axyseo 2.0.0-alpha.0.0.2 → 2.0.0-alpha.0.0.21

package/build/parsedPaper/assess/cornerstone/assessmentListFactories.js

@@ -0,0 +1,51 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.constructSEOAssessments = exports.constructRelatedKeyphraseAssessments = exports.constructReadabilityAssessments = void 0;
+/**
+ * Factory functions for creating lists of assessments for cornerstone content.
+ *
+ * To be used in creating the different kinds of assessors.
+ */
+
+/**
+ * Creates a new list of SEO assessments.
+ *
+ * @returns {module:parsedPaper/assess.Assessment[]} The list of SEO assessments.
+ *
+ * @private
+ * @memberOf module:parsedPaper/assess
+ */
+const constructSEOAssessments = () => [
+  // Needs to be populated by fancy new assessments that work on the tree representation of the text.
+];
+
+/**
+ * Creates a new list of readability assessments.
+ *
+ * @returns {module:parsedPaper/assess.Assessment[]} The list of readability assessments.
+ *
+ * @private
+ * @memberOf module:parsedPaper/assess
+ */
+exports.constructSEOAssessments = constructSEOAssessments;
+const constructReadabilityAssessments = () => [
+  // Needs to be populated by fancy new assessments that work on the tree representation of the text.
+];
+
+/**
+ * Creates a new list of SEO assessments for related keyphrases.
+ *
+ * @returns {module:parsedPaper/assess.Assessment[]} The list of SEO assessments.
+ *
+ * @private
+ * @memberOf module:parsedPaper/assess
+ */
+exports.constructReadabilityAssessments = constructReadabilityAssessments;
+const constructRelatedKeyphraseAssessments = () => [
+  // Needs to be populated by fancy new assessments that work on the tree representation of the text.
+];
+exports.constructRelatedKeyphraseAssessments = constructRelatedKeyphraseAssessments;
+//# sourceMappingURL=assessmentListFactories.js.map

package/build/parsedPaper/assess/cornerstone/assessmentListFactories.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"assessmentListFactories.js","names":["constructSEOAssessments","exports","constructReadabilityAssessments","constructRelatedKeyphraseAssessments"],"sources":["../../../../src/parsedPaper/assess/cornerstone/assessmentListFactories.js"],"sourcesContent":["/**\n * Factory functions for creating lists of assessments for cornerstone content.\n *\n * To be used in creating the different kinds of assessors.\n */\n\n/**\n * Creates a new list of SEO assessments.\n *\n * @returns {module:parsedPaper/assess.Assessment[]} The list of SEO assessments.\n *\n * @private\n * @memberOf module:parsedPaper/assess\n */\nconst constructSEOAssessments = () => [\n\t// Needs to be populated by fancy new assessments that work on the tree representation of the text.\n];\n\n/**\n * Creates a new list of readability assessments.\n *\n * @returns {module:parsedPaper/assess.Assessment[]} The list of readability assessments.\n *\n * @private\n * @memberOf module:parsedPaper/assess\n */\nconst constructReadabilityAssessments = () => [\n\t// Needs to be populated by fancy new assessments that work on the tree representation of the text.\n];\n\n/**\n * Creates a new list of SEO assessments for related keyphrases.\n *\n * @returns {module:parsedPaper/assess.Assessment[]} The list of SEO assessments.\n *\n * @private\n * @memberOf module:parsedPaper/assess\n */\nconst constructRelatedKeyphraseAssessments = () => [\n\t// Needs to be populated by fancy new assessments that work on the tree representation of the text.\n];\n\nexport {\n\tconstructSEOAssessments,\n\tconstructReadabilityAssessments,\n\tconstructRelatedKeyphraseAssessments,\n};\n"],"mappings":";;;;;;AAAA;AACA;AACA;AACA;AACA;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMA,uBAAuB,GAAGA,CAAA,KAAM;EACrC;AAAA,CACA;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AAPAC,OAAA,CAAAD,uBAAA,GAAAA,uBAAA;AAQA,MAAME,+BAA+B,GAAGA,CAAA,KAAM;EAC7C;AAAA,CACA;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AAPAD,OAAA,CAAAC,+BAAA,GAAAA,+BAAA;AAQA,MAAMC,oCAAoC,GAAGA,CAAA,KAAM;EAClD;AAAA,CACA;AAACF,OAAA,CAAAE,oCAAA,GAAAA,oCAAA","ignoreList":[]}

package/build/parsedPaper/assess/cornerstone/index.js

@@ -0,0 +1,11 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.cornerstoneAssessmentListFactories = void 0;
+var cornerstoneAssessmentListFactories = _interopRequireWildcard(require("./assessmentListFactories"));
+exports.cornerstoneAssessmentListFactories = cornerstoneAssessmentListFactories;
+function _getRequireWildcardCache(e) { if ("function" != typeof WeakMap) return null; var r = new WeakMap(), t = new WeakMap(); return (_getRequireWildcardCache = function (e) { return e ? t : r; })(e); }
+function _interopRequireWildcard(e, r) { if (!r && e && e.__esModule) return e; if (null === e || "object" != typeof e && "function" != typeof e) return { default: e }; var t = _getRequireWildcardCache(r); if (t && t.has(e)) return t.get(e); var n = { __proto__: null }, a = Object.defineProperty && Object.getOwnPropertyDescriptor; for (var u in e) if ("default" !== u && {}.hasOwnProperty.call(e, u)) { var i = a ? Object.getOwnPropertyDescriptor(e, u) : null; i && (i.get || i.set) ? Object.defineProperty(n, u, i) : n[u] = e[u]; } return n.default = e, t && t.set(e, n), n; }
+//# sourceMappingURL=index.js.map

