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

package/build/languageProcessing/helpers/html/getSubheadings.js

@@ -0,0 +1,82 @@
+/**
+ * Gets all subheadings from the text and returns these in an array.
+ *
+ * @param {string} text The text to return the headings from.
+ *
+ * @returns {Array<string[]>} Matches of subheadings in the text, first key is everything including tags,
+ *                            second is the heading level, third is the content of the subheading.
+ */
+function getSubheadings(text) {
+  const subheadings = [];
+  const regex = /<h([1-6])(?:[^>]+)?>(.*?)<\/h\1>/ig;
+  let match;
+  while ((match = regex.exec(text)) !== null) {
+    subheadings.push(match);
+  }
+  return subheadings;
+}
+
+/**
+ * Gets all the level 2 and 3 subheadings from the text and returns these in an array.
+ *
+ * @param {string} text The text to return the headings from.
+ *
+ * @returns {Array<string[]>} Matches of subheadings in the text, first key is everything including tags,
+ *                            second is the heading level, third is the content of the subheading.
+ */
+function getSubheadingsTopLevel(text) {
+  const subheadings = [];
+  const regex = /<h([2-3])(?:[^>]+)?>(.*?)<\/h\1>/ig;
+  let match;
+  while ((match = regex.exec(text)) !== null) {
+    subheadings.push(match);
+  }
+  return subheadings;
+}
+
+/**
+ * Gets the content of subheadings in the text.
+ *
+ * @param {string} text The text to get the subheading contents from.
+ *
+ * @returns {string[]} A list of all the subheadings with their content.
+ */
+function getSubheadingContents(text) {
+  const subheadings = getSubheadings(text);
+  return subheadings.map(subheading => subheading[0]);
+}
+
+/**
+ * Gets the content of subheadings h2 and h3 in the text.
+ *
+ * @param {string} text The text to get the subheading contents from.
+ *
+ * @returns {string[]} A list of all the subheadings with their content.
+ */
+function getSubheadingContentsTopLevel(text) {
+  const subheadings = getSubheadingsTopLevel(text);
+
+  // Only return the entire string matched, not the rest of the outputs of the regex.exec function.
+  return subheadings.map(subheading => subheading[0]);
+}
+
+/**
+ * Removes all level 2 and 3 subheadings from the text.
+ *
+ * @param {string} text The text to remove the headings from.
+ *
+ * @returns {string} The text with removed subheadings.
+ */
+function removeSubheadingsTopLevel(text) {
+  const regex = /<h([2-3])(?:[^>]+)?>(.*?)<\/h\1>/ig;
+  return text.replace(regex, "");
+}
+export { getSubheadings, getSubheadingsTopLevel, getSubheadingContents, getSubheadingContentsTopLevel, removeSubheadingsTopLevel };
+export default {
+  getSubheadings: getSubheadings,
+  getSubheadingsTopLevel: getSubheadingsTopLevel,
+  getSubheadingContents: getSubheadingContents,
+  getSubheadingContentsTopLevel: getSubheadingContentsTopLevel,
+  removeSubheadingsTopLevel: removeSubheadingsTopLevel
+};
+//# sourceMappingURL=getSubheadings.js.map

package/build/languageProcessing/helpers/html/getSubheadings.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getSubheadings.js","names":["getSubheadings","text","subheadings","regex","match","exec","push","getSubheadingsTopLevel","getSubheadingContents","map","subheading","getSubheadingContentsTopLevel","removeSubheadingsTopLevel","replace"],"sources":["../../../../src/languageProcessing/helpers/html/getSubheadings.js"],"sourcesContent":["/**\n * Gets all subheadings from the text and returns these in an array.\n *\n * @param {string} text The text to return the headings from.\n *\n * @returns {Array<string[]>} Matches of subheadings in the text, first key is everything including tags,\n *                            second is the heading level, third is the content of the subheading.\n */\nfunction getSubheadings( text ) {\n\tconst subheadings = [];\n\tconst regex = /<h([1-6])(?:[^>]+)?>(.*?)<\\/h\\1>/ig;\n\tlet match;\n\n\twhile ( ( match = regex.exec( text ) ) !== null ) {\n\t\tsubheadings.push( match );\n\t}\n\n\treturn subheadings;\n}\n\n/**\n * Gets all the level 2 and 3 subheadings from the text and returns these in an array.\n *\n * @param {string} text The text to return the headings from.\n *\n * @returns {Array<string[]>} Matches of subheadings in the text, first key is everything including tags,\n *                            second is the heading level, third is the content of the subheading.\n */\nfunction getSubheadingsTopLevel( text ) {\n\tconst subheadings = [];\n\tconst regex = /<h([2-3])(?:[^>]+)?>(.*?)<\\/h\\1>/ig;\n\tlet match;\n\n\twhile ( ( match = regex.exec( text ) ) !== null ) {\n\t\tsubheadings.push( match );\n\t}\n\n\treturn subheadings;\n}\n\n/**\n * Gets the content of subheadings in the text.\n *\n * @param {string} text The text to get the subheading contents from.\n *\n * @returns {string[]} A list of all the subheadings with their content.\n */\nfunction getSubheadingContents( text ) {\n\tconst subheadings = getSubheadings( text );\n\n\treturn subheadings.map( subheading => subheading[ 0 ] );\n}\n\n/**\n * Gets the content of subheadings h2 and h3 in the text.\n *\n * @param {string} text The text to get the subheading contents from.\n *\n * @returns {string[]} A list of all the subheadings with their content.\n */\nfunction getSubheadingContentsTopLevel( text ) {\n\tconst subheadings = getSubheadingsTopLevel( text );\n\n\t// Only return the entire string matched, not the rest of the outputs of the regex.exec function.\n\treturn subheadings.map( subheading => subheading[ 0 ] );\n}\n\n/**\n * Removes all level 2 and 3 subheadings from the text.\n *\n * @param {string} text The text to remove the headings from.\n *\n * @returns {string} The text with removed subheadings.\n */\nfunction removeSubheadingsTopLevel( text ) {\n\tconst regex = /<h([2-3])(?:[^>]+)?>(.*?)<\\/h\\1>/ig;\n\n\treturn text.replace( regex, \"\" );\n}\n\nexport {\n\tgetSubheadings,\n\tgetSubheadingsTopLevel,\n\tgetSubheadingContents,\n\tgetSubheadingContentsTopLevel,\n\tremoveSubheadingsTopLevel,\n};\n\nexport default {\n\tgetSubheadings: getSubheadings,\n\tgetSubheadingsTopLevel: getSubheadingsTopLevel,\n\tgetSubheadingContents: getSubheadingContents,\n\tgetSubheadingContentsTopLevel: getSubheadingContentsTopLevel,\n\tremoveSubheadingsTopLevel: removeSubheadingsTopLevel,\n};\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASA,cAAcA,CAAEC,IAAI,EAAG;EAC/B,MAAMC,WAAW,GAAG,EAAE;EACtB,MAAMC,KAAK,GAAG,oCAAoC;EAClD,IAAIC,KAAK;EAET,OAAQ,CAAEA,KAAK,GAAGD,KAAK,CAACE,IAAI,CAAEJ,IAAK,CAAC,MAAO,IAAI,EAAG;IACjDC,WAAW,CAACI,IAAI,CAAEF,KAAM,CAAC;EAC1B;EAEA,OAAOF,WAAW;AACnB;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASK,sBAAsBA,CAAEN,IAAI,EAAG;EACvC,MAAMC,WAAW,GAAG,EAAE;EACtB,MAAMC,KAAK,GAAG,oCAAoC;EAClD,IAAIC,KAAK;EAET,OAAQ,CAAEA,KAAK,GAAGD,KAAK,CAACE,IAAI,CAAEJ,IAAK,CAAC,MAAO,IAAI,EAAG;IACjDC,WAAW,CAACI,IAAI,CAAEF,KAAM,CAAC;EAC1B;EAEA,OAAOF,WAAW;AACnB;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASM,qBAAqBA,CAAEP,IAAI,EAAG;EACtC,MAAMC,WAAW,GAAGF,cAAc,CAAEC,IAAK,CAAC;EAE1C,OAAOC,WAAW,CAACO,GAAG,CAAEC,UAAU,IAAIA,UAAU,CAAE,CAAC,CAAG,CAAC;AACxD;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,6BAA6BA,CAAEV,IAAI,EAAG;EAC9C,MAAMC,WAAW,GAAGK,sBAAsB,CAAEN,IAAK,CAAC;;EAElD;EACA,OAAOC,WAAW,CAACO,GAAG,CAAEC,UAAU,IAAIA,UAAU,CAAE,CAAC,CAAG,CAAC;AACxD;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASE,yBAAyBA,CAAEX,IAAI,EAAG;EAC1C,MAAME,KAAK,GAAG,oCAAoC;EAElD,OAAOF,IAAI,CAACY,OAAO,CAAEV,KAAK,EAAE,EAAG,CAAC;AACjC;AAEA,SACCH,cAAc,EACdO,sBAAsB,EACtBC,qBAAqB,EACrBG,6BAA6B,EAC7BC,yBAAyB;AAG1B,eAAe;EACdZ,cAAc,EAAEA,cAAc;EAC9BO,sBAAsB,EAAEA,sBAAsB;EAC9CC,qBAAqB,EAAEA,qBAAqB;EAC5CG,6BAA6B,EAAEA,6BAA6B;EAC5DC,yBAAyB,EAAEA;AAC5B,CAAC","ignoreList":[]}

