Formatting

This commit is contained in:
Aaron Po
2026-07-19 04:05:30 -04:00
parent 8e7ecf2fc3
commit ec770aa724
78 changed files with 13388 additions and 32143 deletions

View File

@@ -25,26 +25,26 @@ using SurnamesByCountryMap = std::unordered_map<std::string, SurnameList>;
* brewery/user generation.
*/
class ICuratedDataService {
public:
ICuratedDataService() = default;
virtual ~ICuratedDataService() = default;
public:
ICuratedDataService() = default;
virtual ~ICuratedDataService() = default;
ICuratedDataService(const ICuratedDataService&) = delete;
ICuratedDataService& operator=(const ICuratedDataService&) = delete;
ICuratedDataService(ICuratedDataService&&) = delete;
ICuratedDataService& operator=(ICuratedDataService&&) = delete;
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 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;
/**
* @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_

View File

@@ -16,48 +16,48 @@
* CuratedJsonDataService.
*/
struct CuratedDataFilePaths {
std::filesystem::path locations_path;
std::filesystem::path personas_path;
std::filesystem::path forenames_path;
std::filesystem::path surnames_path;
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;
struct cache {
LocationsList locations;
PersonasList personas;
ForenamesByCountryMap forenames_by_country;
SurnamesByCountryMap surnames_by_country;
cache() = default;
~cache() = default;
};
cache() = default;
~cache() = default;
};
CuratedDataFilePaths filepaths_;
cache cache_;
CuratedDataFilePaths filepaths_;
cache cache_;
public:
explicit CuratedJsonDataService(CuratedDataFilePaths filepaths);
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 location records.
*/
const LocationsList& LoadLocations() override;
/**
* @brief Parses a JSON array file and returns all persona records.
*/
const PersonasList& LoadPersonas() override;
/**
* @brief Parses a JSON array file and returns all persona records.
*/
const PersonasList& LoadPersonas() override;
const ForenamesByCountryMap& LoadForenamesByCountry() override;
const ForenamesByCountryMap& LoadForenamesByCountry() override;
/**
* @brief Parses a JSON file and returns all the forenames per country.
*/
const SurnamesByCountryMap& LoadSurnamesByCountry() 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_

View File

@@ -17,22 +17,22 @@
* place of the JSON fixture files used by JsonLoader.
*/
class MockCuratedDataService final : public ICuratedDataService {
public:
MockCuratedDataService();
public:
MockCuratedDataService();
const LocationsList& LoadLocations() override;
const LocationsList& LoadLocations() override;
const PersonasList& LoadPersonas() override;
const PersonasList& LoadPersonas() override;
const ForenamesByCountryMap& LoadForenamesByCountry() override;
const ForenamesByCountryMap& LoadForenamesByCountry() override;
const SurnamesByCountryMap& LoadSurnamesByCountry() override;
const SurnamesByCountryMap& LoadSurnamesByCountry() override;
private:
LocationsList locations_;
PersonasList personas_;
ForenamesByCountryMap forenames_by_country_;
SurnamesByCountryMap surnames_by_country_;
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_

View File

@@ -14,38 +14,38 @@
* @brief Interface for services that persist generated brewery records.
*/
class IExportService {
public:
IExportService() = default;
virtual ~IExportService() = default;
public:
IExportService() = default;
virtual ~IExportService() = default;
IExportService(const IExportService&) = delete;
IExportService& operator=(const IExportService&) = delete;
IExportService(IExportService&&) = delete;
IExportService& operator=(IExportService&&) = delete;
IExportService(const IExportService&) = delete;
IExportService& operator=(const IExportService&) = delete;
IExportService(IExportService&&) = delete;
IExportService& operator=(IExportService&&) = delete;
/**
* @brief Prepares the export destination for a new run.
*/
virtual void Initialize() = 0;
/**
* @brief Prepares the export destination for a new run.
*/
virtual void Initialize() = 0;
/**
* @brief Persists one generated brewery record.
*
* @param brewery Generated brewery payload to store.
*/
virtual uint64_t ProcessRecord(const BreweryRecord& brewery) = 0;
/**
* @brief Persists one generated brewery record.
*
* @param brewery Generated brewery payload to store.
*/
virtual uint64_t ProcessRecord(const BreweryRecord& brewery) = 0;
/**
* @brief Persists one generated user record.
*
* @param user Generated user payload to store.
*/
virtual uint64_t ProcessRecord(const UserRecord& user) = 0;
/**
* @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;
/**
* @brief Finalizes the export destination.
*/
virtual void Finalize() = 0;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_EXPORT_SERVICE_H_

