axyseo 2.0.0-alpha.0.0.4 → 2.0.0-alpha.0.0.40

package/build/languageProcessing/helpers/sanitize/quotes.js

@@ -1,14 +1,5 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = exports.SINGLE_QUOTES_REGEX = exports.SINGLE_QUOTES_ARRAY = void 0;
-exports.normalize = normalizeQuotes;
-exports.normalizeDouble = normalizeDoubleQuotes;
-exports.normalizeSingle = normalizeSingleQuotes;
-const SINGLE_QUOTES_ARRAY = exports.SINGLE_QUOTES_ARRAY = ["'", "‘", "’", "‛", "`", "‹", "›"];
-const SINGLE_QUOTES_REGEX = exports.SINGLE_QUOTES_REGEX = new RegExp("[" + SINGLE_QUOTES_ARRAY.join("") + "]", "g");
+const SINGLE_QUOTES_ARRAY = ["'", "‘", "’", "‛", "`", "‹", "›"];
+const SINGLE_QUOTES_REGEX = new RegExp("[" + SINGLE_QUOTES_ARRAY.join("") + "]", "g");
 
 /**
  * Normalizes single quotes to 'regular' quotes.
@@ -39,7 +30,8 @@ function normalizeDoubleQuotes(text) {
 function normalizeQuotes(text) {
   return normalizeDoubleQuotes(normalizeSingleQuotes(text));
 }
-var _default = exports.default = {
+export { normalizeSingleQuotes as normalizeSingle, normalizeDoubleQuotes as normalizeDouble, normalizeQuotes as normalize, SINGLE_QUOTES_REGEX, SINGLE_QUOTES_ARRAY };
+export default {
   normalizeSingle: normalizeSingleQuotes,
   normalizeDouble: normalizeDoubleQuotes,
   normalize: normalizeQuotes

package/build/languageProcessing/helpers/sanitize/quotes.js.map

@@ -1 +1 @@
-{"version":3,"file":"quotes.js","names":["SINGLE_QUOTES_ARRAY","exports","SINGLE_QUOTES_REGEX","RegExp","join","normalizeSingleQuotes","text","replace","normalizeDoubleQuotes","normalizeQuotes","_default","default","normalizeSingle","normalizeDouble","normalize"],"sources":["../../../../src/languageProcessing/helpers/sanitize/quotes.js"],"sourcesContent":["const SINGLE_QUOTES_ARRAY = [ \"'\", \"‘\", \"’\", \"‛\", \"`\", \"‹\", \"›\" ];\nconst SINGLE_QUOTES_REGEX = new RegExp( \"[\" + SINGLE_QUOTES_ARRAY.join( \"\" ) + \"]\", \"g\" );\n\n/**\n * Normalizes single quotes to 'regular' quotes.\n *\n * @param {string} text Text to normalize.\n * @returns {string} The normalized text.\n */\nfunction normalizeSingleQuotes( text ) {\n\treturn text.replace( SINGLE_QUOTES_REGEX, \"'\" );\n}\n\n/**\n * Normalizes double quotes to 'regular' quotes.\n *\n * @param {string} text Text to normalize.\n * @returns {string} The normalized text.\n */\nfunction normalizeDoubleQuotes( text ) {\n\treturn text.replace( /[“”〝〞〟‟„『』«»]/g, \"\\\"\" );\n}\n\n/**\n * Normalizes quotes to 'regular' quotes.\n *\n * @param {string} text Text to normalize.\n * @returns {string} The normalized text.\n */\nfunction normalizeQuotes( text ) {\n\treturn normalizeDoubleQuotes( normalizeSingleQuotes( text ) );\n}\n\nexport {\n\tnormalizeSingleQuotes as normalizeSingle,\n\tnormalizeDoubleQuotes as normalizeDouble,\n\tnormalizeQuotes as normalize,\n\tSINGLE_QUOTES_REGEX,\n\tSINGLE_QUOTES_ARRAY,\n};\n\nexport default {\n\tnormalizeSingle: normalizeSingleQuotes,\n\tnormalizeDouble: normalizeDoubleQuotes,\n\tnormalize: normalizeQuotes,\n};\n"],"mappings":";;;;;;;;;AAAA,MAAMA,mBAAmB,GAAAC,OAAA,CAAAD,mBAAA,GAAG,CAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,CAAE;AACjE,MAAME,mBAAmB,GAAAD,OAAA,CAAAC,mBAAA,GAAG,IAAIC,MAAM,CAAE,GAAG,GAAGH,mBAAmB,CAACI,IAAI,CAAE,EAAG,CAAC,GAAG,GAAG,EAAE,GAAI,CAAC;;AAEzF;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,qBAAqBA,CAAEC,IAAI,EAAG;EACtC,OAAOA,IAAI,CAACC,OAAO,CAAEL,mBAAmB,EAAE,GAAI,CAAC;AAChD;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA,SAASM,qBAAqBA,CAAEF,IAAI,EAAG;EACtC,OAAOA,IAAI,CAACC,OAAO,CAAE,gBAAgB,EAAE,IAAK,CAAC;AAC9C;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA,SAASE,eAAeA,CAAEH,IAAI,EAAG;EAChC,OAAOE,qBAAqB,CAAEH,qBAAqB,CAAEC,IAAK,CAAE,CAAC;AAC9D;AAAC,IAAAI,QAAA,GAAAT,OAAA,CAAAU,OAAA,GAUc;EACdC,eAAe,EAAEP,qBAAqB;EACtCQ,eAAe,EAAEL,qBAAqB;EACtCM,SAAS,EAAEL;AACZ,CAAC","ignoreList":[]}
+{"version":3,"file":"quotes.js","names":["SINGLE_QUOTES_ARRAY","SINGLE_QUOTES_REGEX","RegExp","join","normalizeSingleQuotes","text","replace","normalizeDoubleQuotes","normalizeQuotes","normalizeSingle","normalizeDouble","normalize"],"sources":["../../../../src/languageProcessing/helpers/sanitize/quotes.js"],"sourcesContent":["const SINGLE_QUOTES_ARRAY = [ \"'\", \"‘\", \"’\", \"‛\", \"`\", \"‹\", \"›\" ];\nconst SINGLE_QUOTES_REGEX = new RegExp( \"[\" + SINGLE_QUOTES_ARRAY.join( \"\" ) + \"]\", \"g\" );\n\n/**\n * Normalizes single quotes to 'regular' quotes.\n *\n * @param {string} text Text to normalize.\n * @returns {string} The normalized text.\n */\nfunction normalizeSingleQuotes( text ) {\n\treturn text.replace( SINGLE_QUOTES_REGEX, \"'\" );\n}\n\n/**\n * Normalizes double quotes to 'regular' quotes.\n *\n * @param {string} text Text to normalize.\n * @returns {string} The normalized text.\n */\nfunction normalizeDoubleQuotes( text ) {\n\treturn text.replace( /[“”〝〞〟‟„『』«»]/g, \"\\\"\" );\n}\n\n/**\n * Normalizes quotes to 'regular' quotes.\n *\n * @param {string} text Text to normalize.\n * @returns {string} The normalized text.\n */\nfunction normalizeQuotes( text ) {\n\treturn normalizeDoubleQuotes( normalizeSingleQuotes( text ) );\n}\n\nexport {\n\tnormalizeSingleQuotes as normalizeSingle,\n\tnormalizeDoubleQuotes as normalizeDouble,\n\tnormalizeQuotes as normalize,\n\tSINGLE_QUOTES_REGEX,\n\tSINGLE_QUOTES_ARRAY,\n};\n\nexport default {\n\tnormalizeSingle: normalizeSingleQuotes,\n\tnormalizeDouble: normalizeDoubleQuotes,\n\tnormalize: normalizeQuotes,\n};\n"],"mappings":"AAAA,MAAMA,mBAAmB,GAAG,CAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,EAAE,GAAG,CAAE;AACjE,MAAMC,mBAAmB,GAAG,IAAIC,MAAM,CAAE,GAAG,GAAGF,mBAAmB,CAACG,IAAI,CAAE,EAAG,CAAC,GAAG,GAAG,EAAE,GAAI,CAAC;;AAEzF;AACA;AACA;AACA;AACA;AACA;AACA,SAASC,qBAAqBA,CAAEC,IAAI,EAAG;EACtC,OAAOA,IAAI,CAACC,OAAO,CAAEL,mBAAmB,EAAE,GAAI,CAAC;AAChD;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA,SAASM,qBAAqBA,CAAEF,IAAI,EAAG;EACtC,OAAOA,IAAI,CAACC,OAAO,CAAE,gBAAgB,EAAE,IAAK,CAAC;AAC9C;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA,SAASE,eAAeA,CAAEH,IAAI,EAAG;EAChC,OAAOE,qBAAqB,CAAEH,qBAAqB,CAAEC,IAAK,CAAE,CAAC;AAC9D;AAEA,SACCD,qBAAqB,IAAIK,eAAe,EACxCF,qBAAqB,IAAIG,eAAe,EACxCF,eAAe,IAAIG,SAAS,EAC5BV,mBAAmB,EACnBD,mBAAmB;AAGpB,eAAe;EACdS,eAAe,EAAEL,qBAAqB;EACtCM,eAAe,EAAEH,qBAAqB;EACtCI,SAAS,EAAEH;AACZ,CAAC","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/removeEmailAddresses.js

@@ -1,9 +1,3 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
 const emailRegex = new RegExp("[^\\s@]+@[^\\s@]+\\.[^\\s@]+", "igm");
 
 /**
@@ -13,7 +7,7 @@ const emailRegex = new RegExp("[^\\s@]+@[^\\s@]+\\.[^\\s@]+", "igm");
  *
  * @returns {string} The text without email addresses.
  */
-function _default(text) {
+export default function (text) {
   return text.replace(emailRegex, "");
 }
 //# sourceMappingURL=removeEmailAddresses.js.map

package/build/languageProcessing/helpers/sanitize/removeEmailAddresses.js.map

@@ -1 +1 @@
-{"version":3,"file":"removeEmailAddresses.js","names":["emailRegex","RegExp","_default","text","replace"],"sources":["../../../../src/languageProcessing/helpers/sanitize/removeEmailAddresses.js"],"sourcesContent":["const emailRegex = new RegExp( \"[^\\\\s@]+@[^\\\\s@]+\\\\.[^\\\\s@]+\", \"igm\" );\n\n/**\n * Removes email addresses from a text.\n *\n * @param {string} text The text to remove emails from.\n *\n * @returns {string} The text without email addresses.\n */\nexport default function( text ) {\n\treturn text.replace( emailRegex, \"\" );\n}\n"],"mappings":";;;;;;AAAA,MAAMA,UAAU,GAAG,IAAIC,MAAM,CAAE,8BAA8B,EAAE,KAAM,CAAC;;AAEtE;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAC,SAAUC,IAAI,EAAG;EAC/B,OAAOA,IAAI,CAACC,OAAO,CAAEJ,UAAU,EAAE,EAAG,CAAC;AACtC","ignoreList":[]}
+{"version":3,"file":"removeEmailAddresses.js","names":["emailRegex","RegExp","text","replace"],"sources":["../../../../src/languageProcessing/helpers/sanitize/removeEmailAddresses.js"],"sourcesContent":["const emailRegex = new RegExp( \"[^\\\\s@]+@[^\\\\s@]+\\\\.[^\\\\s@]+\", \"igm\" );\n\n/**\n * Removes email addresses from a text.\n *\n * @param {string} text The text to remove emails from.\n *\n * @returns {string} The text without email addresses.\n */\nexport default function( text ) {\n\treturn text.replace( emailRegex, \"\" );\n}\n"],"mappings":"AAAA,MAAMA,UAAU,GAAG,IAAIC,MAAM,CAAE,8BAA8B,EAAE,KAAM,CAAC;;AAEtE;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,IAAI,EAAG;EAC/B,OAAOA,IAAI,CAACC,OAAO,CAAEH,UAAU,EAAE,EAAG,CAAC;AACtC","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/removePunctuation.js

