Index more text file types from Desktop, Github (#692)

### Index more text file types 
- Index all text, code files in Github repos. Not just md, org files
- Send more text file types from Desktop app and improve indexing them
- Identify file type by content & allow server to index all text files

### Deprecate Github Indexing Features
- Stop indexing commits, issues and issue comments in a Github repo
- Skip indexing Github repo on hitting Github API rate limit

### Fixes and Improvements
- **Fix indexing files in sub-folders from Desktop app**
- Standardize structure of text to entries to match other entry processors

pyproject.toml

@@ -46,6 +46,7 @@ dependencies = [
     "openai >= 1.0.0",
     "tiktoken >= 0.3.2",
     "tenacity >= 8.2.2",
+    "magika ~= 0.5.1",
     "pillow ~= 9.5.0",
     "pydantic >= 2.0.0",
     "pyyaml ~= 6.0",

src/interface/desktop/main.js

@@ -1,4 +1,5 @@
 const { app, BrowserWindow, ipcMain, Tray, Menu, nativeImage, shell } = require('electron');
+const Magika = require('magika').MagikaNode;
 const todesktop = require("@todesktop/runtime");
 const khojPackage = require('./package.json');
 
@@ -14,8 +15,8 @@ const KHOJ_URL = 'https://app.khoj.dev';
 
 const Store = require('electron-store');
 
-const validFileTypes = ['org', 'md', 'markdown', 'txt', 'html', 'xml', 'pdf']
-
+const magika = new Magika();
+let validFileTypes;
 const binaryFileTypes = ['pdf', 'png', 'jpg', 'jpeg']
 
 const schema = {
@@ -67,6 +68,7 @@ const schema = {
     }
 };
 
+let isMagikaLoaded = false;
 let syncing = false;
 let state = {}
 const store = new Store({ schema });
@@ -111,22 +113,39 @@ function filenameToMimeType (filename) {
     }
 }
 
-function processDirectory(filesToPush, folder) {
-    const files = fs.readdirSync(folder.path, { withFileTypes: true, recursive: true });
+async function isPlainTextFile(filePath) {
+    if (!isMagikaLoaded) {
+        await magika.load();
+        isMagikaLoaded = true;
+    }
+    try {
+        const fileContent = fs.readFileSync(filePath);
+        const fileType = await magika.identifyBytes(fileContent);
+        const fileLabel = magika.config.labels.filter(l => l.name == fileType.label)?.[0]
+        return fileLabel?.is_text
+    } catch (err) {
+        console.error("Failed to identify file type: ", err);
+        return false;
+    }
+}
+
+async function processDirectory(filesToPush, folder) {
+    const files = fs.readdirSync(folder.path, { withFileTypes: true });
 
     for (const file of files) {
-        if (file.isFile() && validFileTypes.includes(file.name.split('.').pop())) {
-            console.log(`Add ${file.name} in ${folder.path} for indexing`);
-            filesToPush.push(path.join(folder.path, file.name));
+        const filePath = path.join(file.path, file.name || '');
+        if (file.isFile() && await isPlainTextFile(filePath)) {
+            console.log(`Add ${file.name} in ${file.path} for indexing`);
+            filesToPush.push(filePath);
         }
 
         if (file.isDirectory()) {
-            processDirectory(filesToPush, {'path': path.join(folder.path, file.name)});
+            await processDirectory(filesToPush, {'path': filePath});
         }
     }
 }
 
-function pushDataToKhoj (regenerate = false) {
+async function pushDataToKhoj (regenerate = false) {
     // Don't sync if token or hostURL is not set or if already syncing
     if (store.get('khojToken') === '' || store.get('hostURL') === '' || syncing === true) {
         const win = BrowserWindow.getAllWindows()[0];
@@ -148,7 +167,7 @@ function pushDataToKhoj (regenerate = false) {
 
     // Collect paths of all indexable files in configured folders
     for (const folder of folders) {
-        processDirectory(filesToPush, folder);
+        await processDirectory(filesToPush, folder);
     }
 
     const lastSync = store.get('lastSync') || [];
@@ -222,6 +241,7 @@ function pushDataToKhoj (regenerate = false) {
         } else if (error?.code === 'ECONNREFUSED') {
             state["error"] = `Could not connect to Khoj server. Ensure you can connect to it at ${error.address}:${error.port}.`;
         } else {
+            currentTime = new Date();
             state["error"] = `Sync was unsuccessful at ${currentTime.toLocaleTimeString()}. Contact team@khoj.dev to report this issue.`;
         }
     })
@@ -238,6 +258,15 @@ function pushDataToKhoj (regenerate = false) {
 pushDataToKhoj();
 
 async function handleFileOpen (type) {
+    if (!isMagikaLoaded) {
+        await magika.load();
+        isMagikaLoaded = true;
+        validFileTypes = [
+            "org", "md", "pdf",
+            // all text file extensions known to Magika
+            ...magika.config.labels.filter(l => l.is_text == true).map(l => l.name)];
+    }
+
     let { canceled, filePaths } = {canceled: true, filePaths: []};
     if (type === 'file') {
         ({ canceled, filePaths } = await dialog.showOpenDialog({properties: ['openFile' ], filters: [{ name: "Valid Khoj Files", extensions: validFileTypes }] }));
@@ -331,7 +360,7 @@ async function removeFolder (event, folderPath) {
 
 async function syncData (regenerate = false) {
     try {
-        pushDataToKhoj(regenerate);
+        await pushDataToKhoj(regenerate);
         const date = new Date();
         console.log('Pushing data to Khoj at: ', date);
     } catch (err) {
@@ -343,7 +372,7 @@ async function deleteAllFiles () {
     try {
         store.set('files', []);
         store.set('folders', []);
-        pushDataToKhoj(true);
+        await pushDataToKhoj(true);
         const date = new Date();
         console.log('Pushing data to Khoj at: ', date);
     } catch (err) {
@@ -379,9 +408,9 @@ const createWindow = (tab = 'chat.html') => {
       }
     })
 
-    const job = new cron('0 */10 * * * *', function() {
+    const job = new cron('0 */10 * * * *', async function() {
         try {
-            pushDataToKhoj();
+            await pushDataToKhoj();
             const date = new Date();
             console.log('Pushing data to Khoj at: ', date);
             win.webContents.send('update-state', state);
@@ -501,11 +530,11 @@ app.whenReady().then(() => {
         try {
             const result = await todesktop.autoUpdater.checkForUpdates();
             if (result.updateInfo) {
-              console.log("Update found:", result.updateInfo.version);
+              console.log("Desktop app update found:", result.updateInfo.version);
               todesktop.autoUpdater.restartAndInstall();
             }
           } catch (e) {
-            console.log("Update check failed:", e);
+            console.warn("Desktop app update check failed:", e);
         }
     })
 

src/interface/desktop/package.json

@@ -20,6 +20,6 @@
     "axios": "^1.6.4",
     "cron": "^2.4.3",
     "electron-store": "^8.1.0",
-    "fs": "^0.0.1-security"
+    "magika": "^0.2.13"
   }
 }

src/interface/desktop/yarn.lock

@@ -17,6 +17,21 @@
   optionalDependencies:
     global-agent "^3.0.0"
 
+"@mapbox/node-pre-gyp@1.0.9":
+  version "1.0.9"
+  resolved "https://registry.yarnpkg.com/@mapbox/node-pre-gyp/-/node-pre-gyp-1.0.9.tgz#09a8781a3a036151cdebbe8719d6f8b25d4058bc"
+  integrity sha512-aDF3S3rK9Q2gey/WAttUlISduDItz5BU3306M9Eyv6/oS40aMprnopshtlKTykxRNIBEZuRMaZAnbrQ4QtKGyw==
+  dependencies:
+    detect-libc "^2.0.0"
+    https-proxy-agent "^5.0.0"
+    make-dir "^3.1.0"
+    node-fetch "^2.6.7"
+    nopt "^5.0.0"
+    npmlog "^5.0.1"
+    rimraf "^3.0.2"
+    semver "^7.3.5"
+    tar "^6.1.11"
+
 "@nodelib/fs.scandir@2.1.5":
   version "2.1.5"
   resolved "https://registry.yarnpkg.com/@nodelib/fs.scandir/-/fs.scandir-2.1.5.tgz#7619c2eb21b25483f6d167548b4cfd5a7488c3d5"
@@ -50,6 +65,87 @@
   dependencies:
     defer-to-connect "^2.0.0"
 
+"@tensorflow/tfjs-backend-cpu@4.17.0":
+  version "4.17.0"
+  resolved "https://registry.yarnpkg.com/@tensorflow/tfjs-backend-cpu/-/tfjs-backend-cpu-4.17.0.tgz#b0c495de686cf700f2ae1f6d8bc2eb6f1964d250"
+  integrity sha512-2VSCHnX9qhYTjw9HiVwTBSnRVlntKXeBlK7aSVsmZfHGwWE2faErTtO7bWmqNqw0U7gyznJbVAjlow/p+0RNGw==
+  dependencies:
+    "@types/seedrandom" "^2.4.28"
+    seedrandom "^3.0.5"
+
+"@tensorflow/tfjs-backend-webgl@4.17.0":
+  version "4.17.0"
+  resolved "https://registry.yarnpkg.com/@tensorflow/tfjs-backend-webgl/-/tfjs-backend-webgl-4.17.0.tgz#7d540a92343582d37d2cdf9509060598a19cd17a"
+  integrity sha512-CC5GsGECCd7eYAUaKq0XJ48FjEZdgXZWPxgUYx4djvfUx5fQPp35hCSP9w/k463jllBMbjl2tKRg8u7Ia/LYzg==
+  dependencies:
+    "@tensorflow/tfjs-backend-cpu" "4.17.0"
+    "@types/offscreencanvas" "~2019.3.0"
+    "@types/seedrandom" "^2.4.28"
+    seedrandom "^3.0.5"
+
+"@tensorflow/tfjs-converter@4.17.0":
+  version "4.17.0"
+  resolved "https://registry.yarnpkg.com/@tensorflow/tfjs-converter/-/tfjs-converter-4.17.0.tgz#f4407bd53d5e300b05ed0b0f068506bc50c956b0"
+  integrity sha512-qFxIjPfomCuTrYxsFjtKbi3QfdmTTCWo+RvqD64oCMS0sjp7sUDNhJyKDoLx6LZhXlwXpHIVDJctLMRMwet0Zw==
+
+"@tensorflow/tfjs-core@4.17.0":
+  version "4.17.0"
+  resolved "https://registry.yarnpkg.com/@tensorflow/tfjs-core/-/tfjs-core-4.17.0.tgz#1ea128555a4d197aed417d70461fcbc7eaec635f"
+  integrity sha512-v9Q5430EnRpyhWNd9LVgXadciKvxLiq+sTrLKRowh26BHyAsams4tZIgX3lFKjB7b90p+FYifVMcqLTTHgjGpQ==
+  dependencies:
+    "@types/long" "^4.0.1"
+    "@types/offscreencanvas" "~2019.7.0"
+    "@types/seedrandom" "^2.4.28"
+    "@webgpu/types" "0.1.38"
+    long "4.0.0"
+    node-fetch "~2.6.1"
+    seedrandom "^3.0.5"
+
+"@tensorflow/tfjs-data@4.17.0":
+  version "4.17.0"
+  resolved "https://registry.yarnpkg.com/@tensorflow/tfjs-data/-/tfjs-data-4.17.0.tgz#612c095576724f1dbec9488373e9ed6027282a05"
+  integrity sha512-aPKrDFip+gXicWOFALeNT7KKQjRXFkHd/hNe/zs4mCFcIN00hy1PkZ6xkYsgrsdLDQMBSGeS4B4ZM0k5Cs88QA==
+  dependencies:
+    "@types/node-fetch" "^2.1.2"
+    node-fetch "~2.6.1"
+    string_decoder "^1.3.0"
+
+"@tensorflow/tfjs-layers@4.17.0":
+  version "4.17.0"
+  resolved "https://registry.yarnpkg.com/@tensorflow/tfjs-layers/-/tfjs-layers-4.17.0.tgz#c789f4285f358b192675790365bdd491b490501e"
+  integrity sha512-DEE0zRKvf3LJ0EcvG5XouJYOgFGWYAneZ0K1d23969z7LfSyqVmBdLC6BTwdLKuJk3ouUJIKXU1TcpFmjDuh7g==
+
+"@tensorflow/tfjs-node@^4.17.0":
+  version "4.17.0"
+  resolved "https://registry.yarnpkg.com/@tensorflow/tfjs-node/-/tfjs-node-4.17.0.tgz#d35cc1466cc58a5a12d27e6fed4b730d8b0a982d"
+  integrity sha512-lRe5XPwLzVgpLoxgKWWlqCX9uYybklMai3npgVcvniLQnd6JjkGx+RY2D+7jyQmdo1zJUACfxw3conP88OcBug==
+  dependencies:
+    "@mapbox/node-pre-gyp" "1.0.9"
+    "@tensorflow/tfjs" "4.17.0"
+    adm-zip "^0.5.2"
+    google-protobuf "^3.9.2"
+    https-proxy-agent "^2.2.1"
+    progress "^2.0.0"
+    rimraf "^2.6.2"
+    tar "^4.4.6"
+
+"@tensorflow/tfjs@4.17.0", "@tensorflow/tfjs@^4.17.0":
+  version "4.17.0"
+  resolved "https://registry.yarnpkg.com/@tensorflow/tfjs/-/tfjs-4.17.0.tgz#895fed25872a572cb1ec4ddee91586c2590c4019"
+  integrity sha512-yXRBhpM3frlNA/YaPp6HNk9EfIi8han5RYeQA3R8OCa0Od+AfoG1PUmlxV8fE2wCorlGVyHsgpiJ6M9YZPB56w==
+  dependencies:
+    "@tensorflow/tfjs-backend-cpu" "4.17.0"
+    "@tensorflow/tfjs-backend-webgl" "4.17.0"
+    "@tensorflow/tfjs-converter" "4.17.0"
+    "@tensorflow/tfjs-core" "4.17.0"
+    "@tensorflow/tfjs-data" "4.17.0"
+    "@tensorflow/tfjs-layers" "4.17.0"
+    argparse "^1.0.10"
+    chalk "^4.1.0"
+    core-js "3.29.1"
+    regenerator-runtime "^0.13.5"
+    yargs "^16.0.3"
+
 "@todesktop/runtime@^1.3.0":
   version "1.3.0"
   resolved "https://registry.yarnpkg.com/@todesktop/runtime/-/runtime-1.3.0.tgz#7baa64fd5c2e4daa591bda96270a0e39947ec3c7"
@@ -84,11 +180,24 @@
   dependencies:
     "@types/node" "*"
 