package/build/languageProcessing/helpers/html/html.js

@@ -0,0 +1,144 @@
+const blockElements = ["address", "article", "aside", "blockquote", "canvas", "dd", "div", "dl", "fieldset", "figcaption", "figure", "footer", "form", "h1", "h2", "h3", "h4", "h5", "h6", "header", "hgroup", "hr", "li", "main", "nav", "noscript", "ol", "output", "p", "pre", "section", "table", "tfoot", "ul", "video"];
+const inlineElements = ["b", "big", "i", "small", "tt", "abbr", "acronym", "cite", "code", "dfn", "em", "kbd", "strong", "samp", "time", "var", "a", "bdo", "br", "img", "map", "object", "q", "script", "span", "sub", "sup", "button", "input", "label", "select", "textarea"];
+const blockElementsRegex = new RegExp("^(" + blockElements.join("|") + ")$", "i");
+const inlineElementsRegex = new RegExp("^(" + inlineElements.join("|") + ")$", "i");
+const blockElementStartRegex = new RegExp("^<(" + blockElements.join("|") + ")[^>]*?>$", "i");
+const blockElementEndRegex = new RegExp("^</(" + blockElements.join("|") + ")[^>]*?>$", "i");
+const inlineElementStartRegex = new RegExp("^<(" + inlineElements.join("|") + ")[^>]*>$", "i");
+const inlineElementEndRegex = new RegExp("^</(" + inlineElements.join("|") + ")[^>]*>$", "i");
+const otherElementStartRegex = /^<([^>\s/]+)[^>]*>$/;
+const otherElementEndRegex = /^<\/([^>\s]+)[^>]*>$/;
+const contentRegex = /^[^<]+$/;
+const greaterThanContentRegex = /^<[^><]*$/;
+const commentRegex = /<!--(.|[\r\n])*?-->/g;
+import { forEach, memoize } from "lodash";
+import core from "tokenizer2/core";
+let tokens = [];
+let htmlBlockTokenizer;
+
+/**
+ * Creates a tokenizer to tokenize HTML into blocks.
+ *
+ * @returns {void}
+ */
+function createTokenizer() {
+  tokens = [];
+  htmlBlockTokenizer = core(function (token) {
+    tokens.push(token);
+  });
+  htmlBlockTokenizer.addRule(contentRegex, "content");
+  htmlBlockTokenizer.addRule(greaterThanContentRegex, "greater-than-sign-content");
+  htmlBlockTokenizer.addRule(blockElementStartRegex, "block-start");
+  htmlBlockTokenizer.addRule(blockElementEndRegex, "block-end");
+  htmlBlockTokenizer.addRule(inlineElementStartRegex, "inline-start");
+  htmlBlockTokenizer.addRule(inlineElementEndRegex, "inline-end");
+  htmlBlockTokenizer.addRule(otherElementStartRegex, "other-element-start");
+  htmlBlockTokenizer.addRule(otherElementEndRegex, "other-element-end");
+}
+
+/**
+ * Returns whether or not the given element name is a block element.
+ *
+ * @param {string} htmlElementName The name of the HTML element.
+ * @returns {boolean} Whether or not it is a block element.
+ */
+function isBlockElement(htmlElementName) {
+  return blockElementsRegex.test(htmlElementName);
+}
+
+/**
+ * Returns whether or not the given element name is an inline element.
+ *
+ * @param {string} htmlElementName The name of the HTML element.
+ * @returns {boolean} Whether or not it is an inline element.
+ */
+function isInlineElement(htmlElementName) {
+  return inlineElementsRegex.test(htmlElementName);
+}
+
+/**
+ * Splits a text into blocks based on HTML block elements.
+ *
+ * @param {string} text The text to split.
+ * @returns {Array} A list of blocks based on HTML block elements.
+ */
+function getBlocks(text) {
+  const blocks = [];
+  let depth = 0,
+    blockStartTag = "",
+    currentBlock = "",
+    blockEndTag = "";
+
+  // Remove all comments because it is very hard to tokenize them.
+  text = text.replace(commentRegex, "");
+  createTokenizer();
+  htmlBlockTokenizer.onText(text);
+  htmlBlockTokenizer.end();
+  forEach(tokens, function (token, i) {
+    const nextToken = tokens[i + 1];
+    switch (token.type) {
+      case "content":
+      case "greater-than-sign-content":
+      case "inline-start":
+      case "inline-end":
+      case "other-tag":
+      case "other-element-start":
+      case "other-element-end":
+      case "greater than sign":
+        if (!nextToken || depth === 0 && (nextToken.type === "block-start" || nextToken.type === "block-end")) {
+          currentBlock += token.src;
+          blocks.push(currentBlock);
+          blockStartTag = "";
+          currentBlock = "";
+          blockEndTag = "";
+        } else {
+          currentBlock += token.src;
+        }
+        break;
+      case "block-start":
+        if (depth !== 0) {
+          if (currentBlock.trim() !== "") {
+            blocks.push(currentBlock);
+          }
+          currentBlock = "";
+          blockEndTag = "";
+        }
+        depth++;
+        blockStartTag = token.src;
+        break;
+      case "block-end":
+        depth--;
+        blockEndTag = token.src;
+
+        /*
+         * We try to match the most deep blocks so discard any other blocks that have been started but not
+         * finished.
+         */
+        if ("" !== blockStartTag && "" !== blockEndTag) {
+          blocks.push(blockStartTag + currentBlock + blockEndTag);
+        } else if ("" !== currentBlock.trim()) {
+          blocks.push(currentBlock);
+        }
+        blockStartTag = "";
+        currentBlock = "";
+        blockEndTag = "";
+        break;
+    }
+
+    // Handles HTML with too many closing tags.
+    if (depth < 0) {
+      depth = 0;
+    }
+  });
+  return blocks;
+}
+const memoizedGetBlocks = memoize(getBlocks);
+export { blockElements, inlineElements, isBlockElement, isInlineElement, memoizedGetBlocks as getBlocks };
+export default {
+  blockElements: blockElements,
+  inlineElements: inlineElements,
+  isBlockElement: isBlockElement,
+  isInlineElement: isInlineElement,
+  getBlocks: memoizedGetBlocks
+};
+//# sourceMappingURL=html.js.map

