Refactor regex patterns to use native RegExp (#3595)

And fix invalid "\p{han}".

Author: tobiasdiez

BibLaTeX.js

@@ -17,7 +17,7 @@
 	},
 	"inRepository": true,
 	"translatorType": 2,
-	"lastUpdated": "2024-03-25 14:49:42"
+	"lastUpdated": "2026-04-01 18:00:00"
 }
 
 /*
@@ -302,9 +302,8 @@ function writeField(field, value, isMacro, noEscape) {
 
 		// Case of words with uppercase characters in non-initial positions is preserved with braces.
 		// we're looking at all unicode letters
-		var protectCaps = new ZU.XRegExp("\\b\\p{Letter}+\\p{Uppercase_Letter}\\p{Letter}*", 'g');
 		if (field != "pages") {
-			value = ZU.XRegExp.replace(value, protectCaps, "{$0}");
+			value = value.replace(/\b\p{L}+\p{Lu}\p{L}*/gu, "{$&}");
 		}
 
 		// Page ranges should use double dash

BibTeX.js

@@ -18,7 +18,7 @@
 	},
 	"inRepository": true,
 	"translatorType": 3,
-	"lastUpdated": "2024-03-25 14:51:02"
+	"lastUpdated": "2026-04-01 18:00:00"
 }
 
 /*
@@ -1082,7 +1082,7 @@ function writeField(field, value, isMacro) {
 		value = escapeSpecialCharacters(value);
 
 		if (caseProtectedFields.includes(field)) {
-			value = ZU.XRegExp.replace(value, protectCapsRE, "$1{$2$3}"); // only $2 or $3 will have a value, not both
+			value = value.replace(protectCapsRE, "$1{$2$3}"); // only $2 or $3 will have a value, not both
 		}
 	}
 	var exportCharset = Zotero.getOption("exportCharset");
@@ -1341,15 +1341,12 @@ function doExport() {
 		// Case of words with uppercase characters in non-initial positions is
 		// preserved with braces.
 		// Two extra captures because of the other regexp below
-		protectCapsRE = new ZU.XRegExp("()()\\b([\\p{Letter}\\d]+\\p{Uppercase_Letter}[\\p{Letter}\\d]*)", 'g');
+		protectCapsRE = /()()\b([\p{L}\d]+\p{Lu}[\p{L}\d]*)/gu;
 	} else {
 		// Protect all upper case letters, even if the uppercase letter is only in
 		// initial position of the word.
 		// Don't protect first word if only first letter is capitalized
-		protectCapsRE = new ZU.XRegExp(
-			"(.)\\b([\\p{Letter}\\d]*\\p{Uppercase_Letter}[\\p{Letter}\\d]*)" // Non-initial words with capital letter anywhere
-				+ "|^([\\p{Letter}\\d]+\\p{Uppercase_Letter}[\\p{Letter}\\d]*)" // Initial word with capital in non-initial position
-			, 'g');
+		protectCapsRE = /(.)\b([\p{L}\d]*\p{Lu}[\p{L}\d]*)|^([\p{L}\d]+\p{Lu}[\p{L}\d]*)/gu;
 	}
 
 	//Zotero.write("% BibTeX export generated by Zotero "+Zotero.Utilities.getVersion());

Korean National Library.js

@@ -9,7 +9,7 @@
 	"inRepository": true,
 	"translatorType": 4,
 	"browserSupport": "gcsibv",
-	"lastUpdated": "2022-12-28 02:37:11"
+	"lastUpdated": "2026-04-01 18:00:00"
 }
 
 /*
@@ -80,11 +80,10 @@ function getType(type) {
 function fixKoreanCreators(creators) {
 	for (let i = 0; i < creators.length; i++) {
 		var len = creators[i].lastName.length;
-		var regex = "[\\p{hangul}\\{han}]{" + len + "}";
-		var korean = new ZU.XRegExp(regex);
+		var korean = new RegExp("^[\\p{Script=Hangul}\\p{Script=Han}]{" + len + "}$", 'u');
 		if (creators[i].firstName) continue; // likely a Western name
 		else if (len > 3) continue; // likely Japanese name
-		else if (ZU.XRegExp.test(creators[i].lastName, korean)) {
+		else if (korean.test(creators[i].lastName)) {
 			// name is almost certainly Korean. First character is lastName
 			creators[i].firstName = creators[i].lastName.replace(/^./, "");
 			creators[i].lastName = creators[i].lastName.replace(/^(.).*/, "$1");

eLibrary.ru.js

@@ -9,7 +9,7 @@
 	"inRepository": true,
 	"translatorType": 4,
 	"browserSupport": "gcsibv",
-	"lastUpdated": "2024-07-14 15:27:57"
+	"lastUpdated": "2026-04-01 18:00:00"
 }
 
 /*
@@ -170,13 +170,9 @@ async function scrape(doc, url = doc.location.href) {
 		   In all these cases, we put comma after LAST for `ZU.cleanAuthor()` to work.
 		   Other formats are rare, but possible, e.g. "ВАН ДЕ КЕРЧОВЕ Р." == "Van de Kerchove R.".
 		   They go to single-field mode (assuming they got no comma). */
-		var nameFormat1RE = new ZU.XRegExp("^\\p{Letter}+\\s\\p{Letter}+\\s\\p{Letter}+$");
-		var nameFormat2RE = new ZU.XRegExp("^\\p{Letter}+\\s\\p{Letter}\\.(\\s?\\p{Letter}\\.?)?$");
-		var nameFormat3RE = new ZU.XRegExp("^\\p{Letter}+\\s\\(\\p{Letter}+\\)\\s\\p{Letter}+\\s\\p{Letter}+$");
-
-		var isFormat1 = ZU.XRegExp.test(dirty, nameFormat1RE);
-		var isFormat2 = ZU.XRegExp.test(dirty, nameFormat2RE);
-		var isFormat3 = ZU.XRegExp.test(dirty, nameFormat3RE);
+		var isFormat1 = /^\p{L}+\s\p{L}+\s\p{L}+$/u.test(dirty);
+		var isFormat2 = /^\p{L}+\s\p{L}\.(\s?\p{L}\.?)?$/u.test(dirty);
+		var isFormat3 = /^\p{L}+\s\(\p{L}+\)\s\p{L}+\s\p{L}+$/u.test(dirty);
 
 		if (isFormat1 || isFormat2) {
 			// add comma before the first space