@@ -1,26 +1,20 @@
-"use strict";
+import { unifyNonBreakingSpace } from "./unifyWhitespace";
 
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
-exports.punctuationRegexString = exports.punctuationRegexStart = exports.punctuationRegexEnd = exports.punctuationList = void 0;
-var _unifyWhitespace = require("./unifyWhitespace");
 /**
  * String containing all the characters that we consider punctuation.
  * Characters that can also be used as control characters in regular expressions (like `-` and `(`) are escaped.
  * @type {string}
  */
-const punctuationRegexString = exports.punctuationRegexString = "\\–\\-\\(\\)_\\[\\]’‘“”〝〞〟‟„\"'.?!:;,¿¡«»‹›\u2014\u00d7\u002b\u0026\u06d4\u061f\u060C\u061B\u3002\uff61" + "\uff01\u203c\uff1f\u2047\u2049\u2048\u2025\u2026\u30fb\u30fc\u3001\u3003\u3004\u3006\u3007\u3008\u3009\u300a\u300b\u300c\u300d\u300e" + "\u300f\u3010\u3011\u3012\u3013\u3014\u3015\u3016\u3017\u3018\u3019\u301a\u301b\u301c\u301d\u301e\u301f\u3020\u3036\u303c\u303d\uff5b" + "\uff5d\uff5c\uff5e\uff5f\uff60\uff62\uff63\uff64\uff3b\uff3d\uff65\uffe5\uff04\uff05\uff20\uff06\uff07\uff08\uff09\uff0a\uff0f\uff1a" + "\uff1b\uff1c\uff1e\uff3c\\<>";
+export const punctuationRegexString = "\\–\\-\\(\\)_\\[\\]’‘“”〝〞〟‟„\"'.?!:;,¿¡«»‹›\u2014\u00d7\u002b\u0026\u06d4\u061f\u060C\u061B\u3002\uff61" + "\uff01\u203c\uff1f\u2047\u2049\u2048\u2025\u2026\u30fb\u30fc\u3001\u3003\u3004\u3006\u3007\u3008\u3009\u300a\u300b\u300c\u300d\u300e" + "\u300f\u3010\u3011\u3012\u3013\u3014\u3015\u3016\u3017\u3018\u3019\u301a\u301b\u301c\u301d\u301e\u301f\u3020\u3036\u303c\u303d\uff5b" + "\uff5d\uff5c\uff5e\uff5f\uff60\uff62\uff63\uff64\uff3b\uff3d\uff65\uffe5\uff04\uff05\uff20\uff06\uff07\uff08\uff09\uff0a\uff0f\uff1a" + "\uff1b\uff1c\uff1e\uff3c\\<>";
 
 /**
  * Array containing all the characters that we consider punctuation.
  * Characters that can also be used as control characters in regular expressions (like `-` and `(`) are escaped.
  * @type {string[]}
  */
-const punctuationList = exports.punctuationList = punctuationRegexString.split("");
-const punctuationRegexStart = exports.punctuationRegexStart = new RegExp("^[" + punctuationRegexString + "]+");
-const punctuationRegexEnd = exports.punctuationRegexEnd = new RegExp("[" + punctuationRegexString + "]+$");
+export const punctuationList = punctuationRegexString.split("");
+export const punctuationRegexStart = new RegExp("^[" + punctuationRegexString + "]+");
+export const punctuationRegexEnd = new RegExp("[" + punctuationRegexString + "]+$");
 
 /*
  * \u2014 - em-dash
@@ -40,9 +34,9 @@ const punctuationRegexEnd = exports.punctuationRegexEnd = new RegExp("[" + punct
  *
  * @returns {String} The sanitized text.
  */
-function _default(text) {
+export default function (text) {
   // Unify whitespaces and non-breaking spaces.
-  text = (0, _unifyWhitespace.unifyNonBreakingSpace)(text);
+  text = unifyNonBreakingSpace(text);
 
   // Remove &amp from the string. In some editors (a.o. Block and Elementor) the ampersand (&) is transformed into &amp.
   // If it is not removed, then it is returned as "amp" and counted as a word in assessments downstream.

package/build/languageProcessing/helpers/sanitize/removePunctuation.js.map

@@ -1 +1 @@
-{"version":3,"file":"removePunctuation.js","names":["_unifyWhitespace","require","punctuationRegexString","exports","punctuationList","split","punctuationRegexStart","RegExp","punctuationRegexEnd","_default","text","unifyNonBreakingSpace","replace","backslashRegex"],"sources":["../../../../src/languageProcessing/helpers/sanitize/removePunctuation.js"],"sourcesContent":["import { unifyNonBreakingSpace } from \"./unifyWhitespace\";\n\n/**\n * String containing all the characters that we consider punctuation.\n * Characters that can also be used as control characters in regular expressions (like `-` and `(`) are escaped.\n * @type {string}\n */\nexport const punctuationRegexString = \"\\\\–\\\\-\\\\(\\\\)_\\\\[\\\\]’‘“”〝〞〟‟„\\\"'.?!:;,¿¡«»‹›\\u2014\\u00d7\\u002b\\u0026\\u06d4\\u061f\\u060C\\u061B\\u3002\\uff61\" +\n\"\\uff01\\u203c\\uff1f\\u2047\\u2049\\u2048\\u2025\\u2026\\u30fb\\u30fc\\u3001\\u3003\\u3004\\u3006\\u3007\\u3008\\u3009\\u300a\\u300b\\u300c\\u300d\\u300e\" +\n\"\\u300f\\u3010\\u3011\\u3012\\u3013\\u3014\\u3015\\u3016\\u3017\\u3018\\u3019\\u301a\\u301b\\u301c\\u301d\\u301e\\u301f\\u3020\\u3036\\u303c\\u303d\\uff5b\" +\n\"\\uff5d\\uff5c\\uff5e\\uff5f\\uff60\\uff62\\uff63\\uff64\\uff3b\\uff3d\\uff65\\uffe5\\uff04\\uff05\\uff20\\uff06\\uff07\\uff08\\uff09\\uff0a\\uff0f\\uff1a\" +\n\"\\uff1b\\uff1c\\uff1e\\uff3c\\\\<>\";\n\n/**\n * Array containing all the characters that we consider punctuation.\n * Characters that can also be used as control characters in regular expressions (like `-` and `(`) are escaped.\n * @type {string[]}\n */\nexport const punctuationList = punctuationRegexString.split( \"\" );\n\nexport const punctuationRegexStart = new RegExp( \"^[\" + punctuationRegexString + \"]+\" );\nexport const punctuationRegexEnd = new RegExp( \"[\" + punctuationRegexString +  \"]+$\" );\n\n/*\n * \\u2014 - em-dash\n * \\u00d7 - multiplication sign\n * \\u002b - plus sign\n * \\u0026 - ampersand\n * \\u06d4 - Urdu full stop\n * \\u061f - Arabic question mark\n * \\u060C - Arabic comma\n * \\u061B - Arabic semicolon\n */\n\n/**\n * Replaces punctuation characters from the given text string.\n *\n * @param {String} text The text to remove the punctuation characters for.\n *\n * @returns {String} The sanitized text.\n */\nexport default function( text ) {\n\t// Unify whitespaces and non-breaking spaces.\n\ttext = unifyNonBreakingSpace( text );\n\n\t// Remove &amp from the string. In some editors (a.o. Block and Elementor) the ampersand (&) is transformed into &amp.\n\t// If it is not removed, then it is returned as \"amp\" and counted as a word in assessments downstream.\n\ttext = text.replace( \"\\u0026amp\", \"\" );\n\n\t/*\n\t * Remove backslash from the beginning and end of a word/text.\n\t * When a string such as `This is a \\\"calico\\\" cat` enters the Paper,\n\t * the Paper adds two extra backslash in front of the original backslash.\n\t * After the text is split into words, we also need to remove those backslashes from the word.\n\t * Otherwise, it will be problematic when word boundary regex is added to the word.\n\t */\n\tconst backslashRegex = new RegExp( \"(\\\\\\\\)\", \"g\" );\n\n\ttext = text.replace( backslashRegex, \"\" );\n\ttext = text.replace( punctuationRegexStart, \"\" );\n\ttext = text.replace( punctuationRegexEnd, \"\" );\n\n\treturn text;\n}\n"],"mappings":";;;;;;;AAAA,IAAAA,gBAAA,GAAAC,OAAA;AAEA;AACA;AACA;AACA;AACA;AACO,MAAMC,sBAAsB,GAAAC,OAAA,CAAAD,sBAAA,GAAG,yGAAyG,GAC/I,sIAAsI,GACtI,sIAAsI,GACtI,sIAAsI,GACtI,8BAA8B;;AAE9B;AACA;AACA;AACA;AACA;AACO,MAAME,eAAe,GAAAD,OAAA,CAAAC,eAAA,GAAGF,sBAAsB,CAACG,KAAK,CAAE,EAAG,CAAC;AAE1D,MAAMC,qBAAqB,GAAAH,OAAA,CAAAG,qBAAA,GAAG,IAAIC,MAAM,CAAE,IAAI,GAAGL,sBAAsB,GAAG,IAAK,CAAC;AAChF,MAAMM,mBAAmB,GAAAL,OAAA,CAAAK,mBAAA,GAAG,IAAID,MAAM,CAAE,GAAG,GAAGL,sBAAsB,GAAI,KAAM,CAAC;;AAEtF;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAO,SAAUC,IAAI,EAAG;EAC/B;EACAA,IAAI,GAAG,IAAAC,sCAAqB,EAAED,IAAK,CAAC;;EAEpC;EACA;EACAA,IAAI,GAAGA,IAAI,CAACE,OAAO,CAAE,WAAW,EAAE,EAAG,CAAC;;EAEtC;AACD;AACA;AACA;AACA;AACA;AACA;EACC,MAAMC,cAAc,GAAG,IAAIN,MAAM,CAAE,QAAQ,EAAE,GAAI,CAAC;EAElDG,IAAI,GAAGA,IAAI,CAACE,OAAO,CAAEC,cAAc,EAAE,EAAG,CAAC;EACzCH,IAAI,GAAGA,IAAI,CAACE,OAAO,CAAEN,qBAAqB,EAAE,EAAG,CAAC;EAChDI,IAAI,GAAGA,IAAI,CAACE,OAAO,CAAEJ,mBAAmB,EAAE,EAAG,CAAC;EAE9C,OAAOE,IAAI;AACZ","ignoreList":[]}
+{"version":3,"file":"removePunctuation.js","names":["unifyNonBreakingSpace","punctuationRegexString","punctuationList","split","punctuationRegexStart","RegExp","punctuationRegexEnd","text","replace","backslashRegex"],"sources":["../../../../src/languageProcessing/helpers/sanitize/removePunctuation.js"],"sourcesContent":["import { unifyNonBreakingSpace } from \"./unifyWhitespace\";\n\n/**\n * String containing all the characters that we consider punctuation.\n * Characters that can also be used as control characters in regular expressions (like `-` and `(`) are escaped.\n * @type {string}\n */\nexport const punctuationRegexString = \"\\\\–\\\\-\\\\(\\\\)_\\\\[\\\\]’‘“”〝〞〟‟„\\\"'.?!:;,¿¡«»‹›\\u2014\\u00d7\\u002b\\u0026\\u06d4\\u061f\\u060C\\u061B\\u3002\\uff61\" +\n\"\\uff01\\u203c\\uff1f\\u2047\\u2049\\u2048\\u2025\\u2026\\u30fb\\u30fc\\u3001\\u3003\\u3004\\u3006\\u3007\\u3008\\u3009\\u300a\\u300b\\u300c\\u300d\\u300e\" +\n\"\\u300f\\u3010\\u3011\\u3012\\u3013\\u3014\\u3015\\u3016\\u3017\\u3018\\u3019\\u301a\\u301b\\u301c\\u301d\\u301e\\u301f\\u3020\\u3036\\u303c\\u303d\\uff5b\" +\n\"\\uff5d\\uff5c\\uff5e\\uff5f\\uff60\\uff62\\uff63\\uff64\\uff3b\\uff3d\\uff65\\uffe5\\uff04\\uff05\\uff20\\uff06\\uff07\\uff08\\uff09\\uff0a\\uff0f\\uff1a\" +\n\"\\uff1b\\uff1c\\uff1e\\uff3c\\\\<>\";\n\n/**\n * Array containing all the characters that we consider punctuation.\n * Characters that can also be used as control characters in regular expressions (like `-` and `(`) are escaped.\n * @type {string[]}\n */\nexport const punctuationList = punctuationRegexString.split( \"\" );\n\nexport const punctuationRegexStart = new RegExp( \"^[\" + punctuationRegexString + \"]+\" );\nexport const punctuationRegexEnd = new RegExp( \"[\" + punctuationRegexString +  \"]+$\" );\n\n/*\n * \\u2014 - em-dash\n * \\u00d7 - multiplication sign\n * \\u002b - plus sign\n * \\u0026 - ampersand\n * \\u06d4 - Urdu full stop\n * \\u061f - Arabic question mark\n * \\u060C - Arabic comma\n * \\u061B - Arabic semicolon\n */\n\n/**\n * Replaces punctuation characters from the given text string.\n *\n * @param {String} text The text to remove the punctuation characters for.\n *\n * @returns {String} The sanitized text.\n */\nexport default function( text ) {\n\t// Unify whitespaces and non-breaking spaces.\n\ttext = unifyNonBreakingSpace( text );\n\n\t// Remove &amp from the string. In some editors (a.o. Block and Elementor) the ampersand (&) is transformed into &amp.\n\t// If it is not removed, then it is returned as \"amp\" and counted as a word in assessments downstream.\n\ttext = text.replace( \"\\u0026amp\", \"\" );\n\n\t/*\n\t * Remove backslash from the beginning and end of a word/text.\n\t * When a string such as `This is a \\\"calico\\\" cat` enters the Paper,\n\t * the Paper adds two extra backslash in front of the original backslash.\n\t * After the text is split into words, we also need to remove those backslashes from the word.\n\t * Otherwise, it will be problematic when word boundary regex is added to the word.\n\t */\n\tconst backslashRegex = new RegExp( \"(\\\\\\\\)\", \"g\" );\n\n\ttext = text.replace( backslashRegex, \"\" );\n\ttext = text.replace( punctuationRegexStart, \"\" );\n\ttext = text.replace( punctuationRegexEnd, \"\" );\n\n\treturn text;\n}\n"],"mappings":"AAAA,SAASA,qBAAqB;;AAE9B;AACA;AACA;AACA;AACA;AACA,OAAO,MAAMC,sBAAsB,GAAG,yGAAyG,GAC/I,sIAAsI,GACtI,sIAAsI,GACtI,sIAAsI,GACtI,8BAA8B;;AAE9B;AACA;AACA;AACA;AACA;AACA,OAAO,MAAMC,eAAe,GAAGD,sBAAsB,CAACE,KAAK,CAAE,EAAG,CAAC;AAEjE,OAAO,MAAMC,qBAAqB,GAAG,IAAIC,MAAM,CAAE,IAAI,GAAGJ,sBAAsB,GAAG,IAAK,CAAC;AACvF,OAAO,MAAMK,mBAAmB,GAAG,IAAID,MAAM,CAAE,GAAG,GAAGJ,sBAAsB,GAAI,KAAM,CAAC;;AAEtF;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUM,IAAI,EAAG;EAC/B;EACAA,IAAI,GAAGP,qBAAqB,CAAEO,IAAK,CAAC;;EAEpC;EACA;EACAA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,WAAW,EAAE,EAAG,CAAC;;EAEtC;AACD;AACA;AACA;AACA;AACA;AACA;EACC,MAAMC,cAAc,GAAG,IAAIJ,MAAM,CAAE,QAAQ,EAAE,GAAI,CAAC;EAElDE,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEC,cAAc,EAAE,EAAG,CAAC;EACzCF,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEJ,qBAAqB,EAAE,EAAG,CAAC;EAChDG,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEF,mBAAmB,EAAE,EAAG,CAAC;EAE9C,OAAOC,IAAI;AACZ","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/removePunctuationExceptQuotes.js

