Pipeline: Add LLM and mocked user generation to the pipeline (#230)

This commit is contained in:
2026-07-01 07:47:24 -04:00
committed by GitHub
parent 880f73e004
commit 2b8a900d12
90 changed files with 57254 additions and 800 deletions

View File

@@ -14,6 +14,7 @@ void SqliteExportService::Finalize() {
}
try {
insert_user_stmt_.reset();
insert_brewery_stmt_.reset();
insert_location_stmt_.reset();
if (transaction_open_) {

View File

@@ -33,7 +33,7 @@ void ResetStatement(SqliteStatementHandle& statement) {
}
void Bind(const SqliteStatementHandle& statement,
const BindParam<std::string_view>& param) {
const BoundParam<std::string_view>& param) {
const auto byte_count = param.value.size();
if (byte_count > static_cast<std::size_t>(std::numeric_limits<int>::max())) {
ThrowSqliteError(sqlite3_db_handle(statement.get()), param.action);
@@ -60,7 +60,7 @@ void Bind(const SqliteStatementHandle& statement,
}
void Bind(const SqliteStatementHandle& statement,
const BindParam<double>& param) {
const BoundParam<double>& param) {
if (sqlite3_bind_double(statement.get(), param.index, param.value) !=
SQLITE_OK) {
ThrowSqliteError(sqlite3_db_handle(statement.get()), param.action);
@@ -68,7 +68,7 @@ void Bind(const SqliteStatementHandle& statement,
}
void Bind(const SqliteStatementHandle& statement,
const BindParam<sqlite3_int64>& param) {
const BoundParam<sqlite3_int64>& param) {
if (sqlite3_bind_int64(statement.get(), param.index, param.value) !=
SQLITE_OK) {
ThrowSqliteError(sqlite3_db_handle(statement.get()), param.action);

View File

@@ -18,9 +18,9 @@ std::filesystem::path SqliteExportService::BuildDatabasePath() const {
std::filesystem::path candidate = output_path_ / base_filename;
for (int suffix = 1; std::filesystem::exists(candidate); ++suffix) {
candidate = output_path_ /
std::filesystem::path(std::format("biergarten_seed_{}-{}.sqlite",
run_timestamp_utc_, suffix));
candidate = output_path_ / std::filesystem::path(
std::format("biergarten_seed_{}-{}.sqlite",
run_timestamp_utc_, suffix));
}
return candidate;
@@ -33,6 +33,9 @@ void SqliteExportService::InitializeSchema() const {
sqlite_export_service_internal::ExecSql(
db_handle_, sqlite_export_service_internal::kCreateBreweriesTableSql,
"Failed to create SQLite breweries table");
sqlite_export_service_internal::ExecSql(
db_handle_, sqlite_export_service_internal::kCreateUsersTableSql,
"Failed to create SQLite users table");
}
void SqliteExportService::PrepareStatements() {
@@ -42,6 +45,9 @@ void SqliteExportService::PrepareStatements() {
insert_brewery_stmt_ = sqlite_export_service_internal::PrepareStatement(
db_handle_, sqlite_export_service_internal::kInsertBrewerySql,
"Failed to prepare SQLite brewery insert statement");
insert_user_stmt_ = sqlite_export_service_internal::PrepareStatement(
db_handle_, sqlite_export_service_internal::kInsertUserSql,
"Failed to prepare SQLite user insert statement");
}
void SqliteExportService::RollbackAndCloseNoThrow() noexcept {
@@ -54,6 +60,7 @@ void SqliteExportService::RollbackAndCloseNoThrow() noexcept {
transaction_open_ = false;
}
insert_user_stmt_.reset();
insert_brewery_stmt_.reset();
insert_location_stmt_.reset();
db_handle_.reset();

