axyseo 2.1.8 → 2.1.9

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/researches/metaDescriptionKeyword.js

@@ -13,7 +13,7 @@ import getSentences from "../helpers/sentence/getSentences";
 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, "");
+    description = description.replace(match, '');
   }));
   return description;
 };
@@ -62,9 +62,21 @@ const matchPerSentence = function (sentence, topicForms, locale, matchWordCustom
 export default function (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 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 = getSentences(description, memoizedTokenizer);
   const sentenceMatches = sentences.map(sentence => matchPerSentence(sentence, topicForms, locale, matchWordCustomHelper));
   return sentenceMatches.reduce((sum, count) => sum + count, 0);

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

@@ -1 +1 @@
-{"version":3,"file":"metaDescriptionKeyword.js","names":["matchWords","getSentences","replaceFoundKeywordForms","description","matchedKeywordForms","maxToRemove","forEach","keywordForm","matches","slice","match","replace","matchPerSentence","sentence","topicForms","locale","matchWordCustomHelper","matchesKeyphrase","keyphraseForms","map","keywordForms","fullKeyphraseMatches","Math","min","count","fullSynonymsMatches","synonymsForms","synonymForms","fullSynonymMatches","reduce","sum","paper","researcher","getDescription","getLocale","getResearch","getHelper","memoizedTokenizer","sentences","sentenceMatches"],"sources":["../../../src/languageProcessing/researches/metaDescriptionKeyword.js"],"sourcesContent":["import matchWords from \"../helpers/match/matchTextWithArray\";\nimport getSentences from \"../helpers/sentence/getSentences\";\n\n/**\n * Replaces found keyword forms in the given description.\n *\n * @param {string}      description         The description to remove the matched keyword forms from.\n * @param {Object[]}    matchedKeywordForms The matched keyword forms to remove from the description.\n * @param {Number}      maxToRemove         The maximum amount of matches of each individual keyword to remove.\n *\n * @returns {string} The description with the keywords removed.\n */\nconst replaceFoundKeywordForms = function( description, matchedKeywordForms, maxToRemove ) {\n\t// Replace matches so we do not match them for synonyms.\n\tmatchedKeywordForms.forEach( keywordForm =>\n\t\tkeywordForm.matches.slice( 0, maxToRemove ).forEach(\n\t\t\tmatch => {\n\t\t\t\tdescription = description.replace( match, \"\" );\n\t\t\t}\n\t\t)\n\t);\n\treturn 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\t// Focus keyphrase matches.\n\tconst matchesKeyphrase = topicForms.keyphraseForms.map( keywordForms => matchWords( sentence, keywordForms, locale, matchWordCustomHelper ) );\n\t// Count the number of matches that contain every word in the entire keyphrase.