Fix temp dir for thumbnails

package.json

@@ -1,7 +1,7 @@
 {
-  "name": "subtitle-merge",
+  "name": "deafblind-video-assistant",
   "private": true,
-  "version": "0.1.0",
+  "version": "1.0.0",
   "type": "module",
   "scripts": {
     "dev": "vite",

src-tauri/src/lib.rs

@@ -5,6 +5,7 @@ use std::io::BufRead;
 use tauri::{Runtime, State, Emitter};
 use tempfile::TempDir;
 use std::fs;
+use base64::Engine;
 
 #[derive(Debug, thiserror::Error)]
 pub enum Error {
@@ -60,7 +61,6 @@ pub struct TranscriptionArgs {
 #[derive(Debug, Serialize)]
 #[serde(rename_all = "camelCase")]
 pub struct TranscriptionResult {
-    pub visual_description: String,
     pub narrative: String,
 }
 
@@ -70,8 +70,27 @@ pub struct Thumbnail {
     pub time: u32,
 }
 
-// Note: Removed unused Gemini request/response structs since we're handling 
+pub struct ThumbnailState {
-// the API interaction through the Python script
+    temp_dir: Option<TempDir>,
+}
+
+impl Default for ThumbnailState {
+    fn default() -> Self {
+        Self {
+            temp_dir: None,
+        }
+    }
+}
+
+impl ThumbnailState {
+    pub fn set_temp_dir(&mut self, dir: TempDir) {
+        self.temp_dir = Some(dir);
+    }
+
+    pub fn get_temp_dir(&self) -> Option<&TempDir> {
+        self.temp_dir.as_ref()
+    }
+}
 
 #[derive(Debug, Serialize, Clone)]
 pub struct ProgressUpdate {
@@ -201,24 +220,21 @@ pub async fn test_gemini_api_impl(api_key: &str) -> Result<(), Error> {
     Ok(())
 }
 
-pub async fn extract_thumbnails_impl(video_path: &str, interval: u32) -> Result<Vec<Thumbnail>, Error> {
+pub async fn extract_thumbnails_impl(
-    // Create a directory in the system temp directory
+    video_path: &str, 
-    let temp_dir = std::env::temp_dir().join("video_thumbs");
+    interval: u32,
-    let thumb_dir = temp_dir.join(format!("session_{}", std::time::SystemTime::now()
+    thumbnail_state: State<'_, Mutex<ThumbnailState>>
-        .duration_since(std::time::UNIX_EPOCH)
+) -> Result<Vec<Thumbnail>, Error> {
-        .unwrap()
+    // Create a new temporary directory
-        .as_secs()));
+    let temp_dir = TempDir::new().map_err(|e| Error::IoError(e))?;
-
+    println!("Extracting thumbnails to temporary directory: {:?}", temp_dir.path());
-    std::fs::create_dir_all(&thumb_dir)
-        .map_err(|e| Error::IoError(e))?;
-
-    println!("Extracting thumbnails to: {:?}", thumb_dir);
     
     let duration = get_video_duration(video_path).await? as u32;
     let mut thumbnails = Vec::new();
 
+    // Process all frames before moving temp_dir into state
     for time in (0..duration).step_by(interval as usize) {
-        let output_path = thumb_dir.join(format!("thumb_{}.jpg", time));
+        let output_path = temp_dir.path().join(format!("thumb_{}.jpg", time));
         match extract_frame(video_path, time, output_path.to_str().unwrap()).await {
             Ok(_) => {
                 println!("Successfully extracted frame at time {}", time);
@@ -238,6 +254,8 @@ pub async fn extract_thumbnails_impl(video_path: &str, interval: u32) -> Result<
         return Err(Error::FFmpegError("Failed to extract any thumbnails".to_string()));
     }
 
+    // Store the TempDir in the state only after we're done using it
+    thumbnail_state.lock().unwrap().set_temp_dir(temp_dir);
     Ok(thumbnails)
 }
 
@@ -258,7 +276,7 @@ pub async fn process_transcription_impl(args: TranscriptionArgs) -> Result<Trans
         
         // Save base64 image to temp file
         let frame_path = temp_dir.path().join(format!("frame_{}.jpg", frame.time));
-        let image_data = base64::decode(&frame.base64_image)
+        let image_data = base64::engine::general_purpose::STANDARD.decode(&frame.base64_image)
             .map_err(|e| Error::ImageError(format!("Failed to decode base64 image: {}", e)))?;
         fs::write(&frame_path, image_data)
             .map_err(|e| Error::IoError(e))?;
@@ -279,12 +297,6 @@ pub async fn process_transcription_impl(args: TranscriptionArgs) -> Result<Trans
         .collect::<Vec<_>>()
         .join("\n\n");
 