View File

@@ -20,54 +20,54 @@
* @brief Persists generated brewery records into a fresh SQLite database.
*/
class SqliteExportService final : public IExportService {
public:
explicit SqliteExportService(const ApplicationOptions& options);
~SqliteExportService() override;
public:
explicit SqliteExportService(const ApplicationOptions& options);
~SqliteExportService() override;
SqliteExportService(const SqliteExportService&) = delete;
SqliteExportService& operator=(const SqliteExportService&) = delete;
SqliteExportService(SqliteExportService&&) = delete;
SqliteExportService& operator=(SqliteExportService&&) = delete;
SqliteExportService(const SqliteExportService&) = delete;
SqliteExportService& operator=(const SqliteExportService&) = delete;
SqliteExportService(SqliteExportService&&) = delete;
SqliteExportService& operator=(SqliteExportService&&) = delete;
void Initialize() override;
uint64_t ProcessRecord(const BreweryRecord& brewery) override;
uint64_t ProcessRecord(const UserRecord& user) override;
void Finalize() override;
void Initialize() override;
uint64_t ProcessRecord(const BreweryRecord& brewery) override;
uint64_t ProcessRecord(const UserRecord& user) override;
void Finalize() override;
private:
using SqliteDatabaseHandle =
sqlite_export_service_internal::SqliteDatabaseHandle;
using SqliteStatementHandle =
sqlite_export_service_internal::SqliteStatementHandle;
private:
using SqliteDatabaseHandle =
sqlite_export_service_internal::SqliteDatabaseHandle;
using SqliteStatementHandle =
sqlite_export_service_internal::SqliteStatementHandle;
void InitializeSchema() const;
void PrepareStatements();
void RollbackAndCloseNoThrow() noexcept;
void InitializeSchema() const;
void PrepareStatements();
void RollbackAndCloseNoThrow() noexcept;
[[nodiscard]] std::filesystem::path BuildDatabasePath() const;
[[nodiscard]] static std::string BuildCityKey(const City& city);
[[nodiscard]] std::filesystem::path BuildDatabasePath() const;
[[nodiscard]] static std::string BuildCityKey(const City& city);
/**
* @brief Returns the row id for @p city, inserting it first if it has
* not already been seen during this run.
*
* Shared by both ProcessRecord() overloads so brewery and user addresses
* referencing the same city resolve to the same row.
*/
[[nodiscard]] sqlite3_int64 ResolveCityId(const City& city);
/**
* @brief Returns the row id for @p city, inserting it first if it has
* not already been seen during this run.
*
* Shared by both ProcessRecord() overloads so brewery and user addresses
* referencing the same city resolve to the same row.
*/
[[nodiscard]] sqlite3_int64 ResolveCityId(const City& city);
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_city_stmt_;
SqliteStatementHandle insert_brewery_stmt_;
SqliteStatementHandle insert_brewery_address_stmt_;
SqliteStatementHandle insert_user_stmt_;
SqliteStatementHandle insert_user_address_stmt_;
bool transaction_open_ = false;
std::unordered_map<std::string, sqlite3_int64> city_cache_;
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_city_stmt_;
SqliteStatementHandle insert_brewery_stmt_;
SqliteStatementHandle insert_brewery_address_stmt_;
SqliteStatementHandle insert_user_stmt_;
SqliteStatementHandle insert_user_address_stmt_;
bool transaction_open_ = false;
std::unordered_map<std::string, sqlite3_int64> city_cache_;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_H_

View File

@@ -13,11 +13,11 @@
namespace sqlite_export_service_internal {
struct SqliteDatabaseDeleter {
void operator()(sqlite3* handle) const noexcept;
void operator()(sqlite3* handle) const noexcept;
};
struct SqliteStatementDeleter {
void operator()(sqlite3_stmt* statement) const noexcept;
void operator()(sqlite3_stmt* statement) const noexcept;
};
using SqliteDatabaseHandle = std::unique_ptr<sqlite3, SqliteDatabaseDeleter>;
@@ -28,9 +28,9 @@ using SqliteStatementHandle =
// N.B. indices are 1 based.
template <typename T>
struct BoundParam {
int index;
T value;
std::string_view action;
int index;
T value;
std::string_view action;
};
} // namespace sqlite_export_service_internal

View File

@@ -152,44 +152,44 @@ INSERT INTO user_addresses (
// sqlite3_bind_*() parameter indices are 1-based, matching the "?"
// placeholder order in the SQL above.
enum CityBindIndex {
kCityCityBindIndex = 1,
kCityStateProvinceBindIndex,
kCityIso31662BindIndex,
kCityCountryBindIndex,
kCityIso31661BindIndex,
kCityLanguagesBindIndex,
kCityPostalCodeCountryFormatRegexBindIndex,
kCityPostalCodeCityRegexJsonBindIndex,
kCityCityBindIndex = 1,
kCityStateProvinceBindIndex,
kCityIso31662BindIndex,
kCityCountryBindIndex,
kCityIso31661BindIndex,
kCityLanguagesBindIndex,
kCityPostalCodeCountryFormatRegexBindIndex,
kCityPostalCodeCityRegexJsonBindIndex,
};
enum BreweryBindIndex {
kBreweryEnglishNameBindIndex = 1,
kBreweryEnglishDescriptionBindIndex,
kBreweryLocalNameBindIndex,
kBreweryLocalDescriptionBindIndex,
kBreweryEnglishNameBindIndex = 1,
kBreweryEnglishDescriptionBindIndex,
kBreweryLocalNameBindIndex,
kBreweryLocalDescriptionBindIndex,
};
enum BreweryAddressBindIndex {
kBreweryAddressBreweryIdBindIndex = 1,
kBreweryAddressCityIdBindIndex,
kBreweryAddressPostalCodeBindIndex,
kBreweryAddressBreweryIdBindIndex = 1,
kBreweryAddressCityIdBindIndex,
kBreweryAddressPostalCodeBindIndex,
};
enum UserBindIndex {
kUserFirstNameBindIndex = 1,
kUserLastNameBindIndex,
kUserGenderBindIndex,
kUserUsernameBindIndex,
kUserBioBindIndex,
kUserActivityWeightBindIndex,
kUserEmailBindIndex,
kUserDateOfBirthBindIndex,
kUserFirstNameBindIndex = 1,
kUserLastNameBindIndex,
kUserGenderBindIndex,
kUserUsernameBindIndex,
kUserBioBindIndex,
kUserActivityWeightBindIndex,
kUserEmailBindIndex,
kUserDateOfBirthBindIndex,
};
enum UserAddressBindIndex {
kUserAddressUserIdBindIndex = 1,
kUserAddressCityIdBindIndex,
kUserAddressPostalCodeBindIndex,
kUserAddressUserIdBindIndex = 1,
kUserAddressCityIdBindIndex,
kUserAddressPostalCodeBindIndex,
};
SqliteStatementHandle PrepareStatement(const SqliteDatabaseHandle& db_handle,