\n\tconst fullKeyphraseMatches = Math.min( ...matchesKeyphrase.map( match => match.count ) );\n\n\t// Replace all full keyphrase matches so we do not match them for synonyms.\n\tsentence = replaceFoundKeywordForms( sentence, matchesKeyphrase, fullKeyphraseMatches );\n\n\t// Keyphrase synonyms matches.\n\tconst fullSynonymsMatches = topicForms.synonymsForms.map(\n\t\tsynonymForms => {\n\t\t\t// Synonym keyphrase matches.\n\t\t\tconst matches = synonymForms.map( keywordForms => matchWords( sentence, keywordForms, locale, matchWordCustomHelper ) );\n\t\t\t// Count the number of matches that contain every word in the entire synonym keyphrase.\n\t\t\tconst fullSynonymMatches = Math.min( ...matches.map( match => match.count ) );\n\t\t\t// Replace all full matches so we do not match them for other synonyms.\n\t\t\tsentence = replaceFoundKeywordForms( sentence, matchesKeyphrase, fullSynonymMatches );\n\t\t\treturn fullSynonymMatches;\n\t\t}\n\t);\n\n\treturn [ 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\tconst description = paper.getDescription();\n\tconst locale = paper.getLocale();\n\n\tconst topicForms = researcher.getResearch( \"morphology\" );\n\tconst matchWordCustomHelper = researcher.getHelper( \"matchWordCustomHelper\" );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\n\tconst sentences = getSentences( description, memoizedTokenizer );\n\n\tconst sentenceMatches = sentences.map(\n\t\tsentence => matchPerSentence( sentence, topicForms, locale, matchWordCustomHelper )\n\t);\n\n\treturn sentenceMatches.reduce( ( sum, count ) => sum + count, 0 );\n}\n\n"],"mappings":"AAAA,OAAOA,UAAU;AACjB,OAAOC,YAAY;;AAEnB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,wBAAwB,GAAG,SAAAA,CAAUC,WAAW,EAAEC,mBAAmB,EAAEC,WAAW,EAAG;EAC1F;EACAD,mBAAmB,CAACE,OAAO,CAAEC,WAAW,IACvCA,WAAW,CAACC,OAAO,CAACC,KAAK,CAAE,CAAC,EAAEJ,WAAY,CAAC,CAACC,OAAO,CAClDI,KAAK,IAAI;IACRP,WAAW,GAAGA,WAAW,CAACQ,OAAO,CAAED,KAAK,EAAE,EAAG,CAAC;EAC/C,CACD,CACD,CAAC;EACD,OAAOP,WAAW;AACnB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMS,gBAAgB,GAAG,SAAAA,CAAUC,QAAQ,EAAEC,UAAU,EAAEC,MAAM,EAAEC,qBAAqB,EAAG;EACxF;EACA,MAAMC,gBAAgB,GAAGH,UAAU,CAACI,cAAc,CAACC,GAAG,CAAEC,YAAY,IAAIpB,UAAU,CAAEa,QAAQ,EAAEO,YAAY,EAAEL,MAAM,EAAEC,qBAAsB,CAAE,CAAC;EAC7I;EACA,MAAMK,oBAAoB,GAAGC,IAAI,CAACC,GAAG,CAAE,GAAGN,gBAAgB,CAACE,GAAG,CAAET,KAAK,IAAIA,KAAK,CAACc,KAAM,CAAE,CAAC;;EAExF;EACAX,QAAQ,GAAGX,wBAAwB,CAAEW,QAAQ,EAAEI,gBAAgB,EAAEI,oBAAqB,CAAC;;EAEvF;EACA,MAAMI,mBAAmB,GAAGX,UAAU,CAACY,aAAa,CAACP,GAAG,CACvDQ,YAAY,IAAI;IACf;IACA,MAAMnB,OAAO,GAAGmB,YAAY,CAACR,GAAG,CAAEC,YAAY,IAAIpB,UAAU,CAAEa,QAAQ,EAAEO,YAAY,EAAEL,MAAM,EAAEC,qBAAsB,CAAE,CAAC;IACvH;IACA,MAAMY,kBAAkB,GAAGN,IAAI,CAACC,GAAG,CAAE,GAAGf,OAAO,CAACW,GAAG,CAAET,KAAK,IAAIA,KAAK,CAACc,KAAM,CAAE,CAAC;IAC7E;IACAX,QAAQ,GAAGX,wBAAwB,CAAEW,QAAQ,EAAEI,gBAAgB,EAAEW,kBAAmB,CAAC;IACrF,OAAOA,kBAAkB;EAC1B,CACD,CAAC;EAED,OAAO,CAAEP,oBAAoB,EAAE,GAAGI,mBAAmB,CAAE,CAACI,MAAM,CAAE,CAAEC,GAAG,EAAEN,KAAK,KAAMM,GAAG,GAAGN,KAAK,EAAE,CAAE,CAAC;AACnG,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUO,KAAK,EAAEC,UAAU,EAAG;EAC5C,MAAM7B,WAAW,GAAG4B,KAAK,CAACE,cAAc,CAAC,CAAC;EAC1C,MAAMlB,MAAM,GAAGgB,KAAK,CAACG,SAAS,CAAC,CAAC;EAEhC,MAAMpB,UAAU,GAAGkB,UAAU,CAACG,WAAW,CAAE,YAAa,CAAC;EACzD,MAAMnB,qBAAqB,GAAGgB,UAAU,CAACI,SAAS,CAAE,uBAAwB,CAAC;EAC7E,MAAMC,iBAAiB,GAAGL,UAAU,CAACI,SAAS,CAAE,mBAAoB,CAAC;EAErE,MAAME,SAAS,GAAGrC,YAAY,CAAEE,WAAW,EAAEkC,iBAAkB,CAAC;EAEhE,MAAME,eAAe,GAAGD,SAAS,CAACnB,GAAG,CACpCN,QAAQ,IAAID,gBAAgB,CAAEC,QAAQ,EAAEC,UAAU,EAAEC,MAAM,EAAEC,qBAAsB,CACnF,CAAC;EAED,OAAOuB,eAAe,CAACV,MAAM,CAAE,CAAEC,GAAG,EAAEN,KAAK,KAAMM,GAAG,GAAGN,KAAK,EAAE,CAAE,CAAC;AAClE","ignoreList":[]}
+{"version":3,"file":"metaDescriptionKeyword.js","names":["matchWords","getSentences","replaceFoundKeywordForms","description","matchedKeywordForms","maxToRemove","forEach","keywordForm","matches","slice","match","replace","matchPerSentence","sentence","topicForms","locale","matchWordCustomHelper","matchesKeyphrase","keyphraseForms","map","keywordForms","fullKeyphraseMatches","Math","min","count","fullSynonymsMatches","synonymsForms","synonymForms","fullSynonymMatches","reduce","sum","paper","researcher","getDescription","getLocale","getResearch","getHelper","memoizedTokenizer","keyphrase","getKeyword","isChinese","test","pos","indexOf","length","sentences","sentenceMatches"],"sources":["../../../src/languageProcessing/researches/metaDescriptionKeyword.js"],"sourcesContent":["import matchWords from '../helpers/match/matchTextWithArray';\nimport getSentences from '../helpers/sentence/getSentences';\n\n/**\n * Replaces found keyword forms in the given description.\n *\n * @param {string}      description         The description to remove the matched keyword forms from.\n * @param {Object[]}    matchedKeywordForms The matched keyword forms to remove from the description.\n * @param {Number}      maxToRemove         The maximum amount of matches of each individual keyword to remove.\n *\n * @returns {string} The description with the keywords removed.\n */\nconst replaceFoundKeywordForms = function(description, matchedKeywordForms, maxToRemove) {\n  // Replace matches so we do not match them for synonyms.\n  matchedKeywordForms.forEach(keywordForm =>\n    keywordForm.matches.slice(0, maxToRemove).forEach(match => {\n      description = description.replace(match, '');\n    })\n  );\n  return description;\n};\n\n/**\n * Counts the number of full keyphrase matches in the given sentence. Takes synonyms into account.\n * A full keyphrase is when all keywords in the keyphrase match.\n *\n * @param {string}      sentence        The sentence that needs to be analyzed.\n * @param {Object}      topicForms      The keyphrase (and its optional synonyms') word forms.