axyseo 2.1.12 → 2.1.13

package/build/cjs/languageProcessing/helpers/url/url.js

@@ -0,0 +1,174 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _url = _interopRequireDefault(require("url"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+const urlFromAnchorRegex = /href=(["'])([^"']+)\1/i;
+/**
+ * Removes a hash from a URL, assumes a well formed URL.
+ *
+ * @param {string} url The URL to remove a hash from.
+ * @returns {string} The URL without the hash.
+ */
+function removeHash(url) {
+  return url.split("#")[0];
+}
+
+/**
+ * Removes all query args from a URL, assumes a well formed URL.
+ *
+ * @param {string} url The URL to remove the query args from.
+ * @returns {string} The URL without the query args.
+ */
+function removeQueryArgs(url) {
+  return url.split("?")[0];
+}
+
+/**
+ * Removes the trailing slash of a URL.
+ *
+ * @param {string} url The URL to remove the trailing slash from.
+ * @returns {string} A URL without a trailing slash.
+ */
+function removeTrailingSlash(url) {
+  return url.replace(/\/$/, "");
+}
+
+/**
+ * Adds a trailing slash to a URL if it is not present.
+ *
+ * @param {string} url The URL to add a trailing slash to.
+ * @returns {string} A URL with a trailing slash.
+ */
+function addTrailingSlash(url) {
+  return removeTrailingSlash(url) + "/";
+}
+
+/**
+ * Retrieves the URL from an anchor tag.
+ *
+ * @param {string} anchorTag An anchor tag.
+ * @returns {string} The URL in the anchor tag.
+ */
+function getFromAnchorTag(anchorTag) {
+  const urlMatch = urlFromAnchorRegex.exec(anchorTag);
+  return urlMatch === null ? "" : urlMatch[2];
+}
+
+/**
+ * Returns whether or not the given URLs are equal.
+ *
+ * @param {string} urlA The first URL to compare.
+ * @param {string} urlB The second URL to compare.
+ *
+ * @returns {boolean} Whether or not the given URLs are equal.
+ */
+function areEqual(urlA, urlB) {
+  // Make sure we are comparing URLs without query arguments and hashes.
+  urlA = removeQueryArgs(removeHash(urlA));
+  urlB = removeQueryArgs(removeHash(urlB));
+  return addTrailingSlash(urlA) === addTrailingSlash(urlB);
+}
+
+/**
+ * Returns the domain name of a URL.
+ *
+ * @param {string} url The URL to retrieve the domain name of.
+ * @returns {string} The domain name of the URL.
+ */
+function getHostname(url) {
+  url = _url.default.parse(url);
+  return url.hostname;
+}
+
+/**
+ * Returns the protocol of a URL.
+ *
+ * Note that the colon (http:) is also part of the protocol, conform to node's url.parse api.
+ *
+ * @param {string} url The URL to retrieve the protocol of.
+ * @returns {string|null} The protocol of the URL or null if no protocol is present.
+ */
+function getProtocol(url) {
+  return _url.default.parse(url).protocol;
+}
+
+/**
+ * Determine whether an anchor URL is internal.
+ *
+ * @param {string} anchorUrl 		The anchor URL to test.
+ * @param {string} siteUrlOrDomain  The current site's URL or domain.
+ *
+ * @returns {boolean} Whether or not the anchor URL is internal.
+ */
+function isInternalLink(anchorUrl, siteUrlOrDomain) {
+  const parsedAnchorUrl = _url.default.parse(anchorUrl, false, true);
+  const anchorUrlHostName = parsedAnchorUrl.hostname;
+
+  // Check if the anchor URL starts with a single slash.
+  if (anchorUrl.indexOf("//") === -1 && anchorUrl.indexOf("/") === 0) {
+    return true;
+  }
+
+  // Check if the anchor URL starts with a # indicating a fragment.
+  if (anchorUrl.indexOf("#") === 0) {
+    return false;
+  }
+
+  // No host of the anchor URL indicates an internal link.
+  if (!anchorUrlHostName) {
+    return true;
+  }
+
+  // If the siteUrlOrDomain variable is a domain, it would be idential to the anchor URL's hostname in case of an internal link.
+  if (anchorUrlHostName === siteUrlOrDomain) {
+    return true;
+  }
+
+  // If the siteUrlOrDomain variable is a URL and it shares the hostname with the anchor URL, it's an internal link.
+  const parsedSiteUrlOrDomain = _url.default.parse(siteUrlOrDomain);
+  const siteUrlOrDomainHostName = parsedSiteUrlOrDomain.hostname;
+  return anchorUrlHostName === siteUrlOrDomainHostName;
+}
+
+/**
+ * Checks whether the protocol is either HTTP: or HTTPS:.
+ *
+ * @param {string} protocol The protocol to test.
+ *
+ * @returns {boolean} Whether the protocol is http(s):.
+ */
+function protocolIsHttpScheme(protocol) {
+  if (!protocol) {
+    return false;
+  }
+  return protocol === "http:" || protocol === "https:";
+}
+
+/**
+ * Determines whether the link is a relative fragment URL.
+ *
+ * @param {string} url The URL to test.
+ *
+ * @returns {boolean} Whether the link is a relative fragment URL.
+ */
+function isRelativeFragmentURL(url) {
+  return url.indexOf("#") === 0;
+}
+var _default = exports.default = {
+  removeHash: removeHash,
+  removeQueryArgs: removeQueryArgs,
+  removeTrailingSlash: removeTrailingSlash,
+  addTrailingSlash: addTrailingSlash,
+  getFromAnchorTag: getFromAnchorTag,
+  areEqual: areEqual,
+  getHostname: getHostname,
+  getProtocol: getProtocol,
+  isInternalLink: isInternalLink,
+  protocolIsHttpScheme: protocolIsHttpScheme,
+  isRelativeFragmentURL: isRelativeFragmentURL
+};
+//# sourceMappingURL=url.js.map