package/build/languageProcessing/helpers/html/html.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"html.js","names":["blockElements","inlineElements","blockElementsRegex","RegExp","join","inlineElementsRegex","blockElementStartRegex","blockElementEndRegex","inlineElementStartRegex","inlineElementEndRegex","otherElementStartRegex","otherElementEndRegex","contentRegex","greaterThanContentRegex","commentRegex","forEach","memoize","core","tokens","htmlBlockTokenizer","createTokenizer","token","push","addRule","isBlockElement","htmlElementName","test","isInlineElement","getBlocks","text","blocks","depth","blockStartTag","currentBlock","blockEndTag","replace","onText","end","i","nextToken","type","src","trim","memoizedGetBlocks"],"sources":["../../../../src/languageProcessing/helpers/html/html.js"],"sourcesContent":["const blockElements = [ \"address\", \"article\", \"aside\", \"blockquote\", \"canvas\", \"dd\", \"div\", \"dl\", \"fieldset\", \"figcaption\",\n\t\"figure\", \"footer\", \"form\", \"h1\", \"h2\", \"h3\", \"h4\", \"h5\", \"h6\", \"header\", \"hgroup\", \"hr\", \"li\", \"main\", \"nav\",\n\t\"noscript\", \"ol\", \"output\", \"p\", \"pre\", \"section\", \"table\", \"tfoot\", \"ul\", \"video\" ];\nconst inlineElements = [ \"b\", \"big\", \"i\", \"small\", \"tt\", \"abbr\", \"acronym\", \"cite\", \"code\", \"dfn\", \"em\", \"kbd\", \"strong\",\n\t\"samp\", \"time\", \"var\", \"a\", \"bdo\", \"br\", \"img\", \"map\", \"object\", \"q\", \"script\", \"span\", \"sub\", \"sup\", \"button\",\n\t\"input\", \"label\", \"select\", \"textarea\" ];\n\nconst blockElementsRegex = new RegExp( \"^(\" + blockElements.join( \"|\" ) + \")$\", \"i\" );\nconst inlineElementsRegex = new RegExp( \"^(\" + inlineElements.join( \"|\" ) + \")$\", \"i\" );\n\nconst blockElementStartRegex = new RegExp( \"^<(\" + blockElements.join( \"|\" ) + \")[^>]*?>$\", \"i\" );\nconst blockElementEndRegex = new RegExp( \"^</(\" + blockElements.join( \"|\" ) + \")[^>]*?>$\", \"i\" );\n\nconst inlineElementStartRegex = new RegExp( \"^<(\" + inlineElements.join( \"|\" ) + \")[^>]*>$\", \"i\" );\nconst inlineElementEndRegex = new RegExp( \"^</(\" + inlineElements.join( \"|\" ) + \")[^>]*>$\", \"i\" );\n\nconst otherElementStartRegex = /^<([^>\\s/]+)[^>]*>$/;\nconst otherElementEndRegex = /^<\\/([^>\\s]+)[^>]*>$/;\n\nconst contentRegex = /^[^<]+$/;\nconst greaterThanContentRegex = /^<[^><]*$/;\n\nconst commentRegex = /<!--(.|[\\r\\n])*?-->/g;\n\nimport { forEach, memoize } from \"lodash\";\nimport core from \"tokenizer2/core\";\n\nlet tokens = [];\nlet htmlBlockTokenizer;\n\n/**\n * Creates a tokenizer to tokenize HTML into blocks.\n *\n * @returns {void}\n */\nfunction createTokenizer() {\n\ttokens = [];\n\n\thtmlBlockTokenizer = core( function( token ) {\n\t\ttokens.push( token );\n\t} );\n\n\thtmlBlockTokenizer.addRule( contentRegex, \"content\" );\n\thtmlBlockTokenizer.addRule( greaterThanContentRegex, \"greater-than-sign-content\" );\n\n\thtmlBlockTokenizer.addRule( blockElementStartRegex, \"block-start\" );\n\thtmlBlockTokenizer.addRule( blockElementEndRegex, \"block-end\" );\n\thtmlBlockTokenizer.addRule( inlineElementStartRegex, \"inline-start\" );\n\thtmlBlockTokenizer.addRule( inlineElementEndRegex, \"inline-end\" );\n\n\thtmlBlockTokenizer.addRule( otherElementStartRegex, \"other-element-start\" );\n\thtmlBlockTokenizer.addRule( otherElementEndRegex, \"other-element-end\" );\n}\n\n/**\n * Returns whether or not the given element name is a block element.\n *\n * @param {string} htmlElementName The name of the HTML element.\n * @returns {boolean} Whether or not it is a block element.\n */\nfunction isBlockElement( htmlElementName ) {\n\treturn blockElementsRegex.test( htmlElementName );\n}\n\n/**\n * Returns whether or not the given element name is an inline element.\n *\n * @param {string} htmlElementName The name of the HTML element.\n * @returns {boolean} Whether or not it is an inline element.\n */\nfunction isInlineElement( htmlElementName ) {\n\treturn inlineElementsRegex.test( htmlElementName );\n}\n\n/**\n * Splits a text into blocks based on HTML block elements.\n *\n * @param {string} text The text to split.\n * @returns {Array} A list of blocks based on HTML block elements.\n */\nfunction getBlocks( text ) {\n\tconst blocks = [];\n\tlet depth = 0,\n\t\tblockStartTag = \"\",\n\t\tcurrentBlock = \"\",\n\t\tblockEndTag = \"\";\n\n\t// Remove all comments because it is very hard to tokenize them.\n\ttext = text.replace( commentRegex, \"\" );\n\n\tcreateTokenizer();\n\thtmlBlockTokenizer.onText( text );\n\thtmlBlockTokenizer.end();\n\n\tforEach( tokens, function( token, i ) {\n\t\tconst nextToken = tokens[ i + 1 ];\n\n\t\tswitch ( token.type ) {\n\t\t\tcase \"content\":\n\t\t\tcase \"greater-than-sign-content\":\n\t\t\tcase \"inline-start\":\n\t\t\tcase \"inline-end\":\n\t\t\tcase \"other-tag\":\n\t\t\tcase \"other-element-start\":\n\t\t\tcase \"other-element-end\":\n\t\t\tcase \"greater than sign\":\n\t\t\t\tif ( ! nextToken || ( depth === 0 && ( nextToken.type === \"block-start\" || nextToken.type === \"block-end\" ) ) ) {\n\t\t\t\t\tcurrentBlock += token.src;\n\n\t\t\t\t\tblocks.push( currentBlock );\n\t\t\t\t\tblockStartTag = \"\";\n\t\t\t\t\tcurrentBlock = \"\";\n\t\t\t\t\tblockEndTag = \"\";\n\t\t\t\t} else {\n\t\t\t\t\tcurrentBlock += token.src;\n\t\t\t\t}\n\t\t\t\tbreak;\n\n\t\t\tcase \"block-start\":\n\t\t\t\tif ( depth !== 0 ) {\n\t\t\t\t\tif ( currentBlock.trim() !