axyseo 2.0.0-alpha.2 → 2.1.0

package/build/languageProcessing/helpers/word/getWords.js

@@ -1,18 +1,8 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
-var _sanitizeString = _interopRequireDefault(require("../sanitize/sanitizeString"));
-var _lodash = require("lodash");
-var _removePunctuation = _interopRequireWildcard(require("../sanitize/removePunctuation.js"));
-function _getRequireWildcardCache(e) { if ("function" != typeof WeakMap) return null; var r = new WeakMap(), t = new WeakMap(); return (_getRequireWildcardCache = function (e) { return e ? t : r; })(e); }
-function _interopRequireWildcard(e, r) { if (!r && e && e.__esModule) return e; if (null === e || "object" != typeof e && "function" != typeof e) return { default: e }; var t = _getRequireWildcardCache(r); if (t && t.has(e)) return t.get(e); var n = { __proto__: null }, a = Object.defineProperty && Object.getOwnPropertyDescriptor; for (var u in e) if ("default" !== u && {}.hasOwnProperty.call(e, u)) { var i = a ? Object.getOwnPropertyDescriptor(e, u) : null; i && (i.get || i.set) ? Object.defineProperty(n, u, i) : n[u] = e[u]; } return n.default = e, t && t.set(e, n), n; }
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /** @module stringProcessing/countWords */
-
-const punctuationRegex = new RegExp(`([${_removePunctuation.punctuationRegexString}])`, "g");
+import sanitizeString from "../sanitize/sanitizeString";
+import { filter, flatMap } from "lodash";
+import removePunctuation, { punctuationRegexString } from "../sanitize/removePunctuation.js";
+const punctuationRegex = new RegExp(`([${punctuationRegexString}])`, "g");
 
 /**
  * Returns an array with words used in the text.
@@ -23,24 +13,24 @@ const punctuationRegex = new RegExp(`([${_removePunctuation.punctuationRegexStri
  *
  * @returns {Array} The array with all words.
  */
-function _default(text, wordBoundaryRegexString = "\\s", shouldRemovePunctuation = true) {
+export default function (text, wordBoundaryRegexString = "\\s", shouldRemovePunctuation = true) {
   // Unify whitespaces and non-breaking spaces, remove table of content and strip the tags and multiple spaces.
-  text = (0, _sanitizeString.default)(text);
+  text = sanitizeString(text);
   if (text === "") {
     return [];
   }
   const wordBoundaryRegex = new RegExp(wordBoundaryRegexString, "g");
   let words = text.split(wordBoundaryRegex);
   if (shouldRemovePunctuation) {
-    words = words.map(_removePunctuation.default);
+    words = words.map(removePunctuation);
   } else {
     // If punctuation is not removed, punctuation marks are tokenized as if they were words.
-    words = (0, _lodash.flatMap)(words, word => {
+    words = flatMap(words, word => {
       const newWord = word.replace(punctuationRegex, " $1 ");
       return newWord.split(" ");
     });
   }
-  return (0, _lodash.filter)(words, function (word) {
+  return filter(words, function (word) {
     return word.trim() !== "";
   });
 }

package/build/languageProcessing/helpers/word/getWords.js.map

@@ -1 +1 @@
-{"version":3,"file":"getWords.js","names":["_sanitizeString","_interopRequireDefault","require","_lodash","_removePunctuation","_interopRequireWildcard","_getRequireWildcardCache","e","WeakMap","r","t","__esModule","default","has","get","n","__proto__","a","Object","defineProperty","getOwnPropertyDescriptor","u","hasOwnProperty","call","i","set","punctuationRegex","RegExp","punctuationRegexString","_default","text","wordBoundaryRegexString","shouldRemovePunctuation","sanitizeString","wordBoundaryRegex","words","split","map","removePunctuation","flatMap","word","newWord","replace","filter","trim"],"sources":["../../../../src/languageProcessing/helpers/word/getWords.js"],"sourcesContent":["/** @module stringProcessing/countWords */\nimport sanitizeString from \"../sanitize/sanitizeString\";\nimport { filter, flatMap } from \"lodash\";\nimport removePunctuation, { punctuationRegexString } from \"../sanitize/removePunctuation.js\";\n\nconst punctuationRegex = new RegExp( `([${punctuationRegexString}])`, \"g\" );\n\n/**\n * Returns an array with words used in the text.\n *\n * @param {string} text The text to be counted.\n * @param {string} [wordBoundaryRegexString=\\\\s] The regex string for the word boundary that should be used to split the text into words.\n * @param {boolean} [shouldRemovePunctuation=true] If punctuation should be removed. Defaults to `true`.\n *\n * @returns {Array} The array with all words.\n */\nexport default function( text, wordBoundaryRegexString = \"\\\\s\", shouldRemovePunctuation = true ) {\n\t// Unify whitespaces and non-breaking spaces, remove table of content and strip the tags and multiple spaces.\n\ttext = sanitizeString( text );\n\n\tif ( text === \"\" ) {\n\t\treturn [];\n\t}\n\n\tconst wordBoundaryRegex = new RegExp( wordBoundaryRegexString, \"g\" );\n\n\tlet words = text.split( wordBoundaryRegex );\n\n\tif ( shouldRemovePunctuation ) {\n\t\twords = words.map( removePunctuation );\n\t} else {\n\t\t// If punctuation is not removed, punctuation marks are tokenized as if they were words.\n\t\twords = flatMap( words, ( word ) => {\n\t\t\tconst newWord = word.replace( punctuationRegex, \" $1 \" );\n\t\t\treturn newWord.split( \" \" );\n\t\t} );\n\t}\n\n\treturn filter( words, function( word ) {\n\t\treturn word.trim() !== \"\";\n\t} );\n}\n\n"],"mappings":";;;;;;AACA,IAAAA,eAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,OAAA,GAAAD,OAAA;AACA,IAAAE,kBAAA,GAAAC,uBAAA,CAAAH,OAAA;AAA6F,SAAAI,yBAAAC,CAAA,6BAAAC,OAAA,mBAAAC,CAAA,OAAAD,OAAA,IAAAE,CAAA,OAAAF,OAAA,YAAAF,wBAAA,YAAAA,CAAAC,CAAA,WAAAA,CAAA,GAAAG,CAAA,GAAAD,CAAA,KAAAF,CAAA;AAAA,SAAAF,wBAAAE,CAAA,EAAAE,CAAA,SAAAA,CAAA,IAAAF,CAAA,IAAAA,CAAA,CAAAI,UAAA,SAAAJ,CAAA,eAAAA,CAAA,uBAAAA,CAAA,yBAAAA,CAAA,WAAAK,OAAA,EAAAL,CAAA,QAAAG,CAAA,GAAAJ,wBAAA,CAAAG,CAAA,OAAAC,CAAA,IAAAA,CAAA,CAAAG,GAAA,CAAAN,CAAA,UAAAG,CAAA,CAAAI,GAAA,CAAAP,CAAA,OAAAQ,CAAA,KAAAC,SAAA,UAAAC,CAAA,GAAAC,MAAA,CAAAC,cAAA,IAAAD,MAAA,CAAAE,wBAAA,WAAAC,CAAA,IAAAd,CAAA,oBAAAc,CAAA,OAAAC,cAAA,CAAAC,IAAA,CAAAhB,CAAA,EAAAc,CAAA,SAAAG,CAAA,GAAAP,CAAA,GAAAC,MAAA,CAAAE,wBAAA,CAAAb,CAAA,EAAAc,CAAA,UAAAG,CAAA,KAAAA,CAAA,CAAAV,GAAA,IAAAU,CAAA,CAAAC,GAAA,IAAAP,MAAA,CAAAC,cAAA,CAAAJ,CAAA,EAAAM,CAAA,EAAAG,CAAA,IAAAT,CAAA,CAAAM,CAAA,IAAAd,CAAA,CAAAc,CAAA,YAAAN,CAAA,CAAAH,OAAA,GAAAL,CAAA,EAAAG,CAAA,IAAAA,CAAA,CAAAe,GAAA,CAAAlB,CAAA,EAAAQ,CAAA,GAAAA,CAAA;AAAA,SAAAd,uBAAAM,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAI,UAAA,GAAAJ,CAAA,KAAAK,OAAA,EAAAL,CAAA;AAH7F;;AAKA,MAAMmB,gBAAgB,GAAG,IAAIC,MAAM,CAAE,KAAKC,yCAAsB,IAAI,EAAE,GAAI,CAAC;;AAE3E;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAC,SAAUC,IAAI,EAAEC,uBAAuB,GAAG,KAAK,EAAEC,uBAAuB,GAAG,IAAI,EAAG;EAChG;EACAF,IAAI,GAAG,IAAAG,uBAAc,EAAEH,IAAK,CAAC;EAE7B,IAAKA,IAAI,KAAK,EAAE,EAAG;IAClB,OAAO,EAAE;EACV;EAEA,MAAMI,iBAAiB,GAAG,IAAIP,MAAM,CAAEI,uBAAuB,EAAE,GAAI,CAAC;EAEpE,IAAII,KAAK,GAAGL,IAAI,CAACM,KAAK,CAAEF,iBAAkB,CAAC;EAE3C,IAAKF,uBAAuB,EAAG;IAC9BG,KAAK,GAAGA,KAAK,CAACE,GAAG,CAAEC,0BAAkB,CAAC;EACvC,CAAC,MAAM;IACN;IACAH,KAAK,GAAG,IAAAI,eAAO,EAAEJ,KAAK,EAAIK,IAAI,IAAM;MACnC,MAAMC,OAAO,GAAGD,IAAI,CAACE,OAAO,CAAEhB,gBAAgB,EAAE,MAAO,CAAC;MACxD,OAAOe,OAAO,CAACL,KAAK,CAAE,GAAI,CAAC;IAC5B,CAAE,CAAC;EACJ;EAEA,OAAO,IAAAO,cAAM,EAAER,KAAK,EAAE,UAAUK,IAAI,EAAG;IACtC,OAAOA,IAAI,CAACI,IAAI,CAAC,CAAC,KAAK,EAAE;EAC1B,CAAE,CAAC;AACJ","ignoreList":[]}
+{"version":3,"file":"getWords.js","names":["sanitizeString","filter","flatMap","removePunctuation","punctuationRegexString","punctuationRegex","RegExp","text","wordBoundaryRegexString","shouldRemovePunctuation","wordBoundaryRegex","words","split","map","word","newWord","replace","trim"],"sources":["../../../../src/languageProcessing/helpers/word/getWords.js"],"sourcesContent":["/** @module stringProcessing/countWords */\nimport sanitizeString from \"../sanitize/sanitizeString\";\nimport { filter, flatMap } from \"lodash\";\nimport removePunctuation, { punctuationRegexString } from \"../sanitize/removePunctuation.js\";\n\nconst punctuationRegex = new RegExp( `([${punctuationRegexString}])`, \"g\" );\n\n/**\n * Returns an array with words used in the text.\n *\n * @param {string} text The text to be counted.\n * @param {string} [wordBoundaryRegexString=\\\\s] The regex string for the word boundary that should be used to split the text into words.\n * @param {boolean} [shouldRemovePunctuation=true] If punctuation should be removed. Defaults to `true`.\n *\n * @returns {Array} The array with all words.\n */\nexport default function( text, wordBoundaryRegexString = \"\\\\s\", shouldRemovePunctuation = true ) {\n\t// Unify whitespaces and non-breaking spaces, remove table of content and strip the tags and multiple spaces.\n\ttext = sanitizeString( text );\n\n\tif ( text === \"\" ) {\n\t\treturn [];\n\t}\n\n\tconst wordBoundaryRegex = new RegExp( wordBoundaryRegexString, \"g\" );\n\n\tlet words = text.split( wordBoundaryRegex );\n\n\tif ( shouldRemovePunctuation ) {\n\t\twords = words.map( removePunctuation );\n\t} else {\n\t\t// If punctuation is not removed, punctuation marks are tokenized as if they were words.\n\t\twords = flatMap( words, ( word ) => {\n\t\t\tconst newWord = word.replace( punctuationRegex, \" $1 \" );\n\t\t\treturn newWord.split( \" \" );\n\t\t} );\n\t}\n\n\treturn filter( words, function( word ) {\n\t\treturn word.trim() !== \"\";\n\t} );\n}\n\n"],"mappings":"AAAA;AACA,OAAOA,cAAc;AACrB,SAASC,MAAM,EAAEC,OAAO,QAAQ,QAAQ;AACxC,OAAOC,iBAAiB,IAAIC,sBAAsB;AAElD,MAAMC,gBAAgB,GAAG,IAAIC,MAAM,CAAE,KAAKF,sBAAsB,IAAI,EAAE,GAAI,CAAC;;AAE3E;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUG,IAAI,EAAEC,uBAAuB,GAAG,KAAK,EAAEC,uBAAuB,GAAG,IAAI,EAAG;EAChG;EACAF,IAAI,GAAGP,cAAc,CAAEO,IAAK,CAAC;EAE7B,IAAKA,IAAI,KAAK,EAAE,EAAG;IAClB,OAAO,EAAE;EACV;EAEA,MAAMG,iBAAiB,GAAG,IAAIJ,MAAM,CAAEE,uBAAuB,EAAE,GAAI,CAAC;EAEpE,IAAIG,KAAK,GAAGJ,IAAI,CAACK,KAAK,CAAEF,iBAAkB,CAAC;EAE3C,IAAKD,uBAAuB,EAAG;IAC9BE,KAAK,GAAGA,KAAK,CAACE,GAAG,CAAEV,iBAAkB,CAAC;EACvC,CAAC,MAAM;IACN;IACAQ,KAAK,GAAGT,OAAO,CAAES,KAAK,EAAIG,IAAI,IAAM;MACnC,MAAMC,OAAO,GAAGD,IAAI,CAACE,OAAO,CAAEX,gBAAgB,EAAE,MAAO,CAAC;MACxD,OAAOU,OAAO,CAACH,KAAK,CAAE,GAAI,CAAC;IAC5B,CAAE,CAAC;EACJ;EAEA,OAAOX,MAAM,CAAEU,KAAK,EAAE,UAAUG,IAAI,EAAG;IACtC,OAAOA,IAAI,CAACG,IAAI,CAAC,CAAC,KAAK,EAAE;EAC1B,CAAE,CAAC;AACJ","ignoreList":[]}

package/build/languageProcessing/helpers/word/includesIndex.js

@@ -1,10 +1,5 @@
-"use strict";
+import { forEach, includes, isEmpty } from "lodash";
 
