axyseo 2.0.0-alpha.0.0.38 → 2.0.0-alpha.0.0.39

package/build/languageProcessing/researches/getLinks.js

@@ -1,23 +1,17 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
-var _getAnchorsFromText = _interopRequireDefault(require("../helpers/link/getAnchorsFromText.js"));
-var _lodash = require("lodash");
-var _url = _interopRequireDefault(require("../helpers/url/url.js"));
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /** @module analyses/getLinkStatistics */
 
+import getAnchors from "../helpers/link/getAnchorsFromText.js";
+import { map } from "lodash";
+import url from "../helpers/url/url.js";
+
 /**
  * Checks a text for anchors and returns the number found.
  *
  * @param {Object} paper The paper to get the text from.
  * @returns {Array} An array with the anchors
  */
-function _default(paper) {
-  const anchors = (0, _getAnchorsFromText.default)(paper.getText());
-  return (0, _lodash.map)(anchors, _url.default.getFromAnchorTag);
+export default function (paper) {
+  const anchors = getAnchors(paper.getText());
+  return map(anchors, url.getFromAnchorTag);
 }
 //# sourceMappingURL=getLinks.js.map

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

@@ -1 +1 @@
-{"version":3,"file":"getLinks.js","names":["_getAnchorsFromText","_interopRequireDefault","require","_lodash","_url","e","__esModule","default","_default","paper","anchors","getAnchors","getText","map","url","getFromAnchorTag"],"sources":["../../../src/languageProcessing/researches/getLinks.js"],"sourcesContent":["/** @module analyses/getLinkStatistics */\n\nimport getAnchors from \"../helpers/link/getAnchorsFromText.js\";\n\nimport { map } from \"lodash\";\nimport url from \"../helpers/url/url.js\";\n\n/**\n * Checks a text for anchors and returns the number found.\n *\n * @param {Object} paper The paper to get the text from.\n * @returns {Array} An array with the anchors\n */\nexport default function( paper ) {\n\tconst anchors = getAnchors( paper.getText() );\n\n\treturn map( anchors, url.getFromAnchorTag );\n}\n"],"mappings":";;;;;;AAEA,IAAAA,mBAAA,GAAAC,sBAAA,CAAAC,OAAA;AAEA,IAAAC,OAAA,GAAAD,OAAA;AACA,IAAAE,IAAA,GAAAH,sBAAA,CAAAC,OAAA;AAAwC,SAAAD,uBAAAI,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AALxC;;AAOA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAAUC,KAAK,EAAG;EAChC,MAAMC,OAAO,GAAG,IAAAC,2BAAU,EAAEF,KAAK,CAACG,OAAO,CAAC,CAAE,CAAC;EAE7C,OAAO,IAAAC,WAAG,EAAEH,OAAO,EAAEI,YAAG,CAACC,gBAAiB,CAAC;AAC5C","ignoreList":[]}
+{"version":3,"file":"getLinks.js","names":["getAnchors","map","url","paper","anchors","getText","getFromAnchorTag"],"sources":["../../../src/languageProcessing/researches/getLinks.js"],"sourcesContent":["/** @module analyses/getLinkStatistics */\n\nimport getAnchors from \"../helpers/link/getAnchorsFromText.js\";\n\nimport { map } from \"lodash\";\nimport url from \"../helpers/url/url.js\";\n\n/**\n * Checks a text for anchors and returns the number found.\n *\n * @param {Object} paper The paper to get the text from.\n * @returns {Array} An array with the anchors\n */\nexport default function( paper ) {\n\tconst anchors = getAnchors( paper.getText() );\n\n\treturn map( anchors, url.getFromAnchorTag );\n}\n"],"mappings":"AAAA;;AAEA,OAAOA,UAAU;AAEjB,SAASC,GAAG,QAAQ,QAAQ;AAC5B,OAAOC,GAAG;;AAEV;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,KAAK,EAAG;EAChC,MAAMC,OAAO,GAAGJ,UAAU,CAAEG,KAAK,CAACE,OAAO,CAAC,CAAE,CAAC;EAE7C,OAAOJ,GAAG,CAAEG,OAAO,EAAEF,GAAG,CAACI,gBAAiB,CAAC;AAC5C","ignoreList":[]}

package/build/languageProcessing/researches/getLongCenterAlignedTexts.js

@@ -1,9 +1,3 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
 /**
  * The maximum allowed length of a center-aligned paragraph or heading in characters.
  * @type {number}
@@ -33,7 +27,7 @@ function getLongCenterAlignedElements(nodes) {
  * @param {Paper} paper The paper to analyze.
  * @returns {Node[]} An array of nodes containing too long center-aligned paragraphs/headings.
  */
-function _default(paper) {
+export default function (paper) {
   const tree = paper.getTree();
   const paragraphs = tree.findAll(node => node.name === "p");
   const headings = tree.findAll(node => HEADING_TAGS_REGEX.test(node.name));

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

@@ -1 +1 @@
-{"version":3,"file":"getLongCenterAlignedTexts.js","names":["MAX_CENTER_ALIGNED_LENGTH","HEADING_TAGS_REGEX","getLongCenterAlignedElements","nodes","filter","node","isCenterAligned","attributes","class","Set","has","innerText","length","_default","paper","tree","getTree","paragraphs","findAll","name","headings","test","concat"],"sources":["../../../src/languageProcessing/researches/getLongCenterAlignedTexts.js"],"sourcesContent":["/**\n * The maximum allowed length of a center-aligned paragraph or heading in characters.\n * @type {number}\n */\nconst MAX_CENTER_ALIGNED_LENGTH = 50;\n\n/**\n * A regular expression to match heading tags.\n * @type {RegExp}\n */\nconst HEADING_TAGS_REGEX = /^h[1-6]$/;\n\n/**\n * Filters out all nodes that are center-aligned and longer than 50 characters (as defined in `MAX_CENTER_ALIGNED_LENGTH`).\n * @param {Node[]} nodes An array of nodes.\n * @returns {Node[]} An array containing all center-aligned nodes that are longer than 50 characters.\n */\nfunction getLongCenterAlignedElements( nodes ) {\n\treturn nodes.filter( node => {\n\t\tconst isCenterAligned = node.attributes.class instanceof Set && node.attributes.class.has( \"has-text-align-center\" );\n\t\treturn isCenterAligned && node.innerText().length > MAX_CENTER_ALIGNED_LENGTH;\n\t} );\n}\n\n/**\n * Finds all paragraphs and headings that are center-aligned and longer than 50 characters (after stripping HTML tags).\n * @param {Paper} paper The paper to analyze.\n * @returns {Node[]} An array of nodes containing too long center-aligned paragraphs/headings.\n */\nexport default function( paper ) {\n\tconst tree = paper.getTree();\n\n\tconst paragraphs = tree.findAll( node => node.name === \"p\" );\n\tconst headings = tree.findAll( node => HEADING_TAGS_REGEX.test( node.name ) );\n\n\treturn getLongCenterAlignedElements( paragraphs.concat( headings ) );\n}\n"],"mappings":";;;;;;AAAA;AACA;AACA;AACA;AACA,MAAMA,yBAAyB,GAAG,EAAE;;AAEpC;AACA;AACA;AACA;AACA,MAAMC,kBAAkB,GAAG,UAAU;;AAErC;AACA;AACA;AACA;AACA;AACA,SAASC,4BAA4BA,CAAEC,KAAK,EAAG;EAC9C,OAAOA,KAAK,CAACC,MAAM,CAAEC,IAAI,IAAI;IAC5B,MAAMC,eAAe,GAAGD,IAAI,CAACE,UAAU,CAACC,KAAK,YAAYC,GAAG,IAAIJ,IAAI,CAACE,UAAU,CAACC,KAAK,CAACE,GAAG,CAAE,uBAAwB,CAAC;IACpH,OAAOJ,eAAe,IAAID,IAAI,CAACM,SAAS,CAAC,CAAC,CAACC,MAAM,GAAGZ,yBAAyB;EAC9E,CAAE,CAAC;AACJ;;AAEA;AACA;AACA;AACA;AACA;AACe,SAAAa,SAAUC,KAAK,EAAG;EAChC,MAAMC,IAAI,GAAGD,KAAK,CAACE,OAAO,CAAC,CAAC;EAE5B,MAAMC,UAAU,GAAGF,IAAI,CAACG,OAAO,CAAEb,IAAI,IAAIA,IAAI,CAACc,IAAI,KAAK,GAAI,CAAC;EAC5D,MAAMC,QAAQ,GAAGL,IAAI,CAACG,OAAO,CAAEb,IAAI,IAAIJ,kBAAkB,CAACoB,IAAI,CAAEhB,IAAI,CAACc,IAAK,CAAE,CAAC;EAE7E,OAAOjB,4BAA4B,CAAEe,UAAU,CAACK,MAAM,CAAEF,QAAS,CAAE,CAAC;AACrE","ignoreList":[]}
+{"version":3,"file":"getLongCenterAlignedTexts.js","names":["MAX_CENTER_ALIGNED_LENGTH","HEADING_TAGS_REGEX","getLongCenterAlignedElements","nodes","filter","node","isCenterAligned","attributes","class","Set","has","innerText","length","paper","tree","getTree","paragraphs","findAll","name","headings","test","concat"],"sources":["../../../src/languageProcessing/researches/getLongCenterAlignedTexts.js"],"sourcesContent":["/**\n * The maximum allowed length of a center-aligned paragraph or heading in characters.\n * @type {number}\n */\nconst MAX_CENTER_ALIGNED_LENGTH = 50;\n\n/**\n * A regular expression to match heading tags.\n * @type {RegExp}\n */\nconst HEADING_TAGS_REGEX = /^h[1-6]$/;\n\n/**\n * Filters out all nodes that are center-aligned and longer than 50 characters (as defined in `MAX_CENTER_ALIGNED_LENGTH`).\n * @param {Node[]} nodes An array of nodes.\n * @returns {Node[]} An array containing all center-aligned nodes that are longer than 50 characters.\n */\nfunction getLongCenterAlignedElements( nodes ) {\n\treturn nodes.filter( node => {\n\t\tconst isCenterAligned = node.attributes.class instanceof Set && node.attributes.class.has( \"has-text-align-center\" );\n\t\treturn isCenterAligned && node.innerText().length > MAX_CENTER_ALIGNED_LENGTH;\n\t} );\n}\n\n/**\n * Finds all paragraphs and headings that are center-aligned and longer than 50 characters (after stripping HTML tags).\n * @param {Paper} paper The paper to analyze.\n * @returns {Node[]} An array of nodes containing too long center-aligned paragraphs/headings.\n */\nexport default function( paper ) {\n\tconst tree = paper.getTree();\n\n\tconst paragraphs = tree.findAll( node => node.name === \"p\" );\n\tconst headings = tree.findAll( node => HEADING_TAGS_REGEX.test( node.name ) );\n\n\treturn getLongCenterAlignedElements( paragraphs.concat( headings ) );\n}\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA,MAAMA,yBAAyB,GAAG,EAAE;;AAEpC;AACA;AACA;AACA;AACA,MAAMC,kBAAkB,GAAG,UAAU;;AAErC;AACA;AACA;AACA;AACA;AACA,SAASC,4BAA4BA,CAAEC,KAAK,EAAG;EAC9C,OAAOA,KAAK,CAACC,MAAM,CAAEC,IAAI,IAAI;IAC5B,MAAMC,eAAe,GAAGD,IAAI,CAACE,UAAU,CAACC,KAAK,YAAYC,GAAG,IAAIJ,IAAI,CAACE,UAAU,CAACC,KAAK,CAACE,GAAG,CAAE,uBAAwB,CAAC;IACpH,OAAOJ,eAAe,IAAID,IAAI,CAACM,SAAS,CAAC,CAAC,CAACC,MAAM,GAAGZ,yBAAyB;EAC9E,CAAE,CAAC;AACJ;;AAEA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUa,KAAK,EAAG;EAChC,MAAMC,IAAI,GAAGD,KAAK,CAACE,OAAO,CAAC,CAAC;EAE5B,MAAMC,UAAU,GAAGF,IAAI,CAACG,OAAO,CAAEZ,IAAI,IAAIA,IAAI,CAACa,IAAI,KAAK,GAAI,CAAC;EAC5D,MAAMC,QAAQ,GAAGL,IAAI,CAACG,OAAO,CAAEZ,IAAI,IAAIJ,kBAAkB,CAACmB,IAAI,CAAEf,IAAI,CAACa,IAAK,CAAE,CAAC;EAE7E,OAAOhB,4BAA4B,CAAEc,UAAU,CAACK,MAAM,CAAEF,QAAS,CAAE,CAAC;AACrE","ignoreList":[]}

package/build/languageProcessing/researches/getParagraphLength.js

@@ -1,17 +1,11 @@
-"use strict";
+import { imageRegex } from "../helpers/image/imageInText";
+import sanitizeLineBreakTag from "../helpers/sanitize/sanitizeLineBreakTag";
+import countWords from "../helpers/word/countWords.js";
+import matchParagraphs from "../helpers/html/matchParagraphs.js";
+import { filter } from "lodash";
+import removeHtmlBlocks from "../helpers/html/htmlParser";
+import { filterShortcodesFromHTML } from "../helpers";
 
