AaronPo/the-biergarten-app
1
0
Fork 0
mirror of https://github.com/aaronpo97/the-biergarten-app.git synced 2026-10-15 01:54:43 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add reverse geocoding for brewery street addresses (#245)

Browse Source 
* Add geocoding to seed application, remove postal codes from generator

Update comments
This commit is contained in:
Aaron Po
2026-08-23 23:53:56 -04:00
committed by Aaron Po
parent e738fe484a
commit cd5fd2d998
41 changed files with 2966 additions and 2297 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tooling/pipeline/includes/biergarten_pipeline.h
View File

@@ -61,10 +61,7 @@
#include "services/enrichment/mock_enrichment.h"
#include "services/enrichment/wikipedia_service.h"
// --- services: postal_code ---
#include "services/postal_code/mock_postal_code_service.h"
#include "services/postal_code/postal_code_service.h"
#include "services/postal_code/xeger_postal_code_service.h"
// --- services: xeger ---
#include "services/xeger/xeger.h"
// --- services: logging ---

5
tooling/pipeline/includes/biergarten_pipeline_orchestrator.h
View File

@@ -16,7 +16,6 @@
#include "services/database/export_service.h"
#include "services/enrichment/enrichment_service.h"
#include "services/logging/logger.h"
#include "services/postal_code/postal_code_service.h"
/**
* @brief Main orchestrator for the Biergarten data generation pipeline.
@@ -35,8 +34,6 @@ class BiergartenPipelineOrchestrator {
* @param exporter Database backend for persisting generated records.
* @param curated_data_service Loads curated location, persona, and name
* data used to seed generation.
* @param postal_code_service Resolves a postal code for a city from its
* curated postal-code data.
* @param application_options CLI configuration and paths.
*/
BiergartenPipelineOrchestrator(
@@ -45,7 +42,6 @@ class BiergartenPipelineOrchestrator {
std::unique_ptr<DataGenerator> generator,
std::unique_ptr<IExportService> exporter,
std::unique_ptr<ICuratedDataService> curated_data_service,
std::unique_ptr<IPostalCodeService> postal_code_service,
const ApplicationOptions& application_options);
/**
@@ -82,7 +78,6 @@ class BiergartenPipelineOrchestrator {
*/
std::unique_ptr<IExportService> exporter_;
std::unique_ptr<ICuratedDataService> curated_data_service_;
std::unique_ptr<IPostalCodeService> postal_code_service_;
ApplicationOptions application_options_;

58
tooling/pipeline/includes/biergarten_pipeline_orchestrator/coords.h Normal file
View File

@@ -0,0 +1,58 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_COORDS_H_
#define BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_COORDS_H_
/**
* @file biergarten_pipeline_orchestrator/coords.h
* @brief Shared coordinate jitter helper used to place generated
* brewery/user addresses near a city's centre.
*/
#include <cmath>
#include <numbers>
#include <random>
namespace biergarten_pipeline_orchestrator_internal {
struct Coords {
double longitude;
double latitude;
};
inline constexpr double kEarthRadiusKm = 6371.0;
inline double DegreesToRadians(double degrees) {
return degrees * std::numbers::pi / 180.0;
}
inline double RadiansToDegrees(double radians) {
return radians * 180.0 / std::numbers::pi;
}
/**
* @brief Samples a point uniformly at random within @p distance_km of
* @p centre.
*/
inline Coords GetRandomCoordsWithinRange(const Coords& centre,
const int distance_km,
std::mt19937& rng) {
std::uniform_real_distribution<double> angle_dist(0.0,
2.0 * std::numbers::pi);
std::uniform_real_distribution<double> unit_dist(0.0, 1.0);
const double angle_radians = angle_dist(rng);
// sqrt() keeps points uniformly distributed over the disc's area.
const double radius_km = distance_km * std::sqrt(unit_dist(rng));
const double delta_latitude_degrees =
RadiansToDegrees(radius_km * std::cos(angle_radians) / kEarthRadiusKm);
const double delta_longitude_degrees = RadiansToDegrees(
radius_km * std::sin(angle_radians) /
(kEarthRadiusKm * std::cos(DegreesToRadians(centre.latitude))));
return Coords{.longitude = centre.longitude + delta_longitude_degrees,
.latitude = centre.latitude + delta_latitude_degrees};
}
} // namespace biergarten_pipeline_orchestrator_internal
#endif // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_COORDS_H_

14
tooling/pipeline/includes/data_generation/generation_json_validation.h
View File

@@ -3,9 +3,9 @@
/**
* @file data_generation/generation_json_validation.h
* @brief Generator-agnostic helpers for preparing prompt context and
* validating structured JSON output. Shared across all DataGenerator
* implementations (Llama, OpenAI, ...).
* @brief Generator-agnostic helpers, shared across all DataGenerator
* implementations (Llama, OpenAI, ...), for preparing prompt context and
* validating structured JSON output.
*/
#include <cstddef>
@@ -36,11 +36,9 @@ 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.
* @brief Validates and parses user JSON output, populating only
* `username`, `bio`, and `activity_weight` (`first_name` and `last_name`
* come from the sampled Name).
*
* @param raw Raw model output.
* @param user_out Parsed user payload.