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
-var _lodash = require("lodash");
 /**
  * Checks whether a given word is directly preceded by a word from a list of words.
  *
@@ -14,21 +9,21 @@ var _lodash = require("lodash");
  *
  * @returns {boolean} Returns true if the match is preceded by a given word, otherwise returns false.
  */
-function _default(precedingWords, matchIndex, addSpace = true) {
+export default function (precedingWords, matchIndex, addSpace = true) {
   /*
   1 if there is a space between the match and the preceding word
   (because the end word boundary is not included in the match).
   0 if the preceding word is a contraction.
   */
   const space = addSpace ? 1 : 0;
-  if ((0, _lodash.isEmpty)(precedingWords)) {
+  if (isEmpty(precedingWords)) {
     return false;
   }
   const precedingWordsEndIndices = [];
-  (0, _lodash.forEach)(precedingWords, function (precedingWord) {
+  forEach(precedingWords, function (precedingWord) {
     const precedingWordsEndIndex = precedingWord.index + precedingWord.match.length + space;
     precedingWordsEndIndices.push(precedingWordsEndIndex);
   });
-  return (0, _lodash.includes)(precedingWordsEndIndices, matchIndex);
+  return includes(precedingWordsEndIndices, matchIndex);
 }
 //# sourceMappingURL=includesIndex.js.map

package/build/languageProcessing/helpers/word/includesIndex.js.map

@@ -1 +1 @@
-{"version":3,"file":"includesIndex.js","names":["_lodash","require","_default","precedingWords","matchIndex","addSpace","space","isEmpty","precedingWordsEndIndices","forEach","precedingWord","precedingWordsEndIndex","index","match","length","push","includes"],"sources":["../../../../src/languageProcessing/helpers/word/includesIndex.js"],"sourcesContent":["import { forEach, includes, isEmpty } from \"lodash\";\n\n/**\n * Checks whether a given word is directly preceded by a word from a list of words.\n *\n * @param {Array} precedingWords    The array of objects with matches and indices.\n * @param {number} matchIndex       The index of the word for which to check whether it's preceded by one of the other words.\n * @param {boolean} addSpace        True if a space should be added.\n *\n * @returns {boolean} Returns true if the match is preceded by a given word, otherwise returns false.\n */\nexport default function( precedingWords, matchIndex, addSpace = true ) {\n\t/*\n\t1 if there is a space between the match and the preceding word\n\t(because the end word boundary is not included in the match).\n\t0 if the preceding word is a contraction.\n\t*/\n\tconst space = addSpace ? 1 : 0;\n\n\tif ( isEmpty( precedingWords ) ) {\n\t\treturn false;\n\t}\n\n\tconst precedingWordsEndIndices = [];\n\tforEach( precedingWords, function( precedingWord ) {\n\t\tconst precedingWordsEndIndex = precedingWord.index + precedingWord.match.length + space;\n\t\tprecedingWordsEndIndices.push( precedingWordsEndIndex );\n\t} );\n\treturn includes( precedingWordsEndIndices, matchIndex );\n}\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAC,SAAUC,cAAc,EAAEC,UAAU,EAAEC,QAAQ,GAAG,IAAI,EAAG;EACtE;AACD;AACA;AACA;AACA;EACC,MAAMC,KAAK,GAAGD,QAAQ,GAAG,CAAC,GAAG,CAAC;EAE9B,IAAK,IAAAE,eAAO,EAAEJ,cAAe,CAAC,EAAG;IAChC,OAAO,KAAK;EACb;EAEA,MAAMK,wBAAwB,GAAG,EAAE;EACnC,IAAAC,eAAO,EAAEN,cAAc,EAAE,UAAUO,aAAa,EAAG;IAClD,MAAMC,sBAAsB,GAAGD,aAAa,CAACE,KAAK,GAAGF,aAAa,CAACG,KAAK,CAACC,MAAM,GAAGR,KAAK;IACvFE,wBAAwB,CAACO,IAAI,CAAEJ,sBAAuB,CAAC;EACxD,CAAE,CAAC;EACH,OAAO,IAAAK,gBAAQ,EAAER,wBAAwB,EAAEJ,UAAW,CAAC;AACxD","ignoreList":[]}
+{"version":3,"file":"includesIndex.js","names":["forEach","includes","isEmpty","precedingWords","matchIndex","addSpace","space","precedingWordsEndIndices","precedingWord","precedingWordsEndIndex","index","match","length","push"],"sources":["../../../../src/languageProcessing/helpers/word/includesIndex.js"],"sourcesContent":["import { forEach, includes, isEmpty } from \"lodash\";\n\n/**\n * Checks whether a given word is directly preceded by a word from a list of words.\n *\n * @param {Array} precedingWords    The array of objects with matches and indices.\n * @param {number} matchIndex       The index of the word for which to check whether it's preceded by one of the other words.\n * @param {boolean} addSpace        True if a space should be added.\n *\n * @returns {boolean} Returns true if the match is preceded by a given word, otherwise returns false.\n */\nexport default function( precedingWords, matchIndex, addSpace = true ) {\n\t/*\n\t1 if there is a space between the match and the preceding word\n\t(because the end word boundary is not included in the match).\n\t0 if the preceding word is a contraction.\n\t*/\n\tconst space = addSpace ? 1 : 0;\n\n\tif ( isEmpty( precedingWords ) ) {\n\t\treturn false;\n\t}\n\n\tconst precedingWordsEndIndices = [];\n\tforEach( precedingWords, function( precedingWord ) {\n\t\tconst precedingWordsEndIndex = precedingWord.index + precedingWord.match.length + space;\n\t\tprecedingWordsEndIndices.push( precedingWordsEndIndex );\n\t} );\n\treturn includes( precedingWordsEndIndices, matchIndex );\n}\n"],"mappings":"AAAA,SAASA,OAAO,EAAEC,QAAQ,EAAEC,OAAO,QAAQ,QAAQ;;AAEnD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,cAAc,EAAEC,UAAU,EAAEC,QAAQ,GAAG,IAAI,EAAG;EACtE;AACD;AACA;AACA;AACA;EACC,MAAMC,KAAK,GAAGD,QAAQ,GAAG,CAAC,GAAG,CAAC;EAE9B,IAAKH,OAAO,CAAEC,cAAe,CAAC,EAAG;IAChC,OAAO,KAAK;EACb;EAEA,MAAMI,wBAAwB,GAAG,EAAE;EACnCP,OAAO,CAAEG,cAAc,EAAE,UAAUK,aAAa,EAAG;IAClD,MAAMC,sBAAsB,GAAGD,aAAa,CAACE,KAAK,GAAGF,aAAa,CAACG,KAAK,CAACC,MAAM,GAAGN,KAAK;IACvFC,wBAAwB,CAACM,IAAI,CAAEJ,sBAAuB,CAAC;EACxD,CAAE,CAAC;EACH,OAAOR,QAAQ,CAAEM,wBAAwB,EAAEH,UAAW,CAAC;AACxD","ignoreList":[]}

package/build/languageProcessing/helpers/word/indices.js

@@ -1,15 +1,7 @@
-"use strict";
+import { isUndefined, forEach } from "lodash";
+import stripSpaces from "../sanitize/stripSpaces.js";
+import { isWordInSentence as matchWordInSentence, characterInBoundary } from "./matchWordInSentence.js";
 
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.filterIndices = exports.default = void 0;
-exports.getIndicesByWord = getIndicesByWord;
-exports.sortIndices = exports.getIndicesByWordListSorted = exports.getIndicesByWordList = void 0;
-var _lodash = require("lodash");
-var _stripSpaces = _interopRequireDefault(require("../sanitize/stripSpaces.js"));
-var _matchWordInSentence = require("./matchWordInSentence.js");
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /**
  * Returns the indices of a string in a text. If it is found multiple times, it will return multiple indices.
  *
@@ -25,8 +17,8 @@ function getIndicesByWord(word, text) {
   const indices = [];
   while ((index = text.indexOf(word, startIndex)) > -1) {
     // Check if the previous and next character are word boundaries to determine if a complete word was detected
-    const isPreviousCharacterWordBoundary = (0, _matchWordInSentence.characterInBoundary)(text[index - 1]) || index === 0;
-    const isNextCharacterWordBoundary = (0, _matchWordInSentence.characterInBoundary)(text[index + searchStringLength]) || text.length === index + searchStringLength;
+    const isPreviousCharacterWordBoundary = characterInBoundary(text[index - 1]) || index === 0;
+    const isNextCharacterWordBoundary = characterInBoundary(text[index + searchStringLength]) || text.length === index + searchStringLength;
     if (isPreviousCharacterWordBoundary && isNextCharacterWordBoundary) {
       indices.push({
         index: index,
@@ -49,9 +41,9 @@ function getIndicesByWord(word, text) {
  */
 const getIndicesByWordList = function (words, text) {
   let matchedWords = [];
-  (0, _lodash.forEach)(words, function (word) {
-    word = (0, _stripSpaces.default)(word);
-    if (!(0, _matchWordInSentence.isWordInSentence)(word, text)) {
+  forEach(words, function (word) {
+    word = stripSpaces(word);
+    if (!matchWordInSentence(word, text)) {
       return;
     }
     matchedWords = matchedWords.concat(getIndicesByWord(word, text));
@@ -66,7 +58,6 @@ const getIndicesByWordList = function (words, text) {
  *
  * @returns {Array} The sorted array with indices.
  */
-exports.getIndicesByWordList = getIndicesByWordList;
 const sortIndices = function (indices) {
   return indices.sort(function (a, b) {
     return a.index - b.index;
@@ -80,14 +71,13 @@ const sortIndices = function (indices) {
  *
  * @returns {Array} The filtered array.
  */
-exports.sortIndices = sortIndices;
 const filterIndices = function (indices) {
   indices = sortIndices(indices);
   const filtered = [];
   for (let i = 0; i < indices.length; i++) {
     // If the next index is within the range of the current index and the length of the word, remove it
     // This makes sure we don't match combinations twice, like "even though" and "though".
-    if (!(0, _lodash.isUndefined)(indices[i + 1]) && indices[i + 1].index < indices[i].index + indices[i].match.length) {
+    if (!isUndefined(indices[i + 1]) && indices[i + 1].index < indices[i].index + indices[i].match.length) {
       filtered.push(indices[i]);
 
       // Adds 1 to i, so we skip the next index that is overlapping with the current index.
@@ -109,12 +99,11 @@ const filterIndices = function (indices) {
  * @returns {Array} The array with words, containing the index of the match and the matched string.
  * Returns an empty array if none are found.
  */
-exports.filterIndices = filterIndices;
 const getIndicesByWordListSorted = function (words, text) {
   let matchedWords = [];
-  (0, _lodash.forEach)(words, function (word) {
-    word = (0, _stripSpaces.default)(word);
-    if (!(0, _matchWordInSentence.isWordInSentence)(word, text)) {
+  forEach(words, function (word) {
+    word = stripSpaces(word);
+    if (!matchWordInSentence(word, text)) {
       return matchedWords;
     }
     matchedWords = matchedWords.concat(getIndicesByWord(word, text));
@@ -130,8 +119,8 @@ const getIndicesByWordListSorted = function (words, text) {
   });
   return matchedWords;
 };
-exports.getIndicesByWordListSorted = getIndicesByWordListSorted;
-var _default = exports.default = {
+export { getIndicesByWord, getIndicesByWordList, filterIndices, sortIndices, getIndicesByWordListSorted };
+export default {
   getIndicesByWord,
   getIndicesByWordList,
   filterIndices,

