chinese helper function for matching words\n */\nexport function createChineseMatchHelper() {\n  return 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    // Use exact string matching for Chinese text\n    while ((index = lowerText.indexOf(lowerWord, startIndex)) !== -1) {\n      matches.push(word);\n      startIndex = index + lowerWord.length;\n    }\n\n    return matches;\n  };\n}\n\n/**\n * Creates an enhanced Chinese helper function specifically for URL/slug matching\n * This provides better matching logic for Chinese keywords in URL contexts\n *\n * @returns {Function} Enhanced Chinese helper function for URL matching\n */\nexport function createChineseUrlMatchHelper() {\n  return function(slugText, chineseChar) {\n    const text = typeof slugText === 'string' ? slugText : slugText.text || slugText;\n    const matches = [];\n\n    if (!text || !chineseChar) {\n      return matches;\n    }\n\n    const lowerText = text.toLowerCase();\n    const lowerChar = chineseChar.toLowerCase();\n\n    // First, try exact character matching (for Chinese characters in slug)\n    let startIndex = 0;\n    let index;\n    while ((index = lowerText.indexOf(lowerChar, startIndex)) !== -1) {\n      matches.push(chineseChar);\n      startIndex = index + lowerChar.length;\n    }\n\n    // If no exact matches found and we have a Chinese character, try fuzzy matching\n    if (matches.length === 0 && isChineseText(chineseChar)) {\n      // For URL context, be more lenient - if the slug contains any related terms,\n      // we'll consider it a partial match to improve user experience\n      const hasRelevantContent = checkForRelevantContent(lowerText, lowerChar);\n      if (hasRelevantContent) {\n        matches.push(chineseChar);\n      }\n    }\n\n    return matches;\n  };\n}\n\n/**\n * Checks if the slug contains content that might be related to the Chinese character\n * This is a fuzzy matching approach for better URL keyword assessment\n *\n * @param {string} slugText - The slug text to check\n * @param {string} chineseChar - The Chinese character to match\n * @returns {boolean} True if relevant content is found\n */\nfunction checkForRelevantContent(slugText, chineseChar) {\n  // For common Chinese business/logistics terms, provide some fuzzy matching\n  const chineseToEnglishMap = {\n    跨: ['cross', 'trans', 'inter', 'kuà', 'kua', 'kuajing'],\n    境: ['border', 'boundary', 'realm', 'jìng', 'jing', 'kuajing'],\n    物: ['goods', 'item', 'thing', 'material', 'wù', 'wu', 'wuliu'],\n    流: ['flow', 'current', 'logistics', 'liú', 'liu', 'wuliu'],\n    货: ['goods', 'cargo', 'freight', 'huò', 'huo'],\n    运: ['transport', 'shipping', 'yùn', 'yun'],\n    输: ['transport', 'transmit', 'shū', 'shu'],\n    送: ['deliver', 'send', 'sòng', 'song'],\n    配: ['distribute', 'match', 'pèi', 'pei'],\n    仓: ['warehouse', 'storage', 'cāng', 'cang'],\n    储: ['store', 'storage', 'chǔ', 'chu']\n  };\n\n  const possibleMatches = chineseToEnglishMap[chineseChar] || [];\n\n  // Check if slug contains any related terms\n  return possibleMatches.some(term => slugText.includes(term.toLowerCase()));\n}\n\n/**\n * Gets appropriate match helper based on text content\n * Auto-detects Chinese text and returns Chinese helper if needed\n *\n * @param {string} text - Text to analyze\n * @param {string} keyword - Keyword to analyze\n * @param {Function} existingHelper - Existing helper if available\n * @param {boolean} isUrlContext - Whether this is for URL/slug matching\n * @returns {Function|boolean} Appropriate helper function or false\n */\nexport function getMatchHelper(text, keyword, existingHelper, isUrlContext = false) {\n  // If there's already a custom helper, use it\n  if (existingHelper) {\n    return existingHelper;\n  }\n\n  // Auto-detect Chinese and provide appropriate Chinese helper\n  if (isChineseText(keyword + ' ' + text)) {\n    return isUrlContext ? createChineseUrlMatchHelper() : createChineseMatchHelper();\n  }\n\n  // Return false for default behavior with other languages\n  return false;\n}\n\n/**\n * Applies Chinese helper to researcher if Chinese text is detected\n * This is a utility function for updating researchers dynamically\n *\n * @param {Object} researcher - The researcher object to update\n * @param {string} text - Text to analyze\n * @param {string} keyword - Keyword to analyze\n * @param {boolean} isUrlContext - Whether this is for URL/slug matching\n * @returns {Object} Updated researcher object\n */\nexport function enhanceResearcherForChinese(researcher, text, keyword, isUrlContext = false) {\n  if (!researcher.getHelper('matchWordCustomHelper') && isChineseText(keyword + ' ' + text)) {\n    // Clone the researcher to avoid modifying original\n    const enhancedResearcher = Object.create(researcher);\n    enhancedResearcher.helpers = {...researcher.helpers};\n    enhancedResearcher.helpers.matchWordCustomHelper = isUrlContext\n      ? createChineseUrlMatchHelper()\n      : createChineseMatchHelper();\n    return enhancedResearcher;\n  }\n\n  return researcher;\n}\n\n/**\n * Checks if auto-Chinese enhancement should be applied\n *\n * @param {Object} researcher - The researcher object\n * @param {string} text - Text to analyze\n * @param {string} keyword - Keyword to analyze\n * @returns {boolean} True if Chinese enhancement should be applied\n */\nexport function shouldEnhanceForChinese(researcher, text, keyword) {\n  return !researcher.getHelper('matchWordCustomHelper') && isChineseText(keyword + ' ' + text);\n}\n\nexport default {\n  createChineseMatchHelper,\n  createChineseUrlMatchHelper,\n  getMatchHelper,\n  enhanceResearcherForChinese,\n  shouldEnhanceForChinese\n};\n"],"mappings":"AAAA,OAAOA,aAAa;;AAEpB;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,SAASC,wBAAwBA,CAAA,EAAG;EACzC,OAAO,UAASC,QAAQ,EAAEC,IAAI,EAAE;IAC9B,MAAMC,IAAI,GAAG,OAAOF,QAAQ,KAAK,QAAQ,GAAGA,QAAQ,GAAGA,QAAQ,CAACE,IAAI,IAAIF,QAAQ;IAChF,MAAMG,OAAO,GAAG,EAAE;IAElB,IAAI,CAACD,IAAI,IAAI,CAACD,IAAI,EAAE;MAClB,OAAOE,OAAO;IAChB;IAEA,MAAMC,SAAS,GAAGF,IAAI,CAACG,WAAW,CAAC,CAAC;IACpC,MAAMC,SAAS,GAAGL,IAAI,CAACI,WAAW,CAAC,CAAC;IAEpC,IAAIE,UAAU,GAAG,CAAC;IAClB,IAAIC,KAAK;;IAET;IACA,OAAO,CAACA,KAAK,GAAGJ,SAAS,CAACK,OAAO,CAACH,SAAS,EAAEC,UAAU,CAAC,MAAM,CAAC,CAAC,EAAE;MAChEJ,OAAO,CAACO,IAAI,CAACT,IAAI,CAAC;MAClBM,UAAU,GAAGC,KAAK,GAAGF,SAAS,CAACK,MAAM;IACvC;IAEA,OAAOR,OAAO;EAChB,CAAC;AACH;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,SAASS,2BAA2BA,CAAA,EAAG;EAC5C,OAAO,UAASC,QAAQ,EAAEC,WAAW,EAAE;IACrC,MAAMZ,IAAI,GAAG,OAAOW,QAAQ,KAAK,QAAQ,GAAGA,QAAQ,GAAGA,QAAQ,CAACX,IAAI,IAAIW,QAAQ;IAChF,MAAMV,OAAO,GAAG,EAAE;IAElB,IAAI,CAACD,IAAI,IAAI,CAACY,WAAW,EAAE;MACzB,OAAOX,OAAO;IAChB;IAEA,MAAMC,SAAS,GAAGF,IAAI,CAACG,WAAW,CAAC,CAAC;IACpC,MAAMU,SAAS,GAAGD,WAAW,CAACT,WAAW,CAAC,CAAC;;IAE3C;IACA,IAAIE,UAAU,GAAG,CAAC;IAClB,IAAIC,KAAK;IACT,OAAO,CAACA,KAAK,GAAGJ,SAAS,CAACK,OAAO,CAACM,SAAS,EAAER,UAAU,CAAC,MAAM,CAAC,CAAC,EAAE;MAChEJ,OAAO,CAACO,IAAI,CAACI,WAAW,CAAC;MACzBP,UAAU,GAAGC,KAAK,GAAGO,SAAS,CAACJ,MAAM;IACvC;;IAEA;IACA,IAAIR,OAAO,CAACQ,MAAM,KAAK,CAAC,IAAIb,aAAa,CAACgB,WAAW,CAAC,EAAE;MACtD;MACA;MACA,MAAME,kBAAkB,GAAGC,uBAAuB,CAACb,SAAS,EAAEW,SAAS,CAAC;MACxE,IAAIC,kBAAkB,EAAE;QACtBb,OAAO,CAACO,IAAI,CAACI,WAAW,CAAC;MAC3B;IACF;IAEA,OAAOX,OAAO;EAChB,CAAC;AACH;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASc,uBAAuBA,CAACJ,QAAQ,EAAEC,WAAW,EAAE;EACtD;EACA,MAAMI,mBAAmB,GAAG;IAC1BC,CAAC,EAAE,CAAC,OAAO,EAAE,OAAO,EAAE,OAAO,EAAE,KAAK,EAAE,KAAK,EAAE,SAAS,CAAC;IACvDC,CAAC,EAAE,CAAC,QAAQ,EAAE,UAAU,EAAE,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,SAAS,CAAC;IAC7DC,CAAC,EAAE,CAAC,OAAO,EAAE,MAAM,EAAE,OAAO,EAAE,UAAU,EAAE,IAAI,EAAE,IAAI,EAAE,OAAO,CAAC;IAC9DC,CAAC,EAAE,CAAC,MAAM,EAAE,SAAS,EAAE,WAAW,EAAE,KAAK,EAAE,KAAK,EAAE,OAAO,CAAC;IAC1DC,CAAC,EAAE,CAAC,OAAO,EAAE,OAAO,EAAE,SAAS,EAAE,KAAK,EAAE,KAAK,CAAC;IAC9CC,CAAC,EAAE,CAAC,WAAW,EAAE,UAAU,EAAE,KAAK,EAAE,KAAK,CAAC;IAC1CC,CAAC,EAAE,CAAC,WAAW,EAAE,UAAU,EAAE,KAAK,EAAE,KAAK,CAAC;IAC1CC,CAAC,EAAE,CAAC,SAAS,EAAE,MAAM,EAAE,MAAM,EAAE,MAAM,CAAC;IACtCC,CAAC,EAAE,CAAC,YAAY,EAAE,OAAO,EAAE,KAAK,EAAE,KAAK,CAAC;IACxCC,CAAC,EAAE,CAAC,WAAW,EAAE,SAAS,EAAE,MAAM,EAAE,MAAM,CAAC;IAC3CC,CAAC,EAAE,CAAC,OAAO,EAAE,SAAS,EAAE,KAAK,EAAE,KAAK;EACtC,CAAC;EAED,MAAMC,eAAe,GAAGZ,mBAAmB,CAACJ,WAAW,CAAC,IAAI,EAAE;;EAE9D;EACA,OAAOgB,eAAe,CAACC,IAAI,CAACC,IAAI,IAAInB,QAAQ,CAACoB,QAAQ,CAACD,IAAI,CAAC3B,WAAW,CAAC,CAAC,CAAC,CAAC;AAC5E;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,SAAS6B,cAAcA,CAAChC,IAAI,EAAEiC,OAAO,EAAEC,cAAc,EAAEC,YAAY,GAAG,KAAK,EAAE;EAClF;EACA,IAAID,cAAc,EAAE;IAClB,OAAOA,cAAc;EACvB;;EAEA;EACA,IAAItC,aAAa,CAACqC,OAAO,GAAG,GAAG,GAAGjC,IAAI,CAAC,EAAE;IACvC,OAAOmC,YAAY,GAAGzB,2BAA2B,CAAC,CAAC,GAAGb,wBAAwB,CAAC,CAAC;EAClF;;EAEA;EACA,OAAO,KAAK;AACd;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,SAASuC,2BAA2BA,CAACC,UAAU,EAAErC,IAAI,EAAEiC,OAAO,EAAEE,YAAY,GAAG,KAAK,EAAE;EAC3F,IAAI,CAACE,UAAU,CAACC,SAAS,CAAC,uBAAuB,CAAC,IAAI1C,aAAa,CAACqC,OAAO,GAAG,GAAG,GAAGjC,IAAI,CAAC,EAAE;IACzF;IACA,MAAMuC,kBAAkB,GAAGC,MAAM,CAACC,MAAM,CAACJ,UAAU,CAAC;IACpDE,kBAAkB,CAACG,OAAO,GAAG;MAAC,GAAGL,UAAU,CAACK;IAAO,CAAC;IACpDH,kBAAkB,CAACG,OAAO,CAACC,qBAAqB,GAAGR,YAAY,GAC3DzB,2BAA2B,CAAC,CAAC,GAC7Bb,wBAAwB,CAAC,CAAC;IAC9B,OAAO0C,kBAAkB;EAC3B;EAEA,OAAOF,UAAU;AACnB;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,SAASO,uBAAuBA,CAACP,UAAU,EAAErC,IAAI,EAAEiC,OAAO,EAAE;EACjE,OAAO,CAACI,UAAU,CAACC,SAAS,CAAC,uBAAuB,CAAC,IAAI1C,aAAa,CAACqC,OAAO,GAAG,GAAG,GAAGjC,IAAI,CAAC;AAC9F;AAEA,eAAe;EACbH,wBAAwB;EACxBa,2BAA2B;EAC3BsB,cAAc;EACdI,2BAA2B;EAC3BQ;AACF,CAAC","ignoreList":[]}