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
-var _imageInText = require("../helpers/image/imageInText");
-var _sanitizeLineBreakTag = _interopRequireDefault(require("../helpers/sanitize/sanitizeLineBreakTag"));
-var _countWords = _interopRequireDefault(require("../helpers/word/countWords.js"));
-var _matchParagraphs = _interopRequireDefault(require("../helpers/html/matchParagraphs.js"));
-var _lodash = require("lodash");
-var _htmlParser = _interopRequireDefault(require("../helpers/html/htmlParser"));
-var _helpers = require("../helpers");
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /**
  * Gets all paragraphs and their word counts or character counts from the text.
  *
@@ -20,29 +14,29 @@ function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e
  *
  * @returns {Array} The array containing an object with the paragraph word or character count and paragraph text.
  */
-function _default(paper, researcher) {
+export default function (paper, researcher) {
   let text = paper.getText();
-  text = (0, _htmlParser.default)(text);
-  text = (0, _helpers.filterShortcodesFromHTML)(text, paper._attributes && paper._attributes.shortcodes);
+  text = removeHtmlBlocks(text);
+  text = filterShortcodesFromHTML(text, paper._attributes && paper._attributes.shortcodes);
 
   // Remove images from text before retrieving the paragraphs.
   // This step is done here so that applying highlight in captions is possible for ParagraphTooLongAssessment.
-  text = text.replace(_imageInText.imageRegex, "");
+  text = text.replace(imageRegex, "");
 
   // Replace line break tags containing attribute(s) with paragraph tag.
-  text = (0, _sanitizeLineBreakTag.default)(text);
-  const paragraphs = (0, _matchParagraphs.default)(text);
+  text = sanitizeLineBreakTag(text);
+  const paragraphs = matchParagraphs(text);
   const paragraphsLength = [];
 
   // An optional custom helper to count length to use instead of countWords.
   const customCountLength = researcher.getHelper("customCountLength");
   paragraphs.map(function (paragraph) {
     paragraphsLength.push({
-      countLength: customCountLength ? customCountLength(paragraph) : (0, _countWords.default)(paragraph),
+      countLength: customCountLength ? customCountLength(paragraph) : countWords(paragraph),
       text: paragraph
     });
   });
-  return (0, _lodash.filter)(paragraphsLength, function (paragraphLength) {
+  return filter(paragraphsLength, function (paragraphLength) {
     return paragraphLength.countLength > 0;
   });
 }

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

@@ -1 +1 @@
-{"version":3,"file":"getParagraphLength.js","names":["_imageInText","require","_sanitizeLineBreakTag","_interopRequireDefault","_countWords","_matchParagraphs","_lodash","_htmlParser","_helpers","e","__esModule","default","_default","paper","researcher","text","getText","removeHtmlBlocks","filterShortcodesFromHTML","_attributes","shortcodes","replace","imageRegex","sanitizeLineBreakTag","paragraphs","matchParagraphs","paragraphsLength","customCountLength","getHelper","map","paragraph","push","countLength","countWords","filter","paragraphLength"],"sources":["../../../src/languageProcessing/researches/getParagraphLength.js"],"sourcesContent":["import { imageRegex } from \"../helpers/image/imageInText\";\nimport sanitizeLineBreakTag from \"../helpers/sanitize/sanitizeLineBreakTag\";\nimport countWords from \"../helpers/word/countWords.js\";\nimport matchParagraphs from \"../helpers/html/matchParagraphs.js\";\nimport { filter } from \"lodash\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\n\n/**\n * Gets all paragraphs and their word counts or character counts from the text.\n *\n * @param {Paper} \t\tpaper \t\tThe paper object to get the text from.\n * @param {Researcher} \tresearcher \tThe researcher to use for analysis.\n *\n * @returns {Array} The array containing an object with the paragraph word or character count and paragraph text.\n */\nexport default function( paper, researcher ) {\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\n\t// Remove images from text before retrieving the paragraphs.\n\t// This step is done here so that applying highlight in captions is possible for ParagraphTooLongAssessment.\n\ttext = text.replace( imageRegex, \"\" );\n\n\t// Replace line break tags containing attribute(s) with paragraph tag.\n\ttext = sanitizeLineBreakTag( text );\n\tconst paragraphs = matchParagraphs( text );\n\tconst paragraphsLength = [];\n\n\t// An optional custom helper to count length to use instead of countWords.\n\tconst customCountLength = researcher.getHelper( \"customCountLength\" );\n\n\tparagraphs.map( function( paragraph ) {\n\t\tparagraphsLength.push( {\n\t\t\tcountLength: customCountLength ? customCountLength( paragraph ) : countWords( paragraph ),\n\t\t\ttext: paragraph,\n\t\t} );\n\t} );\n\n\treturn filter( paragraphsLength, function( paragraphLength ) {\n\t\treturn ( paragraphLength.countLength > 0 );\n\t} );\n}\n"],"mappings":";;;;;;AAAA,IAAAA,YAAA,GAAAC,OAAA;AACA,IAAAC,qBAAA,GAAAC,sBAAA,CAAAF,OAAA;AACA,IAAAG,WAAA,GAAAD,sBAAA,CAAAF,OAAA;AACA,IAAAI,gBAAA,GAAAF,sBAAA,CAAAF,OAAA;AACA,IAAAK,OAAA,GAAAL,OAAA;AACA,IAAAM,WAAA,GAAAJ,sBAAA,CAAAF,OAAA;AACA,IAAAO,QAAA,GAAAP,OAAA;AAAsD,SAAAE,uBAAAM,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEtD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C,IAAIC,IAAI,GAAGF,KAAK,CAACG,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAG,IAAAE,mBAAgB,EAAEF,IAAK,CAAC;EAC/BA,IAAI,GAAG,IAAAG,iCAAwB,EAAEH,IAAI,EAAEF,KAAK,CAACM,WAAW,IAAIN,KAAK,CAACM,WAAW,CAACC,UAAW,CAAC;;EAE1F;EACA;EACAL,IAAI,GAAGA,IAAI,CAACM,OAAO,CAAEC,uBAAU,EAAE,EAAG,CAAC;;EAErC;EACAP,IAAI,GAAG,IAAAQ,6BAAoB,EAAER,IAAK,CAAC;EACnC,MAAMS,UAAU,GAAG,IAAAC,wBAAe,EAAEV,IAAK,CAAC;EAC1C,MAAMW,gBAAgB,GAAG,EAAE;;EAE3B;EACA,MAAMC,iBAAiB,GAAGb,UAAU,CAACc,SAAS,CAAE,mBAAoB,CAAC;EAErEJ,UAAU,CAACK,GAAG,CAAE,UAAUC,SAAS,EAAG;IACrCJ,gBAAgB,CAACK,IAAI,CAAE;MACtBC,WAAW,EAAEL,iBAAiB,GAAGA,iBAAiB,CAAEG,SAAU,CAAC,GAAG,IAAAG,mBAAU,EAAEH,SAAU,CAAC;MACzFf,IAAI,EAAEe;IACP,CAAE,CAAC;EACJ,CAAE,CAAC;EAEH,OAAO,IAAAI,cAAM,EAAER,gBAAgB,EAAE,UAAUS,eAAe,EAAG;IAC5D,OAASA,eAAe,CAACH,WAAW,GAAG,CAAC;EACzC,CAAE,CAAC;AACJ","ignoreList":[]}
+{"version":3,"file":"getParagraphLength.js","names":["imageRegex","sanitizeLineBreakTag","countWords","matchParagraphs","filter","removeHtmlBlocks","filterShortcodesFromHTML","paper","researcher","text","getText","_attributes","shortcodes","replace","paragraphs","paragraphsLength","customCountLength","getHelper","map","paragraph","push","countLength","paragraphLength"],"sources":["../../../src/languageProcessing/researches/getParagraphLength.js"],"sourcesContent":["import { imageRegex } from \"../helpers/image/imageInText\";\nimport sanitizeLineBreakTag from \"../helpers/sanitize/sanitizeLineBreakTag\";\nimport countWords from \"../helpers/word/countWords.js\";\nimport matchParagraphs from \"../helpers/html/matchParagraphs.js\";\nimport { filter } from \"lodash\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\n\n/**\n * Gets all paragraphs and their word counts or character counts from the text.\n *\n * @param {Paper} \t\tpaper \t\tThe paper object to get the text from.\n * @param {Researcher} \tresearcher \tThe researcher to use for analysis.\n *\n * @returns {Array} The array containing an object with the paragraph word or character count and paragraph text.\n */\nexport default function( paper, researcher ) {\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\n\t// Remove images from text before retrieving the paragraphs.\n\t// This step is done here so that applying highlight in captions is possible for ParagraphTooLongAssessment.\n\ttext = text.replace( imageRegex, \"\" );\n\n\t// Replace line break tags containing attribute(s) with paragraph tag.\n\ttext = sanitizeLineBreakTag( text );\n\tconst paragraphs = matchParagraphs( text );\n\tconst paragraphsLength = [];\n\n\t// An optional custom helper to count length to use instead of countWords.\n\tconst customCountLength = researcher.getHelper( \"customCountLength\" );\n\n\tparagraphs.map( function( paragraph ) {\n\t\tparagraphsLength.push( {\n\t\t\tcountLength: customCountLength ? customCountLength( paragraph ) : countWords( paragraph ),\n\t\t\ttext: paragraph,\n\t\t} );\n\t} );\n\n\treturn filter( paragraphsLength, function( paragraphLength ) {\n\t\treturn ( paragraphLength.countLength > 0 );\n\t} );\n}\n"],"mappings":"AAAA,SAASA,UAAU;AACnB,OAAOC,oBAAoB;AAC3B,OAAOC,UAAU;AACjB,OAAOC,eAAe;AACtB,SAASC,MAAM,QAAQ,QAAQ;AAC/B,OAAOC,gBAAgB;AACvB,SAASC,wBAAwB;;AAEjC;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,KAAK,EAAEC,UAAU,EAAG;EAC5C,IAAIC,IAAI,GAAGF,KAAK,CAACG,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAGJ,gBAAgB,CAAEI,IAAK,CAAC;EAC/BA,IAAI,GAAGH,wBAAwB,CAAEG,IAAI,EAAEF,KAAK,CAACI,WAAW,IAAIJ,KAAK,CAACI,WAAW,CAACC,UAAW,CAAC;;EAE1F;EACA;EACAH,IAAI,GAAGA,IAAI,CAACI,OAAO,CAAEb,UAAU,EAAE,EAAG,CAAC;;EAErC;EACAS,IAAI,GAAGR,oBAAoB,CAAEQ,IAAK,CAAC;EACnC,MAAMK,UAAU,GAAGX,eAAe,CAAEM,IAAK,CAAC;EAC1C,MAAMM,gBAAgB,GAAG,EAAE;;EAE3B;EACA,MAAMC,iBAAiB,GAAGR,UAAU,CAACS,SAAS,CAAE,mBAAoB,CAAC;EAErEH,UAAU,CAACI,GAAG,CAAE,UAAUC,SAAS,EAAG;IACrCJ,gBAAgB,CAACK,IAAI,CAAE;MACtBC,WAAW,EAAEL,iBAAiB,GAAGA,iBAAiB,CAAEG,SAAU,CAAC,GAAGjB,UAAU,CAAEiB,SAAU,CAAC;MACzFV,IAAI,EAAEU;IACP,CAAE,CAAC;EACJ,CAAE,CAAC;EAEH,OAAOf,MAAM,CAAEW,gBAAgB,EAAE,UAAUO,eAAe,EAAG;IAC5D,OAASA,eAAe,CAACD,WAAW,GAAG,CAAC;EACzC,CAAE,CAAC;AACJ","ignoreList":[]}

package/build/languageProcessing/researches/getParagraphs.js

@@ -1,10 +1,5 @@
-"use strict";
+import { reject } from "lodash";
 
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
-var _lodash = require("lodash");
 /**
  * Returns all paragraphs in a given Paper.
  * Remove paragraphs that do not contain sentences or only consist of links.
@@ -12,12 +7,12 @@ var _lodash = require("lodash");
  * @param {Paper} paper The current paper.
  * @returns {Paragraph[]} All paragraphs in the paper.
  */
-function _default(paper) {
+export default function (paper) {
   let paragraphs = paper.getTree().findAll(node => node.name === "p");
 
   // Remove empty paragraphs without sentences and paragraphs only consisting of links.
-  paragraphs = (0, _lodash.reject)(paragraphs, paragraph => paragraph.sentences.length === 0);
-  paragraphs = (0, _lodash.reject)(paragraphs, paragraph => paragraph.childNodes.every(node => node.name === "a"));
+  paragraphs = reject(paragraphs, paragraph => paragraph.sentences.length === 0);
+  paragraphs = reject(paragraphs, paragraph => paragraph.childNodes.every(node => node.name === "a"));
   return paragraphs;
 }
 //# sourceMappingURL=getParagraphs.js.map

