Merge branch 'features/unicode-format' of https://github.com/mattnotmitt/CyberChef into mattnotmitt-features/unicode-format

src/core/config/Categories.json

@@ -200,6 +200,7 @@
         "ops": [
             "Encode text",
             "Decode text",
+            "Unicode Text Format",
             "Remove Diacritics",
             "Unescape Unicode Characters",
             "Convert to NATO alphabet"

src/core/operations/RemoveDiacritics.mjs

@@ -19,7 +19,7 @@ class RemoveDiacritics extends Operation {
 
         this.name = "Remove Diacritics";
         this.module = "Default";
-        this.description = "Replaces accented characters with their latin character equivalent.";
+        this.description = "Replaces accented characters with their latin character equivalent. Accented characters are made up of Unicode combining characters, so unicode text formatting such as strikethroughs and underlines will also be removed.";
         this.infoURL = "https://wikipedia.org/wiki/Diacritic";
         this.inputType = "string";
         this.outputType = "string";

src/core/operations/UnicodeTextFormat.mjs

@@ -0,0 +1,67 @@
+/**
+ * @author Matt C [me@mitt.dev]
+ * @copyright Crown Copyright 2020
+ * @license Apache-2.0
+ */
+
+import Operation from "../Operation.mjs";
+import Utils from "../Utils.mjs";
+
+/**
+ * Unicode Text Format operation
+ */
+class UnicodeTextFormat extends Operation {
+
+    /**
+     * UnicodeTextFormat constructor
+     */
+    constructor() {
+        super();
+
+        this.name = "Unicode Text Format";
+        this.module = "Default";
+        this.description = "Adds Unicode combining characters to change formatting of plaintext.";
+        this.infoURL = "https://en.wikipedia.org/wiki/Combining_character";
+        this.inputType = "byteArray";
+        this.outputType = "byteArray";
+        this.args = [
+            {
+                name: "Underline",
+                type: "boolean",
+                value: "false"
+            },
+            {
+                name: "Strikethrough",
+                type: "boolean",
+                value: "false"
+            }
+        ];
+    }
+
+    /**
+     * @param {byteArray} input
+     * @param {Object[]} args
+     * @returns {byteArray}
+     */
+    run(input, args) {
+        const [underline, strikethrough] = args;
+        let output = input.map(char => [char]);
+        if (strikethrough) {
+            output = output.map(charFormat => {
+                charFormat.push(...Utils.strToUtf8ByteArray("\u0336"));
+                return charFormat;
+            });
+        }
+        if (underline) {
+            output = output.map(charFormat => {
+                charFormat.push(...Utils.strToUtf8ByteArray("\u0332"));
+                return charFormat;
+            });
+        }
+        // return output.flat(); - Not supported in Node 10, polyfilled
+        return [].concat(...output);
+    }
+
+}
+
+export default UnicodeTextFormat;