mirror of
https://github.com/aaronpo97/the-biergarten-app.git
synced 2026-07-16 17:47:22 +00:00
Compare commits
64 Commits
main-2.0
...
ee917d0f1b
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
ee917d0f1b | ||
|
|
13785f67e7 | ||
|
|
9a2ecfea82 | ||
|
|
385dcd2095 | ||
|
|
2fd2a35233 | ||
|
|
1b242e86b5 | ||
|
|
8a6cbe5efd | ||
|
|
056fb47b93 | ||
|
|
88527f7709 | ||
|
|
49f4ed6787 | ||
|
|
4d4b897d02 | ||
|
|
f71e4ddc83 | ||
|
|
212077793e | ||
|
|
e6d1954506 | ||
|
|
ce56532728 | ||
|
|
9649c993e8 | ||
|
|
f782fdb51d | ||
|
|
fcc7a5dc8b | ||
|
|
44a74ed2ad | ||
|
|
6682b5de01 | ||
|
|
62dfb5e14a | ||
|
|
ddf4bcb981 | ||
|
|
15853c62fd | ||
|
|
ff4b7f2578 | ||
|
|
3c70c46957 | ||
|
|
c7abc808ea | ||
|
|
ef4f47d415 | ||
|
|
035b30abba | ||
|
|
1cd30488eb | ||
|
|
823599a96f | ||
|
|
56ec728ba7 | ||
|
|
7ca651a886 | ||
|
|
b53f9e5582 | ||
|
|
824f5b2b4f | ||
|
|
5d93d76e99 | ||
|
|
028786b8b5 | ||
|
|
d7a31b5264 | ||
|
|
b31be494d7 | ||
|
|
7807f0bc2a | ||
|
|
772ef0cdfb | ||
|
|
a6e2ea21d0 | ||
|
|
a7cbf7507f | ||
|
|
3c7e74e3c1 | ||
|
|
b1ac3a6068 | ||
|
|
06d329cac5 | ||
|
|
54c403526b | ||
|
|
b8e96a6d45 | ||
|
|
60ee2ecf74 | ||
|
|
e4e16a5084 | ||
|
|
8d306bf691 | ||
|
|
077f6ab4ae | ||
|
|
534403734a | ||
|
|
3af053f0eb | ||
|
|
ba165d8aa7 | ||
|
|
eb9a2767b4 | ||
|
|
29ea47fdb6 | ||
|
|
52e2333304 | ||
|
|
a1f0ca5b20 | ||
|
|
2ea8aa52b4 | ||
|
|
98083ab40c | ||
|
|
ac136f7179 | ||
|
|
280c9c61bd | ||
|
|
248a51b35f | ||
|
|
35aa7bc0df |
13
.config/dotnet-tools.json
Normal file
13
.config/dotnet-tools.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"version": 1,
|
||||
"isRoot": true,
|
||||
"tools": {
|
||||
"csharpier": {
|
||||
"version": "1.2.1",
|
||||
"commands": [
|
||||
"csharpier"
|
||||
],
|
||||
"rollForward": false
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1,5 +1,7 @@
|
||||
{
|
||||
"printWidth": 100,
|
||||
"$schema": "https://json.schemastore.org/csharpier.json",
|
||||
|
||||
"printWidth": 80,
|
||||
"useTabs": false,
|
||||
"indentSize": 4,
|
||||
"endOfLine": "lf",
|
||||
@@ -49,10 +49,8 @@ CONFIRMATION_TOKEN_SECRET=your-secure-jwt-confirmation-secret-key
|
||||
# provider (e.g., SendGrid, Mailgun, Amazon SES).
|
||||
SMTP_HOST=mailpit
|
||||
SMTP_PORT=1025
|
||||
SMTP_USERNAME=ayerble
|
||||
SMTP_PASSWORD=checkers
|
||||
SMTP_USERNAME=
|
||||
SMTP_PASSWORD=
|
||||
SMTP_USE_SSL=false
|
||||
SMTP_FROM_EMAIL=noreply@thebiergarten.app
|
||||
SMTP_FROM_NAME=The Biergarten App
|
||||
|
||||
WEBSITE_BASE_URL=http://localhost:3000
|
||||
1
.gitattributes
vendored
1
.gitattributes
vendored
@@ -1 +0,0 @@
|
||||
archive/** linguist-vendored
|
||||
20
.github/ISSUE_TEMPLATE/feature_request.md
vendored
20
.github/ISSUE_TEMPLATE/feature_request.md
vendored
@@ -7,7 +7,6 @@ assignees: []
|
||||
---
|
||||
|
||||
## User Story
|
||||
|
||||
**As a** (who wants to accomplish something)
|
||||
**I want to** (what they want to accomplish)
|
||||
**So that** (why they want to accomplish that thing)
|
||||
@@ -16,18 +15,29 @@ assignees: []
|
||||
|
||||
### Scenario 1
|
||||
|
||||
Given ... When ... Then ...
|
||||
|
||||
Given ...
|
||||
When ...
|
||||
Then ...
|
||||
|
||||
|
||||
### Scenario 2
|
||||
|
||||
Given ... When ... Then ...
|
||||
|
||||
Given ...
|
||||
When ...
|
||||
Then ...
|
||||
|
||||
|
||||
### Scenario 3
|
||||
|
||||
Given ... When ... Then ...
|
||||
|
||||
Given ...
|
||||
When ...
|
||||
Then ...
|
||||
|
||||
|
||||
## Subtasks
|
||||
|
||||
- [ ] Task 1
|
||||
- [ ] Task 2
|
||||
- [ ] Task 3
|
||||
962
LICENSE.md
962
LICENSE.md
File diff suppressed because it is too large
Load Diff
162
README.md
162
README.md
@@ -1,56 +1,40 @@
|
||||
# The Biergarten App
|
||||
|
||||
The Biergarten App is a full-stack directory and discovery platform for
|
||||
breweries. It features a robust user authentication system, a searchable
|
||||
database of brewery locations, and a custom offline data-generation pipeline
|
||||
that uses LLMs (Llama.cpp) and Wikipedia to synthesize realistic seed data.
|
||||
The Biergarten App is a multi-project monorepo with a .NET backend and an active React
|
||||
Router frontend in `src/Website`. The current website focuses on account flows, theme
|
||||
switching, shared UI components, Storybook coverage, and integration with the API.
|
||||
|
||||
It features:
|
||||
## Documentation
|
||||
|
||||
- A .NET backend (Web API + database migrations/seed) under `web/backend/`
|
||||
- A server-rendered React website (React Router + Vite) under `web/frontend/`
|
||||
- A C++20 “pipeline” CLI for generating seed data under `tooling/pipeline/`
|
||||
|
||||
Specialized documentation (setup, architecture, docker, testing, diagrams, and
|
||||
pipeline notes) lives under `docs/`.
|
||||
|
||||
## Documentation (Start Here)
|
||||
|
||||
Website + backend (active stack):
|
||||
|
||||
- [Getting Started](docs/website/getting-started.md)
|
||||
- [Architecture](docs/architecture.md)
|
||||
- [Docker Guide](docs/website/docker.md)
|
||||
- [Testing](docs/website/testing.md)
|
||||
- [Environment Variables](docs/website/environment-variables.md)
|
||||
- [Token Validation](docs/website/token-validation.md)
|
||||
|
||||
Data generation pipeline (C++):
|
||||
|
||||
- [Pipeline README](docs/pipeline/README.md)
|
||||
- [Ethics & Known Issues](docs/pipeline/ETHICS-AND-KNOWN-ISSUES.md)
|
||||
- [Getting Started](docs/getting-started.md) - Local setup for backend and active website
|
||||
- [Architecture](docs/architecture.md) - Current backend and frontend architecture
|
||||
- [Docker Guide](docs/docker.md) - Container-based backend development and testing
|
||||
- [Testing](docs/testing.md) - Backend and frontend test commands
|
||||
- [Environment Variables](docs/environment-variables.md) - Active configuration reference
|
||||
- [Token Validation](docs/token-validation.md) - JWT validation architecture
|
||||
- [Legacy Website Archive](docs/archive/legacy-website-v1.md) - Archived notes for the old Next.js frontend
|
||||
|
||||
## Diagrams
|
||||
|
||||
- [Architecture](docs/website/diagrams-out/architecture.svg)
|
||||
- [Deployment](docs/website/diagrams-out/deployment.svg)
|
||||
- [Authentication Flow](docs/website/diagrams-out/authentication-flow.svg)
|
||||
- [Database Schema](docs/website/diagrams-out/database-schema.svg)
|
||||
- [Architecture](docs/diagrams-out/architecture.svg) - Layered architecture
|
||||
- [Deployment](docs/diagrams-out/deployment.svg) - Docker topology
|
||||
- [Authentication Flow](docs/diagrams-out/authentication-flow.svg) - Auth sequence
|
||||
- [Database Schema](docs/diagrams-out/database-schema.svg) - Entity relationships
|
||||
|
||||
## Current Status
|
||||
|
||||
Active areas in the repository:
|
||||
|
||||
- .NET 10 backend (vertical-slice architecture with MediatR) + SQL Server
|
||||
- React 19 website (React Router 7 + Vite)
|
||||
- Shared Biergarten theme system + Storybook coverage
|
||||
- Auth flows and account/email integration (local Mailpit in dev compose)
|
||||
- Data generation pipeline with C++ and Llama.cpp
|
||||
- .NET 10 backend with layered architecture and SQL Server
|
||||
- React Router 7 website in `src/Website`
|
||||
- Shared Biergarten theme system with a theme guide route
|
||||
- Storybook stories and browser-based checks for shared UI
|
||||
- Auth demo flows for home, login, register, dashboard, logout, and confirmation
|
||||
- Toast-based feedback for auth outcomes
|
||||
|
||||
Archived/reference areas:
|
||||
Legacy area retained for reference:
|
||||
|
||||
- `archive/next-js-web-app/` contains an older Next.js frontend retained for
|
||||
reference
|
||||
- `src/Website-v1` contains the archived Next.js frontend and is no longer the active website
|
||||
|
||||
## Tech Stack
|
||||
|
||||
@@ -59,43 +43,36 @@ Archived/reference areas:
|
||||
- **UI Documentation**: Storybook 10, Vitest browser mode, Playwright
|
||||
- **Testing**: xUnit, Reqnroll (BDD), FluentAssertions, Moq
|
||||
- **Infrastructure**: Docker, Docker Compose
|
||||
- **Security**: Argon2id password hashing, JWT access/refresh/confirmation
|
||||
tokens
|
||||
- **Data Pipeline**: C++20, CMake, Boost, libcurl, SQLite, llama.cpp
|
||||
- **Security**: Argon2id password hashing, JWT access/refresh/confirmation tokens
|
||||
|
||||
## Quick Start
|
||||
|
||||
For full setup details, use [Getting Started](docs/website/getting-started.md).
|
||||
This section is the shortest path to a working dev environment.
|
||||
|
||||
### Backend (Docker)
|
||||
### Backend
|
||||
|
||||
```bash
|
||||
git clone https://github.com/aaronpo97/the-biergarten-app
|
||||
cd the-biergarten-app
|
||||
|
||||
cp web/.env.example web/.env.dev
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml up --build -d
|
||||
cp .env.example .env.dev
|
||||
docker compose -f docker-compose.dev.yaml up -d
|
||||
```
|
||||
|
||||
Backend access:
|
||||
|
||||
- API Swagger: http://localhost:8080/swagger
|
||||
- Health Check: http://localhost:8080/health
|
||||
- Mailpit UI (dev SMTP): http://localhost:8025
|
||||
|
||||
### Frontend (Node)
|
||||
### Frontend
|
||||
|
||||
```bash
|
||||
cd web/frontend
|
||||
cd src/Website
|
||||
npm install
|
||||
API_BASE_URL=http://localhost:8080 SESSION_SECRET=dev-secret-change-me npm run dev
|
||||
API_BASE_URL=http://localhost:8080 SESSION_SECRET=dev-secret npm run dev
|
||||
```
|
||||
|
||||
Optional frontend tools:
|
||||
|
||||
```bash
|
||||
cd web/frontend
|
||||
cd src/Website
|
||||
npm run storybook
|
||||
npm run test:storybook
|
||||
npm run test:storybook:playwright
|
||||
@@ -104,43 +81,62 @@ npm run test:storybook:playwright
|
||||
## Repository Structure
|
||||
|
||||
```text
|
||||
web/
|
||||
backend/ .NET API: API.Core (host), Features.* (vertical slices),
|
||||
Shared.*, Domain.*, Infrastructure.*, Database.* projects
|
||||
frontend/ React Router website + Storybook + Playwright/Vitest
|
||||
|
||||
tooling/
|
||||
pipeline/ C++20 seed-data generation CLI (CMake)
|
||||
|
||||
docs/
|
||||
architecture.md High-level architecture overview
|
||||
website/ Backend/frontend setup, docker, testing, diagrams
|
||||
pipeline/ Pipeline docs, ethics notes, PlantUML diagrams
|
||||
|
||||
archive/
|
||||
next-js-web-app/ Older Next.js frontend (reference only)
|
||||
src/Core/ Backend projects (.NET)
|
||||
src/Website/ Active React Router frontend
|
||||
src/Website-v1/ Archived legacy Next.js frontend
|
||||
docs/ Active project documentation
|
||||
docs/archive/ Archived legacy documentation
|
||||
```
|
||||
|
||||
## Key Features
|
||||
|
||||
Implemented today:
|
||||
|
||||
- User registration and login against the API
|
||||
- JWT-based auth with access, refresh, and confirmation flows
|
||||
- SQL Server migrations and seed projects
|
||||
- Shared form components and auth screens
|
||||
- Theme switching with Lager, Stout, Cassis, and Weizen variants
|
||||
- Storybook documentation and automated story interaction tests
|
||||
- Toast feedback for auth-related outcomes
|
||||
|
||||
Planned next:
|
||||
|
||||
- Brewery discovery and management
|
||||
- Beer reviews and ratings
|
||||
- Social follow relationships
|
||||
- Geospatial brewery experiences
|
||||
- Additional frontend routes beyond the auth demo
|
||||
|
||||
## Testing
|
||||
|
||||
Run the backend test stack with Docker:
|
||||
Backend suites:
|
||||
|
||||
- `API.Specs` - integration tests
|
||||
- `Infrastructure.Repository.Tests` - repository unit tests
|
||||
- `Service.Auth.Tests` - service unit tests
|
||||
|
||||
Frontend suites:
|
||||
|
||||
- Storybook interaction tests via Vitest
|
||||
- Storybook browser regression checks via Playwright
|
||||
|
||||
Run all backend tests with Docker:
|
||||
|
||||
```bash
|
||||
docker compose --env-file web/.env.test -f web/docker-compose.test.yaml up --abort-on-container-exit
|
||||
docker compose -f docker-compose.test.yaml up --abort-on-container-exit
|
||||
```
|
||||
|
||||
See [Testing](docs/website/testing.md) for the full command list.
|
||||
See [Testing](docs/testing.md) for the full command list.
|
||||
|
||||
## Configuration
|
||||
|
||||
Common active variables:
|
||||
|
||||
- Backend/Docker: `DB_SERVER`, `DB_NAME`, `DB_USER`, `DB_PASSWORD`,
|
||||
`ACCESS_TOKEN_SECRET`, `REFRESH_TOKEN_SECRET`, `CONFIRMATION_TOKEN_SECRET`,
|
||||
`WEBSITE_BASE_URL`
|
||||
- Frontend runtime: `API_BASE_URL`, `SESSION_SECRET`, `NODE_ENV`
|
||||
- Backend: `DB_SERVER`, `DB_NAME`, `DB_USER`, `DB_PASSWORD`, `ACCESS_TOKEN_SECRET`, `REFRESH_TOKEN_SECRET`, `CONFIRMATION_TOKEN_SECRET`
|
||||
- Frontend: `API_BASE_URL`, `SESSION_SECRET`, `NODE_ENV`
|
||||
|
||||
See [Environment Variables](docs/website/environment-variables.md) for details.
|
||||
See [Environment Variables](docs/environment-variables.md) for details.
|
||||
|
||||
## Contributing
|
||||
|
||||
@@ -149,3 +145,15 @@ See [Environment Variables](docs/website/environment-variables.md) for details.
|
||||
3. Commit your changes (`git commit -m 'Add amazing feature'`)
|
||||
4. Push to the branch (`git push origin feature/amazing-feature`)
|
||||
5. Open a Pull Request
|
||||
|
||||
### Development Workflow
|
||||
|
||||
1. Start development environment: `docker compose -f docker-compose.dev.yaml up -d`
|
||||
2. Make changes to code
|
||||
3. Run tests: `docker compose -f docker-compose.test.yaml up --abort-on-container-exit`
|
||||
4. Rebuild if needed: `docker compose -f docker-compose.dev.yaml up -d --build api.core`
|
||||
|
||||
## Support
|
||||
|
||||
- **Documentation**: [docs/](docs/)
|
||||
- **Architecture**: See [Architecture Guide](docs/architecture.md)
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
services:
|
||||
sqlserver:
|
||||
sqlserver:
|
||||
env_file: ".env.dev"
|
||||
image: mcr.microsoft.com/mssql/server:2022-latest
|
||||
platform: linux/amd64
|
||||
@@ -13,18 +13,14 @@ services:
|
||||
volumes:
|
||||
- sqlserverdata-dev:/var/opt/mssql
|
||||
healthcheck:
|
||||
test:
|
||||
[
|
||||
"CMD-SHELL",
|
||||
"/opt/mssql-tools18/bin/sqlcmd -S localhost -U sa -P '${DB_PASSWORD}' -C -Q 'SELECT 1' || exit 1",
|
||||
]
|
||||
test: ["CMD-SHELL", "/opt/mssql-tools18/bin/sqlcmd -S localhost -U sa -P '${DB_PASSWORD}' -C -Q 'SELECT 1' || exit 1"]
|
||||
interval: 10s
|
||||
timeout: 5s
|
||||
retries: 12
|
||||
start_period: 30s
|
||||
networks:
|
||||
- devnet
|
||||
database.migrations:
|
||||
database.migrations:
|
||||
env_file: ".env.dev"
|
||||
image: database.migrations
|
||||
container_name: dev-env-database-migrations
|
||||
@@ -32,7 +28,7 @@ services:
|
||||
sqlserver:
|
||||
condition: service_healthy
|
||||
build:
|
||||
context: ./backend/Database
|
||||
context: ./src/Core/Database
|
||||
dockerfile: Database.Migrations/Dockerfile
|
||||
args:
|
||||
BUILD_CONFIGURATION: Release
|
||||
@@ -48,7 +44,7 @@ services:
|
||||
networks:
|
||||
- devnet
|
||||
|
||||
database.seed:
|
||||
database.seed:
|
||||
env_file: ".env.dev"
|
||||
image: database.seed
|
||||
container_name: dev-env-database-seed
|
||||
@@ -56,7 +52,7 @@ services:
|
||||
database.migrations:
|
||||
condition: service_completed_successfully
|
||||
build:
|
||||
context: ./backend
|
||||
context: ./src/Core
|
||||
dockerfile: Database/Database.Seed/Dockerfile
|
||||
args:
|
||||
BUILD_CONFIGURATION: Release
|
||||
@@ -13,11 +13,7 @@ services:
|
||||
volumes:
|
||||
- sqlserverdata-dev:/var/opt/mssql
|
||||
healthcheck:
|
||||
test:
|
||||
[
|
||||
"CMD-SHELL",
|
||||
"/opt/mssql-tools18/bin/sqlcmd -S localhost -U sa -P '${DB_PASSWORD}' -C -Q 'SELECT 1' || exit 1",
|
||||
]
|
||||
test: [ "CMD-SHELL", "/opt/mssql-tools18/bin/sqlcmd -S localhost -U sa -P '${DB_PASSWORD}' -C -Q 'SELECT 1' || exit 1" ]
|
||||
interval: 10s
|
||||
timeout: 5s
|
||||
retries: 12
|
||||
@@ -32,7 +28,7 @@ services:
|
||||
sqlserver:
|
||||
condition: service_healthy
|
||||
build:
|
||||
context: ./backend/Database
|
||||
context: ./src/Core/Database
|
||||
dockerfile: Database.Migrations/Dockerfile
|
||||
args:
|
||||
BUILD_CONFIGURATION: Release
|
||||
@@ -56,7 +52,7 @@ services:
|
||||
database.migrations:
|
||||
condition: service_completed_successfully
|
||||
build:
|
||||
context: ./backend
|
||||
context: ./src/Core
|
||||
dockerfile: Database/Database.Seed/Dockerfile
|
||||
args:
|
||||
BUILD_CONFIGURATION: Release
|
||||
@@ -79,7 +75,7 @@ services:
|
||||
database.seed:
|
||||
condition: service_completed_successfully
|
||||
build:
|
||||
context: ./backend
|
||||
context: ./src/Core
|
||||
dockerfile: API/API.Core/Dockerfile
|
||||
args:
|
||||
BUILD_CONFIGURATION: Release
|
||||
@@ -13,11 +13,7 @@ services:
|
||||
volumes:
|
||||
- sqlserverdata-dev:/var/opt/mssql
|
||||
healthcheck:
|
||||
test:
|
||||
[
|
||||
"CMD-SHELL",
|
||||
"/opt/mssql-tools18/bin/sqlcmd -S localhost -U sa -P '${DB_PASSWORD}' -C -Q 'SELECT 1' || exit 1",
|
||||
]
|
||||
test: [ "CMD-SHELL", "/opt/mssql-tools18/bin/sqlcmd -S localhost -U sa -P '${DB_PASSWORD}' -C -Q 'SELECT 1' || exit 1" ]
|
||||
interval: 10s
|
||||
timeout: 5s
|
||||
retries: 12
|
||||
@@ -32,7 +28,7 @@ services:
|
||||
sqlserver:
|
||||
condition: service_healthy
|
||||
build:
|
||||
context: ./backend/Database
|
||||
context: ./src/Core/Database
|
||||
dockerfile: Database.Migrations/Dockerfile
|
||||
args:
|
||||
BUILD_CONFIGURATION: Release
|
||||
@@ -70,7 +66,7 @@ services:
|
||||
database.migrations:
|
||||
condition: service_completed_successfully
|
||||
build:
|
||||
context: ./backend
|
||||
context: ./src/Core
|
||||
dockerfile: Database/Database.Seed/Dockerfile
|
||||
args:
|
||||
BUILD_CONFIGURATION: Release
|
||||
@@ -11,11 +11,7 @@ services:
|
||||
volumes:
|
||||
- sqlserverdata-prod:/var/opt/mssql
|
||||
healthcheck:
|
||||
test:
|
||||
[
|
||||
"CMD-SHELL",
|
||||
"/opt/mssql-tools18/bin/sqlcmd -S localhost -U sa -P '${DB_PASSWORD}' -C -Q 'SELECT 1' || exit 1",
|
||||
]
|
||||
test: ["CMD-SHELL", "/opt/mssql-tools18/bin/sqlcmd -S localhost -U sa -P '${DB_PASSWORD}' -C -Q 'SELECT 1' || exit 1"]
|
||||
interval: 10s
|
||||
timeout: 5s
|
||||
retries: 12
|
||||
@@ -31,7 +27,7 @@ services:
|
||||
sqlserver:
|
||||
condition: service_healthy
|
||||
build:
|
||||
context: ./backend/Database
|
||||
context: ./src/Core/Database
|
||||
dockerfile: Database.Migrations/Dockerfile
|
||||
args:
|
||||
BUILD_CONFIGURATION: Release
|
||||
@@ -54,7 +50,7 @@ services:
|
||||
sqlserver:
|
||||
condition: service_healthy
|
||||
build:
|
||||
context: ./backend
|
||||
context: ./src/Core
|
||||
dockerfile: API/API.Core/Dockerfile
|
||||
args:
|
||||
BUILD_CONFIGURATION: Release
|
||||
@@ -12,11 +12,7 @@ services:
|
||||
volumes:
|
||||
- sqlserverdata-test:/var/opt/mssql
|
||||
healthcheck:
|
||||
test:
|
||||
[
|
||||
"CMD-SHELL",
|
||||
"/opt/mssql-tools18/bin/sqlcmd -S localhost -U sa -P '${DB_PASSWORD}' -C -Q 'SELECT 1' || exit 1",
|
||||
]
|
||||
test: [ "CMD-SHELL", "/opt/mssql-tools18/bin/sqlcmd -S localhost -U sa -P '${DB_PASSWORD}' -C -Q 'SELECT 1' || exit 1" ]
|
||||
interval: 10s
|
||||
timeout: 5s
|
||||
retries: 12
|
||||
@@ -32,7 +28,7 @@ services:
|
||||
sqlserver:
|
||||
condition: service_healthy
|
||||
build:
|
||||
context: ./backend/Database
|
||||
context: ./src/Core/Database
|
||||
dockerfile: Database.Migrations/Dockerfile
|
||||
args:
|
||||
BUILD_CONFIGURATION: Release
|
||||
@@ -56,7 +52,7 @@ services:
|
||||
database.migrations:
|
||||
condition: service_completed_successfully
|
||||
build:
|
||||
context: ./backend
|
||||
context: ./src/Core
|
||||
dockerfile: Database/Database.Seed/Dockerfile
|
||||
args:
|
||||
BUILD_CONFIGURATION: Release
|
||||
@@ -79,7 +75,7 @@ services:
|
||||
database.seed:
|
||||
condition: service_completed_successfully
|
||||
build:
|
||||
context: ./backend
|
||||
context: ./src/Core
|
||||
dockerfile: API/API.Specs/Dockerfile
|
||||
args:
|
||||
BUILD_CONFIGURATION: Release
|
||||
@@ -99,16 +95,36 @@ services:
|
||||
networks:
|
||||
- testnet
|
||||
|
||||
unit.tests:
|
||||
repository.tests:
|
||||
env_file: ".env.test"
|
||||
image: unit.tests
|
||||
container_name: test-env-unit-tests
|
||||
image: repository.tests
|
||||
container_name: test-env-repository-tests
|
||||
depends_on:
|
||||
database.seed:
|
||||
condition: service_completed_successfully
|
||||
build:
|
||||
context: ./backend
|
||||
dockerfile: Dockerfile.tests
|
||||
context: ./src/Core
|
||||
dockerfile: Infrastructure/Infrastructure.Repository.Tests/Dockerfile
|
||||
args:
|
||||
BUILD_CONFIGURATION: Release
|
||||
environment:
|
||||
DOTNET_RUNNING_IN_CONTAINER: "true"
|
||||
volumes:
|
||||
- ./test-results:/app/test-results
|
||||
restart: "no"
|
||||
networks:
|
||||
- testnet
|
||||
|
||||
service.auth.tests:
|
||||
env_file: ".env.test"
|
||||
image: service.auth.tests
|
||||
container_name: test-env-service-auth-tests
|
||||
depends_on:
|
||||
database.seed:
|
||||
condition: service_completed_successfully
|
||||
build:
|
||||
context: ./src/Core
|
||||
dockerfile: Service/Service.Auth.Tests/Dockerfile
|
||||
args:
|
||||
BUILD_CONFIGURATION: Release
|
||||
environment:
|
||||
@@ -4,68 +4,60 @@ This document describes the active architecture of The Biergarten App.
|
||||
|
||||
## High-Level Overview
|
||||
|
||||
The Biergarten App is a monorepo with a clear split between the backend and the
|
||||
active website:
|
||||
The Biergarten App is a monorepo with a clear split between the backend and the active
|
||||
website:
|
||||
|
||||
- **Backend**: .NET 10 Web API with SQL Server, organized as vertical feature
|
||||
slices with MediatR
|
||||
- **Frontend**: React 19 + React Router 7 website in `web/frontend`
|
||||
- **Architecture Style**: Vertical-slice backend plus server-rendered React
|
||||
frontend
|
||||
- **Backend**: .NET 10 Web API with SQL Server and a layered architecture
|
||||
- **Frontend**: React 19 + React Router 7 website in `src/Website`
|
||||
- **Architecture Style**: Layered backend plus server-rendered React frontend
|
||||
|
||||
The legacy Next.js frontend has been retained in `archive/next-js-web-app/`
|
||||
for reference only.
|
||||
The legacy Next.js frontend has been retained in `src/Website-v1` for reference only and is
|
||||
documented in [archive/legacy-website-v1.md](archive/legacy-website-v1.md).
|
||||
|
||||
## Diagrams
|
||||
|
||||
For visual representations, see:
|
||||
|
||||
- [architecture.svg](website/diagrams-out/architecture.svg) - Vertical-slice
|
||||
architecture diagram
|
||||
- [deployment.svg](website/diagrams-out/deployment.svg) - Docker deployment
|
||||
diagram
|
||||
- [authentication-flow.svg](website/diagrams-out/authentication-flow.svg) -
|
||||
Authentication workflow
|
||||
- [database-schema.svg](website/diagrams-out/database-schema.svg) - Database
|
||||
relationships
|
||||
- [architecture.svg](diagrams-out/architecture.svg) - Layered architecture diagram
|
||||
- [deployment.svg](diagrams-out/deployment.svg) - Docker deployment diagram
|
||||
- [authentication-flow.svg](diagrams-out/authentication-flow.svg) - Authentication workflow
|
||||
- [database-schema.svg](diagrams-out/database-schema.svg) - Database relationships
|
||||
|
||||
## Backend Architecture
|
||||
|
||||
### Vertical Slice Architecture Pattern
|
||||
### Layered Architecture Pattern
|
||||
|
||||
The backend organizes business capabilities as feature slices instead of
|
||||
technical layers. Each feature (`Features.Auth`, `Features.Breweries`,
|
||||
`Features.UserManagement`, `Features.Emails`) is a single project that owns
|
||||
its own controller, MediatR commands/queries/handlers, validators, and
|
||||
repository, end to end:
|
||||
The backend follows a strict layered architecture:
|
||||
|
||||
```
|
||||
┌───────────────────────────────────────────────────────────────────────┐
|
||||
│ API.Core (thin host) │
|
||||
│ - Program.cs wiring: MediatR + AddApplicationPart per slice │
|
||||
│ - Swagger/OpenAPI, JWT auth middleware, global exception filter │
|
||||
└───────────────────────────────────────────────────────────────────────┘
|
||||
↓ discovers controllers via AddApplicationPart
|
||||
┌───────────────┬───────────────┬───────────────────┬───────────────────┐
|
||||
│ Features.Auth │Features. │ Features. │ Features.Emails │
|
||||
│ │Breweries │ UserManagement │ (no controller, │
|
||||
│ Controller │ Controller │ Controller │ internal only) │
|
||||
│ Commands/ │ Commands/ │ Commands/ │ Commands/ │
|
||||
│ Queries + │ Queries + │ Queries + │ Handlers │
|
||||
│ Handlers │ Handlers │ Handlers │ │
|
||||
│ Repository │ Repository │ Repository │ EmailDispatcher │
|
||||
└───────────────┴───────────────┴───────────────────┴───────────────────┘
|
||||
↓ each slice depends only on shared/domain/infra, never on another slice
|
||||
┌─────────────────────────┬─────────────────────────┬────────────────────┐
|
||||
│ Shared.Contracts │ Shared.Application │ Domain.Entities / │
|
||||
│ (ResponseBody envelope) │ (ValidationBehavior, │ Domain.Exceptions │
|
||||
│ │ cross-slice email cmds) │ │
|
||||
└─────────────────────────┴─────────────────────────┴────────────────────┘
|
||||
↓
|
||||
┌─────────────────────────────────────────────────────────────────────────┐
|
||||
│ Infrastructure.Sql, Infrastructure.Jwt, Infrastructure.PasswordHashing, │
|
||||
│ Infrastructure.Email, Infrastructure.Email.Templates │
|
||||
└─────────────────────────────────────────────────────────────────────────┘
|
||||
┌─────────────────────────────────────┐
|
||||
│ API Layer (Controllers) │
|
||||
│ - HTTP Endpoints │
|
||||
│ - Request/Response mapping │
|
||||
│ - Swagger/OpenAPI │
|
||||
└─────────────────────────────────────┘
|
||||
↓
|
||||
┌─────────────────────────────────────┐
|
||||
│ Service Layer (Business Logic) │
|
||||
│ - Authentication logic │
|
||||
│ - User management │
|
||||
│ - Validation & orchestration │
|
||||
└─────────────────────────────────────┘
|
||||
↓
|
||||
┌─────────────────────────────────────┐
|
||||
│ Infrastructure Layer (Tools) │
|
||||
│ - JWT token generation │
|
||||
│ - Password hashing (Argon2id) │
|
||||
│ - Email services │
|
||||
│ - Repository implementations │
|
||||
└─────────────────────────────────────┘
|
||||
↓
|
||||
┌─────────────────────────────────────┐
|
||||
│ Domain Layer (Entities) │
|
||||
│ - UserAccount, UserCredential │
|
||||
│ - Pure POCO classes │
|
||||
│ - No external dependencies │
|
||||
└─────────────────────────────────────┘
|
||||
↓
|
||||
┌─────────────────────────────────────┐
|
||||
│ Database (SQL Server) │
|
||||
@@ -74,123 +66,75 @@ repository, end to end:
|
||||
└─────────────────────────────────────┘
|
||||
```
|
||||
|
||||
Slices never reference each other's project. The one cross-slice
|
||||
interaction (`Features.Auth` triggering a confirmation email handled by
|
||||
`Features.Emails`) goes through a MediatR command (`SendRegistrationEmailCommand`)
|
||||
whose contract lives in `Shared.Application`, so neither slice takes a
|
||||
project reference on the other.
|
||||
|
||||
### Layer Responsibilities
|
||||
|
||||
#### API Layer (`API.Core`)
|
||||
|
||||
**Purpose**: Thin ASP.NET Core host: no business logic, no controllers of
|
||||
its own
|
||||
**Purpose**: HTTP interface and request handling
|
||||
|
||||
**Components**:
|
||||
|
||||
- `Program.cs`: registers MediatR (scanning every `Features.*` assembly),
|
||||
FluentValidation, and uses `AddApplicationPart` so each slice's controllers
|
||||
are discovered by MVC
|
||||
- `GlobalException.cs`: global exception filter (host-level cross-cutting
|
||||
concern)
|
||||
- `Authentication/JwtAuthenticationHandler.cs`: JWT auth scheme middleware
|
||||
- Swagger/OpenAPI documentation, health check endpoints
|
||||
- Controllers (`AuthController`, `UserController`)
|
||||
- Middleware for error handling
|
||||
- Swagger/OpenAPI documentation
|
||||
- Health check endpoints
|
||||
|
||||
**Dependencies**:
|
||||
|
||||
- Every `Features.*` project (for controller/MediatR discovery)
|
||||
- `Shared.Contracts`, `Shared.Application`
|
||||
- `Infrastructure.Jwt` (for the auth middleware)
|
||||
- Service layer
|
||||
- ASP.NET Core framework
|
||||
|
||||
**Rules**:
|
||||
|
||||
- No controllers, no business logic, no feature-specific contracts
|
||||
- Exists purely to host and wire up the feature slices
|
||||
- No business logic
|
||||
- Only request/response transformation
|
||||
- Delegates all work to Service layer
|
||||
|
||||
#### Feature Slices (`Features.Auth`, `Features.Breweries`, `Features.UserManagement`, `Features.Emails`)
|
||||
#### Service Layer (`Service.Auth`, `Service.UserManagement`)
|
||||
|
||||
**Purpose**: Each slice is the complete vertical for one business capability
|
||||
|
||||
**Components** (per slice):
|
||||
|
||||
- `Controllers/`: HTTP endpoints, binding directly to Command/Query types
|
||||
as the request contract
|
||||
- `Commands/<Operation>/` and `Queries/<Operation>/`: one folder per
|
||||
operation, each containing the Command/Query record, its
|
||||
`IRequestHandler`, and (for commands) a FluentValidation validator
|
||||
- `Repository/`: the slice's own stored-procedure repository
|
||||
implementation
|
||||
- `Dtos/`: response shapes returned by query handlers (never the raw
|
||||
domain entity)
|
||||
- `DependencyInjection/`: an `AddFeaturesX()` extension method registering
|
||||
the slice's repository/services
|
||||
|
||||
`Features.Emails` has no `Controllers/` folder. It's invoked only via
|
||||
MediatR commands sent from other slices, never over HTTP.
|
||||
|
||||
**Dependencies**:
|
||||
|
||||
- `Domain.Entities`, `Domain.Exceptions`
|
||||
- `Infrastructure.Sql` (generic ADO.NET plumbing) plus whichever
|
||||
infrastructure project the slice needs (`Infrastructure.Jwt`/
|
||||
`Infrastructure.PasswordHashing` for Auth, `Infrastructure.Email`/
|
||||
`Infrastructure.Email.Templates` for Emails)
|
||||
- `Shared.Contracts`, `Shared.Application`
|
||||
- **Never** another `Features.*` project
|
||||
|
||||
**Rules**:
|
||||
|
||||
- All business logic for that feature lives in its command/query handlers
|
||||
- No direct controller-to-repository calls; everything flows through
|
||||
MediatR
|
||||
- Read endpoints return a dedicated `Dto`, never the domain entity directly
|
||||
|
||||
#### Shared Projects (`Shared.Contracts`, `Shared.Application`)
|
||||
|
||||
**Purpose**: The minimum cross-slice surface area required because every
|
||||
slice needs it, or because duplicating it four times would be worse than
|
||||
sharing it
|
||||
**Purpose**: Business logic and orchestration
|
||||
|
||||
**Components**:
|
||||
|
||||
- `Shared.Contracts`: `ResponseBody<T>`/`ResponseBody`, the API response
|
||||
envelope every controller returns
|
||||
- `Shared.Application`: `ValidationBehavior<TRequest,TResponse>` (the
|
||||
MediatR pipeline behavior that runs FluentValidation before a handler
|
||||
executes) and the cross-slice email commands
|
||||
(`SendRegistrationEmailCommand`, `SendResendConfirmationEmailCommand`)
|
||||
- Authentication services (login, registration)
|
||||
- User management services
|
||||
- Business rule validation
|
||||
- Transaction coordination
|
||||
|
||||
**Dependencies**:
|
||||
|
||||
- Infrastructure layer (repositories, JWT, password hashing)
|
||||
- Domain entities
|
||||
|
||||
**Rules**:
|
||||
|
||||
- Kept deliberately small: this is the exception to "no slice depends on
|
||||
another slice," not a general-purpose dumping ground
|
||||
- Contains all business logic
|
||||
- Coordinates multiple infrastructure components
|
||||
- No direct database access (uses repositories)
|
||||
- Returns domain models, not DTOs
|
||||
|
||||
#### Infrastructure Layer
|
||||
|
||||
**Purpose**: Technical capabilities and external integrations, shared by
|
||||
whichever slices need them
|
||||
**Purpose**: Technical capabilities and external integrations
|
||||
|
||||
**Components**:
|
||||
|
||||
- **Infrastructure.Sql**: generic ADO.NET connection/command plumbing
|
||||
(`ISqlConnectionFactory`, the abstract `Repository<T>` base class), not
|
||||
domain-specific; each slice's own `Repository/` folder builds on this
|
||||
- **Infrastructure.Repository**: Data access via stored procedures
|
||||
- **Infrastructure.Jwt**: JWT token generation and validation
|
||||
- **Infrastructure.PasswordHashing**: Argon2id password hashing
|
||||
- **Infrastructure.Email**: Email sending capabilities (SMTP/MailKit)
|
||||
- **Infrastructure.Email.Templates**: Email template rendering (Razor
|
||||
components)
|
||||
- **Infrastructure.Email**: Email sending capabilities
|
||||
- **Infrastructure.Email.Templates**: Email template rendering
|
||||
|
||||
**Dependencies**:
|
||||
|
||||
- Domain entities
|
||||
- External libraries (ADO.NET, JWT, Argon2, MailKit, etc.)
|
||||
- External libraries (ADO.NET, JWT, Argon2, etc.)
|
||||
|
||||
**Rules**:
|
||||
|
||||
- Implements technical concerns only, no business logic
|
||||
- Reusable across slices
|
||||
- Implements technical concerns
|
||||
- No business logic
|
||||
- Reusable across services
|
||||
|
||||
#### Domain Layer (`Domain.Entities`)
|
||||
|
||||
@@ -215,55 +159,21 @@ whichever slices need them
|
||||
|
||||
### Design Patterns
|
||||
|
||||
#### Vertical Slice + MediatR
|
||||
|
||||
**Purpose**: Organize code by feature instead of by technical layer, so
|
||||
everything needed to understand or change one capability lives in one
|
||||
project
|
||||
|
||||
**Implementation**:
|
||||
|
||||
- Each HTTP write operation is a `Command` (e.g. `CreateBreweryCommand` in
|
||||
`Features.Breweries/Commands/CreateBrewery/`); each read operation is a
|
||||
`Query` (e.g. `GetBreweryByIdQuery`)
|
||||
- Controllers bind directly to the Command/Query as the request body;
|
||||
there is no separate request DTO + mapping step for writes
|
||||
- A single shared `ValidationBehavior<TRequest,TResponse>`
|
||||
(`Shared.Application/Behaviors/`) runs FluentValidation validators in the
|
||||
MediatR pipeline before any handler executes
|
||||
- Query handlers map to a dedicated response `Dto`, so domain entities never
|
||||
leak over the wire
|
||||
|
||||
**Example**:
|
||||
|
||||
```csharp
|
||||
public record CreateBreweryCommand(Guid PostedById, string BreweryName, string Description, ...)
|
||||
: IRequest<BreweryDto>;
|
||||
|
||||
public class CreateBreweryHandler(IBreweryRepository repository) : IRequestHandler<CreateBreweryCommand, BreweryDto>
|
||||
{
|
||||
public async Task<BreweryDto> Handle(CreateBreweryCommand request, CancellationToken cancellationToken) { ... }
|
||||
}
|
||||
```
|
||||
|
||||
#### Repository Pattern
|
||||
|
||||
**Purpose**: Abstract database access behind interfaces
|
||||
|
||||
**Implementation**: each slice owns its own repository, scoped to that
|
||||
feature only:
|
||||
**Implementation**:
|
||||
|
||||
- `Features.Auth/Repository/IAuthRepository.cs`
|
||||
- `Features.Breweries/Repository/IBreweryRepository.cs`
|
||||
- `Features.UserManagement/Repository/IUserAccountRepository.cs`
|
||||
- `Infrastructure.Sql/DefaultSqlConnectionFactory.cs`: the generic
|
||||
connection factory every slice's repository builds on
|
||||
- `IAuthRepository` - Authentication queries
|
||||
- `IUserAccountRepository` - User account queries
|
||||
- `DefaultSqlConnectionFactory` - Connection management
|
||||
|
||||
**Benefits**:
|
||||
|
||||
- Testable (easy to mock)
|
||||
- SQL-first approach (stored procedures)
|
||||
- Each slice's data access logic is self-contained
|
||||
- Centralized data access logic
|
||||
|
||||
**Example**:
|
||||
|
||||
@@ -279,19 +189,17 @@ public interface IAuthRepository
|
||||
|
||||
**Purpose**: Loose coupling and testability
|
||||
|
||||
**Configuration**: `Program.cs` wires up MediatR/FluentValidation across
|
||||
every `Features.*` assembly; each slice exposes its own `AddFeaturesX()`
|
||||
extension method that registers its repository and slice-internal services
|
||||
**Configuration**: `Program.cs` registers all services
|
||||
|
||||
**Lifetimes**:
|
||||
|
||||
- Scoped: Repositories, slice-internal services (per request)
|
||||
- Singleton: `ISqlConnectionFactory`
|
||||
- Scoped: Repositories, Services (per request)
|
||||
- Singleton: Connection factories, JWT configuration
|
||||
- Transient: Utilities, helpers
|
||||
|
||||
#### SQL-First Approach
|
||||
|
||||
**Purpose**: Push complex logic into the database
|
||||
**Purpose**: Leverage database capabilities
|
||||
|
||||
**Strategy**:
|
||||
|
||||
@@ -308,13 +216,12 @@ extension method that registers its repository and slice-internal services
|
||||
|
||||
## Frontend Architecture
|
||||
|
||||
### Active Website (`web/frontend`)
|
||||
### Active Website (`src/Website`)
|
||||
|
||||
The current website is a React Router 7 application with server-side rendering
|
||||
enabled.
|
||||
The current website is a React Router 7 application with server-side rendering enabled.
|
||||
|
||||
```text
|
||||
web/frontend/
|
||||
src/Website/
|
||||
├── app/
|
||||
│ ├── components/ Shared UI such as Navbar, FormField, SubmitButton, ToastProvider
|
||||
│ ├── lib/ Auth helpers, schemas, and theme metadata
|
||||
@@ -337,22 +244,21 @@ web/frontend/
|
||||
|
||||
### Theme System
|
||||
|
||||
The active website uses semantic DaisyUI theme tokens backed by four Biergarten
|
||||
themes:
|
||||
The active website uses semantic DaisyUI theme tokens backed by four Biergarten themes:
|
||||
|
||||
- Biergarten Lager
|
||||
- Biergarten Stout
|
||||
- Biergarten Cassis
|
||||
- Biergarten Weizen
|
||||
|
||||
All component styling should prefer semantic tokens such as `primary`,
|
||||
`success`, `surface`, and `highlight` instead of hard-coded color values.
|
||||
All component styling should prefer semantic tokens such as `primary`, `success`,
|
||||
`surface`, and `highlight` instead of hard-coded color values.
|
||||
|
||||
### Legacy Frontend
|
||||
|
||||
The previous Next.js frontend has been archived at `archive/next-js-web-app/`
|
||||
for reference only. Active product and engineering documentation should point
|
||||
to `web/frontend`.
|
||||
The previous Next.js frontend has been archived at `src/Website-v1`. Active product and
|
||||
engineering documentation should point to `src/Website`, while legacy notes live in
|
||||
[archive/legacy-website-v1.md](archive/legacy-website-v1.md).
|
||||
|
||||
## Security Architecture
|
||||
|
||||
@@ -477,12 +383,12 @@ scripts/
|
||||
- Testing (`docker-compose.test.yaml`)
|
||||
- Production (`docker-compose.prod.yaml`)
|
||||
|
||||
For details, see [Docker Guide](website/docker.md).
|
||||
For details, see [Docker Guide](docker.md).
|
||||
|
||||
### Health Checks
|
||||
|
||||
**SQL Server**: Validates database connectivity **API**: Checks service health
|
||||
and dependencies
|
||||
**SQL Server**: Validates database connectivity **API**: Checks service health and
|
||||
dependencies
|
||||
|
||||
**Configuration**:
|
||||
|
||||
@@ -503,10 +409,11 @@ healthcheck:
|
||||
│ Integration │ ← API.Specs (Reqnroll)
|
||||
│ Tests │
|
||||
├──────────────┤
|
||||
│ Unit Tests │ ← Features.Auth.Tests, Features.Breweries.Tests,
|
||||
│ (per slice, │ Features.UserManagement.Tests, Features.Emails.Tests
|
||||
│ handlers + │ (commands/queries/handlers + that slice's own
|
||||
│ repository) │ repository, mocked with Moq/DbMocker)
|
||||
│ Unit Tests │ ← Service.Auth.Tests
|
||||
│ (Service) │ Repository.Tests
|
||||
├──────────────┤
|
||||
│ Unit Tests │
|
||||
│ (Repository) │
|
||||
└──────────────┘
|
||||
```
|
||||
|
||||
@@ -517,4 +424,4 @@ healthcheck:
|
||||
- Mock external dependencies
|
||||
- Test database for integration tests
|
||||
|
||||
For details, see [Testing Guide](website/testing.md).
|
||||
For details, see [Testing Guide](testing.md).
|
||||
|
||||
56
docs/archive/legacy-website-v1.md
Normal file
56
docs/archive/legacy-website-v1.md
Normal file
@@ -0,0 +1,56 @@
|
||||
# Legacy Website Archive (`src/Website-v1`)
|
||||
|
||||
This archive captures high-level notes about the previous Biergarten frontend so active
|
||||
project documentation can focus on the current website in `src/Website`.
|
||||
|
||||
## Status
|
||||
|
||||
- `src/Website-v1` is retained for historical reference only
|
||||
- It is not the active frontend used by current setup, docs, or testing guidance
|
||||
- New product and engineering work should target `src/Website`
|
||||
|
||||
## Legacy Stack Summary
|
||||
|
||||
The archived frontend used a different application model from the current website:
|
||||
|
||||
- Next.js 14
|
||||
- React 18
|
||||
- Prisma
|
||||
- Postgres / Neon-hosted database workflows
|
||||
- Next.js API routes and server-side controllers
|
||||
- Additional third-party integrations such as Cloudinary, Mapbox, and SparkPost
|
||||
|
||||
## Why It Was Archived
|
||||
|
||||
The active website moved to a React Router-based frontend that talks directly to the .NET
|
||||
API. As part of that shift, the main docs were updated to describe:
|
||||
|
||||
- `src/Website` as the active frontend
|
||||
- React Router route modules and server rendering
|
||||
- Storybook-based component documentation and tests
|
||||
- Current frontend runtime variables: `API_BASE_URL`, `SESSION_SECRET`, and `NODE_ENV`
|
||||
|
||||
## Legacy Documentation Topics Moved Out of Active Docs
|
||||
|
||||
The following categories were removed from active documentation and intentionally archived:
|
||||
|
||||
- Next.js application structure guidance
|
||||
- Prisma and Postgres frontend setup
|
||||
- Legacy frontend environment variables
|
||||
- External service setup that only applied to `src/Website-v1`
|
||||
- Old frontend local setup instructions
|
||||
|
||||
## When To Use This Archive
|
||||
|
||||
Use this file only if you need to:
|
||||
|
||||
- inspect the historical frontend implementation
|
||||
- compare old flows against the current website
|
||||
- migrate or recover legacy logic from `src/Website-v1`
|
||||
|
||||
For all active work, use:
|
||||
|
||||
- [Getting Started](../getting-started.md)
|
||||
- [Architecture](../architecture.md)
|
||||
- [Environment Variables](../environment-variables.md)
|
||||
- [Testing](../testing.md)
|
||||
1
docs/diagrams-out/architecture.svg
Normal file
1
docs/diagrams-out/architecture.svg
Normal file
File diff suppressed because one or more lines are too long
75
docs/diagrams-src/architecture.puml
Normal file
75
docs/diagrams-src/architecture.puml
Normal file
@@ -0,0 +1,75 @@
|
||||
@startuml architecture
|
||||
!theme plain
|
||||
skinparam backgroundColor #FFFFFF
|
||||
skinparam defaultFontName Arial
|
||||
skinparam packageStyle rectangle
|
||||
|
||||
title The Biergarten App - Layered Architecture
|
||||
|
||||
package "API Layer" #E3F2FD {
|
||||
[API.Core\nASP.NET Core Web API] as API
|
||||
note right of API
|
||||
- Controllers (Auth, User)
|
||||
- Swagger/OpenAPI
|
||||
- Middleware
|
||||
- Health Checks
|
||||
end note
|
||||
}
|
||||
|
||||
package "Service Layer" #F3E5F5 {
|
||||
[Service.Auth] as AuthSvc
|
||||
[Service.UserManagement] as UserSvc
|
||||
note right of AuthSvc
|
||||
- Business Logic
|
||||
- Validation
|
||||
- Orchestration
|
||||
end note
|
||||
}
|
||||
|
||||
package "Infrastructure Layer" #FFF3E0 {
|
||||
[Infrastructure.Repository] as Repo
|
||||
[Infrastructure.Jwt] as JWT
|
||||
[Infrastructure.PasswordHashing] as PwdHash
|
||||
[Infrastructure.Email] as Email
|
||||
}
|
||||
|
||||
package "Domain Layer" #E8F5E9 {
|
||||
[Domain.Entities] as Domain
|
||||
note right of Domain
|
||||
- UserAccount
|
||||
- UserCredential
|
||||
- UserVerification
|
||||
end note
|
||||
}
|
||||
|
||||
database "SQL Server" {
|
||||
[Stored Procedures] as SP
|
||||
[Tables] as Tables
|
||||
}
|
||||
|
||||
' Relationships
|
||||
API --> AuthSvc
|
||||
API --> UserSvc
|
||||
|
||||
AuthSvc --> Repo
|
||||
AuthSvc --> JWT
|
||||
AuthSvc --> PwdHash
|
||||
AuthSvc --> Email
|
||||
|
||||
UserSvc --> Repo
|
||||
|
||||
Repo --> SP
|
||||
Repo --> Domain
|
||||
SP --> Tables
|
||||
|
||||
AuthSvc --> Domain
|
||||
UserSvc --> Domain
|
||||
|
||||
' Notes
|
||||
note left of Repo
|
||||
SQL-first approach
|
||||
All queries via
|
||||
stored procedures
|
||||
end note
|
||||
|
||||
@enduml
|
||||
@@ -112,32 +112,38 @@ package "Test Environment\n(docker-compose.test.yaml)" #FFF3E0 {
|
||||
end note
|
||||
}
|
||||
|
||||
node "unit.tests\n(Features.*.Tests, one container)" as UnitTests {
|
||||
component "xUnit + Moq + DbMocker" as UnitComp
|
||||
node "Infrastructure.Repository.Tests\n(Unit Tests)" as RepoTests {
|
||||
component "xUnit + DbMocker" as RepoComp
|
||||
note right
|
||||
Builds Dockerfile.tests, which
|
||||
restores/builds against Core.slnx
|
||||
then runs `dotnet test` for every
|
||||
Features/*.Tests project in turn:
|
||||
- Features.Auth.Tests
|
||||
- Features.Breweries.Tests
|
||||
- Features.UserManagement.Tests
|
||||
- Features.Emails.Tests
|
||||
Tests:
|
||||
- AuthRepository
|
||||
- UserAccountRepository
|
||||
- SQL command building
|
||||
|
||||
Uses: Moq for handlers,
|
||||
DbMocker for repositories
|
||||
Uses: Mock connections
|
||||
No real database needed
|
||||
end note
|
||||
}
|
||||
|
||||
node "Service.Auth.Tests\n(Unit Tests)" as SvcTests {
|
||||
component "xUnit + Moq" as SvcComp
|
||||
note right
|
||||
Tests:
|
||||
- RegisterService
|
||||
- LoginService
|
||||
- Token generation
|
||||
|
||||
Uses: Mocked dependencies
|
||||
No database or infrastructure
|
||||
end note
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
folder "test-results/\n(mounted volume)" as Results {
|
||||
file "api-specs/\n results.trx" as Result1
|
||||
file "Features.Auth.Tests.trx" as Result2
|
||||
file "Features.Breweries.Tests.trx" as Result3
|
||||
file "Features.UserManagement.Tests.trx" as Result4
|
||||
file "Features.Emails.Tests.trx" as Result5
|
||||
file "repository-tests/\n results.trx" as Result2
|
||||
file "service-auth-tests/\n results.trx" as Result3
|
||||
|
||||
note bottom
|
||||
TRX format
|
||||
@@ -164,16 +170,17 @@ DevAPI .up.> DevSeed : depends_on
|
||||
TestMig --> TestDB : 1. Migrate
|
||||
TestSeed --> TestDB : 2. Seed
|
||||
Specs --> TestDB : 3. Integration test
|
||||
UnitTests ..> TestDB : depends_on for startup\nordering only (Moq/DbMocker,\nno real connection)
|
||||
RepoTests ..> TestDB : Mock (no connection)
|
||||
SvcTests ..> TestDB : Mock (no connection)
|
||||
|
||||
TestMig .up.> TestDB : depends_on
|
||||
TestSeed .up.> TestMig : depends_on
|
||||
Specs .up.> TestSeed : depends_on
|
||||
UnitTests .up.> TestSeed : depends_on
|
||||
|
||||
' Test results export
|
||||
Specs --> Results : Export TRX
|
||||
UnitTests --> Results : Export TRX (one .trx per slice)
|
||||
RepoTests --> Results : Export TRX
|
||||
SvcTests --> Results : Export TRX
|
||||
|
||||
' Network notes
|
||||
note bottom of DevDB
|
||||
@@ -1,7 +1,7 @@
|
||||
# Docker Guide
|
||||
|
||||
This document covers Docker deployment, configuration, and troubleshooting for
|
||||
The Biergarten App.