package/build/parsedPaper/assess/cornerstone/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","names":["cornerstoneAssessmentListFactories","_interopRequireWildcard","require","exports","_getRequireWildcardCache","e","WeakMap","r","t","__esModule","default","has","get","n","__proto__","a","Object","defineProperty","getOwnPropertyDescriptor","u","hasOwnProperty","call","i","set"],"sources":["../../../../src/parsedPaper/assess/cornerstone/index.js"],"sourcesContent":["import * as cornerstoneAssessmentListFactories from \"./assessmentListFactories\";\n\nexport {\n\tcornerstoneAssessmentListFactories,\n};\n"],"mappings":";;;;;;AAAA,IAAAA,kCAAA,GAAAC,uBAAA,CAAAC,OAAA;AAAgFC,OAAA,CAAAH,kCAAA,GAAAA,kCAAA;AAAA,SAAAI,yBAAAC,CAAA,6BAAAC,OAAA,mBAAAC,CAAA,OAAAD,OAAA,IAAAE,CAAA,OAAAF,OAAA,YAAAF,wBAAA,YAAAA,CAAAC,CAAA,WAAAA,CAAA,GAAAG,CAAA,GAAAD,CAAA,KAAAF,CAAA;AAAA,SAAAJ,wBAAAI,CAAA,EAAAE,CAAA,SAAAA,CAAA,IAAAF,CAAA,IAAAA,CAAA,CAAAI,UAAA,SAAAJ,CAAA,eAAAA,CAAA,uBAAAA,CAAA,yBAAAA,CAAA,WAAAK,OAAA,EAAAL,CAAA,QAAAG,CAAA,GAAAJ,wBAAA,CAAAG,CAAA,OAAAC,CAAA,IAAAA,CAAA,CAAAG,GAAA,CAAAN,CAAA,UAAAG,CAAA,CAAAI,GAAA,CAAAP,CAAA,OAAAQ,CAAA,KAAAC,SAAA,UAAAC,CAAA,GAAAC,MAAA,CAAAC,cAAA,IAAAD,MAAA,CAAAE,wBAAA,WAAAC,CAAA,IAAAd,CAAA,oBAAAc,CAAA,OAAAC,cAAA,CAAAC,IAAA,CAAAhB,CAAA,EAAAc,CAAA,SAAAG,CAAA,GAAAP,CAAA,GAAAC,MAAA,CAAAE,wBAAA,CAAAb,CAAA,EAAAc,CAAA,UAAAG,CAAA,KAAAA,CAAA,CAAAV,GAAA,IAAAU,CAAA,CAAAC,GAAA,IAAAP,MAAA,CAAAC,cAAA,CAAAJ,CAAA,EAAAM,CAAA,EAAAG,CAAA,IAAAT,CAAA,CAAAM,CAAA,IAAAd,CAAA,CAAAc,CAAA,YAAAN,CAAA,CAAAH,OAAA,GAAAL,CAAA,EAAAG,CAAA,IAAAA,CAAA,CAAAe,GAAA,CAAAlB,CAAA,EAAAQ,CAAA,GAAAA,CAAA","ignoreList":[]}

package/build/parsedPaper/assess/index.js

@@ -0,0 +1,31 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.ScoreAggregators = exports.Assessments = void 0;
+Object.defineProperty(exports, "TreeAssessor", {
+  enumerable: true,
+  get: function () {
+    return _TreeAssessor.default;
+  }
+});
+exports.assessorFactories = void 0;
+Object.defineProperty(exports, "cornerstoneAssessmentListFactories", {
+  enumerable: true,
+  get: function () {
+    return _cornerstone.cornerstoneAssessmentListFactories;
+  }
+});
+var _TreeAssessor = _interopRequireDefault(require("./TreeAssessor"));
+var ScoreAggregators = _interopRequireWildcard(require("../../scoring/scoreAggregators"));
+exports.ScoreAggregators = ScoreAggregators;
+var Assessments = _interopRequireWildcard(require("./assessments"));
+exports.Assessments = Assessments;
+var assessorFactories = _interopRequireWildcard(require("./assessorFactories"));
+exports.assessorFactories = assessorFactories;
+var _cornerstone = require("./cornerstone");
+function _getRequireWildcardCache(e) { if ("function" != typeof WeakMap) return null; var r = new WeakMap(), t = new WeakMap(); return (_getRequireWildcardCache = function (e) { return e ? t : r; })(e); }
+function _interopRequireWildcard(e, r) { if (!r && e && e.__esModule) return e; if (null === e || "object" != typeof e && "function" != typeof e) return { default: e }; var t = _getRequireWildcardCache(r); if (t && t.has(e)) return t.get(e); var n = { __proto__: null }, a = Object.defineProperty && Object.getOwnPropertyDescriptor; for (var u in e) if ("default" !== u && {}.hasOwnProperty.call(e, u)) { var i = a ? Object.getOwnPropertyDescriptor(e, u) : null; i && (i.get || i.set) ? Object.defineProperty(n, u, i) : n[u] = e[u]; } return n.default = e, t && t.set(e, n), n; }
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+//# sourceMappingURL=index.js.map

