diff --git a/.env b/.env
index a860be4..0c0e8b8 100644
--- a/.env
+++ b/.env
@@ -1,60 +1,60 @@
-# Application Configuration
-# ========================
-
-# Base URL for the application (required, string)
-# Format: http://hostname:port or https://hostname:port
-BASE_URL=http://localhost:8000
-
-# CPU Limit for container (optional, float)
-# Number of CPU cores to allocate (e.g., 0.5, 1, 2)
-# Default: 2 (will be used if not specified)
-CPU_LIMIT=2
-
-# Snippet character limit (optional, integer)
-# Maximum length for text snippets in characters
-# Default: 100
-SNIPPET_CHAR_LIMIT=100
-
-# Debug mode (optional, boolean)
-# Enable debug output when set to True
-# Default: False
-DEBUG=False
-
-# Application port (optional, integer)
-# Port the application listens on
-# Default: 5000
-PORT=5000
-
-
-# Elasticsearch Configuration
-# ==========================
-
-# Elasticsearch host (required, string)
-# Hostname or IP of Elasticsearch service
-ELASTICSEARCH_HOST=elasticsearch
-
-# Elasticsearch username (sensitive, required, string)
-# Admin username for Elasticsearch
-ELASTICSEARCH_USERNAME=admin
-
-# Elasticsearch password (sensitive, required, string)
-# Admin password for Elasticsearch
-ELASTICSEARCH_PASSWORD=password
-
-
-# File Storage Configuration
-# =========================
-
-# SMB share path (optional, string)
-# Local path where books are mounted
-# Default: ./smb_share
-SMB_SHARE_PATH=./smb_share
-
-# Admin Credentials
-# ================
-
-# Admin username for API management (required, string)
-ADMIN_USER=admin
-
-# Admin password for API management (required, string)
+# Application Configuration
+# ========================
+
+# Base URL for the application (required, string)
+# Format: http://hostname:port or https://hostname:port
+BASE_URL=http://localhost:8000
+
+# CPU Limit for container (optional, float)
+# Number of CPU cores to allocate (e.g., 0.5, 1, 2)
+# Default: 2 (will be used if not specified)
+CPU_LIMIT=2
+
+# Snippet character limit (optional, integer)
+# Maximum length for text snippets in characters
+# Default: 100
+SNIPPET_CHAR_LIMIT=100
+
+# Debug mode (optional, boolean)
+# Enable debug output when set to True
+# Default: False
+DEBUG=False
+
+# Application port (optional, integer)
+# Port the application listens on
+# Default: 5000
+PORT=5000
+
+
+# Elasticsearch Configuration
+# ==========================
+
+# Elasticsearch host (required, string)
+# Hostname or IP of Elasticsearch service
+ELASTICSEARCH_HOST=elasticsearch
+
+# Elasticsearch username (sensitive, required, string)
+# Admin username for Elasticsearch
+ELASTICSEARCH_USERNAME=admin
+
+# Elasticsearch password (sensitive, required, string)
+# Admin password for Elasticsearch
+ELASTICSEARCH_PASSWORD=password
+
+
+# File Storage Configuration
+# =========================
+
+# SMB share path (optional, string)
+# Local path where books are mounted
+# Default: ./smb_share
+SMB_SHARE_PATH=./smb_share
+
+# Admin Credentials
+# ================
+
+# Admin username for API management (required, string)
+ADMIN_USER=admin
+
+# Admin password for API management (required, string)
ADMIN_PASSWORD=securepassword123
\ No newline at end of file
diff --git a/.github/workflows/test-epub-viewer.yml b/.github/workflows/test-epub-viewer.yml
index 52a723a..2fc6597 100644
--- a/.github/workflows/test-epub-viewer.yml
+++ b/.github/workflows/test-epub-viewer.yml
@@ -1,39 +1,39 @@
-name: Test EPUB Viewer
-
-on:
- push:
- branches: [ main ]
- pull_request:
- branches: [ main ]
-
-jobs:
- test:
- runs-on: ubuntu-latest
-
- steps:
- - uses: actions/checkout@v3
-
- - name: Set up Python
- uses: actions/setup-python@v4
- with:
- python-version: '3.10'
-
- - name: Install dependencies
- run: |
- python -m pip install --upgrade pip
- pip install pytest
- pip install flask elasticsearch ebooklib beautifulsoup4 PyPDF2
- if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
-
- - name: Run tests
- run: |
- cd api
- python -m pytest test_epub_viewer.py -v
-
- - name: Run integration tests with Playwright
- run: |
- pip install playwright pytest-playwright
- playwright install
- cd api
- python -m pytest test_epub_viewer_integration.py -v
+name: Test EPUB Viewer
+
+on:
+ push:
+ branches: [ main ]
+ pull_request:
+ branches: [ main ]
+
+jobs:
+ test:
+ runs-on: ubuntu-latest
+
+ steps:
+ - uses: actions/checkout@v3
+
+ - name: Set up Python
+ uses: actions/setup-python@v4
+ with:
+ python-version: '3.10'
+
+ - name: Install dependencies
+ run: |
+ python -m pip install --upgrade pip
+ pip install pytest
+ pip install flask elasticsearch ebooklib beautifulsoup4 PyPDF2
+ if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
+
+ - name: Run tests
+ run: |
+ cd api
+ python -m pytest test_epub_viewer.py -v
+
+ - name: Run integration tests with Playwright
+ run: |
+ pip install playwright pytest-playwright
+ playwright install
+ cd api
+ python -m pytest test_epub_viewer_integration.py -v
if: false # Disabled until we create the integration tests with Playwright
\ No newline at end of file
diff --git a/.gitignore b/.gitignore
index bf64a5c..999ef3a 100644
--- a/.gitignore
+++ b/.gitignore
@@ -1,30 +1,30 @@
-# Ignore all EPUB files in smb_share
-smb_share/*.epub
-
-# Ignore sample text file
-smb_share/sample.txt
-
-# Python cache
-__pycache__/
-*.py[cod]
-*$py.class
-
-# Virtual environment
-venv/
-
-# IDE specific files
-.vscode/
-.idea/
-
-# Logs and databases
-*.log
-*.sqlite
-
-# OS generated files
-.DS_Store
-.DS_Store?
-._*
-.Spotlight-V100
-.Trashes
-ehthumbs.db
+# Ignore all EPUB files in smb_share
+smb_share/*.epub
+
+# Ignore sample text file
+smb_share/sample.txt
+
+# Python cache
+__pycache__/
+*.py[cod]
+*$py.class
+
+# Virtual environment
+venv/
+
+# IDE specific files
+.vscode/
+.idea/
+
+# Logs and databases
+*.log
+*.sqlite
+
+# OS generated files
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
Thumbs.db
\ No newline at end of file
diff --git a/Dockerfile b/Dockerfile
index 06b0849..c670ef8 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -1,29 +1,29 @@
-FROM python:3.9-alpine
-
-WORKDIR /app
-
-# Install dependencies
-RUN pip install flask elasticsearch ebooklib beautifulsoup4 PyPDF2 pytz
-
-# Create books directory with proper permissions
-RUN mkdir -p /books && chmod 777 /books
-
-# Copy the API code and static files
-COPY src/api/app.py .
-COPY src/api/static /app/static
-COPY src/api/templates /app/templates
-
-# Expose the API port
-EXPOSE 5000
-
-# Copy the indexing script
-COPY src/core/index.py .
-
-# Copy the test file
-COPY tests/unit/test_app.py .
-
-# Add a dummy file to invalidate cache
-ADD dummy.txt .
-
-# Command to run the API
+FROM python:3.9-alpine
+
+WORKDIR /app
+
+# Install dependencies
+RUN pip install flask elasticsearch ebooklib beautifulsoup4 PyPDF2 pytz
+
+# Create books directory with proper permissions
+RUN mkdir -p /books && chmod 777 /books
+
+# Copy the API code and static files
+COPY src/api/app.py .
+COPY src/api/static /app/static
+COPY src/api/templates /app/templates
+
+# Expose the API port
+EXPOSE 5000
+
+# Copy the indexing script
+COPY src/core/index.py .
+
+# Copy the test file
+COPY tests/unit/test_app.py .
+
+# Add a dummy file to invalidate cache
+ADD dummy.txt .
+
+# Command to run the API
CMD ["python", "app.py"]
\ No newline at end of file
diff --git a/ai.md b/ai.md
index 702db09..9f302d4 100644
--- a/ai.md
+++ b/ai.md
@@ -1,33 +1,33 @@
-# Final Deployment Status
-
-## Configuration Summary:
-1. **Container Auto-Restart**:
- - Both services configured with `restart: unless-stopped`
- - Containers will automatically restart on failures
-
-2. **Resource Limits**:
- - CPU: `${CPU_LIMIT}` cores
- - Memory: 2GB limit
-
-3. **Dependencies**:
- - pytz installed in container (version 2025.2)
- - All required Python packages verified
- - Dockerfile updated to include pytz for future builds
-
-4. **Known Issues**:
- - Docker Compose v1.25.0 limitations:
- - Doesn't respect container_name directives
- - Shows harmless deploy key warnings
- - Solution: Upgrade to Docker Compose v2.x
-
-## Verification:
-- All services running
-- CORS headers properly configured
-- pytz module successfully imported (version 2025.2)
-- API endpoints functional
-
-## System Status: OPERATIONAL
-- API: Running on port 8000
-- Elasticsearch: Running on port 9200
-- Auto-restart configured
+# Final Deployment Status
+
+## Configuration Summary:
+1. **Container Auto-Restart**:
+ - Both services configured with `restart: unless-stopped`
+ - Containers will automatically restart on failures
+
+2. **Resource Limits**:
+ - CPU: `${CPU_LIMIT}` cores
+ - Memory: 2GB limit
+
+3. **Dependencies**:
+ - pytz installed in container (version 2025.2)
+ - All required Python packages verified
+ - Dockerfile updated to include pytz for future builds
+
+4. **Known Issues**:
+ - Docker Compose v1.25.0 limitations:
+ - Doesn't respect container_name directives
+ - Shows harmless deploy key warnings
+ - Solution: Upgrade to Docker Compose v2.x
+
+## Verification:
+- All services running
+- CORS headers properly configured
+- pytz module successfully imported (version 2025.2)
+- API endpoints functional
+
+## System Status: OPERATIONAL
+- API: Running on port 8000
+- Elasticsearch: Running on port 9200
+- Auto-restart configured
- All features functional
\ No newline at end of file
diff --git a/docker-compose.yml b/docker-compose.yml
index a8e4ee6..ffc004f 100644
--- a/docker-compose.yml
+++ b/docker-compose.yml
@@ -1,39 +1,39 @@
-version: '3.7'
-services:
- booksearch_app:
- build: .
- container_name: booksearch_app
- ports:
- - "8000:5000"
- environment:
- - ELASTICSEARCH_HOST=booksearch_elastic
- - BASE_URL=${BASE_URL}
- - CPU_LIMIT=${CPU_LIMIT}
- - SNIPPET_CHAR_LIMIT=${SNIPPET_CHAR_LIMIT}
- volumes:
- - ./smb_share:/books
- depends_on:
- - booksearch_elastic
- restart: unless-stopped
- deploy:
- resources:
- limits:
- cpus: ${CPU_LIMIT}
- memory: 2G
-
- booksearch_elastic:
- container_name: booksearch_elastic
- image: bitnami/elasticsearch:latest
- ports:
- - "9200:9200"
- - "9300:9300"
- environment:
- - discovery.type=single-node
- - ELASTICSEARCH_USERNAME=admin
- - ELASTICSEARCH_PASSWORD=password
- restart: unless-stopped
- healthcheck:
- test: ["CMD", "curl", "-f", "http://localhost:9200"]
- interval: 30s
- timeout: 10s
+version: '3.7'
+services:
+ booksearch_app:
+ build: .
+ container_name: booksearch_app
+ ports:
+ - "8000:5000"
+ environment:
+ - ELASTICSEARCH_HOST=booksearch_elastic
+ - BASE_URL=${BASE_URL}
+ - CPU_LIMIT=${CPU_LIMIT}
+ - SNIPPET_CHAR_LIMIT=${SNIPPET_CHAR_LIMIT}
+ volumes:
+ - ./smb_share:/books
+ depends_on:
+ - booksearch_elastic
+ restart: unless-stopped
+ deploy:
+ resources:
+ limits:
+ cpus: ${CPU_LIMIT}
+ memory: 2G
+
+ booksearch_elastic:
+ container_name: booksearch_elastic
+ image: bitnami/elasticsearch:latest
+ ports:
+ - "9200:9200"
+ - "9300:9300"
+ environment:
+ - discovery.type=single-node
+ - ELASTICSEARCH_USERNAME=admin
+ - ELASTICSEARCH_PASSWORD=password
+ restart: unless-stopped
+ healthcheck:
+ test: ["CMD", "curl", "-f", "http://localhost:9200"]
+ interval: 30s
+ timeout: 10s
retries: 5
\ No newline at end of file
diff --git a/plugin/search_books.js b/plugin/search_books.js
index 85ed68e..180bde3 100644
--- a/plugin/search_books.js
+++ b/plugin/search_books.js
@@ -1,109 +1,109 @@
-function search_books(params, userSettings) {
- const query = params.query;
- const apiUrl = (userSettings.apiUrl || 'http://localhost:8000').replace(/\/$/, '');
- const useProxy = userSettings.useProxy || false;
- const proxyUrl = userSettings.proxyUrl || 'https://cors-anywhere.herokuapp.com/';
-
- // Debugging headers - WARNING: Only for development/testing
- const debugHeaders = userSettings.debugHeaders || {};
-
- if (!query) {
- throw new Error('Search query is required');
- }
-
- // Prepare the target URL
- const targetUrl = `${apiUrl}/search?query=${encodeURIComponent(query)}`;
- const requestUrl = useProxy ? `${proxyUrl}${targetUrl}` : targetUrl;
-
- // Add timeout handling
- const controller = new AbortController();
- const timeoutId = setTimeout(() => controller.abort(), 10000);
-
- // Prepare headers
- const headers = {
- 'Accept': 'application/json',
- ...(useProxy ? { 'X-Requested-With': 'XMLHttpRequest' } : {}),
- ...debugHeaders // Add debug headers if provided
- };
-
- return fetch(requestUrl, {
- method: 'GET',
- headers: headers,
- signal: controller.signal
- })
- .then(async response => {
- clearTimeout(timeoutId);
-
- if (!response.ok) {
- const errorBody = await response.text().catch(() => '');
- throw new Error(`API request failed with status ${response.status}. Response: ${errorBody}`);
- }
-
- const contentType = response.headers.get('content-type');
- if (!contentType || !contentType.includes('application/json')) {
- throw new Error(`Invalid content type: ${contentType}`);
- }
-
- return response.json();
- })
- .then(results => {
- if (!Array.isArray(results)) {
- throw new Error(`Invalid response format. Expected array, got ${typeof results}`);
- }
-
- if (results.length === 0) {
- return 'No books found matching your search';
- }
-
- // Format results with book paths and snippets
- return results.map(result => {
- if (!result.file_path || !result.snippet) {
- throw new Error('Invalid result format - missing required fields');
- }
-
- // Create properly encoded URL
- let formattedUrl = '';
- if (result.raw_url) {
- try {
- // Split URL into parts and encode components separately
- const url = new URL(result.raw_url);
- const pathParts = url.pathname.split('/').map(part =>
- encodeURIComponent(part).replace(/'/g, "%27")
- );
- const search = url.search ? '?' + encodeURIComponent(url.search.slice(1)) : '';
- formattedUrl = `${url.origin}${pathParts.join('/')}${search}`;
- } catch (e) {
- formattedUrl = result.raw_url; // Fallback to original if URL parsing fails
- }
- }
-
- return `Book: ${result.file_path}\n` +
- `Snippet: ${result.snippet}\n` +
- (formattedUrl ? `URL: ${formattedUrl}\n` : '');
- }).join('\n\n');
- })
- .catch(error => {
- clearTimeout(timeoutId);
- let errorMessage = `Error searching books: ${error.message}`;
-
- if (error.name === 'AbortError') {
- errorMessage += '\n\nDiagnostics: Request timed out. Check if:';
- errorMessage += `\n- The API is running at ${apiUrl}`;
- errorMessage += '\n- The server is accessible from your network';
- if (!useProxy) {
- errorMessage += '\n- Try enabling proxy in plugin settings';
- }
- } else if (error.message.includes('Failed to fetch') || error.message.includes('CORS')) {
- errorMessage += '\n\nDiagnostics: Network request failed. Check if:';
- errorMessage += `\n- The API URL (${apiUrl}) is correct`;
- errorMessage += '\n- CORS is properly configured on the server';
- errorMessage += '\n- The server is running and accessible';
- if (!useProxy) {
- errorMessage += '\n- Try enabling proxy in plugin settings to bypass CORS';
- }
- errorMessage += '\n- For debugging, you can add CORS headers in plugin settings';
- }
-
- return errorMessage;
- });
+function search_books(params, userSettings) {
+ const query = params.query;
+ const apiUrl = (userSettings.apiUrl || 'http://localhost:8000').replace(/\/$/, '');
+ const useProxy = userSettings.useProxy || false;
+ const proxyUrl = userSettings.proxyUrl || 'https://cors-anywhere.herokuapp.com/';
+
+ // Debugging headers - WARNING: Only for development/testing
+ const debugHeaders = userSettings.debugHeaders || {};
+
+ if (!query) {
+ throw new Error('Search query is required');
+ }
+
+ // Prepare the target URL
+ const targetUrl = `${apiUrl}/search?query=${encodeURIComponent(query)}`;
+ const requestUrl = useProxy ? `${proxyUrl}${targetUrl}` : targetUrl;
+
+ // Add timeout handling
+ const controller = new AbortController();
+ const timeoutId = setTimeout(() => controller.abort(), 10000);
+
+ // Prepare headers
+ const headers = {
+ 'Accept': 'application/json',
+ ...(useProxy ? { 'X-Requested-With': 'XMLHttpRequest' } : {}),
+ ...debugHeaders // Add debug headers if provided
+ };
+
+ return fetch(requestUrl, {
+ method: 'GET',
+ headers: headers,
+ signal: controller.signal
+ })
+ .then(async response => {
+ clearTimeout(timeoutId);
+
+ if (!response.ok) {
+ const errorBody = await response.text().catch(() => '');
+ throw new Error(`API request failed with status ${response.status}. Response: ${errorBody}`);
+ }
+
+ const contentType = response.headers.get('content-type');
+ if (!contentType || !contentType.includes('application/json')) {
+ throw new Error(`Invalid content type: ${contentType}`);
+ }
+
+ return response.json();
+ })
+ .then(results => {
+ if (!Array.isArray(results)) {
+ throw new Error(`Invalid response format. Expected array, got ${typeof results}`);
+ }
+
+ if (results.length === 0) {
+ return 'No books found matching your search';
+ }
+
+ // Format results with book paths and snippets
+ return results.map(result => {