-    // Combine all visual descriptions for the raw visual description output
-    let visual_description = frame_descriptions.iter()
-        .map(|(time, desc)| format!("At timestamp {}:\n{}", time, desc))
-        .collect::<Vec<_>>()
-        .join("\n\n");
-
     // Process subtitle content if provided
     let narrative = if let Some(subtitle_path) = &args.subtitle_path {
         println!("\nReading and parsing subtitle content...");
@@ -366,24 +378,19 @@ pub async fn process_transcription_impl(args: TranscriptionArgs) -> Result<Trans
     };
 
     println!("\n=== Final Transcription Result ===");
-    println!("\nVisual Description:");
-    println!("{}", visual_description);
     println!("\nNarrative:");
     println!("{}", narrative);
 
     // Create the result struct
     let result = TranscriptionResult {
-        visual_description: visual_description.clone(),
         narrative: narrative.clone(),
     };
 
     // Log the final result structure
     println!("\nReturning transcription result with:");
-    println!("- Visual description length: {}", result.visual_description.len());
     println!("- Narrative length: {}", result.narrative.len());
     println!("\nFinal TranscriptionResult struct:");
     println!("{{");
-    println!("  \"visualDescription\": \"{}\",", result.visual_description);
     println!("  \"narrative\": \"{}\"", result.narrative);
     println!("}}");
 

src-tauri/src/main.rs

@@ -4,11 +4,12 @@
 use subtitle_merge_lib::{
     ProgressState, MergeArgs, Error, merge_video_subtitle_impl, check_ffmpeg,
     test_gemini_api_impl, extract_thumbnails_impl, process_transcription_impl,
-    TranscriptionArgs, get_video_duration
+    TranscriptionArgs, get_video_duration, ThumbnailState
 };
 use std::fs;
-use base64::prelude::*;
+use base64::Engine;
 use tauri::Runtime;
+use std::sync::Mutex;
 
 #[tauri::command]
 async fn check_dependencies() -> Result<(), Error> {
@@ -40,8 +41,12 @@ async fn get_video_duration_command(path: String) -> Result<f32, Error> {
 }
 
 #[tauri::command]
-async fn extract_thumbnails(path: String, interval: u32) -> Result<Vec<subtitle_merge_lib::Thumbnail>, Error> {
+async fn extract_thumbnails(
-    extract_thumbnails_impl(&path, interval).await
+    path: String,
+    interval: u32,
+    thumbnail_state: tauri::State<'_, Mutex<ThumbnailState>>,
+) -> Result<Vec<subtitle_merge_lib::Thumbnail>, Error> {
+    extract_thumbnails_impl(&path, interval, thumbnail_state).await
 }
 
 #[tauri::command]
@@ -50,15 +55,41 @@ async fn process_transcription(args: TranscriptionArgs) -> Result<subtitle_merge
 }
 
 #[tauri::command]
-async fn generate_thumbnails(video_path: String) -> Result<Vec<subtitle_merge_lib::Thumbnail>, Error> {
+async fn generate_thumbnails(
+    video_path: String,
+    thumbnail_state: tauri::State<'_, Mutex<ThumbnailState>>,
+) -> Result<Vec<subtitle_merge_lib::Thumbnail>, Error> {
     // Generate thumbnails every 10 seconds
-    extract_thumbnails_impl(&video_path, 10).await
+    extract_thumbnails_impl(&video_path, 10, thumbnail_state).await
 }
 
 #[tauri::command]
-async fn read_thumbnail(path: String) -> Result<String, Error> {
+async fn read_thumbnail(
-    let data = fs::read(&path).map_err(|e| Error::IoError(e))?;
+    path: String,
-    Ok(BASE64_STANDARD.encode(&data))
+    thumbnail_state: tauri::State<'_, Mutex<ThumbnailState>>,
+) -> Result<String, Error> {
+    // Verify the path is within our temp directory to prevent unauthorized access
+    let state = thumbnail_state.lock().unwrap();
+    if let Some(temp_dir) = state.get_temp_dir() {
+        let temp_path = temp_dir.path();
+        let requested_path = std::path::Path::new(&path);
+        
+        // Check if the requested path is within our temp directory
+        if !requested_path.starts_with(temp_path) {
+            return Err(Error::IoError(std::io::Error::new(
+                std::io::ErrorKind::PermissionDenied,
+                "Attempted to access file outside of temporary directory",
+            )));
+        }
+        
+        let data = fs::read(&path).map_err(|e| Error::IoError(e))?;
+        Ok(base64::engine::general_purpose::STANDARD.encode(&data))
+    } else {
+        Err(Error::IoError(std::io::Error::new(
+            std::io::ErrorKind::NotFound,
+            "No active thumbnail session",
+        )))
+    }
 }
 
