Bump CyberChef to v10.8.2

Add devcontainer configuration and .gitattributes

.devcontainer/devcontainer.json

@@ -0,0 +1,41 @@
+// For format details, see https://aka.ms/devcontainer.json. For config options, see the
+// README at: https://github.com/devcontainers/templates/tree/main/src/javascript-node
+{
+	"name": "CyberChef",
+	// Or use a Dockerfile or Docker Compose file. More info: https://containers.dev/guide/dockerfile
+	"image": "mcr.microsoft.com/devcontainers/javascript-node:1-18-bookworm",
+
+	// Features to add to the dev container. More info: https://containers.dev/features.
+	"features": {
+		"ghcr.io/devcontainers/features/github-cli": "latest"
+	},
+
+	// Use 'forwardPorts' to make a list of ports inside the container available locally.
+	"forwardPorts": [8080],
+
+	// Use 'postCreateCommand' to run commands after the container is created.
+	"postCreateCommand": {
+		"npm": "bash -c \"sudo chown node node_modules && npm install\""
+	},
+
+	"containerEnv": {
+		"DISPLAY": ":99"
+	},
+
+	"mounts": [
+		"source=${localWorkspaceFolderBasename}-node_modules,target=${containerWorkspaceFolder}/node_modules,type=volume"
+	],
+
+	// Configure tool-specific properties.
+	"customizations": {
+		"vscode": {
+			"extensions": [
+				"dbaeumer.vscode-eslint",
+				"GitHub.vscode-github-actions"
+			]
+		}
+	}
+
+	// Uncomment to connect as root instead. More info: https://aka.ms/dev-containers-non-root.
+	// "remoteUser": "root"
+}

.gitattributes

@@ -0,0 +1 @@
+* text=auto eol=lf

.github/workflows/releases.yml

@@ -15,8 +15,6 @@ env:
 jobs:
   main:
     runs-on: ubuntu-latest
-    permissions:
-      packages: write
     steps:
     - uses: actions/checkout@v3
 

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "cyberchef",
-  "version": "10.8.0",
+  "version": "10.8.2",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "cyberchef",
-      "version": "10.8.0",
+      "version": "10.8.2",
       "hasInstallScript": true,
       "license": "Apache-2.0",
       "dependencies": {

package.json

@@ -1,6 +1,6 @@
 {
   "name": "cyberchef",
-  "version": "10.8.0",
+  "version": "10.8.2",
   "description": "The Cyber Swiss Army Knife for encryption, encoding, compression and data analysis.",
   "author": "n1474335 <n1474335@gmail.com>",
   "homepage": "https://gchq.github.io/CyberChef",

src/core/config/Categories.json

@@ -70,6 +70,7 @@
             "Avro to JSON",
             "CBOR Encode",
             "CBOR Decode",
+            "Caret/M-decode",
             "Rison Encode",
             "Rison Decode"
         ]
@@ -333,7 +334,8 @@
             "CSS selector",
             "Extract EXIF",
             "Extract ID3",
-            "Extract Files"
+            "Extract Files",
+            "RAKE"
         ]
     },
     {