+ if (!result.file_path || !result.snippet) {
+ throw new Error('Invalid result format - missing required fields');
+ }
+
+ // Create properly encoded URL
+ let formattedUrl = '';
+ if (result.raw_url) {
+ try {
+ // Split URL into parts and encode components separately
+ const url = new URL(result.raw_url);
+ const pathParts = url.pathname.split('/').map(part =>
+ encodeURIComponent(part).replace(/'/g, "%27")
+ );
+ const search = url.search ? '?' + encodeURIComponent(url.search.slice(1)) : '';
+ formattedUrl = `${url.origin}${pathParts.join('/')}${search}`;
+ } catch (e) {
+ formattedUrl = result.raw_url; // Fallback to original if URL parsing fails
+ }
+ }
+
+ return `Book: ${result.file_path}\n` +
+ `Snippet: ${result.snippet}\n` +
+ (formattedUrl ? `URL: ${formattedUrl}\n` : '');
+ }).join('\n\n');
+ })
+ .catch(error => {
+ clearTimeout(timeoutId);
+ let errorMessage = `Error searching books: ${error.message}`;
+
+ if (error.name === 'AbortError') {
+ errorMessage += '\n\nDiagnostics: Request timed out. Check if:';
+ errorMessage += `\n- The API is running at ${apiUrl}`;
+ errorMessage += '\n- The server is accessible from your network';
+ if (!useProxy) {
+ errorMessage += '\n- Try enabling proxy in plugin settings';
+ }
+ } else if (error.message.includes('Failed to fetch') || error.message.includes('CORS')) {
+ errorMessage += '\n\nDiagnostics: Network request failed. Check if:';
+ errorMessage += `\n- The API URL (${apiUrl}) is correct`;
+ errorMessage += '\n- CORS is properly configured on the server';
+ errorMessage += '\n- The server is running and accessible';
+ if (!useProxy) {
+ errorMessage += '\n- Try enabling proxy in plugin settings to bypass CORS';
+ }
+ errorMessage += '\n- For debugging, you can add CORS headers in plugin settings';
+ }
+
+ return errorMessage;
+ });
}
\ No newline at end of file
diff --git a/plugin/search_books.spec.json b/plugin/search_books.spec.json
index b0b6ffe..0c5ad6d 100644
--- a/plugin/search_books.spec.json
+++ b/plugin/search_books.spec.json
@@ -1,16 +1,16 @@
-{
- "name": "search_books",
- "description": "Search for books by content using the book search API.",
- "parameters": {
- "type": "object",
- "properties": {
- "query": {
- "type": "string",
- "description": "The search query to find matching book content"
- }
- },
- "required": [
- "query"
- ]
- }
+{
+ "name": "search_books",
+ "description": "Search for books by content using the book search API.",
+ "parameters": {
+ "type": "object",
+ "properties": {
+ "query": {
+ "type": "string",
+ "description": "The search query to find matching book content"
+ }
+ },
+ "required": [
+ "query"
+ ]
+ }
}
\ No newline at end of file
diff --git a/plugin/userSettings.json b/plugin/userSettings.json
index 96b2754..eee8787 100644
--- a/plugin/userSettings.json
+++ b/plugin/userSettings.json
@@ -1,45 +1,45 @@
-[
- {
- "name": "cors_allow_origin",
- "label": "CORS Allowed Origin",
- "required": false,
- "default": "*",
- "description": "Value for Access-Control-Allow-Origin header, typically '*' for public APIs"
- },
- {
- "name": "cors_allow_methods",
- "label": "CORS Allowed Methods",
- "required": false,
- "default": "GET, POST, PUT",
- "description": "Comma-separated HTTP methods for Access-Control-Allow-Methods header"
- },
- {
- "name": "cors_allow_headers",
- "label": "CORS Allowed Headers",
- "required": false,
- "default": "Content-Type",
- "description": "Comma-separated headers for Access-Control-Allow-Headers"
- },
- {
- "name": "proxyUrl",
- "label": "Proxy Server URL",
- "required": false,
- "default": "",
- "description": "URL of the proxy server to use for external requests"
- },
- {
- "name": "bookSearchAPIKey",
- "label": "Search Engine API Key",
- "type": "password",
- "default":"",
- "required":false,
- "description": "API Key to use for while making requests (not yet used)"
- },
- {
- "name": "apiUrl",
- "label": "API Base URL",
- "required": false,
- "default": "http://localhost:8000",
- "description": "Base URL for the API endpoints"
- }
+[
+ {
+ "name": "cors_allow_origin",
+ "label": "CORS Allowed Origin",
+ "required": false,
+ "default": "*",
+ "description": "Value for Access-Control-Allow-Origin header, typically '*' for public APIs"
+ },
+ {
+ "name": "cors_allow_methods",
+ "label": "CORS Allowed Methods",
+ "required": false,
+ "default": "GET, POST, PUT",
+ "description": "Comma-separated HTTP methods for Access-Control-Allow-Methods header"
+ },
+ {
+ "name": "cors_allow_headers",
+ "label": "CORS Allowed Headers",
+ "required": false,
+ "default": "Content-Type",
+ "description": "Comma-separated headers for Access-Control-Allow-Headers"
+ },
+ {
+ "name": "proxyUrl",
+ "label": "Proxy Server URL",
+ "required": false,
+ "default": "",
+ "description": "URL of the proxy server to use for external requests"
+ },
+ {
+ "name": "bookSearchAPIKey",
+ "label": "Search Engine API Key",
+ "type": "password",
+ "default":"",
+ "required":false,
+ "description": "API Key to use for while making requests (not yet used)"
+ },
+ {
+ "name": "apiUrl",
+ "label": "API Base URL",
+ "required": false,
+ "default": "http://localhost:8000",
+ "description": "Base URL for the API endpoints"
+ }
]
\ No newline at end of file
diff --git a/readme.md b/readme.md
index 4a46b1c..9e68480 100644
--- a/readme.md
+++ b/readme.md
@@ -1,241 +1,241 @@
-
-# What it IS?
-
-## TypeMind Plugin: EPUB/PDF/TXT Search Integration
-
-A plugin for [TypeMind](https://docs.typingmind.com/plugins/build-a-typingmind-plugin) that mimics the **WebSearch** feature but focuses on retrieving books/documents. Users can query, e.g., *"Find me books about Hecate"*, and the plugin returns **clickable links** to relevant files (EPUB, PDF, TXT).
-
-### Features
-- **File Formats**: Supports EPUB, PDF, and TXT (assumed compatibility).
-- **Requirement**: Users must provide their own files for indexing.
-
-### Technical Context
-- **Language**: Python.
-- **Skill Level**:
- - My Python knowledge is **extremely rusty** (last project: a not too simple game bot years ago).
- - Self-assessment: **Python novice**.
-- **Tools Used**:
- - **Sonnet 3.7** and **DeepSeek-V3-0324** (for AI/ML integration).
- - **RooCode**
-
-### Purpose
-1. **Experiment**: Test RooCode’s capabilities and identify practical applications.
-2. **Non-Production**: **⚠️ Do NOT deploy this in production** (even if "fixed" by someone).
-
----
-
-### Key Notes
-- Humor/self-deprecation preserved (e.g., "extremely rusty," "novice").
-- Technical terms standardized (Sonnet 3.7, DeepSeek-V3-0324).
-- Critical warnings emphasized (**bold + emoji** for production risk).
-
-
-
-# Application Deployment Guide (Ubuntu LTS)
-
-## Prerequisites
-
-### System Requirements
-- Ubuntu 22.04 LTS (64-bit)
-- Minimum 2 CPU cores, 4GB RAM
-- 20GB free disk space
-- Open ports: 8000 (app), 9200 (Elasticsearch)
-
-### Required Software
-```bash
-# Update package lists
-sudo apt update
-
-# Install Docker and Docker Compose
-sudo apt install -y docker.io docker-compose
-sudo systemctl enable --now docker
-
-# Add current user to docker group (logout required)
-sudo usermod -aG docker $USER
-```
-
-## Environment Configuration
-
-1. Clone the repository:
-```bash
-git clone https://github.com/intari/roocodetests_1.git
-cd roocodetests_1
-```
-
-2. Configure environment variables:
-```bash
-# Copy example .env file
-cp .env.example .env
-
-# Edit configuration (nano/vim)
-nano .env
-```
-Key variables to configure:
-- `BASE_URL`: Public URL of your application
-- `ELASTICSEARCH_PASSWORD`: Secure password for Elasticsearch
-- `CPU_LIMIT`: CPU cores to allocate (default: 2)
-
-## Application Deployment
-
-1. Start all services:
-```bash
-docker-compose up -d
-```
-
-2. Verify services are running:
-```bash
-docker-compose ps
-```
-
-3. Check application logs:
-```bash
-docker-compose logs -f api
-```
-
-4. Access the application:
-- Web interface: http://your-server-ip:8000
-- Elasticsearch: http://your-server-ip:9200
-
-## Maintenance
-
-## restart & rebuild
-```bash
-docker-compose down && docker-compose up -d --build
-```
-
-Logs
-```bash
- docker logs booksearch_app -f
-```
-
-### Log Rotation
-Configure Docker log rotation in `/etc/docker/daemon.json`:
-```json
-{
- "log-driver": "json-file",
- "log-opts": {
- "max-size": "10m",
- "max-file": "3"
- }
-}
-```
-Then restart Docker:
-```bash
-sudo systemctl restart docker
-```
-
-### Backups
-1. Create backup script (`/usr/local/bin/backup-app.sh`):
-```bash
-#!/bin/bash
-BACKUP_DIR=/var/backups/app
-mkdir -p $BACKUP_DIR
-docker-compose exec -T elasticsearch curl -X POST "localhost:9200/_snapshot/backup_repo/_all" -H "Content-Type: application/json"
-docker-compose exec -T elasticsearch curl -X GET "localhost:9200/_snapshot/backup_repo/snapshot_$(date +%Y-%m-%d)?pretty"
-```
-
-2. Make executable and schedule daily cron job:
-```bash
-sudo chmod +x /usr/local/bin/backup-app.sh
-sudo crontab -e
-# Add: 0 3 * * * /usr/local/bin/backup-app.sh
-```
-
-### Updates
-1. Pull latest changes:
-```bash
-git pull origin main
-```
-
-2. Rebuild containers:
-```bash
-docker-compose up -d --build
-```
-
-## Troubleshooting
-
-### Common Issues
-
-**Application not starting:**
-```bash
-# Check container status
-docker ps -a
-
-# View logs
-docker-compose logs api
-```
-
-**Elasticsearch health issues:**
-```bash
-# Check cluster health
-curl -X GET "localhost:9200/_cluster/health?pretty"
-
-# Check node stats
-curl -X GET "localhost:9200/_nodes/stats?pretty"
-```
-
-**Port conflicts:**
-```bash
-# Check used ports
-sudo netstat -tulnp
-
-# Change ports in docker-compose.yml if needed
-```
-
-### Debugging
-1. Access running container shell:
-```bash
-docker-compose exec api bash
-```
-
-2. Check resource usage:
-```bash
-docker stats
-```
-
-## Check Request via JSON :
-curl -H "Accept: application/json" -X GET https://booksearch.yourdomain.com/search?query=android
-
-# Simple search
-curl -H "Accept: application/json" "https://booksearch.yourdomain.com/search?query=android"
-
-# Search with format parameter
-curl "https://booksearch.yourdomain.com/search?query=android&format=json"
-
-# Error case
-curl -H "Accept: application/json" "https://booksearch.yourdomain.com/search"
-
-
-## API Endpoints
-
-### Search API
-```
-GET /search?query={query}[&format=json]
-```
-
-### Reset Elasticsearch Index
-```
-POST /reset_index
-Headers:
-- Authorization: Basic base64(username:password)
-```
-
-Example:
-```bash
-curl -X POST -u admin:securepassword123 https://booksearch.yourdomain.com/reset_index
-```
-
-## References
-- [Ubuntu Docker Installation](https://docs.docker.com/engine/install/ubuntu/)
-- [Docker Compose Reference](https://docs.docker.com/compose/reference/)
-- [Elasticsearch Documentation](https://www.elastic.co/guide/en/elasticsearch/reference/current/index.html)
-
-
-## Plugin-alt
-method:get
-https://booksearch.yourdomain.com/search?query={prompt}&format=json
-alt version for plugin
-request headers
-{
-"Accept": "application/json"
+
+# What it IS?
+
+## TypeMind Plugin: EPUB/PDF/TXT Search Integration
+
+A plugin for [TypeMind](https://docs.typingmind.com/plugins/build-a-typingmind-plugin) that mimics the **WebSearch** feature but focuses on retrieving books/documents. Users can query, e.g., *"Find me books about Hecate"*, and the plugin returns **clickable links** to relevant files (EPUB, PDF, TXT).
+
+### Features
+- **File Formats**: Supports EPUB, PDF, and TXT (assumed compatibility).
+- **Requirement**: Users must provide their own files for indexing.
+
+### Technical Context
+- **Language**: Python.
+- **Skill Level**:
+ - My Python knowledge is **extremely rusty** (last project: a not too simple game bot years ago).
+ - Self-assessment: **Python novice**.
+- **Tools Used**:
+ - **Sonnet 3.7** and **DeepSeek-V3-0324** (for AI/ML integration).
+ - **RooCode**
+
+### Purpose
+1. **Experiment**: Test RooCode’s capabilities and identify practical applications.
+2. **Non-Production**: **⚠️ Do NOT deploy this in production** (even if "fixed" by someone).
+
+---
+
+### Key Notes
+- Humor/self-deprecation preserved (e.g., "extremely rusty," "novice").
+- Technical terms standardized (Sonnet 3.7, DeepSeek-V3-0324).
+- Critical warnings emphasized (**bold + emoji** for production risk).
+
+
+
+# Application Deployment Guide (Ubuntu LTS)
+
+## Prerequisites
+
+### System Requirements
+- Ubuntu 22.04 LTS (64-bit)
+- Minimum 2 CPU cores, 4GB RAM
+- 20GB free disk space
+- Open ports: 8000 (app), 9200 (Elasticsearch)
+
+### Required Software
+```bash
+# Update package lists
+sudo apt update
+
+# Install Docker and Docker Compose
+sudo apt install -y docker.io docker-compose
+sudo systemctl enable --now docker
+
+# Add current user to docker group (logout required)
+sudo usermod -aG docker $USER
+```
+
+## Environment Configuration
+
+1. Clone the repository:
+```bash
+git clone https://github.com/intari/roocodetests_1.git
+cd roocodetests_1
+```
+
+2. Configure environment variables:
+```bash
+# Copy example .env file
+cp .env.example .env
+
+# Edit configuration (nano/vim)
+nano .env
+```
+Key variables to configure:
+- `BASE_URL`: Public URL of your application
+- `ELASTICSEARCH_PASSWORD`: Secure password for Elasticsearch
+- `CPU_LIMIT`: CPU cores to allocate (default: 2)
+
+## Application Deployment
+
+1. Start all services:
+```bash
+docker-compose up -d
+```
+
+2. Verify services are running:
+```bash
+docker-compose ps
+```
+
+3. Check application logs:
+```bash
+docker-compose logs -f api
+```
+
+4. Access the application:
+- Web interface: http://your-server-ip:8000
+- Elasticsearch: http://your-server-ip:9200
+
+## Maintenance
+
+## restart & rebuild
+```bash
+docker-compose down && docker-compose up -d --build
+```
+
+Logs
+```bash
+ docker logs booksearch_app -f
+```
+
+### Log Rotation
+Configure Docker log rotation in `/etc/docker/daemon.json`:
+```json
+{
+ "log-driver": "json-file",
+ "log-opts": {
+ "max-size": "10m",
+ "max-file": "3"
+ }
+}
+```
+Then restart Docker:
+```bash
+sudo systemctl restart docker
+```
+
+### Backups
+1. Create backup script (`/usr/local/bin/backup-app.sh`):
+```bash
+#!/bin/bash
+BACKUP_DIR=/var/backups/app
+mkdir -p $BACKUP_DIR
+docker-compose exec -T elasticsearch curl -X POST "localhost:9200/_snapshot/backup_repo/_all" -H "Content-Type: application/json"
+docker-compose exec -T elasticsearch curl -X GET "localhost:9200/_snapshot/backup_repo/snapshot_$(date +%Y-%m-%d)?pretty"
+```
+
+2. Make executable and schedule daily cron job:
+```bash
+sudo chmod +x /usr/local/bin/backup-app.sh
+sudo crontab -e
+# Add: 0 3 * * * /usr/local/bin/backup-app.sh
+```
+
+### Updates
+1. Pull latest changes:
+```bash
+git pull origin main
+```
+
+2. Rebuild containers:
+```bash
+docker-compose up -d --build
+```
+
+## Troubleshooting
+
+### Common Issues
+
+**Application not starting:**
+```bash
+# Check container status
+docker ps -a
+
+# View logs
+docker-compose logs api
+```
+
+**Elasticsearch health issues:**
+```bash
+# Check cluster health
+curl -X GET "localhost:9200/_cluster/health?pretty"
+
+# Check node stats
+curl -X GET "localhost:9200/_nodes/stats?pretty"
+```
+
+**Port conflicts:**
+```bash
+# Check used ports
+sudo netstat -tulnp
+
+# Change ports in docker-compose.yml if needed
+```
+
+### Debugging
+1. Access running container shell:
+```bash
+docker-compose exec api bash
+```
+
+2. Check resource usage:
+```bash
+docker stats
+```
+
+## Check Request via JSON :
+curl -H "Accept: application/json" -X GET https://booksearch.yourdomain.com/search?query=android
+
+# Simple search
+curl -H "Accept: application/json" "https://booksearch.yourdomain.com/search?query=android"
+
+# Search with format parameter
+curl "https://booksearch.yourdomain.com/search?query=android&format=json"
+
+# Error case
+curl -H "Accept: application/json" "https://booksearch.yourdomain.com/search"
+
+
+## API Endpoints
+
+### Search API
+```
+GET /search?query={query}[&format=json]
+```
+
+### Reset Elasticsearch Index
+```
+POST /reset_index
+Headers:
+- Authorization: Basic base64(username:password)
+```
+
+Example:
+```bash
+curl -X POST -u admin:securepassword123 https://booksearch.yourdomain.com/reset_index
+```
+
+## References
+- [Ubuntu Docker Installation](https://docs.docker.com/engine/install/ubuntu/)
+- [Docker Compose Reference](https://docs.docker.com/compose/reference/)
+- [Elasticsearch Documentation](https://www.elastic.co/guide/en/elasticsearch/reference/current/index.html)
+
+
+## Plugin-alt
+method:get
+https://booksearch.yourdomain.com/search?query={prompt}&format=json
+alt version for plugin
+request headers
+{
+"Accept": "application/json"
}
\ No newline at end of file
diff --git a/roocodetest.code-workspace b/roocodetest.code-workspace
index 876a149..9017da0 100644
--- a/roocodetest.code-workspace
+++ b/roocodetest.code-workspace
@@ -1,8 +1,8 @@
-{
- "folders": [
- {
- "path": "."