package/build/cjs/languageProcessing/helpers/url/url.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"url.js","names":["_url","_interopRequireDefault","require","e","__esModule","default","urlFromAnchorRegex","removeHash","url","split","removeQueryArgs","removeTrailingSlash","replace","addTrailingSlash","getFromAnchorTag","anchorTag","urlMatch","exec","areEqual","urlA","urlB","getHostname","urlMethods","parse","hostname","getProtocol","protocol","isInternalLink","anchorUrl","siteUrlOrDomain","parsedAnchorUrl","anchorUrlHostName","indexOf","parsedSiteUrlOrDomain","siteUrlOrDomainHostName","protocolIsHttpScheme","isRelativeFragmentURL","_default","exports"],"sources":["../../../../../src/languageProcessing/helpers/url/url.js"],"sourcesContent":["const urlFromAnchorRegex = /href=([\"'])([^\"']+)\\1/i;\nimport urlMethods from \"url\";\n\n/**\n * Removes a hash from a URL, assumes a well formed URL.\n *\n * @param {string} url The URL to remove a hash from.\n * @returns {string} The URL without the hash.\n */\nfunction removeHash( url ) {\n\treturn url.split( \"#\" )[ 0 ];\n}\n\n/**\n * Removes all query args from a URL, assumes a well formed URL.\n *\n * @param {string} url The URL to remove the query args from.\n * @returns {string} The URL without the query args.\n */\nfunction removeQueryArgs( url ) {\n\treturn url.split( \"?\" )[ 0 ];\n}\n\n/**\n * Removes the trailing slash of a URL.\n *\n * @param {string} url The URL to remove the trailing slash from.\n * @returns {string} A URL without a trailing slash.\n */\nfunction removeTrailingSlash( url ) {\n\treturn url.replace( /\\/$/, \"\" );\n}\n\n/**\n * Adds a trailing slash to a URL if it is not present.\n *\n * @param {string} url The URL to add a trailing slash to.\n * @returns {string} A URL with a trailing slash.\n */\nfunction addTrailingSlash( url ) {\n\treturn removeTrailingSlash( url ) + \"/\";\n}\n\n/**\n * Retrieves the URL from an anchor tag.\n *\n * @param {string} anchorTag An anchor tag.\n * @returns {string} The URL in the anchor tag.\n */\nfunction getFromAnchorTag( anchorTag ) {\n\tconst urlMatch = urlFromAnchorRegex.exec( anchorTag );\n\n\treturn ( urlMatch === null ) ? \"\" : urlMatch[ 2 ];\n}\n\n/**\n * Returns whether or not the given URLs are equal.\n *\n * @param {string} urlA The first URL to compare.\n * @param {string} urlB The second URL to compare.\n *\n * @returns {boolean} Whether or not the given URLs are equal.\n */\nfunction areEqual( urlA, urlB ) {\n\t// Make sure we are comparing URLs without query arguments and hashes.\n\turlA = removeQueryArgs( removeHash( urlA ) );\n\turlB = removeQueryArgs( removeHash( urlB ) );\n\n\treturn addTrailingSlash( urlA ) === addTrailingSlash( urlB );\n}\n\n/**\n * Returns the domain name of a URL.\n *\n * @param {string} url The URL to retrieve the domain name of.\n * @returns {string} The domain name of the URL.\n */\nfunction getHostname( url ) {\n\turl = urlMethods.parse( url );\n\n\treturn url.hostname;\n}\n\n/**\n * Returns the protocol of a URL.\n *\n * Note that the colon (http:) is also part of the protocol, conform to node's url.parse api.\n *\n * @param {string} url The URL to retrieve the protocol of.\n * @returns {string|null} The protocol of the URL or null if no protocol is present.\n */\nfunction getProtocol( url ) {\n\treturn urlMethods.parse( url ).protocol;\n}\n\n/**\n * Determine whether an anchor URL is internal.\n *\n * @param {string} anchorUrl \t\tThe anchor URL to test.\n * @param {string} siteUrlOrDomain  The current site's URL or domain.\n *\n * @returns {boolean} Whether or not the anchor URL is internal.\n */\nfunction isInternalLink( anchorUrl, siteUrlOrDomain ) {\n\tconst parsedAnchorUrl = urlMethods.parse( anchorUrl, false, true );\n\tconst anchorUrlHostName = parsedAnchorUrl.hostname;\n\n\t// Check if the anchor URL starts with a single slash.\n\tif ( anchorUrl.indexOf( \"//\" ) === -1 && anchorUrl.indexOf( \"/\" ) === 0 ) {\n\t\treturn true;\n\t}\n\n\t// Check if the anchor URL starts with a # indicating a fragment.\n\tif ( anchorUrl.indexOf( \"#\" ) === 0 ) {\n\t\treturn false;\n\t}\n\n\t// No host of the anchor URL indicates an internal link.\n\tif ( ! anchorUrlHostName ) {\n\t\treturn true;\n\t}\n\n\t// If the siteUrlOrDomain variable is a domain, it would be idential to the anchor URL's hostname in case of an internal link.\n\tif ( anchorUrlHostName === siteUrlOrDomain ) {\n\t\treturn true;\n\t}\n\n\t// If the siteUrlOrDomain variable is a URL and it shares the hostname with the anchor URL, it's an internal link.\n\tconst parsedSiteUrlOrDomain = urlMethods.parse( siteUrlOrDomain );\n\tconst siteUrlOrDomainHostName = parsedSiteUrlOrDomain.hostname;\n\treturn anchorUrlHostName === siteUrlOrDomainHostName;\n}\n\n/**\n * Checks whether the protocol is either HTTP: or HTTPS:.\n *\n * @param {string} protocol The protocol to test.\n *\n * @returns {boolean} Whether the protocol is http(s):.\n */\nfunction protocolIsHttpScheme( protocol ) {\n\tif ( ! protocol ) {\n\t\treturn false;\n\t}\n\n\treturn ( protocol === \"http:\" || protocol === \"https:\" );\n}\n\n/**\n * Determines whether the link is a relative fragment URL.\n *\n * @param {string} url The URL to test.\n *\n * @returns {boolean} Whether the link is a relative fragment URL.\n */\nfunction isRelativeFragmentURL( url ) {\n\treturn url.indexOf( \"#\" ) === 0;\n}\n\nexport default {\n\tremoveHash: removeHash,\n\tremoveQueryArgs: removeQueryArgs,\n\tremoveTrailingSlash: removeTrailingSlash,\n\taddTrailingSlash: addTrailingSlash,\n\tgetFromAnchorTag: getFromAnchorTag,\n\tareEqual: areEqual,\n\tgetHostname: getHostname,\n\tgetProtocol: getProtocol,\n\tisInternalLink: isInternalLink,\n\tprotocolIsHttpScheme: protocolIsHttpScheme,\n\tisRelativeFragmentURL: isRelativeFragmentURL,\n};\n"],"mappings":";;;;;;AACA,IAAAA,IAAA,GAAAC,sBAAA,CAAAC,OAAA;AAA6B,SAAAD,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAD7B,MAAMG,kBAAkB,GAAG,wBAAwB;AAGnD;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,UAAUA,CAAEC,GAAG,EAAG;EAC1B,OAAOA,GAAG,CAACC,KAAK,CAAE,GAAI,CAAC,CAAE,CAAC,CAAE;AAC7B;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,eAAeA,CAAEF,GAAG,EAAG;EAC/B,OAAOA,GAAG,CAACC,KAAK,CAAE,GAAI,CAAC,CAAE,CAAC,CAAE;AAC7B;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA,SAASE,mBAAmBA,CAAEH,GAAG,EAAG;EACnC,OAAOA,GAAG,CAACI,OAAO,CAAE,KAAK,EAAE,EAAG,CAAC;AAChC;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,gBAAgBA,CAAEL,GAAG,EAAG;EAChC,OAAOG,mBAAmB,CAAEH,GAAI,CAAC,GAAG,GAAG;AACxC;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA,SAASM,gBAAgBA,CAAEC,SAAS,EAAG;EACtC,MAAMC,QAAQ,GAAGV,kBAAkB,CAACW,IAAI,CAAEF,SAAU,CAAC;EAErD,OAASC,QAAQ,KAAK,IAAI,GAAK,EAAE,GAAGA,QAAQ,CAAE,CAAC,CAAE;AAClD;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASE,QAAQA,CAAEC,IAAI,EAAEC,IAAI,EAAG;EAC/B;EACAD,IAAI,GAAGT,eAAe,CAAEH,UAAU,CAAEY,IAAK,CAAE,CAAC;EAC5CC,IAAI,GAAGV,eAAe,CAAEH,UAAU,CAAEa,IAAK,CAAE,CAAC;EAE5C,OAAOP,gBAAgB,CAAEM,IAAK,CAAC,KAAKN,gBAAgB,CAAEO,IAAK,CAAC;AAC7D;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,WAAWA,CAAEb,GAAG,EAAG;EAC3BA,GAAG,GAAGc,YAAU,CAACC,KAAK,CAAEf,GAAI,CAAC;EAE7B,OAAOA,GAAG,CAACgB,QAAQ;AACpB;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,WAAWA,CAAEjB,GAAG,EAAG;EAC3B,OAAOc,YAAU,CAACC,KAAK,CAAEf,GAAI,CAAC,CAACkB,QAAQ;AACxC;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,cAAcA,CAAEC,SAAS,EAAEC,eAAe,EAAG;EACrD,MAAMC,eAAe,GAAGR,YAAU,CAACC,KAAK,CAAEK,SAAS,EAAE,KAAK,EAAE,IAAK,CAAC;EAClE,MAAMG,iBAAiB,GAAGD,eAAe,CAACN,QAAQ;;EAElD;EACA,IAAKI,SAAS,CAACI,OAAO,CAAE,IAAK,CAAC,KAAK,CAAC,CAAC,IAAIJ,SAAS,CAACI,OAAO,CAAE,GAAI,CAAC,KAAK,CAAC,EAAG;IACzE,OAAO,IAAI;EACZ;;EAEA;EACA,IAAKJ,SAAS,CAACI,OAAO,CAAE,GAAI,CAAC,KAAK,CAAC,EAAG;IACrC,OAAO,KAAK;EACb;;EAEA;EACA,IAAK,CAAED,iBAAiB,EAAG;IAC1B,OAAO,IAAI;EACZ;;EAEA;EACA,IAAKA,iBAAiB,KAAKF,eAAe,EAAG;IAC5C,OAAO,IAAI;EACZ;;EAEA;EACA,MAAMI,qBAAqB,GAAGX,YAAU,CAACC,KAAK,CAAEM,eAAgB,CAAC;EACjE,MAAMK,uBAAuB,GAAGD,qBAAqB,CAACT,QAAQ;EAC9D,OAAOO,iBAAiB,KAAKG,uBAAuB;AACrD;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,oBAAoBA,CAAET,QAAQ,EAAG;EACzC,IAAK,CAAEA,QAAQ,EAAG;IACjB,OAAO,KAAK;EACb;EAEA,OAASA,QAAQ,KAAK,OAAO,IAAIA,QAAQ,KAAK,QAAQ;AACvD;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,SAASU,qBAAqBA,CAAE5B,GAAG,EAAG;EACrC,OAAOA,GAAG,CAACwB,OAAO,CAAE,GAAI,CAAC,KAAK,CAAC;AAChC;AAAC,IAAAK,QAAA,GAAAC,OAAA,CAAAjC,OAAA,GAEc;EACdE,UAAU,EAAEA,UAAU;EACtBG,eAAe,EAAEA,eAAe;EAChCC,mBAAmB,EAAEA,mBAAmB;EACxCE,gBAAgB,EAAEA,gBAAgB;EAClCC,gBAAgB,EAAEA,gBAAgB;EAClCI,QAAQ,EAAEA,QAAQ;EAClBG,WAAW,EAAEA,WAAW;EACxBI,WAAW,EAAEA,WAAW;EACxBE,cAAc,EAAEA,cAAc;EAC9BQ,oBAAoB,EAAEA,oBAAoB;EAC1CC,qBAAqB,EAAEA;AACxB,CAAC","ignoreList":[]}

