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

package/build/languageProcessing/languages/ja/customResearches/findKeyphraseInSEOTitle.js

@@ -0,0 +1,96 @@
+import { isEmpty } from "lodash";
+import { findWordFormsInString } from "../../../helpers/match/findKeywordFormsInString";
+import wordMatch from "../../../helpers/match/matchTextWithArray";
+import processExactMatchRequest from "../../../helpers/match/processExactMatchRequest";
+import getContentWords from "../helpers/getContentWords";
+import japaneseWordMatchHelper from "../helpers/matchTextWithWord";
+import functionWords from "../config/functionWords";
+import getWords from "../helpers/getWords";
+
+/**
+ * Checks the position of the keyphrase in the SEO title.
+ *
+ * @param {string} title    The SEO title of the paper.
+ * @param {number} position The position of the keyphrase in the SEO title.
+ *
+ * @returns {number} Potentially adjusted position of the keyphrase in the SEO title.
+ */
+function adjustPosition(title, position) {
+  // Don't do anything if position if already 0.
+  if (position === 0) {
+    return position;
+  }
+
+  // Retrieve the SEO title words before the keyphrase.
+  let titleBeforeKeyword = title.substring(0, position);
+  titleBeforeKeyword = getWords(titleBeforeKeyword);
+  // Retrieve the non-function words.
+  titleBeforeKeyword = titleBeforeKeyword.filter(word => !functionWords.includes(word));
+  if (isEmpty(titleBeforeKeyword)) {
+    /*
+     * Return position 0 if there are no words left in the SEO title before the keyword after filtering
+     * the function words (such that "楽しい旅行" in "その楽しい旅行" is still counted as position 0).
+    	 */
+    return 0;
+  }
+  return position;
+}
+
+/**
+ * Checks the occurrences of the keyphrase in the SEO title. Returns a result that contains information on
+ * (1) whether all the keyphrase forms are found,
+ * (2) the lowest number of the positions of the matches, and
+ * (3) whether the exact match keyphrase is requested.
+ *
+ * @param {Object} paper 			The paper containing SEO title and keyword.
+ * @param {Researcher} researcher 	The researcher to use for analysis.
+ *
+ * @returns {Object} An object containing these info: (1) whether all the keyphrase forms are found,
+ * (2) the lowest number of the positions of the matches, and (3) whether the exact match keyphrase is requested.
+ */
+export default function (paper, researcher) {
+  const title = paper.getTitle();
+  let keyphrase = paper.getKeyword();
+  const result = {
+    allWordsFound: false,
+    position: -1,
+    exactMatchKeyphrase: false
+  };
+
+  /*
+   * Check if the keyword is enclosed in quotation mark.
+   * If yes, remove the quotation marks and check if the exact match of the keyphrase is found in the SEO title.
+   */
+  const exactMatchRequest = processExactMatchRequest(keyphrase);
+  if (exactMatchRequest.exactMatchRequested) {
+    result.exactMatchKeyphrase = true;
+
+    // Check if the exact match of the keyphrase is found in the SEO title and directly return the result if there is no match.
+    if (!title.includes(exactMatchRequest.keyphrase)) {
+      return result;
+    }
+    keyphrase = getContentWords(exactMatchRequest.keyphrase);
+    const keyphraseMatched = wordMatch(title, keyphrase, "ja", japaneseWordMatchHelper);
+
+    // It's an exact match if the length of the matched keyphrase is the same as the keyphrase length.
+    if (keyphraseMatched.matches.length === keyphrase.length) {
+      result.allWordsFound = true;
+      result.position = adjustPosition(title, keyphraseMatched.position);
+    }
+    /*
+     * When the exact match process is requested, we don't need to run the check for the different word forms,
+     * and return the result here.
+     */
+    return result;
+  }
+
+  // Get the forms of the keyphrase (using the morphology research).
+  const keyphraseForms = researcher.getResearch("morphology").keyphraseForms;
+  const separateWordFormsMatched = findWordFormsInString(keyphraseForms, title, "ja", japaneseWordMatchHelper);
+  if (separateWordFormsMatched.percentWordMatches === 100) {
+    result.allWordsFound = true;
+    result.position = adjustPosition(title, separateWordFormsMatched.position);
+  }
+  return result;
+}
+//# sourceMappingURL=findKeyphraseInSEOTitle.js.map

