axyseo 2.0.0-alpha.1

package/build/parsedPaper/build/tree/html/HTMLTreeConverter.js

@@ -0,0 +1,226 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _tree = require("../../../structure/tree");
+var _LeafNode = _interopRequireDefault(require("../../../structure/tree/nodes/LeafNode"));
+var _htmlConstants = require("./htmlConstants");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Converts a parse5 tree to a tree that can be analyzed.
+ */
+class HTMLTreeConverter {
+  /**
+   * Converts the parse5 tree to a Yoast tree.
+   *
+   * @param {Object} parse5Tree The parse5 tree to convert.
+   *
+   * @returns {module:parsedPaper/structure.Node} The converted tree.
+   */
+  convert(parse5Tree) {
+    const root = new _tree.StructuredNode("root", null);
+    this._convert(parse5Tree, root);
+    return root;
+  }
+
+  /**
+   * Converts the tree from a parse5 implementation to a Yoast tree.
+   *
+   * @param {Object}                                parse5Tree    The parse5 tree to convert.
+   * @param {module:parsedPaper/structure.Node}     parent        The tree in progress.
+   *
+   * @returns {void}
+   *
+   * @private
+   */
+  _convert(parse5Tree, parent) {
+    if (_htmlConstants.ignoredHtmlElements.includes(parse5Tree.nodeName)) {
+      return;
+    }
+    if (parse5Tree.childNodes) {
+      for (const node of parse5Tree.childNodes) {
+        const child = this._createChild(node, parent);
+        if (child) {
+          parent.addChild(child);
+          this._convert(node, child);
+        } else {
+          this._convert(node, parent);
+        }
+      }
+    }
+  }
+
+  /**
+   * Creates a new node for in the structured tree from the given parse 5 node.
+   * Returns `null` if no node should be added to the tree.
+   *
+   * @param {Object}                            parse5Node The parse5 node that should be parsed.
+   * @param {module:parsedPaper/structure.Node} parentNode The parent node.
+   *
+   * @returns {module:parsedPaper/structure.Node|null} The node that should be added to the tree, or `null` if no node should be added.
+   *
+   * @private
+   */
+  _createChild(parse5Node, parentNode) {
+    let child = null;
+    const nodeType = parse5Node.nodeName;
+    if (_htmlConstants.ignoredHtmlElements.includes(nodeType)) {
+      const formatting = new _tree.FormattingElement(nodeType, parse5Node.sourceCodeLocation, this._parseAttributes(parse5Node.attrs));
+      this._addLeafNodeContent(formatting, this._addFormatting, parentNode, parse5Node.sourceCodeLocation);
+    } else if (nodeType === "p") {
+      // Paragraph.
+      child = new _tree.Paragraph(parse5Node.sourceCodeLocation);
+    } else if (_htmlConstants.headings.includes(nodeType)) {
+      // Heading.
+      child = new _tree.Heading(parseInt(nodeType[1], 10), parse5Node.sourceCodeLocation);
+    } else if (nodeType === "li") {
+      // List item.
+      child = new _tree.ListItem(parse5Node.sourceCodeLocation);
+    } else if (nodeType === "ol" || nodeType === "ul") {
+      // List node.
+      child = new _tree.List(nodeType === "ol", parse5Node.sourceCodeLocation);
+    } else if (nodeType === "#text") {
+      // Text (outside of an ignored element).
+      child = this._addLeafNodeContent(parse5Node.value, this._addText, parentNode, parse5Node.sourceCodeLocation);
+    } else if (_htmlConstants.formattingElements.includes(nodeType)) {
+      // Formatting element.
+      const formatting = new _tree.FormattingElement(nodeType, parse5Node.sourceCodeLocation, this._parseAttributes(parse5Node.attrs));
+      child = this._addLeafNodeContent(formatting, this._addFormatting, parentNode, parse5Node.sourceCodeLocation);
+    } else {
+      // Other element (`div`, `section`, `article`, etc.).
+      child = new _tree.StructuredNode(nodeType, parse5Node.sourceCodeLocation);
+    }
+    return child;
+  }
+
+  /**
+   * Adds leaf node content (text or formatting) to the tree according to a predefined strategy:
+   *
+   * If the content has a leaf node (paragraph, heading, list item) parent or ancestor: add it to this leaf node.
+   * Else: wrap the content in an implicit paragraph, and add the content to it in such a way that runs
+   * of phrasing content make up one implicit paragraph.
+   *
+   * @param {string|module:parsedPaper/structure.FormattingElement} contentToAdd The content to add.
+   * @param {function}                                              add          A function that adds the content to the specified leaf node.
+   * @param {module:parsedPaper/structure.Node}                     parent       The parent to which to try to add the content.
+   * @param {Object}                                                location     The location of the content as parsed by parse5.
+   *
+   * @returns {null|module:parsedPaper/structure.Paragraph|null} The implicit paragraph, if one was created.
+   *
+   * @private
+   */
+  _addLeafNodeContent(contentToAdd, add, parent, location) {
+    if (parent instanceof _LeafNode.default) {
+      add(parent, contentToAdd);
+      return null;
+    }
+    const previousChild = this._previousChild(parent);
+    const leafNodeAncestor = this._leafNodeAncestor(parent);
+    if (leafNodeAncestor instanceof _tree.Paragraph) {
+      add(leafNodeAncestor, contentToAdd);
+      return null;
+    } else if (previousChild && previousChild instanceof _tree.Paragraph && previousChild.isImplicit) {
+      add(previousChild, contentToAdd);
+      return null;
+    }
+
+    // Don't create an implicit paragraph when the content is whitespace only.
+    if (/^\s*$/.exec(contentToAdd)) {
+      return null;
+    }
+    const child = new _tree.Paragraph(location, true);
+    add(child, contentToAdd);
+    return child;
+  }
+
+  /**
+   * Add text to the parent leaf node.
+   *
+   * @param {module:parsedPaper/structure.LeafNode} parent The leaf node to which to add the text.
+   * @param {string}                                text   The text to add to the node.
+   *
+   * @returns {void}
+   *
+   * @private
+   */
+  _addText(parent, text) {
+    parent.appendText(text);
+  }
+
+  /**
+   * Add a formatting element to the parent leaf node.
+   *
+   * @param {module:parsedPaper/structure.LeafNode}          parent     The leaf node to which to add the formatting.
+   * @param {module:parsedPaper/structure.FormattingElement} formatting The formatting element to add.
+   *
+   * @returns {void}
+   *
+   * @private
+   */
+  _addFormatting(parent, formatting) {
+    parent.addFormatting(formatting);
+  }
+
+  /**
+   * Parses the HTML element attributes from parse5's format to a plain JS object.
+   *
+   * @example
+   *
+   * const attributes = _parseAttributes( { name: "id", value: "an-id" } ) // becomes { id: "an-id" }.
+   *
+   * @param {Array<{ name: string, value: string }>} parse5attributes The attributes as parsed by parse5.
+   *
+   * @returns {Object} The parsed attributes.
+   *
+   * @private
+   */
+  _parseAttributes(parse5attributes) {
+    if (parse5attributes && parse5attributes.length > 0) {
+      return parse5attributes.reduce((attributes, attribute) => {
+        attributes[attribute.name] = attribute.value;
+        return attributes;
+      }, {});
+    }
+    return null;
+  }
+
+  /**
+   * Returns the last child of the given parent.
+   *
+   * @param {module:parsedPaper/structure.StructuredNode} parent The parent.
+   *
+   * @returns {module:parsedPaper/structure.Node} The parent's last child.
+   *
+   * @private
+   */
+  _previousChild(parent) {
+    if (parent.children) {
+      return parent.children[parent.children.length - 1];
+    }
+    return null;
+  }
+
+  /**
+   * Try to find the leaf node ancestor of this node. Returns `null` if the node does not have one.
+   *
+   * @param {module:parsedPaper/structure.Node} element The node for which to find the leaf node ancestor.
+   *
+   * @returns {null|module:parsedPaper/structure.Node} The leaf node ancestor, if it has one, `null` if not.
+   *
+   * @private
+   */
+  _leafNodeAncestor(element) {
+    const parent = element.parent;
+    if (!parent) {
+      return null;
+    }
+    if (element instanceof _LeafNode.default) {
+      return parent;
+    }
+    return this._leafNodeAncestor(parent);
+  }
+}
+var _default = exports.default = HTMLTreeConverter;
+//# sourceMappingURL=HTMLTreeConverter.js.map

