axyseo 2.0.0-alpha.0.0.37 → 2.0.0-alpha.0.0.39

package/build/languageProcessing/helpers/prominentWords/determineProminentWords.js

@@ -0,0 +1,191 @@
+import { memoize, uniq } from "lodash";
+import getWords from "../word/getWords";
+import { normalizeSingle } from "../sanitize/quotes";
+import ProminentWord from "../../values/ProminentWord";
+const specialCharacters = /[1234567890‘’“”"'.…?!:;,¿¡«»&*@#±^%$|~=+§`[\](){}⟨⟩<>/\\–\-\u2014\u00d7\s]/g;
+
+/**
+ * Returns only those prominent words that occur more than a certain number of times and do not consist of special characters.
+ *
+ * @param {ProminentWord[]} prominentWords A list of prominent words.
+ * @param {int} [minimalNumberOfOccurrences] A minimal number of occurrences that is needed for a relevant prominentWord, default 2.
+ *
+ * @returns {ProminentWord[]} Only relevant words.
+ */
+function filterProminentWords(prominentWords, minimalNumberOfOccurrences = 2) {
+  prominentWords = prominentWords.filter(function (word) {
+    return word.getOccurrences() >= minimalNumberOfOccurrences && word.getWord().replace(specialCharacters, "") !== "";
+  });
+  return prominentWords;
+}
+
+/**
+ * Sorts prominent words based on their number of occurrences and length.
+ *
+ * @param {ProminentWord[]} prominentWords The prominent words to sort.
+ *
+ * @returns {void}
+ */
+function sortProminentWords(prominentWords) {
+  prominentWords.sort(function (wordA, wordB) {
+    const difference = wordB.getOccurrences() - wordA.getOccurrences();
+    // The word with the highest number of occurrences comes first.
+    if (difference !== 0) {
+      return difference;
+    }
+
+    // In case of a tie on occurrence number, the alphabetically first word comes first.
+    return wordA.getStem().localeCompare(wordB.getStem());
+  });
+}
+
+/**
+ * Collapses prominent words that have the same stem.
+ *
+ * @param {ProminentWord[]} prominentWords All prominentWords.
+ *
+ * @returns {ProminentWord[]} The original array with collapsed duplicates.
+ */
+function collapseProminentWordsOnStem(prominentWords) {
+  if (prominentWords.length === 0) {
+    return [];
+  }
+
+  // Sort the input array by stem
+  prominentWords.sort(function (wordA, wordB) {
+    return wordA.getStem().localeCompare(wordB.getStem());
+  });
+  const collapsedProminentWords = [];
+  let previousWord = new ProminentWord(prominentWords[0].getWord(), prominentWords[0].getStem(), prominentWords[0].getOccurrences());
+  for (let i = 1; i < prominentWords.length; i++) {
+    const currentWord = new ProminentWord(prominentWords[i].getWord(), prominentWords[i].getStem(), prominentWords[i].getOccurrences());
+
+    /*
+     * Compare the stem of the current word in the loop with the previously available stem.
+     * If they are equal, the word should be collapsed.
+     * When collapsing, the numbers of occurrences get summed.
+     * If the stem happens to equal the real word that occurred in the text, we can be sure it's ok to display it
+     * to the customer. So, the stem reassigns the word.
+     */
+    if (currentWord.getStem() === previousWord.getStem()) {
+      previousWord.setOccurrences(previousWord.getOccurrences() + currentWord.getOccurrences());
+      if (currentWord.getWord() === previousWord.getStem() || currentWord.getWord().toLocaleLowerCase() === previousWord.getStem()) {
+        previousWord.setWord(currentWord.getWord());
+      }
+    } else {
+      collapsedProminentWords.push(previousWord);
+      previousWord = currentWord;
+    }
+  }
+  collapsedProminentWords.push(previousWord);
+  return collapsedProminentWords;
+}
+
+/**
+ * Retrieves a list of all abbreviations from the text. Returns an empty array if the input text is empty.
+ *
+ * @param {string} text A text.
+ *
+ * @returns {string[]} A list of abbreviations from the list.
+ */
+function retrieveAbbreviations(text) {
+  const words = getWords(normalizeSingle(text));
+  const abbreviations = [];
+  words.forEach(function (word) {
+    if (word.length > 1 && word.length < 5 && word === word.toLocaleUpperCase()) {
+      abbreviations.push(word.toLocaleLowerCase());
+    }
+  });
+  return uniq(abbreviations);
+}
+
+/**
+ * Computes prominent words from an array of words. In order to do so, checks whether the word is included in the list of
+ * function words and determines the number of occurrences for every word. Then checks if any two words have the same stem
+ * and if so collapses over them.
+ *
+ * @param {string[]} words          The words to determine relevance for.
+ * @param {string[]} abbreviations  Abbreviations that should not be stemmed.
+ * @param {Function} stemmer        The available stemmer.
+ * @param {Array} functionWords     The available function words list.
+ *
+ * @returns {ProminentWord[]} All prominent words sorted and filtered for this text.
+ */
+function computeProminentWords(words, abbreviations, stemmer, functionWords) {
+  if (words.length === 0) {
+    return [];
+  }
+  const uniqueContentWords = uniq(words.filter(word => !functionWords.includes(word.trim())));
+  const prominentWords = [];
+  uniqueContentWords.forEach(function (word) {
+    if (abbreviations.includes(word)) {
+      prominentWords.push(new ProminentWord(word.toLocaleUpperCase(), word, words.filter(element => element === word).length));
+    } else {
+      prominentWords.push(new ProminentWord(word, stemmer(word), words.filter(element => element === word).length));
+    }
+  });
+  return collapseProminentWordsOnStem(prominentWords);
+}
+
+/**
+ * Caches prominent words depending on text words.
+ * Only the words and abbreviations are used as the cache key as the stemmer and function words
+ * are config and shouldn't change in the scope of one request.
+ *
+ * @param {string[]} words          The words to determine relevance for.
+ * @param {string[]} abbreviations  Abbreviations that should not be stemmed.
+ * @param {Function} stemmer        The available stemmer.
+ * @param {Array} functionWords     The available function words list.
+ *
+ * @returns {function} The function that collects prominent words for a given set of text words, language and morphologyData.
+ */
+const computeProminentWordsMemoized = memoize((words, abbreviations, stemmer, functionWords) => {
+  return computeProminentWords(words, abbreviations, stemmer, functionWords);
+}, (words, abbreviations) => {
+  return words.join(",") + "," + abbreviations.join(",");
+});
+
+/**
+ * Gets prominent words from the paper text.
+ *
+ * @param {string} text             The text to retrieve the prominent words from.
+ * @param {string[]} abbreviations  The abbreviations that occur in the text and attributes of the paper.
+ * @param {Function} stemmer        The available stemmer.
+ * @param {Array} functionWords     The available function words list.
+ * @param {function} getWordsCustomHelper   The custom helper to get words.
+ *
+ * @returns {ProminentWord[]} All prominent words sorted and filtered for this text.
+ */
+function getProminentWords(text, abbreviations, stemmer, functionWords, getWordsCustomHelper) {
+  if (text === "") {
+    return [];
+  }
+  const words = getWordsCustomHelper ? getWordsCustomHelper(normalizeSingle(text).toLocaleLowerCase()) : getWords(normalizeSingle(text).toLocaleLowerCase());
+  return computeProminentWordsMemoized(words, abbreviations, stemmer, functionWords);
+}
+
+/**
+ * Gets prominent words from keyphrase and synonyms, metadescription, title, and subheadings.
+ *
+ * @param {string[]} attributes     The array with attributes to process.
+ * @param {string[]} abbreviations  The abbreviations that occur in the text and attributes of the paper.
+ * @param {Function} stemmer        The available stemmer.
+ * @param {Array} functionWords     The available function words list.
+ * @param {function} getWordsCustomHelper   The custom helper to get words.
+ *
+ * @returns {ProminentWord[]} Prominent words from the paper attributes.
+ */
+function getProminentWordsFromPaperAttributes(attributes, abbreviations, stemmer, functionWords, getWordsCustomHelper) {
+  const wordsFromAttributes = getWordsCustomHelper ? getWordsCustomHelper(attributes.join(" ").toLocaleLowerCase()) : getWords(attributes.join(" ").toLocaleLowerCase());
+  return computeProminentWords(wordsFromAttributes, abbreviations, stemmer, functionWords);
+}
+export { getProminentWords, getProminentWordsFromPaperAttributes, filterProminentWords, sortProminentWords, collapseProminentWordsOnStem, retrieveAbbreviations };
+export default {
+  getProminentWords,
+  getProminentWordsFromPaperAttributes,
+  filterProminentWords,
+  sortProminentWords,
+  collapseProminentWordsOnStem,
+  retrieveAbbreviations
+};
+//# sourceMappingURL=determineProminentWords.js.map

