axyseo 2.0.0-alpha.1

package/build/languageProcessing/helpers/sentence/countSentences.js

@@ -0,0 +1,27 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _getSentences = _interopRequireDefault(require("./getSentences.js"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/** @module stringProcessing/countSentences */
+
+/**
+ * Counts the number of sentences in a given string.
+ *
+ * @param {string}      text                The text used to count sentences.
+ * @param {function}    memoizedTokenizer   The memoized sentence tokenizer.
+ *
+ * @returns {number} The number of sentences in the text.
+ */
+function _default(text, memoizedTokenizer) {
+  const sentences = (0, _getSentences.default)(text, memoizedTokenizer);
+  let sentenceCount = 0;
+  for (let i = 0; i < sentences.length; i++) {
+    sentenceCount++;
+  }
+  return sentenceCount;
+}
+//# sourceMappingURL=countSentences.js.map

package/build/languageProcessing/helpers/sentence/countSentences.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"countSentences.js","names":["_getSentences","_interopRequireDefault","require","e","__esModule","default","_default","text","memoizedTokenizer","sentences","getSentences","sentenceCount","i","length"],"sources":["../../../../src/languageProcessing/helpers/sentence/countSentences.js"],"sourcesContent":["/** @module stringProcessing/countSentences */\n\nimport getSentences from \"./getSentences.js\";\n\n/**\n * Counts the number of sentences in a given string.\n *\n * @param {string}      text                The text used to count sentences.\n * @param {function}    memoizedTokenizer   The memoized sentence tokenizer.\n *\n * @returns {number} The number of sentences in the text.\n */\nexport default function( text, memoizedTokenizer ) {\n\tconst sentences = getSentences( text, memoizedTokenizer );\n\tlet sentenceCount = 0;\n\tfor ( let i = 0; i < sentences.length; i++ ) {\n\t\tsentenceCount++;\n\t}\n\treturn sentenceCount;\n}\n"],"mappings":";;;;;;AAEA,IAAAA,aAAA,GAAAC,sBAAA,CAAAC,OAAA;AAA6C,SAAAD,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAF7C;;AAIA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAAUC,IAAI,EAAEC,iBAAiB,EAAG;EAClD,MAAMC,SAAS,GAAG,IAAAC,qBAAY,EAAEH,IAAI,EAAEC,iBAAkB,CAAC;EACzD,IAAIG,aAAa,GAAG,CAAC;EACrB,KAAM,IAAIC,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGH,SAAS,CAACI,MAAM,EAAED,CAAC,EAAE,EAAG;IAC5CD,aAAa,EAAE;EAChB;EACA,OAAOA,aAAa;AACrB","ignoreList":[]}

package/build/languageProcessing/helpers/sentence/getSentences.js

@@ -0,0 +1,71 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _lodash = require("lodash");
+var _html = require("../html/html.js");
+var _imageInText = require("../image/imageInText");
+var _stripHTMLTags = require("../sanitize/stripHTMLTags");
+var _unifyWhitespace = require("../sanitize/unifyWhitespace");
+var _memoizedSentenceTokenizer = _interopRequireDefault(require("./memoizedSentenceTokenizer"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+// Lodash imports.
+
+// Internal dependencies.
+
+// Character classes.
+const newLines = "\n\r|\n|\r";
+
+// Regular expressions.
+const newLineRegex = new RegExp(newLines);
+const paragraphTagsRegex = new RegExp("^(<p>|</p>)$");
+
+/**
+ * Returns sentences in a string.
+ *
+ * @param {String}      text                The string to count sentences in.
+ * @param {function}    memoizedTokenizer   The memoized sentence tokenizer.
+ *
+ * @returns {Array} Sentences found in the text.
+ */
+function _default(text, memoizedTokenizer = _memoizedSentenceTokenizer.default) {
+  // We don't remove the other HTML tags here since removing them might lead to incorrect results when running the sentence tokenizer.
+  // Unify only non-breaking spaces and not the other whitespaces since a whitespace could signify a sentence break or a new line.
+  text = (0, _unifyWhitespace.unifyNonBreakingSpace)(text);
+  /*
+   * Remove images from text before tokenizing it into sentences.
+   * This is necessary since the highlighting feature doesn't work if the yoastmark tags are enclosing a sentence starting with an image.
+   * This step is done here so that applying highlight in captions is possible for all assessments that use this helper.
+   */
+  text = text.replace(_imageInText.imageRegex, "");
+  let blocks = (0, _html.getBlocks)(text);
+
+  // Split each block on newlines.
+  blocks = (0, _lodash.flatMap)(blocks, function (block) {
+    return block.split(newLineRegex);
+  });
+
+  /*
+   * Filter blocks that contain only paragraph tags. This step is necessary
+   * since switching between editors might add extra paragraph tags with a new line tag in the end
+   * that are incorrectly converted into separate blocks.
+   */
+  blocks = blocks.filter(block => !paragraphTagsRegex.test(block));
+
+  /*
+   * We use the `map` method followed by `flat` instead of `flatMap` because `flatMap` would override the second
+   * argument of the memoizedTokenizer with the index of the iteratee.
+   */
+  let sentences = blocks.map(block => memoizedTokenizer(block)).flat();
+
+  /*
+   * Strip block tags from the start and/or the end of each sentence and whitespaces if present.
+   * After tokenized, sometimes there are still block tags present in the beginning/end of a sentence.
+   * Unstripped, these tags could potentially break the highlighting functionality.
+   */
+  sentences = sentences.map(sentence => (0, _stripHTMLTags.stripBlockTagsAtStartEnd)(sentence).trim());
+  return (0, _lodash.filter)(sentences, (0, _lodash.negate)(_lodash.isEmpty));
+}
+//# sourceMappingURL=getSentences.js.map