package/build/cjs/languageProcessing/helpers/word/addWordboundary.js

@@ -0,0 +1,41 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+/**
+ * Returns a string that can be used in a regex to match a matchString with word boundaries.
+ *
+ * @param {string}  matchString                 The string to generate a regex string for.
+ * @param {boolean} [positiveLookAhead=false]   Boolean indicating whether or not to include a positive look ahead
+ * for the word boundaries at the end.
+ * @param {string} [extraWordBoundary=""]       Extra characters to match a word boundary on.
+ * @param {string} [language=""]                The language used to determine the word boundary.
+ *
+ * @returns {string} A regex string that matches the matchString with word boundaries.
+ */
+function _default(matchString, positiveLookAhead = false, extraWordBoundary = "", language = "") {
+  let wordBoundary, wordBoundaryEnd;
+  if (language === "id") {
+    wordBoundary = "[ \\u00a0\\n\\r\\t.,()”“〝〞〟‟„\"+;!¡?¿:/»«‹›" + extraWordBoundary + "<>";
+  } else {
+    /*
+     * \u00a0 - no-break space
+     * \u2014 - em dash
+           * \u06d4 - Urdu full stop
+           * \u061f - Arabic question mark
+           * \u060C - Arabic comma
+           * \u061B - Arabic semicolon
+           */
+    wordBoundary = "[ \\u00a0\\u2014\\u06d4\\u061f\\u060C\\u061B\\n\\r\\t.,()”“〝〞〟‟„\"+\\-;!¡?¿:/»«‹›" + extraWordBoundary + "<>";
+  }
+  const wordBoundaryStart = "(^|" + wordBoundary + "'‘’‛`])";
+  if (positiveLookAhead) {
+    wordBoundaryEnd = "($|((?=" + wordBoundary + "]))|((['‘’‛`])(" + wordBoundary + "])))";
+  } else {
+    wordBoundaryEnd = "($|(" + wordBoundary + "])|((['‘’‛`])(" + wordBoundary + "])))";
+  }
+  return wordBoundaryStart + matchString + wordBoundaryEnd;
+}
+//# sourceMappingURL=addWordboundary.js.map

