Rename JsonLoader to CuratedJsonDataService and add the address-lookup classes to the pipeline diagrams

This commit is contained in:
Aaron Po
2026-08-31 22:03:24 -04:00
parent 399ae86c1f
commit a6d6724251
3 changed files with 64 additions and 25 deletions

View File

@@ -5,6 +5,7 @@ classDiagram
-unique_ptr~DataGenerator~ generator_
-unique_ptr~IExportService~ exporter_
-unique_ptr~ICuratedDataService~ curated_data_service_
-unique_ptr~IAddressService~ address_service_
-ApplicationOptions application_options_
-vector~BreweryRecord~ generated_breweries_
-vector~UserRecord~ generated_users_
@@ -14,7 +15,7 @@ classDiagram
-GenerateUsers(cities) void
-LogResults() void
}
note for BiergartenPipelineOrchestrator "GenerateBreweries/GenerateUsers jitter each address via GetRandomCoordsWithinRange(), uniformly within 5km of the city centre"
note for BiergartenPipelineOrchestrator "GenerateBreweries/GenerateUsers jitter each address via GetRandomCoordsWithinRange(), uniformly within 5km of the city centre. GenerateBreweries additionally reverse-geocodes the jittered coordinates via address_service_."
class LogLevel {
<<enumeration>>
@@ -157,32 +158,50 @@ classDiagram
class ICuratedDataService {
<<interface>>
+LoadLocations(filepath) vector~Location~
+LoadPersonas(filepath) vector~UserPersona~
+LoadForenamesByCountry(filepath) unordered_map~string, forename_list~
+LoadSurnamesByCountry(filepath) unordered_map~string, surname_list~
+LoadLocations() vector~Location~
+LoadPersonas() vector~UserPersona~
+LoadForenamesByCountry() unordered_map~string, forename_list~
+LoadSurnamesByCountry() unordered_map~string, surname_list~
}
class JsonLoader {
class CuratedJsonDataService {
-CuratedDataFilePaths filepaths_
-cache cache_
+LoadLocations(filepath) vector~Location~
+LoadPersonas(filepath) vector~UserPersona~
+LoadForenamesByCountry(filepath) unordered_map~string, forename_list~
+LoadSurnamesByCountry(filepath) unordered_map~string, surname_list~
+LoadLocations() vector~Location~
+LoadPersonas() vector~UserPersona~
+LoadForenamesByCountry() unordered_map~string, forename_list~
+LoadSurnamesByCountry() unordered_map~string, surname_list~
}
note for JsonLoader "Each Load* method memoizes its result in cache_ after its first call"
note for CuratedJsonDataService "Takes a CuratedDataFilePaths DTO (locations/personas/forenames/surnames paths) once at construction, not per Load* call. Each Load* method memoizes its result in cache_ after its first call."
class MockCuratedDataService {
-vector~Location~ locations_
-vector~UserPersona~ personas_
-unordered_map~string, forename_list~ forenames_by_country_
-unordered_map~string, surname_list~ surnames_by_country_
+LoadLocations(filepath) vector~Location~
+LoadPersonas(filepath) vector~UserPersona~
+LoadForenamesByCountry(filepath) unordered_map~string, forename_list~
+LoadSurnamesByCountry(filepath) unordered_map~string, surname_list~
+LoadLocations() vector~Location~
+LoadPersonas() vector~UserPersona~
+LoadForenamesByCountry() unordered_map~string, forename_list~
+LoadSurnamesByCountry() unordered_map~string, surname_list~
}
note for MockCuratedDataService "Fixed 4-location/3-persona dataset (US, DE, FR, BE) for --mocked runs; filepath arguments are ignored"
note for MockCuratedDataService "Fixed 4-location/3-persona dataset (US, DE, FR, BE) for --mocked runs"
class IAddressService {
<<interface>>
+ReverseGeocode(longitude, latitude) optional~AddressLookupResult~
}
class NominatimAddressService {
-unique_ptr~WebClient~ client_
-shared_ptr~ILogger~ logger_
+ReverseGeocode(longitude, latitude) optional~AddressLookupResult~
}
note for NominatimAddressService "Queries the public Nominatim API; sleeps 1s per request per its usage policy; returns nullopt on failure or when no usable street address is found"
class MockAddressService {
+ReverseGeocode(longitude, latitude) optional~AddressLookupResult~
}
note for MockAddressService "Returns a fixed placeholder address ('123 Mock Street', '00000') for --mocked runs, no network call"
class IExportService {
<<interface>>
@@ -197,17 +216,19 @@ classDiagram
-string run_timestamp_utc_
-path database_path_
-SqliteDatabaseHandle db_handle_
-SqliteStatementHandle insert_location_stmt_
-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_
-unordered_map~string, sqlite3_int64~ location_cache_
-unordered_map~string, sqlite3_int64~ city_cache_
+Initialize() void
+ProcessRecord(brewery) uint64_t
+ProcessRecord(user) uint64_t
+Finalize() void
-InitializeSchema() void
-ResolveLocationId(location) sqlite3_int64
-ResolveCityId(city) sqlite3_int64
}
class IDateTimeProvider {
@@ -224,6 +245,7 @@ classDiagram
BiergartenPipelineOrchestrator *-- DataGenerator : owns
BiergartenPipelineOrchestrator *-- IExportService : owns
BiergartenPipelineOrchestrator *-- ICuratedDataService : owns
BiergartenPipelineOrchestrator *-- IAddressService : owns
LogEntry *-- LogLevel
LogEntry *-- PipelinePhase
@@ -252,9 +274,12 @@ classDiagram
IPromptFormatter <|.. Gemma4JinjaPromptFormatter : implements
IPromptDirectory <|.. PromptDirectory : implements
ICuratedDataService <|.. JsonLoader : implements
ICuratedDataService <|.. CuratedJsonDataService : implements
ICuratedDataService <|.. MockCuratedDataService : implements
IAddressService <|.. NominatimAddressService : implements
IAddressService <|.. MockAddressService : implements
IExportService <|.. SqliteExportService : implements
SqliteExportService *-- IDateTimeProvider : owns
IDateTimeProvider <|.. SystemDateTimeProvider : implements