Persist generated users to SQLite and code cleanup

tooling/pipeline/includes/data_generation/mock_generator.h

@@ -33,7 +33,7 @@ class MockGenerator final : public DataGenerator {
    *
    * @param city Enriched city the user is associated with.
    * @param persona Persona archetype.
-   * @param name Sampled first/last name. Unused for mock generation.
+   * @param name Sampled first/last name, copied directly into the result.
    * @return Generated user result.
    */
   UserResult GenerateUser(const EnrichedCity& city, const UserPersona& persona,

tooling/pipeline/includes/data_model/models.h

@@ -119,7 +119,7 @@ struct UserPersona {
  * @brief LLM sampling parameters.
  */
 struct SamplingOptions {
-  /// @brief LLM sampling temperature (0.0 to 1.0, higher = more random).
+  /// @brief LLM sampling temperature (higher = more random).
   float temperature = 1.0F;
 
   /// @brief LLM nucleus sampling top-p parameter.

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

@@ -35,6 +35,13 @@ class IExportService {
    */
   virtual uint64_t ProcessRecord(const GeneratedBrewery& brewery) = 0;
 
+  /**
+   * @brief Persists one generated user record.
+   *
+   * @param user Generated user payload to store.
+   */
+  virtual uint64_t ProcessRecord(const GeneratedUser& user) = 0;
+
   /// @brief Finalizes the export destination.
   virtual void Finalize() = 0;
 };

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

@@ -31,6 +31,7 @@ class SqliteExportService final : public IExportService {
 
   void Initialize() override;
   uint64_t ProcessRecord(const GeneratedBrewery& brewery) override;
+  uint64_t ProcessRecord(const GeneratedUser& user) override;
   void Finalize() override;
 
  private:
@@ -46,6 +47,15 @@ class SqliteExportService final : public IExportService {
   [[nodiscard]] std::filesystem::path BuildDatabasePath() const;
   [[nodiscard]] static std::string BuildLocationKey(const Location& location);
 
+  /**
+   * @brief Returns the row id for @p location, inserting it first if it has
+   * not already been seen during this run.
+   *
+   * Shared by both ProcessRecord() overloads so breweries and users
+   * referencing the same location resolve to the same row.
+   */
+  [[nodiscard]] sqlite3_int64 ResolveLocationId(const Location& location);
+
   std::unique_ptr<IDateTimeProvider> date_time_provider_;
   std::filesystem::path output_path_;
   std::string run_timestamp_utc_;
@@ -53,6 +63,7 @@ class SqliteExportService final : public IExportService {
   SqliteDatabaseHandle db_handle_;
   SqliteStatementHandle insert_location_stmt_;
   SqliteStatementHandle insert_brewery_stmt_;
+  SqliteStatementHandle insert_user_stmt_;
   bool transaction_open_ = false;
   std::unordered_map<std::string, sqlite3_int64> location_cache_;
 };

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

@@ -50,6 +50,27 @@ CREATE INDEX IF NOT EXISTS idx_breweries_location_id ON breweries(location_id);
 
 )sql";
 
+inline constexpr std::string_view kCreateUsersTableSql = R"sql(
+
+CREATE TABLE IF NOT EXISTS users (
+  id INTEGER PRIMARY KEY AUTOINCREMENT,
+  location_id INTEGER NOT NULL,
+  first_name TEXT NOT NULL,
+  last_name TEXT NOT NULL,
+  gender TEXT NOT NULL,
+  username TEXT NOT NULL,
+  bio TEXT NOT NULL,
+  activity_weight REAL NOT NULL,
+  email TEXT NOT NULL UNIQUE,
+  date_of_birth TEXT NOT NULL,
+  password TEXT NOT NULL,
+  FOREIGN KEY(location_id) REFERENCES locations(id) ON DELETE CASCADE
+);
+
+CREATE INDEX IF NOT EXISTS idx_users_location_id ON users(location_id);
+
+)sql";
+
 inline constexpr std::string_view kInsertLocationSql = R"sql(
 INSERT INTO locations (
   city,
@@ -73,6 +94,21 @@ INSERT INTO breweries (
 ) VALUES (?, ?, ?, ?, ?);
 )sql";
 
+inline constexpr std::string_view kInsertUserSql = R"sql(
+INSERT INTO users (
+  location_id,
+  first_name,
+  last_name,
+  gender,
+  username,
+  bio,
+  activity_weight,
+  email,
+  date_of_birth,
+  password
+) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?);
+)sql";
+
 inline constexpr int kLocationCityBindIndex = 1;
 inline constexpr int kLocationStateProvinceBindIndex = 2;
 inline constexpr int kLocationIso31662BindIndex = 3;
@@ -88,6 +124,17 @@ inline constexpr int kBreweryEnglishDescriptionBindIndex = 3;
 inline constexpr int kBreweryLocalNameBindIndex = 4;
 inline constexpr int kBreweryLocalDescriptionBindIndex = 5;
 
+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;
+inline constexpr int kUserPasswordBindIndex = 10;
+
 SqliteStatementHandle PrepareStatement(const SqliteDatabaseHandle& db_handle,
                                        std::string_view sql,
                                        const char* action);

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

@@ -35,6 +35,7 @@ enum class LogLevel {
  */
 enum class PipelinePhase {
   Startup,                   ///< Initialization and validation.
+  Enrichment,                ///< Location/context enrichment (e.g. Wikipedia lookups).
   UserGeneration,            ///< User profile generation.
   BreweryAndBeerGeneration,  ///< Brewery and beer data generation.
   CheckinGeneration,         ///< Checkin (visit) record generation.