package/build/languageProcessing/helpers/sentence/getSentences.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getSentences.js","names":["_lodash","require","_html","_imageInText","_stripHTMLTags","_unifyWhitespace","_memoizedSentenceTokenizer","_interopRequireDefault","e","__esModule","default","newLines","newLineRegex","RegExp","paragraphTagsRegex","_default","text","memoizedTokenizer","defaultSentenceTokenizer","unifyNonBreakingSpace","replace","imageRegex","blocks","getBlocks","flatMap","block","split","filter","test","sentences","map","flat","sentence","stripBlockTagsAtStartEnd","trim","negate","isEmpty"],"sources":["../../../../src/languageProcessing/helpers/sentence/getSentences.js"],"sourcesContent":["// Lodash imports.\nimport { filter, flatMap, isEmpty, negate } from \"lodash\";\n\n// Internal dependencies.\nimport { getBlocks } from \"../html/html.js\";\nimport { imageRegex } from \"../image/imageInText\";\nimport { stripBlockTagsAtStartEnd } from \"../sanitize/stripHTMLTags\";\nimport { unifyNonBreakingSpace } from \"../sanitize/unifyWhitespace\";\nimport defaultSentenceTokenizer from \"./memoizedSentenceTokenizer\";\n\n// Character classes.\nconst newLines = \"\\n\\r|\\n|\\r\";\n\n// Regular expressions.\nconst newLineRegex = new RegExp( newLines );\nconst paragraphTagsRegex = new RegExp( \"^(<p>|</p>)$\" );\n\n/**\n * Returns sentences in a string.\n *\n * @param {String}      text                The string to count sentences in.\n * @param {function}    memoizedTokenizer   The memoized sentence tokenizer.\n *\n * @returns {Array} Sentences found in the text.\n */\nexport default function( text, memoizedTokenizer = defaultSentenceTokenizer ) {\n\t// We don't remove the other HTML tags here since removing them might lead to incorrect results when running the sentence tokenizer.\n\t// Unify only non-breaking spaces and not the other whitespaces since a whitespace could signify a sentence break or a new line.\n\ttext = unifyNonBreakingSpace( text );\n\t/*\n\t * Remove images from text before tokenizing it into sentences.\n\t * This is necessary since the highlighting feature doesn't work if the yoastmark tags are enclosing a sentence starting with an image.\n\t * This step is done here so that applying highlight in captions is possible for all assessments that use this helper.\n\t */\n\ttext = text.replace( imageRegex, \"\" );\n\n\tlet blocks = getBlocks( text );\n\n\t// Split each block on newlines.\n\tblocks = flatMap( blocks, function( block ) {\n\t\treturn block.split( newLineRegex );\n\t} );\n\n\t/*\n\t * Filter blocks that contain only paragraph tags. This step is necessary\n\t * since switching between editors might add extra paragraph tags with a new line tag in the end\n\t * that are incorrectly converted into separate blocks.\n\t */\n\tblocks = blocks.filter( block => ! paragraphTagsRegex.test( block ) );\n\n\t/*\n\t * We use the `map` method followed by `flat` instead of `flatMap` because `flatMap` would override the second\n\t * argument of the memoizedTokenizer with the index of the iteratee.\n\t */\n\tlet sentences = blocks.map( block => memoizedTokenizer( block ) ).flat();\n\n\t/*\n\t * Strip block tags from the start and/or the end of each sentence and whitespaces if present.\n\t * After tokenized, sometimes there are still block tags present in the beginning/end of a sentence.\n\t * Unstripped, these tags could potentially break the highlighting functionality.\n\t */\n\tsentences = sentences.map( sentence => stripBlockTagsAtStartEnd( sentence ).trim() );\n\n\treturn filter( sentences, negate( isEmpty ) );\n}\n"],"mappings":";;;;;;AACA,IAAAA,OAAA,GAAAC,OAAA;AAGA,IAAAC,KAAA,GAAAD,OAAA;AACA,IAAAE,YAAA,GAAAF,OAAA;AACA,IAAAG,cAAA,GAAAH,OAAA;AACA,IAAAI,gBAAA,GAAAJ,OAAA;AACA,IAAAK,0BAAA,GAAAC,sBAAA,CAAAN,OAAA;AAAmE,SAAAM,uBAAAC,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AARnE;;AAGA;;AAOA;AACA,MAAMG,QAAQ,GAAG,YAAY;;AAE7B;AACA,MAAMC,YAAY,GAAG,IAAIC,MAAM,CAAEF,QAAS,CAAC;AAC3C,MAAMG,kBAAkB,GAAG,IAAID,MAAM,CAAE,cAAe,CAAC;;AAEvD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAE,SAAUC,IAAI,EAAEC,iBAAiB,GAAGC,kCAAwB,EAAG;EAC7E;EACA;EACAF,IAAI,GAAG,IAAAG,sCAAqB,EAAEH,IAAK,CAAC;EACpC;AACD;AACA;AACA;AACA;EACCA,IAAI,GAAGA,IAAI,CAACI,OAAO,CAAEC,uBAAU,EAAE,EAAG,CAAC;EAErC,IAAIC,MAAM,GAAG,IAAAC,eAAS,EAAEP,IAAK,CAAC;;EAE9B;EACAM,MAAM,GAAG,IAAAE,eAAO,EAAEF,MAAM,EAAE,UAAUG,KAAK,EAAG;IAC3C,OAAOA,KAAK,CAACC,KAAK,CAAEd,YAAa,CAAC;EACnC,CAAE,CAAC;;EAEH;AACD;AACA;AACA;AACA;EACCU,MAAM,GAAGA,MAAM,CAACK,MAAM,CAAEF,KAAK,IAAI,CAAEX,kBAAkB,CAACc,IAAI,CAAEH,KAAM,CAAE,CAAC;;EAErE;AACD;AACA;AACA;EACC,IAAII,SAAS,GAAGP,MAAM,CAACQ,GAAG,CAAEL,KAAK,IAAIR,iBAAiB,CAAEQ,KAAM,CAAE,CAAC,CAACM,IAAI,CAAC,CAAC;;EAExE;AACD;AACA;AACA;AACA;EACCF,SAAS,GAAGA,SAAS,CAACC,GAAG,CAAEE,QAAQ,IAAI,IAAAC,uCAAwB,EAAED,QAAS,CAAC,CAACE,IAAI,CAAC,CAAE,CAAC;EAEpF,OAAO,IAAAP,cAAM,EAAEE,SAAS,EAAE,IAAAM,cAAM,EAAEC,eAAQ,CAAE,CAAC;AAC9C","ignoreList":[]}

package/build/languageProcessing/helpers/sentence/getSentencesFromTree.js

@@ -0,0 +1,60 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+exports.getParentNode = getParentNode;
+/**
+ * Retrieves the start offset for a given node.
+ * @param {Node} node The current node.
+ * @returns {number} The start offset.
+ */
+function getStartOffset(node) {
+  return node.sourceCodeLocation && (node.sourceCodeLocation.startTag && node.sourceCodeLocation.startTag.endOffset || node.sourceCodeLocation.startOffset) || 0;
+}
+
+/**
+ * Retrieves the parent node for a given node.
+ * @param {Paper} 	paper 	The current paper.
+ * @param {Node} 	node 	The current node.
+ * @returns {Node} The parent node.
+ */
+function getParentNode(paper, node) {
+  // Includes a fallback so that if a parent node cannot be found for an implicit paragraph, we use the current node as the parent node.
+  return paper.getTree().findAll(treeNode => treeNode.childNodes && treeNode.childNodes.includes(node))[0] || node;
+}
+
+/**
+ * Gets all the sentences from paragraph and heading nodes.
+ * These two node types are the nodes that should contain sentences for the analysis.
+ *
+ * @param {Paper} paper The paper to get the sentences from.
+ *
+ * @returns {Sentence[]} The array of sentences retrieved from paragraph and heading nodes plus sourceCodeLocation of the parent node.
+ */
+function _default(paper) {
+  // Get all nodes that have a sentence property which is not an empty array.
+  const tree = paper.getTree().findAll(treeNode => !!treeNode.sentences);
+  return tree.flatMap(node => node.sentences.map(sentence => {
+    let parentNode = node;
+
+    // For implicit paragraphs, base the details on the parent of this node.
+    if (node.isImplicit) {
+      parentNode = getParentNode(paper, node);
+    }
+    return {
+      ...sentence,
+      // The parent node's start offset is the start offset of the parent node if it doesn't have a `startTag` property.
+      parentStartOffset: getStartOffset(parentNode),
+      // The block client id of the parent node.
+      parentClientId: parentNode.clientId || "",
+      // The attribute id of the parent node, if available, otherwise an empty string.
+      // Only used for position-based highlighting in sub-blocks of Yoast blocks.
+      parentAttributeId: node.attributeId || "",
+      // Whether the parent node is the first section of Yoast sub-blocks. Only used for position-based highlighting.
+      isParentFirstSectionOfBlock: node.isFirstSection || false
+    };
+  }));
+}
+//# sourceMappingURL=getSentencesFromTree.js.map