@@ -1,9 +1,3 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
 // Replace all other punctuation characters at the beginning or at the end of a word.
 const punctuationRegexString = "[\\–\\-\\(\\)_\\[\\]’'.?!:;,¿¡«»‹›\u2014\u00d7\u002b\u0026<>]+";
 const punctuationRegexStart = new RegExp("^" + punctuationRegexString);
@@ -16,7 +10,7 @@ const punctuationRegexEnd = new RegExp(punctuationRegexString + "$");
  *
  * @returns {String} The sanitized text.
  */
-function _default(text) {
+export default function (text) {
   text = text.replace(punctuationRegexStart, "");
   text = text.replace(punctuationRegexEnd, "");
   return text;

package/build/languageProcessing/helpers/sanitize/removePunctuationExceptQuotes.js.map

@@ -1 +1 @@
-{"version":3,"file":"removePunctuationExceptQuotes.js","names":["punctuationRegexString","punctuationRegexStart","RegExp","punctuationRegexEnd","_default","text","replace"],"sources":["../../../../src/languageProcessing/helpers/sanitize/removePunctuationExceptQuotes.js"],"sourcesContent":["// Replace all other punctuation characters at the beginning or at the end of a word.\nconst punctuationRegexString = \"[\\\\–\\\\-\\\\(\\\\)_\\\\[\\\\]’'.?!:;,¿¡«»‹›\\u2014\\u00d7\\u002b\\u0026<>]+\";\nconst punctuationRegexStart = new RegExp( \"^\" + punctuationRegexString );\nconst punctuationRegexEnd = new RegExp( punctuationRegexString + \"$\" );\n\n/**\n * Replaces punctuation characters at the beginning and end of a given text string.\n *\n * @param {String} text The text to remove the punctuation characters for.\n *\n * @returns {String} The sanitized text.\n */\nexport default function( text ) {\n\ttext = text.replace( punctuationRegexStart, \"\" );\n\ttext = text.replace( punctuationRegexEnd, \"\" );\n\n\treturn text;\n}\n"],"mappings":";;;;;;AAAA;AACA,MAAMA,sBAAsB,GAAG,gEAAgE;AAC/F,MAAMC,qBAAqB,GAAG,IAAIC,MAAM,CAAE,GAAG,GAAGF,sBAAuB,CAAC;AACxE,MAAMG,mBAAmB,GAAG,IAAID,MAAM,CAAEF,sBAAsB,GAAG,GAAI,CAAC;;AAEtE;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAI,SAAUC,IAAI,EAAG;EAC/BA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEL,qBAAqB,EAAE,EAAG,CAAC;EAChDI,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEH,mBAAmB,EAAE,EAAG,CAAC;EAE9C,OAAOE,IAAI;AACZ","ignoreList":[]}
+{"version":3,"file":"removePunctuationExceptQuotes.js","names":["punctuationRegexString","punctuationRegexStart","RegExp","punctuationRegexEnd","text","replace"],"sources":["../../../../src/languageProcessing/helpers/sanitize/removePunctuationExceptQuotes.js"],"sourcesContent":["// Replace all other punctuation characters at the beginning or at the end of a word.\nconst punctuationRegexString = \"[\\\\–\\\\-\\\\(\\\\)_\\\\[\\\\]’'.?!:;,¿¡«»‹›\\u2014\\u00d7\\u002b\\u0026<>]+\";\nconst punctuationRegexStart = new RegExp( \"^\" + punctuationRegexString );\nconst punctuationRegexEnd = new RegExp( punctuationRegexString + \"$\" );\n\n/**\n * Replaces punctuation characters at the beginning and end of a given text string.\n *\n * @param {String} text The text to remove the punctuation characters for.\n *\n * @returns {String} The sanitized text.\n */\nexport default function( text ) {\n\ttext = text.replace( punctuationRegexStart, \"\" );\n\ttext = text.replace( punctuationRegexEnd, \"\" );\n\n\treturn text;\n}\n"],"mappings":"AAAA;AACA,MAAMA,sBAAsB,GAAG,gEAAgE;AAC/F,MAAMC,qBAAqB,GAAG,IAAIC,MAAM,CAAE,GAAG,GAAGF,sBAAuB,CAAC;AACxE,MAAMG,mBAAmB,GAAG,IAAID,MAAM,CAAEF,sBAAsB,GAAG,GAAI,CAAC;;AAEtE;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUI,IAAI,EAAG;EAC/BA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEJ,qBAAqB,EAAE,EAAG,CAAC;EAChDG,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEF,mBAAmB,EAAE,EAAG,CAAC;EAE9C,OAAOC,IAAI;AACZ","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/removeSentenceTerminators.js

@@ -1,9 +1,3 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
 // These are sentence terminators, that never should be in the middle of a word.
 const sentenceTerminators = /[.?!:;,]/g;
 
@@ -14,7 +8,7 @@ const sentenceTerminators = /[.?!:;,]/g;
  *
  * @returns {String} The sanitized text.
  */
-function _default(text) {
+export default function (text) {
   return text.replace(sentenceTerminators, "");
 }
 //# sourceMappingURL=removeSentenceTerminators.js.map

package/build/languageProcessing/helpers/sanitize/removeSentenceTerminators.js.map

