midterm-submission

Dockerfile

@@ -1,42 +1,51 @@
-# Build frontend
-FROM node:18-alpine as frontend-build
-
-WORKDIR /frontend
-COPY podcraft/package*.json ./
-RUN npm install
-COPY podcraft/ .
-RUN npm run build
-
-# Build backend
-FROM python:3.11-slim
-
-WORKDIR /app
-
-# Install system dependencies
-RUN apt-get update && apt-get install -y \
-    build-essential \
-    && rm -rf /var/lib/apt/lists/*
-
-# Copy and install Python dependencies
-COPY server/requirements.txt .
-RUN pip install --no-cache-dir -r requirements.txt
-
-# Copy backend code
-COPY server/ .
-
-# Create necessary directories with proper permissions
-RUN mkdir -p audio_storage transcripts logs && \
-    chmod -R 777 audio_storage transcripts logs && \
-    chown -R nobody:nogroup audio_storage transcripts logs
-
-# Copy frontend build to a static directory
-COPY --from=frontend-build /frontend/dist /app/static
-
-# Switch to non-root user
-USER nobody
-
-# Expose port
-EXPOSE 7860
-
-# Start FastAPI application
+# Build frontend
+FROM node:18-alpine as frontend-build
+
+WORKDIR /frontend
+COPY podcraft/package*.json ./
+RUN npm install
+COPY podcraft/ .
+RUN npm run build
+
+# Build backend
+FROM python:3.11-slim
+
+WORKDIR /app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create a non-root user to run the application
+RUN useradd -m -u 1000 appuser
+
+# Copy and install Python dependencies
+COPY server/requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy backend code
+COPY server/ .
+
+# Create necessary directories
+RUN mkdir -p audio_storage transcripts logs
+
+# Set ownership and permissions for application directories
+RUN chown -R appuser:appuser /app \
+    && chmod -R 755 /app \
+    && chmod -R 777 /app/audio_storage \
+    && chmod -R 777 /app/transcripts \
+    && chmod -R 777 /app/logs
+
+# Copy frontend build to a static directory
+COPY --from=frontend-build /frontend/dist /app/static
+RUN chown -R appuser:appuser /app/static
+
+# Switch to non-root user
+USER appuser
+
+# Expose port
+EXPOSE 7860
+
+# Start FastAPI application
 CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "7860"] 

