Co-authored-by: Copilot <copilot@github.com>
This commit is contained in:
Aaron Po
2026-04-23 13:49:37 -04:00
parent 8f5471d96c
commit 4331865281
3 changed files with 468 additions and 436 deletions

View File

@@ -3,220 +3,413 @@
' ==========================================
' CONFIGURATION & STYLING
' ==========================================
skinparam classAttributeFontSize 13
' --- Typography ---
skinparam defaultFontName "DM Sans"
skinparam defaultFontSize 20
skinparam titleFontName "Volkhov"
!include ../biergarten-weizen-theme.puml
skinparam classAttributeFontSize 9
skinparam defaultFontSize 25
skinparam titleFontSize 30
package "Domain" {
package "Domain Models" {
package "Domain: Models" {
class Location {
+ city : std::string
+ state_province : std::string
+ iso3166_2 : std::string
+ country : std::string
+ iso3166_1 : std::string
+ local_languages : std::vector<std::string>
+ latitude : double
+ longitude : double
}
class LocationContext {
+ text : std::string
+ completeness : Completeness
+ char_count : size_t
}
enum Completeness {
Full
Partial
Absent
}
class EnrichedCity {
+ location : Location
+ context : LocationContext
}
class BeerStyle {
+ name : std::string
+ description : std::string
+ min_abv : float
+ max_abv : float
+ min_ibu : int
+ max_ibu : int
}
class BreweryResult {
+ name_en : std::string
+ description_en : std::string
+ name_local : std::string
+ description_local : std::string
}
class BeerResult {
+ name_en : std::string
+ description_en : std::string
+ name_local : std::string
+ description_local : std::string
+ style : std::string
+ abv : float
+ ibu : int
}
class UserResult {
+ username : std::string
+ bio : std::string
+ activity_weight : float
}
class CheckinResult {
+ checked_in_at : std::string
+ note : std::string
}
class RatingResult {
+ score : float
+ note : std::string
}
class GeneratedBrewery {
+ brewery_id : sqlite3_int64
+ location : Location
+ brewery : BreweryResult
+ context_completeness : LocationContext::Completeness
+ generated_at : std::string
}
class GeneratedBeer {
+ beer_id : sqlite3_int64
+ brewery_id : sqlite3_int64
+ location : Location
+ style : BeerStyle
+ beer : BeerResult
+ generated_at : std::string
}
class GeneratedUser {
+ user_id : sqlite3_int64
+ location : Location
+ user : UserResult
+ generated_at : std::string
}
class GeneratedCheckin {
+ checkin_id : sqlite3_int64
+ user_id : sqlite3_int64
+ brewery_id : sqlite3_int64
+ checkin : CheckinResult
+ generated_at : std::string
}
class GeneratedRating {
+ user_id : sqlite3_int64
+ beer_id : sqlite3_int64
+ checkin_id : sqlite3_int64
+ rating : RatingResult
+ generated_at : std::string
}
LocationContext *-- Completeness
class Location {
+ city : std::string
+ state_province : std::string
+ iso3166_2 : std::string
+ country : std::string
+ iso3166_1 : std::string
+ local_languages : std::vector<std::string>
+ latitude : double
+ longitude : double
}
package "Domain: Application Configuration"{
class SamplingOptions {
+ temperature : float = 1.0F
+ top_p : float = 0.95F
+ top_k : uint32_t = 64
+ n_ctx : uint32_t = 8192
+ seed : int = -1
}
class GeneratorOptions {
+ model_path : std::filesystem::path
+ use_mocked : bool = false
+ sampling : SamplingOptions
}
class PipelineOptions {
+ output_path : std::filesystem::path
+ log_path : std::filesystem::path
}
class ApplicationOptions {
+ generator : GeneratorOptions
+ pipeline : PipelineOptions