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

@@ -1 +1 @@
-{"version":3,"file":"getParagraphs.js","names":["_lodash","require","_default","paper","paragraphs","getTree","findAll","node","name","reject","paragraph","sentences","length","childNodes","every"],"sources":["../../../src/languageProcessing/researches/getParagraphs.js"],"sourcesContent":["import { reject } from \"lodash\";\n\n/**\n * Returns all paragraphs in a given Paper.\n * Remove paragraphs that do not contain sentences or only consist of links.\n *\n * @param {Paper} paper The current paper.\n * @returns {Paragraph[]} All paragraphs in the paper.\n */\nexport default function( paper ) {\n\tlet paragraphs = paper.getTree().findAll( node => node.name === \"p\" );\n\n\t// Remove empty paragraphs without sentences and paragraphs only consisting of links.\n\tparagraphs = reject( paragraphs, paragraph => paragraph.sentences.length === 0 );\n\tparagraphs = reject( paragraphs, paragraph => paragraph.childNodes.every( node => node.name === \"a\" ) );\n\n\treturn paragraphs;\n}\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAC,SAAUC,KAAK,EAAG;EAChC,IAAIC,UAAU,GAAGD,KAAK,CAACE,OAAO,CAAC,CAAC,CAACC,OAAO,CAAEC,IAAI,IAAIA,IAAI,CAACC,IAAI,KAAK,GAAI,CAAC;;EAErE;EACAJ,UAAU,GAAG,IAAAK,cAAM,EAAEL,UAAU,EAAEM,SAAS,IAAIA,SAAS,CAACC,SAAS,CAACC,MAAM,KAAK,CAAE,CAAC;EAChFR,UAAU,GAAG,IAAAK,cAAM,EAAEL,UAAU,EAAEM,SAAS,IAAIA,SAAS,CAACG,UAAU,CAACC,KAAK,CAAEP,IAAI,IAAIA,IAAI,CAACC,IAAI,KAAK,GAAI,CAAE,CAAC;EAEvG,OAAOJ,UAAU;AAClB","ignoreList":[]}
+{"version":3,"file":"getParagraphs.js","names":["reject","paper","paragraphs","getTree","findAll","node","name","paragraph","sentences","length","childNodes","every"],"sources":["../../../src/languageProcessing/researches/getParagraphs.js"],"sourcesContent":["import { reject } from \"lodash\";\n\n/**\n * Returns all paragraphs in a given Paper.\n * Remove paragraphs that do not contain sentences or only consist of links.\n *\n * @param {Paper} paper The current paper.\n * @returns {Paragraph[]} All paragraphs in the paper.\n */\nexport default function( paper ) {\n\tlet paragraphs = paper.getTree().findAll( node => node.name === \"p\" );\n\n\t// Remove empty paragraphs without sentences and paragraphs only consisting of links.\n\tparagraphs = reject( paragraphs, paragraph => paragraph.sentences.length === 0 );\n\tparagraphs = reject( paragraphs, paragraph => paragraph.childNodes.every( node => node.name === \"a\" ) );\n\n\treturn paragraphs;\n}\n"],"mappings":"AAAA,SAASA,MAAM,QAAQ,QAAQ;;AAE/B;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,KAAK,EAAG;EAChC,IAAIC,UAAU,GAAGD,KAAK,CAACE,OAAO,CAAC,CAAC,CAACC,OAAO,CAAEC,IAAI,IAAIA,IAAI,CAACC,IAAI,KAAK,GAAI,CAAC;;EAErE;EACAJ,UAAU,GAAGF,MAAM,CAAEE,UAAU,EAAEK,SAAS,IAAIA,SAAS,CAACC,SAAS,CAACC,MAAM,KAAK,CAAE,CAAC;EAChFP,UAAU,GAAGF,MAAM,CAAEE,UAAU,EAAEK,SAAS,IAAIA,SAAS,CAACG,UAAU,CAACC,KAAK,CAAEN,IAAI,IAAIA,IAAI,CAACC,IAAI,KAAK,GAAI,CAAE,CAAC;EAEvG,OAAOJ,UAAU;AAClB","ignoreList":[]}

package/build/languageProcessing/researches/getPassiveVoiceResult.js

@@ -1,17 +1,10 @@
-"use strict";
+import getSentences from "../helpers/sentence/getSentences.js";
+import { stripFullTags as stripHTMLTags } from "../helpers/sanitize/stripHTMLTags.js";
+import Sentence from "../../languageProcessing/values/Sentence.js";
+import { forEach } from "lodash";
+import removeHtmlBlocks from "../helpers/html/htmlParser";
+import { filterShortcodesFromHTML } from "../helpers";
 
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = getPassiveVoice;
-exports.getPeriphrasticPassives = exports.getMorphologicalPassives = void 0;
-var _getSentences = _interopRequireDefault(require("../helpers/sentence/getSentences.js"));
-var _stripHTMLTags = require("../helpers/sanitize/stripHTMLTags.js");
-var _Sentence = _interopRequireDefault(require("../../languageProcessing/values/Sentence.js"));
-var _lodash = require("lodash");
-var _htmlParser = _interopRequireDefault(require("../helpers/html/htmlParser"));
-var _helpers = require("../helpers");
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /**
  * Looks for morphological passive voice.
  * Supported morphological languages: "ru", "sv", "id", "ar", "he", "tr", "fa".
@@ -21,19 +14,19 @@ function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e
  *
  * @returns {Object} The found passive sentences.
  */
-const getMorphologicalPassives = function (paper, researcher) {
+export const getMorphologicalPassives = function (paper, researcher) {
   const isPassiveSentence = researcher.getHelper("isPassiveSentence");
   let text = paper.getText();
-  text = (0, _htmlParser.default)(text);
-  text = (0, _helpers.filterShortcodesFromHTML)(text, paper._attributes && paper._attributes.shortcodes);
+  text = removeHtmlBlocks(text);
+  text = filterShortcodesFromHTML(text, paper._attributes && paper._attributes.shortcodes);
   const memoizedTokenizer = researcher.getHelper("memoizedTokenizer");
-  const sentences = (0, _getSentences.default)(text, memoizedTokenizer).map(function (sentence) {
-    return new _Sentence.default(sentence);
+  const sentences = getSentences(text, memoizedTokenizer).map(function (sentence) {
+    return new Sentence(sentence);
   });
   const totalNumberSentences = sentences.length;
   const passiveSentences = [];
-  (0, _lodash.forEach)(sentences, function (sentence) {
-    const strippedSentence = (0, _stripHTMLTags.stripFullTags)(sentence.getSentenceText()).toLocaleLowerCase();
+  forEach(sentences, function (sentence) {
+    const strippedSentence = stripHTMLTags(sentence.getSentenceText()).toLocaleLowerCase();
     sentence.setPassive(isPassiveSentence(strippedSentence));
     if (sentence.isPassive() === true) {
       passiveSentences.push(sentence.getSentenceText());
@@ -54,20 +47,19 @@ const getMorphologicalPassives = function (paper, researcher) {
  *
  * @returns {Object} The found passive sentences.
  */
-exports.getMorphologicalPassives = getMorphologicalPassives;
-const getPeriphrasticPassives = function (paper, researcher) {
+export const getPeriphrasticPassives = function (paper, researcher) {
   const getClauses = researcher.getHelper("getClauses");
   let text = paper.getText();
-  text = (0, _htmlParser.default)(text);
-  text = (0, _helpers.filterShortcodesFromHTML)(text, paper._attributes && paper._attributes.shortcodes);
+  text = removeHtmlBlocks(text);
+  text = filterShortcodesFromHTML(text, paper._attributes && paper._attributes.shortcodes);
   const memoizedTokenizer = researcher.getHelper("memoizedTokenizer");
-  const sentences = (0, _getSentences.default)(text, memoizedTokenizer).map(function (sentence) {
-    return new _Sentence.default(sentence);
+  const sentences = getSentences(text, memoizedTokenizer).map(function (sentence) {
+    return new Sentence(sentence);
   });
   const totalNumberSentences = sentences.length;
   const passiveSentences = [];
-  (0, _lodash.forEach)(sentences, function (sentence) {
-    const strippedSentence = (0, _stripHTMLTags.stripFullTags)(sentence.getSentenceText()).toLocaleLowerCase();
+  forEach(sentences, function (sentence) {
+    const strippedSentence = stripHTMLTags(sentence.getSentenceText()).toLocaleLowerCase();
 
     // The functionality based on sentencePart objects should be rewritten using array indices of stopwords and auxiliaries.
 
@@ -96,7 +88,6 @@ const getPeriphrasticPassives = function (paper, researcher) {
  *
  * @returns {Object} The found passive sentences.
  */
-exports.getPeriphrasticPassives = getPeriphrasticPassives;
 const getMorphologicalAndPeriphrasticPassive = function (paper, researcher) {
   const morphologicalPassives = getMorphologicalPassives(paper, researcher);
   const periphrasticPassives = getPeriphrasticPassives(paper, researcher).passives;
@@ -114,7 +105,7 @@ const getMorphologicalAndPeriphrasticPassive = function (paper, researcher) {
  *
  * @returns {Object} The found passive sentences.
  */
-function getPassiveVoice(paper, researcher) {
+export default function getPassiveVoice(paper, researcher) {
   const passiveType = researcher.getConfig("passiveConstructionType");
   if (passiveType === "periphrastic") {
     return getPeriphrasticPassives(paper, researcher);