+"@types/long@^4.0.1":
+  version "4.0.2"
+  resolved "https://registry.yarnpkg.com/@types/long/-/long-4.0.2.tgz#b74129719fc8d11c01868010082d483b7545591a"
+  integrity sha512-MqTGEo5bj5t157U6fA/BiDynNkn0YknVdh48CMPkTSpFTVmvao5UQmm7uEF6xBEo7qIMAlY/JSleYaE6VOdpaA==
+
 "@types/luxon@~3.3.0":
   version "3.3.1"
   resolved "https://registry.yarnpkg.com/@types/luxon/-/luxon-3.3.1.tgz#08727da7d81ee6a6c702b9dc6c8f86be010eb4dc"
   integrity sha512-XOS5nBcgEeP2PpcqJHjCWhUCAzGfXIU8ILOSLpx2FhxqMW9KdxgCGXNOEKGVBfveKtIpztHzKK5vSRVLyW/NqA==
 
+"@types/node-fetch@^2.1.2":
+  version "2.6.11"
+  resolved "https://registry.yarnpkg.com/@types/node-fetch/-/node-fetch-2.6.11.tgz#9b39b78665dae0e82a08f02f4967d62c66f95d24"
+  integrity sha512-24xFj9R5+rfQJLRyM56qh+wnVSYhyXC2tkoBndtY0U+vubqNsYXGjufB2nn8Q6gt0LrARwL6UBtMCSVCwl4B1g==
+  dependencies:
+    "@types/node" "*"
+    form-data "^4.0.0"
+
 "@types/node@*":
   version "20.5.7"
   resolved "https://registry.yarnpkg.com/@types/node/-/node-20.5.7.tgz#4b8ecac87fbefbc92f431d09c30e176fc0a7c377"
@@ -99,6 +208,16 @@
   resolved "https://registry.yarnpkg.com/@types/node/-/node-18.17.12.tgz#c6bd7413a13e6ad9cfb7e97dd5c4e904c1821e50"
   integrity sha512-d6xjC9fJ/nSnfDeU0AMDsaJyb1iHsqCSOdi84w4u+SlN/UgQdY5tRhpMzaFYsI4mnpvgTivEaQd0yOUhAtOnEQ==
 
+"@types/offscreencanvas@~2019.3.0":
+  version "2019.3.0"
+  resolved "https://registry.yarnpkg.com/@types/offscreencanvas/-/offscreencanvas-2019.3.0.tgz#3336428ec7e9180cf4566dfea5da04eb586a6553"
+  integrity sha512-esIJx9bQg+QYF0ra8GnvfianIY8qWB0GBx54PK5Eps6m+xTj86KLavHv6qDhzKcu5UUOgNfJ2pWaIIV7TRUd9Q==
+
+"@types/offscreencanvas@~2019.7.0":
+  version "2019.7.3"
+  resolved "https://registry.yarnpkg.com/@types/offscreencanvas/-/offscreencanvas-2019.7.3.tgz#90267db13f64d6e9ccb5ae3eac92786a7c77a516"
+  integrity sha512-ieXiYmgSRXUDeOntE1InxjWyvEelZGP63M+cGuquuRLuIKKT1osnkXjxev9B7d1nXSug5vpunx+gNlbVxMlC9A==
+
 "@types/responselike@^1.0.0":
   version "1.0.0"
   resolved "https://registry.yarnpkg.com/@types/responselike/-/responselike-1.0.0.tgz#251f4fe7d154d2bad125abe1b429b23afd262e29"
@@ -106,6 +225,11 @@
   dependencies:
     "@types/node" "*"
 
+"@types/seedrandom@^2.4.28":
+  version "2.4.34"
+  resolved "https://registry.yarnpkg.com/@types/seedrandom/-/seedrandom-2.4.34.tgz#c725cd0fc0442e2d3d0e5913af005686ffb7eb99"
+  integrity sha512-ytDiArvrn/3Xk6/vtylys5tlY6eo7Ane0hvcx++TKo6RxQXuVfW0AF/oeWqAj9dN29SyhtawuXstgmPlwNcv/A==
+
 "@types/semver@^7.3.6":
   version "7.5.1"
   resolved "https://registry.yarnpkg.com/@types/semver/-/semver-7.5.1.tgz#0480eeb7221eb9bc398ad7432c9d7e14b1a5a367"
@@ -118,6 +242,35 @@
   dependencies:
     "@types/node" "*"
 
+"@webgpu/types@0.1.38":
+  version "0.1.38"
+  resolved "https://registry.yarnpkg.com/@webgpu/types/-/types-0.1.38.tgz#6fda4b410edc753d3213c648320ebcf319669020"
+  integrity sha512-7LrhVKz2PRh+DD7+S+PVaFd5HxaWQvoMqBbsV9fNJO1pjUs1P8bM2vQVNfk+3URTqbuTI7gkXi0rfsN0IadoBA==
+
+abbrev@1:
+  version "1.1.1"
+  resolved "https://registry.yarnpkg.com/abbrev/-/abbrev-1.1.1.tgz#f8f2c887ad10bf67f634f005b6987fed3179aac8"
+  integrity sha512-nne9/IiQ/hzIhY6pdDnbBtz7DjPTKrY00P/zvPSm5pOFkl6xuGrGnXn/VtTNNfNtAfZ9/1RtehkszU9qcTii0Q==
+
+adm-zip@^0.5.2:
+  version "0.5.12"
+  resolved "https://registry.yarnpkg.com/adm-zip/-/adm-zip-0.5.12.tgz#87786328e91d54b37358d8a50f954c4cd73ba60b"
+  integrity sha512-6TVU49mK6KZb4qG6xWaaM4C7sA/sgUMLy/JYMOzkcp3BvVLpW0fXDFQiIzAuxFCt/2+xD7fNIiPFAoLZPhVNLQ==
+
+agent-base@6:
+  version "6.0.2"
+  resolved "https://registry.yarnpkg.com/agent-base/-/agent-base-6.0.2.tgz#49fff58577cfee3f37176feab4c22e00f86d7f77"
+  integrity sha512-RZNwNclF7+MS/8bDg70amg32dyeZGZxiDuQmZxKLAlQjr3jGyLx+4Kkk58UO7D2QdgFIQCovuSuZESne6RG6XQ==
+  dependencies:
+    debug "4"
+
+agent-base@^4.3.0:
+  version "4.3.0"
+  resolved "https://registry.yarnpkg.com/agent-base/-/agent-base-4.3.0.tgz#8165f01c436009bccad0b1d122f05ed770efc6ee"
+  integrity sha512-salcGninV0nPrwpGNn4VTXBb1SOuXQBiqbrNXoeizJsHrsL6ERFM2Ne3JUSBWRE6aeNJI2ROP/WEEIDUiDe3cg==
+  dependencies:
+    es6-promisify "^5.0.0"
+
 aggregate-error@^3.0.0:
   version "3.1.0"
   resolved "https://registry.yarnpkg.com/aggregate-error/-/aggregate-error-3.1.0.tgz#92670ff50f5359bdb7a3e0d40d0ec30c5737687a"
@@ -143,6 +296,38 @@ ajv@^8.0.0, ajv@^8.6.3:
     require-from-string "^2.0.2"
     uri-js "^4.2.2"
 
+ansi-regex@^5.0.1:
+  version "5.0.1"
+  resolved "https://registry.yarnpkg.com/ansi-regex/-/ansi-regex-5.0.1.tgz#082cb2c89c9fe8659a311a53bd6a4dc5301db304"
+  integrity sha512-quJQXlTSUGL2LH9SUXo8VwsY4soanhgo6LNSm84E1LBcE8s3O0wpdiRzyR9z/ZZJMlMWv37qOOb9pdJlMUEKFQ==
+
+ansi-styles@^4.0.0, ansi-styles@^4.1.0:
+  version "4.3.0"
+  resolved "https://registry.yarnpkg.com/ansi-styles/-/ansi-styles-4.3.0.tgz#edd803628ae71c04c85ae7a0906edad34b648937"
+  integrity sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg==
+  dependencies:
+    color-convert "^2.0.1"
+
+"aproba@^1.0.3 || ^2.0.0":
+  version "2.0.0"
+  resolved "https://registry.yarnpkg.com/aproba/-/aproba-2.0.0.tgz#52520b8ae5b569215b354efc0caa3fe1e45a8adc"
+  integrity sha512-lYe4Gx7QT+MKGbDsA+Z+he/Wtef0BiwDOlK/XkBrdfsh9J/jPPXbX0tE9x9cl27Tmu5gg3QUbUrQYa/y+KOHPQ==
+
+are-we-there-yet@^2.0.0:
+  version "2.0.0"
+  resolved "https://registry.yarnpkg.com/are-we-there-yet/-/are-we-there-yet-2.0.0.tgz#372e0e7bd279d8e94c653aaa1f67200884bf3e1c"
+  integrity sha512-Ci/qENmwHnsYo9xKIcUJN5LeDKdJ6R1Z1j9V/J5wyq8nh/mYPEpIKJbBZXtZjG04HiK7zV/p6Vs9952MrMeUIw==
+  dependencies:
+    delegates "^1.0.0"
+    readable-stream "^3.6.0"
+
+argparse@^1.0.10:
+  version "1.0.10"
+  resolved "https://registry.yarnpkg.com/argparse/-/argparse-1.0.10.tgz#bcd6791ea5ae09725e17e5ad988134cd40b3d911"
+  integrity sha512-o5Roy6tNG4SL/FOkCAN6RzjiakZS25RLYFrcMttJqbdd8BWrnA+fGz57iN5Pb06pvBGvl5gQ0B48dJlslXvoTg==
+  dependencies:
+    sprintf-js "~1.0.2"
+
 argparse@^2.0.1:
   version "2.0.1"
   resolved "https://registry.yarnpkg.com/argparse/-/argparse-2.0.1.tgz#246f50f3ca78a3240f6c997e8a9bd1eac49e4b38"
@@ -228,11 +413,43 @@ cacheable-request@^7.0.2:
     normalize-url "^6.0.1"
     responselike "^2.0.0"
 
+chalk@^4.1.0:
+  version "4.1.2"
+  resolved "https://registry.yarnpkg.com/chalk/-/chalk-4.1.2.tgz#aac4e2b7734a740867aeb16bf02aad556a1e7a01"
+  integrity sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA==
+  dependencies:
+    ansi-styles "^4.1.0"
+    supports-color "^7.1.0"
+
+chalk@^5.3.0:
+  version "5.3.0"
+  resolved "https://registry.yarnpkg.com/chalk/-/chalk-5.3.0.tgz#67c20a7ebef70e7f3970a01f90fa210cb6860385"
+  integrity sha512-dLitG79d+GV1Nb/VYcCDFivJeK1hiukt9QjRNVOsUtTy1rR1YJsmpGGTZ3qJos+uw7WmWF4wUwBd9jxjocFC2w==
+
+chownr@^1.1.4:
+  version "1.1.4"
+  resolved "https://registry.yarnpkg.com/chownr/-/chownr-1.1.4.tgz#6fc9d7b42d32a583596337666e7d08084da2cc6b"
+  integrity sha512-jJ0bqzaylmJtVnNgzTeSOs8DPavpbYgEr/b0YL8/2GO3xJEhInFmhKMUnEJQjZumK7KXGFhUy89PrsJWlakBVg==
+
+chownr@^2.0.0:
+  version "2.0.0"
+  resolved "https://registry.yarnpkg.com/chownr/-/chownr-2.0.0.tgz#15bfbe53d2eab4cf70f18a8cd68ebe5b3cb1dece"
+  integrity sha512-bIomtDF5KGpdogkLd9VspvFzk9KfpyyGlS8YFVZl7TGPBHL5snIOnxeshwVgPteQ9b4Eydl+pVbIyE1DcvCWgQ==
+
 clean-stack@^2.0.0:
   version "2.2.0"
   resolved "https://registry.yarnpkg.com/clean-stack/-/clean-stack-2.2.0.tgz#ee8472dbb129e727b31e8a10a427dee9dfe4008b"
   integrity sha512-4diC9HaTE+KRAMWhDhrGOECgWZxoevMc5TlkObMqNSsVU62PYzXZ/SMTjzyGAFF1YusgxGcSWTEXBhp0CPwQ1A==
 