- }
- ],
- "settings": {}
+{
+ "folders": [
+ {
+ "path": "."
+ }
+ ],
+ "settings": {}
}
\ No newline at end of file
diff --git a/scripts/run_tests.bat b/scripts/run_tests.bat
index 17ac1c6..cacacf2 100644
--- a/scripts/run_tests.bat
+++ b/scripts/run_tests.bat
@@ -1,37 +1,37 @@
-@echo off
-echo Setting up test environment...
-
-echo Checking Python version...
-python --version
-if errorlevel 1 (
- echo Python not found. Please install Python 3.10+ first.
- pause
- exit /b 1
-)
-
-echo Installing Python dependencies...
-python -m pip install --upgrade pip --user
-if errorlevel 1 (
- echo Failed to upgrade pip
- pause
- exit /b 1
-)
-
-pip install -r requirements.txt --user
-if errorlevel 1 (
- echo Failed to install dependencies
- pause
- exit /b 1
-)
-
-echo Running EPUB viewer tests...
-cd api
-python -m pytest test_epub_viewer.py -v
-if errorlevel 1 (
- echo Some tests failed
- pause
- exit /b 1
-)
-
-echo All tests completed successfully!
+@echo off
+echo Setting up test environment...
+
+echo Checking Python version...
+python --version
+if errorlevel 1 (
+ echo Python not found. Please install Python 3.10+ first.
+ pause
+ exit /b 1
+)
+
+echo Installing Python dependencies...
+python -m pip install --upgrade pip --user
+if errorlevel 1 (
+ echo Failed to upgrade pip
+ pause
+ exit /b 1
+)
+
+pip install -r requirements.txt --user
+if errorlevel 1 (
+ echo Failed to install dependencies
+ pause
+ exit /b 1
+)
+
+echo Running EPUB viewer tests...
+cd api
+python -m pytest test_epub_viewer.py -v
+if errorlevel 1 (
+ echo Some tests failed
+ pause
+ exit /b 1
+)
+
+echo All tests completed successfully!
pause
\ No newline at end of file
diff --git a/scripts/run_tests.sh b/scripts/run_tests.sh
index 6f6bba6..0aed9f0 100644
--- a/scripts/run_tests.sh
+++ b/scripts/run_tests.sh
@@ -1,29 +1,29 @@
-#!/bin/bash
-
-echo "Setting up test environment..."
-
-echo "Checking Python version..."
-python3 --version || {
- echo "Python 3 not found. Please install Python 3.10+ first."
- exit 1
-}
-
-echo "Installing Python dependencies..."
-python3 -m pip install --upgrade pip --user || {
- echo "Failed to upgrade pip"
- exit 1
-}
-
-pip3 install -r requirements.txt --user || {
- echo "Failed to install dependencies"
- exit 1
-}
-
-echo "Running EPUB viewer tests..."
-cd api
-python3 -m pytest test_epub_viewer.py -v || {
- echo "Some tests failed"
- exit 1
-}
-
+#!/bin/bash
+
+echo "Setting up test environment..."
+
+echo "Checking Python version..."
+python3 --version || {
+ echo "Python 3 not found. Please install Python 3.10+ first."
+ exit 1
+}
+
+echo "Installing Python dependencies..."
+python3 -m pip install --upgrade pip --user || {
+ echo "Failed to upgrade pip"
+ exit 1
+}
+
+pip3 install -r requirements.txt --user || {
+ echo "Failed to install dependencies"
+ exit 1
+}
+
+echo "Running EPUB viewer tests..."
+cd api
+python3 -m pytest test_epub_viewer.py -v || {
+ echo "Some tests failed"
+ exit 1
+}
+
echo "All tests completed successfully!"
\ No newline at end of file
diff --git a/src/api/app.py b/src/api/app.py
index eac3325..ea4713d 100644
--- a/src/api/app.py
+++ b/src/api/app.py
@@ -1,406 +1,406 @@
-from flask import Flask, request, jsonify, render_template, send_from_directory
-from urllib.parse import unquote
-from elasticsearch import Elasticsearch
-import os
-import ebooklib
-from ebooklib import epub
-from bs4 import BeautifulSoup
-import PyPDF2
-import time
-import logging
-import multiprocessing
-import sys
-from pathlib import Path
-sys.path.append(str(Path(__file__).parent.parent))
-from index import index_files, get_progress
-from io import StringIO
-import sys
-
-app = Flask(__name__, static_folder='static')
-
-@app.after_request
-def add_cors_headers(response):
- response.headers['Access-Control-Allow-Origin'] = '*'
- response.headers['Access-Control-Allow-Methods'] = 'GET, POST, PUT'
- response.headers['Access-Control-Allow-Headers'] = 'Content-Type'
- return response
-
-# Elasticsearch Configuration
-ELASTICSEARCH_HOST = os.environ.get("ELASTICSEARCH_HOST", "localhost")
-ELASTICSEARCH_PORT = int(os.environ.get("ELASTICSEARCH_PORT", 9200))
-INDEX_NAME = "book_index"
-
-# Wait for Elasticsearch to be available
-es = None
-while True:
- try:
- es = Elasticsearch([{'host': ELASTICSEARCH_HOST, 'port': ELASTICSEARCH_PORT, 'scheme': 'http'}])
- if es.ping():
- print("Connected to Elasticsearch")
- break
- else:
- print("Elasticsearch not available, retrying...")
- except Exception as e:
- print(f"Error connecting to Elasticsearch: {e}")
- time.sleep(5)
-
-def extract_text_from_epub(epub_path):
- try:
- book = epub.read_epub(epub_path)
- text = ''
- for item in book.get_items():
- if item.media_type == 'application/xhtml+xml':
- content = item.get_content()
- if content:
- soup = BeautifulSoup(content, 'html.parser')
- text += soup.get_text()
- return text
- except Exception as e:
- logging.error(f"Error processing EPUB {epub_path}: {str(e)}")
- return f"Error extracting text: {str(e)}"
-
-def extract_text_from_pdf(pdf_path):
- text = ''
- with open(pdf_path, 'rb') as pdf_file:
- pdf_reader = PyPDF2.PdfReader(pdf_file)
- for page_num in range(len(pdf_reader.pages)):
- page = pdf_reader.pages[page_num]
- text += page.extract_text()
- return text
-
-@app.route('/', methods=['GET'])
-def home():
- return render_template('search.html')
-
-@app.route('/search', methods=['GET'])
-def search():
- query = request.args.get('query')
- if not query:
- if request.headers.get('Accept') == 'application/json':
- return jsonify({"error": "Query parameter is required"}), 400
- return render_template('search.html', query='')
-
- try:
- results = es.search(index=INDEX_NAME, query={'match': {'content': query}})
- hits = results['hits']['hits']
-
- search_results = []
- for hit in hits:
- file_path = hit['_source']['file_path']
- content = hit['_source']['content']
-
- # Highlight snippet (simple version)
- snippet_char_limit = int(os.environ.get("SNIPPET_CHAR_LIMIT", 100))
- index = content.lower().find(query.lower())
- if index != -1:
- start = max(0, index - snippet_char_limit)
- end = min(len(content), index + snippet_char_limit + len(query))
- snippet = content[start:end]
- else:
- snippet = "No snippet found"
-
- # Get base URL from environment
- base_url = os.environ.get("BASE_URL", "http://localhost:8000")
- # Construct URLs
- # Remove "/books/" from path start if it's here
- if file_path.startswith("/books/"):
- file_path = file_path[len("/books/"):]
-
- url = f"{base_url}/{file_path}"
- raw_url = f"{base_url}/file/{file_path}?format=html"
-
- search_results.append({
- "file_path": file_path,
- "url": url,
- "raw_url": raw_url,
- "snippet": snippet,
- "score": hit['_score']
- })
-
- # If it's an API request or format=json is specified
- if request.headers.get('Accept') == 'application/json' or request.args.get('format') == 'json':
- response = jsonify({
- "query": query,
- "results": search_results,
- "total": len(search_results),
- "took": results['took']
- })
- response.headers['Content-Type'] = 'application/json'
- return response
-
- # Otherwise, render the HTML template
- return render_template('search.html', results=search_results, query=query)
-
- except Exception as e:
- if request.headers.get('Accept') == 'application/json' or request.args.get('format') == 'json':
- response = jsonify({
- "error": str(e),
- "query": query
- })
- response.headers['Content-Type'] = 'application/json'
- return response, 500
- return render_template('search.html', error=str(e), query=query)
-
-@app.route('/files', methods=['GET'])
-def list_files():
- books_dir = "/books"
- files = []
-
- try:
- # Check if indexing is in progress
- indexing_in_progress = get_progress() is not None
-
- for filename in os.listdir(books_dir):
- file_path = os.path.join(books_dir, filename)
- if os.path.isfile(file_path):
- file_size = os.path.getsize(file_path)
- # Extract book title from filename if possible
- title = filename
- if ' - ' in filename: # Common pattern in filenames
- title_parts = filename.split(' - ')
- if len(title_parts) > 1:
- title = ' - '.join(title_parts[:-1]) # Take all but last part
-
- files.append({
- 'name': filename,
- 'title': title,
- 'path': filename,
- 'size': file_size,
- 'size_mb': round(file_size / (1024 * 1024), 2)
- })
-
- # Calculate totals
- total_files = len(files)
- total_size = sum(f['size'] for f in files)
- total_size_mb = round(total_size / (1024 * 1024), 2)
-
- # If it's an API request, return JSON
- if request.headers.get('Accept') == 'application/json':
- return jsonify({
- 'files': files,
- 'total_files': total_files,
- 'total_size': total_size,
- 'total_size_mb': total_size_mb,
- 'indexing_in_progress': indexing_in_progress
- })
-
- # Otherwise, render the HTML template
- return render_template('files.html',
- files=files,
- total_files=total_files,
- total_size=total_size,
- total_size_mb=total_size_mb,
- indexing_in_progress=indexing_in_progress)
- except Exception as e:
- if request.headers.get('Accept') == 'application/json':
- return jsonify({"error": str(e)}), 500
- return render_template('files.html', error=str(e))
-
-@app.route('/file/<path:file_path>', methods=['GET'])
-def get_file(file_path):
- # Ensure the file path is within the /books directory
- books_dir = "/books"
-
- # Decode URL-encoded path and normalize
- decoded_path = unquote(file_path)
- # Remove any leading slashes or duplicate 'books/' segments
- decoded_path = decoded_path.lstrip('/')
- if decoded_path.startswith('books/'):
- decoded_path = decoded_path[6:]
-
- # Join paths safely
- full_path = os.path.normpath(os.path.join(books_dir, decoded_path))
-
- # Validate the path is within the books directory
- if not os.path.abspath(full_path).startswith(os.path.abspath(books_dir)):
- return jsonify({"error": "Access denied: File path outside of books directory"}), 403
-
- try:
- # Handle EPUB files
- if file_path.lower().endswith('.epub'):
- if request.args.get('format') == 'html':
- # Convert EPUB to HTML
- try:
- book = epub.read_epub(full_path)
- html_content = []
- for item in book.get_items():
- if item.get_type() == ebooklib.ITEM_DOCUMENT:
- content = item.get_content()
- if content:
- soup = BeautifulSoup(content, 'html.parser')
- # Preserve basic formatting tags
- for tag in soup.find_all():
- if tag.name not in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'p', 'br', 'div', 'span', 'strong', 'em', 'b', 'i', 'ul', 'ol', 'li']:
- tag.unwrap()
- html_content.append(str(soup))
- except Exception as e:
- logging.error(f"Error processing EPUB {full_path}: {str(e)}")
- return jsonify({"error": f"Failed to process EPUB: {str(e)}"}), 500
- return render_template('text_file.html',
- file_path=file_path,
- content='<hr>'.join(html_content),
- is_html=True)
- else:
- # Render the viewer template
- return render_template('epub_viewer.html', file_path=file_path)
-
- # Handle regular text files
- with open(full_path, 'r', encoding='utf-8', errors='ignore') as f:
- content = f.read()
-
- # If it's an API request or the Accept header doesn't include HTML, return plain text
- if request.headers.get('Accept') == 'application/json' or 'text/html' not in request.headers.get('Accept', ''):
- return content, 200, {'Content-Type': 'text/plain; charset=utf-8'}
-
- # Otherwise, render a simple HTML page with the content
- return render_template('text_file.html', file_path=file_path, content=content)
- except Exception as e:
- return jsonify({"error": str(e)}), 404
-
-@app.route('/epub/<path:file_path>', methods=['GET'])
-def get_epub_file(file_path):
- """Serve the raw EPUB file with proper headers"""
- books_dir = "/books"
- full_path = os.path.join(books_dir, file_path)
-
- # Validate the path is within the books directory
- if not os.path.abspath(full_path).startswith(os.path.abspath(books_dir)):
- return jsonify({"error": "Access denied: File path outside of books directory"}), 403
-
- try:
- # Serve the raw EPUB file with proper headers
- response = send_from_directory(
- books_dir,
- file_path,
- as_attachment=True,
- mimetype='application/epub+zip'
- )
- response.headers['Access-Control-Allow-Origin'] = '*'
- response.headers['Access-Control-Allow-Methods'] = 'GET'
- response.headers['Content-Disposition'] = f'attachment; filename="{os.path.basename(file_path)}"'
- return response
- except Exception as e:
- return jsonify({"error": str(e)}), 404
-
-@app.route('/index_books', methods=['GET'])
-def index_books():
- logging.info("Indexing books endpoint called")
-
- # Get CPU configuration
- cpu_limit = os.environ.get("CPU_LIMIT")
- available_cpus = multiprocessing.cpu_count()
- used_cpus = float(cpu_limit) if cpu_limit else max(1, available_cpus - 1)
-
- # Capture stdout to a string
- old_stdout = sys.stdout
- sys.stdout = captured_output = StringIO()
-
- try:
- # Start indexing in a separate thread
- from threading import Thread
- index_thread = Thread(target=index_files, args=("/books",))
- index_thread.start()
-
- # If it's an API request, return immediately
- if request.headers.get('Accept') == 'application/json':
- return jsonify({"message": "Indexing started in background"})
-
- # Otherwise, render the progress page with CPU info
- return render_template('indexing.html',
- available_cpus=available_cpus,
- used_cpus=used_cpus)
-
- except Exception as e:
- logging.error(f"Indexing failed: {e}")
- sys.stdout = old_stdout
-
- if request.headers.get('Accept') == 'application/json':
- return jsonify({"error": str(e)}), 500
-
- # Create a simple HTML response for errors
- return render_template('indexing_error.html', error=str(e))
- finally:
- sys.stdout = old_stdout
-
-@app.route('/indexing_progress', methods=['GET'])
-def get_indexing_progress():
- progress = get_progress()
- if progress is None:
- return jsonify({"status": "not_running"})
-
- # Format time for display
- from datetime import datetime
- import pytz
-
- # Get browser timezone from Accept-Language header or use UTC as fallback
- browser_tz = request.headers.get('X-Timezone', 'UTC')
- try:
- tz = pytz.timezone(browser_tz)
- except pytz.UnknownTimeZoneError:
- tz = pytz.UTC
-
- elapsed_min = int(progress['elapsed_time'] // 60)
- elapsed_sec = int(progress['elapsed_time'] % 60)
-
- if progress['estimated_remaining'] > 0:
- remaining_min = int(progress['estimated_remaining'] // 60)
- remaining_sec = int(progress['estimated_remaining'] % 60)
- completion_time = datetime.fromtimestamp(progress['estimated_completion'], tz).strftime('%H:%M:%S (%Z)')
- else:
- remaining_min = 0
- remaining_sec = 0
- completion_time = "N/A"
-
- return jsonify({
- "status": "running",
- "total_files": progress['total_files'],
- "processed_files": progress['processed_files'],
- "percentage": round(progress['percentage'], 1),
- "current_file": progress['current_file'],
- "elapsed_time": f"{elapsed_min}m {elapsed_sec}s",
- "estimated_remaining": f"{remaining_min}m {remaining_sec}s",
- "estimated_completion": completion_time,
- "errors": progress['errors']
- })
-
-@app.route('/abort_indexing', methods=['POST'])
-def abort_indexing():
- # In a real implementation, we would set a flag to stop the indexing
- # For now, we'll just return a message
- return jsonify({"status": "abort_requested", "message": "Indexing will stop after current file"})
-
-@app.route('/reset_index', methods=['POST'])
-def reset_index():
- """Reset the Elasticsearch index by deleting and recreating it"""
- try:
- # Check for basic auth
- auth = request.authorization
- if not auth or auth.username != os.environ.get("ADMIN_USER") or auth.password != os.environ.get("ADMIN_PASSWORD"):
- return jsonify({"error": "Authentication required"}), 401
-
- # Delete existing index if it exists
- if es.indices.exists(index=INDEX_NAME):
- es.indices.delete(index=INDEX_NAME)
-
- # Create new index with mapping
- es.indices.create(index=INDEX_NAME, body={
- "settings": {
- "number_of_shards": 1,
- "number_of_replicas": 0
- },
- "mappings": {
- "properties": {
- "file_path": {"type": "keyword"},
- "content": {"type": "text"}
- }
- }
- })
-
- return jsonify({"status": "success", "message": "Index reset successfully"})
- except Exception as e:
- return jsonify({"error": str(e)}), 500
-
-if __name__ == '__main__':
- logging.basicConfig(level=logging.DEBUG)
- logging.info("Starting the API - inside main block")
+from flask import Flask, request, jsonify, render_template, send_from_directory
+from urllib.parse import unquote
+from elasticsearch import Elasticsearch
+import os
+import ebooklib
+from ebooklib import epub
+from bs4 import BeautifulSoup
+import PyPDF2
+import time
+import logging
+import multiprocessing
+import sys
+from pathlib import Path
+sys.path.append(str(Path(__file__).parent.parent))
+from index import index_files, get_progress
+from io import StringIO
+import sys
+
+app = Flask(__name__, static_folder='static')
+
+@app.after_request
+def add_cors_headers(response):
+ response.headers['Access-Control-Allow-Origin'] = '*'
+ response.headers['Access-Control-Allow-Methods'] = 'GET, POST, PUT'
+ response.headers['Access-Control-Allow-Headers'] = 'Content-Type'
+ return response
+
+# Elasticsearch Configuration
+ELASTICSEARCH_HOST = os.environ.get("ELASTICSEARCH_HOST", "localhost")
+ELASTICSEARCH_PORT = int(os.environ.get("ELASTICSEARCH_PORT", 9200))
+INDEX_NAME = "book_index"
+
+# Wait for Elasticsearch to be available
+es = None
+while True:
+ try:
+ es = Elasticsearch([{'host': ELASTICSEARCH_HOST, 'port': ELASTICSEARCH_PORT, 'scheme': 'http'}])
+ if es.ping():
+ print("Connected to Elasticsearch")
+ break
+ else:
+ print("Elasticsearch not available, retrying...")