package/build/cjs/languageProcessing/helpers/word/addWordboundary.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"addWordboundary.js","names":["_default","matchString","positiveLookAhead","extraWordBoundary","language","wordBoundary","wordBoundaryEnd","wordBoundaryStart"],"sources":["../../../../../src/languageProcessing/helpers/word/addWordboundary.js"],"sourcesContent":["/**\n * Returns a string that can be used in a regex to match a matchString with word boundaries.\n *\n * @param {string}  matchString                 The string to generate a regex string for.\n * @param {boolean} [positiveLookAhead=false]   Boolean indicating whether or not to include a positive look ahead\n * for the word boundaries at the end.\n * @param {string} [extraWordBoundary=\"\"]       Extra characters to match a word boundary on.\n * @param {string} [language=\"\"]                The language used to determine the word boundary.\n *\n * @returns {string} A regex string that matches the matchString with word boundaries.\n */\nexport default function( matchString, positiveLookAhead = false, extraWordBoundary = \"\", language = \"\" ) {\n\tlet wordBoundary, wordBoundaryEnd;\n\n\tif ( language === \"id\" ) {\n\t\twordBoundary = \"[ \\\\u00a0\\\\n\\\\r\\\\t.,()”“〝〞〟‟„\\\"+;!¡?¿:/»«‹›\" + extraWordBoundary + \"<>\";\n\t} else {\n\t\t/*\n\t\t * \\u00a0 - no-break space\n\t\t * \\u2014 - em dash\n         * \\u06d4 - Urdu full stop\n         * \\u061f - Arabic question mark\n         * \\u060C - Arabic comma\n         * \\u061B - Arabic semicolon\n         */\n\t\twordBoundary = \"[ \\\\u00a0\\\\u2014\\\\u06d4\\\\u061f\\\\u060C\\\\u061B\\\\n\\\\r\\\\t.,()”“〝〞〟‟„\\\"+\\\\-;!¡?¿:/»«‹›\" + extraWordBoundary + \"<>\";\n\t}\n\n\tconst wordBoundaryStart = \"(^|\" + wordBoundary + \"'‘’‛`])\";\n\tif ( positiveLookAhead ) {\n\t\twordBoundaryEnd = \"($|((?=\" + wordBoundary + \"]))|((['‘’‛`])(\" + wordBoundary + \"])))\";\n\t} else {\n\t\twordBoundaryEnd = \"($|(\" + wordBoundary + \"])|((['‘’‛`])(\" + wordBoundary + \"])))\";\n\t}\n\n\treturn wordBoundaryStart + matchString + wordBoundaryEnd;\n}\n"],"mappings":";;;;;;AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAA,SAAUC,WAAW,EAAEC,iBAAiB,GAAG,KAAK,EAAEC,iBAAiB,GAAG,EAAE,EAAEC,QAAQ,GAAG,EAAE,EAAG;EACxG,IAAIC,YAAY,EAAEC,eAAe;EAEjC,IAAKF,QAAQ,KAAK,IAAI,EAAG;IACxBC,YAAY,GAAG,6CAA6C,GAAGF,iBAAiB,GAAG,IAAI;EACxF,CAAC,MAAM;IACN;AACF;AACA;AACA;AACA;AACA;AACA;AACA;IACEE,YAAY,GAAG,mFAAmF,GAAGF,iBAAiB,GAAG,IAAI;EAC9H;EAEA,MAAMI,iBAAiB,GAAG,KAAK,GAAGF,YAAY,GAAG,SAAS;EAC1D,IAAKH,iBAAiB,EAAG;IACxBI,eAAe,GAAG,SAAS,GAAGD,YAAY,GAAG,iBAAiB,GAAGA,YAAY,GAAG,MAAM;EACvF,CAAC,MAAM;IACNC,eAAe,GAAG,MAAM,GAAGD,YAAY,GAAG,gBAAgB,GAAGA,YAAY,GAAG,MAAM;EACnF;EAEA,OAAOE,iBAAiB,GAAGN,WAAW,GAAGK,eAAe;AACzD","ignoreList":[]}

package/build/cjs/languageProcessing/helpers/word/areWordsInSentence.js

@@ -0,0 +1,23 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = areWordsInSentence;
+var _lodash = require("lodash");
+var _getWords = _interopRequireDefault(require("./getWords.js"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Checks if one or more words of a list occur in a sentence.
+ *
+ * @param {Array} words The list of words.
+ * @param {string} sentence The sentence to match against.
+ * @returns {Boolean} Whether the sentence contains the word.
+ */
+function areWordsInSentence(words, sentence) {
+  const matches = (0, _lodash.filter)((0, _getWords.default)(sentence), function (word) {
+    return words.includes(word.toLocaleLowerCase());
+  });
+  return matches.length !== 0;
+}
+//# sourceMappingURL=areWordsInSentence.js.map

package/build/cjs/languageProcessing/helpers/word/areWordsInSentence.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"areWordsInSentence.js","names":["_lodash","require","_getWords","_interopRequireDefault","e","__esModule","default","areWordsInSentence","words","sentence","matches","filter","getWords","word","includes","toLocaleLowerCase","length"],"sources":["../../../../../src/languageProcessing/helpers/word/areWordsInSentence.js"],"sourcesContent":["import { filter } from \"lodash\";\nimport getWords from \"./getWords.js\";\n\n/**\n * Checks if one or more words of a list occur in a sentence.\n *\n * @param {Array} words The list of words.\n * @param {string} sentence The sentence to match against.\n * @returns {Boolean} Whether the sentence contains the word.\n */\nexport default function areWordsInSentence( words, sentence ) {\n\tconst matches = filter( getWords( sentence ), function( word ) {\n\t\treturn words.includes( word.toLocaleLowerCase() );\n\t} );\n\treturn matches.length !== 0;\n}\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AACA,IAAAC,SAAA,GAAAC,sBAAA,CAAAF,OAAA;AAAqC,SAAAE,uBAAAC,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAErC;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAASG,kBAAkBA,CAAEC,KAAK,EAAEC,QAAQ,EAAG;EAC7D,MAAMC,OAAO,GAAG,IAAAC,cAAM,EAAE,IAAAC,iBAAQ,EAAEH,QAAS,CAAC,EAAE,UAAUI,IAAI,EAAG;IAC9D,OAAOL,KAAK,CAACM,QAAQ,CAAED,IAAI,CAACE,iBAAiB,CAAC,CAAE,CAAC;EAClD,CAAE,CAAC;EACH,OAAOL,OAAO,CAACM,MAAM,KAAK,CAAC;AAC5B","ignoreList":[]}

package/build/cjs/languageProcessing/helpers/word/countMetaDescriptionLength.js

@@ -0,0 +1,24 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+/**
+ * Check the length of the description.
+ *
+ * @param {string}  date          The date.
+ * @param {string}  description   The meta description.
+ *
+ * @returns {number} The length of the description.
+ */
+function _default(date, description) {
+  let descriptionLength = description.length;
+  /* If the meta description is preceded by a date, two spaces and a hyphen (" - ") are added as well. Therefore,
+  three needs to be added to the total length. */
+  if (date !== "" && descriptionLength > 0) {
+    descriptionLength += date.length + 3;
+  }
+  return descriptionLength;
+}
+//# sourceMappingURL=countMetaDescriptionLength.js.map

package/build/cjs/languageProcessing/helpers/word/countMetaDescriptionLength.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"countMetaDescriptionLength.js","names":["_default","date","description","descriptionLength","length"],"sources":["../../../../../src/languageProcessing/helpers/word/countMetaDescriptionLength.js"],"sourcesContent":["/**\n * Check the length of the description.\n *\n * @param {string}  date          The date.\n * @param {string}  description   The meta description.\n *\n * @returns {number} The length of the description.\n */\nexport default function( date, description ) {\n\tlet descriptionLength = description.length;\n\t/* If the meta description is preceded by a date, two spaces and a hyphen (\" - \") are added as well. Therefore,\n\tthree needs to be added to the total length. */\n\tif ( date !== \"\" && descriptionLength > 0 ) {\n\t\tdescriptionLength += date.length + 3;\n\t}\n\n\treturn descriptionLength;\n}\n"],"mappings":";;;;;;AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAA,SAAUC,IAAI,EAAEC,WAAW,EAAG;EAC5C,IAAIC,iBAAiB,GAAGD,WAAW,CAACE,MAAM;EAC1C;AACD;EACC,IAAKH,IAAI,KAAK,EAAE,IAAIE,iBAAiB,GAAG,CAAC,EAAG;IAC3CA,iBAAiB,IAAIF,IAAI,CAACG,MAAM,GAAG,CAAC;EACrC;EAEA,OAAOD,iBAAiB;AACzB","ignoreList":[]}