 fn main() {
@@ -67,6 +98,7 @@ fn main() {
         .plugin(tauri_plugin_dialog::init())
         .plugin(tauri_plugin_fs::init())
         .manage(ProgressState::default())
+        .manage(Mutex::new(ThumbnailState::default()))
         .setup(|_app| {
             Ok(())
         })

src-tauri/tauri.conf.json

@@ -1,8 +1,8 @@
 {
   "$schema": "https://raw.githubusercontent.com/tauri-apps/tauri/dev/tooling/cli/schema.json",
-  "productName": "Video Subtitle Merger 2.0",
+  "productName": "DeafBlind Video Assistant",
-  "version": "0.1.0",
+  "version": "1.0.0",
-  "identifier": "com.subtitle-merge.app",
+  "identifier": "com.deafblind-video-assistant.app",
   "app": {
     "security": {
       "csp": null,
@@ -12,7 +12,7 @@
       {
         "fullscreen": false,
         "resizable": true,
-        "title": "Video Subtitle Merger 2.0",
+        "title": "DeafBlind Video Assistant",
         "width": 800,
         "height": 600,
         "visible": true,

src/App.tsx

@@ -41,18 +41,8 @@ function App() {
   return (
     <div className="min-h-screen bg-gray-100 py-8 px-4">
       <div className="max-w-2xl mx-auto bg-white rounded-lg shadow-md p-6">
-        <div className="flex justify-between items-center mb-8">
+        <div className="mb-8">
-          <h1 className="text-2xl font-bold">Video Subtitle Merger <span className="text-blue-500">3.0</span></h1>
+          <h1 className="text-2xl font-bold text-center">DeafBlind Video Assistant <span className="text-blue-500">1.0</span></h1>
-          <button
-            onClick={() => setIsSettingsOpen(true)}
-            className="inline-flex items-center px-3 py-2 border border-transparent text-sm font-medium rounded-md text-gray-700 bg-gray-100 hover:bg-gray-200 focus:outline-none focus:ring-2 focus:ring-offset-2 focus:ring-blue-500"
-          >
-            <svg className="w-5 h-5 mr-2" fill="none" stroke="currentColor" viewBox="0 0 24 24">
-              <path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M10.325 4.317c.426-1.756 2.924-1.756 3.35 0a1.724 1.724 0 002.573 1.066c1.543-.94 3.31.826 2.37 2.37a1.724 1.724 0 001.065 2.572c1.756.426 1.756 2.924 0 3.35a1.724 1.724 0 00-1.066 2.573c.94 1.543-.826 3.31-2.37 2.37a1.724 1.724 0 00-2.572 1.065c-.426 1.756-2.924 1.756-3.35 0a1.724 1.724 0 00-2.573-1.066c-1.543.94-3.31-.826-2.37-2.37a1.724 1.724 0 00-1.065-2.572c-1.756-.426-1.756-2.924 0-3.35a1.724 1.724 0 001.066-2.573c-.94-1.543.826-3.31 2.37-2.37.996.608 2.296.07 2.572-1.065z" />
-              <path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M15 12a3 3 0 11-6 0 3 3 0 016 0z" />
-            </svg>
-            Settings
-          </button>
         </div>
 
         {error && (
@@ -64,6 +54,18 @@ function App() {
 
         {!selectedTask ? (
           <div className="space-y-6">
+            <div className="flex justify-end mb-4">
+              <button
+                onClick={() => setIsSettingsOpen(true)}
+                className="inline-flex items-center px-3 py-2 border border-transparent text-sm font-medium rounded-md text-gray-700 bg-gray-100 hover:bg-gray-200 focus:outline-none focus:ring-2 focus:ring-offset-2 focus:ring-blue-500"
+              >
+                <svg className="w-5 h-5 mr-2" fill="none" stroke="currentColor" viewBox="0 0 24 24">
+                  <path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M10.325 4.317c.426-1.756 2.924-1.756 3.35 0a1.724 1.724 0 002.573 1.066c1.543-.94 3.31.826 2.37 2.37a1.724 1.724 0 001.065 2.572c1.756.426 1.756 2.924 0 3.35a1.724 1.724 0 00-1.066 2.573c.94 1.543-.826 3.31-2.37 2.37a1.724 1.724 0 00-2.572 1.065c-.426 1.756-2.924 1.756-3.35 0a1.724 1.724 0 00-2.573-1.066c-1.543.94-3.31-.826-2.37-2.37a1.724 1.724 0 00-1.065-2.572c-1.756-.426-1.756-2.924 0-3.35a1.724 1.724 0 001.066-2.573c-.94-1.543.826-3.31 2.37-2.37.996.608 2.296.07 2.572-1.065z" />
+                  <path strokeLinecap="round" strokeLinejoin="round" strokeWidth={2} d="M15 12a3 3 0 11-6 0 3 3 0 016 0z" />
+                </svg>
+                Settings
+              </button>
+            </div>
             <h2 className="text-lg font-semibold text-center mb-8">Choose a Task</h2>
             <div className="grid grid-cols-2 gap-6">
               <button