package/build/parsedPaper/build/tree/html/HTMLTreeConverter.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"HTMLTreeConverter.js","names":["_tree","require","_LeafNode","_interopRequireDefault","_htmlConstants","e","__esModule","default","HTMLTreeConverter","convert","parse5Tree","root","StructuredNode","_convert","parent","ignoredHtmlElements","includes","nodeName","childNodes","node","child","_createChild","addChild","parse5Node","parentNode","nodeType","formatting","FormattingElement","sourceCodeLocation","_parseAttributes","attrs","_addLeafNodeContent","_addFormatting","Paragraph","headings","Heading","parseInt","ListItem","List","value","_addText","formattingElements","contentToAdd","add","location","LeafNode","previousChild","_previousChild","leafNodeAncestor","_leafNodeAncestor","isImplicit","exec","text","appendText","addFormatting","parse5attributes","length","reduce","attributes","attribute","name","children","element","_default","exports"],"sources":["../../../../../src/parsedPaper/build/tree/html/HTMLTreeConverter.js"],"sourcesContent":["import { FormattingElement, Heading, Paragraph, StructuredNode, List, ListItem } from \"../../../structure/tree\";\nimport LeafNode from \"../../../structure/tree/nodes/LeafNode\";\nimport { formattingElements, headings, ignoredHtmlElements } from \"./htmlConstants\";\n\n/**\n * Converts a parse5 tree to a tree that can be analyzed.\n */\nclass HTMLTreeConverter {\n\t/**\n\t * Converts the parse5 tree to a Yoast tree.\n\t *\n\t * @param {Object} parse5Tree The parse5 tree to convert.\n\t *\n\t * @returns {module:parsedPaper/structure.Node} The converted tree.\n\t */\n\tconvert( parse5Tree ) {\n\t\tconst root = new StructuredNode( \"root\", null );\n\t\tthis._convert( parse5Tree, root );\n\t\treturn root;\n\t}\n\n\t/**\n\t * Converts the tree from a parse5 implementation to a Yoast tree.\n\t *\n\t * @param {Object}                                parse5Tree    The parse5 tree to convert.\n\t * @param {module:parsedPaper/structure.Node}     parent        The tree in progress.\n\t *\n\t * @returns {void}\n\t *\n\t * @private\n\t */\n\t_convert( parse5Tree, parent ) {\n\t\tif ( ignoredHtmlElements.includes( parse5Tree.nodeName ) ) {\n\t\t\treturn;\n\t\t}\n\t\tif ( parse5Tree.childNodes ) {\n\t\t\tfor ( const node of parse5Tree.childNodes ) {\n\t\t\t\tconst child = this._createChild( node, parent );\n\n\t\t\t\tif ( child ) {\n\t\t\t\t\tparent.addChild( child );\n\t\t\t\t\tthis._convert( node, child );\n\t\t\t\t} else {\n\t\t\t\t\tthis._convert( node, parent );\n\t\t\t\t}\n\t\t\t}\n\t\t}\n\t}\n\n\t/**\n\t * Creates a new node for in the structured tree from the given parse 5 node.\n\t * Returns `null` if no node should be added to the tree.\n\t *\n\t * @param {Object}                            parse5Node The parse5 node that should be parsed.\n\t * @param {module:parsedPaper/structure.Node} parentNode The parent node.\n\t *\n\t * @returns {module:parsedPaper/structure.Node|null} The node that should be added to the tree, or `null` if no node should be added.\n\t *\n\t * @private\n\t */\n\t_createChild( parse5Node, parentNode ) {\n\t\tlet child = null;\n\n\t\tconst nodeType = parse5Node.nodeName;\n\n\t\tif ( ignoredHtmlElements.includes( nodeType ) ) {\n\t\t\tconst formatting = new FormattingElement( nodeType, parse5Node.sourceCodeLocation, this._parseAttributes( parse5Node.attrs ) );\n\t\t\tthis._addLeafNodeContent( formatting, this._addFormatting, parentNode, parse5Node.sourceCodeLocation );\n\t\t} else if ( nodeType === \"p\" ) {\n\t\t\t// Paragraph.\n\t\t\tchild = new Paragraph( parse5Node.sourceCodeLocation );\n\t\t} else if ( headings.includes( nodeType ) ) {\n\t\t\t// Heading.\n\t\t\tchild = new Heading( parseInt( nodeType[ 1 ], 10 ), parse5Node.sourceCodeLocation );\n\t\t} else if ( nodeType === \"li\" ) {\n\t\t\t// List item.\n\t\t\tchild = new ListItem( parse5Node.sourceCodeLocation );\n\t\t} else if ( nodeType === \"ol\" || nodeType === \"ul\" ) {\n\t\t\t// List node.\n\t\t\tchild = new List( nodeType === \"ol\", parse5Node.sourceCodeLocation );\n\t\t} else if ( nodeType === \"#text\" ) {\n\t\t\t// Text (outside of an ignored element).\n\t\t\tchild = this._addLeafNodeContent( parse5Node.value, this._addText, parentNode, parse5Node.sourceCodeLocation );\n\t\t} else if ( formattingElements.includes( nodeType ) ) {\n\t\t\t// Formatting element.\n\t\t\tconst formatting = new FormattingElement( nodeType, parse5Node.sourceCodeLocation, this._parseAttributes( parse5Node.attrs ) );\n\t\t\tchild = this._addLeafNodeContent( formatting, this._addFormatting, parentNode, parse5Node.sourceCodeLocation );\n\t\t} else {\n\t\t\t// Other element (`div`, `section`, `article`, etc.).\n\t\t\tchild = new StructuredNode( nodeType, parse5Node.sourceCodeLocation );\n\t\t}\n\n\t\treturn child;\n\t}\n\n\t/**\n\t * Adds leaf node content (text or formatting) to the tree according to a predefined strategy:\n\t *\n\t * If the content has a leaf node (paragraph, heading, list item) parent or ancestor: add it to this leaf node.\n\t * Else: wrap the content in an implicit paragraph, and add the content to it in such a way that runs\n\t * of phrasing content make up one implicit paragraph.\n\t *\n\t * @param {string|module:parsedPaper/structure.FormattingElement} contentToAdd The content to add.\n\t * @param {function}                                              add          A function that adds the content to the specified leaf node.\n\t * @param {module:parsedPaper/structure.Node}                     parent       The parent to which to try to add the content.\n\t * @param {Object}                                                location     The location of the content as parsed by parse5.\n\t *\n\t * @returns {null|module:parsedPaper/structure.Paragraph|null} The implicit paragraph, if one was created.\n\t *\n\t * @private\n\t */\n\t_addLeafNodeContent( contentToAdd, add, parent, location ) {\n\t\tif ( parent instanceof LeafNode ) {\n\t\t\tadd( parent, contentToAdd );\n\t\t\treturn null;\n\t\t}\n\n\t\tconst previousChild = this._previousChild( parent );\n\t\tconst leafNodeAncestor = this._leafNodeAncestor( parent );\n\n\t\tif ( leafNodeAncestor instanceof Paragraph ) {\n\t\t\tadd( leafNodeAncestor, contentToAdd );\n\t\t\treturn null;\n\t\t} else if ( previousChild && previousChild instanceof Paragraph && previousChild.isImplicit ) {\n\t\t\tadd( previousChild, contentToAdd );\n\t\t\treturn null;\n\t\t}\n\n\t\t// Don't create an implicit paragraph when the content is whitespace only.\n\t\tif ( /^\\s*$/.exec( contentToAdd ) ) {\n\t\t\treturn null;\n\t\t}\n\n\t\tconst child = new Paragraph( location, true );\n\t\tadd( child, contentToAdd );\n\t\treturn child;\n\t}\n\n\t/**\n\t * Add text to the parent leaf node.\n\t *\n\t * @param {module:parsedPaper/structure.LeafNode} parent The leaf node to which to add the text.