Document which parts of the getSupplementaryPrivateUseRegExp regex …

…refer to which unicode range
dequelabs · Mar 19, 2020 · 6a90379 · 6a90379
1 parent 0e3777a
commit 6a90379
Showing 1 changed file with 6 additions and 5 deletions.
diff --git a/lib/commons/text/unicode.js b/lib/commons/text/unicode.js
@@ -130,10 +130,11 @@ function getPunctuationRegExp() {
  * @returns {RegExp}
  */
 function getSupplementaryPrivateUseRegExp() {
-	/**
-	 * Reference: https://www.unicode.org/charts/PDF/UD800.pdf
-	 * https://www.unicode.org/charts/PDF/UDC00.pdf
-	 * https://www.unicode.org/charts/PDF/UF0000.pdf
-	 */
+	// 1. High surrogate area (https://www.unicode.org/charts/PDF/UD800.pdf)
+	// 2. Low surrogate area (https://www.unicode.org/charts/PDF/UDC00.pdf)
+	// 3. Supplementary private use area A (https://www.unicode.org/charts/PDF/UF0000.pdf)
+	//
+	//             1              2                                  3
+	//      ┏━━━━━━┻━━━━━━┓┏━━━━━━┻━━━━━━┓ ┏━━━━━━━━━━━━━━━━━━━━━━━━━┻━━━━━━━━━━━━━━━━━━━━━━━━━━━━┓
 	return /[\uDB80-\uDBBF][\uDC00-\uDFFD]|(?:[\uDB80-\uDBBE][\uDC00-\uDFFF]|\uDBBF[\uDC00-\uDFFD])/g;
 }