axyseo 2.0.0-alpha.1

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

@@ -0,0 +1,20 @@
+"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;
+
+/**
+ * Replaces sentence terminators from the text.
+ *
+ * @param {String} text The text to remove the terminators from.
+ *
+ * @returns {String} The sanitized text.
+ */
+function _default(text) {
+  return text.replace(sentenceTerminators, "");
+}
+//# sourceMappingURL=removeSentenceTerminators.js.map

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

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

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

@@ -0,0 +1,19 @@
+"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.
+ * It doesn't match domain names (e.g. "yoast.com" in "We got so much traffic on yoast.com after the latest release").
+ *
+ * @param {string} text The text to remove URLs from.
+ *
+ * @returns {string} The text without URLs.
+ */
+function _default(text) {
+  return text.replace(urlRegex, "");
+}
+//# sourceMappingURL=removeURLs.js.map

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

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

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

@@ -0,0 +1,18 @@
+"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.
+ *
+ * @param {string} text The text to sanitize.
+ *
+ * @returns {string} The sanitized text.
+ */
+function _default(text) {
+  return text.replace(/<br.*?>\s*<.*?br.*?>/gm, "</p><p>");
+}
+//# sourceMappingURL=sanitizeLineBreakTag.js.map

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

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

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

@@ -0,0 +1,23 @@
+"use strict";
+
+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.
+ *
+ * @param {String} text The text to be sanitized.
+ *
+ * @returns {String} The sanitized text.
+ */
+function _default(text) {
+  // Unify whitespaces and non-breaking spaces.
+  text = (0, _unifyWhitespace.unifyAllSpaces)(text);
+  // Strip the tags and multiple spaces.
+  text = (0, _stripHTMLTags.stripFullTags)(text);
+  return text;
+}
+//# sourceMappingURL=sanitizeString.js.map

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

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

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

@@ -0,0 +1,59 @@
+"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("|") + ")[^>]*?>$", "i");
+
+/**
+ * Strip incomplete tags within a text. Strips an end tag at the beginning of a string and the start tag at the end of a
+ * start of a string.
+ *
+ * @param {String} text The text to strip the HTML-tags from at the begin and end.
+ * @returns {String} The text without HTML-tags at the begin and end.
+ */
+const stripIncompleteTags = function (text) {
+  text = text.replace(/^(<\/([^>]+)>)+/i, "");
+  text = text.replace(/(<([^/>]+)>)+$/i, "");
+  return text;
+};
+
+/**
+ * Removes the block element tags at the beginning and end of a string and returns this string.
+ *
+ * @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, "");
+  return text;
+};
+
+/**
+ * Strip HTML-tags from 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);
+  return text;
+};
+exports.stripFullTags = stripFullTags;
+var _default = exports.default = {
+  stripFullTags: stripFullTags,
+  stripIncompleteTags: stripIncompleteTags,
+  stripBlockTagsAtStartEnd: stripBlockTagsAtStartEnd
+};
+//# sourceMappingURL=stripHTMLTags.js.map

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

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

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

@@ -0,0 +1,22 @@
+"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 */
+
+/**
+ * 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) {
+  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);
+  return text;
+}
+//# sourceMappingURL=stripNonTextTags.js.map

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

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

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

@@ -0,0 +1,26 @@
+"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 */
+
+/**
+ * Removes all words comprised only of numbers.
+ *
+ * @param {string} text to remove words
+ * @returns {string} The text with 'numberonly' words removed.
+ */
+function _default(text) {
+  // Remove "words" comprised only of numbers
+  text = text.replace(/\b[0-9]+\b/g, "");
+  text = (0, _stripSpaces.default)(text);
+  if (text === ".") {
+    text = "";
+  }
+  return text;
+}
+//# sourceMappingURL=stripNumbers.js.map