+ except Exception as e:
+ print(f"Error connecting to Elasticsearch: {e}")
+ time.sleep(5)
+
+def extract_text_from_epub(epub_path):
+ try:
+ book = epub.read_epub(epub_path)
+ text = ''
+ for item in book.get_items():
+ if item.media_type == 'application/xhtml+xml':
+ content = item.get_content()
+ if content:
+ soup = BeautifulSoup(content, 'html.parser')
+ text += soup.get_text()
+ return text
+ except Exception as e:
+ logging.error(f"Error processing EPUB {epub_path}: {str(e)}")
+ return f"Error extracting text: {str(e)}"
+
+def extract_text_from_pdf(pdf_path):
+ text = ''
+ with open(pdf_path, 'rb') as pdf_file:
+ pdf_reader = PyPDF2.PdfReader(pdf_file)
+ for page_num in range(len(pdf_reader.pages)):
+ page = pdf_reader.pages[page_num]
+ text += page.extract_text()
+ return text
+
+@app.route('/', methods=['GET'])
+def home():
+ return render_template('search.html')
+
+@app.route('/search', methods=['GET'])
+def search():
+ query = request.args.get('query')
+ if not query:
+ if request.headers.get('Accept') == 'application/json':
+ return jsonify({"error": "Query parameter is required"}), 400
+ return render_template('search.html', query='')
+
+ try:
+ results = es.search(index=INDEX_NAME, query={'match': {'content': query}})
+ hits = results['hits']['hits']
+
+ search_results = []
+ for hit in hits:
+ file_path = hit['_source']['file_path']
+ content = hit['_source']['content']
+
+ # Highlight snippet (simple version)
+ snippet_char_limit = int(os.environ.get("SNIPPET_CHAR_LIMIT", 100))
+ index = content.lower().find(query.lower())
+ if index != -1:
+ start = max(0, index - snippet_char_limit)
+ end = min(len(content), index + snippet_char_limit + len(query))
+ snippet = content[start:end]
+ else:
+ snippet = "No snippet found"
+
+ # Get base URL from environment
+ base_url = os.environ.get("BASE_URL", "http://localhost:8000")
+ # Construct URLs
+ # Remove "/books/" from path start if it's here
+ if file_path.startswith("/books/"):
+ file_path = file_path[len("/books/"):]
+
+ url = f"{base_url}/{file_path}"
+ raw_url = f"{base_url}/file/{file_path}?format=html"
+
+ search_results.append({
+ "file_path": file_path,
+ "url": url,
+ "raw_url": raw_url,
+ "snippet": snippet,
+ "score": hit['_score']
+ })
+
+ # If it's an API request or format=json is specified
+ if request.headers.get('Accept') == 'application/json' or request.args.get('format') == 'json':
+ response = jsonify({
+ "query": query,
+ "results": search_results,
+ "total": len(search_results),
+ "took": results['took']
+ })
+ response.headers['Content-Type'] = 'application/json'
+ return response
+
+ # Otherwise, render the HTML template
+ return render_template('search.html', results=search_results, query=query)
+
+ except Exception as e:
+ if request.headers.get('Accept') == 'application/json' or request.args.get('format') == 'json':
+ response = jsonify({
+ "error": str(e),
+ "query": query
+ })
+ response.headers['Content-Type'] = 'application/json'
+ return response, 500
+ return render_template('search.html', error=str(e), query=query)
+
+@app.route('/files', methods=['GET'])
+def list_files():
+ books_dir = "/books"
+ files = []
+
+ try:
+ # Check if indexing is in progress
+ indexing_in_progress = get_progress() is not None
+
+ for filename in os.listdir(books_dir):
+ file_path = os.path.join(books_dir, filename)
+ if os.path.isfile(file_path):
+ file_size = os.path.getsize(file_path)
+ # Extract book title from filename if possible
+ title = filename
+ if ' - ' in filename: # Common pattern in filenames
+ title_parts = filename.split(' - ')
+ if len(title_parts) > 1:
+ title = ' - '.join(title_parts[:-1]) # Take all but last part
+
+ files.append({
+ 'name': filename,
+ 'title': title,
+ 'path': filename,
+ 'size': file_size,
+ 'size_mb': round(file_size / (1024 * 1024), 2)
+ })
+
+ # Calculate totals
+ total_files = len(files)
+ total_size = sum(f['size'] for f in files)
+ total_size_mb = round(total_size / (1024 * 1024), 2)
+
+ # If it's an API request, return JSON
+ if request.headers.get('Accept') == 'application/json':
+ return jsonify({
+ 'files': files,
+ 'total_files': total_files,
+ 'total_size': total_size,
+ 'total_size_mb': total_size_mb,
+ 'indexing_in_progress': indexing_in_progress
+ })
+
+ # Otherwise, render the HTML template
+ return render_template('files.html',
+ files=files,
+ total_files=total_files,
+ total_size=total_size,
+ total_size_mb=total_size_mb,
+ indexing_in_progress=indexing_in_progress)
+ except Exception as e:
+ if request.headers.get('Accept') == 'application/json':
+ return jsonify({"error": str(e)}), 500
+ return render_template('files.html', error=str(e))
+
+@app.route('/file/<path:file_path>', methods=['GET'])
+def get_file(file_path):
+ # Ensure the file path is within the /books directory
+ books_dir = "/books"
+
+ # Decode URL-encoded path and normalize
+ decoded_path = unquote(file_path)
+ # Remove any leading slashes or duplicate 'books/' segments
+ decoded_path = decoded_path.lstrip('/')
+ if decoded_path.startswith('books/'):
+ decoded_path = decoded_path[6:]
+
+ # Join paths safely
+ full_path = os.path.normpath(os.path.join(books_dir, decoded_path))
+
+ # Validate the path is within the books directory
+ if not os.path.abspath(full_path).startswith(os.path.abspath(books_dir)):
+ return jsonify({"error": "Access denied: File path outside of books directory"}), 403
+
+ try:
+ # Handle EPUB files
+ if file_path.lower().endswith('.epub'):
+ if request.args.get('format') == 'html':
+ # Convert EPUB to HTML
+ try:
+ book = epub.read_epub(full_path)
+ html_content = []
+ for item in book.get_items():
+ if item.get_type() == ebooklib.ITEM_DOCUMENT:
+ content = item.get_content()
+ if content:
+ soup = BeautifulSoup(content, 'html.parser')
+ # Preserve basic formatting tags
+ for tag in soup.find_all():
+ if tag.name not in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'p', 'br', 'div', 'span', 'strong', 'em', 'b', 'i', 'ul', 'ol', 'li']:
+ tag.unwrap()
+ html_content.append(str(soup))
+ except Exception as e:
+ logging.error(f"Error processing EPUB {full_path}: {str(e)}")
+ return jsonify({"error": f"Failed to process EPUB: {str(e)}"}), 500
+ return render_template('text_file.html',
+ file_path=file_path,
+ content='<hr>'.join(html_content),
+ is_html=True)
+ else:
+ # Render the viewer template
+ return render_template('epub_viewer.html', file_path=file_path)
+
+ # Handle regular text files
+ with open(full_path, 'r', encoding='utf-8', errors='ignore') as f:
+ content = f.read()
+
+ # If it's an API request or the Accept header doesn't include HTML, return plain text
+ if request.headers.get('Accept') == 'application/json' or 'text/html' not in request.headers.get('Accept', ''):
+ return content, 200, {'Content-Type': 'text/plain; charset=utf-8'}
+
+ # Otherwise, render a simple HTML page with the content
+ return render_template('text_file.html', file_path=file_path, content=content)
+ except Exception as e:
+ return jsonify({"error": str(e)}), 404
+
+@app.route('/epub/<path:file_path>', methods=['GET'])
+def get_epub_file(file_path):
+ """Serve the raw EPUB file with proper headers"""
+ books_dir = "/books"
+ full_path = os.path.join(books_dir, file_path)
+
+ # Validate the path is within the books directory
+ if not os.path.abspath(full_path).startswith(os.path.abspath(books_dir)):
+ return jsonify({"error": "Access denied: File path outside of books directory"}), 403
+
+ try:
+ # Serve the raw EPUB file with proper headers
+ response = send_from_directory(
+ books_dir,
+ file_path,
+ as_attachment=True,
+ mimetype='application/epub+zip'
+ )
+ response.headers['Access-Control-Allow-Origin'] = '*'
+ response.headers['Access-Control-Allow-Methods'] = 'GET'
+ response.headers['Content-Disposition'] = f'attachment; filename="{os.path.basename(file_path)}"'
+ return response
+ except Exception as e:
+ return jsonify({"error": str(e)}), 404
+
+@app.route('/index_books', methods=['GET'])
+def index_books():
+ logging.info("Indexing books endpoint called")
+
+ # Get CPU configuration
+ cpu_limit = os.environ.get("CPU_LIMIT")
+ available_cpus = multiprocessing.cpu_count()
+ used_cpus = float(cpu_limit) if cpu_limit else max(1, available_cpus - 1)
+
+ # Capture stdout to a string
+ old_stdout = sys.stdout
+ sys.stdout = captured_output = StringIO()
+
+ try:
+ # Start indexing in a separate thread
+ from threading import Thread
+ index_thread = Thread(target=index_files, args=("/books",))
+ index_thread.start()
+
+ # If it's an API request, return immediately
+ if request.headers.get('Accept') == 'application/json':
+ return jsonify({"message": "Indexing started in background"})
+
+ # Otherwise, render the progress page with CPU info
+ return render_template('indexing.html',
+ available_cpus=available_cpus,
+ used_cpus=used_cpus)
+
+ except Exception as e:
+ logging.error(f"Indexing failed: {e}")
+ sys.stdout = old_stdout
+
+ if request.headers.get('Accept') == 'application/json':
+ return jsonify({"error": str(e)}), 500
+
+ # Create a simple HTML response for errors
+ return render_template('indexing_error.html', error=str(e))
+ finally:
+ sys.stdout = old_stdout
+
+@app.route('/indexing_progress', methods=['GET'])
+def get_indexing_progress():
+ progress = get_progress()
+ if progress is None:
+ return jsonify({"status": "not_running"})
+
+ # Format time for display
+ from datetime import datetime
+ import pytz
+
+ # Get browser timezone from Accept-Language header or use UTC as fallback
+ browser_tz = request.headers.get('X-Timezone', 'UTC')
+ try:
+ tz = pytz.timezone(browser_tz)
+ except pytz.UnknownTimeZoneError:
+ tz = pytz.UTC
+
+ elapsed_min = int(progress['elapsed_time'] // 60)
+ elapsed_sec = int(progress['elapsed_time'] % 60)
+
+ if progress['estimated_remaining'] > 0:
+ remaining_min = int(progress['estimated_remaining'] // 60)
+ remaining_sec = int(progress['estimated_remaining'] % 60)
+ completion_time = datetime.fromtimestamp(progress['estimated_completion'], tz).strftime('%H:%M:%S (%Z)')
+ else:
+ remaining_min = 0
+ remaining_sec = 0
+ completion_time = "N/A"
+
+ return jsonify({
+ "status": "running",
+ "total_files": progress['total_files'],
+ "processed_files": progress['processed_files'],
+ "percentage": round(progress['percentage'], 1),
+ "current_file": progress['current_file'],
+ "elapsed_time": f"{elapsed_min}m {elapsed_sec}s",
+ "estimated_remaining": f"{remaining_min}m {remaining_sec}s",
+ "estimated_completion": completion_time,
+ "errors": progress['errors']
+ })
+
+@app.route('/abort_indexing', methods=['POST'])
+def abort_indexing():
+ # In a real implementation, we would set a flag to stop the indexing
+ # For now, we'll just return a message
+ return jsonify({"status": "abort_requested", "message": "Indexing will stop after current file"})
+
+@app.route('/reset_index', methods=['POST'])
+def reset_index():
+ """Reset the Elasticsearch index by deleting and recreating it"""
+ try:
+ # Check for basic auth
+ auth = request.authorization
+ if not auth or auth.username != os.environ.get("ADMIN_USER") or auth.password != os.environ.get("ADMIN_PASSWORD"):
+ return jsonify({"error": "Authentication required"}), 401
+
+ # Delete existing index if it exists
+ if es.indices.exists(index=INDEX_NAME):
+ es.indices.delete(index=INDEX_NAME)
+
+ # Create new index with mapping
+ es.indices.create(index=INDEX_NAME, body={
+ "settings": {
+ "number_of_shards": 1,
+ "number_of_replicas": 0
+ },
+ "mappings": {
+ "properties": {
+ "file_path": {"type": "keyword"},
+ "content": {"type": "text"}
+ }
+ }
+ })
+
+ return jsonify({"status": "success", "message": "Index reset successfully"})
+ except Exception as e:
+ return jsonify({"error": str(e)}), 500
+
+if __name__ == '__main__':
+ logging.basicConfig(level=logging.DEBUG)
+ logging.info("Starting the API - inside main block")
app.run(debug=True, host='0.0.0.0')
\ No newline at end of file
diff --git a/src/api/static/css/epub_viewer.css b/src/api/static/css/epub_viewer.css
index 3341c8d..1d6a7ba 100644
--- a/src/api/static/css/epub_viewer.css
+++ b/src/api/static/css/epub_viewer.css
@@ -1,66 +1,66 @@
-#viewerContainer {
- position: absolute;
- top: 50px;
- left: 0;
- right: 0;
- bottom: 0;
- overflow: auto;
-}
-
-#viewer {
- width: 100%;
- height: 90vh;
- margin: 0 auto;
-}
-
-.controls {
- text-align: center;
- padding: 10px;
-}
-
-#prev, #next {
- padding: 10px 20px;
- margin: 10px;
- background: #007bff;
- color: white;
- border: none;
- border-radius: 4px;
- cursor: pointer;
-}
-
-.error {
- color: red;
- padding: 20px;
- text-align: center;
-}
-
-header {
- text-align: center;
- padding: 20px 0;
-}
-
-.nav {
- background-color: #f8f9fa;
- padding: 10px;
-}
-
-.nav ul {
- list-style: none;
- display: flex;
- justify-content: center;
- gap: 20px;
- padding: 0;
- margin: 0;
-}
-
-.nav a {
- text-decoration: none;
- color: #007bff;
-}
-
-footer {
- text-align: center;
- padding: 20px;
- margin-top: 20px;
- background-color: #f8f9fa;
+#viewerContainer {
+ position: absolute;
+ top: 50px;
+ left: 0;
+ right: 0;
+ bottom: 0;
+ overflow: auto;
+}
+
+#viewer {
+ width: 100%;
+ height: 90vh;
+ margin: 0 auto;
+}
+
+.controls {
+ text-align: center;
+ padding: 10px;
+}
+
+#prev, #next {
+ padding: 10px 20px;
+ margin: 10px;
+ background: #007bff;
+ color: white;
+ border: none;
+ border-radius: 4px;
+ cursor: pointer;
+}
+
+.error {
+ color: red;
+ padding: 20px;
+ text-align: center;
+}
+
+header {
+ text-align: center;
+ padding: 20px 0;
+}
+
+.nav {
+ background-color: #f8f9fa;
+ padding: 10px;
+}
+
+.nav ul {
+ list-style: none;
+ display: flex;
+ justify-content: center;
+ gap: 20px;
+ padding: 0;
+ margin: 0;
+}
+
+.nav a {
+ text-decoration: none;
+ color: #007bff;
+}
+
+footer {
+ text-align: center;
+ padding: 20px;
+ margin-top: 20px;
+ background-color: #f8f9fa;
}
\ No newline at end of file
diff --git a/src/api/static/css/style.css b/src/api/static/css/style.css
index 1607718..df31208 100644
--- a/src/api/static/css/style.css
+++ b/src/api/static/css/style.css
@@ -1,236 +1,236 @@
-body {
- font-family: 'Arial', sans-serif;
- line-height: 1.6;
- margin: 0;
- padding: 0;
- background-color: #f4f4f4;
- color: #333;
-}
-
-.container {
- width: 80%;
- margin: auto;
- overflow: hidden;
- padding: 20px;
-}
-
-header {
- background: #35424a;
- color: white;
- padding: 20px;
- text-align: center;
- border-bottom: 4px solid #1abc9c;
-}
-
-header h1 {
- margin: 0;
-}
-
-.search-container {
- margin: 30px 0;
- text-align: center;
-}
-
-.search-box {
- width: 70%;
- padding: 12px;
- border: 1px solid #ddd;
- border-radius: 4px;
- font-size: 16px;
-}
-
-.search-button {
- padding: 12px 24px;
- background: #1abc9c;
- color: white;
- border: none;
- border-radius: 4px;
- cursor: pointer;
- font-size: 16px;
-}
-
-.search-button:hover {
- background: #16a085;
-}
-
-.results {
- margin-top: 30px;
-}
-
-.result-item {
- background: white;
- padding: 15px;
- margin-bottom: 15px;
- border-radius: 5px;
- box-shadow: 0 2px 5px rgba(0,0,0,0.1);
-}
-
-.result-item h3 {
- margin-top: 0;
- color: #1abc9c;
-}
-
-.result-item p {
- margin-bottom: 10px;
-}
-
-.result-item a {
- color: #3498db;
- text-decoration: none;
-}
-
-.result-item a:hover {
- text-decoration: underline;
-}
-
-.file-list {
- list-style: none;
- padding: 0;
-}
-
-.file-list li {
- background: white;
- padding: 15px;