@@ -1 +1 @@
-{"version":3,"file":"removeSentenceTerminators.js","names":["sentenceTerminators","_default","text","replace"],"sources":["../../../../src/languageProcessing/helpers/sanitize/removeSentenceTerminators.js"],"sourcesContent":["// These are sentence terminators, that never should be in the middle of a word.\nconst sentenceTerminators = /[.?!:;,]/g;\n\n/**\n * Replaces sentence terminators from the text.\n *\n * @param {String} text The text to remove the terminators from.\n *\n * @returns {String} The sanitized text.\n */\nexport default function( text ) {\n\treturn text.replace( sentenceTerminators, \"\" );\n}\n"],"mappings":";;;;;;AAAA;AACA,MAAMA,mBAAmB,GAAG,WAAW;;AAEvC;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAC,SAAUC,IAAI,EAAG;EAC/B,OAAOA,IAAI,CAACC,OAAO,CAAEH,mBAAmB,EAAE,EAAG,CAAC;AAC/C","ignoreList":[]}
+{"version":3,"file":"removeSentenceTerminators.js","names":["sentenceTerminators","text","replace"],"sources":["../../../../src/languageProcessing/helpers/sanitize/removeSentenceTerminators.js"],"sourcesContent":["// These are sentence terminators, that never should be in the middle of a word.\nconst sentenceTerminators = /[.?!:;,]/g;\n\n/**\n * Replaces sentence terminators from the text.\n *\n * @param {String} text The text to remove the terminators from.\n *\n * @returns {String} The sanitized text.\n */\nexport default function( text ) {\n\treturn text.replace( sentenceTerminators, \"\" );\n}\n"],"mappings":"AAAA;AACA,MAAMA,mBAAmB,GAAG,WAAW;;AAEvC;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,IAAI,EAAG;EAC/B,OAAOA,IAAI,CAACC,OAAO,CAAEF,mBAAmB,EAAE,EAAG,CAAC;AAC/C","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/removeURLs.js

@@ -1,9 +1,3 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
 const urlRegex = new RegExp("(ftp|http(s)?:\\/\\/.)(www\\\\.)?[-a-zA-Z0-9@:%._\\/+~#=]{2,256}\\.[a-z]{2,6}\\b([-a-zA-Z0-9@:;%_\\/+.~#?&()=]*)" + "|www\\.[-a-zA-Z0-9@:%._\\/+~#=]{2,256}\\.[a-z]{2,6}\\b([-a-zA-Z0-9@:;%_\\/+.~#?&()=]*)", "igm");
 /**
  * This regex is used to match URLs, whether they are embedded in tags or not.
@@ -13,7 +7,7 @@ const urlRegex = new RegExp("(ftp|http(s)?:\\/\\/.)(www\\\\.)?[-a-zA-Z0-9@:%._\\
  *
  * @returns {string} The text without URLs.
  */
-function _default(text) {
+export default function (text) {
   return text.replace(urlRegex, "");
 }
 //# sourceMappingURL=removeURLs.js.map

package/build/languageProcessing/helpers/sanitize/removeURLs.js.map

@@ -1 +1 @@
-{"version":3,"file":"removeURLs.js","names":["urlRegex","RegExp","_default","text","replace"],"sources":["../../../../src/languageProcessing/helpers/sanitize/removeURLs.js"],"sourcesContent":["const urlRegex = new RegExp( \"(ftp|http(s)?:\\\\/\\\\/.)(www\\\\\\\\.)?[-a-zA-Z0-9@:%._\\\\/+~#=]{2,256}\\\\.[a-z]{2,6}\\\\b([-a-zA-Z0-9@:;%_\\\\/+.~#?&()=]*)\" +\n\t\"|www\\\\.[-a-zA-Z0-9@:%._\\\\/+~#=]{2,256}\\\\.[a-z]{2,6}\\\\b([-a-zA-Z0-9@:;%_\\\\/+.~#?&()=]*)\", \"igm\" );\n/**\n * This regex is used to match URLs, whether they are embedded in tags or not.\n * It doesn't match domain names (e.g. \"yoast.com\" in \"We got so much traffic on yoast.com after the latest release\").\n *\n * @param {string} text The text to remove URLs from.\n *\n * @returns {string} The text without URLs.\n */\nexport default function( text ) {\n\treturn text.replace( urlRegex, \"\" );\n}\n"],"mappings":";;;;;;AAAA,MAAMA,QAAQ,GAAG,IAAIC,MAAM,CAAE,kHAAkH,GAC9I,wFAAwF,EAAE,KAAM,CAAC;AAClG;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAC,SAAUC,IAAI,EAAG;EAC/B,OAAOA,IAAI,CAACC,OAAO,CAAEJ,QAAQ,EAAE,EAAG,CAAC;AACpC","ignoreList":[]}
+{"version":3,"file":"removeURLs.js","names":["urlRegex","RegExp","text","replace"],"sources":["../../../../src/languageProcessing/helpers/sanitize/removeURLs.js"],"sourcesContent":["const urlRegex = new RegExp( \"(ftp|http(s)?:\\\\/\\\\/.)(www\\\\\\\\.)?[-a-zA-Z0-9@:%._\\\\/+~#=]{2,256}\\\\.[a-z]{2,6}\\\\b([-a-zA-Z0-9@:;%_\\\\/+.~#?&()=]*)\" +\n\t\"|www\\\\.[-a-zA-Z0-9@:%._\\\\/+~#=]{2,256}\\\\.[a-z]{2,6}\\\\b([-a-zA-Z0-9@:;%_\\\\/+.~#?&()=]*)\", \"igm\" );\n/**\n * This regex is used to match URLs, whether they are embedded in tags or not.\n * It doesn't match domain names (e.g. \"yoast.com\" in \"We got so much traffic on yoast.com after the latest release\").\n *\n * @param {string} text The text to remove URLs from.\n *\n * @returns {string} The text without URLs.\n */\nexport default function( text ) {\n\treturn text.replace( urlRegex, \"\" );\n}\n"],"mappings":"AAAA,MAAMA,QAAQ,GAAG,IAAIC,MAAM,CAAE,kHAAkH,GAC9I,wFAAwF,EAAE,KAAM,CAAC;AAClG;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,IAAI,EAAG;EAC/B,OAAOA,IAAI,CAACC,OAAO,CAAEH,QAAQ,EAAE,EAAG,CAAC;AACpC","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/sanitizeLineBreakTag.js

@@ -1,9 +1,3 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
 /**
  * Replaces line break tag that contains an attribute with paragraph tag.
  * Line break tags with attribute aren't properly sanitized using wordpress `autop` function.
@@ -12,7 +6,7 @@ exports.default = _default;
  *
  * @returns {string} The sanitized text.
  */
-function _default(text) {
+export default function (text) {
   return text.replace(/<br.*?>\s*<.*?br.*?>/gm, "</p><p>");
 }
 //# sourceMappingURL=sanitizeLineBreakTag.js.map

package/build/languageProcessing/helpers/sanitize/sanitizeLineBreakTag.js.map

@@ -1 +1 @@
-{"version":3,"file":"sanitizeLineBreakTag.js","names":["_default","text","replace"],"sources":["../../../../src/languageProcessing/helpers/sanitize/sanitizeLineBreakTag.js"],"sourcesContent":["/**\n * Replaces line break tag that contains an attribute with paragraph tag.\n * Line break tags with attribute aren't properly sanitized using wordpress `autop` function.\n *\n * @param {string} text The text to sanitize.\n *\n * @returns {string} The sanitized text.\n */\nexport default function( text ) {\n\treturn text.replace( /<br.*?>\\s*<.*?br.*?>/gm, \"</p><p>\" );\n}\n"],"mappings":";;;;;;AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAA,SAAUC,IAAI,EAAG;EAC/B,OAAOA,IAAI,CAACC,OAAO,CAAE,wBAAwB,EAAE,SAAU,CAAC;AAC3D","ignoreList":[]}
+{"version":3,"file":"sanitizeLineBreakTag.js","names":["text","replace"],"sources":["../../../../src/languageProcessing/helpers/sanitize/sanitizeLineBreakTag.js"],"sourcesContent":["/**\n * Replaces line break tag that contains an attribute with paragraph tag.\n * Line break tags with attribute aren't properly sanitized using wordpress `autop` function.\n *\n * @param {string} text The text to sanitize.\n *\n * @returns {string} The sanitized text.\n */\nexport default function( text ) {\n\treturn text.replace( /<br.*?>\\s*<.*?br.*?>/gm, \"</p><p>\" );\n}\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUA,IAAI,EAAG;EAC/B,OAAOA,IAAI,CAACC,OAAO,CAAE,wBAAwB,EAAE,SAAU,CAAC;AAC3D","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/sanitizeString.js

@@ -1,11 +1,6 @@
-"use strict";
+import { stripFullTags as stripTags } from "./stripHTMLTags.js";
+import { unifyAllSpaces } from "./unifyWhitespace";
 
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
-var _stripHTMLTags = require("./stripHTMLTags.js");
-var _unifyWhitespace = require("./unifyWhitespace");
 /**
  * Sanitizes the text before we use the text for the analysis.
  *
@@ -13,11 +8,11 @@ var _unifyWhitespace = require("./unifyWhitespace");
  *
  * @returns {String} The sanitized text.
  */
-function _default(text) {
+export default function (text) {
   // Unify whitespaces and non-breaking spaces.
-  text = (0, _unifyWhitespace.unifyAllSpaces)(text);
+  text = unifyAllSpaces(text);
   // Strip the tags and multiple spaces.
-  text = (0, _stripHTMLTags.stripFullTags)(text);
+  text = stripTags(text);
   return text;
 }
 //# sourceMappingURL=sanitizeString.js.map

package/build/languageProcessing/helpers/sanitize/sanitizeString.js.map

@@ -1 +1 @@
-{"version":3,"file":"sanitizeString.js","names":["_stripHTMLTags","require","_unifyWhitespace","_default","text","unifyAllSpaces","stripTags"],"sources":["../../../../src/languageProcessing/helpers/sanitize/sanitizeString.js"],"sourcesContent":["import { stripFullTags as stripTags } from \"./stripHTMLTags.js\";\nimport { unifyAllSpaces } from \"./unifyWhitespace\";\n\n/**\n * Sanitizes the text before we use the text for the analysis.\n *\n * @param {String} text The text to be sanitized.\n *\n * @returns {String} The sanitized text.\n */\nexport default function( text ) {\n\t// Unify whitespaces and non-breaking spaces.\n\ttext = unifyAllSpaces( text );\n\t// Strip the tags and multiple spaces.\n\ttext = stripTags( text );\n\n\treturn text;\n}\n"],"mappings":";;;;;;AAAA,IAAAA,cAAA,GAAAC,OAAA;AACA,IAAAC,gBAAA,GAAAD,OAAA;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAE,SAAUC,IAAI,EAAG;EAC/B;EACAA,IAAI,GAAG,IAAAC,+BAAc,EAAED,IAAK,CAAC;EAC7B;EACAA,IAAI,GAAG,IAAAE,4BAAS,EAAEF,IAAK,CAAC;EAExB,OAAOA,IAAI;AACZ","ignoreList":[]}
+{"version":3,"file":"sanitizeString.js","names":["stripFullTags","stripTags","unifyAllSpaces","text"],"sources":["../../../../src/languageProcessing/helpers/sanitize/sanitizeString.js"],"sourcesContent":["import { stripFullTags as stripTags } from \"./stripHTMLTags.js\";\nimport { unifyAllSpaces } from \"./unifyWhitespace\";\n\n/**\n * Sanitizes the text before we use the text for the analysis.\n *\n * @param {String} text The text to be sanitized.\n *\n * @returns {String} The sanitized text.\n */\nexport default function( text ) {\n\t// Unify whitespaces and non-breaking spaces.\n\ttext = unifyAllSpaces( text );\n\t// Strip the tags and multiple spaces.\n\ttext = stripTags( text );\n\n\treturn text;\n}\n"],"mappings":"AAAA,SAASA,aAAa,IAAIC,SAAS;AACnC,SAASC,cAAc;;AAEvB;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,IAAI,EAAG;EAC/B;EACAA,IAAI,GAAGD,cAAc,CAAEC,IAAK,CAAC;EAC7B;EACAA,IAAI,GAAGF,SAAS,CAAEE,IAAK,CAAC;EAExB,OAAOA,IAAI;AACZ","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/stripHTMLTags.js

