AaronPo/the-biergarten-app
1
0
Fork 0
mirror of https://github.com/aaronpo97/the-biergarten-app.git synced 2026-07-16 17:47:22 +00:00
Code Issues Packages Projects Releases Wiki Activity

Pipeline: rename Location to City, wire postal code into breweries

Browse Source
This commit is contained in:
Aaron Po
2026-07-13 02:26:44 -04:00
parent fbcf438381
commit d52dba904c
48 changed files with 2261 additions and 1227 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
tooling/pipeline/includes/biergarten_pipeline.h
View File

@@ -64,6 +64,10 @@
#include "services/logging/log_producer.h"
#include "services/logging/logger.h"
// --- services: postal_code ---
#include "services/postal_code/mock_postal_code_service.h"
#include "services/postal_code/postal_code_service.h"
// --- services: prompting ---
#include "services/prompting/prompt_directory.h"

7
tooling/pipeline/includes/biergarten_pipeline_orchestrator.h
View File

@@ -16,7 +16,7 @@
#include "services/database/export_service.h"
#include "services/enrichment/enrichment_service.h"
#include "services/logging/logger.h"
#include "services/postal_code/postal_code_service.h"
/**
* @brief Main orchestrator for the Biergarten data generation pipeline.
*
@@ -34,6 +34,7 @@ class BiergartenPipelineOrchestrator {
* @param exporter Database backend for persisting generated records.
* @param curated_data_service Loads curated location, persona, and name
* data used to seed generation.
* @param postal_code_service
* @param application_options CLI configuration and paths.
*/
BiergartenPipelineOrchestrator(
@@ -42,6 +43,7 @@ class BiergartenPipelineOrchestrator {
std::unique_ptr<DataGenerator> generator,
std::unique_ptr<IExportService> exporter,
std::unique_ptr<ICuratedDataService> curated_data_service,
std::unique_ptr<IPostalCodeService> postal_code_service,
const ApplicationOptions& application_options);
/**
@@ -78,6 +80,7 @@ class BiergartenPipelineOrchestrator {
*/
std::unique_ptr<IExportService> exporter_;
std::unique_ptr<ICuratedDataService> curated_data_service_;
std::unique_ptr<IPostalCodeService> postal_code_service_;
ApplicationOptions application_options_;
@@ -87,7 +90,7 @@ class BiergartenPipelineOrchestrator {
* @return Vector of locations randomly sampled per
* PipelineOptions::location_count.
*/
std::vector<Location> QueryCitiesWithCountries();
std::vector<City> QueryCitiesWithCountries();
/**
* @brief Generate breweries for enriched cities.

2
tooling/pipeline/includes/data_generation/data_generator.h
View File

@@ -24,7 +24,7 @@ class DataGenerator {
* @param region_context Additional regional context text.
* @return Brewery generation result.
*/
virtual BreweryResult GenerateBrewery(const Location& location,
virtual BreweryResult GenerateBrewery(const City& location,
const std::string& region_context) = 0;
/**

2
tooling/pipeline/includes/data_generation/llama_generator.h
View File

@@ -55,7 +55,7 @@ class LlamaGenerator final : public DataGenerator {
* @param region_context Additional regional context.
* @return Generated brewery result.
*/
BreweryResult GenerateBrewery(const Location& location,
BreweryResult GenerateBrewery(const City& location,
const std::string& region_context) override;
/**

6
tooling/pipeline/includes/data_generation/mock_generator.h
View File

@@ -24,7 +24,7 @@ class MockGenerator final : public DataGenerator {
* @param region_context Unused for mock generation.
* @return Generated brewery result.
*/
BreweryResult GenerateBrewery(const Location& location,
BreweryResult GenerateBrewery(const City& location,
const std::string& region_context) override;
/**
@@ -46,7 +46,7 @@ class MockGenerator final : public DataGenerator {
* @param location City and country names.
* @return Deterministic hash value.
*/
static size_t DeterministicHash(const Location& location);
static size_t DeterministicHash(const City& location);
/**
* @brief Combines city, persona, and name into a stable hash value.
@@ -56,7 +56,7 @@ class MockGenerator final : public DataGenerator {
* @param name Sampled first/last name.
* @return Deterministic hash value.
*/
static size_t DeterministicHash(const Location& location,
static size_t DeterministicHash(const City& location,
const UserPersona& persona, const Name& name);
// Hash stride constants for deterministic distribution across fixed-size