src/components/ProcessingAnimation.tsx

@@ -0,0 +1,51 @@
+import React from 'react';
+import '../styles/ProcessingAnimation.css';
+
+export const ProcessingAnimation: React.FC = () => {
+  return (
+    <div className="flex flex-col items-center justify-center py-8 space-y-4">
+      {/* Brain container with pulse and glow animation */}
+      <div className="relative">
+        {/* Brain icon with pulse animation */}
+        <div className="w-16 h-16 animate-pulse-gentle text-gray-600">
+          <svg
+            xmlns="http://www.w3.org/2000/svg"
+            viewBox="0 0 24 24"
+            fill="none"
+            stroke="currentColor"
+            strokeWidth="1.5"
+            strokeLinecap="round"
+            strokeLinejoin="round"
+            className="animate-spin-slow"
+          >
+            <path d="M9.5 2A2.5 2.5 0 0 1 12 4.5v15a2.5 2.5 0 0 1-4.96.44 2.5 2.5 0 0 1-2.96-3.08 3 3 0 0 1-.34-5.58 2.5 2.5 0 0 1 1.32-4.24 2.5 2.5 0 0 1 1.98-3A2.5 2.5 0 0 1 9.5 2Z" />
+            <path d="M14.5 2A2.5 2.5 0 0 0 12 4.5v15a2.5 2.5 0 0 0 4.96.44 2.5 2.5 0 0 0 2.96-3.08 3 3 0 0 0 .34-5.58 2.5 2.5 0 0 0-1.32-4.24 2.5 2.5 0 0 0-1.98-3A2.5 2.5 0 0 0 14.5 2Z" />
+          </svg>
+        </div>
+
+        {/* Glowing effect */}
+        <div className="absolute inset-0 animate-glow bg-blue-400 rounded-full opacity-20" />
+      </div>
+
+      {/* Thought bubbles */}
+      <div className="relative h-16 w-16">
+        {/* Multiple bubbles with different animations */}
+        {[...Array(3)].map((_, i) => (
+          <div
+            key={i}
+            className="absolute left-1/2 bottom-0 w-3 h-3 rounded-full bg-white border-2 border-blue-400 thought-bubble opacity-0"
+            style={{
+              transform: 'translateX(-50%)',
+            }}
+          />
+        ))}
+      </div>
+
+      {/* Processing text */}
+      <p className="text-gray-600 font-medium animate-pulse">
+        Processing with AI...
+      </p>
+
+    </div>
+  );
+};

src/components/TranscriptionTask.tsx

@@ -3,6 +3,7 @@ import { invoke } from '@tauri-apps/api/core';
 import { FileSelector } from './FileSelector';
 import { GeminiSettings } from './GeminiSettings';
 import { VideoTimeline } from './VideoTimeline';
+import { ProcessingAnimation } from './ProcessingAnimation';
 
 interface FileState {
   path: string;
@@ -10,7 +11,6 @@ interface FileState {
 }
 
 interface TranscriptionState {
-  visualDescription: string;
   narrative: string;
 }
 
@@ -39,7 +39,6 @@ export const TranscriptionTask: React.FC<TranscriptionTaskProps> = ({
 }) => {
   const [videoFile, setVideoFile] = useState<FileState | null>(null);
   const [subtitleFile, setSubtitleFile] = useState<FileState | null>(null);
-  const [progress, setProgress] = useState<number>(0);
   const [isProcessing, setIsProcessing] = useState(false);
   const [error, setError] = useState<string | null>(null);
   const [selectedFrames, setSelectedFrames] = useState<SelectedFrame[]>([]);
@@ -68,15 +67,12 @@ export const TranscriptionTask: React.FC<TranscriptionTaskProps> = ({
     }
 
     setIsProcessing(true);
-    setProgress(0);
     setError(null);
     setTranscription(null);
 
     try {
-      setProgress(10); // Starting
       console.log('Starting transcription process...');
       