View File

@@ -20,49 +20,49 @@
* directly
*/
class IDateTimeProvider {
public:
virtual ~IDateTimeProvider() = default;
public:
virtual ~IDateTimeProvider() = default;
IDateTimeProvider() = default;
IDateTimeProvider(const IDateTimeProvider&) = delete;
IDateTimeProvider& operator=(const IDateTimeProvider&) = delete;
IDateTimeProvider(IDateTimeProvider&&) = delete;
IDateTimeProvider& operator=(IDateTimeProvider&&) = delete;
IDateTimeProvider() = default;
IDateTimeProvider(const IDateTimeProvider&) = delete;
IDateTimeProvider& operator=(const IDateTimeProvider&) = delete;
IDateTimeProvider(IDateTimeProvider&&) = delete;
IDateTimeProvider& operator=(IDateTimeProvider&&) = delete;
/**
* @brief Returns the current UTC timestamp in a file-safe format.
*
* @return UTC timestamp string.
*/
virtual std::string GetUtcTimestamp() = 0;
/**
* @brief Returns the current UTC timestamp in a file-safe format.
*
* @return UTC timestamp string.
*/
virtual std::string GetUtcTimestamp() = 0;
};
/**
* @brief Timestamp provider backed by the system clock.
*/
class SystemDateTimeProvider final : public IDateTimeProvider {
public:
std::string GetUtcTimestamp() override {
constexpr int kFractionalSecondWidth = 6;
public:
std::string GetUtcTimestamp() override {
constexpr int kFractionalSecondWidth = 6;
const auto now = std::chrono::system_clock::now();
const auto now_time = std::chrono::system_clock::to_time_t(now);
const std::tm* utc_time_ptr = std::gmtime(&now_time);
if (utc_time_ptr == nullptr) {
throw std::runtime_error("Failed to format UTC timestamp");
}
const auto now = std::chrono::system_clock::now();
const auto now_time = std::chrono::system_clock::to_time_t(now);
const std::tm* utc_time_ptr = std::gmtime(&now_time);
if (utc_time_ptr == nullptr) {
throw std::runtime_error("Failed to format UTC timestamp");
}
const auto fractional_seconds =
std::chrono::duration_cast<std::chrono::microseconds>(
now.time_since_epoch()) %
std::chrono::seconds(1);
const auto fractional_seconds =
std::chrono::duration_cast<std::chrono::microseconds>(
now.time_since_epoch()) %
std::chrono::seconds(1);
std::ostringstream output;
output << std::put_time(utc_time_ptr, "%Y-%m-%dT%H-%M-%S");
output << '.' << std::setw(kFractionalSecondWidth) << std::setfill('0')
<< fractional_seconds.count() << 'Z';
return output.str();
}
std::ostringstream output;
output << std::put_time(utc_time_ptr, "%Y-%m-%dT%H-%M-%S");
output << '.' << std::setw(kFractionalSecondWidth) << std::setfill('0')
<< fractional_seconds.count() << 'Z';
return output.str();
}
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_DATE_TIME_PROVIDER_H_

View File

@@ -8,28 +8,28 @@
* @brief Simple timer utility for measuring elapsed time.
*/
class Timer {
std::chrono::steady_clock::time_point start_time =
std::chrono::steady_clock::now();
std::chrono::steady_clock::time_point start_time =
std::chrono::steady_clock::now();
public:
Timer(const Timer&) = delete;
Timer& operator=(const Timer&) = delete;
Timer(Timer&&) = delete;
Timer& operator=(Timer&&) = delete;
Timer() = default;
~Timer() = default;
public:
Timer(const Timer&) = delete;
Timer& operator=(const Timer&) = delete;
Timer(Timer&&) = delete;
Timer& operator=(Timer&&) = delete;
Timer() = default;
~Timer() = default;
[[nodiscard]] int64_t Elapsed() const {
return std::chrono::duration_cast<std::chrono::milliseconds>(
std::chrono::steady_clock::now() - start_time)
.count();
}
[[nodiscard]] int64_t Elapsed() const {
return std::chrono::duration_cast<std::chrono::milliseconds>(
std::chrono::steady_clock::now() - start_time)
.count();
}
[[nodiscard]] int64_t Reset() {
auto previous_elapsed = Elapsed();
start_time = std::chrono::steady_clock::now();
return previous_elapsed;
}
[[nodiscard]] int64_t Reset() {
auto previous_elapsed = Elapsed();
start_time = std::chrono::steady_clock::now();
return previous_elapsed;
}
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_TIMER_H_