src/core/operations/CaretMdecode.mjs

@@ -0,0 +1,98 @@
+/**
+ * @author tedk [tedk@ted.do]
+ * @copyright Crown Copyright 2024
+ * @license Apache-2.0
+ */
+
+import Operation from "../Operation.mjs";
+
+/**
+ * Caret/M-decode operation
+ *
+ * https://gist.githubusercontent.com/JaHIY/3c91bbf7bea5661e6abfbd1349ee81a2/raw/c7b480e9ff24bcb8f5287a8a8a2dcb9bf5628506/decode_m_notation.cpp
+ */
+class CaretMdecode extends Operation {
+
+    /**
+     * CaretMdecode constructor
+     */
+    constructor() {
+        super();
+
+        this.name = "Caret/M-decode";
+        this.module = "Default";
+        this.description = "Decodes caret or M-encoded strings, i.e. ^M turns into a newline, M-^] turns into 0x9d. Sources such as `cat -v`.\n\nPlease be aware that when using `cat -v` ^_ (caret-underscore) will not be encoded, but represents a valid encoding (namely that of 0x1f).";
+        this.infoURL = "https://en.wikipedia.org/wiki/Caret_notation";
+        this.inputType = "string";
+        this.outputType = "byteArray";
+        this.args = [];
+    }
+
+    /**
+     * @param {string} input
+     * @param {Object[]} args
+     * @returns {byteArray}
+     */
+    run(input, args) {
+
+        const bytes = [];
+
+        let prev = "";
+
+        for (let i = 0; i < input.length; i++) {
+
+            const charCode = input.charCodeAt(i);
+            const curChar = input.charAt(i);
+
+            if (prev === "M-^") {
+                if (charCode > 63 && charCode <= 95) {
+                    bytes.push(charCode + 64);
+                } else if (charCode === 63) {
+                    bytes.push(255);
+                } else {
+                    bytes.push(77, 45, 94, charCode);
+                }
+                prev = "";
+            } else if (prev === "M-") {
+                if (curChar === "^") {
+                    prev = prev + "^";
+                } else if (charCode >= 32 && charCode <= 126) {
+                    bytes.push(charCode + 128);
+                    prev = "";
+                } else {
+                    bytes.push(77, 45, charCode);
+                    prev = "";
+                }
+            } else if (prev === "M") {
+                if (curChar === "-") {
+                    prev = prev + "-";
+                } else {
+                    bytes.push(77, charCode);
+                    prev = "";
+                }
+            } else if (prev === "^") {
+                if (charCode > 63 && charCode <= 126) {
+                    bytes.push(charCode - 64);
+                } else if (charCode === 63) {
+                    bytes.push(127);
+                } else {
+                    bytes.push(94, charCode);
+                }
+                prev = "";
+            } else {
+                if (curChar === "M") {
+                    prev = "M";
+                } else if (curChar === "^") {
+                    prev = "^";
+                } else {
+                    bytes.push(charCode);
+                }
+            }
+
+        }
+        return bytes;
+    }
+
+}
+
+export default CaretMdecode;

src/core/operations/Diff.mjs

@@ -119,9 +119,9 @@ class Diff extends Operation {
 
         for (let i = 0; i < diff.length; i++) {
             if (diff[i].added) {
-                if (showAdded) output += "<span class='hl5'>" + Utils.escapeHtml(diff[i].value) + "</span>";
+                if (showAdded) output += "<ins>" + Utils.escapeHtml(diff[i].value) + "</ins>";
             } else if (diff[i].removed) {
-                if (showRemoved) output += "<span class='hl3'>" + Utils.escapeHtml(diff[i].value) + "</span>";
+                if (showRemoved) output += "<del>" + Utils.escapeHtml(diff[i].value) + "</del>";
             } else if (!showSubtraction) {
                 output += Utils.escapeHtml(diff[i].value);
             }