package/build/languageProcessing/helpers/word/indices.js.map

@@ -1 +1 @@
-{"version":3,"file":"indices.js","names":["_lodash","require","_stripSpaces","_interopRequireDefault","_matchWordInSentence","e","__esModule","default","getIndicesByWord","word","text","startIndex","searchStringLength","length","index","indices","indexOf","isPreviousCharacterWordBoundary","characterInBoundary","isNextCharacterWordBoundary","push","match","getIndicesByWordList","words","matchedWords","forEach","stripSpaces","matchWordInSentence","concat","exports","sortIndices","sort","a","b","filterIndices","filtered","i","isUndefined","getIndicesByWordListSorted","_default"],"sources":["../../../../src/languageProcessing/helpers/word/indices.js"],"sourcesContent":["import { isUndefined, forEach } from \"lodash\";\nimport stripSpaces from \"../sanitize/stripSpaces.js\";\nimport { isWordInSentence as matchWordInSentence, characterInBoundary } from \"./matchWordInSentence.js\";\n\n/**\n * Returns the indices of a string in a text. If it is found multiple times, it will return multiple indices.\n *\n * @param {string} word The word to find in the text.\n * @param {string} text The text to check for the given word.\n *\n * @returns {Array} All indices found.\n */\nfunction getIndicesByWord( word, text ) {\n\tlet startIndex = 0;\n\tconst searchStringLength = word.length;\n\tlet index;\n\tconst indices = [];\n\twhile ( ( index = text.indexOf( word, startIndex ) ) > -1 ) {\n\t\t// Check if the previous and next character are word boundaries to determine if a complete word was detected\n\t\tconst isPreviousCharacterWordBoundary = characterInBoundary( text[ index - 1 ] ) || index === 0;\n\n\t\tconst isNextCharacterWordBoundary = characterInBoundary( text[ index + searchStringLength ] ) ||\n\t\t\t( text.length === index + searchStringLength );\n\n\t\tif ( isPreviousCharacterWordBoundary && isNextCharacterWordBoundary ) {\n\t\t\tindices.push(\n\t\t\t\t{\n\t\t\t\t\tindex: index,\n\t\t\t\t\tmatch: word,\n\t\t\t\t}\n\t\t\t);\n\t\t}\n\t\tstartIndex = index + searchStringLength;\n\t}\n\treturn indices;\n}\n\n/**\n * Matches string with an array, returns the word and the index it was found on.\n *\n * @param {Array} words The array with strings to match.\n * @param {string} text The text to match the strings from the array to.\n *\n * @returns {Array} The array with words, containing the index of the match and the matched string.\n * Returns an empty array if none are found.\n */\nconst getIndicesByWordList = function( words, text ) {\n\tlet matchedWords = [];\n\n\tforEach( words, function( word ) {\n\t\tword = stripSpaces( word );\n\t\tif ( ! matchWordInSentence( word, text ) ) {\n\t\t\treturn;\n\t\t}\n\t\tmatchedWords = matchedWords.concat( getIndicesByWord( word, text ) );\n\t} );\n\treturn matchedWords;\n};\n\n/**\n * Sorts the array on the index property of each entry.\n *\n * @param {Array} indices The array with indices.\n *\n * @returns {Array} The sorted array with indices.\n */\nconst sortIndices = function( indices ) {\n\treturn indices.sort( function( a, b ) {\n\t\treturn ( a.index - b.index );\n\t} );\n};\n\n/**\n * Filters duplicate entries if the indices overlap.\n *\n * @param {Array} indices The array with indices to be filtered.\n *\n * @returns {Array} The filtered array.\n */\nconst filterIndices = function( indices ) {\n\tindices = sortIndices( indices );\n\tconst filtered = [];\n\tfor ( let i = 0; i < indices.length; i++ ) {\n\t\t// If the next index is within the range of the current index and the length of the word, remove it\n\t\t// This makes sure we don't match combinations twice, like \"even though\" and \"though\".\n\t\tif ( ! isUndefined( indices[ i + 1 ] ) && indices[ i + 1 ].index < indices[ i ].index + indices[ i ].match.length ) {\n\t\t\tfiltered.push( indices[ i ] );\n\n\t\t\t// Adds 1 to i, so we skip the next index that is overlapping with the current index.\n\t\t\ti++;\n\t\t\tcontinue;\n\t\t}\n\t\tfiltered.push( indices[ i ] );\n\t}\n\treturn filtered;\n};\n\n/**\n * Matches string with an array, returns the word and the index it was found on, and sorts the match instances based on\n * the index property of the match.\n *\n * @param {Array} words The array with strings to match.\n * @param {string} text The text to match the strings from the array to.\n *\n * @returns {Array} The array with words, containing the index of the match and the matched string.\n * Returns an empty array if none are found.\n */\nconst getIndicesByWordListSorted = function( words, text ) {\n\tlet matchedWords = [];\n\n\tforEach( words, function( word ) {\n\t\tword = stripSpaces( word );\n\t\tif ( ! matchWordInSentence( word, text ) ) {\n\t\t\treturn matchedWords;\n\t\t}\n\t\tmatchedWords = matchedWords.concat( getIndicesByWord( word, text ) );\n\t} );\n\n\tmatchedWords = matchedWords.sort( function( a, b ) {\n\t\tif ( a.index < b.index ) {\n\t\t\treturn -1;\n\t\t}\n\t\tif ( a.index > b.index ) {\n\t\t\treturn 1;\n\t\t}\n\t\treturn 0;\n\t} );\n\n\treturn matchedWords;\n};\n\nexport {\n\tgetIndicesByWord,\n\tgetIndicesByWordList,\n\tfilterIndices,\n\tsortIndices,\n\tgetIndicesByWordListSorted,\n};\n\nexport default {\n\tgetIndicesByWord,\n\tgetIndicesByWordList,\n\tfilterIndices,\n\tsortIndices,\n\tgetIndicesByWordListSorted,\n};\n"],"mappings":";;;;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AACA,IAAAC,YAAA,GAAAC,sBAAA,CAAAF,OAAA;AACA,IAAAG,oBAAA,GAAAH,OAAA;AAAwG,SAAAE,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAExG;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASG,gBAAgBA,CAAEC,IAAI,EAAEC,IAAI,EAAG;EACvC,IAAIC,UAAU,GAAG,CAAC;EAClB,MAAMC,kBAAkB,GAAGH,IAAI,CAACI,MAAM;EACtC,IAAIC,KAAK;EACT,MAAMC,OAAO,GAAG,EAAE;EAClB,OAAQ,CAAED,KAAK,GAAGJ,IAAI,CAACM,OAAO,CAAEP,IAAI,EAAEE,UAAW,CAAC,IAAK,CAAC,CAAC,EAAG;IAC3D;IACA,MAAMM,+BAA+B,GAAG,IAAAC,wCAAmB,EAAER,IAAI,CAAEI,KAAK,GAAG,CAAC,CAAG,CAAC,IAAIA,KAAK,KAAK,CAAC;IAE/F,MAAMK,2BAA2B,GAAG,IAAAD,wCAAmB,EAAER,IAAI,CAAEI,KAAK,GAAGF,kBAAkB,CAAG,CAAC,IAC1FF,IAAI,CAACG,MAAM,KAAKC,KAAK,GAAGF,kBAAoB;IAE/C,IAAKK,+BAA+B,IAAIE,2BAA2B,EAAG;MACrEJ,OAAO,CAACK,IAAI,CACX;QACCN,KAAK,EAAEA,KAAK;QACZO,KAAK,EAAEZ;MACR,CACD,CAAC;IACF;IACAE,UAAU,GAAGG,KAAK,GAAGF,kBAAkB;EACxC;EACA,OAAOG,OAAO;AACf;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMO,oBAAoB,GAAG,SAAAA,CAAUC,KAAK,EAAEb,IAAI,EAAG;EACpD,IAAIc,YAAY,GAAG,EAAE;EAErB,IAAAC,eAAO,EAAEF,KAAK,EAAE,UAAUd,IAAI,EAAG;IAChCA,IAAI,GAAG,IAAAiB,oBAAW,EAAEjB,IAAK,CAAC;IAC1B,IAAK,CAAE,IAAAkB,qCAAmB,EAAElB,IAAI,EAAEC,IAAK,CAAC,EAAG;MAC1C;IACD;IACAc,YAAY,GAAGA,YAAY,CAACI,MAAM,CAAEpB,gBAAgB,CAAEC,IAAI,EAAEC,IAAK,CAAE,CAAC;EACrE,CAAE,CAAC;EACH,OAAOc,YAAY;AACpB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AANAK,OAAA,CAAAP,oBAAA,GAAAA,oBAAA;AAOA,MAAMQ,WAAW,GAAG,SAAAA,CAAUf,OAAO,EAAG;EACvC,OAAOA,OAAO,CAACgB,IAAI,CAAE,UAAUC,CAAC,EAAEC,CAAC,EAAG;IACrC,OAASD,CAAC,CAAClB,KAAK,GAAGmB,CAAC,CAACnB,KAAK;EAC3B,CAAE,CAAC;AACJ,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AANAe,OAAA,CAAAC,WAAA,GAAAA,WAAA;AAOA,MAAMI,aAAa,GAAG,SAAAA,CAAUnB,OAAO,EAAG;EACzCA,OAAO,GAAGe,WAAW,CAAEf,OAAQ,CAAC;EAChC,MAAMoB,QAAQ,GAAG,EAAE;EACnB,KAAM,IAAIC,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGrB,OAAO,CAACF,MAAM,EAAEuB,CAAC,EAAE,EAAG;IAC1C;IACA;IACA,IAAK,CAAE,IAAAC,mBAAW,EAAEtB,OAAO,CAAEqB,CAAC,GAAG,CAAC,CAAG,CAAC,IAAIrB,OAAO,CAAEqB,CAAC,GAAG,CAAC,CAAE,CAACtB,KAAK,GAAGC,OAAO,CAAEqB,CAAC,CAAE,CAACtB,KAAK,GAAGC,OAAO,CAAEqB,CAAC,CAAE,CAACf,KAAK,CAACR,MAAM,EAAG;MACnHsB,QAAQ,CAACf,IAAI,CAAEL,OAAO,CAAEqB,CAAC,CAAG,CAAC;;MAE7B;MACAA,CAAC,EAAE;MACH;IACD;IACAD,QAAQ,CAACf,IAAI,CAAEL,OAAO,CAAEqB,CAAC,CAAG,CAAC;EAC9B;EACA,OAAOD,QAAQ;AAChB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AATAN,OAAA,CAAAK,aAAA,GAAAA,aAAA;AAUA,MAAMI,0BAA0B,GAAG,SAAAA,CAAUf,KAAK,EAAEb,IAAI,EAAG;EAC1D,IAAIc,YAAY,GAAG,EAAE;EAErB,IAAAC,eAAO,EAAEF,KAAK,EAAE,UAAUd,IAAI,EAAG;IAChCA,IAAI,GAAG,IAAAiB,oBAAW,EAAEjB,IAAK,CAAC;IAC1B,IAAK,CAAE,IAAAkB,qCAAmB,EAAElB,IAAI,EAAEC,IAAK,CAAC,EAAG;MAC1C,OAAOc,YAAY;IACpB;IACAA,YAAY,GAAGA,YAAY,CAACI,MAAM,CAAEpB,gBAAgB,CAAEC,IAAI,EAAEC,IAAK,CAAE,CAAC;EACrE,CAAE,CAAC;EAEHc,YAAY,GAAGA,YAAY,CAACO,IAAI,CAAE,UAAUC,CAAC,EAAEC,CAAC,EAAG;IAClD,IAAKD,CAAC,CAAClB,KAAK,GAAGmB,CAAC,CAACnB,KAAK,EAAG;MACxB,OAAO,CAAC,CAAC;IACV;IACA,IAAKkB,CAAC,CAAClB,KAAK,GAAGmB,CAAC,CAACnB,KAAK,EAAG;MACxB,OAAO,CAAC;IACT;IACA,OAAO,CAAC;EACT,CAAE,CAAC;EAEH,OAAOU,YAAY;AACpB,CAAC;AAACK,OAAA,CAAAS,0BAAA,GAAAA,0BAAA;AAAA,IAAAC,QAAA,GAAAV,OAAA,CAAAtB,OAAA,GAUa;EACdC,gBAAgB;EAChBc,oBAAoB;EACpBY,aAAa;EACbJ,WAAW;EACXQ;AACD,CAAC","ignoreList":[]}
+{"version":3,"file":"indices.js","names":["isUndefined","forEach","stripSpaces","isWordInSentence","matchWordInSentence","characterInBoundary","getIndicesByWord","word","text","startIndex","searchStringLength","length","index","indices","indexOf","isPreviousCharacterWordBoundary","isNextCharacterWordBoundary","push","match","getIndicesByWordList","words","matchedWords","concat","sortIndices","sort","a","b","filterIndices","filtered","i","getIndicesByWordListSorted"],"sources":["../../../../src/languageProcessing/helpers/word/indices.js"],"sourcesContent":["import { isUndefined, forEach } from \"lodash\";\nimport stripSpaces from \"../sanitize/stripSpaces.js\";\nimport { isWordInSentence as matchWordInSentence, characterInBoundary } from \"./matchWordInSentence.js\";\n\n/**\n * Returns the indices of a string in a text. If it is found multiple times, it will return multiple indices.\n *\n * @param {string} word The word to find in the text.\n * @param {string} text The text to check for the given word.\n *\n * @returns {Array} All indices found.\n */\nfunction getIndicesByWord( word, text ) {\n\tlet startIndex = 0;\n\tconst searchStringLength = word.length;\n\tlet index;\n\tconst indices = [];\n\twhile ( ( index = text.indexOf( word, startIndex ) ) > -1 ) {\n\t\t// Check if the previous and next character are word boundaries to determine if a complete word was detected\n\t\tconst isPreviousCharacterWordBoundary = characterInBoundary( text[ index - 1 ] ) || index === 0;\n\n\t\tconst isNextCharacterWordBoundary = characterInBoundary( text[ index + searchStringLength ] ) ||\n\t\t\t( text.length === index + searchStringLength );\n\n\t\tif ( isPreviousCharacterWordBoundary && isNextCharacterWordBoundary ) {\n\t\t\tindices.push(\n\t\t\t\t{\n\t\t\t\t\tindex: index,\n\t\t\t\t\tmatch: word,\n\t\t\t\t}\n\t\t\t);\n\t\t}\n\t\tstartIndex = index + searchStringLength;\n\t}\n\treturn indices;\n}\n\n/**\n * Matches string with an array, returns the word and the index it was found on.\n *\n * @param {Array} words The array with strings to match.\n * @param {string} text The text to match the strings from the array to.\n *\n * @returns {Array} The array with words, containing the index of the match and the matched string.\n * Returns an empty array if none are found.\n */\nconst getIndicesByWordList = function( words, text ) {\n\tlet matchedWords = [];\n\n\tforEach( words, function( word ) {\n\t\tword = stripSpaces( word );\n\t\tif ( ! matchWordInSentence( word, text ) ) {\n\t\t\treturn;\n\t\t}\n\t\tmatchedWords = matchedWords.concat( getIndicesByWord( word, text ) );\n\t} );\n\treturn matchedWords;\n};\n\n/**\n * Sorts the array on the index property of each entry.\n *\n * @param {Array} indices The array with indices.\n *\n * @returns {Array} The sorted array with indices.\n */\nconst sortIndices = function( indices ) {\n\treturn indices.sort( function( a, b ) {\n\t\treturn ( a.index - b.index );\n\t} );\n};\n\n/**\n * Filters duplicate entries if the indices overlap.\n *\n * @param {Array} indices The array with indices to be filtered.\n *\n * @returns {Array} The filtered array.\n */\nconst filterIndices = function( indices ) {\n\tindices = sortIndices( indices );\n\tconst filtered = [];\n\tfor ( let i = 0; i < indices.length; i++ ) {\n\t\t// If the next index is within the range of the current index and the length of the word, remove it\n\t\t// This makes sure we don't match combinations twice, like \"even though\" and \"though\".\n\t\tif ( ! isUndefined( indices[ i + 1 ] ) && indices[ i + 1 ].index < indices[ i ].index + indices[ i ].match.length ) {\n\t\t\tfiltered.push( indices[ i ] );\n\n\t\t\t// Adds 1 to i, so we skip the next index that is overlapping with the current index.\n\t\t\ti++;\n\t\t\tcontinue;\n\t\t}\n\t\tfiltered.push( indices[ i ] );\n\t}\n\treturn filtered;\n};\n\n/**\n * Matches string with an array, returns the word and the index it was found on, and sorts the match instances based on\n * the index property of the match.\n *\n * @param {Array} words The array with strings to match.\n * @param {string} text The text to match the strings from the array to.\n *\n * @returns {Array} The array with words, containing the index of the match and the matched string.\n * Returns an empty array if none are found.\n */\nconst getIndicesByWordListSorted = function( words, text ) {\n\tlet matchedWords = [];\n\n\tforEach( words, function( word ) {\n\t\tword = stripSpaces( word );\n\t\tif ( ! matchWordInSentence( word, text ) ) {\n\t\t\treturn matchedWords;\n\t\t}\n\t\tmatchedWords = matchedWords.concat( getIndicesByWord( word, text ) );\n\t} );\n\n\tmatchedWords = matchedWords.sort( function( a, b ) {\n\t\tif ( a.index < b.index ) {\n\t\t\treturn -1;\n\t\t}\n\t\tif ( a.index > b.index ) {\n\t\t\treturn 1;\n\t\t}\n\t\treturn 0;\n\t} );\n\n\treturn matchedWords;\n};\n\nexport {\n\tgetIndicesByWord,\n\tgetIndicesByWordList,\n\tfilterIndices,\n\tsortIndices,\n\tgetIndicesByWordListSorted,\n};\n\nexport default {\n\tgetIndicesByWord,\n\tgetIndicesByWordList,\n\tfilterIndices,\n\tsortIndices,\n\tgetIndicesByWordListSorted,\n};\n"],"mappings":"AAAA,SAASA,WAAW,EAAEC,OAAO,QAAQ,QAAQ;AAC7C,OAAOC,WAAW;AAClB,SAASC,gBAAgB,IAAIC,mBAAmB,EAAEC,mBAAmB;;AAErE;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,gBAAgBA,CAAEC,IAAI,EAAEC,IAAI,EAAG;EACvC,IAAIC,UAAU,GAAG,CAAC;EAClB,MAAMC,kBAAkB,GAAGH,IAAI,CAACI,MAAM;EACtC,IAAIC,KAAK;EACT,MAAMC,OAAO,GAAG,EAAE;EAClB,OAAQ,CAAED,KAAK,GAAGJ,IAAI,CAACM,OAAO,CAAEP,IAAI,EAAEE,UAAW,CAAC,IAAK,CAAC,CAAC,EAAG;IAC3D;IACA,MAAMM,+BAA+B,GAAGV,mBAAmB,CAAEG,IAAI,CAAEI,KAAK,GAAG,CAAC,CAAG,CAAC,IAAIA,KAAK,KAAK,CAAC;IAE/F,MAAMI,2BAA2B,GAAGX,mBAAmB,CAAEG,IAAI,CAAEI,KAAK,GAAGF,kBAAkB,CAAG,CAAC,IAC1FF,IAAI,CAACG,MAAM,KAAKC,KAAK,GAAGF,kBAAoB;IAE/C,IAAKK,+BAA+B,IAAIC,2BAA2B,EAAG;MACrEH,OAAO,CAACI,IAAI,CACX;QACCL,KAAK,EAAEA,KAAK;QACZM,KAAK,EAAEX;MACR,CACD,CAAC;IACF;IACAE,UAAU,GAAGG,KAAK,GAAGF,kBAAkB;EACxC;EACA,OAAOG,OAAO;AACf;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMM,oBAAoB,GAAG,SAAAA,CAAUC,KAAK,EAAEZ,IAAI,EAAG;EACpD,IAAIa,YAAY,GAAG,EAAE;EAErBpB,OAAO,CAAEmB,KAAK,EAAE,UAAUb,IAAI,EAAG;IAChCA,IAAI,GAAGL,WAAW,CAAEK,IAAK,CAAC;IAC1B,IAAK,CAAEH,mBAAmB,CAAEG,IAAI,EAAEC,IAAK,CAAC,EAAG;MAC1C;IACD;IACAa,YAAY,GAAGA,YAAY,CAACC,MAAM,CAAEhB,gBAAgB,CAAEC,IAAI,EAAEC,IAAK,CAAE,CAAC;EACrE,CAAE,CAAC;EACH,OAAOa,YAAY;AACpB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,WAAW,GAAG,SAAAA,CAAUV,OAAO,EAAG;EACvC,OAAOA,OAAO,CAACW,IAAI,CAAE,UAAUC,CAAC,EAAEC,CAAC,EAAG;IACrC,OAASD,CAAC,CAACb,KAAK,GAAGc,CAAC,CAACd,KAAK;EAC3B,CAAE,CAAC;AACJ,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMe,aAAa,GAAG,SAAAA,CAAUd,OAAO,EAAG;EACzCA,OAAO,GAAGU,WAAW,CAAEV,OAAQ,CAAC;EAChC,MAAMe,QAAQ,GAAG,EAAE;EACnB,KAAM,IAAIC,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGhB,OAAO,CAACF,MAAM,EAAEkB,CAAC,EAAE,EAAG;IAC1C;IACA;IACA,IAAK,CAAE7B,WAAW,CAAEa,OAAO,CAAEgB,CAAC,GAAG,CAAC,CAAG,CAAC,IAAIhB,OAAO,CAAEgB,CAAC,GAAG,CAAC,CAAE,CAACjB,KAAK,GAAGC,OAAO,CAAEgB,CAAC,CAAE,CAACjB,KAAK,GAAGC,OAAO,CAAEgB,CAAC,CAAE,CAACX,KAAK,CAACP,MAAM,EAAG;MACnHiB,QAAQ,CAACX,IAAI,CAAEJ,OAAO,CAAEgB,CAAC,CAAG,CAAC;;MAE7B;MACAA,CAAC,EAAE;MACH;IACD;IACAD,QAAQ,CAACX,IAAI,CAAEJ,OAAO,CAAEgB,CAAC,CAAG,CAAC;EAC9B;EACA,OAAOD,QAAQ;AAChB,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,0BAA0B,GAAG,SAAAA,CAAUV,KAAK,EAAEZ,IAAI,EAAG;EAC1D,IAAIa,YAAY,GAAG,EAAE;EAErBpB,OAAO,CAAEmB,KAAK,EAAE,UAAUb,IAAI,EAAG;IAChCA,IAAI,GAAGL,WAAW,CAAEK,IAAK,CAAC;IAC1B,IAAK,CAAEH,mBAAmB,CAAEG,IAAI,EAAEC,IAAK,CAAC,EAAG;MAC1C,OAAOa,YAAY;IACpB;IACAA,YAAY,GAAGA,YAAY,CAACC,MAAM,CAAEhB,gBAAgB,CAAEC,IAAI,EAAEC,IAAK,CAAE,CAAC;EACrE,CAAE,CAAC;EAEHa,YAAY,GAAGA,YAAY,CAACG,IAAI,CAAE,UAAUC,CAAC,EAAEC,CAAC,EAAG;IAClD,IAAKD,CAAC,CAACb,KAAK,GAAGc,CAAC,CAACd,KAAK,EAAG;MACxB,OAAO,CAAC,CAAC;IACV;IACA,IAAKa,CAAC,CAACb,KAAK,GAAGc,CAAC,CAACd,KAAK,EAAG;MACxB,OAAO,CAAC;IACT;IACA,OAAO,CAAC;EACT,CAAE,CAAC;EAEH,OAAOS,YAAY;AACpB,CAAC;AAED,SACCf,gBAAgB,EAChBa,oBAAoB,EACpBQ,aAAa,EACbJ,WAAW,EACXO,0BAA0B;AAG3B,eAAe;EACdxB,gBAAgB;EAChBa,oBAAoB;EACpBQ,aAAa;EACbJ,WAAW;EACXO;AACD,CAAC","ignoreList":[]}