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

@@ -1 +1 @@
-{"version":3,"file":"getPassiveVoiceResult.js","names":["_getSentences","_interopRequireDefault","require","_stripHTMLTags","_Sentence","_lodash","_htmlParser","_helpers","e","__esModule","default","getMorphologicalPassives","paper","researcher","isPassiveSentence","getHelper","text","getText","removeHtmlBlocks","filterShortcodesFromHTML","_attributes","shortcodes","memoizedTokenizer","sentences","getSentences","map","sentence","Sentence","totalNumberSentences","length","passiveSentences","forEach","strippedSentence","stripHTMLTags","getSentenceText","toLocaleLowerCase","setPassive","isPassive","push","total","passives","exports","getPeriphrasticPassives","getClauses","clauses","setClauses","getMorphologicalAndPeriphrasticPassive","morphologicalPassives","periphrasticPassives","concat","getPassiveVoice","passiveType","getConfig"],"sources":["../../../src/languageProcessing/researches/getPassiveVoiceResult.js"],"sourcesContent":["import getSentences from \"../helpers/sentence/getSentences.js\";\nimport { stripFullTags as stripHTMLTags } from \"../helpers/sanitize/stripHTMLTags.js\";\nimport Sentence from \"../../languageProcessing/values/Sentence.js\";\n\nimport { forEach } from \"lodash\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\n\n/**\n * Looks for morphological passive voice.\n * Supported morphological languages: \"ru\", \"sv\", \"id\", \"ar\", \"he\", \"tr\", \"fa\".\n * Farsi is implemented as morphological because the periphrastic passives are used as compound verbs (among other compound passives).\n * @param {Paper}      paper      The paper object.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The found passive sentences.\n */\nexport const getMorphologicalPassives = function( paper, researcher ) {\n\tconst isPassiveSentence = researcher.getHelper( \"isPassiveSentence\" );\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\tconst sentences = getSentences( text, memoizedTokenizer )\n\t\t.map( function( sentence ) {\n\t\t\treturn new Sentence( sentence );\n\t\t} );\n\tconst totalNumberSentences = sentences.length;\n\tconst passiveSentences = [];\n\n\tforEach( sentences, function( sentence ) {\n\t\tconst strippedSentence = stripHTMLTags( sentence.getSentenceText() ).toLocaleLowerCase();\n\n\t\tsentence.setPassive( isPassiveSentence( strippedSentence ) );\n\n\t\tif ( sentence.isPassive() === true ) {\n\t\t\tpassiveSentences.push( sentence.getSentenceText() );\n\t\t}\n\t} );\n\n\treturn {\n\t\ttotal: totalNumberSentences,\n\t\tpassives: passiveSentences,\n\t};\n};\n\n/**\n * Looks for periphrastic passive voice.\n * Supported periphrastic languages: \"en\", \"de\", \"nl\", \"fr\", \"es\", \"it\", \"pt\", \"pl\", \"sk\".\n *\n * @param {Paper}      paper      The paper object.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The found passive sentences.\n */\nexport const getPeriphrasticPassives = function( paper, researcher ) {\n\tconst getClauses = researcher.getHelper( \"getClauses\" );\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\tconst sentences = getSentences( text, memoizedTokenizer )\n\t\t.map( function( sentence ) {\n\t\t\treturn new Sentence( sentence );\n\t\t} );\n\tconst totalNumberSentences = sentences.length;\n\tconst passiveSentences = [];\n\n\tforEach( sentences, function( sentence ) {\n\t\tconst strippedSentence = stripHTMLTags( sentence.getSentenceText() ).toLocaleLowerCase();\n\n\t\t// The functionality based on sentencePart objects should be rewritten using array indices of stopwords and auxiliaries.\n\n\t\t// Divide a sentence into clauses and return an array of clause objects that have been checked for passiveness.\n\t\tconst clauses = getClauses( strippedSentence );\n\t\tsentence.setClauses( clauses );\n\n\t\t// Check sentence passiveness based on its clause passiveness.\n\t\tif ( sentence.isPassive() ) {\n\t\t\tpassiveSentences.push( sentence.getSentenceText() );\n\t\t}\n\t} );\n\n\treturn {\n\t\ttotal: totalNumberSentences,\n\t\tpassives: passiveSentences,\n\t};\n};\n\n/**\n * Looks for both morphological and periphrastic passive voice\n * Supported languages with both morphological and periphrastic passives: \"hu\", \"nb\".\n * Due to technical difficulties \"nb\" is only implemented as periphrastic at the moment. Languages that have not been implemented yet: \"da\".\n *\n * @param {Paper}      paper      The paper object.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The found passive sentences.\n */\nconst getMorphologicalAndPeriphrasticPassive = function( paper, researcher ) {\n\tconst morphologicalPassives = getMorphologicalPassives( paper, researcher );\n\tconst periphrasticPassives = getPeriphrasticPassives( paper, researcher ).passives;\n\n\treturn {\n\t\ttotal: morphologicalPassives.total,\n\t\tpassives: periphrasticPassives.concat( morphologicalPassives.passives ),\n\t};\n};\n\n/**\n * Looks for passive voice.\n *\n * @param {Paper}      paper      The paper object.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The found passive sentences.\n */\nexport default function getPassiveVoice( paper, researcher ) {\n\tconst passiveType = researcher.getConfig( \"passiveConstructionType\" );\n\n\tif ( passiveType === \"periphrastic\" ) {\n\t\treturn getPeriphrasticPassives( paper, researcher );\n\t}\n\tif ( passiveType === \"morphological\" ) {\n\t\treturn getMorphologicalPassives( paper, researcher );\n\t}\n\n\treturn getMorphologicalAndPeriphrasticPassive( paper, researcher );\n}\n"],"mappings":";;;;;;;AAAA,IAAAA,aAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,cAAA,GAAAD,OAAA;AACA,IAAAE,SAAA,GAAAH,sBAAA,CAAAC,OAAA;AAEA,IAAAG,OAAA,GAAAH,OAAA;AACA,IAAAI,WAAA,GAAAL,sBAAA,CAAAC,OAAA;AACA,IAAAK,QAAA,GAAAL,OAAA;AAAsD,SAAAD,uBAAAO,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEtD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACO,MAAMG,wBAAwB,GAAG,SAAAA,CAAUC,KAAK,EAAEC,UAAU,EAAG;EACrE,MAAMC,iBAAiB,GAAGD,UAAU,CAACE,SAAS,CAAE,mBAAoB,CAAC;EACrE,IAAIC,IAAI,GAAGJ,KAAK,CAACK,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAG,IAAAE,mBAAgB,EAAEF,IAAK,CAAC;EAC/BA,IAAI,GAAG,IAAAG,iCAAwB,EAAEH,IAAI,EAAEJ,KAAK,CAACQ,WAAW,IAAIR,KAAK,CAACQ,WAAW,CAACC,UAAW,CAAC;EAC1F,MAAMC,iBAAiB,GAAGT,UAAU,CAACE,SAAS,CAAE,mBAAoB,CAAC;EACrE,MAAMQ,SAAS,GAAG,IAAAC,qBAAY,EAAER,IAAI,EAAEM,iBAAkB,CAAC,CACvDG,GAAG,CAAE,UAAUC,QAAQ,EAAG;IAC1B,OAAO,IAAIC,iBAAQ,CAAED,QAAS,CAAC;EAChC,CAAE,CAAC;EACJ,MAAME,oBAAoB,GAAGL,SAAS,CAACM,MAAM;EAC7C,MAAMC,gBAAgB,GAAG,EAAE;EAE3B,IAAAC,eAAO,EAAER,SAAS,EAAE,UAAUG,QAAQ,EAAG;IACxC,MAAMM,gBAAgB,GAAG,IAAAC,4BAAa,EAAEP,QAAQ,CAACQ,eAAe,CAAC,CAAE,CAAC,CAACC,iBAAiB,CAAC,CAAC;IAExFT,QAAQ,CAACU,UAAU,CAAEtB,iBAAiB,CAAEkB,gBAAiB,CAAE,CAAC;IAE5D,IAAKN,QAAQ,CAACW,SAAS,CAAC,CAAC,KAAK,IAAI,EAAG;MACpCP,gBAAgB,CAACQ,IAAI,CAAEZ,QAAQ,CAACQ,eAAe,CAAC,CAAE,CAAC;IACpD;EACD,CAAE,CAAC;EAEH,OAAO;IACNK,KAAK,EAAEX,oBAAoB;IAC3BY,QAAQ,EAAEV;EACX,CAAC;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AARAW,OAAA,CAAA9B,wBAAA,GAAAA,wBAAA;AASO,MAAM+B,uBAAuB,GAAG,SAAAA,CAAU9B,KAAK,EAAEC,UAAU,EAAG;EACpE,MAAM8B,UAAU,GAAG9B,UAAU,CAACE,SAAS,CAAE,YAAa,CAAC;EACvD,IAAIC,IAAI,GAAGJ,KAAK,CAACK,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAG,IAAAE,mBAAgB,EAAEF,IAAK,CAAC;EAC/BA,IAAI,GAAG,IAAAG,iCAAwB,EAAEH,IAAI,EAAEJ,KAAK,CAACQ,WAAW,IAAIR,KAAK,CAACQ,WAAW,CAACC,UAAW,CAAC;EAC1F,MAAMC,iBAAiB,GAAGT,UAAU,CAACE,SAAS,CAAE,mBAAoB,CAAC;EACrE,MAAMQ,SAAS,GAAG,IAAAC,qBAAY,EAAER,IAAI,EAAEM,iBAAkB,CAAC,CACvDG,GAAG,CAAE,UAAUC,QAAQ,EAAG;IAC1B,OAAO,IAAIC,iBAAQ,CAAED,QAAS,CAAC;EAChC,CAAE,CAAC;EACJ,MAAME,oBAAoB,GAAGL,SAAS,CAACM,MAAM;EAC7C,MAAMC,gBAAgB,GAAG,EAAE;EAE3B,IAAAC,eAAO,EAAER,SAAS,EAAE,UAAUG,QAAQ,EAAG;IACxC,MAAMM,gBAAgB,GAAG,IAAAC,4BAAa,EAAEP,QAAQ,CAACQ,eAAe,CAAC,CAAE,CAAC,CAACC,iBAAiB,CAAC,CAAC;;IAExF;;IAEA;IACA,MAAMS,OAAO,GAAGD,UAAU,CAAEX,gBAAiB,CAAC;IAC9CN,QAAQ,CAACmB,UAAU,CAAED,OAAQ,CAAC;;IAE9B;IACA,IAAKlB,QAAQ,CAACW,SAAS,CAAC,CAAC,EAAG;MAC3BP,gBAAgB,CAACQ,IAAI,CAAEZ,QAAQ,CAACQ,eAAe,CAAC,CAAE,CAAC;IACpD;EACD,CAAE,CAAC;EAEH,OAAO;IACNK,KAAK,EAAEX,oBAAoB;IAC3BY,QAAQ,EAAEV;EACX,CAAC;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AATAW,OAAA,CAAAC,uBAAA,GAAAA,uBAAA;AAUA,MAAMI,sCAAsC,GAAG,SAAAA,CAAUlC,KAAK,EAAEC,UAAU,EAAG;EAC5E,MAAMkC,qBAAqB,GAAGpC,wBAAwB,CAAEC,KAAK,EAAEC,UAAW,CAAC;EAC3E,MAAMmC,oBAAoB,GAAGN,uBAAuB,CAAE9B,KAAK,EAAEC,UAAW,CAAC,CAAC2B,QAAQ;EAElF,OAAO;IACND,KAAK,EAAEQ,qBAAqB,CAACR,KAAK;IAClCC,QAAQ,EAAEQ,oBAAoB,CAACC,MAAM,CAAEF,qBAAqB,CAACP,QAAS;EACvE,CAAC;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAASU,eAAeA,CAAEtC,KAAK,EAAEC,UAAU,EAAG;EAC5D,MAAMsC,WAAW,GAAGtC,UAAU,CAACuC,SAAS,CAAE,yBAA0B,CAAC;EAErE,IAAKD,WAAW,KAAK,cAAc,EAAG;IACrC,OAAOT,uBAAuB,CAAE9B,KAAK,EAAEC,UAAW,CAAC;EACpD;EACA,IAAKsC,WAAW,KAAK,eAAe,EAAG;IACtC,OAAOxC,wBAAwB,CAAEC,KAAK,EAAEC,UAAW,CAAC;EACrD;EAEA,OAAOiC,sCAAsC,CAAElC,KAAK,EAAEC,UAAW,CAAC;AACnE","ignoreList":[]}
+{"version":3,"file":"getPassiveVoiceResult.js","names":["getSentences","stripFullTags","stripHTMLTags","Sentence","forEach","removeHtmlBlocks","filterShortcodesFromHTML","getMorphologicalPassives","paper","researcher","isPassiveSentence","getHelper","text","getText","_attributes","shortcodes","memoizedTokenizer","sentences","map","sentence","totalNumberSentences","length","passiveSentences","strippedSentence","getSentenceText","toLocaleLowerCase","setPassive","isPassive","push","total","passives","getPeriphrasticPassives","getClauses","clauses","setClauses","getMorphologicalAndPeriphrasticPassive","morphologicalPassives","periphrasticPassives","concat","getPassiveVoice","passiveType","getConfig"],"sources":["../../../src/languageProcessing/researches/getPassiveVoiceResult.js"],"sourcesContent":["import getSentences from \"../helpers/sentence/getSentences.js\";\nimport { stripFullTags as stripHTMLTags } from \"../helpers/sanitize/stripHTMLTags.js\";\nimport Sentence from \"../../languageProcessing/values/Sentence.js\";\n\nimport { forEach } from \"lodash\";\nimport removeHtmlBlocks from \"../helpers/html/htmlParser\";\nimport { filterShortcodesFromHTML } from \"../helpers\";\n\n/**\n * Looks for morphological passive voice.\n * Supported morphological languages: \"ru\", \"sv\", \"id\", \"ar\", \"he\", \"tr\", \"fa\".\n * Farsi is implemented as morphological because the periphrastic passives are used as compound verbs (among other compound passives).\n * @param {Paper}      paper      The paper object.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The found passive sentences.\n */\nexport const getMorphologicalPassives = function( paper, researcher ) {\n\tconst isPassiveSentence = researcher.getHelper( \"isPassiveSentence\" );\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\tconst sentences = getSentences( text, memoizedTokenizer )\n\t\t.map( function( sentence ) {\n\t\t\treturn new Sentence( sentence );\n\t\t} );\n\tconst totalNumberSentences = sentences.length;\n\tconst passiveSentences = [];\n\n\tforEach( sentences, function( sentence ) {\n\t\tconst strippedSentence = stripHTMLTags( sentence.getSentenceText() ).toLocaleLowerCase();\n\n\t\tsentence.setPassive( isPassiveSentence( strippedSentence ) );\n\n\t\tif ( sentence.isPassive() === true ) {\n\t\t\tpassiveSentences.push( sentence.getSentenceText() );\n\t\t}\n\t} );\n\n\treturn {\n\t\ttotal: totalNumberSentences,\n\t\tpassives: passiveSentences,\n\t};\n};\n\n/**\n * Looks for periphrastic passive voice.\n * Supported periphrastic languages: \"en\", \"de\", \"nl\", \"fr\", \"es\", \"it\", \"pt\", \"pl\", \"sk\".\n *\n * @param {Paper}      paper      The paper object.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The found passive sentences.\n */\nexport const getPeriphrasticPassives = function( paper, researcher ) {\n\tconst getClauses = researcher.getHelper( \"getClauses\" );\n\tlet text = paper.getText();\n\ttext = removeHtmlBlocks( text );\n\ttext = filterShortcodesFromHTML( text, paper._attributes && paper._attributes.shortcodes );\n\tconst memoizedTokenizer = researcher.getHelper( \"memoizedTokenizer\" );\n\tconst sentences = getSentences( text, memoizedTokenizer )\n\t\t.map( function( sentence ) {\n\t\t\treturn new Sentence( sentence );\n\t\t} );\n\tconst totalNumberSentences = sentences.length;\n\tconst passiveSentences = [];\n\n\tforEach( sentences, function( sentence ) {\n\t\tconst strippedSentence = stripHTMLTags( sentence.getSentenceText() ).toLocaleLowerCase();\n\n\t\t// The functionality based on sentencePart objects should be rewritten using array indices of stopwords and auxiliaries.\n\n\t\t// Divide a sentence into clauses and return an array of clause objects that have been checked for passiveness.\n\t\tconst clauses = getClauses( strippedSentence );\n\t\tsentence.setClauses( clauses );\n\n\t\t// Check sentence passiveness based on its clause passiveness.\n\t\tif ( sentence.isPassive() ) {\n\t\t\tpassiveSentences.push( sentence.getSentenceText() );\n\t\t}\n\t} );\n\n\treturn {\n\t\ttotal: totalNumberSentences,\n\t\tpassives: passiveSentences,\n\t};\n};\n\n/**\n * Looks for both morphological and periphrastic passive voice\n * Supported languages with both morphological and periphrastic passives: \"hu\", \"nb\".\n * Due to technical difficulties \"nb\" is only implemented as periphrastic at the moment. Languages that have not been implemented yet: \"da\".\n *\n * @param {Paper}      paper      The paper object.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The found passive sentences.\n */\nconst getMorphologicalAndPeriphrasticPassive = function( paper, researcher ) {\n\tconst morphologicalPassives = getMorphologicalPassives( paper, researcher );\n\tconst periphrasticPassives = getPeriphrasticPassives( paper, researcher ).passives;\n\n\treturn {\n\t\ttotal: morphologicalPassives.total,\n\t\tpassives: periphrasticPassives.concat( morphologicalPassives.passives ),\n\t};\n};\n\n/**\n * Looks for passive voice.\n *\n * @param {Paper}      paper      The paper object.\n * @param {Researcher} researcher The researcher.\n *\n * @returns {Object} The found passive sentences.\n */\nexport default function getPassiveVoice( paper, researcher ) {\n\tconst passiveType = researcher.getConfig( \"passiveConstructionType\" );\n\n\tif ( passiveType === \"periphrastic\" ) {\n\t\treturn getPeriphrasticPassives( paper, researcher );\n\t}\n\tif ( passiveType === \"morphological\" ) {\n\t\treturn getMorphologicalPassives( paper, researcher );\n\t}\n\n\treturn getMorphologicalAndPeriphrasticPassive( paper, researcher );\n}\n"],"mappings":"AAAA,OAAOA,YAAY;AACnB,SAASC,aAAa,IAAIC,aAAa;AACvC,OAAOC,QAAQ;AAEf,SAASC,OAAO,QAAQ,QAAQ;AAChC,OAAOC,gBAAgB;AACvB,SAASC,wBAAwB;;AAEjC;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,MAAMC,wBAAwB,GAAG,SAAAA,CAAUC,KAAK,EAAEC,UAAU,EAAG;EACrE,MAAMC,iBAAiB,GAAGD,UAAU,CAACE,SAAS,CAAE,mBAAoB,CAAC;EACrE,IAAIC,IAAI,GAAGJ,KAAK,CAACK,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAGP,gBAAgB,CAAEO,IAAK,CAAC;EAC/BA,IAAI,GAAGN,wBAAwB,CAAEM,IAAI,EAAEJ,KAAK,CAACM,WAAW,IAAIN,KAAK,CAACM,WAAW,CAACC,UAAW,CAAC;EAC1F,MAAMC,iBAAiB,GAAGP,UAAU,CAACE,SAAS,CAAE,mBAAoB,CAAC;EACrE,MAAMM,SAAS,GAAGjB,YAAY,CAAEY,IAAI,EAAEI,iBAAkB,CAAC,CACvDE,GAAG,CAAE,UAAUC,QAAQ,EAAG;IAC1B,OAAO,IAAIhB,QAAQ,CAAEgB,QAAS,CAAC;EAChC,CAAE,CAAC;EACJ,MAAMC,oBAAoB,GAAGH,SAAS,CAACI,MAAM;EAC7C,MAAMC,gBAAgB,GAAG,EAAE;EAE3BlB,OAAO,CAAEa,SAAS,EAAE,UAAUE,QAAQ,EAAG;IACxC,MAAMI,gBAAgB,GAAGrB,aAAa,CAAEiB,QAAQ,CAACK,eAAe,CAAC,CAAE,CAAC,CAACC,iBAAiB,CAAC,CAAC;IAExFN,QAAQ,CAACO,UAAU,CAAEhB,iBAAiB,CAAEa,gBAAiB,CAAE,CAAC;IAE5D,IAAKJ,QAAQ,CAACQ,SAAS,CAAC,CAAC,KAAK,IAAI,EAAG;MACpCL,gBAAgB,CAACM,IAAI,CAAET,QAAQ,CAACK,eAAe,CAAC,CAAE,CAAC;IACpD;EACD,CAAE,CAAC;EAEH,OAAO;IACNK,KAAK,EAAET,oBAAoB;IAC3BU,QAAQ,EAAER;EACX,CAAC;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,MAAMS,uBAAuB,GAAG,SAAAA,CAAUvB,KAAK,EAAEC,UAAU,EAAG;EACpE,MAAMuB,UAAU,GAAGvB,UAAU,CAACE,SAAS,CAAE,YAAa,CAAC;EACvD,IAAIC,IAAI,GAAGJ,KAAK,CAACK,OAAO,CAAC,CAAC;EAC1BD,IAAI,GAAGP,gBAAgB,CAAEO,IAAK,CAAC;EAC/BA,IAAI,GAAGN,wBAAwB,CAAEM,IAAI,EAAEJ,KAAK,CAACM,WAAW,IAAIN,KAAK,CAACM,WAAW,CAACC,UAAW,CAAC;EAC1F,MAAMC,iBAAiB,GAAGP,UAAU,CAACE,SAAS,CAAE,mBAAoB,CAAC;EACrE,MAAMM,SAAS,GAAGjB,YAAY,CAAEY,IAAI,EAAEI,iBAAkB,CAAC,CACvDE,GAAG,CAAE,UAAUC,QAAQ,EAAG;IAC1B,OAAO,IAAIhB,QAAQ,CAAEgB,QAAS,CAAC;EAChC,CAAE,CAAC;EACJ,MAAMC,oBAAoB,GAAGH,SAAS,CAACI,MAAM;EAC7C,MAAMC,gBAAgB,GAAG,EAAE;EAE3BlB,OAAO,CAAEa,SAAS,EAAE,UAAUE,QAAQ,EAAG;IACxC,MAAMI,gBAAgB,GAAGrB,aAAa,CAAEiB,QAAQ,CAACK,eAAe,CAAC,CAAE,CAAC,CAACC,iBAAiB,CAAC,CAAC;;IAExF;;IAEA;IACA,MAAMQ,OAAO,GAAGD,UAAU,CAAET,gBAAiB,CAAC;IAC9CJ,QAAQ,CAACe,UAAU,CAAED,OAAQ,CAAC;;IAE9B;IACA,IAAKd,QAAQ,CAACQ,SAAS,CAAC,CAAC,EAAG;MAC3BL,gBAAgB,CAACM,IAAI,CAAET,QAAQ,CAACK,eAAe,CAAC,CAAE,CAAC;IACpD;EACD,CAAE,CAAC;EAEH,OAAO;IACNK,KAAK,EAAET,oBAAoB;IAC3BU,QAAQ,EAAER;EACX,CAAC;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMa,sCAAsC,GAAG,SAAAA,CAAU3B,KAAK,EAAEC,UAAU,EAAG;EAC5E,MAAM2B,qBAAqB,GAAG7B,wBAAwB,CAAEC,KAAK,EAAEC,UAAW,CAAC;EAC3E,MAAM4B,oBAAoB,GAAGN,uBAAuB,CAAEvB,KAAK,EAAEC,UAAW,CAAC,CAACqB,QAAQ;EAElF,OAAO;IACND,KAAK,EAAEO,qBAAqB,CAACP,KAAK;IAClCC,QAAQ,EAAEO,oBAAoB,CAACC,MAAM,CAAEF,qBAAqB,CAACN,QAAS;EACvE,CAAC;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,SAASS,eAAeA,CAAE/B,KAAK,EAAEC,UAAU,EAAG;EAC5D,MAAM+B,WAAW,GAAG/B,UAAU,CAACgC,SAAS,CAAE,yBAA0B,CAAC;EAErE,IAAKD,WAAW,KAAK,cAAc,EAAG;IACrC,OAAOT,uBAAuB,CAAEvB,KAAK,EAAEC,UAAW,CAAC;EACpD;EACA,IAAK+B,WAAW,KAAK,eAAe,EAAG;IACtC,OAAOjC,wBAAwB,CAAEC,KAAK,EAAEC,UAAW,CAAC;EACrD;EAEA,OAAO0B,sCAAsC,CAAE3B,KAAK,EAAEC,UAAW,CAAC;AACnE","ignoreList":[]}

