Refactor BiergartenDataGenerator to use dependency injection container

pipeline/includes/biergarten_data_generator.h

@@ -6,14 +6,14 @@
  * @brief Core orchestration class for pipeline data generation.
  */
 
+#include <cstdint>
 #include <memory>
 #include <string>
 #include <vector>
 
 #include "data_generation/data_generator.h"
 #include "data_model/location.h"
-#include "web_client/web_client.h"
-#include "wikipedia/wikipedia_service.h"
+#include "services/enrichment_service.h"
 
 /**
  * @brief Program options for the Biergarten pipeline application.
@@ -53,18 +53,18 @@ class BiergartenDataGenerator {
    /**
     * @brief Construct a BiergartenDataGenerator with injected dependencies.
     *
-    * @param options Application configuration options.
-    * @param web_client HTTP client for downloading data.
+    * @param context_service Context provider for sampled locations.
+    * @param generator Brewery and user data generator.
     */
-   BiergartenDataGenerator(const ApplicationOptions& options,
-                           std::shared_ptr<WebClient> web_client);
+   BiergartenDataGenerator(std::shared_ptr<IEnrichmentService> context_service,
+                           std::unique_ptr<DataGenerator> generator);
 
    /**
     * @brief Run the data generation pipeline.
     *
     * Performs the following steps:
     * 1. Load curated locations from JSON
-    * 2. Initialize the generator (LLM or Mock)
+    * 2. Resolve context for each city using the injected context service
     * 3. Generate brewery data for sampled cities
     *
     * @return true if successful, false if not
@@ -72,11 +72,11 @@ class BiergartenDataGenerator {
    bool Run();
 
   private:
-   /// @brief Immutable application options.
-   const ApplicationOptions options_;
+   /// @brief Shared context provider dependency.
+   std::shared_ptr<IEnrichmentService> context_service_;
 
-   /// @brief Shared HTTP client dependency.
-   std::shared_ptr<WebClient> webClient_;
+   /// @brief Generator dependency selected in the composition root.
+   std::unique_ptr<DataGenerator> generator_;
 
    /**
     * @brief Enriched city data with Wikipedia context.
@@ -86,15 +86,6 @@ class BiergartenDataGenerator {
       std::string region_context;
    };
 
-   /**
-    * @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<DataGenerator> InitializeGenerator() const;
-
    /**
     * @brief Load locations from JSON and sample cities.
     *
@@ -102,23 +93,12 @@ class BiergartenDataGenerator {
     */
    static std::vector<Location> QueryCitiesWithCountries();
 
-   /**
-    * @brief Enrich cities with Wikipedia summaries.
-    *
-    * @param cities Vector of sampled locations.
-    * @return Vector of enriched city data with context.
-    */
-   std::vector<EnrichedCity> EnrichWithWikipedia(
-       const std::vector<Location>& cities);
-
    /**
     * @brief Generate breweries for enriched cities.
     *
-    * @param generator The data generator instance.
     * @param cities Vector of enriched city data.
     */
-   void GenerateBreweries(DataGenerator& generator,
-                          const std::vector<EnrichedCity>& cities);
+   void GenerateBreweries(const std::vector<EnrichedCity>& cities);
 
    /**
     * @brief Log the generated brewery results.

pipeline/includes/data_generation/data_generator.h

@@ -38,13 +38,6 @@ class DataGenerator {
    /// @brief Virtual destructor for polymorphic cleanup.
    virtual ~DataGenerator() = default;
 
-   /**
-    * @brief Loads and initializes generator resources.
-    *
-    * @param model_path Path to model assets. Implementations may ignore this.
-    */
-   virtual void Load(const std::string& model_path) = 0;
-
    /**
     * @brief Generates brewery data for a location.
     *

pipeline/includes/data_generation/llama_generator.h

@@ -11,6 +11,8 @@
 
 #include "data_generation/data_generator.h"
 
+struct ApplicationOptions;
+
 struct llama_model;
 struct llama_context;
 
@@ -19,35 +21,19 @@ struct llama_context;
  */
 class LlamaGenerator final : public DataGenerator {
   public:
-   /// @brief Constructs a generator with default sampling and context settings.
-   LlamaGenerator() = default;
+   /**
+    * @brief Constructs a generator using parsed application options and loads
+    * the configured model immediately.
+    *
+    * @param options Parsed application options.
+    * @param model_path Filesystem path to GGUF model assets.
+    */
+   LlamaGenerator(const ApplicationOptions& options,
+                  const std::string& model_path);
 