@@ -1,16 +1,9 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.stripIncompleteTags = exports.stripFullTags = exports.stripBlockTagsAtStartEnd = exports.default = void 0;
-var _stripSpaces = _interopRequireDefault(require("./stripSpaces.js"));
-var _html = require("../html/html.js");
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /** @module stringProcessing/stripHTMLTags */
 
-const blockElementStartRegex = new RegExp("^<(" + _html.blockElements.join("|") + ")[^>]*?>", "i");
-const blockElementEndRegex = new RegExp("</(" + _html.blockElements.join("|") + ")[^>]*?>$", "i");
+import stripSpaces from "./stripSpaces.js";
+import { blockElements } from "../html/html.js";
+const blockElementStartRegex = new RegExp("^<(" + blockElements.join("|") + ")[^>]*?>", "i");
+const blockElementEndRegex = new RegExp("</(" + blockElements.join("|") + ")[^>]*?>$", "i");
 
 /**
  * Strip incomplete tags within a text. Strips an end tag at the beginning of a string and the start tag at the end of a
@@ -31,7 +24,6 @@ const stripIncompleteTags = function (text) {
  * @param {string} text The unformatted string.
  * @returns {string} The text with removed HTML begin and end block elements
  */
-exports.stripIncompleteTags = stripIncompleteTags;
 const stripBlockTagsAtStartEnd = function (text) {
   text = text.replace(blockElementStartRegex, "");
   text = text.replace(blockElementEndRegex, "");
@@ -44,14 +36,13 @@ const stripBlockTagsAtStartEnd = function (text) {
  * @param {String} text The text to strip the HTML-tags from.
  * @returns {String} The text without HTML-tags.
  */
-exports.stripBlockTagsAtStartEnd = stripBlockTagsAtStartEnd;
 const stripFullTags = function (text) {
   text = text.replace(/(<([^>]+)>)/ig, " ");
-  text = (0, _stripSpaces.default)(text);
+  text = stripSpaces(text);
   return text;
 };
-exports.stripFullTags = stripFullTags;
-var _default = exports.default = {
+export { stripFullTags, stripIncompleteTags, stripBlockTagsAtStartEnd };
+export default {
   stripFullTags: stripFullTags,
   stripIncompleteTags: stripIncompleteTags,
   stripBlockTagsAtStartEnd: stripBlockTagsAtStartEnd

package/build/languageProcessing/helpers/sanitize/stripHTMLTags.js.map

@@ -1 +1 @@
-{"version":3,"file":"stripHTMLTags.js","names":["_stripSpaces","_interopRequireDefault","require","_html","e","__esModule","default","blockElementStartRegex","RegExp","blockElements","join","blockElementEndRegex","stripIncompleteTags","text","replace","exports","stripBlockTagsAtStartEnd","stripFullTags","stripSpaces","_default"],"sources":["../../../../src/languageProcessing/helpers/sanitize/stripHTMLTags.js"],"sourcesContent":["/** @module stringProcessing/stripHTMLTags */\n\nimport stripSpaces from \"./stripSpaces.js\";\n\nimport { blockElements } from \"../html/html.js\";\n\nconst blockElementStartRegex = new RegExp( \"^<(\" + blockElements.join( \"|\" ) + \")[^>]*?>\", \"i\" );\nconst blockElementEndRegex = new RegExp( \"</(\" + blockElements.join( \"|\" ) + \")[^>]*?>$\", \"i\" );\n\n/**\n * Strip incomplete tags within a text. Strips an end tag at the beginning of a string and the start tag at the end of a\n * start of a string.\n *\n * @param {String} text The text to strip the HTML-tags from at the begin and end.\n * @returns {String} The text without HTML-tags at the begin and end.\n */\nconst stripIncompleteTags = function( text ) {\n\ttext = text.replace( /^(<\\/([^>]+)>)+/i, \"\" );\n\ttext = text.replace( /(<([^/>]+)>)+$/i, \"\" );\n\treturn text;\n};\n\n/**\n * Removes the block element tags at the beginning and end of a string and returns this string.\n *\n * @param {string} text The unformatted string.\n * @returns {string} The text with removed HTML begin and end block elements\n */\nconst stripBlockTagsAtStartEnd = function( text ) {\n\ttext = text.replace( blockElementStartRegex, \"\" );\n\ttext = text.replace( blockElementEndRegex, \"\" );\n\treturn text;\n};\n\n/**\n * Strip HTML-tags from text\n *\n * @param {String} text The text to strip the HTML-tags from.\n * @returns {String} The text without HTML-tags.\n */\nconst stripFullTags = function( text ) {\n\ttext = text.replace( /(<([^>]+)>)/ig, \" \" );\n\ttext = stripSpaces( text );\n\treturn text;\n};\n\nexport {\n\tstripFullTags,\n\tstripIncompleteTags,\n\tstripBlockTagsAtStartEnd,\n};\n\nexport default {\n\tstripFullTags: stripFullTags,\n\tstripIncompleteTags: stripIncompleteTags,\n\tstripBlockTagsAtStartEnd: stripBlockTagsAtStartEnd,\n};\n"],"mappings":";;;;;;AAEA,IAAAA,YAAA,GAAAC,sBAAA,CAAAC,OAAA;AAEA,IAAAC,KAAA,GAAAD,OAAA;AAAgD,SAAAD,uBAAAG,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAJhD;;AAMA,MAAMG,sBAAsB,GAAG,IAAIC,MAAM,CAAE,KAAK,GAAGC,mBAAa,CAACC,IAAI,CAAE,GAAI,CAAC,GAAG,UAAU,EAAE,GAAI,CAAC;AAChG,MAAMC,oBAAoB,GAAG,IAAIH,MAAM,CAAE,KAAK,GAAGC,mBAAa,CAACC,IAAI,CAAE,GAAI,CAAC,GAAG,WAAW,EAAE,GAAI,CAAC;;AAE/F;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,mBAAmB,GAAG,SAAAA,CAAUC,IAAI,EAAG;EAC5CA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,kBAAkB,EAAE,EAAG,CAAC;EAC7CD,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,iBAAiB,EAAE,EAAG,CAAC;EAC5C,OAAOD,IAAI;AACZ,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AALAE,OAAA,CAAAH,mBAAA,GAAAA,mBAAA;AAMA,MAAMI,wBAAwB,GAAG,SAAAA,CAAUH,IAAI,EAAG;EACjDA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEP,sBAAsB,EAAE,EAAG,CAAC;EACjDM,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEH,oBAAoB,EAAE,EAAG,CAAC;EAC/C,OAAOE,IAAI;AACZ,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AALAE,OAAA,CAAAC,wBAAA,GAAAA,wBAAA;AAMA,MAAMC,aAAa,GAAG,SAAAA,CAAUJ,IAAI,EAAG;EACtCA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,eAAe,EAAE,GAAI,CAAC;EAC3CD,IAAI,GAAG,IAAAK,oBAAW,EAAEL,IAAK,CAAC;EAC1B,OAAOA,IAAI;AACZ,CAAC;AAACE,OAAA,CAAAE,aAAA,GAAAA,aAAA;AAAA,IAAAE,QAAA,GAAAJ,OAAA,CAAAT,OAAA,GAQa;EACdW,aAAa,EAAEA,aAAa;EAC5BL,mBAAmB,EAAEA,mBAAmB;EACxCI,wBAAwB,EAAEA;AAC3B,CAAC","ignoreList":[]}
+{"version":3,"file":"stripHTMLTags.js","names":["stripSpaces","blockElements","blockElementStartRegex","RegExp","join","blockElementEndRegex","stripIncompleteTags","text","replace","stripBlockTagsAtStartEnd","stripFullTags"],"sources":["../../../../src/languageProcessing/helpers/sanitize/stripHTMLTags.js"],"sourcesContent":["/** @module stringProcessing/stripHTMLTags */\n\nimport stripSpaces from \"./stripSpaces.js\";\n\nimport { blockElements } from \"../html/html.js\";\n\nconst blockElementStartRegex = new RegExp( \"^<(\" + blockElements.join( \"|\" ) + \")[^>]*?>\", \"i\" );\nconst blockElementEndRegex = new RegExp( \"</(\" + blockElements.join( \"|\" ) + \")[^>]*?>$\", \"i\" );\n\n/**\n * Strip incomplete tags within a text. Strips an end tag at the beginning of a string and the start tag at the end of a\n * start of a string.\n *\n * @param {String} text The text to strip the HTML-tags from at the begin and end.\n * @returns {String} The text without HTML-tags at the begin and end.\n */\nconst stripIncompleteTags = function( text ) {\n\ttext = text.replace( /^(<\\/([^>]+)>)+/i, \"\" );\n\ttext = text.replace( /(<([^/>]+)>)+$/i, \"\" );\n\treturn text;\n};\n\n/**\n * Removes the block element tags at the beginning and end of a string and returns this string.\n *\n * @param {string} text The unformatted string.\n * @returns {string} The text with removed HTML begin and end block elements\n */\nconst stripBlockTagsAtStartEnd = function( text ) {\n\ttext = text.replace( blockElementStartRegex, \"\" );\n\ttext = text.replace( blockElementEndRegex, \"\" );\n\treturn text;\n};\n\n/**\n * Strip HTML-tags from text\n *\n * @param {String} text The text to strip the HTML-tags from.\n * @returns {String} The text without HTML-tags.\n */\nconst stripFullTags = function( text ) {\n\ttext = text.replace( /(<([^>]+)>)/ig, \" \" );\n\ttext = stripSpaces( text );\n\treturn text;\n};\n\nexport {\n\tstripFullTags,\n\tstripIncompleteTags,\n\tstripBlockTagsAtStartEnd,\n};\n\nexport default {\n\tstripFullTags: stripFullTags,\n\tstripIncompleteTags: stripIncompleteTags,\n\tstripBlockTagsAtStartEnd: stripBlockTagsAtStartEnd,\n};\n"],"mappings":"AAAA;;AAEA,OAAOA,WAAW;AAElB,SAASC,aAAa;AAEtB,MAAMC,sBAAsB,GAAG,IAAIC,MAAM,CAAE,KAAK,GAAGF,aAAa,CAACG,IAAI,CAAE,GAAI,CAAC,GAAG,UAAU,EAAE,GAAI,CAAC;AAChG,MAAMC,oBAAoB,GAAG,IAAIF,MAAM,CAAE,KAAK,GAAGF,aAAa,CAACG,IAAI,CAAE,GAAI,CAAC,GAAG,WAAW,EAAE,GAAI,CAAC;;AAE/F;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,mBAAmB,GAAG,SAAAA,CAAUC,IAAI,EAAG;EAC5CA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,kBAAkB,EAAE,EAAG,CAAC;EAC7CD,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,iBAAiB,EAAE,EAAG,CAAC;EAC5C,OAAOD,IAAI;AACZ,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,wBAAwB,GAAG,SAAAA,CAAUF,IAAI,EAAG;EACjDA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEN,sBAAsB,EAAE,EAAG,CAAC;EACjDK,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEH,oBAAoB,EAAE,EAAG,CAAC;EAC/C,OAAOE,IAAI;AACZ,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,aAAa,GAAG,SAAAA,CAAUH,IAAI,EAAG;EACtCA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,eAAe,EAAE,GAAI,CAAC;EAC3CD,IAAI,GAAGP,WAAW,CAAEO,IAAK,CAAC;EAC1B,OAAOA,IAAI;AACZ,CAAC;AAED,SACCG,aAAa,EACbJ,mBAAmB,EACnBG,wBAAwB;AAGzB,eAAe;EACdC,aAAa,EAAEA,aAAa;EAC5BJ,mBAAmB,EAAEA,mBAAmB;EACxCG,wBAAwB,EAAEA;AAC3B,CAAC","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/stripNonTextTags.js