View File

@@ -14,16 +14,16 @@
* @brief Interface for services that can enrich a location with context.
*/
class IEnrichmentService {
public:
virtual ~IEnrichmentService() = default;
public:
virtual ~IEnrichmentService() = default;
/**
* @brief Resolves contextual enrichment for a location.
*
* @param loc City to enrich.
* @return Context text, or an empty string if unavailable.
*/
virtual std::string GetLocationContext(const City& loc) = 0;
/**
* @brief Resolves contextual enrichment for a location.
*
* @param loc City to enrich.
* @return Context text, or an empty string if unavailable.
*/
virtual std::string GetLocationContext(const City& loc) = 0;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_ENRICHMENT_SERVICE_H_

View File

@@ -14,9 +14,7 @@
* @brief Enrichment service that returns no context for any location.
*/
class MockEnrichmentService final : public IEnrichmentService {
public:
std::string GetLocationContext(const City& /*loc*/) override {
return {};
}
public:
std::string GetLocationContext(const City& /*loc*/) override { return {}; }
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_

View File

@@ -19,30 +19,30 @@
* @brief Provides Wikipedia summary lookups backed by cached raw extracts.
*/
class WikipediaEnrichmentService final : public IEnrichmentService {
public:
/**
* @brief Creates a new Wikipedia service with the provided web client.
*/
explicit WikipediaEnrichmentService(std::unique_ptr<WebClient> client,
std::shared_ptr<ILogger> logger);
public:
/**
* @brief Creates a new Wikipedia service with the provided web client.
*/
explicit WikipediaEnrichmentService(std::unique_ptr<WebClient> client,
std::shared_ptr<ILogger> logger);
/**
* @brief Returns the Wikipedia-derived context for a location.
*/
[[nodiscard]] std::string GetLocationContext(const City& loc) override;
/**
* @brief Returns the Wikipedia-derived context for a location.
*/
[[nodiscard]] std::string GetLocationContext(const City& loc) override;
private:
std::string FetchExtract(std::string_view query);
std::unique_ptr<WebClient> client_;
std::shared_ptr<ILogger> logger_;
/**
* @brief Cache for raw Wikipedia query extracts, keyed by query string.
*
* GetLocationContext() always queries "brewing" and reuses "beer in
* {country}" for every city in that country, so caching avoids refetching
* the same extract across locations in a run.
*/
std::unordered_map<std::string, std::string> extract_cache_;
private:
std::string FetchExtract(std::string_view query);
std::unique_ptr<WebClient> client_;
std::shared_ptr<ILogger> logger_;
/**
* @brief Cache for raw Wikipedia query extracts, keyed by query string.
*
* GetLocationContext() always queries "brewing" and reuses "beer in
* {country}" for every city in that country, so caching avoids refetching
* the same extract across locations in a run.
*/
std::unordered_map<std::string, std::string> extract_cache_;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_WIKIPEDIA_SERVICE_H_

View File

@@ -22,32 +22,32 @@
* and exit once the channel has been closed and drained.
*/
class LogDispatcher {
public:
/**
* @brief Construct a log dispatcher.
*
* @param channel Reference to the bounded channel used for log retrieval.
*/
explicit LogDispatcher(BoundedChannel<LogEntry>& channel);
public:
/**
* @brief Construct a log dispatcher.
*
* @param channel Reference to the bounded channel used for log retrieval.
*/
explicit LogDispatcher(BoundedChannel<LogEntry>& channel);
LogDispatcher(const LogDispatcher&) = delete;
LogDispatcher& operator=(const LogDispatcher&) = delete;
LogDispatcher(LogDispatcher&&) = delete;
LogDispatcher& operator=(LogDispatcher&&) = delete;
~LogDispatcher() = default;
LogDispatcher(const LogDispatcher&) = delete;
LogDispatcher& operator=(const LogDispatcher&) = delete;
LogDispatcher(LogDispatcher&&) = delete;
LogDispatcher& operator=(LogDispatcher&&) = delete;
~LogDispatcher() = default;
/**
* @brief Drain the channel and forward entries to spdlog.
*
* Intended to be called once on a dedicated thread. The loop returns after
* the channel has been closed and all queued entries have been processed.
*/
void Run();
/**
* @brief Drain the channel and forward entries to spdlog.
*
* Intended to be called once on a dedicated thread. The loop returns after
* the channel has been closed and all queued entries have been processed.
*/
void Run();
private:
BoundedChannel<LogEntry>& channel_;
private:
BoundedChannel<LogEntry>& channel_;
static spdlog::level::level_enum ToSpdlogLevel(LogLevel level);
static spdlog::level::level_enum ToSpdlogLevel(LogLevel level);
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_