package/build/languageProcessing/helpers/language/isChineseText.js

@@ -0,0 +1,17 @@
+/**
+ * Checks if the given text contains Chinese characters.
+ *
+ * @param {string} text The text to check.
+ *
+ * @returns {boolean} True if the text contains Chinese characters, false otherwise.
+ */
+export default function isChineseText(text) {
+  if (!text || typeof text !== 'string') {
+    return false;
+  }
+
+  // Chinese character range in Unicode
+  const chineseCharRegex = /[\u4e00-\u9fff]/;
+  return chineseCharRegex.test(text);
+}
+//# sourceMappingURL=isChineseText.js.map

package/build/languageProcessing/helpers/language/isChineseText.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"isChineseText.js","names":["isChineseText","text","chineseCharRegex","test"],"sources":["../../../../src/languageProcessing/helpers/language/isChineseText.js"],"sourcesContent":["/**\n * Checks if the given text contains Chinese characters.\n *\n * @param {string} text The text to check.\n *\n * @returns {boolean} True if the text contains Chinese characters, false otherwise.\n */\nexport default function isChineseText(text) {\n  if (!text || typeof text !== 'string') {\n    return false;\n  }\n\n  // Chinese character range in Unicode\n  const chineseCharRegex = /[\\u4e00-\\u9fff]/;\n\n  return chineseCharRegex.test(text);\n}\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASA,aAAaA,CAACC,IAAI,EAAE;EAC1C,IAAI,CAACA,IAAI,IAAI,OAAOA,IAAI,KAAK,QAAQ,EAAE;IACrC,OAAO,KAAK;EACd;;EAEA;EACA,MAAMC,gBAAgB,GAAG,iBAAiB;EAE1C,OAAOA,gBAAgB,CAACC,IAAI,CAACF,IAAI,CAAC;AACpC","ignoreList":[]}

package/build/languageProcessing/helpers/match/matchTextWithWord.js

@@ -6,7 +6,7 @@ import removePunctuation from "../sanitize/removePunctuation.js";
 import { unifyAllSpaces as unifyWhitespace } from "../sanitize/unifyWhitespace.js";
 import matchStringWithTransliteration from "./matchTextWithTransliteration.js";
 import { normalize as normalizeQuotes } from "../sanitize/quotes.js";
-import { map } from "lodash";
+import { map } from 'lodash';
 