package/build/languageProcessing/helpers/sentence/getSentencesFromTree.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getSentencesFromTree.js","names":["getStartOffset","node","sourceCodeLocation","startTag","endOffset","startOffset","getParentNode","paper","getTree","findAll","treeNode","childNodes","includes","_default","tree","sentences","flatMap","map","sentence","parentNode","isImplicit","parentStartOffset","parentClientId","clientId","parentAttributeId","attributeId","isParentFirstSectionOfBlock","isFirstSection"],"sources":["../../../../src/languageProcessing/helpers/sentence/getSentencesFromTree.js"],"sourcesContent":["/**\n * Retrieves the start offset for a given node.\n * @param {Node} node The current node.\n * @returns {number} The start offset.\n */\nfunction getStartOffset( node ) {\n\treturn node.sourceCodeLocation &&\n\t\t( ( node.sourceCodeLocation.startTag && node.sourceCodeLocation.startTag.endOffset ) || node.sourceCodeLocation.startOffset ) || 0;\n}\n\n/**\n * Retrieves the parent node for a given node.\n * @param {Paper} \tpaper \tThe current paper.\n * @param {Node} \tnode \tThe current node.\n * @returns {Node} The parent node.\n */\nexport function getParentNode( paper, node ) {\n\t// Includes a fallback so that if a parent node cannot be found for an implicit paragraph, we use the current node as the parent node.\n\treturn paper.getTree().findAll( treeNode => treeNode.childNodes && treeNode.childNodes.includes( node ) )[ 0 ] || node;\n}\n\n/**\n * Gets all the sentences from paragraph and heading nodes.\n * These two node types are the nodes that should contain sentences for the analysis.\n *\n * @param {Paper} paper The paper to get the sentences from.\n *\n * @returns {Sentence[]} The array of sentences retrieved from paragraph and heading nodes plus sourceCodeLocation of the parent node.\n */\nexport default function( paper ) {\n\t// Get all nodes that have a sentence property which is not an empty array.\n\tconst tree = paper.getTree().findAll( treeNode => !! treeNode.sentences );\n\n\treturn tree.flatMap( node => node.sentences.map( sentence => {\n\t\tlet parentNode = node;\n\n\t\t// For implicit paragraphs, base the details on the parent of this node.\n\t\tif ( node.isImplicit ) {\n\t\t\tparentNode = getParentNode( paper, node );\n\t\t}\n\n\t\treturn {\n\t\t\t...sentence,\n\t\t\t// The parent node's start offset is the start offset of the parent node if it doesn't have a `startTag` property.\n\t\t\tparentStartOffset: getStartOffset( parentNode ),\n\t\t\t// The block client id of the parent node.\n\t\t\tparentClientId: parentNode.clientId || \"\",\n\t\t\t// The attribute id of the parent node, if available, otherwise an empty string.\n\t\t\t// Only used for position-based highlighting in sub-blocks of Yoast blocks.\n\t\t\tparentAttributeId: node.attributeId || \"\",\n\t\t\t// Whether the parent node is the first section of Yoast sub-blocks. Only used for position-based highlighting.\n\t\t\tisParentFirstSectionOfBlock: node.isFirstSection || false,\n\t\t};\n\t} ) );\n}\n"],"mappings":";;;;;;;AAAA;AACA;AACA;AACA;AACA;AACA,SAASA,cAAcA,CAAEC,IAAI,EAAG;EAC/B,OAAOA,IAAI,CAACC,kBAAkB,KACzBD,IAAI,CAACC,kBAAkB,CAACC,QAAQ,IAAIF,IAAI,CAACC,kBAAkB,CAACC,QAAQ,CAACC,SAAS,IAAMH,IAAI,CAACC,kBAAkB,CAACG,WAAW,CAAE,IAAI,CAAC;AACpI;;AAEA;AACA;AACA;AACA;AACA;AACA;AACO,SAASC,aAAaA,CAAEC,KAAK,EAAEN,IAAI,EAAG;EAC5C;EACA,OAAOM,KAAK,CAACC,OAAO,CAAC,CAAC,CAACC,OAAO,CAAEC,QAAQ,IAAIA,QAAQ,CAACC,UAAU,IAAID,QAAQ,CAACC,UAAU,CAACC,QAAQ,CAAEX,IAAK,CAAE,CAAC,CAAE,CAAC,CAAE,IAAIA,IAAI;AACvH;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAY,SAAUN,KAAK,EAAG;EAChC;EACA,MAAMO,IAAI,GAAGP,KAAK,CAACC,OAAO,CAAC,CAAC,CAACC,OAAO,CAAEC,QAAQ,IAAI,CAAC,CAAEA,QAAQ,CAACK,SAAU,CAAC;EAEzE,OAAOD,IAAI,CAACE,OAAO,CAAEf,IAAI,IAAIA,IAAI,CAACc,SAAS,CAACE,GAAG,CAAEC,QAAQ,IAAI;IAC5D,IAAIC,UAAU,GAAGlB,IAAI;;IAErB;IACA,IAAKA,IAAI,CAACmB,UAAU,EAAG;MACtBD,UAAU,GAAGb,aAAa,CAAEC,KAAK,EAAEN,IAAK,CAAC;IAC1C;IAEA,OAAO;MACN,GAAGiB,QAAQ;MACX;MACAG,iBAAiB,EAAErB,cAAc,CAAEmB,UAAW,CAAC;MAC/C;MACAG,cAAc,EAAEH,UAAU,CAACI,QAAQ,IAAI,EAAE;MACzC;MACA;MACAC,iBAAiB,EAAEvB,IAAI,CAACwB,WAAW,IAAI,EAAE;MACzC;MACAC,2BAA2B,EAAEzB,IAAI,CAAC0B,cAAc,IAAI;IACrD,CAAC;EACF,CAAE,CAAE,CAAC;AACN","ignoreList":[]}

package/build/languageProcessing/helpers/sentence/memoizedSentenceTokenizer.js

@@ -0,0 +1,37 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _SentenceTokenizer = _interopRequireDefault(require("./SentenceTokenizer"));
+var _lodash = require("lodash");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Returns the sentences from a certain text.
+ *
+ * @param {string} text 					The text to retrieve sentences from.
+ * @param {boolean} [trimSentences=true] 	Whether to trim whitespace from the beginning and end of the sentences or not.
+ *
+ * @returns {Array<string>} The list of sentences in the text.
+ */
+function getSentenceTokenizer(text, trimSentences = true) {
+  const sentenceTokenizer = new _SentenceTokenizer.default();
+  const {
+    tokenizer,
+    tokens
+  } = sentenceTokenizer.createTokenizer();
+  sentenceTokenizer.tokenize(tokenizer, text);
+  return tokens.length === 0 ? [] : sentenceTokenizer.getSentencesFromTokens(tokens, trimSentences);
+}
+
+/*
+ * The second argument to the memoize function is a so-called resolver function.
+ * It creates a cache key consisting of a combination of all arguments to a function.
+ * This is needed because by default, only the first argument to a function is used as the map cache key by the memoize function.
+ * This means that a function is only re-run if the value of the first argument changes.
+ * We want to re-run the getSentenceTokenizer function also when only the second argument changes to prevent cache collisions.
+ * @see https://lodash.com/docs/4.17.15#memoize
+ */
+var _default = exports.default = (0, _lodash.memoize)(getSentenceTokenizer, (...args) => JSON.stringify(args));
+//# sourceMappingURL=memoizedSentenceTokenizer.js.map

package/build/languageProcessing/helpers/sentence/memoizedSentenceTokenizer.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"memoizedSentenceTokenizer.js","names":["_SentenceTokenizer","_interopRequireDefault","require","_lodash","e","__esModule","default","getSentenceTokenizer","text","trimSentences","sentenceTokenizer","SentenceTokenizer","tokenizer","tokens","createTokenizer","tokenize","length","getSentencesFromTokens","_default","exports","memoize","args","JSON","stringify"],"sources":["../../../../src/languageProcessing/helpers/sentence/memoizedSentenceTokenizer.js"],"sourcesContent":["import SentenceTokenizer from \"./SentenceTokenizer\";\nimport { memoize } from \"lodash\";\n\n/**\n * Returns the sentences from a certain text.\n *\n * @param {string} text \t\t\t\t\tThe text to retrieve sentences from.\n * @param {boolean} [trimSentences=true] \tWhether to trim whitespace from the beginning and end of the sentences or not.\n *\n * @returns {Array<string>} The list of sentences in the text.\n */\nfunction getSentenceTokenizer( text, trimSentences = true ) {\n\tconst sentenceTokenizer = new SentenceTokenizer();\n\tconst { tokenizer, tokens } = sentenceTokenizer.createTokenizer();\n\tsentenceTokenizer.tokenize( tokenizer, text );\n\n\treturn ( tokens.length === 0 ? [] : sentenceTokenizer.getSentencesFromTokens( tokens, trimSentences ) );\n}\n\n/*\n * The second argument to the memoize function is a so-called resolver function.\n * It creates a cache key consisting of a combination of all arguments to a function.\n * This is needed because by default, only the first argument to a function is used as the map cache key by the memoize function.\n * This means that a function is only re-run if the value of the first argument changes.\n * We want to re-run the getSentenceTokenizer function also when only the second argument changes to prevent cache collisions.\n * @see https://lodash.com/docs/4.17.15#memoize\n */\nexport default memoize( getSentenceTokenizer, ( ...args ) => JSON.stringify( args ) );\n"],"mappings":";;;;;;AAAA,IAAAA,kBAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,OAAA,GAAAD,OAAA;AAAiC,SAAAD,uBAAAG,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEjC;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASG,oBAAoBA,CAAEC,IAAI,EAAEC,aAAa,GAAG,IAAI,EAAG;EAC3D,MAAMC,iBAAiB,GAAG,IAAIC,0BAAiB,CAAC,CAAC;EACjD,MAAM;IAAEC,SAAS;IAAEC;EAAO,CAAC,GAAGH,iBAAiB,CAACI,eAAe,CAAC,CAAC;EACjEJ,iBAAiB,CAACK,QAAQ,CAAEH,SAAS,EAAEJ,IAAK,CAAC;EAE7C,OAASK,MAAM,CAACG,MAAM,KAAK,CAAC,GAAG,EAAE,GAAGN,iBAAiB,CAACO,sBAAsB,CAAEJ,MAAM,EAAEJ,aAAc,CAAC;AACtG;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AAPA,IAAAS,QAAA,GAAAC,OAAA,CAAAb,OAAA,GAQe,IAAAc,eAAO,EAAEb,oBAAoB,EAAE,CAAE,GAAGc,IAAI,KAAMC,IAAI,CAACC,SAAS,CAAEF,IAAK,CAAE,CAAC","ignoreList":[]}