package/build/parsedPaper/assess/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","names":["_TreeAssessor","_interopRequireDefault","require","ScoreAggregators","_interopRequireWildcard","exports","Assessments","assessorFactories","_cornerstone","_getRequireWildcardCache","e","WeakMap","r","t","__esModule","default","has","get","n","__proto__","a","Object","defineProperty","getOwnPropertyDescriptor","u","hasOwnProperty","call","i","set"],"sources":["../../../src/parsedPaper/assess/index.js"],"sourcesContent":["import TreeAssessor from \"./TreeAssessor\";\nimport * as ScoreAggregators from \"../../scoring/scoreAggregators\";\nimport * as Assessments from \"./assessments\";\nimport * as assessorFactories from \"./assessorFactories\";\nimport { cornerstoneAssessmentListFactories } from \"./cornerstone\";\n\n/**\n * Contains the logic to assess a tree representation of a text.\n *\n * @module tree/assess\n *\n * @see module:parsedPaper/structure\n */\nexport {\n\tTreeAssessor,\n\tScoreAggregators,\n\tAssessments,\n\tassessorFactories,\n\tcornerstoneAssessmentListFactories,\n};\n"],"mappings":";;;;;;;;;;;;;;;;;;;AAAA,IAAAA,aAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,gBAAA,GAAAC,uBAAA,CAAAF,OAAA;AAAmEG,OAAA,CAAAF,gBAAA,GAAAA,gBAAA;AACnE,IAAAG,WAAA,GAAAF,uBAAA,CAAAF,OAAA;AAA6CG,OAAA,CAAAC,WAAA,GAAAA,WAAA;AAC7C,IAAAC,iBAAA,GAAAH,uBAAA,CAAAF,OAAA;AAAyDG,OAAA,CAAAE,iBAAA,GAAAA,iBAAA;AACzD,IAAAC,YAAA,GAAAN,OAAA;AAAmE,SAAAO,yBAAAC,CAAA,6BAAAC,OAAA,mBAAAC,CAAA,OAAAD,OAAA,IAAAE,CAAA,OAAAF,OAAA,YAAAF,wBAAA,YAAAA,CAAAC,CAAA,WAAAA,CAAA,GAAAG,CAAA,GAAAD,CAAA,KAAAF,CAAA;AAAA,SAAAN,wBAAAM,CAAA,EAAAE,CAAA,SAAAA,CAAA,IAAAF,CAAA,IAAAA,CAAA,CAAAI,UAAA,SAAAJ,CAAA,eAAAA,CAAA,uBAAAA,CAAA,yBAAAA,CAAA,WAAAK,OAAA,EAAAL,CAAA,QAAAG,CAAA,GAAAJ,wBAAA,CAAAG,CAAA,OAAAC,CAAA,IAAAA,CAAA,CAAAG,GAAA,CAAAN,CAAA,UAAAG,CAAA,CAAAI,GAAA,CAAAP,CAAA,OAAAQ,CAAA,KAAAC,SAAA,UAAAC,CAAA,GAAAC,MAAA,CAAAC,cAAA,IAAAD,MAAA,CAAAE,wBAAA,WAAAC,CAAA,IAAAd,CAAA,oBAAAc,CAAA,OAAAC,cAAA,CAAAC,IAAA,CAAAhB,CAAA,EAAAc,CAAA,SAAAG,CAAA,GAAAP,CAAA,GAAAC,MAAA,CAAAE,wBAAA,CAAAb,CAAA,EAAAc,CAAA,UAAAG,CAAA,KAAAA,CAAA,CAAAV,GAAA,IAAAU,CAAA,CAAAC,GAAA,IAAAP,MAAA,CAAAC,cAAA,CAAAJ,CAAA,EAAAM,CAAA,EAAAG,CAAA,IAAAT,CAAA,CAAAM,CAAA,IAAAd,CAAA,CAAAc,CAAA,YAAAN,CAAA,CAAAH,OAAA,GAAAL,CAAA,EAAAG,CAAA,IAAAA,CAAA,CAAAe,GAAA,CAAAlB,CAAA,EAAAQ,CAAA,GAAAA,CAAA;AAAA,SAAAjB,uBAAAS,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAI,UAAA,GAAAJ,CAAA,KAAAK,OAAA,EAAAL,CAAA","ignoreList":[]}