    /// @brief Releases model/context resources.
    ~LlamaGenerator() override;
 
-   /**
-    * @brief Configures sampling parameters for generation.
-    *
-    * @param temperature Sampling temperature.
-    * @param top_p Nucleus sampling threshold.
-    * @param seed Seed for sampling; use -1 for random seed.
-    */
-   void SetSamplingOptions(float temperature, float top_p, int seed = -1);
-
-   /**
-    * @brief Sets context window size used during model load.
-    *
-    * @param n_ctx Context size in tokens.
-    */
-   void SetContextSize(uint32_t n_ctx);
-
-   /**
-    * @brief Loads model and prepares inference context.
-    *
-    * @param model_path Filesystem path to GGUF model.
-    */
-   void Load(const std::string& model_path) override;
-
    /**
     * @brief Generates brewery data for a specific location.
     *
@@ -69,6 +55,13 @@ class LlamaGenerator final : public DataGenerator {
    UserResult GenerateUser(const std::string& locale) override;
 
   private:
+   /**
+    * @brief Loads model and prepares inference context.
+    *
+    * @param model_path Filesystem path to GGUF model.
+    */
+   void Load(const std::string& model_path);
+
    /**
     * @brief Infers text from a user prompt.
     *

pipeline/includes/data_generation/mock_generator.h

@@ -16,13 +16,6 @@
  */
 class MockGenerator final : public DataGenerator {
   public:
-   /**
-    * @brief Initializes the mock generator.
-    *
-    * @param model_path Unused for mock generation.
-    */
-   void Load(const std::string& model_path) override;
-
    /**
     * @brief Generates deterministic brewery data for a location.
     *

pipeline/includes/services/enrichment_service.h

@@ -0,0 +1,30 @@
+#ifndef BIERGARTEN_PIPELINE_SERVICES_ENRICHMENT_SERVICE_H_
+#define BIERGARTEN_PIPELINE_SERVICES_ENRICHMENT_SERVICE_H_
+
+/**
+ * @file services/enrichment_service.h
+ * @brief Abstraction for resolving contextual enrichment for a location.
+ */
+
+#include <string>
+
+#include "data_model/location.h"
+
+/**
+ * @brief Interface for services that can enrich a location with context.
+ */
+class IEnrichmentService {
+  public:
+   /// @brief Virtual destructor for polymorphic cleanup.
+   virtual ~IEnrichmentService() = default;
+
+   /**
+    * @brief Resolves contextual enrichment for a location.
+    *
+    * @param loc Location to enrich.
+    * @return Context text, or an empty string if unavailable.
+    */
+   virtual std::string GetLocationContext(const Location& loc) = 0;
+};
+
+#endif  // BIERGARTEN_PIPELINE_SERVICES_ENRICHMENT_SERVICE_H_

pipeline/includes/services/wikipedia_service.h

@@ -2,7 +2,7 @@
 #define BIERGARTEN_PIPELINE_WIKIPEDIA_SERVICE_H_
 
 /**
- * @file wikipedia/wikipedia_service.h
+ * @file services/wikipedia_service.h
  * @brief Wikipedia summary retrieval service with in-memory caching.
  */
 
@@ -11,17 +11,17 @@
 #include <string_view>
 #include <unordered_map>
 
+#include "services/enrichment_service.h"
 #include "web_client/web_client.h"
 
 /// @brief Provides cached Wikipedia summary lookups for city and country pairs.
-class WikipediaService {
+class WikipediaService final : public IEnrichmentService {
   public:
    /// @brief Creates a new Wikipedia service with the provided web client.
    explicit WikipediaService(std::shared_ptr<WebClient> client);
 
-   /// @brief Returns the Wikipedia summary extract for city and country.
-   [[nodiscard]] std::string GetSummary(std::string_view city,
-                                        std::string_view country);
+   /// @brief Returns the Wikipedia-derived context for a location.
+   [[nodiscard]] std::string GetLocationContext(const Location& loc) override;
 
   private:
    std::string FetchExtract(std::string_view query) const;