package/build/languageProcessing/helpers/prominentWords/determineProminentWords.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"determineProminentWords.js","names":["memoize","uniq","getWords","normalizeSingle","ProminentWord","specialCharacters","filterProminentWords","prominentWords","minimalNumberOfOccurrences","filter","word","getOccurrences","getWord","replace","sortProminentWords","sort","wordA","wordB","difference","getStem","localeCompare","collapseProminentWordsOnStem","length","collapsedProminentWords","previousWord","i","currentWord","setOccurrences","toLocaleLowerCase","setWord","push","retrieveAbbreviations","text","words","abbreviations","forEach","toLocaleUpperCase","computeProminentWords","stemmer","functionWords","uniqueContentWords","includes","trim","element","computeProminentWordsMemoized","join","getProminentWords","getWordsCustomHelper","getProminentWordsFromPaperAttributes","attributes","wordsFromAttributes"],"sources":["../../../../src/languageProcessing/helpers/prominentWords/determineProminentWords.js"],"sourcesContent":["import { memoize, uniq } from \"lodash\";\n\nimport getWords from \"../word/getWords\";\nimport { normalizeSingle } from \"../sanitize/quotes\";\nimport ProminentWord from \"../../values/ProminentWord\";\n\nconst specialCharacters = /[1234567890‘’“”\"'.…?!:;,¿¡«»&*@#±^%$|~=+§`[\\](){}⟨⟩<>/\\\\–\\-\\u2014\\u00d7\\s]/g;\n\n/**\n * Returns only those prominent words that occur more than a certain number of times and do not consist of special characters.\n *\n * @param {ProminentWord[]} prominentWords A list of prominent words.\n * @param {int} [minimalNumberOfOccurrences] A minimal number of occurrences that is needed for a relevant prominentWord, default 2.\n *\n * @returns {ProminentWord[]} Only relevant words.\n */\nfunction filterProminentWords( prominentWords, minimalNumberOfOccurrences = 2 ) {\n\tprominentWords = prominentWords.filter( function( word ) {\n\t\treturn (\n\t\t\tword.getOccurrences() >= minimalNumberOfOccurrences &&\n\t\t\tword.getWord().replace( specialCharacters, \"\" ) !== \"\"\n\t\t);\n\t} );\n\treturn prominentWords;\n}\n\n/**\n * Sorts prominent words based on their number of occurrences and length.\n *\n * @param {ProminentWord[]} prominentWords The prominent words to sort.\n *\n * @returns {void}\n */\nfunction sortProminentWords( prominentWords ) {\n\tprominentWords.sort( function( wordA, wordB ) {\n\t\tconst difference = wordB.getOccurrences() - wordA.getOccurrences();\n\t\t// The word with the highest number of occurrences comes first.\n\t\tif ( difference !== 0 ) {\n\t\t\treturn difference;\n\t\t}\n\n\t\t// In case of a tie on occurrence number, the alphabetically first word comes first.\n\t\treturn wordA.getStem().localeCompare( wordB.getStem() );\n\t} );\n}\n\n/**\n * Collapses prominent words that have the same stem.\n *\n * @param {ProminentWord[]} prominentWords All prominentWords.\n *\n * @returns {ProminentWord[]} The original array with collapsed duplicates.\n */\nfunction collapseProminentWordsOnStem( prominentWords ) {\n\tif ( prominentWords.length === 0 ) {\n\t\treturn [];\n\t}\n\n\t// Sort the input array by stem\n\tprominentWords.sort( function( wordA, wordB ) {\n\t\treturn wordA.getStem().localeCompare( wordB.getStem() );\n\t} );\n\n\tconst collapsedProminentWords = [];\n\tlet previousWord = new ProminentWord(\n\t\tprominentWords[ 0 ].getWord(),\n\t\tprominentWords[ 0 ].getStem(),\n\t\tprominentWords[ 0 ].getOccurrences()\n\t);\n\n\tfor ( let i = 1; i < prominentWords.length; i++ ) {\n\t\tconst currentWord = new ProminentWord(\n\t\t\tprominentWords[ i ].getWord(),\n\t\t\tprominentWords[ i ].getStem(),\n\t\t\tprominentWords[ i ].getOccurrences()\n\t\t);\n\n\t\t/*\n\t\t * Compare the stem of the current word in the loop with the previously available stem.\n\t\t * If they are equal, the word should be collapsed.\n\t\t * When collapsing, the numbers of occurrences get summed.\n\t\t * If the stem happens to equal the real word that occurred in the text, we can be sure it's ok to display it\n\t\t * to the customer. So, the stem reassigns the word.\n\t\t */\n\t\tif ( currentWord.getStem() ===  previousWord.getStem() ) {\n\t\t\tpreviousWord.setOccurrences( previousWord.getOccurrences() + currentWord.getOccurrences() );\n\n\t\t\tif ( currentWord.getWord() === previousWord.getStem() || currentWord.getWord().toLocaleLowerCase() === previousWord.getStem() ) {\n\t\t\t\tpreviousWord.setWord( currentWord.getWord() );\n\t\t\t}\n\t\t} else {\n\t\t\tcollapsedProminentWords.push( previousWord );\n\t\t\tpreviousWord = currentWord;\n\t\t}\n\t}\n\n\tcollapsedProminentWords.push( previousWord );\n\n\treturn collapsedProminentWords;\n}\n\n/**\n * Retrieves a list of all abbreviations from the text. Returns an empty array if the input text is empty.\n *\n * @param {string} text A text.\n *\n * @returns {string[]} A list of abbreviations from the list.\n */\nfunction retrieveAbbreviations( text ) {\n\tconst words = getWords( normalizeSingle( text ) );\n\tconst abbreviations = [];\n\n\twords.forEach( function( word ) {\n\t\tif ( word.length > 1 && word.length < 5 && word === word.toLocaleUpperCase() ) {\n\t\t\tabbreviations.push( word.toLocaleLowerCase() );\n\t\t}\n\t} );\n\n\treturn uniq( abbreviations );\n}\n\n/**\n * Computes prominent words from an array of words. In order to do so, checks whether the word is included in the list of\n * function words and determines the number of occurrences for every word. Then checks if any two words have the same stem\n * and if so collapses over them.\n *\n * @param {string[]} words          The words to determine relevance for.\n * @param {string[]} abbreviations  Abbreviations that should not be stemmed.\n * @param {Function} stemmer        The available stemmer.\n * @param {Array} functionWords     The available function words list.\n *\n * @returns {ProminentWord[]} All prominent words sorted and filtered for this text.\n */\nfunction computeProminentWords( words, abbreviations, stemmer, functionWords ) {\n\tif ( words.length === 0 ) {\n\t\treturn [];\n\t}\n\n\tconst uniqueContentWords = uniq( words.filter( word => ! functionWords.includes( word.trim() ) ) );\n\tconst prominentWords = [];\n\n\tuniqueContentWords.forEach( function( word ) {\n\t\tif ( abbreviations.includes( word ) ) {\n\t\t\tprominentWords.push( new ProminentWord(\n\t\t\t\tword.toLocaleUpperCase(),\n\t\t\t\tword,\n\t\t\t\twords.filter( element => element === word ).length\n\t\t\t) );\n\t\t} else {\n\t\t\tprominentWords.push( new ProminentWord(\n\t\t\t\tword,\n\t\t\t\tstemmer( word ),\n\t\t\t\twords.filter( element => element === word ).length\n\t\t\t) );\n\t\t}\n\t} );\n\n\treturn collapseProminentWordsOnStem( prominentWords );\n}\n\n/**\n * Caches prominent words depending on text words.\n * Only the words and abbreviations are used as the cache key as the stemmer and function words\n * are config and shouldn't change in the scope of one request.\n *\n * @param {string[]} words          The words to determine relevance for.\n * @param {string[]} abbreviations  Abbreviations that should not be stemmed.\n * @param {Function} stemmer        The available stemmer.\n * @param {Array} functionWords     The available function words list.\n *\n * @returns {function} The function that collects prominent words for a given set of text words, language and morphologyData.