Pipeline: Add LLM and mocked user generation to the pipeline (#230)

tooling/pipeline/includes/services/curated_data/curated_data_service.h

@@ -0,0 +1,50 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_CURATED_DATA_CURATED_DATA_SERVICE_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_CURATED_DATA_CURATED_DATA_SERVICE_H_
+
+/**
+ * @file services/curated_data/curated_data_service.h
+ * @brief Abstraction for loading curated location, persona, and name data.
+ */
+
+#include <filesystem>
+#include <unordered_map>
+#include <unordered_set>
+#include <vector>
+
+#include "data_model/models.h"
+
+using ForenameList = std::vector<ForenameEntry>;
+using SurnameList = std::vector<std::string>;
+using LocationsList = std::vector<Location>;
+using PersonasList = std::vector<UserPersona>;
+using ForenamesByCountryMap = std::unordered_map<std::string, ForenameList>;
+using SurnamesByCountryMap = std::unordered_map<std::string, SurnameList>;
+
+/**
+ * @brief Interface for services that load curated data used to seed
+ * brewery/user generation.
+ */
+class ICuratedDataService {
+ public:
+  ICuratedDataService() = default;
+  virtual ~ICuratedDataService() = default;
+
+  ICuratedDataService(const ICuratedDataService&) = delete;
+  ICuratedDataService& operator=(const ICuratedDataService&) = delete;
+  ICuratedDataService(ICuratedDataService&&) = delete;
+  ICuratedDataService& operator=(ICuratedDataService&&) = delete;
+
+  /**
+   * @brief Loads all curated location records.
+   */
+  virtual const LocationsList& LoadLocations() = 0;
+
+  /**
+   * @brief Loads all curated persona records.
+   */
+  virtual const PersonasList& LoadPersonas() = 0;
+  virtual const ForenamesByCountryMap& LoadForenamesByCountry() = 0;
+  virtual const SurnamesByCountryMap& LoadSurnamesByCountry() = 0;
+};
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_CURATED_DATA_CURATED_DATA_SERVICE_H_

tooling/pipeline/includes/services/curated_data/curated_json_data_service.h

@@ -0,0 +1,63 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_JSON_LOADER_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_JSON_LOADER_H_
+
+/**
+ * @file json_handling/json_loader.h
+ * @brief JSON-backed implementation of ICuratedDataService.
+ */
+
+#include <filesystem>
+
+#include "data_model/models.h"
+#include "services/curated_data/curated_data_service.h"
+
+/**
+ * @brief File locations for the curated JSON fixtures consumed by
+ * CuratedJsonDataService.
+ */
+struct CuratedDataFilePaths {
+  std::filesystem::path locations_path;
+  std::filesystem::path personas_path;
+  std::filesystem::path forenames_path;
+  std::filesystem::path surnames_path;
+};
+
+/**
+ * @brief Loads curated location, persona, and name data from JSON files.
+ */
+class CuratedJsonDataService final : public ICuratedDataService {
+  struct cache {
+    LocationsList locations;
+    PersonasList personas;
+    ForenamesByCountryMap forenames_by_country;
+    SurnamesByCountryMap surnames_by_country;
+
+    cache() = default;
+    ~cache() = default;
+  };
+
+  CuratedDataFilePaths filepaths_;
+  cache cache_;
+
+ public:
+  explicit CuratedJsonDataService(CuratedDataFilePaths filepaths);
+
+  /**
+   * @brief Parses a JSON array file and returns all location records.
+   */
+  const LocationsList& LoadLocations() override;
+
+  /**
+   * @brief Parses a JSON array file and returns all persona records.
+   */
+  const PersonasList& LoadPersonas() override;
+
+  const ForenamesByCountryMap& LoadForenamesByCountry() override;
+
+  /**
+   * @brief Parses a JSON file and returns all the forenames per country.
+   */
+  const SurnamesByCountryMap& LoadSurnamesByCountry() override;
+};
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_JSON_LOADER_H_

tooling/pipeline/includes/services/curated_data/mock_curated_data_service.h

@@ -0,0 +1,38 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_CURATED_DATA_MOCK_CURATED_DATA_SERVICE_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_CURATED_DATA_MOCK_CURATED_DATA_SERVICE_H_
+
+/**
+ * @file services/curated_data/mock_curated_data_service.h
+ * @brief In-memory ICuratedDataService backed by a small fixed dataset, used
+ * when file-backed curated data is disabled (mock mode).
+ */
+
+#include <filesystem>
+
+#include "data_model/models.h"
+#include "services/curated_data/curated_data_service.h"
+
+/**
+ * @brief Curated data service returning a small fixed in-memory dataset in
+ * place of the JSON fixture files used by JsonLoader.
+ */
+class MockCuratedDataService final : public ICuratedDataService {
+ public:
+  MockCuratedDataService();
+
+  const LocationsList& LoadLocations() override;
+
+  const PersonasList& LoadPersonas() override;
+
+  const ForenamesByCountryMap& LoadForenamesByCountry() override;
+
+  const SurnamesByCountryMap& LoadSurnamesByCountry() override;
+
+ private:
+  LocationsList locations_;
+  PersonasList personas_;
+  ForenamesByCountryMap forenames_by_country_;
+  SurnamesByCountryMap surnames_by_country_;
+};
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_CURATED_DATA_MOCK_CURATED_DATA_SERVICE_H_