\n\t * @param {string}                                text   The text to add to the node.\n\t *\n\t * @returns {void}\n\t *\n\t * @private\n\t */\n\t_addText( parent, text ) {\n\t\tparent.appendText( text );\n\t}\n\n\t/**\n\t * Add a formatting element to the parent leaf node.\n\t *\n\t * @param {module:parsedPaper/structure.LeafNode}          parent     The leaf node to which to add the formatting.\n\t * @param {module:parsedPaper/structure.FormattingElement} formatting The formatting element to add.\n\t *\n\t * @returns {void}\n\t *\n\t * @private\n\t */\n\t_addFormatting( parent, formatting ) {\n\t\tparent.addFormatting( formatting );\n\t}\n\n\t/**\n\t * Parses the HTML element attributes from parse5's format to a plain JS object.\n\t *\n\t * @example\n\t *\n\t * const attributes = _parseAttributes( { name: \"id\", value: \"an-id\" } ) // becomes { id: \"an-id\" }.\n\t *\n\t * @param {Array<{ name: string, value: string }>} parse5attributes The attributes as parsed by parse5.\n\t *\n\t * @returns {Object} The parsed attributes.\n\t *\n\t * @private\n\t */\n\t_parseAttributes( parse5attributes ) {\n\t\tif ( parse5attributes && parse5attributes.length > 0 ) {\n\t\t\treturn parse5attributes.reduce( ( attributes, attribute ) => {\n\t\t\t\tattributes[ attribute.name ] = attribute.value;\n\t\t\t\treturn attributes;\n\t\t\t}, {} );\n\t\t}\n\t\treturn null;\n\t}\n\n\t/**\n\t * Returns the last child of the given parent.\n\t *\n\t * @param {module:parsedPaper/structure.StructuredNode} parent The parent.\n\t *\n\t * @returns {module:parsedPaper/structure.Node} The parent's last child.\n\t *\n\t * @private\n\t */\n\t_previousChild( parent ) {\n\t\tif ( parent.children ) {\n\t\t\treturn parent.children[ parent.children.length - 1 ];\n\t\t}\n\t\treturn null;\n\t}\n\n\t/**\n\t * Try to find the leaf node ancestor of this node. Returns `null` if the node does not have one.\n\t *\n\t * @param {module:parsedPaper/structure.Node} element The node for which to find the leaf node ancestor.\n\t *\n\t * @returns {null|module:parsedPaper/structure.Node} The leaf node ancestor, if it has one, `null` if not.\n\t *\n\t * @private\n\t */\n\t_leafNodeAncestor( element ) {\n\t\tconst parent = element.parent;\n\n\t\tif ( ! parent ) {\n\t\t\treturn null;\n\t\t}\n\n\t\tif ( element instanceof LeafNode ) {\n\t\t\treturn parent;\n\t\t}\n\n\t\treturn this._leafNodeAncestor( parent );\n\t}\n}\n\nexport default HTMLTreeConverter;\n"],"mappings":";;;;;;AAAA,IAAAA,KAAA,GAAAC,OAAA;AACA,IAAAC,SAAA,GAAAC,sBAAA,CAAAF,OAAA;AACA,IAAAG,cAAA,GAAAH,OAAA;AAAoF,SAAAE,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEpF;AACA;AACA;AACA,MAAMG,iBAAiB,CAAC;EACvB;AACD;AACA;AACA;AACA;AACA;AACA;EACCC,OAAOA,CAAEC,UAAU,EAAG;IACrB,MAAMC,IAAI,GAAG,IAAIC,oBAAc,CAAE,MAAM,EAAE,IAAK,CAAC;IAC/C,IAAI,CAACC,QAAQ,CAAEH,UAAU,EAAEC,IAAK,CAAC;IACjC,OAAOA,IAAI;EACZ;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACCE,QAAQA,CAAEH,UAAU,EAAEI,MAAM,EAAG;IAC9B,IAAKC,kCAAmB,CAACC,QAAQ,CAAEN,UAAU,CAACO,QAAS,CAAC,EAAG;MAC1D;IACD;IACA,IAAKP,UAAU,CAACQ,UAAU,EAAG;MAC5B,KAAM,MAAMC,IAAI,IAAIT,UAAU,CAACQ,UAAU,EAAG;QAC3C,MAAME,KAAK,GAAG,IAAI,CAACC,YAAY,CAAEF,IAAI,EAAEL,MAAO,CAAC;QAE/C,IAAKM,KAAK,EAAG;UACZN,MAAM,CAACQ,QAAQ,CAAEF,KAAM,CAAC;UACxB,IAAI,CAACP,QAAQ,CAAEM,IAAI,EAAEC,KAAM,CAAC;QAC7B,CAAC,MAAM;UACN,IAAI,CAACP,QAAQ,CAAEM,IAAI,EAAEL,MAAO,CAAC;QAC9B;MACD;IACD;EACD;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACCO,YAAYA,CAAEE,UAAU,EAAEC,UAAU,EAAG;IACtC,IAAIJ,KAAK,GAAG,IAAI;IAEhB,MAAMK,QAAQ,GAAGF,UAAU,CAACN,QAAQ;IAEpC,IAAKF,kCAAmB,CAACC,QAAQ,CAAES,QAAS,CAAC,EAAG;MAC/C,MAAMC,UAAU,GAAG,IAAIC,uBAAiB,CAAEF,QAAQ,EAAEF,UAAU,CAACK,kBAAkB,EAAE,IAAI,CAACC,gBAAgB,CAAEN,UAAU,CAACO,KAAM,CAAE,CAAC;MAC9H,IAAI,CAACC,mBAAmB,CAAEL,UAAU,EAAE,IAAI,CAACM,cAAc,EAAER,UAAU,EAAED,UAAU,CAACK,kBAAmB,CAAC;IACvG,CAAC,MAAM,IAAKH,QAAQ,KAAK,GAAG,EAAG;MAC9B;MACAL,KAAK,GAAG,IAAIa,eAAS,CAAEV,UAAU,CAACK,kBAAmB,CAAC;IACvD,CAAC,MAAM,IAAKM,uBAAQ,CAAClB,QAAQ,CAAES,QAAS,CAAC,EAAG;MAC3C;MACAL,KAAK,GAAG,IAAIe,aAAO,CAAEC,QAAQ,CAAEX,QAAQ,CAAE,CAAC,CAAE,EAAE,EAAG,CAAC,EAAEF,UAAU,CAACK,kBAAmB,CAAC;IACpF,CAAC,MAAM,IAAKH,QAAQ,KAAK,IAAI,EAAG;MAC/B;MACAL,KAAK,GAAG,IAAIiB,cAAQ,CAAEd,UAAU,CAACK,kBAAmB,CAAC;IACtD,CAAC,MAAM,IAAKH,QAAQ,KAAK,IAAI,IAAIA,QAAQ,KAAK,IAAI,EAAG;MACpD;MACAL,KAAK,GAAG,IAAIkB,UAAI,CAAEb,QAAQ,KAAK,IAAI,EAAEF,UAAU,CAACK,kBAAmB,CAAC;IACrE,CAAC,MAAM,IAAKH,QAAQ,KAAK,OAAO,EAAG;MAClC;MACAL,KAAK,GAAG,IAAI,CAACW,mBAAmB,CAAER,UAAU,CAACgB,KAAK,EAAE,IAAI,CAACC,QAAQ,EAAEhB,UAAU,EAAED,UAAU,CAACK,kBAAmB,CAAC;IAC/G,CAAC,MAAM,IAAKa,iCAAkB,CAACzB,QAAQ,CAAES,QAAS,CAAC,EAAG;MACrD;MACA,MAAMC,UAAU,GAAG,IAAIC,uBAAiB,CAAEF,QAAQ,EAAEF,UAAU,CAACK,kBAAkB,EAAE,IAAI,CAACC,gBAAgB,CAAEN,UAAU,CAACO,KAAM,CAAE,CAAC;MAC9HV,KAAK,GAAG,IAAI,CAACW,mBAAmB,CAAEL,UAAU,EAAE,IAAI,CAACM,cAAc,EAAER,UAAU,EAAED,UAAU,CAACK,kBAAmB,CAAC;IAC/G,CAAC,MAAM;MACN;MACAR,KAAK,GAAG,IAAIR,oBAAc,CAAEa,QAAQ,EAAEF,UAAU,CAACK,kBAAmB,CAAC;IACtE;IAEA,OAAOR,KAAK;EACb;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACCW,mBAAmBA,CAAEW,YAAY,EAAEC,GAAG,EAAE7B,MAAM,EAAE8B,QAAQ,EAAG;IAC1D,IAAK9B,MAAM,YAAY+B,iBAAQ,EAAG;MACjCF,GAAG,CAAE7B,MAAM,EAAE4B,YAAa,CAAC;MAC3B,OAAO,IAAI;IACZ;IAEA,MAAMI,aAAa,GAAG,IAAI,CAACC,cAAc,CAAEjC,MAAO,CAAC;IACnD,MAAMkC,gBAAgB,GAAG,IAAI,CAACC,iBAAiB,CAAEnC,MAAO,CAAC;IAEzD,IAAKkC,gBAAgB,YAAYf,eAAS,EAAG;MAC5CU,GAAG,CAAEK,gBAAgB,EAAEN,YAAa,CAAC;MACrC,OAAO,IAAI;IACZ,CAAC,MAAM,IAAKI,aAAa,IAAIA,aAAa,YAAYb,eAAS,IAAIa,aAAa,CAACI,UAAU,EAAG;MAC7FP,GAAG,CAAEG,aAAa,EAAEJ,YAAa,CAAC;MAClC,OAAO,IAAI;IACZ;;IAEA;IACA,IAAK,OAAO,CAACS,IAAI,CAAET,YAAa,CAAC,EAAG;MACnC,OAAO,IAAI;IACZ;IAEA,MAAMtB,KAAK,GAAG,IAAIa,eAAS,CAAEW,QAAQ,EAAE,IAAK,CAAC;IAC7CD,GAAG,CAAEvB,KAAK,EAAEsB,YAAa,CAAC;IAC1B,OAAOtB,KAAK;EACb;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACCoB,QAAQA,CAAE1B,MAAM,EAAEsC,IAAI,EAAG;IACxBtC,MAAM,CAACuC,UAAU,CAAED,IAAK,CAAC;EAC1B;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACCpB,cAAcA,CAAElB,MAAM,EAAEY,UAAU,EAAG;IACpCZ,MAAM,CAACwC,aAAa,CAAE5B,UAAW,CAAC;EACnC;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACCG,gBAAgBA,CAAE0B,gBAAgB,EAAG;IACpC,IAAKA,gBAAgB,IAAIA,gBAAgB,CAACC,MAAM,GAAG,CAAC,EAAG;MACtD,OAAOD,gBAAgB,CAACE,MAAM,CAAE,CAAEC,UAAU,EAAEC,SAAS,KAAM;QAC5DD,UAAU,CAAEC,SAAS,CAACC,IAAI,CAAE,GAAGD,SAAS,CAACpB,KAAK;QAC9C,OAAOmB,UAAU;MAClB,CAAC,EAAE,CAAC,CAAE,CAAC;IACR;IACA,OAAO,IAAI;EACZ;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACCX,cAAcA,CAAEjC,MAAM,EAAG;IACxB,IAAKA,MAAM,CAAC+C,QAAQ,EAAG;MACtB,OAAO/C,MAAM,CAAC+C,QAAQ,CAAE/C,MAAM,CAAC+C,QAAQ,CAACL,MAAM,GAAG,CAAC,CAAE;IACrD;IACA,OAAO,IAAI;EACZ;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACCP,iBAAiBA,CAAEa,OAAO,EAAG;IAC5B,MAAMhD,MAAM,GAAGgD,OAAO,CAAChD,MAAM;IAE7B,IAAK,CAAEA,MAAM,EAAG;MACf,OAAO,IAAI;IACZ;IAEA,IAAKgD,OAAO,YAAYjB,iBAAQ,EAAG;MAClC,OAAO/B,MAAM;IACd;IAEA,OAAO,IAAI,CAACmC,iBAAiB,CAAEnC,MAAO,CAAC;EACxC;AACD;AAAC,IAAAiD,QAAA,GAAAC,OAAA,CAAAzD,OAAA,GAEcC,iBAAiB","ignoreList":[]}