|
||||
This document covers Docker deployment, configuration, and troubleshooting for The
|
||||
Biergarten App.
|
||||
|
||||
## Overview
|
||||
|
||||
@@ -13,8 +13,7 @@ The project uses Docker Compose to orchestrate multiple services:
|
||||
- .NET API
|
||||
- Test runners
|
||||
|
||||
See the [deployment diagram](diagrams-out/deployment.svg) for visual
|
||||
representation.
|
||||
See the [deployment diagram](diagrams/pdf/deployment.pdf) for visual representation.
|
||||
|
||||
## Docker Compose Environments
|
||||
|
||||
@@ -25,10 +24,9 @@ representation.
|
||||
**Features**:
|
||||
|
||||
- Persistent SQL Server volume
|
||||
- NuGet package cache volume (speeds up rebuilds)
|
||||
- Hot reload support
|
||||
- Swagger UI enabled
|
||||
- Seed data included
|
||||
- Local Mailpit SMTP server for dev email testing
|
||||
- `CLEAR_DATABASE=true` (drops and recreates schema)
|
||||
|
||||
**Services**:
|
||||
@@ -38,30 +36,28 @@ sqlserver # SQL Server 2022 (port 1433)
|
||||
database.migrations # DbUp migrations
|
||||
database.seed # Seed initial data
|
||||
api.core # Web API (ports 8080, 8081)
|
||||
mailpit # Local dev SMTP server + UI (port 8025)
|
||||
```
|
||||
|
||||
**Start Development Environment**:
|
||||
|
||||
```bash
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml up -d
|
||||
docker compose -f docker-compose.dev.yaml up -d
|
||||
```
|
||||
|
||||
**Access**:
|
||||
|
||||
- API Swagger: http://localhost:8080/swagger
|
||||
- Health Check: http://localhost:8080/health
|
||||
- Mailpit UI: http://localhost:8025
|
||||
- SQL Server: localhost:1433 (sa credentials from .env.dev)
|
||||
|
||||
**Stop Environment**:
|
||||
|
||||
```bash
|
||||
# Stop services (keep volumes)
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml down
|
||||
docker compose -f docker-compose.dev.yaml down
|
||||
|
||||
# Stop and remove volumes (fresh start)
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml down -v
|
||||
docker compose -f docker-compose.dev.yaml down -v
|
||||
```
|
||||
|
||||
### 2. Testing (`docker-compose.test.yaml`)
|
||||
@@ -83,22 +79,24 @@ sqlserver # Test database
|
||||
database.migrations # Fresh schema
|
||||
database.seed # Test data
|
||||
api.specs # Reqnroll BDD tests
|
||||
unit.tests # All Features.*.Tests unit test projects
|
||||
repository.tests # Repository unit tests
|
||||
service.auth.tests # Service unit tests
|
||||
```
|
||||
|
||||
**Run Tests**:
|
||||
|
||||
```bash
|
||||
# Run all tests
|
||||
docker compose --env-file web/.env.test -f web/docker-compose.test.yaml up --abort-on-container-exit
|
||||
docker compose -f docker-compose.test.yaml up --abort-on-container-exit
|
||||
|
||||
# View results
|
||||
ls -la test-results/
|
||||
cat test-results/api-specs/results.trx
|
||||
cat test-results/Features.Auth.Tests.trx
|
||||
cat test-results/repository-tests/results.trx
|
||||
cat test-results/service-auth-tests/results.trx
|
||||
|
||||
# Clean up
|
||||
docker compose --env-file web/.env.test -f web/docker-compose.test.yaml down -v
|
||||
docker compose -f docker-compose.test.yaml down -v
|
||||
```
|
||||
|
||||
### 3. Production (`docker-compose.prod.yaml`)
|
||||
@@ -125,7 +123,7 @@ api.core # Production API
|
||||
**Deploy Production**:
|
||||
|
||||
```bash
|
||||
docker compose --env-file web/.env.prod -f web/docker-compose.prod.yaml up -d
|
||||
docker compose -f docker-compose.prod.yaml up -d
|
||||
```
|
||||
|
||||
## Service Dependencies
|
||||
@@ -146,11 +144,7 @@ api.core / tests (start when ready)
|
||||
|
||||
```yaml
|
||||
healthcheck:
|
||||
test:
|
||||
[
|
||||
"CMD-SHELL",
|
||||
"sqlcmd -S localhost -U sa -P '${DB_PASSWORD}' -C -Q 'SELECT 1'",
|
||||
]
|
||||
test: ['CMD-SHELL', "sqlcmd -S localhost -U sa -P '${DB_PASSWORD}' -C -Q 'SELECT 1'"]
|
||||
interval: 10s
|
||||
timeout: 5s
|
||||
retries: 12
|
||||
@@ -195,6 +189,13 @@ volumes:
|
||||
|
||||
Test results are written to host filesystem for CI/CD integration.
|
||||
|
||||
**Code Volumes** (development only):
|
||||
|
||||
```yaml
|
||||
volumes:
|
||||
- ./src:/app/src # Hot reload for development
|
||||
```
|
||||
|
||||
## Networks
|
||||
|
||||
Each environment uses isolated bridge networks:
|
||||
@@ -208,18 +209,16 @@ Each environment uses isolated bridge networks:
|
||||
All containers are configured via environment variables from `.env` files:
|
||||
|
||||
```yaml
|
||||
env_file: ".env.dev" # or .env.test, .env.prod
|
||||
env_file: '.env.dev' # or .env.test, .env.prod
|
||||
|
||||
environment:
|
||||
ASPNETCORE_ENVIRONMENT: "Development"
|
||||
DOTNET_RUNNING_IN_CONTAINER: "true"
|
||||
DB_SERVER: "${DB_SERVER}"
|
||||
DB_NAME: "${DB_NAME}"
|
||||
DB_USER: "${DB_USER}"
|
||||
DB_PASSWORD: "${DB_PASSWORD}"
|
||||
ACCESS_TOKEN_SECRET: "${ACCESS_TOKEN_SECRET}"
|
||||
REFRESH_TOKEN_SECRET: "${REFRESH_TOKEN_SECRET}"
|
||||
CONFIRMATION_TOKEN_SECRET: "${CONFIRMATION_TOKEN_SECRET}"
|
||||
ASPNETCORE_ENVIRONMENT: 'Development'
|
||||
DOTNET_RUNNING_IN_CONTAINER: 'true'
|
||||
DB_SERVER: '${DB_SERVER}'
|
||||
DB_NAME: '${DB_NAME}'
|
||||
DB_USER: '${DB_USER}'
|
||||
DB_PASSWORD: '${DB_PASSWORD}'
|
||||
JWT_SECRET: '${JWT_SECRET}'
|
||||
```
|
||||
|
||||
For complete list, see [Environment Variables](environment-variables.md).
|
||||
@@ -230,7 +229,7 @@ For complete list, see [Environment Variables](environment-variables.md).
|
||||
|
||||
```bash
|
||||
# Running services
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml ps
|
||||
docker compose -f docker-compose.dev.yaml ps
|
||||
|
||||
# All containers (including stopped)
|
||||
docker ps -a
|
||||
@@ -240,13 +239,13 @@ docker ps -a
|
||||
|
||||
```bash
|
||||
# All services
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml logs -f
|
||||
docker compose -f docker-compose.dev.yaml logs -f
|
||||
|
||||
# Specific service
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml logs -f api.core
|
||||
docker compose -f docker-compose.dev.yaml logs -f api.core
|
||||
|
||||
# Last 100 lines
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml logs --tail=100 api.core
|
||||
docker compose -f docker-compose.dev.yaml logs --tail=100 api.core
|
||||
```
|
||||
|
||||
### Execute Commands in Container
|
||||
@@ -263,39 +262,39 @@ docker exec dev-env-sqlserver /opt/mssql-tools18/bin/sqlcmd -S localhost -U sa -
|
||||
|
||||
```bash
|
||||
# Restart all services
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml restart
|
||||
docker compose -f docker-compose.dev.yaml restart
|
||||
|
||||
# Restart specific service
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml restart api.core
|
||||
docker compose -f docker-compose.dev.yaml restart api.core
|
||||
|
||||
# Rebuild and restart
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml up -d --build api.core
|
||||
docker compose -f docker-compose.dev.yaml up -d --build api.core
|
||||
```
|
||||
|
||||
### Build Images
|
||||
|
||||
```bash
|
||||
# Build all images
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml build
|
||||
docker compose -f docker-compose.dev.yaml build
|
||||
|
||||
# Build specific service
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml build api.core
|
||||
docker compose -f docker-compose.dev.yaml build api.core
|
||||
|
||||
# Build without cache
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml build --no-cache
|
||||
docker compose -f docker-compose.dev.yaml build --no-cache
|
||||
```
|
||||
|
||||
### Clean Up
|
||||
|
||||
```bash
|
||||
# Stop and remove containers
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml down
|
||||
docker compose -f docker-compose.dev.yaml down
|
||||
|
||||
# Remove containers and volumes
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml down -v
|
||||
docker compose -f docker-compose.dev.yaml down -v
|
||||
|
||||
# Remove containers, volumes, and images
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml down -v --rmi all
|
||||
docker compose -f docker-compose.dev.yaml down -v --rmi all
|
||||
|
||||
# System-wide cleanup
|
||||
docker system prune -af --volumes
|
||||
@@ -1,7 +1,7 @@
|
||||
# Environment Variables
|
||||
|
||||
This document covers the active environment variables used by the current
|
||||
Biergarten stack.
|
||||
This document covers the active environment variables used by the current Biergarten
|
||||
stack.
|
||||
|
||||
## Overview
|
||||
|
||||
@@ -17,10 +17,10 @@ The application uses environment variables for:
|
||||
|
||||
Direct environment variable access via `Environment.GetEnvironmentVariable()`.
|
||||
|
||||
### Frontend (`web/frontend`)
|
||||
### Frontend (`src/Website`)
|
||||
|
||||
The active website reads runtime values from the server environment for its auth
|
||||
and API integration.
|
||||
The active website reads runtime values from the server environment for its auth and API
|
||||
integration.
|
||||
|
||||
### Docker
|
||||
|
||||
@@ -54,15 +54,14 @@ Provide complete connection string:
|
||||
DB_CONNECTION_STRING="Server=localhost,1433;Database=Biergarten;User Id=sa;Password=YourStrong!Passw0rd;TrustServerCertificate=True;"
|
||||
```
|
||||
|
||||
**Priority**: `DB_CONNECTION_STRING` is checked first. If not found, connection
|
||||
string is built from components.
|
||||
**Priority**: `DB_CONNECTION_STRING` is checked first. If not found, connection string is
|
||||
built from components.
|
||||
|
||||
**Implementation**: See `DefaultSqlConnectionFactory.cs`
|
||||
|
||||
### JWT Authentication Secrets (Backend)
|
||||
|
||||
The backend uses separate secrets for different token types to enable
|
||||
independent key rotation and validation isolation.
|
||||
The backend uses separate secrets for different token types to enable independent key rotation and validation isolation.
|
||||
|
||||
```bash
|
||||
# Access token secret (1-hour tokens)
|
||||
@@ -130,10 +129,10 @@ ASPNETCORE_URLS=http://0.0.0.0:8080 # Binding address and port
|
||||
DOTNET_RUNNING_IN_CONTAINER=true # Flag for container execution
|
||||
```
|
||||
|
||||
## Frontend Variables (`web/frontend`)
|
||||
## Frontend Variables (`src/Website`)
|
||||
|
||||
The active website does not use the old Next.js/Prisma environment model. Its
|
||||
core runtime variables are:
|
||||
The active website does not use the old Next.js/Prisma environment model. Its core runtime
|
||||
variables are:
|
||||
|
||||
```bash
|
||||
API_BASE_URL=http://localhost:8080 # Base URL for the .NET API
|
||||
@@ -147,7 +146,7 @@ NODE_ENV=development # Standard Node runtime mode
|
||||
|
||||
- **Required**: Yes for local development
|
||||
- **Default in code**: `http://localhost:8080`
|
||||
- **Used by**: `web/frontend/app/lib/auth.server.ts`
|
||||
- **Used by**: `src/Website/app/lib/auth.server.ts`
|
||||
- **Purpose**: Routes website auth actions to the .NET API
|
||||
|
||||
#### `SESSION_SECRET`
|
||||
@@ -163,27 +162,15 @@ NODE_ENV=development # Standard Node runtime mode
|
||||
- **Typical values**: `development`, `production`, `test`
|
||||
- **Purpose**: Controls secure cookie behavior and runtime mode
|
||||
|
||||
### SMTP Configuration (Backend)
|
||||
|
||||
Read by `Infrastructure.Email/SmtpEmailProvider.cs` for sending confirmation
|
||||
and account emails.
|
||||
### Admin Account (Seeding)
|
||||
|
||||
```bash
|
||||
SMTP_HOST=mailpit # Required, no default
|
||||
SMTP_PORT=1025 # Optional, defaults to 587
|
||||
SMTP_USERNAME=<username> # Optional, no default
|
||||
SMTP_PASSWORD=<password> # Optional, no default
|
||||
SMTP_USE_SSL=false # Optional, defaults to true
|
||||
SMTP_FROM_EMAIL=noreply@thebiergarten.app # Required, no default
|
||||
SMTP_FROM_NAME=The Biergarten App # Optional, defaults to "The Biergarten"
|
||||
ADMIN_PASSWORD=SecureAdminPassword123! # Initial admin password for seeding
|
||||
```
|
||||
|
||||
- **Implementation**: `Infrastructure.Email/SmtpEmailProvider.cs` throws on
|
||||
startup if `SMTP_HOST` or `SMTP_FROM_EMAIL` is missing
|
||||
- **Local dev**: point at the `mailpit` Docker service (SMTP on port 1025, web
|
||||
UI on http://localhost:8025)
|
||||
- **Production**: point at a real provider (SendGrid, Mailgun, Amazon SES,
|
||||
etc.)
|
||||
- **Required**: No (only needed for seeding)
|
||||
- **Purpose**: Sets admin account password during database seeding
|
||||
- **Security**: Use strong password, change immediately in production
|
||||
|
||||
## Docker-Specific Variables
|
||||
|
||||
@@ -203,33 +190,33 @@ MSSQL_PID=Express # SQL Server edition (Express, Developer, Ente
|
||||
|
||||
## Environment File Structure
|
||||
|
||||
### Backend/Docker (`web/` Directory)
|
||||
### Backend/Docker (Root Directory)
|
||||
|
||||
```
|
||||
web/.env.example # Template (tracked in Git)
|
||||
web/.env.dev # Development config (gitignored)
|
||||
web/.env.test # Testing config (gitignored)
|
||||
web/.env.prod # Production config (gitignored)
|
||||
.env.example # Template (tracked in Git)
|
||||
.env.dev # Development config (gitignored)
|
||||
.env.test # Testing config (gitignored)
|
||||
.env.prod # Production config (gitignored)
|
||||
```
|
||||
|
||||
**Setup**:
|
||||
|
||||
```bash
|
||||
cp web/.env.example web/.env.dev
|
||||
# Edit web/.env.dev with your values
|
||||
cp .env.example .env.dev
|
||||
# Edit .env.dev with your values
|
||||
```
|
||||
|
||||
## Legacy Frontend Variables
|
||||
|
||||
Variables for the archived Next.js frontend (`archive/next-js-web-app/`) have
|
||||
been removed from this active reference, since that app is retained for
|
||||
reference only and is not run as part of the active stack.
|
||||
Variables for the archived Next.js frontend (`src/Website-v1`) have been removed from this
|
||||
active reference. See [archive/legacy-website-v1.md](archive/legacy-website-v1.md) if you
|
||||
need the legacy Prisma, Cloudinary, Mapbox, or SparkPost notes.
|
||||
|
||||
**Docker Compose Mapping**:
|
||||
|
||||
- `web/docker-compose.dev.yaml` → `web/.env.dev`
|
||||
- `web/docker-compose.test.yaml` → `web/.env.test`
|
||||
- `web/docker-compose.prod.yaml` → `web/.env.prod`
|
||||
- `docker-compose.dev.yaml` → `.env.dev`
|
||||
- `docker-compose.test.yaml` → `.env.test`
|
||||
- `docker-compose.prod.yaml` → `.env.prod`
|
||||
|
||||
## Variable Reference Table
|
||||
|
||||
@@ -245,13 +232,6 @@ reference only and is not run as part of the active stack.
|
||||
| `REFRESH_TOKEN_SECRET` | ✓ | | ✓ | Yes | Refresh token signing |
|
||||
| `CONFIRMATION_TOKEN_SECRET` | ✓ | | ✓ | Yes | Confirmation token signing |
|
||||
| `WEBSITE_BASE_URL` | ✓ | | | Yes | Website URL for emails |
|
||||
| `SMTP_HOST` | ✓ | | ✓ | Yes | SMTP server host |
|
||||
| `SMTP_PORT` | ✓ | | ✓ | No | Defaults to `587` |
|
||||
| `SMTP_USERNAME` | ✓ | | ✓ | No | SMTP auth username |
|
||||
| `SMTP_PASSWORD` | ✓ | | ✓ | No | SMTP auth password |
|
||||
| `SMTP_USE_SSL` | ✓ | | ✓ | No | Defaults to `true` |
|
||||
| `SMTP_FROM_EMAIL` | ✓ | | ✓ | Yes | Email sender address |
|
||||
| `SMTP_FROM_NAME` | ✓ | | ✓ | No | Defaults to `The Biergarten` |
|
||||
| `API_BASE_URL` | | ✓ | | Yes | Website-to-API base URL |
|
||||
| `SESSION_SECRET` | | ✓ | | Yes | Website session signing |
|
||||
| `NODE_ENV` | | ✓ | | No | Runtime mode |
|
||||
@@ -263,8 +243,8 @@ reference only and is not run as part of the active stack.
|
||||
| `MSSQL_PID` | | | ✓ | No | SQL Server edition |
|
||||
| `DOTNET_RUNNING_IN_CONTAINER` | ✓ | | ✓ | No | Container flag |
|
||||
|
||||
\* Either `DB_CONNECTION_STRING` OR the component variables (`DB_SERVER`,
|
||||
`DB_NAME`, `DB_USER`, `DB_PASSWORD`) must be provided.
|
||||
\* Either `DB_CONNECTION_STRING` OR the component variables (`DB_SERVER`, `DB_NAME`,
|
||||
`DB_USER`, `DB_PASSWORD`) must be provided.
|
||||
|
||||
## Validation
|
||||
|
||||
@@ -272,17 +252,14 @@ reference only and is not run as part of the active stack.
|
||||
|
||||
Variables are validated at startup:
|
||||
|
||||
- Missing required variables (`ACCESS_TOKEN_SECRET`, `REFRESH_TOKEN_SECRET`,
|
||||
`CONFIRMATION_TOKEN_SECRET`, `SMTP_HOST`, `SMTP_FROM_EMAIL`, DB connection
|
||||
values) cause the application to fail with an `InvalidOperationException`
|
||||
- No minimum length is enforced on the token secrets in code; the
|
||||
"minimum 32 characters" guidance above is a recommendation, not an
|
||||
enforced check
|
||||
- Missing required variables cause application to fail
|
||||
- JWT_SECRET length is enforced (min 32 chars)
|
||||
- Connection string format is validated
|
||||
|
||||
### Frontend Validation
|
||||
|
||||
The active website relies on runtime defaults for local development and the
|
||||
surrounding server environment in deployed environments.
|
||||
The active website relies on runtime defaults for local development and the surrounding
|
||||
server environment in deployed environments.
|
||||
|
||||
- `API_BASE_URL` defaults to `http://localhost:8080`
|
||||
- `SESSION_SECRET` falls back to a development-only local secret
|
||||
@@ -305,13 +282,6 @@ REFRESH_TOKEN_SECRET=<generated-with-openssl>
|
||||
CONFIRMATION_TOKEN_SECRET=<generated-with-openssl>
|
||||
WEBSITE_BASE_URL=http://localhost:3000
|
||||
|
||||
# SMTP (Mailpit in dev)
|
||||
SMTP_HOST=mailpit
|
||||
SMTP_PORT=1025
|
||||
SMTP_USE_SSL=false
|
||||
SMTP_FROM_EMAIL=noreply@thebiergarten.app
|
||||
SMTP_FROM_NAME=The Biergarten App
|
||||
|
||||
# Migration
|
||||
CLEAR_DATABASE=true
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# Getting Started
|
||||
|
||||
This guide covers local setup for the current Biergarten stack: the .NET backend
|
||||
in `web/backend` and the active React Router frontend in `web/frontend`.
|
||||
This guide covers local setup for the current Biergarten stack: the .NET backend in
|
||||
`src/Core` and the active React Router frontend in `src/Website`.
|
||||
|
||||
## Prerequisites
|
||||
|
||||
@@ -22,7 +22,7 @@ cd the-biergarten-app
|
||||
### 2. Configure Backend Environment Variables
|
||||
|
||||
```bash
|
||||
cp web/.env.example web/.env.dev
|
||||
cp .env.example .env.dev
|
||||
```
|
||||
|
||||
At minimum, ensure `.env.dev` includes valid database and token values:
|
||||
@@ -43,21 +43,20 @@ See [Environment Variables](environment-variables.md) for the full list.
|
||||
### 3. Start the Backend Stack
|
||||
|
||||
```bash
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml up -d
|
||||
docker compose -f docker-compose.dev.yaml up -d
|
||||
```
|
||||
|
||||
This starts SQL Server, migrations, seeding, the API, and Mailpit (local dev SMTP).
|
||||
This starts SQL Server, migrations, seeding, and the API.
|
||||
|
||||
Available endpoints:
|
||||
|
||||
- API Swagger: http://localhost:8080/swagger
|
||||
- Health Check: http://localhost:8080/health
|
||||
- Mailpit UI: http://localhost:8025
|
||||
|
||||
### 4. Start the Active Frontend
|
||||
|
||||
```bash
|
||||
cd web/frontend
|
||||
cd src/Website
|
||||
npm install
|
||||
API_BASE_URL=http://localhost:8080 SESSION_SECRET=dev-secret-change-me npm run dev
|
||||
```
|
||||
@@ -72,7 +71,7 @@ Required frontend runtime variables for local work:
|
||||
### 5. Optional: Run Storybook
|
||||
|
||||
```bash
|
||||
cd web/frontend
|
||||
cd src/Website
|
||||
npm run storybook
|
||||
```
|
||||
|
||||
@@ -83,15 +82,15 @@ Storybook runs at http://localhost:6006 by default.
|
||||
### Backend
|
||||
|
||||
```bash
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml logs -f
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml down
|
||||
docker compose --env-file web/.env.dev -f web/docker-compose.dev.yaml down -v
|
||||
docker compose -f docker-compose.dev.yaml logs -f
|
||||
docker compose -f docker-compose.dev.yaml down
|
||||
docker compose -f docker-compose.dev.yaml down -v
|
||||
```
|
||||
|
||||
### Frontend
|
||||
|
||||
```bash
|
||||
cd web/frontend
|
||||
cd src/Website
|
||||
npm run lint
|
||||
npm run typecheck
|
||||
npm run format:check
|
||||
@@ -116,7 +115,7 @@ export WEBSITE_BASE_URL="http://localhost:3000"
|
||||
### 2. Run Migrations and Seed
|
||||
|
||||
```bash
|
||||
cd web/backend
|
||||
cd src/Core
|
||||
dotnet run --project Database/Database.Migrations/Database.Migrations.csproj
|
||||
dotnet run --project Database/Database.Seed/Database.Seed.csproj
|
||||
```
|
||||
@@ -129,11 +128,11 @@ dotnet run --project API/API.Core/API.Core.csproj
|
||||
|
||||
## Legacy Frontend Note
|
||||
|
||||
The previous Next.js frontend lives in `archive/next-js-web-app/` for reference
|
||||
only and is not the active website.
|
||||
The previous Next.js frontend now lives in `src/Website-v1` and is not the active website.
|
||||
Legacy setup details have been moved to [docs/archive/legacy-website-v1.md](archive/legacy-website-v1.md).
|
||||
|
||||
## Next Steps
|
||||
|
||||
- Review [Architecture](../architecture.md)
|
||||
- Review [Architecture](architecture.md)
|
||||
- Run backend and frontend checks from [Testing](testing.md)
|
||||
- Use [Docker Guide](docker.md) for container troubleshooting
|
||||
@@ -1,364 +0,0 @@
|
||||
# Ethics, Bias, and Known Issues
|
||||
|
||||
This document covers the ethical context of the Biergarten Pipeline's output,
|
||||
the model's biases, and known issues including hallucinated brewing science and
|
||||
low-resource language failures.
|
||||
|
||||
> Note that all testing was used using `google_gemma-4-E4B-it-Q6_K.gguf`.
|
||||
|
||||
## Table of Contents
|
||||
|
||||
- [What This Dataset Is](#what-this-dataset-is)
|
||||
- [What This Dataset Is Not](#what-this-dataset-is-not)
|
||||
- [Model Bias and Language Quality](#model-bias-and-language-quality)
|
||||
- [Western and Eurocentric Lens](#western-and-eurocentric-lens)
|
||||
- [Wikipedia Enrichment](#wikipedia-enrichment)
|
||||
- [Names-by-Country Dataset](#names-by-country-dataset)
|
||||
- [The "Avoid AI Phrases" Prompt Instruction](#the-avoid-ai-phrases-prompt-instruction)
|
||||
- [Known Issues](#known-issues)
|
||||
- [Hallucinated Brewing Techniques](#hallucinated-brewing-techniques)
|
||||
- [Low-Resource Language Hallucination](#low-resource-language-hallucination)
|
||||
|
||||
---
|
||||
|
||||
## What This Dataset Is
|
||||
|
||||
This is AI-generated fixture data for a proof-of-concept version of The
|
||||
Biergarten App. Anyone who interacts with an application seeded from this
|
||||
pipeline must be told upfront that the content is AI-generated.
|
||||
|
||||
---
|
||||
|
||||
## What This Dataset Is Not
|
||||
|
||||
The pipeline is not intended to produce accurate brewing science, faithful
|
||||
cultural representation, or reliable local-language text. Hallucinations such as
|
||||
invented fermentation techniques, or incoherent local-language prose, are
|
||||
expected, observed, and partially documented in [Known Issues](#known-issues)
|
||||
below.
|
||||
|
||||
Human control sits at the context layer (i.e. prompt design, Wikipedia
|
||||
enrichment). Statistical output shapes in future pipeline stages (check-in
|
||||
distributions, rating skews, activity profiles) will be handled the same way.
|
||||
|
||||
**Treat this data as an exercise in prompt engineering and model behaviour, not
|
||||
as a source of truth for brewing techniques or cultural representation.**
|
||||
|
||||
**Natural language processing, although a powerful tool for data analysis and
|
||||
generation is to be taken with scrutiny. Human language is not simply just data
|
||||
points to be analyzed, but it also carries deep cultural and human meaning that
|
||||
artificial intelligence is incapable of.**
|
||||
|
||||
---
|
||||
|
||||
## Model Bias and Language Quality
|
||||
|
||||
The underlying model's training biases surface within this pipeline. Output
|
||||
quality tracks with how well a language is represented in the training corpus:
|
||||
standard French (`fr-FR`) produces coherent text; regional variants like `fr-CD`
|
||||
and `fr-CI` are noticeably weaker; low-resource languages like Welsh, Māori, and
|
||||
Sicilian produce output that is syntactically plausible but often semantically
|
||||
broken.
|
||||
|
||||
This is a property of the training distribution, not something that can be
|
||||
mitigated through prompt design. This is a well-documented characteristic of
|
||||
large language models trained predominantly on English-language
|
||||
material.[^llm-bias]
|
||||
|
||||
Mitigations are documented in
|
||||
[Known Issues: Low-Resource Language Hallucination](#low-resource-language-hallucination).
|
||||
|
||||
### Western and Eurocentric Lens
|
||||
|
||||
The model's training data skews heavily Western and North American. When
|
||||
generating brewery descriptions for Kinshasa, Abidjan, or Osaka, for example, it
|
||||
defaults to framing and cultural reference points drawn from that perspective
|
||||
rather than from the lived context of those cities. Wikipedia enrichment grounds
|
||||
some generation in city-specific material, but it does not eliminate the skew.
|
||||
|
||||
**Output should be read with an understanding of this bias.**
|
||||
|
||||
---
|
||||
|
||||
## Wikipedia Enrichment
|
||||
|
||||
City and beer context is fetched from the Wikipedia API. Wikipedia text is
|
||||
co-licensed under the **Creative Commons Attribution-ShareAlike 4.0
|
||||
International License (CC BY-SA 4.0)** and the **GNU Free Documentation License
|
||||
(GFDL)**.[^wp-license]
|
||||
|
||||
Wikipedia's own accuracy limitations and editorial biases can propagate into
|
||||
generated descriptions.
|
||||
|
||||
---
|
||||
|
||||
## Names-by-Country Dataset
|
||||
|
||||
`tooling/pipeline/forenames-by-country.json` and `surnames-by-country.json`
|
||||
(used to sample a `Name` per ISO 3166-1 country code for user generation) are
|
||||
vendored verbatim, unmodified, from
|
||||
[sigpwned/popular-names-by-country-dataset](https://github.com/sigpwned/popular-names-by-country-dataset)
|
||||
(the `common-forenames-by-country.json` / `common-surnames-by-country.json`
|
||||
release assets), released under **CC0** (public domain). That dataset's own
|
||||
forename/surname lists are pulled from Wikipedia's "Lists of most common
|
||||
surnames" and "List of most popular given names" as of the week of
|
||||
2023-07-08 — see that project's README for full provenance. Names are not
|
||||
LLM-generated; this is curated fixture data per ROADMAP.md §2. Per-forename
|
||||
gender from the source data is preserved through to the sampled `Name`
|
||||
(rather than discarded during loading) so it's available for gender-aware
|
||||
persona/bio generation later.
|
||||
|
||||
The full multinational dataset is kept as-is (106 countries for forenames,
|
||||
75 for surnames) rather than trimmed to `locations.json`'s current country
|
||||
list, so it doesn't need re-sourcing if more countries are added later.
|
||||
`SampleName()` (a free helper in `generate_users.cc`) returns no result for
|
||||
a country present in neither file; of the countries in `locations.json`,
|
||||
that's currently `KE`, `SE`, `SG`, `TH`, `VN`, and `ZA` — `GenerateUsers`
|
||||
skips cities in those countries the same way brewery generation skips
|
||||
cities whose enrichment lookup fails.
|
||||
|
||||
---
|
||||
|
||||
## The "Avoid AI Phrases" Prompt Instruction
|
||||
|
||||
The system prompt instructs the model to avoid common AI-generated phrasing
|
||||
patterns. This is a prompt engineering experiment:
|
||||
|
||||
> How far can a model be pushed against its own stylistic defaults?
|
||||
|
||||
This is not an attempt to disguise the content as human-written. All downstream
|
||||
consumers are informed of the AI-generated origin before engagement.
|
||||
|
||||
---
|
||||
|
||||
## Known Issues
|
||||
|
||||
### Hallucinated Brewing Techniques
|
||||
|
||||
When forced by the system prompt to generate a "highly specialized technical
|
||||
brewing detail," the model frequently hallucinates fermentation science and
|
||||
brewing chemistry. While the resulting sounds confident, it will be nonsensical
|
||||
to reader with brewing and/or scientific expertise.
|
||||
|
||||
Small-parameter models such as Gemma 4 E4B cannot reliably satisfy prompts
|
||||
calling for specialist brewing detail. This is consistent with the **CHOKE**
|
||||
failure mode (Certain Hallucinations Overriding Known Evidence) [^llm-choke]
|
||||
where a specific-sounding prompt causes a model to produce confident, coherent,
|
||||
and factually wrong output.
|
||||
|
||||
#### Example — Osaka, produced using Gemma 4 E4B
|
||||
|
||||
```log
|
||||
[2026-04-21 15:04:40.258] [info] 11. city="Osaka" country="Japan" state="Osaka" iso3166_2=JP-27 lat=34.6937 lon=135.5023
|
||||
[2026-04-21 15:04:40.258] [info] brewery_name_en="Kani-no-Kuni Brewing"
|
||||
[2026-04-21 15:04:40.258] [info] brewery_description_en="The humid scent of takoyaki and savory grilled squid always settles over the neighborhood early in the morning, mingling strangely with the metallic tang of spent grain outside our drying shed. We decided to build this place here because Osaka is a city that never pauses, a place built around the constant exchange of goods and tastes, and that is what we want our beer to reflect. Many people here are accustomed to the dependable, clean taste of the major pale lagers, but we are interested in exploring the deeper, more textured expressions of fermentation. Our base malts are specifically crafted by incorporating strains of local rice, like Yamada Nishiki, which we malt and use not for sake, but for its complex, buttery flavor profile during the mash. This combination, followed by a slow, anaerobic aging process, gives our beers a profound, satisfying depth that stands apart from the hurried mass-market style. The heavy, deep red brick of the original warehouse wall has absorbed decades of Kansai humidity and seasonal rains, creating a patina that tells the exact story of this district's tireless movement. We chose this structure not for its charm, but for its resilience and the sheer density of the local history held within its mortar. Our goal is simply to serve a drink worthy of this powerful trading city. If you are looking for a quiet spot away from the main thoroughfare, look for us just off the side street near Shinsekai."
|
||||
[2026-04-21 15:04:40.258] [info] brewery_name_local="カニの国ブルワリー"
|
||||
[2026-04-21 15:04:40.258] [info] brewery_description_local="早朝の、たこ焼きや香ばしいイカ焼きの湿った匂いは、いつも乾燥小屋の外にある使用済み麦芽の金属的な匂いと奇妙に混ざり合って近隣に漂います。私たちはこの場所に店を構えることを決めたのです。なぜなら、大阪は決して止まることのない都市であり、商品と味が絶え間なく交換されることで築かれた場所だからです。地元の多くの方々は、信頼できる大規模な淡麗ラガーの味が習慣になっていますが、私たちは発酵の、より深く、より複雑な表現を探求することに関心があります。私たちのベースモルトは、山田錦のような地元の米の品種を意図的に組み込んで作られています。この米を酒ではなく、麦芽として、仕込みの最中にその複雑でバターのような風味を引き出すために使用しています。この組み合わせを、ゆっくりとした嫌気的な熟成プロセスに続けることで、私たちのビールは、慌ただしい市場のスタイルとは一線を画す、深みのある、満足感のある複雑さを持っています。オリジナルの倉庫の重く深紅のレンガ壁は、関西特有の湿気と季節の雨を何十年も吸収し、この地区の絶え間ない動きの正確な物語を語るような古色を帯びています。私たちはこの構造物を、その魅力のためではなく、その回復力とモルタルに込められた地域の歴史の密度ゆえに選びました。私たちの目標は、ただこの力強い交易都市に値する飲み物を提供することだけです。もしメインの通りから離れた静かな場所をお探しなら、新世界近くの脇道にある私たちを探してください。"
|
||||
```
|
||||
|
||||
A review of the following text for brewing techniques reveals several
|
||||
inaccuracies, and no comments could be made on the local-language version due to
|
||||
my own lack of proficiency in Japanese:
|
||||
|
||||
#### 1. "Buttery flavours" framed as a desirable malt-derived flavour
|
||||
|
||||
**Incorrect.**
|
||||
|
||||
Diacetyl is a fermentation byproduct of yeast metabolism, not a malt-derived
|
||||
compound.[^diacetyl-source] Diacetyl produces a buttery or butterscotch
|
||||
off-flavour and is carefully managed in many beer styles, in particular lighter
|
||||
beers, through a process called a _diacetyl rest_. In this process, fermentation
|
||||
temperature is briefly raised to allow yeast to reabsorb the compound before
|
||||
packaging.[^diacetyl-rest]
|
||||
|
||||
The Oxford Companion to Beer claims that, while low levels are tolerable in some
|
||||
ales and stouts, diacetyl is considered undesirable at any perceptible
|
||||
concentration when it results from bacterial contamination or stressed
|
||||
fermentation.[^oxford-beer]
|
||||
|
||||
#### 2. Yamada Nishiki sake rice described as a self-saccharifying base malt
|
||||
|
||||
**Incorrect.**
|
||||
|
||||
Yamada Nishiki (_山田錦_) is a short-grain Japanese rice bred specifically for
|
||||
sake production.[^yn-wiki] Its value lies in its large starchy core
|
||||
(_shinpaku_), low protein content, and amenability to _koji_ mold penetration
|
||||
during saccharification.[^yn-sakestreet] Sake brewing does not use the grain's
|
||||
own enzymatic activity for saccharification — it relies on _Aspergillus oryzae_
|
||||
(koji mold) grown on a portion of the steamed rice to convert starches to
|
||||
fermentable sugars.[^yn-sakeonline]
|
||||
|
||||
#### 3. "Anaerobic aging" presented as a differentiating technique
|
||||
|
||||
**Misleading**
|
||||
|
||||
Anaerobic conditions during packaging and aging are not differentiating
|
||||
technique. Anaerobic conditions are the standard baseline for all commercial
|
||||
beer production. Breweries exclude oxygen as a top priority for packaging and
|
||||
shelf stability; published research in _Microbiology Spectrum_ confirms that
|
||||
packaged beer constitutes an anaerobic environment by definition.[^anaerobic]
|
||||
Professional packaging lines use CO_2 purges and closed transfers specifically
|
||||
to maintain this state.[^packaging] Framing anaerobic aging as a distinctive
|
||||
practice is misleading and suggests hallucinated output.
|
||||
|
||||
### Low-Resource Language Hallucination
|
||||
|
||||
The generation pipeline passes local language codes to the model to retrieve a
|
||||
translated `description_local`. Output quality is reliable for high-resource
|
||||
languages such as French, though it may struggle with regional variants and
|
||||
idiomatic phrasing.
|
||||
|
||||
```json
|
||||
[
|
||||
{
|
||||
"city": "Kinshasa",
|
||||
"state_province": "Kinshasa",
|
||||
"iso3166_2": "CD-KN",
|
||||
"country": "Democratic Republic of the Congo",
|
||||
"iso3166_1": "CD",
|
||||
"latitude": -4.4419,
|
||||
"longitude": 15.2663,
|
||||
"local_languages": ["fr-CD", "ln"]
|
||||
},
|
||||
{
|
||||
"city": "Paris",
|
||||
"state_province": "Île-de-France",
|
||||
"iso3166_2": "FR-IDF",
|
||||
"country": "France",
|
||||
"iso3166_1": "FR",
|
||||
"latitude": 48.8566,
|
||||
"longitude": 2.3522,
|
||||
"local_languages": ["fr-FR"]
|
||||
},
|
||||
{
|
||||
"city": "Abidjan",
|
||||
"state_province": "Abidjan",
|
||||
"iso3166_2": "CI-AB",
|
||||
"country": "Ivory Coast",
|
||||
"iso3166_1": "CI",
|
||||
"latitude": 5.36,
|
||||
"longitude": -4.0083,
|
||||
"local_languages": ["fr-CI"]
|
||||
},
|
||||
{
|
||||
"city": "Montreal",
|
||||
"state_province": "Quebec",
|
||||
"iso3166_2": "CA-QC",
|
||||
"country": "Canada",
|
||||
"iso3166_1": "CA",
|
||||
"latitude": 45.5017,
|
||||
"longitude": -73.5673,
|
||||
"local_languages": ["fr-CA"]
|
||||
},
|
||||
{
|
||||
"city": "Brussels",
|
||||
"state_province": "Brussels-Capital Region",
|
||||
"iso3166_2": "BE-BRU",
|
||||
"country": "Belgium",
|
||||
"iso3166_1": "BE",
|
||||
"latitude": 50.8503,
|
||||
"longitude": 4.3517,
|
||||
"local_languages": ["fr-BE", "nl-BE"]
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
This dataset, when fed into the pipeline will often times reason that a local
|
||||
variant of French is needed, but will often times just default to a standardized
|
||||
dialect of French, devoid of any cultural or linguistic nuance.
|
||||
|
||||
For languages such as Welsh (Wales), Māori (Aotearoa/New Zealand), or Sicilian
|
||||
(Sicily, Italy), the model can generate text that looks syntactically plausible
|
||||
but is semantically incoherent. This comes from limited training-data coverage
|
||||
rather than prompt engineering.
|
||||
|
||||
Output sample:
|
||||
[./french-cities.example](french-cities.example)
|
||||
|
||||
#### Proposed Mitigations
|
||||
|
||||
- **Prevention via allowlist:** introduce a high-resource language allowlist. If
|
||||
a location's code is unlisted, skip `description_local` generation and fall
|
||||
back to English.
|
||||
- **Upstream sanitization:** strip known low-resource language codes from the
|
||||
`locations.json` payload before generation.
|
||||
- **Downstream flagging:** add a `description_local_confidence` column to the
|
||||
SQLite schema so downstream applications can filter or flag potentially
|
||||
hallucinated text by language tier.
|
||||
|
||||
---
|
||||
|
||||
## Footnotes
|
||||
|
||||
[^llm-choke]:
|
||||
CHOKE (Certain Hallucinations Overriding Known Evidence) is a hallucination
|
||||
failure mode defined by Simhi et al. (2025), in which a model that can
|
||||
consistently answer a question correctly produces a confident, wrong
|
||||
response when the prompt is trivially perturbed. Source: Trust Me, I'm
|
||||
Wrong: LLMs Hallucinate with Certainty Despite Knowing the Answer — Adi
|
||||
Simhi, Itay Itzhak, Fazl Barez, Gabriel Stanovsky, Yonatan Belinkov.
|
||||
|
||||
[^llm-bias]:
|
||||
e.g., Blasi et al. (2022), "Systematic Inequalities in Language Technology
|
||||
Performance across the World's Languages," _ACL Anthology_. The pattern is
|
||||
consistent with models trained predominantly on English-language web
|
||||
corpora.
|
||||
|
||||
[^wp-license]:
|
||||
Source:
|
||||
[Wikipedia:FAQ/Copyright](https://en.wikipedia.org/wiki/Wikipedia:FAQ/Copyright).
|
||||
|
||||
[^cc-sa]:
|
||||
Creative Commons CC BY-SA 4.0 deed: "If you remix, transform, or build upon
|
||||
the material, you must distribute your contributions under the same license
|
||||
as the original." Source:
|
||||
[creativecommons.org/licenses/by-sa/4.0](https://creativecommons.org/licenses/by-sa/4.0/deed.en).
|
||||
|
||||
[^diacetyl-source]:
|
||||
White Labs confirms that diacetyl is a yeast-derived fermentation byproduct:
|
||||
specifically, a compound produced during amino acid metabolism that leaks
|
||||
out of the yeast cell and oxidises into its characteristic buttery
|
||||
off-flavour. It is generally considered undesirable at any perceived level
|
||||
in most styles, though low levels are tolerated in some English ales and
|
||||
European lagers. Source:
|
||||
[whitelabs.com — Compound Spotlight: Diacetyl](https://www.whitelabs.com/news-update-detail?id=54).
|
||||
|
||||
[^diacetyl-rest]:
|
||||
Brewing Science Institute: diacetyl "is produced during the fermentation
|
||||
process, primarily as a byproduct of yeast metabolism… generally considered
|
||||
a flaw in most beer styles." Source:
|
||||
[brewingscience.com — Diacetyl: Understanding Its Role as an Off-Flavor in Beer](https://brewingscience.com/diacetyl-understanding-its-role-as-an-off-flavor-in-beer/).
|
||||
|
||||
[^oxford-beer]:
|
||||
Oxford Companion to Beer via _Beer & Brewing_: "At low to moderate levels,
|
||||
diacetyl can be perceived as a positive flavor characteristic in some ales
|
||||
and stouts" but "particularly unwelcome in lager-style beers." Source:
|
||||
[beerandbrewing.com — diacetyl](https://www.beerandbrewing.com/dictionary/48TDqQibPi).
|
||||
|
||||
[^yn-wiki]:
|
||||
Wikipedia: "Yamada Nishiki (山田錦) is a short-grain Japanese rice famous
|
||||
for its use in high-quality sake." Source:
|
||||
[en.wikipedia.org/wiki/Yamada_Nishiki](https://en.wikipedia.org/wiki/Yamada_Nishiki).
|
||||
|
||||
[^yn-sakestreet]:
|
||||
Sake Street: Yamadanishiki's large _shinpaku_ allows koji mold to penetrate
|
||||
to the centre of the rice grain, making it "particularly suitable for
|
||||
producing good koji." Source:
|
||||
[sakestreet.com — What is Yamadanishiki?](https://sakestreet.com/en/media/what-is-yamadanishiki).
|
||||
|
||||
[^yn-sakeonline]:
|
||||
Sake Online: "Steamed rice is added to make koji (rice malt) and yeast
|
||||
starter, which promotes alcohol fermentation." Source:
|
||||
[sakeonline.com.au — Types of Sake Rice: Yamada Nishiki](https://sakeonline.com.au/blogs/news/types-of-sake-rice-yamada-nishiki-and-its-characteristics).
|
||||
|
||||
[^anaerobic]:
|
||||
Pai et al. (2022): "Breweries have recognized oxygen exclusion as a top
|
||||
priority for the proper packaging and aging of beer… packaged beer is an
|
||||
anaerobic environment." _Microbiology Spectrum._ Source:
|
||||
[journals.asm.org](https://journals.asm.org/doi/10.1128/spectrum.02656-22).
|
||||
|
||||
[^packaging]:
|
||||
Beer Production Processes (oboe.com): Professional packaging lines use
|
||||
double CO_2 pre-evacuation cycles and closed transfers "so the beer moves in
|
||||
a completely anaerobic environment." Source:
|
||||
[oboe.com — Flavor Quality Control](https://oboe.com/learn/beer-production-processes-308lmf/flavor-quality-control-4).
|
||||
@@ -1,496 +0,0 @@
|
||||
# Biergarten Pipeline
|
||||
|
||||
A C++20 command-line pipeline that samples city records from local JSON,
|
||||
enriches each with Wikipedia context, and generates bilingual brewery names
|
||||
and descriptions plus locale-grounded user profiles via a local GGUF model or
|
||||
a deterministic mock.
|
||||
|
||||
> **This pipeline produces AI-generated data.** It is not a source of truth for
|
||||
> brewing techniques, cultural representation, or local-language accuracy. See
|
||||
> [ETHICS-AND-KNOWN-ISSUES.md](./ETHICS-AND-KNOWN-ISSUES.md) for a full
|
||||
> documentation of limitations, hallucination patterns, and bias.
|
||||
|
||||
---
|
||||
|
||||
## Table of Contents
|
||||
|
||||
- [How It Fits The Main App](#how-it-fits-the-main-app)
|
||||
- [Quick Start](#quick-start)
|
||||
- [Build](#build)
|
||||
- [Model](#model)
|
||||
- [Run](#run)
|
||||
- [Docker / RunPod](#docker--runpod)
|
||||
- [Architecture](#architecture)
|
||||
- [Pipeline Stages](#pipeline-stages)
|
||||
- [Key Components](#key-components)
|
||||
- [Runtime Behaviour](#runtime-behaviour)
|
||||
- [Generated Output](#generated-output)
|
||||
- [Tech Stack](#tech-stack)
|
||||
- [Tested Hardware](#tested-hardware)
|
||||
- [Fixture Strategy](#fixture-strategy)
|
||||
- [Repo Layout](#repo-layout)
|
||||
- [Code Tour](#code-tour)
|
||||
- [Next Steps](#next-steps)
|
||||
|
||||
---
|
||||
|
||||
## How It Fits The Main App
|
||||
|
||||
The pipeline is a data ingestion layer. It sits outside the web app runtime and
|
||||
produces seed records the app imports at startup or during a dedicated seed
|
||||
step.