+cliui@^7.0.2:
+  version "7.0.4"
+  resolved "https://registry.yarnpkg.com/cliui/-/cliui-7.0.4.tgz#a0265ee655476fc807aea9df3df8df7783808b4f"
+  integrity sha512-OcRE68cOsVMXp1Yvonl/fzkQOyjLSu/8bhPDfQt0e0/Eb283TKP20Fs2MqoPsr9SwA595rRCA+QMzYc9nBP+JQ==
+  dependencies:
+    string-width "^4.2.0"
+    strip-ansi "^6.0.0"
+    wrap-ansi "^7.0.0"
+
 clone-response@^1.0.2:
   version "1.0.3"
   resolved "https://registry.yarnpkg.com/clone-response/-/clone-response-1.0.3.tgz#af2032aa47816399cf5f0a1d0db902f517abb8c3"
@@ -240,6 +457,23 @@ clone-response@^1.0.2:
   dependencies:
     mimic-response "^1.0.0"
 
+color-convert@^2.0.1:
+  version "2.0.1"
+  resolved "https://registry.yarnpkg.com/color-convert/-/color-convert-2.0.1.tgz#72d3a68d598c9bdb3af2ad1e84f21d896abd4de3"
+  integrity sha512-RRECPsj7iu/xb5oKYcsFHSppFNnsj/52OVTRKb4zP5onXwVF3zVmmToNcOfGC+CRDpfK/U584fMg38ZHCaElKQ==
+  dependencies:
+    color-name "~1.1.4"
+
+color-name@~1.1.4:
+  version "1.1.4"
+  resolved "https://registry.yarnpkg.com/color-name/-/color-name-1.1.4.tgz#c2a09a87acbde69543de6f63fa3995c826c536a2"
+  integrity sha512-dOy+3AuW3a2wNbZHIuMZpTcgjGuLU/uBL/ubcZF9OXbDo8ff4O8yVp5Bf0efS8uEoYo5q4Fx7dY9OgQGXgAsQA==
+
+color-support@^1.1.2:
+  version "1.1.3"
+  resolved "https://registry.yarnpkg.com/color-support/-/color-support-1.1.3.tgz#93834379a1cc9a0c61f82f52f0d04322251bd5a2"
+  integrity sha512-qiBjkpbMLO/HL68y+lh4q0/O1MZFj2RX6X/KmMa3+gJD3z+WwI1ZzDHysvqHGS3mP6mznPckpXmw1nI9cJjyRg==
+
 combined-stream@^1.0.8:
   version "1.0.8"
   resolved "https://registry.yarnpkg.com/combined-stream/-/combined-stream-1.0.8.tgz#c3d45a8b34fd730631a110a8a2520682b31d5a7f"
@@ -247,6 +481,11 @@ combined-stream@^1.0.8:
   dependencies:
     delayed-stream "~1.0.0"
 
+commander@^12.0.0:
+  version "12.0.0"
+  resolved "https://registry.yarnpkg.com/commander/-/commander-12.0.0.tgz#b929db6df8546080adfd004ab215ed48cf6f2592"
+  integrity sha512-MwVNWlYjDTtOjX5PiD7o5pK0UrFU/OYgcJfjjK4RaHZETNtjJqrZa9Y9ds88+A+f+d5lv+561eZ+yCKoS3gbAA==
+
 concat-map@0.0.1:
   version "0.0.1"
   resolved "https://registry.yarnpkg.com/concat-map/-/concat-map-0.0.1.tgz#d8a96bd77fd68df7793a73036a3ba0d5405d477b"
@@ -268,6 +507,16 @@ conf@^10.2.0:
     pkg-up "^3.1.0"
     semver "^7.3.5"
 
+console-control-strings@^1.0.0, console-control-strings@^1.1.0:
+  version "1.1.0"
+  resolved "https://registry.yarnpkg.com/console-control-strings/-/console-control-strings-1.1.0.tgz#3d7cf4464db6446ea644bf4b39507f9851008e8e"
+  integrity sha512-ty/fTekppD2fIwRvnZAVdeOiGd1c7YXEixbgJTNzqcxJWKQnjJ/V1bNEEE6hygpM3WjwHFUVK6HTjWSzV4a8sQ==
+
+core-js@3.29.1:
+  version "3.29.1"
+  resolved "https://registry.yarnpkg.com/core-js/-/core-js-3.29.1.tgz#40ff3b41588b091aaed19ca1aa5cb111803fa9a6"
+  integrity sha512-+jwgnhg6cQxKYIIjGtAHq2nwUOolo9eoFZ4sHfUH09BLXBgxnH4gA0zEd+t+BO2cNB8idaBtZFcFTRjQJRJmAw==
+
 cron@^2.4.3:
   version "2.4.3"
   resolved "https://registry.yarnpkg.com/cron/-/cron-2.4.3.tgz#4e43d8d9a6373b8f28d876c4e9a47c14422d8652"
@@ -292,13 +541,20 @@ debounce-fn@^4.0.0:
   dependencies:
     mimic-fn "^3.0.0"
 
-debug@^4.1.0, debug@^4.1.1, debug@^4.3.2:
+debug@4, debug@^4.1.0, debug@^4.1.1, debug@^4.3.2:
   version "4.3.4"
   resolved "https://registry.yarnpkg.com/debug/-/debug-4.3.4.tgz#1319f6579357f2338d3337d2cdd4914bb5dcc865"
   integrity sha512-PRWFHuSU3eDtQJPvnNY7Jcket1j0t5OuOsFzPPzsekD52Zl8qUfFIPEiswXqIvHWGVHOgX+7G/vCNNhehwxfkQ==
   dependencies:
     ms "2.1.2"
 
+debug@^3.1.0:
+  version "3.2.7"
+  resolved "https://registry.yarnpkg.com/debug/-/debug-3.2.7.tgz#72580b7e9145fb39b6676f9c5e5fb100b934179a"
+  integrity sha512-CFjzYYAi4ThfiQvizrFQevTTXHtnCqWfe7x1AhgEscTz6ZbLbfoLRLPugTQyBth6f8ZERVUSyWHFD/7Wu4t1XQ==
+  dependencies:
+    ms "^2.1.1"
+
 decompress-response@^6.0.0:
   version "6.0.0"
   resolved "https://registry.yarnpkg.com/decompress-response/-/decompress-response-6.0.0.tgz#ca387612ddb7e104bd16d85aab00d5ecf09c66fc"
@@ -338,6 +594,16 @@ delayed-stream@~1.0.0:
   resolved "https://registry.yarnpkg.com/delayed-stream/-/delayed-stream-1.0.0.tgz#df3ae199acadfb7d440aaae0b29e2272b24ec619"
   integrity sha512-ZySD7Nf91aLB0RxL4KGrKHBXl7Eds1DAmEdcoVawXnLD7SDhpNgtuII2aAkg7a7QS41jxPSZ17p4VdGnMHk3MQ==
 
+delegates@^1.0.0:
+  version "1.0.0"
+  resolved "https://registry.yarnpkg.com/delegates/-/delegates-1.0.0.tgz#84c6e159b81904fdca59a0ef44cd870d31250f9a"
+  integrity sha512-bd2L678uiWATM6m5Z1VzNCErI3jiGzt6HGY8OVICs40JQq/HALfbyNJmp0UDakEY4pMMaN0Ly5om/B1VI/+xfQ==
+
+detect-libc@^2.0.0:
+  version "2.0.3"
+  resolved "https://registry.yarnpkg.com/detect-libc/-/detect-libc-2.0.3.tgz#f0cd503b40f9939b894697d19ad50895e30cf700"
+  integrity sha512-bwy0MGW55bG41VqxxypOsdSdGqLwXPI/focwgTYCFMbdUiBAxLg9CFzG08sz2aqzknwiX7Hkl0bQENjg8iLByw==
+
 detect-node@^2.0.4:
   version "2.1.0"
   resolved "https://registry.yarnpkg.com/detect-node/-/detect-node-2.1.0.tgz#c9c70775a49c3d03bc2c06d9a73be550f978f8b1"
@@ -388,6 +654,11 @@ electron@28.2.1:
     "@types/node" "^18.11.18"
     extract-zip "^2.0.1"
 
+emoji-regex@^8.0.0:
+  version "8.0.0"
+  resolved "https://registry.yarnpkg.com/emoji-regex/-/emoji-regex-8.0.0.tgz#e818fd69ce5ccfcb404594f842963bf53164cc37"
+  integrity sha512-MSjYzcWNOA0ewAHpz0MxpYFvwg6yjy1NG3xteoqz644VCo/RPgnr1/GGt+ic3iJTzQ8Eu3TdM14SawnVUmGE6A==
+
 end-of-stream@^1.1.0:
   version "1.4.4"
   resolved "https://registry.yarnpkg.com/end-of-stream/-/end-of-stream-1.4.4.tgz#5ae64a5f45057baf3626ec14da0ca5e4b2431eb0"
@@ -405,6 +676,23 @@ es6-error@^4.1.1:
   resolved "https://registry.yarnpkg.com/es6-error/-/es6-error-4.1.1.tgz#9e3af407459deed47e9a91f9b885a84eb05c561d"
   integrity sha512-Um/+FxMr9CISWh0bi5Zv0iOD+4cFh5qLeks1qhAopKVAJw3drgKbKySikp7wGhDL0HPeaja0P5ULZrxLkniUVg==
 
+es6-promise@^4.0.3:
+  version "4.2.8"
+  resolved "https://registry.yarnpkg.com/es6-promise/-/es6-promise-4.2.8.tgz#4eb21594c972bc40553d276e510539143db53e0a"
+  integrity sha512-HJDGx5daxeIvxdBxvG2cb9g4tEvwIk3i8+nhX0yGrYmZUzbkdg8QbDevheDB8gd0//uPj4c1EQua8Q+MViT0/w==
+
+es6-promisify@^5.0.0:
+  version "5.0.0"
+  resolved "https://registry.yarnpkg.com/es6-promisify/-/es6-promisify-5.0.0.tgz#5109d62f3e56ea967c4b63505aef08291c8a5203"
+  integrity sha512-C+d6UdsYDk0lMebHNR4S2NybQMMngAOnOwYBQjTOiv0MkoJMP0Myw2mgpDLBcpfCmRLxyFqYhS/CfOENq4SJhQ==
+  dependencies:
+    es6-promise "^4.0.3"
+
+escalade@^3.1.1:
+  version "3.1.2"
+  resolved "https://registry.yarnpkg.com/escalade/-/escalade-3.1.2.tgz#54076e9ab29ea5bf3d8f1ed62acffbb88272df27"
+  integrity sha512-ErCHMCae19vR8vQGe50xIsVomy19rg6gFu3+r3jkEO46suLMWBksvVyoGgQV+jOfl84ZSOSlmv6Gxa89PmTGmA==
+
 escape-string-regexp@^4.0.0:
   version "4.0.0"
   resolved "https://registry.yarnpkg.com/escape-string-regexp/-/escape-string-regexp-4.0.0.tgz#14ba83a5d373e3d311e5afca29cf5bfad965bf34"
@@ -517,21 +805,50 @@ fs-extra@^8.1.0:
     jsonfile "^4.0.0"
     universalify "^0.1.0"
 
+fs-minipass@^1.2.7:
+  version "1.2.7"
+  resolved "https://registry.yarnpkg.com/fs-minipass/-/fs-minipass-1.2.7.tgz#ccff8570841e7fe4265693da88936c55aed7f7c7"
+  integrity sha512-GWSSJGFy4e9GUeCcbIkED+bgAoFyj7XF1mV8rma3QW4NIqX9Kyx79N/PF61H5udOV3aY1IaMLs6pGbH71nlCTA==
+  dependencies:
+    minipass "^2.6.0"
+
+fs-minipass@^2.0.0:
+  version "2.1.0"
+  resolved "https://registry.yarnpkg.com/fs-minipass/-/fs-minipass-2.1.0.tgz#7f5036fdbf12c63c169190cbe4199c852271f9fb"
+  integrity sha512-V/JgOLFCS+R6Vcq0slCuaeWEdNC3ouDlJMNIsacH2VtALiu9mV4LPrHc5cDl8k5aw6J8jwgWWpiTo5RYhmIzvg==
+  dependencies:
+    minipass "^3.0.0"
+
 fs.realpath@^1.0.0:
   version "1.0.0"
   resolved "https://registry.yarnpkg.com/fs.realpath/-/fs.realpath-1.0.0.tgz#1504ad2523158caa40db4a2787cb01411994ea4f"
   integrity sha512-OO0pH2lK6a0hZnAdau5ItzHPI6pUlvI7jMVnxUQRtw4owF2wk8lOSabtGDCTP4Ggrg2MbGnWO9X8K1t4+fGMDw==
 
-fs@^0.0.1-security:
-  version "0.0.1-security"
-  resolved "https://registry.yarnpkg.com/fs/-/fs-0.0.1-security.tgz#8a7bd37186b6dddf3813f23858b57ecaaf5e41d4"
-  integrity sha512-3XY9e1pP0CVEUCdj5BmfIZxRBTSDycnbqhIOGec9QYtmVH2fbLpj86CFWkrNOkt/Fvty4KZG5lTglL9j/gJ87w==
-
 function-bind@^1.1.1:
   version "1.1.1"
   resolved "https://registry.yarnpkg.com/function-bind/-/function-bind-1.1.1.tgz#a56899d3ea3c9bab874bb9773b7c5ede92f4895d"
   integrity sha512-yIovAzMX49sF8Yl58fSCWJ5svSLuaibPxXQJFLmBObTuCr0Mf1KiPopGM9NiFjiYBCbfaa2Fh6breQ6ANVTI0A==
 