View File

@@ -20,22 +20,22 @@
* @brief Severity levels supported by the logging infra.
*/
enum class LogLevel {
/**
* @brief Development/debugging information.
*/
Debug,
/**
* @brief General informational messages.
*/
Info,
/**
* @brief Warning conditions.
*/
Warn,
/**
* @brief Error conditions.
*/
Error,
/**
* @brief Development/debugging information.
*/
Debug,
/**
* @brief General informational messages.
*/
Info,
/**
* @brief Warning conditions.
*/
Warn,
/**
* @brief Error conditions.
*/
Error,
};
/**
@@ -46,38 +46,38 @@ enum class LogLevel {
* pipeline that emitted it.
*/
enum class PipelinePhase {
/**
* @brief Initialization and validation.
*/
Startup,
/**
* @brief City/context enrichment (e.g. Wikipedia lookups).
*/
Enrichment,
/**
* @brief User profile generation.
*/
UserGeneration,
/**
* @brief Brewery and beer data generation.
*/
BreweryAndBeerGeneration,
/**
* @brief Checkin (visit) record generation.
*/
CheckinGeneration,
/**
* @brief Rating and review generation.
*/
RatingGeneration,
/**
* @brief Follow relationship generation.
*/
FollowGeneration,
/**
* @brief Finalization and cleanup.
*/
Teardown,
/**
* @brief Initialization and validation.
*/
Startup,
/**
* @brief City/context enrichment (e.g. Wikipedia lookups).
*/
Enrichment,
/**
* @brief User profile generation.
*/
UserGeneration,
/**
* @brief Brewery and beer data generation.
*/
BreweryAndBeerGeneration,
/**
* @brief Checkin (visit) record generation.
*/
CheckinGeneration,
/**
* @brief Rating and review generation.
*/
RatingGeneration,
/**
* @brief Follow relationship generation.
*/
FollowGeneration,
/**
* @brief Finalization and cleanup.
*/
Teardown,
};
/**
@@ -86,9 +86,9 @@ enum class PipelinePhase {
* transparently.
*/
struct LogDTO {
LogLevel level;
PipelinePhase phase;
std::string message;
LogLevel level;
PipelinePhase phase;
std::string message;
};
/**
@@ -102,35 +102,35 @@ struct LogDTO {
* before the entry is dispatched.
*/
struct LogEntry {
/**
* @brief Timestamp when the entry was created.
*/
std::chrono::system_clock::time_point timestamp{};
/**
* @brief Timestamp when the entry was created.
*/
std::chrono::system_clock::time_point timestamp{};
/**
* @brief Source location where the log call was made.
*/
std::source_location origin{};
/**
* @brief Source location where the log call was made.
*/
std::source_location origin{};
/**
* @brief Thread responsible for emitting the log.
*/
std::thread::id thread_id{};
/**
* @brief Thread responsible for emitting the log.
*/
std::thread::id thread_id{};
/**
* @brief Severity level of this entry.
*/
LogLevel level;
/**
* @brief Severity level of this entry.
*/
LogLevel level;
/**
* @brief Pipeline phase associated with the entry.
*/
PipelinePhase phase;
/**
* @brief Pipeline phase associated with the entry.
*/
PipelinePhase phase;
/**
* @brief Log message text.
*/
std::string message;
/**
* @brief Log message text.
*/
std::string message;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_

View File

@@ -23,31 +23,31 @@
* remain valid for the lifetime of the producer.
*/
class LogProducer final : public ILogger {
public:
/**
* @brief Construct a channel-backed producer.
*
* @param channel Reference to the bounded channel used for log transfer.
*/
explicit LogProducer(BoundedChannel<LogEntry>& channel);
public:
/**
* @brief Construct a channel-backed producer.
*
* @param channel Reference to the bounded channel used for log transfer.
*/
explicit LogProducer(BoundedChannel<LogEntry>& channel);
LogProducer(const LogProducer&) = delete;
LogProducer& operator=(const LogProducer&) = delete;
LogProducer(LogProducer&&) = delete;
LogProducer& operator=(LogProducer&&) = delete;
LogProducer(const LogProducer&) = delete;
LogProducer& operator=(const LogProducer&) = delete;
LogProducer(LogProducer&&) = delete;
LogProducer& operator=(LogProducer&&) = delete;
~LogProducer() override = default;
~LogProducer() override = default;
/**
* @brief Queue a log message for asynchronous processing.
*
* Blocks while the channel applies backpressure. This blocking behavior
* under heavy load is an accepted trade-off for simplicity.
*/
void DoLog(LogEntry log_entry) override;
/**
* @brief Queue a log message for asynchronous processing.
*
* Blocks while the channel applies backpressure. This blocking behavior
* under heavy load is an accepted trade-off for simplicity.
*/
void DoLog(LogEntry log_entry) override;
private:
BoundedChannel<LogEntry>& channel_;
private:
BoundedChannel<LogEntry>& channel_;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_PRODUCER_H_