|
||||
|
||||
| Planned app area | Pipeline contribution |
|
||||
| -------------------------------- | ------------------------------------------------------------------ |
|
||||
| Brewery discovery and management | Sampled city records, localized names, long-form descriptions |
|
||||
| Beer reviews and ratings | Stable brewery fixtures with enough context to anchor review pages |
|
||||
| Social follow relationships | Repeatable brewery entities for feeds, follows, and saved lists |
|
||||
| Geospatial brewery experiences | Latitude, longitude, and country-level metadata |
|
||||
| User accounts and profiles | Locale-grounded names, bios, and an auth-ready email/date-of-birth pair for seeding real accounts |
|
||||
|
||||
---
|
||||
|
||||
## Quick Start
|
||||
|
||||
### Build
|
||||
|
||||
Requirements: C++20 compiler, CMake 3.31+, OpenSSL, Boost (JSON and
|
||||
ProgramOptions). SQLite is fetched from the upstream amalgamation, so no system
|
||||
SQLite package is required.
|
||||
|
||||
```bash
|
||||
cmake -S . -B build
|
||||
cmake --build build
|
||||
```
|
||||
|
||||
CMake automatically detects whether a compatible llama.cpp installation is
|
||||
present on the system (`libllama`, `libggml`, `libggml-base`, and `llama.h`
|
||||
visible on the default search paths). If found, it links against those
|
||||
libraries and skips the FetchContent build. If not found, it fetches and builds
|
||||
llama.cpp from source at tag `b9012`. No additional flags are required in
|
||||
either case.
|
||||
|
||||
Metal is enabled automatically on Apple Silicon. CUDA or HIP/ROCm is detected
|
||||
automatically on Linux when the relevant toolkit is present.
|
||||
|
||||
### Model
|
||||
|
||||
> Skip this step if you only need `--mocked`.
|
||||
|
||||
```bash
|
||||
mkdir -p models
|
||||
curl -L \
|
||||
-o models/google_gemma-4-E4B-it-Q6_K.gguf \
|
||||
https://huggingface.co/bartowski/google_gemma-4-E4B-it-GGUF/resolve/main/google_gemma-4-E4B-it-Q6_K.gguf?download=true
|
||||
```
|
||||
|
||||
### Run
|
||||
|
||||
Run from `build/` so the copied `locations.json` and `prompts/` are available.
|
||||
Each run writes a fresh dated SQLite file such as
|
||||
`biergarten_seed_2026-04-19T15-30-45.123456Z.sqlite` into the working directory.
|
||||
|
||||
```bash
|
||||
./biergarten-pipeline --mocked
|
||||
|
||||
./biergarten-pipeline \
|
||||
--model ../models/google_gemma-4-E4B-it-Q6_K.gguf \
|
||||
--prompt-dir prompts \
|
||||
--location-count 25 \
|
||||
--temperature 1.0 --top-p 0.95 --top-k 64 --n-ctx 8192 --seed -1
|
||||
```
|
||||
|
||||
#### CLI Flags
|
||||
|
||||
| Flag | Purpose |
|
||||
| ------------------ | ---------------------------------------------------------------------------------------------------- |
|
||||
| `--mocked` | Deterministic mock generator, no model required. |
|
||||
| `--model, -m` | Path to a GGUF file. Required unless `--mocked` is set. |
|
||||
| `--prompt-dir` | Directory containing prompt files (e.g. `BREWERY_GENERATION.md`). Required unless `--mocked` is set. |
|
||||
| `--output, -o` | Directory for generated SQLite artifacts. Default: `output`. |
|
||||
| `--log-path` | Path for application logs. Default: `pipeline.log`. |
|
||||
| `--location-count` | Number of cities to sample from `locations.json` per run. Default: `10`. |
|
||||
| `--temperature` | Sampling temperature. Default: `1.0`. |
|
||||
| `--top-p` | Nucleus sampling. Default: `0.95`. |
|
||||
| `--top-k` | Top-k sampling. Default: `64`. |
|
||||
| `--n-ctx` | Context window size. Default: `8192`. |
|
||||
| `--seed` | Random seed. Default: `-1` (random at runtime). |
|
||||
| `--n-gpu-layers` | Number of model layers to offload to GPU. Default: `0`. |
|
||||
| `--help, -h` | Print usage and exit. |
|
||||
|
||||
`--mocked` and `--model` are mutually exclusive. Omitting both exits with an
|
||||
error before the pipeline starts. Sampling flags are ignored when `--mocked` is
|
||||
set.
|
||||
|
||||
The post-build step copies `prompts/` into `build/prompts/`. Rebuild after
|
||||
editing any prompt file.
|
||||
|
||||
---
|
||||
|
||||
## Docker / RunPod
|
||||
|
||||
The `tooling/pipeline/runpod/` directory contains a GPU-ready container
|
||||
configuration for running the pipeline on RunPod or any Docker host with an
|
||||
NVIDIA GPU.
|
||||
|
||||
### How it works
|
||||
|
||||
The container uses a two-stage build. The builder stage installs CMake/Ninja,
|
||||
clones the matching llama.cpp release tag for its headers only (installed into
|
||||
`/usr/local/include`), and copies prebuilt shared libraries (`libllama`,
|
||||
`libggml`, and CUDA/CPU backend plugins) from `ghcr.io/ggml-org/llama.cpp:full-cuda`
|
||||
into `/usr/local/lib`. With both headers and libraries present, CMake's
|
||||
system-library detection (see [Build](#build) above) finds them and skips the
|
||||
FetchContent source build, keeping image build times short.
|
||||
|
||||
The runtime stage copies the compiled binary, the same prebuilt shared
|
||||
libraries, and config/prompt assets into a slim CUDA runtime image. It sets
|
||||
`LD_LIBRARY_PATH=/usr/local/lib:$LD_LIBRARY_PATH` so the dynamic linker
|
||||
resolves `libllama`/`libggml` at startup, and also co-locates
|
||||
`libggml-cuda.so` and the CPU backend plugins next to the binary for
|
||||
`ggml_backend_load_all()`'s `dlopen` scan.
|
||||
|
||||
### Build the image
|
||||
|
||||
Run from the `tooling/pipeline/` directory (the CMake project root), not from
|
||||
inside `runpod/`, so the `COPY . .` step picks up the full project context.
|
||||
|
||||
```bash
|
||||
docker build -t biergarten-pipeline:latest -f runpod/Dockerfile .
|
||||
```
|
||||
|
||||
To monitor the full build output and confirm CMake selects the system llama.cpp:
|
||||
|
||||
```bash
|
||||
docker build \
|
||||
--progress=plain \
|
||||
--no-cache \
|
||||
-t biergarten-pipeline:latest \
|
||||
-f runpod/Dockerfile \
|
||||
. 2>&1 | tee build.log
|
||||
```
|
||||
|
||||
Look for `[biergarten] Found system llama.cpp — skipping FetchContent` in the
|
||||
output to confirm the fast path was taken.
|
||||
|
||||
### Run the container
|
||||
|
||||
The container always runs the model-backed path; there is no `--mocked`
|
||||
container mode (use a native build for that — see [Quick Start](#quick-start)).
|
||||
The entrypoint, `runpod/start.sh`, downloads the GGUF model automatically if
|
||||
it is not already present at the configured path.
|
||||
|
||||
```bash
|
||||
docker run --rm \
|
||||
--runtime=nvidia \
|
||||
-v "$PWD/models:/workspace/models" \
|
||||
-v "$PWD/output:/workspace/output" \
|
||||
-v "$PWD/logs:/workspace/logs" \
|
||||
biergarten-pipeline:latest
|
||||
```
|
||||
|
||||
By default this downloads `google_gemma-4-E4B-it-Q6_K.gguf` to
|
||||
`./models/` on first run if it isn't already there. To use a pre-downloaded
|
||||
model, place it at that path first — see [Model](#model) above.
|
||||
|
||||
#### Environment variables
|
||||
|
||||
| Variable | Purpose |
|
||||
| ------------------------- | ----------------------------------------------------------------- |
|
||||
| `BIERGARTEN_MODEL_PATH` | GGUF model path. Default: `/workspace/models/google_gemma-4-E4B-it-Q6_K.gguf`. |
|
||||
| `BIERGARTEN_OUTPUT_DIR` | SQLite output directory. Default: `/workspace/output`. |
|
||||
| `BIERGARTEN_LOG_PATH` | Log file path. Default: `/workspace/logs/pipeline.log`. |
|
||||
| `BIERGARTEN_GL_LAYERS` | GPU layers to offload (`--n-gpu-layers`). Default: `40`. |
|
||||
| `BIERGARTEN_TEMPERATURE`, `BIERGARTEN_TOP_P`, `BIERGARTEN_TOP_K`, `BIERGARTEN_N_CTX`, `BIERGARTEN_SEED` | Optional sampling overrides, unset by default (binary defaults apply). |
|
||||
| `BIERGARTEN_EXTRA_ARGS` | Additional raw CLI args appended verbatim. |
|
||||
|
||||
`--prompt-dir` is hardcoded to `/app/prompts` inside the container and is not
|
||||
configurable via environment variable.
|
||||
|
||||
### RunPod deployment
|
||||
|
||||
Use a GPU pod template. Mount persistent storage for `/workspace/models`,
|
||||
`/workspace/output`, and `/workspace/logs`. See
|
||||
`tooling/pipeline/runpod/pod-template.yaml` for a starter template — set the
|
||||
environment variables listed above to match your run.
|
||||
|
||||
---
|
||||
|
||||
## Architecture
|
||||
|
||||
### Pipeline Stages
|
||||
|
||||
| Stage | Implementation |
|
||||
| --------------- | ----------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Load | `ICuratedDataService` (`CuratedJsonDataService`) reads `locations.json`, `personas.json`, `forenames-by-country.json`, and `surnames-by-country.json` (paths supplied via a `CuratedDataFilePaths` DTO at construction) into typed records, caching each after its first load. `--mocked` runs use `MockCuratedDataService`'s fixed in-memory dataset instead. |
|
||||
| Sample | `BiergartenPipelineOrchestrator::QueryCitiesWithCountries()` samples `--location-count` locations per run (default `10`). |
|
||||
| Enrich | `WikipediaEnrichmentService` fetches brewing and beer-related context. Keeps going when a lookup fails. `--mocked` runs use `MockEnrichmentService` instead and skip Wikipedia entirely. |
|
||||
| Generate Users | `GenerateUsers()` samples a persona and a forename/surname pair per enriched city (skipping countries with no name data), then `MockGenerator` or `LlamaGenerator` produces a username, bio, and activity weight around the sampled name. |
|
||||
| Generate Breweries | `MockGenerator` or `LlamaGenerator` produces brewery names and descriptions in English and the local language. |
|
||||
| Store | `SqliteExportService` writes each successful user and brewery into a fresh dated `.sqlite` database with normalized `locations`, `users`, and `breweries` tables. |
|
||||
| Log | `spdlog` writes results and warnings to the console. |
|
||||
|
||||
If name sampling, enrichment, or generation fails for a city, that city is
|
||||
skipped and the pipeline continues. `GenerateUsers()` runs before
|
||||
`GenerateBreweries()` in `BiergartenPipelineOrchestrator::Run()`.
|
||||
|
||||
### Key Components
|
||||
|
||||
- `src/main.cc` — argument parsing and Boost.DI composition root.
|
||||
- `CuratedJsonDataService` — implements `ICuratedDataService`; takes a
|
||||
`CuratedDataFilePaths` DTO (locations/personas/forenames/surnames paths) in
|
||||
its constructor, then parses and validates curated location, persona, and
|
||||
forename/surname JSON, memoizing each result after its first load on a
|
||||
given instance. `MockCuratedDataService` is the in-memory substitute (4
|
||||
fixed locations, 3 personas, and name data for `US`/`DE`/`FR`/`BE`) used in
|
||||
`--mocked` runs.
|
||||
- `WikipediaEnrichmentService` — queries Wikipedia extracts, caches results,
|
||||
returns empty context on failure. `MockEnrichmentService` is the no-op
|
||||
substitute used in `--mocked` runs.
|
||||
- `LlamaGenerator` — formats prompts for Gemma 4, validates JSON output for
|
||||
both `GenerateBrewery` and `GenerateUser`, retries malformed responses up
|
||||
to three times with corrective feedback in the retry prompt. The token
|
||||
budget is fixed across attempts; it is not raised automatically on
|
||||
truncation.
|
||||
- `MockGenerator` — stable hash-based output so the same city/persona/name
|
||||
input always produces the same brewery or user.
|
||||
- `SqliteExportService` — creates a dated SQLite file per run and persists
|
||||
each successful user and brewery into normalized tables.
|
||||
- Brewery payloads include English and local-language name and description
|
||||
fields. User payloads carry a sampled first/last name and gender, an
|
||||
LLM-generated username/bio/activity weight, and a programmatically
|
||||
generated (not LLM-authored) unique email and date of birth.
|
||||
|
||||
### Runtime Behaviour
|
||||
|
||||
`WikipediaEnrichmentService` fetches two Wikipedia extracts per city: a
|
||||
generic "brewing" extract and a "beer in `{country}`" extract. It does not
|
||||
currently query a city- or region-specific page. Each query string is cached
|
||||
after its first successful (or empty) lookup.
|
||||
|
||||
`GetLocationContext()` returns an empty string when the web client is
|
||||
unavailable or when lookup/parsing fails.
|
||||
|
||||
`LlamaGenerator` validates model output as structured JSON. On validation
|
||||
failure it retries up to three times, replaying the previous error message in
|
||||
the next prompt so the model can self-correct. All runs to date have produced
|
||||
valid output on the first pass; the retry path is kept for resilience.
|
||||
|
||||
`MockGenerator` uses stable hashes for repeatable output in demos and Storybook
|
||||
runs.
|
||||
|
||||
`CuratedJsonDataService` memoizes each of `LoadLocations()`, `LoadPersonas()`,
|
||||
`LoadForenamesByCountry()`, and `LoadSurnamesByCountry()` independently the
|
||||
first time each is called, since `BiergartenPipelineOrchestrator` owns a
|
||||
single `ICuratedDataService` instance for the whole run — later calls return
|
||||
the cached result instead of re-parsing.
|
||||
|
||||
`GenerateUsers()` samples a forename/surname pair per city via `SampleName()`,
|
||||
keyed by the city's ISO 3166-1 code. Countries present in `locations.json`
|
||||
but absent from either name fixture (currently `KE`, `SE`, `SG`, `TH`, `VN`,
|
||||
`ZA`) are skipped, the same way a failed enrichment or generation call skips
|
||||
a city — see ETHICS-AND-KNOWN-ISSUES.md's Names-by-Country Dataset section.
|
||||
|
||||
### Process Flow - Activity Diagram
|
||||
|
||||

|
||||
|
||||
### Architectural Overview - Class Diagram
|
||||
|
||||

|
||||
|
||||
---
|
||||
|
||||
## Generated Output
|
||||
|
||||
Each successful run stores a `BreweryRecord` pair with the source location
|
||||
and a `BreweryResult` payload, and a `UserRecord` pair with the source
|
||||
location and a `UserResult` payload. The same generated records are also
|
||||
written to a fresh SQLite export file named with the current UTC timestamp.
|
||||
|
||||
| Field | Meaning |
|
||||
| ------------------- | ------------------------------------------ |
|
||||
| `name_en` | Brewery name in English. |
|
||||
| `description_en` | Brewery description in English. |
|
||||
| `name_local` | Brewery name in the local language. |
|
||||
| `description_local` | Brewery description in the local language. |
|
||||
|
||||
| Field | Meaning |
|
||||
| ----------------- | ----------------------------------------------------------------- |
|
||||
| `first_name` | Sampled forename, copied from the curated name data (not LLM-invented). |
|
||||
| `last_name` | Sampled surname, copied from the curated name data (not LLM-invented). |
|
||||
| `gender` | Gender associated with the sampled forename in the source dataset. |
|
||||
| `username` | LLM-generated handle. |
|
||||
| `bio` | LLM-generated short biography. |
|
||||
| `activity_weight` | Relative check-in/activity weight, reserved for a future J-curve activity profile. |
|
||||
| `email` | Unique `@thebiergarten.app` address, generated programmatically from the sampled name. |
|
||||
| `date_of_birth` | Randomized date of birth (age 19-48), generated programmatically. |
|
||||
|
||||
The log dump also includes city, country, state or province, ISO subdivision
|
||||
code, latitude, and longitude for each entry.
|
||||
|
||||
### Consumer Data Shape
|
||||
|
||||
| Field | Why it matters |
|
||||
| ----------------------------------- | ------------------------------------------------ |
|
||||
| `city`, `state_province`, `country` | Human-readable location labels and page headings |
|
||||
| `iso3166_1`, `iso3166_2` | Filtering, regional grouping, locale matching |
|
||||
| `latitude`, `longitude` | Map pins and nearby brewery views |
|
||||
| `local_languages` | Locale-aware copy selection |
|
||||
| `name_en`, `description_en` | Default English display content |
|
||||
| `name_local`, `description_local` | Local-language display content |
|
||||
|
||||
---
|
||||
|
||||
## Tech Stack
|
||||
|
||||
- C++20
|
||||
- CMake 3.31+
|
||||
- Boost.JSON, Boost.ProgramOptions, Boost.DI
|
||||
- spdlog
|
||||
- cpp-httplib (with OpenSSL)
|
||||
- SQLite amalgamation fetched and compiled via CMake FetchContent
|
||||
- llama.cpp (auto-detected from system install or fetched via FetchContent)
|
||||
- Docker with NVIDIA CUDA 12.6 base image for GPU container builds
|
||||
- RunPod for cloud GPU inference
|
||||
|
||||
The build fetches Boost.DI, spdlog, and SQLite via CMake. llama.cpp is fetched
|
||||
only when a system installation is not detected. Metal is enabled on Apple
|
||||
Silicon; CUDA or HIP/ROCm is detected on Linux when the toolkit is present.
|
||||
|
||||
> **Code Style:** Modern C++20 throughout — RAII for ownership,
|
||||
> `std::unique_ptr` for injected dependencies, `std::optional` for parse
|
||||
> outcomes, `std::span` for read-only views over generated city data, structured
|
||||
> bindings in pipeline loops. Formatting follows the Google C++ Style Guide via
|
||||
> `.clang-format` with a narrow column limit and two-space indentation.
|
||||
|
||||
---
|
||||
|
||||
## Tested Hardware
|
||||
|
||||
### ARM macOS — M1 Pro
|
||||
|
||||
| | |
|
||||
| --------- | --------------------------------- |
|
||||
| Host | MacBook Pro 14" (2021) |
|
||||
| CPU | Apple M1 Pro (8-core) |
|
||||
| GPU | Apple M1 Pro (14-core integrated) |
|
||||
| Memory | 16 GB |
|
||||
| Model | Gemma 4 E4B |
|
||||
| Inference | llama.cpp with Metal |
|
||||
|
||||
### x86_64 Linux — NVIDIA RTX 2000
|
||||
|
||||
| | |
|
||||
| --------- | ------------------------------ |
|
||||
| Host | ThinkPad P1 Gen 7 (Fedora 43) |
|
||||
| CPU | Intel Core Ultra 7 155H |
|
||||
| GPU | NVIDIA RTX 2000 Ada Generation |
|
||||
| Memory | 32 GB |
|
||||
| Model | Gemma 4 E4B |
|
||||
| Inference | llama.cpp with CUDA 12.x |
|
||||
|
||||
### x86_64 Linux — Docker / RunPod (NVIDIA CUDA)
|
||||
|
||||
| | |
|
||||
| --------- | ------------------------------------------- |
|
||||
| Host | RunPod GPU pod |
|
||||
| Base | nvidia/cuda:12.6.3-devel-ubuntu24.04 |
|
||||
| Model | Gemma 4 E4B Q6_K |
|
||||
| Inference | llama.cpp prebuilt CUDA backends via dlopen |
|
||||
|
||||
---
|
||||
|
||||
## Fixture Strategy
|
||||
|
||||
- `--mocked` for stable fixtures, repeatable screenshots, and Storybook runs.
|
||||
`MockCuratedDataService` swaps in for `CuratedJsonDataService`, so no
|
||||
fixture files need to be present on disk.
|
||||
- `--model` when geographically grounded content matters for demos.
|
||||
- Keep `locations.json` structured enough to support discovery and future
|
||||
filtering.
|
||||
- `personas.json`, `forenames-by-country.json`, and
|
||||
`surnames-by-country.json` are curated/vendored fixture data, not
|
||||
LLM-generated — see ETHICS-AND-KNOWN-ISSUES.md's Names-by-Country Dataset
|
||||
section for provenance.
|
||||
- Treat SQLite output as seed material for the app's brewery and user
|
||||
domains, not production data.
|
||||
|
||||
---
|
||||
|
||||
## Repo Layout
|
||||
|
||||
| Path | Purpose |
|
||||
| -------------------------------------- | -------------------------------------------------- |
|
||||
| `tooling/pipeline/includes/` | Public headers and shared models. |
|
||||
| `tooling/pipeline/src/` | Implementation files. |
|
||||
| `tooling/pipeline/locations.json` | Curated city input copied into the build tree. |
|
||||
| `tooling/pipeline/personas.json` | Curated user persona archetypes copied into the build tree. |
|
||||
| `tooling/pipeline/forenames-by-country.json` | Vendored (CC0) forename data by ISO 3166-1 country code. |
|
||||
| `tooling/pipeline/surnames-by-country.json` | Vendored (CC0) surname data by ISO 3166-1 country code. |
|
||||
| `tooling/pipeline/prompts/` | System prompts used by the model-backed path. |
|
||||
| `tooling/pipeline/runpod/` | Dockerfile, launcher, and RunPod pod template. |
|
||||
| `docs/pipeline/diagrams/` | Architecture and pipeline diagrams. |
|
||||
| `docs/pipeline/ETHICS-AND-KNOWN-ISSUES.md` | Ethics, bias, hallucination analysis, mitigations. |
|
||||
|
||||
---
|
||||
|
||||
## Code Tour
|
||||
|
||||
Paths below are relative to `tooling/pipeline/`.
|
||||
|
||||
- `src/main.cc` — argument parsing and DI composition root.
|
||||
- `src/biergarten_pipeline_orchestrator/` — orchestration, sampling, logging,
|
||||
and export.
|
||||
- `src/services/curated_data/` — `CuratedJsonDataService`, the file-backed
|
||||
`ICuratedDataService`, and `MockCuratedDataService`, the in-memory
|
||||
`ICuratedDataService` used in `--mocked` runs.
|
||||
- `src/services/enrichment/wikipedia/` — enrichment service and cache.
|
||||
- `src/services/sqlite/` — SQLite export implementation.
|
||||
- `src/data_generation/llama/` — local inference, prompt loading, output
|
||||
validation.
|
||||
- `src/data_generation/mock/` — deterministic fallback.
|
||||
- `runpod/` — container build and runtime launcher.
|
||||
|
||||
---
|
||||
|
||||
## Next Steps
|
||||
|
||||
The pipeline currently produces city-aware brewery and user records and
|
||||
dated SQLite exports. The next passes add additional fixture types so the
|
||||
app can exercise the full brewery and social domains without live data. For
|
||||
the detailed engineering breakdown of what's needed to reach the
|
||||
architecture in [`diagrams/planned/`](./diagrams/planned/), see
|
||||
[ROADMAP.md](./ROADMAP.md).
|
||||
|
||||
### Testing — Very High Priority
|
||||
|
||||
- Unit test JSON validation and retry logic against malformed, truncated, and
|
||||
empty model outputs.
|
||||
- Integration test the enrichment pipeline with missing context, short context,
|
||||
and fake context inputs.
|
||||
- Adversarial context tests: feed plausible but geographically incorrect
|
||||
Wikipedia extracts and verify the model does not silently blend them with
|
||||
training data.
|
||||
- Verify bilingual enrichment behaviour when only an English extract is
|
||||
available versus when both extracts are present.
|
||||
- Confirm the retry path is reachable when the reasoning block consumes
|
||||
available token budget.
|
||||
|
||||
### Beer Generation
|
||||
|
||||
Generate catalog entries with style, ABV, IBU, color, aroma notes, and food
|
||||
pairing hints. Link beers back to breweries and cities. Keep style coverage wide
|
||||
enough to exercise search, sort, and category filters.
|
||||
|
||||
### Check-In System
|
||||
|
||||
Produce timestamped check-in events between users and breweries. Use a J-curve
|
||||
activity profile — a small set of users accounts for most check-ins, the rest
|
||||
appear occasionally. Add bursty behaviour around weekends and travel periods.
|
||||
|
||||
### Beer Ratings
|
||||
|
||||
Generate rating events with a strong positive skew and a long tail of lower
|
||||
scores. Avoid uniform distributions. Attach timestamps and user IDs so the app
|
||||
can compute averages, trends, and per-style comparisons.
|
||||
@@ -1,252 +0,0 @@
|
||||
# Pipeline Roadmap — Reaching the Planned Architecture
|
||||
|
||||
This is the engineering breakdown for closing the gap between the **current**
|
||||
pipeline and the **planned** architecture documented in
|
||||
[`diagrams/planned/class.puml`](./diagrams/planned/class.puml) and
|
||||
[`diagrams/planned/activity.puml`](./diagrams/planned/activity.puml). Nothing
|
||||
in `diagrams/planned/` is implemented yet — this file tracks what it would
|
||||
take to get there. For the current implementation, see
|
||||
[README.md](./README.md).
|
||||
|
||||
Items are grouped by layer and roughly ordered by dependency: later groups
|
||||
build on types and services introduced earlier.
|
||||
|
||||
The only concurrency in the current pipeline is the log dispatcher thread
|
||||
(`main.cc` spawns it to drain a `BoundedChannel<LogEntry>` into spdlog for the
|
||||
whole run). Sampling, enrichment, generation, and export all happen
|
||||
synchronously on the main thread inside `BiergartenPipelineOrchestrator::Run()`
|
||||
— §6 below is what introduces the additional worker threads the planned
|
||||
architecture needs.
|
||||
|
||||
---
|
||||
|
||||
## 1. Domain Models
|
||||
|
||||
`tooling/pipeline/includes/data_model/generated_models.h` and `models.h`.
|
||||
|
||||
- [ ] Add `Completeness` enum (`Full`, `Partial`, `Absent`) and a
|
||||
`LocationContext` struct (`text`, `completeness`, `char_count`).
|
||||
Replace `EnrichedCity::region_context` (currently a plain
|
||||
`std::string`) with `context : LocationContext`.
|
||||
- [ ] Add `BeerStyle` (`name`, `description`, `min_abv`, `max_abv`,
|
||||
`min_ibu`, `max_ibu`).
|
||||
- [ ] Add `BeerResult`, `CheckinResult`, `RatingResult` result payloads.
|
||||
- [ ] Add `GenerationMetadata` (`generation_id`, `generated_time`,
|
||||
`context_provided`, `generated_with`).
|
||||
- [x] Add `first_name`, `last_name`, `gender`, and `activity_weight` to
|
||||
`UserResult` (currently just `username`, `bio`). `first_name`/
|
||||
`last_name`/`gender` are copied from the sampled `Name` (see below),
|
||||
not LLM-invented.
|
||||
- [x] Add `Name` (`first_name`, `last_name`, `gender`) — the sampled result
|
||||
handed to `DataGenerator::GenerateUser`. Add `ForenameEntry` (`name`,
|
||||
`gender`). Landed as a flatter shape than originally planned here: no
|
||||
`NamesByCountry` wrapper class. `curated_data_service.h` instead
|
||||
declares `ForenameList = std::vector<ForenameEntry>` and
|
||||
`SurnameList = std::vector<std::string>`, and
|
||||
`ICuratedDataService` exposes two maps keyed by ISO 3166-1 code —
|
||||
`ForenamesByCountryMap = unordered_map<string, ForenameList>` and
|
||||
`SurnamesByCountryMap = unordered_map<string, SurnameList>` —
|
||||
directly (see §2). Sampling is
|
||||
a free function, `SampleName(forenames_by_country,
|
||||
surnames_by_country, iso3166_1, rng)`, in
|
||||
`generate_users.cc`'s anonymous namespace, not a method on a class.
|
||||
Pairing a forename with a surname happens at sample time so gender
|
||||
(present per-forename in the source data) is never discarded the way a
|
||||
pre-flattened `{first_name, last_name}` list would lose it; see §2.
|
||||
- [ ] Extend `GeneratedBrewery` with `brewery_id`, `context_completeness`,
|
||||
`metadata` (currently just `{location, brewery}`).
|
||||
- [ ] Add `GeneratedBeer`, `GeneratedCheckin`, `GeneratedRating`,
|
||||
`GeneratedFollow` aggregate structs.
|
||||
- [x] Add `UserRecord` (`location`, `user : UserResult`, `email`,
|
||||
`date_of_birth`) as the current stand-in for the planned
|
||||
`GeneratedUser` — `email` and `date_of_birth` are programmatically
|
||||
generated by the orchestrator, never LLM-authored, so a downstream
|
||||
auth-account seeding consumer can register real accounts from the
|
||||
pipeline's SQLite export. No `password`, `user_id`, or `metadata`
|
||||
field yet, matching `BreweryRecord`'s equally pre-`metadata` shape.
|
||||
Already wired into `IExportService`/`SqliteExportService`: a `users`
|
||||
table exists and `GenerateUsers()` exports each successful record via
|
||||
`ProcessRecord(const UserRecord&)` (see §5) in addition to logging and
|
||||
holding `generated_users_` in memory. Still missing vs. the planned
|
||||
`GeneratedUser`: `user_id`, `password`, and `metadata`.
|
||||
- [x] Add `UserPersona` (`name`, `description`, `style_affinities`).
|
||||
|
||||
## 2. Data Preloading
|
||||
|
||||
`tooling/pipeline/includes/services/curated_data/`, fixture files.
|
||||
|
||||
- [x] Extract an interface; have `CuratedJsonDataService` implement it.
|
||||
Landed as `ICuratedDataService`
|
||||
(`services/curated_data/curated_data_service.h`), not `DataPreloader`
|
||||
— `LoadLocations()`, `LoadPersonas()`, `LoadForenamesByCountry()`, and
|
||||
`LoadSurnamesByCountry()` are all virtual methods returning `const&`
|
||||
and take no arguments. `CuratedJsonDataService`
|
||||
(`services/curated_data/curated_json_data_service.h`, originally
|
||||
landed as `JsonLoader` under `json_handling/` before being renamed and
|
||||
moved) takes a `CuratedDataFilePaths` DTO (`locations_path`,
|
||||
`personas_path`, `forenames_path`, `surnames_path`) in its
|
||||
constructor rather than a path per `Load*()` call, and memoizes each
|
||||
result in a private `cache` struct (`locations`, `personas`,
|
||||
`forenames_by_country`, `surnames_by_country`), so a second call on
|
||||
the same instance returns the cached result instead of re-parsing —
|
||||
safe because `CuratedJsonDataService` outlives every call site (owned
|
||||
by `BiergartenPipelineOrchestrator` via
|
||||
`unique_ptr<ICuratedDataService>` for the whole run). `main.cc`'s DI
|
||||
injector also gained a `MockCuratedDataService` (fixed in-memory
|
||||
data: 4 locations across `US`/`DE`/`FR`/`BE`, 3 personas, and
|
||||
matching forename/surname sets for those four countries), bound in
|
||||
place of `CuratedJsonDataService` under `--mocked`, mirroring the
|
||||
existing `MockEnrichmentService`/`MockGenerator` pattern.
|
||||
- [ ] Add `LoadBeerStyles()`. `beer-styles.json` already exists in the repo
|
||||
and is already copied into the Docker image
|
||||
(`runpod/Dockerfile`), but no loader reads it yet, and the native
|
||||
CMake build doesn't copy it into `build/` at all — `CMakeLists.txt`'s
|
||||
"Runtime Assets" step only copies `locations.json` and `prompts/`.
|
||||
- [x] Add `LoadPersonas()` and author `personas.json` (doesn't exist yet).
|
||||
- [x] Add name-by-country loading, parsing
|
||||
`tooling/pipeline/forenames-by-country.json` and
|
||||
`surnames-by-country.json`. Landed as two separate methods —
|
||||
`LoadForenamesByCountry()` and `LoadSurnamesByCountry()` — each
|
||||
returning a flat `ForenamesByCountryMap` / `SurnamesByCountryMap`
|
||||
(aliases for `unordered_map<string, ForenameList>` /
|
||||
`unordered_map<string, SurnameList>`) keyed by ISO 3166-1 code, rather
|
||||
than one combined `LoadNamesByCountry() : NamesByCountry` call. Both
|
||||
files are vendored verbatim (unmodified,
|
||||
full multinational coverage) from
|
||||
`sigpwned/popular-names-by-country-dataset` (CC0) — see
|
||||
ETHICS-AND-KNOWN-ISSUES.md's Names-by-Country Dataset section for
|
||||
provenance. Deliberately not pre-paired or filtered down to just the
|
||||
countries in `locations.json`: keeping the source shape (including
|
||||
per-forename gender) intact means the loader can support more
|
||||
countries later, or gender-aware persona/bio generation, without
|
||||
re-sourcing data.
|
||||
|
||||
## 3. Policy / Strategy Layer
|
||||
|
||||
Entirely new — no `includes/policy/` (or equivalent) directory exists today.
|
||||
|
||||
- [ ] `ContextStrategy` interface + `BreweryContextStrategy` /
|
||||
`BeerContextStrategy`. Today `WikipediaEnrichmentService::GetLocationContext`
|
||||
hardcodes a generic `"brewing"` query and a `"beer in {country}"`
|
||||
query directly — no per-phase strategy selection.
|
||||
- [ ] `SamplingStrategy` interface + `UniformSamplingStrategy`, replacing
|
||||
the inline `std::ranges::sample(...)` call in
|
||||
`BiergartenPipelineOrchestrator::QueryCitiesWithCountries()`.
|
||||
- [ ] `BeerSelectionStrategy` interface + `RandomBeerSelectionStrategy`, to
|
||||
pick styles per brewery from the `BeerStyle` palette (depends on §1
|
||||
and §2).
|
||||
- [ ] `CheckinDistributionStrategy` interface + `JCurveCheckinStrategy` /
|
||||
`RandomCheckinStrategy` — this is the "Check-In System" item already
|
||||
called out in README.md's Next Steps, made concrete.
|
||||
- [ ] `FollowGenerationStrategy` interface + `RandomFollowStrategy` /
|
||||
`ActivityWeightedFollowStrategy`.
|
||||
|
||||
## 4. Data Generation
|
||||
|
||||
`tooling/pipeline/includes/data_generation/`, `src/data_generation/`.
|
||||
|
||||
- [ ] Extend the `DataGenerator` interface with `GenerateBeer`,
|
||||
`GenerateCheckin`, `GenerateRating` (today: only `GenerateBrewery` and
|
||||
`GenerateUser`).
|
||||
- [x] Implement `LlamaGenerator::GenerateUser` for real, with a retry loop
|
||||
mirroring `GenerateBrewery` (GBNF grammar, `ValidateUserJson`, up to 3
|
||||
attempts with corrective feedback) and a new
|
||||
`prompts/USER_GENERATION.md`. Changed the `DataGenerator::GenerateUser`
|
||||
signature to
|
||||
`(city : const EnrichedCity&, persona : const UserPersona&, name : const Name&) : UserResult`,
|
||||
matching what the activity diagram actually passes. `MockGenerator::GenerateUser`
|
||||
updated to match the new signature too.
|
||||
- [ ] Implement `MockGenerator::GenerateBeer` / `GenerateCheckin` /
|
||||
`GenerateRating`.
|
||||
- [ ] Add `IPromptFormatter::ExpectedArchitecture()` and
|
||||
`LlamaGenerator::ValidateModelArchitecture()` so loading a GGUF that
|
||||
doesn't match the configured chat template fails fast instead of
|
||||
silently producing degraded output.
|
||||
- [ ] Add prompt template files for beer/checkin/rating generation next to
|
||||
the existing `prompts/BREWERY_GENERATION.md`.
|
||||
|
||||
## 5. Export Service
|
||||
|
||||
`tooling/pipeline/includes/services/database/`, `src/services/sqlite/`.
|
||||
|
||||
- [x] `IExportService::ProcessRecord(const UserRecord&)` and
|
||||
`SqliteExportService`'s `users` table (see
|
||||
`kCreateUsersTableSql` / `kInsertUserSql` in
|
||||
`includes/services/database/sqlite_statement_helpers.h`) are
|
||||
implemented — `GenerateUsers()` exports every successful user
|
||||
alongside its resolved `location_id`.
|
||||
- [ ] Extend `IExportService` with `ProcessBeer`, `ProcessCheckin`,
|
||||
`ProcessRating`, `ProcessFollow` (today `ProcessRecord(const
|
||||
BreweryRecord&)` and `ProcessRecord(const UserRecord&)` exist).
|
||||
- [ ] Add `beers`, `checkins`, `ratings`, `follows` tables to
|
||||
`SqliteExportService::InitializeSchema()` (`locations`, `breweries`,
|
||||
and `users` already exist) — see `kCreateLocationsTableSql` /
|
||||
`kCreateBreweriesTableSql` / `kCreateUsersTableSql` in
|
||||
`includes/services/database/sqlite_statement_helpers.h` for the
|
||||
existing pattern to follow.
|
||||
- [ ] Add a `brewery_cache_` alongside the existing `location_cache_`, and
|
||||
move from one open transaction for the whole run to per-phase batched
|
||||
commits (`BEGIN` / `COMMIT & BEGIN` on a batch-size threshold), as
|
||||
shown in the planned activity diagram.
|
||||
|
||||
## 6. Concurrency & Orchestration
|
||||
|
||||
`tooling/pipeline/includes/concurrency/`,
|
||||
`src/biergarten_pipeline_orchestrator/`.
|
||||
|
||||
- [ ] `BoundedChannel<T>` already exists and is production-tested — but
|
||||
it's only wired to the single log channel today. Stand up the
|
||||
per-phase producer/consumer channels (`loc_ch`, `exp_ch`, etc.) the
|
||||
planned activity diagram describes, each with a dedicated LLM worker
|
||||
thread and SQLite worker thread.
|
||||
- [ ] Rewrite `BiergartenPipelineOrchestrator::Run()` from one synchronous
|
||||
pass over `generated_breweries_` into phased methods —
|
||||
`RunUserPhase` → `RunBreweryAndBeerPhase` (with a `RunBeerPhase`
|
||||
sub-step once `brewery_pool_` is populated) → `RunCheckinPhase` /
|
||||
`RunFollowPhase` (these two can run in parallel) → `RunRatingPhase` —
|
||||
backed by `user_pool_`, `brewery_pool_`, `beer_pool_`,
|
||||
`checkin_pool_`, `follow_pool_`.
|
||||
- [ ] Honor the structural-concurrency requirement already called out in a
|
||||
comment on `BiergartenPipelineOrchestrator::Run()` in
|
||||
`biergarten_pipeline_orchestrator.h`: once real worker threads exist,
|
||||
they must be structurally joined (e.g. via `std::jthread`) before
|
||||
`Run()` returns, so no worker logs to a closed channel during
|
||||
teardown.
|
||||
|
||||
## 7. Enrichment
|
||||
|
||||
- [ ] Decide whether to restore the city/region-specific Wikipedia query
|
||||
that's currently commented out in
|
||||
`src/services/enrichment/wikipedia/get_summary.cc`
|
||||
(`GetLocationContext`). The `ContextStrategy` work in §3 is a natural
|
||||
place to reintroduce it via `BreweryContextStrategy::QueriesFor()`.
|
||||
- [ ] Pre-warm caches at startup (`PreWarmBeerStyleCache`,
|
||||
`PreWarmLocationCache` in the planned activity diagram) instead of
|
||||
fetching lazily per record, so the streaming phases never block on a
|
||||
cold cache mid-run.
|
||||
|
||||
## 8. Fixtures / Build
|
||||
|
||||
- [x] Author `personas.json`, `forenames-by-country.json`, and
|
||||
`surnames-by-country.json` (see §2).
|
||||
- [ ] Fix the `beer-styles.json` build-tree gap: add it to the "Runtime
|
||||
Assets" `configure_file` step in `CMakeLists.txt` so native builds and
|
||||
the Docker image agree on what's available at runtime.
|
||||
|
||||
---
|
||||
|
||||
## Suggested build order
|
||||
|
||||
The planned activity diagram's own phase notes ("brewery*pool* is now fully
|
||||
populated. Phase 1b may begin.", etc.) imply a dependency order. Roughly:
|
||||
|
||||
1. Domain models (§1) and data preloading (§2) — nothing else compiles
|
||||
without these.
|
||||
2. Export schema (§5) — so every later generation phase has somewhere to
|
||||
land its output.
|
||||
3. Policy/strategy layer (§3) and generator interface (§4).
|
||||
4. Concurrency/orchestration rewrite (§6), which is the only piece that
|
||||
actually wires §1–§5 into the phased, parallel pipeline shown in the
|
||||
planned diagrams.
|
||||
5. Enrichment cache pre-warming and the city/region query decision (§7) —
|
||||
useful at any point, but most valuable once phases run concurrently.
|
||||
@@ -1,34 +0,0 @@
|
||||
skinparam shadowing false
|
||||
skinparam backgroundColor #FCFCF7
|
||||
skinparam defaultFontName "DM Sans"
|
||||
skinparam defaultFontColor #14180C
|
||||
skinparam titleFontName "Volkhov"
|
||||
skinparam titleFontColor #14180C
|
||||
skinparam ArrowColor #656F33
|
||||
skinparam NoteBackgroundColor #DBEEDD
|
||||
skinparam NoteFontColor #14180C
|
||||
skinparam NoteBorderColor #4A5837
|
||||
skinparam SwimlaneBorderColor #4A5837
|
||||
skinparam SwimlaneBorderThickness 1
|
||||
skinparam activityStartColor #EBECE3
|
||||
skinparam activityEndColor #4A5837
|
||||
skinparam activityStopColor #4A5837
|
||||
skinparam ActivityBackgroundColor #EBECE3
|
||||
skinparam ActivityBorderColor #4A5837
|
||||
skinparam ActivityDiamondBackgroundColor #CBD2B5
|
||||
skinparam ActivityDiamondBorderColor #4A5837
|
||||
skinparam packageStyle rectangle
|
||||
skinparam packageBackgroundColor #F1F3EA
|
||||
skinparam packageBorderColor #4A5837
|
||||
skinparam packageFontColor #14180C
|
||||
skinparam classBackgroundColor #EBECE3
|
||||
skinparam classBorderColor #4A5837
|
||||
skinparam classFontColor #14180C
|
||||
skinparam classAttributeFontColor #3F4724
|
||||
skinparam classStereotypeFontColor #4A5837
|
||||
skinparam interfaceBackgroundColor #DBEEDD
|
||||
skinparam interfaceBorderColor #4A5837
|
||||
skinparam interfaceFontColor #14180C
|
||||
skinparam enumBackgroundColor #E4E6D8
|
||||
skinparam enumBorderColor #4A5837
|
||||
skinparam enumFontColor #14180C
|
||||
@@ -1,235 +0,0 @@
|
||||
@startuml
|
||||
skinparam style strictuml
|
||||
skinparam defaultFontName "DM Sans"
|
||||
skinparam defaultFontSize 14
|
||||
skinparam titleFontName "Volkhov"
|
||||
skinparam titleFontSize 20
|
||||
skinparam backgroundColor #FAFCF9
|
||||
skinparam defaultFontColor #28342A
|
||||
skinparam titleFontColor #28342A
|
||||
skinparam ArrowColor #628A5B
|
||||
skinparam NoteBackgroundColor #EAF0E8
|
||||
skinparam NoteBorderColor #547461
|
||||
skinparam ActivityBackgroundColor #FAFCF9
|
||||
skinparam ActivityBorderColor #547461
|
||||
skinparam ActivityDiamondBackgroundColor #FAFCF9
|
||||
skinparam ActivityDiamondBorderColor #628A5B
|
||||
skinparam ActivityBarColor #628A5B
|
||||
skinparam SwimlaneBorderColor #547461
|
||||
skinparam SwimlaneBorderThickness 0.3
|
||||
|
||||
title The Biergarten Data Pipeline (Current — Synchronous Data Path)
|
||||
|
||||
|#F2F6F0|main.cc|
|
||||
start
|
||||
:Create BoundedChannel<LogEntry> log_channel;
|
||||
:Spawn log dispatcher thread\n(LogDispatcher::Run());
|
||||
note right
|
||||
The only concurrency in the current pipeline:
|
||||
a dedicated thread drains log_channel and
|
||||
forwards entries to spdlog for the entire run.
|
||||
Joined during shutdown after log_channel closes.
|
||||
end note
|
||||
:ParseArguments(argc, argv);
|
||||
if (Are arguments valid?) then (no)
|
||||
:Log error / usage info;
|
||||
stop
|
||||
else (yes)
|
||||
endif
|
||||
|
||||
:Init OpenSSL global state & LlamaBackendState;
|
||||
:di::make_injector(...);
|
||||
note right
|
||||
Binds ILogger, IEnrichmentService, DataGenerator,
|
||||
IExportService, IPromptFormatter, WebClient based
|
||||
on --mocked vs. model-backed mode.
|
||||
end note
|
||||
:injector.create<std::unique_ptr<BiergartenPipelineOrchestrator>>();
|
||||
:BiergartenPipelineOrchestrator::Run();
|
||||
note right
|
||||
Run() itself is synchronous — sampling, enrichment,
|
||||
generation, and export all happen on this thread.
|
||||
end note
|
||||
|
||||
|#EAF0E8|BiergartenPipelineOrchestrator|
|
||||
:Initialize SQLite export;
|
||||
|
||||
|#E0EAE0|SqliteExportService|
|
||||
:GetUtcTimestamp() from SystemDateTimeProvider;
|
||||
:Initialize();
|
||||
note right
|
||||
Builds a fresh biergarten_seed_<UTC datetime>.sqlite filename
|
||||
Appends a numeric suffix if the timestamp already exists
|
||||
Opens DB Connection
|
||||
Executes Schema DDL
|
||||
Begins Transaction
|
||||
end note
|
||||
|
||||
|#EAF0E8|BiergartenPipelineOrchestrator|
|
||||
:QueryCitiesWithCountries();
|
||||
|
||||
|#E2EBDC|JsonLoader|
|
||||
:JsonLoader::LoadLocations("locations.json");
|
||||
:std::ranges::sample(all_locations, --location-count);
|
||||
note right
|
||||
--location-count defaults to 10.
|
||||
end note
|
||||
|
||||
|#EAF0E8|BiergartenPipelineOrchestrator|
|
||||
while (For each sampled Location?) is (Remaining cities)
|
||||
|#DCE8D8|IEnrichmentService|
|
||||
:GetLocationContext(loc);
|
||||
note right
|
||||
WikipediaEnrichmentService fetches a generic
|
||||
"brewing" extract and a "beer in {country}" extract
|
||||
(not a city/region-specific page). MockEnrichmentService
|
||||
(--mocked) returns an empty string instead.
|
||||
end note
|
||||
|#EAF0E8|BiergartenPipelineOrchestrator|
|
||||
if (Lookup failed?) then (yes)
|
||||
:Log warning, skip city;
|
||||
else (no)
|
||||
:Store EnrichedCity{Location, region_context};
|
||||
endif
|
||||
endwhile (Done)
|
||||
|
||||
|#EAF0E8|BiergartenPipelineOrchestrator|
|
||||
:GenerateUsers(enriched_cities);
|
||||
|
||||
|#E2EBDC|JsonLoader|
|
||||
:LoadPersonas("personas.json");
|
||||
:LoadForenamesByCountry("forenames-by-country.json");
|
||||
:LoadSurnamesByCountry("surnames-by-country.json");
|
||||
note right
|
||||
Each call is cached after its first parse.
|
||||
MockCuratedDataService (--mocked) returns a
|
||||
fixed in-memory dataset instead and skips
|
||||
these three JSON files entirely.
|
||||
end note
|
||||
|
||||
|#EAF0E8|BiergartenPipelineOrchestrator|
|
||||
while (For each EnrichedCity?) is (Remaining cities)
|
||||
:SampleName(forenames_by_country,\n surnames_by_country, location.iso3166_1);
|
||||
if (Names available for country?) then (no)
|
||||
:Log warning, skip city;
|
||||
else (yes)
|
||||
:Sample UserPersona (uniform random);
|
||||
|
||||
|#E5EDE1|DataGenerator|
|
||||
if (Generator Mode) then (MockGenerator)
|
||||
:DeterministicHash & Format;
|
||||
else (LlamaGenerator)
|
||||
:prompt_directory_->Load("USER_GENERATION");
|
||||
note right
|
||||
Resolves to USER_GENERATION.md inside --prompt-dir.
|
||||
end note
|
||||
repeat
|
||||
:Infer(system_prompt, user_prompt, max_tokens, kUserJsonGrammar);
|
||||
:ValidateUserJson(raw, user);
|
||||
if (Is JSON Valid?) then (yes)
|
||||
break
|
||||
else (no)
|
||||
:Attempt++;
|
||||
:Append validation error to retry prompt;
|
||||
endif
|
||||
repeat while (Attempt < 3?) is (yes)
|
||||
endif
|
||||
|
||||
|#EAF0E8|BiergartenPipelineOrchestrator|
|
||||
if (Generation successful?) then (yes)
|
||||
:BuildEmail(name, used_email_local_parts);
|
||||
:GenerateDateOfBirth(rng);
|
||||
note right
|
||||
email and date_of_birth are generated
|
||||
programmatically, never LLM-authored.
|
||||
end note
|
||||
|
||||
|#E0EAE0|SqliteExportService|
|
||||
:ProcessRecord(UserRecord);
|
||||
if (Location in cache?) then (yes)
|
||||
:Reuse location_id;
|
||||
else (no)
|
||||
:Insert Location & Cache ID;
|
||||
endif
|
||||
:Insert User (FK: location_id);
|
||||
|
||||
if (Exception caught during insert?) then (yes)
|
||||
|#EAF0E8|BiergartenPipelineOrchestrator|
|
||||
:Log warning "SQLite export failed";
|
||||
else (no)
|
||||
endif
|
||||
else (no)
|
||||
:Log warning "Generation failed, skipping...";
|
||||
endif
|
||||
endif
|
||||
endwhile (Done)
|
||||
|
||||
|#EAF0E8|BiergartenPipelineOrchestrator|
|
||||
:GenerateBreweries(enriched_cities);
|
||||
|
||||
|#E5EDE1|DataGenerator|
|
||||
while (For each EnrichedCity?) is (Remaining cities)
|
||||
if (Generator Mode) then (MockGenerator)
|
||||
:DeterministicHash & Format;
|
||||
else (LlamaGenerator)
|
||||
:PrepareRegionContext;
|
||||
:prompt_directory_->Load("BREWERY_GENERATION");
|
||||
note right
|
||||
Resolves to BREWERY_GENERATION.md inside --prompt-dir.
|
||||
end note
|
||||
repeat
|
||||
:Infer(system_prompt, user_prompt, max_tokens, kBreweryJsonGrammar);
|
||||
:ValidateBreweryJson(raw, brewery);
|
||||
if (Is JSON Valid?) then (yes)
|
||||
break
|
||||
else (no)
|
||||
:Attempt++;
|
||||
:Append validation error to retry prompt;
|
||||
endif
|
||||
repeat while (Attempt < 3?) is (yes)
|
||||
note right
|
||||
max_tokens is fixed across retries —
|
||||
it is not raised on truncation.
|
||||
end note
|
||||
endif
|
||||
|
||||
|#EAF0E8|BiergartenPipelineOrchestrator|
|
||||
if (Generation successful?) then (yes)
|
||||
|#E0EAE0|SqliteExportService|
|
||||
:ProcessRecord(GeneratedBrewery);
|
||||
if (Location in cache?) then (yes)
|
||||
:Reuse location_id;
|
||||
else (no)
|
||||
:Insert Location & Cache ID;
|
||||
endif
|
||||
:Insert Brewery (FK: location_id);
|
||||
|
||||
if (Exception caught during insert?) then (yes)
|
||||
|#EAF0E8|BiergartenPipelineOrchestrator|
|
||||
:Log warning "SQLite export failed";
|
||||
note right
|
||||
Data loss is prevented per-record.
|
||||
The pipeline continues running.