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

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

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

@@ -0,0 +1,29 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.default = _default;
+/** @module stringProcessing/stripSpaces */
+
+/**
+ * Replaces multiple spaces with a single space.
+ * Removes spaces followed by a period (if there's no text after the period) and spaces in the beginning or end of a string.
+ *
+ * @param {String} text The text to strip spaces from.
+ * @returns {String} The text with stripped spaces.
+ */
+function _default(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.
+  text = text.replace(/\s\.$/, ".");
+  // Removes first/last character if it's a space.
+  text = text.replace(/^\s+|\s+$/g, "");
+  // Replaces spaces followed by a Japanese period with only the period.
+  text = text.replace(/\s。/g, "。");
+  // Replaces spaces after a Japanese period with only the period.
+  text = text.replace(/。\s/g, "。");
+  return text;
+}
+//# sourceMappingURL=stripSpaces.js.map

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

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

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

@@ -0,0 +1,65 @@
+"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
+ * \u061f - Arabic question mark
+ * \u060C - Arabic comma
+ * \u061B - Arabic semicolon
+ */
+const wordBoundary = "[ \\u00a0\\u06d4\\u061f\\u060C\\u061B \\n\\r\\t.,'()\"+\\-;!?:/»«‹›<>]";
+const wordBoundaryStart = new RegExp("^(" + wordBoundary + "+)", "ig");
+const wordBoundaryEnd = new RegExp("(" + wordBoundary + "+$)", "ig");
+
+/**
+ * Strip word boundary markers from text in the beginning
+ *
+ * @param {String} text The text to strip word boundary markers from.
+ *
+ * @returns {String} The text without double word boundary markers.
+ */
+const stripWordBoundariesStart = function (text) {
+  // Remove first character if word boundary
+  text = text.replace(wordBoundaryStart, "");
+  return text;
+};
+
+/**
+ * Strip word boundary markers from text in the end
+ *
+ * @param {String} text The text to strip word boundary markers from.
+ *
+ * @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, "");
+  return text;
+};
+
+/**
+ * Strip word boundary markers from text in the beginning and in the end
+ *
+ * @param {String} text The text to strip word boundary markers from.
+ *
+ * @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 = {
+  stripWordBoundariesStart: stripWordBoundariesStart,
+  stripWordBoundariesEnd: stripWordBoundariesEnd,
+  stripWordBoundariesEverywhere: stripWordBoundariesEverywhere
+};
+//# sourceMappingURL=stripWordBoundaries.js.map

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

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

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

@@ -0,0 +1,64 @@
+"use strict";
+
+Object.defineProperty(exports, "__esModule", {
+  value: true
+});
+exports.unifyWhiteSpace = exports.unifyNonBreakingSpace = exports.unifyEmDash = exports.unifyAllSpaces = exports.default = void 0;
+/** @module stringProcessing/unifyWhitespace */
+
+/**
+ * Replaces a non-breaking space with a normal space.
+ *
+ * @param {string} text The string to replace the non-breaking space in.
+ *
+ * @returns {string} The text with unified spaces.
+ */
+const unifyNonBreakingSpace = function (text) {
+  return text.replace(/ /g, " ");
+};
+
+/**
+ * Replaces an em dash with a normal space.
+ *
+ * @param {string} text The string to replace the em dash in.
+ *
+ * @returns {string} The text with unified spaces.
+ */
+exports.unifyNonBreakingSpace = unifyNonBreakingSpace;
+const unifyEmDash = function (text) {
+  return text.replace(/\u2014/g, " ");
+};
+
+/**
+ * Replaces all whitespace characters with a normal space.
+ *
+ * @param {string} text The string to replace the whitespace characters in.
+ *
+ * @returns {string} The text with unified spaces.
+ */
+exports.unifyEmDash = unifyEmDash;
+const unifyWhiteSpace = function (text) {
+  return text.replace(/\s/g, " ");
+};
+
+/**
+ * Converts all whitespace to spaces.
+ *
+ * @param {string} text The text to replace spaces.
+ *
+ * @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 = {
+  unifyNonBreakingSpace: unifyNonBreakingSpace,
+  unifyEmDash: unifyEmDash,
+  unifyWhiteSpace: unifyWhiteSpace,
+  unifyAllSpaces: unifyAllSpaces
+};
+//# sourceMappingURL=unifyWhitespace.js.map

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

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