Split "Text encoding" op into two ops

This commit splits "Text encoding" into two operations:
+ Encode text `string -> byteArray`
+ Decode text `byteArray -> string`

Base64 and Hex support are removed "Encode text" and "Decode text" as
they have their own operations.

Encode and decode operations now have support for the following
encodings:
+ IBM EBCDIC US-Canada
+ IBM EBCDIC International
+ Windows-874 Thai
+ Japanese Shift-JIS
+ Simplified Chinese GBK
+ Korean
+ Traditional Chinese Big5
+ UTF-16, little endian
+ UTF-16, big endian
+ Windows-1250 Central European
+ Windows-1251 Cyrillic
+ Windows-1252 Latin
+ Windows-1253 Greek
+ Windows-1254 Turkish
+ Windows-1255 Hebrew
+ Windows-1256 Arabic
+ Windows-1257 Baltic
+ Windows-1258 Vietnam
+ US-ASCII
+ Russian Cyrillic KOI8-R
+ Simplified Chinese GB2312
+ KOI8-U Ukrainian Cyrillic
+ ISO-8859-1 Latin 1 (Western European)
+ ISO-8859-2 Latin 2 (Central European)
+ ISO-8859-3 Latin 3
+ ISO-8859-4 Baltic
+ ISO-8859-5 Cyrillic
+ ISO-8859-6 Arabic
+ ISO-8859-7 Greek
+ ISO-8859-8 Hebrew
+ ISO-8859-9 Turkish
+ ISO-8859-10 Latin 6
+ ISO-8859-11 Latin (Thai)
+ ISO-8859-13 Latin 7 (Estonian)
+ ISO-8859-14 Latin 8 (Celtic)
+ ISO-8859-15 Latin 9
+ ISO-8859-16 Latin 10
+ ISO-2022 JIS Japanese
+ EUC Japanese
+ EUC Korean
+ Simplified Chinese GB18030
+ UTF-7
+ UTF-8

src/core/config/Categories.js

@@ -61,7 +61,8 @@ const Categories = [
             "Hex to PEM",
             "Parse ASN.1 hex string",
             "Change IP format",
-            "Text encoding",
+            "Encode text",
+            "Decode text",
             "Swap endianness",
         ]
     },
@@ -143,7 +144,8 @@ const Categories = [
     {
         name: "Language",
         ops: [
-            "Text encoding",
+            "Encode text",
+            "Decode text",
             "Unescape Unicode Characters",
         ]
     },

src/core/config/OperationConfig.js

@@ -872,21 +872,43 @@ const OperationConfig = {
             }
         ]
     },
-    "Text encoding": {
-        description: "Translates the data between different character encodings.<br><br>Supported charsets are:<ul><li>UTF8</li><li>UTF16</li><li>UTF16LE (little-endian)</li><li>UTF16BE (big-endian)</li><li>Hex</li><li>Base64</li><li>Latin1 (ISO-8859-1)</li><li>Windows-1251</li></ul>",
-        run: CharEnc.run,
+    "Encode text": {
+        description: [
+            "Encodes text into the chosen character encoding.",
+            "<br><br>",
+            "Supported charsets are:",
+            "<ul>",
+            Object.keys(CharEnc.IO_FORMAT).map(e => `<li>${e}</li>`).join("<br>"),
+            "</ul>",
+        ].join("\n"),
+        run: CharEnc.runEncode,
         inputType: "string",
+        outputType: "byteArray",
+        args: [
+            {
+                name: "Encoding",
+                type: "option",
+                value: Object.keys(CharEnc.IO_FORMAT),
+            },
+        ]
+    },
+    "Decode text": {
+        description: [
+            "Decodes text from the chosen character encoding.",
+            "<br><br>",
+            "Supported charsets are:",
+            "<ul>",
+            Object.keys(CharEnc.IO_FORMAT).map(e => `<li>${e}</li>`).join("<br>"),
+            "</ul>",
+        ].join("\n"),
+        run: CharEnc.runDecode,
+        inputType: "byteArray",
         outputType: "string",
         args: [
             {
-                name: "Input type",
+                name: "Encoding",
                 type: "option",
-                value: CharEnc.IO_FORMAT
-            },
-            {
-                name: "Output type",
-                type: "option",
-                value: CharEnc.IO_FORMAT
+                value: Object.keys(CharEnc.IO_FORMAT),
             },
         ]
     },
@@ -3249,44 +3271,6 @@ const OperationConfig = {
             },
         ]
     },
-    "To EBCDIC": {
-        description: [
-            "This operation converts ASCII text to EBCDIC.",
-            "<br>",
-            "You can choose between a few versions of EBCDIC.",
-            "<br>",
-            "EBCDIC is a proprietary encoding pre-dating ASCII that originated at IBM.",
-        ].join("\n"),
-        run: CharEnc.runToEBCDIC,
-        inputType: "string",
-        outputType: "byteArray",
-        args: [
-            {
-                name: "EBCDIC version",
-                type: "option",
-                value: Object.keys(CharEnc.EBCDIC_CODEPAGES_MAPPING),
-            },
-        ]
-    },
-    "From EBCDIC": {
-        description: [
-            "This operation converts ASCII text from EBCDIC.",
-            "<br>",
-            "You can choose between a few versions of EBCDIC.",
-            "<br>",
-            "EBCDIC is a proprietary encoding pre-dating ASCII that originated at IBM.",
-        ].join("\n"),
-        run: CharEnc.runFromEBCDIC,
-        inputType: "byteArray",
-        outputType: "string",
-        args: [
-            {
-                name: "EBCDIC version",
-                type: "option",
-                value: Object.keys(CharEnc.EBCDIC_CODEPAGES_MAPPING),
-            },
-        ]
-    },
 };
 