+gauge@^3.0.0:
+  version "3.0.2"
+  resolved "https://registry.yarnpkg.com/gauge/-/gauge-3.0.2.tgz#03bf4441c044383908bcfa0656ad91803259b395"
+  integrity sha512-+5J6MS/5XksCuXq++uFRsnUd7Ovu1XenbeuIuNRJxYWjgQbPuFhT14lAvsWfqfAmnwluf1OwMjz39HjfLPci0Q==
+  dependencies:
+    aproba "^1.0.3 || ^2.0.0"
+    color-support "^1.1.2"
+    console-control-strings "^1.0.0"
+    has-unicode "^2.0.1"
+    object-assign "^4.1.1"
+    signal-exit "^3.0.0"
+    string-width "^4.2.3"
+    strip-ansi "^6.0.1"
+    wide-align "^1.1.2"
+
+get-caller-file@^2.0.5:
+  version "2.0.5"
+  resolved "https://registry.yarnpkg.com/get-caller-file/-/get-caller-file-2.0.5.tgz#4f94412a82db32f36e3b0b9741f8a97feb031f7e"
+  integrity sha512-DyFP3BM/3YHTQOCUL/w0OZHR0lpKeGrxotcHWcqNEdnltqFwXVfhEBQ94eIo34AfQpo0rGki4cyIiftY06h2Fg==
+
 get-intrinsic@^1.1.1:
   version "1.2.1"
   resolved "https://registry.yarnpkg.com/get-intrinsic/-/get-intrinsic-1.2.1.tgz#d295644fed4505fc9cde952c37ee12b477a83d82"
@@ -604,6 +921,11 @@ globby@^11.0.1:
     merge2 "^1.4.1"
     slash "^3.0.0"
 
+google-protobuf@^3.9.2:
+  version "3.21.2"
+  resolved "https://registry.yarnpkg.com/google-protobuf/-/google-protobuf-3.21.2.tgz#4580a2bea8bbb291ee579d1fefb14d6fa3070ea4"
+  integrity sha512-3MSOYFO5U9mPGikIYCzK0SaThypfGgS6bHqrUGXG3DPHCrb+txNqeEcns1W0lkGfk0rCyNXm7xB9rMxnCiZOoA==
+
 got@^11.8.5:
   version "11.8.6"
   resolved "https://registry.yarnpkg.com/got/-/got-11.8.6.tgz#276e827ead8772eddbcfc97170590b841823233a"
@@ -626,6 +948,11 @@ graceful-fs@^4.1.6, graceful-fs@^4.2.0, graceful-fs@^4.2.4:
   resolved "https://registry.yarnpkg.com/graceful-fs/-/graceful-fs-4.2.11.tgz#4183e4e8bf08bb6e05bbb2f7d2e0c8f712ca40e3"
   integrity sha512-RbJ5/jmFcNNCcDV5o9eTnBLJ/HszWV0P73bc+Ff4nS/rJj+YaS6IGyiOL0VoBYX+l1Wrl3k63h/KrH+nhJ0XvQ==
 
+has-flag@^4.0.0:
+  version "4.0.0"
+  resolved "https://registry.yarnpkg.com/has-flag/-/has-flag-4.0.0.tgz#944771fd9c81c81265c4d6941860da06bb59479b"
+  integrity sha512-EykJT/Q1KjTWctppgIAgfSO0tKVuZUjhgMr17kqTumMl6Afv3EISleU7qZUzoXDFTAHTDC4NOoG/ZxU3EvlMPQ==
+
 has-property-descriptors@^1.0.0:
   version "1.0.0"
   resolved "https://registry.yarnpkg.com/has-property-descriptors/-/has-property-descriptors-1.0.0.tgz#610708600606d36961ed04c196193b6a607fa861"
@@ -643,6 +970,11 @@ has-symbols@^1.0.3:
   resolved "https://registry.yarnpkg.com/has-symbols/-/has-symbols-1.0.3.tgz#bb7b2c4349251dce87b125f7bdf874aa7c8b39f8"
   integrity sha512-l3LCuF6MgDNwTDKkdYGEihYjt5pRPbEg46rtlmnSPlUbgmB8LOIrKJbYYFBSbnPaJexMKtiPO8hmeRjRz2Td+A==
 
+has-unicode@^2.0.1:
+  version "2.0.1"
+  resolved "https://registry.yarnpkg.com/has-unicode/-/has-unicode-2.0.1.tgz#e0e6fe6a28cf51138855e086d1691e771de2a8b9"
+  integrity sha512-8Rf9Y83NBReMnx0gFzA8JImQACstCYWUplepDa9xprwwtmgEZUF0h/i5xSA625zB/I37EtrswSST6OXxwaaIJQ==
+
 has@^1.0.3:
   version "1.0.3"
   resolved "https://registry.yarnpkg.com/has/-/has-1.0.3.tgz#722d7cbfc1f6aa8241f16dd814e011e1f41e8796"
@@ -663,6 +995,22 @@ http2-wrapper@^1.0.0-beta.5.2:
     quick-lru "^5.1.1"
     resolve-alpn "^1.0.0"
 
+https-proxy-agent@^2.2.1:
+  version "2.2.4"
+  resolved "https://registry.yarnpkg.com/https-proxy-agent/-/https-proxy-agent-2.2.4.tgz#4ee7a737abd92678a293d9b34a1af4d0d08c787b"
+  integrity sha512-OmvfoQ53WLjtA9HeYP9RNrWMJzzAz1JGaSFr1nijg0PVR1JaD/xbJq1mdEIIlxGpXp9eSe/O2LgU9DJmTPd0Eg==
+  dependencies:
+    agent-base "^4.3.0"
+    debug "^3.1.0"
+
+https-proxy-agent@^5.0.0:
+  version "5.0.1"
+  resolved "https://registry.yarnpkg.com/https-proxy-agent/-/https-proxy-agent-5.0.1.tgz#c59ef224a04fe8b754f3db0063a25ea30d0005d6"
+  integrity sha512-dFcAjpTQFgoLMzC2VwU+C/CbS7uRL0lWmxDITmqm7C+7F0Odmj6s9l6alZc6AELXhrnggM2CeWSXHGOdX2YtwA==
+  dependencies:
+    agent-base "6"
+    debug "4"
+
 human-signals@^2.1.0:
   version "2.1.0"
   resolved "https://registry.yarnpkg.com/human-signals/-/human-signals-2.1.0.tgz#dc91fcba42e4d06e4abaed33b3e7a3c02f514ea0"
@@ -686,7 +1034,7 @@ inflight@^1.0.4:
     once "^1.3.0"
     wrappy "1"
 
-inherits@2:
+inherits@2, inherits@^2.0.3:
   version "2.0.4"
   resolved "https://registry.yarnpkg.com/inherits/-/inherits-2.0.4.tgz#0fa2c64f932917c3433a0ded55363aae37416b7c"
   integrity sha512-k/vGaX4/Yla3WzyMCvTQOXYeIHvqOKtnqBduzTHpzpQZzAskKMhZ2K+EnBiSM9zGSoIFeMpXKxa4dYeZIQqewQ==
@@ -696,6 +1044,11 @@ is-extglob@^2.1.1:
   resolved "https://registry.yarnpkg.com/is-extglob/-/is-extglob-2.1.1.tgz#a88c02535791f02ed37c76a1b9ea9773c833f8c2"
   integrity sha512-SbKbANkN603Vi4jEZv49LeVJMn4yGwsbzZworEoyEiutsN3nJYdbO36zfhGJ6QEDpOZIFkDtnq5JRxmvl3jsoQ==
 
+is-fullwidth-code-point@^3.0.0:
+  version "3.0.0"
+  resolved "https://registry.yarnpkg.com/is-fullwidth-code-point/-/is-fullwidth-code-point-3.0.0.tgz#f116f8064fe90b3f7844a38997c0b75051269f1d"
+  integrity sha512-zymm5+u+sCsSWyD9qNaejV3DFvhCKclKdizYaJUuHA83RLjb7nSuGnddCHGv0hk+KY7BMAlsWeK4Ueg6EV6XQg==
+
 is-glob@^4.0.1:
   version "4.0.3"
   resolved "https://registry.yarnpkg.com/is-glob/-/is-glob-4.0.3.tgz#64f61e42cbbb2eec2071a9dac0b28ba1e65d5084"
@@ -811,6 +1164,11 @@ lodash.once@^4.1.1:
   resolved "https://registry.yarnpkg.com/lodash.once/-/lodash.once-4.1.1.tgz#0dd3971213c7c56df880977d504c88fb471a97ac"
   integrity sha512-Sb487aTOCr9drQVL8pIxOzVhafOjZN9UU54hiN8PU3uAiSV7lx1yYNpbNmex2PK6dSJoNTSJUUswT651yww3Mg==
 
+long@4.0.0:
+  version "4.0.0"
+  resolved "https://registry.yarnpkg.com/long/-/long-4.0.0.tgz#9a7b71cfb7d361a194ea555241c92f7468d5bf28"
+  integrity sha512-XsP+KhQif4bjX1kbuSiySJFNAehNxgLb6hPRGJ9QsUr8ajHkuXGdrHmFUTUUXhDwVX2R5bY4JNZEwbUiMhV+MA==
+
 lowercase-keys@^2.0.0:
   version "2.0.0"
   resolved "https://registry.yarnpkg.com/lowercase-keys/-/lowercase-keys-2.0.0.tgz#2603e78b7b4b0006cbca2fbcc8a3202558ac9479"
@@ -828,6 +1186,24 @@ luxon@~3.3.0:
   resolved "https://registry.yarnpkg.com/luxon/-/luxon-3.3.0.tgz#d73ab5b5d2b49a461c47cedbc7e73309b4805b48"
   integrity sha512-An0UCfG/rSiqtAIiBPO0Y9/zAnHUZxAMiCpTd5h2smgsj7GGmcenvrvww2cqNA8/4A5ZrD1gJpHN2mIHZQF+Mg==
 
+magika@^0.2.13:
+  version "0.2.13"
+  resolved "https://registry.yarnpkg.com/magika/-/magika-0.2.13.tgz#f39bc565f0d3703b592d3fc155a5d3ee056b0471"
+  integrity sha512-CIMx6aJ6SCX2uiAdLpghGeQPhMIOsnvmVpYjX/ao5ks0PFvJF1f9fWNGlayGfazNpJmTA1cuZG21DVVhfZkoUw==
+  dependencies:
+    "@tensorflow/tfjs" "^4.17.0"
+  optionalDependencies:
+    "@tensorflow/tfjs-node" "^4.17.0"
+    chalk "^5.3.0"
+    commander "^12.0.0"
+
+make-dir@^3.1.0:
+  version "3.1.0"
+  resolved "https://registry.yarnpkg.com/make-dir/-/make-dir-3.1.0.tgz#415e967046b3a7f1d185277d84aa58203726a13f"
+  integrity sha512-g3FeP20LNwhALb/6Cz6Dd4F2ngze0jz7tbzrD2wAV+o9FeNHe4rL+yK2md0J/fiSf1sa1ADhXqi5+oVwOM/eGw==
+  dependencies:
+    semver "^6.0.0"
+
 matcher@^3.0.0:
   version "3.0.0"
   resolved "https://registry.yarnpkg.com/matcher/-/matcher-3.0.0.tgz#bd9060f4c5b70aa8041ccc6f80368760994f30ca"
@@ -892,11 +1268,89 @@ minimatch@^3.1.1:
   dependencies:
     brace-expansion "^1.1.7"
 