\n */\nconst computeProminentWordsMemoized = memoize( ( words, abbreviations, stemmer, functionWords ) => {\n\treturn computeProminentWords( words, abbreviations, stemmer, functionWords );\n}, ( words, abbreviations ) => {\n\treturn words.join( \",\" ) + \",\" + abbreviations.join( \",\" );\n} );\n\n\n/**\n * Gets prominent words from the paper text.\n *\n * @param {string} text             The text to retrieve the prominent words from.\n * @param {string[]} abbreviations  The abbreviations that occur in the text and attributes of the paper.\n * @param {Function} stemmer        The available stemmer.\n * @param {Array} functionWords     The available function words list.\n * @param {function} getWordsCustomHelper   The custom helper to get words.\n *\n * @returns {ProminentWord[]} All prominent words sorted and filtered for this text.\n */\nfunction getProminentWords( text, abbreviations, stemmer, functionWords, getWordsCustomHelper ) {\n\tif ( text === \"\" ) {\n\t\treturn [];\n\t}\n\n\tconst words = getWordsCustomHelper\n\t\t? getWordsCustomHelper( normalizeSingle( text ).toLocaleLowerCase() )\n\t\t: getWords( normalizeSingle( text ).toLocaleLowerCase() );\n\n\treturn computeProminentWordsMemoized( words, abbreviations, stemmer, functionWords );\n}\n\n/**\n * Gets prominent words from keyphrase and synonyms, metadescription, title, and subheadings.\n *\n * @param {string[]} attributes     The array with attributes to process.\n * @param {string[]} abbreviations  The abbreviations that occur in the text and attributes of the paper.\n * @param {Function} stemmer        The available stemmer.\n * @param {Array} functionWords     The available function words list.\n * @param {function} getWordsCustomHelper   The custom helper to get words.\n *\n * @returns {ProminentWord[]} Prominent words from the paper attributes.\n */\nfunction getProminentWordsFromPaperAttributes( attributes, abbreviations, stemmer, functionWords, getWordsCustomHelper ) {\n\tconst wordsFromAttributes = getWordsCustomHelper\n\t\t? getWordsCustomHelper( attributes.join( \" \" ).toLocaleLowerCase() )\n\t\t: getWords( attributes.join( \" \" ).toLocaleLowerCase() );\n\n\treturn computeProminentWords( wordsFromAttributes, abbreviations, stemmer, functionWords );\n}\n\nexport {\n\tgetProminentWords,\n\tgetProminentWordsFromPaperAttributes,\n\tfilterProminentWords,\n\tsortProminentWords,\n\tcollapseProminentWordsOnStem,\n\tretrieveAbbreviations,\n};\n\nexport default {\n\tgetProminentWords,\n\tgetProminentWordsFromPaperAttributes,\n\tfilterProminentWords,\n\tsortProminentWords,\n\tcollapseProminentWordsOnStem,\n\tretrieveAbbreviations,\n};\n"],"mappings":"AAAA,SAASA,OAAO,EAAEC,IAAI,QAAQ,QAAQ;AAEtC,OAAOC,QAAQ;AACf,SAASC,eAAe;AACxB,OAAOC,aAAa;AAEpB,MAAMC,iBAAiB,GAAG,6EAA6E;;AAEvG;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,oBAAoBA,CAAEC,cAAc,EAAEC,0BAA0B,GAAG,CAAC,EAAG;EAC/ED,cAAc,GAAGA,cAAc,CAACE,MAAM,CAAE,UAAUC,IAAI,EAAG;IACxD,OACCA,IAAI,CAACC,cAAc,CAAC,CAAC,IAAIH,0BAA0B,IACnDE,IAAI,CAACE,OAAO,CAAC,CAAC,CAACC,OAAO,CAAER,iBAAiB,EAAE,EAAG,CAAC,KAAK,EAAE;EAExD,CAAE,CAAC;EACH,OAAOE,cAAc;AACtB;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASO,kBAAkBA,CAAEP,cAAc,EAAG;EAC7CA,cAAc,CAACQ,IAAI,CAAE,UAAUC,KAAK,EAAEC,KAAK,EAAG;IAC7C,MAAMC,UAAU,GAAGD,KAAK,CAACN,cAAc,CAAC,CAAC,GAAGK,KAAK,CAACL,cAAc,CAAC,CAAC;IAClE;IACA,IAAKO,UAAU,KAAK,CAAC,EAAG;MACvB,OAAOA,UAAU;IAClB;;IAEA;IACA,OAAOF,KAAK,CAACG,OAAO,CAAC,CAAC,CAACC,aAAa,CAAEH,KAAK,CAACE,OAAO,CAAC,CAAE,CAAC;EACxD,CAAE,CAAC;AACJ;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASE,4BAA4BA,CAAEd,cAAc,EAAG;EACvD,IAAKA,cAAc,CAACe,MAAM,KAAK,CAAC,EAAG;IAClC,OAAO,EAAE;EACV;;EAEA;EACAf,cAAc,CAACQ,IAAI,CAAE,UAAUC,KAAK,EAAEC,KAAK,EAAG;IAC7C,OAAOD,KAAK,CAACG,OAAO,CAAC,CAAC,CAACC,aAAa,CAAEH,KAAK,CAACE,OAAO,CAAC,CAAE,CAAC;EACxD,CAAE,CAAC;EAEH,MAAMI,uBAAuB,GAAG,EAAE;EAClC,IAAIC,YAAY,GAAG,IAAIpB,aAAa,CACnCG,cAAc,CAAE,CAAC,CAAE,CAACK,OAAO,CAAC,CAAC,EAC7BL,cAAc,CAAE,CAAC,CAAE,CAACY,OAAO,CAAC,CAAC,EAC7BZ,cAAc,CAAE,CAAC,CAAE,CAACI,cAAc,CAAC,CACpC,CAAC;EAED,KAAM,IAAIc,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGlB,cAAc,CAACe,MAAM,EAAEG,CAAC,EAAE,EAAG;IACjD,MAAMC,WAAW,GAAG,IAAItB,aAAa,CACpCG,cAAc,CAAEkB,CAAC,CAAE,CAACb,OAAO,CAAC,CAAC,EAC7BL,cAAc,CAAEkB,CAAC,CAAE,CAACN,OAAO,CAAC,CAAC,EAC7BZ,cAAc,CAAEkB,CAAC,CAAE,CAACd,cAAc,CAAC,CACpC,CAAC;;IAED;AACF;AACA;AACA;AACA;AACA;AACA;IACE,IAAKe,WAAW,CAACP,OAAO,CAAC,CAAC,KAAMK,YAAY,CAACL,OAAO,CAAC,CAAC,EAAG;MACxDK,YAAY,CAACG,cAAc,CAAEH,YAAY,CAACb,cAAc,CAAC,CAAC,GAAGe,WAAW,CAACf,cAAc,CAAC,CAAE,CAAC;MAE3F,IAAKe,WAAW,CAACd,OAAO,CAAC,CAAC,KAAKY,YAAY,CAACL,OAAO,CAAC,CAAC,IAAIO,WAAW,CAACd,OAAO,CAAC,CAAC,CAACgB,iBAAiB,CAAC,CAAC,KAAKJ,YAAY,CAACL,OAAO,CAAC,CAAC,EAAG;QAC/HK,YAAY,CAACK,OAAO,CAAEH,WAAW,CAACd,OAAO,CAAC,CAAE,CAAC;MAC9C;IACD,CAAC,MAAM;MACNW,uBAAuB,CAACO,IAAI,CAAEN,YAAa,CAAC;MAC5CA,YAAY,GAAGE,WAAW;IAC3B;EACD;EAEAH,uBAAuB,CAACO,IAAI,CAAEN,YAAa,CAAC;EAE5C,OAAOD,uBAAuB;AAC/B;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASQ,qBAAqBA,CAAEC,IAAI,EAAG;EACtC,MAAMC,KAAK,GAAG/B,QAAQ,CAAEC,eAAe,CAAE6B,IAAK,CAAE,CAAC;EACjD,MAAME,aAAa,GAAG,EAAE;EAExBD,KAAK,CAACE,OAAO,CAAE,UAAUzB,IAAI,EAAG;IAC/B,IAAKA,IAAI,CAACY,MAAM,GAAG,CAAC,IAAIZ,IAAI,CAACY,MAAM,GAAG,CAAC,IAAIZ,IAAI,KAAKA,IAAI,CAAC0B,iBAAiB,CAAC,CAAC,EAAG;MAC9EF,aAAa,CAACJ,IAAI,CAAEpB,IAAI,CAACkB,iBAAiB,CAAC,CAAE,CAAC;IAC/C;EACD,CAAE,CAAC;EAEH,OAAO3B,IAAI,CAAEiC,aAAc,CAAC;AAC7B;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASG,qBAAqBA,CAAEJ,KAAK,EAAEC,aAAa,EAAEI,OAAO,EAAEC,aAAa,EAAG;EAC9E,IAAKN,KAAK,CAACX,MAAM,KAAK,CAAC,EAAG;IACzB,OAAO,EAAE;EACV;EAEA,MAAMkB,kBAAkB,GAAGvC,IAAI,CAAEgC,KAAK,CAACxB,MAAM,CAAEC,IAAI,IAAI,CAAE6B,aAAa,CAACE,QAAQ,CAAE/B,IAAI,CAACgC,IAAI,CAAC,CAAE,CAAE,CAAE,CAAC;EAClG,MAAMnC,cAAc,GAAG,EAAE;EAEzBiC,kBAAkB,CAACL,OAAO,CAAE,UAAUzB,IAAI,EAAG;IAC5C,IAAKwB,aAAa,CAACO,QAAQ,CAAE/B,IAAK,CAAC,EAAG;MACrCH,cAAc,CAACuB,IAAI,CAAE,IAAI1B,aAAa,CACrCM,IAAI,CAAC0B,iBAAiB,CAAC,CAAC,EACxB1B,IAAI,EACJuB,KAAK,CAACxB,MAAM,CAAEkC,OAAO,IAAIA,OAAO,KAAKjC,IAAK,CAAC,CAACY,MAC7C,CAAE,CAAC;IACJ,CAAC,MAAM;MACNf,cAAc,CAACuB,IAAI,CAAE,IAAI1B,aAAa,CACrCM,IAAI,EACJ4B,OAAO,CAAE5B,IAAK,CAAC,EACfuB,KAAK,CAACxB,MAAM,CAAEkC,OAAO,IAAIA,OAAO,KAAKjC,IAAK,CAAC,CAACY,MAC7C,CAAE,CAAC;IACJ;EACD,CAAE,CAAC;EAEH,OAAOD,4BAA4B,CAAEd,cAAe,CAAC;AACtD;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMqC,6BAA6B,GAAG5C,OAAO,CAAE,CAAEiC,KAAK,EAAEC,aAAa,EAAEI,OAAO,EAAEC,aAAa,KAAM;EAClG,OAAOF,qBAAqB,CAAEJ,KAAK,EAAEC,aAAa,EAAEI,OAAO,EAAEC,aAAc,CAAC;AAC7E,CAAC,EAAE,CAAEN,KAAK,EAAEC,aAAa,KAAM;EAC9B,OAAOD,KAAK,CAACY,IAAI,CAAE,GAAI,CAAC,GAAG,GAAG,GAAGX,aAAa,CAACW,IAAI,CAAE,GAAI,CAAC;AAC3D,CAAE,CAAC;;AAGH;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,iBAAiBA,CAAEd,IAAI,EAAEE,aAAa,EAAEI,OAAO,EAAEC,aAAa,EAAEQ,oBAAoB,EAAG;EAC/F,IAAKf,IAAI,KAAK,EAAE,EAAG;IAClB,OAAO,EAAE;EACV;EAEA,MAAMC,KAAK,GAAGc,oBAAoB,GAC/BA,oBAAoB,CAAE5C,eAAe,CAAE6B,IAAK,CAAC,CAACJ,iBAAiB,CAAC,CAAE,CAAC,GACnE1B,QAAQ,CAAEC,eAAe,CAAE6B,IAAK,CAAC,CAACJ,iBAAiB,CAAC,CAAE,CAAC;EAE1D,OAAOgB,6BAA6B,CAAEX,KAAK,EAAEC,aAAa,EAAEI,OAAO,EAAEC,aAAc,CAAC;AACrF;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASS,oCAAoCA,CAAEC,UAAU,EAAEf,aAAa,EAAEI,OAAO,EAAEC,aAAa,EAAEQ,oBAAoB,EAAG;EACxH,MAAMG,mBAAmB,GAAGH,oBAAoB,GAC7CA,oBAAoB,CAAEE,UAAU,CAACJ,IAAI,CAAE,GAAI,CAAC,CAACjB,iBAAiB,CAAC,CAAE,CAAC,GAClE1B,QAAQ,CAAE+C,UAAU,CAACJ,IAAI,CAAE,GAAI,CAAC,CAACjB,iBAAiB,CAAC,CAAE,CAAC;EAEzD,OAAOS,qBAAqB,CAAEa,mBAAmB,EAAEhB,aAAa,EAAEI,OAAO,EAAEC,aAAc,CAAC;AAC3F;AAEA,SACCO,iBAAiB,EACjBE,oCAAoC,EACpC1C,oBAAoB,EACpBQ,kBAAkB,EAClBO,4BAA4B,EAC5BU,qBAAqB;AAGtB,eAAe;EACde,iBAAiB;EACjBE,oCAAoC;EACpC1C,oBAAoB;EACpBQ,kBAAkB;EAClBO,4BAA4B;EAC5BU;AACD,CAAC","ignoreList":[]}