package/build/parsedPaper/build/tree/html/buildTree.js

@@ -0,0 +1,36 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _parse = require("parse5");
+var _HTMLTreeConverter = _interopRequireDefault(require("./HTMLTreeConverter"));
+var _postParsing = _interopRequireDefault(require("../cleanup/postParsing"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Parses the given html-string to a tree, to be used in further analysis.
+ *
+ * @param {string} html The html-string that should be parsed.
+ *
+ * @returns {module:parsedPaper/structure.Node} The build tree.
+ *
+ * @memberOf module:parsedPaper/builder
+ */
+const buildTree = function (html) {
+  /*
+   * Parsing of a HTML article takes on average 19ms
+   * (based on the fullTexts in the specs (n=24), measured using `console.time`).
+   */
+  const parse5Tree = (0, _parse.parseFragment)(html, {
+    sourceCodeLocationInfo: true
+  });
+  const htmlTreeConverter = new _HTMLTreeConverter.default();
+  let tree = htmlTreeConverter.convert(parse5Tree);
+
+  // Cleanup takes < 2ms.
+  tree = (0, _postParsing.default)(tree);
+  return tree;
+};
+var _default = exports.default = buildTree;
+//# sourceMappingURL=buildTree.js.map

package/build/parsedPaper/build/tree/html/buildTree.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"buildTree.js","names":["_parse","require","_HTMLTreeConverter","_interopRequireDefault","_postParsing","e","__esModule","default","buildTree","html","parse5Tree","parseFragment","sourceCodeLocationInfo","htmlTreeConverter","HTMLTreeConverter","tree","convert","cleanUpTree","_default","exports"],"sources":["../../../../../src/parsedPaper/build/tree/html/buildTree.js"],"sourcesContent":["import { parseFragment } from \"parse5\";\n\nimport HTMLTreeConverter from \"./HTMLTreeConverter\";\nimport cleanUpTree from \"../cleanup/postParsing\";\n\n\n/**\n * Parses the given html-string to a tree, to be used in further analysis.\n *\n * @param {string} html The html-string that should be parsed.\n *\n * @returns {module:parsedPaper/structure.Node} The build tree.\n *\n * @memberOf module:parsedPaper/builder\n */\nconst buildTree = function( html ) {\n\t/*\n\t * Parsing of a HTML article takes on average 19ms\n\t * (based on the fullTexts in the specs (n=24), measured using `console.time`).\n\t */\n\tconst parse5Tree = parseFragment( html, { sourceCodeLocationInfo: true } );\n\n\tconst htmlTreeConverter = new HTMLTreeConverter();\n\tlet tree = htmlTreeConverter.convert( parse5Tree );\n\n\t// Cleanup takes < 2ms.\n\ttree = cleanUpTree( tree );\n\treturn tree;\n};\n\nexport default buildTree;\n"],"mappings":";;;;;;AAAA,IAAAA,MAAA,GAAAC,OAAA;AAEA,IAAAC,kBAAA,GAAAC,sBAAA,CAAAF,OAAA;AACA,IAAAG,YAAA,GAAAD,sBAAA,CAAAF,OAAA;AAAiD,SAAAE,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAGjD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,SAAS,GAAG,SAAAA,CAAUC,IAAI,EAAG;EAClC;AACD;AACA;AACA;EACC,MAAMC,UAAU,GAAG,IAAAC,oBAAa,EAAEF,IAAI,EAAE;IAAEG,sBAAsB,EAAE;EAAK,CAAE,CAAC;EAE1E,MAAMC,iBAAiB,GAAG,IAAIC,0BAAiB,CAAC,CAAC;EACjD,IAAIC,IAAI,GAAGF,iBAAiB,CAACG,OAAO,CAAEN,UAAW,CAAC;;EAElD;EACAK,IAAI,GAAG,IAAAE,oBAAW,EAAEF,IAAK,CAAC;EAC1B,OAAOA,IAAI;AACZ,CAAC;AAAC,IAAAG,QAAA,GAAAC,OAAA,CAAAZ,OAAA,GAEaC,SAAS","ignoreList":[]}

package/build/parsedPaper/build/tree/html/htmlConstants.js

@@ -0,0 +1,35 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.ignoredHtmlElements = exports.headings = exports.formattingElements = void 0;
+/**
+ * All HTML element tags that we treat as formatting / phrasing content.
+ * @type {string[]}
+ * @const
+ *
+ * @see https://developer.mozilla.org/en-US/docs/Web/Guide/HTML/Content_categories#Phrasing_content
+ *
+ * @memberOf module:parsedPaper/builder
+ */
+const formattingElements = exports.formattingElements = ["a", "abbr", "audio", "b", "bdo", "button", "canvas", "cite", "command", "data", "datalist", "dfn", "del", "em", "embed", "i", "iframe", "img", "input", "kbd", "keygen", "label", "mark", "math", "meter", "noscript", "object", "output", "progress", "q", "ruby", "samp", "select", "small", "span", "strong", "sub", "sup", "svg", "textarea", "time", "var", "video", "wbr"];
+
+/**
+ * All tags of the HTML element types that are ignored in our analysis.
+ * @type {string[]}
+ * @const
+ *
+ * @memberOf module:parsedPaper/builder
+ */
+const ignoredHtmlElements = exports.ignoredHtmlElements = ["script", "style", "pre", "#comment", "code", "br"];
+
+/**
+ * All HTML heading element tags, from `h1` to `h6`.
+ * @type {string[]}
+ * @const
+ *
+ * @memberOf module:parsedPaper/builder
+ */
+const headings = exports.headings = ["h1", "h2", "h3", "h4", "h5", "h6"];
+//# sourceMappingURL=htmlConstants.js.map

package/build/parsedPaper/build/tree/html/htmlConstants.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"htmlConstants.js","names":["formattingElements","exports","ignoredHtmlElements","headings"],"sources":["../../../../../src/parsedPaper/build/tree/html/htmlConstants.js"],"sourcesContent":["/**\n * All HTML element tags that we treat as formatting / phrasing content.\n * @type {string[]}\n * @const\n *\n * @see https://developer.mozilla.org/en-US/docs/Web/Guide/HTML/Content_categories#Phrasing_content\n *\n * @memberOf module:parsedPaper/builder\n */\nconst formattingElements = [ \"a\", \"abbr\", \"audio\", \"b\", \"bdo\", \"button\", \"canvas\", \"cite\", \"command\",\n\t\"data\", \"datalist\", \"dfn\", \"del\", \"em\", \"embed\", \"i\", \"iframe\", \"img\", \"input\", \"kbd\", \"keygen\", \"label\", \"mark\",\n\t\"math\", \"meter\", \"noscript\", \"object\", \"output\", \"progress\", \"q\", \"ruby\", \"samp\", \"select\", \"small\",\n\t\"span\", \"strong\", \"sub\", \"sup\", \"svg\", \"textarea\", \"time\", \"var\", \"video\", \"wbr\" ];\n\n/**\n * All tags of the HTML element types that are ignored in our analysis.\n * @type {string[]}\n * @const\n *\n * @memberOf module:parsedPaper/builder\n */\nconst ignoredHtmlElements = [ \"script\", \"style\", \"pre\", \"#comment\", \"code\", \"br\" ];\n\n/**\n * All HTML heading element tags, from `h1` to `h6`.\n * @type {string[]}\n * @const\n *\n * @memberOf module:parsedPaper/builder\n */\nconst headings = [ \"h1\", \"h2\", \"h3\", \"h4\", \"h5\", \"h6\" ];\n\nexport {\n\tformattingElements,\n\tignoredHtmlElements,\n\theadings,\n};\n"],"mappings":";;;;;;AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMA,kBAAkB,GAAAC,OAAA,CAAAD,kBAAA,GAAG,CAAE,GAAG,EAAE,MAAM,EAAE,OAAO,EAAE,GAAG,EAAE,KAAK,EAAE,QAAQ,EAAE,QAAQ,EAAE,MAAM,EAAE,SAAS,EACnG,MAAM,EAAE,UAAU,EAAE,KAAK,EAAE,KAAK,EAAE,IAAI,EAAE,OAAO,EAAE,GAAG,EAAE,QAAQ,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,EAAE,QAAQ,EAAE,OAAO,EAAE,MAAM,EAChH,MAAM,EAAE,OAAO,EAAE,UAAU,EAAE,QAAQ,EAAE,QAAQ,EAAE,UAAU,EAAE,GAAG,EAAE,MAAM,EAAE,MAAM,EAAE,QAAQ,EAAE,OAAO,EACnG,MAAM,EAAE,QAAQ,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,UAAU,EAAE,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,KAAK,CAAE;;AAEnF;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,mBAAmB,GAAAD,OAAA,CAAAC,mBAAA,GAAG,CAAE,QAAQ,EAAE,OAAO,EAAE,KAAK,EAAE,UAAU,EAAE,MAAM,EAAE,IAAI,CAAE;;AAElF;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,QAAQ,GAAAF,OAAA,CAAAE,QAAA,GAAG,CAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,CAAE","ignoreList":[]}

package/build/parsedPaper/build/tree/index.js

@@ -0,0 +1,20 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _TreeBuilder = _interopRequireDefault(require("./TreeBuilder"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * This module contains the main logic to transform a formatted text (for now only HTML is supported)
+ * to a tree representation.
+ *
+ * This tree structure in turn can be used for further textual analysis.
+ *
+ * @module parsedPaper/builder
+ *
+ * @see module:parsedPaper/structure
+ */
+var _default = exports.default = _TreeBuilder.default;
+//# sourceMappingURL=index.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","names":["_TreeBuilder","_interopRequireDefault","require","e","__esModule","default","_default","exports","TreeBuilder"],"sources":["../../../../src/parsedPaper/build/tree/index.js"],"sourcesContent":["import TreeBuilder from \"./TreeBuilder\";\n\n/**\n * This module contains the main logic to transform a formatted text (for now only HTML is supported)\n * to a tree representation.\n *\n * This tree structure in turn can be used for further textual analysis.\n *\n * @module parsedPaper/builder\n *\n * @see module:parsedPaper/structure\n */\n\nexport default TreeBuilder;\n"],"mappings":";;;;;;AAAA,IAAAA,YAAA,GAAAC,sBAAA,CAAAC,OAAA;AAAwC,SAAAD,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAExC;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AATA,IAAAG,QAAA,GAAAC,OAAA,CAAAF,OAAA,GAWeG,oBAAW","ignoreList":[]}