18
tooling/pipeline/includes/data_model/generated_models.h
View File

@@ -87,15 +87,27 @@ struct UserResult {
* @brief Enriched city data with Wikipedia context.
*/
struct EnrichedCity {
Location location;
City location;
std::string region_context{};
};
/**
* @brief A brewery's street-level address, distinct from the shared `City`
* it belongs to. Mirrors the backend's `BreweryPostLocation` shape.
*
* Only `postal_code` is populated today -- street-address generation has no
* fixture data or service yet.
*/
struct Address {
std::string postal_code{};
};
/**
* @brief Helper struct to store generated brewery data.
*/
struct BreweryRecord {
Location location;
City location;
Address address;
BreweryResult brewery;
};
@@ -107,7 +119,7 @@ struct BreweryRecord {
* consumer can register real accounts from the pipeline's SQLite export.
*/
struct UserRecord {
Location location;
City location;
UserResult user;
std::string email{};
std::string date_of_birth{};

16
tooling/pipeline/includes/data_model/models.h
View File

@@ -22,13 +22,13 @@ class ILogger;
namespace prog_opts = boost::program_options;
// ============================================================================
// Location Models
// City Models
// ============================================================================
/**
* @brief Canonical location record for city-level generation.
*/
struct Location {
struct City {
std::string city{};
std::string state_province{};
@@ -44,6 +44,18 @@ struct Location {
*/
std::string iso3166_1{};
/**
* @brief A list of regular expressions used for valid postal codes in the
* region.
*
*/
std::vector<std::string> postal_regex{};
/**
* @brief Example postal codes for the region.
*/
std::vector<std::string> postal_code_examples{};
/**
* @brief Local language codes in priority order.
*/

4
tooling/pipeline/includes/services/curated_data/curated_data_service.h
View File

@@ -15,7 +15,7 @@
using ForenameList = std::vector<ForenameEntry>;
using SurnameList = std::vector<std::string>;
using LocationsList = std::vector<Location>;
using CityList = std::vector<City>;
using PersonasList = std::vector<UserPersona>;
using ForenamesByCountryMap = std::unordered_map<std::string, ForenameList>;
using SurnamesByCountryMap = std::unordered_map<std::string, SurnameList>;
@@ -37,7 +37,7 @@ class ICuratedDataService {
/**
* @brief Loads all curated location records.
*/
virtual const LocationsList& LoadLocations() = 0;
virtual const CityList& LoadCities() = 0;
/**
* @brief Loads all curated persona records.

8
tooling/pipeline/includes/services/curated_data/curated_json_data_service.h
View File

@@ -16,7 +16,7 @@
* CuratedJsonDataService.
*/
struct CuratedDataFilePaths {
std::filesystem::path locations_path;
std::filesystem::path cities_path;
std::filesystem::path personas_path;
std::filesystem::path forenames_path;
std::filesystem::path surnames_path;
@@ -27,7 +27,7 @@ struct CuratedDataFilePaths {
*/
class CuratedJsonDataService final : public ICuratedDataService {
struct cache {
LocationsList locations;
CityList locations;
PersonasList personas;
ForenamesByCountryMap forenames_by_country;
SurnamesByCountryMap surnames_by_country;
@@ -43,9 +43,9 @@ class CuratedJsonDataService final : public ICuratedDataService {
explicit CuratedJsonDataService(CuratedDataFilePaths filepaths);
/**
* @brief Parses a JSON array file and returns all location records.
* @brief Parses a JSON array file and returns all city records.
*/
const LocationsList& LoadLocations() override;
const CityList& LoadCities() override;
/**
* @brief Parses a JSON array file and returns all persona records.

