6 Commits

Author SHA1 Message Date
Aaron Po
c58e4c1986 updates 2026-05-15 14:11:34 -04:00
Aaron Po
e6a20324e4 update logging to use logger channel 2026-05-15 01:13:53 -04:00
Aaron Po
a4968eb043 update doxygen comments for concurrent logger 2026-05-14 21:21:28 -04:00
Aaron Po
74f11b57e2 Implement pipeline logging with bounded channels and orchestrator integration 2026-05-14 21:16:29 -04:00
Aaron Po
f93b14897b Add bounded channels 2026-05-14 19:50:08 -04:00
Aaron Po
688c28f85d update class diagram 2026-05-14 19:49:14 -04:00
30 changed files with 385 additions and 732 deletions

View File

@@ -26,7 +26,6 @@ skinparam note {
title The Biergarten Data Pipeline - Class Diagram
class BiergartenDataGenerator {
- logger_ : std::shared_ptr<ILogger>
- context_service_ : std::unique_ptr<IEnrichmentService>
- generator_ : std::unique_ptr<DataGenerator>
- exporter_ : std::unique_ptr<IExportService>
@@ -37,46 +36,6 @@ class BiergartenDataGenerator {
- LogResults() : void
}
class LogLevel <<enumeration>> {
Debug
Info
Warn
Error
}
class PipelinePhase <<enumeration>> {
Startup
UserGeneration
BreweryAndBeerGeneration
CheckinGeneration
RatingGeneration
FollowGeneration
Teardown
}
struct 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
}
interface IEnrichmentService <<interface>> {
+ GetLocationContext(loc : const Location&) : std::string
}
@@ -164,17 +123,10 @@ class SystemDateTimeProvider {
}
' Structural Relationships / Dependency Injection
BiergartenDataGenerator *-- ILogger : owns
BiergartenDataGenerator *-- IEnrichmentService : owns
BiergartenDataGenerator *-- DataGenerator : owns
BiergartenDataGenerator *-- IExportService : owns
LogEntry *-- LogLevel
LogEntry *-- PipelinePhase
ILogger <|.. LogProducer : implements
LogProducer ..> LogEntry : emits
LogDispatcher ..> LogEntry : consumes
IEnrichmentService <|.. WikipediaService : implements
WikipediaService *-- WebClient : owns

View File

@@ -275,29 +275,32 @@ package "Infrastructure: Logging" {
+ level : LogLevel
+ phase : PipelinePhase
+ message : std::string
+ city : std::optional<std::string>
+ entity_id : std::optional<std::string>
+ worker : std::optional<std::string>
}
interface ILogger <<interface>> {
+ Log(entry : const LogEntry&) : void
interface Logger <<interface>> {
+ Log(level, phase, message,\n city, entity_id, worker) : void
}
class LogProducer {
- channel_ : BoundedChannel<LogEntry>&
+ Log(entry : const LogEntry&) : void
class PipelineLogger {
- log_ch_ : BoundedChannel<LogEntry>&
+ Log(level, phase, message,\n city, entity_id, worker) : void
}
class LogDispatcher {
- channel_ : BoundedChannel<LogEntry>&
class LogWorker {
- log_ch_ : BoundedChannel<LogEntry>&
+ Run() : void
- FormatTimestamp(tp) : std::string
- ToSpdlogLevel(level) : spdlog::level::level_enum
- ToString(phase) : std::string
}
LogEntry *-- LogLevel
LogEntry *-- PipelinePhase
ILogger <|.. LogProducer
LogProducer ..> LogEntry : emits
LogDispatcher ..> LogEntry : consumes
PipelineLogger ..> LogEntry : emits
LogWorker ..> LogEntry : consumes
}
package "Infrastructure: Pipeline Channel" {

View File

@@ -138,8 +138,7 @@ FetchContent_MakeAvailable(cpp-httplib)
# 5. Executable & Sources
add_executable(${PROJECT_NAME}
includes/services/enrichment/mock_enrichment.h
includes/json_handling/pretty_print.h)
includes/services/enrichment/mock_enrichment.h)
# --- Entry point ---
target_sources(${PROJECT_NAME} PRIVATE
@@ -249,11 +248,6 @@ target_compile_definitions(${PROJECT_NAME} PRIVATE
$<$<CONFIG:Debug>:DEBUG>
)
target_compile_options(biergarten-pipeline PRIVATE
-fmacro-prefix-map=${CMAKE_SOURCE_DIR}/tooling/pipeline/src/=
)
# 7. Runtime Assets
configure_file(
${CMAKE_SOURCE_DIR}/locations.json
@@ -265,4 +259,3 @@ add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
${CMAKE_SOURCE_DIR}/prompts
${CMAKE_BINARY_DIR}/prompts
)

View File

@@ -51,12 +51,6 @@ class BiergartenPipelineOrchestrator {
* 2. Resolve context for each city using the injected context service
* 3. Generate brewery data for sampled cities
*
* @note STRUCTURAL CONCURRENCY REQUIREMENT:
* When transitioned to a multithreaded design, this method MUST structurally
* enforce that all deployed worker threads are joined before returning (e.g.
* by using std::jthread or a structured concurrency primitive). This ensures
* workers do not attempt to log to a closed channel during application teardown.
*
* @return true if successful, false if not
*/
bool Run();