package/build/parsedPaper/build/tree/metadata/buildTree.js

@@ -0,0 +1,36 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _parseSynonyms = _interopRequireDefault(require("../../../../languageProcessing/helpers/sanitize/parseSynonyms"));
+var _nodes = require("../../../structure/tree/nodes");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Parses the given paper attributes to a tree.
+ *
+ * @param {Paper} paper The Paper to parse.
+ *
+ * @memberOf module:parsedPaper/builder
+ *
+ * @returns {module:parsedPaper/structure.Node} The build tree.
+ */
+const buildTree = function buildTree(paper) {
+  const metadata = new _nodes.StructuredNode("metadata", null);
+
+  // Add text types.
+  metadata.addChild(new _nodes.MetadataText("title", paper.getTitle()));
+  metadata.addChild(new _nodes.MetadataText("description", paper.getDescription()));
+
+  // Add miscellaneous types.
+  metadata.addChild(new _nodes.MetadataMiscellaneous("keyphrase", paper.getKeyword()));
+  metadata.addChild(new _nodes.MetadataMiscellaneous("synonyms", (0, _parseSynonyms.default)(paper.getSynonyms())));
+  metadata.addChild(new _nodes.MetadataMiscellaneous("slug", paper.getSlug()));
+  metadata.addChild(new _nodes.MetadataMiscellaneous("titleWidth", paper.getTitleWidth()));
+  metadata.addChild(new _nodes.MetadataMiscellaneous("permalink", paper.getPermalink()));
+  metadata.addChild(new _nodes.MetadataMiscellaneous("locale", paper.getLocale()));
+  return metadata;
+};
+var _default = exports.default = buildTree;
+//# sourceMappingURL=buildTree.js.map

package/build/parsedPaper/build/tree/metadata/buildTree.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"buildTree.js","names":["_parseSynonyms","_interopRequireDefault","require","_nodes","e","__esModule","default","buildTree","paper","metadata","StructuredNode","addChild","MetadataText","getTitle","getDescription","MetadataMiscellaneous","getKeyword","parseSynonyms","getSynonyms","getSlug","getTitleWidth","getPermalink","getLocale","_default","exports"],"sources":["../../../../../src/parsedPaper/build/tree/metadata/buildTree.js"],"sourcesContent":["import parseSynonyms from \"../../../../languageProcessing/helpers/sanitize/parseSynonyms\";\n\nimport { MetadataMiscellaneous, MetadataText, StructuredNode } from \"../../../structure/tree/nodes\";\n\n/**\n * Parses the given paper attributes to a tree.\n *\n * @param {Paper} paper The Paper to parse.\n *\n * @memberOf module:parsedPaper/builder\n *\n * @returns {module:parsedPaper/structure.Node} The build tree.\n */\nconst buildTree = function buildTree( paper ) {\n\tconst metadata = new StructuredNode( \"metadata\", null );\n\n\t// Add text types.\n\tmetadata.addChild( new MetadataText( \"title\", paper.getTitle() ) );\n\tmetadata.addChild( new MetadataText( \"description\", paper.getDescription() ) );\n\n\t// Add miscellaneous types.\n\tmetadata.addChild( new MetadataMiscellaneous( \"keyphrase\", paper.getKeyword() ) );\n\tmetadata.addChild( new MetadataMiscellaneous( \"synonyms\", parseSynonyms( paper.getSynonyms() ) ) );\n\tmetadata.addChild( new MetadataMiscellaneous( \"slug\", paper.getSlug() ) );\n\tmetadata.addChild( new MetadataMiscellaneous( \"titleWidth\", paper.getTitleWidth() ) );\n\tmetadata.addChild( new MetadataMiscellaneous( \"permalink\", paper.getPermalink() ) );\n\tmetadata.addChild( new MetadataMiscellaneous( \"locale\", paper.getLocale() ) );\n\n\treturn metadata;\n};\n\nexport default buildTree;\n"],"mappings":";;;;;;AAAA,IAAAA,cAAA,GAAAC,sBAAA,CAAAC,OAAA;AAEA,IAAAC,MAAA,GAAAD,OAAA;AAAoG,SAAAD,uBAAAG,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEpG;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,SAAS,GAAG,SAASA,SAASA,CAAEC,KAAK,EAAG;EAC7C,MAAMC,QAAQ,GAAG,IAAIC,qBAAc,CAAE,UAAU,EAAE,IAAK,CAAC;;EAEvD;EACAD,QAAQ,CAACE,QAAQ,CAAE,IAAIC,mBAAY,CAAE,OAAO,EAAEJ,KAAK,CAACK,QAAQ,CAAC,CAAE,CAAE,CAAC;EAClEJ,QAAQ,CAACE,QAAQ,CAAE,IAAIC,mBAAY,CAAE,aAAa,EAAEJ,KAAK,CAACM,cAAc,CAAC,CAAE,CAAE,CAAC;;EAE9E;EACAL,QAAQ,CAACE,QAAQ,CAAE,IAAII,4BAAqB,CAAE,WAAW,EAAEP,KAAK,CAACQ,UAAU,CAAC,CAAE,CAAE,CAAC;EACjFP,QAAQ,CAACE,QAAQ,CAAE,IAAII,4BAAqB,CAAE,UAAU,EAAE,IAAAE,sBAAa,EAAET,KAAK,CAACU,WAAW,CAAC,CAAE,CAAE,CAAE,CAAC;EAClGT,QAAQ,CAACE,QAAQ,CAAE,IAAII,4BAAqB,CAAE,MAAM,EAAEP,KAAK,CAACW,OAAO,CAAC,CAAE,CAAE,CAAC;EACzEV,QAAQ,CAACE,QAAQ,CAAE,IAAII,4BAAqB,CAAE,YAAY,EAAEP,KAAK,CAACY,aAAa,CAAC,CAAE,CAAE,CAAC;EACrFX,QAAQ,CAACE,QAAQ,CAAE,IAAII,4BAAqB,CAAE,WAAW,EAAEP,KAAK,CAACa,YAAY,CAAC,CAAE,CAAE,CAAC;EACnFZ,QAAQ,CAACE,QAAQ,CAAE,IAAII,4BAAqB,CAAE,QAAQ,EAAEP,KAAK,CAACc,SAAS,CAAC,CAAE,CAAE,CAAC;EAE7E,OAAOb,QAAQ;AAChB,CAAC;AAAC,IAAAc,QAAA,GAAAC,OAAA,CAAAlB,OAAA,GAEaC,SAAS","ignoreList":[]}