package/build/parsedPaper/build/PaperParser.js

@@ -0,0 +1,103 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _ParsedPaper = _interopRequireDefault(require("../ParsedPaper"));
+var _lodash = require("lodash");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * A class responsible for pre-processing the Paper, returning a ParsedPaper.
+ *
+ * @module parsedPaper
+ *
+ * @see module:parsedPaper/builder
+ * @see module:parsedPaper/structure
+ */
+class PaperParser {
+  /**
+   * Constructs a PaperParser class.
+   *
+   * @param {Function} treeBuilder A function that receives text and returns a tree.
+   *
+   * @constructor
+   */
+  constructor(treeBuilder) {
+    this._parsedPaper = new _ParsedPaper.default();
+    this._treeBuilder = treeBuilder;
+    this._metaDataModifiers = {};
+  }
+
+  /**
+   * Processes a Paper resulting in a ParsedPaper.
+   *
+   * @param {Paper} paper The Paper to parse.
+   *
+   * @returns {ParsedPaper} A parsedPaper instance.
+   */
+  parse(paper) {
+    // Build tree and set it to the ParsedPaper.
+    this._parsedPaper.setTree(this._treeBuilder(paper.getText()));
+
+    // Build metaData and set it to the ParsedPaper.
+    this._parsedPaper.setMetaData(this.constructMetaData(paper));
+    return this._parsedPaper;
+  }
+
+  /**
+   * Constructs the metaData from the Paper.
+   *
+   * @param {Paper} paper The paper to construct the metaData from.
+   *
+   * @returns {Object} The metaData.
+   */
+  constructMetaData(paper) {
+    let metaData = {};
+
+    // Map things to metaData.
+
+    // Run additional modifiers;
+    metaData = Object.assign({}, this.runMetaDataModifiers(metaData, paper));
+    return metaData;
+  }
+
+  /**
+   * Sets a metaData modifying function behind a function name on the internal metaDataModifiers object.
+   *
+   * @param {string}   modifierName       The name of the to be registered function.
+   * @param {Function} modifierFunction   The function that modifies the metaData. Should accept a metaData object
+   * 									    and optionally the paper.
+   * @returns {void}
+   */
+  registerMetaDataModifier(modifierName, modifierFunction) {
+    /*
+     * The metaDataModifier should accept the metaData and return the altered metaData.
+     */
+    this._metaDataModifiers[modifierName] = modifierFunction;
+  }
+
+  /**
+   * Runs all registered metaDataModifiers.
+   * If one of the functions errors, it is skipped and its metaData changes are discarded.
+   *
+   * @param {Object} metaData The initial state of the metaData, that should be modified.
+   * @param {Paper}  paper    The paper.
+   *
+   * @returns {Object} A modified metaData object.
+   */
+  runMetaDataModifiers(metaData, paper) {
+    let modifiedMetaData = metaData;
+    (0, _lodash.forEach)(this._metaDataModifiers, (modifierFunction, modifierName) => {
+      try {
+        const previousMetaData = Object.assign({}, modifiedMetaData);
+        modifiedMetaData = modifierFunction(previousMetaData, paper);
+      } catch (modifierError) {
+        console.warn(`An error with message "${modifierError.message}" occurred in metaData modifier ` + `function called ${modifierName}. Skipping that function...`);
+      }
+    });
+    return modifiedMetaData;
+  }
+}
+var _default = exports.default = PaperParser;
+//# sourceMappingURL=PaperParser.js.map