package/build/languageProcessing/helpers/word/markWordsInSentences.js

@@ -1,20 +1,11 @@
-"use strict";
+import matchWords from "../match/matchTextWithArray";
+import arrayToRegex from "../regex/createRegexFromArray";
+import addMark from "../../../markers/addMarkSingleWord";
+import Mark from "../../../values/Mark";
+import { escapeRegExp } from "lodash";
+import getAnchorsFromText from "../link/getAnchorsFromText";
+import { SINGLE_QUOTES_ARRAY, SINGLE_QUOTES_REGEX } from "../sanitize/quotes";
 
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.deConstructAnchor = exports.collectMarkingsInSentence = void 0;
-exports.markWordsInASentence = markWordsInASentence;
-exports.markWordsInSentences = markWordsInSentences;
-exports.reConstructAnchor = void 0;
-var _matchTextWithArray = _interopRequireDefault(require("../match/matchTextWithArray"));
-var _createRegexFromArray = _interopRequireDefault(require("../regex/createRegexFromArray"));
-var _addMarkSingleWord = _interopRequireDefault(require("../../../markers/addMarkSingleWord"));
-var _Mark = _interopRequireDefault(require("../../../values/Mark"));
-var _lodash = require("lodash");
-var _getAnchorsFromText = _interopRequireDefault(require("../link/getAnchorsFromText"));
-var _quotes = require("../sanitize/quotes");
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 // Regex to deconstruct an anchor into open tag, content and close tag.
 const anchorDeconstructionRegex = /(<a[\s]+[^>]+>)([^]*?)(<\/a>)/;
 
@@ -26,7 +17,7 @@ const anchorDeconstructionRegex = /(<a[\s]+[^>]+>)([^]*?)(<\/a>)/;
  *
  * @returns {object} An object containing the opening tag and the content.
  */
-const deConstructAnchor = function (anchor) {
+export const deConstructAnchor = function (anchor) {
   // The const array mirrors the anchorDeconstructionRegex, using a comma to access the first element without a name.
   const [, openTag, content] = anchor.match(anchorDeconstructionRegex);
   return {
@@ -43,8 +34,7 @@ const deConstructAnchor = function (anchor) {
  *
  * @returns {string} An anchor.
  */
-exports.deConstructAnchor = deConstructAnchor;
-const reConstructAnchor = function (openTag, content) {
+export const reConstructAnchor = function (openTag, content) {
   return `${openTag}${content}</a>`;
 };
 
@@ -56,10 +46,9 @@ const reConstructAnchor = function (openTag, content) {
  *
  * @returns {Object} The anchors and the marked anchors.
  */
-exports.reConstructAnchor = reConstructAnchor;
 const getMarkedAnchors = function (sentence, wordsRegex) {
   // Retrieve the anchors.
-  const anchors = (0, _getAnchorsFromText.default)(sentence);
+  const anchors = getAnchorsFromText(sentence);
   // For every anchor, apply the markings only to the anchor tag.
   const markedAnchors = anchors.map(anchor => {
     // Retrieve the open tag and the content/anchor text.
@@ -69,7 +58,7 @@ const getMarkedAnchors = function (sentence, wordsRegex) {
     } = deConstructAnchor(anchor);
 
     // Apply the marking to the anchor text if there is a match.
-    const markedAnchorText = content.replace(wordsRegex, x => (0, _addMarkSingleWord.default)(x));
+    const markedAnchorText = content.replace(wordsRegex, x => addMark(x));
 
     // Create a new anchor tag with a (marked) anchor text.
     return reConstructAnchor(openTag, markedAnchorText);
@@ -91,11 +80,11 @@ const getMarkedAnchors = function (sentence, wordsRegex) {
  *
  * @returns {string} The sentence with marks.
  */
-const collectMarkingsInSentence = function (sentence, wordsFoundInSentence, matchWordCustomHelper) {
+export const collectMarkingsInSentence = function (sentence, wordsFoundInSentence, matchWordCustomHelper) {
   const allWordsFound = [];
   wordsFoundInSentence.forEach(word => {
     // Check if the word in `wordsFoundInSentence` contains single quote(s).
-    const matchedSingleQuotes = word.match(_quotes.SINGLE_QUOTES_REGEX);
+    const matchedSingleQuotes = word.match(SINGLE_QUOTES_REGEX);
     if (matchedSingleQuotes) {
       /*
        * If yes, make all different combinations of the word with different types of single quotes in the array.
@@ -107,18 +96,18 @@ const collectMarkingsInSentence = function (sentence, wordsFoundInSentence, matc
        * "panda's", "panda‘s", "panda’s", "panda‛s", "panda`s", "panda‹s", "panda›s"
        * And those variations will be added to `allWordsFound`.
        */
-      _quotes.SINGLE_QUOTES_ARRAY.forEach(singleQuote => {
+      SINGLE_QUOTES_ARRAY.forEach(singleQuote => {
         matchedSingleQuotes.forEach(matchedSingleQuote => {
-          allWordsFound.push((0, _lodash.escapeRegExp)(word.replace(new RegExp(matchedSingleQuote, "g"), singleQuote)));
+          allWordsFound.push(escapeRegExp(word.replace(new RegExp(matchedSingleQuote, "g"), singleQuote)));
         });
       });
     } else {
-      allWordsFound.push((0, _lodash.escapeRegExp)(word));
+      allWordsFound.push(escapeRegExp(word));
     }
   });
 
   // If a language has a custom helper to match words, we disable the word boundary when creating the regex.
-  const wordsRegex = matchWordCustomHelper ? (0, _createRegexFromArray.default)(allWordsFound, true) : (0, _createRegexFromArray.default)(allWordsFound);
+  const wordsRegex = matchWordCustomHelper ? arrayToRegex(allWordsFound, true) : arrayToRegex(allWordsFound);
 
   // Retrieve the anchors and mark the anchors' text if the words are found in the anchors' text.
   const {
@@ -126,7 +115,7 @@ const collectMarkingsInSentence = function (sentence, wordsFoundInSentence, matc
     markedAnchors
   } = getMarkedAnchors(sentence, wordsRegex);
   let markup = sentence.replace(wordsRegex, function (x) {
-    return (0, _addMarkSingleWord.default)(x);
+    return addMark(x);
   });
 