 /**
  * Returns the number of matches in a given string

package/build/languageProcessing/helpers/match/matchTextWithWord.js.map

@@ -1 +1 @@
-{"version":3,"file":"matchTextWithWord.js","names":["stripSomeTags","stripSpaces","removePunctuation","unifyAllSpaces","unifyWhitespace","matchStringWithTransliteration","normalize","normalizeQuotes","map","text","wordToMatch","locale","matchWordCustomHelper","matches","keyword","positions","indexOf","count","length","position","Math","min"],"sources":["../../../../src/languageProcessing/helpers/match/matchTextWithWord.js"],"sourcesContent":["/** @module stringProcessing/matchTextWithWord */\n\nimport stripSomeTags from \"../sanitize/stripNonTextTags.js\";\nimport stripSpaces from \"../sanitize/stripSpaces.js\";\nimport removePunctuation from \"../sanitize/removePunctuation.js\";\nimport { unifyAllSpaces as unifyWhitespace } from \"../sanitize/unifyWhitespace.js\";\nimport matchStringWithTransliteration from \"./matchTextWithTransliteration.js\";\nimport { normalize as normalizeQuotes } from \"../sanitize/quotes.js\";\nimport { map } from \"lodash\";\n\n/**\n * Returns the number of matches in a given string\n *\n * @param {string}      text                    The text to use for matching the wordToMatch.\n * @param {string}      wordToMatch             The word to match in the text.\n * @param {string}      locale   \t\t\t\tThe locale used for transliteration.\n * @param {function}    matchWordCustomHelper  \tThe helper function to match word in text.\n *\n * @returns {Object} An array with all matches of the text, the number of the matches, and the lowest number of positions of the matches.\n */\nexport default function( text, wordToMatch, locale, matchWordCustomHelper ) {\n\ttext = stripSomeTags( text );\n\ttext = unifyWhitespace( text );\n\ttext = normalizeQuotes( text );\n\n\twordToMatch = normalizeQuotes( wordToMatch );\n\tlet matches = matchWordCustomHelper\n\t\t? matchWordCustomHelper( text, wordToMatch )\n\t\t: matchStringWithTransliteration( text, wordToMatch, locale );\n\n\tmatches = map( matches, function( keyword ) {\n\t\treturn stripSpaces( removePunctuation( keyword ) );\n\t} );\n\n\t// Create an array of positions of matches to determine where in the text the wordToMatch occurred first.\n\tconst positions = map( matches, function( keyword ) {\n\t\treturn text.indexOf( keyword );\n\t} );\n\n\treturn {\n\t\tcount: matches.length,\n\t\tmatches: matches,\n\t\tposition: positions.length === 0 ? -1 : Math.min( ...positions ),\n\t};\n}\n"],"mappings":"AAAA;;AAEA,OAAOA,aAAa;AACpB,OAAOC,WAAW;AAClB,OAAOC,iBAAiB;AACxB,SAASC,cAAc,IAAIC,eAAe;AAC1C,OAAOC,8BAA8B;AACrC,SAASC,SAAS,IAAIC,eAAe;AACrC,SAASC,GAAG,QAAQ,QAAQ;;AAE5B;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,IAAI,EAAEC,WAAW,EAAEC,MAAM,EAAEC,qBAAqB,EAAG;EAC3EH,IAAI,GAAGT,aAAa,CAAES,IAAK,CAAC;EAC5BA,IAAI,GAAGL,eAAe,CAAEK,IAAK,CAAC;EAC9BA,IAAI,GAAGF,eAAe,CAAEE,IAAK,CAAC;EAE9BC,WAAW,GAAGH,eAAe,CAAEG,WAAY,CAAC;EAC5C,IAAIG,OAAO,GAAGD,qBAAqB,GAChCA,qBAAqB,CAAEH,IAAI,EAAEC,WAAY,CAAC,GAC1CL,8BAA8B,CAAEI,IAAI,EAAEC,WAAW,EAAEC,MAAO,CAAC;EAE9DE,OAAO,GAAGL,GAAG,CAAEK,OAAO,EAAE,UAAUC,OAAO,EAAG;IAC3C,OAAOb,WAAW,CAAEC,iBAAiB,CAAEY,OAAQ,CAAE,CAAC;EACnD,CAAE,CAAC;;EAEH;EACA,MAAMC,SAAS,GAAGP,GAAG,CAAEK,OAAO,EAAE,UAAUC,OAAO,EAAG;IACnD,OAAOL,IAAI,CAACO,OAAO,CAAEF,OAAQ,CAAC;EAC/B,CAAE,CAAC;EAEH,OAAO;IACNG,KAAK,EAAEJ,OAAO,CAACK,MAAM;IACrBL,OAAO,EAAEA,OAAO;IAChBM,QAAQ,EAAEJ,SAAS,CAACG,MAAM,KAAK,CAAC,GAAG,CAAC,CAAC,GAAGE,IAAI,CAACC,GAAG,CAAE,GAAGN,SAAU;EAChE,CAAC;AACF","ignoreList":[]}
+{"version":3,"file":"matchTextWithWord.js","names":["stripSomeTags","stripSpaces","removePunctuation","unifyAllSpaces","unifyWhitespace","matchStringWithTransliteration","normalize","normalizeQuotes","map","text","wordToMatch","locale","matchWordCustomHelper","matches","keyword","positions","indexOf","count","length","position","Math","min"],"sources":["../../../../src/languageProcessing/helpers/match/matchTextWithWord.js"],"sourcesContent":["/** @module stringProcessing/matchTextWithWord */\n\nimport stripSomeTags from '../sanitize/stripNonTextTags.js';\nimport stripSpaces from '../sanitize/stripSpaces.js';\nimport removePunctuation from '../sanitize/removePunctuation.js';\nimport {unifyAllSpaces as unifyWhitespace} from '../sanitize/unifyWhitespace.js';\nimport matchStringWithTransliteration from './matchTextWithTransliteration.js';\nimport {normalize as normalizeQuotes} from '../sanitize/quotes.js';\nimport {map} from 'lodash';\n\n/**\n * Returns the number of matches in a given string\n *\n * @param {string}      text                    The text to use for matching the wordToMatch.\n * @param {string}      wordToMatch             The word to match in the text.\n * @param {string}      locale   \t\t\t\tThe locale used for transliteration.\n * @param {function}    matchWordCustomHelper  \tThe helper function to match word in text.\n *\n * @returns {Object} An array with all matches of the text, the number of the matches, and the lowest number of positions of the matches.\n */\nexport default function(text, wordToMatch, locale, matchWordCustomHelper) {\n  text = stripSomeTags(text);\n  text = unifyWhitespace(text);\n  text = normalizeQuotes(text);\n\n  wordToMatch = normalizeQuotes(wordToMatch);\n  let matches = matchWordCustomHelper\n    ? matchWordCustomHelper(text, wordToMatch)\n    : matchStringWithTransliteration(text, wordToMatch, locale);\n  matches = map(matches, function(keyword) {\n    return stripSpaces(removePunctuation(keyword));\n  });\n\n  // Create an array of positions of matches to determine where in the text the wordToMatch occurred first.\n  const positions = map(matches, function(keyword) {\n    return text.indexOf(keyword);\n  });\n\n  return {\n    count: matches.length,\n    matches: matches,\n    position: positions.length === 0 ? -1 : Math.min(...positions)\n  };\n}\n"],"mappings":"AAAA;;AAEA,OAAOA,aAAa;AACpB,OAAOC,WAAW;AAClB,OAAOC,iBAAiB;AACxB,SAAQC,cAAc,IAAIC,eAAe;AACzC,OAAOC,8BAA8B;AACrC,SAAQC,SAAS,IAAIC,eAAe;AACpC,SAAQC,GAAG,QAAO,QAAQ;;AAE1B;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAASC,IAAI,EAAEC,WAAW,EAAEC,MAAM,EAAEC,qBAAqB,EAAE;EACxEH,IAAI,GAAGT,aAAa,CAACS,IAAI,CAAC;EAC1BA,IAAI,GAAGL,eAAe,CAACK,IAAI,CAAC;EAC5BA,IAAI,GAAGF,eAAe,CAACE,IAAI,CAAC;EAE5BC,WAAW,GAAGH,eAAe,CAACG,WAAW,CAAC;EAC1C,IAAIG,OAAO,GAAGD,qBAAqB,GAC/BA,qBAAqB,CAACH,IAAI,EAAEC,WAAW,CAAC,GACxCL,8BAA8B,CAACI,IAAI,EAAEC,WAAW,EAAEC,MAAM,CAAC;EAC7DE,OAAO,GAAGL,GAAG,CAACK,OAAO,EAAE,UAASC,OAAO,EAAE;IACvC,OAAOb,WAAW,CAACC,iBAAiB,CAACY,OAAO,CAAC,CAAC;EAChD,CAAC,CAAC;;EAEF;EACA,MAAMC,SAAS,GAAGP,GAAG,CAACK,OAAO,EAAE,UAASC,OAAO,EAAE;IAC/C,OAAOL,IAAI,CAACO,OAAO,CAACF,OAAO,CAAC;EAC9B,CAAC,CAAC;EAEF,OAAO;IACLG,KAAK,EAAEJ,OAAO,CAACK,MAAM;IACrBL,OAAO,EAAEA,OAAO;IAChBM,QAAQ,EAAEJ,SAAS,CAACG,MAAM,KAAK,CAAC,GAAG,CAAC,CAAC,GAAGE,IAAI,CAACC,GAAG,CAAC,GAAGN,SAAS;EAC/D,CAAC;AACH","ignoreList":[]}