- margin-bottom: 10px;
- border-radius: 5px;
- box-shadow: 0 2px 5px rgba(0,0,0,0.1);
-}
-
-.file-list a {
- color: #3498db;
- text-decoration: none;
- font-weight: bold;
-}
-
-.file-list a:hover {
- text-decoration: underline;
-}
-
-.nav {
- background: #35424a;
- color: white;
- padding: 10px 0;
-}
-
-.nav ul {
- padding: 0;
- list-style: none;
- text-align: center;
-}
-
-.nav li {
- display: inline;
- margin: 0 15px;
-}
-
-.nav a {
- color: white;
- text-decoration: none;
-}
-
-.nav a:hover {
- color: #1abc9c;
-}
-
-footer {
- background: #35424a;
- color: white;
- text-align: center;
- padding: 20px;
- margin-top: 40px;
-}
-
-/* Indexing page styles */
-.progress-container {
- margin: 20px 0;
- padding: 20px;
- background: #f5f5f5;
- border-radius: 5px;
-}
-
-.progress-bar {
- height: 20px;
- background: #e0e0e0;
- border-radius: 10px;
- margin: 10px 0;
- overflow: hidden;
-}
-
-.progress-fill {
- height: 100%;
- background: #4CAF50;
- width: 0%;
- transition: width 0.3s;
-}
-
-.progress-stats {
- display: flex;
- justify-content: space-between;
- margin-bottom: 10px;
-}
-
-.progress-details {
- margin-top: 20px;
-}
-
-.current-file {
- font-weight: bold;
- margin: 10px 0;
- word-break: break-all;
-}
-
-.time-stats {
- display: grid;
- grid-template-columns: repeat(2, 1fr);
- gap: 10px;
- margin-top: 15px;
-}
-
-.time-stat {
- background: #e9e9e9;
- padding: 10px;
- border-radius: 5px;
-}
-
-.abort-button {
- background: #f44336;
- color: white;
- border: none;
- padding: 10px 20px;
- border-radius: 5px;
- cursor: pointer;
- margin-top: 20px;
-}
-
-.abort-button:hover {
- background: #d32f2f;
-}
-
-.error-list {
- margin-top: 10px;
-}
-
-.error-item {
- padding: 10px;
- margin-bottom: 5px;
- background: #ffebee;
- border-left: 3px solid #f44336;
-}
-
-.file-actions {
- margin-top: 10px;
-}
-
-.file-action {
- color: #3498db;
- text-decoration: none;
-}
-
-.file-action:hover {
- text-decoration: underline;
-}
-
-.action-separator {
- margin: 0 5px;
- color: #999;
+body {
+ font-family: 'Arial', sans-serif;
+ line-height: 1.6;
+ margin: 0;
+ padding: 0;
+ background-color: #f4f4f4;
+ color: #333;
+}
+
+.container {
+ width: 80%;
+ margin: auto;
+ overflow: hidden;
+ padding: 20px;
+}
+
+header {
+ background: #35424a;
+ color: white;
+ padding: 20px;
+ text-align: center;
+ border-bottom: 4px solid #1abc9c;
+}
+
+header h1 {
+ margin: 0;
+}
+
+.search-container {
+ margin: 30px 0;
+ text-align: center;
+}
+
+.search-box {
+ width: 70%;
+ padding: 12px;
+ border: 1px solid #ddd;
+ border-radius: 4px;
+ font-size: 16px;
+}
+
+.search-button {
+ padding: 12px 24px;
+ background: #1abc9c;
+ color: white;
+ border: none;
+ border-radius: 4px;
+ cursor: pointer;
+ font-size: 16px;
+}
+
+.search-button:hover {
+ background: #16a085;
+}
+
+.results {
+ margin-top: 30px;
+}
+
+.result-item {
+ background: white;
+ padding: 15px;
+ margin-bottom: 15px;
+ border-radius: 5px;
+ box-shadow: 0 2px 5px rgba(0,0,0,0.1);
+}
+
+.result-item h3 {
+ margin-top: 0;
+ color: #1abc9c;
+}
+
+.result-item p {
+ margin-bottom: 10px;
+}
+
+.result-item a {
+ color: #3498db;
+ text-decoration: none;
+}
+
+.result-item a:hover {
+ text-decoration: underline;
+}
+
+.file-list {
+ list-style: none;
+ padding: 0;
+}
+
+.file-list li {
+ background: white;
+ padding: 15px;
+ margin-bottom: 10px;
+ border-radius: 5px;
+ box-shadow: 0 2px 5px rgba(0,0,0,0.1);
+}
+
+.file-list a {
+ color: #3498db;
+ text-decoration: none;
+ font-weight: bold;
+}
+
+.file-list a:hover {
+ text-decoration: underline;
+}
+
+.nav {
+ background: #35424a;
+ color: white;
+ padding: 10px 0;
+}
+
+.nav ul {
+ padding: 0;
+ list-style: none;
+ text-align: center;
+}
+
+.nav li {
+ display: inline;
+ margin: 0 15px;
+}
+
+.nav a {
+ color: white;
+ text-decoration: none;
+}
+
+.nav a:hover {
+ color: #1abc9c;
+}
+
+footer {
+ background: #35424a;
+ color: white;
+ text-align: center;
+ padding: 20px;
+ margin-top: 40px;
+}
+
+/* Indexing page styles */
+.progress-container {
+ margin: 20px 0;
+ padding: 20px;
+ background: #f5f5f5;
+ border-radius: 5px;
+}
+
+.progress-bar {
+ height: 20px;
+ background: #e0e0e0;
+ border-radius: 10px;
+ margin: 10px 0;
+ overflow: hidden;
+}
+
+.progress-fill {
+ height: 100%;
+ background: #4CAF50;
+ width: 0%;
+ transition: width 0.3s;
+}
+
+.progress-stats {
+ display: flex;
+ justify-content: space-between;
+ margin-bottom: 10px;
+}
+
+.progress-details {
+ margin-top: 20px;
+}
+
+.current-file {
+ font-weight: bold;
+ margin: 10px 0;
+ word-break: break-all;
+}
+
+.time-stats {
+ display: grid;
+ grid-template-columns: repeat(2, 1fr);
+ gap: 10px;
+ margin-top: 15px;
+}
+
+.time-stat {
+ background: #e9e9e9;
+ padding: 10px;
+ border-radius: 5px;
+}
+
+.abort-button {
+ background: #f44336;
+ color: white;
+ border: none;
+ padding: 10px 20px;
+ border-radius: 5px;
+ cursor: pointer;
+ margin-top: 20px;
+}
+
+.abort-button:hover {
+ background: #d32f2f;
+}
+
+.error-list {
+ margin-top: 10px;
+}
+
+.error-item {
+ padding: 10px;
+ margin-bottom: 5px;
+ background: #ffebee;
+ border-left: 3px solid #f44336;
+}
+
+.file-actions {
+ margin-top: 10px;
+}
+
+.file-action {
+ color: #3498db;
+ text-decoration: none;
+}
+
+.file-action:hover {
+ text-decoration: underline;
+}
+
+.action-separator {
+ margin: 0 5px;
+ color: #999;
}
\ No newline at end of file
diff --git a/src/api/templates/epub_viewer.html b/src/api/templates/epub_viewer.html
index e826e2b..ed49f9e 100644
--- a/src/api/templates/epub_viewer.html
+++ b/src/api/templates/epub_viewer.html
@@ -1,262 +1,262 @@
-<!DOCTYPE html>
-<html>
-<head>
- <title>{{ file_path }}</title>
- <link rel="stylesheet" href="/static/css/style.css">
- <link rel="stylesheet" href="/static/css/epub_viewer.css">
- <script src="https://cdn.jsdelivr.net/npm/epubjs@0.3.93/dist/epub.min.js"></script>
- <script src="https://cdn.jsdelivr.net/npm/jszip@3.10.1/dist/jszip.min.js"></script>
-</head>
-<body>
- <header>
- <h1>EPUB: {{ file_path }}</h1>
- </header>
-
- <nav class="nav">
- <ul>
- <li><a href="/">Home</a></li>
- <li><a href="/files">File List</a></li>
- <li><a href="/index_books">Re-Index Books</a></li>
- </ul>
- </nav>
-
- <div class="container">
- <div id="viewer"></div>
- <div class="controls">
- <button id="prev">Previous</button>
- <button id="next">Next</button>
- </div>
- </div>
-
- <script>
- // Debug logging function
- function debug(message, obj) {
- console.log("EPUB DEBUG: " + message, obj || '');
- // Add to page for visibility
- const debugDiv = document.getElementById('debug-output') ||
- (function() {
- const div = document.createElement('div');
- div.id = 'debug-output';
- div.style.position = 'fixed';
- div.style.bottom = '10px';
- div.style.right = '10px';
- div.style.backgroundColor = 'rgba(0,0,0,0.7)';
- div.style.color = 'white';
- div.style.padding = '10px';
- div.style.maxHeight = '200px';
- div.style.overflow = 'auto';
- div.style.zIndex = '9999';
- document.body.appendChild(div);
- return div;
- })();
-
- const logEntry = document.createElement('div');
- logEntry.textContent = message + (obj ? ': ' + JSON.stringify(obj) : '');
- debugDiv.appendChild(logEntry);
- }
-
- // Global variables
- var book = null;
- var rendition = null;
-
- function handlePrev() {
- debug("Previous button clicked");
- if (!rendition) {
- debug("ERROR: rendition not available for prev");
- return;
- }
- try {
- rendition.prev().then(() => {
- debug("Navigation to previous page successful");
- }).catch(err => {
- debug("Navigation to previous page failed", err.message);
- });
- } catch (err) {
- debug("Error in prev navigation", err.message);
- }
- }
-
- function handleNext() {
- debug("Next button clicked");
- if (!rendition) {
- debug("ERROR: rendition not available for next");
- return;
- }
- try {
- rendition.next().then(() => {
- debug("Navigation to next page successful");
- }).catch(err => {
- debug("Navigation to next page failed", err.message);
- });
- } catch (err) {
- debug("Error in next navigation", err.message);
- }
- }
-
- function handleKeydown(e) {
- if (!rendition) {
- debug("ERROR: rendition not available for keydown");
- return;
- }
- if (e.keyCode === 37) {
- debug("Left arrow key pressed");
- rendition.prev();
- }
- if (e.keyCode === 39) {
- debug("Right arrow key pressed");
- rendition.next();
- }
- }
-
- function initializeEPUB() {
- debug("Initializing EPUB viewer");
-
- try {
- // Use dedicated endpoint for EPUB files
- const fileUrl = "/epub/" + encodeURIComponent("{{ file_path }}");
- debug("Loading EPUB from URL", fileUrl);
- // TEST_EPUB_URL: /epub/{{ file_path }}
-
- // Create book object
- window.book = book = ePub(fileUrl);
- debug("Book object created successfully");
- console.log("Book object details:", book);
-
- if (!book) {
- throw new Error("Failed to initialize EPUB reader");
- }
-
- // Set up error handler
- book.on('error', function(err) {
- debug("EPUB error event", err);
- document.getElementById("viewer").innerHTML =
- '<div class="error">Error loading EPUB: ' + err.message + '</div>';
- });
-
- // Set up ready handler
- book.on('ready', function() {
- debug("Book ready event fired");
- });
-
- // Create rendition
- debug("Creating rendition");
- window.rendition = rendition = book.renderTo("viewer", {
- width: "100%",
- height: "100%",
- spread: "none",
- manager: "continuous",
- style: `
- body {
- margin: 0;
- padding: 20px;
- background-color: white;
- color: black;
- font-size: 1.2em;
- line-height: 1.5;
- }
- img {
- max-width: 100%;
- }
- `
- });
-
- // Hide iframe initially to prevent flash of unstyled content
- const viewer = document.getElementById("viewer");
- if (viewer) {
- viewer.style.visibility = "hidden";
- }
-
- debug("Displaying rendition");
- rendition.display()
- .then(() => {
- debug("Rendition displayed successfully");
-
- // Set up resize handler
- const resizeHandler = function() {
- try {
- if (rendition) {
- rendition.resize();
- }
- } catch (err) {
- console.error("Resize error:", err);
- }
- };
- window.addEventListener('resize', resizeHandler);
-
- // Show content and initialize navigation
- setTimeout(() => {
- try {
- if (rendition) {
- rendition.resize();
- const viewer = document.getElementById('viewer');
- if (viewer) {
- viewer.style.visibility = 'visible';
- }
- // Initialize navigation
- rendition.start();
- }
- } catch (err) {
- debug("Content display error", err.message);
- }
- }, 100);
-
- return rendition;
- })
- .catch(err => {
- debug("Rendition error", err);
- document.getElementById("viewer").innerHTML =
- '<div class="error">Error displaying EPUB: ' + err.message + '</div>';
- });
-
- // Set up event listeners
- debug("Setting up event listeners");
- try {
- document.getElementById("prev").addEventListener("click", handlePrev);
- document.getElementById("next").addEventListener("click", handleNext);
- document.addEventListener("keydown", handleKeydown);
-
- // Add loading indicator
- const loadingIndicator = document.createElement('div');
- loadingIndicator.id = 'loading-indicator';
- loadingIndicator.style.position = 'fixed';
- loadingIndicator.style.top = '50%';
- loadingIndicator.style.left = '50%';
- loadingIndicator.style.transform = 'translate(-50%, -50%)';
- loadingIndicator.style.backgroundColor = 'rgba(0,0,0,0.7)';
- loadingIndicator.style.color = 'white';
- loadingIndicator.style.padding = '20px';
- loadingIndicator.style.borderRadius = '5px';
- loadingIndicator.style.zIndex = '1000';
- loadingIndicator.textContent = 'Loading EPUB...';
- document.body.appendChild(loadingIndicator);
-
- // Remove indicator when loaded
- book.on('ready', function() {
- const indicator = document.getElementById('loading-indicator');
- if (indicator) {
- indicator.remove();
- }
- });
-
- } catch (err) {
- debug("Error setting up event listeners", err.message);
- console.error("Event listener setup error:", err);
- }
-
- } catch (err) {
- debug("EPUB initialization error", err);
- document.getElementById("viewer").innerHTML =
- '<div class="error">Failed to load EPUB: ' + err.message + '</div>';
- }
- }
-
- // Initialize when DOM is loaded
- debug("Setting up DOMContentLoaded listener");
- document.addEventListener('DOMContentLoaded', initializeEPUB);
- </script>
-
- <footer>
- <p>© 2025 Book Search Engine</p>
- </footer>
-</body>
+<!DOCTYPE html>
+<html>
+<head>
+ <title>{{ file_path }}</title>
+ <link rel="stylesheet" href="/static/css/style.css">
+ <link rel="stylesheet" href="/static/css/epub_viewer.css">
+ <script src="https://cdn.jsdelivr.net/npm/epubjs@0.3.93/dist/epub.min.js"></script>
+ <script src="https://cdn.jsdelivr.net/npm/jszip@3.10.1/dist/jszip.min.js"></script>
+</head>
+<body>
+ <header>
+ <h1>EPUB: {{ file_path }}</h1>
+ </header>
+
+ <nav class="nav">
+ <ul>
+ <li><a href="/">Home</a></li>
+ <li><a href="/files">File List</a></li>
+ <li><a href="/index_books">Re-Index Books</a></li>
+ </ul>
+ </nav>
+
+ <div class="container">
+ <div id="viewer"></div>
+ <div class="controls">
+ <button id="prev">Previous</button>
+ <button id="next">Next</button>
+ </div>
+ </div>
+
+ <script>
+ // Debug logging function
+ function debug(message, obj) {
+ console.log("EPUB DEBUG: " + message, obj || '');
+ // Add to page for visibility
+ const debugDiv = document.getElementById('debug-output') ||
+ (function() {
+ const div = document.createElement('div');
+ div.id = 'debug-output';
+ div.style.position = 'fixed';
+ div.style.bottom = '10px';
+ div.style.right = '10px';
+ div.style.backgroundColor = 'rgba(0,0,0,0.7)';
+ div.style.color = 'white';
+ div.style.padding = '10px';
+ div.style.maxHeight = '200px';
+ div.style.overflow = 'auto';
+ div.style.zIndex = '9999';
+ document.body.appendChild(div);
+ return div;
+ })();
+
+ const logEntry = document.createElement('div');
+ logEntry.textContent = message + (obj ? ': ' + JSON.stringify(obj) : '');
+ debugDiv.appendChild(logEntry);
+ }
+
+ // Global variables
+ var book = null;
+ var rendition = null;
+
+ function handlePrev() {
+ debug("Previous button clicked");
+ if (!rendition) {
+ debug("ERROR: rendition not available for prev");
+ return;
+ }
+ try {
+ rendition.prev().then(() => {
+ debug("Navigation to previous page successful");
+ }).catch(err => {
+ debug("Navigation to previous page failed", err.message);
+ });
+ } catch (err) {
+ debug("Error in prev navigation", err.message);
+ }
+ }
+
+ function handleNext() {
+ debug("Next button clicked");
+ if (!rendition) {
+ debug("ERROR: rendition not available for next");
+ return;
+ }
+ try {
+ rendition.next().then(() => {
+ debug("Navigation to next page successful");
+ }).catch(err => {
+ debug("Navigation to next page failed", err.message);
+ });
+ } catch (err) {
+ debug("Error in next navigation", err.message);
+ }
+ }
+
+ function handleKeydown(e) {
+ if (!rendition) {
+ debug("ERROR: rendition not available for keydown");
+ return;
+ }
+ if (e.keyCode === 37) {
+ debug("Left arrow key pressed");
+ rendition.prev();
+ }
+ if (e.keyCode === 39) {
+ debug("Right arrow key pressed");
+ rendition.next();
+ }
+ }
+
+ function initializeEPUB() {
+ debug("Initializing EPUB viewer");
+
+ try {
+ // Use dedicated endpoint for EPUB files
+ const fileUrl = "/epub/" + encodeURIComponent("{{ file_path }}");
+ debug("Loading EPUB from URL", fileUrl);
+ // TEST_EPUB_URL: /epub/{{ file_path }}
+
+ // Create book object
+ window.book = book = ePub(fileUrl);