}
' --- Domain Model Relationships ---
ApplicationOptions *-- GeneratorOptions
ApplicationOptions *-- PipelineOptions
GeneratorOptions *-- SamplingOptions
class LocationContext {
+ text : std::string
+ completeness : Completeness
+ char_count : size_t
}
' ==========================================
' DOMAIN POLICY
' ==========================================
package "Domain Policy" {
enum Completeness {
Full
Partial
Absent
}
interface ContextStrategy <<interface>> {
+ QueriesFor(loc : const Location&) : std::vector<std::string>
+ MaxContextChars() : size_t
}
class EnrichedCity {
+ location : Location
+ context : LocationContext
}
class BreweryContextStrategy {
+ QueriesFor(loc : const Location&) : std::vector<std::string>
+ MaxContextChars() : size_t
}
class BeerStyle {
+ name : std::string
+ description : std::string
+ min_abv : float
+ max_abv : float
+ min_ibu : int
+ max_ibu : int
}
class BeerContextStrategy {
+ QueriesFor(loc : const Location&) : std::vector<std::string>
+ MaxContextChars() : size_t
}
class BreweryResult {
+ name_en : std::string
+ description_en : std::string
+ name_local : std::string
+ description_local : std::string
}
interface SamplingStrategy <<interface>> {
+ Sample(locations : const std::vector<Location>&) : std::vector<Location>
}
class BeerResult {
+ name_en : std::string
+ description_en : std::string
+ name_local : std::string
+ description_local : std::string
+ style : std::string
+ abv : float
+ ibu : int
}
class UniformSamplingStrategy {
- sample_size_ : size_t
+ Sample(locations : const std::vector<Location>&) : std::vector<Location>
}
class UserResult {
+ username : std::string
+ bio : std::string
+ activity_weight : float
}
interface BeerSelectionStrategy <<interface>> {
+ SelectStyles(brewery : const GeneratedBrewery&,\n palette : std::span<const BeerStyle>) : std::vector<BeerStyle>
}
class CheckinResult {
+ checked_in_at : std::string
+ note : std::string
}
class RandomBeerSelectionStrategy {
- rng_ : std::mt19937
- min_beers_ : size_t
- max_beers_ : size_t
+ SelectStyles(brewery : const GeneratedBrewery&,\n palette : std::span<const BeerStyle>) : std::vector<BeerStyle>
}
class RatingResult {
+ score : float
+ note : std::string
}
interface CheckinDistributionStrategy <<interface>> {
+ AssignActivityWeights(users : std::vector<GeneratedUser>&) : void
+ CheckinsForUser(user : const GeneratedUser&,\n brewery_count : size_t) : size_t
+ TimestampFor(user : const GeneratedUser&,\n index : size_t) : std::string
}
class GeneratedBrewery {
+ brewery_id : sqlite3_int64
+ location : Location
+ brewery : BreweryResult
+ context_completeness : LocationContext::Completeness
+ generated_at : std::string
}
class JCurveCheckinStrategy {
- rng_ : std::mt19937
+ AssignActivityWeights(users : std::vector<GeneratedUser>&) : void
+ CheckinsForUser(user : const GeneratedUser&,\n brewery_count : size_t) : size_t
+ TimestampFor(user : const GeneratedUser&,\n index : size_t) : std::string
}
class GeneratedBeer {
+ beer_id : sqlite3_int64
+ brewery_id : sqlite3_int64
+ location : Location
+ style : BeerStyle
+ beer : BeerResult
+ generated_at : std::string
}
class GeneratedUser {
+ user_id : sqlite3_int64
+ location : Location
+ user : UserResult
+ generated_at : std::string
}
class GeneratedCheckin {
+ checkin_id : sqlite3_int64
+ user_id : sqlite3_int64
+ brewery_id : sqlite3_int64
+ checkin : CheckinResult