package/build/languageProcessing/languages/ja/customResearches/findKeyphraseInSEOTitle.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"findKeyphraseInSEOTitle.js","names":["isEmpty","findWordFormsInString","wordMatch","processExactMatchRequest","getContentWords","japaneseWordMatchHelper","functionWords","getWords","adjustPosition","title","position","titleBeforeKeyword","substring","filter","word","includes","paper","researcher","getTitle","keyphrase","getKeyword","result","allWordsFound","exactMatchKeyphrase","exactMatchRequest","exactMatchRequested","keyphraseMatched","matches","length","keyphraseForms","getResearch","separateWordFormsMatched","percentWordMatches"],"sources":["../../../../../src/languageProcessing/languages/ja/customResearches/findKeyphraseInSEOTitle.js"],"sourcesContent":["import { isEmpty } from \"lodash\";\nimport { findWordFormsInString } from \"../../../helpers/match/findKeywordFormsInString\";\nimport wordMatch from \"../../../helpers/match/matchTextWithArray\";\nimport processExactMatchRequest from \"../../../helpers/match/processExactMatchRequest\";\nimport getContentWords from \"../helpers/getContentWords\";\nimport japaneseWordMatchHelper from \"../helpers/matchTextWithWord\";\nimport functionWords from \"../config/functionWords\";\nimport getWords from \"../helpers/getWords\";\n\n/**\n * Checks the position of the keyphrase in the SEO title.\n *\n * @param {string} title    The SEO title of the paper.\n * @param {number} position The position of the keyphrase in the SEO title.\n *\n * @returns {number} Potentially adjusted position of the keyphrase in the SEO title.\n */\nfunction adjustPosition( title, position ) {\n\t// Don't do anything if position if already 0.\n\tif ( position === 0 ) {\n\t\treturn position;\n\t}\n\n\t// Retrieve the SEO title words before the keyphrase.\n\tlet titleBeforeKeyword = title.substring( 0, position );\n\ttitleBeforeKeyword = getWords( titleBeforeKeyword );\n\t// Retrieve the non-function words.\n\ttitleBeforeKeyword = titleBeforeKeyword.filter( word => ! functionWords.includes( word ) );\n\n\tif ( isEmpty( titleBeforeKeyword ) ) {\n\t\t/*\n\t\t * Return position 0 if there are no words left in the SEO title before the keyword after filtering\n\t\t * the function words (such that \"楽しい旅行\" in \"その楽しい旅行\" is still counted as position 0).\n \t\t */\n\t\treturn 0;\n\t}\n\n\treturn position;\n}\n\n/**\n * Checks the occurrences of the keyphrase in the SEO title. Returns a result that contains information on\n * (1) whether all the keyphrase forms are found,\n * (2) the lowest number of the positions of the matches, and\n * (3) whether the exact match keyphrase is requested.\n *\n * @param {Object} paper \t\t\tThe paper containing SEO title and keyword.\n * @param {Researcher} researcher \tThe researcher to use for analysis.\n *\n * @returns {Object} An object containing these info: (1) whether all the keyphrase forms are found,\n * (2) the lowest number of the positions of the matches, and (3) whether the exact match keyphrase is requested.\n */\nexport default function( paper, researcher ) {\n\tconst title = paper.getTitle();\n\tlet keyphrase = paper.getKeyword();\n\n\tconst result = { allWordsFound: false, position: -1, exactMatchKeyphrase: false  };\n\n\t/*\n\t * Check if the keyword is enclosed in quotation mark.\n\t * If yes, remove the quotation marks and check if the exact match of the keyphrase is found in the SEO title.\n\t */\n\tconst exactMatchRequest = processExactMatchRequest( keyphrase );\n\tif ( exactMatchRequest.exactMatchRequested ) {\n\t\tresult.exactMatchKeyphrase = true;\n\n\t\t// Check if the exact match of the keyphrase is found in the SEO title and directly return the result if there is no match.\n\t\tif ( ! title.includes( exactMatchRequest.keyphrase ) ) {\n\t\t\treturn result;\n\t\t}\n\n\t\tkeyphrase = getContentWords( exactMatchRequest.keyphrase );\n\n\t\tconst keyphraseMatched = wordMatch( title, keyphrase, \"ja\", japaneseWordMatchHelper );\n\n\t\t// It's an exact match if the length of the matched keyphrase is the same as the keyphrase length.\n\t\tif ( keyphraseMatched.matches.length === keyphrase.length ) {\n\t\t\tresult.allWordsFound = true;\n\t\t\tresult.position = adjustPosition( title, keyphraseMatched.position );\n\t\t}\n\t\t/*\n\t\t * When the exact match process is requested, we don't need to run the check for the different word forms,\n\t\t * and return the result here.\n\t\t */\n\t\treturn result;\n\t}\n\n\t// Get the forms of the keyphrase (using the morphology research).\n\tconst keyphraseForms = researcher.getResearch( \"morphology\" ).keyphraseForms;\n\tconst separateWordFormsMatched = findWordFormsInString( keyphraseForms, title, \"ja\", japaneseWordMatchHelper );\n\n\tif ( separateWordFormsMatched.percentWordMatches === 100 ) {\n\t\tresult.allWordsFound = true;\n\t\tresult.position = adjustPosition( title, separateWordFormsMatched.position );\n\t}\n\n\treturn result;\n}\n"],"mappings":"AAAA,SAASA,OAAO,QAAQ,QAAQ;AAChC,SAASC,qBAAqB;AAC9B,OAAOC,SAAS;AAChB,OAAOC,wBAAwB;AAC/B,OAAOC,eAAe;AACtB,OAAOC,uBAAuB;AAC9B,OAAOC,aAAa;AACpB,OAAOC,QAAQ;;AAEf;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,cAAcA,CAAEC,KAAK,EAAEC,QAAQ,EAAG;EAC1C;EACA,IAAKA,QAAQ,KAAK,CAAC,EAAG;IACrB,OAAOA,QAAQ;EAChB;;EAEA;EACA,IAAIC,kBAAkB,GAAGF,KAAK,CAACG,SAAS,CAAE,CAAC,EAAEF,QAAS,CAAC;EACvDC,kBAAkB,GAAGJ,QAAQ,CAAEI,kBAAmB,CAAC;EACnD;EACAA,kBAAkB,GAAGA,kBAAkB,CAACE,MAAM,CAAEC,IAAI,IAAI,CAAER,aAAa,CAACS,QAAQ,CAAED,IAAK,CAAE,CAAC;EAE1F,IAAKd,OAAO,CAAEW,kBAAmB,CAAC,EAAG;IACpC;AACF;AACA;AACA;IACE,OAAO,CAAC;EACT;EAEA,OAAOD,QAAQ;AAChB;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUM,KAAK,EAAEC,UAAU,EAAG;EAC5C,MAAMR,KAAK,GAAGO,KAAK,CAACE,QAAQ,CAAC,CAAC;EAC9B,IAAIC,SAAS,GAAGH,KAAK,CAACI,UAAU,CAAC,CAAC;EAElC,MAAMC,MAAM,GAAG;IAAEC,aAAa,EAAE,KAAK;IAAEZ,QAAQ,EAAE,CAAC,CAAC;IAAEa,mBAAmB,EAAE;EAAO,CAAC;;EAElF;AACD;AACA;AACA;EACC,MAAMC,iBAAiB,GAAGrB,wBAAwB,CAAEgB,SAAU,CAAC;EAC/D,IAAKK,iBAAiB,CAACC,mBAAmB,EAAG;IAC5CJ,MAAM,CAACE,mBAAmB,GAAG,IAAI;;IAEjC;IACA,IAAK,CAAEd,KAAK,CAACM,QAAQ,CAAES,iBAAiB,CAACL,SAAU,CAAC,EAAG;MACtD,OAAOE,MAAM;IACd;IAEAF,SAAS,GAAGf,eAAe,CAAEoB,iBAAiB,CAACL,SAAU,CAAC;IAE1D,MAAMO,gBAAgB,GAAGxB,SAAS,CAAEO,KAAK,EAAEU,SAAS,EAAE,IAAI,EAAEd,uBAAwB,CAAC;;IAErF;IACA,IAAKqB,gBAAgB,CAACC,OAAO,CAACC,MAAM,KAAKT,SAAS,CAACS,MAAM,EAAG;MAC3DP,MAAM,CAACC,aAAa,GAAG,IAAI;MAC3BD,MAAM,CAACX,QAAQ,GAAGF,cAAc,CAAEC,KAAK,EAAEiB,gBAAgB,CAAChB,QAAS,CAAC;IACrE;IACA;AACF;AACA;AACA;IACE,OAAOW,MAAM;EACd;;EAEA;EACA,MAAMQ,cAAc,GAAGZ,UAAU,CAACa,WAAW,CAAE,YAAa,CAAC,CAACD,cAAc;EAC5E,MAAME,wBAAwB,GAAG9B,qBAAqB,CAAE4B,cAAc,EAAEpB,KAAK,EAAE,IAAI,EAAEJ,uBAAwB,CAAC;EAE9G,IAAK0B,wBAAwB,CAACC,kBAAkB,KAAK,GAAG,EAAG;IAC1DX,MAAM,CAACC,aAAa,GAAG,IAAI;IAC3BD,MAAM,CAACX,QAAQ,GAAGF,cAAc,CAAEC,KAAK,EAAEsB,wBAAwB,CAACrB,QAAS,CAAC;EAC7E;EAEA,OAAOW,MAAM;AACd","ignoreList":[]}

package/build/languageProcessing/languages/ja/customResearches/getKeyphraseLength.js

@@ -0,0 +1,19 @@
+import getWords from "../helpers/getWords";
+import characterCountHelper from "../helpers/wordsCharacterCount";
+
+/**
+ * Calculates the character length of the keyphrase.
+ *
+ * @param {Paper} paper The paper to research
+ *
+ * @returns {Object} The length of the keyphrase and an empty array of function words.
+ */
+export default function (paper) {
+  const keyphrase = getWords(paper.getKeyword());
+  return {
+    keyphraseLength: characterCountHelper(keyphrase),
+    // Returns empty array because we don't take function words into account for Japanese keyphrase length calculations.
+    functionWords: []
+  };
+}
+//# sourceMappingURL=getKeyphraseLength.js.map

package/build/languageProcessing/languages/ja/customResearches/getKeyphraseLength.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getKeyphraseLength.js","names":["getWords","characterCountHelper","paper","keyphrase","getKeyword","keyphraseLength","functionWords"],"sources":["../../../../../src/languageProcessing/languages/ja/customResearches/getKeyphraseLength.js"],"sourcesContent":["import getWords from \"../helpers/getWords\";\nimport characterCountHelper from \"../helpers/wordsCharacterCount\";\n\n/**\n * Calculates the character length of the keyphrase.\n *\n * @param {Paper} paper The paper to research\n *\n * @returns {Object} The length of the keyphrase and an empty array of function words.\n */\nexport default function( paper ) {\n\tconst keyphrase = getWords( paper.getKeyword() );\n\n\treturn {\n\t\tkeyphraseLength: characterCountHelper( keyphrase ),\n\t\t// Returns empty array because we don't take function words into account for Japanese keyphrase length calculations.\n\t\tfunctionWords: [],\n\t};\n}\n"],"mappings":"AAAA,OAAOA,QAAQ;AACf,OAAOC,oBAAoB;;AAE3B;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,KAAK,EAAG;EAChC,MAAMC,SAAS,GAAGH,QAAQ,CAAEE,KAAK,CAACE,UAAU,CAAC,CAAE,CAAC;EAEhD,OAAO;IACNC,eAAe,EAAEJ,oBAAoB,CAAEE,SAAU,CAAC;IAClD;IACAG,aAAa,EAAE;EAChB,CAAC;AACF","ignoreList":[]}