+minimist@^1.2.6:
+  version "1.2.8"
+  resolved "https://registry.yarnpkg.com/minimist/-/minimist-1.2.8.tgz#c1a464e7693302e082a075cee0c057741ac4772c"
+  integrity sha512-2yyAR8qBkN3YuheJanUpWC5U3bb5osDywNB8RzDVlDwDHbocAJveqqj1u8+SVD7jkWT4yvsHCpWqqWqAxb0zCA==
+
+minipass@^2.6.0, minipass@^2.9.0:
+  version "2.9.0"
+  resolved "https://registry.yarnpkg.com/minipass/-/minipass-2.9.0.tgz#e713762e7d3e32fed803115cf93e04bca9fcc9a6"
+  integrity sha512-wxfUjg9WebH+CUDX/CdbRlh5SmfZiy/hpkxaRI16Y9W56Pa75sWgd/rvFilSgrauD9NyFymP/+JFV3KwzIsJeg==
+  dependencies:
+    safe-buffer "^5.1.2"
+    yallist "^3.0.0"
+
+minipass@^3.0.0:
+  version "3.3.6"
+  resolved "https://registry.yarnpkg.com/minipass/-/minipass-3.3.6.tgz#7bba384db3a1520d18c9c0e5251c3444e95dd94a"
+  integrity sha512-DxiNidxSEK+tHG6zOIklvNOwm3hvCrbUrdtzY74U6HKTJxvIDfOUL5W5P2Ghd3DTkhhKPYGqeNUIh5qcM4YBfw==
+  dependencies:
+    yallist "^4.0.0"
+
+minipass@^5.0.0:
+  version "5.0.0"
+  resolved "https://registry.yarnpkg.com/minipass/-/minipass-5.0.0.tgz#3e9788ffb90b694a5d0ec94479a45b5d8738133d"
+  integrity sha512-3FnjYuehv9k6ovOEbyOswadCDPX1piCfhV8ncmYtHOjuPwylVWsghTLo7rabjC3Rx5xD4HDx8Wm1xnMF7S5qFQ==
+
+minizlib@^1.3.3:
+  version "1.3.3"
+  resolved "https://registry.yarnpkg.com/minizlib/-/minizlib-1.3.3.tgz#2290de96818a34c29551c8a8d301216bd65a861d"
+  integrity sha512-6ZYMOEnmVsdCeTJVE0W9ZD+pVnE8h9Hma/iOwwRDsdQoePpoX56/8B6z3P9VNwppJuBKNRuFDRNRqRWexT9G9Q==
+  dependencies:
+    minipass "^2.9.0"
+
+minizlib@^2.1.1:
+  version "2.1.2"
+  resolved "https://registry.yarnpkg.com/minizlib/-/minizlib-2.1.2.tgz#e90d3466ba209b932451508a11ce3d3632145931"
+  integrity sha512-bAxsR8BVfj60DWXHE3u30oHzfl4G7khkSuPW+qvpd7jFRHm7dLxOjUk1EHACJ/hxLY8phGJ0YhYHZo7jil7Qdg==
+  dependencies:
+    minipass "^3.0.0"
+    yallist "^4.0.0"
+
+mkdirp@^0.5.5:
+  version "0.5.6"
+  resolved "https://registry.yarnpkg.com/mkdirp/-/mkdirp-0.5.6.tgz#7def03d2432dcae4ba1d611445c48396062255f6"
+  integrity sha512-FP+p8RB8OWpF3YZBCrP5gtADmtXApB5AMLn+vdyA+PyxCjrCs00mjyUozssO33cwDeT3wNGdLxJ5M//YqtHAJw==
+  dependencies:
+    minimist "^1.2.6"
+
+mkdirp@^1.0.3:
+  version "1.0.4"
+  resolved "https://registry.yarnpkg.com/mkdirp/-/mkdirp-1.0.4.tgz#3eb5ed62622756d79a5f0e2a221dfebad75c2f7e"
+  integrity sha512-vVqVZQyf3WLx2Shd0qJ9xuvqgAyKPLAiqITEtqW0oIUjzo3PePDd6fW9iFz30ef7Ysp/oiWqbhszeGWW2T6Gzw==
+
 ms@2.1.2:
   version "2.1.2"
   resolved "https://registry.yarnpkg.com/ms/-/ms-2.1.2.tgz#d09d1f357b443f493382a8eb3ccd183872ae6009"
   integrity sha512-sGkPx+VjMtmA6MX27oA4FBFELFCZZ4S4XqeGOXCv68tT+jb3vk/RyaKWP0PTKyWtmLSM0b+adUTEvbs1PEaH2w==
 
+ms@^2.1.1:
+  version "2.1.3"
+  resolved "https://registry.yarnpkg.com/ms/-/ms-2.1.3.tgz#574c8138ce1d2b5861f0b44579dbadd60c6615b2"
+  integrity sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA==
+
+node-fetch@^2.6.7:
+  version "2.7.0"
+  resolved "https://registry.yarnpkg.com/node-fetch/-/node-fetch-2.7.0.tgz#d0f0fa6e3e2dc1d27efcd8ad99d550bda94d187d"
+  integrity sha512-c4FRfUm/dbcWZ7U+1Wq0AwCyFL+3nt2bEw05wfxSz+DWpWsitgmSgYmy2dQdWyKC1694ELPqMs/YzUSNozLt8A==
+  dependencies:
+    whatwg-url "^5.0.0"
+
+node-fetch@~2.6.1:
+  version "2.6.13"
+  resolved "https://registry.yarnpkg.com/node-fetch/-/node-fetch-2.6.13.tgz#a20acbbec73c2e09f9007de5cda17104122e0010"
+  integrity sha512-StxNAxh15zr77QvvkmveSQ8uCQ4+v5FkvNTj0OESmiHu+VRi/gXArXtkWMElOsOUNLtUEvI4yS+rdtOHZTwlQA==
+  dependencies:
+    whatwg-url "^5.0.0"
+
+nopt@^5.0.0:
+  version "5.0.0"
+  resolved "https://registry.yarnpkg.com/nopt/-/nopt-5.0.0.tgz#530942bb58a512fccafe53fe210f13a25355dc88"
+  integrity sha512-Tbj67rffqceeLpcRXrT7vKAN8CwfPeIBgM7E6iBkmKLV7bEMwpGgYLGv0jACUsECaa/vuxP0IjEont6umdMgtQ==
+  dependencies:
+    abbrev "1"
+
 normalize-url@^6.0.1:
   version "6.1.0"
   resolved "https://registry.yarnpkg.com/normalize-url/-/normalize-url-6.1.0.tgz#40d0885b535deffe3f3147bec877d05fe4c5668a"
@@ -909,6 +1363,21 @@ npm-run-path@^4.0.1:
   dependencies:
     path-key "^3.0.0"
 
+npmlog@^5.0.1:
+  version "5.0.1"
+  resolved "https://registry.yarnpkg.com/npmlog/-/npmlog-5.0.1.tgz#f06678e80e29419ad67ab964e0fa69959c1eb8b0"
+  integrity sha512-AqZtDUWOMKs1G/8lwylVjrdYgqA4d9nu8hc+0gzRxlDb1I10+FHBGMXs6aiQHFdCUUlqH99MUMuLfzWDNDtfxw==
+  dependencies:
+    are-we-there-yet "^2.0.0"
+    console-control-strings "^1.1.0"
+    gauge "^3.0.0"
+    set-blocking "^2.0.0"
+
+object-assign@^4.1.1:
+  version "4.1.1"
+  resolved "https://registry.yarnpkg.com/object-assign/-/object-assign-4.1.1.tgz#2109adc7965887cfc05cbbd442cac8bfbb360863"
+  integrity sha512-rJgTQnkUnH1sFw8yT6VSU3zD3sWmu6sZhIseY8VX+GRu3P6F7Fu+JNDoXfklElbLJSnc3FUQHVe4cU5hj+BcUg==
+
 object-keys@^1.1.1:
   version "1.1.1"
   resolved "https://registry.yarnpkg.com/object-keys/-/object-keys-1.1.1.tgz#1c47f272df277f3b1daf061677d9c82e2322c60e"
@@ -996,7 +1465,7 @@ pkg-up@^3.1.0:
   dependencies:
     find-up "^3.0.0"
 
-progress@^2.0.3:
+progress@^2.0.0, progress@^2.0.3:
   version "2.0.3"
   resolved "https://registry.yarnpkg.com/progress/-/progress-2.0.3.tgz#7e8cf8d8f5b8f239c1bc68beb4eb78567d572ef8"
   integrity sha512-7PiHtLll5LdnKIMw100I+8xJXR5gW2QwWYkT6iJva0bXitZKa/XMrSbdmg3r2Xnaidz9Qumd0VPaMrZlF9V9sA==
@@ -1029,6 +1498,25 @@ quick-lru@^5.1.1:
   resolved "https://registry.yarnpkg.com/quick-lru/-/quick-lru-5.1.1.tgz#366493e6b3e42a3a6885e2e99d18f80fb7a8c932"
   integrity sha512-WuyALRjWPDGtt/wzJiadO5AXY+8hZ80hVpe6MyivgraREW751X3SbhRvG3eLKOYN+8VEvqLcf3wdnt44Z4S4SA==
 
+readable-stream@^3.6.0:
+  version "3.6.2"
+  resolved "https://registry.yarnpkg.com/readable-stream/-/readable-stream-3.6.2.tgz#56a9b36ea965c00c5a93ef31eb111a0f11056967"
+  integrity sha512-9u/sniCrY3D5WdsERHzHE4G2YCXqoG5FTHUiCC4SIbr6XcLZBY05ya9EKjYek9O5xOAwjGq+1JdGBAS7Q9ScoA==
+  dependencies:
+    inherits "^2.0.3"
+    string_decoder "^1.1.1"
+    util-deprecate "^1.0.1"
+
+regenerator-runtime@^0.13.5:
+  version "0.13.11"
+  resolved "https://registry.yarnpkg.com/regenerator-runtime/-/regenerator-runtime-0.13.11.tgz#f6dca3e7ceec20590d07ada785636a90cdca17f9"
+  integrity sha512-kY1AZVr2Ra+t+piVaJ4gxaFaReZVH40AKNo7UCX6W+dEwBo/2oZJzqfuN1qLq1oL45o56cPaTXELwrTh8Fpggg==
+
+require-directory@^2.1.1:
+  version "2.1.1"
+  resolved "https://registry.yarnpkg.com/require-directory/-/require-directory-2.1.1.tgz#8c64ad5fd30dab1c976e2344ffe7f792a6a6df42"
+  integrity sha512-fGxEI7+wsG9xrvdjsrlmL22OMTTiHRwAMroiEeMgq8gzoLC/PQr7RsRDSTLUg/bZAZtF+TVIkHc6/4RIKrui+Q==
+
 require-from-string@^2.0.2:
   version "2.0.2"
   resolved "https://registry.yarnpkg.com/require-from-string/-/require-from-string-2.0.2.tgz#89a7fdd938261267318eafe14f9c32e598c36909"
@@ -1051,6 +1539,13 @@ reusify@^1.0.4:
   resolved "https://registry.yarnpkg.com/reusify/-/reusify-1.0.4.tgz#90da382b1e126efc02146e90845a88db12925d76"
   integrity sha512-U9nH88a3fc/ekCF1l0/UP1IosiuIjyTh7hBvXVMHYgVcfGvt897Xguj2UOLDeI5BG2m7/uwyaLVT6fbtCwTyzw==
 
+rimraf@^2.6.2:
+  version "2.7.1"
+  resolved "https://registry.yarnpkg.com/rimraf/-/rimraf-2.7.1.tgz#35797f13a7fdadc566142c29d4f07ccad483e3ec"
+  integrity sha512-uWjbaKIK3T1OSVptzX7Nl6PvQ3qAGtKEtVRjRuazjfL3Bx5eI409VZSqgND+4UNnmzLVdPj9FqFJNPqBZFve4w==
+  dependencies:
+    glob "^7.1.3"
+
 rimraf@^3.0.2:
   version "3.0.2"
   resolved "https://registry.yarnpkg.com/rimraf/-/rimraf-3.0.2.tgz#f1a5402ba6220ad52cc1282bac1ae3aa49fd061a"
@@ -1077,17 +1572,27 @@ run-parallel@^1.1.9:
   dependencies:
     queue-microtask "^1.2.2"
 
+safe-buffer@^5.1.2, safe-buffer@^5.2.1, safe-buffer@~5.2.0:
+  version "5.2.1"
+  resolved "https://registry.yarnpkg.com/safe-buffer/-/safe-buffer-5.2.1.tgz#1eaf9fa9bdb1fdd4ec75f58f9cdb4e6b7827eec6"
+  integrity sha512-rp3So07KcdmmKbGvgaNxQSJr7bGVSVk5S9Eq1F+ppbRo70+YeaDxkw5Dd8NPN+GD6bjnYm2VuPuCXmpuYvmCXQ==
+
 sax@^1.2.4:
   version "1.2.4"
   resolved "https://registry.yarnpkg.com/sax/-/sax-1.2.4.tgz#2816234e2378bddc4e5354fab5caa895df7100d9"
   integrity sha512-NqVDv9TpANUjFm0N8uM5GxL36UgKi9/atZw+x7YFnQ8ckwFGKrl4xX4yWtrey3UJm5nP1kUbnYgLopqWNSRhWw==
 
+seedrandom@^3.0.5:
+  version "3.0.5"
+  resolved "https://registry.yarnpkg.com/seedrandom/-/seedrandom-3.0.5.tgz#54edc85c95222525b0c7a6f6b3543d8e0b3aa0a7"
+  integrity sha512-8OwmbklUNzwezjGInmZ+2clQmExQPvomqjL7LFqOYqtmuxRgQYqOD3mHaU+MvZn5FLUeVxVfQjwLZW/n/JFuqg==
+
 semver-compare@^1.0.0:
   version "1.0.0"
   resolved "https://registry.yarnpkg.com/semver-compare/-/semver-compare-1.0.0.tgz#0dee216a1c941ab37e9efb1788f6afc5ff5537fc"
   integrity sha512-YM3/ITh2MJ5MtzaM429anh+x2jiLVjqILF4m4oyQB18W7Ggea7BfqdH/wGMK7dDiMghv/6WG7znWMwUDzJiXow==
 
-semver@^6.2.0:
+semver@^6.0.0, semver@^6.2.0:
   version "6.3.1"
   resolved "https://registry.yarnpkg.com/semver/-/semver-6.3.1.tgz#556d2ef8689146e46dcea4bfdd095f3434dffcb4"
   integrity sha512-BR7VvDCVHO+q2xBEWskxS6DJE1qRnb7DxzUrogb71CWoSficBxYsiAGd+Kl0mmq/MprG9yArRkyrQxTO6XjMzA==
@@ -1106,6 +1611,11 @@ serialize-error@^7.0.1:
   dependencies:
     type-fest "^0.13.1"
 
