Add user generation feature

This commit is contained in:
Aaron Po
2026-06-21 11:59:55 -04:00
parent 880f73e004
commit 51b40a39c9
30 changed files with 53719 additions and 59 deletions

View File

@@ -43,7 +43,7 @@ fork again
:EnrichmentService::PreWarmLocationCache(sampled_locations);
end fork
fork
:JsonLoader::LoadNamesByCountry("names-by-country.json");
:JsonLoader::LoadNamesByCountry(\n "forenames-by-country.json",\n "surnames-by-country.json");
fork again
:JsonLoader::LoadPersonas("personas.json");
end fork

View File

@@ -67,11 +67,47 @@ package "Domain: Models" {
}
class UserResult {
+ first_name : std::string
+ last_name : std::string
+ gender : std::string
+ username : std::string
+ bio : std::string
+ activity_weight : float
}
class Name {
+ first_name : std::string
+ last_name : std::string
+ gender : std::string
}
class ForenameEntry {
+ name : std::string
+ gender : std::string
}
class NamesByCountry {
- forenames_by_country_ : std::unordered_map<std::string, std::vector<ForenameEntry>>
- surnames_by_country_ : std::unordered_map<std::string, std::vector<std::string>>
+ SampleName(iso3166_1 : const std::string&,\n rng : std::mt19937&) : std::optional<Name>
}
note right of NamesByCountry
Backed by two source-shaped maps,
keyed by ISO 3166-1 country code,
sourced from popular-names-by-country-dataset
(CC0) -- see ETHICS-AND-KNOWN-ISSUES.md.
Gender is preserved per forename so it can
be threaded through to persona/bio generation
later; surnames carry no gender in the source
data. Pairing happens at sample time, not at
fixture-authoring time, so no information from
the source dataset is discarded up front.
end note
NamesByCountry *-- "0..*" ForenameEntry
NamesByCountry ..> Name : produces
class CheckinResult {
+ checked_in_at : std::string
+ note : std::string
@@ -110,9 +146,20 @@ package "Domain: Models" {
+ user_id : uint64_t
+ location : Location
+ user : UserResult
+ email : std::string
+ date_of_birth : std::string
+ password : std::string
+ metadata : GenerationMetadata
}
note right of GeneratedUser
email, date_of_birth, and password are
programmatically generated by the orchestrator
(not LLM-authored) so a downstream auth-account
seeding consumer can register real accounts from
this export. See ROADMAP.md §1.
end note
class GeneratedCheckin {
+ checkin_id : uint64_t
+ user_id : uint64_t
@@ -321,15 +368,15 @@ package "Infrastructure: Data Preloading" {
interface DataPreloader <<interface>> {
+ LoadLocations(filepath : const std::filesystem::path&) : std::vector<Location>
+ LoadBeerStyles(filepath : const std::filesystem::path&) : std::vector<BeerStyle>
+ LoadPersonas(filepath : const std::filesystem::path&) : std::vector<Persona>
+ LoadNamesByCountry(filepath : const std::filesystem::path&) : NamesByCountry
+ LoadPersonas(filepath : const std::filesystem::path&) : std::vector<UserPersona>
+ LoadNamesByCountry(forenames_filepath : const std::filesystem::path&,\n surnames_filepath : const std::filesystem::path&) : NamesByCountry
}
class JsonLoader {
+ LoadLocations(filepath : const std::filesystem::path&) : std::vector<Location>
+ LoadBeerStyles(filepath : const std::filesystem::path&) : std::vector<BeerStyle>
+ LoadPersonas(filepath : const std::filesystem::path&) : std::vector<Persona>
+ LoadNamesByCountry(filepath : const std::filesystem::path&) : NamesByCountry
+ LoadPersonas(filepath : const std::filesystem::path&) : std::vector<UserPersona>
+ LoadNamesByCountry(forenames_filepath : const std::filesystem::path&,\n surnames_filepath : const std::filesystem::path&) : NamesByCountry
}
}
@@ -380,7 +427,7 @@ package "Infrastructure: Data Generation" {
interface DataGenerator <<interface>> {
+ GenerateBrewery(location : const Location&,\n context : const LocationContext&) : BreweryResult
+ GenerateBeer(brewery_id : uint64_t,\n location : const Location&,\n context : const LocationContext&,\n style : const BeerStyle&) : BeerResult
+ GenerateUser(location : const Location&) : UserResult
+ GenerateUser(city : const EnrichedCity&,\n persona : const UserPersona&,\n name : const Name&) : UserResult
+ GenerateCheckin(user : const GeneratedUser&,\n brewery : const GeneratedBrewery&,\n timestamp : const std::string&) : CheckinResult
+ GenerateRating(user : const GeneratedUser&,\n beer : const GeneratedBeer&,\n checkin_id : uint64_t) : RatingResult
}

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 106 KiB

After

Width:  |  Height:  |  Size: 139 KiB

File diff suppressed because one or more lines are too long

Before

Width:  |  Height:  |  Size: 184 KiB

After

Width:  |  Height:  |  Size: 234 KiB