Update user generation

tooling/pipeline/includes/biergarten_pipeline.h

@@ -0,0 +1,69 @@
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_H_
+
+/**
+ * @file biergarten_pipeline.h
+ * @brief Master umbrella header — includes every public header in the
+ * Biergarten pipeline.
+ */
+
+// --- orchestrator ---
+#include "biergarten_pipeline_orchestrator.h"
+
+// --- concurrency ---
+#include "concurrency/bounded_channel.h"
+
+// --- data_generation ---
+#include "data_generation/data_generator.h"
+#include "data_generation/json_grammars.h"
+#include "data_generation/llama_generator.h"
+#include "data_generation/llama_generator_helpers.h"
+#include "data_generation/mock_generator.h"
+#include "data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.h"
+#include "data_generation/prompt_formatting/prompt_formatter.h"
+
+// --- data_model ---
+#include "data_model/generated_models.h"
+#include "data_model/models.h"
+
+// --- json_handling ---
+#include "json_handling/json_loader.h"
+#include "json_handling/pretty_print.h"
+
+// --- llama backend ---
+#include "llama_backend_state.h"
+
+// --- services: curated_data ---
+#include "services/curated_data/curated_data_service.h"
+
+// --- services: database ---
+#include "services/database/export_service.h"
+#include "services/database/sqlite_connection_helpers.h"
+#include "services/database/sqlite_export_service.h"
+#include "services/database/sqlite_export_service_helpers.h"
+#include "services/database/sqlite_handle_types.h"
+#include "services/database/sqlite_statement_helpers.h"
+
+// --- services: datetime ---
+#include "services/datetime/date_time_provider.h"
+#include "services/datetime/timer.h"
+
+// --- services: enrichment ---
+#include "services/enrichment/enrichment_service.h"
+#include "services/enrichment/mock_enrichment.h"
+#include "services/enrichment/wikipedia_service.h"
+
+// --- services: logging ---
+#include "services/logging/log_dispatcher.h"
+#include "services/logging/log_entry.h"
+#include "services/logging/log_producer.h"
+#include "services/logging/logger.h"
+
+// --- services: prompting ---
+#include "services/prompting/prompt_directory.h"
+
+// --- web_client ---
+#include "web_client/http_web_client.h"
+#include "web_client/web_client.h"
+
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_H_

tooling/pipeline/includes/biergarten_pipeline_orchestrator.h

@@ -1,12 +1,9 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_H_
 
 /**
  * @file biergarten_pipeline_orchestrator.h
  * @brief Orchestration for end-to-end brewery and user data generation.
- *
- * Coordinates location loading, enrichment, and generation phases to produce
- * a complete dataset, wiring dependencies selected at the composition root.
  */
 
 #include <memory>
@@ -103,10 +100,6 @@ class BiergartenPipelineOrchestrator {
    * @brief Generate users grounded in sampled names and personas for
    * enriched cities.
    *
-   * Loads personas.json / forenames-by-country.json /
-   * surnames-by-country.json itself, mirroring how QueryCitiesWithCountries()
-   * owns its own locations.json load.
-   *
    * @param cities Span of enriched city data.
    */
   void GenerateUsers(std::span<const EnrichedCity> cities);
@@ -120,4 +113,4 @@ class BiergartenPipelineOrchestrator {
   std::vector<UserRecord> generated_users_;
 };
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_H_

tooling/pipeline/includes/concurrency/bounded_channel.tcc

@@ -1,4 +1,4 @@
-#include "bounded_channel.h"
+#include "concurrency/bounded_channel.h"
 
 template <typename T>
 void BoundedChannel<T>::Send(T item) {

tooling/pipeline/includes/data_generation/llama_generator.h

@@ -1,24 +1,23 @@
 #ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_H_
 #define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_H_
 
-#include <filesystem>
-
 /**
  * @file data_generation/llama_generator.h
  * @brief llama.cpp-backed implementation of DataGenerator.
  */
 
 #include <cstdint>
+#include <filesystem>
 #include <memory>
 #include <random>
 #include <string>
 #include <string_view>
 