server/utils.py

@@ -1,85 +1,52 @@
-import os
-import json
-import uuid
-import logging
-import stat
-
-# Configure logging
-logger = logging.getLogger(__name__)
-
-# Create transcripts directory if it doesn't exist
-TRANSCRIPTS_DIR = os.path.join(os.path.dirname(__file__), "transcripts")
-os.makedirs(TRANSCRIPTS_DIR, exist_ok=True)
-TRANSCRIPTS_FILE = os.path.join(TRANSCRIPTS_DIR, "podcasts.json")
-
-# Ensure directory has correct permissions
-try:
-    os.chmod(TRANSCRIPTS_DIR, stat.S_IRWXU | stat.S_IRWXG | stat.S_IRWXO)  # 0777 permissions
-except Exception as e:
-    logger.warning(f"Could not set permissions on transcripts directory: {e}")
-
-# Initialize empty transcripts file if it doesn't exist
-if not os.path.exists(TRANSCRIPTS_FILE):
-    try:
-        with open(TRANSCRIPTS_FILE, 'w') as f:
-            json.dump([], f)
-        os.chmod(TRANSCRIPTS_FILE, stat.S_IRWXU | stat.S_IRWXG | stat.S_IRWXO)  # 0777 permissions
-    except Exception as e:
-        logger.warning(f"Could not initialize transcripts file: {e}")
-
-def save_transcript(podcast_script: str, user_query: str) -> None:
-    """Save podcast transcript to JSON file."""
-    # Create new transcript entry
-    transcript = {
-        "id": str(uuid.uuid4()),
-        "podcastScript": podcast_script,
-        "topic": user_query
-    }
-    
-    try:
-        # Ensure directory exists with correct permissions
-        os.makedirs(TRANSCRIPTS_DIR, exist_ok=True)
-        os.chmod(TRANSCRIPTS_DIR, stat.S_IRWXU | stat.S_IRWXG | stat.S_IRWXO)
-        
-        # Load existing transcripts
-        transcripts = []
-        if os.path.exists(TRANSCRIPTS_FILE):
-            try:
-                with open(TRANSCRIPTS_FILE, 'r') as f:
-                    transcripts = json.load(f)
-                    if not isinstance(transcripts, list):
-                        transcripts = []
-            except (json.JSONDecodeError, PermissionError) as e:
-                logger.warning(f"Error reading transcripts file: {e}, initializing empty list")
-                transcripts = []
-        
-        # Append new transcript
-        transcripts.append(transcript)
-        
-        # Save updated transcripts
-        try:
-            with open(TRANSCRIPTS_FILE, 'w') as f:
-                json.dump(transcripts, f, indent=2)
-            os.chmod(TRANSCRIPTS_FILE, stat.S_IRWXU | stat.S_IRWXG | stat.S_IRWXO)
-            logger.info("Successfully saved transcript")
-        except PermissionError:
-            # Try creating a new file in case the original has wrong permissions
-            temp_file = os.path.join(TRANSCRIPTS_DIR, f"podcasts_temp_{uuid.uuid4()}.json")
-            with open(temp_file, 'w') as f:
-                json.dump(transcripts, f, indent=2)
-            os.chmod(temp_file, stat.S_IRWXU | stat.S_IRWXG | stat.S_IRWXO)
-            os.replace(temp_file, TRANSCRIPTS_FILE)
-            logger.info("Successfully saved transcript using temporary file")
-            
-    except Exception as e:
-        logger.error(f"Error saving transcript: {str(e)}")
-        # Try one last time with a new file
-        try:
-            temp_file = os.path.join(TRANSCRIPTS_DIR, f"podcasts_new_{uuid.uuid4()}.json")
-            with open(temp_file, 'w') as f:
-                json.dump([transcript], f, indent=2)
-            os.chmod(temp_file, stat.S_IRWXU | stat.S_IRWXG | stat.S_IRWXO)
-            logger.info("Saved single transcript to new file")
-        except Exception as e2:
-            logger.error(f"Final attempt to save transcript failed: {str(e2)}")
-            raise 
+import os
+import json
+import uuid
+import logging
+
+# Configure logging
+logger = logging.getLogger(__name__)
+
+# Create transcripts directory if it doesn't exist
+TRANSCRIPTS_DIR = os.path.join(os.path.dirname(__file__), "transcripts")
+os.makedirs(TRANSCRIPTS_DIR, exist_ok=True)
+TRANSCRIPTS_FILE = os.path.join(TRANSCRIPTS_DIR, "podcasts.json")
+
+def save_transcript(podcast_script: str, user_query: str) -> None:
+    """Save podcast transcript to JSON file."""
+    # Create new transcript entry
+    transcript = {
+        "id": str(uuid.uuid4()),
+        "podcastScript": podcast_script,
+        "topic": user_query
+    }
+    
+    try:
+        # Load existing transcripts
+        if os.path.exists(TRANSCRIPTS_FILE):
+            try:
+                with open(TRANSCRIPTS_FILE, 'r') as f:
+                    transcripts = json.load(f)
+                    if not isinstance(transcripts, list):
+                        transcripts = []
+            except json.JSONDecodeError:
+                logger.warning("Error reading transcripts file, initializing empty list")
+                transcripts = []
+        else:
+            transcripts = []
+        
+        # Append new transcript
+        transcripts.append(transcript)
+        
+        # Save updated transcripts
+        with open(TRANSCRIPTS_FILE, 'w') as f:
+            json.dump(transcripts, f, indent=2)
+            logger.info("Successfully saved transcript")
+            
+    except Exception as e:
+        logger.error(f"Error saving transcript: {str(e)}")
+        # Create directory if it doesn't exist
+        os.makedirs(os.path.dirname(TRANSCRIPTS_FILE), exist_ok=True)
+        # Try to save just this transcript
+        with open(TRANSCRIPTS_FILE, 'w') as f:
+            json.dump([transcript], f, indent=2)
+            logger.info("Saved single transcript after error")