package/build/languageProcessing/helpers/regex/createRegexFromArray.js

@@ -0,0 +1,32 @@
+/** @module stringProcessing/createRegexFromArray */
+
+import { map } from "lodash";
+import addWordBoundary from "../word/addWordboundary.js";
+import replaceDiacritics from "../transliterate/replaceDiacritics";
+import sanitizeString from "../sanitize/sanitizeString";
+
+/**
+ * Creates a regex of combined strings from the input array.
+ *
+ * @param {string[]} array                      The array with strings
+ * @param {boolean} [disableWordBoundary=false] Boolean indicating whether or not to disable word boundaries.
+ * @param {string} [extraBoundary=""]           A string that is used as extra boundary for the regex.
+ * @param {boolean} [doReplaceDiacritics=false] If set to true, it replaces diacritics. Defaults to false.
+ *
+ * @returns {RegExp} regex                              The regex created from the array.
+ */
+export default function (array, disableWordBoundary = false, extraBoundary = "", doReplaceDiacritics = false) {
+  array = map(array, function (string) {
+    if (doReplaceDiacritics) {
+      string = replaceDiacritics(string);
+    }
+    string = sanitizeString(string);
+    if (disableWordBoundary) {
+      return string;
+    }
+    return addWordBoundary(string, true, extraBoundary);
+  });
+  const regexString = "(" + array.join(")|(") + ")";
+  return new RegExp(regexString, "ig");
+}
+//# sourceMappingURL=createRegexFromArray.js.map

package/build/languageProcessing/helpers/regex/createRegexFromArray.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"createRegexFromArray.js","names":["map","addWordBoundary","replaceDiacritics","sanitizeString","array","disableWordBoundary","extraBoundary","doReplaceDiacritics","string","regexString","join","RegExp"],"sources":["../../../../src/languageProcessing/helpers/regex/createRegexFromArray.js"],"sourcesContent":["/** @module stringProcessing/createRegexFromArray */\n\nimport { map } from \"lodash\";\nimport addWordBoundary from \"../word/addWordboundary.js\";\nimport replaceDiacritics from \"../transliterate/replaceDiacritics\";\nimport sanitizeString from \"../sanitize/sanitizeString\";\n\n/**\n * Creates a regex of combined strings from the input array.\n *\n * @param {string[]} array                      The array with strings\n * @param {boolean} [disableWordBoundary=false] Boolean indicating whether or not to disable word boundaries.\n * @param {string} [extraBoundary=\"\"]           A string that is used as extra boundary for the regex.\n * @param {boolean} [doReplaceDiacritics=false] If set to true, it replaces diacritics. Defaults to false.\n *\n * @returns {RegExp} regex                              The regex created from the array.\n */\nexport default function( array, disableWordBoundary = false, extraBoundary = \"\", doReplaceDiacritics = false ) {\n\tarray = map( array, function( string ) {\n\t\tif ( doReplaceDiacritics ) {\n\t\t\tstring = replaceDiacritics( string );\n\t\t}\n\n\t\tstring = sanitizeString( string );\n\n\t\tif ( disableWordBoundary ) {\n\t\t\treturn string;\n\t\t}\n\t\treturn addWordBoundary( string, true, extraBoundary );\n\t} );\n\n\tconst regexString = \"(\" + array.join( \")|(\" ) + \")\";\n\n\treturn new RegExp( regexString, \"ig\" );\n}\n"],"mappings":"AAAA;;AAEA,SAASA,GAAG,QAAQ,QAAQ;AAC5B,OAAOC,eAAe;AACtB,OAAOC,iBAAiB;AACxB,OAAOC,cAAc;;AAErB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,KAAK,EAAEC,mBAAmB,GAAG,KAAK,EAAEC,aAAa,GAAG,EAAE,EAAEC,mBAAmB,GAAG,KAAK,EAAG;EAC9GH,KAAK,GAAGJ,GAAG,CAAEI,KAAK,EAAE,UAAUI,MAAM,EAAG;IACtC,IAAKD,mBAAmB,EAAG;MAC1BC,MAAM,GAAGN,iBAAiB,CAAEM,MAAO,CAAC;IACrC;IAEAA,MAAM,GAAGL,cAAc,CAAEK,MAAO,CAAC;IAEjC,IAAKH,mBAAmB,EAAG;MAC1B,OAAOG,MAAM;IACd;IACA,OAAOP,eAAe,CAAEO,MAAM,EAAE,IAAI,EAAEF,aAAc,CAAC;EACtD,CAAE,CAAC;EAEH,MAAMG,WAAW,GAAG,GAAG,GAAGL,KAAK,CAACM,IAAI,CAAE,KAAM,CAAC,GAAG,GAAG;EAEnD,OAAO,IAAIC,MAAM,CAAEF,WAAW,EAAE,IAAK,CAAC;AACvC","ignoreList":[]}

package/build/languageProcessing/helpers/regex/createRegexFromDoubleArray.js

@@ -0,0 +1,33 @@
+/** @module stringProcessing/createRegexFromDoubleArray */
+
+import addWordBoundary from "../word/addWordboundary.js";
+
+/**
+ * Creates a regex string of combined strings from the input array.
+ *
+ * @param {array} array The array containing the various parts of a transition word combination.
+ *
+ * @returns {array} The array with replaced entries.
+ */
+const wordCombinationToRegexString = function (array) {
+  array = array.map(function (word) {
+    return addWordBoundary(word);
+  });
+  return array.join("(.*?)");
+};
+
+/**
+ * Creates a regex of combined strings from the input array, containing arrays with two entries.
+ *
+ * @param {array} array The array containing arrays.
+ *
+ * @returns {RegExp} The regex created from the array.
+ */
+export default function (array) {
+  array = array.map(function (wordCombination) {
+    return wordCombinationToRegexString(wordCombination);
+  });
+  const regexString = "(" + array.join(")|(") + ")";
+  return new RegExp(regexString, "ig");
+}
+//# sourceMappingURL=createRegexFromDoubleArray.js.map