@@ -1,22 +1,16 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
-var _stripSpaces = _interopRequireDefault(require("./stripSpaces.js"));
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /** @module stringProcessing/stripNonTextTags */
 
+import stripSpaces from "./stripSpaces.js";
+
 /**
  * Strips all tags from the text, except li, p, dd and h1-h6 tags from the text that contain content to check.
  *
  * @param {string} text The text to strip tags from
  * @returns {string} The text stripped of tags, except for li, p, dd and h1-h6 tags.
  */
-function _default(text) {
+export default function (text) {
   text = text.replace(/<(?!li|\/li|p|\/p|h1|\/h1|h2|\/h2|h3|\/h3|h4|\/h4|h5|\/h5|h6|\/h6|dd).*?>/g, "");
-  text = (0, _stripSpaces.default)(text);
+  text = stripSpaces(text);
   return text;
 }
 //# sourceMappingURL=stripNonTextTags.js.map

package/build/languageProcessing/helpers/sanitize/stripNonTextTags.js.map

@@ -1 +1 @@
-{"version":3,"file":"stripNonTextTags.js","names":["_stripSpaces","_interopRequireDefault","require","e","__esModule","default","_default","text","replace","stripSpaces"],"sources":["../../../../src/languageProcessing/helpers/sanitize/stripNonTextTags.js"],"sourcesContent":["/** @module stringProcessing/stripNonTextTags */\n\nimport stripSpaces from \"./stripSpaces.js\";\n\n/**\n * Strips all tags from the text, except li, p, dd and h1-h6 tags from the text that contain content to check.\n *\n * @param {string} text The text to strip tags from\n * @returns {string} The text stripped of tags, except for li, p, dd and h1-h6 tags.\n */\nexport default function( text ) {\n\ttext = text.replace( /<(?!li|\\/li|p|\\/p|h1|\\/h1|h2|\\/h2|h3|\\/h3|h4|\\/h4|h5|\\/h5|h6|\\/h6|dd).*?>/g, \"\" );\n\ttext = stripSpaces( text );\n\treturn text;\n}\n"],"mappings":";;;;;;AAEA,IAAAA,YAAA,GAAAC,sBAAA,CAAAC,OAAA;AAA2C,SAAAD,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAF3C;;AAIA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAAUC,IAAI,EAAG;EAC/BA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,4EAA4E,EAAE,EAAG,CAAC;EACvGD,IAAI,GAAG,IAAAE,oBAAW,EAAEF,IAAK,CAAC;EAC1B,OAAOA,IAAI;AACZ","ignoreList":[]}
+{"version":3,"file":"stripNonTextTags.js","names":["stripSpaces","text","replace"],"sources":["../../../../src/languageProcessing/helpers/sanitize/stripNonTextTags.js"],"sourcesContent":["/** @module stringProcessing/stripNonTextTags */\n\nimport stripSpaces from \"./stripSpaces.js\";\n\n/**\n * Strips all tags from the text, except li, p, dd and h1-h6 tags from the text that contain content to check.\n *\n * @param {string} text The text to strip tags from\n * @returns {string} The text stripped of tags, except for li, p, dd and h1-h6 tags.\n */\nexport default function( text ) {\n\ttext = text.replace( /<(?!li|\\/li|p|\\/p|h1|\\/h1|h2|\\/h2|h3|\\/h3|h4|\\/h4|h5|\\/h5|h6|\\/h6|dd).*?>/g, \"\" );\n\ttext = stripSpaces( text );\n\treturn text;\n}\n"],"mappings":"AAAA;;AAEA,OAAOA,WAAW;;AAElB;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,IAAI,EAAG;EAC/BA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,4EAA4E,EAAE,EAAG,CAAC;EACvGD,IAAI,GAAGD,WAAW,CAAEC,IAAK,CAAC;EAC1B,OAAOA,IAAI;AACZ","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/stripNumbers.js

@@ -1,23 +1,17 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
-var _stripSpaces = _interopRequireDefault(require("./stripSpaces.js"));
-function _interopRequireDefault(e) { return e && e.__esModule ? e : { default: e }; }
 /** @module stringProcessing/stripNumbers */
 
+import stripSpaces from "./stripSpaces.js";
+
 /**
  * Removes all words comprised only of numbers.
  *
  * @param {string} text to remove words
  * @returns {string} The text with 'numberonly' words removed.
  */
-function _default(text) {
+export default function (text) {
   // Remove "words" comprised only of numbers
   text = text.replace(/\b[0-9]+\b/g, "");
-  text = (0, _stripSpaces.default)(text);
+  text = stripSpaces(text);
   if (text === ".") {
     text = "";
   }

package/build/languageProcessing/helpers/sanitize/stripNumbers.js.map

@@ -1 +1 @@
-{"version":3,"file":"stripNumbers.js","names":["_stripSpaces","_interopRequireDefault","require","e","__esModule","default","_default","text","replace","stripSpaces"],"sources":["../../../../src/languageProcessing/helpers/sanitize/stripNumbers.js"],"sourcesContent":["/** @module stringProcessing/stripNumbers */\n\nimport stripSpaces from \"./stripSpaces.js\";\n\n/**\n * Removes all words comprised only of numbers.\n *\n * @param {string} text to remove words\n * @returns {string} The text with 'numberonly' words removed.\n */\nexport default function( text ) {\n\t// Remove \"words\" comprised only of numbers\n\ttext = text.replace( /\\b[0-9]+\\b/g, \"\" );\n\n\ttext = stripSpaces( text );\n\n\tif ( text === \".\" ) {\n\t\ttext = \"\";\n\t}\n\treturn text;\n}\n"],"mappings":";;;;;;AAEA,IAAAA,YAAA,GAAAC,sBAAA,CAAAC,OAAA;AAA2C,SAAAD,uBAAAE,CAAA,WAAAA,CAAA,IAAAA,CAAA,CAAAC,UAAA,GAAAD,CAAA,KAAAE,OAAA,EAAAF,CAAA;AAF3C;;AAIA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAG,SAAUC,IAAI,EAAG;EAC/B;EACAA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,aAAa,EAAE,EAAG,CAAC;EAExCD,IAAI,GAAG,IAAAE,oBAAW,EAAEF,IAAK,CAAC;EAE1B,IAAKA,IAAI,KAAK,GAAG,EAAG;IACnBA,IAAI,GAAG,EAAE;EACV;EACA,OAAOA,IAAI;AACZ","ignoreList":[]}
+{"version":3,"file":"stripNumbers.js","names":["stripSpaces","text","replace"],"sources":["../../../../src/languageProcessing/helpers/sanitize/stripNumbers.js"],"sourcesContent":["/** @module stringProcessing/stripNumbers */\n\nimport stripSpaces from \"./stripSpaces.js\";\n\n/**\n * Removes all words comprised only of numbers.\n *\n * @param {string} text to remove words\n * @returns {string} The text with 'numberonly' words removed.\n */\nexport default function( text ) {\n\t// Remove \"words\" comprised only of numbers\n\ttext = text.replace( /\\b[0-9]+\\b/g, \"\" );\n\n\ttext = stripSpaces( text );\n\n\tif ( text === \".\" ) {\n\t\ttext = \"\";\n\t}\n\treturn text;\n}\n"],"mappings":"AAAA;;AAEA,OAAOA,WAAW;;AAElB;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUC,IAAI,EAAG;EAC/B;EACAA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,aAAa,EAAE,EAAG,CAAC;EAExCD,IAAI,GAAGD,WAAW,CAAEC,IAAK,CAAC;EAE1B,IAAKA,IAAI,KAAK,GAAG,EAAG;IACnBA,IAAI,GAAG,EAAE;EACV;EACA,OAAOA,IAAI;AACZ","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/stripSpaces.js

@@ -1,9 +1,3 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.default = _default;
 /** @module stringProcessing/stripSpaces */
 
 /**
@@ -13,7 +7,7 @@ exports.default = _default;
  * @param {String} text The text to strip spaces from.
  * @returns {String} The text with stripped spaces.
  */
-function _default(text) {
+export default function (text) {
   // Replaces multiple spaces with a single space.
   text = text.replace(/\s{2,}/g, " ");
   // Replaces space(s) followed by a period, if the period is the last character, with only the period.