package/build/parsedPaper/build/PaperParser.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"PaperParser.js","names":["_ParsedPaper","_interopRequireDefault","require","_lodash","e","__esModule","default","PaperParser","constructor","treeBuilder","_parsedPaper","ParsedPaper","_treeBuilder","_metaDataModifiers","parse","paper","setTree","getText","setMetaData","constructMetaData","metaData","Object","assign","runMetaDataModifiers","registerMetaDataModifier","modifierName","modifierFunction","modifiedMetaData","forEach","previousMetaData","modifierError","console","warn","message","_default","exports"],"sources":["../../../src/parsedPaper/build/PaperParser.js"],"sourcesContent":["import ParsedPaper from \"../ParsedPaper\";\nimport { forEach } from \"lodash\";\n\n/**\n * A class responsible for pre-processing the Paper, returning a ParsedPaper.\n *\n * @module parsedPaper\n *\n * @see module:parsedPaper/builder\n * @see module:parsedPaper/structure\n */\nclass PaperParser {\n\t/**\n\t * Constructs a PaperParser class.\n\t *\n\t * @param {Function} treeBuilder A function that receives text and returns a tree.\n\t *\n\t * @constructor\n\t */\n\tconstructor( treeBuilder ) {\n\t\tthis._parsedPaper = new ParsedPaper();\n\t\tthis._treeBuilder = treeBuilder;\n\n\t\tthis._metaDataModifiers = {};\n\t}\n\n\t/**\n\t * Processes a Paper resulting in a ParsedPaper.\n\t *\n\t * @param {Paper} paper The Paper to parse.\n\t *\n\t * @returns {ParsedPaper} A parsedPaper instance.\n\t */\n\tparse( paper ) {\n\t\t// Build tree and set it to the ParsedPaper.\n\t\tthis._parsedPaper.setTree(\n\t\t\tthis._treeBuilder( paper.getText() )\n\t\t);\n\n\t\t// Build metaData and set it to the ParsedPaper.\n\t\tthis._parsedPaper.setMetaData(\n\t\t\tthis.constructMetaData( paper )\n\t\t);\n\n\t\treturn this._parsedPaper;\n\t}\n\n\t/**\n\t * Constructs the metaData from the Paper.\n\t *\n\t * @param {Paper} paper The paper to construct the metaData from.\n\t *\n\t * @returns {Object} The metaData.\n\t */\n\tconstructMetaData( paper ) {\n\t\tlet metaData = {};\n\n\t\t// Map things to metaData.\n\n\t\t// Run additional modifiers;\n\t\tmetaData = Object.assign( {}, this.runMetaDataModifiers( metaData, paper ) );\n\n\t\treturn metaData;\n\t}\n\n\t/**\n\t * Sets a metaData modifying function behind a function name on the internal metaDataModifiers object.\n\t *\n\t * @param {string}   modifierName       The name of the to be registered function.\n\t * @param {Function} modifierFunction   The function that modifies the metaData. Should accept a metaData object\n\t * \t\t\t\t\t\t\t\t\t    and optionally the paper.\n\t * @returns {void}\n\t */\n\tregisterMetaDataModifier( modifierName, modifierFunction ) {\n\t\t/*\n\t\t * The metaDataModifier should accept the metaData and return the altered metaData.\n\t\t */\n\t\tthis._metaDataModifiers[ modifierName ] = modifierFunction;\n\t}\n\n\t/**\n\t * Runs all registered metaDataModifiers.\n\t * If one of the functions errors, it is skipped and its metaData changes are discarded.\n\t *\n\t * @param {Object} metaData The initial state of the metaData, that should be modified.\n\t * @param {Paper}  paper    The paper.\n\t *\n\t * @returns {Object} A modified metaData object.\n\t */\n\trunMetaDataModifiers( metaData, paper ) {\n\t\tlet modifiedMetaData = metaData;\n\t\tforEach( this._metaDataModifiers, ( modifierFunction, modifierName ) => {\n\t\t\ttry {\n\t\t\t\tconst previousMetaData = Object.assign( {}, modifiedMetaData );\n\t\t\t\tmodifiedMetaData = modifierFunction( previousMetaData, paper );\n\t\t\t} catch ( modifierError ) {\n\t\t\t\tconsole.warn( `An error with message \"${ modifierError.message}\" occurred in metaData modifier ` +\n\t\t\t\t`function called ${ modifierName }. Skipping that function...` );\n\t\t\t}\n\t\t} );\n\t\treturn modifiedMetaData;\n\t}\n}\n\nexport default PaperParser;\n"],"mappings":";;;;;;AAAA,IAAAA,YAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,OAAA,GAAAD,OAAA;AAAiC,SAAAD,uBAAAG,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEjC;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,WAAW,CAAC;EACjB;AACD;AACA;AACA;AACA;AACA;AACA;EACCC,WAAWA,CAAEC,WAAW,EAAG;IAC1B,IAAI,CAACC,YAAY,GAAG,IAAIC,oBAAW,CAAC,CAAC;IACrC,IAAI,CAACC,YAAY,GAAGH,WAAW;IAE/B,IAAI,CAACI,kBAAkB,GAAG,CAAC,CAAC;EAC7B;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;EACCC,KAAKA,CAAEC,KAAK,EAAG;IACd;IACA,IAAI,CAACL,YAAY,CAACM,OAAO,CACxB,IAAI,CAACJ,YAAY,CAAEG,KAAK,CAACE,OAAO,CAAC,CAAE,CACpC,CAAC;;IAED;IACA,IAAI,CAACP,YAAY,CAACQ,WAAW,CAC5B,IAAI,CAACC,iBAAiB,CAAEJ,KAAM,CAC/B,CAAC;IAED,OAAO,IAAI,CAACL,YAAY;EACzB;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;EACCS,iBAAiBA,CAAEJ,KAAK,EAAG;IAC1B,IAAIK,QAAQ,GAAG,CAAC,CAAC;;IAEjB;;IAEA;IACAA,QAAQ,GAAGC,MAAM,CAACC,MAAM,CAAE,CAAC,CAAC,EAAE,IAAI,CAACC,oBAAoB,CAAEH,QAAQ,EAAEL,KAAM,CAAE,CAAC;IAE5E,OAAOK,QAAQ;EAChB;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;EACCI,wBAAwBA,CAAEC,YAAY,EAAEC,gBAAgB,EAAG;IAC1D;AACF;AACA;IACE,IAAI,CAACb,kBAAkB,CAAEY,YAAY,CAAE,GAAGC,gBAAgB;EAC3D;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACCH,oBAAoBA,CAAEH,QAAQ,EAAEL,KAAK,EAAG;IACvC,IAAIY,gBAAgB,GAAGP,QAAQ;IAC/B,IAAAQ,eAAO,EAAE,IAAI,CAACf,kBAAkB,EAAE,CAAEa,gBAAgB,EAAED,YAAY,KAAM;MACvE,IAAI;QACH,MAAMI,gBAAgB,GAAGR,MAAM,CAACC,MAAM,CAAE,CAAC,CAAC,EAAEK,gBAAiB,CAAC;QAC9DA,gBAAgB,GAAGD,gBAAgB,CAAEG,gBAAgB,EAAEd,KAAM,CAAC;MAC/D,CAAC,CAAC,OAAQe,aAAa,EAAG;QACzBC,OAAO,CAACC,IAAI,CAAE,0BAA2BF,aAAa,CAACG,OAAO,kCAAkC,GAChG,mBAAoBR,YAAY,6BAA+B,CAAC;MACjE;IACD,CAAE,CAAC;IACH,OAAOE,gBAAgB;EACxB;AACD;AAAC,IAAAO,QAAA,GAAAC,OAAA,CAAA7B,OAAA,GAEcC,WAAW","ignoreList":[]}

package/build/parsedPaper/build/linguisticParsing/Sentence.js

@@ -0,0 +1,95 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+/**
+ * Represents a sentence in a text.
+ */
+class Sentence {
+  /**
+   * Represents a sentence within a text.
+   *
+   * @param {string} text     The text of this sentence.
+   * @param {number} startIndex   The start index of this sentence.
+   * @param {number} endIndex     The end index of this sentence.
+   */
+  constructor(text, startIndex = 0, endIndex = 0) {
+    this.text = text;
+    this.words = [];
+    this.startIndex = startIndex;
+    this.endIndex = endIndex;
+  }
+
+  /**
+   * Sets a text for this sentence.
+   *
+   * @param {string} text The text to be set for the sentence.
+   *
+   * @returns {void}
+   */
+  setText(text) {
+    this.text = text;
+  }
+
+  /**
+   * Appends text to this sentence.
+   *
+   * @param {string} text The text to be added to the sentence.
+   *
+   * @returns {void}
+   */
+  appendText(text) {
+    this.text += text;
+  }
+
+  /**
+   * Returns the text of this sentence.
+   *
+   * @returns {string} The text of this senence.
+   */
+  getText() {
+    return this.text;
+  }
+
+  /**
+   * Sets the start index of this sentence.
+   *
+   * @param {number} startIndex The start index of this sentence.
+   * @returns {void}
+   */
+  setStartIndex(startIndex) {
+    this.startIndex = startIndex;
+  }
+
+  /**
+   * Sets the end index of this sentence.
+   *
+   * @param {number} endIndex The end index of this sentence.
+   * @returns {void}
+   */
+  setEndIndex(endIndex) {
+    this.endIndex = endIndex;
+  }
+
+  /**
+   * Returns the start index of this sentence.
+   *
+   * @returns {number} The start index of this sentence.
+   */
+  getStartIndex() {
+    return this.startIndex;
+  }
+
+  /**
+   * Returns the end index of this sentence.
+   *
+   * @returns {number} The end index of this sentence.
+   */
+  getEndIndex() {
+    return this.endIndex;
+  }
+}
+var _default = exports.default = Sentence;
+//# sourceMappingURL=Sentence.js.map