View File

@@ -23,43 +23,43 @@
* by the composition root and injected into services that emit diagnostics.
*/
class ILogger {
public:
ILogger() = default;
ILogger(const ILogger&) = delete;
ILogger& operator=(const ILogger&) = delete;
ILogger(ILogger&&) = delete;
ILogger& operator=(ILogger&&) = delete;
virtual ~ILogger() = default;
public:
ILogger() = default;
ILogger(const ILogger&) = delete;
ILogger& operator=(const ILogger&) = delete;
ILogger(ILogger&&) = delete;
ILogger& operator=(ILogger&&) = delete;
virtual ~ILogger() = default;
/**
* @brief Submit a log message to the logging subsystem.
*
* @param payload User-provided log data (level, phase, message).
* @param origin Auto-captured source location of the call site.
*/
void Log(LogDTO payload,
std::source_location origin = std::source_location::current(),
std::chrono::system_clock::time_point timestamp =
std::chrono::system_clock::now(),
std::thread::id thread_id = std::this_thread::get_id()) {
LogEntry entry;
entry.timestamp = timestamp;
entry.thread_id = thread_id;
entry.level = payload.level;
entry.phase = payload.phase;
entry.message = std::move(payload.message);
entry.origin = origin;
DoLog(std::move(entry));
}
/**
* @brief Submit a log message to the logging subsystem.
*
* @param payload User-provided log data (level, phase, message).
* @param origin Auto-captured source location of the call site.
*/
void Log(LogDTO payload,
std::source_location origin = std::source_location::current(),
std::chrono::system_clock::time_point timestamp =
std::chrono::system_clock::now(),
std::thread::id thread_id = std::this_thread::get_id()) {
LogEntry entry;
entry.timestamp = timestamp;
entry.thread_id = thread_id;
entry.level = payload.level;
entry.phase = payload.phase;
entry.message = std::move(payload.message);
entry.origin = origin;
DoLog(std::move(entry));
}
protected:
/**
* @brief Underlying implementation to transport the log entry.
*
* Implementations must be thread-safe as DoLog can be called concurrently
* from multiple worker threads.
*/
virtual void DoLog(LogEntry log_entry) = 0;
protected:
/**
* @brief Underlying implementation to transport the log entry.
*
* Implementations must be thread-safe as DoLog can be called concurrently
* from multiple worker threads.
*/
virtual void DoLog(LogEntry log_entry) = 0;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_

View File

@@ -24,56 +24,57 @@
* example that fails validation, throws so the caller can skip the city.
*/
class MockPostalCodeService final : public IPostalCodeService {
public:
std::string GeneratePostalCode(const City& city) override {
const PostalCodeSpec& spec = city.postal_code;
public:
std::string GeneratePostalCode(const City& city) override {
const PostalCodeSpec& spec = city.postal_code;
if (spec.examples.empty()) {
throw std::runtime_error(std::format(
"No postal-code examples available for city '{}'", city.city));
}
const std::string& candidate = spec.examples.front();
if (!MatchesAnyPattern(candidate, spec)) {
throw std::runtime_error(
std::format("Postal code '{}' for city '{}' does not match the "
"curated postal-code regex",
candidate, city.city));
}
return candidate;
}
private:
/**
* @brief Returns true if @p candidate matches any city regex, or the
* country format regex when no city regex matches. When the spec carries no
* usable regex at all, validation is skipped (returns true).
*/
static bool MatchesAnyPattern(const std::string& candidate,
const PostalCodeSpec& spec) {
bool has_pattern = false;
for (const std::string& pattern : spec.city_regexes) {
if (pattern.empty()) {
continue;
if (spec.examples.empty()) {
throw std::runtime_error(std::format(
"No postal-code examples available for city '{}'", city.city));
}
has_pattern = true;
if (std::regex_match(candidate, std::regex(pattern))) {
return true;
}
}
if (!spec.country_format_regex.empty()) {
has_pattern = true;
if (std::regex_match(candidate, std::regex(spec.country_format_regex))) {
return true;
}
}
const std::string& candidate = spec.examples.front();
return !has_pattern;
}
if (!MatchesAnyPattern(candidate, spec)) {
throw std::runtime_error(
std::format("Postal code '{}' for city '{}' does not match the "
"curated postal-code regex",
candidate, city.city));
}
return candidate;
}
private:
/**
* @brief Returns true if @p candidate matches any city regex, or the
* country format regex when no city regex matches. When the spec carries no
* usable regex at all, validation is skipped (returns true).
*/
static bool MatchesAnyPattern(const std::string& candidate,
const PostalCodeSpec& spec) {
bool has_pattern = false;
for (const std::string& pattern : spec.city_regexes) {
if (pattern.empty()) {
continue;
}
has_pattern = true;
if (std::regex_match(candidate, std::regex(pattern))) {
return true;
}
}
if (!spec.country_format_regex.empty()) {
has_pattern = true;
if (std::regex_match(candidate,
std::regex(spec.country_format_regex))) {
return true;
}
}
return !has_pattern;
}
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_MOCK_POSTAL_CODE_SERVICE_H_

View File

@@ -14,22 +14,22 @@
* @brief Interface for services that resolve a postal code for a city.
*/
class IPostalCodeService {
public:
IPostalCodeService() = default;
virtual ~IPostalCodeService() = default;
public:
IPostalCodeService() = default;
virtual ~IPostalCodeService() = default;
IPostalCodeService(const IPostalCodeService&) = delete;
IPostalCodeService& operator=(const IPostalCodeService&) = delete;
IPostalCodeService(IPostalCodeService&&) = delete;
IPostalCodeService& operator=(IPostalCodeService&&) = delete;
IPostalCodeService(const IPostalCodeService&) = delete;
IPostalCodeService& operator=(const IPostalCodeService&) = delete;
IPostalCodeService(IPostalCodeService&&) = delete;
IPostalCodeService& operator=(IPostalCodeService&&) = delete;
/**
* @brief Resolves a postal code for @p city.
*
* @param city City whose curated postal-code examples supply the result.
* @return A postal code string, or an empty string if none is available.
*/
virtual std::string GeneratePostalCode(const City& city) = 0;
/**
* @brief Resolves a postal code for @p city.
*
* @param city City whose curated postal-code examples supply the result.
* @return A postal code string, or an empty string if none is available.
*/
virtual std::string GeneratePostalCode(const City& city) = 0;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_POSTAL_CODE_SERVICE_H_