package/build/languageProcessing/languages/ja/customResearches/getWordForms.js

@@ -0,0 +1,51 @@
+import { get } from "lodash";
+import parseSynonyms from "../../../helpers/sanitize/parseSynonyms";
+import getContentWords from "../helpers/getContentWords";
+import createWordForms from "../helpers/internal/createWordForms";
+import doubleQuotes from "../../../helpers/sanitize/doubleQuotes";
+
+/**
+ * Creates word forms for each word in the given keyphrase.
+ *
+ * @param {string}      keyphrase   The keyphrase to generate word forms for.
+ * @param {Researcher}  researcher  The researcher.
+ *
+ * @returns {Array<string[]>} The word forms for each word in the keyphrase.
+ */
+function getKeyphraseForms(keyphrase, researcher) {
+  // The keyphrase is in double quotes: use it as an exact match keyphrase.
+  if (doubleQuotes.includes(keyphrase[0]) && doubleQuotes.includes(keyphrase[keyphrase.length - 1])) {
+    return [[keyphrase]];
+  }
+  const keyphraseWords = getContentWords(keyphrase);
+
+  // If the keyphrase does not contain content words, return an empty list.
+  if (keyphraseWords.length === 0) {
+    return [[]];
+  }
+  const morphologyData = get(researcher.getData("morphology"), "ja", false);
+  return keyphraseWords.map(word => morphologyData ? createWordForms(word, morphologyData) : [word]);
+}
+
+/**
+ * Gets all matching word forms for the keyphrase and synonyms.
+ *
+ * @param {Paper}       paper       The paper.
+ * @param {Researcher}  researcher  The researcher.
+ *
+ * @returns {Object} Object with an array of keyphrase forms and an array of arrays of synonyms forms, based on the forms
+ * found in the text or created forms.
+ */
+export default function (paper, researcher) {
+  let keyphrase = paper.getKeyword().toLocaleLowerCase("ja").trim();
+  // Remove spaces from the keyphrase.
+  keyphrase = keyphrase.replace(/\s/g, "");
+  const synonyms = parseSynonyms(paper.getSynonyms().toLocaleLowerCase("ja").trim());
+  const keyphraseForms = getKeyphraseForms(keyphrase, researcher);
+  const synonymsForms = synonyms.map(synonym => getKeyphraseForms(synonym, researcher));
+  return {
+    keyphraseForms,
+    synonymsForms
+  };
+}
+//# sourceMappingURL=getWordForms.js.map

package/build/languageProcessing/languages/ja/customResearches/getWordForms.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getWordForms.js","names":["get","parseSynonyms","getContentWords","createWordForms","doubleQuotes","getKeyphraseForms","keyphrase","researcher","includes","length","keyphraseWords","morphologyData","getData","map","word","paper","getKeyword","toLocaleLowerCase","trim","replace","synonyms","getSynonyms","keyphraseForms","synonymsForms","synonym"],"sources":["../../../../../src/languageProcessing/languages/ja/customResearches/getWordForms.js"],"sourcesContent":["import { get } from \"lodash\";\nimport parseSynonyms from \"../../../helpers/sanitize/parseSynonyms\";\nimport getContentWords from \"../helpers/getContentWords\";\nimport createWordForms from \"../helpers/internal/createWordForms\";\nimport doubleQuotes from \"../../../helpers/sanitize/doubleQuotes\";\n\n/**\n * Creates word forms for each word in the given keyphrase.\n *\n * @param {string}      keyphrase   The keyphrase to generate word forms for.\n * @param {Researcher}  researcher  The researcher.\n *\n * @returns {Array<string[]>} The word forms for each word in the keyphrase.\n */\nfunction getKeyphraseForms( keyphrase, researcher ) {\n\t// The keyphrase is in double quotes: use it as an exact match keyphrase.\n\tif ( doubleQuotes.includes( keyphrase[ 0 ] ) && doubleQuotes.includes( keyphrase[ keyphrase.length - 1 ] ) ) {\n\t\treturn [ [ keyphrase ] ];\n\t}\n\n\tconst keyphraseWords = getContentWords( keyphrase );\n\n\t// If the keyphrase does not contain content words, return an empty list.\n\tif ( keyphraseWords.length === 0 ) {\n\t\treturn [ [] ];\n\t}\n\n\tconst morphologyData = get( researcher.getData( \"morphology\" ), \"ja\", false );\n\treturn keyphraseWords.map( word => morphologyData ? createWordForms( word, morphologyData ) : [ word ] );\n}\n\n/**\n * Gets all matching word forms for the keyphrase and synonyms.\n *\n * @param {Paper}       paper       The paper.\n * @param {Researcher}  researcher  The researcher.\n *\n * @returns {Object} Object with an array of keyphrase forms and an array of arrays of synonyms forms, based on the forms\n * found in the text or created forms.\n */\nexport default function( paper, researcher ) {\n\tlet keyphrase = paper.getKeyword().toLocaleLowerCase( \"ja\" ).trim();\n\t// Remove spaces from the keyphrase.\n\tkeyphrase = keyphrase.replace( /\\s/g, \"\" );\n\tconst synonyms = parseSynonyms( paper.getSynonyms().toLocaleLowerCase( \"ja\" ).trim() );\n\tconst keyphraseForms = getKeyphraseForms( keyphrase, researcher );\n\tconst synonymsForms = synonyms.map( synonym => getKeyphraseForms( synonym, researcher ) );\n\n\treturn { keyphraseForms, synonymsForms };\n}\n"],"mappings":"AAAA,SAASA,GAAG,QAAQ,QAAQ;AAC5B,OAAOC,aAAa;AACpB,OAAOC,eAAe;AACtB,OAAOC,eAAe;AACtB,OAAOC,YAAY;;AAEnB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,iBAAiBA,CAAEC,SAAS,EAAEC,UAAU,EAAG;EACnD;EACA,IAAKH,YAAY,CAACI,QAAQ,CAAEF,SAAS,CAAE,CAAC,CAAG,CAAC,IAAIF,YAAY,CAACI,QAAQ,CAAEF,SAAS,CAAEA,SAAS,CAACG,MAAM,GAAG,CAAC,CAAG,CAAC,EAAG;IAC5G,OAAO,CAAE,CAAEH,SAAS,CAAE,CAAE;EACzB;EAEA,MAAMI,cAAc,GAAGR,eAAe,CAAEI,SAAU,CAAC;;EAEnD;EACA,IAAKI,cAAc,CAACD,MAAM,KAAK,CAAC,EAAG;IAClC,OAAO,CAAE,EAAE,CAAE;EACd;EAEA,MAAME,cAAc,GAAGX,GAAG,CAAEO,UAAU,CAACK,OAAO,CAAE,YAAa,CAAC,EAAE,IAAI,EAAE,KAAM,CAAC;EAC7E,OAAOF,cAAc,CAACG,GAAG,CAAEC,IAAI,IAAIH,cAAc,GAAGR,eAAe,CAAEW,IAAI,EAAEH,cAAe,CAAC,GAAG,CAAEG,IAAI,CAAG,CAAC;AACzG;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,KAAK,EAAER,UAAU,EAAG;EAC5C,IAAID,SAAS,GAAGS,KAAK,CAACC,UAAU,CAAC,CAAC,CAACC,iBAAiB,CAAE,IAAK,CAAC,CAACC,IAAI,CAAC,CAAC;EACnE;EACAZ,SAAS,GAAGA,SAAS,CAACa,OAAO,CAAE,KAAK,EAAE,EAAG,CAAC;EAC1C,MAAMC,QAAQ,GAAGnB,aAAa,CAAEc,KAAK,CAACM,WAAW,CAAC,CAAC,CAACJ,iBAAiB,CAAE,IAAK,CAAC,CAACC,IAAI,CAAC,CAAE,CAAC;EACtF,MAAMI,cAAc,GAAGjB,iBAAiB,CAAEC,SAAS,EAAEC,UAAW,CAAC;EACjE,MAAMgB,aAAa,GAAGH,QAAQ,CAACP,GAAG,CAAEW,OAAO,IAAInB,iBAAiB,CAAEmB,OAAO,EAAEjB,UAAW,CAAE,CAAC;EAEzF,OAAO;IAAEe,cAAc;IAAEC;EAAc,CAAC;AACzC","ignoreList":[]}

package/build/languageProcessing/languages/ja/customResearches/textLength.js

@@ -0,0 +1,25 @@
+import countCharacters from "../helpers/countCharacters";
+
+/**
+ * A result of the character count calculation.
+ *
+ * @typedef CharacterCountResult
+ * @param {number} count The number of characters found in the text.
+ * @param {string} unit The unit used in the text length calculations, always "character".
+ */
+
+/**
+ * Count the characters in the text.
+ *
+ * @param {Paper} paper The Paper object.
+ *
+ * @returns {CharacterCountResult} The number of characters found in the text, plus "character" as the unit used in calculating the text length.
+ */
+export default function (paper) {
+  return {
+    text: paper.getText(),
+    count: countCharacters(paper.getText()),
+    unit: "character"
+  };
+}
+//# sourceMappingURL=textLength.js.map