10
tooling/pipeline/includes/data_generation/openai_generator.h
View File

@@ -18,13 +18,9 @@
/**
* @brief Data generator implementation backed by the OpenAI Chat
* Completions API.
*
* Unlike LlamaGenerator, this generator has no local model state and no
* chat-template formatting step -- Chat Completions takes system/user
* messages directly, and Structured Outputs (response_format: json_schema,
* strict: true) guarantee schema-valid JSON, replacing llama.cpp's GBNF
* grammar constraint.
* Completions API, sending system/user messages directly and using
* Structured Outputs (response_format: json_schema, strict: true) to
* guarantee schema-valid JSON.
*/
class OpenAIGenerator final : public DataGenerator {
public:

11
tooling/pipeline/includes/data_generation/openai_json_schemas.h
View File

@@ -4,14 +4,9 @@
/**
* @file data_generation/openai_json_schemas.h
* @brief JSON Schemas constraining structured output from OpenAIGenerator
* Chat Completions requests, via response_format.json_schema (Structured
* Outputs, strict mode). This is OpenAI's equivalent of the GBNF grammars
* in json_grammars.h -- the API guarantees the response message content is
* a single JSON string that validates against the schema, so there's no
* grammar-level "thought-block" prefix to account for.
*
* OpenAI's strict mode requires "additionalProperties": false on every
* object in the schema, which these already have.
* Chat Completions requests via response_format.json_schema (Structured
* Outputs, strict mode), each setting "additionalProperties": false as
* strict mode requires.
*/
#include <string_view>

12
tooling/pipeline/includes/data_model/generated_models.h
View File

@@ -88,23 +88,23 @@ struct EnrichedCity {
};
/**
* @brief A physical address: the city plus a concrete postal code selected
* from that city's curated postal-code examples.
* @brief A physical address: the city plus a coordinate pair sampled near
* the city's centre.
*/
struct BreweryAddress {
City city;
std::string postal_code{};
double longitude{};
double latitude{};
};
/**
* @brief A physical address for a generated user: the city plus a concrete
* postal code selected from that city's curated postal-code examples.
* @brief A physical address for a generated user: the city plus a
* coordinate pair sampled near the city's centre.
*/
struct UserAddress {
City city;
std::string postal_code{};
double longitude{};
double latitude{};
};
/**

16
tooling/pipeline/includes/services/database/sqlite_statement_helpers.h
View File

@@ -54,7 +54,6 @@ CREATE TABLE IF NOT EXISTS brewery_addresses (
id INTEGER PRIMARY KEY AUTOINCREMENT,
brewery_id INTEGER NOT NULL,
city_id INTEGER NOT NULL,
postal_code TEXT NOT NULL,
longitude REAL NOT NULL,
latitude REAL NOT NULL,
FOREIGN KEY(brewery_id) REFERENCES breweries(id) ON DELETE CASCADE,
@@ -90,7 +89,8 @@ CREATE TABLE IF NOT EXISTS user_addresses (
id INTEGER PRIMARY KEY AUTOINCREMENT,
user_id INTEGER NOT NULL,
city_id INTEGER NOT NULL,
postal_code TEXT NOT NULL,
longitude REAL NOT NULL,
latitude REAL NOT NULL,
FOREIGN KEY(user_id) REFERENCES users(id) ON DELETE CASCADE,
FOREIGN KEY(city_id) REFERENCES cities(id) ON DELETE CASCADE
);
@@ -130,10 +130,9 @@ inline constexpr std::string_view kInsertBreweryAddressSql = R"sql(
INSERT INTO brewery_addresses (
brewery_id,
city_id,
postal_code,
longitude,
latitude
) VALUES (?, ?, ?, ?, ?);
) VALUES (?, ?, ?, ?);
)sql";
inline constexpr std::string_view kInsertUserSql = R"sql(
@@ -153,8 +152,9 @@ inline constexpr std::string_view kInsertUserAddressSql = R"sql(
INSERT INTO user_addresses (
user_id,
city_id,
postal_code
) VALUES (?, ?, ?);
longitude,
latitude
) VALUES (?, ?, ?, ?);
)sql";
// sqlite3_bind_*() parameter indices are 1-based, matching the "?"
@@ -182,7 +182,6 @@ enum BreweryBindIndex {
enum BreweryAddressBindIndex {
kBreweryAddressBreweryIdBindIndex = 1,
kBreweryAddressCityIdBindIndex,
kBreweryAddressPostalCodeBindIndex,
kBreweryAddressLongitudeBindIndex,
kBreweryAddressLatitudeBindIndex,
};
@@ -201,7 +200,8 @@ enum UserBindIndex {
enum UserAddressBindIndex {
kUserAddressUserIdBindIndex = 1,
kUserAddressCityIdBindIndex,
kUserAddressPostalCodeBindIndex,
kUserAddressLongitudeBindIndex,
kUserAddressLatitudeBindIndex,
};
SqliteStatementHandle PrepareStatement(const SqliteDatabaseHandle& db_handle,