4
tooling/pipeline/includes/services/curated_data/mock_curated_data_service.h
View File

@@ -20,7 +20,7 @@ class MockCuratedDataService final : public ICuratedDataService {
public:
MockCuratedDataService();
const LocationsList& LoadLocations() override;
const CityList& LoadCities() override;
const PersonasList& LoadPersonas() override;
@@ -29,7 +29,7 @@ class MockCuratedDataService final : public ICuratedDataService {
const SurnamesByCountryMap& LoadSurnamesByCountry() override;
private:
LocationsList locations_;
CityList locations_;
PersonasList personas_;
ForenamesByCountryMap forenames_by_country_;
SurnamesByCountryMap surnames_by_country_;

8
tooling/pipeline/includes/services/database/sqlite_export_service.h
View File

@@ -45,7 +45,7 @@ class SqliteExportService final : public IExportService {
void RollbackAndCloseNoThrow() noexcept;
[[nodiscard]] std::filesystem::path BuildDatabasePath() const;
[[nodiscard]] static std::string BuildLocationKey(const Location& location);
[[nodiscard]] static std::string BuildCityKey(const City& location);
/**
* @brief Returns the row id for @p location, inserting it first if it has
@@ -54,18 +54,18 @@ class SqliteExportService final : public IExportService {
* 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);
[[nodiscard]] sqlite3_int64 ResolveCityId(const City& location);
std::unique_ptr<IDateTimeProvider> date_time_provider_;
std::filesystem::path output_path_;
std::string run_timestamp_utc_;
std::filesystem::path database_path_;
SqliteDatabaseHandle db_handle_;
SqliteStatementHandle insert_location_stmt_;
SqliteStatementHandle insert_city_stmt_;
SqliteStatementHandle insert_brewery_stmt_;
SqliteStatementHandle insert_user_stmt_;
bool transaction_open_ = false;
std::unordered_map<std::string, sqlite3_int64> location_cache_;
std::unordered_map<std::string, sqlite3_int64> city_cache_;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_H_

53
tooling/pipeline/includes/services/database/sqlite_statement_helpers.h
View File

@@ -17,9 +17,9 @@
namespace sqlite_export_service_internal {
inline constexpr std::string_view kCreateLocationsTableSql = R"sql(
inline constexpr std::string_view kCreateCitiesTableSql = R"sql(
CREATE TABLE IF NOT EXISTS locations (
CREATE TABLE IF NOT EXISTS cities (
id INTEGER PRIMARY KEY AUTOINCREMENT,
city TEXT NOT NULL,
state_province TEXT NOT NULL,
@@ -38,15 +38,16 @@ inline constexpr std::string_view kCreateBreweriesTableSql = R"sql(
CREATE TABLE IF NOT EXISTS breweries (
id INTEGER PRIMARY KEY AUTOINCREMENT,
location_id INTEGER NOT NULL,
city_id INTEGER NOT NULL,
name_en TEXT NOT NULL,
description_en TEXT NOT NULL,
name_local TEXT NOT NULL,
description_local TEXT NOT NULL,
FOREIGN KEY(location_id) REFERENCES locations(id) ON DELETE CASCADE
postal_code TEXT NOT NULL,
FOREIGN KEY(city_id) REFERENCES cities(id) ON DELETE CASCADE
);
CREATE INDEX IF NOT EXISTS idx_breweries_location_id ON breweries(location_id);
CREATE INDEX IF NOT EXISTS idx_breweries_city_id ON breweries(city_id);
)sql";
@@ -54,7 +55,7 @@ inline constexpr std::string_view kCreateUsersTableSql = R"sql(
CREATE TABLE IF NOT EXISTS users (
id INTEGER PRIMARY KEY AUTOINCREMENT,
location_id INTEGER NOT NULL,
city_id INTEGER NOT NULL,
first_name TEXT NOT NULL,
last_name TEXT NOT NULL,
gender TEXT NOT NULL,
@@ -63,15 +64,15 @@ CREATE TABLE IF NOT EXISTS users (
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
FOREIGN KEY(city_id) REFERENCES cities(id) ON DELETE CASCADE
);
CREATE INDEX IF NOT EXISTS idx_users_location_id ON users(location_id);
CREATE INDEX IF NOT EXISTS idx_users_city_id ON users(city_id);
)sql";
inline constexpr std::string_view kInsertLocationSql = R"sql(
INSERT INTO locations (
inline constexpr std::string_view kInsertCitySql = R"sql(
INSERT INTO cities (
city,
state_province,
iso3166_2,
@@ -85,17 +86,18 @@ INSERT INTO locations (
inline constexpr std::string_view kInsertBrewerySql = R"sql(
INSERT INTO breweries (
location_id,
city_id,
name_en,
description_en,
name_local,
description_local
) VALUES (?, ?, ?, ?, ?);
description_local,
postal_code
) VALUES (?, ?, ?, ?, ?, ?);
)sql";
inline constexpr std::string_view kInsertUserSql = R"sql(
INSERT INTO users (
location_id,
city_id,
first_name,
last_name,
gender,
@@ -109,27 +111,28 @@ INSERT INTO users (
// 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 CityBindIndex {
kCityNameBindIndex = 1,
kCityStateProvinceBindIndex,
kCityIso31662BindIndex,
kCityCountryBindIndex,
kCityIso31661BindIndex,
kCityLanguagesBindIndex,
kCityLatitudeBindIndex,
kCityLongitudeBindIndex,
};
enum BreweryBindIndex {
kBreweryLocationIdBindIndex = 1,
kBreweryCityIdBindIndex = 1,
kBreweryEnglishNameBindIndex,
kBreweryEnglishDescriptionBindIndex,
kBreweryLocalNameBindIndex,
kBreweryLocalDescriptionBindIndex,
kBreweryPostalCodeBindIndex,
};
enum UserBindIndex {
kUserLocationIdBindIndex = 1,
kUserCityIdBindIndex = 1,
kUserFirstNameBindIndex,
kUserLastNameBindIndex,
kUserGenderBindIndex,