+set-blocking@^2.0.0:
+  version "2.0.0"
+  resolved "https://registry.yarnpkg.com/set-blocking/-/set-blocking-2.0.0.tgz#045f9782d011ae9a6803ddd382b24392b3d890f7"
+  integrity sha512-KiKBS8AnWGEyLzofFfmvKwpdPzqiy16LvQfK3yv/fVH7Bj13/wl3JSR1J+rfgRE9q7xUJK4qvgS8raSOeLUehw==
+
 shebang-command@^2.0.0:
   version "2.0.0"
   resolved "https://registry.yarnpkg.com/shebang-command/-/shebang-command-2.0.0.tgz#ccd0af4f8835fbdc265b82461aaf0c36663f34ea"
@@ -1118,7 +1628,7 @@ shebang-regex@^3.0.0:
   resolved "https://registry.yarnpkg.com/shebang-regex/-/shebang-regex-3.0.0.tgz#ae16f1644d873ecad843b0307b143362d4c42172"
   integrity sha512-7++dFhtcx3353uBaq8DDR4NuxBetBzC7ZQOhmTQInHEd6bSrXdiEyzCvG07Z44UYdLShWUyXt5M/yhz8ekcb1A==
 
-signal-exit@^3.0.3:
+signal-exit@^3.0.0, signal-exit@^3.0.3:
   version "3.0.7"
   resolved "https://registry.yarnpkg.com/signal-exit/-/signal-exit-3.0.7.tgz#a9a1767f8af84155114eaabd73f99273c8f59ad9"
   integrity sha512-wnD2ZE+l+SPC/uoS0vXeE9L1+0wuaMqKlfz9AMUo38JsyLSBWSFcHR1Rri62LZc12vLr1gb3jl7iwQhgwpAbGQ==
@@ -1133,6 +1643,34 @@ sprintf-js@^1.1.2:
   resolved "https://registry.yarnpkg.com/sprintf-js/-/sprintf-js-1.1.2.tgz#da1765262bf8c0f571749f2ad6c26300207ae673"
   integrity sha512-VE0SOVEHCk7Qc8ulkWw3ntAzXuqf7S2lvwQaDLRnUeIEaKNQJzV6BwmLKhOqT61aGhfUMrXeaBk+oDGCzvhcug==
 
+sprintf-js@~1.0.2:
+  version "1.0.3"
+  resolved "https://registry.yarnpkg.com/sprintf-js/-/sprintf-js-1.0.3.tgz#04e6926f662895354f3dd015203633b857297e2c"
+  integrity sha512-D9cPgkvLlV3t3IzL0D0YLvGA9Ahk4PcvVwUbN0dSGr1aP0Nrt4AEnTUbuGvquEC0mA64Gqt1fzirlRs5ibXx8g==
+
+"string-width@^1.0.2 || 2 || 3 || 4", string-width@^4.1.0, string-width@^4.2.0, string-width@^4.2.3:
+  version "4.2.3"
+  resolved "https://registry.yarnpkg.com/string-width/-/string-width-4.2.3.tgz#269c7117d27b05ad2e536830a8ec895ef9c6d010"
+  integrity sha512-wKyQRQpjJ0sIp62ErSZdGsjMJWsap5oRNihHhu6G7JVO/9jIB6UyevL+tXuOqrng8j/cxKTWyWUwvSTriiZz/g==
+  dependencies:
+    emoji-regex "^8.0.0"
+    is-fullwidth-code-point "^3.0.0"
+    strip-ansi "^6.0.1"
+
+string_decoder@^1.1.1, string_decoder@^1.3.0:
+  version "1.3.0"
+  resolved "https://registry.yarnpkg.com/string_decoder/-/string_decoder-1.3.0.tgz#42f114594a46cf1a8e30b0a84f56c78c3edac21e"
+  integrity sha512-hkRX8U1WjJFd8LsDJ2yQ/wWWxaopEsABU1XfkM8A+j0+85JAGppt16cr1Whg6KIbb4okU6Mql6BOj+uup/wKeA==
+  dependencies:
+    safe-buffer "~5.2.0"
+
+strip-ansi@^6.0.0, strip-ansi@^6.0.1:
+  version "6.0.1"
+  resolved "https://registry.yarnpkg.com/strip-ansi/-/strip-ansi-6.0.1.tgz#9e26c63d30f53443e9489495b2105d37b67a85d9"
+  integrity sha512-Y38VPSHcqkFrCpFnQ9vuSXmquuv5oXOKpGeT6aGrr3o3Gc9AlVa6JBfUSOCnbxGGZF+/0ooI7KrPuUSztUdU5A==
+  dependencies:
+    ansi-regex "^5.0.1"
+
 strip-final-newline@^2.0.0:
   version "2.0.0"
   resolved "https://registry.yarnpkg.com/strip-final-newline/-/strip-final-newline-2.0.0.tgz#89b852fb2fcbe936f6f4b3187afb0a12c1ab58ad"
@@ -1145,6 +1683,38 @@ sumchecker@^3.0.1:
   dependencies:
     debug "^4.1.0"
 
+supports-color@^7.1.0:
+  version "7.2.0"
+  resolved "https://registry.yarnpkg.com/supports-color/-/supports-color-7.2.0.tgz#1b7dcdcb32b8138801b3e478ba6a51caa89648da"
+  integrity sha512-qpCAvRl9stuOHveKsn7HncJRvv501qIacKzQlO/+Lwxc9+0q2wLyv4Dfvt80/DPn2pqOBsJdDiogXGR9+OvwRw==
+  dependencies:
+    has-flag "^4.0.0"
+
+tar@^4.4.6:
+  version "4.4.19"
+  resolved "https://registry.yarnpkg.com/tar/-/tar-4.4.19.tgz#2e4d7263df26f2b914dee10c825ab132123742f3"
+  integrity sha512-a20gEsvHnWe0ygBY8JbxoM4w3SJdhc7ZAuxkLqh+nvNQN2IOt0B5lLgM490X5Hl8FF0dl0tOf2ewFYAlIFgzVA==
+  dependencies:
+    chownr "^1.1.4"
+    fs-minipass "^1.2.7"
+    minipass "^2.9.0"
+    minizlib "^1.3.3"
+    mkdirp "^0.5.5"
+    safe-buffer "^5.2.1"
+    yallist "^3.1.1"
+
+tar@^6.1.11:
+  version "6.2.1"
+  resolved "https://registry.yarnpkg.com/tar/-/tar-6.2.1.tgz#717549c541bc3c2af15751bea94b1dd068d4b03a"
+  integrity sha512-DZ4yORTwrbTj/7MZYq2w+/ZFdI6OZ/f9SFHR+71gIVUZhOQPHzVCLpvRnPgyaMpfWxxk/4ONva3GQSyNIKRv6A==
+  dependencies:
+    chownr "^2.0.0"
+    fs-minipass "^2.0.0"
+    minipass "^5.0.0"
+    minizlib "^2.1.1"
+    mkdirp "^1.0.3"
+    yallist "^4.0.0"
+
 to-regex-range@^5.0.1:
   version "5.0.1"
   resolved "https://registry.yarnpkg.com/to-regex-range/-/to-regex-range-5.0.1.tgz#1648c44aae7c8d988a326018ed72f5b4dd0392e4"
@@ -1152,6 +1722,11 @@ to-regex-range@^5.0.1:
   dependencies:
     is-number "^7.0.0"
 
+tr46@~0.0.3:
+  version "0.0.3"
+  resolved "https://registry.yarnpkg.com/tr46/-/tr46-0.0.3.tgz#8184fd347dac9cdc185992f3a6622e14b9d9ab6a"
+  integrity sha512-N3WMsuqV66lT30CrXNbEjx4GEwlow3v6rr4mCcv6prnfwhS01rkgyFdjPNBYd9br7LpXV1+Emh01fHnq2Gdgrw==
+
 type-fest@^0.13.1:
   version "0.13.1"
   resolved "https://registry.yarnpkg.com/type-fest/-/type-fest-0.13.1.tgz#0172cb5bce80b0bd542ea348db50c7e21834d934"
@@ -1179,6 +1754,24 @@ uri-js@^4.2.2:
   dependencies:
     punycode "^2.1.0"
 
+util-deprecate@^1.0.1:
+  version "1.0.2"
+  resolved "https://registry.yarnpkg.com/util-deprecate/-/util-deprecate-1.0.2.tgz#450d4dc9fa70de732762fbd2d4a28981419a0ccf"
+  integrity sha512-EPD5q1uXyFxJpCrLnCc1nHnq3gOa6DZBocAIiI2TaSCA7VCJ1UJDMagCzIkXNsUYfD1daK//LTEQ8xiIbrHtcw==
+
+webidl-conversions@^3.0.0:
+  version "3.0.1"
+  resolved "https://registry.yarnpkg.com/webidl-conversions/-/webidl-conversions-3.0.1.tgz#24534275e2a7bc6be7bc86611cc16ae0a5654871"
+  integrity sha512-2JAn3z8AR6rjK8Sm8orRC0h/bcl/DqL7tRPdGZ4I1CjdF+EaMLmYxBHyXuKL849eucPFhvBoxMsflfOb8kxaeQ==
+
+whatwg-url@^5.0.0:
+  version "5.0.0"
+  resolved "https://registry.yarnpkg.com/whatwg-url/-/whatwg-url-5.0.0.tgz#966454e8765462e37644d3626f6742ce8b70965d"
+  integrity sha512-saE57nupxk6v3HY35+jzBwYa0rKSy0XR8JSxZPwgLr7ys0IBzhGviA1/TUGJLmSVqs8pb9AnvICXEuOHLprYTw==
+  dependencies:
+    tr46 "~0.0.3"
+    webidl-conversions "^3.0.0"
+
 which@^2.0.1:
   version "2.0.2"
   resolved "https://registry.yarnpkg.com/which/-/which-2.0.2.tgz#7c6a8dd0a636a0327e10b59c9286eee93f3f51b1"
@@ -1186,16 +1779,60 @@ which@^2.0.1:
   dependencies:
     isexe "^2.0.0"
 
+wide-align@^1.1.2:
+  version "1.1.5"
+  resolved "https://registry.yarnpkg.com/wide-align/-/wide-align-1.1.5.tgz#df1d4c206854369ecf3c9a4898f1b23fbd9d15d3"
+  integrity sha512-eDMORYaPNZ4sQIuuYPDHdQvf4gyCF9rEEV/yPxGfwPkRodwEgiMUUXTx/dex+Me0wxx53S+NgUHaP7y3MGlDmg==
+  dependencies:
+    string-width "^1.0.2 || 2 || 3 || 4"
+
+wrap-ansi@^7.0.0:
+  version "7.0.0"
+  resolved "https://registry.yarnpkg.com/wrap-ansi/-/wrap-ansi-7.0.0.tgz#67e145cff510a6a6984bdf1152911d69d2eb9e43"
+  integrity sha512-YVGIj2kamLSTxw6NsZjoBxfSwsn0ycdesmc4p+Q21c5zPuZ1pl+NfxVdxPtdHvmNVOQ6XSYG4AUtyt/Fi7D16Q==
+  dependencies:
+    ansi-styles "^4.0.0"
+    string-width "^4.1.0"
+    strip-ansi "^6.0.0"
+
 wrappy@1:
   version "1.0.2"
   resolved "https://registry.yarnpkg.com/wrappy/-/wrappy-1.0.2.tgz#b5243d8f3ec1aa35f1364605bc0d1036e30ab69f"
   integrity sha512-l4Sp/DRseor9wL6EvV2+TuQn63dMkPjZ/sp9XkghTEbV9KlPS1xUsZ3u7/IQO4wxtcFB4bgpQPRcR3QCvezPcQ==
 
+y18n@^5.0.5:
+  version "5.0.8"
+  resolved "https://registry.yarnpkg.com/y18n/-/y18n-5.0.8.tgz#7f4934d0f7ca8c56f95314939ddcd2dd91ce1d55"
+  integrity sha512-0pfFzegeDWJHJIAmTLRP2DwHjdF5s7jo9tuztdQxAhINCdvS+3nGINqPd00AphqJR/0LhANUS6/+7SCb98YOfA==
+
+yallist@^3.0.0, yallist@^3.1.1:
+  version "3.1.1"
+  resolved "https://registry.yarnpkg.com/yallist/-/yallist-3.1.1.tgz#dbb7daf9bfd8bac9ab45ebf602b8cbad0d5d08fd"
+  integrity sha512-a4UGQaWPH59mOXUYnAG2ewncQS4i4F43Tv3JoAM+s2VDAmS9NsK8GpDMLrCHPksFT7h3K6TOoUNn2pb7RoXx4g==
+
 yallist@^4.0.0:
   version "4.0.0"
   resolved "https://registry.yarnpkg.com/yallist/-/yallist-4.0.0.tgz#9bb92790d9c0effec63be73519e11a35019a3a72"
   integrity sha512-3wdGidZyq5PB084XLES5TpOSRA3wjXAlIWMhum2kRcv/41Sn2emQ0dycQW4uZXLejwKvg6EsvbdlVL+FYEct7A==
 