== \"\" ) {\n\t\t\t\t\t\tblocks.push( currentBlock );\n\t\t\t\t\t}\n\t\t\t\t\tcurrentBlock = \"\";\n\t\t\t\t\tblockEndTag = \"\";\n\t\t\t\t}\n\n\t\t\t\tdepth++;\n\t\t\t\tblockStartTag = token.src;\n\t\t\t\tbreak;\n\n\t\t\tcase \"block-end\":\n\t\t\t\tdepth--;\n\t\t\t\tblockEndTag = token.src;\n\n\t\t\t\t/*\n\t\t\t\t * We try to match the most deep blocks so discard any other blocks that have been started but not\n\t\t\t\t * finished.\n\t\t\t\t */\n\t\t\t\tif ( \"\" !== blockStartTag && \"\" !== blockEndTag ) {\n\t\t\t\t\tblocks.push( blockStartTag + currentBlock + blockEndTag );\n\t\t\t\t} else if ( \"\" !== currentBlock.trim() ) {\n\t\t\t\t\tblocks.push( currentBlock );\n\t\t\t\t}\n\t\t\t\tblockStartTag = \"\";\n\t\t\t\tcurrentBlock = \"\";\n\t\t\t\tblockEndTag = \"\";\n\t\t\t\tbreak;\n\t\t}\n\n\t\t// Handles HTML with too many closing tags.\n\t\tif ( depth < 0 ) {\n\t\t\tdepth = 0;\n\t\t}\n\t} );\n\n\treturn blocks;\n}\n\nconst memoizedGetBlocks = memoize( getBlocks );\n\nexport {\n\tblockElements,\n\tinlineElements,\n\tisBlockElement,\n\tisInlineElement,\n\tmemoizedGetBlocks as getBlocks,\n};\n\nexport default {\n\tblockElements: blockElements,\n\tinlineElements: inlineElements,\n\tisBlockElement: isBlockElement,\n\tisInlineElement: isInlineElement,\n\tgetBlocks: memoizedGetBlocks,\n};\n"],"mappings":"AAAA,MAAMA,aAAa,GAAG,CAAE,SAAS,EAAE,SAAS,EAAE,OAAO,EAAE,YAAY,EAAE,QAAQ,EAAE,IAAI,EAAE,KAAK,EAAE,IAAI,EAAE,UAAU,EAAE,YAAY,EACzH,QAAQ,EAAE,QAAQ,EAAE,MAAM,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,IAAI,EAAE,QAAQ,EAAE,QAAQ,EAAE,IAAI,EAAE,IAAI,EAAE,MAAM,EAAE,KAAK,EAC7G,UAAU,EAAE,IAAI,EAAE,QAAQ,EAAE,GAAG,EAAE,KAAK,EAAE,SAAS,EAAE,OAAO,EAAE,OAAO,EAAE,IAAI,EAAE,OAAO,CAAE;AACrF,MAAMC,cAAc,GAAG,CAAE,GAAG,EAAE,KAAK,EAAE,GAAG,EAAE,OAAO,EAAE,IAAI,EAAE,MAAM,EAAE,SAAS,EAAE,MAAM,EAAE,MAAM,EAAE,KAAK,EAAE,IAAI,EAAE,KAAK,EAAE,QAAQ,EACvH,MAAM,EAAE,MAAM,EAAE,KAAK,EAAE,GAAG,EAAE,KAAK,EAAE,IAAI,EAAE,KAAK,EAAE,KAAK,EAAE,QAAQ,EAAE,GAAG,EAAE,QAAQ,EAAE,MAAM,EAAE,KAAK,EAAE,KAAK,EAAE,QAAQ,EAC9G,OAAO,EAAE,OAAO,EAAE,QAAQ,EAAE,UAAU,CAAE;AAEzC,MAAMC,kBAAkB,GAAG,IAAIC,MAAM,CAAE,IAAI,GAAGH,aAAa,CAACI,IAAI,CAAE,GAAI,CAAC,GAAG,IAAI,EAAE,GAAI,CAAC;AACrF,MAAMC,mBAAmB,GAAG,IAAIF,MAAM,CAAE,IAAI,GAAGF,cAAc,CAACG,IAAI,CAAE,GAAI,CAAC,GAAG,IAAI,EAAE,GAAI,CAAC;AAEvF,MAAME,sBAAsB,GAAG,IAAIH,MAAM,CAAE,KAAK,GAAGH,aAAa,CAACI,IAAI,CAAE,GAAI,CAAC,GAAG,WAAW,EAAE,GAAI,CAAC;AACjG,MAAMG,oBAAoB,GAAG,IAAIJ,MAAM,CAAE,MAAM,GAAGH,aAAa,CAACI,IAAI,CAAE,GAAI,CAAC,GAAG,WAAW,EAAE,GAAI,CAAC;AAEhG,MAAMI,uBAAuB,GAAG,IAAIL,MAAM,CAAE,KAAK,GAAGF,cAAc,CAACG,IAAI,CAAE,GAAI,CAAC,GAAG,UAAU,EAAE,GAAI,CAAC;AAClG,MAAMK,qBAAqB,GAAG,IAAIN,MAAM,CAAE,MAAM,GAAGF,cAAc,CAACG,IAAI,CAAE,GAAI,CAAC,GAAG,UAAU,EAAE,GAAI,CAAC;AAEjG,MAAMM,sBAAsB,GAAG,qBAAqB;AACpD,MAAMC,oBAAoB,GAAG,sBAAsB;AAEnD,MAAMC,YAAY,GAAG,SAAS;AAC9B,MAAMC,uBAAuB,GAAG,WAAW;AAE3C,MAAMC,YAAY,GAAG,sBAAsB;AAE3C,SAASC,OAAO,EAAEC,OAAO,QAAQ,QAAQ;AACzC,OAAOC,IAAI,MAAM,iBAAiB;AAElC,IAAIC,MAAM,GAAG,EAAE;AACf,IAAIC,kBAAkB;;AAEtB;AACA;AACA;AACA;AACA;AACA,SAASC,eAAeA,CAAA,EAAG;EAC1BF,MAAM,GAAG,EAAE;EAEXC,kBAAkB,GAAGF,IAAI,CAAE,UAAUI,KAAK,EAAG;IAC5CH,MAAM,CAACI,IAAI,CAAED,KAAM,CAAC;EACrB,CAAE,CAAC;EAEHF,kBAAkB,CAACI,OAAO,CAAEX,YAAY,EAAE,SAAU,CAAC;EACrDO,kBAAkB,CAACI,OAAO,CAAEV,uBAAuB,EAAE,2BAA4B,CAAC;EAElFM,kBAAkB,CAACI,OAAO,CAAEjB,sBAAsB,EAAE,aAAc,CAAC;EACnEa,kBAAkB,CAACI,OAAO,CAAEhB,oBAAoB,EAAE,WAAY,CAAC;EAC/DY,kBAAkB,CAACI,OAAO,CAAEf,uBAAuB,EAAE,cAAe,CAAC;EACrEW,kBAAkB,CAACI,OAAO,CAAEd,qBAAqB,EAAE,YAAa,CAAC;EAEjEU,kBAAkB,CAACI,OAAO,CAAEb,sBAAsB,EAAE,qBAAsB,CAAC;EAC3ES,kBAAkB,CAACI,OAAO,CAAEZ,oBAAoB,EAAE,mBAAoB,CAAC;AACxE;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA,SAASa,cAAcA,CAAEC,eAAe,EAAG;EAC1C,OAAOvB,kBAAkB,CAACwB,IAAI,CAAED,eAAgB,CAAC;AAClD;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA,SAASE,eAAeA,CAAEF,eAAe,EAAG;EAC3C,OAAOpB,mBAAmB,CAACqB,IAAI,CAAED,eAAgB,CAAC;AACnD;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA,SAASG,SAASA,CAAEC,IAAI,EAAG;EAC1B,MAAMC,MAAM,GAAG,EAAE;EACjB,IAAIC,KAAK,GAAG,CAAC;IACZC,aAAa,GAAG,EAAE;IAClBC,YAAY,GAAG,EAAE;IACjBC,WAAW,GAAG,EAAE;;EAEjB;EACAL,IAAI,GAAGA,IAAI,CAACM,OAAO,CAAErB,YAAY,EAAE,EAAG,CAAC;EAEvCM,eAAe,CAAC,CAAC;EACjBD,kBAAkB,CAACiB,MAAM,CAAEP,IAAK,CAAC;EACjCV,kBAAkB,CAACkB,GAAG,CAAC,CAAC;EAExBtB,OAAO,CAAEG,MAAM,EAAE,UAAUG,KAAK,EAAEiB,CAAC,EAAG;IACrC,MAAMC,SAAS,GAAGrB,MAAM,CAAEoB,CAAC,GAAG,CAAC,CAAE;IAEjC,QAASjB,KAAK,CAACmB,IAAI;MAClB,KAAK,SAAS;MACd,KAAK,2BAA2B;MAChC,KAAK,cAAc;MACnB,KAAK,YAAY;MACjB,KAAK,WAAW;MAChB,KAAK,qBAAqB;MAC1B,KAAK,mBAAmB;MACxB,KAAK,mBAAmB;QACvB,IAAK,CAAED,SAAS,IAAMR,KAAK,KAAK,CAAC,KAAMQ,SAAS,CAACC,IAAI,KAAK,aAAa,IAAID,SAAS,CAACC,IAAI,KAAK,WAAW,CAAI,EAAG;UAC/GP,YAAY,IAAIZ,KAAK,CAACoB,GAAG;UAEzBX,MAAM,CAACR,IAAI,CAAEW,YAAa,CAAC;UAC3BD,aAAa,GAAG,EAAE;UAClBC,YAAY,GAAG,EAAE;UACjBC,WAAW,GAAG,EAAE;QACjB,CAAC,MAAM;UACND,YAAY,IAAIZ,KAAK,CAACoB,GAAG;QAC1B;QACA;MAED,KAAK,aAAa;QACjB,IAAKV,KAAK,KAAK,CAAC,EAAG;UAClB,IAAKE,YAAY,CAACS,IAAI,CAAC,CAAC,KAAK,EAAE,EAAG;YACjCZ,MAAM,CAACR,IAAI,CAAEW,YAAa,CAAC;UAC5B;UACAA,YAAY,GAAG,EAAE;UACjBC,WAAW,GAAG,EAAE;QACjB;QAEAH,KAAK,EAAE;QACPC,aAAa,GAAGX,KAAK,CAACoB,GAAG;QACzB;MAED,KAAK,WAAW;QACfV,KAAK,EAAE;QACPG,WAAW,GAAGb,KAAK,CAACoB,GAAG;;QAEvB;AACJ;AACA;AACA;QACI,IAAK,EAAE,KAAKT,aAAa,IAAI,EAAE,KAAKE,WAAW,EAAG;UACjDJ,MAAM,CAACR,IAAI,CAAEU,aAAa,GAAGC,YAAY,GAAGC,WAAY,CAAC;QAC1D,CAAC,MAAM,IAAK,EAAE,KAAKD,YAAY,CAACS,IAAI,CAAC,CAAC,EAAG;UACxCZ,MAAM,CAACR,IAAI,CAAEW,YAAa,CAAC;QAC5B;QACAD,aAAa,GAAG,EAAE;QAClBC,YAAY,GAAG,EAAE;QACjBC,WAAW,GAAG,EAAE;QAChB;IACF;;IAEA;IACA,IAAKH,KAAK,GAAG,CAAC,EAAG;MAChBA,KAAK,GAAG,CAAC;IACV;EACD,CAAE,CAAC;EAEH,OAAOD,MAAM;AACd;AAEA,MAAMa,iBAAiB,GAAG3B,OAAO,CAAEY,SAAU,CAAC;AAE9C,SACC5B,aAAa,EACbC,cAAc,EACduB,cAAc,EACdG,eAAe,EACfgB,iBAAiB,IAAIf,SAAS;AAG/B,eAAe;EACd5B,aAAa,EAAEA,aAAa;EAC5BC,cAAc,EAAEA,cAAc;EAC9BuB,cAAc,EAAEA,cAAc;EAC9BG,eAAe,EAAEA,eAAe;EAChCC,SAAS,EAAEe;AACZ,CAAC","ignoreList":[]}

