gutendex processing implementation

2026-03-29 15:23:02 +03:00
parent 7be6af781b
commit 93fef1512a
7 changed files with 542 additions and 0 deletions
@@ -0,0 +1,139 @@
+<?php
+
+return [
+
+    /*
+    |--------------------------------------------------------------------------
+    | Gutendex API Base URL
+    |--------------------------------------------------------------------------
+    |
+    | The base URL for the Gutendex API. This is the Project Gutenberg
+    | catalog API that provides metadata about public domain books.
+    |
+    */
+
+    'api_url' => env('GUTENDEX_API_URL', 'https://gutendex.com'),
+
+    /*
+    |--------------------------------------------------------------------------
+    | Default Language Filter
+    |--------------------------------------------------------------------------
+    |
+    | The default language code to use when fetching books from Gutendex.
+    | Common values: 'en' (English), 'fr' (French), 'de' (German), etc.
+    |
+    */
+
+    'default_language' => env('GUTENDEX_DEFAULT_LANGUAGE', 'en'),
+
+    /*
+    |--------------------------------------------------------------------------
+    | Batch Size
+    |--------------------------------------------------------------------------
+    |
+    | The number of books to process in a single batch import operation.
+    | Adjust based on your server capacity and Ollama processing speed.
+    |
+    */
+
+    'batch_size' => env('GUTENDEX_BATCH_SIZE', 50),
+
+    /*
+    |--------------------------------------------------------------------------
+    | Rate Limit Delay
+    |--------------------------------------------------------------------------
+    |
+    | Delay in milliseconds between API requests to respect rate limits.
+    | Increase if you encounter 429 (Too Many Requests) errors.
+    |
+    */
+
+    'rate_limit_delay' => env('GUTENDEX_RATE_LIMIT_DELAY', 1000),
+
+    /*
+    |--------------------------------------------------------------------------
+    | Request Timeout
+    |--------------------------------------------------------------------------
+    |
+    | Maximum time in seconds to wait for a response from the Gutendex API.
+    |
+    */
+
+    'timeout' => env('GUTENDEX_TIMEOUT', 30),
+
+    /*
+    |--------------------------------------------------------------------------
+    | Retry Configuration
+    |--------------------------------------------------------------------------
+    |
+    | Configuration for retrying failed API requests.
+    | - max_attempts: Maximum number of retry attempts
+    | - backoff_multiplier: Multiplier for exponential backoff (in seconds)
+    |
+    */
+
+    'retry' => [
+        'max_attempts' => env('GUTENDEX_RETRY_MAX_ATTEMPTS', 3),
+        'backoff_multiplier' => env('GUTENDEX_RETRY_BACKOFF', 2),
+    ],
+
+    /*
+    |--------------------------------------------------------------------------
+    | Copyright Filter
+    |--------------------------------------------------------------------------
+    |
+    | Filter books by copyright status. Setting to 'false' will only fetch
+    | public domain books. Setting to 'true' includes copyrighted works.
+    | It's recommended to keep this as 'false' for legal compliance.
+    |
+    */
+
+    'copyright' => env('GUTENDEX_COPYRIGHT_FILTER', 'false'),
+
+    /*
+    |--------------------------------------------------------------------------
+    | Cache Configuration
+    |--------------------------------------------------------------------------
+    |
+    | Enable caching of Gutendex API responses to reduce API calls.
+    | - enabled: Whether to cache responses
+    | - ttl: Time to live in seconds (default: 24 hours)
+    |
+    */
+
+    'cache' => [
+        'enabled' => env('GUTENDEX_CACHE_ENABLED', true),
+        'ttl' => env('GUTENDEX_CACHE_TTL', 86400),
+    ],
+
+    /*
+    |--------------------------------------------------------------------------
+    | Category Mapping
+    |--------------------------------------------------------------------------
+    |
+    | Map Gutendex subjects/bookshelves to your application's categories.
+    | This helps in auto-categorizing imported books.
+    |
+    */
+
+    'category_mapping' => [
+        'Fiction' => 'fiction',
+        'Science Fiction' => 'science-fiction',
+        'Fantasy' => 'fantasy',
+        'Mystery' => 'mystery',
+        'Romance' => 'romance',
+        'Historical Fiction' => 'historical-fiction',
+        'Biography' => 'biography',
+        'History' => 'history',
+        'Philosophy' => 'philosophy',
+        'Science' => 'science',
+        'Technology' => 'technology',
+        'Business' => 'business',
+        'Self-Help' => 'self-help',
+        'Poetry' => 'poetry',
+        'Drama' => 'drama',
+        'Children' => 'children',
+        // Add more mappings as needed
+    ],
+
+];