package/build/languageProcessing/helpers/regex/createRegexFromDoubleArray.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"createRegexFromDoubleArray.js","names":["addWordBoundary","wordCombinationToRegexString","array","map","word","join","wordCombination","regexString","RegExp"],"sources":["../../../../src/languageProcessing/helpers/regex/createRegexFromDoubleArray.js"],"sourcesContent":["/** @module stringProcessing/createRegexFromDoubleArray */\n\nimport addWordBoundary from \"../word/addWordboundary.js\";\n\n/**\n * Creates a regex string of combined strings from the input array.\n *\n * @param {array} array The array containing the various parts of a transition word combination.\n *\n * @returns {array} The array with replaced entries.\n */\nconst wordCombinationToRegexString = function( array ) {\n\tarray = array.map( function( word ) {\n\t\treturn addWordBoundary( word );\n\t} );\n\treturn array.join( \"(.*?)\" );\n};\n\n/**\n * Creates a regex of combined strings from the input array, containing arrays with two entries.\n *\n * @param {array} array The array containing arrays.\n *\n * @returns {RegExp} The regex created from the array.\n */\nexport default function( array ) {\n\tarray = array.map( function( wordCombination ) {\n\t\treturn wordCombinationToRegexString( wordCombination );\n\t} );\n\n\tconst regexString = \"(\" + array.join( \")|(\" ) + \")\";\n\n\treturn new RegExp( regexString, \"ig\" );\n}\n"],"mappings":"AAAA;;AAEA,OAAOA,eAAe;;AAEtB;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,4BAA4B,GAAG,SAAAA,CAAUC,KAAK,EAAG;EACtDA,KAAK,GAAGA,KAAK,CAACC,GAAG,CAAE,UAAUC,IAAI,EAAG;IACnC,OAAOJ,eAAe,CAAEI,IAAK,CAAC;EAC/B,CAAE,CAAC;EACH,OAAOF,KAAK,CAACG,IAAI,CAAE,OAAQ,CAAC;AAC7B,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUH,KAAK,EAAG;EAChCA,KAAK,GAAGA,KAAK,CAACC,GAAG,CAAE,UAAUG,eAAe,EAAG;IAC9C,OAAOL,4BAA4B,CAAEK,eAAgB,CAAC;EACvD,CAAE,CAAC;EAEH,MAAMC,WAAW,GAAG,GAAG,GAAGL,KAAK,CAACG,IAAI,CAAE,KAAM,CAAC,GAAG,GAAG;EAEnD,OAAO,IAAIG,MAAM,CAAED,WAAW,EAAE,IAAK,CAAC;AACvC","ignoreList":[]}

package/build/languageProcessing/helpers/regex/createWordRegex.js

@@ -0,0 +1,28 @@
+/** @module stringProcessing/stringToRegex */
+import { escapeRegExp, isUndefined, memoize } from "lodash";
+import sanitizeString from "../sanitize/sanitizeString";
+import replaceDiacritics from "../transliterate/replaceDiacritics.js";
+import addWordBoundary from "../word/addWordboundary.js";
+
+/**
+ * Creates a regex from a string so it can be matched everywhere in the same way.
+ *
+ * @param {string}  string                     The string to make a regex from.
+ * @param {string}  [extraBoundary=""]         A string that is used as extra boundary for the regex.
+ * @param {boolean} [doReplaceDiacritics=true] If set to false, it doesn't replace diacritics. Defaults to true.
+ *
+ * @returns {RegExp} regex The regex made from the keyword
+ */
+export default memoize(function (string, extraBoundary, doReplaceDiacritics) {
+  if (isUndefined(extraBoundary)) {
+    extraBoundary = "";
+  }
+  if (isUndefined(doReplaceDiacritics) || doReplaceDiacritics === true) {
+    string = replaceDiacritics(string);
+  }
+  string = sanitizeString(string);
+  string = escapeRegExp(string);
+  string = addWordBoundary(string, false, extraBoundary);
+  return new RegExp(string, "ig");
+});
+//# sourceMappingURL=createWordRegex.js.map

package/build/languageProcessing/helpers/regex/createWordRegex.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"createWordRegex.js","names":["escapeRegExp","isUndefined","memoize","sanitizeString","replaceDiacritics","addWordBoundary","string","extraBoundary","doReplaceDiacritics","RegExp"],"sources":["../../../../src/languageProcessing/helpers/regex/createWordRegex.js"],"sourcesContent":["/** @module stringProcessing/stringToRegex */\nimport { escapeRegExp, isUndefined, memoize } from \"lodash\";\nimport sanitizeString from \"../sanitize/sanitizeString\";\nimport replaceDiacritics from \"../transliterate/replaceDiacritics.js\";\nimport addWordBoundary from \"../word/addWordboundary.js\";\n\n/**\n * Creates a regex from a string so it can be matched everywhere in the same way.\n *\n * @param {string}  string                     The string to make a regex from.\n * @param {string}  [extraBoundary=\"\"]         A string that is used as extra boundary for the regex.\n * @param {boolean} [doReplaceDiacritics=true] If set to false, it doesn't replace diacritics. Defaults to true.\n *\n * @returns {RegExp} regex The regex made from the keyword\n */\nexport default memoize( function( string, extraBoundary, doReplaceDiacritics ) {\n\tif ( isUndefined( extraBoundary ) ) {\n\t\textraBoundary = \"\";\n\t}\n\n\tif ( isUndefined( doReplaceDiacritics ) || doReplaceDiacritics === true ) {\n\t\tstring = replaceDiacritics( string );\n\t}\n\n\tstring = sanitizeString( string );\n\tstring = escapeRegExp( string );\n\tstring = addWordBoundary( string, false, extraBoundary );\n\n\treturn new RegExp( string, \"ig\" );\n} );\n"],"mappings":"AAAA;AACA,SAASA,YAAY,EAAEC,WAAW,EAAEC,OAAO,QAAQ,QAAQ;AAC3D,OAAOC,cAAc;AACrB,OAAOC,iBAAiB;AACxB,OAAOC,eAAe;;AAEtB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAeH,OAAO,CAAE,UAAUI,MAAM,EAAEC,aAAa,EAAEC,mBAAmB,EAAG;EAC9E,IAAKP,WAAW,CAAEM,aAAc,CAAC,EAAG;IACnCA,aAAa,GAAG,EAAE;EACnB;EAEA,IAAKN,WAAW,CAAEO,mBAAoB,CAAC,IAAIA,mBAAmB,KAAK,IAAI,EAAG;IACzEF,MAAM,GAAGF,iBAAiB,CAAEE,MAAO,CAAC;EACrC;EAEAA,MAAM,GAAGH,cAAc,CAAEG,MAAO,CAAC;EACjCA,MAAM,GAAGN,YAAY,CAAEM,MAAO,CAAC;EAC/BA,MAAM,GAAGD,eAAe,CAAEC,MAAM,EAAE,KAAK,EAAEC,aAAc,CAAC;EAExD,OAAO,IAAIE,MAAM,CAAEH,MAAM,EAAE,IAAK,CAAC;AAClC,CAAE,CAAC","ignoreList":[]}

package/build/languageProcessing/helpers/regex/matchStringWithRegex.js

@@ -0,0 +1,18 @@
+/** @module stringProcessing/matchStringWithRegex */
+
+/**
+ * Checks a string with a regex, return all matches found with that regex.
+ *
+ * @param {String} 		text        The text to match.
+ * @param {object} 		regex  		A compiled regular expression.
+ *
+ * @returns {Array} Array with matches, empty array if no matches found.
+ */
+export default function (text, regex) {
+  let matches = text.match(regex);
+  if (matches === null) {
+    matches = [];
+  }
+  return matches;
+}
+//# sourceMappingURL=matchStringWithRegex.js.map

package/build/languageProcessing/helpers/regex/matchStringWithRegex.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"matchStringWithRegex.js","names":["text","regex","matches","match"],"sources":["../../../../src/languageProcessing/helpers/regex/matchStringWithRegex.js"],"sourcesContent":["/** @module stringProcessing/matchStringWithRegex */\n\n/**\n * Checks a string with a regex, return all matches found with that regex.\n *\n * @param {String} \t\ttext        The text to match.\n * @param {object} \t\tregex  \t\tA compiled regular expression.\n *\n * @returns {Array} Array with matches, empty array if no matches found.\n */\nexport default function( text, regex ) {\n\tlet matches = text.match( regex );\n\n\tif ( matches === null ) {\n\t\tmatches = [];\n\t}\n\n\treturn matches;\n}\n"],"mappings":"AAAA;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUA,IAAI,EAAEC,KAAK,EAAG;EACtC,IAAIC,OAAO,GAAGF,IAAI,CAACG,KAAK,CAAEF,KAAM,CAAC;EAEjC,IAAKC,OAAO,KAAK,IAAI,EAAG;IACvBA,OAAO,GAAG,EAAE;EACb;EAEA,OAAOA,OAAO;AACf","ignoreList":[]}

package/build/languageProcessing/helpers/regex/searchAndReplaceWithOneRegex.js

@@ -0,0 +1,15 @@
+/**
+ * Checks whether a given regex matches a given word and if so, performs the replacement.
+ *
+ * @param {string}      word 					The word that may need to be modified.
+ * @param {string[]}    regexAndReplacement     A regex and the required replacement.
+ *
+ * @returns {?string} The modified stem or undefined if no match was found.
+ */
+export default function searchAndReplaceWithOneRegex(word, regexAndReplacement) {
+  if (word.search(new RegExp(regexAndReplacement[0])) !== -1) {
+    word = word.replace(new RegExp(regexAndReplacement[0]), regexAndReplacement[1]);
+    return word;
+  }
+}
+//# sourceMappingURL=searchAndReplaceWithOneRegex.js.map