src/core/operations/RAKE.mjs

@@ -0,0 +1,149 @@
+/**
+ * @author sw5678
+ * @copyright Crown Copyright 2024
+ * @license Apache-2.0
+ */
+
+import Operation from "../Operation.mjs";
+
+/**
+ * RAKE operation
+ */
+class RAKE extends Operation {
+
+    /**
+     * RAKE constructor
+     */
+    constructor() {
+        super();
+
+        this.name = "RAKE";
+        this.module = "Default";
+        this.description = [
+            "Rapid Keyword Extraction (RAKE)",
+            "<br><br>",
+            "RAKE is a domain-independent keyword extraction algorithm in Natural Language Processing.",
+            "<br><br>",
+            "The list of stop words are from the NLTK python package",
+        ].join("\n");
+        this.inputType = "string";
+        this.outputType = "string";
+        this.args = [
+            {
+                name: "Word Delimiter (Regex)",
+                type: "text",
+                value: "\\s"
+            },
+            {
+                name: "Sentence Delimiter (Regex)",
+                type: "text",
+                value: "\\.\\s|\\n"
+            },
+            {
+                name: "Stop Words",
+                type: "text",
+                value: "i,me,my,myself,we,our,ours,ourselves,you,you're,you've,you'll,you'd,your,yours,yourself,yourselves,he,him,his,himself,she,she's,her,hers,herself,it,it's,its,itsef,they,them,their,theirs,themselves,what,which,who,whom,this,that,that'll,these,those,am,is,are,was,were,be,been,being,have,has,had,having,do,does',did,doing,a,an,the,and,but,if,or,because,as,until,while,of,at,by,for,with,about,against,between,into,through,during,before,after,above,below,to,from,up,down,in,out,on,off,over,under,again,further,then,once,here,there,when,where,why,how,all,any,both,each,few,more,most,other,some,such,no,nor,not,only,own,same,so,than,too,very,s,t,can,will,just,don,don't,should,should've,now,d,ll,m,o,re,ve,y,ain,aren,aren't,couldn,couldn't,didn,didn't,doesn,doesn't,hadn,hadn't,hasn,hasn't,haven,haven't,isn,isn't,ma,mightn,mightn't,mustn,mustn't,needn,needn't,shan,shan't,shouldn,shouldn't,wasn,wasn't,weren,weren't,won,won't,wouldn,wouldn't"
+            }
+        ];
+    }
+
+    /**
+     * @param {string} input
+     * @param {Object[]} args
+     * @returns {string}
+     */
+    run(input, args) {
+
+        // Get delimiter regexs
+        const wordDelim =  new RegExp(args[0], "g");
+        const sentDelim = new RegExp(args[1], "g");
+
+        // Deduplicate the stop words and add the empty string
+        const stopWords = args[2].toLowerCase().replace(/ /g, "").split(",").unique();
+        stopWords.push("");
+
+        // Lower case input and remove start and ending whitespace
+        input = input.toLowerCase().trim();
+
+        // Get tokens, token count, and phrases
+        const tokens = [];
+        const wordFrequencies = [];
+        let phrases = [];
+
+        // Build up list of phrases and token counts
+        const sentences = input.split(sentDelim);
+        for (const sent of sentences) {
+
+            // Split sentence into words
+            const splitSent = sent.split(wordDelim);
+            let startIndex = 0;
+
+            for (let i = 0; i < splitSent.length; i++) {
+                const token = splitSent[i];
+                if (stopWords.includes(token)) {
+                    // If token is stop word then split to create phrase
+                    phrases.push(splitSent.slice(startIndex, i));
+                    startIndex = i + 1;
+                } else {
+                    // If token is not a stop word add to the count of the list of words
+                    if (tokens.includes(token)) {
+                        wordFrequencies[tokens.indexOf(token)]+=1;
+                    } else {
+                        tokens.push(token);
+                        wordFrequencies.push(1);
+                    }
+                }
+            }
+            phrases.push(splitSent.slice(startIndex));
+        }
+
+        // remove empty phrases
+        phrases = phrases.filter(subArray => subArray.length > 0);
+
+        // Remove duplicate phrases
+        const uniquePhrases = [...new Set(phrases.map(function (phrase) {
+            return phrase.join(" ");
+        }))];
+        phrases = uniquePhrases.map(function (phrase) {
+            return phrase.split(" ");
+        });
+
+        // Generate word_degree_matrix and populate
+        const wordDegreeMatrix = Array.from(Array(tokens.length), _ => Array(tokens.length).fill(0));
+        phrases.forEach(function (phrase) {
+            phrase.forEach(function (word1) {
+                phrase.forEach(function (word2) {
+                    wordDegreeMatrix[tokens.indexOf(word1)][tokens.indexOf(word2)]++;
+                });
+            });
+        });
+
+        // Calculate degree score for each token
+        const degreeScores = Array(tokens.length).fill(0);
+        for (let i=0; i<tokens.length; i++) {
+            let wordDegree = 0;
+            for (let j=0; j<wordDegreeMatrix.length; j++) {
+                wordDegree += wordDegreeMatrix[j][i];
+            }
+            degreeScores[i] = wordDegree / wordFrequencies[i];
+        }
+
+        // Calculate score for each phrase
+        const scores = phrases.map(function (phrase) {
+            let score = 0;
+            phrase.forEach(function (token) {
+                score += degreeScores[tokens.indexOf(token)];
+            });
+            return new Array(score, phrase.join(" "));
+        });
+        scores.sort((a, b) => b[0] - a[0]);
+        scores.unshift(new Array("Scores: ", "Keywords: "));
+
+        // Output works with the 'To Table' functionality already built into CC
+        return scores.map(function (score) {
+            return score.join(", ");
+        }).join("\n");
+    }
+}
+
+export default RAKE;

