Reorganize directory structure

pipeline/includes/application_options.h

@@ -0,0 +1,2 @@
+#pragma once
+

pipeline/includes/biergarten_data_generator.h

@@ -0,0 +1,111 @@
+#pragma once
+
+#include <memory>
+#include <string>
+#include <vector>
+#include <unordered_map>
+
+#include "application_options.h"
+#include "data_generation/data_generator.h"
+#include "database/database.h"
+#include "web_client/web_client.h"
+#include "wikipedia/wikipedia_service.h"
+
+
+/**
+ * @brief Program options for the Biergarten pipeline application.
+ */
+struct ApplicationOptions {
+  /// @brief Path to the LLM model file (gguf format).
+  std::string modelPath;
+
+  /// @brief Directory for cached JSON and database files.
+  std::string cacheDir;
+
+  /// @brief LLM sampling temperature (0.0 to 1.0, higher = more random).
+  float temperature = 0.8f;
+
+  /// @brief LLM nucleus sampling top-p parameter (0.0 to 1.0, higher = more random).
+  float topP = 0.92f;
+
+  /// @brief Random seed for sampling (-1 for random, otherwise non-negative).
+  int seed = -1;
+
+  /// @brief Git commit hash for database consistency.
+  std::string commit = "c5eb7772";
+};
+
+
+/**
+ * @brief Main data generator class for the Biergarten pipeline.
+ *
+ * This class encapsulates the core logic for generating brewery data.
+ * It handles database initialization, data loading/downloading, and brewery generation.
+ */
+class BiergartenDataGenerator {
+public:
+  /**
+   * @brief Construct a BiergartenDataGenerator with injected dependencies.
+   *
+   * @param options Application configuration options.
+   * @param webClient HTTP client for downloading data.
+   * @param database SQLite database instance.
+   */
+  BiergartenDataGenerator(const ApplicationOptions &options,
+                          std::shared_ptr<IWebClient> webClient,
+                          SqliteDatabase &database);
+
+  /**
+   * @brief Run the data generation pipeline.
+   *
+   * Performs the following steps:
+   * 1. Initialize database
+   * 2. Download geographic data if needed
+   * 3. Initialize the generator (LLM or Mock)
+   * 4. Generate brewery data for sample cities
+   *
+   * @return 0 on success, 1 on failure.
+   */
+  int Run();
+
+private:
+  /// @brief Immutable application options.
+  const ApplicationOptions options_;
+
+  /// @brief Shared HTTP client dependency.
+  std::shared_ptr<IWebClient> webClient_;
+
+  /// @brief Database dependency.
+  SqliteDatabase &database_;
+
+  /**
+   * @brief Initialize the data generator based on options.
+   *
+   * Creates either a MockGenerator (if no model path) or LlamaGenerator.
+   *
+   * @return A unique_ptr to the initialized generator.
+   */
+  std::unique_ptr<IDataGenerator> InitializeGenerator();
+
+  /**
+   * @brief Download and load geographic data if not cached.
+   */
+  void LoadGeographicData();
+
+  /**
+   * @brief Generate sample breweries for demonstration.
+   */
+  void GenerateSampleBreweries();
+
+  /**
+   * @brief Helper struct to store generated brewery data.
+   */
+  struct GeneratedBrewery {
+    int cityId;
+    std::string cityName;
+    BreweryResult brewery;
+  };
+
+  /// @brief Stores generated brewery data.
+  std::vector<GeneratedBrewery> generatedBreweries_;
+};

pipeline/includes/data_generation/data_downloader.h

@@ -5,7 +5,7 @@
 #include <stdexcept>
 #include <string>
 
-#include "web_client.h"
+#include "web_client/web_client.h"
 
 /// @brief Downloads and caches source geography JSON payloads.
 class DataDownloader {

pipeline/includes/data_generation/llama_generator.h

@@ -3,7 +3,7 @@
 #include <cstdint>
 #include <string>
 
-#include "data_generator.h"
+#include "data_generation/data_generator.h"
 
 struct llama_model;
 struct llama_context;

pipeline/includes/data_generation/mock_generator.h

@@ -1,6 +1,6 @@
 #pragma once
 
-#include "data_generator.h"
+#include "data_generation/data_generator.h"
 #include <string>
 #include <vector>
 

pipeline/includes/json_handling/json_loader.h

@@ -1,7 +1,7 @@
 #pragma once
 
-#include "database.h"
-#include "stream_parser.h"
+#include "database/database.h"
+#include "json_handling/stream_parser.h"
 #include <string>
 
 /// @brief Loads world-city JSON data into SQLite through streaming parsing.

pipeline/includes/json_handling/stream_parser.h

@@ -1,6 +1,6 @@
 #pragma once
 
-#include "database.h"
+#include "database/database.h"
 #include <functional>
 #include <string>
 

pipeline/includes/web_client/curl_web_client.h

@@ -1,6 +1,6 @@
 #pragma once
 
-#include "web_client.h"
+#include "web_client/web_client.h"
 #include <memory>
 
 // RAII for curl_global_init/cleanup.

pipeline/includes/wikipedia/wikipedia_service.h

@@ -5,7 +5,7 @@
 #include <string_view>
 #include <unordered_map>
 
-#include "web_client.h"
+#include "web_client/web_client.h"
 
 /// @brief Provides cached Wikipedia summary lookups for city and country pairs.
 class WikipediaService {