package/build/languageProcessing/researches/getProminentWordsForInsights.js

@@ -1,14 +1,8 @@
-"use strict";
+import { take } from "lodash";
+import { collapseProminentWordsOnStem, filterProminentWords, getProminentWords, retrieveAbbreviations, sortProminentWords } from "../helpers/prominentWords/determineProminentWords";
+import removeURLs from "../helpers/sanitize/removeURLs.js";
+import removeEmailAddresses from "../helpers/sanitize/removeEmailAddresses";
 
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = void 0;
-var _lodash = require("lodash");
-var _determineProminentWords = require("../helpers/prominentWords/determineProminentWords");
-var _removeURLs = _interopRequireDefault(require("../helpers/sanitize/removeURLs.js"));
-var _removeEmailAddresses = _interopRequireDefault(require("../helpers/sanitize/removeEmailAddresses"));
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /**
  * Retrieves the prominent words from the given paper.
  *
@@ -26,20 +20,20 @@ function getProminentWordsForInsights(paper, researcher) {
   const getWordsCustomHelper = researcher.getHelper("getWordsCustomHelper");
   let text = paper.getText();
   // We don't want to include URLs or email addresses in prominent words.
-  text = (0, _removeURLs.default)(text);
-  text = (0, _removeEmailAddresses.default)(text);
+  text = removeURLs(text);
+  text = removeEmailAddresses(text);
 
   // If the language has a custom helper to get words from the text, we don't retrieve the abbreviation.
-  const abbreviations = getWordsCustomHelper ? [] : (0, _determineProminentWords.retrieveAbbreviations)(text);
-  const prominentWordsFromText = (0, _determineProminentWords.getProminentWords)(text, abbreviations, stemmer, functionWords, getWordsCustomHelper);
-  const collapsedWords = (0, _determineProminentWords.collapseProminentWordsOnStem)(prominentWordsFromText);
-  (0, _determineProminentWords.sortProminentWords)(collapsedWords);
+  const abbreviations = getWordsCustomHelper ? [] : retrieveAbbreviations(text);
+  const prominentWordsFromText = getProminentWords(text, abbreviations, stemmer, functionWords, getWordsCustomHelper);
+  const collapsedWords = collapseProminentWordsOnStem(prominentWordsFromText);
+  sortProminentWords(collapsedWords);
 
   /*
    * Collapse the list of prominent words on stems, sort it, filter out all words that occur less than
    * 5 times in the text. Return the 20 top items from this list.
    */
-  return (0, _lodash.take)((0, _determineProminentWords.filterProminentWords)(collapsedWords, 5), 20);
+  return take(filterProminentWords(collapsedWords, 5), 20);
 }
-var _default = exports.default = getProminentWordsForInsights;
+export default getProminentWordsForInsights;
 //# sourceMappingURL=getProminentWordsForInsights.js.map