package/build/languageProcessing/languages/ja/customResearches/textLength.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"textLength.js","names":["countCharacters","paper","text","getText","count","unit"],"sources":["../../../../../src/languageProcessing/languages/ja/customResearches/textLength.js"],"sourcesContent":["import countCharacters from \"../helpers/countCharacters\";\n\n/**\n * A result of the character count calculation.\n *\n * @typedef CharacterCountResult\n * @param {number} count The number of characters found in the text.\n * @param {string} unit The unit used in the text length calculations, always \"character\".\n */\n\n/**\n * Count the characters in the text.\n *\n * @param {Paper} paper The Paper object.\n *\n * @returns {CharacterCountResult} The number of characters found in the text, plus \"character\" as the unit used in calculating the text length.\n */\nexport default function( paper ) {\n\treturn {\n\t\ttext: paper.getText(),\n\t\tcount: countCharacters( paper.getText() ),\n\t\tunit: \"character\",\n\t};\n}\n"],"mappings":"AAAA,OAAOA,eAAe;;AAEtB;AACA;AACA;AACA;AACA;AACA;AACA;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,KAAK,EAAG;EAChC,OAAO;IACNC,IAAI,EAAED,KAAK,CAACE,OAAO,CAAC,CAAC;IACrBC,KAAK,EAAEJ,eAAe,CAAEC,KAAK,CAACE,OAAO,CAAC,CAAE,CAAC;IACzCE,IAAI,EAAE;EACP,CAAC;AACF","ignoreList":[]}

package/build/languageProcessing/languages/ja/helpers/countCharacters.js

@@ -0,0 +1,21 @@
+import { languageProcessing } from "../../../../index.js";
+const {
+  sanitizeString
+} = languageProcessing;
+import removeURLs from "../../../helpers/sanitize/removeURLs.js";
+
+/**
+ * Calculates the character count which serves as a measure of text length.
+ * The character count includes letters, punctuation, and numbers. It doesn't include URLs, HTML tags, and spaces.
+ *
+ * @param {string} text The text to be counted.
+ *
+ * @returns {number} The character count of the given text.
+ */
+export default function (text) {
+  text = removeURLs(text);
+  text = sanitizeString(text);
+  text = text.replace(/\s/g, '');
+  return text.length;
+}
+//# sourceMappingURL=countCharacters.js.map

package/build/languageProcessing/languages/ja/helpers/countCharacters.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"countCharacters.js","names":["languageProcessing","sanitizeString","removeURLs","text","replace","length"],"sources":["../../../../../src/languageProcessing/languages/ja/helpers/countCharacters.js"],"sourcesContent":["import {languageProcessing} from '@axyseo/index.js';\nconst {sanitizeString} = languageProcessing;\nimport removeURLs from '../../../helpers/sanitize/removeURLs.js';\n\n/**\n * Calculates the character count which serves as a measure of text length.\n * The character count includes letters, punctuation, and numbers. It doesn't include URLs, HTML tags, and spaces.\n *\n * @param {string} text The text to be counted.\n *\n * @returns {number} The character count of the given text.\n */\nexport default function(text) {\n  text = removeURLs(text);\n  text = sanitizeString(text);\n  text = text.replace(/\\s/g, '');\n\n  return text.length;\n}\n"],"mappings":"AAAA,SAAQA,kBAAkB;AAC1B,MAAM;EAACC;AAAc,CAAC,GAAGD,kBAAkB;AAC3C,OAAOE,UAAU;;AAEjB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAASC,IAAI,EAAE;EAC5BA,IAAI,GAAGD,UAAU,CAACC,IAAI,CAAC;EACvBA,IAAI,GAAGF,cAAc,CAACE,IAAI,CAAC;EAC3BA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAC,KAAK,EAAE,EAAE,CAAC;EAE9B,OAAOD,IAAI,CAACE,MAAM;AACpB","ignoreList":[]}

package/build/languageProcessing/languages/ja/helpers/customGetStemmer.js

@@ -0,0 +1,22 @@
+import { get } from 'lodash';
+import { languageProcessing } from "../../../../index.js";
+const {
+  baseStemmer
+} = languageProcessing;
+import determineStem from "./internal/determineStem";
+
+/**
+ * Returns the stemmer for a researcher. This helper is currently only used for Prominent Words functionality.
+ *
+ * @param {Researcher} researcher The researcher.
+ *
+ * @returns {Function} The stemmer.
+ */
+export default function getStemmer(researcher) {
+  const morphologyData = get(researcher.getData('morphology'), 'ja', false);
+  if (morphologyData) {
+    return word => determineStem(word, morphologyData);
+  }
+  return baseStemmer;
+}
+//# sourceMappingURL=customGetStemmer.js.map

package/build/languageProcessing/languages/ja/helpers/customGetStemmer.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"customGetStemmer.js","names":["get","languageProcessing","baseStemmer","determineStem","getStemmer","researcher","morphologyData","getData","word"],"sources":["../../../../../src/languageProcessing/languages/ja/helpers/customGetStemmer.js"],"sourcesContent":["import {get} from 'lodash';\nimport {languageProcessing} from '@axyseo/index.js';\nconst {baseStemmer} = languageProcessing;\nimport determineStem from './internal/determineStem';\n\n/**\n * Returns the stemmer for a researcher. This helper is currently only used for Prominent Words functionality.\n *\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Function} The stemmer.\n */\nexport default function getStemmer(researcher) {\n  const morphologyData = get(researcher.getData('morphology'), 'ja', false);\n\n  if (morphologyData) {\n    return word => determineStem(word, morphologyData);\n  }\n\n  return baseStemmer;\n}\n"],"mappings":"AAAA,SAAQA,GAAG,QAAO,QAAQ;AAC1B,SAAQC,kBAAkB;AAC1B,MAAM;EAACC;AAAW,CAAC,GAAGD,kBAAkB;AACxC,OAAOE,aAAa;;AAEpB;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASC,UAAUA,CAACC,UAAU,EAAE;EAC7C,MAAMC,cAAc,GAAGN,GAAG,CAACK,UAAU,CAACE,OAAO,CAAC,YAAY,CAAC,EAAE,IAAI,EAAE,KAAK,CAAC;EAEzE,IAAID,cAAc,EAAE;IAClB,OAAOE,IAAI,IAAIL,aAAa,CAACK,IAAI,EAAEF,cAAc,CAAC;EACpD;EAEA,OAAOJ,WAAW;AACpB","ignoreList":[]}

package/build/languageProcessing/languages/ja/helpers/getContentWords.js

@@ -0,0 +1,21 @@
+import getWords from "./getWords";
+import functionWords from "../config/functionWords";
+
+/**
+ * Filters out function words and removes じゃ ending if a words ends in it.
+ *
+ * @param {string} text The input text.
+ *
+ * @returns {Array} The array words with function words filtered out and じゃ removed.
+ */
+export default function (text) {
+  let words = getWords(text);
+  // Filter function words and morphemes.
+  words = words.filter(word => !functionWords.includes(word));
+
+  // Check if the segment ends in -じゃ, and remove the ending if it does.
+  const ending = "じゃ";
+  words = words.map(word => word.endsWith(ending) ? word.slice(0, -ending.length) : word);
+  return words;
+}
+//# sourceMappingURL=getContentWords.js.map

package/build/languageProcessing/languages/ja/helpers/getContentWords.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getContentWords.js","names":["getWords","functionWords","text","words","filter","word","includes","ending","map","endsWith","slice","length"],"sources":["../../../../../src/languageProcessing/languages/ja/helpers/getContentWords.js"],"sourcesContent":["import getWords from \"./getWords\";\nimport functionWords from \"../config/functionWords\";\n\n/**\n * Filters out function words and removes じゃ ending if a words ends in it.\n *\n * @param {string} text The input text.\n *\n * @returns {Array} The array words with function words filtered out and じゃ removed.\n */\nexport default function( text ) {\n\tlet words = getWords( text );\n\t// Filter function words and morphemes.\n\twords = words.filter( word => ! functionWords.includes( word ) );\n\n\t// Check if the segment ends in -じゃ, and remove the ending if it does.\n\tconst ending = \"じゃ\";\n\twords = words.map( word => word.endsWith( ending ) ? word.slice( 0, -ending.length ) : word );\n\n\treturn words;\n}\n"],"mappings":"AAAA,OAAOA,QAAQ;AACf,OAAOC,aAAa;;AAEpB;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,IAAI,EAAG;EAC/B,IAAIC,KAAK,GAAGH,QAAQ,CAAEE,IAAK,CAAC;EAC5B;EACAC,KAAK,GAAGA,KAAK,CAACC,MAAM,CAAEC,IAAI,IAAI,CAAEJ,aAAa,CAACK,QAAQ,CAAED,IAAK,CAAE,CAAC;;EAEhE;EACA,MAAME,MAAM,GAAG,IAAI;EACnBJ,KAAK,GAAGA,KAAK,CAACK,GAAG,CAAEH,IAAI,IAAIA,IAAI,CAACI,QAAQ,CAAEF,MAAO,CAAC,GAAGF,IAAI,CAACK,KAAK,CAAE,CAAC,EAAE,CAACH,MAAM,CAACI,MAAO,CAAC,GAAGN,IAAK,CAAC;EAE7F,OAAOF,KAAK;AACb","ignoreList":[]}