 export default OperationConfig;

src/core/operations/CharEnc.js

@@ -18,80 +18,79 @@ const CharEnc = {
      * @constant
      * @default
      */
-    IO_FORMAT: ["UTF8", "UTF16", "UTF16LE", "UTF16BE", "Latin1", "Windows-1251", "Hex", "Base64"],
-
-    /**
-     * Text encoding operation.
-     *
-     * @param {string} input
-     * @param {Object[]} args
-     * @returns {string}
-     */
-    run: function(input, args) {
-        var inputFormat = args[0],
-            outputFormat = args[1];
-
-        if (inputFormat === "Windows-1251") {
-            input = Utils.win1251ToUnicode(input);
-            input = CryptoJS.enc.Utf8.parse(input);
-        } else {
-            input = Utils.format[inputFormat].parse(input);
-        }
-
-        if (outputFormat === "Windows-1251") {
-            input = CryptoJS.enc.Utf8.stringify(input);
-            return Utils.unicodeToWin1251(input);
-        } else {
-            return Utils.format[outputFormat].stringify(input);
-        }
-    },
-
-    /**
-     *
-     * @author tlwr [toby@toby.codes]
-     *
-     * @constant
-     * @default
-     */
-    EBCDIC_CODEPAGES_MAPPING: {
+    IO_FORMAT: {
+        "UTF-8": 65001,
+        "UTF-7": 65000,
+        "UTF16LE": 1200,
+        "UTF16BE": 1201,
+        "UTF16": 1201,
         "IBM EBCDIC International": 500,
         "IBM EBCDIC US-Canada": 37,
+        "Windows-874 Thai": 874,
+        "Japanese Shift-JIS": 932,
+        "Simplified Chinese GBK": 936,
+        "Korean": 949,
+        "Traditional Chinese Big5": 950,
+        "Windows-1250 Central European": 1250,
+        "Windows-1251 Cyrillic": 1251,
+        "Windows-1252 Latin": 1252,
+        "Windows-1253 Greek": 1253,
+        "Windows-1254 Turkish": 1254,
+        "Windows-1255 Hebrew": 1255,
+        "Windows-1256 Arabic": 1256,
+        "Windows-1257 Baltic": 1257,
+        "Windows-1258 Vietnam": 1258,
+        "US-ASCII": 20127,
+        "Russian Cyrillic KOI8-R": 20866,
+        "Simplified Chinese GB2312": 20936,
+        "KOI8-U Ukrainian Cyrillic": 21866,
+        "ISO-8859-1 Latin 1 (Western European)": 28591,
+        "ISO-8859-2 Latin 2 (Central European)": 28592,
+        "ISO-8859-3 Latin 3": 28593,
+        "ISO-8859-4 Baltic": 28594,
+        "ISO-8859-5 Cyrillic": 28595,
+        "ISO-8859-6 Arabic": 28596,
+        "ISO-8859-7 Greek": 28597,
+        "ISO-8859-8 Hebrew": 28598,
+        "ISO-8859-9 Turkish": 28599,
+        "ISO-8859-10 Latin 6": 28600,
+        "ISO-8859-11 Latin (Thai)": 28601,
+        "ISO-8859-13 Latin 7 (Estonian)": 28603,
+        "ISO-8859-14 Latin 8 (Celtic)": 28604,
+        "ISO-8859-15 Latin 9": 28605,
+        "ISO-8859-16 Latin 10": 28606,
+        "ISO-2022 JIS Japanese": 50222,
+        "EUC Japanese": 51932,
+        "EUC Korean": 51949,
+        "Simplified Chinese GB18030": 54936,
     },
 