package/build/languageProcessing/helpers/sentence/sentencesLength.js

@@ -0,0 +1,37 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _countWords = _interopRequireDefault(require("../word/countWords.js"));
+var _lodash = require("lodash");
+var _stripHTMLTags = require("../sanitize/stripHTMLTags.js");
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Returns an array with the length of each sentence.
+ *
+ * @param {Array} sentences Array with sentences from text.
+ * @param {Researcher} 	researcher 	The researcher to use for analysis.
+ *
+ * @returns {Array} Array with the length of each sentence.
+ */
+function _default(sentences, researcher) {
+  const sentencesWordCount = [];
+  (0, _lodash.forEach)(sentences, function (sentence) {
+    // For counting words we want to omit the HTMLtags.
+    const strippedSentence = (0, _stripHTMLTags.stripFullTags)(sentence);
+    // A helper to count characters for languages that don't count number of words for text length.
+    const countCharacters = researcher.getHelper("customCountLength");
+    const length = countCharacters ? countCharacters(strippedSentence) : (0, _countWords.default)(strippedSentence);
+    if (length <= 0) {
+      return;
+    }
+    sentencesWordCount.push({
+      sentence: sentence,
+      sentenceLength: length
+    });
+  });
+  return sentencesWordCount;
+}
+//# sourceMappingURL=sentencesLength.js.map

package/build/languageProcessing/helpers/sentence/sentencesLength.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"sentencesLength.js","names":["_countWords","_interopRequireDefault","require","_lodash","_stripHTMLTags","e","__esModule","default","_default","sentences","researcher","sentencesWordCount","forEach","sentence","strippedSentence","stripHTMLTags","countCharacters","getHelper","length","wordCount","push","sentenceLength"],"sources":["../../../../src/languageProcessing/helpers/sentence/sentencesLength.js"],"sourcesContent":["import wordCount from \"../word/countWords.js\";\nimport { forEach } from \"lodash\";\nimport { stripFullTags as stripHTMLTags } from \"../sanitize/stripHTMLTags.js\";\n\n/**\n * Returns an array with the length of each sentence.\n *\n * @param {Array} sentences Array with sentences from text.\n * @param {Researcher} \tresearcher \tThe researcher to use for analysis.\n *\n * @returns {Array} Array with the length of each sentence.\n */\nexport default function( sentences, researcher ) {\n\tconst sentencesWordCount = [];\n\tforEach( sentences, function( sentence ) {\n\t\t// For counting words we want to omit the HTMLtags.\n\t\tconst strippedSentence = stripHTMLTags( sentence );\n\t\t// A helper to count characters for languages that don't count number of words for text length.\n\t\tconst countCharacters = researcher.getHelper( \"customCountLength\" );\n\t\tconst length = countCharacters ? countCharacters( strippedSentence ) : wordCount( strippedSentence );\n\t\tif ( length <= 0 ) {\n\t\t\treturn;\n\t\t}\n\n\t\tsentencesWordCount.push( {\n\t\t\tsentence: sentence,\n\t\t\tsentenceLength: length,\n\t\t} );\n\t} );\n\treturn sentencesWordCount;\n}\n"],"mappings":";;;;;;AAAA,IAAAA,WAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,OAAA,GAAAD,OAAA;AACA,IAAAE,cAAA,GAAAF,OAAA;AAA8E,SAAAD,uBAAAI,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAE9E;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAAUC,SAAS,EAAEC,UAAU,EAAG;EAChD,MAAMC,kBAAkB,GAAG,EAAE;EAC7B,IAAAC,eAAO,EAAEH,SAAS,EAAE,UAAUI,QAAQ,EAAG;IACxC;IACA,MAAMC,gBAAgB,GAAG,IAAAC,4BAAa,EAAEF,QAAS,CAAC;IAClD;IACA,MAAMG,eAAe,GAAGN,UAAU,CAACO,SAAS,CAAE,mBAAoB,CAAC;IACnE,MAAMC,MAAM,GAAGF,eAAe,GAAGA,eAAe,CAAEF,gBAAiB,CAAC,GAAG,IAAAK,mBAAS,EAAEL,gBAAiB,CAAC;IACpG,IAAKI,MAAM,IAAI,CAAC,EAAG;MAClB;IACD;IAEAP,kBAAkB,CAACS,IAAI,CAAE;MACxBP,QAAQ,EAAEA,QAAQ;MAClBQ,cAAc,EAAEH;IACjB,CAAE,CAAC;EACJ,CAAE,CAAC;EACH,OAAOP,kBAAkB;AAC1B","ignoreList":[]}

package/build/languageProcessing/helpers/syllables/DeviationFragment.js

@@ -0,0 +1,108 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _lodash = require("lodash");
+/**
+ * A DeviationFragment represents a partial deviation when counting syllables.
+ */
+class DeviationFragment {
+  /**
+   * Constructs a new DeviationFragment.
+   *
+   * @param {Object} options Extra options that are used to match this deviation fragment.
+   * @param {string} options.location The location in the word where this deviation can occur.
+   * @param {string} options.word The actual string that should be counted differently.
+   * @param {number} options.syllables The amount of syllables this fragment has.
+   * @param {string[]} [options.notFollowedBy] A list of characters that this fragment shouldn't be followed with.
+   * @param {string[]} [options.alsoFollowedBy] A list of characters that this fragment could be followed with.
+   *
+   * @constructor
+   */
+  constructor(options) {
+    this._location = options.location;
+    this._fragment = options.word;
+    this._syllables = options.syllables;
+    this._regex = null;
+    this._options = (0, _lodash.pick)(options, ["notFollowedBy", "alsoFollowedBy"]);
+  }
+
+  /**
+   * Creates a regex that matches this fragment inside a word.
+   *
+   * @returns {void}
+   */
+  createRegex() {
+    const options = this._options;
+    let fragment = this._fragment;
+    if (!(0, _lodash.isUndefined)(options.notFollowedBy)) {
+      fragment += "(?![" + options.notFollowedBy.join("") + "])";
+    }
+    if (!(0, _lodash.isUndefined)(options.alsoFollowedBy)) {
+      fragment += "[" + options.alsoFollowedBy.join("") + "]?";
+    }
+    let regexString;
+    switch (this._location) {
+      case "atBeginning":
+        regexString = "^" + fragment;
+        break;
+      case "atEnd":
+        regexString = fragment + "$";
+        break;
+      case "atBeginningOrEnd":
+        regexString = "(^" + fragment + ")|(" + fragment + "$)";
+        break;
+      default:
+        regexString = fragment;
+        break;
+    }
+    this._regex = new RegExp(regexString);
+  }
+
+  /**
+   * Returns the regex that matches this fragment inside a word.
+   *
+   * @returns {RegExp} The regex that matches this fragment.
+   */
+  getRegex() {
+    if (null === this._regex) {
+      this.createRegex();
+    }
+    return this._regex;
+  }
+
+  /**
+   * Returns whether this fragment occurs in a word.
+   *
+   * @param {string} word The word to match the fragment in.
+   * @returns {boolean} Whether or not this fragment occurs in a word.
+   */
+  occursIn(word) {
+    const regex = this.getRegex();
+    return regex.test(word);
+  }
+
+  /**
+   * Removes this fragment from the given word.
+   *
+   * @param {string} word The word to remove this fragment from.
+   * @returns {string} The modified word.
+   */
+  removeFrom(word) {
+    // Replace by a space to keep the remaining parts separated.
+    return word.replace(this._fragment, " ");
+  }
+
+  /**
+   * Returns the amount of syllables for this fragment.
+   *
+   * @returns {number} The amount of syllables for this fragment.
+   */
+  getSyllables() {
+    return this._syllables;
+  }
+}
+exports.default = DeviationFragment;
+//# sourceMappingURL=DeviationFragment.js.map