\n * @param {string}      locale          The current locale.\n * @param {function}    matchWordCustomHelper   The language-specific helper function to match word in text.\n *\n * @returns {Number} The number of matched keyphrases in the sentence.\n */\nconst matchPerSentence = function(sentence, topicForms, locale, matchWordCustomHelper) {\n  // Focus keyphrase matches.\n  const matchesKeyphrase = topicForms.keyphraseForms.map(keywordForms =>\n    matchWords(sentence, keywordForms, locale, matchWordCustomHelper)\n  );\n  // Count the number of matches that contain every word in the entire keyphrase.\n  const fullKeyphraseMatches = Math.min(...matchesKeyphrase.map(match => match.count));\n\n  // Replace all full keyphrase matches so we do not match them for synonyms.\n  sentence = replaceFoundKeywordForms(sentence, matchesKeyphrase, fullKeyphraseMatches);\n\n  // Keyphrase synonyms matches.\n  const fullSynonymsMatches = topicForms.synonymsForms.map(synonymForms => {\n    // Synonym keyphrase matches.\n    const matches = synonymForms.map(keywordForms =>\n      matchWords(sentence, keywordForms, locale, matchWordCustomHelper)\n    );\n    // Count the number of matches that contain every word in the entire synonym keyphrase.\n    const fullSynonymMatches = Math.min(...matches.map(match => match.count));\n    // Replace all full matches so we do not match them for other synonyms.\n    sentence = replaceFoundKeywordForms(sentence, matchesKeyphrase, fullSynonymMatches);\n    return fullSynonymMatches;\n  });\n\n  return [fullKeyphraseMatches, ...fullSynonymsMatches].reduce((sum, count) => sum + count, 0);\n};\n\n/**\n * Counts the number of full keyphrase matches in the description.\n *\n * @param {Paper}       paper       The paper object containing the description.\n * @param {Researcher}  researcher  The researcher object to gather researchers from.\n *\n * @returns {Number} The number of keyphrase matches for the entire description.\n */\nexport default function(paper, researcher) {\n  const description = paper.getDescription();\n  const locale = paper.getLocale();\n\n  const topicForms = researcher.getResearch('morphology');\n  const matchWordCustomHelper = researcher.getHelper('matchWordCustomHelper');\n  const memoizedTokenizer = researcher.getHelper('memoizedTokenizer');\n\n  const keyphrase = paper.getKeyword && paper.getKeyword();\n  const isChinese = keyphrase && /[\\u4e00-\\u9fff]/.test(keyphrase);\n\n  if (isChinese) {\n    if (!keyphrase) return 0;\n    let count = 0;\n    let pos = description.indexOf(keyphrase);\n    while (pos !