View File

@@ -1,6 +1,7 @@
/**
* @file services/sqlite/process_record.cc
* @brief SqliteExportService::ProcessRecord() implementation.
* @brief SqliteExportService::ProcessRecord() implementation
* and the shared location-resolution helper.
*/
#include <iomanip>
@@ -29,111 +30,117 @@ std::string SqliteExportService::BuildLocationKey(const Location& location) {
return key_stream.str();
}
uint64_t SqliteExportService::ProcessRecord(const GeneratedBrewery& brewery) {
sqlite3_int64 SqliteExportService::ResolveLocationId(const Location& location) {
const std::string location_key = BuildLocationKey(location);
const auto cached_location = location_cache_.find(location_key);
if (cached_location != location_cache_.end()) {
return cached_location->second;
}
const std::string local_languages_json =
sqlite_export_service_internal::SerializeVector(location.local_languages);
sqlite_export_service_internal::Bind(
insert_location_stmt_,
sqlite_export_service_internal::BoundParam<std::string_view>{
.index = sqlite_export_service_internal::kLocationCityBindIndex,
.value = location.city,
.action = "Failed to bind SQLite location city"});
sqlite_export_service_internal::Bind(
insert_location_stmt_,
sqlite_export_service_internal::BoundParam<std::string_view>{
.index =
sqlite_export_service_internal::kLocationStateProvinceBindIndex,
.value = location.state_province,
.action = "Failed to bind SQLite location state/province"});
sqlite_export_service_internal::Bind(
insert_location_stmt_,
sqlite_export_service_internal::BoundParam<std::string_view>{
.index = sqlite_export_service_internal::kLocationIso31662BindIndex,
.value = location.iso3166_2,
.action = "Failed to bind SQLite location ISO 3166-2 code"});
sqlite_export_service_internal::Bind(
insert_location_stmt_,
sqlite_export_service_internal::BoundParam<std::string_view>{
.index = sqlite_export_service_internal::kLocationCountryBindIndex,
.value = location.country,
.action = "Failed to bind SQLite location country"});
sqlite_export_service_internal::Bind(
insert_location_stmt_,
sqlite_export_service_internal::BoundParam<std::string_view>{
.index = sqlite_export_service_internal::kLocationIso31661BindIndex,
.value = location.iso3166_1,
.action = "Failed to bind SQLite location ISO 3166-1 code"});
sqlite_export_service_internal::Bind(
insert_location_stmt_,
sqlite_export_service_internal::BoundParam<std::string_view>{
.index = sqlite_export_service_internal::kLocationLanguagesBindIndex,
.value = local_languages_json,
.action = "Failed to bind SQLite location languages"});
sqlite_export_service_internal::Bind(
insert_location_stmt_,
sqlite_export_service_internal::BoundParam{
.index = sqlite_export_service_internal::kLocationLatitudeBindIndex,
.value = location.latitude,
.action = "Failed to bind SQLite location latitude"});
sqlite_export_service_internal::Bind(
insert_location_stmt_,
sqlite_export_service_internal::BoundParam{
.index = sqlite_export_service_internal::kLocationLongitudeBindIndex,
.value = location.longitude,
.action = "Failed to bind SQLite location longitude"});
sqlite_export_service_internal::StepStatement(
db_handle_, insert_location_stmt_,
"Failed to insert SQLite location row");
const sqlite3_int64 location_id =
sqlite_export_service_internal::LastInsertRowId(db_handle_);
location_cache_.emplace(location_key, location_id);
sqlite_export_service_internal::ResetStatement(insert_location_stmt_);
return location_id;
}
uint64_t SqliteExportService::ProcessRecord(const BreweryRecord& brewery) {
if (db_handle_ == nullptr || !transaction_open_) {
throw std::runtime_error("SQLite export service is not initialized");
}
const std::string location_key = BuildLocationKey(brewery.location);
const auto cached_location = location_cache_.find(location_key);
sqlite3_int64 location_id = 0;
if (cached_location != location_cache_.end()) {
location_id = cached_location->second;
} else {
const std::string local_languages_json =
sqlite_export_service_internal::SerializeVector(
brewery.location.local_languages);
sqlite_export_service_internal::Bind(
insert_location_stmt_,
sqlite_export_service_internal::BindParam<std::string_view>{