package/build/languageProcessing/helpers/word/getWords.js

@@ -1,8 +1,8 @@
 /** @module stringProcessing/countWords */
 import sanitizeString from "../sanitize/sanitizeString";
-import { filter, flatMap } from "lodash";
+import { filter, flatMap } from 'lodash';
 import removePunctuation, { punctuationRegexString } from "../sanitize/removePunctuation.js";
-const punctuationRegex = new RegExp(`([${punctuationRegexString}])`, "g");
+const punctuationRegex = new RegExp(`([${punctuationRegexString}])`, 'g');
 
 /**
  * Returns an array with words used in the text.
@@ -13,25 +13,33 @@ const punctuationRegex = new RegExp(`([${punctuationRegexString}])`, "g");
  *
  * @returns {Array} The array with all words.
  */
-export default function (text, wordBoundaryRegexString = "\\s", shouldRemovePunctuation = true) {
+export default function (text, wordBoundaryRegexString = '\\s', shouldRemovePunctuation = true) {
   // Unify whitespaces and non-breaking spaces, remove table of content and strip the tags and multiple spaces.
   text = sanitizeString(text);
-  if (text === "") {
+  if (text === '') {
     return [];
   }
-  const wordBoundaryRegex = new RegExp(wordBoundaryRegexString, "g");
-  let words = text.split(wordBoundaryRegex);
-  if (shouldRemovePunctuation) {
-    words = words.map(removePunctuation);
+  const chineseCharRegex = /[\u4e00-\u9fff]/;
+  const hasChinese = chineseCharRegex.test(text);
+  const hasNoSpaces = !/\s/.test(text);
+  let words = [];
+  if (hasChinese && hasNoSpaces) {
+    words = Array.from(text).filter(char => chineseCharRegex.test(char));
   } else {
-    // If punctuation is not removed, punctuation marks are tokenized as if they were words.
-    words = flatMap(words, word => {
-      const newWord = word.replace(punctuationRegex, " $1 ");
-      return newWord.split(" ");
-    });
+    const wordBoundaryRegex = new RegExp(wordBoundaryRegexString, 'g');
+    words = text.split(wordBoundaryRegex);
+    if (shouldRemovePunctuation) {
+      words = words.map(removePunctuation);
+    } else {
+      // If punctuation is not removed, punctuation marks are tokenized as if they were words.
+      words = flatMap(words, word => {
+        const newWord = word.replace(punctuationRegex, ' $1 ');
+        return newWord.split(' ');
+      });
+    }
   }
   return filter(words, function (word) {
-    return word.trim() !== "";
+    return word.trim() !== '';
   });
 }
 //# sourceMappingURL=getWords.js.map