+ debug("Book object created successfully");
+ console.log("Book object details:", book);
+
+ if (!book) {
+ throw new Error("Failed to initialize EPUB reader");
+ }
+
+ // Set up error handler
+ book.on('error', function(err) {
+ debug("EPUB error event", err);
+ document.getElementById("viewer").innerHTML =
+ '<div class="error">Error loading EPUB: ' + err.message + '</div>';
+ });
+
+ // Set up ready handler
+ book.on('ready', function() {
+ debug("Book ready event fired");
+ });
+
+ // Create rendition
+ debug("Creating rendition");
+ window.rendition = rendition = book.renderTo("viewer", {
+ width: "100%",
+ height: "100%",
+ spread: "none",
+ manager: "continuous",
+ style: `
+ body {
+ margin: 0;
+ padding: 20px;
+ background-color: white;
+ color: black;
+ font-size: 1.2em;
+ line-height: 1.5;
+ }
+ img {
+ max-width: 100%;
+ }
+ `
+ });
+
+ // Hide iframe initially to prevent flash of unstyled content
+ const viewer = document.getElementById("viewer");
+ if (viewer) {
+ viewer.style.visibility = "hidden";
+ }
+
+ debug("Displaying rendition");
+ rendition.display()
+ .then(() => {
+ debug("Rendition displayed successfully");
+
+ // Set up resize handler
+ const resizeHandler = function() {
+ try {
+ if (rendition) {
+ rendition.resize();
+ }
+ } catch (err) {
+ console.error("Resize error:", err);
+ }
+ };
+ window.addEventListener('resize', resizeHandler);
+
+ // Show content and initialize navigation
+ setTimeout(() => {
+ try {
+ if (rendition) {
+ rendition.resize();
+ const viewer = document.getElementById('viewer');
+ if (viewer) {
+ viewer.style.visibility = 'visible';
+ }
+ // Initialize navigation
+ rendition.start();
+ }
+ } catch (err) {
+ debug("Content display error", err.message);
+ }
+ }, 100);
+
+ return rendition;
+ })
+ .catch(err => {
+ debug("Rendition error", err);
+ document.getElementById("viewer").innerHTML =
+ '<div class="error">Error displaying EPUB: ' + err.message + '</div>';
+ });
+
+ // Set up event listeners
+ debug("Setting up event listeners");
+ try {
+ document.getElementById("prev").addEventListener("click", handlePrev);
+ document.getElementById("next").addEventListener("click", handleNext);
+ document.addEventListener("keydown", handleKeydown);
+
+ // Add loading indicator
+ const loadingIndicator = document.createElement('div');
+ loadingIndicator.id = 'loading-indicator';
+ loadingIndicator.style.position = 'fixed';
+ loadingIndicator.style.top = '50%';
+ loadingIndicator.style.left = '50%';
+ loadingIndicator.style.transform = 'translate(-50%, -50%)';
+ loadingIndicator.style.backgroundColor = 'rgba(0,0,0,0.7)';
+ loadingIndicator.style.color = 'white';
+ loadingIndicator.style.padding = '20px';
+ loadingIndicator.style.borderRadius = '5px';
+ loadingIndicator.style.zIndex = '1000';
+ loadingIndicator.textContent = 'Loading EPUB...';
+ document.body.appendChild(loadingIndicator);
+
+ // Remove indicator when loaded
+ book.on('ready', function() {
+ const indicator = document.getElementById('loading-indicator');
+ if (indicator) {
+ indicator.remove();
+ }
+ });
+
+ } catch (err) {
+ debug("Error setting up event listeners", err.message);
+ console.error("Event listener setup error:", err);
+ }
+
+ } catch (err) {
+ debug("EPUB initialization error", err);
+ document.getElementById("viewer").innerHTML =
+ '<div class="error">Failed to load EPUB: ' + err.message + '</div>';
+ }
+ }
+
+ // Initialize when DOM is loaded
+ debug("Setting up DOMContentLoaded listener");
+ document.addEventListener('DOMContentLoaded', initializeEPUB);
+ </script>
+
+ <footer>
+ <p>© 2025 Book Search Engine</p>
+ </footer>
+</body>
</html>
\ No newline at end of file
diff --git a/src/api/templates/files.html b/src/api/templates/files.html
index 99c4b31..e89a227 100644
--- a/src/api/templates/files.html
+++ b/src/api/templates/files.html
@@ -1,141 +1,141 @@
-<!DOCTYPE html>
-<html lang="en">
-<head>
- <meta charset="UTF-8">
- <meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Book Files</title>
- <link rel="stylesheet" href="/static/css/style.css">
- <style>
- .file-list {
- list-style: none;
- padding: 0;
- }
- .file-item {
- display: flex;
- justify-content: space-between;
- padding: 8px 0;
- border-bottom: 1px solid #eee;
- }
- .file-name {
- flex: 1;
- word-break: break-all;
- }
- .file-size {
- color: #666;
- min-width: 80px;
- text-align: right;
- }
- .book-title {
- font-weight: bold;
- color: #333;
- }
- .file-name-muted {
- color: #999;
- font-size: 0.9em;
- margin-left: 8px;
- }
- .summary {
- background: #f5f5f5;
- padding: 15px;
- border-radius: 5px;
- margin-bottom: 20px;
- }
- .summary-item {
- display: flex;
- justify-content: space-between;
- margin-bottom: 5px;
- }
- .summary-label {
- font-weight: bold;
- }
- .indexing-status {
- background: #fff8e1;
- padding: 15px;
- border-radius: 5px;
- margin-bottom: 20px;
- border-left: 4px solid #ffc107;
- }
- .indexing-link {
- color: #2196f3;
- text-decoration: none;
- }
- .indexing-link:hover {
- text-decoration: underline;
- }
- .plain-view-link {
- font-size: 0.8em;
- color: #666;
- text-decoration: none;
- margin-left: 8px;
- }
- .plain-view-link:hover {
- text-decoration: underline;
- color: #2196f3;
- }
- </style>
-</head>
-<body>
- <header>
- <h1>Book Files</h1>
- </header>
-
- <nav class="nav">
- <ul>
- <li><a href="/">Home</a></li>
- <li><a href="/files">File List</a></li>
- <li><a href="/index_books">Re-Index Books</a></li>
- </ul>
- </nav>
-
- <div class="container">
- <div class="summary">
- <div class="summary-item">
- <span class="summary-label">Total Files:</span>
- <span>{{ total_files }}</span>
- </div>
- <div class="summary-item">
- <span class="summary-label">Total Size:</span>
- <span>{{ total_size_mb }} MB</span>
- </div>
- </div>
-
- {% if indexing_in_progress %}
- <div class="indexing-status">
- Indexing is currently in progress.
- <a href="/index_books" class="indexing-link">View re-indexing progress</a>
- </div>
- {% endif %}
-
- <h2>Available Files</h2>
-
- {% if files %}
- <ul class="file-list">
- {% for file in files %}
- <li class="file-item">
- <span class="file-name">
- <a href="/file/{{ file.path }}">
- {% if file.path.endswith('.epub') %}
- <br><a href="/file/{{ file.path }}?format=html" class="plain-view-link">(View as HTML)</a>
- {% endif %}
- {% if file.title != file.name %}
- <span class="book-title">{{ file.title }}</span>
- <span class="file-name-muted">{{ file.name }}</span>
- {% else %}
- {{ file.name }}
- {% endif %}
- </a>
- </span>
- <span class="file-size">{{ file.size_mb }} MB</span>
- </li>
- {% endfor %}
- </ul>
- {% else %}
- <p>No files available. Please add files to the books directory.</p>
- {% endif %}
- </div>
-
- <footer>
- <p>© 2025 Intari</p>
- </footer>
-</body>
+<!DOCTYPE html>
+<html lang="en">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
+ <title>Book Files</title>
+ <link rel="stylesheet" href="/static/css/style.css">
+ <style>
+ .file-list {
+ list-style: none;
+ padding: 0;
+ }
+ .file-item {
+ display: flex;
+ justify-content: space-between;
+ padding: 8px 0;
+ border-bottom: 1px solid #eee;
+ }
+ .file-name {
+ flex: 1;
+ word-break: break-all;
+ }
+ .file-size {
+ color: #666;
+ min-width: 80px;
+ text-align: right;
+ }
+ .book-title {
+ font-weight: bold;
+ color: #333;
+ }
+ .file-name-muted {
+ color: #999;
+ font-size: 0.9em;
+ margin-left: 8px;
+ }
+ .summary {
+ background: #f5f5f5;
+ padding: 15px;
+ border-radius: 5px;
+ margin-bottom: 20px;
+ }
+ .summary-item {
+ display: flex;
+ justify-content: space-between;
+ margin-bottom: 5px;
+ }
+ .summary-label {
+ font-weight: bold;
+ }
+ .indexing-status {
+ background: #fff8e1;
+ padding: 15px;
+ border-radius: 5px;
+ margin-bottom: 20px;
+ border-left: 4px solid #ffc107;
+ }
+ .indexing-link {
+ color: #2196f3;
+ text-decoration: none;
+ }
+ .indexing-link:hover {
+ text-decoration: underline;
+ }
+ .plain-view-link {
+ font-size: 0.8em;
+ color: #666;
+ text-decoration: none;
+ margin-left: 8px;
+ }
+ .plain-view-link:hover {
+ text-decoration: underline;
+ color: #2196f3;
+ }
+ </style>
+</head>
+<body>
+ <header>
+ <h1>Book Files</h1>
+ </header>
+
+ <nav class="nav">
+ <ul>
+ <li><a href="/">Home</a></li>
+ <li><a href="/files">File List</a></li>
+ <li><a href="/index_books">Re-Index Books</a></li>
+ </ul>
+ </nav>
+
+ <div class="container">
+ <div class="summary">
+ <div class="summary-item">
+ <span class="summary-label">Total Files:</span>
+ <span>{{ total_files }}</span>
+ </div>
+ <div class="summary-item">
+ <span class="summary-label">Total Size:</span>
+ <span>{{ total_size_mb }} MB</span>
+ </div>
+ </div>
+
+ {% if indexing_in_progress %}
+ <div class="indexing-status">
+ Indexing is currently in progress.
+ <a href="/index_books" class="indexing-link">View re-indexing progress</a>
+ </div>
+ {% endif %}
+
+ <h2>Available Files</h2>
+
+ {% if files %}
+ <ul class="file-list">
+ {% for file in files %}
+ <li class="file-item">
+ <span class="file-name">
+ <a href="/file/{{ file.path }}">
+ {% if file.path.endswith('.epub') %}
+ <br><a href="/file/{{ file.path }}?format=html" class="plain-view-link">(View as HTML)</a>
+ {% endif %}
+ {% if file.title != file.name %}
+ <span class="book-title">{{ file.title }}</span>
+ <span class="file-name-muted">{{ file.name }}</span>
+ {% else %}
+ {{ file.name }}
+ {% endif %}
+ </a>
+ </span>
+ <span class="file-size">{{ file.size_mb }} MB</span>
+ </li>
+ {% endfor %}
+ </ul>
+ {% else %}
+ <p>No files available. Please add files to the books directory.</p>
+ {% endif %}
+ </div>
+
+ <footer>
+ <p>© 2025 Intari</p>
+ </footer>
+</body>
</html>
\ No newline at end of file
diff --git a/src/api/templates/indexing.html b/src/api/templates/indexing.html
index 0189159..564166d 100644
--- a/src/api/templates/indexing.html
+++ b/src/api/templates/indexing.html
@@ -1,163 +1,163 @@
-<!DOCTYPE html>
-<html lang="en">
-<head>
- <meta charset="UTF-8">
- <meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Indexing Books</title>
- <link rel="stylesheet" href="/static/css/style.css">
- <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
-</head>
-<body>
- <header>
- <h1>Indexing Books</h1>
- </header>
-
- <nav class="nav">
- <ul>
- <li><a href="/">Home</a></li>
- <li><a href="/files">File List</a></li>
- <li><a href="/index_books">Re-Index Books</a></li>
- </ul>
- </nav>
-
- <div class="container">
- <div class="progress-container">
- <h2>Indexing Progress</h2>
- <div class="progress-stats">
- <span id="processed-files">0</span> of <span id="total-files">0</span> files processed
- <span id="percentage">0%</span>
- </div>
- <div class="progress-bar">
- <div class="progress-fill" id="progress-fill"></div>
- </div>
-
- <div class="current-file" id="current-file">
- Current file: Starting indexing...
- </div>
-
- <div class="time-stats">
- <div class="time-stat">
- <div>CPU cores:</div>
- <div>{{ used_cpus }} of {{ available_cpus }}</div>
- </div>
- <div class="time-stat">
- <div>Time elapsed:</div>
- <div id="elapsed-time">0m 0s</div>
- </div>
- <div class="time-stat">
- <div>Estimated remaining:</div>
- <div id="estimated-remaining">Calculating...</div>
- </div>
- <div class="time-stat">
- <div>Estimated completion:</div>
- <div id="estimated-completion">Calculating...</div>
- </div>
- <div class="time-stat">
- <div>Files per minute:</div>
- <div id="files-per-minute">0</div>
- </div>
- </div>
-
- <button class="abort-button" id="abort-button">Abort Indexing</button>
- </div>
-
- <div class="progress-details">
- <h3>Recent Errors</h3>
- <div id="error-list" class="error-list">
- No errors yet
- </div>
- </div>
- </div>
-
- <footer>
- <p>© 2025 Intari</p>
- </footer>
-
- <script>
- const progressFill = document.getElementById('progress-fill');
- const processedFiles = document.getElementById('processed-files');
- const totalFiles = document.getElementById('total-files');
- const percentage = document.getElementById('percentage');
- const currentFile = document.getElementById('current-file');
- const elapsedTime = document.getElementById('elapsed-time');
- const estimatedRemaining = document.getElementById('estimated-remaining');
- const estimatedCompletion = document.getElementById('estimated-completion');
- const filesPerMinute = document.getElementById('files-per-minute');
- const errorList = document.getElementById('error-list');
- const abortButton = document.getElementById('abort-button');
-
- let updateInterval;
- let speedChart;
-
- // Update progress every second
- function updateProgress() {
- // Get browser timezone
- const timezone = Intl.DateTimeFormat().resolvedOptions().timeZone;
-
- fetch('/indexing_progress', {
- headers: {
- 'X-Timezone': timezone
- }
- })
- .then(response => response.json())
- .then(data => {
- if (data.status === 'not_running') {
- // Indexing completed
- clearInterval(updateInterval);
- window.location.href = '/files';
- return;
- }
-
- // Update progress bar
- progressFill.style.width = `${data.percentage}%`;
- processedFiles.textContent = data.processed_files;
- totalFiles.textContent = data.total_files;
- percentage.textContent = `${data.percentage.toFixed(1)}%`;
-
- // Update current file
- currentFile.textContent = `Current file: ${data.current_file || 'Processing...'}`;
-
- // Update time stats
- elapsedTime.textContent = data.elapsed_time;
- estimatedRemaining.textContent = data.estimated_remaining;
- estimatedCompletion.textContent = data.estimated_completion;
-
- // Calculate files per minute
- if (data.elapsed_time) {
- const [min, sec] = data.elapsed_time.split(/[ms]/).filter(Boolean).map(Number);
- const totalSeconds = min * 60 + sec;
- if (totalSeconds > 0) {
- const fpm = (data.processed_files / totalSeconds * 60).toFixed(1);
- filesPerMinute.textContent = fpm;
- }
- }
-
- // Update errors
- if (data.errors && data.errors.length > 0) {
- errorList.innerHTML = data.errors.map(err =>
- `<div class="error-item">${err}</div>`
- ).join('');
- }
- })
- .catch(error => {
- console.error('Error fetching progress:', error);
- });
- }
-
- // Start updating progress
- updateInterval = setInterval(updateProgress, 1000);
- updateProgress();
-
- // Handle abort button
- abortButton.addEventListener('click', () => {
- if (confirm('Are you sure you want to abort indexing?')) {
- fetch('/abort_indexing', { method: 'POST' })
- .then(response => response.json())
- .then(data => {
- alert(data.message);
- });
- }
- });
- </script>
-</body>
+<!DOCTYPE html>
+<html lang="en">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
+ <title>Indexing Books</title>
+ <link rel="stylesheet" href="/static/css/style.css">
+ <script src="https://cdn.jsdelivr.net/npm/chart.js"></script>
+</head>
+<body>
+ <header>
+ <h1>Indexing Books</h1>
+ </header>
+
+ <nav class="nav">
+ <ul>
+ <li><a href="/">Home</a></li>
+ <li><a href="/files">File List</a></li>
+ <li><a href="/index_books">Re-Index Books</a></li>
+ </ul>
+ </nav>
+
+ <div class="container">
+ <div class="progress-container">
+ <h2>Indexing Progress</h2>
+ <div class="progress-stats">
+ <span id="processed-files">0</span> of <span id="total-files">0</span> files processed
+ <span id="percentage">0%</span>
+ </div>
+ <div class="progress-bar">
+ <div class="progress-fill" id="progress-fill"></div>
+ </div>
+
+ <div class="current-file" id="current-file">
+ Current file: Starting indexing...