-      setProgress(20); // Processing frames
       const transcriptionResult = await invoke<TranscriptionState>('process_transcription', {
         args: {
           video_path: videoFile.path,
@@ -92,20 +88,13 @@ export const TranscriptionTask: React.FC<TranscriptionTaskProps> = ({
         }
       });
       
-      // Validate and clean the content
+      // Clean the content
-      const visualDescription = String(transcriptionResult.visualDescription || '').trim();
       const narrative = String(transcriptionResult.narrative || '').trim();
       
-      if (!visualDescription) {
-        throw new Error('Visual description is missing from the response');
-      }
-
       setTranscription({
-        visualDescription,
         narrative
       });
       
-      setProgress(100); // Complete
     } catch (error) {
       console.error('Transcription error:', error);
       setError(`Transcription error: ${error}`);
@@ -155,38 +144,19 @@ export const TranscriptionTask: React.FC<TranscriptionTaskProps> = ({
         />
       )}
 
+      {isProcessing && <ProcessingAnimation />}
+
       {transcription && (
         <div className="mt-6 space-y-4">
-          <h3 className="text-lg font-semibold">DeafBlind Accessibility Transcription</h3>
+          <h3 className="text-lg font-semibold">Scene Narrative</h3>
-          <div className="h-[400px] overflow-y-auto p-4 bg-gray-50 rounded-lg text-sm space-y-6">
+          <div className="h-[400px] overflow-y-auto p-4 bg-gray-50 rounded-lg text-sm">
-            <div>
+            <div className="bg-white p-4 rounded border border-gray-200">
-              <h4 className="font-semibold text-gray-700 mb-2">Visual Description</h4>
+              <p className="whitespace-pre-wrap leading-relaxed">{transcription.narrative}</p>
-              <div className="bg-white p-4 rounded border border-gray-200">
-                <p className="whitespace-pre-wrap leading-relaxed">{transcription.visualDescription}</p>
-              </div>
-            </div>
-            <div>
-              <h4 className="font-semibold text-gray-700 mb-2">Narrative</h4>
-              <div className="bg-white p-4 rounded border border-gray-200">
-                <p className="whitespace-pre-wrap leading-relaxed">{transcription.narrative}</p>
-              </div>
             </div>
           </div>
         </div>
       )}
 
-      <div className="space-y-2">
-        <div className="h-2.5 bg-gray-200 rounded-full">
-          <div 
-            className="h-2.5 bg-blue-600 rounded-full transition-all duration-300"
-            style={{ width: `${progress}%` }}
-          />
-        </div>
-        <p className="text-center text-sm text-gray-600">
-          {isProcessing ? `${Math.round(progress)}%` : ''}
-        </p>
-      </div>
-
       {error && (
         <div className="bg-red-100 border border-red-400 text-red-700 px-4 py-3 rounded relative mb-4">
           <strong className="font-bold">Error: </strong>

src/styles/ProcessingAnimation.css

@@ -0,0 +1,33 @@
+@keyframes float {
+  0% {
+    transform: translate(-50%, 0) scale(0.5);
+    opacity: 0;
+  }
+  50% {
+    transform: translate(-50%, -40px) scale(1);
+    opacity: 1;
+  }
+  100% {
+    transform: translate(-50%, -80px) scale(0.5);
+    opacity: 0;
+  }
+}
+
+.thought-bubble {
+  animation: float ease-in-out infinite;
+}
+
+.thought-bubble:nth-child(1) {
+  animation-duration: 1.5s;
+  animation-delay: 0s;
+}
+
+.thought-bubble:nth-child(2) {
+  animation-duration: 2s;
+  animation-delay: 0.5s;
+}
+
+.thought-bubble:nth-child(3) {
+  animation-duration: 2.5s;
+  animation-delay: 1s;
+}

tailwind.config.js

@@ -15,6 +15,22 @@ export default {
       spacing: {
         '128': '32rem',
       },
+      animation: {
+        'spin-slow': 'spin 8s linear infinite',
+        'pulse-gentle': 'pulse 2s ease-in-out infinite',
+        'glow': 'ping 2s ease-in-out infinite',
+      },
+      keyframes: {
+        ping: {
+          '0%': { transform: 'scale(1)', opacity: '0.2' },
+          '50%': { transform: 'scale(1.2)', opacity: '0.3' },
+          '100%': { transform: 'scale(1)', opacity: '0.2' },
+        },
+        pulse: {
+          '0%, 100%': { transform: 'scale(1)' },
+          '50%': { transform: 'scale(1.05)' },
+        },
+      },
     },
   },
   plugins: [],