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

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

@@ -16,8 +16,6 @@
 class IExportService {
  public:
   IExportService() = default;
-
-  /// @brief Virtual destructor for polymorphic cleanup.
   virtual ~IExportService() = default;
 
   IExportService(const IExportService&) = delete;
@@ -25,7 +23,9 @@ class IExportService {
   IExportService(IExportService&&) = delete;
   IExportService& operator=(IExportService&&) = delete;
 
-  /// @brief Prepares the export destination for a new run.
+  /**
+   * @brief Prepares the export destination for a new run.
+   */
   virtual void Initialize() = 0;
 
   /**
@@ -33,9 +33,18 @@ class IExportService {
    *
    * @param brewery Generated brewery payload to store.
    */
-  virtual uint64_t ProcessRecord(const GeneratedBrewery& brewery) = 0;
+  virtual uint64_t ProcessRecord(const BreweryRecord& brewery) = 0;
 
-  /// @brief Finalizes the export destination.
+  /**
+   * @brief Persists one generated user record.
+   *
+   * @param user Generated user payload to store.
+   */
+  virtual uint64_t ProcessRecord(const UserRecord& user) = 0;
+
+  /**
+   * @brief Finalizes the export destination.
+   */
   virtual void Finalize() = 0;
 };
 

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

@@ -12,9 +12,9 @@
 #include <unordered_map>
 
 #include "data_model/models.h"
-#include "../datetime/date_time_provider.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.
@@ -30,7 +30,8 @@ class SqliteExportService final : public IExportService {
   SqliteExportService& operator=(SqliteExportService&&) = delete;
 
   void Initialize() override;
-  uint64_t ProcessRecord(const GeneratedBrewery& brewery) override;
+  uint64_t ProcessRecord(const BreweryRecord& brewery) override;
+  uint64_t ProcessRecord(const UserRecord& 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_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_handle_types.h

@@ -24,8 +24,10 @@ using SqliteDatabaseHandle = std::unique_ptr<sqlite3, SqliteDatabaseDeleter>;
 using SqliteStatementHandle =
     std::unique_ptr<sqlite3_stmt, SqliteStatementDeleter>;
 
+// Represents a parameter that is bound to a prepared SQLite statement.
+// N.B. indices are 1 based.
 template <typename T>
-struct BindParam {
+struct BoundParam {
   int index;
   T value;
   std::string_view action;

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 {
 
@@ -50,6 +50,26 @@ 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,
+  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,
@@ -73,20 +93,52 @@ INSERT INTO breweries (
 ) VALUES (?, ?, ?, ?, ?);
 )sql";
 
-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;
+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
+) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?);
+)sql";
 
-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;
+// sqlite3_bind_*() parameter indices are 1-based, matching the "?"
+// placeholder order in the SQL above.
+enum LocationBindIndex {
+  kLocationCityBindIndex = 1,
+  kLocationStateProvinceBindIndex,
+  kLocationIso31662BindIndex,
+  kLocationCountryBindIndex,
+  kLocationIso31661BindIndex,
+  kLocationLanguagesBindIndex,
+  kLocationLatitudeBindIndex,
+  kLocationLongitudeBindIndex,
+};
+
+enum BreweryBindIndex {
+  kBreweryLocationIdBindIndex = 1,
+  kBreweryEnglishNameBindIndex,
+  kBreweryEnglishDescriptionBindIndex,
+  kBreweryLocalNameBindIndex,
+  kBreweryLocalDescriptionBindIndex,
+};
+
+enum UserBindIndex {
+  kUserLocationIdBindIndex = 1,
+  kUserFirstNameBindIndex,
+  kUserLastNameBindIndex,
+  kUserGenderBindIndex,
+  kUserUsernameBindIndex,
+  kUserBioBindIndex,
+  kUserActivityWeightBindIndex,
+  kUserEmailBindIndex,
+  kUserDateOfBirthBindIndex,
+};
 
 SqliteStatementHandle PrepareStatement(const SqliteDatabaseHandle& db_handle,
                                        std::string_view sql,
@@ -95,13 +147,13 @@ SqliteStatementHandle PrepareStatement(const SqliteDatabaseHandle& db_handle,
 void ResetStatement(SqliteStatementHandle& statement);
 
 void Bind(const SqliteStatementHandle& statement,
-          const BindParam<std::string_view>& param);
+          const BoundParam<std::string_view>& param);
 
 void Bind(const SqliteStatementHandle& statement,
-          const BindParam<double>& param);
+          const BoundParam<double>& param);
 
 void Bind(const SqliteStatementHandle& statement,
-          const BindParam<sqlite3_int64>& param);
+          const BoundParam<sqlite3_int64>& param);
 
 void StepStatement(const SqliteDatabaseHandle& db_handle,
                    const SqliteStatementHandle& statement,