+ </div>
+
+ <div class="time-stats">
+ <div class="time-stat">
+ <div>CPU cores:</div>
+ <div>{{ used_cpus }} of {{ available_cpus }}</div>
+ </div>
+ <div class="time-stat">
+ <div>Time elapsed:</div>
+ <div id="elapsed-time">0m 0s</div>
+ </div>
+ <div class="time-stat">
+ <div>Estimated remaining:</div>
+ <div id="estimated-remaining">Calculating...</div>
+ </div>
+ <div class="time-stat">
+ <div>Estimated completion:</div>
+ <div id="estimated-completion">Calculating...</div>
+ </div>
+ <div class="time-stat">
+ <div>Files per minute:</div>
+ <div id="files-per-minute">0</div>
+ </div>
+ </div>
+
+ <button class="abort-button" id="abort-button">Abort Indexing</button>
+ </div>
+
+ <div class="progress-details">
+ <h3>Recent Errors</h3>
+ <div id="error-list" class="error-list">
+ No errors yet
+ </div>
+ </div>
+ </div>
+
+ <footer>
+ <p>© 2025 Intari</p>
+ </footer>
+
+ <script>
+ const progressFill = document.getElementById('progress-fill');
+ const processedFiles = document.getElementById('processed-files');
+ const totalFiles = document.getElementById('total-files');
+ const percentage = document.getElementById('percentage');
+ const currentFile = document.getElementById('current-file');
+ const elapsedTime = document.getElementById('elapsed-time');
+ const estimatedRemaining = document.getElementById('estimated-remaining');
+ const estimatedCompletion = document.getElementById('estimated-completion');
+ const filesPerMinute = document.getElementById('files-per-minute');
+ const errorList = document.getElementById('error-list');
+ const abortButton = document.getElementById('abort-button');
+
+ let updateInterval;
+ let speedChart;
+
+ // Update progress every second
+ function updateProgress() {
+ // Get browser timezone
+ const timezone = Intl.DateTimeFormat().resolvedOptions().timeZone;
+
+ fetch('/indexing_progress', {
+ headers: {
+ 'X-Timezone': timezone
+ }
+ })
+ .then(response => response.json())
+ .then(data => {
+ if (data.status === 'not_running') {
+ // Indexing completed
+ clearInterval(updateInterval);
+ window.location.href = '/files';
+ return;
+ }
+
+ // Update progress bar
+ progressFill.style.width = `${data.percentage}%`;
+ processedFiles.textContent = data.processed_files;
+ totalFiles.textContent = data.total_files;
+ percentage.textContent = `${data.percentage.toFixed(1)}%`;
+
+ // Update current file
+ currentFile.textContent = `Current file: ${data.current_file || 'Processing...'}`;
+
+ // Update time stats
+ elapsedTime.textContent = data.elapsed_time;
+ estimatedRemaining.textContent = data.estimated_remaining;
+ estimatedCompletion.textContent = data.estimated_completion;
+
+ // Calculate files per minute
+ if (data.elapsed_time) {
+ const [min, sec] = data.elapsed_time.split(/[ms]/).filter(Boolean).map(Number);
+ const totalSeconds = min * 60 + sec;
+ if (totalSeconds > 0) {
+ const fpm = (data.processed_files / totalSeconds * 60).toFixed(1);
+ filesPerMinute.textContent = fpm;
+ }
+ }
+
+ // Update errors
+ if (data.errors && data.errors.length > 0) {
+ errorList.innerHTML = data.errors.map(err =>
+ `<div class="error-item">${err}</div>`
+ ).join('');
+ }
+ })
+ .catch(error => {
+ console.error('Error fetching progress:', error);
+ });
+ }
+
+ // Start updating progress
+ updateInterval = setInterval(updateProgress, 1000);
+ updateProgress();
+
+ // Handle abort button
+ abortButton.addEventListener('click', () => {
+ if (confirm('Are you sure you want to abort indexing?')) {
+ fetch('/abort_indexing', { method: 'POST' })
+ .then(response => response.json())
+ .then(data => {
+ alert(data.message);
+ });
+ }
+ });
+ </script>
+</body>
</html>
\ No newline at end of file
diff --git a/src/api/templates/search.html b/src/api/templates/search.html
index 2861a62..604cfeb 100644
--- a/src/api/templates/search.html
+++ b/src/api/templates/search.html
@@ -1,56 +1,56 @@
-<!DOCTYPE html>
-<html lang="en">
-<head>
- <meta charset="UTF-8">
- <meta name="viewport" content="width=device-width, initial-scale=1.0">
- <title>Book Search</title>
- <link rel="stylesheet" href="/static/css/style.css">
-</head>
-<body>
- <header>
- <h1>Book Search Engine</h1>
- </header>
-
- <nav class="nav">
- <ul>
- <li><a href="/">Home</a></li>
- <li><a href="/files">File List</a></li>
- <li><a href="/index_books">Re-Index Books</a></li>
- </ul>
- </nav>
-
- <div class="container">
- <div class="search-container">
- <form action="/search" method="GET">
- <input type="text" name="query" placeholder="Search for content..." class="search-box" value="{{ query }}">
- <button type="submit" class="search-button">Search</button>
- </form>
- </div>
-
- {% if results %}
- <div class="results">
- <h2>Search Results</h2>
- {% for result in results %}
- <div class="result-item">
- <h3>{{ result.file_path.split('/')[-1] }}</h3>
- <p>{{ result.snippet }}</p>
- <div class="file-actions">
- <a href="/file/{{ result.file_path.replace('/books/', '') }}" class="file-action">View Full File</a>
- <span class="action-separator">|</span>
- <a href="/file/{{ result.file_path.replace('/books/', '') }}?format=html" class="file-action">View as HTML</a>
- </div>
- </div>
- {% endfor %}
- </div>
- {% elif query %}
- <div class="results">
- <p>No results found for "{{ query }}"</p>
- </div>
- {% endif %}
- </div>
-
- <footer>
- <p>© 2025 Intari</p>
- </footer>
-</body>
+<!DOCTYPE html>
+<html lang="en">
+<head>
+ <meta charset="UTF-8">
+ <meta name="viewport" content="width=device-width, initial-scale=1.0">
+ <title>Book Search</title>
+ <link rel="stylesheet" href="/static/css/style.css">
+</head>
+<body>
+ <header>
+ <h1>Book Search Engine</h1>
+ </header>
+
+ <nav class="nav">
+ <ul>
+ <li><a href="/">Home</a></li>
+ <li><a href="/files">File List</a></li>
+ <li><a href="/index_books">Re-Index Books</a></li>
+ </ul>
+ </nav>
+
+ <div class="container">
+ <div class="search-container">
+ <form action="/search" method="GET">
+ <input type="text" name="query" placeholder="Search for content..." class="search-box" value="{{ query }}">
+ <button type="submit" class="search-button">Search</button>
+ </form>
+ </div>
+
+ {% if results %}
+ <div class="results">
+ <h2>Search Results</h2>
+ {% for result in results %}
+ <div class="result-item">
+ <h3>{{ result.file_path.split('/')[-1] }}</h3>
+ <p>{{ result.snippet }}</p>
+ <div class="file-actions">
+ <a href="/file/{{ result.file_path.replace('/books/', '') }}" class="file-action">View Full File</a>
+ <span class="action-separator">|</span>
+ <a href="/file/{{ result.file_path.replace('/books/', '') }}?format=html" class="file-action">View as HTML</a>
+ </div>
+ </div>
+ {% endfor %}
+ </div>
+ {% elif query %}
+ <div class="results">
+ <p>No results found for "{{ query }}"</p>
+ </div>
+ {% endif %}
+ </div>
+
+ <footer>
+ <p>© 2025 Intari</p>
+ </footer>
+</body>
</html>
\ No newline at end of file
diff --git a/src/api/templates/text_file.html b/src/api/templates/text_file.html
index cb05941..9c4a300 100644
--- a/src/api/templates/text_file.html
+++ b/src/api/templates/text_file.html
@@ -1,64 +1,64 @@
-и<!DOCTYPE html>
-<html>
-<head>
- <title>{{ file_path }}</title>
- <link rel="stylesheet" href="/static/css/style.css">
- <style>
- pre {
- background-color: white;
- padding: 20px;
- border-radius: 5px;
- white-space: pre-wrap;
- word-wrap: break-word;
- }
- .html-content {
- background-color: white;
- padding: 20px;
- border-radius: 5px;
- }
- .html-content hr {
- margin: 30px 0;
- border: 0;
- border-top: 1px solid #eee;
- }
- .html-content h1,
- .html-content h2,
- .html-content h3,
- .html-content h4,
- .html-content h5,
- .html-content h6 {
- margin: 1em 0 0.5em 0;
- line-height: 1.2;
- }
- .html-content p {
- margin: 0 0 1em 0;
- line-height: 1.5;
- }
- </style>
-</head>
-<body>
- <header>
- <h1>File: {{ file_path }}</h1>
- </header>
-
- <nav class="nav">
- <ul>
- <li><a href="/">Home</a></li>
- <li><a href="/files">File List</a></li>
- <li><a href="/index_books">Re-Index Books</a></li>
- </ul>
- </nav>
-
- <div class="container">
- {% if is_html %}
- <div class="html-content">{{ content|safe }}</div>
- {% else %}
- <pre>{{ content }}</pre>
- {% endif %}
- </div>
-
- <footer>
- <p>© 2025 Book Search Engine</p>
- </footer>
-</body>
+и<!DOCTYPE html>
+<html>
+<head>
+ <title>{{ file_path }}</title>
+ <link rel="stylesheet" href="/static/css/style.css">
+ <style>
+ pre {
+ background-color: white;
+ padding: 20px;
+ border-radius: 5px;
+ white-space: pre-wrap;
+ word-wrap: break-word;
+ }
+ .html-content {
+ background-color: white;
+ padding: 20px;
+ border-radius: 5px;
+ }
+ .html-content hr {
+ margin: 30px 0;
+ border: 0;
+ border-top: 1px solid #eee;
+ }
+ .html-content h1,
+ .html-content h2,
+ .html-content h3,
+ .html-content h4,
+ .html-content h5,
+ .html-content h6 {
+ margin: 1em 0 0.5em 0;
+ line-height: 1.2;
+ }
+ .html-content p {
+ margin: 0 0 1em 0;
+ line-height: 1.5;
+ }
+ </style>
+</head>
+<body>
+ <header>
+ <h1>File: {{ file_path }}</h1>
+ </header>
+
+ <nav class="nav">
+ <ul>
+ <li><a href="/">Home</a></li>
+ <li><a href="/files">File List</a></li>
+ <li><a href="/index_books">Re-Index Books</a></li>
+ </ul>
+ </nav>
+
+ <div class="container">
+ {% if is_html %}
+ <div class="html-content">{{ content|safe }}</div>
+ {% else %}
+ <pre>{{ content }}</pre>
+ {% endif %}
+ </div>
+
+ <footer>
+ <p>© 2025 Book Search Engine</p>
+ </footer>
+</body>
</html>
\ No newline at end of file
diff --git a/src/core/index.py b/src/core/index.py
index e935ef3..3b41a21 100644
--- a/src/core/index.py
+++ b/src/core/index.py
@@ -1,142 +1,142 @@
-from elasticsearch import Elasticsearch
-import os
-import ebooklib
-from ebooklib import epub
-from bs4 import BeautifulSoup
-import PyPDF2
-import time
-from threading import Lock
-
-# Elasticsearch Configuration
-ELASTICSEARCH_HOST = os.environ.get("ELASTICSEARCH_HOST", "localhost")
-ELASTICSEARCH_PORT = int(os.environ.get("ELASTICSEARCH_PORT", 9200))
-es = Elasticsearch([{'host': ELASTICSEARCH_HOST, 'port': ELASTICSEARCH_PORT, 'scheme': 'http'}])
-INDEX_NAME = "book_index"
-
-# Global variables for progress tracking
-indexing_progress = {
- 'total_files': 0,
- 'processed_files': 0,
- 'start_time': None,
- 'is_running': False,
- 'current_file': '',
- 'errors': []
-}
-progress_lock = Lock()
-
-def create_index():
- if not es.indices.exists(index=INDEX_NAME):
- es.indices.create(index=INDEX_NAME)
-
-def extract_text_from_epub(epub_path):
- book = epub.read_epub(epub_path)
- text = ''
- for item in book.get_items():
- if item.media_type == 'application/xhtml+xml':
- soup = BeautifulSoup(item.get_content(), 'html.parser')
- text += soup.get_text()
- return text
-
-def extract_text_from_pdf(pdf_path):
- text = ''
- with open(pdf_path, 'rb') as pdf_file:
- pdf_reader = PyPDF2.PdfReader(pdf_file)
- for page_num in range(len(pdf_reader.pages)):
- page = pdf_reader.pages[page_num]
- text += page.extract_text()
- return text
-
-def get_progress():
- with progress_lock:
- if not indexing_progress['is_running']:
- return None
-
- progress = indexing_progress.copy()
- if progress['total_files'] > 0:
- progress['percentage'] = (progress['processed_files'] / progress['total_files']) * 100
- else:
- progress['percentage'] = 0
-
- elapsed = time.time() - progress['start_time']
- progress['elapsed_time'] = elapsed
- if progress['processed_files'] > 0:
- time_per_file = elapsed / progress['processed_files']
- remaining_files = progress['total_files'] - progress['processed_files']
- progress['estimated_remaining'] = time_per_file * remaining_files
- progress['estimated_completion'] = time.time() + progress['estimated_remaining']
- else:
- progress['estimated_remaining'] = 0
- progress['estimated_completion'] = 0
-
- return progress
-
-def index_files(directory):
- global indexing_progress
-
- with progress_lock:
- indexing_progress = {
- 'total_files': 0,
- 'processed_files': 0,
- 'start_time': time.time(),
- 'is_running': True,
- 'current_file': '',
- 'errors': []
- }
-
- try:
- create_index()
-
- # First count all files
- total_files = 0
- for root, _, files in os.walk(directory):
- for file in files:
- if file.endswith(('.epub', '.pdf', '.txt')):
- total_files += 1
-
- with progress_lock:
- indexing_progress['total_files'] = total_files
-
- # Now process files
- for root, _, files in os.walk(directory):
- for file in files:
- file_path = os.path.join(root, file)
-
- with progress_lock:
- indexing_progress['current_file'] = file_path
-
- try:
- encoded_file_path = file_path.encode('utf-8').decode('utf-8')
- if file_path.endswith(".epub"):
- text = extract_text_from_epub(file_path)
- elif file_path.endswith(".pdf"):
- text = extract_text_from_pdf(file_path)
- elif file_path.endswith(".txt"):
- with open(encoded_file_path, 'r', encoding='utf-8', errors='ignore') as f:
- text = f.read()
- else:
- print(f"Skipping unsupported file type: {file_path}")
- continue
-
- doc = {
- 'file_path': file_path,
- 'content': text
- }
- es.index(index=INDEX_NAME, document=doc)
- print(f"Indexed: {file_path}")
-
- with progress_lock:
- indexing_progress['processed_files'] += 1
-
- except Exception as e:
- error_msg = f"Error indexing {file_path}: {type(e)}, {e}"
- print(error_msg)
- with progress_lock:
- indexing_progress['errors'].append(error_msg)
-
- finally:
- with progress_lock:
- indexing_progress['is_running'] = False
-
-if __name__ == '__main__':
- BOOKS_DIR = "/books" # This should match the volume mount in docker-compose.yml
+from elasticsearch import Elasticsearch
+import os
+import ebooklib
+from ebooklib import epub
+from bs4 import BeautifulSoup
+import PyPDF2
+import time
+from threading import Lock
+
+# Elasticsearch Configuration
+ELASTICSEARCH_HOST = os.environ.get("ELASTICSEARCH_HOST", "localhost")
+ELASTICSEARCH_PORT = int(os.environ.get("ELASTICSEARCH_PORT", 9200))
+es = Elasticsearch([{'host': ELASTICSEARCH_HOST, 'port': ELASTICSEARCH_PORT, 'scheme': 'http'}])
+INDEX_NAME = "book_index"
+
+# Global variables for progress tracking
+indexing_progress = {
+ 'total_files': 0,
+ 'processed_files': 0,
+ 'start_time': None,
+ 'is_running': False,
+ 'current_file': '',
+ 'errors': []
+}
+progress_lock = Lock()
+
+def create_index():
+ if not es.indices.exists(index=INDEX_NAME):
+ es.indices.create(index=INDEX_NAME)
+
+def extract_text_from_epub(epub_path):
+ book = epub.read_epub(epub_path)
+ text = ''
+ for item in book.get_items():
+ if item.media_type == 'application/xhtml+xml':
+ soup = BeautifulSoup(item.get_content(), 'html.parser')
+ text += soup.get_text()
+ return text
+
+def extract_text_from_pdf(pdf_path):
+ text = ''
+ with open(pdf_path, 'rb') as pdf_file:
+ pdf_reader = PyPDF2.PdfReader(pdf_file)
+ for page_num in range(len(pdf_reader.pages)):
+ page = pdf_reader.pages[page_num]
+ text += page.extract_text()
+ return text
+
+def get_progress():
+ with progress_lock:
+ if not indexing_progress['is_running']:
+ return None
+
+ progress = indexing_progress.copy()
+ if progress['total_files'] > 0:
+ progress['percentage'] = (progress['processed_files'] / progress['total_files']) * 100
+ else:
+ progress['percentage'] = 0
+
+ elapsed = time.time() - progress['start_time']
+ progress['elapsed_time'] = elapsed
+ if progress['processed_files'] > 0:
+ time_per_file = elapsed / progress['processed_files']
+ remaining_files = progress['total_files'] - progress['processed_files']
+ progress['estimated_remaining'] = time_per_file * remaining_files
+ progress['estimated_completion'] = time.time() + progress['estimated_remaining']
+ else:
+ progress['estimated_remaining'] = 0
+ progress['estimated_completion'] = 0
+
+ return progress
+
+def index_files(directory):
+ global indexing_progress
+
+ with progress_lock:
+ indexing_progress = {
+ 'total_files': 0,
+ 'processed_files': 0,
+ 'start_time': time.time(),
+ 'is_running': True,
+ 'current_file': '',
+ 'errors': []
+ }
+
+ try:
+ create_index()
+
+ # First count all files
+ total_files = 0
+ for root, _, files in os.walk(directory):
+ for file in files:
+ if file.endswith(('.epub', '.pdf', '.txt')):
+ total_files += 1
+
+ with progress_lock:
+ indexing_progress['total_files'] = total_files
+
+ # Now process files
+ for root, _, files in os.walk(directory):
+ for file in files:
+ file_path = os.path.join(root, file)
+
+ with progress_lock:
+ indexing_progress['current_file'] = file_path
+
+ try:
+ encoded_file_path = file_path.encode('utf-8').decode('utf-8')
+ if file_path.endswith(".epub"):
+ text = extract_text_from_epub(file_path)
+ elif file_path.endswith(".pdf"):
+ text = extract_text_from_pdf(file_path)
+ elif file_path.endswith(".txt"):
+ with open(encoded_file_path, 'r', encoding='utf-8', errors='ignore') as f:
+ text = f.read()
+ else:
+ print(f"Skipping unsupported file type: {file_path}")
+ continue
+
+ doc = {
+ 'file_path': file_path,
+ 'content': text
+ }
+ es.index(index=INDEX_NAME, document=doc)
+ print(f"Indexed: {file_path}")
+
+ with progress_lock:
+ indexing_progress['processed_files'] += 1
+
+ except Exception as e:
+ error_msg = f"Error indexing {file_path}: {type(e)}, {e}"
+ print(error_msg)
+ with progress_lock:
+ indexing_progress['errors'].append(error_msg)
+
+ finally:
+ with progress_lock:
+ indexing_progress['is_running'] = False
+
+if __name__ == '__main__':
+ BOOKS_DIR = "/books" # This should match the volume mount in docker-compose.yml
index_files(BOOKS_DIR)
\ No newline at end of file
diff --git a/src/requirements.txt b/src/requirements.txt
index 590f8f2..051e80d 100644
--- a/src/requirements.txt
+++ b/src/requirements.txt
@@ -1,7 +1,7 @@
-flask==3.0.2
-ebooklib==0.18
-beautifulsoup4==4.12.3
-pytest==8.3.2
-PyPDF2==3.0.1
-pytz==2024.1
+flask==3.0.2
+ebooklib==0.18
+beautifulsoup4==4.12.3
+pytest==8.3.2
+PyPDF2==3.0.1
+pytz==2024.1
elasticsearch>=8.0.0
\ No newline at end of file
diff --git a/tests/unit/test_app.py b/tests/unit/test_app.py
index 069a53d..65ef2df 100644
--- a/tests/unit/test_app.py
+++ b/tests/unit/test_app.py
@@ -1,127 +1,127 @@
-import unittest
-import json
-import os
-import tempfile
-import shutil
-from app import app
-from unittest.mock import patch, MagicMock
-
-class BookSearchAPITest(unittest.TestCase):
- def setUp(self):
- app.config['TESTING'] = True
- self.client = app.test_client()
-
- # Create a temporary directory for test books
- self.test_books_dir = tempfile.mkdtemp()
-
- # Create a sample test file
- self.sample_file_path = os.path.join(self.test_books_dir, 'test_sample.txt')
- with open(self.sample_file_path, 'w', encoding='utf-8') as f:
- f.write("This is a test sample file for testing the book search API.")