+yargs-parser@^20.2.2:
+  version "20.2.9"
+  resolved "https://registry.yarnpkg.com/yargs-parser/-/yargs-parser-20.2.9.tgz#2eb7dc3b0289718fc295f362753845c41a0c94ee"
+  integrity sha512-y11nGElTIV+CT3Zv9t7VKl+Q3hTQoT9a1Qzezhhl6Rp21gJ/IVTW7Z3y9EWXhuUBC2Shnf+DX0antecpAwSP8w==
+
+yargs@^16.0.3:
+  version "16.2.0"
+  resolved "https://registry.yarnpkg.com/yargs/-/yargs-16.2.0.tgz#1c82bf0f6b6a66eafce7ef30e376f49a12477f66"
+  integrity sha512-D1mvvtDG0L5ft/jGWkLpG1+m0eQxOfaBvTNELraWj22wSVUMWxZUvYgJYcKh6jGGIkJFhH4IZPQhR4TKpc8mBw==
+  dependencies:
+    cliui "^7.0.2"
+    escalade "^3.1.1"
+    get-caller-file "^2.0.5"
+    require-directory "^2.1.1"
+    string-width "^4.2.0"
+    y18n "^5.0.5"
+    yargs-parser "^20.2.2"
+
 yauzl@^2.10.0:
   version "2.10.0"
   resolved "https://registry.yarnpkg.com/yauzl/-/yauzl-2.10.0.tgz#c7eb17c93e112cb1086fa6d8e51fb0667b79a5f9"

src/khoj/processor/content/github/github_to_entries.py

@@ -1,19 +1,21 @@
 import logging
 import time
-from datetime import datetime
-from typing import Any, Dict, List, Tuple, Union
+from typing import Any, Dict, List, Tuple
 
 import requests
+from magika import Magika
 
 from khoj.database.models import Entry as DbEntry
 from khoj.database.models import GithubConfig, KhojUser
 from khoj.processor.content.markdown.markdown_to_entries import MarkdownToEntries
 from khoj.processor.content.org_mode.org_to_entries import OrgToEntries
+from khoj.processor.content.plaintext.plaintext_to_entries import PlaintextToEntries
 from khoj.processor.content.text_to_entries import TextToEntries
 from khoj.utils.helpers import timer
-from khoj.utils.rawconfig import Entry, GithubContentConfig, GithubRepoConfig
+from khoj.utils.rawconfig import GithubContentConfig, GithubRepoConfig
 
 logger = logging.getLogger(__name__)
+magika = Magika()
 
 
 class GithubToEntries(TextToEntries):
@@ -62,15 +64,18 @@ class GithubToEntries(TextToEntries):
         repo_url = f"https://api.github.com/repos/{repo.owner}/{repo.name}"
         repo_shorthand = f"{repo.owner}/{repo.name}"
         logger.info(f"Processing github repo {repo_shorthand}")
-        with timer("Download markdown files from github repo", logger):
+        with timer("Download files from github repo", logger):
             try:
-                markdown_files, org_files = self.get_files(repo_url, repo)
+                markdown_files, org_files, plaintext_files = self.get_files(repo_url, repo)
+            except ConnectionAbortedError as e:
+                logger.error(f"Github rate limit reached. Skip indexing github repo {repo_shorthand}")
             except Exception as e:
                 logger.error(f"Unable to download github repo {repo_shorthand}", exc_info=True)
                 raise e
 
-        logger.info(f"Found {len(markdown_files)} markdown files in github repo {repo_shorthand}")
-        logger.info(f"Found {len(org_files)} org files in github repo {repo_shorthand}")
+        logger.info(
+            f"Found {len(markdown_files)} md, {len(org_files)} org and {len(plaintext_files)} text files in github repo {repo_shorthand}"
+        )
         current_entries = []
 
         with timer(f"Extract markdown entries from github repo {repo_shorthand}", logger):
@@ -83,14 +88,10 @@ class GithubToEntries(TextToEntries):
                 *GithubToEntries.extract_org_entries(org_files)
             )
 
-        with timer(f"Extract commit messages from github repo {repo_shorthand}", logger):
-            current_entries += self.convert_commits_to_entries(self.get_commits(repo_url), repo)
-
-        with timer(f"Extract issues from github repo {repo_shorthand}", logger):
-            issue_entries = GithubToEntries.convert_issues_to_entries(
-                *GithubToEntries.extract_github_issues(self.get_issues(repo_url))
+        with timer(f"Extract plaintext entries from github repo {repo_shorthand}", logger):
+            current_entries += PlaintextToEntries.convert_text_files_to_entries(
+                *GithubToEntries.extract_plaintext_entries(plaintext_files)
             )
-            current_entries += issue_entries
 
         with timer(f"Split entries by max token size supported by model {repo_shorthand}", logger):
             current_entries = TextToEntries.split_entries_by_max_tokens(current_entries, max_tokens=256)
@@ -119,16 +120,16 @@ class GithubToEntries(TextToEntries):
         response = requests.get(repo_content_url, headers=headers, params=params)
         contents = response.json()
 
-        # Wait for rate limit reset if needed
-        result = self.wait_for_rate_limit_reset(response, self.get_files, repo_url, repo)
-        if result is not None:
-            return result
+        # Raise exception if hit rate limit
+        if response.status_code != 200 and response.headers.get("X-RateLimit-Remaining") == "0":
+            raise ConnectionAbortedError("Github rate limit reached")
 
         # Extract markdown files from the repository
-        markdown_files: List[Any] = []
-        org_files: List[Any] = []
+        markdown_files: List[Dict[str, str]] = []
+        org_files: List[Dict[str, str]] = []
+        plaintext_files: List[Dict[str, str]] = []
         if "tree" not in contents:
-            return markdown_files, org_files
+            return markdown_files, org_files, plaintext_files
 
         for item in contents["tree"]:
             # Find all markdown files in the repository
@@ -147,144 +148,46 @@ class GithubToEntries(TextToEntries):
                 # Add org file contents and URL to list
                 org_files += [{"content": self.get_file_contents(item["url"]), "path": url_path}]
 
-        return markdown_files, org_files
+            # Find, index remaining non-binary files in the repository
+            elif item["type"] == "blob":
+                url_path = f'https://github.com/{repo.owner}/{repo.name}/blob/{repo.branch}/{item["path"]}'
+                content_bytes = self.get_file_contents(item["url"], decode=False)
+                content_type, content_str = None, None
+                try:
+                    content_type = magika.identify_bytes(content_bytes).output.mime_type
+                    content_str = content_bytes.decode("utf-8")
+                except:
+                    logger.error(
+                        f"Unable to identify content type or decode content of file at {url_path}. Skip indexing it"
+                    )
+                    continue
 
-    def get_file_contents(self, file_url):
+                # Add non-binary file contents and URL to list
+                if content_type.startswith("text/"):
+                    plaintext_files += [{"content": content_str, "path": url_path}]
+
+        return markdown_files, org_files, plaintext_files
+
+    def get_file_contents(self, file_url, decode=True):
         # Get text from each markdown file
         headers = {"Accept": "application/vnd.github.v3.raw"}
         response = self.session.get(file_url, headers=headers, stream=True)
 
-        # Wait for rate limit reset if needed
-        result = self.wait_for_rate_limit_reset(response, self.get_file_contents, file_url)
-        if result is not None:
-            return result
+        # Stop indexing on hitting rate limit
+        if response.status_code != 200 and response.headers.get("X-RateLimit-Remaining") == "0":
+            raise ConnectionAbortedError("Github rate limit reached")
 
-        content = ""
+        content = "" if decode else b""
         for chunk in response.iter_content(chunk_size=2048):
             if chunk:
                 try:
-                    content += chunk.decode("utf-8")
+                    content += chunk.decode("utf-8") if decode else chunk
                 except Exception as e:
                     logger.error(f"Unable to decode chunk from {file_url}")
                     logger.error(e)
 
         return content
 
-    def get_commits(self, repo_url: str) -> List[Dict]:
-        return self._get_commits(f"{repo_url}/commits")
-
-    def _get_commits(self, commits_url: Union[str, None]) -> List[Dict]:
-        # Get commit messages from the repository using the Github API
-        params = {"per_page": 100}
-        commits = []
-
-        while commits_url is not None:
-            # Get the next page of commits
-            response = self.session.get(commits_url, params=params, stream=True)
-
-            # Read the streamed response into a JSON object
-            content = response.json()
-
-            # Wait for rate limit reset if needed
-            result = self.wait_for_rate_limit_reset(response, self._get_commits, commits_url)
-            if result is not None:
-                return result
-
-            # Extract commit messages from the response
-            for commit in content:
-                if "commit" in commit and "message" in commit["commit"] and "html_url" in commit:
-                    commits += [{"content": commit["commit"]["message"], "path": commit["html_url"]}]
-                else:
-                    logger.debug(f"Skipping commit with missing properties: {commit}")
-
-            # Get the URL for the next page of commits, if any
-            commits_url = response.links.get("next", {}).get("url")
-
-        return commits
-
-    def get_issues(self, repo_url: str) -> List[Dict]:
-        return self._get_issues(f"{repo_url}/issues")
-
-    def _get_issues(self, issues_url: Union[str, None]) -> List[Dict]:
-        issues = []
-        per_page = 100
-        params = {"per_page": per_page, "state": "all"}
-
-        while issues_url is not None:
-            # Get the next page of issues
-            response = self.session.get(issues_url, params=params, stream=True)  # type: ignore
-            raw_issues = response.json()
-
-            # Wait for rate limit reset if needed
-            result = self.wait_for_rate_limit_reset(response, self._get_issues, issues_url)
-            if result is not None:
-                return result
-
-            for issue in raw_issues:
-                username = issue["user"]["login"]
-                user_url = f"[{username}]({issue['user']['html_url']})"
-                issue_content = {
-                    "content": f"## [Issue {issue['number']}]({issue['html_url']}) {issue['title']}\nby {user_url}\n\n{issue['body']}",
-                    "path": issue["html_url"],
-                }
-                issue_content["created_at"] = {issue["created_at"]}
-                if issue["comments"] > 0:
-                    issue_content["comments"] = self.get_comments(issue["comments_url"])
-                issues += [issue_content]
-
-            issues_url = response.links.get("next", {}).get("url")
-
-        return issues
-
-    def get_comments(self, comments_url: Union[str, None]) -> List[Dict]:
-        # By default, the number of results per page is 30. We'll keep it as-is for now.
-        comments = []
-        per_page = 100
-        params = {"per_page": per_page}
-
-        while comments_url is not None:
-            # Get the next page of comments
-            response = self.session.get(comments_url, params=params, stream=True)
-            raw_comments = response.json()
-
-            # Wait for rate limit reset if needed
-            result = self.wait_for_rate_limit_reset(response, self.get_comments, comments_url)
-            if result is not None:
-                return result
-
-            for comment in raw_comments:
-                created_at = datetime.strptime(comment["created_at"], "%Y-%m-%dT%H:%M:%SZ").strftime("%Y-%m-%d %H:%M")
-                commenter = comment["user"]["login"]
-                commenter_url = comment["user"]["html_url"]
-                comment_url = comment["html_url"]
-                comment_url_link = f"[{created_at}]({comment_url})"
-                avatar_url = comment["user"]["avatar_url"]
-                avatar = f"![{commenter}]({avatar_url})"
-                comments += [
-                    {
-                        "content": f"### {avatar} [{commenter}]({commenter_url}) - ({comment_url_link})\n\n{comment['body']}"
-                    }
-                ]
-
-            comments_url = response.links.get("next", {}).get("url")
-
-        return comments
-
-    def convert_commits_to_entries(self, commits, repo: GithubRepoConfig) -> List[Entry]:
-        entries: List[Entry] = []
-        for commit in commits:
-            compiled = f'Commit message from {repo.owner}/{repo.name}:\n{commit["content"]}'
-            entries.append(
-                Entry(
-                    compiled=compiled,
-                    raw=f'### {commit["content"]}',
-                    heading=commit["content"].split("\n")[0],
-                    file=commit["path"],
-                )
-            )
-
-        return entries
-
     @staticmethod
     def extract_markdown_entries(markdown_files):
         entries = []
@@ -307,30 +210,12 @@ class GithubToEntries(TextToEntries):
         return entries, dict(entry_to_file_map)
 
     @staticmethod
-    def extract_github_issues(issues):
+    def extract_plaintext_entries(plaintext_files):
         entries = []
-        entry_to_file_map = {}
-        for issue in issues:
-            content = issue["content"]
-            if "comments" in issue:
-                for comment in issue["comments"]:
-                    content += "\n\n" + comment["content"]
-            entries.append(content)
-            entry_to_file_map[content] = {"path": issue["path"]}
-        return entries, entry_to_file_map
+        entry_to_file_map = []
 
-    @staticmethod
-    def convert_issues_to_entries(parsed_entries: List[str], entry_to_metadata_map: Dict[str, Dict]) -> List[Entry]:
-        entries = []
-        for entry in parsed_entries:
-            entry_file_name = entry_to_metadata_map[entry]["path"]
-            entries.append(
-                Entry(
-                    compiled=entry,
-                    raw=entry,
-                    heading=entry.split("\n")[0],
-                    file=entry_file_name,
+        for doc in plaintext_files:
+            entries, entry_to_file_map = PlaintextToEntries.process_single_plaintext_file(
+                doc["content"], doc["path"], entries, entry_to_file_map
             )
-            )
-
-        return entries
+        return entries, dict(entry_to_file_map)

src/khoj/processor/content/plaintext/plaintext_to_entries.py

@@ -1,7 +1,9 @@
 import logging
+import re
 from pathlib import Path
-from typing import List, Tuple
+from typing import Dict, List, Tuple
 