package/build/parsedPaper/research/TreeResearcher.js

@@ -0,0 +1,136 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _lodash = require("lodash");
+/**
+ * This contains all possible, default researches
+ * and logic to apply these researches to a formatted text,
+ * represented as a tree structure.
+ *
+ * @memberOf module:parsedPaper/research
+ */
+class TreeResearcher {
+  /**
+   * Makes a new TreeResearcher.
+   */
+  constructor() {
+    this._researches = {};
+    this._data = {};
+  }
+
+  /**
+   * Adds or overwrites a research to the list of available researches.
+   *
+   * **Note**: When a research is already known under the given name,
+   * the previous research with this name gets overwritten!
+   *
+   * @param {string} name       The ID to which to map the research to.
+   * @param {Research} research The research to add.
+   *
+   * @returns {void}
+   */
+  addResearch(name, research) {
+    this._researches[name] = research;
+  }
+
+  /**
+   * Returns all available researches.
+   *
+   * @returns {Object} An object containing all available researches.
+   */
+  getResearches() {
+    return this._researches;
+  }
+
+  /**
+   * Returns whether a research is known under this name.
+   *
+   * @param {string} name The name to get the research from.
+   *
+   * @returns {boolean} If a research is known under this name.
+   */
+  hasResearch(name) {
+    return (0, _lodash.has)(this._researches, name);
+  }
+
+  /**
+   * Gets the research with the given name.
+   * If a research is not known under this name, false is returned instead.
+   *
+   * @throws {Error} When a research is not known under the given name.
+   *
+   * @param {string} name The name of the research to get.
+   *
+   * @returns {Research} The research stored under the given name.
+   */
+  getResearch(name) {
+    if (this.hasResearch(name)) {
+      return this._researches[name];
+    }
+    throw new Error(`'${name}' research does not exist.`);
+  }
+
+  /**
+   * Applies the research with the given name to the node and its descendants.
+   *
+   * @param {string} name The name of the research to apply to the node.
+   * @param {module:parsedPaper/structure.Node} node The node to compute the research of.
+   * @param {module:parsedPaper/structure.StructuredNode} metadata The node that holds the paper metadata.
+   * @param {boolean} [bustCache=false] If we should force the results, as cached on each node, to be recomputed.
+   *
+   * @returns {Promise<*>} A promising research result.
+   */
+  async doResearch(name, node, metadata, bustCache = false) {
+    const research = this.getResearch(name);
+    let researchResult = Promise.resolve();
+    if (research.isLeafNode(node)) {
+      /*
+        Compute research results for this node, or use the cached results when available.
+        Always compute it when we need to bust the cache.
+       */
+      if (!node.hasResearchResult(name) || bustCache) {
+        node.setResearchResult(name, await research.calculateFor(node, metadata));
+      }
+      researchResult = node.getResearchResult(name);
+    } else {
+      const children = node.children;
+
+      // Heading and paragraph nodes do not have children.
+      if (children) {
+        const resultsForChildren = await Promise.all(children.map(child => {
+          return this.doResearch(name, child, metadata);
+        }));
+        researchResult = research.mergeChildrenResults(resultsForChildren);
+      }
+    }
+    return researchResult;
+  }
+
+  /**
+   * Add research data to the researcher by the research name.
+   *
+   * @param {string} researchName The identifier of the research.
+   * @param {Object} data         The data object.
+   *
+   * @returns {void}.
+   */
+  addResearchData(researchName, data) {
+    this._data[researchName] = data;
+  }
+
+  /**
+   * Return the research data from a research data provider by research name.
+   *
+   * @param {string} researchName The identifier of the research.
+   *
+   * @returns {Object|boolean} The data provided by the provider, false if the data do not exist
+   */
+  getData(researchName) {
+    return (0, _lodash.get)(this._data, researchName, false);
+  }
+}
+var _default = exports.default = TreeResearcher;
+//# sourceMappingURL=TreeResearcher.js.map

package/build/parsedPaper/research/TreeResearcher.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"TreeResearcher.js","names":["_lodash","require","TreeResearcher","constructor","_researches","_data","addResearch","name","research","getResearches","hasResearch","has","getResearch","Error","doResearch","node","metadata","bustCache","researchResult","Promise","resolve","isLeafNode","hasResearchResult","setResearchResult","calculateFor","getResearchResult","children","resultsForChildren","all","map","child","mergeChildrenResults","addResearchData","researchName","data","getData","get","_default","exports","default"],"sources":["../../../src/parsedPaper/research/TreeResearcher.js"],"sourcesContent":["import { get, has } from \"lodash\";\n\n/**\n * This contains all possible, default researches\n * and logic to apply these researches to a formatted text,\n * represented as a tree structure.\n *\n * @memberOf module:parsedPaper/research\n */\nclass TreeResearcher {\n\t/**\n\t * Makes a new TreeResearcher.\n\t */\n\tconstructor() {\n\t\tthis._researches = {};\n\t\tthis._data = {};\n\t}\n\n\t/**\n\t * Adds or overwrites a research to the list of available researches.\n\t *\n\t * **Note**: When a research is already known under the given name,\n\t * the previous research with this name gets overwritten!