src/web/stylesheets/index.css

@@ -36,4 +36,5 @@
 @import "./layout/_structure.css";
 
 /* Operations */
+@import "./operations/diff.css";
 @import "./operations/json.css";

src/web/stylesheets/operations/diff.css

@@ -0,0 +1,8 @@
+del {
+    background-color: var(--hl3);
+}
+
+ins {
+    text-decoration: underline; /* shouldn't be needed, but Chromium doesn't copy to clipboard without it */
+    background-color: var(--hl5);
+}

src/web/stylesheets/operations/json.css

@@ -44,7 +44,8 @@ ul.json-dict, ol.json-array {
     display: contents;
 }
 .json-summary {
-    display: contents;
+    display: inline;
+    list-style: none;
 }
 
 /* Display object and array brackets when closed */

tests/browser/02_ops.js

@@ -108,7 +108,7 @@ module.exports = {
         // testOp(browser, "Derive EVP key", "test input", "test_output");
         // testOp(browser, "Derive PBKDF2 key", "test input", "test_output");
         // testOp(browser, "Detect File Type", "test input", "test_output");
-        testOpHtml(browser, "Diff", "The cat sat on the mat\n\nThe mat cat on the sat", ".hl5:first-child", "mat", ["\\n\\n", "Word", true, true, false, false]);
+        testOpHtml(browser, "Diff", "The cat sat on the mat\n\nThe mat cat on the sat", "ins:first-child", "mat", ["\\n\\n", "Word", true, true, false, false]);
         // testOp(browser, "Disassemble x86", "test input", "test_output");
         testOpImage(browser, "Dither Image", "files/Hitchhikers_Guide.jpeg");
     // testOp(browser, "Divide", "test input", "test_output");

tests/operations/index.mjs

@@ -34,6 +34,7 @@ import "./tests/Bombe.mjs";
 import "./tests/BSON.mjs";
 import "./tests/ByteRepr.mjs";
 import "./tests/CaesarBoxCipher.mjs";
+import "./tests/CaretMdecode.mjs";
 import "./tests/CartesianProduct.mjs";
 import "./tests/CBORDecode.mjs";
 import "./tests/CBOREncode.mjs";
@@ -117,6 +118,7 @@ import "./tests/PHP.mjs";
 import "./tests/PowerSet.mjs";
 import "./tests/Protobuf.mjs";
 import "./tests/Rabbit.mjs";
+import "./tests/RAKE.mjs";
 import "./tests/Regex.mjs";
 import "./tests/Register.mjs";
 import "./tests/RisonEncodeDecode.mjs";