package/build/languageProcessing/helpers/regex/searchAndReplaceWithOneRegex.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"searchAndReplaceWithOneRegex.js","names":["searchAndReplaceWithOneRegex","word","regexAndReplacement","search","RegExp","replace"],"sources":["../../../../src/languageProcessing/helpers/regex/searchAndReplaceWithOneRegex.js"],"sourcesContent":["/**\n * Checks whether a given regex matches a given word and if so, performs the replacement.\n *\n * @param {string}      word \t\t\t\t\tThe word that may need to be modified.\n * @param {string[]}    regexAndReplacement     A regex and the required replacement.\n *\n * @returns {?string} The modified stem or undefined if no match was found.\n */\nexport default function searchAndReplaceWithOneRegex( word, regexAndReplacement ) {\n\tif ( word.search( new RegExp( regexAndReplacement[ 0 ] ) ) !== -1 ) {\n\t\tword = word.replace( new RegExp( regexAndReplacement[ 0 ] ), regexAndReplacement[ 1 ] );\n\t\treturn word;\n\t}\n}\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASA,4BAA4BA,CAAEC,IAAI,EAAEC,mBAAmB,EAAG;EACjF,IAAKD,IAAI,CAACE,MAAM,CAAE,IAAIC,MAAM,CAAEF,mBAAmB,CAAE,CAAC,CAAG,CAAE,CAAC,KAAK,CAAC,CAAC,EAAG;IACnED,IAAI,GAAGA,IAAI,CAACI,OAAO,CAAE,IAAID,MAAM,CAAEF,mBAAmB,CAAE,CAAC,CAAG,CAAC,EAAEA,mBAAmB,CAAE,CAAC,CAAG,CAAC;IACvF,OAAOD,IAAI;EACZ;AACD","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/doubleQuotes.js

@@ -0,0 +1,13 @@
+/**
+ * Returns an array with double quotes.
+ *
+ * Japanese-specific quotes:
+ * U300c - left corner bracket.
+ * U300d - right corner bracket.
+ * U300e - left white corner bracket.
+ * U300f - right white corner bracket.
+ *
+ * @returns {string[]} The array with double quotes..
+ */
+export default ["“", "”", "〝", "〞", "〟", "‟", "„", "\"", "\u300c", "\u300d", "\u300e", "\u300f"];
+//# sourceMappingURL=doubleQuotes.js.map

package/build/languageProcessing/helpers/sanitize/doubleQuotes.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"doubleQuotes.js","names":[],"sources":["../../../../src/languageProcessing/helpers/sanitize/doubleQuotes.js"],"sourcesContent":["/**\n * Returns an array with double quotes.\n *\n * Japanese-specific quotes:\n * U300c - left corner bracket.\n * U300d - right corner bracket.\n * U300e - left white corner bracket.\n * U300f - right white corner bracket.\n *\n * @returns {string[]} The array with double quotes..\n */\nexport default [ \"“\", \"”\", \"〝\", \"〞\", \"〟\", \"‟\", \"„\", \"\\\"\", \"\\u300c\", \"\\u300d\", \"\\u300e\", \"\\u300f\" ];\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,CAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,QAAQ,EAAE,QAAQ,CAAE","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/filterShortcodesFromTree.js

@@ -0,0 +1,123 @@
+/**
+ * Creates a regex to filter shortcodes from HTML.
+ * @param {string[]} shortcodeTags The tags of the shortcodes to filter.
+ * @returns {RegExp} The regex to recognize the shortcodes.
+ */
+export const createShortcodeTagsRegex = shortcodeTags => {
+  const shortcodeTagsRegexString = `\\[\\/?(${shortcodeTags.join("|")})[^\\]]*\\]`;
+  return new RegExp(shortcodeTagsRegexString, "g");
+};
+
+/**
+ * Filters shortcodes from HTML string.
+ * @param {string} html The HTML to filter.
+ * @param {string[]} shortcodeTags The tags of the shortcodes to filter.
+ * @returns {string} The filtered HTML.
+ */
+export const filterShortcodesFromHTML = (html, shortcodeTags) => {
+  if (!shortcodeTags || shortcodeTags.length === 0) {
+    return html;
+  }
+  const shortcodeTagsRegex = createShortcodeTagsRegex(shortcodeTags);
+  return html.replace(shortcodeTagsRegex, "");
+};
+
+/**
+ * Checks if a token is part of an opening shortcode.
+ * @param {Token[]} tokens The tokens to check.
+ * @param {number} index The index of the current token.
+ * @returns {boolean} Whether the token is part of an opening shortcode.
+ */
+const tokenIsPartOfOpeningShortcode = (tokens, index) => {
+  return tokens[index - 1] && tokens[index - 1].text === "[";
+};
+
+/**
+ * Checks if a token is part of a closing shortcode.
+ * @param {Token[]} tokens The tokens to check.
+ * @param {number} index The index of the current token.
+ * @returns {boolean} Whether the token is part of a closing shortcode.
+ */
+const tokenIsPartOfClosingShortcode = (tokens, index) => {
+  return tokens[index - 1] && tokens[index - 1].text === "/" && tokens[index - 2] && tokens[index - 2].text === "[";
+};
+
+/**
+ * Checks if a token is part of a shortcode.
+ * @param {Token[]} tokens The tokens to check.
+ * @param {number} index The index of the current token.
+ * @param {string[]} shortcodeTags An array of active shortcode tags.
+ * @param {boolean} encounteredClosingBracket Whether a closing bracket has been encountered (while looping backwards through the tokens).
+ * @returns {boolean} Whether the token is part of a shortcode.
+ */
+const tokenIsShortcode = (tokens, index, shortcodeTags, encounteredClosingBracket) => {
+  return encounteredClosingBracket && shortcodeTags.includes(tokens[index].text) && (tokenIsPartOfOpeningShortcode(tokens, index) || tokenIsPartOfClosingShortcode(tokens, index));
+};
+
+/**
+ * Filters shortcodes from a sentence.
+ * @param {Sentence} sentence The sentence to filter.
+ * @param {string[]} shortcodeTags The tags of the shortcodes to filter.
+ * @param {RegExp} shortcodeTagsRegex The regex to filter the shortcodes.
+ * @returns {void}
+ *
+ */
+const filterShortcodesFromSentence = (sentence, shortcodeTags, shortcodeTagsRegex) => {
+  const tokens = sentence.tokens;
+  let encounteredClosingBracket = false;
+  // traverse through tokens backwards
+  for (let i = tokens.length - 1; i >= 0; i--) {
+    if (tokens[i].text === "]") {
+      encounteredClosingBracket = true;
+    }
+    if (tokenIsShortcode(tokens, i, shortcodeTags, encounteredClosingBracket)) {
+      while (tokens[i].text !== "]") {
+        tokens.splice(i, 1);
+      }
+      tokens.splice(i, 1);
+      encounteredClosingBracket = false;
+      while (tokens[i - 1] && "[/".includes(tokens[i - 1].text)) {
+        tokens.splice(i - 1, 1);
+        i--;
+      }
+    }
+  }
+  sentence.tokens = tokens;
+  sentence.text = sentence.text.replace(shortcodeTagsRegex, "");
+};
+
+/**
+ * A recursive function that filters shortcodes from sentences.
+ * @param {Node} tree The tree to filter.
+ * @param {string[]} shortcodeTags The tags of the shortcodes to filter.
+ * @param {RegExp} shortcodeTagsRegex The regex to filter the shortcodes.
+ * @returns {void}
+ */
+const filterShortcodesFromSentences = (tree, shortcodeTags, shortcodeTagsRegex) => {
+  if (tree.sentences) {
+    tree.sentences.forEach(sentence => {
+      filterShortcodesFromSentence(sentence, shortcodeTags, shortcodeTagsRegex);
+    });
+  }
+  if (tree.childNodes) {
+    tree.childNodes.forEach(childNode => {
+      filterShortcodesFromSentences(childNode, shortcodeTags, shortcodeTagsRegex);
+    });
+  }
+};
+
+/**
+ * Filters shortcodes from the tree.
+ * @param {Node} tree The tree to filter.
+ * @param {string[]} shortcodeTags The tags of the shortcodes to filter.
+ * @returns {void}
+ */
+const filterShortcodesFromTree = (tree, shortcodeTags) => {
+  if (!shortcodeTags || shortcodeTags.length === 0) {
+    return;
+  }
+  const shortcodeTagsRegex = createShortcodeTagsRegex(shortcodeTags);
+  filterShortcodesFromSentences(tree, shortcodeTags, shortcodeTagsRegex);
+};
+export default filterShortcodesFromTree;
+//# sourceMappingURL=filterShortcodesFromTree.js.map