+ generated_at : std::string
}
class GeneratedRating {
+ user_id : sqlite3_int64
+ beer_id : sqlite3_int64
+ checkin_id : sqlite3_int64
+ rating : RatingResult
+ generated_at : std::string
}
LocationContext *-- Completeness
}
package "Domain: Application Configuration"{
class SamplingOptions {
+ temperature : float = 1.0F
+ top_p : float = 0.95F
+ top_k : uint32_t = 64
+ n_ctx : uint32_t = 8192
+ seed : int = -1
}
class GeneratorOptions {
+ model_path : std::filesystem::path
+ use_mocked : bool = false
+ sampling : SamplingOptions
}
class PipelineOptions {
+ output_path : std::filesystem::path
+ log_path : std::filesystem::path
}
class ApplicationOptions {
+ generator : GeneratorOptions
+ pipeline : PipelineOptions
}
' --- Domain Model Relationships ---
ApplicationOptions *-- GeneratorOptions
ApplicationOptions *-- PipelineOptions
GeneratorOptions *-- SamplingOptions
}
package "Domain: Policy" {
interface ContextStrategy <<interface>> {
+ QueriesFor(loc : const Location&) : std::vector<std::string>
+ MaxContextChars() : size_t
}
class BreweryContextStrategy {
+ QueriesFor(loc : const Location&) : std::vector<std::string>
+ MaxContextChars() : size_t
}
class BeerContextStrategy {
+ QueriesFor(loc : const Location&) : std::vector<std::string>
+ MaxContextChars() : size_t
}
interface SamplingStrategy <<interface>> {
+ Sample(locations : const std::vector<Location>&) : std::vector<Location>
}
class UniformSamplingStrategy {
- sample_size_ : size_t
+ Sample(locations : const std::vector<Location>&) : std::vector<Location>
}
interface BeerSelectionStrategy <<interface>> {
+ SelectStyles(brewery : const GeneratedBrewery&,\n palette : std::span<const BeerStyle>) : std::vector<BeerStyle>
}
class RandomBeerSelectionStrategy {
- rng_ : std::mt19937
- min_beers_ : size_t
- max_beers_ : size_t
+ SelectStyles(brewery : const GeneratedBrewery&,\n palette : std::span<const BeerStyle>) : std::vector<BeerStyle>
}
interface CheckinDistributionStrategy <<interface>> {
+ AssignActivityWeights(users : std::vector<GeneratedUser>&) : void
+ CheckinsForUser(user : const GeneratedUser&,\n brewery_count : size_t) : size_t
+ TimestampFor(user : const GeneratedUser&,\n index : size_t) : std::string
}
class JCurveCheckinStrategy {
- rng_ : std::mt19937
+ AssignActivityWeights(users : std::vector<GeneratedUser>&) : void
+ CheckinsForUser(user : const GeneratedUser&,\n brewery_count : size_t) : size_t
+ TimestampFor(user : const GeneratedUser&,\n index : size_t) : std::string
}
}
' ==========================================
' ORCHESTRATION
' ==========================================
package "Infrastructure: Logging" {
enum LogLevel {
Debug
Info
Warn
Error
}
enum PipelinePhase {
Startup
UserGeneration
BreweryAndBeerGeneration
CheckinGeneration
RatingGeneration
Teardown
}
class LogEntry {
+ timestamp : std::chrono::system_clock::time_point
+ level : LogLevel
+ phase : PipelinePhase
+ message : std::string
+ city : std::optional<std::string>
+ entity_id : std::optional<std::string>
+ worker : std::optional<std::string>
}
interface Logger <<interface>> {
+ Log(level, phase, message,\n city, entity_id, worker) : void
}
class PipelineLogger {
- log_ch_ : BoundedChannel<LogEntry>&
+ Log(level, phase, message,\n city, entity_id, worker) : void
}
class LogWorker {
- log_ch_ : BoundedChannel<LogEntry>&
+ Run() : void
- FormatTimestamp(tp) : std::string
- ToSpdlogLevel(level) : spdlog::level::level_enum