package/build/cjs/languageProcessing/helpers/word/countWords.js

@@ -0,0 +1,21 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _getWords = _interopRequireDefault(require("./getWords.js"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/** @module stringProcessing/countWords */
+
+/**
+ * Calculates the word count of a certain text.
+ *
+ * @param {string} text The text to be counted.
+ *
+ * @returns {number} The word count of the given text.
+ */
+function _default(text) {
+  return (0, _getWords.default)(text).length;
+}
+//# sourceMappingURL=countWords.js.map

package/build/cjs/languageProcessing/helpers/word/countWords.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"countWords.js","names":["_getWords","_interopRequireDefault","require","e","__esModule","default","_default","text","getWords","length"],"sources":["../../../../../src/languageProcessing/helpers/word/countWords.js"],"sourcesContent":["/** @module stringProcessing/countWords */\n\nimport getWords from \"./getWords.js\";\n\n/**\n * Calculates the word count of a certain text.\n *\n * @param {string} text The text to be counted.\n *\n * @returns {number} The word count of the given text.\n */\nexport default function( text ) {\n\treturn getWords( text ).length;\n}\n"],"mappings":";;;;;;AAEA,IAAAA,SAAA,GAAAC,sBAAA,CAAAC,OAAA;AAAqC,SAAAD,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAFrC;;AAIA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAAUC,IAAI,EAAG;EAC/B,OAAO,IAAAC,iBAAQ,EAAED,IAAK,CAAC,CAACE,MAAM;AAC/B","ignoreList":[]}

package/build/cjs/languageProcessing/helpers/word/createPunctuationTokens.js

@@ -0,0 +1,46 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = void 0;
+var _removePunctuation = require("../sanitize/removePunctuation");
+var _htmlEntities = require("../../../helpers/htmlEntities");
+/**
+ * Removes punctuation from the beginning and end of a word token, and creates separate tokens from them.
+ *
+ * @param {string[]} rawTokens	The tokens that may contain punctuation at the beginning and end of words.
+ *
+ * @returns {string[]} The tokens with the punctuation moved into separate tokens.
+ */
+const createPunctuationTokens = rawTokens => {
+  const tokenTexts = [];
+  rawTokens.forEach(token => {
+    // Pretokens contains all that occurs before the first letter of the token.
+    const preTokens = [];
+    // Posttokens contains all that occurs after the last letter of the token.
+    const postTokens = [];
+
+    // Add all punctuation marks that occur before the first letter of the token to the pretokens array.
+    // Also, prevent matching with a hashed HTML entity in the beginning of the token.
+    while (_removePunctuation.punctuationRegexStart.test(token) && !_htmlEntities.hashedHtmlEntitiesRegexStart.test(token)) {
+      preTokens.push(token[0]);
+      token = token.slice(1);
+    }
+    // Add all punctuation marks that occur after the last letter of the token to the posttokens array.
+    // Also, prevent matching with a hashed HTML entity at the end of the token.
+    while (_removePunctuation.punctuationRegexEnd.test(token) && !_htmlEntities.hashedHtmlEntitiesRegexEnd.test(token)) {
+      // Using unshift here because we are iterating from the end of the string to the beginning,
+      // and we want to keep the order of the punctuation marks.
+      // Therefore, we add them to the start of the array.
+      postTokens.unshift(token[token.length - 1]);
+      token = token.slice(0, -1);
+    }
+    let currentTokens = [...preTokens, token, ...postTokens];
+    currentTokens = currentTokens.filter(x => x !== "");
+    tokenTexts.push(...currentTokens);
+  });
+  return tokenTexts;
+};
+var _default = exports.default = createPunctuationTokens;
+//# sourceMappingURL=createPunctuationTokens.js.map

package/build/cjs/languageProcessing/helpers/word/createPunctuationTokens.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"createPunctuationTokens.js","names":["_removePunctuation","require","_htmlEntities","createPunctuationTokens","rawTokens","tokenTexts","forEach","token","preTokens","postTokens","punctuationRegexStart","test","hashedHtmlEntitiesRegexStart","push","slice","punctuationRegexEnd","hashedHtmlEntitiesRegexEnd","unshift","length","currentTokens","filter","x","_default","exports","default"],"sources":["../../../../../src/languageProcessing/helpers/word/createPunctuationTokens.js"],"sourcesContent":["import { punctuationRegexEnd, punctuationRegexStart } from \"../sanitize/removePunctuation\";\nimport { hashedHtmlEntitiesRegexEnd, hashedHtmlEntitiesRegexStart } from \"../../../helpers/htmlEntities\";\n\n/**\n * Removes punctuation from the beginning and end of a word token, and creates separate tokens from them.\n *\n * @param {string[]} rawTokens\tThe tokens that may contain punctuation at the beginning and end of words.\n *\n * @returns {string[]} The tokens with the punctuation moved into separate tokens.\n */\nconst createPunctuationTokens = ( rawTokens ) => {\n\tconst tokenTexts = [];\n\trawTokens.forEach( token => {\n\t\t// Pretokens contains all that occurs before the first letter of the token.\n\t\tconst preTokens = [];\n\t\t// Posttokens contains all that occurs after the last letter of the token.\n\t\tconst postTokens = [];\n\n\t\t// Add all punctuation marks that occur before the first letter of the token to the pretokens array.\n\t\t// Also, prevent matching with a hashed HTML entity in the beginning of the token.\n\t\twhile ( punctuationRegexStart.test( token ) && ! hashedHtmlEntitiesRegexStart.test( token ) ) {\n\t\t\tpreTokens.push( token[ 0 ] );\n\t\t\ttoken = token.slice( 1 );\n\t\t}\n\t\t// Add all punctuation marks that occur after the last letter of the token to the posttokens array.\n\t\t// Also, prevent matching with a hashed HTML entity at the end of the token.\n\t\twhile ( punctuationRegexEnd.test( token ) && ! hashedHtmlEntitiesRegexEnd.test( token ) ) {\n\t\t\t// Using unshift here because we are iterating from the end of the string to the beginning,\n\t\t\t// and we want to keep the order of the punctuation marks.\n\t\t\t// Therefore, we add them to the start of the array.\n\t\t\tpostTokens.unshift( token[ token.length - 1 ] );\n\t\t\ttoken = token.slice( 0, -1 );\n\t\t}\n\n\t\tlet currentTokens = [ ...preTokens, token, ...postTokens ];\n\t\tcurrentTokens = currentTokens.filter( x => x !== \"\" );\n\t\ttokenTexts.push( ...currentTokens );\n\t} );\n\treturn tokenTexts;\n};\n\nexport default createPunctuationTokens;\n"],"mappings":";;;;;;AAAA,IAAAA,kBAAA,GAAAC,OAAA;AACA,IAAAC,aAAA,GAAAD,OAAA;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,uBAAuB,GAAKC,SAAS,IAAM;EAChD,MAAMC,UAAU,GAAG,EAAE;EACrBD,SAAS,CAACE,OAAO,CAAEC,KAAK,IAAI;IAC3B;IACA,MAAMC,SAAS,GAAG,EAAE;IACpB;IACA,MAAMC,UAAU,GAAG,EAAE;;IAErB;IACA;IACA,OAAQC,wCAAqB,CAACC,IAAI,CAAEJ,KAAM,CAAC,IAAI,CAAEK,0CAA4B,CAACD,IAAI,CAAEJ,KAAM,CAAC,EAAG;MAC7FC,SAAS,CAACK,IAAI,CAAEN,KAAK,CAAE,CAAC,CAAG,CAAC;MAC5BA,KAAK,GAAGA,KAAK,CAACO,KAAK,CAAE,CAAE,CAAC;IACzB;IACA;IACA;IACA,OAAQC,sCAAmB,CAACJ,IAAI,CAAEJ,KAAM,CAAC,IAAI,CAAES,wCAA0B,CAACL,IAAI,CAAEJ,KAAM,CAAC,EAAG;MACzF;MACA;MACA;MACAE,UAAU,CAACQ,OAAO,CAAEV,KAAK,CAAEA,KAAK,CAACW,MAAM,GAAG,CAAC,CAAG,CAAC;MAC/CX,KAAK,GAAGA,KAAK,CAACO,KAAK,CAAE,CAAC,EAAE,CAAC,CAAE,CAAC;IAC7B;IAEA,IAAIK,aAAa,GAAG,CAAE,GAAGX,SAAS,EAAED,KAAK,EAAE,GAAGE,UAAU,CAAE;IAC1DU,aAAa,GAAGA,aAAa,CAACC,MAAM,CAAEC,CAAC,IAAIA,CAAC,KAAK,EAAG,CAAC;IACrDhB,UAAU,CAACQ,IAAI,CAAE,GAAGM,aAAc,CAAC;EACpC,CAAE,CAAC;EACH,OAAOd,UAAU;AAClB,CAAC;AAAC,IAAAiB,QAAA,GAAAC,OAAA,CAAAC,OAAA,GAEarB,uBAAuB","ignoreList":[]}