   /**
@@ -136,7 +125,7 @@ const collectMarkingsInSentence = function (sentence, wordsFoundInSentence, matc
    * where the markings are only applied in the anchor's text.
    */
   if (anchors.length > 0) {
-    const markupAnchors = (0, _getAnchorsFromText.default)(markup);
+    const markupAnchors = getAnchorsFromText(markup);
     for (let i = 0; i < markupAnchors.length; i++) {
       markup = markup.replace(markupAnchors[i], markedAnchors[i]);
     }
@@ -157,9 +146,8 @@ const collectMarkingsInSentence = function (sentence, wordsFoundInSentence, matc
  * @param {function}    matchWordCustomHelper   The language-specific helper function to match word in text.
  * @returns {Mark[]}  The array of Mark objects of each sentence.
  */
-exports.collectMarkingsInSentence = collectMarkingsInSentence;
-function markWordsInASentence(sentence, wordsFoundInSentence, matchWordCustomHelper) {
-  return [new _Mark.default({
+export function markWordsInASentence(sentence, wordsFoundInSentence, matchWordCustomHelper) {
+  return [new Mark({
     original: sentence,
     marked: collectMarkingsInSentence(sentence, wordsFoundInSentence, matchWordCustomHelper)
   })];
@@ -175,11 +163,11 @@ function markWordsInASentence(sentence, wordsFoundInSentence, matchWordCustomHel
  *
  * @returns {[string]} The sentences with marks.
  */
-function markWordsInSentences(wordsToMark, sentences, locale, matchWordCustomHelper) {
+export function markWordsInSentences(wordsToMark, sentences, locale, matchWordCustomHelper) {
   let wordsFoundInSentence = [];
   let markings = [];
   sentences.forEach(function (sentence) {
-    wordsFoundInSentence = (0, _matchTextWithArray.default)(sentence, wordsToMark, locale, matchWordCustomHelper).matches;
+    wordsFoundInSentence = matchWords(sentence, wordsToMark, locale, matchWordCustomHelper).matches;
     if (wordsFoundInSentence.length > 0) {
       markings = markings.concat(markWordsInASentence(sentence, wordsFoundInSentence, matchWordCustomHelper));
     }