- ToString(phase) : std::string
}
' --- Logging Relationships ---
LogEntry *-- LogLevel
LogEntry *-- PipelinePhase
PipelineLogger ..> LogEntry : emits
LogWorker ..> LogEntry : consumes
}
package "Infrastructure: Pipeline Channel" {
class "BoundedChannel<T>" as BoundedChannel {
- queue_ : std::queue<T>
- mutex_ : std::mutex
- not_full_ : std::condition_variable
- not_empty_ : std::condition_variable
- capacity_ : size_t
- closed_ : bool
+ Send(item : T) : void
+ Receive() : std::optional<T>
+ Close() : void
}
}
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
}
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
}
}
package "Infrastructure: Enrichment" {
interface EnrichmentService <<interface>> {
+ GetLocationContext(loc : const Location&,\n strategy : const ContextStrategy&) : LocationContext
}
class WikipediaService {
- client_ : std::unique_ptr<WebClient>
- extract_cache_ : std::unordered_map<std::string, std::string>
+ GetLocationContext(loc : const Location&,\n strategy : const ContextStrategy&) : LocationContext
- FetchExtract(query : std::string_view) : std::string
}
interface WebClient <<interface>> {
+ Get(url : const std::string&) : std::string
+ UrlEncode(value : const std::string&) : std::string
}
class CURLWebClient {
+ Get(url : const std::string&) : std::string
+ UrlEncode(value : const std::string&) : std::string
}
}
package "Infrastructure: Data Generation" {
interface DataGenerator <<interface>> {
+ GenerateBrewery(location : const Location&,\n context : const LocationContext&) : BreweryResult
+ GenerateBeer(brewery_id : sqlite3_int64,\n location : const Location&,\n context : const LocationContext&,\n style : const BeerStyle&) : BeerResult
+ GenerateUser(location : const Location&) : 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 : sqlite3_int64) : RatingResult
}
class MockGenerator {
+ GenerateBrewery(...) : BreweryResult
+ GenerateBeer(...) : BeerResult
+ GenerateUser(...) : UserResult
+ GenerateCheckin(...) : CheckinResult
+ GenerateRating(...) : RatingResult
- DeterministicHash(location : const Location&) : size_t
}
class LlamaGenerator {
- model_ : ModelHandle
- context_ : ContextHandle
- prompt_formatter_ : std::unique_ptr<PromptFormatter>
- rng_ : std::mt19937
+ GenerateBrewery(...) : BreweryResult
+ GenerateBeer(...) : BeerResult
+ GenerateUser(...) : UserResult
+ GenerateCheckin(...) : CheckinResult
+ GenerateRating(...) : RatingResult
- Load(opts : const GeneratorOptions&) : void
- Infer(system_prompt, user_prompt,\n max_tokens, grammar) : std::string
- ValidateModelArchitecture() : void
}
interface PromptFormatter <<interface>> {
+ Format(system_prompt : std::string_view,\n user_prompt : std::string_view) : std::string
+ ExpectedArchitecture() : std::string_view
}
class Gemma4JinjaPromptFormatter {
+ Format(...) : std::string
+ ExpectedArchitecture() : std::string_view
}
}
package "Infrastructure: Data Export" {
interface ExportService <<interface>> {
+ Initialize() : void
+ ProcessBrewery(brewery : const GeneratedBrewery&) : sqlite3_int64
+ ProcessBeer(beer : const GeneratedBeer&) : sqlite3_int64
+ ProcessUser(user : const GeneratedUser&) : sqlite3_int64
+ ProcessCheckin(checkin : const GeneratedCheckin&) : sqlite3_int64
+ ProcessRating(rating : const GeneratedRating&) : void
+ Finalize() : void
}
class SqliteExportService {
- date_time_provider_ : std::unique_ptr<DateTimeProvider>