80
tooling/pipeline/includes/services/postal_code/mock_postal_code_service.h
View File

@@ -1,80 +0,0 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_MOCK_POSTAL_CODE_SERVICE_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_MOCK_POSTAL_CODE_SERVICE_H_
/**
* @file services/postal_code/mock_postal_code_service.h
* @brief Data-driven postal code service that selects the first curated
* example for a city and validates it against the city's postal-code regex.
*/
#include <format>
#include <regex>
#include <stdexcept>
#include <string>
#include "services/postal_code/postal_code_service.h"
/**
* @brief Postal code service backed entirely by the curated locations
* dataset: it returns the city's first example postal code after checking it
* against the curated postal-code regex.
*
* A precise city regex is preferred when present; otherwise the permissive
* country format regex is used as the fallback. A city with no examples, or an
* example that fails validation, throws so the caller can skip the city.
*/
class MockPostalCodeService final : public IPostalCodeService {
public:
std::string GeneratePostalCode(const City& city) override {
const PostalCodeSpec& spec = city.postal_code;
if (spec.examples.empty()) {
throw std::runtime_error(std::format(
"No postal-code examples available for city '{}'", city.city));
}
const std::string& candidate = spec.examples.front();
if (!MatchesAnyPattern(candidate, spec)) {
throw std::runtime_error(
std::format("Postal code '{}' for city '{}' does not match the "
"curated postal-code regex",
candidate, city.city));
}
return candidate;
}
private:
/**
* @brief Returns true if @p candidate matches any city regex, or the
* country format regex when no city regex matches. When the spec carries no
* usable regex at all, validation is skipped (returns true).
*/
static bool MatchesAnyPattern(const std::string& candidate,
const PostalCodeSpec& spec) {
bool has_pattern = false;
for (const std::string& pattern : spec.city_regexes) {
if (pattern.empty()) {
continue;
}
has_pattern = true;
if (std::regex_match(candidate, std::regex(pattern))) {
return true;
}
}
if (!spec.country_format_regex.empty()) {
has_pattern = true;
if (std::regex_match(candidate,
std::regex(spec.country_format_regex))) {
return true;
}
}
return !has_pattern;
}
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_MOCK_POSTAL_CODE_SERVICE_H_

35
tooling/pipeline/includes/services/postal_code/postal_code_service.h
View File

@@ -1,35 +0,0 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_POSTAL_CODE_SERVICE_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_POSTAL_CODE_SERVICE_H_
/**
* @file services/postal_code/postal_code_service.h
* @brief Abstraction for resolving a postal code for a city.
*/
#include <string>
#include "data_model/models.h"
/**
* @brief Interface for services that resolve a postal code for a city.
*/
class IPostalCodeService {
public:
IPostalCodeService() = default;
virtual ~IPostalCodeService() = default;
IPostalCodeService(const IPostalCodeService&) = delete;
IPostalCodeService& operator=(const IPostalCodeService&) = delete;
IPostalCodeService(IPostalCodeService&&) = delete;
IPostalCodeService& operator=(IPostalCodeService&&) = delete;
/**
* @brief Resolves a postal code for @p city.
*
* @param city City whose curated postal-code examples supply the result.
* @return A postal code string, or an empty string if none is available.
*/
virtual std::string GeneratePostalCode(const City& city) = 0;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_POSTAL_CODE_SERVICE_H_

32
tooling/pipeline/includes/services/postal_code/xeger_postal_code_service.h
View File

@@ -1,32 +0,0 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_XEGER_POSTAL_CODE_SERVICE_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_XEGER_POSTAL_CODE_SERVICE_H_
/**
* @file services/postal_code/xeger_postal_code_service.h
* @brief Postal code service that generates a fresh, format-conformant code
* per call from the curated regex patterns, instead of returning a fixed
* example.
*/
#include <random>
#include "services/postal_code/postal_code_service.h"
/**
* @brief Postal code service using regex-driven generation (xeger).
*
* Picks among the city's curated `city_regexes` (falls back to
* `country_format_regex`), then generates a random string matching that pattern
* via GenerateStringFromRegex().
*/
class XegerPostalCodeService final : public IPostalCodeService {
public:
XegerPostalCodeService();
std::string GeneratePostalCode(const City& city) override;
private:
std::mt19937 rng_;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_XEGER_POSTAL_CODE_SERVICE_H_