.index = sqlite_export_service_internal::kLocationCityBindIndex,
.value = brewery.location.city,
.action = "Failed to bind SQLite location city"});
sqlite_export_service_internal::Bind(
insert_location_stmt_,
sqlite_export_service_internal::BindParam<std::string_view>{
.index =
sqlite_export_service_internal::kLocationStateProvinceBindIndex,
.value = brewery.location.state_province,
.action = "Failed to bind SQLite location state/province"});
sqlite_export_service_internal::Bind(
insert_location_stmt_,
sqlite_export_service_internal::BindParam<std::string_view>{
.index = sqlite_export_service_internal::kLocationIso31662BindIndex,
.value = brewery.location.iso3166_2,
.action = "Failed to bind SQLite location ISO 3166-2 code"});
sqlite_export_service_internal::Bind(
insert_location_stmt_,
sqlite_export_service_internal::BindParam<std::string_view>{
.index = sqlite_export_service_internal::kLocationCountryBindIndex,
.value = brewery.location.country,
.action = "Failed to bind SQLite location country"});
sqlite_export_service_internal::Bind(
insert_location_stmt_,
sqlite_export_service_internal::BindParam<std::string_view>{
.index = sqlite_export_service_internal::kLocationIso31661BindIndex,
.value = brewery.location.iso3166_1,
.action = "Failed to bind SQLite location ISO 3166-1 code"});
sqlite_export_service_internal::Bind(
insert_location_stmt_,
sqlite_export_service_internal::BindParam<std::string_view>{
.index =
sqlite_export_service_internal::kLocationLanguagesBindIndex,
.value = local_languages_json,
.action = "Failed to bind SQLite location languages"});
sqlite_export_service_internal::Bind(
insert_location_stmt_,
sqlite_export_service_internal::BindParam{
.index = sqlite_export_service_internal::kLocationLatitudeBindIndex,
.value = brewery.location.latitude,
.action = "Failed to bind SQLite location latitude"});
sqlite_export_service_internal::Bind(
insert_location_stmt_,
sqlite_export_service_internal::BindParam{
.index =
sqlite_export_service_internal::kLocationLongitudeBindIndex,
.value = brewery.location.longitude,
.action = "Failed to bind SQLite location longitude"});
sqlite_export_service_internal::StepStatement(
db_handle_, insert_location_stmt_,
"Failed to insert SQLite location row");
location_id = sqlite_export_service_internal::LastInsertRowId(db_handle_);
location_cache_.emplace(location_key, location_id);
sqlite_export_service_internal::ResetStatement(insert_location_stmt_);
}
const sqlite3_int64 location_id = ResolveLocationId(brewery.location);
sqlite_export_service_internal::Bind(
insert_brewery_stmt_,
sqlite_export_service_internal::BindParam<sqlite3_int64>{
sqlite_export_service_internal::BoundParam<sqlite3_int64>{
.index = sqlite_export_service_internal::kBreweryLocationIdBindIndex,
.value = location_id,
.action = "Failed to bind SQLite brewery location id"});
sqlite_export_service_internal::Bind(
insert_brewery_stmt_,
sqlite_export_service_internal::BindParam<std::string_view>{
sqlite_export_service_internal::BoundParam<std::string_view>{
.index = sqlite_export_service_internal::kBreweryEnglishNameBindIndex,
.value = brewery.brewery.name_en,
.action = "Failed to bind SQLite brewery English name"});
sqlite_export_service_internal::Bind(
insert_brewery_stmt_,
sqlite_export_service_internal::BindParam<std::string_view>{
sqlite_export_service_internal::BoundParam<std::string_view>{
.index = sqlite_export_service_internal::
kBreweryEnglishDescriptionBindIndex,
.value = brewery.brewery.description_en,
.action = "Failed to bind SQLite brewery English description"});
sqlite_export_service_internal::Bind(
insert_brewery_stmt_,
sqlite_export_service_internal::BindParam<std::string_view>{
sqlite_export_service_internal::BoundParam<std::string_view>{
.index = sqlite_export_service_internal::kBreweryLocalNameBindIndex,
.value = brewery.brewery.name_local,
.action = "Failed to bind SQLite brewery local name"});
sqlite_export_service_internal::Bind(
insert_brewery_stmt_,
sqlite_export_service_internal::BindParam<std::string_view>{
sqlite_export_service_internal::BoundParam<std::string_view>{
.index =
sqlite_export_service_internal::kBreweryLocalDescriptionBindIndex,
.value = brewery.brewery.description_local,