package/build/parsedPaper/build/linguisticParsing/Sentence.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"Sentence.js","names":["Sentence","constructor","text","startIndex","endIndex","words","setText","appendText","getText","setStartIndex","setEndIndex","getStartIndex","getEndIndex","_default","exports","default"],"sources":["../../../../src/parsedPaper/build/linguisticParsing/Sentence.js"],"sourcesContent":["/**\n * Represents a sentence in a text.\n */\nclass Sentence {\n\t/**\n\t * Represents a sentence within a text.\n\t *\n\t * @param {string} text     The text of this sentence.\n\t * @param {number} startIndex   The start index of this sentence.\n\t * @param {number} endIndex     The end index of this sentence.\n\t */\n\tconstructor( text, startIndex = 0, endIndex = 0 ) {\n\t\tthis.text = text;\n\t\tthis.words = [];\n\t\tthis.startIndex = startIndex;\n\t\tthis.endIndex = endIndex;\n\t}\n\n\t/**\n\t * Sets a text for this sentence.\n\t *\n\t * @param {string} text The text to be set for the sentence.\n\t *\n\t * @returns {void}\n\t */\n\tsetText( text ) {\n\t\tthis.text = text;\n\t}\n\n\t/**\n\t * Appends text to this sentence.\n\t *\n\t * @param {string} text The text to be added to the sentence.\n\t *\n\t * @returns {void}\n\t */\n\tappendText( text ) {\n\t\tthis.text += text;\n\t}\n\n\t/**\n\t * Returns the text of this sentence.\n\t *\n\t * @returns {string} The text of this senence.\n\t */\n\tgetText() {\n\t\treturn this.text;\n\t}\n\n\t/**\n\t * Sets the start index of this sentence.\n\t *\n\t * @param {number} startIndex The start index of this sentence.\n\t * @returns {void}\n\t */\n\tsetStartIndex( startIndex ) {\n\t\tthis.startIndex = startIndex;\n\t}\n\n\t/**\n\t * Sets the end index of this sentence.\n\t *\n\t * @param {number} endIndex The end index of this sentence.\n\t * @returns {void}\n\t */\n\tsetEndIndex( endIndex ) {\n\t\tthis.endIndex = endIndex;\n\t}\n\n\t/**\n\t * Returns the start index of this sentence.\n\t *\n\t * @returns {number} The start index of this sentence.\n\t */\n\tgetStartIndex() {\n\t\treturn this.startIndex;\n\t}\n\n\t/**\n\t * Returns the end index of this sentence.\n\t *\n\t * @returns {number} The end index of this sentence.\n\t */\n\tgetEndIndex() {\n\t\treturn this.endIndex;\n\t}\n}\n\nexport default Sentence;\n"],"mappings":";;;;;;AAAA;AACA;AACA;AACA,MAAMA,QAAQ,CAAC;EACd;AACD;AACA;AACA;AACA;AACA;AACA;EACCC,WAAWA,CAAEC,IAAI,EAAEC,UAAU,GAAG,CAAC,EAAEC,QAAQ,GAAG,CAAC,EAAG;IACjD,IAAI,CAACF,IAAI,GAAGA,IAAI;IAChB,IAAI,CAACG,KAAK,GAAG,EAAE;IACf,IAAI,CAACF,UAAU,GAAGA,UAAU;IAC5B,IAAI,CAACC,QAAQ,GAAGA,QAAQ;EACzB;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;EACCE,OAAOA,CAAEJ,IAAI,EAAG;IACf,IAAI,CAACA,IAAI,GAAGA,IAAI;EACjB;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;EACCK,UAAUA,CAAEL,IAAI,EAAG;IAClB,IAAI,CAACA,IAAI,IAAIA,IAAI;EAClB;;EAEA;AACD;AACA;AACA;AACA;EACCM,OAAOA,CAAA,EAAG;IACT,OAAO,IAAI,CAACN,IAAI;EACjB;;EAEA;AACD;AACA;AACA;AACA;AACA;EACCO,aAAaA,CAAEN,UAAU,EAAG;IAC3B,IAAI,CAACA,UAAU,GAAGA,UAAU;EAC7B;;EAEA;AACD;AACA;AACA;AACA;AACA;EACCO,WAAWA,CAAEN,QAAQ,EAAG;IACvB,IAAI,CAACA,QAAQ,GAAGA,QAAQ;EACzB;;EAEA;AACD;AACA;AACA;AACA;EACCO,aAAaA,CAAA,EAAG;IACf,OAAO,IAAI,CAACR,UAAU;EACvB;;EAEA;AACD;AACA;AACA;AACA;EACCS,WAAWA,CAAA,EAAG;IACb,OAAO,IAAI,CAACR,QAAQ;EACrB;AACD;AAAC,IAAAS,QAAA,GAAAC,OAAA,CAAAC,OAAA,GAEcf,QAAQ","ignoreList":[]}