View File

@@ -20,13 +20,13 @@
* via GenerateStringFromRegex().
*/
class XegerPostalCodeService final : public IPostalCodeService {
public:
XegerPostalCodeService();
public:
XegerPostalCodeService();
std::string GeneratePostalCode(const City& city) override;
std::string GeneratePostalCode(const City& city) override;
private:
std::mt19937 rng_;
private:
std::mt19937 rng_;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_XEGER_POSTAL_CODE_SERVICE_H_

View File

@@ -24,22 +24,22 @@
* @brief Interface for loading named prompt files.
*/
class IPromptDirectory {
public:
IPromptDirectory() = default;
IPromptDirectory(const IPromptDirectory&) = delete;
IPromptDirectory& operator=(const IPromptDirectory&) = delete;
IPromptDirectory(IPromptDirectory&&) = delete;
IPromptDirectory& operator=(IPromptDirectory&&) = delete;
virtual ~IPromptDirectory() = default;
public:
IPromptDirectory() = default;
IPromptDirectory(const IPromptDirectory&) = delete;
IPromptDirectory& operator=(const IPromptDirectory&) = delete;
IPromptDirectory(IPromptDirectory&&) = delete;
IPromptDirectory& operator=(IPromptDirectory&&) = delete;
virtual ~IPromptDirectory() = default;
/**
* @brief Loads the prompt associated with @p key.
*
* @param key Logical prompt key, e.g. "BREWERY_GENERATION".
* @return Prompt text.
* @throws std::runtime_error if the prompt file cannot be found or read.
*/
[[nodiscard]] virtual std::string Load(std::string_view key) = 0;
/**
* @brief Loads the prompt associated with @p key.
*
* @param key Logical prompt key, e.g. "BREWERY_GENERATION".
* @return Prompt text.
* @throws std::runtime_error if the prompt file cannot be found or read.
*/
[[nodiscard]] virtual std::string Load(std::string_view key) = 0;
};
/**
@@ -50,33 +50,33 @@ class IPromptDirectory {
* at construction time; individual file absence is reported lazily at Load().
*/
class PromptDirectory final : public IPromptDirectory {
public:
/**
* @brief Constructs a PromptDirectory rooted at @p prompt_dir.
*
* @param prompt_dir Absolute or relative path to the prompt directory.
* @throws std::runtime_error if @p prompt_dir does not exist or is not a
* directory.
*/
explicit PromptDirectory(const std::filesystem::path& prompt_dir);
PromptDirectory(const std::filesystem::path& prompt_dir,
std::shared_ptr<ILogger> logger);
public:
/**
* @brief Constructs a PromptDirectory rooted at @p prompt_dir.
*
* @param prompt_dir Absolute or relative path to the prompt directory.
* @throws std::runtime_error if @p prompt_dir does not exist or is not a
* directory.
*/
explicit PromptDirectory(const std::filesystem::path& prompt_dir);
PromptDirectory(const std::filesystem::path& prompt_dir,
std::shared_ptr<ILogger> logger);
/**
* @brief Loads the prompt for @p key, caching the result.
*
* Maps @p key → <prompt_dir>/<key>.md.
*
* @param key Logical prompt key.
* @return Prompt text.
* @throws std::runtime_error if the file does not exist or is empty.
*/
[[nodiscard]] std::string Load(std::string_view key) override;
/**
* @brief Loads the prompt for @p key, caching the result.
*
* Maps @p key → <prompt_dir>/<key>.md.
*
* @param key Logical prompt key.
* @return Prompt text.
* @throws std::runtime_error if the file does not exist or is empty.
*/
[[nodiscard]] std::string Load(std::string_view key) override;
private:
std::filesystem::path prompt_dir_;
std::shared_ptr<ILogger> logger_;
std::unordered_map<std::string, std::string> cache_;
private:
std::filesystem::path prompt_dir_;
std::shared_ptr<ILogger> logger_;
std::unordered_map<std::string, std::string> cache_;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_PROMPTING_PROMPT_DIRECTORY_H_