2
tooling/pipeline/includes/services/enrichment/enrichment_service.h
View File

@@ -23,7 +23,7 @@ class IEnrichmentService {
* @param loc Location to enrich.
* @return Context text, or an empty string if unavailable.
*/
virtual std::string GetLocationContext(const Location& loc) = 0;
virtual std::string GetLocationContext(const City& loc) = 0;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_ENRICHMENT_SERVICE_H_

2
tooling/pipeline/includes/services/enrichment/mock_enrichment.h
View File

@@ -15,7 +15,7 @@
*/
class MockEnrichmentService final : public IEnrichmentService {
public:
std::string GetLocationContext(const Location& /*loc*/) override {
std::string GetLocationContext(const City& /*loc*/) override {
return {};
}
};

2
tooling/pipeline/includes/services/enrichment/wikipedia_service.h
View File

@@ -29,7 +29,7 @@ class WikipediaEnrichmentService final : public IEnrichmentService {
/**
* @brief Returns the Wikipedia-derived context for a location.
*/
[[nodiscard]] std::string GetLocationContext(const Location& loc) override;
[[nodiscard]] std::string GetLocationContext(const City& loc) override;
private:
std::string FetchExtract(std::string_view query);

32
tooling/pipeline/includes/services/postal_code/mock_postal_code_service.h Normal file
View File

@@ -0,0 +1,32 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_MOCK_POSTAL_CODE_SERVICE_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_MOCK_POSTAL_CODE_SERVICE_H_
/**
* @file services/postal_code/mock_postal_code_service.h
* @brief Placeholder IPostalCodeService used until xeger-based generation is
* implemented.
*/
#include <stdexcept>
#include <string>
#include "data_model/models.h"
#include "services/postal_code/postal_code_service.h"
/**
* @brief Postal code service that returns the location's first known
* example postal code rather than generating one from its regex.
*/
class MockPostalCodeService final : public IPostalCodeService {
public:
std::string GeneratePostalCode(const City& location) override {
if (location.postal_code_examples.empty()) {
throw std::runtime_error(
"MockPostalCodeService: location has no postal_code_examples: " +
location.city);
}
return location.postal_code_examples.front();
}
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_MOCK_POSTAL_CODE_SERVICE_H_

30
tooling/pipeline/includes/services/postal_code/postal_code_service.h Normal file
View File

@@ -0,0 +1,30 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_POSTAL_CODE_SERVICE_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_POSTAL_CODE_SERVICE_H_
/**
* @file services/postal_code/postal_code_service.h
* @brief Abstraction for generating a postal code for a location.
*/
#include <string>
#include "data_model/models.h"
/**
* @brief Interface for services that generate a postal code string matching
* a location's postal code format (`City::postal_regex`).
*/
class IPostalCodeService {
public:
virtual ~IPostalCodeService() = default;
/**
* @brief Generates a postal code for the given location.
*
* @param location Location whose postal code format to generate for.
* @return A postal code string matching `location.postal_regex`.
*/
virtual std::string GeneratePostalCode(const City& location) = 0;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_POSTAL_CODE_SERVICE_H_