package/build/languageProcessing/helpers/syllables/DeviationFragment.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"DeviationFragment.js","names":["_lodash","require","DeviationFragment","constructor","options","_location","location","_fragment","word","_syllables","syllables","_regex","_options","pick","createRegex","fragment","isUndefined","notFollowedBy","join","alsoFollowedBy","regexString","RegExp","getRegex","occursIn","regex","test","removeFrom","replace","getSyllables","exports","default"],"sources":["../../../../src/languageProcessing/helpers/syllables/DeviationFragment.js"],"sourcesContent":["import { isUndefined, pick } from \"lodash\";\n\n/**\n * A DeviationFragment represents a partial deviation when counting syllables.\n */\nexport default class DeviationFragment {\n\t/**\n\t * Constructs a new DeviationFragment.\n\t *\n\t * @param {Object} options Extra options that are used to match this deviation fragment.\n\t * @param {string} options.location The location in the word where this deviation can occur.\n\t * @param {string} options.word The actual string that should be counted differently.\n\t * @param {number} options.syllables The amount of syllables this fragment has.\n\t * @param {string[]} [options.notFollowedBy] A list of characters that this fragment shouldn't be followed with.\n\t * @param {string[]} [options.alsoFollowedBy] A list of characters that this fragment could be followed with.\n\t *\n\t * @constructor\n\t */\n\tconstructor( options ) {\n\t\tthis._location = options.location;\n\t\tthis._fragment = options.word;\n\t\tthis._syllables = options.syllables;\n\t\tthis._regex = null;\n\n\t\tthis._options = pick( options, [ \"notFollowedBy\", \"alsoFollowedBy\" ] );\n\t}\n\n\t/**\n\t * Creates a regex that matches this fragment inside a word.\n\t *\n\t * @returns {void}\n\t */\n\tcreateRegex() {\n\t\tconst options = this._options;\n\n\t\tlet fragment = this._fragment;\n\n\t\tif ( ! isUndefined( options.notFollowedBy ) ) {\n\t\t\tfragment += \"(?![\" + options.notFollowedBy.join( \"\" ) + \"])\";\n\t\t}\n\n\t\tif ( ! isUndefined( options.alsoFollowedBy ) ) {\n\t\t\tfragment += \"[\" + options.alsoFollowedBy.join( \"\" ) + \"]?\";\n\t\t}\n\n\t\tlet regexString;\n\t\tswitch ( this._location ) {\n\t\t\tcase \"atBeginning\":\n\t\t\t\tregexString = \"^\" + fragment;\n\t\t\t\tbreak;\n\n\t\t\tcase \"atEnd\":\n\t\t\t\tregexString = fragment + \"$\";\n\t\t\t\tbreak;\n\n\t\t\tcase \"atBeginningOrEnd\":\n\t\t\t\tregexString = \"(^\" + fragment + \")|(\" + fragment + \"$)\";\n\t\t\t\tbreak;\n\n\t\t\tdefault:\n\t\t\t\tregexString = fragment;\n\t\t\t\tbreak;\n\t\t}\n\n\t\tthis._regex = new RegExp( regexString );\n\t}\n\n\t/**\n\t * Returns the regex that matches this fragment inside a word.\n\t *\n\t * @returns {RegExp} The regex that matches this fragment.\n\t */\n\tgetRegex() {\n\t\tif ( null === this._regex ) {\n\t\t\tthis.createRegex();\n\t\t}\n\n\t\treturn this._regex;\n\t}\n\n\t/**\n\t * Returns whether this fragment occurs in a word.\n\t *\n\t * @param {string} word The word to match the fragment in.\n\t * @returns {boolean} Whether or not this fragment occurs in a word.\n\t */\n\toccursIn( word ) {\n\t\tconst regex = this.getRegex();\n\n\t\treturn regex.test( word );\n\t}\n\n\t/**\n\t * Removes this fragment from the given word.\n\t *\n\t * @param {string} word The word to remove this fragment from.\n\t * @returns {string} The modified word.\n\t */\n\tremoveFrom( word ) {\n\t\t// Replace by a space to keep the remaining parts separated.\n\t\treturn word.replace( this._fragment, \" \" );\n\t}\n\n\t/**\n\t * Returns the amount of syllables for this fragment.\n\t *\n\t * @returns {number} The amount of syllables for this fragment.\n\t */\n\tgetSyllables() {\n\t\treturn this._syllables;\n\t}\n}\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AAEA;AACA;AACA;AACe,MAAMC,iBAAiB,CAAC;EACtC;AACD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;EACCC,WAAWA,CAAEC,OAAO,EAAG;IACtB,IAAI,CAACC,SAAS,GAAGD,OAAO,CAACE,QAAQ;IACjC,IAAI,CAACC,SAAS,GAAGH,OAAO,CAACI,IAAI;IAC7B,IAAI,CAACC,UAAU,GAAGL,OAAO,CAACM,SAAS;IACnC,IAAI,CAACC,MAAM,GAAG,IAAI;IAElB,IAAI,CAACC,QAAQ,GAAG,IAAAC,YAAI,EAAET,OAAO,EAAE,CAAE,eAAe,EAAE,gBAAgB,CAAG,CAAC;EACvE;;EAEA;AACD;AACA;AACA;AACA;EACCU,WAAWA,CAAA,EAAG;IACb,MAAMV,OAAO,GAAG,IAAI,CAACQ,QAAQ;IAE7B,IAAIG,QAAQ,GAAG,IAAI,CAACR,SAAS;IAE7B,IAAK,CAAE,IAAAS,mBAAW,EAAEZ,OAAO,CAACa,aAAc,CAAC,EAAG;MAC7CF,QAAQ,IAAI,MAAM,GAAGX,OAAO,CAACa,aAAa,CAACC,IAAI,CAAE,EAAG,CAAC,GAAG,IAAI;IAC7D;IAEA,IAAK,CAAE,IAAAF,mBAAW,EAAEZ,OAAO,CAACe,cAAe,CAAC,EAAG;MAC9CJ,QAAQ,IAAI,GAAG,GAAGX,OAAO,CAACe,cAAc,CAACD,IAAI,CAAE,EAAG,CAAC,GAAG,IAAI;IAC3D;IAEA,IAAIE,WAAW;IACf,QAAS,IAAI,CAACf,SAAS;MACtB,KAAK,aAAa;QACjBe,WAAW,GAAG,GAAG,GAAGL,QAAQ;QAC5B;MAED,KAAK,OAAO;QACXK,WAAW,GAAGL,QAAQ,GAAG,GAAG;QAC5B;MAED,KAAK,kBAAkB;QACtBK,WAAW,GAAG,IAAI,GAAGL,QAAQ,GAAG,KAAK,GAAGA,QAAQ,GAAG,IAAI;QACvD;MAED;QACCK,WAAW,GAAGL,QAAQ;QACtB;IACF;IAEA,IAAI,CAACJ,MAAM,GAAG,IAAIU,MAAM,CAAED,WAAY,CAAC;EACxC;;EAEA;AACD;AACA;AACA;AACA;EACCE,QAAQA,CAAA,EAAG;IACV,IAAK,IAAI,KAAK,IAAI,CAACX,MAAM,EAAG;MAC3B,IAAI,CAACG,WAAW,CAAC,CAAC;IACnB;IAEA,OAAO,IAAI,CAACH,MAAM;EACnB;;EAEA;AACD;AACA;AACA;AACA;AACA;EACCY,QAAQA,CAAEf,IAAI,EAAG;IAChB,MAAMgB,KAAK,GAAG,IAAI,CAACF,QAAQ,CAAC,CAAC;IAE7B,OAAOE,KAAK,CAACC,IAAI,CAAEjB,IAAK,CAAC;EAC1B;;EAEA;AACD;AACA;AACA;AACA;AACA;EACCkB,UAAUA,CAAElB,IAAI,EAAG;IAClB;IACA,OAAOA,IAAI,CAACmB,OAAO,CAAE,IAAI,CAACpB,SAAS,EAAE,GAAI,CAAC;EAC3C;;EAEA;AACD;AACA;AACA;AACA;EACCqB,YAAYA,CAAA,EAAG;IACd,OAAO,IAAI,CAACnB,UAAU;EACvB;AACD;AAACoB,OAAA,CAAAC,OAAA,GAAA5B,iBAAA","ignoreList":[]}