package/build/cjs/languageProcessing/helpers/word/filterWordsFromArray.js

@@ -0,0 +1,21 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = filterWordsFromArray;
+var _lodash = require("lodash");
+/**
+ * Filters certain words from an array of words.
+ *
+ * @param {Array} array The words to check.
+ * @param {Array} words The words to filter.
+ *
+ * @returns {Array} The original array with the certain words filtered out.
+ */
+function filterWordsFromArray(array, words = []) {
+  return (0, _lodash.filter)(array, function (word) {
+    return !(0, _lodash.includes)(words, word.trim().toLocaleLowerCase());
+  });
+}
+//# sourceMappingURL=filterWordsFromArray.js.map

package/build/cjs/languageProcessing/helpers/word/filterWordsFromArray.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"filterWordsFromArray.js","names":["_lodash","require","filterWordsFromArray","array","words","filter","word","includes","trim","toLocaleLowerCase"],"sources":["../../../../../src/languageProcessing/helpers/word/filterWordsFromArray.js"],"sourcesContent":["import { filter, includes } from \"lodash\";\n\n/**\n * Filters certain words from an array of words.\n *\n * @param {Array} array The words to check.\n * @param {Array} words The words to filter.\n *\n * @returns {Array} The original array with the certain words filtered out.\n */\nexport default function filterWordsFromArray( array, words = [] ) {\n\treturn filter( array, function( word ) {\n\t\treturn ( ! includes( words, word.trim().toLocaleLowerCase() ) );\n\t} );\n}\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAASC,oBAAoBA,CAAEC,KAAK,EAAEC,KAAK,GAAG,EAAE,EAAG;EACjE,OAAO,IAAAC,cAAM,EAAEF,KAAK,EAAE,UAAUG,IAAI,EAAG;IACtC,OAAS,CAAE,IAAAC,gBAAQ,EAAEH,KAAK,EAAEE,IAAI,CAACE,IAAI,CAAC,CAAC,CAACC,iBAAiB,CAAC,CAAE,CAAC;EAC9D,CAAE,CAAC;AACJ","ignoreList":[]}

package/build/cjs/languageProcessing/helpers/word/followsIndex.js

@@ -0,0 +1,29 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _lodash = require("lodash");
+/**
+ * Checks whether a given word is followed by any word from a given list.
+ *
+ * @param {Array} followingWords    The array of objects with matches and indices.
+ * @param {Object} match            The object with the match and index to test the following words for.
+ *
+ * @returns {boolean} Returns true if the match is followed by a given word, otherwise returns false.
+ */
+function _default(followingWords, match) {
+  if ((0, _lodash.isEmpty)(followingWords)) {
+    return false;
+  }
+
+  // The followingWordIndices include the preceding space.
+  const wordAfterMatchIndex = match.index + match.match.length;
+  const followingWordsIndices = [];
+  (0, _lodash.forEach)(followingWords, function (followingWord) {
+    followingWordsIndices.push(followingWord.index);
+  });
+  return (0, _lodash.includes)(followingWordsIndices, wordAfterMatchIndex);
+}
+//# sourceMappingURL=followsIndex.js.map

package/build/cjs/languageProcessing/helpers/word/followsIndex.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"followsIndex.js","names":["_lodash","require","_default","followingWords","match","isEmpty","wordAfterMatchIndex","index","length","followingWordsIndices","forEach","followingWord","push","includes"],"sources":["../../../../../src/languageProcessing/helpers/word/followsIndex.js"],"sourcesContent":["import { isEmpty, forEach, includes } from \"lodash\";\n\n/**\n * Checks whether a given word is followed by any word from a given list.\n *\n * @param {Array} followingWords    The array of objects with matches and indices.\n * @param {Object} match            The object with the match and index to test the following words for.\n *\n * @returns {boolean} Returns true if the match is followed by a given word, otherwise returns false.\n */\nexport default function( followingWords, match ) {\n\tif ( isEmpty( followingWords ) ) {\n\t\treturn false;\n\t}\n\n\t// The followingWordIndices include the preceding space.\n\tconst wordAfterMatchIndex = match.index + match.match.length;\n\tconst followingWordsIndices = [];\n\n\tforEach( followingWords, function( followingWord ) {\n\t\tfollowingWordsIndices.push( followingWord.index );\n\t} );\n\n\treturn includes( followingWordsIndices, wordAfterMatchIndex );\n}\n"],"mappings":";;;;;;AAAA,IAAAA,OAAA,GAAAC,OAAA;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAC,SAAUC,cAAc,EAAEC,KAAK,EAAG;EAChD,IAAK,IAAAC,eAAO,EAAEF,cAAe,CAAC,EAAG;IAChC,OAAO,KAAK;EACb;;EAEA;EACA,MAAMG,mBAAmB,GAAGF,KAAK,CAACG,KAAK,GAAGH,KAAK,CAACA,KAAK,CAACI,MAAM;EAC5D,MAAMC,qBAAqB,GAAG,EAAE;EAEhC,IAAAC,eAAO,EAAEP,cAAc,EAAE,UAAUQ,aAAa,EAAG;IAClDF,qBAAqB,CAACG,IAAI,CAAED,aAAa,CAACJ,KAAM,CAAC;EAClD,CAAE,CAAC;EAEH,OAAO,IAAAM,gBAAQ,EAAEJ,qBAAqB,EAAEH,mBAAoB,CAAC;AAC9D","ignoreList":[]}