package/build/languageProcessing/languages/ja/helpers/getWords.js

@@ -0,0 +1,31 @@
+import { filter, map } from 'lodash';
+import { languageProcessing } from "../../../../index.js";
+const {
+  sanitizeString,
+  removePunctuation
+} = languageProcessing;
+import TinySegmenter from 'tiny-segmenter';
+const segmenter = new TinySegmenter();
+
+/**
+ * Returns an array with words used in the text.
+ *
+ * @param {string} text The text to be counted.
+ *
+ * @returns {Array} The array with all words.
+ */
+export default function (text) {
+  // Strips HTML tags.
+  text = sanitizeString(text);
+  if (text === '') {
+    return [];
+  }
+  let words = segmenter.segment(text);
+  words = map(words, function (word) {
+    return removePunctuation(word);
+  });
+  return filter(words, function (word) {
+    return word.trim() !== '';
+  });
+}
+//# sourceMappingURL=getWords.js.map

package/build/languageProcessing/languages/ja/helpers/getWords.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getWords.js","names":["filter","map","languageProcessing","sanitizeString","removePunctuation","TinySegmenter","segmenter","text","words","segment","word","trim"],"sources":["../../../../../src/languageProcessing/languages/ja/helpers/getWords.js"],"sourcesContent":["import {filter, map} from 'lodash';\nimport {languageProcessing} from '@axyseo/index.js';\nconst {sanitizeString, removePunctuation} = languageProcessing;\nimport TinySegmenter from 'tiny-segmenter';\n\nconst segmenter = new TinySegmenter();\n\n/**\n * Returns an array with words used in the text.\n *\n * @param {string} text The text to be counted.\n *\n * @returns {Array} The array with all words.\n */\nexport default function(text) {\n  // Strips HTML tags.\n  text = sanitizeString(text);\n  if (text === '') {\n    return [];\n  }\n\n  let words = segmenter.segment(text);\n\n  words = map(words, function(word) {\n    return removePunctuation(word);\n  });\n\n  return filter(words, function(word) {\n    return word.trim() !== '';\n  });\n}\n"],"mappings":"AAAA,SAAQA,MAAM,EAAEC,GAAG,QAAO,QAAQ;AAClC,SAAQC,kBAAkB;AAC1B,MAAM;EAACC,cAAc;EAAEC;AAAiB,CAAC,GAAGF,kBAAkB;AAC9D,OAAOG,aAAa,MAAM,gBAAgB;AAE1C,MAAMC,SAAS,GAAG,IAAID,aAAa,CAAC,CAAC;;AAErC;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAASE,IAAI,EAAE;EAC5B;EACAA,IAAI,GAAGJ,cAAc,CAACI,IAAI,CAAC;EAC3B,IAAIA,IAAI,KAAK,EAAE,EAAE;IACf,OAAO,EAAE;EACX;EAEA,IAAIC,KAAK,GAAGF,SAAS,CAACG,OAAO,CAACF,IAAI,CAAC;EAEnCC,KAAK,GAAGP,GAAG,CAACO,KAAK,EAAE,UAASE,IAAI,EAAE;IAChC,OAAON,iBAAiB,CAACM,IAAI,CAAC;EAChC,CAAC,CAAC;EAEF,OAAOV,MAAM,CAACQ,KAAK,EAAE,UAASE,IAAI,EAAE;IAClC,OAAOA,IAAI,CAACC,IAAI,CAAC,CAAC,KAAK,EAAE;EAC3B,CAAC,CAAC;AACJ","ignoreList":[]}

package/build/languageProcessing/languages/ja/helpers/internal/SentenceTokenizer.js

@@ -0,0 +1,92 @@
+import { isNaN } from "lodash";
+import { normalize as normalizeQuotes } from "../../../../helpers/sanitize/quotes.js";
+import SentenceTokenizer from "../../../../helpers/sentence/SentenceTokenizer";
+
+/*
+ * \u2026 - ellipsis.
+ * \u3002 - Japanese ideographic full stop.
+ * \uFF61 - Japanese half-width ideographic full stop.
+ * \uFF01 - Japanese full-width exclamation mark.
+ * \u203C - Japanese double exclamation mark.
+ * \uFF1F - Japanese fullwidth question mark.
+ * \u2047 - Japanese double question mark.
+ * \u2049 - Japanese exclamation question mark.
+ * \u2048 - Japanese question exclamation mark.
+ * \u2025 - Japanese two dot leader.
+ */
+const sentenceDelimiters = "?!\u2026\u3002\uFF61\uFF01\u203C\uFF1F\u2047\u2049\u2048\u2049\u2025";
+
+/**
+ * Class for tokenizing a (html) text into sentences.
+ */
+export default class JapaneseSentenceTokenizer extends SentenceTokenizer {
+  /**
+   * Constructor
+   * @constructor
+   */
+  constructor() {
+    super();
+    this.sentenceDelimiters = sentenceDelimiters;
+  }
+
+  /**
+   * Returns whether a certain character is a number.
+   *
+   * @param {string} character The character to check.
+   * @returns {boolean} Whether or not the character is a capital letter.
+   */
+  isNumber(character) {
+    const japaneseNumbers = [
+    // Full-width.
+    /^[\uFF10-\uFF19]+$/i,
+    // Circled digit, parenthesized digit, and digit with full stop.
+    /^[\u2460-\u249B]+$/i,
+    // Parenthesized ideograph.
+    /^[\u3220-\u3229]+$/i,
+    // Circled ideograph.
+    /^[\u3280-\u3289]+$/i];
+    return !isNaN(parseInt(character, 10)) || japaneseNumbers.some(numberRange => numberRange.test(character));
+  }
+
+  /**
+   * Returns whether a given character is quotation mark.
+   *
+   * @param {string} character The character to check.
+   * @returns {boolean} Whether or not the given character is a quotation mark.
+   */
+  isQuotation(character) {
+    character = normalizeQuotes(character);
+    const japaneseOpeningQuotationMark = /^[\u300C\u300E\u3008\u3014\u3010\uFF5B\uFF3B]+$/i;
+    return "'" === character || "\"" === character || japaneseOpeningQuotationMark.test(character);
+  }
+
+  /**
+   * Checks whether a character is from Japanese language that could be sentence beginning.
+   *
+   * @param {string} letter The letter to check.
+   *
+   * @returns {boolean} Whether the letter is from Japanese language that could be sentence beginning.
+   */
+  isLetterFromSpecificLanguage(letter) {
+    const japaneseLetterRanges = [
+    // Hiragana.
+    /^[\u3040-\u3096]+$/i,
+    // Katakana full-width.
+    /^[\u30A1-\u30FA]+$/i, /^[\u31F0-\u31FF]+$/i,
+    // Katakana half-width.
+    /^[\uFF66-\uFF9D]+$/i,
+    // Kanji.
+    /^[\u4E00-\u9FFC]+$/i];
+    return japaneseLetterRanges.some(ltrLetterRange => ltrLetterRange.test(letter));
+  }
+
+  /**
+   * Always returns true as Japanese sentence beginning doesn't need to be preceded by a whitespace to be a valid one.
+   *
+   * @returns {true}  Always true.
+   */
+  isCharacterASpace() {
+    return true;
+  }
+}
+//# sourceMappingURL=SentenceTokenizer.js.map