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

@@ -1 +1 @@
-{"version":3,"file":"getProminentWordsForInsights.js","names":["_lodash","require","_determineProminentWords","_removeURLs","_interopRequireDefault","_removeEmailAddresses","e","__esModule","default","getProminentWordsForInsights","paper","researcher","functionWords","getConfig","customStemmer","getHelper","stemmer","getWordsCustomHelper","text","getText","removeURLs","removeEmailAddresses","abbreviations","retrieveAbbreviations","prominentWordsFromText","getProminentWords","collapsedWords","collapseProminentWordsOnStem","sortProminentWords","take","filterProminentWords","_default","exports"],"sources":["../../../src/languageProcessing/researches/getProminentWordsForInsights.js"],"sourcesContent":["import { take } from \"lodash\";\nimport {\n\tcollapseProminentWordsOnStem,\n\tfilterProminentWords,\n\tgetProminentWords,\n\tretrieveAbbreviations,\n\tsortProminentWords,\n} from \"../helpers/prominentWords/determineProminentWords\";\nimport removeURLs from \"../helpers/sanitize/removeURLs.js\";\nimport removeEmailAddresses from \"../helpers/sanitize/removeEmailAddresses\";\n\n/**\n * Retrieves the prominent words from the given paper.\n *\n * @param {Paper} paper             The paper to determine the prominent words of.\n * @param {Researcher} researcher   The researcher to use for analysis.\n *\n * @returns {WordCombination[]} Prominent words for this paper, filtered and sorted.\n */\nfunction getProminentWordsForInsights( paper, researcher ) {\n\tconst functionWords = researcher.getConfig( \"functionWords\" );\n\t// An optional custom helper to return custom function to return the stem of a word.\n\tconst customStemmer = researcher.getHelper( \"customGetStemmer\" );\n\tconst stemmer = customStemmer ? customStemmer( researcher ) : researcher.getHelper( \"getStemmer\" )( researcher );\n\t// An optional custom helper to get words from the text.\n\tconst getWordsCustomHelper = researcher.getHelper( \"getWordsCustomHelper\" );\n\n\tlet text = paper.getText();\n\t// We don't want to include URLs or email addresses in prominent words.\n\ttext = removeURLs( text );\n\ttext = removeEmailAddresses( text );\n\n\t// If the language has a custom helper to get words from the text, we don't retrieve the abbreviation.\n\tconst abbreviations = getWordsCustomHelper ? [] : retrieveAbbreviations( text );\n\n\tconst prominentWordsFromText = getProminentWords( text, abbreviations, stemmer, functionWords, getWordsCustomHelper );\n\n\tconst collapsedWords = collapseProminentWordsOnStem( prominentWordsFromText );\n\tsortProminentWords( collapsedWords );\n\n\t/*\n\t * Collapse the list of prominent words on stems, sort it, filter out all words that occur less than\n\t * 5 times in the text. Return the 20 top items from this list.\n\t */\n\treturn take( filterProminentWords( collapsedWords, 5 ), 20 );\n}\n\nexport default getProminentWordsForInsights;\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AACA,IAAAC,wBAAA,GAAAD,OAAA;AAOA,IAAAE,WAAA,GAAAC,sBAAA,CAAAH,OAAA;AACA,IAAAI,qBAAA,GAAAD,sBAAA,CAAAH,OAAA;AAA4E,SAAAG,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAE5E;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASG,4BAA4BA,CAAEC,KAAK,EAAEC,UAAU,EAAG;EAC1D,MAAMC,aAAa,GAAGD,UAAU,CAACE,SAAS,CAAE,eAAgB,CAAC;EAC7D;EACA,MAAMC,aAAa,GAAGH,UAAU,CAACI,SAAS,CAAE,kBAAmB,CAAC;EAChE,MAAMC,OAAO,GAAGF,aAAa,GAAGA,aAAa,CAAEH,UAAW,CAAC,GAAGA,UAAU,CAACI,SAAS,CAAE,YAAa,CAAC,CAAEJ,UAAW,CAAC;EAChH;EACA,MAAMM,oBAAoB,GAAGN,UAAU,CAACI,SAAS,CAAE,sBAAuB,CAAC;EAE3E,IAAIG,IAAI,GAAGR,KAAK,CAACS,OAAO,CAAC,CAAC;EAC1B;EACAD,IAAI,GAAG,IAAAE,mBAAU,EAAEF,IAAK,CAAC;EACzBA,IAAI,GAAG,IAAAG,6BAAoB,EAAEH,IAAK,CAAC;;EAEnC;EACA,MAAMI,aAAa,GAAGL,oBAAoB,GAAG,EAAE,GAAG,IAAAM,8CAAqB,EAAEL,IAAK,CAAC;EAE/E,MAAMM,sBAAsB,GAAG,IAAAC,0CAAiB,EAAEP,IAAI,EAAEI,aAAa,EAAEN,OAAO,EAAEJ,aAAa,EAAEK,oBAAqB,CAAC;EAErH,MAAMS,cAAc,GAAG,IAAAC,qDAA4B,EAAEH,sBAAuB,CAAC;EAC7E,IAAAI,2CAAkB,EAAEF,cAAe,CAAC;;EAEpC;AACD;AACA;AACA;EACC,OAAO,IAAAG,YAAI,EAAE,IAAAC,6CAAoB,EAAEJ,cAAc,EAAE,CAAE,CAAC,EAAE,EAAG,CAAC;AAC7D;AAAC,IAAAK,QAAA,GAAAC,OAAA,CAAAxB,OAAA,GAEcC,4BAA4B","ignoreList":[]}
+{"version":3,"file":"getProminentWordsForInsights.js","names":["take","collapseProminentWordsOnStem","filterProminentWords","getProminentWords","retrieveAbbreviations","sortProminentWords","removeURLs","removeEmailAddresses","getProminentWordsForInsights","paper","researcher","functionWords","getConfig","customStemmer","getHelper","stemmer","getWordsCustomHelper","text","getText","abbreviations","prominentWordsFromText","collapsedWords"],"sources":["../../../src/languageProcessing/researches/getProminentWordsForInsights.js"],"sourcesContent":["import { take } from \"lodash\";\nimport {\n\tcollapseProminentWordsOnStem,\n\tfilterProminentWords,\n\tgetProminentWords,\n\tretrieveAbbreviations,\n\tsortProminentWords,\n} from \"../helpers/prominentWords/determineProminentWords\";\nimport removeURLs from \"../helpers/sanitize/removeURLs.js\";\nimport removeEmailAddresses from \"../helpers/sanitize/removeEmailAddresses\";\n\n/**\n * Retrieves the prominent words from the given paper.\n *\n * @param {Paper} paper             The paper to determine the prominent words of.\n * @param {Researcher} researcher   The researcher to use for analysis.\n *\n * @returns {WordCombination[]} Prominent words for this paper, filtered and sorted.\n */\nfunction getProminentWordsForInsights( paper, researcher ) {\n\tconst functionWords = researcher.getConfig( \"functionWords\" );\n\t// An optional custom helper to return custom function to return the stem of a word.\n\tconst customStemmer = researcher.getHelper( \"customGetStemmer\" );\n\tconst stemmer = customStemmer ? customStemmer( researcher ) : researcher.getHelper( \"getStemmer\" )( researcher );\n\t// An optional custom helper to get words from the text.\n\tconst getWordsCustomHelper = researcher.getHelper( \"getWordsCustomHelper\" );\n\n\tlet text = paper.getText();\n\t// We don't want to include URLs or email addresses in prominent words.\n\ttext = removeURLs( text );\n\ttext = removeEmailAddresses( text );\n\n\t// If the language has a custom helper to get words from the text, we don't retrieve the abbreviation.\n\tconst abbreviations = getWordsCustomHelper ? [] : retrieveAbbreviations( text );\n\n\tconst prominentWordsFromText = getProminentWords( text, abbreviations, stemmer, functionWords, getWordsCustomHelper );\n\n\tconst collapsedWords = collapseProminentWordsOnStem( prominentWordsFromText );\n\tsortProminentWords( collapsedWords );\n\n\t/*\n\t * Collapse the list of prominent words on stems, sort it, filter out all words that occur less than\n\t * 5 times in the text. Return the 20 top items from this list.\n\t */\n\treturn take( filterProminentWords( collapsedWords, 5 ), 20 );\n}\n\nexport default getProminentWordsForInsights;\n"],"mappings":"AAAA,SAASA,IAAI,QAAQ,QAAQ;AAC7B,SACCC,4BAA4B,EAC5BC,oBAAoB,EACpBC,iBAAiB,EACjBC,qBAAqB,EACrBC,kBAAkB;AAEnB,OAAOC,UAAU;AACjB,OAAOC,oBAAoB;;AAE3B;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,4BAA4BA,CAAEC,KAAK,EAAEC,UAAU,EAAG;EAC1D,MAAMC,aAAa,GAAGD,UAAU,CAACE,SAAS,CAAE,eAAgB,CAAC;EAC7D;EACA,MAAMC,aAAa,GAAGH,UAAU,CAACI,SAAS,CAAE,kBAAmB,CAAC;EAChE,MAAMC,OAAO,GAAGF,aAAa,GAAGA,aAAa,CAAEH,UAAW,CAAC,GAAGA,UAAU,CAACI,SAAS,CAAE,YAAa,CAAC,CAAEJ,UAAW,CAAC;EAChH;EACA,MAAMM,oBAAoB,GAAGN,UAAU,CAACI,SAAS,CAAE,sBAAuB,CAAC;EAE3E,IAAIG,IAAI,GAAGR,KAAK,CAACS,OAAO,CAAC,CAAC;EAC1B;EACAD,IAAI,GAAGX,UAAU,CAAEW,IAAK,CAAC;EACzBA,IAAI,GAAGV,oBAAoB,CAAEU,IAAK,CAAC;;EAEnC;EACA,MAAME,aAAa,GAAGH,oBAAoB,GAAG,EAAE,GAAGZ,qBAAqB,CAAEa,IAAK,CAAC;EAE/E,MAAMG,sBAAsB,GAAGjB,iBAAiB,CAAEc,IAAI,EAAEE,aAAa,EAAEJ,OAAO,EAAEJ,aAAa,EAAEK,oBAAqB,CAAC;EAErH,MAAMK,cAAc,GAAGpB,4BAA4B,CAAEmB,sBAAuB,CAAC;EAC7Ef,kBAAkB,CAAEgB,cAAe,CAAC;;EAEpC;AACD;AACA;AACA;EACC,OAAOrB,IAAI,CAAEE,oBAAoB,CAAEmB,cAAc,EAAE,CAAE,CAAC,EAAE,EAAG,CAAC;AAC7D;AAEA,eAAeb,4BAA4B","ignoreList":[]}

package/build/languageProcessing/researches/getProminentWordsForInternalLinking.js

@@ -1,17 +1,11 @@
-"use strict";
+import { take } from "lodash";
+import countWords from "../helpers/word/countWords";
+import { collapseProminentWordsOnStem, filterProminentWords, getProminentWords, getProminentWordsFromPaperAttributes, retrieveAbbreviations, sortProminentWords } from "../helpers/prominentWords/determineProminentWords";
+import { getSubheadingsTopLevel, removeSubheadingsTopLevel } from "../helpers/html/getSubheadings";
+import baseStemmer from "../helpers/morphology/baseStemmer";
+import removeURLs from "../helpers/sanitize/removeURLs.js";
+import removeEmailAddresses from "../helpers/sanitize/removeEmailAddresses";
 
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = void 0;
-var _lodash = require("lodash");
-var _countWords = _interopRequireDefault(require("../helpers/word/countWords"));
-var _determineProminentWords = require("../helpers/prominentWords/determineProminentWords");
-var _getSubheadings = require("../helpers/html/getSubheadings");
-var _baseStemmer = _interopRequireDefault(require("../helpers/morphology/baseStemmer"));
-var _removeURLs = _interopRequireDefault(require("../helpers/sanitize/removeURLs.js"));
-var _removeEmailAddresses = _interopRequireDefault(require("../helpers/sanitize/removeEmailAddresses"));
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /**
  * Removes URLs and email addresses from the text.
  *
@@ -20,8 +14,8 @@ function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e
  * @returns {string} The text without URLs and email addresses.
  */
 const sanitizeText = function (text) {
-  text = (0, _removeURLs.default)(text);
-  return (0, _removeEmailAddresses.default)(text);
+  text = removeURLs(text);
+  return removeEmailAddresses(text);
 };
 
 /**
@@ -60,25 +54,25 @@ function getProminentWordsForInternalLinking(paper, researcher) {
     if (customCountLength(text) < 200) {
       return result;
     }
-  } else if ((0, _countWords.default)(text) < 100) {
+  } else if (countWords(text) < 100) {
     return result;
   }
-  const subheadings = (0, _getSubheadings.getSubheadingsTopLevel)(text).map(subheading => subheading[2]);
+  const subheadings = getSubheadingsTopLevel(text).map(subheading => subheading[2]);
   const attributes = [paper.getKeyword(), paper.getSynonyms(), title, metadescription, subheadings.join(" ")];
 
   // If the language has a custom helper to get words from the text, we don't retrieve the abbreviation.
-  const abbreviations = getWordsCustomHelper ? [] : (0, _determineProminentWords.retrieveAbbreviations)(text.concat(attributes.join(" ")));
-  const removedSubheadingText = (0, _getSubheadings.removeSubheadingsTopLevel)(text);
-  const prominentWordsFromText = (0, _determineProminentWords.getProminentWords)(removedSubheadingText, abbreviations, stemmer, functionWords, getWordsCustomHelper);
-  const prominentWordsFromPaperAttributes = (0, _determineProminentWords.getProminentWordsFromPaperAttributes)(attributes, abbreviations, stemmer, functionWords, getWordsCustomHelper);
+  const abbreviations = getWordsCustomHelper ? [] : retrieveAbbreviations(text.concat(attributes.join(" ")));
+  const removedSubheadingText = removeSubheadingsTopLevel(text);
+  const prominentWordsFromText = getProminentWords(removedSubheadingText, abbreviations, stemmer, functionWords, getWordsCustomHelper);
+  const prominentWordsFromPaperAttributes = getProminentWordsFromPaperAttributes(attributes, abbreviations, stemmer, functionWords, getWordsCustomHelper);
 
   /*
    * If a word is used in any of the attributes, its weight is automatically high.
    * To make sure the word survives weight filters and gets saved in the database, make the number of occurrences times-3.
    */
   prominentWordsFromPaperAttributes.forEach(relevantWord => relevantWord.setOccurrences(relevantWord.getOccurrences() * 3));
-  const collapsedWords = (0, _determineProminentWords.collapseProminentWordsOnStem)(prominentWordsFromPaperAttributes.concat(prominentWordsFromText));
-  (0, _determineProminentWords.sortProminentWords)(collapsedWords);
+  const collapsedWords = collapseProminentWordsOnStem(prominentWordsFromPaperAttributes.concat(prominentWordsFromText));
+  sortProminentWords(collapsedWords);
 
   /*
    * If morphology data are available for a language, the minimum number of occurrences to consider a word to be prominent is 4.
@@ -88,7 +82,7 @@ function getProminentWordsForInternalLinking(paper, researcher) {
    * If morphology data are not available, and therefore word forms are not recognized, the minimum threshold is lowered to 2.
    */
   let minimumNumberOfOccurrences = 4;
-  if (stemmer === _baseStemmer.default) {
+  if (stemmer === baseStemmer) {
     minimumNumberOfOccurrences = 2;
   }
 