== -1) {\n      count++;\n      pos = description.indexOf(keyphrase, pos + keyphrase.length);\n    }\n    return count;\n  }\n\n  const sentences = getSentences(description, memoizedTokenizer);\n\n  const sentenceMatches = sentences.map(sentence =>\n    matchPerSentence(sentence, topicForms, locale, matchWordCustomHelper)\n  );\n\n  return sentenceMatches.reduce((sum, count) => sum + count, 0);\n}\n"],"mappings":"AAAA,OAAOA,UAAU;AACjB,OAAOC,YAAY;;AAEnB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,wBAAwB,GAAG,SAAAA,CAASC,WAAW,EAAEC,mBAAmB,EAAEC,WAAW,EAAE;EACvF;EACAD,mBAAmB,CAACE,OAAO,CAACC,WAAW,IACrCA,WAAW,CAACC,OAAO,CAACC,KAAK,CAAC,CAAC,EAAEJ,WAAW,CAAC,CAACC,OAAO,CAACI,KAAK,IAAI;IACzDP,WAAW,GAAGA,WAAW,CAACQ,OAAO,CAACD,KAAK,EAAE,EAAE,CAAC;EAC9C,CAAC,CACH,CAAC;EACD,OAAOP,WAAW;AACpB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMS,gBAAgB,GAAG,SAAAA,CAASC,QAAQ,EAAEC,UAAU,EAAEC,MAAM,EAAEC,qBAAqB,EAAE;EACrF;EACA,MAAMC,gBAAgB,GAAGH,UAAU,CAACI,cAAc,CAACC,GAAG,CAACC,YAAY,IACjEpB,UAAU,CAACa,QAAQ,EAAEO,YAAY,EAAEL,MAAM,EAAEC,qBAAqB,CAClE,CAAC;EACD;EACA,MAAMK,oBAAoB,GAAGC,IAAI,CAACC,GAAG,CAAC,GAAGN,gBAAgB,CAACE,GAAG,CAACT,KAAK,IAAIA,KAAK,CAACc,KAAK,CAAC,CAAC;;EAEpF;EACAX,QAAQ,GAAGX,wBAAwB,CAACW,QAAQ,EAAEI,gBAAgB,EAAEI,oBAAoB,CAAC;;EAErF;EACA,MAAMI,mBAAmB,GAAGX,UAAU,CAACY,aAAa,CAACP,GAAG,CAACQ,YAAY,IAAI;IACvE;IACA,MAAMnB,OAAO,GAAGmB,YAAY,CAACR,GAAG,CAACC,YAAY,IAC3CpB,UAAU,CAACa,QAAQ,EAAEO,YAAY,EAAEL,MAAM,EAAEC,qBAAqB,CAClE,CAAC;IACD;IACA,MAAMY,kBAAkB,GAAGN,IAAI,CAACC,GAAG,CAAC,GAAGf,OAAO,CAACW,GAAG,CAACT,KAAK,IAAIA,KAAK,CAACc,KAAK,CAAC,CAAC;IACzE;IACAX,QAAQ,GAAGX,wBAAwB,CAACW,QAAQ,EAAEI,gBAAgB,EAAEW,kBAAkB,CAAC;IACnF,OAAOA,kBAAkB;EAC3B,CAAC,CAAC;EAEF,OAAO,CAACP,oBAAoB,EAAE,GAAGI,mBAAmB,CAAC,CAACI,MAAM,CAAC,CAACC,GAAG,EAAEN,KAAK,KAAKM,GAAG,GAAGN,KAAK,EAAE,CAAC,CAAC;AAC9F,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAASO,KAAK,EAAEC,UAAU,EAAE;EACzC,MAAM7B,WAAW,GAAG4B,KAAK,CAACE,cAAc,CAAC,CAAC;EAC1C,MAAMlB,MAAM,GAAGgB,KAAK,CAACG,SAAS,CAAC,CAAC;EAEhC,MAAMpB,UAAU,GAAGkB,UAAU,CAACG,WAAW,CAAC,YAAY,CAAC;EACvD,MAAMnB,qBAAqB,GAAGgB,UAAU,CAACI,SAAS,CAAC,uBAAuB,CAAC;EAC3E,MAAMC,iBAAiB,GAAGL,UAAU,CAACI,SAAS,CAAC,mBAAmB,CAAC;EAEnE,MAAME,SAAS,GAAGP,KAAK,CAACQ,UAAU,IAAIR,KAAK,CAACQ,UAAU,CAAC,CAAC;EACxD,MAAMC,SAAS,GAAGF,SAAS,IAAI,iBAAiB,CAACG,IAAI,CAACH,SAAS,CAAC;EAEhE,IAAIE,SAAS,EAAE;IACb,IAAI,CAACF,SAAS,EAAE,OAAO,CAAC;IACxB,IAAId,KAAK,GAAG,CAAC;IACb,IAAIkB,GAAG,GAAGvC,WAAW,CAACwC,OAAO,CAACL,SAAS,CAAC;IACxC,OAAOI,GAAG,KAAK,CAAC,CAAC,EAAE;MACjBlB,KAAK,EAAE;MACPkB,GAAG,GAAGvC,WAAW,CAACwC,OAAO,CAACL,SAAS,EAAEI,GAAG,GAAGJ,SAAS,CAACM,MAAM,CAAC;IAC9D;IACA,OAAOpB,KAAK;EACd;EAEA,MAAMqB,SAAS,GAAG5C,YAAY,CAACE,WAAW,EAAEkC,iBAAiB,CAAC;EAE9D,MAAMS,eAAe,GAAGD,SAAS,CAAC1B,GAAG,CAACN,QAAQ,IAC5CD,gBAAgB,CAACC,QAAQ,EAAEC,UAAU,EAAEC,MAAM,EAAEC,qBAAqB,CACtE,CAAC;EAED,OAAO8B,eAAe,CAACjB,MAAM,CAAC,CAACC,GAAG,EAAEN,KAAK,KAAKM,GAAG,GAAGN,KAAK,EAAE,CAAC,CAAC;AAC/D","ignoreList":[]}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "axyseo",
-  "version": "2.1.8",
+  "version": "2.1.9",
   "main": "build/index.js",
   "scripts": {
     "prepublishOnly": "npm run build ",