package/build/cjs/languageProcessing/helpers/word/getAllWordsFromTree.js

@@ -0,0 +1,30 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+var _getSentencesFromTree = _interopRequireDefault(require("../sentence/getSentencesFromTree"));
+var _lodash = require("lodash");
+var _removePunctuation = _interopRequireDefault(require("../sanitize/removePunctuation"));
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/**
+ * Gets the words from the tree, i.e. from the paragraph and heading nodes.
+ * These two node types are the nodes that should contain words for the analysis.
+ *
+ * @param {Paper} paper The paper to get the tree and words from.
+ *
+ * @returns {String[]} Array of words retrieved from the tree.
+ */
+function _default(paper) {
+  const sentences = (0, _getSentencesFromTree.default)(paper);
+  // Get all the tokens from each sentence.
+  const tokens = sentences.map(sentence => sentence.tokens);
+  let words = (0, _lodash.flatMap)(tokens).map(token => token.text);
+  // Remove punctuation and spaces.
+  words = words.map(token => (0, _removePunctuation.default)(token));
+
+  // Filter out empty tokens.
+  return words.filter(word => word.trim() !== "");
+}
+//# sourceMappingURL=getAllWordsFromTree.js.map

package/build/cjs/languageProcessing/helpers/word/getAllWordsFromTree.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"getAllWordsFromTree.js","names":["_getSentencesFromTree","_interopRequireDefault","require","_lodash","_removePunctuation","e","__esModule","default","_default","paper","sentences","getSentencesFromTree","tokens","map","sentence","words","flatMap","token","text","removePunctuation","filter","word","trim"],"sources":["../../../../../src/languageProcessing/helpers/word/getAllWordsFromTree.js"],"sourcesContent":["import getSentencesFromTree from \"../sentence/getSentencesFromTree\";\nimport { flatMap } from \"lodash\";\nimport removePunctuation from \"../sanitize/removePunctuation\";\n\n/**\n * Gets the words from the tree, i.e. from the paragraph and heading nodes.\n * These two node types are the nodes that should contain words for the analysis.\n *\n * @param {Paper} paper The paper to get the tree and words from.\n *\n * @returns {String[]} Array of words retrieved from the tree.\n */\nexport default function( paper ) {\n\tconst sentences = getSentencesFromTree( paper );\n\t// Get all the tokens from each sentence.\n\tconst tokens = sentences.map( sentence => sentence.tokens );\n\tlet words = flatMap( tokens ).map( token => token.text );\n\t// Remove punctuation and spaces.\n\twords = words.map( token => removePunctuation( token ) );\n\n\t// Filter out empty tokens.\n\treturn words.filter( word => word.trim() !== \"\" );\n}\n"],"mappings":";;;;;;AAAA,IAAAA,qBAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,OAAA,GAAAD,OAAA;AACA,IAAAE,kBAAA,GAAAH,sBAAA,CAAAC,OAAA;AAA8D,SAAAD,uBAAAI,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAE9D;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAAUC,KAAK,EAAG;EAChC,MAAMC,SAAS,GAAG,IAAAC,6BAAoB,EAAEF,KAAM,CAAC;EAC/C;EACA,MAAMG,MAAM,GAAGF,SAAS,CAACG,GAAG,CAAEC,QAAQ,IAAIA,QAAQ,CAACF,MAAO,CAAC;EAC3D,IAAIG,KAAK,GAAG,IAAAC,eAAO,EAAEJ,MAAO,CAAC,CAACC,GAAG,CAAEI,KAAK,IAAIA,KAAK,CAACC,IAAK,CAAC;EACxD;EACAH,KAAK,GAAGA,KAAK,CAACF,GAAG,CAAEI,KAAK,IAAI,IAAAE,0BAAiB,EAAEF,KAAM,CAAE,CAAC;;EAExD;EACA,OAAOF,KAAK,CAACK,MAAM,CAAEC,IAAI,IAAIA,IAAI,CAACC,IAAI,CAAC,CAAC,KAAK,EAAG,CAAC;AAClD","ignoreList":[]}

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

@@ -0,0 +1,54 @@
+"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 _interopRequireWildcard(e, t) { if ("function" == typeof WeakMap) var r = new WeakMap(), n = new WeakMap(); return (_interopRequireWildcard = function (e, t) { if (!t && e && e.__esModule) return e; var o, i, f = { __proto__: null, default: e }; if (null === e || "object" != typeof e && "function" != typeof e) return f; if (o = t ? n : r) { if (o.has(e)) return o.get(e); o.set(e, f); } for (const t in e) "default" !== t && {}.hasOwnProperty.call(e, t) && ((i = (o = Object.defineProperty) && Object.getOwnPropertyDescriptor(e, t)) && (i.get || i.set) ? o(f, t, i) : f[t] = e[t]); return f; })(e, t); }
+function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
+/** @module stringProcessing/countWords */
+
+const punctuationRegex = new RegExp(`([${_removePunctuation.punctuationRegexString}])`, 'g');
+
+/**
+ * Returns an array with words used in the text.
+ *
+ * @param {string} text The text to be counted.
+ * @param {string} [wordBoundaryRegexString=\\s] The regex string for the word boundary that should be used to split the text into words.
+ * @param {boolean} [shouldRemovePunctuation=true] If punctuation should be removed. Defaults to `true`.
+ *
+ * @returns {Array} The array with all words.
+ */
+function _default(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);
+  if (text === '') {
+    return [];
+  }
+  const chineseCharRegex = /[\u4e00-\u9fff]/;
+  const hasChinese = chineseCharRegex.test(text);
+  const hasNoSpaces = !/\s/.test(text);
+  let words = [];
+  if (hasChinese && hasNoSpaces) {
+    words = Array.from(text).filter(char => chineseCharRegex.test(char));
+  } else {
+    const wordBoundaryRegex = new RegExp(wordBoundaryRegexString, 'g');
+    words = text.split(wordBoundaryRegex);
+    if (shouldRemovePunctuation) {
+      words = words.map(_removePunctuation.default);
+    } else {
+      // If punctuation is not removed, punctuation marks are tokenized as if they were words.
+      words = (0, _lodash.flatMap)(words, word => {
+        const newWord = word.replace(punctuationRegex, ' $1 ');
+        return newWord.split(' ');
+      });
+    }
+  }
+  return (0, _lodash.filter)(words, function (word) {
+    return word.trim() !== '';
+  });
+}
+//# sourceMappingURL=getWords.js.map