|
||||
end note
|
||||
else (no)
|
||||
endif
|
||||
else (no)
|
||||
:Log warning "Generation failed, skipping...";
|
||||
endif
|
||||
|#E5EDE1|DataGenerator|
|
||||
endwhile (Done)
|
||||
|
||||
|#E0EAE0|SqliteExportService|
|
||||
:Finalize();
|
||||
note right
|
||||
Commits Transaction
|
||||
Closes Database Connection
|
||||
end note
|
||||
|
||||
|#F2F6F0|main.cc|
|
||||
:Close log_channel;
|
||||
:Join log dispatcher thread;
|
||||
:Return 0;
|
||||
stop
|
||||
|
||||
@enduml
|
||||
@@ -1,269 +0,0 @@
|
||||
@startuml
|
||||
skinparam style strictuml
|
||||
skinparam defaultFontName "DM Sans"
|
||||
skinparam defaultFontSize 14
|
||||
skinparam titleFontName "Volkhov"
|
||||
skinparam titleFontSize 20
|
||||
skinparam backgroundColor #FAFCF9
|
||||
skinparam defaultFontColor #28342A
|
||||
skinparam titleFontColor #28342A
|
||||
skinparam ArrowColor #628A5B
|
||||
|
||||
skinparam class {
|
||||
BackgroundColor #FAFCF9
|
||||
HeaderBackgroundColor #EAF0E8
|
||||
BorderColor #547461
|
||||
ArrowColor #628A5B
|
||||
FontColor #28342A
|
||||
}
|
||||
|
||||
skinparam note {
|
||||
BackgroundColor #EAF0E8
|
||||
BorderColor #547461
|
||||
FontColor #28342A
|
||||
}
|
||||
|
||||
title The Biergarten Data Pipeline - Class Diagram
|
||||
|
||||
class BiergartenPipelineOrchestrator {
|
||||
- logger_ : std::shared_ptr<ILogger>
|
||||
- context_service_ : std::unique_ptr<IEnrichmentService>
|
||||
- generator_ : std::unique_ptr<DataGenerator>
|
||||
- exporter_ : std::unique_ptr<IExportService>
|
||||
- curated_data_service_ : std::unique_ptr<ICuratedDataService>
|
||||
- application_options_ : ApplicationOptions
|
||||
- generated_breweries_ : std::vector<BreweryRecord>
|
||||
- generated_users_ : std::vector<UserRecord>
|
||||
+ Run() : bool
|
||||
- QueryCitiesWithCountries() : std::vector<Location>
|
||||
- GenerateBreweries(cities : std::span<const EnrichedCity>) : void
|
||||
- GenerateUsers(cities : std::span<const EnrichedCity>) : void
|
||||
- LogResults() : void
|
||||
}
|
||||
|
||||
class LogLevel <<enumeration>> {
|
||||
Debug
|
||||
Info
|
||||
Warn
|
||||
Error
|
||||
}
|
||||
|
||||
class PipelinePhase <<enumeration>> {
|
||||
Startup
|
||||
UserGeneration
|
||||
BreweryAndBeerGeneration
|
||||
CheckinGeneration
|
||||
RatingGeneration
|
||||
FollowGeneration
|
||||
Teardown
|
||||
}
|
||||
|
||||
struct LogDTO {
|
||||
+ level : LogLevel
|
||||
+ phase : PipelinePhase
|
||||
+ message : std::string
|
||||
}
|
||||
|
||||
struct LogEntry {
|
||||
+ timestamp : std::chrono::system_clock::time_point
|
||||
+ origin : std::source_location
|
||||
+ thread_id : std::thread::id
|
||||
+ level : LogLevel
|
||||
+ phase : PipelinePhase
|
||||
+ message : std::string
|
||||
}
|
||||
|
||||
interface ILogger <<interface>> {
|
||||
+ Log(payload : LogDTO) : void
|
||||
- {abstract} DoLog(entry : LogEntry) : void
|
||||
}
|
||||
|
||||
class LogProducer {
|
||||
- channel_ : BoundedChannel<LogEntry>&
|
||||
- DoLog(entry : LogEntry) : void
|
||||
}
|
||||
|
||||
class LogDispatcher {
|
||||
- channel_ : BoundedChannel<LogEntry>&
|
||||
+ Run() : void
|
||||
- ToSpdlogLevel(level) : spdlog::level::level_enum
|
||||
}
|
||||
|
||||
interface IEnrichmentService <<interface>> {
|
||||
+ GetLocationContext(loc : const Location&) : std::string
|
||||
}
|
||||
|
||||
class MockEnrichmentService {
|
||||
+ GetLocationContext(loc : const Location&) : std::string
|
||||
}
|
||||
|
||||
class WikipediaEnrichmentService {
|
||||
- client_ : std::unique_ptr<WebClient>
|
||||
- extract_cache_ : std::unordered_map<std::string, std::string>
|
||||
+ GetLocationContext(loc : const Location&) : std::string
|
||||
- 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 HttpWebClient {
|
||||
+ Get(url : const std::string&) : std::string
|
||||
+ UrlEncode(value : const std::string&) : std::string
|
||||
}
|
||||
|
||||
interface DataGenerator <<interface>> {
|
||||
+ GenerateBrewery(location : const Location&, region_context : const std::string&) : BreweryResult
|
||||
+ GenerateUser(city : const EnrichedCity&, persona : const UserPersona&, name : const Name&) : UserResult
|
||||
}
|
||||
|
||||
class MockGenerator {
|
||||
+ GenerateBrewery(location : const Location&, region_context : const std::string&) : BreweryResult
|
||||
+ GenerateUser(city : const EnrichedCity&, persona : const UserPersona&, name : const Name&) : UserResult
|
||||
- DeterministicHash(location : const Location&) : size_t
|
||||
- DeterministicHash(location : const Location&, persona : const UserPersona&, name : const Name&) : size_t
|
||||
}
|
||||
|
||||
class LlamaGenerator {
|
||||
- model_ : ModelHandle
|
||||
- context_ : ContextHandle
|
||||
- prompt_formatter_ : std::unique_ptr<IPromptFormatter>
|
||||
- prompt_directory_ : std::unique_ptr<IPromptDirectory>
|
||||
- rng_ : std::mt19937
|
||||
+ GenerateBrewery(...) : BreweryResult
|
||||
+ GenerateUser(...) : UserResult
|
||||
- Load(model_path : const std::string&) : void
|
||||
- Infer(...) : std::string
|
||||
- InferFormatted(...) : std::string
|
||||
}
|
||||
|
||||
interface IPromptFormatter <<interface>> {
|
||||
+ Format(system_prompt : std::string_view, user_prompt : std::string_view) : std::string
|
||||
}
|
||||
|
||||
class Gemma4JinjaPromptFormatter {
|
||||
+ Format(system_prompt : std::string_view, user_prompt : std::string_view) : std::string
|
||||
}
|
||||
|
||||
interface IPromptDirectory <<interface>> {
|
||||
+ Load(key : std::string_view) : std::string
|
||||
}
|
||||
|
||||
class PromptDirectory {
|
||||
- prompt_dir_ : std::filesystem::path
|
||||
- cache_ : std::unordered_map<std::string, std::string>
|
||||
+ Load(key : std::string_view) : std::string
|
||||
}
|
||||
|
||||
interface ICuratedDataService <<interface>> {
|
||||
+ LoadLocations(filepath : const std::filesystem::path&) : const std::vector<Location>&
|
||||
+ LoadPersonas(filepath : const std::filesystem::path&) : const std::vector<UserPersona>&
|
||||
+ LoadForenamesByCountry(filepath : const std::filesystem::path&) : const std::unordered_map<std::string, forename_list>&
|
||||
+ LoadSurnamesByCountry(filepath : const std::filesystem::path&) : const std::unordered_map<std::string, surname_list>&
|
||||
}
|
||||
|
||||
class JsonLoader {
|
||||
- cache_ : cache
|
||||
+ LoadLocations(filepath : const std::filesystem::path&) : const std::vector<Location>&
|
||||
+ LoadPersonas(filepath : const std::filesystem::path&) : const std::vector<UserPersona>&
|
||||
+ LoadForenamesByCountry(filepath : const std::filesystem::path&) : const std::unordered_map<std::string, forename_list>&
|
||||
+ LoadSurnamesByCountry(filepath : const std::filesystem::path&) : const std::unordered_map<std::string, surname_list>&
|
||||
}
|
||||
|
||||
note right of JsonLoader
|
||||
Each Load* method memoizes its result in
|
||||
cache_ on first call; later calls on the
|
||||
same instance return the cached value
|
||||
without re-parsing.
|
||||
end note
|
||||
|
||||
class MockCuratedDataService {
|
||||
- locations_ : std::vector<Location>
|
||||
- personas_ : std::vector<UserPersona>
|
||||
- forenames_by_country_ : std::unordered_map<std::string, forename_list>
|
||||
- surnames_by_country_ : std::unordered_map<std::string, surname_list>
|
||||
+ LoadLocations(filepath : const std::filesystem::path&) : const std::vector<Location>&
|
||||
+ LoadPersonas(filepath : const std::filesystem::path&) : const std::vector<UserPersona>&
|
||||
+ LoadForenamesByCountry(filepath : const std::filesystem::path&) : const std::unordered_map<std::string, forename_list>&
|
||||
+ LoadSurnamesByCountry(filepath : const std::filesystem::path&) : const std::unordered_map<std::string, surname_list>&
|
||||
}
|
||||
|
||||
note right of MockCuratedDataService
|
||||
Fixed 4-location / 3-persona dataset
|
||||
(US, DE, FR, BE) used in --mocked runs;
|
||||
filepath arguments are ignored.
|
||||
end note
|
||||
|
||||
interface IExportService <<interface>> {
|
||||
+ Initialize() : void
|
||||
+ ProcessRecord(brewery : const BreweryRecord&) : uint64_t
|
||||
+ ProcessRecord(user : const UserRecord&) : uint64_t
|
||||
+ Finalize() : void
|
||||
}
|
||||
|
||||
class SqliteExportService {
|
||||
- date_time_provider_ : std::unique_ptr<IDateTimeProvider>
|
||||
- run_timestamp_utc_ : std::string
|
||||
- database_path_ : std::filesystem::path
|
||||
- db_handle_ : SqliteDatabaseHandle
|
||||
- insert_location_stmt_ : SqliteStatementHandle
|
||||
- insert_brewery_stmt_ : SqliteStatementHandle
|
||||
- insert_user_stmt_ : SqliteStatementHandle
|
||||
- transaction_open_ : bool
|
||||
- location_cache_ : std::unordered_map<std::string, sqlite3_int64>
|
||||
+ Initialize() : void
|
||||
+ ProcessRecord(brewery : const BreweryRecord&) : uint64_t
|
||||
+ ProcessRecord(user : const UserRecord&) : uint64_t
|
||||
+ Finalize() : void
|
||||
- InitializeSchema() : void
|
||||
- ResolveLocationId(location : const Location&) : sqlite3_int64
|
||||
}
|
||||
|
||||
interface IDateTimeProvider <<interface>> {
|
||||
+ GetUtcTimestamp() : std::string
|
||||
}
|
||||
|
||||
class SystemDateTimeProvider {
|
||||
+ GetUtcTimestamp() : std::string
|
||||
}
|
||||
|
||||
' Structural Relationships / Dependency Injection
|
||||
BiergartenPipelineOrchestrator *-- ILogger : owns
|
||||
BiergartenPipelineOrchestrator *-- IEnrichmentService : owns
|
||||
BiergartenPipelineOrchestrator *-- DataGenerator : owns
|
||||
BiergartenPipelineOrchestrator *-- IExportService : owns
|
||||
BiergartenPipelineOrchestrator *-- ICuratedDataService : owns
|
||||
|
||||
LogEntry *-- LogLevel
|
||||
LogEntry *-- PipelinePhase
|
||||
LogDTO *-- LogLevel
|
||||
LogDTO *-- PipelinePhase
|
||||
ILogger <|.. LogProducer : implements
|
||||
LogProducer ..> LogEntry : emits
|
||||
LogDispatcher ..> LogEntry : consumes
|
||||
|
||||
IEnrichmentService <|.. WikipediaEnrichmentService : implements
|
||||
IEnrichmentService <|.. MockEnrichmentService : implements
|
||||
WikipediaEnrichmentService *-- WebClient : owns
|
||||
|
||||
WebClient <|.. HttpWebClient : implements
|
||||
|
||||
DataGenerator <|.. MockGenerator : implements
|
||||
DataGenerator <|.. LlamaGenerator : implements
|
||||
|
||||
LlamaGenerator *-- IPromptFormatter : uses
|
||||
LlamaGenerator *-- IPromptDirectory : uses
|
||||
|
||||
IPromptFormatter <|.. Gemma4JinjaPromptFormatter : implements
|
||||
IPromptDirectory <|.. PromptDirectory : implements
|
||||
|
||||
ICuratedDataService <|.. JsonLoader : implements
|
||||
ICuratedDataService <|.. MockCuratedDataService : implements
|
||||
|
||||
IExportService <|.. SqliteExportService : implements
|
||||
SqliteExportService *-- IDateTimeProvider : owns
|
||||
IDateTimeProvider <|.. SystemDateTimeProvider : implements
|
||||
|
||||
@enduml
|
||||
File diff suppressed because one or more lines are too long
|
Before Width: | Height: | Size: 86 KiB |
File diff suppressed because one or more lines are too long
|
Before Width: | Height: | Size: 87 KiB |
@@ -1,372 +0,0 @@
|
||||
@startuml biergarten_activity
|
||||
!include ../biergarten-weizen-theme.puml
|
||||
skinparam defaultFontSize 13
|
||||
skinparam titleFontSize 20
|
||||
|
||||
title The Biergarten Data Pipeline — Activity Diagram
|
||||
|
||||
|Main|
|
||||
start
|
||||
:ParseArguments(argc, argv);
|
||||
if (Invalid args?) then (yes)
|
||||
:spdlog::error;
|
||||
stop
|
||||
else (no)
|
||||
endif
|
||||
:Init OpenSSL global state & LlamaBackendState;
|
||||
:Build DI injector;
|
||||
|
||||
:Initialize SqliteExportService;
|
||||
note right
|
||||
Opens SQLite connection.
|
||||
(Transactions are now managed
|
||||
per-phase via batching).
|
||||
end note
|
||||
|
||||
:Create BoundedChannel<LogEntry> log_ch;
|
||||
:Spawn Log Worker thread;
|
||||
note right
|
||||
Log worker drains log_ch for the
|
||||
entire pipeline lifetime.
|
||||
All workers emit LogEntry structs
|
||||
via PipelineLogger -- never spdlog directly.
|
||||
end note
|
||||
|
||||
:BiergartenPipelineOrchestrator::Run();
|
||||
|BiergartenPipelineOrchestrator::Run()|
|
||||
|
||||
fork
|
||||
:JsonLoader::LoadBeerStyles("beer-styles.json");
|
||||
:EnrichmentService::PreWarmBeerStyleCache(beer_styles);
|
||||
fork again
|
||||
:JsonLoader::LoadLocations("locations.json");
|
||||
:EnrichmentService::PreWarmLocationCache(sampled_locations);
|
||||
end fork
|
||||
fork
|
||||
:JsonLoader::LoadForenamesByCountry(\n "forenames-by-country.json");
|
||||
fork again
|
||||
:JsonLoader::LoadSurnamesByCountry(\n "surnames-by-country.json");
|
||||
fork again
|
||||
:JsonLoader::LoadPersonas("personas.json");
|
||||
end fork
|
||||
note right
|
||||
Each call is memoized after its first parse
|
||||
(implemented today). MockCuratedDataService
|
||||
returns a fixed in-memory dataset instead
|
||||
under --mocked, skipping these JSON files.
|
||||
end note
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' PHASE 0 — USER GENERATION
|
||||
' ═══════════════════════════════════════════
|
||||
|Orchestrator|
|
||||
:RunUserPhase(sampled_locations);
|
||||
:Create BoundedChannels\n(loc_ch, exp_ch);
|
||||
|
||||
fork
|
||||
|Orchestrator|
|
||||
:Loop: Send Locations -> loc_ch;
|
||||
:Close loc_ch;
|
||||
note right
|
||||
Producer closes loc_ch.
|
||||
LLM Worker while loop
|
||||
terminates on empty + closed.
|
||||
end note
|
||||
fork again
|
||||
|LLM Worker|
|
||||
while (loc_ch has items?) is (yes)
|
||||
:Receive Location;
|
||||
|
||||
:GetLocationContextFromCache(location);
|
||||
note right
|
||||
Guaranteed cache hit from startup.
|
||||
end note
|
||||
|
||||
:IPersonaSelectionStrategy::SelectPersona(\n personas_palette_);
|
||||
note right
|
||||
Guaranteed cache hit from startup.
|
||||
Returns a Persona struct carrying
|
||||
style_affinities, abv_range,
|
||||
ibu_preference, checkin_weight.
|
||||
end note
|
||||
|
||||
:SampleName(forenames_by_country,\n surnames_by_country, location.iso3166_1, rng);
|
||||
note right
|
||||
Deterministic lookup -- no LLM involved.
|
||||
Free function (implemented today in
|
||||
generate_users.cc), not a class method.
|
||||
Name selected from pre-keyed maps
|
||||
and passed into the generation prompt.
|
||||
Skips the city if either map has no
|
||||
entry for iso3166_1.
|
||||
end note
|
||||
|
||||
:GenerateUser(enriched_city, persona, sampled_name)\nvia DataGenerator;
|
||||
note right
|
||||
LLM receives: EnrichedCity context + persona
|
||||
description + sampled name. Generates
|
||||
bio and preference signals grounded
|
||||
in locale and persona.
|
||||
end note
|
||||
|
||||
:PipelineLogger::Log(Info, UserGeneration,\n city, user_id, "llm");
|
||||
:Send GeneratedUser -> exp_ch;
|
||||
endwhile (no)
|
||||
:Close exp_ch;
|
||||
note right
|
||||
Producer closes exp_ch.
|
||||
SQLite Worker while loop
|
||||
terminates on empty + closed.
|
||||
end note
|
||||
fork again
|
||||
|SQLite Worker|
|
||||
:BEGIN TRANSACTION;
|
||||
while (exp_ch has items?) is (yes)
|
||||
:Receive GeneratedUser;
|
||||
:ProcessUser(user);
|
||||
:PipelineLogger::Log(Info, UserGeneration,\n city, user_id, "sqlite");
|
||||
:Append -> user_pool_;
|
||||
if (Batch size reached?) then (yes)
|
||||
:COMMIT & BEGIN;
|
||||
else (no)
|
||||
endif
|
||||
endwhile (no)
|
||||
:COMMIT (Final);
|
||||
end fork
|
||||
|
||||
|Orchestrator|
|
||||
:Join LLM Worker, SQLite Worker;
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' PHASE 1a — BREWERY GENERATION
|
||||
' ═══════════════════════════════════════════
|
||||
:RunBreweryPhase(sampled_locations);
|
||||
:Create BoundedChannels\n(loc_ch, exp_ch);
|
||||
|
||||
fork
|
||||
|Orchestrator|
|
||||
:Loop: Sample User from user_pool_
|
||||
and pair with Location;
|
||||
:Send BreweryTask(Location, User) -> loc_ch;
|
||||
:Close loc_ch;
|
||||
fork again
|
||||
|LLM Worker|
|
||||
while (loc_ch has items?) is (yes)
|
||||
:Receive BreweryTask(Location, User);
|
||||
|
||||
:GetLocationContextFromCache(task.location);
|
||||
note right
|
||||
Guaranteed cache hit from startup.
|
||||
end note
|
||||
|
||||
:GenerateBrewery(enriched_city, context, task.user)\nvia DataGenerator;
|
||||
note right
|
||||
KV cache stays warm.
|
||||
Brewery is linked to the sampled owner_user_id.
|
||||
end note
|
||||
:PipelineLogger::Log(Info,\n BreweryGeneration,\n city, brewery_id, "llm");
|
||||
:Send GeneratedBrewery -> exp_ch;
|
||||
endwhile (no)
|
||||
:Close exp_ch;
|
||||
fork again
|
||||
|SQLite Worker|
|
||||
:BEGIN TRANSACTION;
|
||||
while (exp_ch has items?) is (yes)
|
||||
:Receive GeneratedBrewery;
|
||||
:ProcessBrewery(brewery);
|
||||
:PipelineLogger::Log(Info,\n BreweryGeneration,\n city, brewery_id, "sqlite");
|
||||
:Append -> brewery_pool_;
|
||||
if (Batch size reached?) then (yes)
|
||||
:COMMIT & BEGIN;
|
||||
else (no)
|
||||
endif
|
||||
endwhile (no)
|
||||
:COMMIT (Final);
|
||||
end fork
|
||||
|
||||
|Orchestrator|
|
||||
:Join LLM Worker, SQLite Worker;
|
||||
note right
|
||||
brewery_pool_ is now fully populated.
|
||||
Phase 1b may begin.
|
||||
end note
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' PHASE 1b — BEER GENERATION
|
||||
' ═══════════════════════════════════════════
|
||||
:RunBeerPhase();
|
||||
:Create BoundedChannels\n(brew_ch, exp_ch);
|
||||
|
||||
fork
|
||||
|Orchestrator|
|
||||
:Loop: Send Breweries -> brew_ch;
|
||||
:Close brew_ch;
|
||||
fork again
|
||||
|LLM Worker|
|
||||
while (brew_ch has items?) is (yes)
|
||||
:Receive GeneratedBrewery;
|
||||
:IBeerSelectionStrategy::SelectStyles(\n brewery, beer_style_palette_);
|
||||
|
||||
while (For each selected BeerStyle?) is (remaining)
|
||||
:GetStyleContextFromCache(style);
|
||||
note right
|
||||
Guaranteed cache hit from startup.
|
||||
KV cache stays warm across all
|
||||
beer generations -- system prompt
|
||||
does not change within this phase.
|
||||
end note
|
||||
:GenerateBeer(brewery, style_context)\nvia DataGenerator;
|
||||
:Attach GeneratedBeer to bundle;
|
||||
endwhile (done)
|
||||
|
||||
:PipelineLogger::Log(Info,\n BeerGeneration,\n city, brewery_id, "llm");
|
||||
:Send BeersBundle -> exp_ch;
|
||||
endwhile (no)
|
||||
:Close exp_ch;
|
||||
fork again
|
||||
|SQLite Worker|
|
||||
:BEGIN TRANSACTION;
|
||||
while (exp_ch has items?) is (yes)
|
||||
:Receive BeersBundle;
|
||||
while (For each beer in bundle?) is (remaining)
|
||||
:Set beer.brewery_id from bundle;
|
||||
:ProcessBeer(beer);
|
||||
:Append -> beer_pool_;
|
||||
endwhile (done)
|
||||
:PipelineLogger::Log(Info,\n BeerGeneration,\n city, brewery_id, "sqlite");
|
||||
if (Batch size reached?) then (yes)
|
||||
:COMMIT & BEGIN;
|
||||
else (no)
|
||||
endif
|
||||
endwhile (no)
|
||||
:COMMIT (Final);
|
||||
end fork
|
||||
|
||||
|Orchestrator|
|
||||
:Join LLM Worker, SQLite Worker;
|
||||
note right
|
||||
Both brewery_pool_ and beer_pool_
|
||||
are now completely populated.
|
||||
Checkin and Follow phases may
|
||||
now run in parallel.
|
||||
end note
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' PHASE 2 — CHECKIN + FOLLOW GENERATION
|
||||
' (parallel — both depend only on user_pool_
|
||||
' and brewery_pool_ being fully populated)
|
||||
' ═══════════════════════════════════════════
|
||||
fork
|
||||
|Orchestrator|
|
||||
:RunCheckinPhase();
|
||||
:ICheckinDistributionStrategy::\nAssignActivityWeights(user_pool_);
|
||||
note right
|
||||
Weights seeded from each user's
|
||||
persona.checkin_weight. J-curve profile
|
||||
emerges from persona distribution.
|
||||
end note
|
||||
|
||||
:BEGIN TRANSACTION;
|
||||
while (For each GeneratedUser in user_pool_?) is (remaining)
|
||||
:CheckinsForUser(user, brewery_pool_.size());
|
||||
while (For each checkin index?) is (remaining)
|
||||
:TimestampFor(user, index);
|
||||
:Select brewery from brewery_pool_;
|
||||
:GenerateCheckin(user, brewery, timestamp)\nvia DataGenerator;
|
||||
:ProcessCheckin(checkin);
|
||||
:PipelineLogger::Log(Info, CheckinGeneration,\n nullopt, checkin_id, "sqlite");
|
||||
:Append -> checkin_pool_;
|
||||
if (Batch size reached?) then (yes)
|
||||
:COMMIT & BEGIN;
|
||||
else (no)
|
||||
endif
|
||||
endwhile (done)
|
||||
endwhile (done)
|
||||
:COMMIT (Final);
|
||||
|
||||
fork again
|
||||
|Orchestrator|
|
||||
:RunFollowPhase();
|
||||
:IFollowGenerationStrategy::\nAssignFollowWeights(user_pool_);
|
||||
note right
|
||||
For RandomFollowStrategy, weights
|
||||
are uniform. For ActivityWeightedFollowStrategy,
|
||||
weights derived from user.activity_weight
|
||||
so high-activity users attract more followers.
|
||||
end note
|
||||
|
||||
:BEGIN TRANSACTION;
|
||||
:IFollowGenerationStrategy::\nGenerateFollows(user_pool_);
|
||||
note right
|
||||
Self-follow constraint (follower_id != followed_id)
|
||||
enforced here and at the DB schema level.
|
||||
end note
|
||||
while (For each GeneratedFollow?) is (remaining)
|
||||
:ProcessFollow(follow);
|
||||
:PipelineLogger::Log(Info, FollowGeneration,\n nullopt, follower_id, "sqlite");
|
||||
:Append -> follow_pool_;
|
||||
if (Batch size reached?) then (yes)
|
||||
:COMMIT & BEGIN;
|
||||
else (no)
|
||||
endif
|
||||
endwhile (done)
|
||||
:COMMIT (Final);
|
||||
|
||||
end fork
|
||||
|
||||
|Orchestrator|
|
||||
:Join CheckinPhase, FollowPhase;
|
||||
note right
|
||||
checkin_pool_ and follow_pool_
|
||||
are now fully populated.
|
||||
Rating phase may begin.
|
||||
end note
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' PHASE 3 — RATING GENERATION
|
||||
' ═══════════════════════════════════════════
|
||||
:RunRatingPhase();
|
||||
note right
|
||||
Beer selection biased by
|
||||
user.persona.style_affinities and abv_range.
|
||||
Rating skew modulated per persona.
|
||||
end note
|
||||
|
||||
:BEGIN TRANSACTION;
|
||||
while (For each GeneratedCheckin in checkin_pool_?) is (remaining)
|
||||
:Match brewery_id, select beer from beer_pool_\n(same brewery_id, biased by persona affinities);
|
||||
if (Beer exists for brewery?) then (yes)
|
||||
:GenerateRating(user, beer, checkin_id)\nvia DataGenerator;
|
||||
:ProcessRating(rating);
|
||||
:PipelineLogger::Log(Info, RatingGeneration,\n nullopt, rating_id, "sqlite");
|
||||
if (Batch size reached?) then (yes)
|
||||
:COMMIT & BEGIN;
|
||||
else (no)
|
||||
endif
|
||||
else (no)
|
||||
:PipelineLogger::Log(Warn, RatingGeneration,\n nullopt, brewery_id, "sqlite");
|
||||
:Skip -- brewery has no beers;
|
||||
endif
|
||||
endwhile (done)
|
||||
:COMMIT (Final);
|
||||
|
||||
' ═══════════════════════════════════════════
|
||||
' TEARDOWN
|
||||
' ═══════════════════════════════════════════
|
||||
|Orchestrator|
|
||||
:Finalize SqliteExportService;
|
||||
note right
|
||||
Safely closes the DB connection.
|
||||
end note
|
||||
:Close log_ch;
|
||||
|
||||
|Main|
|
||||
:spdlog::info "Pipeline complete in X ms";
|
||||
:Join Log Worker;
|
||||
note right
|
||||
Drain guarantees no LogEntry is
|
||||
dropped at shutdown.
|
||||
end note
|
||||
stop
|
||||
|
||||
@enduml
|
||||
@@ -1,646 +0,0 @@
|
||||
@startuml class_diagram
|
||||
|
||||
' ==========================================
|
||||
' CONFIGURATION & STYLING
|
||||
' ==========================================
|
||||
!include ../biergarten-weizen-theme.puml
|
||||
skinparam classAttributeFontSize 9
|
||||
skinparam defaultFontSize 25
|
||||
skinparam titleFontSize 30
|
||||
|
||||
title Biergarten Data Pipeline — Class Diagram
|
||||
|
||||
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 {
|
||||
+ 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
|
||||
}
|
||||
|
||||
note right of ForenameEntry
|
||||
forename_list = std::unordered_set<ForenameEntry>
|
||||
surname_list = std::unordered_set<std::string>
|
||||
(aliases declared in curated_data_service.h).
|
||||
ICuratedDataService::LoadForenamesByCountry() /
|
||||
LoadSurnamesByCountry() each return a flat
|
||||
std::unordered_map<std::string, forename_list>
|
||||
or <std::string, surname_list> keyed by ISO
|
||||
3166-1 country code -- no NamesByCountry
|
||||
wrapper class. SampleName(forenames_by_country,
|
||||
surnames_by_country, iso3166_1, rng) is a free
|
||||
function, not a method, so it can be called by
|
||||
any per-city worker without owning the maps.
|
||||
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
|
||||
|
||||
ForenameEntry ..> Name : SampleName() produces
|
||||
|
||||
class CheckinResult {
|
||||
+ checked_in_at : std::string
|
||||
+ note : std::string
|
||||
}
|
||||
|
||||
class RatingResult {
|
||||
+ score : float
|
||||
+ note : std::string
|
||||
}
|
||||
|
||||
class GenerationMetadata {
|
||||
+ generation_id : uint64_t
|
||||
+ generated_time : std::string
|
||||
+ context_provided : bool
|
||||
+ generated_with : std::string
|
||||
}
|
||||
|
||||
class GeneratedBrewery {
|
||||
+ brewery_id : uint64_t
|
||||
+ location : Location
|
||||
+ brewery : BreweryResult
|
||||
+ context_completeness : LocationContext::Completeness
|
||||
+ metadata : GenerationMetadata
|
||||
}
|
||||
|
||||
class GeneratedBeer {
|
||||
+ beer_id : uint64_t
|
||||
+ brewery_id : uint64_t
|
||||
+ location : Location
|
||||
+ style : BeerStyle
|
||||
+ beer : BeerResult
|
||||
+ metadata : GenerationMetadata
|
||||
}
|
||||
|
||||
class GeneratedUser {
|
||||
+ 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
|
||||
+ brewery_id : uint64_t
|
||||
+ checkin : CheckinResult
|
||||
+ metadata : GenerationMetadata
|
||||
}
|
||||
|
||||
class GeneratedRating {
|
||||
+ user_id : uint64_t
|
||||
+ beer_id : uint64_t
|
||||
+ checkin_id : uint64_t
|
||||
+ rating : RatingResult
|
||||
+ metadata : GenerationMetadata
|
||||
}
|
||||
|
||||
class GeneratedFollow {
|
||||
+ follower_id : uint64_t
|
||||
+ followed_id : uint64_t
|
||||
+ metadata : GenerationMetadata
|
||||
}
|
||||
|
||||
class UserPersona {
|
||||
+ name: std::string
|
||||
+ description: std::string
|
||||
+ style_affinities: std::vector<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: std::optional<SamplingOptions>
|
||||
}
|
||||
|
||||
class PipelineOptions {
|
||||
+ output_path: std::filesystem::path
|
||||
+ log_path: std::filesystem::path
|
||||
}
|
||||
|
||||
class ApplicationOptions {
|
||||
+ generator: GeneratorOptions
|
||||
+ pipeline: PipelineOptions
|
||||
}
|
||||
|
||||
ApplicationOptions *-- GeneratorOptions
|
||||
ApplicationOptions *-- PipelineOptions
|
||||
GeneratorOptions o-- 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
|
||||
}
|
||||
|
||||
class RandomCheckinStrategy {
|
||||
- rng_ : std::mt19937
|
||||
- min_checkins_ : size_t
|
||||
- max_checkins_ : size_t
|
||||
+ 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
|
||||
}
|
||||
|
||||
interface FollowGenerationStrategy <<interface>> {
|
||||
+ GenerateFollows(users : const std::vector<GeneratedUser>&) : std::vector<GeneratedFollow>
|
||||
}
|
||||
|
||||
class RandomFollowStrategy {
|
||||
- rng_ : std::mt19937
|
||||
- min_follows_ : size_t
|
||||
- max_follows_ : size_t
|
||||
+ GenerateFollows(users : const std::vector<GeneratedUser>&) : std::vector<GeneratedFollow>
|
||||
}
|
||||
|
||||
class ActivityWeightedFollowStrategy {
|
||||
- rng_ : std::mt19937
|
||||
- min_follows_ : size_t
|
||||
- max_follows_ : size_t
|
||||
+ GenerateFollows(users : const std::vector<GeneratedUser>&) : std::vector<GeneratedFollow>
|
||||
}
|
||||
}
|
||||
|
||||
package "Infrastructure: Logging" {
|
||||
enum LogLevel {
|
||||
Debug
|
||||
Info
|
||||
Warn
|
||||
Error
|
||||
}
|
||||
|
||||
enum PipelinePhase {
|
||||
Startup
|
||||
UserGeneration
|
||||
BreweryAndBeerGeneration
|
||||
CheckinGeneration
|
||||
RatingGeneration
|
||||
FollowGeneration
|
||||
Teardown
|
||||
}
|
||||
|
||||
class LogEntry {
|
||||
+ timestamp : std::chrono::system_clock::time_point
|
||||
+ level : LogLevel
|
||||
+ phase : PipelinePhase
|
||||
+ message : std::string
|
||||
+ worker : std::optional<std::string>
|
||||
}
|
||||
|
||||
interface ILogger <<interface>> {
|
||||
+ Log(entry : const LogEntry&) : void
|
||||
}
|
||||
|
||||
class LogProducer {
|
||||
- channel_ : BoundedChannel<LogEntry>&
|
||||
+ Log(entry : const LogEntry&) : void
|
||||
}
|
||||
|
||||
class LogDispatcher {
|
||||
- channel_ : BoundedChannel<LogEntry>&
|
||||
+ Run() : void
|
||||
- ToSpdlogLevel(level) : spdlog::level::level_enum
|
||||
}
|
||||
|
||||
LogEntry *-- LogLevel
|
||||
LogEntry *-- PipelinePhase
|
||||
ILogger <|.. LogProducer
|
||||
LogProducer ..> LogEntry : emits
|
||||
LogDispatcher ..> 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 ICuratedDataService <<interface>> {
|
||||
+ LoadLocations(filepath : const std::filesystem::path&) : const std::vector<Location>&
|
||||
+ LoadBeerStyles(filepath : const std::filesystem::path&) : const std::vector<BeerStyle>&
|
||||
+ LoadPersonas(filepath : const std::filesystem::path&) : const std::vector<UserPersona>&
|
||||
+ LoadForenamesByCountry(forenames_filepath : const std::filesystem::path&) : const std::unordered_map<std::string, forename_list>&
|
||||
+ LoadSurnamesByCountry(surnames_filepath : const std::filesystem::path&) : const std::unordered_map<std::string, surname_list>&
|
||||
}
|
||||
|
||||
class JsonLoader {
|
||||
+ LoadLocations(filepath : const std::filesystem::path&) : const std::vector<Location>&
|
||||
+ LoadBeerStyles(filepath : const std::filesystem::path&) : const std::vector<BeerStyle>&
|
||||
+ LoadPersonas(filepath : const std::filesystem::path&) : const std::vector<UserPersona>&
|
||||
+ LoadForenamesByCountry(forenames_filepath : const std::filesystem::path&) : const std::unordered_map<std::string, forename_list>&
|
||||
+ LoadSurnamesByCountry(surnames_filepath : const std::filesystem::path&) : const std::unordered_map<std::string, surname_list>&
|
||||
}
|
||||
|
||||
note right of JsonLoader
|
||||
Each Load* call is memoized after its first
|
||||
parse -- implemented today, ahead of the rest
|
||||
of this package (LoadBeerStyles is still planned).
|
||||
end note
|
||||
|
||||
class MockCuratedDataService {
|
||||
+ LoadLocations(filepath : const std::filesystem::path&) : const std::vector<Location>&
|
||||
+ LoadBeerStyles(filepath : const std::filesystem::path&) : const std::vector<BeerStyle>&
|
||||
+ LoadPersonas(filepath : const std::filesystem::path&) : const std::vector<UserPersona>&
|
||||
+ LoadForenamesByCountry(forenames_filepath : const std::filesystem::path&) : const std::unordered_map<std::string, forename_list>&
|
||||
+ LoadSurnamesByCountry(surnames_filepath : const std::filesystem::path&) : const std::unordered_map<std::string, surname_list>&
|
||||
}
|
||||
|
||||
note right of MockCuratedDataService
|
||||
Fixed in-memory dataset used in --mocked mode,
|
||||
implemented today for Locations/Personas/
|
||||
Forenames/Surnames; would need a LoadBeerStyles
|
||||
fixture too once that method is implemented.
|
||||
end note
|
||||
|
||||
}
|
||||
|
||||
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 HttpWebClient {
|
||||
+ Get(url : const std::string&) : std::string
|
||||
+ UrlEncode(value : const std::string&) : std::string
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
package "Infrastructure: Prompting" {
|
||||
|
||||
interface IPromptDirectory <<interface>> {
|
||||
+ Load(key : std::string_view) : std::string
|
||||
}
|
||||
|
||||
class PromptDirectory {
|
||||
- prompt_dir_ : std::filesystem::path
|
||||
- cache_ : std::unordered_map<std::string, std::string>
|
||||
+ PromptDirectory(prompt_dir : const std::filesystem::path&)
|
||||
+ Load(key : std::string_view) : std::string
|
||||
}
|
||||
|
||||
IPromptDirectory <|.. PromptDirectory
|
||||
}
|
||||
|
||||
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(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
|
||||
}
|
||||
|
||||
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>
|
||||
- prompt_directory_ : std::unique_ptr<IPromptDirectory>
|
||||
- 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&) : uint64_t
|
||||
+ ProcessBeer(beer : const GeneratedBeer&) : uint64_t
|
||||
+ ProcessUser(user : const GeneratedUser&) : uint64_t
|
||||
+ ProcessCheckin(checkin : const GeneratedCheckin&) : uint64_t
|
||||
+ ProcessRating(rating : const GeneratedRating&) : void
|
||||
+ ProcessFollow(follow : const GeneratedFollow&) : 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
|
||||
- insert_follow_stmt_ : SqliteStatementHandle
|
||||
- transaction_open_ : bool
|
||||
- location_cache_ : std::unordered_map<std::string, uint64_t>
|
||||
- brewery_cache_ : std::unordered_map<std::string, uint64_t>
|
||||
+ Initialize() : void
|
||||
+ ProcessRecord(brewery : const GeneratedBrewery&) : uint64_t
|
||||
+ ProcessRecord(beer : const GeneratedBeer&) : uint64_t
|
||||
+ ProcessRecord(user : const GeneratedUser&) : uint64_t
|
||||
+ ProcessRecord(checkin : const GeneratedCheckin&) : uint64_t
|
||||
+ ProcessRecord(rating : const GeneratedRating&) : void
|
||||
+ ProcessRecord(follow : const GeneratedFollow&) : void
|
||||
+ Finalize() : void
|
||||
- InitializeSchema() : void
|
||||
- PrepareStatements() : void
|
||||
- RollbackAndCloseNoThrow() : void
|
||||
- FinalizeStatements() : void
|
||||
}
|
||||
|
||||
interface DateTimeProvider <<interface>> {
|
||||
+ GetUtcTimestamp() : std::string
|
||||
}
|
||||
|
||||
class SystemDateTimeProvider {
|
||||
+ GetUtcTimestamp() : std::string
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
class BiergartenPipelineOrchestrator {
|
||||
- curated_data_service_ : std::unique_ptr<ICuratedDataService>
|
||||
- enrichment_service_ : std::unique_ptr<EnrichmentService>
|
||||
- generator_ : std::unique_ptr<DataGenerator>
|
||||
- logger_ : std::unique_ptr<Logger>
|
||||
- exporter_ : std::unique_ptr<ExportService>
|
||||
- brewery_context_strategy_ : std::unique_ptr<ContextStrategy>
|
||||
- sampling_strategy_ : std::unique_ptr<SamplingStrategy>
|
||||
- beer_selection_strategy_ : std::unique_ptr<BeerSelectionStrategy>
|
||||
- checkin_strategy_ : std::unique_ptr<CheckinDistributionStrategy>
|
||||
- follow_strategy_ : std::unique_ptr<FollowGenerationStrategy>
|
||||
- beer_style_palette_ : std::vector<BeerStyle>
|
||||
- options_ : ApplicationOptions
|
||||
--
|
||||
- user_pool_ : std::vector<GeneratedUser>
|
||||
- brewery_pool_ : std::vector<GeneratedBrewery>
|
||||
- beer_pool_ : std::vector<GeneratedBeer>
|
||||
- checkin_pool_ : std::vector<GeneratedCheckin>
|
||||
- follow_pool_ : std::vector<GeneratedFollow>
|
||||
--
|
||||
+ Run() : bool
|
||||
- RunUserPhase(locations : const std::vector<Location>&) : void
|
||||
- RunBreweryAndBeerPhase(locations : const std::vector<Location>&) : void
|
||||
- RunCheckinPhase() : void
|
||||
- RunRatingPhase() : void
|
||||
- RunFollowPhase() : void
|
||||
}
|
||||
|
||||
' --- Orchestration Aggregations (Services & Strategies) ---
|
||||
BiergartenPipelineOrchestrator *-- ICuratedDataService
|
||||
BiergartenPipelineOrchestrator *-- EnrichmentService
|
||||
BiergartenPipelineOrchestrator *-- DataGenerator
|
||||
BiergartenPipelineOrchestrator *-- ExportService
|
||||
BiergartenPipelineOrchestrator *-- CheckinDistributionStrategy
|
||||
BiergartenPipelineOrchestrator *-- FollowGenerationStrategy
|
||||
BiergartenPipelineOrchestrator *-- SamplingStrategy
|
||||
BiergartenPipelineOrchestrator *-- BeerSelectionStrategy
|
||||
BiergartenPipelineOrchestrator *-- ApplicationOptions
|
||||
BiergartenPipelineOrchestrator *-- Logger
|
||||
|
||||
' --- Orchestration Aggregations (Data Pools) ---
|
||||
BiergartenPipelineOrchestrator *-- "0..*" GeneratedUser : user_pool_
|
||||
BiergartenPipelineOrchestrator *-- "0..*" GeneratedBrewery : brewery_pool_
|
||||
BiergartenPipelineOrchestrator *-- "0..*" GeneratedBeer : beer_pool_
|
||||
BiergartenPipelineOrchestrator *-- "0..*" GeneratedCheckin : checkin_pool_
|
||||
BiergartenPipelineOrchestrator *-- "0..*" GeneratedFollow : follow_pool_
|
||||
|
||||
' --- Interfaces & Implementations ---
|
||||
ICuratedDataService <|.. JsonLoader
|
||||
ICuratedDataService <|.. MockCuratedDataService
|
||||
Logger <|.. PipelineLogger
|
||||
ContextStrategy <|.. BreweryContextStrategy
|
||||
ContextStrategy <|.. BeerContextStrategy
|
||||
SamplingStrategy <|.. UniformSamplingStrategy
|
||||
BeerSelectionStrategy <|.. RandomBeerSelectionStrategy
|
||||
CheckinDistributionStrategy <|.. JCurveCheckinStrategy
|
||||
CheckinDistributionStrategy <|.. RandomCheckinStrategy
|
||||
FollowGenerationStrategy <|.. RandomFollowStrategy
|
||||
FollowGenerationStrategy <|.. ActivityWeightedFollowStrategy
|
||||
EnrichmentService <|.. WikipediaService
|
||||
WebClient <|.. HttpWebClient
|
||||
DataGenerator <|.. MockGenerator
|
||||
DataGenerator <|.. LlamaGenerator
|
||||
PromptFormatter <|.. Gemma4JinjaPromptFormatter
|
||||
ExportService <|.. SqliteExportService
|
||||
DateTimeProvider <|.. SystemDateTimeProvider
|
||||
|
||||
' --- Service Compositions & Dependencies ---
|
||||
WikipediaService *-- WebClient
|
||||
WikipediaService ..> ContextStrategy
|
||||
LlamaGenerator *-- PromptFormatter
|
||||
LlamaGenerator *-- IPromptDirectory
|
||||
LlamaGenerator ..> GeneratorOptions
|
||||
SqliteExportService *-- DateTimeProvider
|
||||
|
||||
' --- Cross-Component Aggregations (Held References) ---
|
||||
PipelineLogger o-- BoundedChannel : logs to
|
||||
LogWorker o-- BoundedChannel : drains from
|
||||
|
||||
' --- Domain Containment ---
|
||||
EnrichedCity *-- Location
|
||||
EnrichedCity *-- LocationContext
|
||||
GeneratedBrewery *-- Location
|
||||
GeneratedBrewery *-- BreweryResult
|
||||
GeneratedBrewery *-- GenerationMetadata
|
||||
GeneratedBeer *-- Location
|
||||
GeneratedBeer *-- BeerStyle
|
||||
GeneratedBeer *-- BeerResult
|
||||
GeneratedBeer *-- GenerationMetadata
|
||||
GeneratedUser *-- Location
|
||||
GeneratedUser *-- UserResult
|
||||
GeneratedUser *-- GenerationMetadata
|
||||
GeneratedCheckin *-- CheckinResult
|
||||
GeneratedCheckin *-- GenerationMetadata
|
||||
GeneratedRating *-- RatingResult
|
||||
GeneratedRating *-- GenerationMetadata
|
||||
GeneratedFollow *-- GenerationMetadata
|
||||
|
||||
@enduml
|
||||
File diff suppressed because one or more lines are too long
|
Before Width: | Height: | Size: 142 KiB |
File diff suppressed because one or more lines are too long
|
Before Width: | Height: | Size: 240 KiB |
340
docs/testing.md
Normal file
340
docs/testing.md
Normal file
@@ -0,0 +1,340 @@
|
||||
# Testing
|
||||
|
||||
This document describes the testing strategy and how to run tests for The Biergarten App.
|
||||
|
||||
## Overview
|
||||
|
||||
The project uses a multi-layered testing approach across backend and frontend:
|
||||
|
||||
- **API.Specs** - BDD integration tests using Reqnroll (Gherkin)
|
||||
- **Infrastructure.Repository.Tests** - Unit tests for data access layer
|
||||
- **Service.Auth.Tests** - Unit tests for authentication business logic
|
||||
- **Storybook Vitest project** - Browser-based interaction tests for shared website stories
|
||||
- **Storybook Playwright suite** - Browser checks against Storybook-rendered components
|
||||
|
||||
## Running Tests with Docker (Recommended)
|
||||
|
||||
The easiest way to run all tests is using Docker Compose, which sets up an isolated test
|
||||
environment:
|
||||
|
||||
```bash
|
||||
docker compose -f docker-compose.test.yaml up --abort-on-container-exit
|
||||
```
|
||||
|
||||
This command:
|
||||
|
||||
1. Starts a fresh SQL Server instance
|
||||
2. Runs database migrations
|
||||
3. Seeds test data
|
||||
4. Executes all test suites in parallel
|
||||
5. Exports results to `./test-results/`
|
||||
6. Exits when tests complete
|
||||
|
||||
### View Test Results
|
||||
|
||||
```bash
|
||||
# List test result files
|
||||
ls -la test-results/
|
||||
|
||||
# View specific test results
|
||||
cat test-results/api-specs/results.trx
|
||||
cat test-results/repository-tests/results.trx
|
||||
cat test-results/service-auth-tests/results.trx
|
||||
```
|
||||
|
||||
### Clean Up
|
||||
|
||||
```bash
|
||||
# Remove test containers and volumes
|
||||
docker compose -f docker-compose.test.yaml down -v
|
||||
```
|
||||
|
||||
## Running Tests Locally
|
||||
|
||||
You can run individual test projects locally without Docker:
|
||||
|
||||
### Integration Tests (API.Specs)
|
||||
|
||||
```bash
|
||||
cd src/Core
|
||||
dotnet test API/API.Specs/API.Specs.csproj
|
||||
```
|
||||
|
||||
**Requirements**:
|
||||
|
||||
- SQL Server instance running
|
||||
- Database migrated and seeded
|
||||
- Environment variables set (DB connection, JWT secret)
|
||||
|
||||
### Repository Tests
|
||||
|
||||
```bash
|
||||
cd src/Core
|
||||
dotnet test Infrastructure/Infrastructure.Repository.Tests/Infrastructure.Repository.Tests.csproj
|
||||
```
|
||||
|
||||
**Requirements**:
|
||||
|
||||
- SQL Server instance running (uses mock data)
|
||||
|
||||
### Service Tests
|
||||
|
||||
```bash
|
||||
cd src/Core
|
||||
dotnet test Service/Service.Auth.Tests/Service.Auth.Tests.csproj
|
||||
```
|
||||
|
||||
**Requirements**:
|
||||
|
||||
- No database required (uses Moq for mocking)
|
||||
|
||||
### Frontend Storybook Tests
|
||||
|
||||
```bash
|
||||
cd src/Website
|
||||
npm install
|
||||
npm run test:storybook
|
||||
```
|
||||
|
||||
**Purpose**:
|
||||
|
||||
- Verifies shared stories such as form fields, submit buttons, navbar states, toasts, and the theme gallery
|
||||
- Runs in browser mode via Vitest and Storybook integration
|
||||
|
||||
### Frontend Playwright Storybook Tests
|
||||
|
||||
```bash
|
||||
cd src/Website
|
||||
npm install
|
||||
npm run test:storybook:playwright
|
||||
```
|
||||
|
||||
**Requirements**:
|
||||
|
||||
- Storybook dependencies installed
|
||||
- Playwright browser dependencies installed
|
||||
- The command will start or reuse the Storybook server defined in `playwright.storybook.config.ts`
|
||||
|
||||
## Test Coverage
|
||||
|
||||
### Current Coverage
|
||||
|
||||
**Authentication & User Management**:
|
||||
|
||||
- User registration with validation
|
||||
- User login with JWT token generation
|
||||
- Password hashing and verification (Argon2id)
|
||||
- JWT token generation and claims
|
||||
- Invalid credentials handling
|
||||
- 404 error responses
|
||||
|
||||
**Repository Layer**:
|
||||
|
||||
- User account creation
|
||||
- User credential management
|
||||
- GetUserByUsername queries
|
||||
- Stored procedure execution
|
||||
|
||||
**Service Layer**:
|
||||
|
||||
- Login service with password verification
|
||||
- Register service with validation
|
||||
- Business logic for authentication flow
|
||||
|
||||
**Frontend UI Coverage**:
|
||||
|
||||
- Shared submit button states
|
||||
- Form field happy path and error presentation
|
||||
- Navbar guest, authenticated, and mobile behavior
|
||||
- Theme gallery rendering across Biergarten themes
|
||||
- Toast interactions and themed notification display
|
||||
|
||||
### Planned Coverage
|
||||
|
||||
- [ ] Email verification workflow
|
||||
- [ ] Password reset functionality
|
||||
- [ ] Token refresh mechanism
|
||||
- [ ] Brewery data management
|
||||
- [ ] Beer post operations
|
||||
- [ ] User follow/unfollow
|
||||
- [ ] Image upload service
|
||||
- [ ] Frontend route integration coverage beyond Storybook stories
|
||||
|
||||
## Testing Frameworks & Tools
|
||||
|
||||
### xUnit
|
||||
|
||||
- Primary unit testing framework
|
||||
- Used for Repository and Service layer tests
|
||||
- Supports parallel test execution
|
||||
|
||||
### Reqnroll (Gherkin/BDD)
|
||||
|
||||
- Behavior-driven development framework
|
||||
- Used for API integration tests
|
||||
- Human-readable test scenarios in `.feature` files
|
||||
|
||||
### FluentAssertions
|
||||
|
||||
- Expressive assertion library
|
||||
- Makes test assertions more readable
|
||||
- Used across all test projects
|
||||
|
||||
### Moq
|
||||
|
||||
- Mocking framework for .NET
|
||||
- Used in Service layer tests
|
||||
- Enables isolated unit testing
|
||||
|
||||
### DbMocker
|
||||
|
||||
- Database mocking for repository tests
|
||||
- Simulates SQL Server responses
|
||||
- No real database required for unit tests
|
||||
|
||||
## Test Structure
|
||||
|
||||
### API.Specs (Integration Tests)
|
||||
|
||||
```
|
||||
API.Specs/
|
||||
├── Features/
|
||||
│ ├── Authentication.feature # Login/register scenarios
|
||||
│ └── UserManagement.feature # User CRUD scenarios
|
||||
├── Steps/
|
||||
│ ├── AuthenticationSteps.cs # Step definitions
|
||||
│ └── UserManagementSteps.cs
|
||||
└── Mocks/
|
||||
└── TestApiFactory.cs # Test server setup
|
||||
```
|
||||
|
||||
**Example Feature**:
|
||||
|
||||
```gherkin
|
||||
Feature: User Authentication
|
||||
As a user
|
||||
I want to register and login
|
||||
So that I can access the platform
|
||||
|
||||
Scenario: Successful user registration
|
||||
Given I have valid registration details
|
||||
When I register a new account
|
||||
Then I should receive a JWT token
|
||||
And my account should be created
|
||||
```
|
||||
|
||||
### Infrastructure.Repository.Tests
|
||||
|
||||
```
|
||||
Infrastructure.Repository.Tests/
|
||||
├── AuthRepositoryTests.cs # Auth repository tests
|
||||
├── UserAccountRepositoryTests.cs # User account tests
|
||||
└── TestFixtures/
|
||||
└── DatabaseFixture.cs # Shared test setup
|
||||
```
|
||||
|
||||
### Service.Auth.Tests
|
||||
|
||||
```
|
||||
Service.Auth.Tests/
|
||||
├── LoginService.test.cs # Login business logic tests
|
||||
└── RegisterService.test.cs # Registration business logic tests
|
||||
```
|
||||
|
||||
## Writing Tests
|
||||
|
||||
### Unit Test Example (xUnit)
|
||||
|
||||
```csharp
|
||||
public class LoginServiceTests
|
||||
{
|
||||
[Fact]
|
||||
public async Task LoginAsync_ValidCredentials_ReturnsToken()
|
||||
{
|
||||
// Arrange
|
||||
var mockRepo = new Mock<IAuthRepository>();
|
||||
var mockJwt = new Mock<IJwtService>();
|
||||
var service = new AuthService(mockRepo.Object, mockJwt.Object);
|
||||
|
||||
// Act
|
||||
var result = await service.LoginAsync("testuser", "password123");
|
||||
|
||||
// Assert
|
||||
result.Should().NotBeNull();
|
||||
result.Token.Should().NotBeNullOrEmpty();
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Integration Test Example (Reqnroll)
|
||||
|
||||
```gherkin
|
||||
Scenario: User login with valid credentials
|
||||
Given a registered user with username "testuser"
|
||||
When I POST to "/api/auth/login" with valid credentials
|
||||
Then the response status should be 200
|
||||
And the response should contain a JWT token
|
||||
```
|
||||
|
||||
## Continuous Integration
|
||||
|
||||
Tests run automatically in CI/CD pipelines using the test Docker Compose configuration:
|
||||
|
||||
```bash
|
||||
# CI/CD command
|
||||
docker compose -f docker-compose.test.yaml build
|
||||
docker compose -f docker-compose.test.yaml up --abort-on-container-exit
|
||||
docker compose -f docker-compose.test.yaml down -v
|
||||
```
|
||||
|
||||
Exit codes:
|
||||
|
||||
- `0` - All tests passed
|
||||
- Non-zero - Test failures occurred
|
||||
|
||||
Frontend UI checks should also be included in CI for the active website workspace:
|
||||
|
||||
```bash
|
||||
cd src/Website
|
||||
npm ci
|
||||
npm run test:storybook
|
||||
npm run test:storybook:playwright
|
||||
```
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Tests Failing Due to Database Connection
|
||||
|
||||
Ensure SQL Server is running and environment variables are set:
|
||||
|
||||
```bash
|
||||
docker compose -f docker-compose.test.yaml ps
|
||||
```
|
||||
|
||||
### Port Conflicts
|
||||
|
||||
If port 1433 is in use, stop other SQL Server instances or modify the port in
|
||||
`docker-compose.test.yaml`.