package/build/languageProcessing/helpers/syllables/countSyllables.js

@@ -0,0 +1,173 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = exports.countSyllablesInWord = void 0;
+var _getWords = _interopRequireDefault(require("../word/getWords.js"));
+var _lodash = require("lodash");
+var _syllableCountIterator = _interopRequireDefault(require("./syllableCountIterator.js"));
+var _DeviationFragment = _interopRequireDefault(require("./DeviationFragment"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/** @module stringProcessing/countSyllables */
+
+/**
+ * Counts vowel groups inside a word.
+ *
+ * @param {string} word         A text with words to count syllables.
+ * @param {Object} syllables    The syllables data for the specific language.
+ *
+ * @returns {number} the syllable count.
+ */
+const countVowelGroups = function (word, syllables) {
+  let numberOfSyllables = 0;
+  const vowelRegex = new RegExp("[^" + syllables.vowels + "]", "ig");
+  const foundVowels = word.split(vowelRegex);
+  const filteredWords = (0, _lodash.filter)(foundVowels, function (vowel) {
+    return vowel !== "";
+  });
+  numberOfSyllables += filteredWords.length;
+  return numberOfSyllables;
+};
+
+/**
+ * Counts the syllables using vowel exclusions. These are used for groups of vowels that are more or less
+ * than 1 syllable.
+ *
+ * @param {String} word         The word to count syllables of.
+ * @param {Object} syllables    The syllables data for the specific language.
+ *
+ * @returns {number} The number of syllables found in the given word.
+ */
+const countVowelDeviations = function (word, syllables) {
+  const syllableCountIterator = new _syllableCountIterator.default(syllables);
+  return syllableCountIterator.countSyllables(word);
+};
+
+/**
+ * Returns the number of syllables for the word if it is in the list of full word deviations.
+ *
+ * @param {String} word         The word to retrieve the syllables for.
+ * @param {Object} syllables    The syllables data for the specific language.
+ *
+ * @returns {number} The number of syllables found.
+ */
+const countFullWordDeviations = function (word, syllables) {
+  const fullWordDeviations = syllables.deviations.words.full;
+  const deviation = (0, _lodash.find)(fullWordDeviations, function (fullWordDeviation) {
+    return fullWordDeviation.word === word;
+  });
+  if (!(0, _lodash.isUndefined)(deviation)) {
+    return deviation.syllables;
+  }
+  return 0;
+};
+
+/**
+ * Creates an array of deviation fragments for a certain locale.
+ *
+ * @param {Object} syllableConfig Syllable config for a certain locale.
+ * @returns {DeviationFragment[]} A list of deviation fragments
+ */
+function createDeviationFragments(syllableConfig) {
+  let deviationFragments = [];
+  const deviations = syllableConfig.deviations;
+  deviationFragments = (0, _lodash.flatMap)(deviations.words.fragments, function (fragments, fragmentLocation) {
+    return (0, _lodash.map)(fragments, function (fragment) {
+      fragment.location = fragmentLocation;
+      return new _DeviationFragment.default(fragment);
+    });
+  });
+  return deviationFragments;
+}
+const createDeviationFragmentsMemoized = (0, _lodash.memoize)(createDeviationFragments);
+
+/**
+ * Counts syllables in partial exclusions. If these are found, returns the number of syllables found, and the modified word.
+ * The word is modified so the excluded part isn't counted by the normal syllable counter.
+ *
+ * @param {String} word 		The word to count syllables of.
+ * @param {Object} syllables    The syllables data for the specific language.
+ *
+ * @returns {object} The number of syllables found and the modified word.
+ */
+const countPartialWordDeviations = function (word, syllables) {
+  const deviationFragments = createDeviationFragmentsMemoized(syllables);
+  let remainingParts = word;
+  let syllableCount = 0;
+  (0, _lodash.forEach)(deviationFragments, function (deviationFragment) {
+    if (deviationFragment.occursIn(remainingParts)) {
+      remainingParts = deviationFragment.removeFrom(remainingParts);
+      syllableCount += deviationFragment.getSyllables();
+    }
+  });
+  return {
+    word: remainingParts,
+    syllableCount: syllableCount
+  };
+};
+
+/**
+ * Count the number of syllables in a word, using vowels and exceptions.
+ *
+ * @param {String} word         The word to count the number of syllables of.
+ * @param {Object} syllables    The syllables data for the specific language.
+ *
+ * @returns {number} The number of syllables found in a word.
+ */
+const countUsingVowels = function (word, syllables) {
+  let syllableCount = 0;
+  syllableCount += countVowelGroups(word, syllables);
+  if (!(0, _lodash.isUndefined)(syllables.deviations) && !(0, _lodash.isUndefined)(syllables.deviations.vowels)) {
+    syllableCount += countVowelDeviations(word, syllables);
+  }
+  return syllableCount;
+};
+
+/**
+ * Counts the number of syllables in a word.
+ *
+ * @param {string} word         The word to count syllables of.
+ * @param {Object} syllables    The syllables data for the specific language.
+ *
+ * @returns {number} The syllable count for the word.
+ */
+const countSyllablesInWord = function (word, syllables) {
+  let syllableCount = 0;
+  if (!(0, _lodash.isUndefined)(syllables.deviations) && !(0, _lodash.isUndefined)(syllables.deviations.words)) {
+    if (!(0, _lodash.isUndefined)(syllables.deviations.words.full)) {
+      const fullWordExclusion = countFullWordDeviations(word, syllables);
+      if (fullWordExclusion !== 0) {
+        return fullWordExclusion;
+      }
+    }
+    if (!(0, _lodash.isUndefined)(syllables.deviations.words.fragments)) {
+      const partialExclusions = countPartialWordDeviations(word, syllables);
+      word = partialExclusions.word;
+      syllableCount += partialExclusions.syllableCount;
+    }
+  }
+  syllableCount += countUsingVowels(word, syllables);
+  return syllableCount;
+};
+
+/**
+ * Counts the number of syllables in a text per word based on vowels.
+ * Uses exclusion words for words that cannot be matched with vowel matching.
+ *
+ * @param {String} text         The text to count the syllables of.
+ * @param {Object} syllables    The syllables data for the specific language.
+ *
+ * @returns {int} The total number of syllables found in the text.
+ */
+exports.countSyllablesInWord = countSyllablesInWord;
+const countSyllablesInText = function (text, syllables) {
+  text = text.toLocaleLowerCase();
+  const words = (0, _getWords.default)(text);
+  const syllableCounts = (0, _lodash.map)(words, function (word) {
+    return countSyllablesInWord(word, syllables);
+  });
+  return (0, _lodash.sum)(syllableCounts);
+};
+var _default = exports.default = countSyllablesInText;
+//# sourceMappingURL=countSyllables.js.map