- db_handle_ : SqliteDatabaseHandle
- insert_location_stmt_ : SqliteStatementHandle
- insert_brewery_stmt_ : SqliteStatementHandle
- insert_beer_stmt_ : SqliteStatementHandle
- insert_user_stmt_ : SqliteStatementHandle
- insert_checkin_stmt_ : SqliteStatementHandle
- insert_rating_stmt_ : SqliteStatementHandle
- transaction_open_ : bool
- location_cache_ : std::unordered_map<std::string, sqlite3_int64>
- brewery_cache_ : std::unordered_map<std::string, sqlite3_int64>
+ Initialize() : void
+ ProcessBrewery(brewery : const GeneratedBrewery&) : sqlite3_int64
+ ProcessBeer(beer : const GeneratedBeer&) : sqlite3_int64
+ ProcessUser(user : const GeneratedUser&) : sqlite3_int64
+ ProcessCheckin(checkin : const GeneratedCheckin&) : sqlite3_int64
+ ProcessRating(rating : const GeneratedRating&) : void
+ Finalize() : void
- InitializeSchema() : void
- PrepareStatements() : void
- RollbackAndCloseNoThrow() : void
- FinalizeStatements() : void
}
interface DateTimeProvider <<interface>> {
+ GetUtcTimestamp() : std::string
}
class SystemDateTimeProvider {
+ GetUtcTimestamp() : std::string
}
}
class BiergartenPipelineOrchestrator {
- preloader_ : std::unique_ptr<DataPreloader>
@@ -243,216 +436,6 @@ class BiergartenPipelineOrchestrator {
- RunRatingPhase() : void
}
package "Infrastructure" {
package "Logging" {
enum LogLevel {
Debug
Info
Warn
Error
}
enum PipelinePhase {
Startup
UserGeneration
BreweryAndBeerGeneration
CheckinGeneration
RatingGeneration
Teardown
}
class LogEntry {
+ timestamp : std::chrono::system_clock::time_point
+ level : LogLevel
+ phase : PipelinePhase
+ message : std::string
+ city : std::optional<std::string>
+ entity_id : std::optional<std::string>
+ worker : std::optional<std::string>
}
interface Logger <<interface>> {
+ Log(level, phase, message,\n city, entity_id, worker) : void
}
class PipelineLogger {
- log_ch_ : BoundedChannel<LogEntry>&
+ Log(level, phase, message,\n city, entity_id, worker) : void
}
class LogWorker {
- log_ch_ : BoundedChannel<LogEntry>&
+ Run() : void
- FormatTimestamp(tp) : std::string
- ToSpdlogLevel(level) : spdlog::level::level_enum
- ToString(phase) : std::string
}
' --- Logging Relationships ---
LogEntry *-- LogLevel
LogEntry *-- PipelinePhase
PipelineLogger ..> LogEntry : emits
LogWorker ..> LogEntry : consumes
}
package "Pipeline Channel" {
class "BoundedChannel<T>" as BoundedChannel {
- queue_ : std::queue<T>
- mutex_ : std::mutex
- not_full_ : std::condition_variable
- not_empty_ : std::condition_variable
- capacity_ : size_t
- closed_ : bool
+ Send(item : T) : void
+ Receive() : std::optional<T>
+ Close() : void
}
}
package "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
}
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
}
}
package "Enrichment" {
interface EnrichmentService <<interface>> {
+ GetLocationContext(loc : const Location&,\n strategy : const ContextStrategy&) : LocationContext
}
class WikipediaService {
- client_ : std::unique_ptr<WebClient>
- extract_cache_ : std::unordered_map<std::string, std::string>
+ GetLocationContext(loc : const Location&,\n strategy : const ContextStrategy&) : LocationContext
- FetchExtract(query : std::string_view) : std::string
}
interface WebClient <<interface>> {
+ Get(url : const std::string&) : std::string
+ UrlEncode(value : const std::string&) : std::string
}
class CURLWebClient {
+ Get(url : const std::string&) : std::string