package/build/languageProcessing/languages/ja/helpers/internal/SentenceTokenizer.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"SentenceTokenizer.js","names":["isNaN","normalize","normalizeQuotes","SentenceTokenizer","sentenceDelimiters","JapaneseSentenceTokenizer","constructor","isNumber","character","japaneseNumbers","parseInt","some","numberRange","test","isQuotation","japaneseOpeningQuotationMark","isLetterFromSpecificLanguage","letter","japaneseLetterRanges","ltrLetterRange","isCharacterASpace"],"sources":["../../../../../../src/languageProcessing/languages/ja/helpers/internal/SentenceTokenizer.js"],"sourcesContent":["import { isNaN } from \"lodash\";\n\nimport { normalize as normalizeQuotes } from \"../../../../helpers/sanitize/quotes.js\";\nimport SentenceTokenizer from \"../../../../helpers/sentence/SentenceTokenizer\";\n\n/*\n * \\u2026 - ellipsis.\n * \\u3002 - Japanese ideographic full stop.\n * \\uFF61 - Japanese half-width ideographic full stop.\n * \\uFF01 - Japanese full-width exclamation mark.\n * \\u203C - Japanese double exclamation mark.\n * \\uFF1F - Japanese fullwidth question mark.\n * \\u2047 - Japanese double question mark.\n * \\u2049 - Japanese exclamation question mark.\n * \\u2048 - Japanese question exclamation mark.\n * \\u2025 - Japanese two dot leader.\n */\nconst sentenceDelimiters = \"?!\\u2026\\u3002\\uFF61\\uFF01\\u203C\\uFF1F\\u2047\\u2049\\u2048\\u2049\\u2025\";\n\n/**\n * Class for tokenizing a (html) text into sentences.\n */\nexport default class JapaneseSentenceTokenizer extends SentenceTokenizer {\n\t/**\n\t * Constructor\n\t * @constructor\n\t */\n\tconstructor() {\n\t\tsuper();\n\t\tthis.sentenceDelimiters = sentenceDelimiters;\n\t}\n\n\t/**\n\t * Returns whether a certain character is a number.\n\t *\n\t * @param {string} character The character to check.\n\t * @returns {boolean} Whether or not the character is a capital letter.\n\t */\n\tisNumber( character ) {\n\t\tconst japaneseNumbers = [\n\t\t\t// Full-width.\n\t\t\t/^[\\uFF10-\\uFF19]+$/i,\n\t\t\t// Circled digit, parenthesized digit, and digit with full stop.\n\t\t\t/^[\\u2460-\\u249B]+$/i,\n\t\t\t// Parenthesized ideograph.\n\t\t\t/^[\\u3220-\\u3229]+$/i,\n\t\t\t// Circled ideograph.\n\t\t\t/^[\\u3280-\\u3289]+$/i,\n\t\t];\n\n\t\treturn ( ! isNaN( parseInt( character, 10 ) ) || japaneseNumbers.some( numberRange => numberRange.test( character ) ) );\n\t}\n\n\t/**\n\t * Returns whether a given character is quotation mark.\n\t *\n\t * @param {string} character The character to check.\n\t * @returns {boolean} Whether or not the given character is a quotation mark.\n\t */\n\tisQuotation( character ) {\n\t\tcharacter = normalizeQuotes( character );\n\n\t\tconst japaneseOpeningQuotationMark = /^[\\u300C\\u300E\\u3008\\u3014\\u3010\\uFF5B\\uFF3B]+$/i;\n\n\t\treturn \"'\" === character || \"\\\"\" === character || japaneseOpeningQuotationMark.test( character );\n\t}\n\n\t/**\n\t * Checks whether a character is from Japanese language that could be sentence beginning.\n\t *\n\t * @param {string} letter The letter to check.\n\t *\n\t * @returns {boolean} Whether the letter is from Japanese language that could be sentence beginning.\n\t */\n\tisLetterFromSpecificLanguage( letter ) {\n\t\tconst japaneseLetterRanges = [\n\t\t\t// Hiragana.\n\t\t\t/^[\\u3040-\\u3096]+$/i,\n\t\t\t// Katakana full-width.\n\t\t\t/^[\\u30A1-\\u30FA]+$/i,\n\t\t\t/^[\\u31F0-\\u31FF]+$/i,\n\t\t\t// Katakana half-width.\n\t\t\t/^[\\uFF66-\\uFF9D]+$/i,\n\t\t\t// Kanji.\n\t\t\t/^[\\u4E00-\\u9FFC]+$/i,\n\t\t];\n\n\t\treturn (\n\t\t\tjapaneseLetterRanges.some( ltrLetterRange => ltrLetterRange.test( letter ) )\n\t\t);\n\t}\n\n\t/**\n\t * Always returns true as Japanese sentence beginning doesn't need to be preceded by a whitespace to be a valid one.\n\t *\n\t * @returns {true}  Always true.\n\t */\n\tisCharacterASpace() {\n\t\treturn true;\n\t}\n}\n\n"],"mappings":"AAAA,SAASA,KAAK,QAAQ,QAAQ;AAE9B,SAASC,SAAS,IAAIC,eAAe;AACrC,OAAOC,iBAAiB;;AAExB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,kBAAkB,GAAG,sEAAsE;;AAEjG;AACA;AACA;AACA,eAAe,MAAMC,yBAAyB,SAASF,iBAAiB,CAAC;EACxE;AACD;AACA;AACA;EACCG,WAAWA,CAAA,EAAG;IACb,KAAK,CAAC,CAAC;IACP,IAAI,CAACF,kBAAkB,GAAGA,kBAAkB;EAC7C;;EAEA;AACD;AACA;AACA;AACA;AACA;EACCG,QAAQA,CAAEC,SAAS,EAAG;IACrB,MAAMC,eAAe,GAAG;IACvB;IACA,qBAAqB;IACrB;IACA,qBAAqB;IACrB;IACA,qBAAqB;IACrB;IACA,qBAAqB,CACrB;IAED,OAAS,CAAET,KAAK,CAAEU,QAAQ,CAAEF,SAAS,EAAE,EAAG,CAAE,CAAC,IAAIC,eAAe,CAACE,IAAI,CAAEC,WAAW,IAAIA,WAAW,CAACC,IAAI,CAAEL,SAAU,CAAE,CAAC;EACtH;;EAEA;AACD;AACA;AACA;AACA;AACA;EACCM,WAAWA,CAAEN,SAAS,EAAG;IACxBA,SAAS,GAAGN,eAAe,CAAEM,SAAU,CAAC;IAExC,MAAMO,4BAA4B,GAAG,kDAAkD;IAEvF,OAAO,GAAG,KAAKP,SAAS,IAAI,IAAI,KAAKA,SAAS,IAAIO,4BAA4B,CAACF,IAAI,CAAEL,SAAU,CAAC;EACjG;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;EACCQ,4BAA4BA,CAAEC,MAAM,EAAG;IACtC,MAAMC,oBAAoB,GAAG;IAC5B;IACA,qBAAqB;IACrB;IACA,qBAAqB,EACrB,qBAAqB;IACrB;IACA,qBAAqB;IACrB;IACA,qBAAqB,CACrB;IAED,OACCA,oBAAoB,CAACP,IAAI,CAAEQ,cAAc,IAAIA,cAAc,CAACN,IAAI,CAAEI,MAAO,CAAE,CAAC;EAE9E;;EAEA;AACD;AACA;AACA;AACA;EACCG,iBAAiBA,CAAA,EAAG;IACnB,OAAO,IAAI;EACZ;AACD","ignoreList":[]}

package/build/languageProcessing/languages/ja/helpers/internal/createWordForms.js