package/build/languageProcessing/helpers/syllables/countSyllables.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"countSyllables.js","names":["_getWords","_interopRequireDefault","require","_lodash","_syllableCountIterator","_DeviationFragment","e","__esModule","default","countVowelGroups","word","syllables","numberOfSyllables","vowelRegex","RegExp","vowels","foundVowels","split","filteredWords","filter","vowel","length","countVowelDeviations","syllableCountIterator","SyllableCountIterator","countSyllables","countFullWordDeviations","fullWordDeviations","deviations","words","full","deviation","find","fullWordDeviation","isUndefined","createDeviationFragments","syllableConfig","deviationFragments","flatMap","fragments","fragmentLocation","map","fragment","location","DeviationFragment","createDeviationFragmentsMemoized","memoize","countPartialWordDeviations","remainingParts","syllableCount","forEach","deviationFragment","occursIn","removeFrom","getSyllables","countUsingVowels","countSyllablesInWord","fullWordExclusion","partialExclusions","exports","countSyllablesInText","text","toLocaleLowerCase","getWords","syllableCounts","sum","_default"],"sources":["../../../../src/languageProcessing/helpers/syllables/countSyllables.js"],"sourcesContent":["/** @module stringProcessing/countSyllables */\n\nimport getWords from \"../word/getWords.js\";\n\nimport { filter, find, flatMap, forEach, isUndefined, map, memoize, sum } from \"lodash\";\n\nimport SyllableCountIterator from \"./syllableCountIterator.js\";\nimport DeviationFragment from \"./DeviationFragment\";\n\n/**\n * Counts vowel groups inside a word.\n *\n * @param {string} word         A text with words to count syllables.\n * @param {Object} syllables    The syllables data for the specific language.\n *\n * @returns {number} the syllable count.\n */\nconst countVowelGroups = function( word, syllables ) {\n\tlet numberOfSyllables = 0;\n\tconst vowelRegex = new RegExp( \"[^\" + syllables.vowels + \"]\", \"ig\" );\n\tconst foundVowels = word.split( vowelRegex );\n\tconst filteredWords = filter( foundVowels, function( vowel ) {\n\t\treturn vowel !== \"\";\n\t} );\n\tnumberOfSyllables += filteredWords.length;\n\n\treturn numberOfSyllables;\n};\n\n/**\n * Counts the syllables using vowel exclusions. These are used for groups of vowels that are more or less\n * than 1 syllable.\n *\n * @param {String} word         The word to count syllables of.\n * @param {Object} syllables    The syllables data for the specific language.\n *\n * @returns {number} The number of syllables found in the given word.\n */\nconst countVowelDeviations = function( word, syllables ) {\n\tconst syllableCountIterator = new SyllableCountIterator( syllables );\n\treturn syllableCountIterator.countSyllables( word );\n};\n\n/**\n * Returns the number of syllables for the word if it is in the list of full word deviations.\n *\n * @param {String} word         The word to retrieve the syllables for.\n * @param {Object} syllables    The syllables data for the specific language.\n *\n * @returns {number} The number of syllables found.\n */\nconst countFullWordDeviations = function( word, syllables ) {\n\tconst fullWordDeviations = syllables.deviations.words.full;\n\n\tconst deviation = find( fullWordDeviations, function( fullWordDeviation ) {\n\t\treturn fullWordDeviation.word === word;\n\t} );\n\n\tif ( ! isUndefined( deviation ) ) {\n\t\treturn deviation.syllables;\n\t}\n\n\treturn 0;\n};\n\n/**\n * Creates an array of deviation fragments for a certain locale.\n *\n * @param {Object} syllableConfig Syllable config for a certain locale.\n * @returns {DeviationFragment[]} A list of deviation fragments\n */\nfunction createDeviationFragments( syllableConfig ) {\n\tlet deviationFragments = [];\n\n\tconst deviations = syllableConfig.deviations;\n\n\tdeviationFragments = flatMap( deviations.words.fragments, function( fragments, fragmentLocation ) {\n\t\treturn map( fragments, function( fragment ) {\n\t\t\tfragment.location = fragmentLocation;\n\n\t\t\treturn new DeviationFragment( fragment );\n\t\t} );\n\t} );\n\n\treturn deviationFragments;\n}\n\nconst createDeviationFragmentsMemoized = memoize( createDeviationFragments );\n\n/**\n * Counts syllables in partial exclusions. If these are found, returns the number of syllables found, and the modified word.\n * The word is modified so the excluded part isn't counted by the normal syllable counter.\n *\n * @param {String} word \t\tThe word to count syllables of.\n * @param {Object} syllables    The syllables data for the specific language.\n *\n * @returns {object} The number of syllables found and the modified word.\n */\nconst countPartialWordDeviations = function( word, syllables ) {\n\tconst deviationFragments = createDeviationFragmentsMemoized( syllables );\n\tlet remainingParts = word;\n\tlet syllableCount = 0;\n\n\tforEach( deviationFragments, function( deviationFragment ) {\n\t\tif ( deviationFragment.occursIn( remainingParts ) ) {\n\t\t\tremainingParts = deviationFragment.removeFrom( remainingParts );\n\t\t\tsyllableCount += deviationFragment.getSyllables();\n\t\t}\n\t} );\n\n\treturn { word: remainingParts, syllableCount: syllableCount };\n};\n\n/**\n * Count the number of syllables in a word, using vowels and exceptions.\n *\n * @param {String} word         The word to count the number of syllables of.\n * @param {Object} syllables    The syllables data for the specific language.\n *\n * @returns {number} The number of syllables found in a word.\n */\nconst countUsingVowels = function( word, syllables ) {\n\tlet syllableCount = 0;\n\n\tsyllableCount += countVowelGroups( word, syllables );\n\tif ( ! isUndefined( syllables.deviations ) && ! isUndefined( syllables.deviations.vowels ) ) {\n\t\tsyllableCount += countVowelDeviations( word, syllables );\n\t}\n\treturn syllableCount;\n};\n\n/**\n * Counts the number of syllables in a word.