     /**
-     * To EBCDIC operation.
-     *
-     * @author tlwr [toby@toby.codes]
+     * Encode text operation.
      *
      * @param {string} input
      * @param {Object[]} args
      * @returns {byteArray}
      */
-    runToEBCDIC: function(input, args) {
-        let pageNum = CharEnc.EBCDIC_CODEPAGES_MAPPING[args[0]];
-
-        let output = cptable.utils.encode(pageNum, input);
-
-        return Array.from(output);
+    runEncode: function(input, args) {
+        let format = CharEnc.IO_FORMAT[args[0]];
+        let encoded = cptable.utils.encode(format, input);
+        encoded = Array.from(encoded);
+        return encoded;
     },
 
     /**
-     * From EBCDIC operation.
-     *
-     * @author tlwr [toby@toby.codes]
+     * Decode text operation.
      *
      * @param {byteArray} input
      * @param {Object[]} args
      * @returns {string}
      */
-    runFromEBCDIC: function(input, args) {
-        let pageNum = CharEnc.EBCDIC_CODEPAGES_MAPPING[args[0]];
-
-        let output = cptable.utils.decode(pageNum, input);
-
-        return output;
+    runDecode: function(input, args) {
+        let format = CharEnc.IO_FORMAT[args[0]];
+        let decoded = cptable.utils.decode(format, input);
+        return decoded;
     },
-
 };
 
 export default CharEnc;

test/tests/operations/CharEnc.js

@@ -9,42 +9,42 @@ import TestRegister from "../../TestRegister.js";
 
 TestRegister.addTests([
     {
-        name: "From EBCDIC: nothing",
+        name: "Encode text, Decode text: nothing",
         input: "",
         expectedOutput: "",
         recipeConfig: [
             {
-                "op": "From Hex",
-                "args": ["Space"]
+                "op": "Encode text",
+                "args": ["UTF-8"]
             },
             {
-                "op": "From EBCDIC",
-                "args": ["IBM EBCDIC International"]
+                "op": "Decode text",
+                "args": ["UTF-8"]
             },
         ],
     },
     {
-        name: "From EBCDIC: hello",
-        input: "88 85 93 93 96",
+        name: "Encode text, Decode text: hello",
+        input: "hello",
         expectedOutput: "hello",
         recipeConfig: [
             {
-                "op": "From Hex",
-                "args": ["Space"]
+                "op": "Encode text",
+                "args": ["UTF-8"]
             },
             {
-                "op": "From EBCDIC",
-                "args": ["IBM EBCDIC International"]
+                "op": "Decode text",
+                "args": ["UTF-8"]
             },
         ],
     },
     {
-        name: "To EBCDIC: hello",
+        name: "Encode text (EBCDIC): hello",
         input: "hello",
         expectedOutput: "88 85 93 93 96",
         recipeConfig: [
             {
-                "op": "To EBCDIC",
+                "op": "Encode text",
                 "args": ["IBM EBCDIC International"]
             },
             {
@@ -53,4 +53,19 @@ TestRegister.addTests([
             },
         ],
     },
+    {
+        name: "Decode text (EBCDIC): 88 85 93 93 96",
+        input: "88 85 93 93 96",
+        expectedOutput: "hello",
+        recipeConfig: [
+            {
+                "op": "From Hex",
+                "args": ["Space"]
+            },
+            {
+                "op": "Decode text",
+                "args": ["IBM EBCDIC International"]
+            },
+        ],
+    },
 ]);