package/build/languageProcessing/helpers/word/markWordsInSentences.js.map

@@ -1 +1 @@
-{"version":3,"file":"markWordsInSentences.js","names":["_matchTextWithArray","_interopRequireDefault","require","_createRegexFromArray","_addMarkSingleWord","_Mark","_lodash","_getAnchorsFromText","_quotes","e","__esModule","default","anchorDeconstructionRegex","deConstructAnchor","anchor","openTag","content","match","exports","reConstructAnchor","getMarkedAnchors","sentence","wordsRegex","anchors","getAnchorsFromText","markedAnchors","map","markedAnchorText","replace","x","addMark","collectMarkingsInSentence","wordsFoundInSentence","matchWordCustomHelper","allWordsFound","forEach","word","matchedSingleQuotes","SINGLE_QUOTES_REGEX","SINGLE_QUOTES_ARRAY","singleQuote","matchedSingleQuote","push","escapeRegExp","RegExp","arrayToRegex","markup","length","markupAnchors","i","markWordsInASentence","Mark","original","marked","markWordsInSentences","wordsToMark","sentences","locale","markings","matchWords","matches","concat"],"sources":["../../../../src/languageProcessing/helpers/word/markWordsInSentences.js"],"sourcesContent":["import matchWords from \"../match/matchTextWithArray\";\nimport arrayToRegex from \"../regex/createRegexFromArray\";\nimport addMark from \"../../../markers/addMarkSingleWord\";\nimport Mark from \"../../../values/Mark\";\nimport { escapeRegExp } from \"lodash\";\nimport getAnchorsFromText from \"../link/getAnchorsFromText\";\nimport { SINGLE_QUOTES_ARRAY, SINGLE_QUOTES_REGEX } from \"../sanitize/quotes\";\n\n// Regex to deconstruct an anchor into open tag, content and close tag.\nconst anchorDeconstructionRegex = /(<a[\\s]+[^>]+>)([^]*?)(<\\/a>)/;\n\n/**\n * Deconstructs an anchor to the opening tag and the content. The content is the anchor text.\n * We don't return the closing tag since the value would always be the same, i.e. </a>.\n *\n * @param {string} anchor An anchor of the shape <a ...>...</a>.\n *\n * @returns {object} An object containing the opening tag and the content.\n */\nexport const deConstructAnchor = function( anchor ) {\n\t// The const array mirrors the anchorDeconstructionRegex, using a comma to access the first element without a name.\n\tconst [ , openTag, content ] = anchor.match( anchorDeconstructionRegex );\n\treturn {\n\t\topenTag: openTag,\n\t\tcontent: content,\n\t};\n};\n\n/**\n * Reconstructs an anchor from an openTag, the content, and the closing tag.\n *\n * @param {string} openTag The opening tag of the anchor. Must be of the shape <a ...>.\n * @param {string} content The text of the anchor.\n *\n * @returns {string} An anchor.\n */\nexport const reConstructAnchor = function( openTag, content ) {\n\treturn `${openTag}${content}</a>`;\n};\n\n\n/**\n * Gets the anchors and marks the anchors' text if the words are found in it.\n *\n * @param {string} sentence The sentence to retrieve the anchors from.\n * @param {RegExp} wordsRegex The regex of the words.\n *\n * @returns {Object} The anchors and the marked anchors.\n */\nconst getMarkedAnchors = function( sentence, wordsRegex ) {\n\t// Retrieve the anchors.\n\tconst anchors = getAnchorsFromText( sentence );\n\t// For every anchor, apply the markings only to the anchor tag.\n\tconst markedAnchors = anchors.map( anchor => {\n\t\t// Retrieve the open tag and the content/anchor text.\n\t\tconst { openTag, content } = deConstructAnchor( anchor );\n\n\t\t// Apply the marking to the anchor text if there is a match.\n\t\tconst markedAnchorText = content.replace( wordsRegex, ( x ) => addMark( x ) );\n\n\t\t// Create a new anchor tag with a (marked) anchor text.\n\t\treturn reConstructAnchor( openTag, markedAnchorText );\n\t} );\n\n\treturn { anchors, markedAnchors };\n};\n\n/**\n * Adds marks to a sentence and merges marks if those are only separated by a space\n * (e.g., if highlighting words \"ballet\" and \"shoes\" in a sentence \"I have a lot of ballet shoes and other paraphernalia.\"\n * the marks will be put around \"ballet shoes\" together, not \"`ballet` `shoes`\".)\n *\n * @param {string}    sentence               The sentence to mark words in.\n * @param {[string]}  wordsFoundInSentence   The words to mark in the sentence.\n * @param {function}  matchWordCustomHelper  The language-specific helper function to match word in text.\n *\n * @returns {string} The sentence with marks.\n */\nexport const collectMarkingsInSentence = function( sentence, wordsFoundInSentence, matchWordCustomHelper ) {\n\tconst allWordsFound = [];\n\twordsFoundInSentence.forEach( word => {\n\t\t// Check if the word in `wordsFoundInSentence` contains single quote(s).\n\t\tconst matchedSingleQuotes = word.match( SINGLE_QUOTES_REGEX );\n\t\tif ( matchedSingleQuotes ) {\n\t\t\t/*\n\t\t\t * If yes, make all different combinations of the word with different types of single quotes in the array.\n\t\t\t * Later, a regex will be created for all words that were found in the sentence including their variations.\n\t\t\t *\n\t\t\t * For example:\n\t\t\t * `wordsFoundInSentence`: [ \"red\", \"panda’s\" ]\n\t\t\t * For the word \"panda’s\", we'll create the following variations:\n\t\t\t * \"panda's\", \"panda‘s\", \"panda’s\", \"panda‛s\", \"panda`s\", \"panda‹s\", \"panda›s\"\n\t\t\t * And those variations will be added to `allWordsFound`.\n\t\t\t */\n\t\t\tSINGLE_QUOTES_ARRAY.forEach( singleQuote => {\n\t\t\t\tmatchedSingleQuotes.forEach( matchedSingleQuote => {\n\t\t\t\t\tallWordsFound.push( escapeRegExp( word.replace( new RegExp( matchedSingleQuote, \"g\" ), singleQuote ) ) );\n\t\t\t\t} );\n\t\t\t} );\n\t\t} else {\n\t\t\tallWordsFound.push( escapeRegExp( word ) );\n\t\t}\n\t} );\n\n\t// If a language has a custom helper to match words, we disable the word boundary when creating the regex.\n\tconst wordsRegex = matchWordCustomHelper ? arrayToRegex( allWordsFound, true ) : arrayToRegex( allWordsFound );\n\n\t// Retrieve the anchors and mark the anchors' text if the words are found in the anchors' text.\n\tconst { anchors, markedAnchors } = getMarkedAnchors( sentence, wordsRegex );\n\n\tlet markup = sentence.replace( wordsRegex, function( x ) {\n\t\treturn addMark( x );\n\t} );\n\n\t/**\n\t * In 'markup', we apply the markings also inside the anchor's attribute if there is a match, on top of\n\t * marking the anchor's text.\n\t * The step below is to replace the incorrectly marked anchors with the marked anchors that we want:\n\t * where the markings are only applied in the anchor's text.\n\t */\n\tif ( anchors.length > 0 ) {\n\t\tconst markupAnchors = getAnchorsFromText( markup );\n\t\tfor ( let i = 0; i < markupAnchors.length; i++ ) {\n\t\t\tmarkup = markup.replace( markupAnchors[ i ], markedAnchors[ i ] );\n\t\t}\n\t}\n\n\t/*\n\t * If two marks are separated by only a space, remove the closing tag of the first mark and the opening tag of the\n\t * second mark so that the two marks can be combined into one.\n\t */\n\treturn ( markup.replace( new RegExp( \"</yoastmark> <yoastmark class='yoast-text-mark'>\", \"ig\" ), \" \" ) );\n};\n\n/**\n * Adds marks to a sentence.\n *\n * @param {string}      sentence                The sentence in which we want to apply highlighting.\n * @param {Array}       wordsFoundInSentence    The words to highlight in a sentence.\n * @param {function}    matchWordCustomHelper   The language-specific helper function to match word in text.\n * @returns {Mark[]}  The array of Mark objects of each sentence.\n */\nexport function markWordsInASentence( sentence, wordsFoundInSentence, matchWordCustomHelper ) {\n\treturn [ new Mark( {\n\t\toriginal: sentence,\n\t\tmarked: collectMarkingsInSentence( sentence, wordsFoundInSentence, matchWordCustomHelper ),\n\t} ) ];\n}\n\n/**\n * Adds marks to an array of sentences.\n *\n * @param {[string]}    wordsToMark The words to mark.\n * @param {[string]}    sentences   The sentences in which to mark these words.\n * @param {string}      locale      The locale.\n * @param {function}    matchWordCustomHelper   The language-specific helper function to match word in text.\n *\n * @returns {[string]} The sentences with marks.\n */\nexport function markWordsInSentences( wordsToMark, sentences, locale, matchWordCustomHelper ) {\n\tlet wordsFoundInSentence = [];\n\tlet markings = [];\n\n\tsentences.forEach( function( sentence ) {\n\t\twordsFoundInSentence = matchWords( sentence, wordsToMark, locale, matchWordCustomHelper ).matches;\n\n\t\tif ( wordsFoundInSentence.length > 0 ) {\n\t\t\tmarkings = markings.concat( markWordsInASentence( sentence, wordsFoundInSentence, matchWordCustomHelper ) );\n\t\t}\n\t} );\n\n\treturn markings;\n}\n"],"mappings":";;;;;;;;;AAAA,IAAAA,mBAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,qBAAA,GAAAF,sBAAA,CAAAC,OAAA;AACA,IAAAE,kBAAA,GAAAH,sBAAA,CAAAC,OAAA;AACA,IAAAG,KAAA,GAAAJ,sBAAA,CAAAC,OAAA;AACA,IAAAI,OAAA,GAAAJ,OAAA;AACA,IAAAK,mBAAA,GAAAN,sBAAA,CAAAC,OAAA;AACA,IAAAM,OAAA,GAAAN,OAAA;AAA8E,SAAAD,uBAAAQ,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAE9E;AACA,MAAMG,yBAAyB,GAAG,+BAA+B;;AAEjE;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACO,MAAMC,iBAAiB,GAAG,SAAAA,CAAUC,MAAM,EAAG;EACnD;EACA,MAAM,GAAIC,OAAO,EAAEC,OAAO,CAAE,GAAGF,MAAM,CAACG,KAAK,CAAEL,yBAA0B,CAAC;EACxE,OAAO;IACNG,OAAO,EAAEA,OAAO;IAChBC,OAAO,EAAEA;EACV,CAAC;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AAPAE,OAAA,CAAAL,iBAAA,GAAAA,iBAAA;AAQO,MAAMM,iBAAiB,GAAG,SAAAA,CAAUJ,OAAO,EAAEC,OAAO,EAAG;EAC7D,OAAO,GAAGD,OAAO,GAAGC,OAAO,MAAM;AAClC,CAAC;;AAGD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AAPAE,OAAA,CAAAC,iBAAA,GAAAA,iBAAA;AAQA,MAAMC,gBAAgB,GAAG,SAAAA,CAAUC,QAAQ,EAAEC,UAAU,EAAG;EACzD;EACA,MAAMC,OAAO,GAAG,IAAAC,2BAAkB,EAAEH,QAAS,CAAC;EAC9C;EACA,MAAMI,aAAa,GAAGF,OAAO,CAACG,GAAG,CAAEZ,MAAM,IAAI;IAC5C;IACA,MAAM;MAAEC,OAAO;MAAEC;IAAQ,CAAC,GAAGH,iBAAiB,CAAEC,MAAO,CAAC;;IAExD;IACA,MAAMa,gBAAgB,GAAGX,OAAO,CAACY,OAAO,CAAEN,UAAU,EAAIO,CAAC,IAAM,IAAAC,0BAAO,EAAED,CAAE,CAAE,CAAC;;IAE7E;IACA,OAAOV,iBAAiB,CAAEJ,OAAO,EAAEY,gBAAiB,CAAC;EACtD,CAAE,CAAC;EAEH,OAAO;IAAEJ,OAAO;IAAEE;EAAc,CAAC;AAClC,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACO,MAAMM,yBAAyB,GAAG,SAAAA,CAAUV,QAAQ,EAAEW,oBAAoB,EAAEC,qBAAqB,EAAG;EAC1G,MAAMC,aAAa,GAAG,EAAE;EACxBF,oBAAoB,CAACG,OAAO,CAAEC,IAAI,IAAI;IACrC;IACA,MAAMC,mBAAmB,GAAGD,IAAI,CAACnB,KAAK,CAAEqB,2BAAoB,CAAC;IAC7D,IAAKD,mBAAmB,EAAG;MAC1B;AACH;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;MACGE,2BAAmB,CAACJ,OAAO,CAAEK,WAAW,IAAI;QAC3CH,mBAAmB,CAACF,OAAO,CAAEM,kBAAkB,IAAI;UAClDP,aAAa,CAACQ,IAAI,CAAE,IAAAC,oBAAY,EAAEP,IAAI,CAACR,OAAO,CAAE,IAAIgB,MAAM,CAAEH,kBAAkB,EAAE,GAAI,CAAC,EAAED,WAAY,CAAE,CAAE,CAAC;QACzG,CAAE,CAAC;MACJ,CAAE,CAAC;IACJ,CAAC,MAAM;MACNN,aAAa,CAACQ,IAAI,CAAE,IAAAC,oBAAY,EAAEP,IAAK,CAAE,CAAC;IAC3C;EACD,CAAE,CAAC;;EAEH;EACA,MAAMd,UAAU,GAAGW,qBAAqB,GAAG,IAAAY,6BAAY,EAAEX,aAAa,EAAE,IAAK,CAAC,GAAG,IAAAW,6BAAY,EAAEX,aAAc,CAAC;;EAE9G;EACA,MAAM;IAAEX,OAAO;IAAEE;EAAc,CAAC,GAAGL,gBAAgB,CAAEC,QAAQ,EAAEC,UAAW,CAAC;EAE3E,IAAIwB,MAAM,GAAGzB,QAAQ,CAACO,OAAO,CAAEN,UAAU,EAAE,UAAUO,CAAC,EAAG;IACxD,OAAO,IAAAC,0BAAO,EAAED,CAAE,CAAC;EACpB,CAAE,CAAC;;EAEH;AACD;AACA;AACA;AACA;AACA;EACC,IAAKN,OAAO,CAACwB,MAAM,GAAG,CAAC,EAAG;IACzB,MAAMC,aAAa,GAAG,IAAAxB,2BAAkB,EAAEsB,MAAO,CAAC;IAClD,KAAM,IAAIG,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGD,aAAa,CAACD,MAAM,EAAEE,CAAC,EAAE,EAAG;MAChDH,MAAM,GAAGA,MAAM,CAAClB,OAAO,CAAEoB,aAAa,CAAEC,CAAC,CAAE,EAAExB,aAAa,CAAEwB,CAAC,CAAG,CAAC;IAClE;EACD;;EAEA;AACD;AACA;AACA;EACC,OAASH,MAAM,CAAClB,OAAO,CAAE,IAAIgB,MAAM,CAAE,kDAAkD,EAAE,IAAK,CAAC,EAAE,GAAI,CAAC;AACvG,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AAPA1B,OAAA,CAAAa,yBAAA,GAAAA,yBAAA;AAQO,SAASmB,oBAAoBA,CAAE7B,QAAQ,EAAEW,oBAAoB,EAAEC,qBAAqB,EAAG;EAC7F,OAAO,CAAE,IAAIkB,aAAI,CAAE;IAClBC,QAAQ,EAAE/B,QAAQ;IAClBgC,MAAM,EAAEtB,yBAAyB,CAAEV,QAAQ,EAAEW,oBAAoB,EAAEC,qBAAsB;EAC1F,CAAE,CAAC,CAAE;AACN;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACO,SAASqB,oBAAoBA,CAAEC,WAAW,EAAEC,SAAS,EAAEC,MAAM,EAAExB,qBAAqB,EAAG;EAC7F,IAAID,oBAAoB,GAAG,EAAE;EAC7B,IAAI0B,QAAQ,GAAG,EAAE;EAEjBF,SAAS,CAACrB,OAAO,CAAE,UAAUd,QAAQ,EAAG;IACvCW,oBAAoB,GAAG,IAAA2B,2BAAU,EAAEtC,QAAQ,EAAEkC,WAAW,EAAEE,MAAM,EAAExB,qBAAsB,CAAC,CAAC2B,OAAO;IAEjG,IAAK5B,oBAAoB,CAACe,MAAM,GAAG,CAAC,EAAG;MACtCW,QAAQ,GAAGA,QAAQ,CAACG,MAAM,CAAEX,oBAAoB,CAAE7B,QAAQ,EAAEW,oBAAoB,EAAEC,qBAAsB,CAAE,CAAC;IAC5G;EACD,CAAE,CAAC;EAEH,OAAOyB,QAAQ;AAChB","ignoreList":[]}
+{"version":3,"file":"markWordsInSentences.js","names":["matchWords","arrayToRegex","addMark","Mark","escapeRegExp","getAnchorsFromText","SINGLE_QUOTES_ARRAY","SINGLE_QUOTES_REGEX","anchorDeconstructionRegex","deConstructAnchor","anchor","openTag","content","match","reConstructAnchor","getMarkedAnchors","sentence","wordsRegex","anchors","markedAnchors","map","markedAnchorText","replace","x","collectMarkingsInSentence","wordsFoundInSentence","matchWordCustomHelper","allWordsFound","forEach","word","matchedSingleQuotes","singleQuote","matchedSingleQuote","push","RegExp","markup","length","markupAnchors","i","markWordsInASentence","original","marked","markWordsInSentences","wordsToMark","sentences","locale","markings","matches","concat"],"sources":["../../../../src/languageProcessing/helpers/word/markWordsInSentences.js"],"sourcesContent":["import matchWords from \"../match/matchTextWithArray\";\nimport arrayToRegex from \"../regex/createRegexFromArray\";\nimport addMark from \"../../../markers/addMarkSingleWord\";\nimport Mark from \"../../../values/Mark\";\nimport { escapeRegExp } from \"lodash\";\nimport getAnchorsFromText from \"../link/getAnchorsFromText\";\nimport { SINGLE_QUOTES_ARRAY, SINGLE_QUOTES_REGEX } from \"../sanitize/quotes\";\n\n// Regex to deconstruct an anchor into open tag, content and close tag.\nconst anchorDeconstructionRegex = /(<a[\\s]+[^>]+>)([^]*?)(<\\/a>)/;\n\n/**\n * Deconstructs an anchor to the opening tag and the content. The content is the anchor text.\n * We don't return the closing tag since the value would always be the same, i.e. </a>.\n *\n * @param {string} anchor An anchor of the shape <a ...>...</a>.\n *\n * @returns {object} An object containing the opening tag and the content.\n */\nexport const deConstructAnchor = function( anchor ) {\n\t// The const array mirrors the anchorDeconstructionRegex, using a comma to access the first element without a name.\n\tconst [ , openTag, content ] = anchor.match( anchorDeconstructionRegex );\n\treturn {\n\t\topenTag: openTag,\n\t\tcontent: content,\n\t};\n};\n\n/**\n * Reconstructs an anchor from an openTag, the content, and the closing tag.\n *\n * @param {string} openTag The opening tag of the anchor. Must be of the shape <a ...>.\n * @param {string} content The text of the anchor.\n *\n * @returns {string} An anchor.\n */\nexport const reConstructAnchor = function( openTag, content ) {\n\treturn `${openTag}${content}</a>`;\n};\n\n\n/**\n * Gets the anchors and marks the anchors' text if the words are found in it.\n *\n * @param {string} sentence The sentence to retrieve the anchors from.\n * @param {RegExp} wordsRegex The regex of the words.\n *\n * @returns {Object} The anchors and the marked anchors.\n */\nconst getMarkedAnchors = function( sentence, wordsRegex ) {\n\t// Retrieve the anchors.\n\tconst anchors = getAnchorsFromText( sentence );\n\t// For every anchor, apply the markings only to the anchor tag.\n\tconst markedAnchors = anchors.map( anchor => {\n\t\t// Retrieve the open tag and the content/anchor text.\n\t\tconst { openTag, content } = deConstructAnchor( anchor );\n\n\t\t// Apply the marking to the anchor text if there is a match.\n\t\tconst markedAnchorText = content.replace( wordsRegex, ( x ) => addMark( x ) );\n\n\t\t// Create a new anchor tag with a (marked) anchor text.\n\t\treturn reConstructAnchor( openTag, markedAnchorText );\n\t} );\n\n\treturn { anchors, markedAnchors };\n};\n\n/**\n * Adds marks to a sentence and merges marks if those are only separated by a space\n * (e.g., if highlighting words \"ballet\" and \"shoes\" in a sentence \"I have a lot of ballet shoes and other paraphernalia.\"\n * the marks will be put around \"ballet shoes\" together, not \"`ballet` `shoes`\".)\n *\n * @param {string}    sentence               The sentence to mark words in.\n * @param {[string]}  wordsFoundInSentence   The words to mark in the sentence.\n * @param {function}  matchWordCustomHelper  The language-specific helper function to match word in text.\n *\n * @returns {string} The sentence with marks.\n */\nexport const collectMarkingsInSentence = function( sentence, wordsFoundInSentence, matchWordCustomHelper ) {\n\tconst allWordsFound = [];\n\twordsFoundInSentence.forEach( word => {\n\t\t// Check if the word in `wordsFoundInSentence` contains single quote(s).\n\t\tconst matchedSingleQuotes = word.match( SINGLE_QUOTES_REGEX );\n\t\tif ( matchedSingleQuotes ) {\n\t\t\t/*\n\t\t\t * If yes, make all different combinations of the word with different types of single quotes in the array.\n\t\t\t * Later, a regex will be created for all words that were found in the sentence including their variations.\n\t\t\t *\n\t\t\t * For example:\n\t\t\t * `wordsFoundInSentence`: [ \"red\", \"panda’s\" ]\n\t\t\t * For the word \"panda’s\", we'll create the following variations:\n\t\t\t * \"panda's\", \"panda‘s\", \"panda’s\", \"panda‛s\", \"panda`s\", \"panda‹s\", \"panda›s\"\n\t\t\t * And those variations will be added to `allWordsFound`.\n\t\t\t */\n\t\t\tSINGLE_QUOTES_ARRAY.forEach( singleQuote => {\n\t\t\t\tmatchedSingleQuotes.forEach( matchedSingleQuote => {\n\t\t\t\t\tallWordsFound.push( escapeRegExp( word.replace( new RegExp( matchedSingleQuote, \"g\" ), singleQuote ) ) );\n\t\t\t\t} );\n\t\t\t} );\n\t\t} else {\n\t\t\tallWordsFound.push( escapeRegExp( word ) );\n\t\t}\n\t} );\n\n\t// If a language has a custom helper to match words, we disable the word boundary when creating the regex.\n\tconst wordsRegex = matchWordCustomHelper ? arrayToRegex( allWordsFound, true ) : arrayToRegex( allWordsFound );\n\n\t// Retrieve the anchors and mark the anchors' text if the words are found in the anchors' text.\n\tconst { anchors, markedAnchors } = getMarkedAnchors( sentence, wordsRegex );\n\n\tlet markup = sentence.replace( wordsRegex, function( x ) {\n\t\treturn addMark( x );\n\t} );\n\n\t/**\n\t * In 'markup', we apply the markings also inside the anchor's attribute if there is a match, on top of\n\t * marking the anchor's text.\n\t * The step below is to replace the incorrectly marked anchors with the marked anchors that we want:\n\t * where the markings are only applied in the anchor's text.\n\t */\n\tif ( anchors.length > 0 ) {\n\t\tconst markupAnchors = getAnchorsFromText( markup );\n\t\tfor ( let i = 0; i < markupAnchors.length; i++ ) {\n\t\t\tmarkup = markup.replace( markupAnchors[ i ], markedAnchors[ i ] );\n\t\t}\n\t}\n\n\t/*\n\t * If two marks are separated by only a space, remove the closing tag of the first mark and the opening tag of the\n\t * second mark so that the two marks can be combined into one.\n\t */\n\treturn ( markup.replace( new RegExp( \"</yoastmark> <yoastmark class='yoast-text-mark'>\", \"ig\" ), \" \" ) );\n};\n\n/**\n * Adds marks to a sentence.\n *\n * @param {string}      sentence                The sentence in which we want to apply highlighting.\n * @param {Array}       wordsFoundInSentence    The words to highlight in a sentence.\n * @param {function}    matchWordCustomHelper   The language-specific helper function to match word in text.\n * @returns {Mark[]}  The array of Mark objects of each sentence.\n */\nexport function markWordsInASentence( sentence, wordsFoundInSentence, matchWordCustomHelper ) {\n\treturn [ new Mark( {\n\t\toriginal: sentence,\n\t\tmarked: collectMarkingsInSentence( sentence, wordsFoundInSentence, matchWordCustomHelper ),\n\t} ) ];\n}\n\n/**\n * Adds marks to an array of sentences.\n *\n * @param {[string]}    wordsToMark The words to mark.\n * @param {[string]}    sentences   The sentences in which to mark these words.\n * @param {string}      locale      The locale.\n * @param {function}    matchWordCustomHelper   The language-specific helper function to match word in text.\n *\n * @returns {[string]} The sentences with marks.\n */\nexport function markWordsInSentences( wordsToMark, sentences, locale, matchWordCustomHelper ) {\n\tlet wordsFoundInSentence = [];\n\tlet markings = [];\n\n\tsentences.forEach( function( sentence ) {\n\t\twordsFoundInSentence = matchWords( sentence, wordsToMark, locale, matchWordCustomHelper ).matches;\n\n\t\tif ( wordsFoundInSentence.length > 0 ) {\n\t\t\tmarkings = markings.concat( markWordsInASentence( sentence, wordsFoundInSentence, matchWordCustomHelper ) );\n\t\t}\n\t} );\n\n\treturn markings;\n}\n"],"mappings":"AAAA,OAAOA,UAAU;AACjB,OAAOC,YAAY;AACnB,OAAOC,OAAO;AACd,OAAOC,IAAI;AACX,SAASC,YAAY,QAAQ,QAAQ;AACrC,OAAOC,kBAAkB;AACzB,SAASC,mBAAmB,EAAEC,mBAAmB;;AAEjD;AACA,MAAMC,yBAAyB,GAAG,+BAA+B;;AAEjE;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,MAAMC,iBAAiB,GAAG,SAAAA,CAAUC,MAAM,EAAG;EACnD;EACA,MAAM,GAAIC,OAAO,EAAEC,OAAO,CAAE,GAAGF,MAAM,CAACG,KAAK,CAAEL,yBAA0B,CAAC;EACxE,OAAO;IACNG,OAAO,EAAEA,OAAO;IAChBC,OAAO,EAAEA;EACV,CAAC;AACF,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,MAAME,iBAAiB,GAAG,SAAAA,CAAUH,OAAO,EAAEC,OAAO,EAAG;EAC7D,OAAO,GAAGD,OAAO,GAAGC,OAAO,MAAM;AAClC,CAAC;;AAGD;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,gBAAgB,GAAG,SAAAA,CAAUC,QAAQ,EAAEC,UAAU,EAAG;EACzD;EACA,MAAMC,OAAO,GAAGb,kBAAkB,CAAEW,QAAS,CAAC;EAC9C;EACA,MAAMG,aAAa,GAAGD,OAAO,CAACE,GAAG,CAAEV,MAAM,IAAI;IAC5C;IACA,MAAM;MAAEC,OAAO;MAAEC;IAAQ,CAAC,GAAGH,iBAAiB,CAAEC,MAAO,CAAC;;IAExD;IACA,MAAMW,gBAAgB,GAAGT,OAAO,CAACU,OAAO,CAAEL,UAAU,EAAIM,CAAC,IAAMrB,OAAO,CAAEqB,CAAE,CAAE,CAAC;;IAE7E;IACA,OAAOT,iBAAiB,CAAEH,OAAO,EAAEU,gBAAiB,CAAC;EACtD,CAAE,CAAC;EAEH,OAAO;IAAEH,OAAO;IAAEC;EAAc,CAAC;AAClC,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,MAAMK,yBAAyB,GAAG,SAAAA,CAAUR,QAAQ,EAAES,oBAAoB,EAAEC,qBAAqB,EAAG;EAC1G,MAAMC,aAAa,GAAG,EAAE;EACxBF,oBAAoB,CAACG,OAAO,CAAEC,IAAI,IAAI;IACrC;IACA,MAAMC,mBAAmB,GAAGD,IAAI,CAAChB,KAAK,CAAEN,mBAAoB,CAAC;IAC7D,IAAKuB,mBAAmB,EAAG;MAC1B;AACH;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;MACGxB,mBAAmB,CAACsB,OAAO,CAAEG,WAAW,IAAI;QAC3CD,mBAAmB,CAACF,OAAO,CAAEI,kBAAkB,IAAI;UAClDL,aAAa,CAACM,IAAI,CAAE7B,YAAY,CAAEyB,IAAI,CAACP,OAAO,CAAE,IAAIY,MAAM,CAAEF,kBAAkB,EAAE,GAAI,CAAC,EAAED,WAAY,CAAE,CAAE,CAAC;QACzG,CAAE,CAAC;MACJ,CAAE,CAAC;IACJ,CAAC,MAAM;MACNJ,aAAa,CAACM,IAAI,CAAE7B,YAAY,CAAEyB,IAAK,CAAE,CAAC;IAC3C;EACD,CAAE,CAAC;;EAEH;EACA,MAAMZ,UAAU,GAAGS,qBAAqB,GAAGzB,YAAY,CAAE0B,aAAa,EAAE,IAAK,CAAC,GAAG1B,YAAY,CAAE0B,aAAc,CAAC;;EAE9G;EACA,MAAM;IAAET,OAAO;IAAEC;EAAc,CAAC,GAAGJ,gBAAgB,CAAEC,QAAQ,EAAEC,UAAW,CAAC;EAE3E,IAAIkB,MAAM,GAAGnB,QAAQ,CAACM,OAAO,CAAEL,UAAU,EAAE,UAAUM,CAAC,EAAG;IACxD,OAAOrB,OAAO,CAAEqB,CAAE,CAAC;EACpB,CAAE,CAAC;;EAEH;AACD;AACA;AACA;AACA;AACA;EACC,IAAKL,OAAO,CAACkB,MAAM,GAAG,CAAC,EAAG;IACzB,MAAMC,aAAa,GAAGhC,kBAAkB,CAAE8B,MAAO,CAAC;IAClD,KAAM,IAAIG,CAAC,GAAG,CAAC,EAAEA,CAAC,GAAGD,aAAa,CAACD,MAAM,EAAEE,CAAC,EAAE,EAAG;MAChDH,MAAM,GAAGA,MAAM,CAACb,OAAO,CAAEe,aAAa,CAAEC,CAAC,CAAE,EAAEnB,aAAa,CAAEmB,CAAC,CAAG,CAAC;IAClE;EACD;;EAEA;AACD;AACA;AACA;EACC,OAASH,MAAM,CAACb,OAAO,CAAE,IAAIY,MAAM,CAAE,kDAAkD,EAAE,IAAK,CAAC,EAAE,GAAI,CAAC;AACvG,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,SAASK,oBAAoBA,CAAEvB,QAAQ,EAAES,oBAAoB,EAAEC,qBAAqB,EAAG;EAC7F,OAAO,CAAE,IAAIvB,IAAI,CAAE;IAClBqC,QAAQ,EAAExB,QAAQ;IAClByB,MAAM,EAAEjB,yBAAyB,CAAER,QAAQ,EAAES,oBAAoB,EAAEC,qBAAsB;EAC1F,CAAE,CAAC,CAAE;AACN;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,OAAO,SAASgB,oBAAoBA,CAAEC,WAAW,EAAEC,SAAS,EAAEC,MAAM,EAAEnB,qBAAqB,EAAG;EAC7F,IAAID,oBAAoB,GAAG,EAAE;EAC7B,IAAIqB,QAAQ,GAAG,EAAE;EAEjBF,SAAS,CAAChB,OAAO,CAAE,UAAUZ,QAAQ,EAAG;IACvCS,oBAAoB,GAAGzB,UAAU,CAAEgB,QAAQ,EAAE2B,WAAW,EAAEE,MAAM,EAAEnB,qBAAsB,CAAC,CAACqB,OAAO;IAEjG,IAAKtB,oBAAoB,CAACW,MAAM,GAAG,CAAC,EAAG;MACtCU,QAAQ,GAAGA,QAAQ,CAACE,MAAM,CAAET,oBAAoB,CAAEvB,QAAQ,EAAES,oBAAoB,EAAEC,qBAAsB,CAAE,CAAC;IAC5G;EACD,CAAE,CAAC;EAEH,OAAOoB,QAAQ;AAChB","ignoreList":[]}