+import urllib3
 from bs4 import BeautifulSoup
 
 from khoj.database.models import Entry as DbEntry
@@ -28,26 +30,13 @@ class PlaintextToEntries(TextToEntries):
         else:
             deletion_file_names = None
 
-        with timer("Scrub plaintext files and extract text", logger):
-            for file in files:
-                try:
-                    plaintext_content = files[file]
-                    if file.endswith(("html", "htm", "xml")):
-                        plaintext_content = PlaintextToEntries.extract_html_content(
-                            plaintext_content, file.split(".")[-1]
-                        )
-                    files[file] = plaintext_content
-                except Exception as e:
-                    logger.warning(f"Unable to read file: {file} as plaintext. Skipping file.")
-                    logger.warning(e, exc_info=True)
-
         # Extract Entries from specified plaintext files
-        with timer("Parse entries from specified Plaintext files", logger):
+        with timer("Extract entries from specified Plaintext files", logger):
             current_entries = PlaintextToEntries.extract_plaintext_entries(files)
 
         # Split entries by max tokens supported by model
         with timer("Split entries by max token size supported by model", logger):
-            current_entries = self.split_entries_by_max_tokens(current_entries, max_tokens=256)
+            current_entries = self.split_entries_by_max_tokens(current_entries, max_tokens=256, raw_is_compiled=True)
 
         # Identify, mark and merge any new entries with previous entries
         with timer("Identify new or updated entries", logger):
@@ -74,16 +63,57 @@ class PlaintextToEntries(TextToEntries):
         return soup.get_text(strip=True, separator="\n")
 
     @staticmethod
-    def extract_plaintext_entries(entry_to_file_map: dict[str, str]) -> List[Entry]:
-        "Convert each plaintext entries into a dictionary"
-        entries = []
-        for file, entry in entry_to_file_map.items():
+    def extract_plaintext_entries(text_files: Dict[str, str]) -> List[Entry]:
+        entries: List[str] = []
+        entry_to_file_map: List[Tuple[str, str]] = []
+        for text_file in text_files:
+            try:
+                text_content = text_files[text_file]
+                entries, entry_to_file_map = PlaintextToEntries.process_single_plaintext_file(
+                    text_content, text_file, entries, entry_to_file_map
+                )
+            except Exception as e:
+                logger.warning(f"Unable to read file: {text_file} as plaintext. Skipping file.")
+                logger.warning(e, exc_info=True)
+
+        # Extract Entries from specified plaintext files
+        return PlaintextToEntries.convert_text_files_to_entries(entries, dict(entry_to_file_map))
+
+    @staticmethod
+    def process_single_plaintext_file(
+        text_content: str,
+        text_file: str,
+        entries: List[str],
+        entry_to_file_map: List[Tuple[str, str]],
+    ) -> Tuple[List[str], List[Tuple[str, str]]]:
+        if text_file.endswith(("html", "htm", "xml")):
+            text_content = PlaintextToEntries.extract_html_content(text_content, text_file.split(".")[-1])
+        entry_to_file_map += [(text_content, text_file)]
+        entries.extend([text_content])
+        return entries, entry_to_file_map
+
+    @staticmethod
+    def convert_text_files_to_entries(parsed_entries: List[str], entry_to_file_map: dict[str, str]) -> List[Entry]:
+        "Convert each plaintext file into an entry"
+        entries: List[Entry] = []
+        for parsed_entry in parsed_entries:
+            raw_filename = entry_to_file_map[parsed_entry]
+            # Check if raw_filename is a URL. If so, save it as is. If not, convert it to a Path.
+            if type(raw_filename) == str and re.search(r"^https?://", raw_filename):
+                # Escape the URL to avoid issues with special characters
+                entry_filename = urllib3.util.parse_url(raw_filename).url
+            else:
+                entry_filename = raw_filename
+
+            # Append base filename to compiled entry for context to model
             entries.append(
                 Entry(
-                    raw=entry,
-                    file=file,
-                    compiled=f"{Path(file).stem}\n{entry}",
-                    heading=Path(file).stem,
+                    raw=parsed_entry,
+                    file=f"{entry_filename}",
+                    compiled=f"{entry_filename}\n{parsed_entry}",
+                    heading=entry_filename,
                 )
             )
+
+        logger.debug(f"Converted {len(parsed_entries)} plaintext files to entries")
         return entries

src/khoj/processor/content/text_to_entries.py

@@ -59,7 +59,7 @@ class TextToEntries(ABC):
 
     @staticmethod
     def split_entries_by_max_tokens(
-        entries: List[Entry], max_tokens: int = 256, max_word_length: int = 500
+        entries: List[Entry], max_tokens: int = 256, max_word_length: int = 500, raw_is_compiled: bool = False
     ) -> List[Entry]:
         "Split entries if compiled entry length exceeds the max tokens supported by the ML model."
         chunked_entries: List[Entry] = []
@@ -94,7 +94,7 @@ class TextToEntries(ABC):
 
                 # Clean entry of unwanted characters like \0 character
                 compiled_entry_chunk = TextToEntries.clean_field(compiled_entry_chunk)
-                entry.raw = TextToEntries.clean_field(entry.raw)
+                entry.raw = compiled_entry_chunk if raw_is_compiled else TextToEntries.clean_field(entry.raw)
                 entry.heading = TextToEntries.clean_field(entry.heading)
                 entry.file = TextToEntries.clean_field(entry.file)
 

src/khoj/routers/indexer.py

@@ -67,11 +67,10 @@ async def update(
     try:
         logger.info(f"📬 Updating content index via API call by {client} client")
         for file in files:
-            file_type, encoding = get_file_type(file.content_type)
+            file_content = file.file.read()
+            file_type, encoding = get_file_type(file.content_type, file_content)
             if file_type in index_files:
-                index_files[file_type][file.filename] = (
-                    file.file.read().decode("utf-8") if encoding == "utf-8" else file.file.read()  # type: ignore
-                )
+                index_files[file_type][file.filename] = file_content.decode(encoding) if encoding else file_content
             else:
                 logger.warning(f"Skipped indexing unsupported file type sent by {client} client: {file.filename}")
 

src/khoj/utils/fs_syncer.py

@@ -1,9 +1,11 @@
 import glob
 import logging
 import os
+from pathlib import Path
 from typing import Optional
 
 from bs4 import BeautifulSoup
+from magika import Magika
 
 from khoj.database.models import (
     LocalMarkdownConfig,
@@ -16,6 +18,7 @@ from khoj.utils.helpers import get_absolute_path, is_none_or_empty
 from khoj.utils.rawconfig import TextContentConfig
 
 logger = logging.getLogger(__name__)
+magika = Magika()
 
 
 def collect_files(search_type: Optional[SearchType] = SearchType.All, user=None) -> dict:
@@ -47,6 +50,11 @@ def construct_config_from_db(db_config) -> TextContentConfig:
 def get_plaintext_files(config: TextContentConfig) -> dict[str, str]:
     def is_plaintextfile(file: str):
         "Check if file is plaintext file"
+        # Check if file path exists
+        mime_type = magika.identify_path(Path(file)).output.mime_type
+        if mime_type != "inode/x-empty" and mime_type != "application/unknown":
+            return mime_type.startswith("text/")
+        # Use file extension to decide plaintext if file content is not identifiable
         return file.endswith(("txt", "md", "markdown", "org", "mbox", "rst", "html", "htm", "xml"))
 
     def extract_html_content(html_content: str):
@@ -65,7 +73,7 @@ def get_plaintext_files(config: TextContentConfig) -> dict[str, str]:
         logger.debug("At least one of input-files or input-file-filter is required to be specified")
         return {}
 
-    "Get all files to process"
+    # Get all plain text files to process
     absolute_plaintext_files, filtered_plaintext_files = set(), set()
     if input_files:
         absolute_plaintext_files = {get_absolute_path(jsonl_file) for jsonl_file in input_files}
@@ -209,7 +217,7 @@ def get_pdf_files(config: TextContentConfig):
         logger.debug("At least one of pdf-files or pdf-file-filter is required to be specified")
         return {}
 
-    "Get PDF files to process"
+    # Get PDF files to process
     absolute_pdf_files, filtered_pdf_files = set(), set()
     if pdf_files:
         absolute_pdf_files = {get_absolute_path(pdf_file) for pdf_file in pdf_files}

src/khoj/utils/helpers.py

@@ -19,6 +19,7 @@ from urllib.parse import urlparse
 
 import torch
 from asgiref.sync import sync_to_async
+from magika import Magika
 
 from khoj.utils import constants
 
@@ -29,6 +30,10 @@ if TYPE_CHECKING:
     from khoj.utils.rawconfig import AppConfig
 
 
+# Initialize Magika for file type identification
+magika = Magika()
+
+
 class AsyncIteratorWrapper:
     def __init__(self, obj):
         self._it = iter(obj)
@@ -88,22 +93,31 @@ def merge_dicts(priority_dict: dict, default_dict: dict):
     return merged_dict
 
 
-def get_file_type(file_type: str) -> tuple[str, str]:
+def get_file_type(file_type: str, file_content: bytes) -> tuple[str, str]:
     "Get file type from file mime type"
 
+    # Extract encoding from file_type
     encoding = file_type.split("=")[1].strip().lower() if ";" in file_type else None
     file_type = file_type.split(";")[0].strip() if ";" in file_type else file_type
-    if file_type in ["text/markdown"]:
+
+    # Infer content type from reading file content
+    try:
+        content_type = magika.identify_bytes(file_content).output.mime_type
+    except Exception:
+        # Fallback to using just file type if content type cannot be inferred
+        content_type = file_type
+
+    if file_type in ["text/markdown"] and content_type.startswith("text/"):
         return "markdown", encoding
-    elif file_type in ["text/org"]:
+    elif file_type in ["text/org"] and content_type.startswith("text/"):
         return "org", encoding
-    elif file_type in ["application/pdf"]:
+    elif file_type in ["application/pdf"] and content_type == "application/pdf":
         return "pdf", encoding
-    elif file_type in ["image/jpeg"]:
+    elif file_type in ["image/jpeg"] and content_type == "image/jpeg":
         return "jpeg", encoding
-    elif file_type in ["image/png"]:
+    elif file_type in ["image/png"] and content_type == "image/png":
         return "png", encoding
-    elif file_type in ["text/plain", "text/html", "application/xml", "text/x-rst"]:
+    elif content_type.startswith("text/"):
         return "plaintext", encoding
     else:
         return "other", encoding

tests/test_client.py

@@ -1,6 +1,5 @@
 # Standard Modules
 import os
-from io import BytesIO
 from urllib.parse import quote
 
 import pytest

tests/test_plaintext_to_entries.py

@@ -15,8 +15,6 @@ def test_plaintext_file(tmp_path):
     """
     plaintextfile = create_file(tmp_path, raw_entry)
 
-    filename = plaintextfile.stem
-
     # Act
     # Extract Entries from specified plaintext files
 
@@ -24,7 +22,7 @@ def test_plaintext_file(tmp_path):
         f"{plaintextfile}": raw_entry,
     }
 
-    entries = PlaintextToEntries.extract_plaintext_entries(entry_to_file_map=data)
+    entries = PlaintextToEntries.extract_plaintext_entries(data)
 
     # Convert each entry.file to absolute path to make them JSON serializable
     for entry in entries:
@@ -35,7 +33,7 @@ def test_plaintext_file(tmp_path):
     # Ensure raw entry with no headings do not get heading prefix prepended
     assert not entries[0].raw.startswith("#")
     # Ensure compiled entry has filename prepended as top level heading
-    assert entries[0].compiled == f"{filename}\n{raw_entry}"
+    assert entries[0].compiled == f"{plaintextfile}\n{raw_entry}"
 
 
 def test_get_plaintext_files(tmp_path):
@@ -100,6 +98,35 @@ def test_parse_html_plaintext_file(content_config, default_user: KhojUser):
     assert "<div>" not in entries[0].raw
 
 
+def test_large_plaintext_file_split_into_multiple_entries(tmp_path):
+    "Convert files with no heading to jsonl."
+    # Arrange
+    max_tokens = 256
+    normal_entry = " ".join([f"{number}" for number in range(max_tokens - 1)])
+    large_entry = " ".join([f"{number}" for number in range(max_tokens)])
+
+    normal_plaintextfile = create_file(tmp_path, normal_entry)
+    large_plaintextfile = create_file(tmp_path, large_entry)
+
+    normal_data = {f"{normal_plaintextfile}": normal_entry}
+    large_data = {f"{large_plaintextfile}": large_entry}
+
+    # Act
+    # Extract Entries from specified plaintext files
+    normal_entries = PlaintextToEntries.split_entries_by_max_tokens(
+        PlaintextToEntries.extract_plaintext_entries(normal_data),
+        max_tokens=max_tokens,
+        raw_is_compiled=True,
+    )
+    large_entries = PlaintextToEntries.split_entries_by_max_tokens(
+        PlaintextToEntries.extract_plaintext_entries(large_data), max_tokens=max_tokens, raw_is_compiled=True
+    )
+
+    # Assert
+    assert len(normal_entries) == 1
+    assert len(large_entries) == 2
+
+
 # Helper Functions
 def create_file(tmp_path: Path, entry=None, filename="test.md"):
     file_ = tmp_path / filename