package/build/languageProcessing/helpers/sanitize/stripSpaces.js.map

@@ -1 +1 @@
-{"version":3,"file":"stripSpaces.js","names":["_default","text","replace"],"sources":["../../../../src/languageProcessing/helpers/sanitize/stripSpaces.js"],"sourcesContent":["/** @module stringProcessing/stripSpaces */\n\n/**\n * Replaces multiple spaces with a single space.\n * Removes spaces followed by a period (if there's no text after the period) and spaces in the beginning or end of a string.\n *\n * @param {String} text The text to strip spaces from.\n * @returns {String} The text with stripped spaces.\n */\nexport default function( text ) {\n\t// Replaces multiple spaces with a single space.\n\ttext = text.replace( /\\s{2,}/g, \" \" );\n\t// Replaces space(s) followed by a period, if the period is the last character, with only the period.\n\ttext = text.replace( /\\s\\.$/, \".\" );\n\t// Removes first/last character if it's a space.\n\ttext = text.replace( /^\\s+|\\s+$/g, \"\" );\n\t// Replaces spaces followed by a Japanese period with only the period.\n\ttext = text.replace( /\\s。/g, \"。\" );\n\t// Replaces spaces after a Japanese period with only the period.\n\ttext = text.replace( /。\\s/g, \"。\" );\n\n\treturn text;\n}\n"],"mappings":";;;;;;AAAA;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACe,SAAAA,SAAUC,IAAI,EAAG;EAC/B;EACAA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,SAAS,EAAE,GAAI,CAAC;EACrC;EACAD,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,OAAO,EAAE,GAAI,CAAC;EACnC;EACAD,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,YAAY,EAAE,EAAG,CAAC;EACvC;EACAD,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,MAAM,EAAE,GAAI,CAAC;EAClC;EACAD,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,MAAM,EAAE,GAAI,CAAC;EAElC,OAAOD,IAAI;AACZ","ignoreList":[]}
+{"version":3,"file":"stripSpaces.js","names":["text","replace"],"sources":["../../../../src/languageProcessing/helpers/sanitize/stripSpaces.js"],"sourcesContent":["/** @module stringProcessing/stripSpaces */\n\n/**\n * Replaces multiple spaces with a single space.\n * Removes spaces followed by a period (if there's no text after the period) and spaces in the beginning or end of a string.\n *\n * @param {String} text The text to strip spaces from.\n * @returns {String} The text with stripped spaces.\n */\nexport default function( text ) {\n\t// Replaces multiple spaces with a single space.\n\ttext = text.replace( /\\s{2,}/g, \" \" );\n\t// Replaces space(s) followed by a period, if the period is the last character, with only the period.\n\ttext = text.replace( /\\s\\.$/, \".\" );\n\t// Removes first/last character if it's a space.\n\ttext = text.replace( /^\\s+|\\s+$/g, \"\" );\n\t// Replaces spaces followed by a Japanese period with only the period.\n\ttext = text.replace( /\\s。/g, \"。\" );\n\t// Replaces spaces after a Japanese period with only the period.\n\ttext = text.replace( /。\\s/g, \"。\" );\n\n\treturn text;\n}\n"],"mappings":"AAAA;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,eAAe,UAAUA,IAAI,EAAG;EAC/B;EACAA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,SAAS,EAAE,GAAI,CAAC;EACrC;EACAD,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,OAAO,EAAE,GAAI,CAAC;EACnC;EACAD,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,YAAY,EAAE,EAAG,CAAC;EACvC;EACAD,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,MAAM,EAAE,GAAI,CAAC;EAClC;EACAD,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAE,MAAM,EAAE,GAAI,CAAC;EAElC,OAAOD,IAAI;AACZ","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/stripWordBoundaries.js

@@ -1,9 +1,3 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.stripWordBoundariesStart = exports.stripWordBoundariesEverywhere = exports.stripWordBoundariesEnd = exports.default = void 0;
 /*
  * \u00a0 - No-break space
  * \u06d4 - Urdu full stop
@@ -35,7 +29,6 @@ const stripWordBoundariesStart = function (text) {
  *
  * @returns {String} The text without double word boundary markers.
  */
-exports.stripWordBoundariesStart = stripWordBoundariesStart;
 const stripWordBoundariesEnd = function (text) {
   // Remove last character if word boundary
   text = text.replace(wordBoundaryEnd, "");
@@ -49,15 +42,14 @@ const stripWordBoundariesEnd = function (text) {
  *
  * @returns {String} The text without word boundary markers.
  */
-exports.stripWordBoundariesEnd = stripWordBoundariesEnd;
 const stripWordBoundariesEverywhere = function (text) {
   // Remove first/last character if word boundary
   text = text.replace(wordBoundaryStart, "");
   text = text.replace(wordBoundaryEnd, "");
   return text;
 };
-exports.stripWordBoundariesEverywhere = stripWordBoundariesEverywhere;
-var _default = exports.default = {
+export { stripWordBoundariesStart, stripWordBoundariesEnd, stripWordBoundariesEverywhere };
+export default {
   stripWordBoundariesStart: stripWordBoundariesStart,
   stripWordBoundariesEnd: stripWordBoundariesEnd,
   stripWordBoundariesEverywhere: stripWordBoundariesEverywhere

package/build/languageProcessing/helpers/sanitize/stripWordBoundaries.js.map

@@ -1 +1 @@
-{"version":3,"file":"stripWordBoundaries.js","names":["wordBoundary","wordBoundaryStart","RegExp","wordBoundaryEnd","stripWordBoundariesStart","text","replace","exports","stripWordBoundariesEnd","stripWordBoundariesEverywhere","_default","default"],"sources":["../../../../src/languageProcessing/helpers/sanitize/stripWordBoundaries.js"],"sourcesContent":["/*\n * \\u00a0 - No-break space\n * \\u06d4 - Urdu full stop\n * \\u061f - Arabic question mark\n * \\u060C - Arabic comma\n * \\u061B - Arabic semicolon\n */\nconst wordBoundary = \"[ \\\\u00a0\\\\u06d4\\\\u061f\\\\u060C\\\\u061B \\\\n\\\\r\\\\t.,'()\\\"+\\\\-;!?:/»«‹›<>]\";\nconst wordBoundaryStart = new RegExp( \"^(\" + wordBoundary + \"+)\", \"ig\" );\nconst wordBoundaryEnd = new RegExp( \"(\" + wordBoundary + \"+$)\", \"ig\" );\n\n/**\n * Strip word boundary markers from text in the beginning\n *\n * @param {String} text The text to strip word boundary markers from.\n *\n * @returns {String} The text without double word boundary markers.\n */\nconst stripWordBoundariesStart = function( text ) {\n\t// Remove first character if word boundary\n\ttext = text.replace( wordBoundaryStart, \"\" );\n\n\treturn text;\n};\n\n/**\n * Strip word boundary markers from text in the end\n *\n * @param {String} text The text to strip word boundary markers from.\n *\n * @returns {String} The text without double word boundary markers.\n */\nconst stripWordBoundariesEnd = function( text ) {\n\t// Remove last character if word boundary\n\ttext = text.replace( wordBoundaryEnd, \"\" );\n\n\treturn text;\n};\n\n/**\n * Strip word boundary markers from text in the beginning and in the end\n *\n * @param {String} text The text to strip word boundary markers from.\n *\n * @returns {String} The text without word boundary markers.\n */\nconst stripWordBoundariesEverywhere = function( text ) {\n\t// Remove first/last character if word boundary\n\ttext = text.replace( wordBoundaryStart, \"\" );\n\ttext = text.replace( wordBoundaryEnd, \"\" );\n\n\treturn text;\n};\n\nexport {\n\tstripWordBoundariesStart,\n\tstripWordBoundariesEnd,\n\tstripWordBoundariesEverywhere,\n};\n\nexport default {\n\tstripWordBoundariesStart: stripWordBoundariesStart,\n\tstripWordBoundariesEnd: stripWordBoundariesEnd,\n\tstripWordBoundariesEverywhere: stripWordBoundariesEverywhere,\n};\n"],"mappings":";;;;;;AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMA,YAAY,GAAG,wEAAwE;AAC7F,MAAMC,iBAAiB,GAAG,IAAIC,MAAM,CAAE,IAAI,GAAGF,YAAY,GAAG,IAAI,EAAE,IAAK,CAAC;AACxE,MAAMG,eAAe,GAAG,IAAID,MAAM,CAAE,GAAG,GAAGF,YAAY,GAAG,KAAK,EAAE,IAAK,CAAC;;AAEtE;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMI,wBAAwB,GAAG,SAAAA,CAAUC,IAAI,EAAG;EACjD;EACAA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEL,iBAAiB,EAAE,EAAG,CAAC;EAE5C,OAAOI,IAAI;AACZ,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AANAE,OAAA,CAAAH,wBAAA,GAAAA,wBAAA;AAOA,MAAMI,sBAAsB,GAAG,SAAAA,CAAUH,IAAI,EAAG;EAC/C;EACAA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEH,eAAe,EAAE,EAAG,CAAC;EAE1C,OAAOE,IAAI;AACZ,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AANAE,OAAA,CAAAC,sBAAA,GAAAA,sBAAA;AAOA,MAAMC,6BAA6B,GAAG,SAAAA,CAAUJ,IAAI,EAAG;EACtD;EACAA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEL,iBAAiB,EAAE,EAAG,CAAC;EAC5CI,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEH,eAAe,EAAE,EAAG,CAAC;EAE1C,OAAOE,IAAI;AACZ,CAAC;AAACE,OAAA,CAAAE,6BAAA,GAAAA,6BAAA;AAAA,IAAAC,QAAA,GAAAH,OAAA,CAAAI,OAAA,GAQa;EACdP,wBAAwB,EAAEA,wBAAwB;EAClDI,sBAAsB,EAAEA,sBAAsB;EAC9CC,6BAA6B,EAAEA;AAChC,CAAC","ignoreList":[]}
+{"version":3,"file":"stripWordBoundaries.js","names":["wordBoundary","wordBoundaryStart","RegExp","wordBoundaryEnd","stripWordBoundariesStart","text","replace","stripWordBoundariesEnd","stripWordBoundariesEverywhere"],"sources":["../../../../src/languageProcessing/helpers/sanitize/stripWordBoundaries.js"],"sourcesContent":["/*\n * \\u00a0 - No-break space\n * \\u06d4 - Urdu full stop\n * \\u061f - Arabic question mark\n * \\u060C - Arabic comma\n * \\u061B - Arabic semicolon\n */\nconst wordBoundary = \"[ \\\\u00a0\\\\u06d4\\\\u061f\\\\u060C\\\\u061B \\\\n\\\\r\\\\t.,'()\\\"+\\\\-;!?:/»«‹›<>]\";\nconst wordBoundaryStart = new RegExp( \"^(\" + wordBoundary + \"+)\", \"ig\" );\nconst wordBoundaryEnd = new RegExp( \"(\" + wordBoundary + \"+$)\", \"ig\" );\n\n/**\n * Strip word boundary markers from text in the beginning\n *\n * @param {String} text The text to strip word boundary markers from.\n *\n * @returns {String} The text without double word boundary markers.\n */\nconst stripWordBoundariesStart = function( text ) {\n\t// Remove first character if word boundary\n\ttext = text.replace( wordBoundaryStart, \"\" );\n\n\treturn text;\n};\n\n/**\n * Strip word boundary markers from text in the end\n *\n * @param {String} text The text to strip word boundary markers from.\n *\n * @returns {String} The text without double word boundary markers.\n */\nconst stripWordBoundariesEnd = function( text ) {\n\t// Remove last character if word boundary\n\ttext = text.replace( wordBoundaryEnd, \"\" );\n\n\treturn text;\n};\n\n/**\n * Strip word boundary markers from text in the beginning and in the end\n *\n * @param {String} text The text to strip word boundary markers from.\n *\n * @returns {String} The text without word boundary markers.\n */\nconst stripWordBoundariesEverywhere = function( text ) {\n\t// Remove first/last character if word boundary\n\ttext = text.replace( wordBoundaryStart, \"\" );\n\ttext = text.replace( wordBoundaryEnd, \"\" );\n\n\treturn text;\n};\n\nexport {\n\tstripWordBoundariesStart,\n\tstripWordBoundariesEnd,\n\tstripWordBoundariesEverywhere,\n};\n\nexport default {\n\tstripWordBoundariesStart: stripWordBoundariesStart,\n\tstripWordBoundariesEnd: stripWordBoundariesEnd,\n\tstripWordBoundariesEverywhere: stripWordBoundariesEverywhere,\n};\n"],"mappings":"AAAA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMA,YAAY,GAAG,wEAAwE;AAC7F,MAAMC,iBAAiB,GAAG,IAAIC,MAAM,CAAE,IAAI,GAAGF,YAAY,GAAG,IAAI,EAAE,IAAK,CAAC;AACxE,MAAMG,eAAe,GAAG,IAAID,MAAM,CAAE,GAAG,GAAGF,YAAY,GAAG,KAAK,EAAE,IAAK,CAAC;;AAEtE;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMI,wBAAwB,GAAG,SAAAA,CAAUC,IAAI,EAAG;EACjD;EACAA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEL,iBAAiB,EAAE,EAAG,CAAC;EAE5C,OAAOI,IAAI;AACZ,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,sBAAsB,GAAG,SAAAA,CAAUF,IAAI,EAAG;EAC/C;EACAA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEH,eAAe,EAAE,EAAG,CAAC;EAE1C,OAAOE,IAAI;AACZ,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,6BAA6B,GAAG,SAAAA,CAAUH,IAAI,EAAG;EACtD;EACAA,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEL,iBAAiB,EAAE,EAAG,CAAC;EAC5CI,IAAI,GAAGA,IAAI,CAACC,OAAO,CAAEH,eAAe,EAAE,EAAG,CAAC;EAE1C,OAAOE,IAAI;AACZ,CAAC;AAED,SACCD,wBAAwB,EACxBG,sBAAsB,EACtBC,6BAA6B;AAG9B,eAAe;EACdJ,wBAAwB,EAAEA,wBAAwB;EAClDG,sBAAsB,EAAEA,sBAAsB;EAC9CC,6BAA6B,EAAEA;AAChC,CAAC","ignoreList":[]}