package/build/languageProcessing/helpers/html/htmlParser.js

@@ -0,0 +1,125 @@
+/**
+ * This file is used for HTML parsing for assessment that not use the HTML Parser.
+ * We use a (simpler) external library, which can be found here: https://github.com/fb55/htmlparser2.
+ */
+import htmlparser from "htmlparser2";
+
+/**
+ * The array containing the text parts without ignored HTML blocks.
+ * @type {string[]}
+ */
+let textArray = [];
+/**
+ * Whether we are currently in an ignored HTML block.
+ * @type {boolean}
+ */
+let inIgnorableBlock = false;
+/**
+ * The stack of currently ignored tags, when we are in an ignorable HTML block.
+ * @type {string[]}
+ */
+let ignoreStack = [];
+
+/**
+ * The HTML tags that should be ignored.
+ * @type {string[]}
+ */
+const IGNORED_TAGS = ["script", "style", "code", "pre", "blockquote", "textarea"];
+/**
+ * The classes of HTML elements that should be ignored.
+ * @type {string[]}
+ */
+const IGNORED_CLASSES = ["yoast-table-of-contents", "yoast-reading-time__wrapper", "elementor-button-wrapper", "elementor-divider", "elementor-spacer", "elementor-custom-embed", "elementor-icon-wrapper", "elementor-icon-box-wrapper", "elementor-counter", "elementor-progress-wrapper", "elementor-alert", "elementor-soundcloud-wrapper", "elementor-shortcode", "elementor-menu-anchor", "elementor-title"];
+
+/**
+ * Parses the text.
+ */
+const parser = new htmlparser.Parser({
+  /**
+   * Handles the opening tag.
+   * If we are in an ignorable block, disregard the tag.
+   * If the opening tag is included in the `IGNORED_TAGS` array, or the class is in the `IGNORED_CLASSES` array,
+   * set `inIgnorableBlock` to true and add the tag to the `ignoreStack`.
+   * Otherwise, push the tag to the `textArray`.
+   *
+   * @param {string} tagName The tag name.
+   * @param {object} nodeValue The attribute with the keys and values of the tag.
+   *
+   * @returns {void}
+   */
+  onopentag: function (tagName, nodeValue) {
+    if (inIgnorableBlock) {
+      ignoreStack.push(tagName);
+      return;
+    }
+    const classNames = nodeValue.class ? nodeValue.class.split(" ") : [];
+    if (IGNORED_TAGS.includes(tagName) || classNames.some(className => IGNORED_CLASSES.includes(className))) {
+      inIgnorableBlock = true;
+      ignoreStack.push(tagName);
+      return;
+    }
+    const nodeValueType = Object.keys(nodeValue);
+    let nodeValueString = "";
+    nodeValueType.forEach(function (node) {
+      // Build the tag again.
+      nodeValueString += " " + node + "='" + nodeValue[node] + "'";
+    });
+    textArray.push("<" + tagName + nodeValueString + ">");
+  },
+  /**
+   * Handles the text that doesn't contain opening or closing tags.
+   * If `inIgnorableBlock` is false, the text gets pushed to the `textArray` array.
+   *
+   * @param {string} text The text that doesn't contain opening or closing tags.
+   *
+   * @returns {void}
+   */
+  ontext: function (text) {
+    if (!inIgnorableBlock) {
+      textArray.push(text);
+    }
+  },
+  /**
+   * Handles the closing tag.
+   * If the closing tag is the last tag on the `ignoreStack`, jump out of the ignorable block.
+   * Otherwise, if we are not currently in an ignorable block, push the tag to the `textArray`.
+   *
+   * @param {string} tagName The tag name.
+   *
+   * @returns {void}
+   */
+  onclosetag: function (tagName) {
+    if (ignoreStack.length === 1 && ignoreStack[0] === tagName) {
+      inIgnorableBlock = false;
+      ignoreStack = [];
+      return;
+    }
+    if (inIgnorableBlock) {
+      ignoreStack.pop();
+      return;
+    }
+    textArray.push("</" + tagName + ">");
+  }
+}, {
+  decodeEntities: true
+});
+
+/**
+ * Calls htmlparser2 and returns the text without HTML blocks that we do not want to consider for the content analysis.
+ * Note that this function will soon be deprecated in favour of our own HTML parser.
+ *
+ * @param {string} text The text to parse.
+ *
+ * @returns {string} The text without the HTML blocks.
+ */
+export default function (text) {
+  // Return the globals to their starting values.
+  textArray = [];
+  inIgnorableBlock = false;
+  ignoreStack = [];
+  parser.write(text);
+  // Make sure to complete the process of parsing and reset the parser to avoid side effects.
+  parser.parseComplete();
+  return textArray.join("");
+}
+//# sourceMappingURL=htmlParser.js.map