|
||||
|
||||
### Stale Test Data
|
||||
|
||||
Clean up test database:
|
||||
|
||||
```bash
|
||||
docker compose -f docker-compose.test.yaml down -v
|
||||
```
|
||||
|
||||
### View Container Logs
|
||||
|
||||
```bash
|
||||
docker compose -f docker-compose.test.yaml logs <service-name>
|
||||
```
|
||||
|
||||
## Best Practices
|
||||
|
||||
1. **Isolation**: Each test should be independent and not rely on other tests
|
||||
2. **Cleanup**: Use fixtures and dispose patterns for resource cleanup
|
||||
3. **Mocking**: Mock external dependencies in unit tests
|
||||
4. **Descriptive Names**: Use clear, descriptive test method names
|
||||
5. **Arrange-Act-Assert**: Follow AAA pattern in unit tests
|
||||
6. **Given-When-Then**: Follow GWT pattern in BDD scenarios
|
||||
@@ -2,114 +2,85 @@
|
||||
|
||||
## Overview
|
||||
|
||||
The Core project validates JWTs across three token types:
|
||||
The Core project implements comprehensive JWT token validation across three token types:
|
||||
|
||||
- **Access Tokens**: Short-lived (1 hour) tokens for API authentication
|
||||
- **Refresh Tokens**: Long-lived (21 days) tokens for obtaining new access
|
||||
tokens
|
||||
- **Confirmation Tokens**: Short-lived (30 minutes) tokens for email
|
||||
confirmation
|
||||
- **Refresh Tokens**: Long-lived (21 days) tokens for obtaining new access tokens
|
||||
- **Confirmation Tokens**: Short-lived (30 minutes) tokens for email confirmation
|
||||
|
||||
## Components
|
||||
|
||||
### Infrastructure Layer
|
||||
|
||||
#### [ITokenInfrastructure](../../web/backend/Infrastructure/Infrastructure.Jwt/ITokenInfrastructure.cs)
|
||||
#### [ITokenInfrastructure](Infrastructure.Jwt/ITokenInfrastructure.cs)
|
||||
|
||||
Low-level JWT operations.
|
||||
|
||||
**Methods:**
|
||||
|
||||
- `GenerateJwt()` - Creates signed JWT tokens
|
||||
- `ValidateJwtAsync()` - Validates token signature, expiration, and format
|
||||
|
||||
**Implementation:**
|
||||
[JwtInfrastructure.cs](../../web/backend/Infrastructure/Infrastructure.Jwt/JwtInfrastructure.cs)
|
||||
|
||||
**Implementation:** [JwtInfrastructure.cs](Infrastructure.Jwt/JwtInfrastructure.cs)
|
||||
- Uses Microsoft.IdentityModel.JsonWebTokens.JsonWebTokenHandler
|
||||
- Algorithm: HS256 (HMAC-SHA256)
|
||||
- Validates token lifetime, signature, and well-formedness
|
||||
|
||||
### Features.Auth Slice
|
||||
### Service Layer
|
||||
|
||||
#### [ITokenService](../../web/backend/Features/Features.Auth/Services/ITokenService.cs)
|
||||
#### [ITokenValidationService](Service.Auth/ITokenValidationService.cs)
|
||||
|
||||
Both token generation and validation live on the same slice-internal
|
||||
service (there is no separate validation service/class).
|
||||
|
||||
**Generation methods:**
|
||||
|
||||
- `GenerateAccessToken(UserAccount)` - Creates 1-hour access token
|
||||
- `GenerateRefreshToken(UserAccount)` - Creates 21-day refresh token
|
||||
- `GenerateConfirmationToken(UserAccount)` - Creates 30-minute confirmation
|
||||
token
|
||||
|
||||
**Validation methods:**
|
||||
High-level token validation with context (token type, user extraction).
|
||||
|
||||
**Methods:**
|
||||
- `ValidateAccessTokenAsync(string token)` - Validates access tokens
|
||||
- `ValidateRefreshTokenAsync(string token)` - Validates refresh tokens
|
||||
- `ValidateConfirmationTokenAsync(string token)` - Validates confirmation tokens
|
||||
|
||||
**Returns (validation):** `ValidatedToken` record containing:
|
||||
|
||||
**Returns:** `ValidatedToken` record containing:
|
||||
- `UserId` (Guid)
|
||||
- `Username` (string)
|
||||
- `Principal` (ClaimsPrincipal) - Full JWT claims
|
||||
|
||||
**Implementation:** [TokenService.cs](../../web/backend/Features/Features.Auth/Services/TokenService.cs)
|
||||
|
||||
**Implementation:** [TokenValidationService.cs](Service.Auth/TokenValidationService.cs)
|
||||
- Reads token secrets from environment variables
|
||||
- Extracts and validates claims (Sub, UniqueName)
|
||||
- Throws `UnauthorizedException` on validation failure
|
||||
|
||||
`TokenService` is registered by `Features.Auth`'s own
|
||||
`AddFeaturesAuth()` extension method, except for the lower-level
|
||||
`ITokenInfrastructure` (JWT signing/verification) it depends on, which is
|
||||
registered by the host (`API.Core/Program.cs`) since
|
||||
`JwtAuthenticationHandler` (host-level auth middleware) also depends on
|
||||
it directly.
|
||||
#### [ITokenService](Service.Auth/ITokenService.cs)
|
||||
|
||||
Token generation (existing service extended).
|
||||
|
||||
**Methods:**
|
||||
- `GenerateAccessToken(UserAccount)` - Creates 1-hour access token
|
||||
- `GenerateRefreshToken(UserAccount)` - Creates 21-day refresh token
|
||||
- `GenerateConfirmationToken(UserAccount)` - Creates 30-minute confirmation token
|
||||
|
||||
### Integration Points
|
||||
|
||||
#### [ConfirmUserHandler](../../web/backend/Features/Features.Auth/Commands/ConfirmUser/ConfirmUserHandler.cs)
|
||||
#### [ConfirmationService](Service.Auth/IConfirmationService.cs)
|
||||
|
||||
**Flow:**
|
||||
|
||||
1. Receives confirmation token from user via `ConfirmUserCommand`
|
||||
2. Calls `ITokenService.ValidateConfirmationTokenAsync()`
|
||||
1. Receives confirmation token from user
|
||||
2. Calls `TokenValidationService.ValidateConfirmationTokenAsync()`
|
||||
3. Extracts user ID from validated token
|
||||
4. Calls `IAuthRepository.ConfirmUserAccountAsync()` to update database
|
||||
4. Calls `AuthRepository.ConfirmUserAccountAsync()` to update database
|
||||
5. Returns confirmation result
|
||||
|
||||
#### [ResendConfirmationEmailHandler](../../web/backend/Features/Features.Auth/Commands/ResendConfirmationEmail/ResendConfirmationEmailHandler.cs)
|
||||
#### [RefreshTokenService](Service.Auth/RefreshTokenService.cs)
|
||||
|
||||
**Flow:**
|
||||
1. Receives refresh token from user
|
||||
2. Calls `TokenValidationService.ValidateRefreshTokenAsync()`
|
||||
3. Retrieves user account via `AuthRepository.GetUserByIdAsync()`
|
||||
4. Issues new access and refresh tokens via `TokenService`
|
||||
5. Returns new token pair
|
||||
|
||||
1. Receives a user ID via `ResendConfirmationEmailCommand`
|
||||
2. Looks up the user and checks they aren't already verified
|
||||
3. Generates a fresh confirmation token via `ITokenService`
|
||||
4. Sends `SendResendConfirmationEmailCommand` over MediatR, handled by the
|
||||
`Features.Emails` slice, with no direct project reference between the two
|
||||
slices
|
||||
|
||||
#### [RefreshTokenHandler](../../web/backend/Features/Features.Auth/Commands/RefreshToken/RefreshTokenHandler.cs)
|
||||
|
||||
**Flow:**
|
||||
|
||||
1. Receives a refresh token via `RefreshTokenCommand`
|
||||
2. Delegates to `ITokenService.RefreshTokenAsync()`, which validates the
|
||||
token, retrieves the user account via `IAuthRepository.GetUserByIdAsync()`,
|
||||
and issues a new access/refresh token pair
|
||||
3. Maps the result onto `LoginPayload`
|
||||
|
||||
#### [AuthController](../../web/backend/Features/Features.Auth/Controllers/AuthController.cs)
|
||||
#### [AuthController](API.Core/Controllers/AuthController.cs)
|
||||
|
||||
**Endpoints:**
|
||||
|
||||
- `POST /api/auth/register` - Register new user
|
||||
- `POST /api/auth/login` - Authenticate user
|
||||
- `POST /api/auth/confirm?token=...` - Confirm email
|
||||
- `POST /api/auth/confirm/resend?userId=...` - Resend the confirmation email
|
||||
- `POST /api/auth/refresh` - Refresh access token
|
||||
|
||||
## Validation Security
|
||||
@@ -117,13 +88,11 @@ it directly.
|
||||
### Token Secrets
|
||||
|
||||
Three independent secrets enable:
|
||||
|
||||
- **Key rotation** - Rotate each secret type independently
|
||||
- **Isolation** - Compromise of one secret doesn't affect others
|
||||
- **Different expiration** - Different token types can expire at different rates
|
||||
|
||||
**Environment Variables:**
|
||||
|
||||
```bash
|
||||
ACCESS_TOKEN_SECRET=... # Signs 1-hour access tokens
|
||||
REFRESH_TOKEN_SECRET=... # Signs 21-day refresh tokens
|
||||
@@ -142,7 +111,6 @@ Each token is validated for:
|
||||
### Error Handling
|
||||
|
||||
Validation failures return HTTP 401 Unauthorized:
|
||||
|
||||
- Invalid signature → "Invalid token"
|
||||
- Expired token → "Invalid token" (message doesn't reveal reason for security)
|
||||
- Missing claims → "Invalid token"
|
||||
@@ -172,60 +140,42 @@ Validation failures return HTTP 401 Unauthorized:
|
||||
1. **Generation**: During user registration (30-minute validity)
|
||||
2. **Delivery**: Emailed to user in confirmation link
|
||||
3. **Usage**: User clicks link, token posted to `/api/auth/confirm`
|
||||
4. **Validation**: Validated by `ConfirmUserHandler`
|
||||
4. **Validation**: Validated by ConfirmationService
|
||||
5. **Completion**: User account marked as confirmed
|
||||
6. **Expiration**: Token becomes invalid after 30 minutes
|
||||
|
||||
## Testing
|
||||
|
||||
All of the following live in `Features.Auth.Tests`.
|
||||
|
||||
### Unit Tests
|
||||
|
||||
**Services/TokenServiceValidationTests.cs**
|
||||
|
||||
**TokenValidationService.test.cs**
|
||||
- Happy path: Valid token extraction
|
||||
- Error cases: Invalid, expired, malformed tokens
|
||||
- Missing/invalid claims scenarios
|
||||
|
||||
**Services/TokenServiceRefreshTests.cs**
|
||||
|
||||
**RefreshTokenService.test.cs**
|
||||
- Successful refresh with valid token
|
||||
- Invalid/expired refresh token rejection
|
||||
- Non-existent user handling
|
||||
|
||||
**Commands/RefreshTokenHandlerTests.cs**
|
||||
|
||||
- Verifies the handler maps `ITokenService.RefreshTokenAsync()`'s result onto
|
||||
`LoginPayload`
|
||||
|
||||
**Commands/ConfirmUserHandlerTests.cs**
|
||||
|
||||
**ConfirmationService.test.cs**
|
||||
- Successful confirmation with valid token
|
||||
- Token validation failures
|
||||
- User not found scenarios
|
||||
|
||||
**Commands/ResendConfirmationEmailHandlerTests.cs**
|
||||
|
||||
- Sends a fresh confirmation email when the user exists and is unverified
|
||||
- No-ops when the user doesn't exist or is already verified
|
||||
|
||||
### BDD Tests (Reqnroll)
|
||||
|
||||
**TokenRefresh.feature**
|
||||
|
||||
- Successful token refresh
|
||||
- Invalid/expired token rejection
|
||||
- Missing token validation
|
||||
|
||||
**Confirmation.feature**
|
||||
|
||||
- Successful email confirmation
|
||||
- Expired/tampered token rejection
|
||||
- Missing token validation
|
||||
|
||||
**AccessTokenValidation.feature**
|
||||
|
||||
- Protected endpoint access token validation
|
||||
- Invalid/expired access token rejection
|
||||
- Token type mismatch (refresh used as access token)
|
||||
File diff suppressed because one or more lines are too long
@@ -1,126 +0,0 @@
|
||||
@startuml architecture
|
||||
!theme plain
|
||||
skinparam backgroundColor #FFFFFF
|
||||
skinparam defaultFontName Arial
|
||||
skinparam packageStyle rectangle
|
||||
|
||||
title The Biergarten App - Vertical Slice Architecture
|
||||
|
||||
package "API.Core (thin host)" #E3F2FD {
|
||||
[API.Core\nASP.NET Core Web API host] as API
|
||||
note right of API
|
||||
- Program.cs wiring only
|
||||
- MediatR + AddApplicationPart
|
||||
per Features.* assembly
|
||||
- Swagger/OpenAPI, health checks
|
||||
- JWT auth middleware
|
||||
- Global exception filter
|
||||
end note
|
||||
}
|
||||
|
||||
package "Feature Slices" #F3E5F5 {
|
||||
[Features.Auth] as AuthSlice
|
||||
[Features.Breweries] as BrewerySlice
|
||||
[Features.UserManagement] as UserSlice
|
||||
[Features.Emails] as EmailsSlice
|
||||
note right of AuthSlice
|
||||
Each slice owns its own:
|
||||
- Controller (HTTP endpoints)
|
||||
- Commands/Queries + Handlers
|
||||
- Validators
|
||||
- Repository
|
||||
end note
|
||||
note right of EmailsSlice
|
||||
No controller - invoked only
|
||||
via MediatR commands sent
|
||||
from other slices
|
||||
end note
|
||||
}
|
||||
|
||||
package "Shared" #FCE4EC {
|
||||
[Shared.Contracts] as SharedContracts
|
||||
[Shared.Application] as SharedApp
|
||||
note right of SharedApp
|
||||
- ValidationBehavior
|
||||
(MediatR pipeline)
|
||||
- Cross-slice email commands
|
||||
(SendRegistrationEmailCommand,
|
||||
SendResendConfirmationEmailCommand)
|
||||
end note
|
||||
}
|
||||
|
||||
package "Infrastructure Layer" #FFF3E0 {
|
||||
[Infrastructure.Sql] as Sql
|
||||
[Infrastructure.Jwt] as JWT
|
||||
[Infrastructure.PasswordHashing] as PwdHash
|
||||
[Infrastructure.Email] as Email
|
||||
[Infrastructure.Email.Templates] as EmailTemplates
|
||||
}
|
||||
|
||||
package "Domain Layer" #E8F5E9 {
|
||||
[Domain.Entities] as Domain
|
||||
[Domain.Exceptions] as DomainExceptions
|
||||
note right of Domain
|
||||
- UserAccount
|
||||
- UserCredential
|
||||
- UserVerification
|
||||
- BreweryPost
|
||||
end note
|
||||
}
|
||||
|
||||
database "SQL Server" {
|
||||
[Stored Procedures] as SP
|
||||
[Tables] as Tables
|
||||
}
|
||||
|
||||
' Relationships
|
||||
API ..> AuthSlice : AddApplicationPart\n+ MediatR scan
|
||||
API ..> BrewerySlice : AddApplicationPart\n+ MediatR scan
|
||||
API ..> UserSlice : AddApplicationPart\n+ MediatR scan
|
||||
API ..> EmailsSlice : MediatR scan only\n(no controller)
|
||||
|
||||
AuthSlice --> Sql
|
||||
AuthSlice --> JWT
|
||||
AuthSlice --> PwdHash
|
||||
AuthSlice --> SharedContracts
|
||||
AuthSlice --> SharedApp
|
||||
|
||||
BrewerySlice --> Sql
|
||||
BrewerySlice --> SharedContracts
|
||||
BrewerySlice --> SharedApp
|
||||
|
||||
UserSlice --> Sql
|
||||
UserSlice --> SharedContracts
|
||||
UserSlice --> SharedApp
|
||||
|
||||
EmailsSlice --> Email
|
||||
EmailsSlice --> EmailTemplates
|
||||
EmailsSlice --> SharedApp
|
||||
|
||||
' The one cross-slice interaction: a MediatR command contract, not a project reference
|
||||
AuthSlice ..> SharedApp : sends\nSendRegistrationEmailCommand
|
||||
EmailsSlice ..> SharedApp : handles\nSendRegistrationEmailCommand
|
||||
|
||||
Sql --> SP
|
||||
Sql --> Domain
|
||||
SP --> Tables
|
||||
|
||||
AuthSlice --> Domain
|
||||
BrewerySlice --> Domain
|
||||
UserSlice --> Domain
|
||||
AuthSlice --> DomainExceptions
|
||||
|
||||
' Notes
|
||||
note left of Sql
|
||||
SQL-first approach
|
||||
All queries via
|
||||
stored procedures
|
||||
end note
|
||||
|
||||
note bottom of AuthSlice
|
||||
No Features.* project
|
||||
ever references another
|
||||
Features.* project directly
|
||||
end note
|
||||
|
||||
@enduml
|
||||
@@ -1,363 +0,0 @@
|
||||
# Testing
|
||||
|
||||
This document describes the testing strategy and how to run tests for The
|
||||
Biergarten App.
|
||||
|
||||
## Overview
|
||||
|
||||
The project uses a multi-layered testing approach across backend and frontend:
|
||||
|
||||
- **API.Specs** - BDD integration tests using Reqnroll (Gherkin), run against
|
||||
a live, seeded database
|
||||
- **Features.\*.Tests** - One unit test project per backend feature slice
|
||||
(`Features.Auth.Tests`, `Features.Breweries.Tests`,
|
||||
`Features.UserManagement.Tests`, `Features.Emails.Tests`), covering that
|
||||
slice's command/query handlers and its own repository (mocked with Moq /
|
||||
DbMocker, no real database required)
|
||||
- **Storybook Vitest project** - Browser-based interaction tests for shared
|
||||
website stories
|
||||
- **Storybook Playwright suite** - Browser checks against Storybook-rendered
|
||||
components
|
||||
|
||||
## Running Tests with Docker (Recommended)
|
||||
|
||||
The easiest way to run all tests is using Docker Compose, which sets up an
|
||||
isolated test environment:
|
||||
|
||||
```bash
|
||||
docker compose --env-file web/.env.test -f web/docker-compose.test.yaml up --abort-on-container-exit
|
||||
```
|
||||
|
||||
This command:
|
||||
|
||||
1. Starts a fresh SQL Server instance
|
||||
2. Runs database migrations
|
||||
3. Seeds test data
|
||||
4. Executes all test suites in parallel
|
||||
5. Exports results to `./test-results/`
|
||||
6. Exits when tests complete
|
||||
|
||||
### View Test Results
|
||||
|
||||
```bash
|
||||
# List test result files
|
||||
ls -la test-results/
|
||||
|
||||
# View specific test results
|
||||
cat test-results/api-specs/results.trx
|
||||
cat test-results/Features.Auth.Tests.trx
|
||||
cat test-results/Features.Breweries.Tests.trx
|
||||
cat test-results/Features.UserManagement.Tests.trx
|
||||
cat test-results/Features.Emails.Tests.trx
|
||||
```
|
||||
|
||||
### Clean Up
|
||||
|
||||
```bash
|
||||
# Remove test containers and volumes
|
||||
docker compose --env-file web/.env.test -f web/docker-compose.test.yaml down -v
|
||||
```
|
||||
|
||||
## Running Tests Locally
|
||||
|
||||
You can run individual test projects locally without Docker:
|
||||
|
||||
### Integration Tests (API.Specs)
|
||||
|
||||
```bash
|
||||
cd web/backend
|
||||
dotnet test API/API.Specs/API.Specs.csproj
|
||||
```
|
||||
|
||||
**Requirements**:
|
||||
|
||||
- SQL Server instance running
|
||||
- Database migrated and seeded
|
||||
- Environment variables set (DB connection, JWT secret)
|
||||
|
||||
### Feature Slice Unit Tests
|
||||
|
||||
Each feature slice has its own test project, covering its command/query
|
||||
handlers and repository:
|
||||
|
||||
```bash
|
||||
cd web/backend
|
||||
dotnet test Features/Features.Auth.Tests/Features.Auth.Tests.csproj
|
||||
dotnet test Features/Features.Breweries.Tests/Features.Breweries.Tests.csproj
|
||||
dotnet test Features/Features.UserManagement.Tests/Features.UserManagement.Tests.csproj
|
||||
dotnet test Features/Features.Emails.Tests/Features.Emails.Tests.csproj
|
||||
|
||||
# Or run all of them at once via the solution:
|
||||
for proj in Features/*.Tests; do dotnet test "$proj"; done
|
||||
```
|
||||
|
||||
**Requirements**:
|
||||
|
||||
- No database required (handlers use Moq; repository tests use DbMocker to
|
||||
simulate SQL Server responses)
|
||||
|
||||
### Frontend Storybook Tests
|
||||
|
||||
```bash
|
||||
cd web/frontend
|
||||
npm install
|
||||
npm run test:storybook
|
||||
```
|
||||
|
||||
**Purpose**:
|
||||
|
||||
- Verifies shared stories such as form fields, submit buttons, navbar states,
|
||||
toasts, and the theme gallery
|
||||
- Runs in browser mode via Vitest and Storybook integration
|
||||
|
||||
### Frontend Playwright Storybook Tests
|
||||
|
||||
```bash
|
||||
cd web/frontend
|
||||
npm install
|
||||
npm run test:storybook:playwright
|
||||
```
|
||||
|
||||
**Requirements**:
|
||||
|
||||
- Storybook dependencies installed
|
||||
- Playwright browser dependencies installed
|
||||
- The command will start or reuse the Storybook server defined in
|
||||
`playwright.storybook.config.ts`
|
||||
|
||||
## Test Coverage
|
||||
|
||||
### Current Coverage
|
||||
|
||||
**Features.Auth.Tests**:
|
||||
|
||||
- User registration with validation
|
||||
- User login with JWT token generation
|
||||
- Password hashing and verification (Argon2id)
|
||||
- Email confirmation and confirmation-email resend
|
||||
- Refresh token exchange
|
||||
- JWT token generation, validation, and claims handling
|
||||
- `IAuthRepository` data access (DbMocker-backed)
|
||||
- Invalid credentials and 404 error responses (via API.Specs)
|
||||
|
||||
**Features.Breweries.Tests**:
|
||||
|
||||
- Brewery create/update/delete commands and get-by-id/get-all queries
|
||||
|
||||
**Features.UserManagement.Tests**:
|
||||
|
||||
- User get-by-id/get-all queries and the (currently unrouted) update command
|
||||
|
||||
**Features.Emails.Tests**:
|
||||
|
||||
- Registration and resend-confirmation email dispatch handlers
|
||||
|
||||
**Frontend UI Coverage**:
|
||||
|
||||
- Shared submit button states
|
||||
- Form field happy path and error presentation
|
||||
- Navbar guest, authenticated, and mobile behavior
|
||||
- Theme gallery rendering across Biergarten themes
|
||||
- Toast interactions and themed notification display
|
||||
|
||||
### Planned Coverage
|
||||
|
||||
- [ ] Password reset functionality
|
||||
- [ ] Beer post operations
|
||||
- [ ] User follow/unfollow
|
||||
- [ ] Image upload service
|
||||
- [ ] Frontend route integration coverage beyond Storybook stories
|
||||
|
||||
## Testing Frameworks & Tools
|
||||
|
||||
### xUnit
|
||||
|
||||
- Primary unit testing framework
|
||||
- Used for Repository and Service layer tests
|
||||
- Supports parallel test execution
|
||||
|
||||
### Reqnroll (Gherkin/BDD)
|
||||
|
||||
- Behavior-driven development framework
|
||||
- Used for API integration tests
|
||||
- Human-readable test scenarios in `.feature` files
|
||||
|
||||
### FluentAssertions
|
||||
|
||||
- Expressive assertion library
|
||||
- Makes test assertions more readable
|
||||
- Used across all test projects
|
||||
|
||||
### Moq
|
||||
|
||||
- Mocking framework for .NET
|
||||
- Used in Service layer tests
|
||||
- Enables isolated unit testing
|
||||
|
||||
### DbMocker
|
||||
|
||||
- Database mocking for repository tests
|
||||
- Simulates SQL Server responses
|
||||
- No real database required for unit tests
|
||||
|
||||
## Test Structure
|
||||
|
||||
### API.Specs (Integration Tests)
|
||||
|
||||
```
|
||||
API.Specs/
|
||||
├── Features/
|
||||
│ ├── Registration.feature # Registration scenarios
|
||||
│ ├── Login.feature # Login scenarios
|
||||
│ ├── Confirmation.feature # Email confirmation scenarios
|
||||
│ ├── ResendConfirmation.feature # Resend-confirmation scenarios
|
||||
│ ├── TokenRefresh.feature # Refresh token scenarios
|
||||
│ ├── AccessTokenValidation.feature # Protected endpoint access scenarios
|
||||
│ └── NotFound.feature # 404 handling
|
||||
├── Steps/
|
||||
│ ├── AuthSteps.cs # Step definitions for the Auth features
|
||||
│ └── ApiGeneralSteps.cs # Shared/general step definitions
|
||||
├── Mocks/
|
||||
│ ├── MockEmailDispatcher.cs # Substitutes Features.Emails' IEmailDispatcher
|
||||
│ └── MockEmailProvider.cs # Substitutes Infrastructure.Email's IEmailProvider
|
||||
└── TestApiFactory.cs # Test server setup (swaps in the mocks above)
|
||||
```
|
||||
|
||||
**Example Feature**:
|
||||
|
||||
```gherkin
|
||||
Feature: User Registration
|
||||
As a user
|
||||
I want to register
|
||||
So that I can access the platform
|
||||
|
||||
Scenario: Successful user registration
|
||||
Given I have valid registration details
|
||||
When I register a new account
|
||||
Then I should receive a JWT token
|
||||
And my account should be created
|
||||
```
|
||||
|
||||
### Features.Auth.Tests
|
||||
|
||||
```
|
||||
Features.Auth.Tests/
|
||||
├── Commands/
|
||||
│ ├── RegisterUserHandlerTests.cs
|
||||
│ ├── ConfirmUserHandlerTests.cs
|
||||
│ ├── ResendConfirmationEmailHandlerTests.cs
|
||||
│ └── RefreshTokenHandlerTests.cs
|
||||
├── Queries/
|
||||
│ └── LoginHandlerTests.cs
|
||||
├── Repository/
|
||||
│ └── AuthRepositoryTests.cs # DbMocker-backed repository tests
|
||||
└── Services/
|
||||
├── TokenServiceRefreshTests.cs
|
||||
└── TokenServiceValidationTests.cs
|
||||
```
|
||||
|
||||
Each of the other three slices (`Features.Breweries.Tests`,
|
||||
`Features.UserManagement.Tests`, `Features.Emails.Tests`) follows the same
|
||||
shape: a `Commands/`/`Queries/` folder with one test file per handler.
|
||||
|
||||
## Writing Tests
|
||||
|
||||
### Unit Test Example (xUnit)
|
||||
|
||||
```csharp
|
||||
public class LoginHandlerTests
|
||||
{
|
||||
[Fact]
|
||||
public async Task Handle_WithValidData_ReturnsPayloadWithMatchingUsername()
|
||||
{
|
||||
// Arrange
|
||||
var authRepoMock = new Mock<IAuthRepository>();
|
||||
var passwordInfraMock = new Mock<IPasswordInfrastructure>();
|
||||
var tokenServiceMock = new Mock<ITokenService>();
|
||||
var handler = new LoginHandler(authRepoMock.Object, passwordInfraMock.Object, tokenServiceMock.Object);
|
||||
// ...set up mocks for a known user/credential...
|
||||
|
||||
// Act
|
||||
var result = await handler.Handle(new LoginQuery("testuser", "password123"), CancellationToken.None);
|
||||
|
||||
// Assert
|
||||
result.Should().NotBeNull();
|
||||
result.AccessToken.Should().NotBeNullOrEmpty();
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
### Integration Test Example (Reqnroll)
|
||||
|
||||
```gherkin
|
||||
Scenario: User login with valid credentials
|
||||
Given a registered user with username "testuser"
|
||||
When I POST to "/api/auth/login" with valid credentials
|
||||
Then the response status should be 200
|
||||
And the response should contain a JWT token
|
||||
```
|
||||
|
||||
## Continuous Integration
|
||||
|
||||
Tests run automatically in CI/CD pipelines using the test Docker Compose
|
||||
configuration:
|
||||
|
||||
```bash
|
||||
# CI/CD command
|
||||
docker compose --env-file web/.env.test -f web/docker-compose.test.yaml build
|
||||
docker compose --env-file web/.env.test -f web/docker-compose.test.yaml up --abort-on-container-exit
|
||||
docker compose --env-file web/.env.test -f web/docker-compose.test.yaml down -v
|
||||
```
|
||||
|
||||
Exit codes:
|
||||
|
||||
- `0` - All tests passed
|
||||
- Non-zero - Test failures occurred
|
||||
|
||||
Frontend UI checks should also be included in CI for the active website
|
||||
workspace:
|
||||
|
||||
```bash
|
||||
cd web/frontend
|
||||
npm ci
|
||||
npm run test:storybook
|
||||
npm run test:storybook:playwright
|
||||
```
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Tests Failing Due to Database Connection
|
||||
|
||||
Ensure SQL Server is running and environment variables are set:
|
||||
|
||||
```bash
|
||||
docker compose --env-file web/.env.test -f web/docker-compose.test.yaml ps
|
||||
```
|
||||
|
||||
### Port Conflicts
|
||||
|
||||
If port 1433 is in use, stop other SQL Server instances or modify the port in
|
||||
`docker-compose.test.yaml`.
|
||||
|
||||
### Stale Test Data
|
||||
|
||||
Clean up test database:
|
||||
|
||||
```bash
|
||||
docker compose --env-file web/.env.test -f web/docker-compose.test.yaml down -v
|
||||
```
|
||||
|
||||
### View Container Logs
|
||||
|
||||
```bash
|
||||
docker compose --env-file web/.env.test -f web/docker-compose.test.yaml logs <service-name>
|
||||
```
|
||||
|
||||
## Best Practices
|
||||
|
||||
1. **Isolation**: Each test should be independent and not rely on other tests
|
||||
2. **Cleanup**: Use fixtures and dispose patterns for resource cleanup
|
||||
3. **Mocking**: Mock external dependencies in unit tests
|
||||
4. **Descriptive Names**: Use clear, descriptive test method names
|
||||
5. **Arrange-Act-Assert**: Follow AAA pattern in unit tests
|
||||
6. **Given-When-Then**: Follow GWT pattern in BDD scenarios
|
||||
2411
misc/raw-data/beers.csv
Normal file
2411
misc/raw-data/beers.csv
Normal file
File diff suppressed because it is too large
Load Diff
559
misc/raw-data/breweries.csv
Normal file
559
misc/raw-data/breweries.csv
Normal file
@@ -0,0 +1,559 @@
|
||||
,name,city,state
|
||||
0,NorthGate Brewing ,Minneapolis, MN
|
||||
1,Against the Grain Brewery,Louisville, KY
|
||||
2,Jack's Abby Craft Lagers,Framingham, MA
|
||||
3,Mike Hess Brewing Company,San Diego, CA
|
||||
4,Fort Point Beer Company,San Francisco, CA
|
||||
5,COAST Brewing Company,Charleston, SC
|
||||
6,Great Divide Brewing Company,Denver, CO
|
||||
7,Tapistry Brewing,Bridgman, MI
|
||||
8,Big Lake Brewing,Holland, MI
|
||||
9,The Mitten Brewing Company,Grand Rapids, MI
|
||||
10,Brewery Vivant,Grand Rapids, MI
|
||||
11,Petoskey Brewing,Petoskey, MI
|
||||
12,Blackrocks Brewery,Marquette, MI
|
||||
13,Perrin Brewing Company,Comstock Park, MI
|
||||
14,Witch's Hat Brewing Company,South Lyon, MI
|
||||
15,Founders Brewing Company,Grand Rapids, MI
|
||||
16,Flat 12 Bierwerks,Indianapolis, IN
|
||||
17,Tin Man Brewing Company,Evansville, IN
|
||||
18,Black Acre Brewing Co.,Indianapolis, IN
|
||||
19,Brew Link Brewing,Plainfield, IN
|
||||
20,Bare Hands Brewery,Granger, IN
|
||||
21,Three Pints Brewing,Martinsville, IN
|
||||
22,Four Fathers Brewing ,Valparaiso, IN
|
||||
23,Indiana City Brewing,Indianapolis, IN
|
||||
24,Burn 'Em Brewing,Michigan City, IN
|
||||
25,Sun King Brewing Company,Indianapolis, IN
|
||||
26,Evil Czech Brewery,Mishawaka, IN
|
||||
27,450 North Brewing Company,Columbus, IN
|
||||
28,Taxman Brewing Company,Bargersville, IN
|
||||
29,Cedar Creek Brewery,Seven Points, TX
|
||||
30,SanTan Brewing Company,Chandler, AZ
|
||||
31,Boulevard Brewing Company,Kansas City, MO
|
||||
32,James Page Brewing Company,Stevens Point, WI
|
||||
33,The Dudes' Brewing Company,Torrance, CA
|
||||
34,Ballast Point Brewing Company,San Diego, CA
|
||||
35,Anchor Brewing Company,San Francisco, CA
|
||||
36,Figueroa Mountain Brewing Company,Buellton, CA
|
||||
37,Avery Brewing Company,Boulder, CO
|
||||
38,Twisted X Brewing Company,Dripping Springs, TX
|
||||
39,Gonzo's BiggDogg Brewing,Kalamazoo, MI
|
||||
40,Big Muddy Brewing,Murphysboro, IL
|
||||
41,Lost Nation Brewing,East Fairfield, VT
|
||||
42,Rising Tide Brewing Company,Portland, ME
|
||||
43,Rivertowne Brewing Company,Export, PA
|
||||
44,Revolution Brewing Company,Chicago, IL
|
||||
45,Tallgrass Brewing Company,Manhattan, KS
|
||||
46,Sixpoint Craft Ales,Brooklyn, NY
|
||||
47,White Birch Brewing,Hooksett, NH
|
||||
48,Firestone Walker Brewing Company,Paso Robles, CA
|
||||
49,SweetWater Brewing Company,Atlanta, GA
|
||||
50,Flying Mouse Brewery,Troutville, VA
|
||||
51,Upslope Brewing Company,Boulder, CO
|
||||
52,Pipeworks Brewing Company,Chicago, IL
|
||||
53,Bent Brewstillery,Roseville, MN
|
||||
54,Flesk Brewing Company,Lombard, IL
|
||||
55,Pollyanna Brewing Company,Lemont, IL
|
||||
56,BuckleDown Brewing,Lyons, IL
|
||||
57,Destihl Brewery,Bloomington, IL
|
||||
58,Summit Brewing Company,St. Paul, MN
|
||||
59,Latitude 42 Brewing Company,Portage, MI
|
||||
60,4 Hands Brewing Company,Saint Louis, MO
|
||||
61,Surly Brewing Company,Brooklyn Center, MN
|
||||
62,Against The Grain Brewery,Louisville, KY
|
||||
63,Crazy Mountain Brewing Company,Edwards, CO
|
||||
64,SlapShot Brewing Company,Chicago, IL
|
||||
65,Mikerphone Brewing,Chicago, IL
|
||||
66,Freetail Brewing Company,San Antonio, TX
|
||||
67,3 Daughters Brewing,St Petersburg, FL
|
||||
68,Red Shedman Farm Brewery and Hop...,Mt. Airy, MD
|
||||
69,Appalachian Mountain Brewery,Boone, NC
|
||||
70,Birdsong Brewing Company,Charlotte, NC
|
||||
71,Union Craft Brewing,Baltimore, MD
|
||||
72,Atwater Brewery,Detroit, MI
|
||||
73,Ale Asylum,Madison, WI
|
||||
74,Two Brothers Brewing Company,Warrenville, IL
|
||||
75,Bent Paddle Brewing Company,Duluth, MN
|
||||
76,Bell's Brewery,Kalamazoo, MI
|
||||
77,Blue Owl Brewing,Austin, TX
|
||||
78,Speakasy Ales & Lagers,San Francisco, CA
|
||||
79,Black Tooth Brewing Company,Sheridan, WY
|
||||
80,Hopworks Urban Brewery,Portland, OR
|
||||
81,Epic Brewing,Denver, CO
|
||||
82,New Belgium Brewing Company,Fort Collins, CO
|
||||
83,Sierra Nevada Brewing Company,Chico, CA
|
||||
84,Keweenaw Brewing Company,Houghton, MI
|
||||
85,Brewery Terra Firma,Traverse City, MI
|
||||
86,Grey Sail Brewing Company,Westerly, RI
|
||||
87,Kirkwood Station Brewing Company,Kirkwood, MO
|
||||
88,Goose Island Brewing Company,Chicago, IL
|
||||
89,Broad Brook Brewing LLC,East Windsor, CT
|
||||
90,The Lion Brewery,Wilkes-Barre, PA
|
||||
91,Madtree Brewing Company,Cincinnati, OH
|
||||
92,Jackie O's Pub & Brewery,Athens, OH
|
||||
93,Rhinegeist Brewery,Cincinnati, OH
|
||||
94,Warped Wing Brewing Company,Dayton, OH
|
||||
95,Blackrocks Brewery,Marquette, MA
|
||||
96,Catawba Valley Brewing Company,Morganton, NC
|
||||
97,Tröegs Brewing Company,Hershey, PA
|
||||
98,Mission Brewery,San Diego, CA
|
||||
99,Christian Moerlein Brewing Company,Cincinnati, OH
|
||||
100,West Sixth Brewing,Lexington, KY
|
||||
101,Coastal Extreme Brewing Company,Newport, RI
|
||||
102,King Street Brewing Company,Anchorage, AK
|
||||
103,Beer Works Brewery,Lowell, MA
|
||||
104,Lone Tree Brewing Company,Lone Tree, CO
|
||||
105,Four String Brewing Company,Columbus, OH
|
||||
106,Glabrous Brewing Company,Pineland, ME
|
||||
107,Bonfire Brewing Company,Eagle, CO
|
||||
108,Thomas Hooker Brewing Company,Bloomfield, CT
|
||||
109,"Woodstock Inn, Station & Brewery",North Woodstock, NH
|
||||
110,Renegade Brewing Company,Denver, CO
|
||||
111,Mother Earth Brew Company,Vista, CA
|
||||
112,Black Market Brewing Company,Temecula, CA
|
||||
113,Vault Brewing Company,Yardley, PA
|
||||
114,Jailbreak Brewing Company,Laurel, MD
|
||||
115,Smartmouth Brewing Company,Norfolk, VA
|
||||
116,Base Camp Brewing Co.,Portland, OR
|
||||
117,Alameda Brewing,Portland, OR
|
||||
118,Southern Star Brewing Company,Conroe, TX
|
||||
119,Steamworks Brewing Company,Durango, CO
|
||||
120,Horny Goat Brew Pub,Milwaukee, WI
|
||||
121,Cheboygan Brewing Company,Cheboygan, MI
|
||||
122,Center of the Universe Brewing C...,Ashland, VA
|
||||
123,Ipswich Ale Brewery,Ipswich, MA
|
||||
124,Griffin Claw Brewing Company,Birmingham, MI
|
||||
125,Karbach Brewing Company,Houston, TX
|
||||
126,Uncle Billy's Brewery and Smokeh...,Austin, TX
|
||||
127,Deep Ellum Brewing Company,Dallas, TX
|
||||
128,Real Ale Brewing Company,Blanco, TX
|
||||
129,Straub Brewery,St Mary's, PA
|
||||
130,Shebeen Brewing Company,Wolcott, CT
|
||||
131,Stevens Point Brewery,Stevens Point, WI
|
||||
132,Weston Brewing Company,Weston, MO
|
||||
133,Southern Prohibition Brewing Com...,Hattiesburg, MS
|
||||
134,Minhas Craft Brewery,Monroe, WI
|
||||
135,Pug Ryan's Brewery,Dillon, CO
|
||||
136,Hops & Grains Brewing Company,Austin, TX
|
||||
137,Sietsema Orchards and Cider Mill,Ada, MI
|
||||
138,Summit Brewing Company,St Paul, MN
|
||||
139,Core Brewing & Distilling Company,Springdale, AR
|
||||
140,Independence Brewing Company,Austin, TX
|
||||
141,Cigar City Brewing Company,Tampa, FL
|
||||
142,Third Street Brewhouse,Cold Spring, MN
|
||||
143,Narragansett Brewing Company,Providence, RI
|
||||
144,Grimm Brothers Brewhouse,Loveland, CO
|
||||
145,Cisco Brewers,Nantucket, MA
|
||||
146,Angry Minnow,Hayward, WI
|
||||
147,Platform Beer Company,Cleveland, OH
|
||||
148,Odyssey Beerwerks,Arvada, CO
|
||||
149,Lonerider Brewing Company,Raleigh, NC
|
||||
150,Oakshire Brewing,Eugene, OR
|
||||
151,Fort Pitt Brewing Company,Latrobe, PA
|
||||
152,Tin Roof Brewing Company,Baton Rouge, LA
|
||||
153,Three Creeks Brewing,Sisters, OR
|
||||
154,2 Towns Ciderhouse,Corvallis, OR
|
||||
155,Caldera Brewing Company,Ashland, OR
|
||||
156,Greenbrier Valley Brewing Company,Lewisburg, WV
|
||||
157,Phoenix Ale Brewery,Phoenix, AZ
|
||||
158,Lumberyard Brewing Company,Flagstaff, AZ
|
||||
159,Uinta Brewing Company,Salt Lake City, UT
|
||||
160,Four Peaks Brewing Company,Tempe, AZ
|
||||
161,Martin House Brewing Company,Fort Worth, TX
|
||||
162,Right Brain Brewery,Traverse City, MI
|
||||
163,Sly Fox Brewing Company,Phoenixville, PA
|
||||
164,Round Guys Brewing,Lansdale, PA
|
||||
165,Great Crescent Brewery,Aurora, IN
|
||||
166,Oskar Blues Brewery,Longmont, CO
|
||||
167,Boxcar Brewing Company,West Chester, PA
|
||||
168,High Hops Brewery,Windsor, CO
|
||||
169,Crooked Fence Brewing Company,Garden City, ID
|
||||
170,Everybody's Brewing,White Salmon, WA
|
||||
171,Anderson Valley Brewing Company,Boonville, CA
|
||||
172,Fiddlehead Brewing Company,Shelburne, VT
|
||||
173,Evil Twin Brewing,Brooklyn, NY
|
||||
174,New Orleans Lager & Ale Brewing ...,New Orleans, LA
|
||||
175,Spiteful Brewing Company,Chicago, IL
|
||||
176,Rahr & Sons Brewing Company,Fort Worth, TX
|
||||
177,18th Street Brewery,Gary, IN
|
||||
178,Cambridge Brewing Company,Cambridge, MA
|
||||
179,Carolina Brewery,Pittsboro, NC
|
||||
180,Frog Level Brewing Company,Waynesville, NC
|
||||
181,Wild Wolf Brewing Company,Nellysford, VA
|
||||
182,COOP Ale Works,Oklahoma City, OK
|
||||
183,Seventh Son Brewing Company,Columbus, OH
|
||||
184,Oasis Texas Brewing Company,Austin, TX
|
||||
185,Vander Mill Ciders,Spring Lake, MI
|
||||
186,St. Julian Winery,Paw Paw, MI
|
||||
187,Pedernales Brewing Company,Fredericksburg, TX
|
||||
188,Mother's Brewing,Springfield, MO
|
||||
189,Modern Monks Brewery,Lincoln, NE
|
||||
190,Two Beers Brewing Company,Seattle, WA
|
||||
191,Snake River Brewing Company,Jackson, WY
|
||||
192,Capital Brewery,Middleton, WI
|
||||
193,Anthem Brewing Company,Oklahoma City, OK
|
||||
194,Goodlife Brewing Co.,Bend, OR
|
||||
195,Breakside Brewery,Portland, OR
|
||||
196,Goose Island Brewery Company,Chicago, IL
|
||||
197,Burnside Brewing Co.,Portland, OR
|
||||
198,Hop Valley Brewing Company,Springfield, OR
|
||||
199,Worthy Brewing Company,Bend, OR
|
||||
200,Occidental Brewing Company,Portland, OR
|
||||
201,Fearless Brewing Company,Estacada, OR
|
||||
202,Upland Brewing Company,Bloomington, IN
|
||||
203,Mehana Brewing Co.,Hilo, HI
|
||||
204,Hawai'i Nui Brewing Co.,Hilo, HI
|
||||
205,People's Brewing Company,Lafayette, IN
|
||||
206,Fort George Brewery,Astoria, OR
|
||||
207,Branchline Brewing Company,San Antonio, TX
|
||||
208,Kalona Brewing Company,Kalona, IA
|
||||
209,Modern Times Beer,San Diego, CA
|
||||
210,Temperance Beer Company,Evanston, IL
|
||||
211,Wisconsin Brewing Company,Verona, WI
|
||||
212,Crow Peak Brewing Company,Spearfish, SD
|
||||
213,Grapevine Craft Brewery,Farmers Branch, TX
|
||||
214,Buffalo Bayou Brewing Company,Houston, TX
|
||||
215,Texian Brewing Co.,Richmond, TX
|
||||
216,Orpheus Brewing,Atlanta, GA
|
||||
217,Forgotten Boardwalk,Cherry Hill, NJ
|
||||
218,Laughing Dog Brewing Company,Ponderay, ID
|
||||
219,Bozeman Brewing Company,Bozeman, MT
|
||||
220,Big Choice Brewing,Broomfield, CO
|
||||
221,Big Storm Brewing Company,Odessa, FL
|
||||
222,Carton Brewing Company,Atlantic Highlands, NJ
|
||||
223,Midnight Sun Brewing Company,Anchorage, AK
|
||||
224,Fat Head's Brewery,Middleburg Heights, OH
|
||||
225,Refuge Brewery,Temecula, CA
|
||||
226,Chatham Brewing,Chatham, NY
|
||||
227,DC Brau Brewing Company,Washington, DC
|
||||
228,Geneva Lake Brewing Company,Lake Geneva, WI
|
||||
229,Rochester Mills Brewing Company,Rochester, MI
|
||||
230,Cape Ann Brewing Company,Gloucester, MA
|
||||
231,Borderlands Brewing Company,Tucson, AZ
|
||||
232,College Street Brewhouse and Pub,Lake Havasu City, AZ
|
||||
233,Joseph James Brewing Company,Henderson, NV
|
||||
234,Harpoon Brewery,Boston, MA
|
||||
235,Back East Brewing Company,Bloomfield, CT
|
||||
236,Champion Brewing Company,Charlottesville, VA
|
||||
237,Devil's Backbone Brewing Company,Lexington, VA
|
||||
238,Newburgh Brewing Company,Newburgh, NY
|
||||
239,Wiseacre Brewing Company,Memphis, TN
|
||||
240,Golden Road Brewing,Los Angeles, CA
|
||||
241,New Republic Brewing Company,College Station, TX
|
||||
242,Infamous Brewing Company,Austin, TX
|
||||
243,Two Henrys Brewing Company,Plant City, FL
|
||||
244,Lift Bridge Brewing Company,Stillwater, MN
|
||||
245,Lucky Town Brewing Company,Jackson, MS
|
||||
246,Quest Brewing Company,Greenville, SC
|
||||
247,Creature Comforts,Athens, GA
|
||||
248,Half Full Brewery,Stamford, CT
|
||||
249,Southampton Publick House,Southampton, NY
|
||||
250,Chapman's Brewing,Angola, IN
|
||||
251,Barrio Brewing Company,Tucson, AZ
|
||||
252,Santa Cruz Mountain Brewing,Santa Cruz, CA
|
||||
253,Frankenmuth Brewery,Frankenmuth, MI
|
||||
254,Meckley's Cidery,Somerset Center, MI
|
||||
255,Stillwater Artisanal Ales,Baltimore, MD
|
||||
256,Finch's Beer Company,Chicago, IL
|
||||
257,South Austin Brewery,South Austin, TX
|
||||
258,Bauhaus Brew Labs,Minneapolis, MN
|
||||
259,Ozark Beer Company,Rogers, AR
|
||||
260,Mountain Town Brewing Company ,Mount Pleasant, MI
|
||||
261,Otter Creek Brewing,Waterbury, VT
|
||||
262,The Brewer's Art,Baltimore, MD
|
||||
263,Denver Beer Company,Denver, CO
|
||||
264,Ska Brewing Company,Durango, CO
|
||||
265,Tractor Brewing Company,Albuquerque, NM
|
||||
266,Peak Organic Brewing Company,Portland, ME
|
||||
267,Cape Cod Beer,Hyannis, MA
|
||||
268,Long Trail Brewing Company,Bridgewater Corners, VT
|
||||
269,Great Raft Brewing Company,Shreveport, LA
|
||||
270,Alaskan Brewing Company,Juneau, AK
|
||||
271,Notch Brewing Company,Ipswich, MA
|
||||
272,The Alchemist,Waterbury, VT
|
||||
273,Three Notch'd Brewing Company,Charlottesville, VA
|
||||
274,Portside Brewery,Cleveland, OH
|
||||
275,Otter Creek Brewing,Middlebury, VT
|
||||
276,Montauk Brewing Company,Montauk, NY
|
||||
277,Indeed Brewing Company,Minneapolis, MN
|
||||
278,Berkshire Brewing Company,South Deerfield, MA
|
||||
279,Foolproof Brewing Company,Pawtucket, RI
|
||||
280,Headlands Brewing Company,Mill Valley, CA
|
||||
281,Bolero Snort Brewery,Ridgefield Park, NJ
|
||||
282,Thunderhead Brewing Company,Kearney, NE
|
||||
283,Defiance Brewing Company,Hays, KS
|
||||
284,Milwaukee Brewing Company,Milwaukee, WI
|
||||
285,Catawba Island Brewing,Port Clinton, OH
|
||||
286,Back Forty Beer Company,Gadsden, AL
|
||||
287,Four Corners Brewing Company,Dallas, TX
|
||||
288,Saint Archer Brewery,San Diego, CA
|
||||
289,Rogue Ales,Newport, OR
|
||||
290,Hale's Ales,Seattle, WA
|
||||
291,Tommyknocker Brewery,Idaho Springs, CO
|
||||
292,Baxter Brewing Company,Lewiston, ME
|
||||
293,Northampton Brewery,Northamtpon, MA
|
||||
294,Black Shirt Brewing Company,Denver, CO
|
||||
295,Wachusett Brewing Company,Westminster, MA
|
||||
296,Widmer Brothers Brewing Company,Portland, OR
|
||||
297,Hop Farm Brewing Company,Pittsburgh, PA
|
||||
298,Liquid Hero Brewery,York, PA
|
||||
299,Matt Brewing Company,Utica, NY
|
||||
300,Boston Beer Company,Boston, MA
|
||||
301,Old Forge Brewing Company,Danville, PA
|
||||
302,Utah Brewers Cooperative,Salt Lake City, UT
|
||||
303,Magic Hat Brewing Company,South Burlington, VT
|
||||
304,Blue Hills Brewery,Canton, MA
|
||||
305,Night Shift Brewing,Everett, MA
|
||||
306,Beach Brewing Company,Virginia Beach, VA
|
||||
307,Payette Brewing Company,Garden City, ID
|
||||
308,Brew Bus Brewing,Tampa, FL
|
||||
309,Sockeye Brewing Company,Boise, ID
|
||||
310,Pine Street Brewery,San Francisco, CA
|
||||
311,Dirty Bucket Brewing Company,Woodinville, WA
|
||||
312,Jackalope Brewing Company,Nashville, TN
|
||||
313,Slanted Rock Brewing Company,Meridian, ID
|
||||
314,Piney River Brewing Company,Bucryus, MO
|
||||
315,Cutters Brewing Company,Avon, IN
|
||||
316,Iron Hill Brewery & Restaurant,Wilmington, DE
|
||||
317,Marshall Wharf Brewing Company,Belfast, ME
|
||||
318,Banner Beer Company,Williamsburg, MA
|
||||
319,Dick's Brewing Company,Centralia, WA
|
||||
320,Claremont Craft Ales,Claremont, CA
|
||||
321,Rivertown Brewing Company,Lockland, OH
|
||||
322,Voodoo Brewery,Meadville, PA
|
||||
323,D.L. Geary Brewing Company,Portland, ME
|
||||
324,Pisgah Brewing Company,Black Mountain, NC
|
||||
325,Neshaminy Creek Brewing Company,Croydon, PA
|
||||
326,Morgan Street Brewery,Saint Louis, MO
|
||||
327,Half Acre Beer Company,Chicago, IL
|
||||
328,The Just Beer Project,Burlington, VT
|
||||
329,The Bronx Brewery,Bronx, NY
|
||||
330,Dead Armadillo Craft Brewing,Tulsa, OK
|
||||
331,Catawba Brewing Company,Morganton, NC
|
||||
332,La Cumbre Brewing Company,Albuquerque, NM
|
||||
333,David's Ale Works,Diamond Springs, CA
|
||||
334,The Traveler Beer Company,Burlington, VT
|
||||
335,Fargo Brewing Company,Fargo, ND
|
||||
336,Big Sky Brewing Company,Missoula, MT
|
||||
337,Nebraska Brewing Company,Papillion, NE
|
||||
338,Uncle John's Fruit House Winery,St. John's, MI
|
||||
339,Wormtown Brewery,Worcester, MA
|
||||
340,Due South Brewing Company,Boynton Beach, FL
|
||||
341,Palisade Brewing Company,Palisade, CO
|
||||
342,KelSo Beer Company,Brooklyn, NY
|
||||
343,Hardywood Park Craft Brewery,Richmond, VA
|
||||
344,Wolf Hills Brewing Company,Abingdon, VA
|
||||
345,Lavery Brewing Company,Erie, PA
|
||||
346,Manzanita Brewing Company,Santee, CA
|
||||
347,Fullsteam Brewery,Durham, NC
|
||||
348,Four Horsemen Brewing Company,South Bend, IN
|
||||
349,Hinterland Brewery,Green Bay, WI
|
||||
350,Central Coast Brewing Company,San Luis Obispo, CA
|
||||
351,Westfield River Brewing Company,Westfield, MA
|
||||
352,Elevator Brewing Company,Columbus, OH
|
||||
353,Aslan Brewing Company,Bellingham, WA
|
||||
354,Kulshan Brewery,Bellingham, WA
|
||||
355,Pikes Peak Brewing Company,Monument, CO
|
||||
356,Manayunk Brewing Company,Philadelphia, PA
|
||||
357,Buckeye Brewing,Cleveland, OH
|
||||
358,Daredevil Brewing Company,Shelbyville, IN
|
||||
359,NoDa Brewing Company,Charlotte, NC
|
||||
360,Aviator Brewing Company,Fuquay-Varina, NC
|
||||
361,Wild Onion Brewing Company,Lake Barrington, IL
|
||||
362,Hilliard's Beer,Seattle, WA
|
||||
363,Mikkeller,Pottstown, PA
|
||||
364,Bohemian Brewery,Midvale, UT
|
||||
365,Great River Brewery,Davenport, IA
|
||||
366,Mustang Brewing Company,Mustang, OK
|
||||
367,Airways Brewing Company,Kent, WA
|
||||
368,21st Amendment Brewery,San Francisco, CA
|
||||
369,Eddyline Brewery & Restaurant,Buena Vista, CO
|
||||
370,Pizza Port Brewing Company,Carlsbad, CA
|
||||
371,Sly Fox Brewing Company,Pottstown, PA
|
||||
372,Spring House Brewing Company,Conestoga, PA
|
||||
373,7venth Sun,Dunedin, FL
|
||||
374,Astoria Brewing Company,Astoria, OR
|
||||
375,Maui Brewing Company,Lahaina, HI
|
||||
376,RoughTail Brewing Company,Midwest City, OK
|
||||
377,Lucette Brewing Company,Menominee, WI
|
||||
378,Bold City Brewery,Jacksonville, FL
|
||||
379,Grey Sail Brewing of Rhode Island,Westerly, RI
|
||||
380,Blue Blood Brewing Company,Lincoln, NE
|
||||
381,Swashbuckler Brewing Company,Manheim, PA
|
||||
382,Blue Mountain Brewery,Afton, VA
|
||||
383,Starr Hill Brewery,Crozet, VA
|
||||
384,Westbrook Brewing Company,Mt. Pleasant, SC
|
||||
385,Shipyard Brewing Company,Portland, ME
|
||||
386,Revolution Brewing,Paonia, CO
|
||||
387,Natian Brewery,Portland, OR
|
||||
388,Alltech's Lexington Brewing Company,Lexington, KY
|
||||
389,Oskar Blues Brewery (North Carol...,Brevard, NC
|
||||
390,Orlison Brewing Company,Airway Heights, WA
|
||||
391,Breckenridge Brewery,Denver, CO
|
||||
392,Santa Fe Brewing Company,Santa Fe, NM
|
||||
393,Miami Brewing Company,Miami, FL
|
||||
394,Schilling & Company,Seattle, WA
|
||||
395,Hops & Grain Brewery,Austin, TX
|
||||
396,White Flame Brewing Company,Hudsonville, MI
|
||||
397,Ruhstaller Beer Company,Sacramento, CA
|
||||
398,Saugatuck Brewing Company,Douglas, MI
|
||||
399,Moab Brewery,Moab, UT
|
||||
400,Macon Beer Company,Macon, GA
|
||||
401,Amnesia Brewing Company,Washougal, WA
|
||||
402,Wolverine State Brewing Company,Ann Arbor, MI
|
||||
403,Red Tank Cider Company,Bend, OR
|
||||
404,Cascadia Ciderworks United,Portland, OR
|
||||
405,Fate Brewing Company,Boulder, CO
|
||||
406,Lazy Monk Brewing,Eau Claire, WI
|
||||
407,Bitter Root Brewing,Hamilton, MT
|
||||
408,10 Barrel Brewing Company,Bend, OR
|
||||
409,Tamarack Brewing Company,Lakeside, MT
|
||||
410,New England Brewing Company,Woodbridge, CT
|
||||
411,Seattle Cider Company,Seattle, WA
|
||||
412,Straight to Ale,Huntsville, AL
|
||||
413,Austin Beerworks,Austin, TX
|
||||
414,Blue Mountain Brewery,Arrington, VA
|
||||
415,Coastal Empire Beer Company,Savannah, GA
|
||||
416,Jack's Hard Cider (Hauser Estate...,Biglerville, PA
|
||||
417,Boulder Beer Company,Boulder, CO
|
||||