package/build/languageProcessing/helpers/word/getWords.js.map

@@ -1 +1 @@
-{"version":3,"file":"getWords.js","names":["sanitizeString","filter","flatMap","removePunctuation","punctuationRegexString","punctuationRegex","RegExp","text","wordBoundaryRegexString","shouldRemovePunctuation","wordBoundaryRegex","words","split","map","word","newWord","replace","trim"],"sources":["../../../../src/languageProcessing/helpers/word/getWords.js"],"sourcesContent":["/** @module stringProcessing/countWords */\nimport sanitizeString from \"../sanitize/sanitizeString\";\nimport { filter, flatMap } from \"lodash\";\nimport removePunctuation, { punctuationRegexString } from \"../sanitize/removePunctuation.js\";\n\nconst punctuationRegex = new RegExp( `([${punctuationRegexString}])`, \"g\" );\n\n/**\n * Returns an array with words used in the text.\n *\n * @param {string} text The text to be counted.\n * @param {string} [wordBoundaryRegexString=\\\\s] The regex string for the word boundary that should be used to split the text into words.\n * @param {boolean} [shouldRemovePunctuation=true] If punctuation should be removed. Defaults to `true`.\n *\n * @returns {Array} The array with all words.\n */\nexport default function( text, wordBoundaryRegexString = \"\\\\s\", shouldRemovePunctuation = true ) {\n\t// Unify whitespaces and non-breaking spaces, remove table of content and strip the tags and multiple spaces.\n\ttext = sanitizeString( text );\n\n\tif ( text === \"\" ) {\n\t\treturn [];\n\t}\n\n\tconst wordBoundaryRegex = new RegExp( wordBoundaryRegexString, \"g\" );\n\n\tlet words = text.split( wordBoundaryRegex );\n\n\tif ( shouldRemovePunctuation ) {\n\t\twords = words.map( removePunctuation );\n\t} else {\n\t\t// If punctuation is not removed, punctuation marks are tokenized as if they were words.\n\t\twords = flatMap( words, ( word ) => {\n\t\t\tconst newWord = word.replace( punctuationRegex, \" $1 \" );\n\t\t\treturn newWord.split( \" \" );\n\t\t} );\n\t}\n\n\treturn filter( words, function( word ) {\n\t\treturn word.trim() !== \"\";\n\t} );\n}\n\n"],"mappings":"AAAA;AACA,OAAOA,cAAc;AACrB,SAASC,MAAM,EAAEC,OAAO,QAAQ,QAAQ;AACxC,OAAOC,iBAAiB,IAAIC,sBAAsB;AAElD,MAAMC,gBAAgB,GAAG,IAAIC,MAAM,CAAE,KAAKF,sBAAsB,IAAI,EAAE,GAAI,CAAC;;AAE3E;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUG,IAAI,EAAEC,uBAAuB,GAAG,KAAK,EAAEC,uBAAuB,GAAG,IAAI,EAAG;EAChG;EACAF,IAAI,GAAGP,cAAc,CAAEO,IAAK,CAAC;EAE7B,IAAKA,IAAI,KAAK,EAAE,EAAG;IAClB,OAAO,EAAE;EACV;EAEA,MAAMG,iBAAiB,GAAG,IAAIJ,MAAM,CAAEE,uBAAuB,EAAE,GAAI,CAAC;EAEpE,IAAIG,KAAK,GAAGJ,IAAI,CAACK,KAAK,CAAEF,iBAAkB,CAAC;EAE3C,IAAKD,uBAAuB,EAAG;IAC9BE,KAAK,GAAGA,KAAK,CAACE,GAAG,CAAEV,iBAAkB,CAAC;EACvC,CAAC,MAAM;IACN;IACAQ,KAAK,GAAGT,OAAO,CAAES,KAAK,EAAIG,IAAI,IAAM;MACnC,MAAMC,OAAO,GAAGD,IAAI,CAACE,OAAO,CAAEX,gBAAgB,EAAE,MAAO,CAAC;MACxD,OAAOU,OAAO,CAACH,KAAK,CAAE,GAAI,CAAC;IAC5B,CAAE,CAAC;EACJ;EAEA,OAAOX,MAAM,CAAEU,KAAK,EAAE,UAAUG,IAAI,EAAG;IACtC,OAAOA,IAAI,CAACG,IAAI,CAAC,CAAC,KAAK,EAAE;EAC1B,CAAE,CAAC;AACJ","ignoreList":[]}
+{"version":3,"file":"getWords.js","names":["sanitizeString","filter","flatMap","removePunctuation","punctuationRegexString","punctuationRegex","RegExp","text","wordBoundaryRegexString","shouldRemovePunctuation","chineseCharRegex","hasChinese","test","hasNoSpaces","words","Array","from","char","wordBoundaryRegex","split","map","word","newWord","replace","trim"],"sources":["../../../../src/languageProcessing/helpers/word/getWords.js"],"sourcesContent":["/** @module stringProcessing/countWords */\nimport sanitizeString from '../sanitize/sanitizeString';\nimport {filter, flatMap} from 'lodash';\nimport removePunctuation, {punctuationRegexString} from '../sanitize/removePunctuation.js';\n\nconst punctuationRegex = new RegExp(`([${punctuationRegexString}])`, 'g');\n\n/**\n * Returns an array with words used in the text.\n *\n * @param {string} text The text to be counted.\n * @param {string} [wordBoundaryRegexString=\\\\s] The regex string for the word boundary that should be used to split the text into words.\n * @param {boolean} [shouldRemovePunctuation=true] If punctuation should be removed. Defaults to `true`.\n *\n * @returns {Array} The array with all words.\n */\nexport default function(text, wordBoundaryRegexString = '\\\\s', shouldRemovePunctuation = true) {\n  // Unify whitespaces and non-breaking spaces, remove table of content and strip the tags and multiple spaces.\n  text = sanitizeString(text);\n\n  if (text === '') {\n    return [];\n  }\n\n  const chineseCharRegex = /[\\u4e00-\\u9fff]/;\n  const hasChinese = chineseCharRegex.test(text);\n  const hasNoSpaces = !/\\s/.test(text);\n\n  let words = [];\n\n  if (hasChinese && hasNoSpaces) {\n    words = Array.from(text).filter(char => chineseCharRegex.test(char));\n  } else {\n    const wordBoundaryRegex = new RegExp(wordBoundaryRegexString, 'g');\n\n    words = text.split(wordBoundaryRegex);\n\n    if (shouldRemovePunctuation) {\n      words = words.map(removePunctuation);\n    } else {\n      // If punctuation is not removed, punctuation marks are tokenized as if they were words.\n      words = flatMap(words, word => {\n        const newWord = word.replace(punctuationRegex, ' $1 ');\n        return newWord.split(' ');\n      });\n    }\n  }\n\n  return filter(words, function(word) {\n    return word.trim() !== '';\n  });\n}\n"],"mappings":"AAAA;AACA,OAAOA,cAAc;AACrB,SAAQC,MAAM,EAAEC,OAAO,QAAO,QAAQ;AACtC,OAAOC,iBAAiB,IAAGC,sBAAsB;AAEjD,MAAMC,gBAAgB,GAAG,IAAIC,MAAM,CAAC,KAAKF,sBAAsB,IAAI,EAAE,GAAG,CAAC;;AAEzE;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAASG,IAAI,EAAEC,uBAAuB,GAAG,KAAK,EAAEC,uBAAuB,GAAG,IAAI,EAAE;EAC7F;EACAF,IAAI,GAAGP,cAAc,CAACO,IAAI,CAAC;EAE3B,IAAIA,IAAI,KAAK,EAAE,EAAE;IACf,OAAO,EAAE;EACX;EAEA,MAAMG,gBAAgB,GAAG,iBAAiB;EAC1C,MAAMC,UAAU,GAAGD,gBAAgB,CAACE,IAAI,CAACL,IAAI,CAAC;EAC9C,MAAMM,WAAW,GAAG,CAAC,IAAI,CAACD,IAAI,CAACL,IAAI,CAAC;EAEpC,IAAIO,KAAK,GAAG,EAAE;EAEd,IAAIH,UAAU,IAAIE,WAAW,EAAE;IAC7BC,KAAK,GAAGC,KAAK,CAACC,IAAI,CAACT,IAAI,CAAC,CAACN,MAAM,CAACgB,IAAI,IAAIP,gBAAgB,CAACE,IAAI,CAACK,IAAI,CAAC,CAAC;EACtE,CAAC,MAAM;IACL,MAAMC,iBAAiB,GAAG,IAAIZ,MAAM,CAACE,uBAAuB,EAAE,GAAG,CAAC;IAElEM,KAAK,GAAGP,IAAI,CAACY,KAAK,CAACD,iBAAiB,CAAC;IAErC,IAAIT,uBAAuB,EAAE;MAC3BK,KAAK,GAAGA,KAAK,CAACM,GAAG,CAACjB,iBAAiB,CAAC;IACtC,CAAC,MAAM;MACL;MACAW,KAAK,GAAGZ,OAAO,CAACY,KAAK,EAAEO,IAAI,IAAI;QAC7B,MAAMC,OAAO,GAAGD,IAAI,CAACE,OAAO,CAAClB,gBAAgB,EAAE,MAAM,CAAC;QACtD,OAAOiB,OAAO,CAACH,KAAK,CAAC,GAAG,CAAC;MAC3B,CAAC,CAAC;IACJ;EACF;EAEA,OAAOlB,MAAM,CAACa,KAAK,EAAE,UAASO,IAAI,EAAE;IAClC,OAAOA,IAAI,CAACG,IAAI,CAAC,CAAC,KAAK,EAAE;EAC3B,CAAC,CAAC;AACJ","ignoreList":[]}