package/build/languageProcessing/helpers/sanitize/unifyWhitespace.js

@@ -1,9 +1,3 @@
-"use strict";
-
-Object.defineProperty(exports, "__esModule", {
-  value: true
-});
-exports.unifyWhiteSpace = exports.unifyNonBreakingSpace = exports.unifyEmDash = exports.unifyAllSpaces = exports.default = void 0;
 /** @module stringProcessing/unifyWhitespace */
 
 /**
@@ -24,7 +18,6 @@ const unifyNonBreakingSpace = function (text) {
  *
  * @returns {string} The text with unified spaces.
  */
-exports.unifyNonBreakingSpace = unifyNonBreakingSpace;
 const unifyEmDash = function (text) {
   return text.replace(/\u2014/g, " ");
 };
@@ -36,7 +29,6 @@ const unifyEmDash = function (text) {
  *
  * @returns {string} The text with unified spaces.
  */
-exports.unifyEmDash = unifyEmDash;
 const unifyWhiteSpace = function (text) {
   return text.replace(/\s/g, " ");
 };
@@ -48,14 +40,13 @@ const unifyWhiteSpace = function (text) {
  *
  * @returns {string} The text with unified spaces.
  */
-exports.unifyWhiteSpace = unifyWhiteSpace;
 const unifyAllSpaces = function (text) {
   text = unifyNonBreakingSpace(text);
   text = unifyEmDash(text);
   return unifyWhiteSpace(text);
 };
-exports.unifyAllSpaces = unifyAllSpaces;
-var _default = exports.default = {
+export { unifyNonBreakingSpace, unifyEmDash, unifyWhiteSpace, unifyAllSpaces };
+export default {
   unifyNonBreakingSpace: unifyNonBreakingSpace,
   unifyEmDash: unifyEmDash,
   unifyWhiteSpace: unifyWhiteSpace,

package/build/languageProcessing/helpers/sanitize/unifyWhitespace.js.map

@@ -1 +1 @@
-{"version":3,"file":"unifyWhitespace.js","names":["unifyNonBreakingSpace","text","replace","exports","unifyEmDash","unifyWhiteSpace","unifyAllSpaces","_default","default"],"sources":["../../../../src/languageProcessing/helpers/sanitize/unifyWhitespace.js"],"sourcesContent":["/** @module stringProcessing/unifyWhitespace */\n\n/**\n * Replaces a non-breaking space with a normal space.\n *\n * @param {string} text The string to replace the non-breaking space in.\n *\n * @returns {string} The text with unified spaces.\n */\nconst unifyNonBreakingSpace = function( text ) {\n\treturn text.replace( / /g, \" \" );\n};\n\n/**\n * Replaces an em dash with a normal space.\n *\n * @param {string} text The string to replace the em dash in.\n *\n * @returns {string} The text with unified spaces.\n */\nconst unifyEmDash = function( text ) {\n\treturn text.replace( /\\u2014/g, \" \" );\n};\n\n/**\n * Replaces all whitespace characters with a normal space.\n *\n * @param {string} text The string to replace the whitespace characters in.\n *\n * @returns {string} The text with unified spaces.\n */\nconst unifyWhiteSpace = function( text ) {\n\treturn text.replace( /\\s/g, \" \" );\n};\n\n/**\n * Converts all whitespace to spaces.\n *\n * @param {string} text The text to replace spaces.\n *\n * @returns {string} The text with unified spaces.\n */\nconst unifyAllSpaces = function( text ) {\n\ttext = unifyNonBreakingSpace( text );\n\ttext = unifyEmDash( text );\n\treturn unifyWhiteSpace( text );\n};\n\nexport {\n\tunifyNonBreakingSpace,\n\tunifyEmDash,\n\tunifyWhiteSpace,\n\tunifyAllSpaces,\n};\n\nexport default {\n\tunifyNonBreakingSpace: unifyNonBreakingSpace,\n\tunifyEmDash: unifyEmDash,\n\tunifyWhiteSpace: unifyWhiteSpace,\n\tunifyAllSpaces: unifyAllSpaces,\n};\n"],"mappings":";;;;;;AAAA;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMA,qBAAqB,GAAG,SAAAA,CAAUC,IAAI,EAAG;EAC9C,OAAOA,IAAI,CAACC,OAAO,CAAE,SAAS,EAAE,GAAI,CAAC;AACtC,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AANAC,OAAA,CAAAH,qBAAA,GAAAA,qBAAA;AAOA,MAAMI,WAAW,GAAG,SAAAA,CAAUH,IAAI,EAAG;EACpC,OAAOA,IAAI,CAACC,OAAO,CAAE,SAAS,EAAE,GAAI,CAAC;AACtC,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AANAC,OAAA,CAAAC,WAAA,GAAAA,WAAA;AAOA,MAAMC,eAAe,GAAG,SAAAA,CAAUJ,IAAI,EAAG;EACxC,OAAOA,IAAI,CAACC,OAAO,CAAE,KAAK,EAAE,GAAI,CAAC;AAClC,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AANAC,OAAA,CAAAE,eAAA,GAAAA,eAAA;AAOA,MAAMC,cAAc,GAAG,SAAAA,CAAUL,IAAI,EAAG;EACvCA,IAAI,GAAGD,qBAAqB,CAAEC,IAAK,CAAC;EACpCA,IAAI,GAAGG,WAAW,CAAEH,IAAK,CAAC;EAC1B,OAAOI,eAAe,CAAEJ,IAAK,CAAC;AAC/B,CAAC;AAACE,OAAA,CAAAG,cAAA,GAAAA,cAAA;AAAA,IAAAC,QAAA,GAAAJ,OAAA,CAAAK,OAAA,GASa;EACdR,qBAAqB,EAAEA,qBAAqB;EAC5CI,WAAW,EAAEA,WAAW;EACxBC,eAAe,EAAEA,eAAe;EAChCC,cAAc,EAAEA;AACjB,CAAC","ignoreList":[]}
+{"version":3,"file":"unifyWhitespace.js","names":["unifyNonBreakingSpace","text","replace","unifyEmDash","unifyWhiteSpace","unifyAllSpaces"],"sources":["../../../../src/languageProcessing/helpers/sanitize/unifyWhitespace.js"],"sourcesContent":["/** @module stringProcessing/unifyWhitespace */\n\n/**\n * Replaces a non-breaking space with a normal space.\n *\n * @param {string} text The string to replace the non-breaking space in.\n *\n * @returns {string} The text with unified spaces.\n */\nconst unifyNonBreakingSpace = function( text ) {\n\treturn text.replace( / /g, \" \" );\n};\n\n/**\n * Replaces an em dash with a normal space.\n *\n * @param {string} text The string to replace the em dash in.\n *\n * @returns {string} The text with unified spaces.\n */\nconst unifyEmDash = function( text ) {\n\treturn text.replace( /\\u2014/g, \" \" );\n};\n\n/**\n * Replaces all whitespace characters with a normal space.\n *\n * @param {string} text The string to replace the whitespace characters in.\n *\n * @returns {string} The text with unified spaces.\n */\nconst unifyWhiteSpace = function( text ) {\n\treturn text.replace( /\\s/g, \" \" );\n};\n\n/**\n * Converts all whitespace to spaces.\n *\n * @param {string} text The text to replace spaces.\n *\n * @returns {string} The text with unified spaces.\n */\nconst unifyAllSpaces = function( text ) {\n\ttext = unifyNonBreakingSpace( text );\n\ttext = unifyEmDash( text );\n\treturn unifyWhiteSpace( text );\n};\n\nexport {\n\tunifyNonBreakingSpace,\n\tunifyEmDash,\n\tunifyWhiteSpace,\n\tunifyAllSpaces,\n};\n\nexport default {\n\tunifyNonBreakingSpace: unifyNonBreakingSpace,\n\tunifyEmDash: unifyEmDash,\n\tunifyWhiteSpace: unifyWhiteSpace,\n\tunifyAllSpaces: unifyAllSpaces,\n};\n"],"mappings":"AAAA;;AAEA;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMA,qBAAqB,GAAG,SAAAA,CAAUC,IAAI,EAAG;EAC9C,OAAOA,IAAI,CAACC,OAAO,CAAE,SAAS,EAAE,GAAI,CAAC;AACtC,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMC,WAAW,GAAG,SAAAA,CAAUF,IAAI,EAAG;EACpC,OAAOA,IAAI,CAACC,OAAO,CAAE,SAAS,EAAE,GAAI,CAAC;AACtC,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAME,eAAe,GAAG,SAAAA,CAAUH,IAAI,EAAG;EACxC,OAAOA,IAAI,CAACC,OAAO,CAAE,KAAK,EAAE,GAAI,CAAC;AAClC,CAAC;;AAED;AACA;AACA;AACA;AACA;AACA;AACA;AACA,MAAMG,cAAc,GAAG,SAAAA,CAAUJ,IAAI,EAAG;EACvCA,IAAI,GAAGD,qBAAqB,CAAEC,IAAK,CAAC;EACpCA,IAAI,GAAGE,WAAW,CAAEF,IAAK,CAAC;EAC1B,OAAOG,eAAe,CAAEH,IAAK,CAAC;AAC/B,CAAC;AAED,SACCD,qBAAqB,EACrBG,WAAW,EACXC,eAAe,EACfC,cAAc;AAGf,eAAe;EACdL,qBAAqB,EAAEA,qBAAqB;EAC5CG,WAAW,EAAEA,WAAW;EACxBC,eAAe,EAAEA,eAAe;EAChCC,cAAc,EAAEA;AACjB,CAAC","ignoreList":[]}