package/build/languageProcessing/helpers/word/matchWordInSentence.js

@@ -1,14 +1,8 @@
-"use strict";
+import wordBoundariesFactory from "../../../config/wordBoundaries.js";
+const wordBoundaries = wordBoundariesFactory();
+import { escapeRegExp, includes } from "lodash";
+import addWordBoundary from "./addWordboundary.js";
 
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.isWordInSentence = exports.default = exports.characterInBoundary = void 0;
-var _wordBoundaries = _interopRequireDefault(require("../../../config/wordBoundaries.js"));
-var _lodash = require("lodash");
-var _addWordboundary = _interopRequireDefault(require("./addWordboundary.js"));
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
-const wordBoundaries = (0, _wordBoundaries.default)();
 /**
  * Checks whether a character is present in the list of word boundaries.
  *
@@ -16,7 +10,7 @@ const wordBoundaries = (0, _wordBoundaries.default)();
  * @returns {boolean} Whether or not the character is present in the list of word boundaries.
  */
 const characterInBoundary = function (character) {
-  return (0, _lodash.includes)(wordBoundaries, character);
+  return includes(wordBoundaries, character);
 };
 
 /**
@@ -26,14 +20,13 @@ const characterInBoundary = function (character) {
  * @param {string} sentence The sentence to look through.
  * @returns {boolean} Whether or not the word is present in the sentence.
  */
-exports.characterInBoundary = characterInBoundary;
 const isWordInSentence = function (word, sentence) {
   // To ensure proper matching, make everything lowercase.
   word = word.toLocaleLowerCase();
   sentence = sentence.toLocaleLowerCase();
 
   // Escape regex in word, since we use regex characters like in abbreviations ("e.g.").
-  const wordWithBoundaries = (0, _addWordboundary.default)((0, _lodash.escapeRegExp)(word));
+  const wordWithBoundaries = addWordBoundary(escapeRegExp(word));
   let occurrenceStart = sentence.search(new RegExp(wordWithBoundaries, "ig"));
   // Return false if no match has been found.
   if (occurrenceStart === -1) {
@@ -55,8 +48,8 @@ const isWordInSentence = function (word, sentence) {
   const nextCharacter = characterInBoundary(sentence[occurrenceEnd]) || occurrenceEnd === sentence.length;
   return previousCharacter && nextCharacter;
 };
-exports.isWordInSentence = isWordInSentence;
-var _default = exports.default = {
+export { characterInBoundary, isWordInSentence };
+export default {
   characterInBoundary,
   isWordInSentence
 };