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

@@ -0,0 +1 @@
+{"version":3,"file":"getWords.js","names":["_sanitizeString","_interopRequireDefault","require","_lodash","_removePunctuation","_interopRequireWildcard","e","t","WeakMap","r","n","__esModule","o","i","f","__proto__","default","has","get","set","hasOwnProperty","call","Object","defineProperty","getOwnPropertyDescriptor","punctuationRegex","RegExp","punctuationRegexString","_default","text","wordBoundaryRegexString","shouldRemovePunctuation","sanitizeString","chineseCharRegex","hasChinese","test","hasNoSpaces","words","Array","from","filter","char","wordBoundaryRegex","split","map","removePunctuation","flatMap","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  // Unify whitespaces and non-breaking spaces, remove table of content and strip the tags and multiple spaces.\n  text = sanitizeString(text);\n\n  if (text === '') {\n    return [];\n  }\n\n  const chineseCharRegex = /[\\u4e00-\\u9fff]/;\n  const hasChinese = chineseCharRegex.test(text);\n  const hasNoSpaces = !/\\s/.test(text);\n\n  let words = [];\n\n  if (hasChinese && hasNoSpaces) {\n    words = Array.from(text).filter(char => chineseCharRegex.test(char));\n  } else {\n    const wordBoundaryRegex = new RegExp(wordBoundaryRegexString, 'g');\n\n    words = text.split(wordBoundaryRegex);\n\n    if (shouldRemovePunctuation) {\n      words = words.map(removePunctuation);\n    } else {\n      // If punctuation is not removed, punctuation marks are tokenized as if they were words.\n      words = flatMap(words, word => {\n        const newWord = word.replace(punctuationRegex, ' $1 ');\n        return newWord.split(' ');\n      });\n    }\n  }\n\n  return filter(words, function(word) {\n    return word.trim() !== '';\n  });\n}\n"],"mappings":";;;;;;AACA,IAAAA,eAAA,GAAAC,sBAAA,CAAAC,OAAA;AACA,IAAAC,OAAA,GAAAD,OAAA;AACA,IAAAE,kBAAA,GAAAC,uBAAA,CAAAH,OAAA;AAA2F,SAAAG,wBAAAC,CAAA,EAAAC,CAAA,6BAAAC,OAAA,MAAAC,CAAA,OAAAD,OAAA,IAAAE,CAAA,OAAAF,OAAA,YAAAH,uBAAA,YAAAA,CAAAC,CAAA,EAAAC,CAAA,SAAAA,CAAA,IAAAD,CAAA,IAAAA,CAAA,CAAAK,UAAA,SAAAL,CAAA,MAAAM,CAAA,EAAAC,CAAA,EAAAC,CAAA,KAAAC,SAAA,QAAAC,OAAA,EAAAV,CAAA,iBAAAA,CAAA,uBAAAA,CAAA,yBAAAA,CAAA,SAAAQ,CAAA,MAAAF,CAAA,GAAAL,CAAA,GAAAG,CAAA,GAAAD,CAAA,QAAAG,CAAA,CAAAK,GAAA,CAAAX,CAAA,UAAAM,CAAA,CAAAM,GAAA,CAAAZ,CAAA,GAAAM,CAAA,CAAAO,GAAA,CAAAb,CAAA,EAAAQ,CAAA,gBAAAP,CAAA,IAAAD,CAAA,gBAAAC,CAAA,OAAAa,cAAA,CAAAC,IAAA,CAAAf,CAAA,EAAAC,CAAA,OAAAM,CAAA,IAAAD,CAAA,GAAAU,MAAA,CAAAC,cAAA,KAAAD,MAAA,CAAAE,wBAAA,CAAAlB,CAAA,EAAAC,CAAA,OAAAM,CAAA,CAAAK,GAAA,IAAAL,CAAA,CAAAM,GAAA,IAAAP,CAAA,CAAAE,CAAA,EAAAP,CAAA,EAAAM,CAAA,IAAAC,CAAA,CAAAP,CAAA,IAAAD,CAAA,CAAAC,CAAA,WAAAO,CAAA,KAAAR,CAAA,EAAAC,CAAA;AAAA,SAAAN,uBAAAK,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAK,UAAA,GAAAL,CAAA,KAAAU,OAAA,EAAAV,CAAA;AAH3F;;AAKA,MAAMmB,gBAAgB,GAAG,IAAIC,MAAM,CAAC,KAAKC,yCAAsB,IAAI,EAAE,GAAG,CAAC;;AAEzE;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAC,SAASC,IAAI,EAAEC,uBAAuB,GAAG,KAAK,EAAEC,uBAAuB,GAAG,IAAI,EAAE;EAC7F;EACAF,IAAI,GAAG,IAAAG,uBAAc,EAACH,IAAI,CAAC;EAE3B,IAAIA,IAAI,KAAK,EAAE,EAAE;IACf,OAAO,EAAE;EACX;EAEA,MAAMI,gBAAgB,GAAG,iBAAiB;EAC1C,MAAMC,UAAU,GAAGD,gBAAgB,CAACE,IAAI,CAACN,IAAI,CAAC;EAC9C,MAAMO,WAAW,GAAG,CAAC,IAAI,CAACD,IAAI,CAACN,IAAI,CAAC;EAEpC,IAAIQ,KAAK,GAAG,EAAE;EAEd,IAAIH,UAAU,IAAIE,WAAW,EAAE;IAC7BC,KAAK,GAAGC,KAAK,CAACC,IAAI,CAACV,IAAI,CAAC,CAACW,MAAM,CAACC,IAAI,IAAIR,gBAAgB,CAACE,IAAI,CAACM,IAAI,CAAC,CAAC;EACtE,CAAC,MAAM;IACL,MAAMC,iBAAiB,GAAG,IAAIhB,MAAM,CAACI,uBAAuB,EAAE,GAAG,CAAC;IAElEO,KAAK,GAAGR,IAAI,CAACc,KAAK,CAACD,iBAAiB,CAAC;IAErC,IAAIX,uBAAuB,EAAE;MAC3BM,KAAK,GAAGA,KAAK,CAACO,GAAG,CAACC,0BAAiB,CAAC;IACtC,CAAC,MAAM;MACL;MACAR,KAAK,GAAG,IAAAS,eAAO,EAACT,KAAK,EAAEU,IAAI,IAAI;QAC7B,MAAMC,OAAO,GAAGD,IAAI,CAACE,OAAO,CAACxB,gBAAgB,EAAE,MAAM,CAAC;QACtD,OAAOuB,OAAO,CAACL,KAAK,CAAC,GAAG,CAAC;MAC3B,CAAC,CAAC;IACJ;EACF;EAEA,OAAO,IAAAH,cAAM,EAACH,KAAK,EAAE,UAASU,IAAI,EAAE;IAClC,OAAOA,IAAI,CAACG,IAAI,CAAC,CAAC,KAAK,EAAE;EAC3B,CAAC,CAAC;AACJ","ignoreList":[]}

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

@@ -0,0 +1,34 @@
+"use strict";
+
+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.
+ *
+ * @param {Array} precedingWords    The array of objects with matches and indices.
+ * @param {number} matchIndex       The index of the word for which to check whether it's preceded by one of the other words.
+ * @param {boolean} addSpace        True if a space should be added.
+ *
+ * @returns {boolean} Returns true if the match is preceded by a given word, otherwise returns false.
+ */
+function _default(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)) {
+    return false;
+  }
+  const precedingWordsEndIndices = [];
+  (0, _lodash.forEach)(precedingWords, function (precedingWord) {
+    const precedingWordsEndIndex = precedingWord.index + precedingWord.match.length + space;
+    precedingWordsEndIndices.push(precedingWordsEndIndex);
+  });
+  return (0, _lodash.includes)(precedingWordsEndIndices, matchIndex);
+}
+//# sourceMappingURL=includesIndex.js.map

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

@@ -0,0 +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":[]}