tests/operations/tests/CaretMdecode.mjs

@@ -0,0 +1,39 @@
+/**
+ * Caesar Box Cipher tests.
+ *
+ * @author tedk [tedk@ted.do]
+ *
+ * @copyright Crown Copyright 2020
+ * @license Apache-2.0
+ */
+import TestRegister from "../../lib/TestRegister.mjs";
+
+TestRegister.addTests([
+    {
+        name: "Caret/M-decode: nothing",
+        input: "",
+        expectedOutput: "",
+        recipeConfig: [
+            {
+                op: "Caret/M-decode",
+                args: [],
+            },
+        ],
+    },
+    {
+        /*
+         * Tests the full range.
+         * Everything except "^_" (\x5e\x5f) will decode correctly.
+         */
+        name: "Caret/M-decode: Full set",
+        input: "^@^A^B^C^D^E^F^G^H^I^J^K^L^M^N^O^P^Q^R^S^T^U^V^W^X^Y^Z^[^\\^]^^^_ !\"#$%&'()*+,-./0123456789:;<=>?@ABCDEFGHIJKLMNOPQRSTUVWXYZ[\\]^_`abcdefghijklmnopqrstuvwxyz{|}~^?M-^@M-^AM-^BM-^CM-^DM-^EM-^FM-^GM-^HM-^IM-^JM-^KM-^LM-^MM-^NM-^OM-^PM-^QM-^RM-^SM-^TM-^UM-^VM-^WM-^XM-^YM-^ZM-^[M-^\\M-^]M-^^M-^_M- M-!M-\"M-#M-$M-%M-&M-'M-(M-)M-*M-+M-,M--M-.M-/M-0M-1M-2M-3M-4M-5M-6M-7M-8M-9M-:M-;M-<M-=M->M-?M-@M-AM-BM-CM-DM-EM-FM-GM-HM-IM-JM-KM-LM-MM-NM-OM-PM-QM-RM-SM-TM-UM-VM-WM-XM-YM-ZM-[M-\\M-]M-^M-_M-`M-aM-bM-cM-dM-eM-fM-gM-hM-iM-jM-kM-lM-mM-nM-oM-pM-qM-rM-sM-tM-uM-vM-wM-xM-yM-zM-{M-|M-}M-~M-^?",
+        expectedOutput: "\x00\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f\x20\x21\x22\x23\x24\x25\x26\x27\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f\x30\x31\x32\x33\x34\x35\x36\x37\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f\x40\x41\x42\x43\x44\x45\x46\x47\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f\x50\x51\x52\x53\x54\x55\x56\x57\x58\x59\x5a\x5b\x5c\x5d\x1f\x60\x61\x62\x63\x64\x65\x66\x67\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f\x70\x71\x72\x73\x74\x75\x76\x77\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\x8d\x2d\x5f\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff",
+        recipeConfig: [
+            {
+                op: "Caret/M-decode",
+                args: [],
+            },
+        ],
+    },
+]);
+

tests/operations/tests/RAKE.mjs

@@ -0,0 +1,22 @@
+/**
+ * RAKE, Rapid Automatic Keyword Extraction tests.
+ * 
+ * @author sw5678
+ * @copyright Crown Copyright 2024
+ * @license Apache-2.0
+ */
+import TestRegister from "../../lib/TestRegister.mjs";
+
+TestRegister.addTests([
+    {
+        "name": "RAKE: Basic Example",
+        "input": "test1 test2. test2",
+        "expectedOutput": "Scores: , Keywords: \n3.5, test1 test2\n1.5, test2",
+        "recipeConfig": [
+            {
+                "op": "RAKE",
+                "args": ["\\s", "\\.\\s|\\n", "i,me,my,myself,we,our"]
+            },
+        ],
+    }
+]);

tests/operations/tests/StrUtils.mjs

@@ -11,7 +11,7 @@ TestRegister.addTests([
     {
         name: "Diff, basic usage",
         input: "testing23\n\ntesting123",
-        expectedOutput: "testing<span class='hl5'>1</span>23",
+        expectedOutput: "testing<ins>1</ins>23",
         recipeConfig: [
             {
                 "op": "Diff",
@@ -22,7 +22,7 @@ TestRegister.addTests([
     {
         name: "Diff added with subtraction, basic usage",
         input: "testing23\n\ntesting123",
-        expectedOutput: "<span class='hl5'>1</span>",
+        expectedOutput: "<ins>1</ins>",
         recipeConfig: [
             {
                 "op": "Diff",
@@ -33,7 +33,7 @@ TestRegister.addTests([
     {
         name: "Diff removed with subtraction, basic usage",
         input: "testing123\n\ntesting3",
-        expectedOutput: "<span class='hl3'>12</span>",
+        expectedOutput: "<del>12</del>",
         recipeConfig: [
             {
                 "op": "Diff",