-#include "../services/prompting/prompt_directory.h"
 #include "data_generation/data_generator.h"
 #include "data_generation/prompt_formatting/prompt_formatter.h"
 #include "data_model/models.h"
 #include "services/logging/logger.h"
+#include "services/prompting/prompt_directory.h"
 
 struct llama_model;
 struct llama_context;

tooling/pipeline/includes/data_model/models.h

@@ -10,6 +10,7 @@
 #include <boost/program_options.hpp>
 #include <cstdint>
 #include <filesystem>
+#include <functional>
 #include <memory>
 #include <optional>
 #include <string>
@@ -93,8 +94,23 @@ struct ForenameEntry {
    * dataset (e.g. "M", "F").
    */
   std::string gender{};
+
+  bool operator==(const ForenameEntry& other) const {
+    return name == other.name && gender == other.gender;
+  }
 };
 
+namespace std {
+template <>
+struct hash<ForenameEntry> {
+  size_t operator()(const ForenameEntry& entry) const noexcept {
+    const size_t name_hash = std::hash<std::string>{}(entry.name);
+    const size_t gender_hash = std::hash<std::string>{}(entry.gender);
+    return name_hash ^ (gender_hash << 1);
+  }
+};
+}  // namespace std
+
 /**
  * @brief A persona archetype used to ground LLM-generated user bios.
  */

tooling/pipeline/includes/data_model/names_by_country.h

@@ -1,51 +0,0 @@
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_NAMES_BY_COUNTRY_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_NAMES_BY_COUNTRY_H_
-
-/**
- * @file data_model/names_by_country.h
- * @brief Sampling over the names-by-country fixture data.
- */
-
-#include <optional>
-#include <random>
-#include <string>
-#include <unordered_map>
-#include <vector>
-
-#include "data_model/models.h"
-
-/**
- * @brief Samples locale-appropriate names from curated forename/surname
- * fixture data, keyed by ISO 3166-1 country code.
- *
- * Forenames and surnames are kept in separate maps (mirroring the source
- * dataset's own shape) so per-forename gender is preserved; pairing happens
- * at sample time rather than being precomputed, so no information from the
- * source dataset is discarded up front.
- */
-class NamesByCountry {
- public:
-  NamesByCountry(std::unordered_map<std::string, std::vector<ForenameEntry>>
-                     forenames_by_country,
-                 std::unordered_map<std::string, std::vector<std::string>>
-                     surnames_by_country);
-
-  /**
-   * @brief Samples a first/last name pair for the given country.
-   *
-   * @param iso3166_1 ISO 3166-1 country code to sample for.
-   * @param rng Random source used for sampling.
-   * @return A sampled Name, or std::nullopt if the country has no forename
-   * or no surname entries.
-   */
-  [[nodiscard]] std::optional<Name> SampleName(const std::string& iso3166_1,
-                                               std::mt19937& rng) const;
-
- private:
-  std::unordered_map<std::string, std::vector<ForenameEntry>>
-      forenames_by_country_;
-  std::unordered_map<std::string, std::vector<std::string>>
-      surnames_by_country_;
-};
-
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_NAMES_BY_COUNTRY_H_

tooling/pipeline/includes/json_handling/json_loader.h

@@ -7,41 +7,49 @@
  */
 
 #include <filesystem>
+#include <unordered_set>
 #include <vector>
 
 #include "data_model/models.h"
-#include "data_model/names_by_country.h"
 #include "services/curated_data/curated_data_service.h"
 
 /**
  * @brief Loads curated location, persona, and name data from JSON files.
  */
 class JsonLoader final : public ICuratedDataService {
+  struct cache {
+    std::vector<Location> locations;
+    std::vector<UserPersona> personas;
+    std::unordered_map<std::string, forename_list> forenames_by_country;
+    std::unordered_map<std::string, surname_list> surnames_by_country;
+
+    cache() = default;
+    ~cache() = default;
+  };
+
+  cache cache_;
+
  public:
   JsonLoader() = default;
 
   /**
    * @brief Parses a JSON array file and returns all location records.
    */
-  std::vector<Location> LoadLocations(
-      const std::filesystem::path& filepath) override;
+  std::vector<Location> LoadLocations(const std::filesystem::path&) override;
 
   /**
    * @brief Parses a JSON array file and returns all persona records.
    */
-  std::vector<UserPersona> LoadPersonas(
-      const std::filesystem::path& filepath) override;
+  std::vector<UserPersona> LoadPersonas(const std::filesystem::path&) override;
+
+  std::unordered_map<std::string, forename_list> LoadForenamesByCountry(
+      const std::filesystem::path&) override;
 