\n *\n * @param {string} word         The word to count syllables of.\n * @param {Object} syllables    The syllables data for the specific language.\n *\n * @returns {number} The syllable count for the word.\n */\nexport const countSyllablesInWord = function( word, syllables ) {\n\tlet syllableCount = 0;\n\n\tif ( ! isUndefined( syllables.deviations ) && ! isUndefined( syllables.deviations.words ) ) {\n\t\tif ( ! isUndefined( syllables.deviations.words.full ) ) {\n\t\t\tconst fullWordExclusion = countFullWordDeviations( word, syllables );\n\t\t\tif ( fullWordExclusion !== 0 ) {\n\t\t\t\treturn fullWordExclusion;\n\t\t\t}\n\t\t}\n\n\t\tif ( ! isUndefined( syllables.deviations.words.fragments ) ) {\n\t\t\tconst partialExclusions = countPartialWordDeviations( word, syllables );\n\t\t\tword = partialExclusions.word;\n\t\t\tsyllableCount += partialExclusions.syllableCount;\n\t\t}\n\t}\n\tsyllableCount += countUsingVowels( word, syllables );\n\n\treturn syllableCount;\n};\n\n/**\n * Counts the number of syllables in a text per word based on vowels.\n * Uses exclusion words for words that cannot be matched with vowel matching.\n *\n * @param {String} text         The text to count the syllables of.\n * @param {Object} syllables    The syllables data for the specific language.\n *\n * @returns {int} The total number of syllables found in the text.\n */\nconst countSyllablesInText = function( text, syllables ) {\n\ttext = text.toLocaleLowerCase();\n\tconst words = getWords( text );\n\n\tconst syllableCounts = map( words,  function( word ) {\n\t\treturn countSyllablesInWord( word, syllables );\n\t} );\n\n\treturn sum( syllableCounts );\n};\n\nexport default countSyllablesInText;\n"],"mappings":";;;;;;AAEA,IAAAA,SAAA,GAAAC,sBAAA,CAAAC,OAAA;AAEA,IAAAC,OAAA,GAAAD,OAAA;AAEA,IAAAE,sBAAA,GAAAH,sBAAA,CAAAC,OAAA;AACA,IAAAG,kBAAA,GAAAJ,sBAAA,CAAAC,OAAA;AAAoD,SAAAD,uBAAAK,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAPpD;;AASA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,gBAAgB,GAAG,SAAAA,CAAUC,IAAI,EAAEC,SAAS,EAAG;EACpD,IAAIC,iBAAiB,GAAG,CAAC;EACzB,MAAMC,UAAU,GAAG,IAAIC,MAAM,CAAE,IAAI,GAAGH,SAAS,CAACI,MAAM,GAAG,GAAG,EAAE,IAAK,CAAC;EACpE,MAAMC,WAAW,GAAGN,IAAI,CAACO,KAAK,CAAEJ,UAAW,CAAC;EAC5C,MAAMK,aAAa,GAAG,IAAAC,cAAM,EAAEH,WAAW,EAAE,UAAUI,KAAK,EAAG;IAC5D,OAAOA,KAAK,KAAK,EAAE;EACpB,CAAE,CAAC;EACHR,iBAAiB,IAAIM,aAAa,CAACG,MAAM;EAEzC,OAAOT,iBAAiB;AACzB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMU,oBAAoB,GAAG,SAAAA,CAAUZ,IAAI,EAAEC,SAAS,EAAG;EACxD,MAAMY,qBAAqB,GAAG,IAAIC,8BAAqB,CAAEb,SAAU,CAAC;EACpE,OAAOY,qBAAqB,CAACE,cAAc,CAAEf,IAAK,CAAC;AACpD,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMgB,uBAAuB,GAAG,SAAAA,CAAUhB,IAAI,EAAEC,SAAS,EAAG;EAC3D,MAAMgB,kBAAkB,GAAGhB,SAAS,CAACiB,UAAU,CAACC,KAAK,CAACC,IAAI;EAE1D,MAAMC,SAAS,GAAG,IAAAC,YAAI,EAAEL,kBAAkB,EAAE,UAAUM,iBAAiB,EAAG;IACzE,OAAOA,iBAAiB,CAACvB,IAAI,KAAKA,IAAI;EACvC,CAAE,CAAC;EAEH,IAAK,CAAE,IAAAwB,mBAAW,EAAEH,SAAU,CAAC,EAAG;IACjC,OAAOA,SAAS,CAACpB,SAAS;EAC3B;EAEA,OAAO,CAAC;AACT,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA,SAASwB,wBAAwBA,CAAEC,cAAc,EAAG;EACnD,IAAIC,kBAAkB,GAAG,EAAE;EAE3B,MAAMT,UAAU,GAAGQ,cAAc,CAACR,UAAU;EAE5CS,kBAAkB,GAAG,IAAAC,eAAO,EAAEV,UAAU,CAACC,KAAK,CAACU,SAAS,EAAE,UAAUA,SAAS,EAAEC,gBAAgB,EAAG;IACjG,OAAO,IAAAC,WAAG,EAAEF,SAAS,EAAE,UAAUG,QAAQ,EAAG;MAC3CA,QAAQ,CAACC,QAAQ,GAAGH,gBAAgB;MAEpC,OAAO,IAAII,0BAAiB,CAAEF,QAAS,CAAC;IACzC,CAAE,CAAC;EACJ,CAAE,CAAC;EAEH,OAAOL,kBAAkB;AAC1B;AAEA,MAAMQ,gCAAgC,GAAG,IAAAC,eAAO,EAAEX,wBAAyB,CAAC;;AAE5E;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMY,0BAA0B,GAAG,SAAAA,CAAUrC,IAAI,EAAEC,SAAS,EAAG;EAC9D,MAAM0B,kBAAkB,GAAGQ,gCAAgC,CAAElC,SAAU,CAAC;EACxE,IAAIqC,cAAc,GAAGtC,IAAI;EACzB,IAAIuC,aAAa,GAAG,CAAC;EAErB,IAAAC,eAAO,EAAEb,kBAAkB,EAAE,UAAUc,iBAAiB,EAAG;IAC1D,IAAKA,iBAAiB,CAACC,QAAQ,CAAEJ,cAAe,CAAC,EAAG;MACnDA,cAAc,GAAGG,iBAAiB,CAACE,UAAU,CAAEL,cAAe,CAAC;MAC/DC,aAAa,IAAIE,iBAAiB,CAACG,YAAY,CAAC,CAAC;IAClD;EACD,CAAE,CAAC;EAEH,OAAO;IAAE5C,IAAI,EAAEsC,cAAc;IAAEC,aAAa,EAAEA;EAAc,CAAC;AAC9D,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMM,gBAAgB,GAAG,SAAAA,CAAU7C,IAAI,EAAEC,SAAS,EAAG;EACpD,IAAIsC,aAAa,GAAG,CAAC;EAErBA,aAAa,IAAIxC,gBAAgB,CAAEC,IAAI,EAAEC,SAAU,CAAC;EACpD,IAAK,CAAE,IAAAuB,mBAAW,EAAEvB,SAAS,CAACiB,UAAW,CAAC,IAAI,CAAE,IAAAM,mBAAW,EAAEvB,SAAS,CAACiB,UAAU,CAACb,MAAO,CAAC,EAAG;IAC5FkC,aAAa,IAAI3B,oBAAoB,CAAEZ,IAAI,EAAEC,SAAU,CAAC;EACzD;EACA,OAAOsC,aAAa;AACrB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACO,MAAMO,oBAAoB,GAAG,SAAAA,CAAU9C,IAAI,EAAEC,SAAS,EAAG;EAC/D,IAAIsC,aAAa,GAAG,CAAC;EAErB,IAAK,CAAE,IAAAf,mBAAW,EAAEvB,SAAS,CAACiB,UAAW,CAAC,IAAI,CAAE,IAAAM,mBAAW,EAAEvB,SAAS,CAACiB,UAAU,CAACC,KAAM,CAAC,EAAG;IAC3F,IAAK,CAAE,IAAAK,mBAAW,EAAEvB,SAAS,CAACiB,UAAU,CAACC,KAAK,CAACC,IAAK,CAAC,EAAG;MACvD,MAAM2B,iBAAiB,GAAG/B,uBAAuB,CAAEhB,IAAI,EAAEC,SAAU,CAAC;MACpE,IAAK8C,iBAAiB,KAAK,CAAC,EAAG;QAC9B,OAAOA,iBAAiB;MACzB;IACD;IAEA,IAAK,CAAE,IAAAvB,mBAAW,EAAEvB,SAAS,CAACiB,UAAU,CAACC,KAAK,CAACU,SAAU,CAAC,EAAG;MAC5D,MAAMmB,iBAAiB,GAAGX,0BAA0B,CAAErC,IAAI,EAAEC,SAAU,CAAC;MACvED,IAAI,GAAGgD,iBAAiB,CAAChD,IAAI;MAC7BuC,aAAa,IAAIS,iBAAiB,CAACT,aAAa;IACjD;EACD;EACAA,aAAa,IAAIM,gBAAgB,CAAE7C,IAAI,EAAEC,SAAU,CAAC;EAEpD,OAAOsC,aAAa;AACrB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AARAU,OAAA,CAAAH,oBAAA,GAAAA,oBAAA;AASA,MAAMI,oBAAoB,GAAG,SAAAA,CAAUC,IAAI,EAAElD,SAAS,EAAG;EACxDkD,IAAI,GAAGA,IAAI,CAACC,iBAAiB,CAAC,CAAC;EAC/B,MAAMjC,KAAK,GAAG,IAAAkC,iBAAQ,EAAEF,IAAK,CAAC;EAE9B,MAAMG,cAAc,GAAG,IAAAvB,WAAG,EAAEZ,KAAK,EAAG,UAAUnB,IAAI,EAAG;IACpD,OAAO8C,oBAAoB,CAAE9C,IAAI,EAAEC,SAAU,CAAC;EAC/C,CAAE,CAAC;EAEH,OAAO,IAAAsD,WAAG,EAAED,cAAe,CAAC;AAC7B,CAAC;AAAC,IAAAE,QAAA,GAAAP,OAAA,CAAAnD,OAAA,GAEaoD,oBAAoB","ignoreList":[]}