View File

@@ -0,0 +1,79 @@
/**
* @file services/sqlite/process_user_record.cc
* @brief SqliteExportService::ProcessRecord(UserRecord) implementation.
*/
#include <stdexcept>
#include "services/database/sqlite_export_service.h"
#include "services/database/sqlite_export_service_helpers.h"
uint64_t SqliteExportService::ProcessRecord(const UserRecord& user) {
if (db_handle_ == nullptr || !transaction_open_) {
throw std::runtime_error("SQLite export service is not initialized");
}
const sqlite3_int64 location_id = ResolveLocationId(user.location);
sqlite_export_service_internal::Bind(
insert_user_stmt_,
sqlite_export_service_internal::BoundParam<sqlite3_int64>{
.index = sqlite_export_service_internal::kUserLocationIdBindIndex,
.value = location_id,
.action = "Failed to bind SQLite user location id"});
sqlite_export_service_internal::Bind(
insert_user_stmt_,
sqlite_export_service_internal::BoundParam<std::string_view>{
.index = sqlite_export_service_internal::kUserFirstNameBindIndex,
.value = user.user.first_name,
.action = "Failed to bind SQLite user first name"});
sqlite_export_service_internal::Bind(
insert_user_stmt_,
sqlite_export_service_internal::BoundParam<std::string_view>{
.index = sqlite_export_service_internal::kUserLastNameBindIndex,
.value = user.user.last_name,
.action = "Failed to bind SQLite user last name"});
sqlite_export_service_internal::Bind(
insert_user_stmt_,
sqlite_export_service_internal::BoundParam<std::string_view>{
.index = sqlite_export_service_internal::kUserGenderBindIndex,
.value = user.user.gender,
.action = "Failed to bind SQLite user gender"});
sqlite_export_service_internal::Bind(
insert_user_stmt_,
sqlite_export_service_internal::BoundParam<std::string_view>{
.index = sqlite_export_service_internal::kUserUsernameBindIndex,
.value = user.user.username,
.action = "Failed to bind SQLite user username"});
sqlite_export_service_internal::Bind(
insert_user_stmt_,
sqlite_export_service_internal::BoundParam<std::string_view>{
.index = sqlite_export_service_internal::kUserBioBindIndex,
.value = user.user.bio,
.action = "Failed to bind SQLite user bio"});
sqlite_export_service_internal::Bind(
insert_user_stmt_,
sqlite_export_service_internal::BoundParam<double>{
.index = sqlite_export_service_internal::kUserActivityWeightBindIndex,
.value = static_cast<double>(user.user.activity_weight),
.action = "Failed to bind SQLite user activity weight"});
sqlite_export_service_internal::Bind(
insert_user_stmt_,
sqlite_export_service_internal::BoundParam<std::string_view>{
.index = sqlite_export_service_internal::kUserEmailBindIndex,
.value = user.email,
.action = "Failed to bind SQLite user email"});
sqlite_export_service_internal::Bind(
insert_user_stmt_,
sqlite_export_service_internal::BoundParam<std::string_view>{
.index = sqlite_export_service_internal::kUserDateOfBirthBindIndex,
.value = user.date_of_birth,
.action = "Failed to bind SQLite user date of birth"});
sqlite_export_service_internal::StepStatement(
db_handle_, insert_user_stmt_, "Failed to insert SQLite user row");
sqlite_export_service_internal::ResetStatement(insert_user_stmt_);
return sqlite_export_service_internal::LastInsertRowId(db_handle_);
}