   /**
-   * @brief Parses the names-by-country fixture pair into a sampling-capable
-   * NamesByCountry.
-   *
-   * @param forenames_filepath Path to forenames-by-country.json.
-   * @param surnames_filepath Path to surnames-by-country.json.
+   * @brief Parses a JSON file and returns all the forenames per country.
    */
-  NamesByCountry LoadNamesByCountry(
-      const std::filesystem::path& forenames_filepath,
-      const std::filesystem::path& surnames_filepath) override;
+  std::unordered_map<std::string, surname_list> LoadSurnamesByCountry(
+      const std::filesystem::path&) override;
 };
 
 #endif  // BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_JSON_LOADER_H_

tooling/pipeline/includes/json_handling/pretty_print.h

@@ -106,4 +106,4 @@ inline void PrettyPrint(std::ostream& outstream,
   }
 }
 
-#endif
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_PRETTY_PRINT_H_

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

@@ -7,11 +7,13 @@
  */
 
 #include <filesystem>
+#include <unordered_set>
 #include <vector>
 
 #include "data_model/models.h"
-#include "data_model/names_by_country.h"
 
+using forename_list = std::unordered_set<ForenameEntry>;
+using surname_list = std::unordered_set<std::string>;
 /**
  * @brief Interface for services that load curated data used to seed
  * brewery/user generation.
@@ -38,16 +40,10 @@ class ICuratedDataService {
   virtual std::vector<UserPersona> LoadPersonas(
       const std::filesystem::path& filepath) = 0;
 
-  /**
-   * @brief Loads the names-by-country fixture pair into a sampling-capable
-   * NamesByCountry.
-   *
-   * @param forenames_filepath Path to forenames-by-country.json.
-   * @param surnames_filepath Path to surnames-by-country.json.
-   */
-  virtual NamesByCountry LoadNamesByCountry(
-      const std::filesystem::path& forenames_filepath,
+  virtual std::unordered_map<std::string, forename_list> LoadForenamesByCountry(
+      const std::filesystem::path& forenames_filepath) = 0;
+  virtual std::unordered_map<std::string, surname_list> LoadSurnamesByCountry(
       const std::filesystem::path& surnames_filepath) = 0;
 };
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_CURATED_DATA_CURATED_DATA_SERVICE_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_CURATED_DATA_CURATED_DATA_SERVICE_H_

tooling/pipeline/includes/services/database/sqlite_connection_helpers.h

@@ -12,7 +12,7 @@
 #include <string>
 #include <string_view>
 
-#include "sqlite_handle_types.h"
+#include "services/database/sqlite_handle_types.h"
 
 namespace sqlite_export_service_internal {
 

tooling/pipeline/includes/services/database/sqlite_export_service.h

@@ -11,10 +11,10 @@
 #include <string>
 #include <unordered_map>
 
-#include "../datetime/date_time_provider.h"
 #include "data_model/models.h"
-#include "export_service.h"
-#include "sqlite_export_service_helpers.h"
+#include "services/database/export_service.h"
+#include "services/database/sqlite_export_service_helpers.h"
+#include "services/datetime/date_time_provider.h"
 
 /**
  * @brief Persists generated brewery records into a fresh SQLite database.

tooling/pipeline/includes/services/database/sqlite_export_service_helpers.h

@@ -3,8 +3,8 @@
 
 /* Umbrella header for backward compatibility. */
 
-#include "sqlite_connection_helpers.h"
-#include "sqlite_handle_types.h"
-#include "sqlite_statement_helpers.h"
+#include "services/database/sqlite_connection_helpers.h"
+#include "services/database/sqlite_handle_types.h"
+#include "services/database/sqlite_statement_helpers.h"
 