\n\t *\n\t * @param {string} name       The ID to which to map the research to.\n\t * @param {Research} research The research to add.\n\t *\n\t * @returns {void}\n\t */\n\taddResearch( name, research ) {\n\t\tthis._researches[ name ] = research;\n\t}\n\n\t/**\n\t * Returns all available researches.\n\t *\n\t * @returns {Object} An object containing all available researches.\n\t */\n\tgetResearches() {\n\t\treturn this._researches;\n\t}\n\n\t/**\n\t * Returns whether a research is known under this name.\n\t *\n\t * @param {string} name The name to get the research from.\n\t *\n\t * @returns {boolean} If a research is known under this name.\n\t */\n\thasResearch( name ) {\n\t\treturn has( this._researches, name );\n\t}\n\n\t/**\n\t * Gets the research with the given name.\n\t * If a research is not known under this name, false is returned instead.\n\t *\n\t * @throws {Error} When a research is not known under the given name.\n\t *\n\t * @param {string} name The name of the research to get.\n\t *\n\t * @returns {Research} The research stored under the given name.\n\t */\n\tgetResearch( name ) {\n\t\tif ( this.hasResearch( name ) ) {\n\t\t\treturn this._researches[ name ];\n\t\t}\n\t\tthrow new Error( `'${name}' research does not exist.` );\n\t}\n\n\t/**\n\t * Applies the research with the given name to the node and its descendants.\n\t *\n\t * @param {string} name The name of the research to apply to the node.\n\t * @param {module:parsedPaper/structure.Node} node The node to compute the research of.\n\t * @param {module:parsedPaper/structure.StructuredNode} metadata The node that holds the paper metadata.\n\t * @param {boolean} [bustCache=false] If we should force the results, as cached on each node, to be recomputed.\n\t *\n\t * @returns {Promise<*>} A promising research result.\n\t */\n\tasync doResearch( name, node, metadata, bustCache = false ) {\n\t\tconst research = this.getResearch( name );\n\t\tlet researchResult = Promise.resolve();\n\n\t\tif ( research.isLeafNode( node ) ) {\n\t\t\t/*\n\t\t\t  Compute research results for this node, or use the cached results when available.\n\t\t\t  Always compute it when we need to bust the cache.\n\t\t\t */\n\t\t\tif ( ! node.hasResearchResult( name ) || bustCache ) {\n\t\t\t\tnode.setResearchResult( name, await research.calculateFor( node, metadata ) );\n\t\t\t}\n\t\t\tresearchResult = node.getResearchResult( name );\n\t\t} else {\n\t\t\tconst children = node.children;\n\n\t\t\t// Heading and paragraph nodes do not have children.\n\t\t\tif ( children ) {\n\t\t\t\tconst resultsForChildren = await Promise.all( children.map( ( child ) => {\n\t\t\t\t\treturn this.doResearch( name, child, metadata );\n\t\t\t\t} ) );\n\n\t\t\t\tresearchResult = research.mergeChildrenResults( resultsForChildren );\n\t\t\t}\n\t\t}\n\n\t\treturn researchResult;\n\t}\n\n\t/**\n\t * Add research data to the researcher by the research name.\n\t *\n\t * @param {string} researchName The identifier of the research.\n\t * @param {Object} data         The data object.\n\t *\n\t * @returns {void}.\n\t */\n\taddResearchData( researchName, data ) {\n\t\tthis._data[ researchName ] = data;\n\t}\n\n\t/**\n\t * Return the research data from a research data provider by research name.\n\t *\n\t * @param {string} researchName The identifier of the research.\n\t *\n\t * @returns {Object|boolean} The data provided by the provider, false if the data do not exist\n\t */\n\tgetData( researchName ) {\n\t\treturn get( this._data, researchName, false );\n\t}\n}\n\nexport default TreeResearcher;\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,cAAc,CAAC;EACpB;AACD;AACA;EACCC,WAAWA,CAAA,EAAG;IACb,IAAI,CAACC,WAAW,GAAG,CAAC,CAAC;IACrB,IAAI,CAACC,KAAK,GAAG,CAAC,CAAC;EAChB;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACCC,WAAWA,CAAEC,IAAI,EAAEC,QAAQ,EAAG;IAC7B,IAAI,CAACJ,WAAW,CAAEG,IAAI,CAAE,GAAGC,QAAQ;EACpC;;EAEA;AACD;AACA;AACA;AACA;EACCC,aAAaA,CAAA,EAAG;IACf,OAAO,IAAI,CAACL,WAAW;EACxB;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;EACCM,WAAWA,CAAEH,IAAI,EAAG;IACnB,OAAO,IAAAI,WAAG,EAAE,IAAI,CAACP,WAAW,EAAEG,IAAK,CAAC;EACrC;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACCK,WAAWA,CAAEL,IAAI,EAAG;IACnB,IAAK,IAAI,CAACG,WAAW,CAAEH,IAAK,CAAC,EAAG;MAC/B,OAAO,IAAI,CAACH,WAAW,CAAEG,IAAI,CAAE;IAChC;IACA,MAAM,IAAIM,KAAK,CAAE,IAAIN,IAAI,4BAA6B,CAAC;EACxD;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACC,MAAMO,UAAUA,CAAEP,IAAI,EAAEQ,IAAI,EAAEC,QAAQ,EAAEC,SAAS,GAAG,KAAK,EAAG;IAC3D,MAAMT,QAAQ,GAAG,IAAI,CAACI,WAAW,CAAEL,IAAK,CAAC;IACzC,IAAIW,cAAc,GAAGC,OAAO,CAACC,OAAO,CAAC,CAAC;IAEtC,IAAKZ,QAAQ,CAACa,UAAU,CAAEN,IAAK,CAAC,EAAG;MAClC;AACH;AACA;AACA;MACG,IAAK,CAAEA,IAAI,CAACO,iBAAiB,CAAEf,IAAK,CAAC,IAAIU,SAAS,EAAG;QACpDF,IAAI,CAACQ,iBAAiB,CAAEhB,IAAI,EAAE,MAAMC,QAAQ,CAACgB,YAAY,CAAET,IAAI,EAAEC,QAAS,CAAE,CAAC;MAC9E;MACAE,cAAc,GAAGH,IAAI,CAACU,iBAAiB,CAAElB,IAAK,CAAC;IAChD,CAAC,MAAM;MACN,MAAMmB,QAAQ,GAAGX,IAAI,CAACW,QAAQ;;MAE9B;MACA,IAAKA,QAAQ,EAAG;QACf,MAAMC,kBAAkB,GAAG,MAAMR,OAAO,CAACS,GAAG,CAAEF,QAAQ,CAACG,GAAG,CAAIC,KAAK,IAAM;UACxE,OAAO,IAAI,CAAChB,UAAU,CAAEP,IAAI,EAAEuB,KAAK,EAAEd,QAAS,CAAC;QAChD,CAAE,CAAE,CAAC;QAELE,cAAc,GAAGV,QAAQ,CAACuB,oBAAoB,CAAEJ,kBAAmB,CAAC;MACrE;IACD;IAEA,OAAOT,cAAc;EACtB;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;AACA;EACCc,eAAeA,CAAEC,YAAY,EAAEC,IAAI,EAAG;IACrC,IAAI,CAAC7B,KAAK,CAAE4B,YAAY,CAAE,GAAGC,IAAI;EAClC;;EAEA;AACD;AACA;AACA;AACA;AACA;AACA;EACCC,OAAOA,CAAEF,YAAY,EAAG;IACvB,OAAO,IAAAG,WAAG,EAAE,IAAI,CAAC/B,KAAK,EAAE4B,YAAY,EAAE,KAAM,CAAC;EAC9C;AACD;AAAC,IAAAI,QAAA,GAAAC,OAAA,CAAAC,OAAA,GAEcrC,cAAc","ignoreList":[]}