@@ -96,8 +90,8 @@ function getProminentWordsForInternalLinking(paper, researcher) {
    * Return the 100 top items from the collapsed and sorted list. The number is picked deliberately to prevent larger
    * articles from getting too long of lists.
    */
-  result.prominentWords = (0, _lodash.take)((0, _determineProminentWords.filterProminentWords)(collapsedWords, minimumNumberOfOccurrences), 100);
+  result.prominentWords = take(filterProminentWords(collapsedWords, minimumNumberOfOccurrences), 100);
   return result;
 }
-var _default = exports.default = getProminentWordsForInternalLinking;
+export default getProminentWordsForInternalLinking;
 //# sourceMappingURL=getProminentWordsForInternalLinking.js.map

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

@@ -1 +1 @@
-{"version":3,"file":"getProminentWordsForInternalLinking.js","names":["_lodash","require","_countWords","_interopRequireDefault","_determineProminentWords","_getSubheadings","_baseStemmer","_removeURLs","_removeEmailAddresses","e","__esModule","default","sanitizeText","text","removeURLs","removeEmailAddresses","getProminentWordsForInternalLinking","paper","researcher","functionWords","getConfig","customStemmer","getHelper","stemmer","getWordsCustomHelper","customCountLength","getText","metadescription","getDescription","title","getTitle","result","hasMetaDescription","hasTitle","prominentWords","countWords","subheadings","getSubheadingsTopLevel","map","subheading","attributes","getKeyword","getSynonyms","join","abbreviations","retrieveAbbreviations","concat","removedSubheadingText","removeSubheadingsTopLevel","prominentWordsFromText","getProminentWords","prominentWordsFromPaperAttributes","getProminentWordsFromPaperAttributes","forEach","relevantWord","setOccurrences","getOccurrences","collapsedWords","collapseProminentWordsOnStem","sortProminentWords","minimumNumberOfOccurrences","baseStemmer","take","filterProminentWords","_default","exports"],"sources":["../../../src/languageProcessing/researches/getProminentWordsForInternalLinking.js"],"sourcesContent":["import { take } from \"lodash\";\nimport countWords from \"../helpers/word/countWords\";\nimport {\n\tcollapseProminentWordsOnStem,\n\tfilterProminentWords,\n\tgetProminentWords,\n\tgetProminentWordsFromPaperAttributes,\n\tretrieveAbbreviations,\n\tsortProminentWords,\n} from \"../helpers/prominentWords/determineProminentWords\";\nimport { getSubheadingsTopLevel, removeSubheadingsTopLevel } from \"../helpers/html/getSubheadings\";\nimport baseStemmer from \"../helpers/morphology/baseStemmer\";\nimport removeURLs from \"../helpers/sanitize/removeURLs.js\";\nimport removeEmailAddresses from \"../helpers/sanitize/removeEmailAddresses\";\n\n/**\n * Removes URLs and email addresses from the text.\n *\n * @param {string}\ttext\tThe text to sanitize.\n *\n * @returns {string} The text without URLs and email addresses.\n */\nconst sanitizeText = function( text ) {\n\ttext = removeURLs( text );\n\treturn removeEmailAddresses( text );\n};\n\n/**\n * Retrieves the prominent words from the given paper.\n *\n * @param {Paper}       paper       The paper to determine the prominent words of.\n * @param {Researcher}  researcher  The researcher to use for analysis.\n *\n * @returns {Object}          result                    A compound result object.\n * @returns {ProminentWord[]} result.prominentWords     Prominent words for this paper, filtered and sorted.\n * @returns {boolean}         result.hasMetaDescription Whether the metadescription is available in the input paper.\n * @returns {boolean}         result.hasTitle           Whether the title is available in the input paper.\n */\nfunction getProminentWordsForInternalLinking( paper, researcher ) {\n\tconst functionWords = researcher.getConfig( \"functionWords\" );\n\t// An optional custom helper to return custom function to return the stem of a word.\n\tconst customStemmer = researcher.getHelper( \"customGetStemmer\" );\n\tconst stemmer = customStemmer ? customStemmer( researcher ) : researcher.getHelper( \"getStemmer\" )( researcher );\n\t// An optional custom helper to get words from the text.\n\tconst getWordsCustomHelper = researcher.getHelper( \"getWordsCustomHelper\" );\n\t// An optional custom helper to count length to use instead of countWords.\n\tconst customCountLength = researcher.getHelper( \"customCountLength\" );\n\n\tconst text = sanitizeText( paper.getText() );\n\tconst metadescription = sanitizeText( paper.getDescription() );\n\tconst title = sanitizeText( paper.getTitle() );\n\n\tconst result = {};\n\tresult.hasMetaDescription = metadescription !== \"\";\n\tresult.hasTitle = title !== \"\";\n\tresult.prominentWords = [];\n\n\t/**\n\t * We only want to return suggestions (and spend time calculating prominent words) if the text is at least 100 words.\n\t * And when a customCountLength is available, we only want to return the suggestions if the text has at least 200 characters.\n \t */\n\tif ( customCountLength ) {\n\t\tif ( customCountLength( text ) < 200 ) {\n\t\t\treturn result;\n\t\t}\n\t} else if ( countWords( text ) < 100 ) {\n\t\treturn result;\n\t}\n\n\tconst subheadings = getSubheadingsTopLevel( text ).map( subheading => subheading[ 2 ] );\n\tconst attributes = [\n\t\tpaper.getKeyword(),\n\t\tpaper.getSynonyms(),\n\t\ttitle,\n\t\tmetadescription,\n\t\tsubheadings.join( \" \" ),\n\t];\n\n\t// If the language has a custom helper to get words from the text, we don't retrieve the abbreviation.\n\tconst abbreviations = getWordsCustomHelper ? [] : retrieveAbbreviations( text.concat( attributes.join( \" \" ) ) );\n\n\tconst removedSubheadingText = removeSubheadingsTopLevel( text );\n\tconst prominentWordsFromText = getProminentWords( removedSubheadingText, abbreviations, stemmer, functionWords, getWordsCustomHelper );\n\n\tconst prominentWordsFromPaperAttributes = getProminentWordsFromPaperAttributes(\n\t\tattributes, abbreviations, stemmer, functionWords, getWordsCustomHelper );\n\n\t/*\n\t * If a word is used in any of the attributes, its weight is automatically high.\n\t * To make sure the word survives weight filters and gets saved in the database, make the number of occurrences times-3.\n\t */\n\tprominentWordsFromPaperAttributes.forEach( relevantWord => relevantWord.setOccurrences( relevantWord.getOccurrences() * 3 ) );\n\n\tconst collapsedWords = collapseProminentWordsOnStem( prominentWordsFromPaperAttributes.concat( prominentWordsFromText ) );\n\tsortProminentWords( collapsedWords );\n\n\t/*\n\t * If morphology data are available for a language, the minimum number of occurrences to consider a word to be prominent is 4.\n\t * This minimum number was chosen in order to avoid premature suggestions of words from the paper attributes.\n\t * These get a times-3 boost and would therefore be prominent with just 1 occurrence.\n\t *\n\t * If morphology data are not available, and therefore word forms are not recognized, the minimum threshold is lowered to 2.\n\t */\n\tlet minimumNumberOfOccurrences = 4;\n\n\tif ( stemmer === baseStemmer ) {\n\t\tminimumNumberOfOccurrences = 2;\n\t}\n\n\t/*\n\t * Return the 100 top items from the collapsed and sorted list. The number is picked deliberately to prevent larger\n\t * articles from getting too long of lists.\n\t */\n\tresult.prominentWords = take( filterProminentWords( collapsedWords, minimumNumberOfOccurrences ), 100 );\n\n\treturn result;\n}\n\nexport default getProminentWordsForInternalLinking;\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AACA,IAAAC,WAAA,GAAAC,sBAAA,CAAAF,OAAA;AACA,IAAAG,wBAAA,GAAAH,OAAA;AAQA,IAAAI,eAAA,GAAAJ,OAAA;AACA,IAAAK,YAAA,GAAAH,sBAAA,CAAAF,OAAA;AACA,IAAAM,WAAA,GAAAJ,sBAAA,CAAAF,OAAA;AACA,IAAAO,qBAAA,GAAAL,sBAAA,CAAAF,OAAA;AAA4E,SAAAE,uBAAAM,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAE5E;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,YAAY,GAAG,SAAAA,CAAUC,IAAI,EAAG;EACrCA,IAAI,GAAG,IAAAC,mBAAU,EAAED,IAAK,CAAC;EACzB,OAAO,IAAAE,6BAAoB,EAAEF,IAAK,CAAC;AACpC,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASG,mCAAmCA,CAAEC,KAAK,EAAEC,UAAU,EAAG;EACjE,MAAMC,aAAa,GAAGD,UAAU,CAACE,SAAS,CAAE,eAAgB,CAAC;EAC7D;EACA,MAAMC,aAAa,GAAGH,UAAU,CAACI,SAAS,CAAE,kBAAmB,CAAC;EAChE,MAAMC,OAAO,GAAGF,aAAa,GAAGA,aAAa,CAAEH,UAAW,CAAC,GAAGA,UAAU,CAACI,SAAS,CAAE,YAAa,CAAC,CAAEJ,UAAW,CAAC;EAChH;EACA,MAAMM,oBAAoB,GAAGN,UAAU,CAACI,SAAS,CAAE,sBAAuB,CAAC;EAC3E;EACA,MAAMG,iBAAiB,GAAGP,UAAU,CAACI,SAAS,CAAE,mBAAoB,CAAC;EAErE,MAAMT,IAAI,GAAGD,YAAY,CAAEK,KAAK,CAACS,OAAO,CAAC,CAAE,CAAC;EAC5C,MAAMC,eAAe,GAAGf,YAAY,CAAEK,KAAK,CAACW,cAAc,CAAC,CAAE,CAAC;EAC9D,MAAMC,KAAK,GAAGjB,YAAY,CAAEK,KAAK,CAACa,QAAQ,CAAC,CAAE,CAAC;EAE9C,MAAMC,MAAM,GAAG,CAAC,CAAC;EACjBA,MAAM,CAACC,kBAAkB,GAAGL,eAAe,KAAK,EAAE;EAClDI,MAAM,CAACE,QAAQ,GAAGJ,KAAK,KAAK,EAAE;EAC9BE,MAAM,CAACG,cAAc,GAAG,EAAE;;EAE1B;AACD;AACA;AACA;EACC,IAAKT,iBAAiB,EAAG;IACxB,IAAKA,iBAAiB,CAAEZ,IAAK,CAAC,GAAG,GAAG,EAAG;MACtC,OAAOkB,MAAM;IACd;EACD,CAAC,MAAM,IAAK,IAAAI,mBAAU,EAAEtB,IAAK,CAAC,GAAG,GAAG,EAAG;IACtC,OAAOkB,MAAM;EACd;EAEA,MAAMK,WAAW,GAAG,IAAAC,sCAAsB,EAAExB,IAAK,CAAC,CAACyB,GAAG,CAAEC,UAAU,IAAIA,UAAU,CAAE,CAAC,CAAG,CAAC;EACvF,MAAMC,UAAU,GAAG,CAClBvB,KAAK,CAACwB,UAAU,CAAC,CAAC,EAClBxB,KAAK,CAACyB,WAAW,CAAC,CAAC,EACnBb,KAAK,EACLF,eAAe,EACfS,WAAW,CAACO,IAAI,CAAE,GAAI,CAAC,CACvB;;EAED;EACA,MAAMC,aAAa,GAAGpB,oBAAoB,GAAG,EAAE,GAAG,IAAAqB,8CAAqB,EAAEhC,IAAI,CAACiC,MAAM,CAAEN,UAAU,CAACG,IAAI,CAAE,GAAI,CAAE,CAAE,CAAC;EAEhH,MAAMI,qBAAqB,GAAG,IAAAC,yCAAyB,EAAEnC,IAAK,CAAC;EAC/D,MAAMoC,sBAAsB,GAAG,IAAAC,0CAAiB,EAAEH,qBAAqB,EAAEH,aAAa,EAAErB,OAAO,EAAEJ,aAAa,EAAEK,oBAAqB,CAAC;EAEtI,MAAM2B,iCAAiC,GAAG,IAAAC,6DAAoC,EAC7EZ,UAAU,EAAEI,aAAa,EAAErB,OAAO,EAAEJ,aAAa,EAAEK,oBAAqB,CAAC;;EAE1E;AACD;AACA;AACA;EACC2B,iCAAiC,CAACE,OAAO,CAAEC,YAAY,IAAIA,YAAY,CAACC,cAAc,CAAED,YAAY,CAACE,cAAc,CAAC,CAAC,GAAG,CAAE,CAAE,CAAC;EAE7H,MAAMC,cAAc,GAAG,IAAAC,qDAA4B,EAAEP,iCAAiC,CAACL,MAAM,CAAEG,sBAAuB,CAAE,CAAC;EACzH,IAAAU,2CAAkB,EAAEF,cAAe,CAAC;;EAEpC;AACD;AACA;AACA;AACA;AACA;AACA;EACC,IAAIG,0BAA0B,GAAG,CAAC;EAElC,IAAKrC,OAAO,KAAKsC,oBAAW,EAAG;IAC9BD,0BAA0B,GAAG,CAAC;EAC/B;;EAEA;AACD;AACA;AACA;EACC7B,MAAM,CAACG,cAAc,GAAG,IAAA4B,YAAI,EAAE,IAAAC,6CAAoB,EAAEN,cAAc,EAAEG,0BAA2B,CAAC,EAAE,GAAI,CAAC;EAEvG,OAAO7B,MAAM;AACd;AAAC,IAAAiC,QAAA,GAAAC,OAAA,CAAAtD,OAAA,GAEcK,mCAAmC","ignoreList":[]}