418,Coalition Brewing Company,Portland, OR
|
||||
419,Sanitas Brewing Company,Boulder, CO
|
||||
420,Gore Range Brewery,Edwards, CO
|
||||
421,Redstone Meadery,Boulder, CO
|
||||
422,Blue Dog Mead,Eugene, OR
|
||||
423,Hess Brewing Company,San Diego, CA
|
||||
424,Wynkoop Brewing Company,Denver, CO
|
||||
425,Ciderboys,Stevens Point, WI
|
||||
426,Armadillo Ale Works,Denton, TX
|
||||
427,Roanoke Railhouse Brewery,Roanoke, VA
|
||||
428,Schlafly Brewing Company,Saint Louis, MO
|
||||
429,Asher Brewing Company,Boulder, CO
|
||||
430,Lost Rhino Brewing Company,Ashburn, VA
|
||||
431,North Country Brewing Company,Slippery Rock, PA
|
||||
432,Seabright Brewery,Santa Cruz, CA
|
||||
433,French Broad Brewery,Asheville, NC
|
||||
434,Angry Orchard Cider Company,Cincinnati, OH
|
||||
435,Two Roads Brewing Company,Stratford, CT
|
||||
436,Southern Oregon Brewing Company,Medford, OR
|
||||
437,Brooklyn Brewery,Brooklyn, NY
|
||||
438,The Right Brain Brewery,Traverse City, MI
|
||||
439,Kona Brewing Company,Kona, HI
|
||||
440,MillKing It Productions,Royal Oak, MI
|
||||
441,Pateros Creek Brewing Company,Fort Collins, CO
|
||||
442,O'Fallon Brewery,O'Fallon, MO
|
||||
443,Marble Brewery,Albuquerque, NM
|
||||
444,Big Wood Brewery,Vadnais Heights, MN
|
||||
445,Howard Brewing Company,Lenoir, NC
|
||||
446,Downeast Cider House,Leominster, MA
|
||||
447,Swamp Head Brewery,Gainesville, FL
|
||||
448,Mavericks Beer Company,Half Moon Bay, CA
|
||||
449,TailGate Beer,San Diego, CA
|
||||
450,Northwest Brewing Company,Pacific, WA
|
||||
451,Dad & Dude's Breweria,Aurora, CO
|
||||
452,Centennial Beer Company,Edwards, CO
|
||||
453,Denali Brewing Company,Talkeetna, AK
|
||||
454,Deschutes Brewery,Bend, OR
|
||||
455,Sunken City Brewing Company,Hardy, VA
|
||||
456,Lucette Brewing Company,Menominie, WI
|
||||
457,The Black Tooth Brewing Company,Sheridan, WY
|
||||
458,Kenai River Brewing Company,Soldotna, AK
|
||||
459,River North Brewery,Denver, CO
|
||||
460,Fremont Brewing Company,Seattle, WA
|
||||
461,Armstrong Brewing Company,South San Francisco, CA
|
||||
462,AC Golden Brewing Company,Golden, CO
|
||||
463,Big Bend Brewing Company,Alpine, TX
|
||||
464,Good Life Brewing Company,Bend, OR
|
||||
465,Engine 15 Brewing,Jacksonville Beach, FL
|
||||
466,Green Room Brewing,Jacksonville, FL
|
||||
467,Brindle Dog Brewing Company,Tampa Bay, FL
|
||||
468,Peace Tree Brewing Company,Knoxville, IA
|
||||
469,Terrapin Brewing Company,Athens, GA
|
||||
470,Pete's Brewing Company,San Antonio, TX
|
||||
471,Okoboji Brewing Company,Spirit Lake, IA
|
||||
472,Crystal Springs Brewing Company,Boulder, CO
|
||||
473,Engine House 9,Tacoma, WA
|
||||
474,Tonka Beer Company,Minnetonka, MN
|
||||
475,Red Hare Brewing Company,Marietta, GA
|
||||
476,Hangar 24 Craft Brewery,Redlands, CA
|
||||
477,Big Elm Brewing,Sheffield, MA
|
||||
478,Good People Brewing Company,Birmingham, AL
|
||||
479,Heavy Seas Beer,Halethorpe, MD
|
||||
480,Telluride Brewing Company,Telluride, CO
|
||||
481,7 Seas Brewing Company,Gig Harbor, WA
|
||||
482,Confluence Brewing Company,Des Moines, IA
|
||||
483,Bale Breaker Brewing Company,Yakima, WA
|
||||
484,The Manhattan Brewing Company,New York, NY
|
||||
485,MacTarnahans Brewing Company,Portland, OR
|
||||
486,Stillmank Beer Company,Green Bay, WI
|
||||
487,Redhook Brewery,Woodinville, WA
|
||||
488,Dock Street Brewery,Philadelphia, PA
|
||||
489,Blue Point Brewing Company,Patchogue, NY
|
||||
490,Tampa Bay Brewing Company,Tampa, FL
|
||||
491,Devil's Canyon Brewery,Belmont, CA
|
||||
492,Stone Coast Brewing Company,Portland, ME
|
||||
493,Broken Tooth Brewing Company,Anchorage, AK
|
||||
494,Seven Brides Brewery,Silverton, OR
|
||||
495,Newburyport Brewing Company,Newburyport, MA
|
||||
496,Dry Dock Brewing Company,Aurora, CO
|
||||
497,Cans Bar and Canteen,Charlotte, NC
|
||||
498,Sprecher Brewing Company,Glendale, WI
|
||||
499,Wildwood Brewing Company,Stevensville, MT
|
||||
500,High Noon Saloon And Brewery,Leavenworth, KS
|
||||
501,Woodchuck Hard Cider,Middlebury, VT
|
||||
502,Sea Dog Brewing Company,Portland, ME
|
||||
503,Oskar Blues Brewery,Lyons, CO
|
||||
504,Carolina Beer & Beverage,Mooresville, NC
|
||||
505,Krebs Brewing Company (Pete's Pl...,Krebs, OK
|
||||
506,Warbird Brewing Company,Fort Wayne, IN
|
||||
507,Mudshark Brewing Company,Lake Havasu City, AZ
|
||||
508,Spilker Ales,Cortland, NE
|
||||
509,Wingman Brewers,Tacoma, WA
|
||||
510,Kettle House Brewing Company,Missoula, MT
|
||||
511,Sherwood Forest Brewers,Marlborough, MA
|
||||
512,Cottrell Brewing,Pawcatuck, CT
|
||||
513,Arctic Craft Brewery,Colorado Springs, CO
|
||||
514,Monkey Paw Pub & Brewery,San Diego, CA
|
||||
515,Crabtree Brewing Company,Greeley, CO
|
||||
516,Emerald City Beer Company,Seattle, WA
|
||||
517,Butcher's Brewing,Carlsbad, CA
|
||||
518,New South Brewing Company,Myrtle Beach, SC
|
||||
519,Big River Brewing Company,Chattanooga, TN
|
||||
520,Twisted Pine Brewing Company,Boulder, CO
|
||||
521,Flying Dog Brewery,Frederick, MD
|
||||
522,Uncommon Brewers,Santa Cruz, CA
|
||||
523,Aspen Brewing Company,Aspen, CO
|
||||
524,Triangle Brewing Company,Durham, NC
|
||||
525,Bomb Beer Company,New York, NY
|
||||
526,Churchkey Can Company,Seattle, WA
|
||||
527,Intuition Ale Works,Jacksonville, FL
|
||||
528,Asheville Brewing Company,Asheville, NC
|
||||
529,Northwoods Brewpub,Eau Claire, WI
|
||||
530,Buckbean Brewing Company,Reno, NV
|
||||
531,Dolores River Brewery,Dolores, CO
|
||||
532,Flat Rock Brewing Company,Smithton, PA
|
||||
533,Abita Brewing Company,Abita Springs, LA
|
||||
534,Mammoth Brewing Company,Mammoth Lakes, CA
|
||||
535,Harvest Moon Brewing Company,Belt, MT
|
||||
536,Grand Canyon Brewing Company,Williams, AZ
|
||||
537,Lewis and Clark Brewing Company,Helena, MT
|
||||
538,Dundee Brewing Company,Rochester, NY
|
||||
539,Twin Lakes Brewing Company,Greenville, DE
|
||||
540,Mother Earth Brewing Company,Kinston, NC
|
||||
541,Arcadia Brewing Company,Battle Creek, MI
|
||||
542,Angry Minnow Brewing Company,Hayward, WI
|
||||
543,Great Northern Brewing Company,Whitefish, MT
|
||||
544,Pyramid Breweries,Seattle, WA
|
||||
545,Lancaster Brewing Company,Lancaster, PA
|
||||
546,Upstate Brewing Company,Elmira, NY
|
||||
547,Moat Mountain Smoke House & Brew...,North Conway, NH
|
||||
548,Prescott Brewing Company,Prescott, AZ
|
||||
549,Mogollon Brewing Company,Flagstaff, AZ
|
||||
550,Wind River Brewing Company,Pinedale, WY
|
||||
551,Silverton Brewery,Silverton, CO
|
||||
552,Mickey Finn's Brewery,Libertyville, IL
|
||||
553,Covington Brewhouse,Covington, LA
|
||||
554,Dave's Brewfarm,Wilson, WI
|
||||
555,Ukiah Brewing Company,Ukiah, CA
|
||||
556,Butternuts Beer and Ale,Garrattsville, NY
|
||||
557,Sleeping Lady Brewing Company,Anchorage, AK
|
||||
|
162686
misc/raw-data/breweries.json
Normal file
162686
misc/raw-data/breweries.json
Normal file
File diff suppressed because it is too large
Load Diff
578
misc/raw-data/ontariobreweries.json
Normal file
578
misc/raw-data/ontariobreweries.json
Normal file
@@ -0,0 +1,578 @@
|
||||
[
|
||||
{
|
||||
"text": "100 Acre Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/100-acre-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "All My Friends Beer Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/all-my-friends-beer-co/"
|
||||
},
|
||||
{
|
||||
"text": "All or Nothing Brewhouse",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/all-or-nothing-brewhouse/"
|
||||
},
|
||||
{
|
||||
"text": "Anderson Craft Ales",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/anderson-craft-ales/"
|
||||
},
|
||||
{
|
||||
"text": "Badlands Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/badlands-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Bancroft Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/bancroft-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Banded Goose Brewing Comany",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/banded-goose-brewing-comany/"
|
||||
},
|
||||
{
|
||||
"text": "Beau’s Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/beaus-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "BeerLab! London",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/beerlab-london/"
|
||||
},
|
||||
{
|
||||
"text": "Bellwoods Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/bellwoods-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Bench Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/bench-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Beyond The Pale Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/beyond-the-pale-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Bicycle Craft Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/bicycle-craft-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Big Rig Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/big-rig-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Big Rock Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/big-rock-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Black Gold Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/black-gold-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Black Oak Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/black-oak-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Block 3 Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/block-3-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Blood Brothers Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/blood-brothers-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Bobcaygeon Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/bobcaygeon-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Boshkung Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/boshkung-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Brauwerk Hoffman – Rockland",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/brauwerk-hoffman-rockland/"
|
||||
},
|
||||
{
|
||||
"text": "Bridge Masters Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/bridge-masters-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Broadhead Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/broadhead-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Broken Rail Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/broken-rail-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Burdock Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/burdock-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "C’est What Durham Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/cest-what-durham-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Calabogie Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/calabogie-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Cameron’s Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/camerons-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Canvas Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/canvas-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Caps Off Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/caps-off-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Century Barn Brewing & Beverage Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/century-barn-brewing-and-beverage-company/"
|
||||
},
|
||||
{
|
||||
"text": "Chronicle Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/chronicle-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Clifford Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/clifford-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Cold Bear Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/cold-bear-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Collective Arts Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/collective-arts-brewing-ltd/"
|
||||
},
|
||||
{
|
||||
"text": "Common Good Beer Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/common-good-beer-co/"
|
||||
},
|
||||
{
|
||||
"text": "Couchiching Craft Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/couchiching-craft-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Cowbell Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/cowbell-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Cured Craft Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/cured-craft-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Daft Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/daft-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Dog House Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/dog-house-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Dominion City Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/dominion-city-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Eastbound Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/eastbound-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Equals Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/equals-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Fairweather Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/fairweather-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Farm League Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/farm-league-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Fixed Gear Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/fixed-gear-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Flying Monkeys Craft Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/flying-monkeys-craft-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Focal Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/focal-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Foundry Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/foundry-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Four Fathers Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/four-fathers-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Frank Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/frank-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Freddy’s",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/freddys/"
|
||||
},
|
||||
{
|
||||
"text": "Full Beard Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/1068-2/"
|
||||
},
|
||||
{
|
||||
"text": "Furnace Room Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/furnace-room-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Gateway City Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/gateway-city-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Glasstown Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/glasstown-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Godspeed Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/godspeed-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Goldenfield Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/goldenfield-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Grand River Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/grand-river-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Granite Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/granite-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Great Lakes Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/great-lakes-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Haliburton Highlands Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/haliburton-highlands-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Imperial City Brew House",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/imperial-city-brew-house/"
|
||||
},
|
||||
{
|
||||
"text": "Indie Ale House",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/indie-ale-house/"
|
||||
},
|
||||
{
|
||||
"text": "Jobsite Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/jobsite-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Kichesippi Beer Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/kichesippi-beer-co/"
|
||||
},
|
||||
{
|
||||
"text": "Kick and Push Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/kick-and-push-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Lake of Bays Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/lake-of-bays-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Lake Of The Woods Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/lake-of-the-woods-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Left Field Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/left-field-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Lightcaster Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/lightcaster-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "MacKinnon Brothers Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/mackinnon-brothers-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Maclean’s Ales Inc.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/macleans-ales-inc/"
|
||||
},
|
||||
{
|
||||
"text": "Magnotta Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/magnotta-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Market Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/market-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Mascot Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/mascot-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Matron Fine Beer",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/matron-fine-beer/"
|
||||
},
|
||||
{
|
||||
"text": "Meyers Creek Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/meyers-creek-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Midtown Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/midtown-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Miski Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/miski-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Muddy York Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/muddy-york-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Muskoka Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/muskoka-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Natterjack Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/natterjack-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Newark Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/newark-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Niagara Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/niagara-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Niagara College Teaching Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/niagara-college-teaching-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Niagara Oast House Brewers",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/niagara-oast-house-brewers/"
|
||||
},
|
||||
{
|
||||
"text": "Nickel Brook Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/nickel-brook-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Northern Superior Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/northern-superior-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Old Credit Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/old-credit-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Old Flame Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/1239-2/"
|
||||
},
|
||||
{
|
||||
"text": "Orléans Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/orleans-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Overflow Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/overflow-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Parsons Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/parsons-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Perth Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/perth-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Prince Eddy’s Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/prince-eddys-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Quayle’s Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/quayles-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Quetico Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/quetico-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Railway City Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/railway-city-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Ramblin’ Road Brewery Farm",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/ramblin-road-brewery-farm/"
|
||||
},
|
||||
{
|
||||
"text": "Red Barn Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/red-barn-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Refined Fool Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/refined-fool-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Rouge River Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/rouge-river-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Royal City Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/royal-city-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Sassy Britches Brewing Co Ltd",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/sassy-britches-brewing-co-ltd/"
|
||||
},
|
||||
{
|
||||
"text": "Sawdust City Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/sawdust-city-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Shawn & Ed Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/shawn-ed-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Silversmith Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/silversmith-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Slake Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/slake-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Sleeping Giant Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/sleeping-giant-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Something in the Water Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/something-in-the-water-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Sonnen Hill Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/sonnen-hill-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Sons of Kent Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/sons-of-kent-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Spark Beer",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/spark-beer/"
|
||||
},
|
||||
{
|
||||
"text": "Split Rail Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/split-rail-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Stack Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/stack-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Steam Whistle Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/steam-whistle-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Steel Wheel Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/steel-wheel-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Stonehooker Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/stonehooker-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Stonepicker Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/stonepicker-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Stray Dog Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/stray-dog-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "The Exchange Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/the-exchange-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "The Grove Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/the-grove-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "The Second Wedge Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/the-second-wedge-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Thornbury Village Craft Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/thornbury-village-craft-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Three Sheets Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/three-sheets-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Tooth and Nail Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/tooth-and-nail-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Torched Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/torched-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Town Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/town-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Trestle Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/trestle-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "True History Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/true-history-brewing/"
|
||||
},
|
||||
{
|
||||
"text": "Upper Thames Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/upper-thames-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Vimy Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/vimy-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Walkerville Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/walkerville-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Wave Maker Craft Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/wave-maker-craft-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Wellington Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/wellington-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Whiprsnapr Brewing Co.",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/whiprsnapr-brewing-co/"
|
||||
},
|
||||
{
|
||||
"text": "Whiskeyjack Beer Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/whiskeyjack-beer-company/"
|
||||
},
|
||||
{
|
||||
"text": "Whitewater Brewing Company",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/whitewater-brewing-company/"
|
||||
},
|
||||
{
|
||||
"text": "Willibald Farm Distillery & Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/willibald-farm-distillery-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Windmill Brewery",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/windmill-brewery/"
|
||||
},
|
||||
{
|
||||
"text": "Wishbone Brewing",
|
||||
"href": "https://ontariocraftbrewers.com/brewery-profile/wishbone-brewing/"
|
||||
}
|
||||
]
|
||||
@@ -6,4 +6,3 @@ data
|
||||
models
|
||||
*.gguf
|
||||
BiergartenPipeline.png
|
||||
output
|
||||
181
pipeline/CMakeLists.txt
Normal file
181
pipeline/CMakeLists.txt
Normal file
@@ -0,0 +1,181 @@
|
||||
cmake_minimum_required(VERSION 3.24)
|
||||
project(biergarten-pipeline)
|
||||
|
||||
set(CMAKE_POLICY_VERSION_MINIMUM 3.5 CACHE STRING "" FORCE)
|
||||
|
||||
# =============================================================================
|
||||
# 1. Platform & GPU Detection
|
||||
# =============================================================================
|
||||
if(WIN32)
|
||||
message(FATAL_ERROR "[biergarten] Windows is currently not supported. Please use Linux (Fedora 43) or macOS (M1 Pro).")
|
||||
endif()
|
||||
|
||||
if(APPLE)
|
||||
if(CMAKE_SYSTEM_PROCESSOR MATCHES "arm64")
|
||||
message(STATUS "[biergarten] Apple Silicon detected — enabling Metal acceleration.")
|
||||
set(GGML_METAL ON CACHE BOOL "Enable Metal for Apple Silicon" FORCE)
|
||||
else()
|
||||
message(STATUS "[biergarten] Intel Mac detected — using CPU / Accelerate framework.")
|
||||
set(GGML_METAL OFF CACHE BOOL "Disable Metal for Intel Macs" FORCE)
|
||||
endif()
|
||||
elseif(UNIX AND NOT APPLE)
|
||||
find_package(CUDAToolkit QUIET)
|
||||
find_package(HIP QUIET)
|
||||
|
||||
if(CUDAToolkit_FOUND)
|
||||
message(STATUS "[biergarten] NVIDIA GPU detected — enabling CUDA acceleration.")
|
||||
set(GGML_CUDA ON CACHE BOOL "Enable CUDA for NVIDIA GPUs" FORCE)
|
||||
set(CMAKE_CUDA_ARCHITECTURES native)
|
||||
elseif(HIP_FOUND OR EXISTS "/opt/rocm")
|
||||
message(STATUS "[biergarten] AMD GPU detected — enabling HIP/ROCm acceleration.")
|
||||
set(GGML_HIPBLAS ON CACHE BOOL "Enable HIP for AMD GPUs" FORCE)
|
||||
else()
|
||||
message(STATUS "[biergarten] No NVIDIA or AMD GPU found — falling back to CPU.")
|
||||
endif()
|
||||
endif()
|
||||
|
||||
# =============================================================================
|
||||
# 2. Project-wide Settings (Standard & Optimization)
|
||||
# =============================================================================
|
||||
|
||||
set(CMAKE_CXX_STANDARD 20)
|
||||
set(CMAKE_CXX_STANDARD_REQUIRED ON)
|
||||
set(CMAKE_EXPORT_COMPILE_COMMANDS ON)
|
||||
|
||||
# Release Build Optimization: Aggressive (-O3), Arch-specific, and LTO
|
||||
set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -O3 -march=native -flto")
|
||||
|
||||
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -Og -g")
|
||||
|
||||
# =============================================================================
|
||||
# 3. Dependencies
|
||||
# =============================================================================
|
||||
include(FetchContent)
|
||||
|
||||
find_package(CURL QUIET)
|
||||
if(NOT CURL_FOUND)
|
||||
message(FATAL_ERROR "[biergarten] libcurl not found. Install it (e.g. 'sudo dnf install libcurl-devel').")
|
||||
endif()
|
||||
|
||||
# Require system Boost for JSON and Program Options to speed up build times
|
||||
find_package(Boost REQUIRED COMPONENTS json program_options)
|
||||
|
||||
FetchContent_Declare(
|
||||
sqlite_amalgamation
|
||||
URL https://www.sqlite.org/2026/sqlite-amalgamation-3530000.zip
|
||||
URL_HASH SHA3_256=c2325c53b3b41761469f91cfb078e96882ac5d85bac10c11b0bd8f253b031e5b
|
||||
)
|
||||
FetchContent_GetProperties(sqlite_amalgamation)
|
||||
if(NOT sqlite_amalgamation_POPULATED)
|
||||
FetchContent_Populate(sqlite_amalgamation)
|
||||
endif()
|
||||
|
||||
if(NOT TARGET sqlite3)
|
||||
add_library(sqlite3 STATIC
|
||||
${sqlite_amalgamation_SOURCE_DIR}/sqlite3.c
|
||||
)
|
||||
target_include_directories(sqlite3 PUBLIC
|
||||
${sqlite_amalgamation_SOURCE_DIR}
|
||||
)
|
||||
target_compile_definitions(sqlite3 PUBLIC
|
||||
SQLITE_THREADSAFE=1
|
||||
)
|
||||
endif()
|
||||
|
||||
FetchContent_Declare(
|
||||
llama-cpp
|
||||
GIT_REPOSITORY https://github.com/ggml-org/llama.cpp.git
|
||||
GIT_TAG b8742
|
||||
)
|
||||
FetchContent_MakeAvailable(llama-cpp)
|
||||
|
||||
FetchContent_Declare(
|
||||
boost-di
|
||||
GIT_REPOSITORY https://github.com/boost-ext/di.git
|
||||
GIT_TAG v1.3.0
|
||||
)
|
||||
FetchContent_MakeAvailable(boost-di)
|
||||
if(TARGET Boost.DI AND NOT TARGET boost::di)
|
||||
add_library(boost::di ALIAS Boost.DI)
|
||||
endif()
|
||||
|
||||
FetchContent_Declare(
|
||||
spdlog
|
||||
GIT_REPOSITORY https://github.com/gabime/spdlog.git
|
||||
GIT_TAG v1.15.3
|
||||
)
|
||||
FetchContent_MakeAvailable(spdlog)
|
||||
|
||||
# =============================================================================
|
||||
# 4. Sources
|
||||
# =============================================================================
|
||||
set(SOURCES
|
||||
src/main.cc
|
||||
src/biergarten_data_generator/biergarten_data_generator.cc
|
||||
src/biergarten_data_generator/run.cc
|
||||
src/biergarten_data_generator/query_cities_with_countries.cc
|
||||
src/biergarten_data_generator/generate_breweries.cc
|
||||
src/biergarten_data_generator/log_results.cc
|
||||
src/services/wikipedia/wikipedia_service.cc
|
||||
src/services/wikipedia/get_summary.cc
|
||||
src/services/wikipedia/fetch_extract.cc
|
||||
src/services/sqlite/sqlite_export_service.cc
|
||||
src/services/sqlite/build_database_path.cc
|
||||
src/services/sqlite/build_location_key.cc
|
||||
src/services/sqlite/initialize_schema.cc
|
||||
src/services/sqlite/prepare_statements.cc
|
||||
src/services/sqlite/initialize.cc
|
||||
src/services/sqlite/process_record.cc
|
||||
src/services/sqlite/finalize_statements.cc
|
||||
src/services/sqlite/rollback_and_close_no_throw.cc
|
||||
src/services/sqlite/finalize.cc
|
||||
src/web_client/curl_global_state.cc
|
||||
src/web_client/curl_web_client_get.cc
|
||||
src/web_client/curl_web_client_url_encode.cc
|
||||
src/data_generation/llama/llama_generator.cc
|
||||
src/data_generation/llama/generate_brewery.cc
|
||||
src/data_generation/llama/generate_user.cc
|
||||
src/data_generation/llama/helpers.cc
|
||||
src/data_generation/llama/infer.cc
|
||||
src/data_generation/llama/load.cc
|
||||
src/data_generation/llama/load_brewery_prompt.cc
|
||||
src/data_generation/prompt_formatting/gemma4_jinja_prompt_formatter.cc
|
||||
src/data_generation/mock/deterministic_hash.cc
|
||||
src/data_generation/mock/generate_brewery.cc
|
||||
src/data_generation/mock/generate_user.cc
|
||||
src/json_handling/json_loader.cc
|
||||
)
|
||||
|
||||
# =============================================================================
|
||||
# 5. Target
|
||||
# =============================================================================
|
||||
add_executable(${PROJECT_NAME} ${SOURCES})
|
||||
target_include_directories(${PROJECT_NAME} PRIVATE
|
||||
includes
|
||||
${llama-cpp_SOURCE_DIR}/include
|
||||
${llama-cpp_SOURCE_DIR}/common
|
||||
)
|
||||
target_link_libraries(${PROJECT_NAME} PRIVATE
|
||||
llama
|
||||
boost::di
|
||||
Boost::json
|
||||
Boost::program_options
|
||||
spdlog::spdlog
|
||||
sqlite3
|
||||
CURL::libcurl
|
||||
)
|
||||
|
||||
# =============================================================================
|
||||
# 6. Runtime Assets
|
||||
# =============================================================================
|
||||
configure_file(
|
||||
${CMAKE_SOURCE_DIR}/locations.json
|
||||
${CMAKE_BINARY_DIR}/locations.json
|
||||
COPYONLY
|
||||
)
|
||||
|
||||
add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
|
||||
COMMAND ${CMAKE_COMMAND} -E copy_directory
|
||||
${CMAKE_SOURCE_DIR}/prompts
|
||||
${CMAKE_BINARY_DIR}/prompts
|
||||
)
|
||||
344
pipeline/README.md
Normal file
344
pipeline/README.md
Normal file
@@ -0,0 +1,344 @@
|
||||
# Biergarten Pipeline
|
||||
|
||||
A C++20 command-line pipeline that samples city records from local JSON, enriches each with Wikipedia context, and generates bilingual brewery names and descriptions via a local GGUF model or a deterministic mock.
|
||||
|
||||
---
|
||||
|
||||
## Table of Contents
|
||||
|
||||
- [How It Fits The Main App](#how-it-fits-the-main-app)
|
||||
- [Tech Stack](#tech-stack)
|
||||
- [Build](#build)
|
||||
- [Model](#model)
|
||||
- [Run](#run)
|
||||
- [Architecture](#architecture)
|
||||
- [Pipeline Stages](#pipeline-stages)
|
||||
- [Key Components](#key-components)
|
||||
- [Runtime Behaviour](#runtime-behaviour)
|
||||
- [Generated Output](#generated-output)
|
||||
- [Language Generation Quality](#language-generation-quality)
|
||||
- [Known Issues](#known-issues)
|
||||
- [Tested Hardware](#tested-hardware)
|
||||
- [Repo Layout](#repo-layout)
|
||||
- [Code Tour](#code-tour)
|
||||
- [Fixture Strategy](#fixture-strategy)
|
||||
- [Next Steps](#next-steps)
|
||||
|
||||
---
|
||||
|
||||
## How It Fits The Main App
|
||||
|
||||
The pipeline is a data ingestion layer. It sits outside the web app runtime and produces seed records the app imports at startup or during a dedicated seed step.
|
||||
|
||||
| Planned app area | Pipeline contribution |
|
||||
| -------------------------------- | ------------------------------------------------------------------ |
|
||||
| Brewery discovery and management | Sampled city records, localized names, long-form descriptions |
|
||||
| Beer reviews and ratings | Stable brewery fixtures with enough context to anchor review pages |
|
||||
| Social follow relationships | Repeatable brewery entities for feeds, follows, and saved lists |
|
||||
| Geospatial brewery experiences | Latitude, longitude, and country-level metadata |
|
||||
|
||||
---
|
||||
|
||||
## Tech Stack
|
||||
|
||||
- C++20
|
||||
- CMake 3.24+
|
||||
- Boost.JSON, Boost.ProgramOptions, Boost.DI
|
||||
- spdlog
|
||||
- libcurl
|
||||
- SQLite amalgamation fetched and compiled via CMake FetchContent
|
||||
- llama.cpp
|
||||
|
||||
The build fetches Boost.DI, spdlog, llama.cpp, and SQLite via CMake. Metal is enabled on Apple Silicon; CUDA or HIP/ROCm is detected on Linux when the toolkit is present.
|
||||
|
||||
> **Code Style:** Modern C++20 throughout - RAII for ownership, `std::unique_ptr` for injected dependencies, `std::optional` for parse outcomes, `std::span` for read-only views over generated city data, structured bindings in pipeline loops. Formatting follows the Google C++ Style Guide via `.clang-format` with a narrow column limit and two-space indentation.
|
||||
|
||||
---
|
||||
|
||||
## Build
|
||||
|
||||
Requirements: C++20 compiler, CMake 3.24+, libcurl, Boost (JSON and ProgramOptions).
|
||||
SQLite is fetched from the upstream amalgamation, so no system SQLite package is required.
|
||||
|
||||
```bash
|
||||
cmake -S . -B build
|
||||
cmake --build build
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Model
|
||||
|
||||
> Skip this step if you only need `--mocked`.
|
||||
|
||||
```bash
|
||||
mkdir -p models
|
||||
curl -L \
|
||||
-o models/google_gemma-4-E4B-it-Q6_K.gguf \
|
||||
https://huggingface.co/bartowski/google_gemma-4-E4B-it-GGUF/resolve/main/google_gemma-4-E4B-it-Q6_K.gguf?download=true
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Run
|
||||
|
||||
Run from `build/` so the copied `locations.json` and `prompts/` are available. Each run also writes a fresh dated SQLite file such as `biergarten_seed_2026-04-19T15-30-45.123456Z.sqlite` into the working directory.
|
||||
|
||||
```bash
|
||||
./biergarten-pipeline --mocked
|
||||
./biergarten-pipeline --model models/google_gemma-4-E4B-it-Q6_K.gguf --temperature 1.0 --top-p 0.95 --top-k 64 --n-ctx 8192 --seed -1
|
||||
```
|
||||
|
||||
### CLI Flags
|
||||
|
||||
| Flag | Purpose |
|
||||
| --------------- | ------------------------------------------------------- |
|
||||
| `--mocked` | Deterministic mock generator, no model required. |
|
||||
| `--model, -m` | Path to a GGUF file. Required unless `--mocked` is set. |
|
||||
| `--temperature` | Sampling temperature. Default: `1.0`. |
|
||||
| `--top-p` | Nucleus sampling. Default: `0.95`. |
|
||||
| `--top-k` | Top-k sampling. Default: `64`. |
|
||||
| `--n-ctx` | Context window size. Default: `8192`. |
|
||||
| `--seed` | Random seed. Default: `-1` (random at runtime). |
|
||||
| `--help, -h` | Print usage and exit. |
|
||||
|
||||
`--mocked` and `--model` are mutually exclusive. Omitting both exits with an error before the pipeline starts. Sampling flags are ignored when `--mocked` is set.
|
||||
|
||||
The post-build step copies `prompts/` into `build/prompts/`. Rebuild after editing `prompts/system.md`.
|
||||
|
||||
---
|
||||
|
||||
## Architecture
|
||||
|
||||
### Pipeline Stages
|
||||
|
||||
| Stage | Implementation |
|
||||
| -------- | --------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Load | `JsonLoader::LoadLocations()` reads `locations.json` into typed `Location` records. |
|
||||
| Sample | `BiergartenDataGenerator::QueryCitiesWithCountries()` samples up to 50 locations per run. |
|
||||
| Enrich | `WikipediaService` fetches city and beer context. Keeps going when a lookup fails. |
|
||||
| Generate | `MockGenerator` or `LlamaGenerator` produces brewery names and descriptions in English and the local language. |
|
||||
| Store | `SqliteExportService` writes each successful brewery into a fresh dated `.sqlite` database with normalized location and brewery tables. |
|
||||
| Log | `spdlog` writes results and warnings to the console. |
|
||||
|
||||
If enrichment or generation fails for a city, that city is skipped and the pipeline continues.
|
||||
|
||||
### Key Components
|
||||
|
||||
- `src/main.cc` - argument parsing and Boost.DI composition root.
|
||||
- `JsonLoader` - validates curated location input.
|
||||
- `WikipediaService` - queries Wikipedia extracts, caches results, returns empty context on failure.
|
||||
- `LlamaGenerator` - formats prompts for Gemma 4, validates JSON output, retries malformed responses up to three times. If output looks truncated, the retry raises the token budget before trying again.
|
||||
- `MockGenerator` - stable hash-based output so the same city input always produces the same brewery.
|
||||
- `SqliteExportService` - creates a dated SQLite file per run and persists each successful brewery into normalized tables.
|
||||
- Brewery payloads include English and local-language name and description fields.
|
||||
|
||||
### Runtime Behaviour
|
||||
|
||||
`WikipediaService` queries city, country, and beer-related Wikipedia extracts using its configured lookup, then caches the first successful response per query string. The fetched extract text is included in the prompt as context for generation.
|
||||
|
||||
`GetLocationContext()` returns an empty string when the web client is unavailable or when lookup/parsing fails.
|
||||
|
||||
`LlamaGenerator` validates model output as structured JSON. The retry path exists as a safety hatch for cases where the reasoning block consumes available token budget and compresses the JSON output space. All runs to date have produced valid output on the first pass; the path is kept for resilience.
|
||||
|
||||
`MockGenerator` uses stable hashes for repeatable output in demos and Storybook runs.
|
||||
|
||||
### Process Flow - Activity Diagram
|
||||
|
||||

|
||||
|
||||
### Architectural Overview - Class Diagram
|
||||
|
||||

|
||||
|
||||
---
|
||||
|
||||
## Generated Output
|
||||
|
||||
Each successful run stores a `GeneratedBrewery` pair with the source location and a `BreweryResult` payload. The same generated records are also written to a fresh SQLite export file named with the current UTC timestamp.
|
||||
|
||||
| Field | Meaning |
|
||||
| ------------------- | ------------------------------------------ |
|
||||
| `name_en` | Brewery name in English. |
|
||||
| `description_en` | Brewery description in English. |
|
||||
| `name_local` | Brewery name in the local language. |
|
||||
| `description_local` | Brewery description in the local language. |
|
||||
|
||||
The log dump also includes city, country, state or province, ISO subdivision code, latitude, and longitude for each entry.
|
||||
|
||||
### Consumer Data Shape
|
||||
|
||||
| Field | Why it matters |
|
||||
| ----------------------------------- | ------------------------------------------------ |
|
||||
| `city`, `state_province`, `country` | Human-readable location labels and page headings |
|
||||
| `iso3166_1`, `iso3166_2` | Filtering, regional grouping, locale matching |
|
||||
| `latitude`, `longitude` | Map pins and nearby brewery views |
|
||||
| `local_languages` | Locale-aware copy selection |
|
||||
| `name_en`, `description_en` | Default English display content |
|
||||
| `name_local`, `description_local` | Local-language display content |
|
||||
| `region_context` | Richer copy for cards and detail pages |
|
||||
|
||||
---
|
||||
|
||||
## Language Generation Quality
|
||||
|
||||
The generation pipeline passes local language codes to the model to retrieve a translated `description_local`.
|
||||
|
||||
Output quality is reliable for high-resource languages such as French, though it may struggle with regional variants and idiomatic phrasing. This can be seen with these data points:
|
||||
|
||||
```json
|
||||
[
|
||||
{
|
||||
"city": "Kinshasa",
|
||||
"state_province": "Kinshasa",
|
||||
"iso3166_2": "CD-KN",
|
||||
"country": "Democratic Republic of the Congo",
|
||||
"iso3166_1": "CD",
|
||||
"latitude": -4.4419,
|
||||
"longitude": 15.2663,
|
||||
"local_languages": ["fr-CD", "ln"]
|
||||
},
|
||||
{
|
||||
"city": "Paris",
|
||||
"state_province": "Île-de-France",
|
||||
"iso3166_2": "FR-IDF",
|
||||
"country": "France",
|
||||
"iso3166_1": "FR",
|
||||
"latitude": 48.8566,
|
||||
"longitude": 2.3522,
|
||||
"local_languages": ["fr-FR"]
|
||||
},
|
||||
{
|
||||
"city": "Abidjan",
|
||||
"state_province": "Abidjan",
|
||||
"iso3166_2": "CI-AB",
|
||||
"country": "Ivory Coast",
|
||||
"iso3166_1": "CI",
|
||||
"latitude": 5.36,
|
||||
"longitude": -4.0083,
|
||||
"local_languages": ["fr-CI"]
|
||||
},
|
||||
{
|
||||
"city": "Montreal",
|
||||
"state_province": "Quebec",
|
||||
"iso3166_2": "CA-QC",
|
||||
"country": "Canada",
|
||||
"iso3166_1": "CA",
|
||||
"latitude": 45.5017,
|
||||
"longitude": -73.5673,
|
||||
"local_languages": ["fr-CA"]
|
||||
},
|
||||
{
|
||||
"city": "Brussels",
|
||||
"state_province": "Brussels-Capital Region",
|
||||
"iso3166_2": "BE-BRU",
|
||||
"country": "Belgium",
|
||||
"iso3166_1": "BE",
|
||||
"latitude": 50.8503,
|
||||
"longitude": 4.3517,
|
||||
"local_languages": ["fr-BE", "nl-BE"]
|
||||
}
|
||||
]
|
||||
```
|
||||
|
||||
Output sample: [./out-sample/french-cities.example](out-sample/french-cities.example)
|
||||
|
||||
### Known Issues
|
||||
|
||||
#### Low-Resource Language Hallucination
|
||||
|
||||
For languages such as Welsh (Wales), Maori (Aotearoa/New Zealand), or Sicilian (Sicily, Italy), the model can generate text that looks syntactically plausible but is semantically incoherent. This comes from limited training-data coverage rather than prompt engineering.
|
||||
|
||||
#### Proposed Mitigations
|
||||
|
||||
- **Prevention via allowlist:** introduce a high-resource language allowlist. If a location's code is unlisted, skip `description_local` generation and fall back to English.
|
||||
- **Upstream sanitization:** strip known low-resource language codes from the `locations.json` payload before generation.
|
||||
- **Downstream flagging:** add a `description_local_confidence` column to the SQLite schema so downstream applications can filter or flag potentially hallucinated text by language tier.
|
||||
|
||||
---
|
||||
|
||||
## Tested Hardware
|
||||
|
||||
### ARM macOS - M1 Pro
|
||||
|
||||
| | |
|
||||
| --------- | --------------------------------- |
|
||||
| Host | MacBook Pro 14" (2021) |
|
||||
| CPU | Apple M1 Pro (8-core) |
|
||||
| GPU | Apple M1 Pro (14-core integrated) |
|
||||
| Memory | 16 GB |
|
||||
| Model | Gemma 4 E4B |
|
||||
| Inference | llama.cpp with Metal |
|
||||
|
||||
### x86_64 Linux - NVIDIA RTX 2000
|
||||
|
||||
| | |
|
||||
| --------- | ------------------------------ |
|
||||
| Host | ThinkPad P1 Gen 7 (Fedora 43) |
|
||||
| CPU | Intel Core Ultra 7 155H |
|
||||
| GPU | NVIDIA RTX 2000 Ada Generation |
|
||||
| Memory | 32 GB |
|
||||
| Model | Gemma 4 E4B |
|
||||
| Inference | llama.cpp with CUDA 12.x |
|
||||
|
||||
---
|
||||
|
||||
## Repo Layout
|
||||
|
||||
| Path | Purpose |
|
||||
| ---------------- | ---------------------------------------------- |
|
||||
| `includes/` | Public headers and shared models. |
|
||||
| `src/` | Implementation files. |
|
||||
| `locations.json` | Curated city input copied into the build tree. |
|
||||
| `prompts/` | System prompt used by the model-backed path. |
|
||||
| `diagrams/` | Architecture and pipeline diagrams. |
|
||||
|
||||
---
|
||||
|
||||
## Code Tour
|
||||
|
||||
- `src/main.cc` - argument parsing and DI composition root.
|
||||
- `src/biergarten_data_generator/` - orchestration, sampling, logging, and export.
|
||||
- `src/services/wikipedia/` - enrichment service and cache.
|
||||
- `src/services/sqlite/` - SQLite export implementation.
|
||||
- `src/data_generation/llama/` - local inference, prompt loading, output validation.
|
||||
- `src/data_generation/mock/` - deterministic fallback.
|
||||
|
||||
---
|
||||
|
||||
## Fixture Strategy
|
||||
|
||||
- `--mocked` for stable fixtures, repeatable screenshots, and Storybook runs.
|
||||
- `--model` when geographically grounded content matters for demos.