 #endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_HELPERS_H_

tooling/pipeline/includes/services/database/sqlite_statement_helpers.h

@@ -13,7 +13,7 @@
 #include <string_view>
 #include <vector>
 
-#include "sqlite_handle_types.h"
+#include "services/database/sqlite_handle_types.h"
 
 namespace sqlite_export_service_internal {
 
@@ -109,30 +109,36 @@ INSERT INTO users (
 
 // sqlite3_bind_*() parameter indices are 1-based, matching the "?"
 // placeholder order in the SQL above.
-inline constexpr int kLocationCityBindIndex = 1;
-inline constexpr int kLocationStateProvinceBindIndex = 2;
-inline constexpr int kLocationIso31662BindIndex = 3;
-inline constexpr int kLocationCountryBindIndex = 4;
-inline constexpr int kLocationIso31661BindIndex = 5;
-inline constexpr int kLocationLanguagesBindIndex = 6;
-inline constexpr int kLocationLatitudeBindIndex = 7;
-inline constexpr int kLocationLongitudeBindIndex = 8;
+enum eLocationBindIndex {
+  kLocationCityBindIndex = 1,
+  kLocationStateProvinceBindIndex,
+  kLocationIso31662BindIndex,
+  kLocationCountryBindIndex,
+  kLocationIso31661BindIndex,
+  kLocationLanguagesBindIndex,
+  kLocationLatitudeBindIndex,
+  kLocationLongitudeBindIndex,
+};
 
-inline constexpr int kBreweryLocationIdBindIndex = 1;
-inline constexpr int kBreweryEnglishNameBindIndex = 2;
-inline constexpr int kBreweryEnglishDescriptionBindIndex = 3;
-inline constexpr int kBreweryLocalNameBindIndex = 4;
-inline constexpr int kBreweryLocalDescriptionBindIndex = 5;
+enum BreweryBindIndex {
+  kBreweryLocationIdBindIndex = 1,
+  kBreweryEnglishNameBindIndex,
+  kBreweryEnglishDescriptionBindIndex,
+  kBreweryLocalNameBindIndex,
+  kBreweryLocalDescriptionBindIndex,
+};
 
-inline constexpr int kUserLocationIdBindIndex = 1;
-inline constexpr int kUserFirstNameBindIndex = 2;
-inline constexpr int kUserLastNameBindIndex = 3;
-inline constexpr int kUserGenderBindIndex = 4;
-inline constexpr int kUserUsernameBindIndex = 5;
-inline constexpr int kUserBioBindIndex = 6;
-inline constexpr int kUserActivityWeightBindIndex = 7;
-inline constexpr int kUserEmailBindIndex = 8;
-inline constexpr int kUserDateOfBirthBindIndex = 9;
+enum UserBindIndex {
+  kUserLocationIdBindIndex = 1,
+  kUserFirstNameBindIndex,
+  kUserLastNameBindIndex,
+  kUserGenderBindIndex,
+  kUserUsernameBindIndex,
+  kUserBioBindIndex,
+  kUserActivityWeightBindIndex,
+  kUserEmailBindIndex,
+  kUserDateOfBirthBindIndex,
+};
 
 SqliteStatementHandle PrepareStatement(const SqliteDatabaseHandle& db_handle,
                                        std::string_view sql,

tooling/pipeline/includes/services/enrichment/mock_enrichment.h

@@ -8,7 +8,7 @@
 
 #include <string>
 
-#include "enrichment_service.h"
+#include "services/enrichment/enrichment_service.h"
 
 /**
  * @brief Enrichment service that returns no context for any location.

tooling/pipeline/includes/services/enrichment/wikipedia_service.h

@@ -11,7 +11,7 @@
 #include <string_view>
 #include <unordered_map>
 
-#include "enrichment_service.h"
+#include "services/enrichment/enrichment_service.h"
 #include "services/logging/logger.h"
 #include "web_client/web_client.h"
 

tooling/pipeline/includes/services/logging/log_producer.h

@@ -6,8 +6,8 @@
  * a bounded channel for later processing by the dispatcher.
  */
 
-#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_CHANNEL_LOGGER_H_
-#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_CHANNEL_LOGGER_H_
+#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_PRODUCER_H_
+#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_PRODUCER_H_
 
 #include <string_view>
 
@@ -50,4 +50,4 @@ class LogProducer final : public ILogger {
   BoundedChannel<LogEntry>& channel_;
 };
 
-#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_CHANNEL_LOGGER_H_
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_PRODUCER_H_

tooling/pipeline/includes/web_client/http_web_client.h

@@ -52,4 +52,4 @@ class HttpWebClient final : public WebClient {
   std::shared_ptr<ILogger> logger_;
 };
 
-#endif
+#endif  // BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_HTTP_WEB_CLIENT_H_