package/build/languageProcessing/helpers/word/matchWordInSentence.js.map

@@ -1 +1 @@
-{"version":3,"file":"matchWordInSentence.js","names":["_wordBoundaries","_interopRequireDefault","require","_lodash","_addWordboundary","e","__esModule","default","wordBoundaries","wordBoundariesFactory","characterInBoundary","character","includes","exports","isWordInSentence","word","sentence","toLocaleLowerCase","wordWithBoundaries","addWordBoundary","escapeRegExp","occurrenceStart","search","RegExp","occurrenceEnd","length","previousCharacter","nextCharacter","_default"],"sources":["../../../../src/languageProcessing/helpers/word/matchWordInSentence.js"],"sourcesContent":["import wordBoundariesFactory from \"../../../config/wordBoundaries.js\";\nconst wordBoundaries = wordBoundariesFactory();\nimport { escapeRegExp, includes } from \"lodash\";\nimport addWordBoundary from \"./addWordboundary.js\";\n\n/**\n * Checks whether a character is present in the list of word boundaries.\n *\n * @param {string} character The character to look for.\n * @returns {boolean} Whether or not the character is present in the list of word boundaries.\n */\nconst characterInBoundary = function( character ) {\n\treturn includes( wordBoundaries, character );\n};\n\n/**\n * Checks whether a word is present in a sentence.\n *\n * @param {string} word The word to search for in the sentence.\n * @param {string} sentence The sentence to look through.\n * @returns {boolean} Whether or not the word is present in the sentence.\n */\nconst isWordInSentence = function( word, sentence ) {\n\t// To ensure proper matching, make everything lowercase.\n\tword = word.toLocaleLowerCase();\n\tsentence = sentence.toLocaleLowerCase();\n\n\t// Escape regex in word, since we use regex characters like in abbreviations (\"e.g.\").\n\tconst wordWithBoundaries = addWordBoundary( escapeRegExp( word ) );\n\tlet occurrenceStart = sentence.search( new RegExp( wordWithBoundaries, \"ig\" ) );\n\t// Return false if no match has been found.\n\tif ( occurrenceStart === -1 ) {\n\t\treturn false;\n\t}\n\t/*\n\tIf there is a word boundary before the matched word, the regex includes this word boundary in the match.\n\tThis means that occurrenceStart is the index of the word boundary before the match. Therefore 1 has to\n\tbe added to occurrenceStart, except when there is no word boundary before the match (i.e. at the start\n\tof a sentence).\n\t */\n\tif ( occurrenceStart > 0 ) {\n\t\toccurrenceStart += 1;\n\t}\n\tconst occurrenceEnd = occurrenceStart + word.length;\n\n\t// Check if the previous and next character are word boundaries to determine if a complete word was detected\n\tconst previousCharacter = characterInBoundary( sentence[ occurrenceStart - 1 ] ) || occurrenceStart === 0;\n\tconst nextCharacter = characterInBoundary( sentence[ occurrenceEnd ] ) || occurrenceEnd === sentence.length;\n\n\treturn ( ( previousCharacter ) && ( nextCharacter ) );\n};\n\nexport {\n\tcharacterInBoundary,\n\tisWordInSentence,\n};\n\nexport default {\n\tcharacterInBoundary,\n\tisWordInSentence,\n};\n"],"mappings":";;;;;;AAAA,IAAAA,eAAA,GAAAC,sBAAA,CAAAC,OAAA;AAEA,IAAAC,OAAA,GAAAD,OAAA;AACA,IAAAE,gBAAA,GAAAH,sBAAA,CAAAC,OAAA;AAAmD,SAAAD,uBAAAI,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAFnD,MAAMG,cAAc,GAAG,IAAAC,uBAAqB,EAAC,CAAC;AAI9C;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,mBAAmB,GAAG,SAAAA,CAAUC,SAAS,EAAG;EACjD,OAAO,IAAAC,gBAAQ,EAAEJ,cAAc,EAAEG,SAAU,CAAC;AAC7C,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AANAE,OAAA,CAAAH,mBAAA,GAAAA,mBAAA;AAOA,MAAMI,gBAAgB,GAAG,SAAAA,CAAUC,IAAI,EAAEC,QAAQ,EAAG;EACnD;EACAD,IAAI,GAAGA,IAAI,CAACE,iBAAiB,CAAC,CAAC;EAC/BD,QAAQ,GAAGA,QAAQ,CAACC,iBAAiB,CAAC,CAAC;;EAEvC;EACA,MAAMC,kBAAkB,GAAG,IAAAC,wBAAe,EAAE,IAAAC,oBAAY,EAAEL,IAAK,CAAE,CAAC;EAClE,IAAIM,eAAe,GAAGL,QAAQ,CAACM,MAAM,CAAE,IAAIC,MAAM,CAAEL,kBAAkB,EAAE,IAAK,CAAE,CAAC;EAC/E;EACA,IAAKG,eAAe,KAAK,CAAC,CAAC,EAAG;IAC7B,OAAO,KAAK;EACb;EACA;AACD;AACA;AACA;AACA;AACA;EACC,IAAKA,eAAe,GAAG,CAAC,EAAG;IAC1BA,eAAe,IAAI,CAAC;EACrB;EACA,MAAMG,aAAa,GAAGH,eAAe,GAAGN,IAAI,CAACU,MAAM;;EAEnD;EACA,MAAMC,iBAAiB,GAAGhB,mBAAmB,CAAEM,QAAQ,CAAEK,eAAe,GAAG,CAAC,CAAG,CAAC,IAAIA,eAAe,KAAK,CAAC;EACzG,MAAMM,aAAa,GAAGjB,mBAAmB,CAAEM,QAAQ,CAAEQ,aAAa,CAAG,CAAC,IAAIA,aAAa,KAAKR,QAAQ,CAACS,MAAM;EAE3G,OAAWC,iBAAiB,IAAQC,aAAe;AACpD,CAAC;AAACd,OAAA,CAAAC,gBAAA,GAAAA,gBAAA;AAAA,IAAAc,QAAA,GAAAf,OAAA,CAAAN,OAAA,GAOa;EACdG,mBAAmB;EACnBI;AACD,CAAC","ignoreList":[]}
+{"version":3,"file":"matchWordInSentence.js","names":["wordBoundariesFactory","wordBoundaries","escapeRegExp","includes","addWordBoundary","characterInBoundary","character","isWordInSentence","word","sentence","toLocaleLowerCase","wordWithBoundaries","occurrenceStart","search","RegExp","occurrenceEnd","length","previousCharacter","nextCharacter"],"sources":["../../../../src/languageProcessing/helpers/word/matchWordInSentence.js"],"sourcesContent":["import wordBoundariesFactory from \"../../../config/wordBoundaries.js\";\nconst wordBoundaries = wordBoundariesFactory();\nimport { escapeRegExp, includes } from \"lodash\";\nimport addWordBoundary from \"./addWordboundary.js\";\n\n/**\n * Checks whether a character is present in the list of word boundaries.\n *\n * @param {string} character The character to look for.\n * @returns {boolean} Whether or not the character is present in the list of word boundaries.\n */\nconst characterInBoundary = function( character ) {\n\treturn includes( wordBoundaries, character );\n};\n\n/**\n * Checks whether a word is present in a sentence.\n *\n * @param {string} word The word to search for in the sentence.\n * @param {string} sentence The sentence to look through.\n * @returns {boolean} Whether or not the word is present in the sentence.\n */\nconst isWordInSentence = function( word, sentence ) {\n\t// To ensure proper matching, make everything lowercase.\n\tword = word.toLocaleLowerCase();\n\tsentence = sentence.toLocaleLowerCase();\n\n\t// Escape regex in word, since we use regex characters like in abbreviations (\"e.g.\").\n\tconst wordWithBoundaries = addWordBoundary( escapeRegExp( word ) );\n\tlet occurrenceStart = sentence.search( new RegExp( wordWithBoundaries, \"ig\" ) );\n\t// Return false if no match has been found.\n\tif ( occurrenceStart === -1 ) {\n\t\treturn false;\n\t}\n\t/*\n\tIf there is a word boundary before the matched word, the regex includes this word boundary in the match.\n\tThis means that occurrenceStart is the index of the word boundary before the match. Therefore 1 has to\n\tbe added to occurrenceStart, except when there is no word boundary before the match (i.e. at the start\n\tof a sentence).\n\t */\n\tif ( occurrenceStart > 0 ) {\n\t\toccurrenceStart += 1;\n\t}\n\tconst occurrenceEnd = occurrenceStart + word.length;\n\n\t// Check if the previous and next character are word boundaries to determine if a complete word was detected\n\tconst previousCharacter = characterInBoundary( sentence[ occurrenceStart - 1 ] ) || occurrenceStart === 0;\n\tconst nextCharacter = characterInBoundary( sentence[ occurrenceEnd ] ) || occurrenceEnd === sentence.length;\n\n\treturn ( ( previousCharacter ) && ( nextCharacter ) );\n};\n\nexport {\n\tcharacterInBoundary,\n\tisWordInSentence,\n};\n\nexport default {\n\tcharacterInBoundary,\n\tisWordInSentence,\n};\n"],"mappings":"AAAA,OAAOA,qBAAqB;AAC5B,MAAMC,cAAc,GAAGD,qBAAqB,CAAC,CAAC;AAC9C,SAASE,YAAY,EAAEC,QAAQ,QAAQ,QAAQ;AAC/C,OAAOC,eAAe;;AAEtB;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,mBAAmB,GAAG,SAAAA,CAAUC,SAAS,EAAG;EACjD,OAAOH,QAAQ,CAAEF,cAAc,EAAEK,SAAU,CAAC;AAC7C,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,gBAAgB,GAAG,SAAAA,CAAUC,IAAI,EAAEC,QAAQ,EAAG;EACnD;EACAD,IAAI,GAAGA,IAAI,CAACE,iBAAiB,CAAC,CAAC;EAC/BD,QAAQ,GAAGA,QAAQ,CAACC,iBAAiB,CAAC,CAAC;;EAEvC;EACA,MAAMC,kBAAkB,GAAGP,eAAe,CAAEF,YAAY,CAAEM,IAAK,CAAE,CAAC;EAClE,IAAII,eAAe,GAAGH,QAAQ,CAACI,MAAM,CAAE,IAAIC,MAAM,CAAEH,kBAAkB,EAAE,IAAK,CAAE,CAAC;EAC/E;EACA,IAAKC,eAAe,KAAK,CAAC,CAAC,EAAG;IAC7B,OAAO,KAAK;EACb;EACA;AACD;AACA;AACA;AACA;AACA;EACC,IAAKA,eAAe,GAAG,CAAC,EAAG;IAC1BA,eAAe,IAAI,CAAC;EACrB;EACA,MAAMG,aAAa,GAAGH,eAAe,GAAGJ,IAAI,CAACQ,MAAM;;EAEnD;EACA,MAAMC,iBAAiB,GAAGZ,mBAAmB,CAAEI,QAAQ,CAAEG,eAAe,GAAG,CAAC,CAAG,CAAC,IAAIA,eAAe,KAAK,CAAC;EACzG,MAAMM,aAAa,GAAGb,mBAAmB,CAAEI,QAAQ,CAAEM,aAAa,CAAG,CAAC,IAAIA,aAAa,KAAKN,QAAQ,CAACO,MAAM;EAE3G,OAAWC,iBAAiB,IAAQC,aAAe;AACpD,CAAC;AAED,SACCb,mBAAmB,EACnBE,gBAAgB;AAGjB,eAAe;EACdF,mBAAmB;EACnBE;AACD,CAAC","ignoreList":[]}

package/build/languageProcessing/helpers/word/splitIntoTokens.js

@@ -1,11 +1,5 @@
-"use strict";
+import createPunctuationTokens from "./createPunctuationTokens";
 
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = void 0;
-var _createPunctuationTokens = _interopRequireDefault(require("./createPunctuationTokens"));
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /*
 *  The following regex is used to split a text into tokens.
  * The regex matches word separators. A word separator is either a whitespace, a slash, a
@@ -46,7 +40,7 @@ const splitIntoTokens = text => {
   const rawTokens = text.split(WORD_SEPARATORS_REGEX).filter(x => x !== "");
 
   // Remove punctuation from the beginning and end of word tokens, and make them into separate tokens.
-  return (0, _createPunctuationTokens.default)(rawTokens);
+  return createPunctuationTokens(rawTokens);
 };
-var _default = exports.default = splitIntoTokens;
+export default splitIntoTokens;
 //# sourceMappingURL=splitIntoTokens.js.map

package/build/languageProcessing/helpers/word/splitIntoTokens.js.map

@@ -1 +1 @@
-{"version":3,"file":"splitIntoTokens.js","names":["_createPunctuationTokens","_interopRequireDefault","require","e","__esModule","default","WORD_SEPARATORS_REGEX","splitIntoTokens","text","rawTokens","split","filter","x","createPunctuationTokens","_default","exports"],"sources":["../../../../src/languageProcessing/helpers/word/splitIntoTokens.js"],"sourcesContent":["import createPunctuationTokens from \"./createPunctuationTokens\";\n\n/*\n*  The following regex is used to split a text into tokens.\n * The regex matches word separators. A word separator is either a whitespace, a slash, a\n * tab, a non-breaking space, a hyphen, an en-dash or an em-dash.\n * Opening and closing square brackets are added to deal correctly with shortcodes downstream.\n * The regex is used to split a text into tokens.\n * Do not add punctuation marks to this regex, as they are handled separately inside `createPunctuationTokens()`.\n * The word separator explicitly only contains characters that split two words and not a word and a space.\n * - A space is a word separator because it separates two words if it occurs between them. For example: \"foo bar\"\n * - A tab is a word separator because it separates two words if it occurs between them. For example: \"foo\tbar\"\n * - A non-breaking space (u00A0) is a word separator because it separates two words if it occurs between them. For example: \"foo\\u00A0bar\".\n * - An en-dash (u2013), an em-dash (u2014), and a hyphen (u002d) are word separators because they separate two words if they occur between them.\n *   For example: \"foo–bar\".\n * Note that   is added here as #nbsp; -- we transform the & to # to prevent parse5 from converting it to a space and messing up highlighting.\n */\nconst WORD_SEPARATORS_REGEX = /([\\s\\t\\u00A0\\u2013\\u2014\\u002d[\\]]|#nbsp;)/;\n\n/**\n * Tokenizes a text similarly to `getWords`, but in a way that's suitable for the HTML parser.\n * 1. It does not normalize whitespace.\n * This operation is too risky for the HTML parser because it may throw away characters and as a result, the token positions are corrupted.\n * 2. It does not remove punctuation marks but keeps them.\n *\n * This algorithm splits the text by word separators: tokens that are the border between two words.\n * This algorithm separates punctuation marks from words and keeps them as separate tokens.\n * It only splits them off if they appear at the start or the end of a word.\n *\n * @param {string} text The text to tokenize.\n *\n * @returns {string[]} \tAn array of tokens.\n */\nconst splitIntoTokens = ( text ) => {\n\tif ( ! text ) {\n\t\treturn [];\n\t}\n\n\t// Split the sentence string into tokens. Those tokens are unrefined as they may contain punctuation.\n\tconst rawTokens = text.split( WORD_SEPARATORS_REGEX ).filter( x => x !== \"\" );\n\n\t// Remove punctuation from the beginning and end of word tokens, and make them into separate tokens.\n\treturn createPunctuationTokens( rawTokens );\n};\n\nexport default splitIntoTokens;\n"],"mappings":";;;;;;AAAA,IAAAA,wBAAA,GAAAC,sBAAA,CAAAC,OAAA;AAAgE,SAAAD,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAEhE;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,qBAAqB,GAAG,4CAA4C;;AAE1E;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,eAAe,GAAKC,IAAI,IAAM;EACnC,IAAK,CAAEA,IAAI,EAAG;IACb,OAAO,EAAE;EACV;;EAEA;EACA,MAAMC,SAAS,GAAGD,IAAI,CAACE,KAAK,CAAEJ,qBAAsB,CAAC,CAACK,MAAM,CAAEC,CAAC,IAAIA,CAAC,KAAK,EAAG,CAAC;;EAE7E;EACA,OAAO,IAAAC,gCAAuB,EAAEJ,SAAU,CAAC;AAC5C,CAAC;AAAC,IAAAK,QAAA,GAAAC,OAAA,CAAAV,OAAA,GAEaE,eAAe","ignoreList":[]}
+{"version":3,"file":"splitIntoTokens.js","names":["createPunctuationTokens","WORD_SEPARATORS_REGEX","splitIntoTokens","text","rawTokens","split","filter","x"],"sources":["../../../../src/languageProcessing/helpers/word/splitIntoTokens.js"],"sourcesContent":["import createPunctuationTokens from \"./createPunctuationTokens\";\n\n/*\n*  The following regex is used to split a text into tokens.\n * The regex matches word separators. A word separator is either a whitespace, a slash, a\n * tab, a non-breaking space, a hyphen, an en-dash or an em-dash.\n * Opening and closing square brackets are added to deal correctly with shortcodes downstream.\n * The regex is used to split a text into tokens.\n * Do not add punctuation marks to this regex, as they are handled separately inside `createPunctuationTokens()`.\n * The word separator explicitly only contains characters that split two words and not a word and a space.\n * - A space is a word separator because it separates two words if it occurs between them. For example: \"foo bar\"\n * - A tab is a word separator because it separates two words if it occurs between them. For example: \"foo\tbar\"\n * - A non-breaking space (u00A0) is a word separator because it separates two words if it occurs between them. For example: \"foo\\u00A0bar\".\n * - An en-dash (u2013), an em-dash (u2014), and a hyphen (u002d) are word separators because they separate two words if they occur between them.\n *   For example: \"foo–bar\".\n * Note that   is added here as #nbsp; -- we transform the & to # to prevent parse5 from converting it to a space and messing up highlighting.\n */\nconst WORD_SEPARATORS_REGEX = /([\\s\\t\\u00A0\\u2013\\u2014\\u002d[\\]]|#nbsp;)/;\n\n/**\n * Tokenizes a text similarly to `getWords`, but in a way that's suitable for the HTML parser.\n * 1. It does not normalize whitespace.\n * This operation is too risky for the HTML parser because it may throw away characters and as a result, the token positions are corrupted.\n * 2. It does not remove punctuation marks but keeps them.\n *\n * This algorithm splits the text by word separators: tokens that are the border between two words.\n * This algorithm separates punctuation marks from words and keeps them as separate tokens.\n * It only splits them off if they appear at the start or the end of a word.\n *\n * @param {string} text The text to tokenize.\n *\n * @returns {string[]} \tAn array of tokens.\n */\nconst splitIntoTokens = ( text ) => {\n\tif ( ! text ) {\n\t\treturn [];\n\t}\n\n\t// Split the sentence string into tokens. Those tokens are unrefined as they may contain punctuation.\n\tconst rawTokens = text.split( WORD_SEPARATORS_REGEX ).filter( x => x !== \"\" );\n\n\t// Remove punctuation from the beginning and end of word tokens, and make them into separate tokens.\n\treturn createPunctuationTokens( rawTokens );\n};\n\nexport default splitIntoTokens;\n"],"mappings":"AAAA,OAAOA,uBAAuB;;AAE9B;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,qBAAqB,GAAG,4CAA4C;;AAE1E;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,eAAe,GAAKC,IAAI,IAAM;EACnC,IAAK,CAAEA,IAAI,EAAG;IACb,OAAO,EAAE;EACV;;EAEA;EACA,MAAMC,SAAS,GAAGD,IAAI,CAACE,KAAK,CAAEJ,qBAAsB,CAAC,CAACK,MAAM,CAAEC,CAAC,IAAIA,CAAC,KAAK,EAAG,CAAC;;EAE7E;EACA,OAAOP,uBAAuB,CAAEI,SAAU,CAAC;AAC5C,CAAC;AAED,eAAeF,eAAe","ignoreList":[]}