+ UrlEncode(value : const std::string&) : std::string
}
}
package "Data Generation" {
interface DataGenerator <<interface>> {
+ GenerateBrewery(location : const Location&,\n context : const LocationContext&) : BreweryResult
+ GenerateBeer(brewery_id : sqlite3_int64,\n location : const Location&,\n context : const LocationContext&,\n style : const BeerStyle&) : BeerResult
+ GenerateUser(location : const Location&) : 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 : sqlite3_int64) : RatingResult
}
class MockGenerator {
+ GenerateBrewery(...) : BreweryResult
+ GenerateBeer(...) : BeerResult
+ GenerateUser(...) : UserResult
+ GenerateCheckin(...) : CheckinResult
+ GenerateRating(...) : RatingResult
- DeterministicHash(location : const Location&) : size_t
}
class LlamaGenerator {
- model_ : ModelHandle
- context_ : ContextHandle
- prompt_formatter_ : std::unique_ptr<PromptFormatter>
- rng_ : std::mt19937
+ GenerateBrewery(...) : BreweryResult
+ GenerateBeer(...) : BeerResult
+ GenerateUser(...) : UserResult
+ GenerateCheckin(...) : CheckinResult
+ GenerateRating(...) : RatingResult
- Load(opts : const GeneratorOptions&) : void
- Infer(system_prompt, user_prompt,\n max_tokens, grammar) : std::string
- ValidateModelArchitecture() : void
}
interface PromptFormatter <<interface>> {
+ Format(system_prompt : std::string_view,\n user_prompt : std::string_view) : std::string
+ ExpectedArchitecture() : std::string_view
}
class Gemma4JinjaPromptFormatter {
+ Format(...) : std::string
+ ExpectedArchitecture() : std::string_view
}
}
package "Data Export" {
interface ExportService <<interface>> {
+ Initialize() : void
+ ProcessBrewery(brewery : const GeneratedBrewery&) : sqlite3_int64
+ ProcessBeer(beer : const GeneratedBeer&) : sqlite3_int64
+ ProcessUser(user : const GeneratedUser&) : sqlite3_int64
+ ProcessCheckin(checkin : const GeneratedCheckin&) : sqlite3_int64
+ ProcessRating(rating : const GeneratedRating&) : void
+ Finalize() : void
}
class SqliteExportService {
- date_time_provider_ : std::unique_ptr<DateTimeProvider>
- db_handle_ : SqliteDatabaseHandle
- insert_location_stmt_ : SqliteStatementHandle
- insert_brewery_stmt_ : SqliteStatementHandle
- insert_beer_stmt_ : SqliteStatementHandle
- insert_user_stmt_ : SqliteStatementHandle
- insert_checkin_stmt_ : SqliteStatementHandle
- insert_rating_stmt_ : SqliteStatementHandle
- transaction_open_ : bool
- location_cache_ : std::unordered_map<std::string, sqlite3_int64>
- brewery_cache_ : std::unordered_map<std::string, sqlite3_int64>
+ Initialize() : void
+ ProcessBrewery(brewery : const GeneratedBrewery&) : sqlite3_int64
+ ProcessBeer(beer : const GeneratedBeer&) : sqlite3_int64
+ ProcessUser(user : const GeneratedUser&) : sqlite3_int64
+ ProcessCheckin(checkin : const GeneratedCheckin&) : sqlite3_int64
+ ProcessRating(rating : const GeneratedRating&) : void
+ Finalize() : void
- InitializeSchema() : void
- PrepareStatements() : void
- RollbackAndCloseNoThrow() : void
- FinalizeStatements() : void
}
interface DateTimeProvider <<interface>> {
+ GetUtcTimestamp() : std::string
}
class SystemDateTimeProvider {
+ GetUtcTimestamp() : std::string
}
}
}
' ==========================================
' GLOBAL RELATIONSHIPS
' ==========================================
' --- Orchestration Aggregations (Services & Strategies) ---
BiergartenPipelineOrchestrator *-- DataPreloader
BiergartenPipelineOrchestrator *-- EnrichmentService