package/build/languageProcessing/helpers/html/htmlParser.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"htmlParser.js","names":["htmlparser","textArray","inIgnorableBlock","ignoreStack","IGNORED_TAGS","IGNORED_CLASSES","parser","Parser","onopentag","tagName","nodeValue","push","classNames","class","split","includes","some","className","nodeValueType","Object","keys","nodeValueString","forEach","node","ontext","text","onclosetag","length","pop","decodeEntities","write","parseComplete","join"],"sources":["../../../../src/languageProcessing/helpers/html/htmlParser.js"],"sourcesContent":["/**\n * This file is used for HTML parsing for assessment that not use the HTML Parser.\n * We use a (simpler) external library, which can be found here: https://github.com/fb55/htmlparser2.\n */\nimport htmlparser from \"htmlparser2\";\n\n/**\n * The array containing the text parts without ignored HTML blocks.\n * @type {string[]}\n */\nlet textArray = [];\n/**\n * Whether we are currently in an ignored HTML block.\n * @type {boolean}\n */\nlet inIgnorableBlock = false;\n/**\n * The stack of currently ignored tags, when we are in an ignorable HTML block.\n * @type {string[]}\n */\nlet ignoreStack = [];\n\n/**\n * The HTML tags that should be ignored.\n * @type {string[]}\n */\nconst IGNORED_TAGS = [ \"script\", \"style\", \"code\", \"pre\", \"blockquote\", \"textarea\" ];\n/**\n * The classes of HTML elements that should be ignored.\n * @type {string[]}\n */\nconst IGNORED_CLASSES = [\n\t\"yoast-table-of-contents\",\n\t\"yoast-reading-time__wrapper\",\n\t\"elementor-button-wrapper\",\n\t\"elementor-divider\",\n\t\"elementor-spacer\",\n\t\"elementor-custom-embed\",\n\t\"elementor-icon-wrapper\",\n\t\"elementor-icon-box-wrapper\",\n\t\"elementor-counter\",\n\t\"elementor-progress-wrapper\",\n\t\"elementor-alert\",\n\t\"elementor-soundcloud-wrapper\",\n\t\"elementor-shortcode\",\n\t\"elementor-menu-anchor\",\n\t\"elementor-title\",\n];\n\n/**\n * Parses the text.\n */\nconst parser = new htmlparser.Parser( {\n\t/**\n\t * Handles the opening tag.\n\t * If we are in an ignorable block, disregard the tag.\n\t * If the opening tag is included in the `IGNORED_TAGS` array, or the class is in the `IGNORED_CLASSES` array,\n\t * set `inIgnorableBlock` to true and add the tag to the `ignoreStack`.\n\t * Otherwise, push the tag to the `textArray`.\n\t *\n\t * @param {string} tagName The tag name.\n\t * @param {object} nodeValue The attribute with the keys and values of the tag.\n\t *\n\t * @returns {void}\n\t */\n\tonopentag: function( tagName, nodeValue ) {\n\t\tif ( inIgnorableBlock ) {\n\t\t\tignoreStack.push( tagName );\n\t\t\treturn;\n\t\t}\n\n\t\tconst classNames = nodeValue.class ? nodeValue.class.split( \" \" ) : [];\n\t\tif ( IGNORED_TAGS.includes( tagName ) || classNames.some( className => IGNORED_CLASSES.includes( className ) ) ) {\n\t\t\tinIgnorableBlock = true;\n\t\t\tignoreStack.push( tagName );\n\t\t\treturn;\n\t\t}\n\n\t\tconst nodeValueType = Object.keys( nodeValue );\n\t\tlet nodeValueString = \"\";\n\n\t\tnodeValueType.forEach( function( node ) {\n\t\t\t// Build the tag again.\n\t\t\tnodeValueString += \" \" + node + \"='\" + nodeValue[ node ] + \"'\";\n\t\t} );\n\n\t\ttextArray.push( \"<\" + tagName + nodeValueString + \">\" );\n\t},\n\t/**\n\t * Handles the text that doesn't contain opening or closing tags.\n\t * If `inIgnorableBlock` is false, the text gets pushed to the `textArray` array.\n\t *\n\t * @param {string} text The text that doesn't contain opening or closing tags.\n\t *\n\t * @returns {void}\n\t */\n\tontext: function( text ) {\n\t\tif ( ! inIgnorableBlock ) {\n\t\t\ttextArray.push( text );\n\t\t}\n\t},\n\t/**\n\t * Handles the closing tag.\n\t * If the closing tag is the last tag on the `ignoreStack`, jump out of the ignorable block.\n\t * Otherwise, if we are not currently in an ignorable block, push the tag to the `textArray`.\n\t *\n\t * @param {string} tagName The tag name.\n\t *\n\t * @returns {void}\n\t */\n\tonclosetag: function( tagName ) {\n\t\tif ( ignoreStack.length === 1 && ignoreStack[ 0 ] === tagName ) {\n\t\t\tinIgnorableBlock = false;\n\t\t\tignoreStack = [];\n\t\t\treturn;\n\t\t}\n\n\t\tif ( inIgnorableBlock ) {\n\t\t\tignoreStack.pop();\n\t\t\treturn;\n\t\t}\n\n\t\ttextArray.push( \"</\" + tagName + \">\" );\n\t},\n}, { decodeEntities: true } );\n\n/**\n * Calls htmlparser2 and returns the text without HTML blocks that we do not want to consider for the content analysis.\n * Note that this function will soon be deprecated in favour of our own HTML parser.\n *\n * @param {string} text The text to parse.\n *\n * @returns {string} The text without the HTML blocks.\n */\nexport default function( text ) {\n\t// Return the globals to their starting values.\n\ttextArray = [];\n\tinIgnorableBlock = false;\n\tignoreStack = [];\n\n\tparser.write( text );\n\t// Make sure to complete the process of parsing and reset the parser to avoid side effects.\n\tparser.parseComplete();\n\treturn textArray.join( \"\" );\n}\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA,OAAOA,UAAU,MAAM,aAAa;;AAEpC;AACA;AACA;AACA;AACA,IAAIC,SAAS,GAAG,EAAE;AAClB;AACA;AACA;AACA;AACA,IAAIC,gBAAgB,GAAG,KAAK;AAC5B;AACA;AACA;AACA;AACA,IAAIC,WAAW,GAAG,EAAE;;AAEpB;AACA;AACA;AACA;AACA,MAAMC,YAAY,GAAG,CAAE,QAAQ,EAAE,OAAO,EAAE,MAAM,EAAE,KAAK,EAAE,YAAY,EAAE,UAAU,CAAE;AACnF;AACA;AACA;AACA;AACA,MAAMC,eAAe,GAAG,CACvB,yBAAyB,EACzB,6BAA6B,EAC7B,0BAA0B,EAC1B,mBAAmB,EACnB,kBAAkB,EAClB,wBAAwB,EACxB,wBAAwB,EACxB,4BAA4B,EAC5B,mBAAmB,EACnB,4BAA4B,EAC5B,iBAAiB,EACjB,8BAA8B,EAC9B,qBAAqB,EACrB,uBAAuB,EACvB,iBAAiB,CACjB;;AAED;AACA;AACA;AACA,MAAMC,MAAM,GAAG,IAAIN,UAAU,CAACO,MAAM,CAAE;EACrC;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACCC,SAAS,EAAE,SAAAA,CAAUC,OAAO,EAAEC,SAAS,EAAG;IACzC,IAAKR,gBAAgB,EAAG;MACvBC,WAAW,CAACQ,IAAI,CAAEF,OAAQ,CAAC;MAC3B;IACD;IAEA,MAAMG,UAAU,GAAGF,SAAS,CAACG,KAAK,GAAGH,SAAS,CAACG,KAAK,CAACC,KAAK,CAAE,GAAI,CAAC,GAAG,EAAE;IACtE,IAAKV,YAAY,CAACW,QAAQ,CAAEN,OAAQ,CAAC,IAAIG,UAAU,CAACI,IAAI,CAAEC,SAAS,IAAIZ,eAAe,CAACU,QAAQ,CAAEE,SAAU,CAAE,CAAC,EAAG;MAChHf,gBAAgB,GAAG,IAAI;MACvBC,WAAW,CAACQ,IAAI,CAAEF,OAAQ,CAAC;MAC3B;IACD;IAEA,MAAMS,aAAa,GAAGC,MAAM,CAACC,IAAI,CAAEV,SAAU,CAAC;IAC9C,IAAIW,eAAe,GAAG,EAAE;IAExBH,aAAa,CAACI,OAAO,CAAE,UAAUC,IAAI,EAAG;MACvC;MACAF,eAAe,IAAI,GAAG,GAAGE,IAAI,GAAG,IAAI,GAAGb,SAAS,CAAEa,IAAI,CAAE,GAAG,GAAG;IAC/D,CAAE,CAAC;IAEHtB,SAAS,CAACU,IAAI,CAAE,GAAG,GAAGF,OAAO,GAAGY,eAAe,GAAG,GAAI,CAAC;EACxD,CAAC;EACD;AACD;AACA;AACA;AACA;AACA;AACA;AACA;EACCG,MAAM,EAAE,SAAAA,CAAUC,IAAI,EAAG;IACxB,IAAK,CAAEvB,gBAAgB,EAAG;MACzBD,SAAS,CAACU,IAAI,CAAEc,IAAK,CAAC;IACvB;EACD,CAAC;EACD;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACCC,UAAU,EAAE,SAAAA,CAAUjB,OAAO,EAAG;IAC/B,IAAKN,WAAW,CAACwB,MAAM,KAAK,CAAC,IAAIxB,WAAW,CAAE,CAAC,CAAE,KAAKM,OAAO,EAAG;MAC/DP,gBAAgB,GAAG,KAAK;MACxBC,WAAW,GAAG,EAAE;MAChB;IACD;IAEA,IAAKD,gBAAgB,EAAG;MACvBC,WAAW,CAACyB,GAAG,CAAC,CAAC;MACjB;IACD;IAEA3B,SAAS,CAACU,IAAI,CAAE,IAAI,GAAGF,OAAO,GAAG,GAAI,CAAC;EACvC;AACD,CAAC,EAAE;EAAEoB,cAAc,EAAE;AAAK,CAAE,CAAC;;AAE7B;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUJ,IAAI,EAAG;EAC/B;EACAxB,SAAS,GAAG,EAAE;EACdC,gBAAgB,GAAG,KAAK;EACxBC,WAAW,GAAG,EAAE;EAEhBG,MAAM,CAACwB,KAAK,CAAEL,IAAK,CAAC;EACpB;EACAnB,MAAM,CAACyB,aAAa,CAAC,CAAC;EACtB,OAAO9B,SAAS,CAAC+B,IAAI,CAAE,EAAG,CAAC;AAC5B","ignoreList":[]}

package/build/languageProcessing/helpers/html/matchParagraphs.js

@@ -0,0 +1,56 @@
+import { filter, flatMap, map } from "lodash";
+import { getBlocks } from "./html";
+
+/**
+ * Matches the paragraphs in <p>-tags and returns the text in them.
+ *
+ * @param {string} text The text to match paragraph in.
+ *
+ * @returns {array} An array containing all paragraphs texts.
+ */
+const getParagraphsInTags = function (text) {
+  let paragraphs = [];
+  // Matches everything between the <p> and </p> tags.
+  const regex = /<p(?:[^>]+)?>(.*?)<\/p>/ig;
+  let match;
+  while ((match = regex.exec(text)) !== null) {
+    paragraphs.push(match);
+  }
+
+  // Returns only the text from within the paragraph tags.
+  paragraphs = map(paragraphs, function (paragraph) {
+    return paragraph[1];
+  });
+  return paragraphs.filter(paragraph => paragraph.length > 0);
+};
+
+/**
+ * Returns an array with all paragraphs from the text.
+ *
+ * @param {string} text The text to match paragraph in.
+ *
+ * @returns {Array} The array containing all paragraphs from the text.
+ */
+export default function (text) {
+  let paragraphs = getParagraphsInTags(text);
+  if (paragraphs.length > 0) {
+    return paragraphs;
+  }
+
+  // If no <p> tags found, split on double linebreaks.
+  let blocks = getBlocks(text);
+  blocks = filter(blocks, function (block) {
+    // Match explicit paragraph tags, or if a block has no HTML tags.
+    return 0 !== block.indexOf("<h");
+  });
+  paragraphs = flatMap(blocks, function (block) {
+    return block.split("\n\n");
+  });
+  if (paragraphs.length > 0) {
+    return paragraphs;
+  }
+
+  // If no paragraphs are found, return an array containing the entire text.
+  return [text];
+}
+//# sourceMappingURL=matchParagraphs.js.map