package/build/parsedPaper/research/index.js

@@ -0,0 +1,14 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+Object.defineProperty(exports, "TreeResearcher", {
+  enumerable: true,
+  get: function () {
+    return _TreeResearcher.default;
+  }
+});
+var _TreeResearcher = _interopRequireDefault(require("./TreeResearcher"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+//# sourceMappingURL=index.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","names":["_TreeResearcher","_interopRequireDefault","require","e","__esModule","default"],"sources":["../../../src/parsedPaper/research/index.js"],"sourcesContent":["import TreeResearcher from \"./TreeResearcher\";\n\n/**\n * Module for applying researches to text, represented as a tree structure.\n *\n * @see module:parsedPaper/structure\n *\n * @module parsedPaper/research\n */\n\nexport {\n\tTreeResearcher,\n};\n"],"mappings":";;;;;;;;;;;AAAA,IAAAA,eAAA,GAAAC,sBAAA,CAAAC,OAAA;AAA8C,SAAAD,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA","ignoreList":[]}

package/build/parsedPaper/research/researches/Headings.js

@@ -0,0 +1,26 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _tree = require("../../structure/tree");
+var _Research = _interopRequireDefault(require("./Research"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * A research giving back the headings located in a text.
+ */
+class Headings extends _Research.default {
+  /**
+   * Calculates the result of the research for the given Node.
+   *
+   * @param {module:parsedPaper/structure.Node} node The node to do the research on.
+   *
+   * @returns {Promise<module:parsedPaper/structure.Heading[]|[]>} The result of the research.
+   */
+  calculateFor(node) {
+    return node instanceof _tree.Heading ? Promise.resolve([node]) : Promise.resolve([]);
+  }
+}
+var _default = exports.default = Headings;
+//# sourceMappingURL=Headings.js.map

package/build/parsedPaper/research/researches/Headings.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"Headings.js","names":["_tree","require","_Research","_interopRequireDefault","e","__esModule","default","Headings","Research","calculateFor","node","Heading","Promise","resolve","_default","exports"],"sources":["../../../../src/parsedPaper/research/researches/Headings.js"],"sourcesContent":["import { Heading } from \"../../structure/tree\";\nimport Research from \"./Research\";\n\n/**\n * A research giving back the headings located in a text.\n */\nclass Headings extends Research {\n\t/**\n\t * Calculates the result of the research for the given Node.\n\t *\n\t * @param {module:parsedPaper/structure.Node} node The node to do the research on.\n\t *\n\t * @returns {Promise<module:parsedPaper/structure.Heading[]|[]>} The result of the research.\n\t */\n\tcalculateFor( node ) {\n\t\treturn node instanceof Heading ? Promise.resolve( [ node ] ) : Promise.resolve( [] );\n\t}\n}\n\nexport default Headings;\n"],"mappings":";;;;;;AAAA,IAAAA,KAAA,GAAAC,OAAA;AACA,IAAAC,SAAA,GAAAC,sBAAA,CAAAF,OAAA;AAAkC,SAAAE,uBAAAC,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAElC;AACA;AACA;AACA,MAAMG,QAAQ,SAASC,iBAAQ,CAAC;EAC/B;AACD;AACA;AACA;AACA;AACA;AACA;EACCC,YAAYA,CAAEC,IAAI,EAAG;IACpB,OAAOA,IAAI,YAAYC,aAAO,GAAGC,OAAO,CAACC,OAAO,CAAE,CAAEH,IAAI,CAAG,CAAC,GAAGE,OAAO,CAACC,OAAO,CAAE,EAAG,CAAC;EACrF;AACD;AAAC,IAAAC,QAAA,GAAAC,OAAA,CAAAT,OAAA,GAEcC,QAAQ","ignoreList":[]}