@@ -0,0 +1,65 @@
+import { flatten, uniq } from "lodash";
+
+/**
+ * Checks if the word matches any paradigm and creates the forms from the matched paradigm(s).
+ * If no matches found, returns an array with the original word.
+ *
+ * @param {string}  word            The word to check.
+ * @param {Object}  morphologyData  The morphology data.
+ *
+ * @returns {Array} The array of created forms.
+ */
+function createForms(word, morphologyData) {
+  const paradigmEndingsGroups = morphologyData.paradigmGroups;
+
+  // The endings in the array are sorted from the longest to the shortest.
+  // This way, if there are multiple matches, the first element in the matched array is always the longest one.
+  let allEndings = uniq(flatten(paradigmEndingsGroups));
+  allEndings = allEndings.sort((a, b) => b.length - a.length || a.localeCompare(b));
+
+  // Check if the word matches any ending(s) and save the ending(s).
+  const matchedEndings = allEndings.filter(ending => word.endsWith(ending));
+  const forms = [];
+  if (matchedEndings.length === 0) {
+    // If there is no match found, add the original word to the forms array.
+    forms.push(word);
+  } else {
+    // Pick the longest ending.
+    const matchedEnding = matchedEndings[0];
+
+    // Extract the stem.
+    const matchedStem = word.slice(0, -matchedEnding.length);
+
+    // Loop over each endings group in the endings group array.
+    for (const endingsGroup of paradigmEndingsGroups) {
+      // Check if the ending of the matched word can be found in the endings group and create all the forms with all the endings in the group.
+      if (endingsGroup.includes(matchedEnding)) {
+        forms.push(endingsGroup.map(ending => matchedStem + ending));
+      }
+    }
+  }
+
+  // If the final character of the input word ends in る, also create an extra form where the character is removed.
+  const ruEnding = "る";
+  if (word.endsWith(ruEnding)) {
+    forms.push(word.slice(0, -ruEnding.length));
+  }
+  return uniq(flatten(forms));
+}
+
+/**
+ * Creates forms for Japanese word.
+ *
+ * @param {string}  word            The word to check. Assume that the input word is a segment as outputted from `getContentWords` helper.
+ * @param {Object}  morphologyData  The morphology data.
+ *
+ * @returns {Array} The array of created forms.
+ */
+export default function (word, morphologyData) {
+  // Check if the word is longer than 1 character.
+  if (word.length <= 1) {
+    return [word];
+  }
+  return createForms(word, morphologyData);
+}
+//# sourceMappingURL=createWordForms.js.map

package/build/languageProcessing/languages/ja/helpers/internal/createWordForms.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"createWordForms.js","names":["flatten","uniq","createForms","word","morphologyData","paradigmEndingsGroups","paradigmGroups","allEndings","sort","a","b","length","localeCompare","matchedEndings","filter","ending","endsWith","forms","push","matchedEnding","matchedStem","slice","endingsGroup","includes","map","ruEnding"],"sources":["../../../../../../src/languageProcessing/languages/ja/helpers/internal/createWordForms.js"],"sourcesContent":["import { flatten, uniq } from \"lodash\";\n\n/**\n * Checks if the word matches any paradigm and creates the forms from the matched paradigm(s).\n * If no matches found, returns an array with the original word.\n *\n * @param {string}  word            The word to check.\n * @param {Object}  morphologyData  The morphology data.\n *\n * @returns {Array} The array of created forms.\n */\nfunction createForms( word, morphologyData ) {\n\tconst paradigmEndingsGroups = morphologyData.paradigmGroups;\n\n\t// The endings in the array are sorted from the longest to the shortest.\n\t// This way, if there are multiple matches, the first element in the matched array is always the longest one.\n\tlet allEndings = uniq( flatten( paradigmEndingsGroups ) );\n\tallEndings = allEndings.sort( ( a, b ) => b.length - a.length || a.localeCompare( b ) );\n\n\t// Check if the word matches any ending(s) and save the ending(s).\n\tconst matchedEndings = allEndings.filter( ending => word.endsWith( ending ) );\n\n\tconst forms = [];\n\n\tif ( matchedEndings.length === 0 ) {\n\t\t// If there is no match found, add the original word to the forms array.\n\t\tforms.push( word );\n\t} else {\n\t\t// Pick the longest ending.\n\t\tconst matchedEnding = matchedEndings[ 0 ];\n\n\t\t// Extract the stem.\n\t\tconst matchedStem = word.slice( 0, -matchedEnding.length );\n\n\t\t// Loop over each endings group in the endings group array.\n\t\tfor ( const endingsGroup of paradigmEndingsGroups ) {\n\t\t\t// Check if the ending of the matched word can be found in the endings group and create all the forms with all the endings in the group.\n\t\t\tif ( endingsGroup.includes( matchedEnding ) ) {\n\t\t\t\tforms.push( endingsGroup.map( ending => matchedStem + ending ) );\n\t\t\t}\n\t\t}\n\t}\n\n\t// If the final character of the input word ends in る, also create an extra form where the character is removed.\n\tconst ruEnding = \"る\";\n\tif ( word.endsWith( ruEnding ) ) {\n\t\tforms.push( word.slice( 0, -ruEnding.length ) );\n\t}\n\n\treturn uniq( flatten( forms ) );\n}\n\n/**\n * Creates forms for Japanese word.\n *\n * @param {string}  word            The word to check. Assume that the input word is a segment as outputted from `getContentWords` helper.\n * @param {Object}  morphologyData  The morphology data.\n *\n * @returns {Array} The array of created forms.\n */\nexport default function( word, morphologyData ) {\n\t// Check if the word is longer than 1 character.\n\tif ( word.length <= 1 ) {\n\t\treturn [ word ];\n\t}\n\n\treturn createForms( word, morphologyData );\n}\n"],"mappings":"AAAA,SAASA,OAAO,EAAEC,IAAI,QAAQ,QAAQ;;AAEtC;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,WAAWA,CAAEC,IAAI,EAAEC,cAAc,EAAG;EAC5C,MAAMC,qBAAqB,GAAGD,cAAc,CAACE,cAAc;;EAE3D;EACA;EACA,IAAIC,UAAU,GAAGN,IAAI,CAAED,OAAO,CAAEK,qBAAsB,CAAE,CAAC;EACzDE,UAAU,GAAGA,UAAU,CAACC,IAAI,CAAE,CAAEC,CAAC,EAAEC,CAAC,KAAMA,CAAC,CAACC,MAAM,GAAGF,CAAC,CAACE,MAAM,IAAIF,CAAC,CAACG,aAAa,CAAEF,CAAE,CAAE,CAAC;;EAEvF;EACA,MAAMG,cAAc,GAAGN,UAAU,CAACO,MAAM,CAAEC,MAAM,IAAIZ,IAAI,CAACa,QAAQ,CAAED,MAAO,CAAE,CAAC;EAE7E,MAAME,KAAK,GAAG,EAAE;EAEhB,IAAKJ,cAAc,CAACF,MAAM,KAAK,CAAC,EAAG;IAClC;IACAM,KAAK,CAACC,IAAI,CAAEf,IAAK,CAAC;EACnB,CAAC,MAAM;IACN;IACA,MAAMgB,aAAa,GAAGN,cAAc,CAAE,CAAC,CAAE;;IAEzC;IACA,MAAMO,WAAW,GAAGjB,IAAI,CAACkB,KAAK,CAAE,CAAC,EAAE,CAACF,aAAa,CAACR,MAAO,CAAC;;IAE1D;IACA,KAAM,MAAMW,YAAY,IAAIjB,qBAAqB,EAAG;MACnD;MACA,IAAKiB,YAAY,CAACC,QAAQ,CAAEJ,aAAc,CAAC,EAAG;QAC7CF,KAAK,CAACC,IAAI,CAAEI,YAAY,CAACE,GAAG,CAAET,MAAM,IAAIK,WAAW,GAAGL,MAAO,CAAE,CAAC;MACjE;IACD;EACD;;EAEA;EACA,MAAMU,QAAQ,GAAG,GAAG;EACpB,IAAKtB,IAAI,CAACa,QAAQ,CAAES,QAAS,CAAC,EAAG;IAChCR,KAAK,CAACC,IAAI,CAAEf,IAAI,CAACkB,KAAK,CAAE,CAAC,EAAE,CAACI,QAAQ,CAACd,MAAO,CAAE,CAAC;EAChD;EAEA,OAAOV,IAAI,CAAED,OAAO,CAAEiB,KAAM,CAAE,CAAC;AAChC;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUd,IAAI,EAAEC,cAAc,EAAG;EAC/C;EACA,IAAKD,IAAI,CAACQ,MAAM,IAAI,CAAC,EAAG;IACvB,OAAO,CAAER,IAAI,CAAE;EAChB;EAEA,OAAOD,WAAW,CAAEC,IAAI,EAAEC,cAAe,CAAC;AAC3C","ignoreList":[]}

package/build/languageProcessing/languages/ja/helpers/internal/determineStem.js

@@ -0,0 +1,17 @@
+import createWordForms from "./createWordForms";
+
+/**
+ * Determines the canonical stem from the word forms.
+ *
+ * @param {string} word             The word input.
+ * @param {object} morphologyData   The morphology data file.
+ *
+ * @returns {string}    The shortest form from the array as the canonical stem.
+ */
+export default function determineStem(word, morphologyData) {
+  let createdWordForms = createWordForms(word, morphologyData);
+  // Sort from the shortest to the longest form.
+  createdWordForms = createdWordForms.sort((a, b) => a.length - b.length || a.localeCompare(b));
+  return createdWordForms[0];
+}
+//# sourceMappingURL=determineStem.js.map