|
||||
- Keep `locations.json` structured enough to support discovery and future filtering.
|
||||
- Treat SQLite output as seed material for the app's brewery domain, not production data.
|
||||
|
||||
---
|
||||
|
||||
## Next Steps
|
||||
|
||||
The pipeline currently produces city-aware brewery records and dated SQLite exports. The next passes add additional fixture types so the app can exercise the full brewery domain without live data.
|
||||
|
||||
### Testing _(Very High Importance)_
|
||||
|
||||
- Unit test JSON validation and retry logic against malformed, truncated, and empty model outputs.
|
||||
- Integration test the enrichment pipeline with missing context, short context, and fake context inputs.
|
||||
- Adversarial context tests: feed plausible but geographically incorrect Wikipedia extracts and verify the model does not silently blend them with training data.
|
||||
- Verify bilingual enrichment behaviour when only an English extract is available versus when both extracts are present.
|
||||
- Confirm the retry path is reachable when the reasoning block consumes available token budget.
|
||||
|
||||
### Beer Generation
|
||||
|
||||
Generate catalog entries with style, ABV, IBU, color, aroma notes, and food pairing hints. Link beers back to breweries and cities. Keep style coverage wide enough to exercise search, sort, and category filters.
|
||||
|
||||
### User Generation
|
||||
|
||||
Generate user profiles with stable names, bios, locale hints, and preference signals. Include stable IDs for downstream fixture joins. Keep output deterministic for screenshots while allowing larger randomized batches.
|
||||
|
||||
### Check-In System
|
||||
|
||||
Produce timestamped check-in events between users and breweries. Use a J-curve activity profile - a small set of users accounts for most check-ins, the rest appear occasionally. Add bursty behaviour around weekends and travel periods.
|
||||
|
||||
### Beer Ratings
|
||||
|
||||
Generate rating events with a strong positive skew and a long tail of lower scores. Avoid uniform distributions. Attach timestamps and user IDs so the app can compute averages, trends, and per-style comparisons.
|
||||
125
pipeline/diagrams/activity-diagram.puml
Normal file
125
pipeline/diagrams/activity-diagram.puml
Normal file
@@ -0,0 +1,125 @@
|
||||
@startuml
|
||||
skinparam style strictuml
|
||||
skinparam defaultFontName "DM Sans"
|
||||
skinparam defaultFontSize 14
|
||||
skinparam titleFontName "Volkhov"
|
||||
skinparam titleFontSize 20
|
||||
skinparam backgroundColor #FAFCF9
|
||||
skinparam defaultFontColor #28342A
|
||||
skinparam titleFontColor #28342A
|
||||
skinparam ArrowColor #628A5B
|
||||
skinparam NoteBackgroundColor #EAF0E8
|
||||
skinparam NoteBorderColor #547461
|
||||
skinparam ActivityBackgroundColor #FAFCF9
|
||||
skinparam ActivityBorderColor #547461
|
||||
skinparam ActivityDiamondBackgroundColor #FAFCF9
|
||||
skinparam ActivityDiamondBorderColor #628A5B
|
||||
skinparam ActivityBarColor #628A5B
|
||||
skinparam SwimlaneBorderColor #547461
|
||||
skinparam SwimlaneBorderThickness 0.3
|
||||
|
||||
title The Biergarten Data Pipeline (Streaming Architecture)
|
||||
|
||||
|#F2F6F0|main.cc|
|
||||
start
|
||||
:ParseArguments(argc, argv);
|
||||
if (Are arguments valid?) then (no)
|
||||
:spdlog::error usage info;
|
||||
stop
|
||||
else (yes)
|
||||
endif
|
||||
|
||||
:Init CurlGlobalState & LlamaBackendState;
|
||||
:di::make_injector(...);
|
||||
:injector.create<std::unique_ptr<BiergartenDataGenerator>>();
|
||||
:BiergartenDataGenerator::Run();
|
||||
|
||||
|#EAF0E8|BiergartenDataGenerator|
|
||||
:Initialize SQLite export;
|
||||
|
||||
|#E0EAE0|SqliteExportService|
|
||||
:GetUtcTimestamp() from SystemDateTimeProvider;
|
||||
:Initialize();
|
||||
note right
|
||||
Builds a fresh biergarten_seed_<UTC datetime>.sqlite filename
|
||||
Appends a numeric suffix if the timestamp already exists
|
||||
Opens DB Connection
|
||||
Executes Schema DDL
|
||||
Begins Transaction
|
||||
end note
|
||||
|
||||
|#EAF0E8|BiergartenDataGenerator|
|
||||
:QueryCitiesWithCountries();
|
||||
|
||||
|#E2EBDC|JsonLoader|
|
||||
:JsonLoader::LoadLocations("locations.json");
|
||||
:std::ranges::sample(all_locations, 50);
|
||||
|
||||
|#EAF0E8|BiergartenDataGenerator|
|
||||
while (For each sampled Location?) is (Remaining cities)
|
||||
|#DCE8D8|WikipediaService|
|
||||
:GetLocationContext(loc);
|
||||
:FetchExtracts(City, Country, Beer);
|
||||
|#EAF0E8|BiergartenDataGenerator|
|
||||
:Store EnrichedCity{Location, region_context};
|
||||
endwhile (Done)
|
||||
|
||||
|#EAF0E8|BiergartenDataGenerator|
|
||||
:GenerateBreweries(enriched_cities);
|
||||
|
||||
|#E5EDE1|DataGenerator|
|
||||
while (For each EnrichedCity?) is (Remaining cities)
|
||||
if (Generator Mode) then (MockGenerator)
|
||||
:DeterministicHash & Format;
|
||||
else (LlamaGenerator)
|
||||
:PrepareRegionContext;
|
||||
:LoadBrewerySystemPrompt("prompts/system.md");
|
||||
repeat
|
||||
:Infer(system_prompt, user_prompt, max_tokens, kBreweryJsonGrammar);
|
||||
:ValidateBreweryJson(raw, brewery);
|
||||
if (Is JSON Valid?) then (yes)
|
||||
break
|
||||
else (no)
|
||||
:Attempt++;
|
||||
endif
|
||||
repeat while (Attempt < 3?) is (yes)
|
||||
endif
|
||||
|
||||
|#EAF0E8|BiergartenDataGenerator|
|
||||
if (Generation successful?) then (yes)
|
||||
|#E0EAE0|SqliteExportService|
|
||||
:ProcessRecord(GeneratedBrewery);
|
||||
if (Location in cache?) then (yes)
|
||||
:Reuse location_id;
|
||||
else (no)
|
||||
:Insert Location & Cache ID;
|
||||
endif
|
||||
:Insert Brewery (FK: location_id);
|
||||
|
||||
if (Exception caught during insert?) then (yes)
|
||||
|#EAF0E8|BiergartenDataGenerator|
|
||||
:spdlog::warn "Failed to stream record to SQLite export";
|
||||
note right
|
||||
Data loss is prevented per-record.
|
||||
The pipeline continues running.
|
||||
end note
|
||||
else (no)
|
||||
endif
|
||||
else (no)
|
||||
:spdlog::warn "Generation failed, skipping...";
|
||||
endif
|
||||
|#E5EDE1|DataGenerator|
|
||||
endwhile (Done)
|
||||
|
||||
|#E0EAE0|SqliteExportService|
|
||||
:Finalize();
|
||||
note right
|
||||
Commits Transaction
|
||||
Closes Database Connection
|
||||
end note
|
||||
|
||||
|#F2F6F0|main.cc|
|
||||
:Return 0;
|
||||
stop
|
||||
|
||||
@enduml
|
||||
1
pipeline/diagrams/activity-diagram.svg
Normal file
1
pipeline/diagrams/activity-diagram.svg
Normal file
File diff suppressed because one or more lines are too long
148
pipeline/diagrams/class-diagram.puml
Normal file
148
pipeline/diagrams/class-diagram.puml
Normal file
@@ -0,0 +1,148 @@
|
||||
@startuml
|
||||
skinparam style strictuml
|
||||
skinparam defaultFontName "DM Sans"
|
||||
skinparam defaultFontSize 14
|
||||
skinparam titleFontName "Volkhov"
|
||||
skinparam titleFontSize 20
|
||||
skinparam backgroundColor #FAFCF9
|
||||
skinparam defaultFontColor #28342A
|
||||
skinparam titleFontColor #28342A
|
||||
skinparam ArrowColor #628A5B
|
||||
|
||||
skinparam class {
|
||||
BackgroundColor #FAFCF9
|
||||
HeaderBackgroundColor #EAF0E8
|
||||
BorderColor #547461
|
||||
ArrowColor #628A5B
|
||||
FontColor #28342A
|
||||
}
|
||||
|
||||
skinparam note {
|
||||
BackgroundColor #EAF0E8
|
||||
BorderColor #547461
|
||||
FontColor #28342A
|
||||
}
|
||||
|
||||
title The Biergarten Data Pipeline - Class Diagram
|
||||
|
||||
class BiergartenDataGenerator {
|
||||
- context_service_ : std::unique_ptr<IEnrichmentService>
|
||||
- generator_ : std::unique_ptr<DataGenerator>
|
||||
- exporter_ : std::unique_ptr<IExportService>
|
||||
- generated_breweries_ : std::vector<GeneratedBrewery>
|
||||
+ Run() : bool
|
||||
- QueryCitiesWithCountries() : std::vector<Location>
|
||||
- GenerateBreweries(cities : std::span<const EnrichedCity>) : void
|
||||
- LogResults() : void
|
||||
}
|
||||
|
||||
interface IEnrichmentService <<interface>> {
|
||||
+ GetLocationContext(loc : const Location&) : std::string
|
||||
}
|
||||
|
||||
class WikipediaService {
|
||||
- client_ : std::unique_ptr<WebClient>
|
||||
- extract_cache_ : std::unordered_map<std::string, std::string>
|
||||
+ GetLocationContext(loc : const Location&) : std::string
|
||||
- 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
|
||||
}
|
||||
|
||||
interface DataGenerator <<interface>> {
|
||||
+ GenerateBrewery(location : const Location&, region_context : const std::string&) : BreweryResult
|
||||
+ GenerateUser(locale : const std::string&) : UserResult
|
||||
}
|
||||
|
||||
class MockGenerator {
|
||||
+ GenerateBrewery(...) : BreweryResult
|
||||
+ GenerateUser(...) : UserResult
|
||||
- DeterministicHash(location : const Location&) : size_t
|
||||
}
|
||||
|
||||
class LlamaGenerator {
|
||||
- model_ : ModelHandle
|
||||
- context_ : ContextHandle
|
||||
- prompt_formatter_ : std::unique_ptr<IPromptFormatter>
|
||||
- rng_ : std::mt19937
|
||||
+ GenerateBrewery(...) : BreweryResult
|
||||
+ GenerateUser(...) : UserResult
|
||||
- Load(model_path : const std::string&) : void
|
||||
- Infer(...) : std::string
|
||||
- InferFormatted(...) : std::string
|
||||
- LoadBrewerySystemPrompt(...) : std::string
|
||||
}
|
||||
|
||||
interface IPromptFormatter <<interface>> {
|
||||
+ Format(system_prompt : std::string_view, user_prompt : std::string_view) : std::string
|
||||
}
|
||||
|
||||
class Gemma4JinjaPromptFormatter {
|
||||
+ Format(system_prompt : std::string_view, user_prompt : std::string_view) : std::string
|
||||
}
|
||||
|
||||
class JsonLoader {
|
||||
+ {static} LoadLocations(filepath : const std::filesystem::path&) : std::vector<Location>
|
||||
}
|
||||
|
||||
interface IExportService <<interface>> {
|
||||
+ Initialize() : void
|
||||
+ ProcessRecord(brewery : const GeneratedBrewery&) : void
|
||||
+ Finalize() : void
|
||||
}
|
||||
|
||||
class SqliteExportService {
|
||||
- date_time_provider_ : std::unique_ptr<IDateTimeProvider>
|
||||
- run_timestamp_utc_ : std::string
|
||||
- database_path_ : std::filesystem::path
|
||||
- db_handle_ : sqlite3*
|
||||
- insert_location_stmt_ : sqlite3_stmt*
|
||||
- insert_brewery_stmt_ : sqlite3_stmt*
|
||||
- transaction_open_ : bool
|
||||
- location_cache_ : std::unordered_map<std::string, sqlite3_int64>
|
||||
+ Initialize() : void
|
||||
+ ProcessRecord(brewery : const GeneratedBrewery&) : void
|
||||
+ Finalize() : void
|
||||
- InitializeSchema() : void
|
||||
}
|
||||
|
||||
interface IDateTimeProvider <<interface>> {
|
||||
+ GetUtcTimestamp() : std::string
|
||||
}
|
||||
|
||||
class SystemDateTimeProvider {
|
||||
+ GetUtcTimestamp() : std::string
|
||||
}
|
||||
|
||||
' Structural Relationships / Dependency Injection
|
||||
BiergartenDataGenerator *-- IEnrichmentService : owns
|
||||
BiergartenDataGenerator *-- DataGenerator : owns
|
||||
BiergartenDataGenerator *-- IExportService : owns
|
||||
|
||||
IEnrichmentService <|.. WikipediaService : implements
|
||||
WikipediaService *-- WebClient : owns
|
||||
|
||||
WebClient <|.. CURLWebClient : implements
|
||||
|
||||
DataGenerator <|.. MockGenerator : implements
|
||||
DataGenerator <|.. LlamaGenerator : implements
|
||||
|
||||
LlamaGenerator *-- IPromptFormatter : uses
|
||||
|
||||
IPromptFormatter <|.. Gemma4JinjaPromptFormatter : implements
|
||||
|
||||
BiergartenDataGenerator ..> JsonLoader : uses
|
||||
|
||||
IExportService <|.. SqliteExportService : implements
|
||||
SqliteExportService *-- IDateTimeProvider : owns
|
||||
IDateTimeProvider <|.. SystemDateTimeProvider : implements
|
||||
|
||||
@enduml
|
||||
1
pipeline/diagrams/class-diagram.svg
Normal file
1
pipeline/diagrams/class-diagram.svg
Normal file
File diff suppressed because one or more lines are too long
83
pipeline/includes/biergarten_data_generator.h
Normal file
83
pipeline/includes/biergarten_data_generator.h
Normal file
@@ -0,0 +1,83 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
|
||||
|
||||
/**
|
||||
* @file biergarten_data_generator.h
|
||||
* @brief Core orchestration class for pipeline data generation.
|
||||
*/
|
||||
|
||||
#include <memory>
|
||||
#include <span>
|
||||
#include <vector>
|
||||
|
||||
#include "data_generation/data_generator.h"
|
||||
#include "data_model/enriched_city.h"
|
||||
#include "data_model/generated_brewery.h"
|
||||
#include "data_model/location.h"
|
||||
#include "services/enrichment_service.h"
|
||||
#include "services/export_service.h"
|
||||
|
||||
/**
|
||||
* @brief Main data generator class for the Biergarten pipeline.
|
||||
*
|
||||
* This class encapsulates the core logic for generating brewery data.
|
||||
* It handles location loading, city enrichment, and brewery generation.
|
||||
*/
|
||||
class BiergartenDataGenerator {
|
||||
public:
|
||||
/**
|
||||
* @brief Construct a BiergartenDataGenerator with injected dependencies.
|
||||
*
|
||||
* @param context_service Context provider for sampled locations.
|
||||
* @param generator Brewery and user data generator.
|
||||
* @param exporter Storage backend for generated brewery data.
|
||||
*/
|
||||
BiergartenDataGenerator(std::unique_ptr<IEnrichmentService> context_service,
|
||||
std::unique_ptr<DataGenerator> generator,
|
||||
std::unique_ptr<IExportService> exporter);
|
||||
|
||||
/**
|
||||
* @brief Run the data generation pipeline.
|
||||
*
|
||||
* Performs the following steps:
|
||||
* 1. Load curated locations from JSON
|
||||
* 2. Resolve context for each city using the injected context service
|
||||
* 3. Generate brewery data for sampled cities
|
||||
*
|
||||
* @return true if successful, false if not
|
||||
*/
|
||||
bool Run();
|
||||
|
||||
private:
|
||||
/// @brief Owning context provider dependency.
|
||||
std::unique_ptr<IEnrichmentService> context_service_;
|
||||
|
||||
/// @brief Generator dependency selected in the composition root.
|
||||
std::unique_ptr<DataGenerator> generator_;
|
||||
|
||||
/// @brief Storage backend for generated brewery records.
|
||||
std::unique_ptr<IExportService> exporter_;
|
||||
|
||||
/**
|
||||
* @brief Load locations from JSON and sample cities.
|
||||
*
|
||||
* @return Vector of sampled locations capped at 50 entries.
|
||||
*/
|
||||
static std::vector<Location> QueryCitiesWithCountries();
|
||||
|
||||
/**
|
||||
* @brief Generate breweries for enriched cities.
|
||||
*
|
||||
* @param cities Span of enriched city data.
|
||||
*/
|
||||
void GenerateBreweries(std::span<const EnrichedCity> cities);
|
||||
|
||||
/**
|
||||
* @brief Log the generated brewery results.
|
||||
*/
|
||||
void LogResults() const;
|
||||
|
||||
/// @brief Stores generated brewery data.
|
||||
std::vector<GeneratedBrewery> generated_breweries_;
|
||||
};
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_DATA_GENERATOR_H_
|
||||
@@ -8,7 +8,9 @@
|
||||
|
||||
#include <string>
|
||||
|
||||
#include "data_model/generated_models.h"
|
||||
#include "data_model/brewery_result.h"
|
||||
#include "data_model/location.h"
|
||||
#include "data_model/user_result.h"
|
||||
|
||||
/**
|
||||
* @brief Interface for data generator implementations.
|
||||
@@ -28,16 +30,12 @@ class DataGenerator {
|
||||
const std::string& region_context) = 0;
|
||||
|
||||
/**
|
||||
* @brief Generates a user profile grounded in a sampled name and persona.
|
||||
* @brief Generates a user profile for a locale.
|
||||
*
|
||||
* @param city Enriched city the user is associated with.
|
||||
* @param persona Persona archetype grounding the generated bio.
|
||||
* @param name Sampled first/last name (and gender)
|
||||
* @param locale Locale hint used by generator.
|
||||
* @return User generation result.
|
||||
*/
|
||||
virtual UserResult GenerateUser(const EnrichedCity& city,
|
||||
const UserPersona& persona,
|
||||
const Name& name) = 0;
|
||||
virtual UserResult GenerateUser(const std::string& locale) = 0;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_DATA_GENERATOR_H_
|
||||
@@ -1,13 +1,14 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_H_
|
||||
|
||||
#include <filesystem>
|
||||
|
||||
/**
|
||||
* @file data_generation/llama_generator.h
|
||||
* @brief llama.cpp-backed implementation of DataGenerator.
|
||||
*/
|
||||
|
||||
#include <cstdint>
|
||||
#include <filesystem>
|
||||
#include <memory>
|
||||
#include <random>
|
||||
#include <string>
|
||||
@@ -15,9 +16,7 @@
|
||||
|
||||
#include "data_generation/data_generator.h"
|
||||
#include "data_generation/prompt_formatting/prompt_formatter.h"
|
||||
#include "data_model/models.h"
|
||||
#include "services/logging/logger.h"
|
||||
#include "services/prompting/prompt_directory.h"
|
||||
#include "data_model/application_options.h"
|
||||
|
||||
struct llama_model;
|
||||
struct llama_context;
|
||||
@@ -34,18 +33,21 @@ class LlamaGenerator final : public DataGenerator {
|
||||
* @param options Parsed application options.
|
||||
* @param model_path Filesystem path to GGUF model assets.
|
||||
* @param prompt_formatter Formatter that produces model-specific prompts.
|
||||
* @param prompt_directory Directory service for loading named prompt files.
|
||||
*/
|
||||
LlamaGenerator(const ApplicationOptions& options,
|
||||
const std::string& model_path, std::shared_ptr<ILogger> logger,
|
||||
std::unique_ptr<IPromptFormatter> prompt_formatter,
|
||||
std::unique_ptr<IPromptDirectory> prompt_directory);
|
||||
const std::string& model_path,
|
||||
std::unique_ptr<IPromptFormatter> prompt_formatter);
|
||||
|
||||
~LlamaGenerator() override;
|
||||
|
||||
// disable copy constructor
|
||||
LlamaGenerator(const LlamaGenerator&) = delete;
|
||||
|
||||
// disable copy assignment operator
|
||||
LlamaGenerator& operator=(const LlamaGenerator&) = delete;
|
||||
// disable move constructor
|
||||
LlamaGenerator(LlamaGenerator&&) = delete;
|
||||
// disable move assignment operator
|
||||
LlamaGenerator& operator=(LlamaGenerator&&) = delete;
|
||||
|
||||
/**
|
||||
@@ -59,15 +61,12 @@ class LlamaGenerator final : public DataGenerator {
|
||||
const std::string& region_context) override;
|
||||
|
||||
/**
|
||||
* @brief Generates a user profile grounded in a sampled name and persona.
|
||||
* @brief Generates a user profile for the provided locale.
|
||||
*
|
||||
* @param city Enriched city the user is associated with.
|
||||
* @param persona Persona archetype grounding the generated bio.
|
||||
* @param name Sampled first/last name -- not LLM-invented.
|
||||
* @param locale Locale hint.
|
||||
* @return Generated user profile.
|
||||
*/
|
||||
UserResult GenerateUser(const EnrichedCity& city, const UserPersona& persona,
|
||||
const Name& name) override;
|
||||
UserResult GenerateUser(const std::string& locale) override;
|
||||
|
||||
private:
|
||||
static constexpr int32_t kDefaultMaxTokens = 10000;
|
||||
@@ -120,6 +119,15 @@ class LlamaGenerator final : public DataGenerator {
|
||||
int max_tokens = kDefaultMaxTokens,
|
||||
std::string_view grammar = {});
|
||||
|
||||
/**
|
||||
* @brief Loads the brewery system prompt from disk.
|
||||
*
|
||||
* @param prompt_file_path Prompt file path to try first.
|
||||
* @return Loaded prompt text.
|
||||
*/
|
||||
std::string LoadBrewerySystemPrompt(
|
||||
const std::filesystem::path& prompt_file_path);
|
||||
|
||||
ModelHandle model_;
|
||||
ContextHandle context_;
|
||||
float sampling_temperature_ = 1.0F;
|
||||
@@ -127,10 +135,8 @@ class LlamaGenerator final : public DataGenerator {
|
||||
uint32_t sampling_top_k_ = kDefaultSamplingTopK;
|
||||
std::mt19937 rng_;
|
||||
uint32_t n_ctx_ = kDefaultContextSize;
|
||||
int n_gpu_layers_ = 0;
|
||||
std::shared_ptr<ILogger> logger_;
|
||||
std::string brewery_system_prompt_;
|
||||
std::unique_ptr<IPromptFormatter> prompt_formatter_;
|
||||
std::unique_ptr<IPromptDirectory> prompt_directory_;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_H_
|
||||
@@ -12,7 +12,7 @@
|
||||
#include <string>
|
||||
#include <string_view>
|
||||
|
||||
#include "data_model/generated_models.h"
|
||||
#include "data_model/brewery_result.h"
|
||||
|
||||
struct llama_vocab;
|
||||
using llama_token = int32_t;
|
||||
@@ -47,18 +47,4 @@ void AppendTokenPiece(const llama_vocab* vocab, llama_token token,
|
||||
std::optional<std::string> ValidateBreweryJson(const std::string& raw,
|
||||
BreweryResult& brewery_out);
|
||||
|
||||
/**
|
||||
* @brief Validates and parses user JSON output.
|
||||
*
|
||||
* Only populates `username`, `bio`, and `activity_weight` -- `first_name`
|
||||
* and `last_name` are not LLM-authored and are set separately from the
|
||||
* sampled Name.
|
||||
*
|
||||
* @param raw Raw model output.
|
||||
* @param user_out Parsed user payload.
|
||||
* @return Validation error message if invalid, or std::nullopt on success.
|
||||
*/
|
||||
std::optional<std::string> ValidateUserJson(const std::string& raw,
|
||||
UserResult& user_out);
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_HELPERS_H_
|
||||
@@ -28,16 +28,12 @@ class MockGenerator final : public DataGenerator {
|
||||
const std::string& region_context) override;
|
||||
|
||||
/**
|
||||
* @brief Generates deterministic user data grounded in a sampled name and
|
||||
* persona.
|
||||
* @brief Generates deterministic user data for a locale.
|
||||
*
|
||||
* @param city Enriched city the user is associated with.
|
||||
* @param persona Persona archetype.
|
||||
* @param name Sampled first/last name, copied directly into the result.
|
||||
* @param locale Locale hint.
|
||||
* @return Generated user result.
|
||||
*/
|
||||
UserResult GenerateUser(const EnrichedCity& city, const UserPersona& persona,
|
||||
const Name& name) override;
|
||||
UserResult GenerateUser(const std::string& locale) override;
|
||||
|
||||
private:
|
||||
/**
|
||||
@@ -48,26 +44,6 @@ class MockGenerator final : public DataGenerator {
|
||||
*/
|
||||
static size_t DeterministicHash(const Location& location);
|
||||
|
||||
/**
|
||||
* @brief Combines city, persona, and name into a stable hash value.
|
||||
*
|
||||
* @param location City and country names.
|
||||
* @param persona Persona archetype.
|
||||
* @param name Sampled first/last name.
|
||||
* @return Deterministic hash value.
|
||||
*/
|
||||
static size_t DeterministicHash(const Location& location,
|
||||
const UserPersona& persona, const Name& name);
|
||||
|
||||
// Hash stride constants for deterministic distribution across fixed-size
|
||||
// arrays. These coprime strides spread hash values uniformly without
|
||||
// clustering, ensuring diverse output across different hash inputs.
|
||||
static constexpr size_t kNounHashStride = 7;
|
||||
static constexpr size_t kDescriptionHashStride = 13;
|
||||
static constexpr size_t kBioHashStride = 11;
|
||||
static constexpr size_t kActivityWeightHashStride = 17;
|
||||
static constexpr size_t kActivityWeightHashRange = 1000;
|
||||
|
||||
static constexpr std::array<std::string_view, 18> kBreweryAdjectives = {
|
||||
"Craft", "Heritage", "Local", "Artisan", "Pioneer", "Golden",
|
||||
"Modern", "Classic", "Summit", "Northern", "Riverstone", "Barrel",
|
||||
@@ -141,8 +117,7 @@ class MockGenerator final : public DataGenerator {
|
||||
"Visits breweries for the stories, stays for the flagship pours.",
|
||||
"Craft beer fan mapping tasting notes and favorite brew routes.",
|
||||
"Always ready to trade recommendations for underrated local breweries.",
|
||||
"Keeping a running list of must-try collab releases and tap "
|
||||
"takeovers."};
|
||||
"Keeping a running list of must-try collab releases and tap takeovers."};
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_MOCK_GENERATOR_H_
|
||||
@@ -1,5 +1,4 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_GEMMA4_JINJA_PROMPT_FORMATTER_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_GEMMA4_JINJA_PROMPT_FORMATTER_H_
|
||||
#pragma once
|
||||
|
||||
#include <string>
|
||||
#include <string_view>
|
||||
@@ -14,5 +13,3 @@ class Gemma4JinjaPromptFormatter final : public IPromptFormatter {
|
||||
[[nodiscard]] std::string Format(std::string_view system_prompt,
|
||||
std::string_view user_prompt) const override;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_GEMMA4_JINJA_PROMPT_FORMATTER_H_
|
||||
@@ -1,5 +1,4 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_
|
||||
#pragma once
|
||||
|
||||
#include <string>
|
||||
#include <string_view>
|
||||
@@ -16,5 +15,3 @@ class IPromptFormatter {
|
||||
[[nodiscard]] virtual std::string Format(
|
||||
std::string_view system_prompt, std::string_view user_prompt) const = 0;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_H_
|
||||
42
pipeline/includes/data_model/application_options.h
Normal file
42
pipeline/includes/data_model/application_options.h
Normal file
@@ -0,0 +1,42 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_APPLICATION_OPTIONS_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_APPLICATION_OPTIONS_H_
|
||||
|
||||
/**
|
||||
* @file data_model/application_options.h
|
||||
* @brief Program options for the Biergarten pipeline application.
|
||||
*/
|
||||
|
||||
#include <cstdint>
|
||||
#include <string>
|
||||
|
||||
/**
|
||||
* @brief Program options for the Biergarten pipeline application.
|
||||
*/
|
||||
struct ApplicationOptions {
|
||||
/// @brief Path to the LLM model file (gguf format); mutually exclusive with
|
||||
/// use_mocked.
|
||||
std::string model_path;
|
||||
|
||||
/// @brief Use mocked generator instead of LLM; mutually exclusive with
|
||||
/// model_path.
|
||||
bool use_mocked = false;
|
||||
|
||||
/// @brief LLM sampling temperature (0.0 to 1.0, higher = more random).
|
||||
float temperature = 1.0F;
|
||||
|
||||
/// @brief LLM nucleus sampling top-p parameter (0.0 to 1.0, higher = more
|
||||
/// random).
|
||||
float top_p = 0.95F;
|
||||
|
||||
/// @brief LLM top-k sampling parameter.
|
||||
uint32_t top_k = 64;
|
||||
|
||||
/// @brief Context window size (tokens) for LLM inference. Higher values
|
||||
/// support longer prompts but use more memory.
|
||||
uint32_t n_ctx = 8192;
|
||||
|
||||
/// @brief Random seed for sampling (-1 for random, otherwise non-negative).
|
||||
int seed = -1;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_APPLICATION_OPTIONS_H_
|
||||
22
pipeline/includes/data_model/brewery_location.h
Normal file
22
pipeline/includes/data_model/brewery_location.h
Normal file
@@ -0,0 +1,22 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_LOCATION_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_LOCATION_H_
|
||||
|
||||
/**
|
||||
* @file data_model/brewery_location.h
|
||||
* @brief Non-owning brewery location input.
|
||||
*/
|
||||
|
||||
#include <string_view>
|
||||
|
||||
/**
|
||||
* @brief Non-owning brewery location input.
|
||||
*/
|
||||
struct BreweryLocation {
|
||||
/// @brief City name.
|
||||
std::string_view city_name;
|
||||
|
||||
/// @brief Country name.
|
||||
std::string_view country_name;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_LOCATION_H_
|
||||
28
pipeline/includes/data_model/brewery_result.h
Normal file
28
pipeline/includes/data_model/brewery_result.h
Normal file
@@ -0,0 +1,28 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_RESULT_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_RESULT_H_
|
||||
|
||||
/**
|
||||
* @file data_model/brewery_result.h
|
||||
* @brief Generated brewery payload.
|
||||
*/
|
||||
|
||||
#include <string>
|
||||
|
||||
/**
|
||||
* @brief Generated brewery payload.
|
||||
*/
|
||||
struct BreweryResult {
|
||||
/// @brief Brewery display name in English.
|
||||
std::string name_en;
|
||||
|
||||
/// @brief Brewery description text in English.
|
||||
std::string description_en;
|
||||
|
||||
/// @brief Brewery display name in the local language.
|
||||
std::string name_local;
|
||||
|
||||
/// @brief Brewery description text in the local language.
|
||||
std::string description_local;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_BREWERY_RESULT_H_
|
||||
21
pipeline/includes/data_model/enriched_city.h
Normal file
21
pipeline/includes/data_model/enriched_city.h
Normal file
@@ -0,0 +1,21 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_ENRICHED_CITY_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_ENRICHED_CITY_H_
|
||||
|
||||
/**
|
||||
* @file data_model/enriched_city.h
|
||||
* @brief Enriched city data with Wikipedia context.
|
||||
*/
|
||||
|
||||
#include <string>
|
||||
|
||||
#include "data_model/location.h"
|
||||
|
||||
/**
|
||||
* @brief Enriched city data with Wikipedia context.
|
||||
*/
|
||||
struct EnrichedCity {
|
||||
Location location;
|
||||
std::string region_context{};
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_ENRICHED_CITY_H_
|
||||
20
pipeline/includes/data_model/generated_brewery.h
Normal file
20
pipeline/includes/data_model/generated_brewery.h
Normal file
@@ -0,0 +1,20 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_BREWERY_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_BREWERY_H_
|
||||
|
||||
/**
|
||||
* @file data_model/generated_brewery.h
|
||||
* @brief Helper struct to store generated brewery data.
|
||||
*/
|
||||
|
||||
#include "data_model/brewery_result.h"
|
||||
#include "data_model/location.h"
|
||||
|
||||
/**
|
||||
* @brief Helper struct to store generated brewery data.
|
||||
*/
|
||||
struct GeneratedBrewery {
|
||||
Location location;
|
||||
BreweryResult brewery;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_BREWERY_H_
|
||||
13
pipeline/includes/data_model/generation_models.h
Normal file
13
pipeline/includes/data_model/generation_models.h
Normal file
@@ -0,0 +1,13 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATION_MODELS_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATION_MODELS_H_
|
||||
|
||||
/**
|
||||
* @file data_model/generation_models.h
|
||||
* @brief Convenience include for shared generation payload models.
|
||||
*/
|
||||
|
||||
#include "data_model/brewery_location.h"
|
||||
#include "data_model/brewery_result.h"
|
||||
#include "data_model/user_result.h"
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATION_MODELS_H_
|
||||
41
pipeline/includes/data_model/location.h
Normal file
41
pipeline/includes/data_model/location.h
Normal file
@@ -0,0 +1,41 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_LOCATION_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_LOCATION_H_
|
||||
|
||||
/**
|
||||
* @file data_model/location.h
|
||||
* @brief Location data model used throughout generation pipeline.
|
||||
*/
|
||||
|
||||
#include <string>
|
||||
#include <vector>
|
||||
|
||||
/**
|
||||
* @brief Canonical location record for city-level generation.
|
||||
*/
|
||||
struct Location {
|
||||
/// @brief City name.
|
||||
std::string city{};
|
||||
|
||||
/// @brief State or province name.
|
||||
std::string state_province{};
|
||||
|
||||
/// @brief ISO 3166-2 subdivision code.
|
||||
std::string iso3166_2{};
|
||||
|
||||
/// @brief Country name.
|
||||
std::string country{};
|
||||
|
||||
/// @brief ISO 3166-1 country code.
|
||||
std::string iso3166_1{};
|
||||
|
||||
/// @brief Local language codes in priority order.
|
||||
std::vector<std::string> local_languages{};
|
||||
|
||||
/// @brief Latitude in decimal degrees.
|
||||
double latitude{};
|
||||
|
||||
/// @brief Longitude in decimal degrees.
|
||||
double longitude{};
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_LOCATION_H_
|
||||
12
pipeline/includes/data_model/pipeline_models.h
Normal file
12
pipeline/includes/data_model/pipeline_models.h
Normal file
@@ -0,0 +1,12 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_PIPELINE_MODELS_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_PIPELINE_MODELS_H_
|
||||
|
||||
/**
|
||||
* @file data_model/pipeline_models.h
|
||||
* @brief Convenience include for pipeline-specific data models.
|
||||
*/
|
||||
|
||||
#include "data_model/enriched_city.h"
|
||||
#include "data_model/generated_brewery.h"
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_PIPELINE_MODELS_H_
|
||||
22
pipeline/includes/data_model/user_result.h
Normal file
22
pipeline/includes/data_model/user_result.h
Normal file
@@ -0,0 +1,22 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_USER_RESULT_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_USER_RESULT_H_
|
||||
|
||||
/**
|
||||
* @file data_model/user_result.h
|
||||
* @brief Generated user profile payload.
|
||||
*/
|
||||
|
||||
#include <string>
|
||||
|
||||
/**
|
||||
* @brief Generated user profile payload.
|
||||
*/
|
||||
struct UserResult {
|
||||
/// @brief Username handle.
|
||||
std::string username{};
|
||||
|
||||
/// @brief Short user biography.
|
||||
std::string bio{};
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_USER_RESULT_H_
|
||||
22
pipeline/includes/json_handling/json_loader.h
Normal file
22
pipeline/includes/json_handling/json_loader.h
Normal file
@@ -0,0 +1,22 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_JSON_LOADER_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_JSON_LOADER_H_
|
||||
|
||||
/**
|
||||
* @file json_handling/json_loader.h
|
||||
* @brief Loader API for curated location data.
|
||||
*/
|
||||
|
||||
#include <filesystem>
|
||||
#include <vector>
|
||||
|
||||
#include "data_model/location.h"
|
||||
|
||||
/// @brief Loads curated world locations from a JSON file into memory.
|
||||
class JsonLoader {
|
||||
public:
|
||||
/// @brief Parses a JSON array file and returns all location records.
|
||||
static std::vector<Location> LoadLocations(
|
||||
const std::filesystem::path& filepath);
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_JSON_LOADER_H_
|
||||
@@ -16,10 +16,16 @@
|
||||
*/
|
||||
class LlamaBackendState {
|
||||
public:
|
||||
/// @brief Initializes global llama backend state.
|
||||
LlamaBackendState() { llama_backend_init(); }
|
||||
|
||||
/// @brief Cleans up global llama backend state.
|
||||
~LlamaBackendState() { llama_backend_free(); }
|
||||
|
||||
/// @brief Non-copyable type.
|
||||
LlamaBackendState(const LlamaBackendState&) = delete;
|
||||
|
||||
/// @brief Non-copyable type.
|
||||
LlamaBackendState& operator=(const LlamaBackendState&) = delete;
|
||||
};
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_DATE_TIME_PROVIDER_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_DATE_TIME_PROVIDER_H_
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATE_TIME_PROVIDER_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATE_TIME_PROVIDER_H_
|
||||
|
||||
/**
|
||||
* @file services/date_time_provider.h
|
||||
@@ -18,6 +18,7 @@
|
||||
*/
|
||||
class IDateTimeProvider {
|
||||
public:
|
||||
/// @brief Virtual destructor for polymorphic cleanup.
|
||||
virtual ~IDateTimeProvider() = default;
|
||||
|
||||
IDateTimeProvider() = default;
|
||||
@@ -62,4 +63,4 @@ class SystemDateTimeProvider final : public IDateTimeProvider {
|
||||
}
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_DATE_TIME_PROVIDER_H_
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATE_TIME_PROVIDER_H_
|
||||
@@ -1,5 +1,5 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_ENRICHMENT_SERVICE_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_ENRICHMENT_SERVICE_H_
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_SERVICE_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_SERVICE_H_
|
||||
|
||||
/**
|
||||
* @file services/enrichment_service.h
|
||||
@@ -8,13 +8,14 @@
|
||||
|
||||
#include <string>
|
||||
|
||||
#include "data_model/models.h"
|
||||
#include "data_model/location.h"
|
||||
|
||||
/**
|
||||
* @brief Interface for services that can enrich a location with context.
|
||||
*/
|
||||
class IEnrichmentService {
|
||||
public:
|
||||
/// @brief Virtual destructor for polymorphic cleanup.
|
||||
virtual ~IEnrichmentService() = default;
|
||||
|
||||
/**
|
||||
@@ -26,4 +27,4 @@ class IEnrichmentService {
|
||||
virtual std::string GetLocationContext(const Location& loc) = 0;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_ENRICHMENT_SERVICE_H_
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_SERVICE_H_
|
||||
@@ -1,14 +1,12 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_EXPORT_SERVICE_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_EXPORT_SERVICE_H_
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_EXPORT_SERVICE_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_EXPORT_SERVICE_H_
|
||||
|
||||
/**
|
||||
* @file services/export_service.h
|
||||
* @brief Abstraction for persisting generated brewery data.
|
||||
*/
|
||||
|
||||
#include <cstdint>
|
||||
|
||||
#include "data_model/generated_models.h"
|
||||
#include "data_model/generated_brewery.h"
|
||||
|
||||
/**
|
||||
* @brief Interface for services that persist generated brewery records.
|
||||
@@ -16,6 +14,8 @@
|
||||
class IExportService {
|
||||
public:
|
||||
IExportService() = default;
|
||||
|
||||
/// @brief Virtual destructor for polymorphic cleanup.
|
||||
virtual ~IExportService() = default;
|
||||
|
||||
IExportService(const IExportService&) = delete;
|
||||
@@ -23,9 +23,7 @@ class IExportService {
|
||||
IExportService(IExportService&&) = delete;
|
||||
IExportService& operator=(IExportService&&) = delete;
|
||||
|
||||
/**
|
||||
* @brief Prepares the export destination for a new run.
|
||||
*/
|
||||
/// @brief Prepares the export destination for a new run.
|
||||
virtual void Initialize() = 0;
|
||||
|
||||
/**
|
||||
@@ -33,19 +31,10 @@ class IExportService {
|
||||
*
|
||||
* @param brewery Generated brewery payload to store.
|
||||
*/
|
||||
virtual uint64_t ProcessRecord(const BreweryRecord& brewery) = 0;
|
||||
virtual void ProcessRecord(const GeneratedBrewery& brewery) = 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.
|
||||
*/
|
||||
/// @brief Finalizes the export destination.
|
||||
virtual void Finalize() = 0;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_EXPORT_SERVICE_H_
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_EXPORT_SERVICE_H_
|
||||
@@ -1,5 +1,5 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_H_
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_H_
|
||||
|
||||
/**
|
||||
* @file services/sqlite_export_service.h
|
||||
@@ -11,17 +11,16 @@
|
||||
#include <string>
|
||||
#include <unordered_map>
|
||||
|
||||
#include "data_model/models.h"
|
||||
#include "services/database/export_service.h"
|
||||
#include "services/database/sqlite_export_service_helpers.h"
|
||||
#include "services/datetime/date_time_provider.h"
|
||||
#include "services/date_time_provider.h"
|
||||
#include "services/export_service.h"
|
||||
#include "services/sqlite_export_service_helpers.h"
|
||||
|
||||
/**
|
||||
* @brief Persists generated brewery records into a fresh SQLite database.
|
||||
*/
|
||||
class SqliteExportService final : public IExportService {
|
||||
public:
|
||||
explicit SqliteExportService(const ApplicationOptions& options);
|
||||
SqliteExportService();
|
||||
~SqliteExportService() override;
|
||||
|
||||
SqliteExportService(const SqliteExportService&) = delete;
|
||||
@@ -30,8 +29,7 @@ class SqliteExportService final : public IExportService {
|
||||
SqliteExportService& operator=(SqliteExportService&&) = delete;
|
||||
|
||||
void Initialize() override;
|
||||
uint64_t ProcessRecord(const BreweryRecord& brewery) override;
|
||||
uint64_t ProcessRecord(const UserRecord& user) override;
|
||||
void ProcessRecord(const GeneratedBrewery& brewery) override;
|
||||
void Finalize() override;
|
||||
|
||||
private:
|
||||
@@ -40,32 +38,22 @@ class SqliteExportService final : public IExportService {
|
||||
using SqliteStatementHandle =
|
||||
sqlite_export_service_internal::SqliteStatementHandle;
|
||||
|
||||
void InitializeSchema() const;
|
||||
void InitializeSchema();
|
||||
void PrepareStatements();
|
||||
void RollbackAndCloseNoThrow() noexcept;
|
||||
void FinalizeStatements() noexcept;
|
||||
|
||||
[[nodiscard]] std::filesystem::path BuildDatabasePath() const;
|
||||
[[nodiscard]] static std::string BuildLocationKey(const Location& location);
|
||||
|
||||
/**
|
||||
* @brief Returns the row id for @p location, inserting it first if it has
|
||||
* not already been seen during this run.
|
||||
*
|
||||
* 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);
|
||||
|
||||
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_brewery_stmt_;
|
||||
SqliteStatementHandle insert_user_stmt_;
|
||||
bool transaction_open_ = false;
|
||||
std::unordered_map<std::string, sqlite3_int64> location_cache_;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_H_
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_H_
|
||||
250
pipeline/includes/services/sqlite_export_service_helpers.h
Normal file
250
pipeline/includes/services/sqlite_export_service_helpers.h
Normal file
@@ -0,0 +1,250 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_HELPERS_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_HELPERS_H_
|
||||
|
||||
/**
|
||||
* @file services/sqlite_export_service_helpers.h
|
||||
* @brief Internal SQLite export helpers shared across per-method translation
|
||||
* units.
|
||||
*/
|
||||
|
||||
#include <sqlite3.h>
|
||||
|
||||
#include <boost/json.hpp>
|
||||
#include <cstddef>
|
||||
#include <cstring>
|
||||
#include <filesystem>
|
||||
#include <limits>
|
||||
#include <memory>
|
||||
#include <stdexcept>
|
||||
#include <string>
|
||||
#include <string_view>
|
||||
#include <vector>
|
||||
|
||||
namespace sqlite_export_service_internal {
|
||||
|
||||
struct SqliteDatabaseDeleter {
|
||||
void operator()(sqlite3* handle) const noexcept {
|
||||
if (handle != nullptr) {
|
||||
sqlite3_close(handle);
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
struct SqliteStatementDeleter {
|
||||
void operator()(sqlite3_stmt* statement) const noexcept {
|
||||
if (statement != nullptr) {
|
||||
sqlite3_finalize(statement);
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
using SqliteDatabaseHandle = std::unique_ptr<sqlite3, SqliteDatabaseDeleter>;
|
||||
using SqliteStatementHandle =
|
||||
std::unique_ptr<sqlite3_stmt, SqliteStatementDeleter>;
|
||||
|
||||
inline constexpr std::string_view kCreateLocationsTableSql = R"sql(
|
||||
|
||||
CREATE TABLE IF NOT EXISTS locations (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
city TEXT NOT NULL,
|
||||
state_province TEXT NOT NULL,
|
||||
iso3166_2 TEXT NOT NULL,
|
||||
country TEXT NOT NULL,
|
||||
iso3166_1 TEXT NOT NULL,
|
||||
local_languages_json TEXT NOT NULL,
|
||||
latitude REAL NOT NULL,
|
||||
longitude REAL NOT NULL,
|
||||
UNIQUE(city, state_province, iso3166_2, country, latitude, longitude)
|
||||
);
|
||||
|
||||
)sql";
|
||||
|
||||
inline constexpr std::string_view kCreateBreweriesTableSql = R"sql(
|
||||
|
||||
CREATE TABLE IF NOT EXISTS breweries (
|
||||
id INTEGER PRIMARY KEY AUTOINCREMENT,
|
||||
location_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
|
||||
);
|
||||
|
||||
CREATE INDEX IF NOT EXISTS idx_breweries_location_id ON breweries(location_id);
|
||||
|
||||
)sql";
|
||||
|
||||
inline constexpr std::string_view kInsertLocationSql = R"sql(
|
||||
INSERT INTO locations (
|
||||
city,
|
||||
state_province,
|
||||
iso3166_2,
|
||||
country,
|
||||
iso3166_1,
|
||||
local_languages_json,
|
||||
latitude,
|
||||
longitude
|
||||
) VALUES (?, ?, ?, ?, ?, ?, ?, ?);
|
||||
)sql";
|
||||
|
||||
inline constexpr std::string_view kInsertBrewerySql = R"sql(
|
||||
INSERT INTO breweries (
|
||||
location_id,
|
||||
name_en,
|
||||
description_en,
|
||||
name_local,
|
||||
description_local
|
||||
) VALUES (?, ?, ?, ?, ?);
|
||||
)sql";
|
||||
|
||||
inline constexpr int kLocationCityBindIndex = 1;
|
||||
inline constexpr int kLocationStateProvinceBindIndex = 2;
|
||||
inline constexpr int kLocationIso31662BindIndex = 3;
|
||||
inline constexpr int kLocationCountryBindIndex = 4;
|
||||
inline constexpr int kLocationIso31661BindIndex = 5;
|
||||
inline constexpr int kLocationLanguagesBindIndex = 6;
|
||||
inline constexpr int kLocationLatitudeBindIndex = 7;
|
||||
inline constexpr int kLocationLongitudeBindIndex = 8;
|
||||
|
||||
inline constexpr int kBreweryLocationIdBindIndex = 1;
|
||||
inline constexpr int kBreweryEnglishNameBindIndex = 2;
|
||||
inline constexpr int kBreweryEnglishDescriptionBindIndex = 3;
|
||||
inline constexpr int kBreweryLocalNameBindIndex = 4;
|
||||
inline constexpr int kBreweryLocalDescriptionBindIndex = 5;
|
||||
|
||||
inline void ThrowSqliteError(sqlite3* db_handle, std::string_view action) {
|
||||
const std::string message =
|
||||
db_handle != nullptr ? sqlite3_errmsg(db_handle) : "unknown SQLite error";
|
||||
throw std::runtime_error(std::string(action) + ": " + message);
|
||||
}
|
||||
|
||||
inline SqliteDatabaseHandle OpenDatabase(const std::filesystem::path& path) {
|
||||
sqlite3* raw_handle = nullptr;
|
||||
const std::string path_string = path.string();
|
||||
const int result = sqlite3_open(path_string.c_str(), &raw_handle);
|
||||
SqliteDatabaseHandle handle(raw_handle);
|
||||
if (result != SQLITE_OK) {
|
||||
const std::string message = raw_handle != nullptr
|
||||
? sqlite3_errmsg(raw_handle)
|
||||
: "unknown SQLite error";
|
||||
throw std::runtime_error("Failed to open SQLite export database: " +
|
||||
message);
|
||||
}
|
||||
|
||||
return handle;
|
||||
}
|
||||
|
||||
inline void ExecSql(const SqliteDatabaseHandle& db_handle, std::string_view sql,
|
||||
const char* action) {
|
||||
char* error_message = nullptr;
|
||||
const std::string sql_text(sql);
|
||||
const int result = sqlite3_exec(db_handle.get(), sql_text.c_str(), nullptr,
|
||||
nullptr, &error_message);
|
||||
if (result != SQLITE_OK) {
|
||||
const std::string message = error_message != nullptr
|
||||
? error_message
|
||||
: sqlite3_errmsg(db_handle.get());
|
||||
sqlite3_free(error_message);
|
||||
throw std::runtime_error(std::string(action) + ": " + message);
|
||||
}
|
||||
}
|
||||
|
||||
inline SqliteStatementHandle PrepareStatement(
|
||||
const SqliteDatabaseHandle& db_handle, std::string_view sql,
|
||||
const char* action) {
|
||||
sqlite3_stmt* raw_statement = nullptr;
|
||||
const std::string sql_text(sql);
|
||||
const int result = sqlite3_prepare_v2(db_handle.get(), sql_text.c_str(), -1,
|
||||
&raw_statement, nullptr);
|
||||
SqliteStatementHandle statement(raw_statement);
|
||||
if (result != SQLITE_OK) {
|
||||
ThrowSqliteError(db_handle.get(), action);
|
||||
}
|
||||
|
||||
return statement;
|
||||
}
|
||||
|
||||
inline void ResetStatement(SqliteStatementHandle& statement) {
|
||||
if (statement != nullptr) {
|
||||
sqlite3_reset(statement.get());
|
||||
sqlite3_clear_bindings(statement.get());
|
||||
}
|
||||
}
|
||||
|
||||
inline void DeleteCharArray(void* data) noexcept {
|
||||
delete[] static_cast<char*>(data);
|
||||
}
|
||||
|
||||
inline void BindText(const SqliteStatementHandle& statement, int index,
|
||||
std::string_view value, const char* action) {
|
||||
const auto byte_count = value.size();
|
||||
if (byte_count > static_cast<std::size_t>(std::numeric_limits<int>::max())) {
|
||||
ThrowSqliteError(sqlite3_db_handle(statement.get()), action);
|
||||
}
|
||||
|
||||
auto buffer = std::make_unique<char[]>(byte_count + 1);
|
||||
std::memcpy(buffer.get(), value.data(), byte_count);
|
||||
buffer[byte_count] = '\0';
|
||||
|
||||
char* raw_buffer = buffer.release();
|
||||
const int result =
|
||||
sqlite3_bind_text(statement.get(), index, raw_buffer,
|
||||
static_cast<int>(byte_count), DeleteCharArray);
|
||||
if (result != SQLITE_OK) {
|
||||
DeleteCharArray(raw_buffer);
|
||||
ThrowSqliteError(sqlite3_db_handle(statement.get()), action);
|
||||
}
|
||||
}
|
||||
|
||||
inline void BindDouble(const SqliteStatementHandle& statement, int index,
|
||||
double value, std::string_view action) {
|
||||
const int result = sqlite3_bind_double(statement.get(), index, value);
|
||||
if (result != SQLITE_OK) {
|
||||
ThrowSqliteError(sqlite3_db_handle(statement.get()), action);
|
||||
}
|
||||
}
|
||||
|
||||
inline void BindInt64(const SqliteStatementHandle& statement, int index,
|
||||
sqlite3_int64 value, std::string_view action) {
|
||||
const int result = sqlite3_bind_int64(statement.get(), index, value);
|
||||
if (result != SQLITE_OK) {
|
||||
ThrowSqliteError(sqlite3_db_handle(statement.get()), action);
|
||||
}
|
||||
}
|
||||
|
||||
inline void StepStatement(const SqliteDatabaseHandle& db_handle,
|
||||
const SqliteStatementHandle& statement,
|
||||
std::string_view action) {
|
||||
const int result = sqlite3_step(statement.get());
|
||||
if (result != SQLITE_DONE) {
|
||||
ThrowSqliteError(db_handle.get(), action);
|
||||
}
|
||||
}
|
||||
|
||||
inline sqlite3_int64 LastInsertRowId(const SqliteDatabaseHandle& db_handle) {
|
||||
return sqlite3_last_insert_rowid(db_handle.get());
|
||||
}
|
||||
|
||||
inline void RollbackTransactionNoThrow(
|
||||
const SqliteDatabaseHandle& db_handle) noexcept {
|
||||
if (!db_handle) {
|
||||
return;
|
||||
}
|
||||
|
||||
sqlite3_exec(db_handle.get(), "ROLLBACK;", nullptr, nullptr, nullptr);
|
||||
}
|
||||
|
||||
inline std::string SerializeLocalLanguages(
|
||||
const std::vector<std::string>& local_languages) {
|
||||
boost::json::array array;
|
||||
array.reserve(local_languages.size());
|
||||
for (const auto& language : local_languages) {
|
||||
array.emplace_back(language);
|
||||
}
|
||||
return boost::json::serialize(array);
|
||||
}
|
||||
|
||||
} // namespace sqlite_export_service_internal
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_SQLITE_EXPORT_SERVICE_HELPERS_H_
|
||||
33
pipeline/includes/services/wikipedia_service.h
Normal file
33
pipeline/includes/services/wikipedia_service.h
Normal file
@@ -0,0 +1,33 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_WIKIPEDIA_SERVICE_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_WIKIPEDIA_SERVICE_H_
|
||||
|
||||
/**
|
||||
* @file services/wikipedia_service.h
|
||||
* @brief Wikipedia summary retrieval service with in-memory caching.