package/build/languageProcessing/helpers/html/matchParagraphs.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"matchParagraphs.js","names":["filter","flatMap","map","getBlocks","getParagraphsInTags","text","paragraphs","regex","match","exec","push","paragraph","length","blocks","block","indexOf","split"],"sources":["../../../../src/languageProcessing/helpers/html/matchParagraphs.js"],"sourcesContent":["import { filter, flatMap, map } from \"lodash\";\n\nimport { getBlocks } from \"./html\";\n\n/**\n * Matches the paragraphs in <p>-tags and returns the text in them.\n *\n * @param {string} text The text to match paragraph in.\n *\n * @returns {array} An array containing all paragraphs texts.\n */\nconst getParagraphsInTags = function( text ) {\n\tlet paragraphs = [];\n\t// Matches everything between the <p> and </p> tags.\n\tconst regex = /<p(?:[^>]+)?>(.*?)<\\/p>/ig;\n\tlet match;\n\n\twhile ( ( match = regex.exec( text ) ) !== null ) {\n\t\tparagraphs.push( match );\n\t}\n\n\t// Returns only the text from within the paragraph tags.\n\tparagraphs = map( paragraphs, function( paragraph ) {\n\t\treturn paragraph[ 1 ];\n\t} );\n\n\treturn paragraphs.filter( paragraph => paragraph.length > 0 );\n};\n\n/**\n * Returns an array with all paragraphs from the text.\n *\n * @param {string} text The text to match paragraph in.\n *\n * @returns {Array} The array containing all paragraphs from the text.\n */\nexport default function( text ) {\n\tlet paragraphs = getParagraphsInTags( text );\n\n\tif ( paragraphs.length > 0 ) {\n\t\treturn paragraphs;\n\t}\n\n\t// If no <p> tags found, split on double linebreaks.\n\tlet blocks = getBlocks( text );\n\n\tblocks = filter( blocks, function( block ) {\n\t\t// Match explicit paragraph tags, or if a block has no HTML tags.\n\t\treturn 0 !== block.indexOf( \"<h\" );\n\t} );\n\n\tparagraphs = flatMap( blocks, function( block ) {\n\t\treturn block.split( \"\\n\\n\" );\n\t} );\n\n\tif ( paragraphs.length > 0 ) {\n\t\treturn paragraphs;\n\t}\n\n\t// If no paragraphs are found, return an array containing the entire text.\n\treturn [ text ];\n}\n"],"mappings":"AAAA,SAASA,MAAM,EAAEC,OAAO,EAAEC,GAAG,QAAQ,QAAQ;AAE7C,SAASC,SAAS;;AAElB;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,mBAAmB,GAAG,SAAAA,CAAUC,IAAI,EAAG;EAC5C,IAAIC,UAAU,GAAG,EAAE;EACnB;EACA,MAAMC,KAAK,GAAG,2BAA2B;EACzC,IAAIC,KAAK;EAET,OAAQ,CAAEA,KAAK,GAAGD,KAAK,CAACE,IAAI,CAAEJ,IAAK,CAAC,MAAO,IAAI,EAAG;IACjDC,UAAU,CAACI,IAAI,CAAEF,KAAM,CAAC;EACzB;;EAEA;EACAF,UAAU,GAAGJ,GAAG,CAAEI,UAAU,EAAE,UAAUK,SAAS,EAAG;IACnD,OAAOA,SAAS,CAAE,CAAC,CAAE;EACtB,CAAE,CAAC;EAEH,OAAOL,UAAU,CAACN,MAAM,CAAEW,SAAS,IAAIA,SAAS,CAACC,MAAM,GAAG,CAAE,CAAC;AAC9D,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUP,IAAI,EAAG;EAC/B,IAAIC,UAAU,GAAGF,mBAAmB,CAAEC,IAAK,CAAC;EAE5C,IAAKC,UAAU,CAACM,MAAM,GAAG,CAAC,EAAG;IAC5B,OAAON,UAAU;EAClB;;EAEA;EACA,IAAIO,MAAM,GAAGV,SAAS,CAAEE,IAAK,CAAC;EAE9BQ,MAAM,GAAGb,MAAM,CAAEa,MAAM,EAAE,UAAUC,KAAK,EAAG;IAC1C;IACA,OAAO,CAAC,KAAKA,KAAK,CAACC,OAAO,CAAE,IAAK,CAAC;EACnC,CAAE,CAAC;EAEHT,UAAU,GAAGL,OAAO,CAAEY,MAAM,EAAE,UAAUC,KAAK,EAAG;IAC/C,OAAOA,KAAK,CAACE,KAAK,CAAE,MAAO,CAAC;EAC7B,CAAE,CAAC;EAEH,IAAKV,UAAU,CAACM,MAAM,GAAG,CAAC,EAAG;IAC5B,OAAON,UAAU;EAClB;;EAEA;EACA,OAAO,CAAED,IAAI,CAAE;AAChB","ignoreList":[]}

package/build/languageProcessing/helpers/html/normalizeHTML.js

@@ -0,0 +1,17 @@
+/**
+ * Replaces single quotes around HTML attribute values with double quotes.
+ * Double quotes are the standard, but we convert these to single quotes when parsing the HTML in `@axyseo` package.
+ * Here, we change them back to double quotes so by parsing the HTML and then outputting it again.
+ * Note that this function does more than just replacing single quotes with double quotes. It also restores corrupted HTML.
+ * @param {string} str The input string.
+ *
+ * @returns {string} The string with single quotes around HTML attributes replaced with double quotes.
+ */
+export default function (str) {
+  const doc = new DOMParser().parseFromString(str, 'text/html');
+  const normalizedHTML = doc.body.innerHTML;
+
+  // Replace ` ` with an actual non breaking space (U+00A0).
+  return normalizedHTML.replace(/ /g, '\u00A0');
+}
+//# sourceMappingURL=normalizeHTML.js.map

package/build/languageProcessing/helpers/html/normalizeHTML.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"normalizeHTML.js","names":["str","doc","DOMParser","parseFromString","normalizedHTML","body","innerHTML","replace"],"sources":["../../../../src/languageProcessing/helpers/html/normalizeHTML.js"],"sourcesContent":["/**\n * Replaces single quotes around HTML attribute values with double quotes.\n * Double quotes are the standard, but we convert these to single quotes when parsing the HTML in `@axyseo` package.\n * Here, we change them back to double quotes so by parsing the HTML and then outputting it again.\n * Note that this function does more than just replacing single quotes with double quotes. It also restores corrupted HTML.\n * @param {string} str The input string.\n *\n * @returns {string} The string with single quotes around HTML attributes replaced with double quotes.\n */\nexport default function(str) {\n  const doc = new DOMParser().parseFromString(str, 'text/html');\n  const normalizedHTML = doc.body.innerHTML;\n\n  // Replace ` ` with an actual non breaking space (U+00A0).\n  return normalizedHTML.replace(/ /g, '\\u00A0');\n}\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAASA,GAAG,EAAE;EAC3B,MAAMC,GAAG,GAAG,IAAIC,SAAS,CAAC,CAAC,CAACC,eAAe,CAACH,GAAG,EAAE,WAAW,CAAC;EAC7D,MAAMI,cAAc,GAAGH,GAAG,CAACI,IAAI,CAACC,SAAS;;EAEzC;EACA,OAAOF,cAAc,CAACG,OAAO,CAAC,SAAS,EAAE,QAAQ,CAAC;AACpD","ignoreList":[]}

package/build/languageProcessing/helpers/image/getAltAttribute.js

@@ -0,0 +1,18 @@
+import stripSpaces from "../sanitize/stripSpaces.js";
+
+/**
+ * Checks for an alt attribute in the image and returns its content.
+ *
+ * @param {Node} imageNode Text string to match the alt attribute.
+ * @returns {String} The contents of the alt attribute, empty if none is set.
+ */
+export default function (imageNode) {
+  let alt = "";
+  if (imageNode.name === "img") {
+    alt = stripSpaces(imageNode.attributes.alt || "");
+    alt = alt.replace(/"/g, "\"");
+    alt = alt.replace(/'/g, "'");
+  }
+  return alt;
+}
+//# sourceMappingURL=getAltAttribute.js.map