package/build/parsedPaper/build/linguisticParsing/SentenceTokenizer.js

@@ -0,0 +1,294 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _lodash = require("lodash");
+var _core = _interopRequireDefault(require("tokenizer2/core"));
+var _quotes = require("../../../languageProcessing/helpers/sanitize/quotes");
+var _Sentence = _interopRequireDefault(require("./Sentence"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+// All characters that indicate a sentence delimiter.
+const fullStop = ".";
+// The \u2026 character is an ellipsis
+const sentenceDelimiters = "?!;\u2026";
+const fullStopRegex = new RegExp("^[" + fullStop + "]$");
+const sentenceDelimiterRegex = new RegExp("^[" + sentenceDelimiters + "]$");
+const sentenceRegex = new RegExp("^[^" + fullStop + sentenceDelimiters + "\\(\\)\\[\\]]+$");
+const blockStartRegex = /^\s*[[({]\s*$/;
+const blockEndRegex = /^\s*[\])}]\s*$/;
+const whiteSpaceStartRegex = /^\s*/;
+const whiteSpaceEndRegex = /\s*$/;
+
+/**
+ * Class for tokenizing a (html) text into sentences.
+ */
+class SentenceTokenizer {
+  /**
+   * Returns whether or not 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) {
+    return !(0, _lodash.isNaN)(parseInt(character, 10));
+  }
+
+  /**
+   * Returns whether or not 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 = (0, _quotes.normalize)(character);
+    return "'" === character || "\"" === character;
+  }
+
+  /**
+   * Returns whether or not a given character is a punctuation mark that can be at the beginning
+   * of a sentence, like ¿ and ¡ used in Spanish.
+   *
+   * @param {string} character The character to check.
+   *
+   * @returns {boolean} Whether or not the given character is a punctuation mark.
+   */
+  isPunctuation(character) {
+    return "¿" === character || "¡" === character;
+  }
+
+  /**
+   * Removes duplicate whitespace from a given text.
+   *
+   * @param {string} text The text with duplicate whitespace.
+   * @returns {string} The text without duplicate whitespace.
+   */
+  removeDuplicateWhitespace(text) {
+    return text.replace(/\s+/, " ");
+  }
+
+  /**
+   * Returns whether or not a certain character is a capital letter.
+   *
+   * @param {string} character The character to check.
+   *
+   * @returns {boolean} Whether or not the character is a capital letter.
+   */
+  isCapitalLetter(character) {
+    return character !== character.toLocaleLowerCase();
+  }
+
+  /**
+   * Retrieves the next two characters from an array with the two next tokens.
+   *
+   * @param {Array} nextTokens The two next tokens. Might be undefined.
+   *
+   * @returns {string} The next two characters.
+   */
+  getNextTwoCharacters(nextTokens) {
+    let next = "";
+    if (!(0, _lodash.isUndefined)(nextTokens[0])) {
+      next += nextTokens[0].src;
+    }
+    if (!(0, _lodash.isUndefined)(nextTokens[1])) {
+      next += nextTokens[1].src;
+    }
+    next = this.removeDuplicateWhitespace(next);
+    return next;
+  }
+
+  /**
+   * Checks if the sentenceBeginning beginning is a valid beginning.
+   *
+   * @param {string} sentenceBeginning The beginning of the sentence to validate.
+   *
+   * @returns {boolean} Returns true if it is a valid beginning, false if it is not.
+   */
+  isValidSentenceBeginning(sentenceBeginning) {
+    return this.isCapitalLetter(sentenceBeginning) || this.isNumber(sentenceBeginning) || this.isQuotation(sentenceBeginning) || this.isPunctuation(sentenceBeginning);
+  }
+
+  /**
+   * Checks if the token is a valid sentence ending.
+   *
+   * @param {Object} token The token to validate.
+   *
+   * @returns {boolean} Returns true if the token is valid ending, false if it is not.
+   */
+  isSentenceStart(token) {
+    return !(0, _lodash.isUndefined)(token) && ("html-start" === token.type || "html-end" === token.type || "block-start" === token.type);
+  }
+
+  /**
+   * Creates a tokenizer.
+   *
+   * @returns {Object} The tokenizer and the tokens.
+   */
+  createTokenizer() {
+    const tokens = [];
+    const tokenizer = (0, _core.default)(function (token) {
+      tokens.push(token);
+    });
+    tokenizer.addRule(fullStopRegex, "full-stop");
+    tokenizer.addRule(blockStartRegex, "block-start");
+    tokenizer.addRule(blockEndRegex, "block-end");
+    tokenizer.addRule(sentenceDelimiterRegex, "sentence-delimiter");
+    tokenizer.addRule(sentenceRegex, "sentence");
+    return {
+      tokenizer,
+      tokens
+    };
+  }
+
+  /**
+   * Tokenizes the given text using the given tokenizer.
+   *
+   * @param {Tokenizer} tokenizer The tokenizer to use.
+   * @param {string}    text      The text to tokenize.
+   *
+   * @returns {void}
+   */
+  tokenize(tokenizer, text) {
+    tokenizer.onText(text);
+    try {
+      tokenizer.end();
+    } catch (e) {
+      console.error("Tokenizer end error:", e, e.tokenizer2);
+    }
+  }
+
+  /**
+   * Determines the start and end indices of a set of sentences form a text.
+   *
+   * @param {Sentence[]} sentences A set of sentences for which to determine indices.
+   *
+   * @returns {void}
+   */
+  determineIndices(sentences) {