|
||||
*/
|
||||
|
||||
#include <memory>
|
||||
#include <string>
|
||||
#include <string_view>
|
||||
#include <unordered_map>
|
||||
|
||||
#include "services/enrichment_service.h"
|
||||
#include "web_client/web_client.h"
|
||||
|
||||
/// @brief Provides Wikipedia summary lookups backed by cached raw extracts.
|
||||
class WikipediaService final : public IEnrichmentService {
|
||||
public:
|
||||
/// @brief Creates a new Wikipedia service with the provided web client.
|
||||
explicit WikipediaService(std::unique_ptr<WebClient> client);
|
||||
|
||||
/// @brief Returns the Wikipedia-derived context for a location.
|
||||
[[nodiscard]] std::string GetLocationContext(const Location& loc) override;
|
||||
|
||||
private:
|
||||
std::string FetchExtract(std::string_view query);
|
||||
std::unique_ptr<WebClient> client_;
|
||||
/// @brief Canonical cache for raw Wikipedia query extracts.
|
||||
std::unordered_map<std::string, std::string> extract_cache_;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_WIKIPEDIA_SERVICE_H_
|
||||
54
pipeline/includes/web_client/curl_web_client.h
Normal file
54
pipeline/includes/web_client/curl_web_client.h
Normal file
@@ -0,0 +1,54 @@
|
||||
#ifndef BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_CURL_WEB_CLIENT_H_
|
||||
#define BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_CURL_WEB_CLIENT_H_
|
||||
|
||||
/**
|
||||
* @file web_client/curl_web_client.h
|
||||
* @brief libcurl-based WebClient implementation.
|
||||
*/
|
||||
|
||||
#include "web_client/web_client.h"
|
||||
|
||||
/**
|
||||
* @brief RAII wrapper for curl_global_init and curl_global_cleanup.
|
||||
*
|
||||
* Create one instance in application startup before using libcurl and keep it
|
||||
* alive for application lifetime.
|
||||
*/
|
||||
class CurlGlobalState {
|
||||
public:
|
||||
/// @brief Initializes global libcurl state.
|
||||
CurlGlobalState();
|
||||
|
||||
/// @brief Cleans up global libcurl state.
|
||||
~CurlGlobalState();
|
||||
|
||||
/// @brief Non-copyable type.
|
||||
CurlGlobalState(const CurlGlobalState&) = delete;
|
||||
|
||||
/// @brief Non-copyable type.
|
||||
CurlGlobalState& operator=(const CurlGlobalState&) = delete;
|
||||
};
|
||||
|
||||
/**
|
||||
* @brief WebClient implementation backed by libcurl.
|
||||
*/
|
||||
class CURLWebClient : public WebClient {
|
||||
public:
|
||||
/**
|
||||
* @brief Executes an HTTP GET request.
|
||||
*
|
||||
* @param url Request URL.
|
||||
* @return Response body.
|
||||
*/
|
||||
std::string Get(const std::string& url) override;
|
||||
|
||||
/**
|
||||
* @brief URL-encodes a string value.
|
||||
*
|
||||
* @param value Raw value.
|
||||
* @return URL-encoded string.
|
||||
*/
|
||||
std::string UrlEncode(const std::string& value) override;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_CURL_WEB_CLIENT_H_
|
||||
@@ -13,6 +13,7 @@
|
||||
*/
|
||||
class WebClient {
|
||||
public:
|
||||
/// @brief Virtual destructor for polymorphic cleanup.
|
||||
virtual ~WebClient() = default;
|
||||
|
||||
/**
|
||||
@@ -29,7 +30,7 @@ class WebClient {
|
||||
* @param value Raw string value.
|
||||
* @return Encoded value safe for URL usage.
|
||||
*/
|
||||
virtual std::string EncodeURL(const std::string& value) = 0;
|
||||
virtual std::string UrlEncode(const std::string& value) = 0;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_WEB_CLIENT_H_
|
||||
113
pipeline/prompts/system.md
Normal file
113
pipeline/prompts/system.md
Normal file
@@ -0,0 +1,113 @@
|
||||
# FULL SYSTEM PROMPT
|
||||
|
||||
You are an expert brewery copywriter, an architectural observer, and a master of zymurgy.
|
||||
|
||||
Your main goal is to come up with a fake, contextually accurate name and a matching description for a craft brewery located in a specific city. You need to base this on the exact geographic and cultural info provided. You also need to seamlessly blend historical background, cultural details, and highly specialized brewing methods to create a realistic and interesting story.
|
||||
|
||||
You will receive the inputs like this:
|
||||
|
||||
## CITY:
|
||||
|
||||
[City Name]
|
||||
|
||||
## COUNTRY:
|
||||
|
||||
[Country Name]
|
||||
|
||||
## LOCAL LANGUAGE CODES:
|
||||
|
||||
[Local language codes in priority order]
|
||||
|
||||
## CONTEXT:
|
||||
|
||||
[Information about local beer culture, history, geography, or language context]
|
||||
|
||||
## CRITICAL OUTPUT FORMAT (READ CAREFULLY):
|
||||
|
||||
ABSOLUTELY NO MARKDOWN FORMATTING. Do NOT wrap your response in json or ``` blocks.
|
||||
|
||||
Do not add markdown, code fences, or postscript around the final JSON object. Do not say "Here is the JSON" or "Enjoy!".
|
||||
|
||||
The JSON must contain exactly four keys ("name_en", "description_en", "name_local", "description_local") in that order. Do not rename or add any other keys.
|
||||
|
||||
ESCAPE ALL QUOTES inside all description fields using \", or use single quotes (' ') instead. This applies equally to description_en and description_local. If the local language uses non-standard quotation marks (such as guillemets or corner brackets), write them as literal Unicode characters rather than escaped HTML entities, and do not nest them inside double quotes without escaping.
|
||||
|
||||
DO NOT use actual line breaks (\n) inside any string. Keep all descriptions as one continuous string each.
|
||||
|
||||
The description_en and description_local must each be between 225 and 300 words. Do not pad with repetition or summary, every sentence must earn its place. Be concise and specific.
|
||||
|
||||
Expected JSON format:
|
||||
|
||||
```json
|
||||
{
|
||||
"name_en": "Fictional Local Brewery Name in English",
|
||||
"description_en": "The English description goes here.",
|
||||
"name_local": "Translated brewery name in the local language",
|
||||
"description_local": "The localised description goes here."
|
||||
}
|
||||
```
|
||||
|
||||
## CONTENT RULES AND CONSTRAINTS:
|
||||
|
||||
### THE HOOK:
|
||||
|
||||
The first sentence must be a sensory environmental hook written as a personal observation, something the owner notices or has always noticed. It should establish the local weather, smell, or soundscape of the city. Do not open with the brewery's name or a generic welcome.
|
||||
|
||||
### GEOGRAPHIC & CULTURAL ANCHOR:
|
||||
|
||||
The story must be deeply tied to the provided geographic and cultural info. Weave in one or two specific historical or cultural details that ground the brewery in its place, enough to feel local, not so much that it reads like a history lesson.
|
||||
|
||||
### TECHNICAL BREWING DETAIL (VARY THIS!):
|
||||
|
||||
You must include one highly specialized technical brewing detail. To avoid sounding repetitive, make sure this varies a lot. Some examples: using local wild yeast (like spontaneous Brettanomyces), adjusting the water profile (like Burtonization), specific mashing techniques, or using local barrels for aging. Don't use basic concepts like generic mash temperatures.
|
||||
|
||||
### ARCHITECTURAL DETAIL (VARY THIS!):
|
||||
|
||||
You must include one specific architectural or environmental detail, highlighting the building's physical wear, structure, or history. The owner should describe it with personal familiarity, something they've lived with long enough to stop noticing, then started noticing again. Avoid overused industry clichés like repurposed dairy equipment or glycol chillers.
|
||||
|
||||
### THE INVITATION:
|
||||
|
||||
The last sentence must be a personal, low-key invitation from the owner, specific about place, not generic about the experience. The owner should point somewhere concrete rather than issuing a formal welcome. Avoid clichés like "come find us," "stop by anytime," "grab a stool," or "ask the bartender."
|
||||
|
||||
### LOCAL LANGUAGE VERSION:
|
||||
|
||||
name_local is a direct translation of name_en into the local language or script.
|
||||
Use the supplied local language codes to choose the language or script, and do not invent a language that is not listed.
|
||||
|
||||
description_local carries the same content and structure as description_en but should read as though written by an owner who assumes their reader shares the local cultural context, references that needed explaining in English can be stated plainly, and phrasing should reflect natural idiom in that language rather than translated English sentence structure.
|
||||
|
||||
The length and anti-AI-pattern requirements apply equally to description_local.
|
||||
|
||||
The register of description_local should match the local variant of the language appropriate to the city, québécois French for Montréal, Belgian French for Brussels, castilian Spanish for Madrid, rioplatense Spanish for Buenos Aires, and so on.
|
||||
|
||||
### THE BLOCKLIST (FORBIDDEN CONCEPTS):
|
||||
|
||||
You absolutely cannot use the following words and phrases. Make sure your final output doesn't have any of these:
|
||||
|
||||
- "hidden gem"
|
||||
- "passion"
|
||||
- "authentic"
|
||||
- "repurposed dairy tank"
|
||||
- "repurposed industrial vat"
|
||||
- "concrete eggs"
|
||||
- "glycol chiller"
|
||||
- "mash temperature"
|
||||
- "grab a stool"
|
||||
- "ask the bartender"
|
||||
- "come find us"
|
||||
- "stop by anytime"
|
||||
|
||||
#### FORBIDDEN WRITING PATTERNS
|
||||
|
||||
The following patterns are common AI writing pitfalls and must not appear in either description:
|
||||
|
||||
- Negative parallelism constructions: "It's not X, it's Y" or "We're not about X, we're about Y"
|
||||
- Inflated significance phrases: "stands as a testament," "plays a vital role," "leaves a lasting impact," "watershed moment," "deeply rooted," "rich cultural heritage," "rich cultural tapestry," "enduring legacy"
|
||||
- Superficial trailing analyses: sentences ending in -ing words that add opinion without content ("ensuring consistency," "reflecting the city's spirit," "highlighting our commitment")
|
||||
- Promotional travel-copy tone: "breathtaking," "must-visit," "stunning," "vibrant"
|
||||
- Overused conjunctive transitions used as sentence openers: "Moreover," "Furthermore," "In addition," "In contrast"
|
||||
- Rule of three: do not consistently organise ideas or examples in triplets
|
||||
|
||||
### VOICE & PERSPECTIVE:
|
||||
|
||||
The description must be written in the first person, from the perspective of the brewery's owner. Favour "we" and "our" over "I" and "my." The owner may use "I" sparingly for personal observations that only they could make, but the default register should be collective. The tone should feel lived-in and a little weathered. Do not use third-person or second-person pronouns.
|
||||
@@ -0,0 +1,16 @@
|
||||
/**
|
||||
* @file biergarten_data_generator/biergarten_data_generator.cc
|
||||
* @brief BiergartenDataGenerator constructor implementation.
|
||||
*/
|
||||
|
||||
#include "biergarten_data_generator.h"
|
||||
|
||||
#include <utility>
|
||||
|
||||
BiergartenDataGenerator::BiergartenDataGenerator(
|
||||
std::unique_ptr<IEnrichmentService> context_service,
|
||||
std::unique_ptr<DataGenerator> generator,
|
||||
std::unique_ptr<IExportService> exporter)
|
||||
: context_service_(std::move(context_service)),
|
||||
generator_(std::move(generator)),
|
||||
exporter_(std::move(exporter)) {}
|
||||
58
pipeline/src/biergarten_data_generator/generate_breweries.cc
Normal file
58
pipeline/src/biergarten_data_generator/generate_breweries.cc
Normal file
@@ -0,0 +1,58 @@
|
||||
/**
|
||||
* @file biergarten_data_generator/generate_breweries.cc
|
||||
* @brief BiergartenDataGenerator::GenerateBreweries() implementation.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include "biergarten_data_generator.h"
|
||||
|
||||
void BiergartenDataGenerator::GenerateBreweries(
|
||||
std::span<const EnrichedCity> cities) {
|
||||
spdlog::info("\n=== SAMPLE BREWERY GENERATION ===");
|
||||
|
||||
generated_breweries_.clear();
|
||||
size_t skipped_count = 0;
|
||||
size_t export_failed_count = 0;
|
||||
|
||||
for (const auto& [location, region_context] : cities) {
|
||||
try {
|
||||
const BreweryResult brewery =
|
||||
generator_->GenerateBrewery(location, region_context);
|
||||
|
||||
const GeneratedBrewery gen{.location = location, .brewery = brewery};
|
||||
|
||||
generated_breweries_.push_back(gen);
|
||||
|
||||
try {
|
||||
exporter_->ProcessRecord(gen);
|
||||
} catch (const std::exception& export_exception) {
|
||||
++export_failed_count;
|
||||
|
||||
spdlog::warn(
|
||||
"[Pipeline] Generated brewery for '{}' ({}) but SQLite export "
|
||||
"failed: {}",
|
||||
location.city, location.country, export_exception.what());
|
||||
}
|
||||
} catch (const std::exception& e) {
|
||||
++skipped_count;
|
||||
|
||||
spdlog::warn(
|
||||
"[Pipeline] Skipping city '{}' ({}): brewery generation failed: "
|
||||
"{}",
|
||||
location.city, location.country, e.what());
|
||||
}
|
||||
}
|
||||
|
||||
if (skipped_count > 0) {
|
||||
spdlog::warn("[Pipeline] Skipped {} city/cities due to generation errors",
|
||||
skipped_count);
|
||||
}
|
||||
|
||||
if (export_failed_count > 0) {
|
||||
spdlog::warn(
|
||||
"[Pipeline] Failed to export {} generated brewery/breweries to "
|
||||
"SQLite",
|
||||
export_failed_count);
|
||||
}
|
||||
}
|
||||
26
pipeline/src/biergarten_data_generator/log_results.cc
Normal file
26
pipeline/src/biergarten_data_generator/log_results.cc
Normal file
@@ -0,0 +1,26 @@
|
||||
/**
|
||||
* @file biergarten_data_generator/log_results.cc
|
||||
* @brief BiergartenDataGenerator::LogResults() implementation.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include "biergarten_data_generator.h"
|
||||
|
||||
void BiergartenDataGenerator::LogResults() const {
|
||||
spdlog::info("\n=== GENERATED DATA DUMP ===");
|
||||
size_t index = 1;
|
||||
for (const auto& [location, brewery] : generated_breweries_) {
|
||||
spdlog::info(
|
||||
"{}. city=\"{}\" country=\"{}\" state=\"{}\" "
|
||||
"iso3166_2={} lat={} lon={}",
|
||||
index, location.city, location.country, location.state_province,
|
||||
location.iso3166_2, location.latitude, location.longitude);
|
||||
spdlog::info(" brewery_name_en=\"{}\"", brewery.name_en);
|
||||
spdlog::info(" brewery_description_en=\"{}\"", brewery.description_en);
|
||||
spdlog::info(" brewery_name_local=\"{}\"", brewery.name_local);
|
||||
spdlog::info(" brewery_description_local=\"{}\"",
|
||||
brewery.description_local);
|
||||
++index;
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,41 @@
|
||||
/**
|
||||
* @file biergarten_data_generator/query_cities_with_countries.cc
|
||||
* @brief BiergartenDataGenerator::QueryCitiesWithCountries() implementation.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <algorithm>
|
||||
#include <filesystem>
|
||||
#include <iterator>
|
||||
#include <random>
|
||||
|
||||
#include "biergarten_data_generator.h"
|
||||
#include "json_handling/json_loader.h"
|
||||
|
||||
static constexpr size_t kBreweryAmount = 50;
|
||||
|
||||
std::vector<Location> BiergartenDataGenerator::QueryCitiesWithCountries() {
|
||||
spdlog::info("\n=== GEOGRAPHIC DATA OVERVIEW ===");
|
||||
|
||||
const std::filesystem::path locations_path = "locations.json";
|
||||
|
||||
auto all_locations = JsonLoader::LoadLocations(locations_path);
|
||||
spdlog::info(" Locations available: {}", all_locations.size());
|
||||
|
||||
const size_t sample_count = std::min(kBreweryAmount, all_locations.size());
|
||||
|
||||
const auto sample_count_signed =
|
||||
static_cast<std::iter_difference_t<decltype(all_locations.cbegin())>>(
|
||||
sample_count);
|
||||
|
||||
std::vector<Location> sampled_locations;
|
||||
sampled_locations.reserve(sample_count);
|
||||
|
||||
std::random_device random_generator;
|
||||
std::ranges::sample(all_locations, std::back_inserter(sampled_locations),
|
||||
sample_count_signed, random_generator);
|
||||
|
||||
spdlog::info(" Sampled locations: {}", sampled_locations.size());
|
||||
return sampled_locations;
|
||||
}
|
||||
52
pipeline/src/biergarten_data_generator/run.cc
Normal file
52
pipeline/src/biergarten_data_generator/run.cc
Normal file
@@ -0,0 +1,52 @@
|
||||
/**
|
||||
* @file biergarten_data_generator/run.cc
|
||||
* @brief BiergartenDataGenerator::Run() implementation.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <utility>
|
||||
|
||||
#include "biergarten_data_generator.h"
|
||||
|
||||
bool BiergartenDataGenerator::Run() {
|
||||
try {
|
||||
exporter_->Initialize();
|
||||
|
||||
std::vector<Location> cities = QueryCitiesWithCountries();
|
||||
std::vector<EnrichedCity> enriched;
|
||||
enriched.reserve(cities.size());
|
||||
|
||||
size_t skipped_count = 0;
|
||||
for (auto& city : cities) {
|
||||
try {
|
||||
std::string region_context = context_service_->GetLocationContext(city);
|
||||
spdlog::debug("[Pipeline] Context for '{}' ({}) gathered:\n{}",
|
||||
city.city, city.country, region_context);
|
||||
|
||||
enriched.push_back(
|
||||
EnrichedCity{.location = std::move(city),
|
||||
.region_context = std::move(region_context)});
|
||||
} catch (const std::exception& exception) {
|
||||
++skipped_count;
|
||||
spdlog::warn(
|
||||
"[Pipeline] Skipping city '{}' ({}): context lookup failed: {}",
|
||||
city.city, city.country, exception.what());
|
||||
}
|
||||
}
|
||||
|
||||
if (skipped_count > 0) {
|
||||
spdlog::warn(
|
||||
"[Pipeline] Skipped {} city/cities due to context lookup errors",
|
||||
skipped_count);
|
||||
}
|
||||
|
||||
this->GenerateBreweries(enriched);
|
||||
exporter_->Finalize();
|
||||
this->LogResults();
|
||||
return true;
|
||||
} catch (const std::exception& e) {
|
||||
spdlog::error("Pipeline execution failed with error: {}", e.what());
|
||||
return false;
|
||||
}
|
||||
}
|
||||
@@ -4,7 +4,8 @@
|
||||
* inference, and validates structured JSON output for brewery records.
|
||||
*/
|
||||
|
||||
#include <chrono>
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <format>
|
||||
#include <optional>
|
||||
#include <stdexcept>
|
||||
@@ -12,7 +13,6 @@
|
||||
#include <string_view>
|
||||
#include <vector>
|
||||
|
||||
#include "data_generation/json_grammars.h"
|
||||
#include "data_generation/llama_generator.h"
|
||||
#include "data_generation/llama_generator_helpers.h"
|
||||
|
||||
@@ -33,6 +33,16 @@ static std::string FormatLocalLanguageCodes(
|
||||
return formatted;
|
||||
}
|
||||
|
||||
static constexpr std::string_view kBreweryJsonGrammar = R"json_brewery(
|
||||
root ::= thought-block "{" ws "\"name_en\"" ws ":" ws string ws "," ws "\"description_en\"" ws ":" ws string ws "," ws "\"name_local\"" ws ":" ws string ws "," ws "\"description_local\"" ws ":" ws string ws "}" ws
|
||||
thought-block ::= [^{]*
|
||||
ws ::= [ \t\n\r]*
|
||||
string ::= "\"" char+ "\""
|
||||
char ::= [^"\\\x7F\x00-\x1F] | [\\] escape
|
||||
escape ::= ["\\/bfnrt] | "u" hex hex hex hex
|
||||
hex ::= [0-9a-fA-F]
|
||||
)json_brewery";
|
||||
|
||||
static constexpr int kBreweryInitialMaxTokens = 2800;
|
||||
|
||||
BreweryResult LlamaGenerator::GenerateBrewery(
|
||||
@@ -49,12 +59,11 @@ BreweryResult LlamaGenerator::GenerateBrewery(
|
||||
location.country.empty() ? std::string{}
|
||||
: std::format(", {}", location.country);
|
||||
/**
|
||||
* Load brewery system prompt via the injected prompt directory.
|
||||
* The key "BREWERY_GENERATION" resolves to BREWERY_GENERATION.md inside
|
||||
* the configured --prompt-dir. Throws on missing or empty file.
|
||||
* Load brewery system prompt from file
|
||||
* Falls back to minimal inline prompt if file not found
|
||||
*/
|
||||
const std::string system_prompt =
|
||||
prompt_directory_->Load("BREWERY_GENERATION");
|
||||
LoadBrewerySystemPrompt("prompts/system.md");
|
||||
|
||||
std::string user_prompt = std::format(
|
||||
"## CITY:\n{}\n\n## COUNTRY:\n{}\n\n## LOCAL LANGUAGE CODES:\n{}\n\n## "
|
||||
@@ -71,14 +80,15 @@ BreweryResult LlamaGenerator::GenerateBrewery(
|
||||
|
||||
/**
|
||||
* RETRY LOOP with validation and error correction
|
||||
* Attempts to generate valid brewery data up to 3 times, with
|
||||
* feedback-based refinement
|
||||
* Attempts to generate valid brewery data up to 3 times, with feedback-based
|
||||
* refinement
|
||||
*/
|
||||
constexpr int max_attempts = 3;
|
||||
std::string raw;
|
||||
std::string last_error;
|
||||
|
||||
// Token budget: too small risks truncating valid JSON mid-string.
|
||||
// Start conservatively but allow adaptive increases on truncation.
|
||||
int max_tokens = kBreweryInitialMaxTokens;
|
||||
|
||||
// Limit output length to keep it concise and focused
|
||||
@@ -86,13 +96,8 @@ BreweryResult LlamaGenerator::GenerateBrewery(
|
||||
// Generate brewery data from LLM
|
||||
raw = this->Infer(system_prompt, user_prompt, max_tokens,
|
||||
kBreweryJsonGrammar);
|
||||
if (logger_) {
|
||||
logger_->Log(
|
||||
{.level = LogLevel::Debug,
|
||||
.phase = PipelinePhase::BreweryAndBeerGeneration,
|
||||
.message = std::format("LlamaGenerator: raw output (attempt {}): {}",
|
||||
attempt + 1, raw)});
|
||||
}
|
||||
spdlog::debug("LlamaGenerator: raw output (attempt {}): {}", attempt + 1,
|
||||
raw);
|
||||
|
||||
// Validate output: parse JSON and check required fields
|
||||
|
||||
@@ -103,14 +108,9 @@ BreweryResult LlamaGenerator::GenerateBrewery(
|
||||
if (!validation_error.has_value()) {
|
||||
// Success: return parsed brewery data
|
||||
|
||||
if (logger_) {
|
||||
logger_->Log(
|
||||
{.level = LogLevel::Info,
|
||||
.phase = PipelinePhase::BreweryAndBeerGeneration,
|
||||
.message = std::format("LlamaGenerator: successfully generated "
|
||||
"brewery data on attempt {}",
|
||||
attempt + 1)});
|
||||
}
|
||||
spdlog::info(
|
||||
"LlamaGenerator: successfully generated brewery data on attempt {}",
|
||||
attempt + 1);
|
||||
|
||||
return brewery;
|
||||
}
|
||||
@@ -118,42 +118,27 @@ BreweryResult LlamaGenerator::GenerateBrewery(
|
||||
// Validation failed: log error and prepare corrective feedback
|
||||
|
||||
last_error = *validation_error;
|
||||
if (logger_) {
|
||||
logger_->Log(
|
||||
{.level = LogLevel::Warn,
|
||||
.phase = PipelinePhase::BreweryAndBeerGeneration,
|
||||
.message = std::format(
|
||||
"LlamaGenerator: malformed brewery JSON (attempt {}): {}",
|
||||
attempt + 1, *validation_error)});
|
||||
}
|
||||
spdlog::warn("LlamaGenerator: malformed brewery JSON (attempt {}): {}",
|
||||
attempt + 1, *validation_error);
|
||||
|
||||
// Update prompt with error details to guide LLM toward correct output.
|
||||
user_prompt = std::format(
|
||||
"Your previous response was invalid. Error: {}\nReturn the thought "
|
||||
"process before the JSON if needed, then return ONLY valid JSON "
|
||||
"with "
|
||||
"exactly these keys, in this exact order: {{\"name_en\": "
|
||||
"\"<English "
|
||||
"process before the JSON if needed, then return ONLY valid JSON with "
|
||||
"exactly these keys, in this exact order: {{\"name_en\": \"<English "
|
||||
"brewery name>\", \"description_en\": \"<English single-paragraph "
|
||||
"description>\", \"name_local\": \"<local-language brewery "
|
||||
"name>\", "
|
||||
"description>\", \"name_local\": \"<local-language brewery name>\", "
|
||||
"\"description_local\": \"<local-language single-paragraph "
|
||||
"description>\"}}.\nDo not include markdown, comments, extra keys, "
|
||||
"or "
|
||||
"literal placeholder values.\n\nKeep the JSON strings concise "
|
||||
"enough "
|
||||
"description>\"}}.\nDo not include markdown, comments, extra keys, or "
|
||||
"literal placeholder values.\n\nKeep the JSON strings concise enough "
|
||||
"to fit within the token budget.\n\n{}",
|
||||
*validation_error, retry_location);
|
||||
}
|
||||
|
||||
// All retry attempts exhausted: log failure and throw exception
|
||||
if (logger_) {
|
||||
logger_->Log({.level = LogLevel::Error,
|
||||
.phase = PipelinePhase::BreweryAndBeerGeneration,
|
||||
.message = std::format(
|
||||
"LlamaGenerator: malformed brewery "
|
||||
"response after {} attempts: {}",
|
||||
max_attempts, last_error.empty() ? raw : last_error)});
|
||||
}
|
||||
spdlog::error(
|
||||
"LlamaGenerator: malformed brewery response after {} attempts: "
|
||||
"{}",
|
||||
max_attempts, last_error.empty() ? raw : last_error);
|
||||
throw std::runtime_error("LlamaGenerator: malformed brewery response");
|
||||
}
|
||||
18
pipeline/src/data_generation/llama/generate_user.cc
Normal file
18
pipeline/src/data_generation/llama/generate_user.cc
Normal file
@@ -0,0 +1,18 @@
|
||||
/**
|
||||
* @file data_generation/llama/generate_user.cc
|
||||
* @brief Generates locale-aware user profiles with strict two-line formatting,
|
||||
* retry handling, and output sanitization for downstream parsing.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <stdexcept>
|
||||
#include <string>
|
||||
|
||||
#include "data_generation/llama_generator.h"
|
||||
#include "data_generation/llama_generator_helpers.h"
|
||||
|
||||
UserResult LlamaGenerator::GenerateUser(const std::string& locale) {
|
||||
return {.username = "test_user",
|
||||
.bio = "This is a test user profile from " + locale + "."};
|
||||
}
|
||||
@@ -9,21 +9,18 @@
|
||||
#include <boost/json.hpp>
|
||||
#include <cctype>
|
||||
#include <optional>
|
||||
#include <span>
|
||||
#include <stdexcept>
|
||||
#include <string>
|
||||
#include <string_view>
|
||||
#include <vector>
|
||||
|
||||
#include <llama.h>
|
||||
|
||||
#include "data_generation/llama_generator_helpers.h"
|
||||
#include "llama.h"
|
||||
|
||||
namespace {
|
||||
/**
|
||||
* String trimming: removes leading and trailing whitespace
|
||||
*/
|
||||
std::string Trim(std::string_view value) {
|
||||
static std::string Trim(std::string_view value) {
|
||||
constexpr std::string_view whitespace = " \t\n\r\f\v";
|
||||
const size_t first_index = value.find_first_not_of(whitespace);
|
||||
if (first_index == std::string_view::npos) {
|
||||
@@ -38,7 +35,7 @@ std::string Trim(std::string_view value) {
|
||||
* Normalize whitespace: collapses multiple spaces/tabs/newlines into single
|
||||
* spaces
|
||||
*/
|
||||
std::string CondenseWhitespace(std::string_view text) {
|
||||
static std::string CondenseWhitespace(std::string_view text) {
|
||||
std::string out;
|
||||
out.reserve(text.size());
|
||||
|
||||
@@ -61,41 +58,6 @@ std::string CondenseWhitespace(std::string_view text) {
|
||||
return out;
|
||||
}
|
||||
|
||||
// Guard against truncating in the first half of the string.
|
||||
// This preserves the critical opening content and avoids cutting critical
|
||||
// context words early in the region description.
|
||||
constexpr size_t kTruncationGuardDivisor = 2;
|
||||
|
||||
bool ReadRequiredTrimmedStringField(const boost::json::object& obj,
|
||||
std::string_view key, std::string& out,
|
||||
std::string* error_out) {
|
||||
const boost::json::value* field = obj.if_contains(key);
|
||||
if (field == nullptr || !field->is_string()) {
|
||||
return false;
|
||||
}
|
||||
|
||||
const auto& string_value = field->as_string();
|
||||
out = Trim(std::string_view(string_value.data(), string_value.size()));
|
||||
return !out.empty();
|
||||
}
|
||||
|
||||
bool HasSchemaPlaceholder(std::span<std::string* const> values) {
|
||||
for (const std::string* value : values) {
|
||||
std::string lowered = *value;
|
||||
std::ranges::transform(lowered, lowered.begin(),
|
||||
[](const unsigned char character) {
|
||||
return static_cast<char>(std::tolower(character));
|
||||
});
|
||||
|
||||
if (lowered == "string") {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
} // namespace
|
||||
|
||||
/**
|
||||
* Truncate region context to fit within max length while preserving word
|
||||
* boundaries
|
||||
@@ -109,8 +71,7 @@ std::string PrepareRegionContext(std::string_view region_context,
|
||||
|
||||
normalized.resize(max_chars);
|
||||
const size_t last_space = normalized.find_last_of(' ');
|
||||
if (last_space != std::string::npos &&
|
||||
last_space > max_chars / kTruncationGuardDivisor) {
|
||||
if (last_space != std::string::npos && last_space > max_chars / 2) {
|
||||
normalized.resize(last_space);
|
||||
}
|
||||
|
||||
@@ -154,6 +115,47 @@ void AppendTokenPiece(const llama_vocab* vocab, llama_token token,
|
||||
"LlamaGenerator: failed to decode sampled token piece");
|
||||
}
|
||||
|
||||
static bool ReadRequiredTrimmedStringField(const boost::json::object& obj,
|
||||
std::string_view key,
|
||||
std::string& out,
|
||||
std::string* error_out) {
|
||||
const boost::json::value* field = obj.if_contains(key);
|
||||
if (field == nullptr || !field->is_string()) {
|
||||
if (error_out != nullptr) {
|
||||
*error_out =
|
||||
"JSON field '" + std::string(key) + "' is missing or not a string";
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
const auto& string_value = field->as_string();
|
||||
out = Trim(std::string_view(string_value.data(), string_value.size()));
|
||||
if (out.empty()) {
|
||||
if (error_out != nullptr) {
|
||||
*error_out = "JSON field '" + std::string(key) + "' must not be empty";
|
||||
}
|
||||
return false;
|
||||
}
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
static bool HasSchemaPlaceholder(const std::array<std::string*, 4>& values) {
|
||||
for (const std::string* value : values) {
|
||||
std::string lowered = *value;
|
||||
std::ranges::transform(lowered, lowered.begin(),
|
||||
[](unsigned char character) {
|
||||
return static_cast<char>(std::tolower(character));
|
||||
});
|
||||
|
||||
if (lowered == "string") {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
return false;
|
||||
}
|
||||
|
||||
std::optional<std::string> ValidateBreweryJson(const std::string& raw,
|
||||
BreweryResult& brewery_out) {
|
||||
boost::system::error_code error_code;
|
||||
@@ -201,7 +203,7 @@ std::optional<std::string> ValidateBreweryJson(const std::string& raw,
|
||||
return validation_error;
|
||||
}
|
||||
|
||||
const std::array schema_placeholders = {
|
||||
const std::array<std::string*, 4> schema_placeholders = {
|
||||
&brewery_out.name_en, &brewery_out.description_en,
|
||||
&brewery_out.name_local, &brewery_out.description_local};
|
||||
if (HasSchemaPlaceholder(schema_placeholders)) {
|
||||
@@ -210,58 +212,3 @@ std::optional<std::string> ValidateBreweryJson(const std::string& raw,
|
||||
|
||||
return std::nullopt;
|
||||
}
|
||||
|
||||
std::optional<std::string> ValidateUserJson(const std::string& raw,
|
||||
UserResult& user_out) {
|
||||
boost::system::error_code error_code;
|
||||
const std::string_view raw_view(raw);
|
||||
const size_t opening_brace = raw_view.find('{');
|
||||
if (opening_brace == std::string_view::npos) {
|
||||
return "JSON parse error: missing opening brace '{'";
|
||||
}
|
||||
|
||||
const std::string_view json_payload = raw_view.substr(opening_brace);
|
||||
boost::json::value json_value = boost::json::parse(json_payload, error_code);
|
||||
if (error_code) {
|
||||
return "JSON parse error: " + error_code.message();
|
||||
}
|
||||
|
||||
if (!json_value.is_object()) {
|
||||
return "JSON root must be an object";
|
||||
}
|
||||
|
||||
const auto& obj = json_value.get_object();
|
||||
if (obj.size() != 3) {
|
||||
return "JSON object must contain exactly three keys";
|
||||
}
|
||||
|
||||
std::string validation_error;
|
||||
if (!ReadRequiredTrimmedStringField(obj, "username", user_out.username,
|
||||
&validation_error)) {
|
||||
return validation_error;
|
||||
}
|
||||
|
||||
if (!ReadRequiredTrimmedStringField(obj, "bio", user_out.bio,
|
||||
&validation_error)) {
|
||||
return validation_error;
|
||||
}
|
||||
|
||||
const boost::json::value* activity_weight_field =
|
||||
obj.if_contains("activity_weight");
|
||||
if (activity_weight_field == nullptr || !activity_weight_field->is_number()) {
|
||||
return "Missing or invalid numeric field: activity_weight";
|
||||
}
|
||||
|
||||
const double activity_weight = activity_weight_field->to_number<double>();
|
||||
if (activity_weight < 0.0 || activity_weight > 1.0) {
|
||||
return "activity_weight must be between 0 and 1";
|
||||
}
|
||||
user_out.activity_weight = static_cast<float>(activity_weight);
|
||||
|
||||
const std::array schema_placeholders = {&user_out.username, &user_out.bio};
|
||||
if (HasSchemaPlaceholder(schema_placeholders)) {
|
||||
return "JSON appears to be a schema placeholder, not content";
|
||||
}
|
||||
|
||||
return std::nullopt;
|
||||
}
|
||||
@@ -5,24 +5,20 @@
|
||||
* output tokens back to text for system+user chat prompts.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <algorithm>
|
||||
#include <chrono>
|
||||
#include <format>
|
||||
#include <memory>
|
||||
#include <stdexcept>
|
||||
#include <string>
|
||||
#include <string_view>
|
||||
#include <vector>
|
||||
|
||||
#include <llama.h>
|
||||
|
||||
#include "data_generation/llama_generator.h"
|
||||
#include "data_generation/llama_generator_helpers.h"
|
||||
#include "llama.h"
|
||||
|
||||
static constexpr size_t kPromptTokenSlack = 8;
|
||||
// Minimum tokens to keep when using top-p sampling. Ensures at least one
|
||||
// candidate token remains available even with very restrictive top-p values.
|
||||
static constexpr size_t kTopPMinKeep = 1;
|
||||
|
||||
namespace {
|
||||
|
||||
@@ -66,7 +62,7 @@ SamplerHandle MakeSamplerChain(const llama_vocab* vocab,
|
||||
"LlamaGenerator: failed to initialize temperature sampler");
|
||||
add_sampler(llama_sampler_init_top_k(static_cast<int32_t>(config.top_k)),
|
||||
"LlamaGenerator: failed to initialize top-k sampler");
|
||||
add_sampler(llama_sampler_init_top_p(config.top_p, kTopPMinKeep),
|
||||
add_sampler(llama_sampler_init_top_p(config.top_p, 1),
|
||||
"LlamaGenerator: failed to initialize top-p sampler");
|
||||
add_sampler(llama_sampler_init_dist(config.seed),
|
||||
"LlamaGenerator: failed to initialize distribution sampler");
|
||||
@@ -108,7 +104,7 @@ std::string LlamaGenerator::InferFormatted(const std::string& formatted_prompt,
|
||||
.top_p = sampling_top_p_,
|
||||
.seed = static_cast<uint32_t>(rng_()),
|
||||
};
|
||||
const auto sampler = MakeSamplerChain(vocab, sampler_config, grammar);
|
||||
auto sampler = MakeSamplerChain(vocab, sampler_config, grammar);
|
||||
|
||||
/**
|
||||
* Clear KV cache to ensure clean inference state (no residual context)
|
||||
@@ -172,14 +168,10 @@ std::string LlamaGenerator::InferFormatted(const std::string& formatted_prompt,
|
||||
*/
|
||||
prompt_tokens.resize(static_cast<size_t>(token_count));
|
||||
if (token_count > prompt_budget) {
|
||||
if (logger_) {
|
||||
logger_->Log({.level = LogLevel::Warn,
|
||||
.phase = PipelinePhase::BreweryAndBeerGeneration,
|
||||
.message = std::format(
|
||||
"LlamaGenerator: prompt too long ({} tokens), "
|
||||
"truncating to {} tokens to fit n_batch/n_ctx limits",
|
||||
token_count, prompt_budget)});
|
||||
}
|
||||
spdlog::warn(
|
||||
"LlamaGenerator: prompt too long ({} tokens), truncating to {} "
|
||||
"tokens to fit n_batch/n_ctx limits",
|
||||
token_count, prompt_budget);
|
||||
prompt_tokens.resize(static_cast<size_t>(prompt_budget));
|
||||
token_count = prompt_budget;
|
||||
}
|
||||
@@ -11,9 +11,8 @@
|
||||
#include <stdexcept>
|
||||
#include <string>
|
||||
|
||||
#include <llama.h>
|
||||
|
||||
#include "data_model/models.h"
|
||||
#include "data_model/application_options.h"
|
||||
#include "llama.h"
|
||||
|
||||
static constexpr uint32_t kMaxContextSize = 32768U;
|
||||
|
||||
@@ -33,13 +32,9 @@ void LlamaGenerator::ContextDeleter::operator()(
|
||||
|
||||
LlamaGenerator::LlamaGenerator(
|
||||
const ApplicationOptions& options, const std::string& model_path,
|
||||
std::shared_ptr<ILogger> logger,
|
||||
std::unique_ptr<IPromptFormatter> prompt_formatter,
|
||||
std::unique_ptr<IPromptDirectory> prompt_directory)
|
||||
std::unique_ptr<IPromptFormatter> prompt_formatter)
|
||||
: rng_(std::random_device{}()),
|
||||
logger_(std::move(logger)),
|
||||
prompt_formatter_(std::move(prompt_formatter)),
|
||||
prompt_directory_(std::move(prompt_directory)) {
|
||||
prompt_formatter_(std::move(prompt_formatter)) {
|
||||
if (model_path.empty()) {
|
||||
throw std::runtime_error("LlamaGenerator: model path must not be empty");
|
||||
}
|
||||
@@ -49,50 +44,41 @@ LlamaGenerator::LlamaGenerator(
|
||||
"LlamaGenerator: prompt formatter dependency must not be null");
|
||||
}
|
||||
|
||||
if (!prompt_directory_) {
|
||||
throw std::runtime_error(
|
||||
"LlamaGenerator: prompt directory dependency must not be null");
|
||||
}
|
||||
|
||||
const auto sampling = options.generator.sampling.value_or(SamplingOptions{});
|
||||
|
||||
if (sampling.temperature < 0.0F) {
|
||||
if (options.temperature < 0.0F) {
|
||||
throw std::runtime_error(
|
||||
"LlamaGenerator: sampling temperature must be >= 0");
|
||||
}
|
||||
|
||||
if (sampling.top_p <= 0.0F || sampling.top_p > 1.0F) {
|
||||
if (options.top_p <= 0.0F || options.top_p > 1.0F) {
|
||||
throw std::runtime_error(
|
||||
"LlamaGenerator: sampling top-p must be in (0, 1]");
|
||||
}
|
||||
|
||||
if (sampling.top_k == 0U) {
|
||||
if (options.top_k == 0U) {
|
||||
throw std::runtime_error("LlamaGenerator: sampling top-k must be > 0");
|
||||
}
|
||||
|
||||
if (sampling.seed < -1) {
|
||||
if (options.seed < -1) {
|
||||
throw std::runtime_error(
|
||||
"LlamaGenerator: seed must be >= 0, or -1 for random");
|
||||
}
|
||||
|
||||
if (sampling.n_ctx == 0 || sampling.n_ctx > kMaxContextSize) {
|
||||
if (options.n_ctx == 0 || options.n_ctx > kMaxContextSize) {
|
||||
throw std::runtime_error(
|
||||
"LlamaGenerator: context size must be in range [1, 32768]");
|
||||
}
|
||||
|
||||
sampling_temperature_ = sampling.temperature;
|
||||
sampling_top_p_ = sampling.top_p;
|
||||
sampling_top_k_ = sampling.top_k;
|
||||
sampling_temperature_ = options.temperature;
|
||||
sampling_top_p_ = options.top_p;
|
||||
sampling_top_k_ = options.top_k;
|
||||
|
||||
if (sampling.seed == -1) {
|
||||
if (options.seed == -1) {
|
||||
std::random_device random_device;
|
||||
rng_.seed(random_device());
|
||||
} else {
|
||||
rng_.seed(static_cast<uint32_t>(sampling.seed));
|
||||
rng_.seed(static_cast<uint32_t>(options.seed));
|
||||
}
|
||||
|
||||
n_ctx_ = sampling.n_ctx;
|
||||
n_gpu_layers_ = sampling.n_gpu_layers;
|
||||
n_ctx_ = options.n_ctx;
|
||||
|
||||
this->Load(model_path);
|
||||
}
|
||||
@@ -4,35 +4,23 @@
|
||||
* context, and resets prior resources during model initialization.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <algorithm>
|
||||
#include <chrono>
|
||||
#include <stdexcept>
|
||||
#include <string>
|
||||
#include <utility>
|
||||
|
||||
#include <ggml-backend.h>
|
||||
#include <llama.h>
|
||||
|
||||
#include "data_generation/llama_generator.h"
|
||||
|
||||
// Maximum batch size for decode operations. Capping the batch prevents
|
||||
// excessive memory allocation while maintaining inference performance.
|
||||
static constexpr uint32_t kMaxBatchSize = 5000U;
|
||||
#include "llama.h"
|
||||
|
||||
void LlamaGenerator::Load(const std::string& model_path) {
|
||||
context_.reset();
|
||||
model_.reset();
|
||||
|
||||
// Specifically load dynamic ggml backends (like CUDA) that are provided
|
||||
// externally before attempting to load a model.
|
||||
ggml_backend_load_all();
|
||||
|
||||
llama_model_params model_params = llama_model_default_params();
|
||||
model_params.n_gpu_layers = n_gpu_layers_;
|
||||
|
||||
ModelHandle loaded_model(
|
||||
const llama_model_params model_params = llama_model_default_params();
|
||||
LlamaGenerator::ModelHandle loaded_model(
|
||||
llama_model_load_from_file(model_path.c_str(), model_params));
|
||||
|
||||
if (!loaded_model) {
|
||||
throw std::runtime_error(
|
||||
"LlamaGenerator: failed to load model from path: " + model_path);
|
||||
@@ -40,11 +28,10 @@ void LlamaGenerator::Load(const std::string& model_path) {
|
||||
|
||||
llama_context_params context_params = llama_context_default_params();
|
||||
context_params.n_ctx = n_ctx_;
|
||||
context_params.n_batch = std::min(n_ctx_, kMaxBatchSize);
|
||||
context_params.n_batch = std::min(n_ctx_, static_cast<uint32_t>(5000));
|
||||
|
||||
ContextHandle loaded_context(
|
||||
LlamaGenerator::ContextHandle loaded_context(
|
||||
llama_init_from_model(loaded_model.get(), context_params));
|
||||
|
||||
if (!loaded_context) {
|
||||
throw std::runtime_error("LlamaGenerator: failed to create context");
|
||||
}
|
||||
@@ -52,10 +39,5 @@ void LlamaGenerator::Load(const std::string& model_path) {
|
||||
model_ = std::move(loaded_model);
|
||||
context_ = std::move(loaded_context);
|
||||
|
||||
if (logger_) {
|
||||
logger_->Log({.level = LogLevel::Info,
|
||||
.phase = PipelinePhase::Startup,
|
||||
.message = std::format("[LlamaGenerator] Loaded model: {} ",
|
||||
model_path)});
|
||||
}
|
||||
spdlog::info("[LlamaGenerator] Loaded model: {}", model_path);
|
||||
}
|
||||
55
pipeline/src/data_generation/llama/load_brewery_prompt.cc
Normal file
55
pipeline/src/data_generation/llama/load_brewery_prompt.cc
Normal file
@@ -0,0 +1,55 @@
|
||||
/**
|
||||
* @file data_generation/llama/load_brewery_prompt.cc
|
||||
* @brief Resolves brewery system prompt content from cache or a configured
|
||||
* filesystem path and provides a robust inline fallback prompt when absent.
|
||||
*/
|
||||
|
||||
#include <spdlog/spdlog.h>
|
||||
|
||||
#include <filesystem>
|
||||
#include <fstream>
|
||||
#include <stdexcept>
|
||||
|
||||
#include "data_generation/llama_generator.h"
|
||||
|
||||
/**
|
||||
* @brief Loads brewery system prompt from disk or cache.
|
||||
*
|
||||
* @param prompt_file_path Preferred prompt file location.
|
||||
* @return Prompt text loaded from disk.
|
||||
*/
|
||||
std::string LlamaGenerator::LoadBrewerySystemPrompt(
|
||||
const std::filesystem::path& prompt_file_path) {
|
||||
// Return cached version if already loaded
|
||||
if (!brewery_system_prompt_.empty()) {
|
||||
return brewery_system_prompt_;
|
||||
}
|
||||
|
||||
std::ifstream prompt_file(prompt_file_path);
|
||||
if (!prompt_file.is_open()) {
|
||||
spdlog::error(
|
||||
"LlamaGenerator: Failed to open brewery system prompt file '{}'",
|
||||
prompt_file_path.string());
|
||||
throw std::runtime_error(
|
||||
"LlamaGenerator: missing brewery system prompt file: " +
|
||||
prompt_file_path.string());
|
||||
}
|
||||
|
||||
const std::string prompt((std::istreambuf_iterator(prompt_file)),
|
||||
std::istreambuf_iterator<char>());
|
||||
prompt_file.close();
|
||||
|
||||
if (prompt.empty()) {
|
||||
spdlog::error("LlamaGenerator: Brewery system prompt file '{}' is empty",
|
||||
prompt_file_path.string());
|
||||
throw std::runtime_error(
|
||||
"LlamaGenerator: empty brewery system prompt file: " +
|
||||
prompt_file_path.string());
|
||||
}
|
||||
|
||||
spdlog::info(
|
||||
"LlamaGenerator: Loaded brewery system prompt from '{}' ({} chars)",
|
||||
prompt_file_path.string(), prompt.length());
|
||||
brewery_system_prompt_ = prompt;
|
||||
return brewery_system_prompt_;
|
||||
}
|
||||
@@ -14,13 +14,3 @@ size_t MockGenerator::DeterministicHash(const Location& location) {
|
||||
boost::hash_combine(seed, location.country);
|
||||
return seed;
|
||||
}
|
||||
|
||||
size_t MockGenerator::DeterministicHash(const Location& location,
|
||||
const UserPersona& persona,
|
||||
const Name& name) {
|
||||
size_t seed = DeterministicHash(location);
|
||||
boost::hash_combine(seed, persona.name);
|
||||
boost::hash_combine(seed, name.first_name);
|
||||
boost::hash_combine(seed, name.last_name);
|
||||
return seed;
|
||||
}
|
||||
@@ -17,9 +17,9 @@ BreweryResult MockGenerator::GenerateBrewery(
|
||||
const std::string_view adjective =
|
||||
kBreweryAdjectives.at(hash % kBreweryAdjectives.size());
|
||||
const std::string_view noun =
|
||||
kBreweryNouns.at(hash / kNounHashStride % kBreweryNouns.size());
|
||||
const std::string_view base_description = kBreweryDescriptions.at(
|
||||
(hash / kDescriptionHashStride) % kBreweryDescriptions.size());
|
||||
kBreweryNouns.at(hash / 7 % kBreweryNouns.size());
|
||||
const std::string_view base_description =
|
||||
kBreweryDescriptions.at((hash / 13) % kBreweryDescriptions.size());
|
||||
|
||||
const std::string name =
|
||||
std::format("{} {} {}", location.city, adjective, noun);
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user