package/build/languageProcessing/languages/zh/Researcher.js

@@ -0,0 +1,41 @@
+import { languageProcessing } from "../../../index.js";
+const {
+  AbstractResearcher
+} = languageProcessing;
+
+// All helpers
+import matchWordCustomHelper from "./helpers/matchTextWithWord";
+import splitIntoTokensCustom from "./helpers/splitIntoTokensCustom";
+import getSentencesCustom from "./helpers/getSentences";
+
+// All config
+import { all as functionWords } from "./config/functionWords";
+
+/**
+ * The researcher contains all the researches, helpers, data, and config for Chinese language.
+ */
+export default class Researcher extends AbstractResearcher {
+  /**
+   * Constructor
+   * @param {Paper} paper The Paper object that is needed within the researches.
+   * @constructor
+   */
+  constructor(paper) {
+    super(paper);
+
+    // Delete researches that are not suitable for Chinese
+    delete this.defaultResearches.getFleschReadingScore;
+    Object.assign(this.config, {
+      language: 'zh',
+      functionWords,
+      // Chinese doesn't use hyphens as word boundaries
+      areHyphensWordBoundaries: false
+    });
+    Object.assign(this.helpers, {
+      matchWordCustomHelper,
+      splitIntoTokensCustom,
+      getSentencesCustom
+    });
+  }
+}
+//# sourceMappingURL=Researcher.js.map

package/build/languageProcessing/languages/zh/Researcher.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"Researcher.js","names":["languageProcessing","AbstractResearcher","matchWordCustomHelper","splitIntoTokensCustom","getSentencesCustom","all","functionWords","Researcher","constructor","paper","defaultResearches","getFleschReadingScore","Object","assign","config","language","areHyphensWordBoundaries","helpers"],"sources":["../../../../src/languageProcessing/languages/zh/Researcher.js"],"sourcesContent":["import {languageProcessing} from '@axyseo/index.js';\nconst {AbstractResearcher} = languageProcessing;\n\n// All helpers\nimport matchWordCustomHelper from './helpers/matchTextWithWord';\nimport splitIntoTokensCustom from './helpers/splitIntoTokensCustom';\nimport getSentencesCustom from './helpers/getSentences';\n\n// All config\nimport {all as functionWords} from './config/functionWords';\n\n/**\n * The researcher contains all the researches, helpers, data, and config for Chinese language.\n */\nexport default class Researcher extends AbstractResearcher {\n  /**\n   * Constructor\n   * @param {Paper} paper The Paper object that is needed within the researches.\n   * @constructor\n   */\n  constructor(paper) {\n    super(paper);\n\n    // Delete researches that are not suitable for Chinese\n    delete this.defaultResearches.getFleschReadingScore;\n\n    Object.assign(this.config, {\n      language: 'zh',\n      functionWords,\n      // Chinese doesn't use hyphens as word boundaries\n      areHyphensWordBoundaries: false\n    });\n\n    Object.assign(this.helpers, {\n      matchWordCustomHelper,\n      splitIntoTokensCustom,\n      getSentencesCustom\n    });\n  }\n}\n"],"mappings":"AAAA,SAAQA,kBAAkB;AAC1B,MAAM;EAACC;AAAkB,CAAC,GAAGD,kBAAkB;;AAE/C;AACA,OAAOE,qBAAqB;AAC5B,OAAOC,qBAAqB;AAC5B,OAAOC,kBAAkB;;AAEzB;AACA,SAAQC,GAAG,IAAIC,aAAa;;AAE5B;AACA;AACA;AACA,eAAe,MAAMC,UAAU,SAASN,kBAAkB,CAAC;EACzD;AACF;AACA;AACA;AACA;EACEO,WAAWA,CAACC,KAAK,EAAE;IACjB,KAAK,CAACA,KAAK,CAAC;;IAEZ;IACA,OAAO,IAAI,CAACC,iBAAiB,CAACC,qBAAqB;IAEnDC,MAAM,CAACC,MAAM,CAAC,IAAI,CAACC,MAAM,EAAE;MACzBC,QAAQ,EAAE,IAAI;MACdT,aAAa;MACb;MACAU,wBAAwB,EAAE;IAC5B,CAAC,CAAC;IAEFJ,MAAM,CAACC,MAAM,CAAC,IAAI,CAACI,OAAO,EAAE;MAC1Bf,qBAAqB;MACrBC,qBAAqB;MACrBC;IACF,CAAC,CAAC;EACJ;AACF","ignoreList":[]}

package/build/languageProcessing/languages/zh/config/functionWords.js

@@ -0,0 +1,40 @@
+/**
+ * Returns an object with Chinese function words.
+ *
+ * @returns {Array} The array of Chinese function words.
+ */
+
+// Articles and determiners
+const articles = ['这', '那', '这个', '那个', '这些', '那些', '一个', '一些'];
+
+// Pronouns
+const pronouns = [
+// Personal pronouns
+'我', '你', '他', '她', '它', '我们', '你们', '他们', '她们', '它们',
+// Possessive pronouns
+'我的', '你的', '他的', '她的', '它的', '我们的', '你们的', '他们的', '她们的', '它们的',
+// Demonstrative pronouns
+'这', '那', '这个', '那个', '这些', '那些', '这里', '那里', '这儿', '那儿'];
+
+// Prepositions
+const prepositions = ['在', '从', '到', '向', '朝', '往', '由', '被', '把', '对', '为', '给', '跟', '和', '与', '同', '关于', '按照', '根据'];
+
+// Conjunctions
+const conjunctions = ['和', '或', '但', '但是', '可是', '然而', '不过', '而且', '并且', '以及', '还有', '或者', '要么', '因为', '所以', '如果', '要是', '虽然', '尽管'];
+
+// Auxiliary verbs and modal verbs
+const auxiliaries = ['是', '有', '没', '没有', '能', '可以', '会', '要', '想', '应该', '必须', '可能', '或许', '也许', '将', '将要', '正在', '已经', '刚刚'];
+
+// Quantifiers and numbers
+const quantifiers = ['一', '二', '三', '四', '五', '六', '七', '八', '九', '十', '百', '千', '万', '亿', '个', '只', '条', '本', '张', '件', '台', '辆', '所', '座', '栋', '间', '层', '些', '点', '种', '样', '次', '遍', '回'];
+
+// Adverbs
+const adverbs = ['很', '非常', '特别', '十分', '极', '太', '更', '最', '还', '也', '都', '只', '就', '才', '又', '再', '还是', '总是', '经常', '有时', '偶尔', '从来', '永远'];
+
+// Particles
+const particles = ['的', '地', '得', '了', '着', '过', '呢', '吗', '吧', '啊', '呀', '哦', '嗯', '哪', '什么', '怎么', '为什么', '哪里', '哪儿', '怎样'];
+
+// Interjections
+const interjections = ['哦', '啊', '呀', '哇', '嗯', '嘿', '喂', '哎', '唉', '咦', '哟', '呵', '嘻', '哈'];
+export const all = [].concat(articles, pronouns, prepositions, conjunctions, auxiliaries, quantifiers, adverbs, particles, interjections);
+//# sourceMappingURL=functionWords.js.map