package/build/languageProcessing/helpers/sanitize/filterShortcodesFromTree.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"filterShortcodesFromTree.js","names":["createShortcodeTagsRegex","shortcodeTags","shortcodeTagsRegexString","join","RegExp","filterShortcodesFromHTML","html","length","shortcodeTagsRegex","replace","tokenIsPartOfOpeningShortcode","tokens","index","text","tokenIsPartOfClosingShortcode","tokenIsShortcode","encounteredClosingBracket","includes","filterShortcodesFromSentence","sentence","i","splice","filterShortcodesFromSentences","tree","sentences","forEach","childNodes","childNode","filterShortcodesFromTree"],"sources":["../../../../src/languageProcessing/helpers/sanitize/filterShortcodesFromTree.js"],"sourcesContent":["\n/**\n * Creates a regex to filter shortcodes from HTML.\n * @param {string[]} shortcodeTags The tags of the shortcodes to filter.\n * @returns {RegExp} The regex to recognize the shortcodes.\n */\nexport const createShortcodeTagsRegex = shortcodeTags => {\n\tconst shortcodeTagsRegexString = `\\\\[\\\\/?(${ shortcodeTags.join( \"|\" ) })[^\\\\]]*\\\\]`;\n\treturn new RegExp( shortcodeTagsRegexString, \"g\" );\n};\n\n/**\n * Filters shortcodes from HTML string.\n * @param {string} html The HTML to filter.\n * @param {string[]} shortcodeTags The tags of the shortcodes to filter.\n * @returns {string} The filtered HTML.\n */\nexport const filterShortcodesFromHTML = ( html, shortcodeTags ) => {\n\tif ( ! shortcodeTags || shortcodeTags.length === 0 ) {\n\t\treturn html;\n\t}\n\tconst shortcodeTagsRegex = createShortcodeTagsRegex( shortcodeTags );\n\treturn html.replace( shortcodeTagsRegex, \"\" );\n};\n\n/**\n * Checks if a token is part of an opening shortcode.\n * @param {Token[]} tokens The tokens to check.\n * @param {number} index The index of the current token.\n * @returns {boolean} Whether the token is part of an opening shortcode.\n */\nconst tokenIsPartOfOpeningShortcode = ( tokens, index ) => {\n\treturn tokens[ index - 1 ] && tokens[ index - 1 ].text === \"[\";\n};\n\n/**\n * Checks if a token is part of a closing shortcode.\n * @param {Token[]} tokens The tokens to check.\n * @param {number} index The index of the current token.\n * @returns {boolean} Whether the token is part of a closing shortcode.\n */\nconst tokenIsPartOfClosingShortcode = ( tokens, index ) => {\n\treturn  tokens[ index - 1 ] && tokens[ index - 1 ].text === \"/\"  && tokens[ index - 2 ]  && tokens[ index - 2 ].text === \"[\";\n};\n\n/**\n * Checks if a token is part of a shortcode.\n * @param {Token[]} tokens The tokens to check.\n * @param {number} index The index of the current token.\n * @param {string[]} shortcodeTags An array of active shortcode tags.\n * @param {boolean} encounteredClosingBracket Whether a closing bracket has been encountered (while looping backwards through the tokens).\n * @returns {boolean} Whether the token is part of a shortcode.\n */\nconst tokenIsShortcode = ( tokens, index, shortcodeTags, encounteredClosingBracket ) => {\n\treturn encounteredClosingBracket && shortcodeTags.includes( tokens[ index ].text ) &&\n\t\t( tokenIsPartOfOpeningShortcode( tokens, index ) || tokenIsPartOfClosingShortcode( tokens, index )  );\n};\n\n/**\n * Filters shortcodes from a sentence.\n * @param {Sentence} sentence The sentence to filter.\n * @param {string[]} shortcodeTags The tags of the shortcodes to filter.\n * @param {RegExp} shortcodeTagsRegex The regex to filter the shortcodes.\n * @returns {void}\n *\n */\nconst filterShortcodesFromSentence = ( sentence, shortcodeTags, shortcodeTagsRegex ) => {\n\tconst tokens = sentence.tokens;\n\n\tlet encounteredClosingBracket = false;\n\t// traverse through tokens backwards\n\tfor ( let i = tokens.length - 1; i >= 0; i-- ) {\n\t\tif ( tokens[ i ].text === \"]\" ) {\n\t\t\tencounteredClosingBracket = true;\n\t\t}\n\n\t\tif ( tokenIsShortcode( tokens, i, shortcodeTags, encounteredClosingBracket ) ) {\n\t\t\twhile ( tokens[ i ].text !== \"]\" ) {\n\t\t\t\ttokens.splice( i, 1 );\n\t\t\t}\n\t\t\ttokens.splice( i, 1 );\n\t\t\tencounteredClosingBracket = false;\n\n\t\t\twhile ( tokens[ i - 1 ] && \"[/\".includes( tokens[ i - 1 ].text ) ) {\n\t\t\t\ttokens.splice( i - 1, 1 );\n\t\t\t\ti--;\n\t\t\t}\n\t\t}\n\t}\n\tsentence.tokens = tokens;\n\n\tsentence.text = sentence.text.replace( shortcodeTagsRegex, \"\" );\n};\n\n/**\n * A recursive function that filters shortcodes from sentences.\n * @param {Node} tree The tree to filter.\n * @param {string[]} shortcodeTags The tags of the shortcodes to filter.\n * @param {RegExp} shortcodeTagsRegex The regex to filter the shortcodes.\n * @returns {void}\n */\nconst filterShortcodesFromSentences = ( tree, shortcodeTags, shortcodeTagsRegex ) => {\n\tif ( tree.sentences ) {\n\t\ttree.sentences.forEach( sentence => {\n\t\t\tfilterShortcodesFromSentence( sentence, shortcodeTags, shortcodeTagsRegex );\n\t\t} );\n\t}\n\n\tif ( tree.childNodes ) {\n\t\ttree.childNodes.forEach( childNode => {\n\t\t\tfilterShortcodesFromSentences( childNode, shortcodeTags, shortcodeTagsRegex );\n\t\t} );\n\t}\n};\n\n/**\n * Filters shortcodes from the tree.\n * @param {Node} tree The tree to filter.\n * @param {string[]} shortcodeTags The tags of the shortcodes to filter.\n * @returns {void}\n */\nconst filterShortcodesFromTree = ( tree, shortcodeTags ) => {\n\tif ( ! shortcodeTags || shortcodeTags.length === 0 ) {\n\t\treturn;\n\t}\n\tconst shortcodeTagsRegex = createShortcodeTagsRegex( shortcodeTags );\n\n\tfilterShortcodesFromSentences( tree, shortcodeTags, shortcodeTagsRegex );\n};\n\nexport default filterShortcodesFromTree;\n"],"mappings":"AACA;AACA;AACA;AACA;AACA;AACA,OAAO,MAAMA,wBAAwB,GAAGC,aAAa,IAAI;EACxD,MAAMC,wBAAwB,GAAG,WAAYD,aAAa,CAACE,IAAI,CAAE,GAAI,CAAC,aAAc;EACpF,OAAO,IAAIC,MAAM,CAAEF,wBAAwB,EAAE,GAAI,CAAC;AACnD,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,MAAMG,wBAAwB,GAAGA,CAAEC,IAAI,EAAEL,aAAa,KAAM;EAClE,IAAK,CAAEA,aAAa,IAAIA,aAAa,CAACM,MAAM,KAAK,CAAC,EAAG;IACpD,OAAOD,IAAI;EACZ;EACA,MAAME,kBAAkB,GAAGR,wBAAwB,CAAEC,aAAc,CAAC;EACpE,OAAOK,IAAI,CAACG,OAAO,CAAED,kBAAkB,EAAE,EAAG,CAAC;AAC9C,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,6BAA6B,GAAGA,CAAEC,MAAM,EAAEC,KAAK,KAAM;EAC1D,OAAOD,MAAM,CAAEC,KAAK,GAAG,CAAC,CAAE,IAAID,MAAM,CAAEC,KAAK,GAAG,CAAC,CAAE,CAACC,IAAI,KAAK,GAAG;AAC/D,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,6BAA6B,GAAGA,CAAEH,MAAM,EAAEC,KAAK,KAAM;EAC1D,OAAQD,MAAM,CAAEC,KAAK,GAAG,CAAC,CAAE,IAAID,MAAM,CAAEC,KAAK,GAAG,CAAC,CAAE,CAACC,IAAI,KAAK,GAAG,IAAKF,MAAM,CAAEC,KAAK,GAAG,CAAC,CAAE,IAAKD,MAAM,CAAEC,KAAK,GAAG,CAAC,CAAE,CAACC,IAAI,KAAK,GAAG;AAC7H,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,gBAAgB,GAAGA,CAAEJ,MAAM,EAAEC,KAAK,EAAEX,aAAa,EAAEe,yBAAyB,KAAM;EACvF,OAAOA,yBAAyB,IAAIf,aAAa,CAACgB,QAAQ,CAAEN,MAAM,CAAEC,KAAK,CAAE,CAACC,IAAK,CAAC,KAC/EH,6BAA6B,CAAEC,MAAM,EAAEC,KAAM,CAAC,IAAIE,6BAA6B,CAAEH,MAAM,EAAEC,KAAM,CAAC,CAAG;AACvG,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMM,4BAA4B,GAAGA,CAAEC,QAAQ,EAAElB,aAAa,EAAEO,kBAAkB,KAAM;EACvF,MAAMG,MAAM,GAAGQ,QAAQ,CAACR,MAAM;EAE9B,IAAIK,yBAAyB,GAAG,KAAK;EACrC;EACA,KAAM,IAAII,CAAC,GAAGT,MAAM,CAACJ,MAAM,GAAG,CAAC,EAAEa,CAAC,IAAI,CAAC,EAAEA,CAAC,EAAE,EAAG;IAC9C,IAAKT,MAAM,CAAES,CAAC,CAAE,CAACP,IAAI,KAAK,GAAG,EAAG;MAC/BG,yBAAyB,GAAG,IAAI;IACjC;IAEA,IAAKD,gBAAgB,CAAEJ,MAAM,EAAES,CAAC,EAAEnB,aAAa,EAAEe,yBAA0B,CAAC,EAAG;MAC9E,OAAQL,MAAM,CAAES,CAAC,CAAE,CAACP,IAAI,KAAK,GAAG,EAAG;QAClCF,MAAM,CAACU,MAAM,CAAED,CAAC,EAAE,CAAE,CAAC;MACtB;MACAT,MAAM,CAACU,MAAM,CAAED,CAAC,EAAE,CAAE,CAAC;MACrBJ,yBAAyB,GAAG,KAAK;MAEjC,OAAQL,MAAM,CAAES,CAAC,GAAG,CAAC,CAAE,IAAI,IAAI,CAACH,QAAQ,CAAEN,MAAM,CAAES,CAAC,GAAG,CAAC,CAAE,CAACP,IAAK,CAAC,EAAG;QAClEF,MAAM,CAACU,MAAM,CAAED,CAAC,GAAG,CAAC,EAAE,CAAE,CAAC;QACzBA,CAAC,EAAE;MACJ;IACD;EACD;EACAD,QAAQ,CAACR,MAAM,GAAGA,MAAM;EAExBQ,QAAQ,CAACN,IAAI,GAAGM,QAAQ,CAACN,IAAI,CAACJ,OAAO,CAAED,kBAAkB,EAAE,EAAG,CAAC;AAChE,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMc,6BAA6B,GAAGA,CAAEC,IAAI,EAAEtB,aAAa,EAAEO,kBAAkB,KAAM;EACpF,IAAKe,IAAI,CAACC,SAAS,EAAG;IACrBD,IAAI,CAACC,SAAS,CAACC,OAAO,CAAEN,QAAQ,IAAI;MACnCD,4BAA4B,CAAEC,QAAQ,EAAElB,aAAa,EAAEO,kBAAmB,CAAC;IAC5E,CAAE,CAAC;EACJ;EAEA,IAAKe,IAAI,CAACG,UAAU,EAAG;IACtBH,IAAI,CAACG,UAAU,CAACD,OAAO,CAAEE,SAAS,IAAI;MACrCL,6BAA6B,CAAEK,SAAS,EAAE1B,aAAa,EAAEO,kBAAmB,CAAC;IAC9E,CAAE,CAAC;EACJ;AACD,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA,MAAMoB,wBAAwB,GAAGA,CAAEL,IAAI,EAAEtB,aAAa,KAAM;EAC3D,IAAK,CAAEA,aAAa,IAAIA,aAAa,CAACM,MAAM,KAAK,CAAC,EAAG;IACpD;EACD;EACA,MAAMC,kBAAkB,GAAGR,wBAAwB,CAAEC,aAAc,CAAC;EAEpEqB,6BAA6B,CAAEC,IAAI,EAAEtB,aAAa,EAAEO,kBAAmB,CAAC;AACzE,CAAC;AAED,eAAeoB,wBAAwB","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/mergeListItems.js