package/build/languageProcessing/helpers/image/getAltAttribute.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getAltAttribute.js","names":["stripSpaces","imageNode","alt","name","attributes","replace"],"sources":["../../../../src/languageProcessing/helpers/image/getAltAttribute.js"],"sourcesContent":["import stripSpaces from \"../sanitize/stripSpaces.js\";\n\n/**\n * Checks for an alt attribute in the image and returns its content.\n *\n * @param {Node} imageNode Text string to match the alt attribute.\n * @returns {String} The contents of the alt attribute, empty if none is set.\n */\nexport default function( imageNode ) {\n\tlet alt = \"\";\n\n\tif ( imageNode.name === \"img\" ) {\n\t\talt = stripSpaces( imageNode.attributes.alt || \"\" );\n\n\t\talt = alt.replace( /"/g, \"\\\"\" );\n\t\talt = alt.replace( /'/g, \"'\" );\n\t}\n\n\treturn alt;\n}\n"],"mappings":"AAAA,OAAOA,WAAW;;AAElB;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,SAAS,EAAG;EACpC,IAAIC,GAAG,GAAG,EAAE;EAEZ,IAAKD,SAAS,CAACE,IAAI,KAAK,KAAK,EAAG;IAC/BD,GAAG,GAAGF,WAAW,CAAEC,SAAS,CAACG,UAAU,CAACF,GAAG,IAAI,EAAG,CAAC;IAEnDA,GAAG,GAAGA,GAAG,CAACG,OAAO,CAAE,SAAS,EAAE,IAAK,CAAC;IACpCH,GAAG,GAAGA,GAAG,CAACG,OAAO,CAAE,SAAS,EAAE,GAAI,CAAC;EACpC;EAEA,OAAOH,GAAG;AACX","ignoreList":[]}

package/build/languageProcessing/helpers/image/getImagesInTree.js

@@ -0,0 +1,15 @@
+/**
+ * Checks the tree for images.
+ *
+ * @param {Paper}       paper       The paper to check for images.
+ *
+ * @returns {Array} Array containing all images in the tree
+ */
+export default function (paper) {
+  const tree = paper.getTree();
+  if (!tree) {
+    return [];
+  }
+  return tree.findAll(node => node.name === "img");
+}
+//# sourceMappingURL=getImagesInTree.js.map

package/build/languageProcessing/helpers/image/getImagesInTree.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getImagesInTree.js","names":["paper","tree","getTree","findAll","node","name"],"sources":["../../../../src/languageProcessing/helpers/image/getImagesInTree.js"],"sourcesContent":["/**\n * Checks the tree for images.\n *\n * @param {Paper}       paper       The paper to check for images.\n *\n * @returns {Array} Array containing all images in the tree\n */\nexport default function( paper ) {\n\tconst tree = paper.getTree();\n\n\tif ( ! tree ) {\n\t\treturn [];\n\t}\n\n\treturn tree.findAll( node => node.name === \"img\" );\n}\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUA,KAAK,EAAG;EAChC,MAAMC,IAAI,GAAGD,KAAK,CAACE,OAAO,CAAC,CAAC;EAE5B,IAAK,CAAED,IAAI,EAAG;IACb,OAAO,EAAE;EACV;EAEA,OAAOA,IAAI,CAACE,OAAO,CAAEC,IAAI,IAAIA,IAAI,CAACC,IAAI,KAAK,KAAM,CAAC;AACnD","ignoreList":[]}

package/build/languageProcessing/helpers/image/imageInText.js

@@ -0,0 +1,19 @@
+/** @module stringProcessing/imageInText */
+
+import matchStringWithRegex from "../regex/matchStringWithRegex.js";
+
+/**
+ * @returns {object} A precompiled regex for recognizing self closing image tags.
+ */
+export const imageRegex = new RegExp("<img(?:[^>]+)?>(</img>)*", "ig");
+
+/**
+ * Checks the text for images.
+ *
+ * @param {string} text The text string to check for images
+ * @returns {Array} Array containing all types of found images
+ */
+export default function (text) {
+  return matchStringWithRegex(text, imageRegex);
+}
+//# sourceMappingURL=imageInText.js.map

package/build/languageProcessing/helpers/image/imageInText.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"imageInText.js","names":["matchStringWithRegex","imageRegex","RegExp","text"],"sources":["../../../../src/languageProcessing/helpers/image/imageInText.js"],"sourcesContent":["/** @module stringProcessing/imageInText */\n\nimport matchStringWithRegex from \"../regex/matchStringWithRegex.js\";\n\n/**\n * @returns {object} A precompiled regex for recognizing self closing image tags.\n */\nexport const imageRegex = new RegExp( \"<img(?:[^>]+)?>(</img>)*\", \"ig\" );\n\n\n/**\n * Checks the text for images.\n *\n * @param {string} text The text string to check for images\n * @returns {Array} Array containing all types of found images\n */\nexport default function( text ) {\n\treturn matchStringWithRegex( text, imageRegex );\n}\n"],"mappings":"AAAA;;AAEA,OAAOA,oBAAoB;;AAE3B;AACA;AACA;AACA,OAAO,MAAMC,UAAU,GAAG,IAAIC,MAAM,CAAE,0BAA0B,EAAE,IAAK,CAAC;;AAGxE;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,IAAI,EAAG;EAC/B,OAAOH,oBAAoB,CAAEG,IAAI,EAAEF,UAAW,CAAC;AAChD","ignoreList":[]}

package/build/languageProcessing/helpers/index.js

@@ -0,0 +1,6 @@
+import { normalize } from "./sanitize/quotes";
+import { createShortcodeTagsRegex, filterShortcodesFromHTML } from "./sanitize/filterShortcodesFromTree";
+import processExactMatchRequest from "./match/processExactMatchRequest";
+import removeHtmlBlocks from "./html/htmlParser";
+export { normalize, removeHtmlBlocks, filterShortcodesFromHTML, createShortcodeTagsRegex, processExactMatchRequest };
+//# sourceMappingURL=index.js.map

package/build/languageProcessing/helpers/index.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"index.js","names":["normalize","createShortcodeTagsRegex","filterShortcodesFromHTML","processExactMatchRequest","removeHtmlBlocks"],"sources":["../../../src/languageProcessing/helpers/index.js"],"sourcesContent":["import { normalize } from \"./sanitize/quotes\";\nimport { createShortcodeTagsRegex, filterShortcodesFromHTML } from \"./sanitize/filterShortcodesFromTree\";\nimport processExactMatchRequest from \"./match/processExactMatchRequest\";\nimport removeHtmlBlocks from \"./html/htmlParser\";\n\nexport {\n\tnormalize,\n\tremoveHtmlBlocks,\n\tfilterShortcodesFromHTML,\n\tcreateShortcodeTagsRegex,\n\tprocessExactMatchRequest,\n};\n"],"mappings":"AAAA,SAASA,SAAS;AAClB,SAASC,wBAAwB,EAAEC,wBAAwB;AAC3D,OAAOC,wBAAwB;AAC/B,OAAOC,gBAAgB;AAEvB,SACCJ,SAAS,EACTI,gBAAgB,EAChBF,wBAAwB,EACxBD,wBAAwB,EACxBE,wBAAwB","ignoreList":[]}

package/build/languageProcessing/helpers/language/getLanguage.js

@@ -0,0 +1,10 @@
+/**
+ * The function getting the language part of the locale.
+ *
+ * @param {string} locale The locale.
+ * @returns {string} The language part of the locale.
+ */
+export default function (locale) {
+  return locale.split("_")[0];
+}
+//# sourceMappingURL=getLanguage.js.map

package/build/languageProcessing/helpers/language/getLanguage.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getLanguage.js","names":["locale","split"],"sources":["../../../../src/languageProcessing/helpers/language/getLanguage.js"],"sourcesContent":["/**\n * The function getting the language part of the locale.\n *\n * @param {string} locale The locale.\n * @returns {string} The language part of the locale.\n */\nexport default function( locale ) {\n\treturn locale.split( \"_\" )[ 0 ];\n}\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUA,MAAM,EAAG;EACjC,OAAOA,MAAM,CAACC,KAAK,CAAE,GAAI,CAAC,CAAE,CAAC,CAAE;AAChC","ignoreList":[]}

package/build/languageProcessing/helpers/link/checkNofollow.js

@@ -0,0 +1,35 @@
+/** @module stringProcessing/checkNofollow */
+
+// We use an external library, which can be found here: https://github.com/fb55/htmlparser2.
+import htmlparser from "htmlparser2";
+
+/**
+ * Checks if a link has a `rel` attribute with a `nofollow` value. If it has, returns Nofollow, otherwise Dofollow.
+ *
+ * @param {string} anchorHTML The anchor HTML to check against.
+ * @returns {string} Returns Dofollow or Nofollow.
+ */
+export default function (anchorHTML) {
+  let linkFollow = "Dofollow";
+  const parser = new htmlparser.Parser({
+    /**
+     * Detects if there is a `nofollow` value in the `rel` attribute of a link.
+     *
+     * @param {string} tagName The tag name.
+     * @param {object} attributes The tag attributes with the names and values of each attribute found.
+     * @returns {void}
+     */
+    onopentag: function (tagName, attributes) {
+      if (tagName !== "a" || !attributes.rel) {
+        return;
+      }
+      if (attributes.rel.toLowerCase().split(/\s/).includes("nofollow")) {
+        linkFollow = "Nofollow";
+      }
+    }
+  });
+  parser.write(anchorHTML);
+  parser.end();
+  return linkFollow;
+}
+//# sourceMappingURL=checkNofollow.js.map