-
- def tearDown(self):
- # Remove the temporary directory
- shutil.rmtree(self.test_books_dir)
-
- @patch('app.es')
- @patch('app.index_files')
- def test_index_books_api(self, mock_index_files, mock_es):
- # Mock the index_files function
- mock_index_files.return_value = None
-
- # Test the API endpoint
- response = self.client.get('/index_books', headers={'Accept': 'application/json'})
-
- # Check if the response is successful
- self.assertEqual(response.status_code, 200)
-
- # Check if the response contains the expected message
- data = json.loads(response.data)
- self.assertIn('message', data)
- self.assertEqual(data['message'], 'Indexing completed')
-
- # Check if the index_files function was called
- mock_index_files.assert_called_once_with('/books')
-
- @patch('app.es')
- def test_search_api(self, mock_es):
- # Mock the Elasticsearch search method
- mock_search_result = {
- 'hits': {
- 'hits': [
- {
- '_source': {
- 'file_path': '/books/test_sample.txt',
- 'content': 'This is a test sample file for testing the book search API.'
- }
- }
- ]
- }
- }
- mock_es.search.return_value = mock_search_result
-
- # Test the API endpoint
- response = self.client.get('/search?query=test', headers={'Accept': 'application/json'})
-
- # Check if the response is successful
- self.assertEqual(response.status_code, 200)
-
- # Check if the response contains the expected data
- data = json.loads(response.data)
- self.assertEqual(len(data), 1)
- self.assertEqual(data[0]['file_path'], '/books/test_sample.txt')
- self.assertIn('snippet', data[0])
-
- # Check if the Elasticsearch search method was called with the correct parameters
- mock_es.search.assert_called_once()
-
- @patch('app.os.listdir')
- @patch('app.os.path.isfile')
- def test_list_files_api(self, mock_isfile, mock_listdir):
- # Mock the os.listdir function
- mock_listdir.return_value = ['test_sample.txt', 'another_file.txt']
- # Mock the os.path.isfile function to always return True
- mock_isfile.return_value = True
-
- # Test the API endpoint
- response = self.client.get('/files', headers={'Accept': 'application/json'})
-
- # Check if the response is successful
- self.assertEqual(response.status_code, 200)
-
- # Check if the response contains the expected data
- data = json.loads(response.data)
- self.assertEqual(len(data), 2)
- self.assertEqual(data[0]['name'], 'test_sample.txt')
- self.assertEqual(data[1]['name'], 'another_file.txt')
-
- # Check if the os.listdir function was called with the correct parameters
- mock_listdir.assert_called_once_with('/books')
-
- @patch('app.open')
- @patch('app.os.path.isfile')
- @patch('app.os.path.abspath')
- def test_get_file_api(self, mock_abspath, mock_isfile, mock_open):
- # Mock the necessary functions
- mock_isfile.return_value = True
- mock_abspath.side_effect = lambda x: x # Return the input unchanged
-
- # Mock the open function
- mock_file = MagicMock()
- mock_file.__enter__.return_value.read.return_value = "This is a test sample file."
- mock_open.return_value = mock_file
-
- # Test the API endpoint
- response = self.client.get('/file/test_sample.txt', headers={'Accept': 'application/json'})
-
- # Check if the response is successful
- self.assertEqual(response.status_code, 200)
-
- # Check if the response contains the expected data
- self.assertEqual(response.data.decode('utf-8'), "This is a test sample file.")
-
- # Check if the open function was called with the correct parameters
- mock_open.assert_called_once()
-
-if __name__ == '__main__':
+import unittest
+import json
+import os
+import tempfile
+import shutil
+from app import app
+from unittest.mock import patch, MagicMock
+
+class BookSearchAPITest(unittest.TestCase):
+ def setUp(self):
+ app.config['TESTING'] = True
+ self.client = app.test_client()
+
+ # Create a temporary directory for test books
+ self.test_books_dir = tempfile.mkdtemp()
+
+ # Create a sample test file
+ self.sample_file_path = os.path.join(self.test_books_dir, 'test_sample.txt')
+ with open(self.sample_file_path, 'w', encoding='utf-8') as f:
+ f.write("This is a test sample file for testing the book search API.")
+
+ def tearDown(self):
+ # Remove the temporary directory
+ shutil.rmtree(self.test_books_dir)
+
+ @patch('app.es')
+ @patch('app.index_files')
+ def test_index_books_api(self, mock_index_files, mock_es):
+ # Mock the index_files function
+ mock_index_files.return_value = None
+
+ # Test the API endpoint
+ response = self.client.get('/index_books', headers={'Accept': 'application/json'})
+
+ # Check if the response is successful
+ self.assertEqual(response.status_code, 200)
+
+ # Check if the response contains the expected message
+ data = json.loads(response.data)
+ self.assertIn('message', data)
+ self.assertEqual(data['message'], 'Indexing completed')
+
+ # Check if the index_files function was called
+ mock_index_files.assert_called_once_with('/books')
+
+ @patch('app.es')
+ def test_search_api(self, mock_es):
+ # Mock the Elasticsearch search method
+ mock_search_result = {
+ 'hits': {
+ 'hits': [
+ {
+ '_source': {
+ 'file_path': '/books/test_sample.txt',
+ 'content': 'This is a test sample file for testing the book search API.'
+ }
+ }
+ ]
+ }
+ }
+ mock_es.search.return_value = mock_search_result
+
+ # Test the API endpoint
+ response = self.client.get('/search?query=test', headers={'Accept': 'application/json'})
+
+ # Check if the response is successful
+ self.assertEqual(response.status_code, 200)
+
+ # Check if the response contains the expected data
+ data = json.loads(response.data)
+ self.assertEqual(len(data), 1)
+ self.assertEqual(data[0]['file_path'], '/books/test_sample.txt')
+ self.assertIn('snippet', data[0])
+
+ # Check if the Elasticsearch search method was called with the correct parameters
+ mock_es.search.assert_called_once()
+
+ @patch('app.os.listdir')
+ @patch('app.os.path.isfile')
+ def test_list_files_api(self, mock_isfile, mock_listdir):
+ # Mock the os.listdir function
+ mock_listdir.return_value = ['test_sample.txt', 'another_file.txt']
+ # Mock the os.path.isfile function to always return True
+ mock_isfile.return_value = True
+
+ # Test the API endpoint
+ response = self.client.get('/files', headers={'Accept': 'application/json'})
+
+ # Check if the response is successful
+ self.assertEqual(response.status_code, 200)
+
+ # Check if the response contains the expected data
+ data = json.loads(response.data)
+ self.assertEqual(len(data), 2)
+ self.assertEqual(data[0]['name'], 'test_sample.txt')
+ self.assertEqual(data[1]['name'], 'another_file.txt')
+
+ # Check if the os.listdir function was called with the correct parameters
+ mock_listdir.assert_called_once_with('/books')
+
+ @patch('app.open')
+ @patch('app.os.path.isfile')
+ @patch('app.os.path.abspath')
+ def test_get_file_api(self, mock_abspath, mock_isfile, mock_open):
+ # Mock the necessary functions
+ mock_isfile.return_value = True
+ mock_abspath.side_effect = lambda x: x # Return the input unchanged
+
+ # Mock the open function
+ mock_file = MagicMock()
+ mock_file.__enter__.return_value.read.return_value = "This is a test sample file."
+ mock_open.return_value = mock_file
+
+ # Test the API endpoint
+ response = self.client.get('/file/test_sample.txt', headers={'Accept': 'application/json'})
+
+ # Check if the response is successful
+ self.assertEqual(response.status_code, 200)
+
+ # Check if the response contains the expected data
+ self.assertEqual(response.data.decode('utf-8'), "This is a test sample file.")
+
+ # Check if the open function was called with the correct parameters
+ mock_open.assert_called_once()
+
+if __name__ == '__main__':
unittest.main()
\ No newline at end of file
diff --git a/tests/unit/test_epub_viewer.py b/tests/unit/test_epub_viewer.py
index bda9e7c..eb50797 100644
--- a/tests/unit/test_epub_viewer.py
+++ b/tests/unit/test_epub_viewer.py
@@ -1,114 +1,114 @@
-import os
-import pytest
-import tempfile
-import shutil
-from app import app
-from unittest.mock import patch, MagicMock
-from ebooklib import epub
-
-def create_test_epub():
- """Create a simple test EPUB file"""
- # Create a simple EPUB file
- book = epub.EpubBook()
-
- # Set metadata
- book.set_identifier('test123456')
- book.set_title('Test EPUB Book')
- book.set_language('en')
- book.add_author('Test Author')
-
- # Add a chapter
- c1 = epub.EpubHtml(title='Chapter 1', file_name='chap_01.xhtml', lang='en')
- c1.content = '<html><body><h1>Chapter 1</h1><p>This is a test EPUB file.</p></body></html>'
- book.add_item(c1)
-
- # Add navigation
- book.toc = [c1]
- book.spine = ['nav', c1]
- book.add_item(epub.EpubNcx())
- book.add_item(epub.EpubNav())
-
- # Create temp directory
- temp_dir = tempfile.mkdtemp()
- epub_path = os.path.join(temp_dir, 'test.epub')
-
- # Write the EPUB file
- epub.write_epub(epub_path, book)
-
- return epub_path, temp_dir
-
-@pytest.fixture
-def client():
- """Create a test client for the Flask app"""
- app.config['TESTING'] = True
- with app.test_client() as client:
- yield client
-
-@pytest.fixture
-def test_epub():
- """Create a test EPUB file and clean up after the test"""
- epub_path, temp_dir = create_test_epub()
-
- # Mock the books directory
- original_join = os.path.join
-
- def mock_join(path, *paths):
- if path == "/books" and paths and paths[0] == "test.epub":
- return epub_path
- return original_join(path, *paths)
-
- def mock_abspath(path):
- if path == os.path.join("/books", "test.epub"):
- return "/books/test.epub"
- elif path == epub_path:
- return "/books/test.epub"
- return path
-
- with patch('os.path.join', side_effect=mock_join):
- with patch('os.path.isfile', return_value=True):
- with patch('os.path.abspath', side_effect=mock_abspath):
- yield epub_path
-
- # Clean up
- shutil.rmtree(temp_dir)
-
-def test_epub_viewer_page(client, test_epub):
- """Test that the EPUB viewer page loads correctly"""
- response = client.get('/file/test.epub')
-
- assert response.status_code == 200
- assert b'<!DOCTYPE html>' in response.data
- assert b'<title>test.epub</title>' in response.data
- assert b'<div id="viewer"></div>' in response.data
- assert b'<script src="https://cdn.jsdelivr.net/npm/epubjs' in response.data
-
-def test_epub_file_endpoint(client, test_epub):
- """Test that the EPUB file is served with correct headers"""
- response = client.get('/epub/test.epub')
-
- assert response.status_code == 200
- assert response.headers['Content-Type'] == 'application/epub+zip'
- assert response.headers['Access-Control-Allow-Origin'] == '*'
-
- # Check that the response contains EPUB data (at least the magic number)
- assert response.data.startswith(b'PK')
-
-def test_epub_viewer_integration(client, test_epub):
- """Test the integration between the viewer and the EPUB file"""
- # This test would ideally use Selenium or Playwright to test the actual rendering
- # Since we can't run a browser in this environment, we'll check for the correct setup
-
- # First, check that the viewer page loads
- viewer_response = client.get('/file/test.epub')
- assert viewer_response.status_code == 200
-
- # Check that the JavaScript is correctly set up to load the EPUB
- assert b'/epub/test.epub' in viewer_response.data
-
- # Check that the EPUB file is accessible
- epub_response = client.get('/epub/test.epub')
- assert epub_response.status_code == 200
- assert epub_response.headers['Content-Type'] == 'application/epub+zip'
-
-if __name__ == '__main__':
+import os
+import pytest
+import tempfile
+import shutil
+from app import app
+from unittest.mock import patch, MagicMock
+from ebooklib import epub
+
+def create_test_epub():
+ """Create a simple test EPUB file"""
+ # Create a simple EPUB file
+ book = epub.EpubBook()
+
+ # Set metadata
+ book.set_identifier('test123456')
+ book.set_title('Test EPUB Book')
+ book.set_language('en')
+ book.add_author('Test Author')
+
+ # Add a chapter
+ c1 = epub.EpubHtml(title='Chapter 1', file_name='chap_01.xhtml', lang='en')
+ c1.content = '<html><body><h1>Chapter 1</h1><p>This is a test EPUB file.</p></body></html>'
+ book.add_item(c1)
+
+ # Add navigation
+ book.toc = [c1]
+ book.spine = ['nav', c1]
+ book.add_item(epub.EpubNcx())
+ book.add_item(epub.EpubNav())
+
+ # Create temp directory
+ temp_dir = tempfile.mkdtemp()
+ epub_path = os.path.join(temp_dir, 'test.epub')
+
+ # Write the EPUB file
+ epub.write_epub(epub_path, book)
+
+ return epub_path, temp_dir
+
+@pytest.fixture
+def client():
+ """Create a test client for the Flask app"""
+ app.config['TESTING'] = True
+ with app.test_client() as client:
+ yield client
+
+@pytest.fixture
+def test_epub():
+ """Create a test EPUB file and clean up after the test"""
+ epub_path, temp_dir = create_test_epub()
+
+ # Mock the books directory
+ original_join = os.path.join
+
+ def mock_join(path, *paths):
+ if path == "/books" and paths and paths[0] == "test.epub":
+ return epub_path
+ return original_join(path, *paths)
+
+ def mock_abspath(path):
+ if path == os.path.join("/books", "test.epub"):
+ return "/books/test.epub"
+ elif path == epub_path:
+ return "/books/test.epub"
+ return path
+
+ with patch('os.path.join', side_effect=mock_join):
+ with patch('os.path.isfile', return_value=True):
+ with patch('os.path.abspath', side_effect=mock_abspath):
+ yield epub_path
+
+ # Clean up
+ shutil.rmtree(temp_dir)
+
+def test_epub_viewer_page(client, test_epub):
+ """Test that the EPUB viewer page loads correctly"""
+ response = client.get('/file/test.epub')
+
+ assert response.status_code == 200
+ assert b'<!DOCTYPE html>' in response.data
+ assert b'<title>test.epub</title>' in response.data
+ assert b'<div id="viewer"></div>' in response.data
+ assert b'<script src="https://cdn.jsdelivr.net/npm/epubjs' in response.data
+
+def test_epub_file_endpoint(client, test_epub):
+ """Test that the EPUB file is served with correct headers"""
+ response = client.get('/epub/test.epub')
+
+ assert response.status_code == 200
+ assert response.headers['Content-Type'] == 'application/epub+zip'
+ assert response.headers['Access-Control-Allow-Origin'] == '*'
+
+ # Check that the response contains EPUB data (at least the magic number)
+ assert response.data.startswith(b'PK')
+
+def test_epub_viewer_integration(client, test_epub):
+ """Test the integration between the viewer and the EPUB file"""
+ # This test would ideally use Selenium or Playwright to test the actual rendering
+ # Since we can't run a browser in this environment, we'll check for the correct setup
+
+ # First, check that the viewer page loads
+ viewer_response = client.get('/file/test.epub')
+ assert viewer_response.status_code == 200
+
+ # Check that the JavaScript is correctly set up to load the EPUB
+ assert b'/epub/test.epub' in viewer_response.data
+
+ # Check that the EPUB file is accessible
+ epub_response = client.get('/epub/test.epub')
+ assert epub_response.status_code == 200
+ assert epub_response.headers['Content-Type'] == 'application/epub+zip'
+
+if __name__ == '__main__':
pytest.main(['-xvs', __file__])
\ No newline at end of file