View File

@@ -55,33 +55,33 @@ struct Alternation;
struct Repeat;
struct Visitor {
virtual void Visit(const Literal&) = 0;
virtual void Visit(const AnyChar&) = 0;
virtual void Visit(const CharClass&) = 0;
virtual void Visit(const Concat&) = 0;
virtual void Visit(const Alternation&) = 0;
virtual void Visit(const Repeat&) = 0;
virtual ~Visitor() = default;
virtual void Visit(const Literal&) = 0;
virtual void Visit(const AnyChar&) = 0;
virtual void Visit(const CharClass&) = 0;
virtual void Visit(const Concat&) = 0;
virtual void Visit(const Alternation&) = 0;
virtual void Visit(const Repeat&) = 0;
virtual ~Visitor() = default;
};
struct Node {
virtual void Accept(Visitor&) const = 0;
virtual ~Node() = default;
virtual void Accept(Visitor&) const = 0;
virtual ~Node() = default;
};
using NodePtr = std::unique_ptr<Node>;
template <typename Derived>
struct Visitable : Node {
void Accept(Visitor& visitor) const override {
visitor.Visit(static_cast<const Derived&>(*this));
}
void Accept(Visitor& visitor) const override {
visitor.Visit(static_cast<const Derived&>(*this));
}
};
// One fixed character, e.g. 'a'.
struct Literal : Visitable<Literal> {
char ch;
explicit Literal(const char c) : ch(c) {}
char ch;
explicit Literal(const char c) : ch(c) {}
};
// The "." wildcard: any single printable character.
@@ -91,18 +91,18 @@ struct AnyChar : Visitable<AnyChar> {};
// character 'x' is the range {'x', 'x'}. `negated` flips the meaning to
// "any character NOT listed" (i.e. `[^...]`).
struct CharClass : Visitable<CharClass> {
std::vector<std::pair<char, char>> ranges;
bool negated = false;
std::vector<std::pair<char, char>> ranges;
bool negated = false;
};
// "Do these children one after another."
struct Concat : Visitable<Concat> {
std::vector<NodePtr> parts;
std::vector<NodePtr> parts;
};
// "Pick exactly one of these options at random" -- the `|` operator.
struct Alternation : Visitable<Alternation> {
std::vector<NodePtr> options;
std::vector<NodePtr> options;
};
// "Repeat one child between min and max times."
@@ -111,9 +111,9 @@ struct Alternation : Visitable<Alternation> {
// a? -> min 0, max 1
// a{2,5} -> min 2, max 5
struct Repeat : Visitable<Repeat> {
NodePtr child;
unsigned int min = 0;
std::optional<unsigned int> max; // std::nullopt means "no upper bound"
NodePtr child;
unsigned int min = 0;
std::optional<unsigned int> max; // std::nullopt means "no upper bound"
};
// Parser (recursive descent)
@@ -125,75 +125,75 @@ struct Repeat : Visitable<Repeat> {
// ParseAtom ::= a . [..] (..) \d
class Parser {
public:
explicit Parser(std::string_view pattern);
public:
explicit Parser(std::string_view pattern);
NodePtr Parse();
NodePtr Parse();
private:
std::string src_;
size_t pos_ = 0;
private:
std::string src_;
size_t pos_ = 0;
// Strips anchors (leading '^' and trailing '$') as they are not needed for
// generation.
static std::string StripAnchors(std::string_view pattern);
// Strips anchors (leading '^' and trailing '$') as they are not needed for
// generation.
static std::string StripAnchors(std::string_view pattern);
[[nodiscard]] bool AtEnd() const;
[[nodiscard]] char Peek() const;
char Advance();
bool Match(char c);
void Expect(char c);
[[nodiscard]] bool AtEnd() const;
[[nodiscard]] char Peek() const;
char Advance();
bool Match(char c);
void Expect(char c);
// Level 1: alternation -- ( concat | concat | concat )
NodePtr ParseAlternation();
// Level 1: alternation -- ( concat | concat | concat )
NodePtr ParseAlternation();
// Level 2: concatenation -- a run of items back to back
NodePtr ParseConcat();
// Level 2: concatenation -- a run of items back to back
NodePtr ParseConcat();
// Level 3: an atom plus an optional quantifier
NodePtr ParseRepeat();
// Level 3: an atom plus an optional quantifier
NodePtr ParseRepeat();
// Curly-brace quantifiers: {n}, {n,}, {n,m}
NodePtr ParseBrace(NodePtr atom);
// Curly-brace quantifiers: {n}, {n,}, {n,m}
NodePtr ParseBrace(NodePtr atom);
// Level 4: an atom -- the smallest standalone unit
NodePtr ParseAtom();
// Level 4: an atom -- the smallest standalone unit
NodePtr ParseAtom();
static NodePtr MakeClass(std::vector<std::pair<char, char>> ranges,
bool negated);
static NodePtr MakeClass(std::vector<std::pair<char, char>> ranges,
bool negated);
NodePtr ParseEscape();
NodePtr ParseEscape();
NodePtr ParseCharClass();
NodePtr ParseCharClass();
// Reads one character inside [ ], turning \] \n etc. into the real
// character they represent.
char ClassChar();
// Reads one character inside [ ], turning \] \n etc. into the real
// character they represent.
char ClassChar();
};
// Generator -- a Visitor that emits a random matching string
class XegerGenerator final : public Visitor {
public:
XegerGenerator(std::mt19937& rng, int unbounded_cap);
public:
XegerGenerator(std::mt19937& rng, int unbounded_cap);
std::string Run(const Node& root);
std::string Run(const Node& root);
void Visit(const Literal& node) override;
void Visit(const AnyChar&) override;
void Visit(const CharClass& node) override;
void Visit(const Concat& node) override;
void Visit(const Alternation& node) override;
void Visit(const Repeat& node) override;
void Visit(const Literal& node) override;
void Visit(const AnyChar&) override;
void Visit(const CharClass& node) override;
void Visit(const Concat& node) override;
void Visit(const Alternation& node) override;
void Visit(const Repeat& node) override;
private:
std::mt19937& rng_;
int unbounded_cap_;
std::string out_;
private:
std::mt19937& rng_;
int unbounded_cap_;
std::string out_;
static bool InRanges(const CharClass& node, char c);
static bool InRanges(const CharClass& node, char c);
char PickFromClass(const CharClass& node);
char PickFromClass(const CharClass& node);
};
} // namespace xeger_internal