@@ -0,0 +1,24 @@
+/**
+ * Removes list-related html tags in a text to be used for the keyphrase distribution assessment.
+ * That way, lists with single words don't result in a skewed keyphrase distribution result.
+ *
+ * @param {string}  text    The text in which to remove the list structures.
+ *
+ * @returns {string} The text with all list structures removed.
+ */
+export function mergeListItems(text) {
+  const listTags = /<\/?(o|ul)(?:[^>]+)?>/g;
+  const listItemTags = /\s?<\/?li(?:[^>]+)?>\s?/g;
+
+  /*
+   * Steps:
+   * 1) Remove all ul and ol tags.
+   * 2) Replace all li tags with spaces to avoid list items being stuck together.
+   * 3) Replace multiple instances of whitespace with a single instance.
+   */
+  text = text.replace(listTags, "");
+  text = text.replace(listItemTags, " ");
+  text = text.replace(/\s+/g, " ");
+  return text;
+}
+//# sourceMappingURL=mergeListItems.js.map

package/build/languageProcessing/helpers/sanitize/mergeListItems.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"mergeListItems.js","names":["mergeListItems","text","listTags","listItemTags","replace"],"sources":["../../../../src/languageProcessing/helpers/sanitize/mergeListItems.js"],"sourcesContent":["/**\n * Removes list-related html tags in a text to be used for the keyphrase distribution assessment.\n * That way, lists with single words don't result in a skewed keyphrase distribution result.\n *\n * @param {string}  text    The text in which to remove the list structures.\n *\n * @returns {string} The text with all list structures removed.\n */\nexport function mergeListItems( text ) {\n\tconst listTags = /<\\/?(o|ul)(?:[^>]+)?>/g;\n\tconst listItemTags = /\\s?<\\/?li(?:[^>]+)?>\\s?/g;\n\n\t/*\n\t * Steps:\n\t * 1) Remove all ul and ol tags.\n\t * 2) Replace all li tags with spaces to avoid list items being stuck together.\n\t * 3) Replace multiple instances of whitespace with a single instance.\n\t */\n\ttext = text.replace( listTags, \"\" );\n\ttext = text.replace( listItemTags, \" \" );\n\ttext = text.replace( /\\s+/g, \" \" );\n\n\treturn text;\n}\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,SAASA,cAAcA,CAAEC,IAAI,EAAG;EACtC,MAAMC,QAAQ,GAAG,wBAAwB;EACzC,MAAMC,YAAY,GAAG,0BAA0B;;EAE/C;AACD;AACA;AACA;AACA;AACA;EACCF,IAAI,GAAGA,IAAI,CAACG,OAAO,CAAEF,QAAQ,EAAE,EAAG,CAAC;EACnCD,IAAI,GAAGA,IAAI,CAACG,OAAO,CAAED,YAAY,EAAE,GAAI,CAAC;EACxCF,IAAI,GAAGA,IAAI,CAACG,OAAO,CAAE,MAAM,EAAE,GAAI,CAAC;EAElC,OAAOH,IAAI;AACZ","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/parseSynonyms.js

@@ -0,0 +1,18 @@
+/** @module stringProcessing/parseSynonyms */
+
+import stripSpaces from "./stripSpaces.js";
+import removePunctuationExceptQuotes from "./removePunctuationExceptQuotes.js";
+
+/**
+ * Parses synonyms from a comma-separated string into an array.
+ *
+ * @param {String} synonyms The text to match
+ *
+ * @returns {Array} An array with all synonyms.
+ */
+export default function (synonyms) {
+  let synonymsSplit = synonyms.split(",");
+  synonymsSplit = synonymsSplit.map(synonym => removePunctuationExceptQuotes(stripSpaces(synonym))).filter(synonym => synonym);
+  return synonymsSplit;
+}
+//# sourceMappingURL=parseSynonyms.js.map

package/build/languageProcessing/helpers/sanitize/parseSynonyms.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"parseSynonyms.js","names":["stripSpaces","removePunctuationExceptQuotes","synonyms","synonymsSplit","split","map","synonym","filter"],"sources":["../../../../src/languageProcessing/helpers/sanitize/parseSynonyms.js"],"sourcesContent":["/** @module stringProcessing/parseSynonyms */\n\nimport stripSpaces from \"./stripSpaces.js\";\nimport removePunctuationExceptQuotes from \"./removePunctuationExceptQuotes.js\";\n\n/**\n * Parses synonyms from a comma-separated string into an array.\n *\n * @param {String} synonyms The text to match\n *\n * @returns {Array} An array with all synonyms.\n */\nexport default function( synonyms ) {\n\tlet synonymsSplit = synonyms.split( \",\" );\n\n\tsynonymsSplit = synonymsSplit.map( synonym =>\n\t\tremovePunctuationExceptQuotes( stripSpaces( synonym ) ) ).filter( synonym => synonym );\n\n\treturn synonymsSplit;\n}\n"],"mappings":"AAAA;;AAEA,OAAOA,WAAW;AAClB,OAAOC,6BAA6B;;AAEpC;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,QAAQ,EAAG;EACnC,IAAIC,aAAa,GAAGD,QAAQ,CAACE,KAAK,CAAE,GAAI,CAAC;EAEzCD,aAAa,GAAGA,aAAa,CAACE,GAAG,CAAEC,OAAO,IACzCL,6BAA6B,CAAED,WAAW,CAAEM,OAAQ,CAAE,CAAE,CAAC,CAACC,MAAM,CAAED,OAAO,IAAIA,OAAQ,CAAC;EAEvF,OAAOH,aAAa;AACrB","ignoreList":[]}