package/build/languageProcessing/languages/ja/helpers/internal/determineStem.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"determineStem.js","names":["createWordForms","determineStem","word","morphologyData","createdWordForms","sort","a","b","length","localeCompare"],"sources":["../../../../../../src/languageProcessing/languages/ja/helpers/internal/determineStem.js"],"sourcesContent":["import createWordForms from \"./createWordForms\";\n\n/**\n * Determines the canonical stem from the word forms.\n *\n * @param {string} word             The word input.\n * @param {object} morphologyData   The morphology data file.\n *\n * @returns {string}    The shortest form from the array as the canonical stem.\n */\nexport default function determineStem( word, morphologyData ) {\n\tlet createdWordForms = createWordForms( word, morphologyData );\n\t// Sort from the shortest to the longest form.\n\tcreatedWordForms = createdWordForms.sort( ( a, b ) => a.length - b.length || a.localeCompare( b ) );\n\n\treturn createdWordForms[ 0 ];\n}\n"],"mappings":"AAAA,OAAOA,eAAe;;AAEtB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASC,aAAaA,CAAEC,IAAI,EAAEC,cAAc,EAAG;EAC7D,IAAIC,gBAAgB,GAAGJ,eAAe,CAAEE,IAAI,EAAEC,cAAe,CAAC;EAC9D;EACAC,gBAAgB,GAAGA,gBAAgB,CAACC,IAAI,CAAE,CAAEC,CAAC,EAAEC,CAAC,KAAMD,CAAC,CAACE,MAAM,GAAGD,CAAC,CAACC,MAAM,IAAIF,CAAC,CAACG,aAAa,CAAEF,CAAE,CAAE,CAAC;EAEnG,OAAOH,gBAAgB,CAAE,CAAC,CAAE;AAC7B","ignoreList":[]}

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

@@ -0,0 +1,52 @@
+import getContentWords from "./getContentWords";
+import processExactMatchRequest from "../../../helpers/match/processExactMatchRequest";
+import { normalizeSingle } from "../../../helpers/sanitize/quotes";
+
+/**
+ * Checks for word matches in a text and returns an array containing the matched word(s).
+ *
+ * @param {string}  text               The text to find the word to match.
+ * @param {string}  wordToMatch        The word to match.
+ *
+ * @returns {Array} An array of the matched word(s).
+ */
+export default function (text, wordToMatch) {
+  /*
+      * Lowercase the text so that it matches the wordToMatch which is already lowercased.
+      * Note that Japanese doesn't differentiate between upper and lower case, so this is only needed in case
+      * the text contains non-Japanese characters.
+      */
+  text = text.toLowerCase();
+
+  // Check if the exact match is requested.
+  const isExactMatchRequested = processExactMatchRequest(wordToMatch);
+  if (isExactMatchRequested.exactMatchRequested) {
+    /*
+     * Normalize single quotes in case they differ between the text and the word to match.
+     * Normalizing is only needed for exact matching, because with non-exact matching single quotes are considered
+     * word boundaries.
+     * Quotes in wordToMatch are already normalized at an earlier point.
+    */
+    text = normalizeSingle(text);
+    const keyphrase = isExactMatchRequested.keyphrase;
+    const matches = [];
+
+    // Return the index of the match. It returns -1 if there is no match.
+    let index = text.indexOf(keyphrase);
+    while (index !== -1) {
+      // Push the match to the array.
+      matches.push(keyphrase);
+      // Look for the next match after the previous one and adjust the index.
+      index = text.indexOf(keyphrase, index + keyphrase.length);
+    }
+    return matches;
+  }
+
+  /*
+   * `getContentWords` is used here to retrieve the words from the text instead of `getWords` because it has an additional step
+   * to remove this ending -じゃ from the segmented words which means that using this method will improve matching possibility.
+   */
+  const words = getContentWords(text);
+  return words.filter(word => wordToMatch === word);
+}
+//# sourceMappingURL=matchTextWithWord.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"matchTextWithWord.js","names":["getContentWords","processExactMatchRequest","normalizeSingle","text","wordToMatch","toLowerCase","isExactMatchRequested","exactMatchRequested","keyphrase","matches","index","indexOf","push","length","words","filter","word"],"sources":["../../../../../src/languageProcessing/languages/ja/helpers/matchTextWithWord.js"],"sourcesContent":["import getContentWords from \"./getContentWords\";\nimport processExactMatchRequest from \"../../../helpers/match/processExactMatchRequest\";\nimport { normalizeSingle } from \"../../../helpers/sanitize/quotes\";\n\n/**\n * Checks for word matches in a text and returns an array containing the matched word(s).\n *\n * @param {string}  text               The text to find the word to match.\n * @param {string}  wordToMatch        The word to match.\n *\n * @returns {Array} An array of the matched word(s).\n */\nexport default function( text, wordToMatch ) {\n\t/*\n     * Lowercase the text so that it matches the wordToMatch which is already lowercased.\n     * Note that Japanese doesn't differentiate between upper and lower case, so this is only needed in case\n     * the text contains non-Japanese characters.\n     */\n\ttext = text.toLowerCase();\n\n\t// Check if the exact match is requested.\n\tconst isExactMatchRequested = processExactMatchRequest( wordToMatch );\n\tif ( isExactMatchRequested.exactMatchRequested ) {\n\t\t/*\n\t\t * Normalize single quotes in case they differ between the text and the word to match.\n\t\t * Normalizing is only needed for exact matching, because with non-exact matching single quotes are considered\n\t\t * word boundaries.\n\t\t * Quotes in wordToMatch are already normalized at an earlier point.\n\t\t*/\n\t\ttext = normalizeSingle( text );\n\n\t\tconst keyphrase = isExactMatchRequested.keyphrase;\n\t\tconst matches = [];\n\n\t\t// Return the index of the match. It returns -1 if there is no match.\n\t\tlet index = text.indexOf( keyphrase );\n\t\twhile ( index !== -1 ) {\n\t\t\t// Push the match to the array.\n\t\t\tmatches.push( keyphrase );\n\t\t\t// Look for the next match after the previous one and adjust the index.\n\t\t\tindex = text.indexOf( keyphrase, index + keyphrase.length );\n\t\t}\n\t\treturn matches;\n\t}\n\n\t/*\n\t * `getContentWords` is used here to retrieve the words from the text instead of `getWords` because it has an additional step\n\t * to remove this ending -じゃ from the segmented words which means that using this method will improve matching possibility.\n\t */\n\tconst words = getContentWords( text );\n\n\treturn words.filter( word => wordToMatch === word );\n}\n"],"mappings":"AAAA,OAAOA,eAAe;AACtB,OAAOC,wBAAwB;AAC/B,SAASC,eAAe;;AAExB;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,IAAI,EAAEC,WAAW,EAAG;EAC5C;AACD;AACA;AACA;AACA;EACCD,IAAI,GAAGA,IAAI,CAACE,WAAW,CAAC,CAAC;;EAEzB;EACA,MAAMC,qBAAqB,GAAGL,wBAAwB,CAAEG,WAAY,CAAC;EACrE,IAAKE,qBAAqB,CAACC,mBAAmB,EAAG;IAChD;AACF;AACA;AACA;AACA;AACA;IACEJ,IAAI,GAAGD,eAAe,CAAEC,IAAK,CAAC;IAE9B,MAAMK,SAAS,GAAGF,qBAAqB,CAACE,SAAS;IACjD,MAAMC,OAAO,GAAG,EAAE;;IAElB;IACA,IAAIC,KAAK,GAAGP,IAAI,CAACQ,OAAO,CAAEH,SAAU,CAAC;IACrC,OAAQE,KAAK,KAAK,CAAC,CAAC,EAAG;MACtB;MACAD,OAAO,CAACG,IAAI,CAAEJ,SAAU,CAAC;MACzB;MACAE,KAAK,GAAGP,IAAI,CAACQ,OAAO,CAAEH,SAAS,EAAEE,KAAK,GAAGF,SAAS,CAACK,MAAO,CAAC;IAC5D;IACA,OAAOJ,OAAO;EACf;;EAEA;AACD;AACA;AACA;EACC,MAAMK,KAAK,GAAGd,eAAe,CAAEG,IAAK,CAAC;EAErC,OAAOW,KAAK,CAACC,MAAM,CAAEC,IAAI,IAAIZ,WAAW,KAAKY,IAAK,CAAC;AACpD","ignoreList":[]}