+    let currentIndex = 0;
+    for (const sentence of sentences) {
+      const startIndex = currentIndex;
+      sentence.setStartIndex(currentIndex);
+      const endIndex = startIndex + sentence.text.length - 1;
+      sentence.setEndIndex(endIndex);
+      currentIndex = endIndex + 1;
+    }
+  }
+
+  /**
+   * Trims the white space from the beginning of a sentence and adjusts the sentence start index accordingly.
+   *
+   * @param {Sentence} sentence The sentence for which to trim the white space at the start.
+   *
+   * @returns {void}
+   */
+  trimWhiteSpaceAtStart(sentence) {
+    const whiteSpaceLength = sentence.text.match(whiteSpaceStartRegex)[0].length;
+    sentence.setText(sentence.getText().slice(whiteSpaceLength));
+    sentence.setStartIndex(sentence.getStartIndex() + whiteSpaceLength);
+  }
+
+  /**
+   * Trims the white space from the end of a sentence and adjusts the sentence end index accordingly.
+   *
+   * @param {Sentence} sentence The sentence for which to trim the white space at the end.
+   *
+   * @returns {void}
+   */
+  trimWhiteSpaceAtEnd(sentence) {
+    const whiteSpaceLength = sentence.text.match(whiteSpaceEndRegex)[0].length;
+    sentence.setText(sentence.getText().slice(0, sentence.getText().length - whiteSpaceLength));
+    sentence.setEndIndex(sentence.getEndIndex() - whiteSpaceLength);
+  }
+
+  /**
+   * Trims white space from the beginning and end of sentences and adjusts the indices
+   * of the sentence beginnings and ends accordingly.
+   *
+   * @param {Sentence[]} sentences The sentences for which to trim the whitespace.
+   *
+   * @returns {void}
+   */
+  trimWhiteSpaces(sentences) {
+    for (const sentence of sentences) {
+      this.trimWhiteSpaceAtStart(sentence);
+      this.trimWhiteSpaceAtEnd(sentence);
+    }
+  }
+
+  /**
+   * Returns an array of sentence objects for a given array of tokens; assumes that the text has already been split into blocks.
+   *
+   * @param {Object[]} tokenArray The tokens from the sentence tokenizer.
+   *
+   * @returns {Sentence[]} An array of sentence objects.
+   */
+  getSentencesFromTokens(tokenArray) {
+    const tokenSentences = [];
+    let currentSentence = new _Sentence.default("", 0, 0),
+      nextSentenceStart;
+    tokenArray.forEach((token, i) => {
+      let hasNextSentence, nextCharacters;
+      const nextToken = tokenArray[i + 1];
+      const secondToNextToken = tokenArray[i + 2];
+      switch (token.type) {
+        case "sentence":
+          currentSentence.appendText(token.src);
+          break;
+        case "sentence-delimiter":
+          currentSentence.appendText(token.src);
+          if (!(0, _lodash.isUndefined)(nextToken) && "block-end" !== nextToken.type && "sentence-delimiter" !== nextToken.type) {
+            tokenSentences.push(currentSentence);
+            currentSentence = new _Sentence.default("");
+          }
+          break;
+        case "full-stop":
+          currentSentence.appendText(token.src);
+          nextCharacters = this.getNextTwoCharacters([nextToken, secondToNextToken]);
+
+          // For a new sentence we need to check the next two characters.
+          hasNextSentence = nextCharacters.length >= 2;
+          nextSentenceStart = hasNextSentence ? nextCharacters[1] : "";
+          // If the next character is a number, never split. For example: IPv4-numbers.
+          if (hasNextSentence && this.isNumber(nextCharacters[0])) {
+            break;
+          }
+          // Only split on sentence delimiters when the next sentence looks like the start of a sentence.
+          if (hasNextSentence && this.isValidSentenceBeginning(nextSentenceStart) || this.isSentenceStart(nextToken)) {
+            tokenSentences.push(currentSentence);
+            currentSentence = new _Sentence.default("");
+          }
+          break;
+        case "block-start":
+          currentSentence.appendText(token.src);
+          break;
+        case "block-end":
+          currentSentence.appendText(token.src);
+          nextCharacters = this.getNextTwoCharacters([nextToken, secondToNextToken]);
+
+          // For a new sentence we need to check the next two characters.
+          hasNextSentence = nextCharacters.length >= 2;
+          nextSentenceStart = hasNextSentence ? nextCharacters[0] : "";
+          // If the next character is a number, never split. For example: IPv4-numbers.
+          if (hasNextSentence && this.isNumber(nextCharacters[0])) {
+            break;
+          }
+          if (hasNextSentence && this.isValidSentenceBeginning(nextSentenceStart) || this.isSentenceStart(nextToken)) {
+            tokenSentences.push(currentSentence);
+            currentSentence = new _Sentence.default("");
+          }
+          break;
+      }
+    });
+    if (currentSentence.getText() !== "") {
+      tokenSentences.push(currentSentence);
+    }
+    this.determineIndices(tokenSentences);
+    this.trimWhiteSpaces(tokenSentences);
+    return tokenSentences;
+  }
+}
+exports.default = SentenceTokenizer;
+//# sourceMappingURL=SentenceTokenizer.js.map