package/build/languageProcessing/languages/zh/config/functionWords.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"functionWords.js","names":["articles","pronouns","prepositions","conjunctions","auxiliaries","quantifiers","adverbs","particles","interjections","all","concat"],"sources":["../../../../../src/languageProcessing/languages/zh/config/functionWords.js"],"sourcesContent":["/**\n * Returns an object with Chinese function words.\n *\n * @returns {Array} The array of Chinese function words.\n */\n\n// Articles and determiners\nconst articles = ['这', '那', '这个', '那个', '这些', '那些', '一个', '一些'];\n\n// Pronouns\nconst pronouns = [\n  // Personal pronouns\n  '我',\n  '你',\n  '他',\n  '她',\n  '它',\n  '我们',\n  '你们',\n  '他们',\n  '她们',\n  '它们',\n  // Possessive pronouns\n  '我的',\n  '你的',\n  '他的',\n  '她的',\n  '它的',\n  '我们的',\n  '你们的',\n  '他们的',\n  '她们的',\n  '它们的',\n  // Demonstrative pronouns\n  '这',\n  '那',\n  '这个',\n  '那个',\n  '这些',\n  '那些',\n  '这里',\n  '那里',\n  '这儿',\n  '那儿'\n];\n\n// Prepositions\nconst prepositions = [\n  '在',\n  '从',\n  '到',\n  '向',\n  '朝',\n  '往',\n  '由',\n  '被',\n  '把',\n  '对',\n  '为',\n  '给',\n  '跟',\n  '和',\n  '与',\n  '同',\n  '关于',\n  '按照',\n  '根据'\n];\n\n// Conjunctions\nconst conjunctions = [\n  '和',\n  '或',\n  '但',\n  '但是',\n  '可是',\n  '然而',\n  '不过',\n  '而且',\n  '并且',\n  '以及',\n  '还有',\n  '或者',\n  '要么',\n  '因为',\n  '所以',\n  '如果',\n  '要是',\n  '虽然',\n  '尽管'\n];\n\n// Auxiliary verbs and modal verbs\nconst auxiliaries = [\n  '是',\n  '有',\n  '没',\n  '没有',\n  '能',\n  '可以',\n  '会',\n  '要',\n  '想',\n  '应该',\n  '必须',\n  '可能',\n  '或许',\n  '也许',\n  '将',\n  '将要',\n  '正在',\n  '已经',\n  '刚刚'\n];\n\n// Quantifiers and numbers\nconst quantifiers = [\n  '一',\n  '二',\n  '三',\n  '四',\n  '五',\n  '六',\n  '七',\n  '八',\n  '九',\n  '十',\n  '百',\n  '千',\n  '万',\n  '亿',\n  '个',\n  '只',\n  '条',\n  '本',\n  '张',\n  '件',\n  '台',\n  '辆',\n  '所',\n  '座',\n  '栋',\n  '间',\n  '层',\n  '些',\n  '点',\n  '种',\n  '样',\n  '次',\n  '遍',\n  '回'\n];\n\n// Adverbs\nconst adverbs = [\n  '很',\n  '非常',\n  '特别',\n  '十分',\n  '极',\n  '太',\n  '更',\n  '最',\n  '还',\n  '也',\n  '都',\n  '只',\n  '就',\n  '才',\n  '又',\n  '再',\n  '还是',\n  '总是',\n  '经常',\n  '有时',\n  '偶尔',\n  '从来',\n  '永远'\n];\n\n// Particles\nconst particles = [\n  '的',\n  '地',\n  '得',\n  '了',\n  '着',\n  '过',\n  '呢',\n  '吗',\n  '吧',\n  '啊',\n  '呀',\n  '哦',\n  '嗯',\n  '哪',\n  '什么',\n  '怎么',\n  '为什么',\n  '哪里',\n  '哪儿',\n  '怎样'\n];\n\n// Interjections\nconst interjections = [\n  '哦',\n  '啊',\n  '呀',\n  '哇',\n  '嗯',\n  '嘿',\n  '喂',\n  '哎',\n  '唉',\n  '咦',\n  '哟',\n  '呵',\n  '嘻',\n  '哈'\n];\n\nexport const all = [].concat(\n  articles,\n  pronouns,\n  prepositions,\n  conjunctions,\n  auxiliaries,\n  quantifiers,\n  adverbs,\n  particles,\n  interjections\n);\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA;;AAEA;AACA,MAAMA,QAAQ,GAAG,CAAC,GAAG,EAAE,GAAG,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAC;;AAE/D;AACA,MAAMC,QAAQ,GAAG;AACf;AACA,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI;AACJ;AACA,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,KAAK,EACL,KAAK,EACL,KAAK,EACL,KAAK,EACL,KAAK;AACL;AACA,GAAG,EACH,GAAG,EACH,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,CACL;;AAED;AACA,MAAMC,YAAY,GAAG,CACnB,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,IAAI,EACJ,IAAI,EACJ,IAAI,CACL;;AAED;AACA,MAAMC,YAAY,GAAG,CACnB,GAAG,EACH,GAAG,EACH,GAAG,EACH,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,CACL;;AAED;AACA,MAAMC,WAAW,GAAG,CAClB,GAAG,EACH,GAAG,EACH,GAAG,EACH,IAAI,EACJ,GAAG,EACH,IAAI,EACJ,GAAG,EACH,GAAG,EACH,GAAG,EACH,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,GAAG,EACH,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,CACL;;AAED;AACA,MAAMC,WAAW,GAAG,CAClB,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,CACJ;;AAED;AACA,MAAMC,OAAO,GAAG,CACd,GAAG,EACH,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,EACJ,IAAI,CACL;;AAED;AACA,MAAMC,SAAS,GAAG,CAChB,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,IAAI,EACJ,IAAI,EACJ,KAAK,EACL,IAAI,EACJ,IAAI,EACJ,IAAI,CACL;;AAED;AACA,MAAMC,aAAa,GAAG,CACpB,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,EACH,GAAG,CACJ;AAED,OAAO,MAAMC,GAAG,GAAG,EAAE,CAACC,MAAM,CAC1BV,QAAQ,EACRC,QAAQ,EACRC,YAAY,EACZC,YAAY,EACZC,WAAW,EACXC,WAAW,EACXC,OAAO,EACPC,SAAS,EACTC,aACF,CAAC","ignoreList":[]}

package/build/languageProcessing/languages/zh/helpers/getSentences.js

@@ -0,0 +1,42 @@
+/**
+ * Gets sentences from Chinese text using Chinese punctuation marks.
+ *
+ * @param {string} text The text to get sentences from.
+ *
+ * @returns {string[]} An array of sentences.
+ */
+export default function getSentences(text) {
+  if (!text) {
+    return [];
+  }
+
+  // Chinese sentence-ending punctuation marks
+  const chineseSentenceEnders = /[。！？；]/;
+  const englishSentenceEnders = /[.!?;]/;
+
+  // Split by Chinese and English sentence enders, keeping the punctuation
+  const sentences = text.split(/([。！？；.!?;])/).filter(sentence => sentence.trim() !== '');
+  const result = [];
+  let currentSentence = '';
+  for (let i = 0; i < sentences.length; i++) {
+    const part = sentences[i];
+    if (chineseSentenceEnders.test(part) || englishSentenceEnders.test(part)) {
+      // This is punctuation - add to current sentence and finalize it
+      currentSentence += part;
+      if (currentSentence.trim()) {
+        result.push(currentSentence.trim());
+      }
+      currentSentence = '';
+    } else {
+      // This is sentence content
+      currentSentence += part;
+    }
+  }
+
+  // Add any remaining sentence
+  if (currentSentence.trim()) {
+    result.push(currentSentence.trim());
+  }
+  return result.filter(sentence => sentence.length > 0);
+}
+//# sourceMappingURL=getSentences.js.map