+{"version":3,"file":"getProminentWordsForInternalLinking.js","names":["take","countWords","collapseProminentWordsOnStem","filterProminentWords","getProminentWords","getProminentWordsFromPaperAttributes","retrieveAbbreviations","sortProminentWords","getSubheadingsTopLevel","removeSubheadingsTopLevel","baseStemmer","removeURLs","removeEmailAddresses","sanitizeText","text","getProminentWordsForInternalLinking","paper","researcher","functionWords","getConfig","customStemmer","getHelper","stemmer","getWordsCustomHelper","customCountLength","getText","metadescription","getDescription","title","getTitle","result","hasMetaDescription","hasTitle","prominentWords","subheadings","map","subheading","attributes","getKeyword","getSynonyms","join","abbreviations","concat","removedSubheadingText","prominentWordsFromText","prominentWordsFromPaperAttributes","forEach","relevantWord","setOccurrences","getOccurrences","collapsedWords","minimumNumberOfOccurrences"],"sources":["../../../src/languageProcessing/researches/getProminentWordsForInternalLinking.js"],"sourcesContent":["import { take } from \"lodash\";\nimport countWords from \"../helpers/word/countWords\";\nimport {\n\tcollapseProminentWordsOnStem,\n\tfilterProminentWords,\n\tgetProminentWords,\n\tgetProminentWordsFromPaperAttributes,\n\tretrieveAbbreviations,\n\tsortProminentWords,\n} from \"../helpers/prominentWords/determineProminentWords\";\nimport { getSubheadingsTopLevel, removeSubheadingsTopLevel } from \"../helpers/html/getSubheadings\";\nimport baseStemmer from \"../helpers/morphology/baseStemmer\";\nimport removeURLs from \"../helpers/sanitize/removeURLs.js\";\nimport removeEmailAddresses from \"../helpers/sanitize/removeEmailAddresses\";\n\n/**\n * Removes URLs and email addresses from the text.\n *\n * @param {string}\ttext\tThe text to sanitize.\n *\n * @returns {string} The text without URLs and email addresses.\n */\nconst sanitizeText = function( text ) {\n\ttext = removeURLs( text );\n\treturn removeEmailAddresses( text );\n};\n\n/**\n * Retrieves the prominent words from the given paper.\n *\n * @param {Paper}       paper       The paper to determine the prominent words of.\n * @param {Researcher}  researcher  The researcher to use for analysis.\n *\n * @returns {Object}          result                    A compound result object.\n * @returns {ProminentWord[]} result.prominentWords     Prominent words for this paper, filtered and sorted.\n * @returns {boolean}         result.hasMetaDescription Whether the metadescription is available in the input paper.\n * @returns {boolean}         result.hasTitle           Whether the title is available in the input paper.\n */\nfunction getProminentWordsForInternalLinking( paper, researcher ) {\n\tconst functionWords = researcher.getConfig( \"functionWords\" );\n\t// An optional custom helper to return custom function to return the stem of a word.\n\tconst customStemmer = researcher.getHelper( \"customGetStemmer\" );\n\tconst stemmer = customStemmer ? customStemmer( researcher ) : researcher.getHelper( \"getStemmer\" )( researcher );\n\t// An optional custom helper to get words from the text.\n\tconst getWordsCustomHelper = researcher.getHelper( \"getWordsCustomHelper\" );\n\t// An optional custom helper to count length to use instead of countWords.\n\tconst customCountLength = researcher.getHelper( \"customCountLength\" );\n\n\tconst text = sanitizeText( paper.getText() );\n\tconst metadescription = sanitizeText( paper.getDescription() );\n\tconst title = sanitizeText( paper.getTitle() );\n\n\tconst result = {};\n\tresult.hasMetaDescription = metadescription !== \"\";\n\tresult.hasTitle = title !== \"\";\n\tresult.prominentWords = [];\n\n\t/**\n\t * We only want to return suggestions (and spend time calculating prominent words) if the text is at least 100 words.\n\t * And when a customCountLength is available, we only want to return the suggestions if the text has at least 200 characters.\n \t */\n\tif ( customCountLength ) {\n\t\tif ( customCountLength( text ) < 200 ) {\n\t\t\treturn result;\n\t\t}\n\t} else if ( countWords( text ) < 100 ) {\n\t\treturn result;\n\t}\n\n\tconst subheadings = getSubheadingsTopLevel( text ).map( subheading => subheading[ 2 ] );\n\tconst attributes = [\n\t\tpaper.getKeyword(),\n\t\tpaper.getSynonyms(),\n\t\ttitle,\n\t\tmetadescription,\n\t\tsubheadings.join( \" \" ),\n\t];\n\n\t// If the language has a custom helper to get words from the text, we don't retrieve the abbreviation.\n\tconst abbreviations = getWordsCustomHelper ? [] : retrieveAbbreviations( text.concat( attributes.join( \" \" ) ) );\n\n\tconst removedSubheadingText = removeSubheadingsTopLevel( text );\n\tconst prominentWordsFromText = getProminentWords( removedSubheadingText, abbreviations, stemmer, functionWords, getWordsCustomHelper );\n\n\tconst prominentWordsFromPaperAttributes = getProminentWordsFromPaperAttributes(\n\t\tattributes, abbreviations, stemmer, functionWords, getWordsCustomHelper );\n\n\t/*\n\t * If a word is used in any of the attributes, its weight is automatically high.\n\t * To make sure the word survives weight filters and gets saved in the database, make the number of occurrences times-3.\n\t */\n\tprominentWordsFromPaperAttributes.forEach( relevantWord => relevantWord.setOccurrences( relevantWord.getOccurrences() * 3 ) );\n\n\tconst collapsedWords = collapseProminentWordsOnStem( prominentWordsFromPaperAttributes.concat( prominentWordsFromText ) );\n\tsortProminentWords( collapsedWords );\n\n\t/*\n\t * If morphology data are available for a language, the minimum number of occurrences to consider a word to be prominent is 4.\n\t * This minimum number was chosen in order to avoid premature suggestions of words from the paper attributes.\n\t * These get a times-3 boost and would therefore be prominent with just 1 occurrence.\n\t *\n\t * If morphology data are not available, and therefore word forms are not recognized, the minimum threshold is lowered to 2.\n\t */\n\tlet minimumNumberOfOccurrences = 4;\n\n\tif ( stemmer === baseStemmer ) {\n\t\tminimumNumberOfOccurrences = 2;\n\t}\n\n\t/*\n\t * Return the 100 top items from the collapsed and sorted list. The number is picked deliberately to prevent larger\n\t * articles from getting too long of lists.\n\t */\n\tresult.prominentWords = take( filterProminentWords( collapsedWords, minimumNumberOfOccurrences ), 100 );\n\n\treturn result;\n}\n\nexport default getProminentWordsForInternalLinking;\n"],"mappings":"AAAA,SAASA,IAAI,QAAQ,QAAQ;AAC7B,OAAOC,UAAU;AACjB,SACCC,4BAA4B,EAC5BC,oBAAoB,EACpBC,iBAAiB,EACjBC,oCAAoC,EACpCC,qBAAqB,EACrBC,kBAAkB;AAEnB,SAASC,sBAAsB,EAAEC,yBAAyB;AAC1D,OAAOC,WAAW;AAClB,OAAOC,UAAU;AACjB,OAAOC,oBAAoB;;AAE3B;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,YAAY,GAAG,SAAAA,CAAUC,IAAI,EAAG;EACrCA,IAAI,GAAGH,UAAU,CAAEG,IAAK,CAAC;EACzB,OAAOF,oBAAoB,CAAEE,IAAK,CAAC;AACpC,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,mCAAmCA,CAAEC,KAAK,EAAEC,UAAU,EAAG;EACjE,MAAMC,aAAa,GAAGD,UAAU,CAACE,SAAS,CAAE,eAAgB,CAAC;EAC7D;EACA,MAAMC,aAAa,GAAGH,UAAU,CAACI,SAAS,CAAE,kBAAmB,CAAC;EAChE,MAAMC,OAAO,GAAGF,aAAa,GAAGA,aAAa,CAAEH,UAAW,CAAC,GAAGA,UAAU,CAACI,SAAS,CAAE,YAAa,CAAC,CAAEJ,UAAW,CAAC;EAChH;EACA,MAAMM,oBAAoB,GAAGN,UAAU,CAACI,SAAS,CAAE,sBAAuB,CAAC;EAC3E;EACA,MAAMG,iBAAiB,GAAGP,UAAU,CAACI,SAAS,CAAE,mBAAoB,CAAC;EAErE,MAAMP,IAAI,GAAGD,YAAY,CAAEG,KAAK,CAACS,OAAO,CAAC,CAAE,CAAC;EAC5C,MAAMC,eAAe,GAAGb,YAAY,CAAEG,KAAK,CAACW,cAAc,CAAC,CAAE,CAAC;EAC9D,MAAMC,KAAK,GAAGf,YAAY,CAAEG,KAAK,CAACa,QAAQ,CAAC,CAAE,CAAC;EAE9C,MAAMC,MAAM,GAAG,CAAC,CAAC;EACjBA,MAAM,CAACC,kBAAkB,GAAGL,eAAe,KAAK,EAAE;EAClDI,MAAM,CAACE,QAAQ,GAAGJ,KAAK,KAAK,EAAE;EAC9BE,MAAM,CAACG,cAAc,GAAG,EAAE;;EAE1B;AACD;AACA;AACA;EACC,IAAKT,iBAAiB,EAAG;IACxB,IAAKA,iBAAiB,CAAEV,IAAK,CAAC,GAAG,GAAG,EAAG;MACtC,OAAOgB,MAAM;IACd;EACD,CAAC,MAAM,IAAK7B,UAAU,CAAEa,IAAK,CAAC,GAAG,GAAG,EAAG;IACtC,OAAOgB,MAAM;EACd;EAEA,MAAMI,WAAW,GAAG1B,sBAAsB,CAAEM,IAAK,CAAC,CAACqB,GAAG,CAAEC,UAAU,IAAIA,UAAU,CAAE,CAAC,CAAG,CAAC;EACvF,MAAMC,UAAU,GAAG,CAClBrB,KAAK,CAACsB,UAAU,CAAC,CAAC,EAClBtB,KAAK,CAACuB,WAAW,CAAC,CAAC,EACnBX,KAAK,EACLF,eAAe,EACfQ,WAAW,CAACM,IAAI,CAAE,GAAI,CAAC,CACvB;;EAED;EACA,MAAMC,aAAa,GAAGlB,oBAAoB,GAAG,EAAE,GAAGjB,qBAAqB,CAAEQ,IAAI,CAAC4B,MAAM,CAAEL,UAAU,CAACG,IAAI,CAAE,GAAI,CAAE,CAAE,CAAC;EAEhH,MAAMG,qBAAqB,GAAGlC,yBAAyB,CAAEK,IAAK,CAAC;EAC/D,MAAM8B,sBAAsB,GAAGxC,iBAAiB,CAAEuC,qBAAqB,EAAEF,aAAa,EAAEnB,OAAO,EAAEJ,aAAa,EAAEK,oBAAqB,CAAC;EAEtI,MAAMsB,iCAAiC,GAAGxC,oCAAoC,CAC7EgC,UAAU,EAAEI,aAAa,EAAEnB,OAAO,EAAEJ,aAAa,EAAEK,oBAAqB,CAAC;;EAE1E;AACD;AACA;AACA;EACCsB,iCAAiC,CAACC,OAAO,CAAEC,YAAY,IAAIA,YAAY,CAACC,cAAc,CAAED,YAAY,CAACE,cAAc,CAAC,CAAC,GAAG,CAAE,CAAE,CAAC;EAE7H,MAAMC,cAAc,GAAGhD,4BAA4B,CAAE2C,iCAAiC,CAACH,MAAM,CAAEE,sBAAuB,CAAE,CAAC;EACzHrC,kBAAkB,CAAE2C,cAAe,CAAC;;EAEpC;AACD;AACA;AACA;AACA;AACA;AACA;EACC,IAAIC,0BAA0B,GAAG,CAAC;EAElC,IAAK7B,OAAO,KAAKZ,WAAW,EAAG;IAC9ByC,0BAA0B,GAAG,CAAC;EAC/B;;EAEA;AACD;AACA;AACA;EACCrB,MAAM,CAACG,cAAc,GAAGjC,IAAI,CAAEG,oBAAoB,CAAE+C,cAAc,EAAEC,0BAA2B,CAAC,EAAE,GAAI,CAAC;EAEvG,OAAOrB,MAAM;AACd;AAEA,eAAef,mCAAmC","ignoreList":[]}