package/build/languageProcessing/languages/zh/helpers/getSentences.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getSentences.js","names":["getSentences","text","chineseSentenceEnders","englishSentenceEnders","sentences","split","filter","sentence","trim","result","currentSentence","i","length","part","test","push"],"sources":["../../../../../src/languageProcessing/languages/zh/helpers/getSentences.js"],"sourcesContent":["/**\n * Gets sentences from Chinese text using Chinese punctuation marks.\n *\n * @param {string} text The text to get sentences from.\n *\n * @returns {string[]} An array of sentences.\n */\nexport default function getSentences(text) {\n  if (!text) {\n    return [];\n  }\n\n  // Chinese sentence-ending punctuation marks\n  const chineseSentenceEnders = /[。！？；]/;\n  const englishSentenceEnders = /[.!?;]/;\n\n  // Split by Chinese and English sentence enders, keeping the punctuation\n  const sentences = text.split(/([。！？；.!?;])/).filter(sentence => sentence.trim() !== '');\n\n  const result = [];\n  let currentSentence = '';\n\n  for (let i = 0; i < sentences.length; i++) {\n    const part = sentences[i];\n\n    if (chineseSentenceEnders.test(part) || englishSentenceEnders.test(part)) {\n      // This is punctuation - add to current sentence and finalize it\n      currentSentence += part;\n      if (currentSentence.trim()) {\n        result.push(currentSentence.trim());\n      }\n      currentSentence = '';\n    } else {\n      // This is sentence content\n      currentSentence += part;\n    }\n  }\n\n  // Add any remaining sentence\n  if (currentSentence.trim()) {\n    result.push(currentSentence.trim());\n  }\n\n  return result.filter(sentence => sentence.length > 0);\n}\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASA,YAAYA,CAACC,IAAI,EAAE;EACzC,IAAI,CAACA,IAAI,EAAE;IACT,OAAO,EAAE;EACX;;EAEA;EACA,MAAMC,qBAAqB,GAAG,QAAQ;EACtC,MAAMC,qBAAqB,GAAG,QAAQ;;EAEtC;EACA,MAAMC,SAAS,GAAGH,IAAI,CAACI,KAAK,CAAC,cAAc,CAAC,CAACC,MAAM,CAACC,QAAQ,IAAIA,QAAQ,CAACC,IAAI,CAAC,CAAC,KAAK,EAAE,CAAC;EAEvF,MAAMC,MAAM,GAAG,EAAE;EACjB,IAAIC,eAAe,GAAG,EAAE;EAExB,KAAK,IAAIC,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGP,SAAS,CAACQ,MAAM,EAAED,CAAC,EAAE,EAAE;IACzC,MAAME,IAAI,GAAGT,SAAS,CAACO,CAAC,CAAC;IAEzB,IAAIT,qBAAqB,CAACY,IAAI,CAACD,IAAI,CAAC,IAAIV,qBAAqB,CAACW,IAAI,CAACD,IAAI,CAAC,EAAE;MACxE;MACAH,eAAe,IAAIG,IAAI;MACvB,IAAIH,eAAe,CAACF,IAAI,CAAC,CAAC,EAAE;QAC1BC,MAAM,CAACM,IAAI,CAACL,eAAe,CAACF,IAAI,CAAC,CAAC,CAAC;MACrC;MACAE,eAAe,GAAG,EAAE;IACtB,CAAC,MAAM;MACL;MACAA,eAAe,IAAIG,IAAI;IACzB;EACF;;EAEA;EACA,IAAIH,eAAe,CAACF,IAAI,CAAC,CAAC,EAAE;IAC1BC,MAAM,CAACM,IAAI,CAACL,eAAe,CAACF,IAAI,CAAC,CAAC,CAAC;EACrC;EAEA,OAAOC,MAAM,CAACH,MAAM,CAACC,QAAQ,IAAIA,QAAQ,CAACK,MAAM,GAAG,CAAC,CAAC;AACvD","ignoreList":[]}

package/build/languageProcessing/languages/zh/helpers/matchTextWithWord.js

@@ -0,0 +1,35 @@
+/**
+ * Matches a word in a text for Chinese language.
+ * Chinese doesn't use spaces between words, so we use exact string matching.
+ * This function is compatible with the matchWordCustomHelper interface.
+ *
+ * @param {string|Object} sentence  The sentence to search in (can be string or sentence object).
+ * @param {string} word             The word to search for.
+ *
+ * @returns {Array} An array of matches found in the text.
+ */
+export default function matchTextWithWord(sentence, word) {
+  const matches = [];
+
+  // Handle both string and sentence object
+  const text = typeof sentence === 'string' ? sentence : sentence.text || sentence;
+  if (!text || !word) {
+    return matches;
+  }
+
+  // Convert both text and word to lowercase for case-insensitive matching
+  const lowerText = text.toLowerCase();
+  const lowerWord = word.toLowerCase();
+  let startIndex = 0;
+  let index;
+
+  // Find all occurrences of the word in the text
+  while ((index = lowerText.indexOf(lowerWord, startIndex)) !== -1) {
+    // For Chinese, we add the matched word directly as a string
+    // This matches the expected return format for the custom helper
+    matches.push(word);
+    startIndex = index + lowerWord.length;
+  }
+  return matches;
+}
+//# sourceMappingURL=matchTextWithWord.js.map

package/build/languageProcessing/languages/zh/helpers/matchTextWithWord.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"matchTextWithWord.js","names":["matchTextWithWord","sentence","word","matches","text","lowerText","toLowerCase","lowerWord","startIndex","index","indexOf","push","length"],"sources":["../../../../../src/languageProcessing/languages/zh/helpers/matchTextWithWord.js"],"sourcesContent":["/**\n * Matches a word in a text for Chinese language.\n * Chinese doesn't use spaces between words, so we use exact string matching.\n * This function is compatible with the matchWordCustomHelper interface.\n *\n * @param {string|Object} sentence  The sentence to search in (can be string or sentence object).\n * @param {string} word             The word to search for.\n *\n * @returns {Array} An array of matches found in the text.\n */\nexport default function matchTextWithWord(sentence, word) {\n  const matches = [];\n\n  // Handle both string and sentence object\n  const text = typeof sentence === 'string' ? sentence : sentence.text || sentence;\n\n  if (!text || !word) {\n    return matches;\n  }\n\n  // Convert both text and word to lowercase for case-insensitive matching\n  const lowerText = text.toLowerCase();\n  const lowerWord = word.toLowerCase();\n\n  let startIndex = 0;\n  let index;\n\n  // Find all occurrences of the word in the text\n  while ((index = lowerText.indexOf(lowerWord, startIndex)) !== -1) {\n    // For Chinese, we add the matched word directly as a string\n    // This matches the expected return format for the custom helper\n    matches.push(word);\n    startIndex = index + lowerWord.length;\n  }\n\n  return matches;\n}\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASA,iBAAiBA,CAACC,QAAQ,EAAEC,IAAI,EAAE;EACxD,MAAMC,OAAO,GAAG,EAAE;;EAElB;EACA,MAAMC,IAAI,GAAG,OAAOH,QAAQ,KAAK,QAAQ,GAAGA,QAAQ,GAAGA,QAAQ,CAACG,IAAI,IAAIH,QAAQ;EAEhF,IAAI,CAACG,IAAI,IAAI,CAACF,IAAI,EAAE;IAClB,OAAOC,OAAO;EAChB;;EAEA;EACA,MAAME,SAAS,GAAGD,IAAI,CAACE,WAAW,CAAC,CAAC;EACpC,MAAMC,SAAS,GAAGL,IAAI,CAACI,WAAW,CAAC,CAAC;EAEpC,IAAIE,UAAU,GAAG,CAAC;EAClB,IAAIC,KAAK;;EAET;EACA,OAAO,CAACA,KAAK,GAAGJ,SAAS,CAACK,OAAO,CAACH,SAAS,EAAEC,UAAU,CAAC,MAAM,CAAC,CAAC,EAAE;IAChE;IACA;IACAL,OAAO,CAACQ,IAAI,CAACT,IAAI,CAAC;IAClBM,UAAU,GAAGC,KAAK,GAAGF,SAAS,CAACK,MAAM;EACvC;EAEA,OAAOT,OAAO;AAChB","ignoreList":[]}