View File

@@ -38,7 +38,8 @@ class LlamaGenerator final : public DataGenerator {
* @param prompt_directory Directory service for loading named prompt files.
*/
LlamaGenerator(const ApplicationOptions& options,
const std::string& model_path, std::shared_ptr<ILogger> logger,
const std::string& model_path,
std::shared_ptr<ILogger> logger,
std::unique_ptr<IPromptFormatter> prompt_formatter,
std::unique_ptr<IPromptDirectory> prompt_directory);

View File

@@ -1,109 +0,0 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_PRETTY_PRINT_H_
#define BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_PRETTY_PRINT_H_
/**
* @file json_handling/pretty_print.h
* @brief Pretty-printing utilities for JSON values.
*
* Provides formatting capability for boost::json::value with indentation and
* readable output. Adapted from Boost JSON library examples.
*/
#include <boost/json.hpp>
#include <ostream>
#include <string>
/**
* @brief Pretty-prints a JSON value to an output stream with indentation.
*
* Recursively formats JSON objects and arrays with consistent 4-space
* indentation. Adapted from:
* https://raw.githubusercontent.com/boostorg/json/refs/heads/develop/example/pretty.cpp
*
* @param outstream Output stream to write formatted JSON.
* @param json_val JSON value to format.
* @param indent Optional indentation string (managed internally on first call).
*/
inline void PrettyPrint(std::ostream& outstream,
boost::json::value const& json_val,
std::string* indent = nullptr) {
std::string str;
if (indent == nullptr) {
indent = &str;
}
switch (json_val.kind()) {
case boost::json::kind::object: {
outstream << "{\n";
indent->append(4, ' ');
auto const& obj = json_val.get_object();
if (!obj.empty()) {
const auto* iter = obj.begin();
for (;;) {
outstream << *indent << boost::json::serialize(iter->key()) << " : ";
PrettyPrint(outstream, iter->value(), indent);
iter = std::next(iter);
if (iter == obj.end()) {
break;
}
outstream << ",\n";
}
}
outstream << "\n";
indent->resize(indent->size() - 4);
outstream << *indent << "}";
break;
}
case boost::json::kind::array: {
outstream << "[\n";
indent->append(4, ' ');
auto const& arr = json_val.get_array();
if (!arr.empty()) {
const auto* iter = arr.begin();
for (;;) {
outstream << *indent;
PrettyPrint(outstream, *iter, indent);
iter = std::next(iter);
if (iter == arr.end()) {
break;
}
outstream << ",\n";
}
}
outstream << "\n";
indent->resize(indent->size() - 4);
outstream << *indent << "]";
break;
}
case boost::json::kind::string: {
outstream << serialize(json_val.get_string());
break;
}
case boost::json::kind::uint64:
case boost::json::kind::int64:
case boost::json::kind::double_:
outstream << json_val;
break;
case boost::json::kind::bool_:
if (json_val.get_bool()) {
outstream << "true";
} else {
outstream << "false";
}
break;
case boost::json::kind::null:
outstream << "null";
break;
}
if (indent->empty()) {
outstream << "\n";
}
}
#endif

View File

@@ -6,8 +6,8 @@
* them to spdlog on a dedicated thread.
*/
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_CONSUMER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_CONSUMER_H_
#include <spdlog/spdlog.h>
@@ -50,4 +50,4 @@ class LogDispatcher {
static spdlog::level::level_enum ToSpdlogLevel(LogLevel level);
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_CONSUMER_H_

View File

@@ -10,10 +10,8 @@
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
#include <chrono>
#include <source_location>
#include <string>
#include <thread>
#include <vector>
#include <string>
/**
* @enum LogLevel
@@ -43,35 +41,17 @@ enum class PipelinePhase {
Teardown, ///< Finalization and cleanup.
};
/**
* @struct LogDTO
* @brief User-provided subset of log fields. Used to capture call-site info transparently.
*/
struct LogDTO {
LogLevel level;
PipelinePhase phase;
std::string message;
};
/**
* @struct LogEntry
* @brief Single structured log event.
*
* All fields are value types, which keeps transfer across the bounded channel
* simple and avoids shared ownership.
*
* NOTE: timestamp, thread_id, and origin must be populated by ILogger::Log()
* before the entry is dispatched.
*/
struct LogEntry {
/// @brief Timestamp when the entry was created.
std::chrono::system_clock::time_point timestamp{};
/// @brief Source location where the log call was made.
std::source_location origin{};
/// @brief Thread responsible for emitting the log.
std::thread::id thread_id{};
std::chrono::system_clock::time_point timestamp =
std::chrono::system_clock::now();
/// @brief Severity level of this entry.

View File

@@ -41,10 +41,10 @@ class LogProducer final : public ILogger {
/**
* @brief Queue a log message for asynchronous processing.
*
* Blocks while the channel applies backpressure. This blocking behavior
* under heavy load is an accepted trade-off for simplicity.
* Blocks while the channel applies backpressure.
*/
void DoLog(LogEntry log_entry) override;
void Log(LogLevel level, PipelinePhase phase,
std::string_view message) override;
private:
BoundedChannel<LogEntry>& channel_;

View File

@@ -9,9 +9,9 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
#include <source_location>
#include <optional>
#include <string>
#include <utility>
#include <string_view>
#include "services/logging/log_entry.h"
@@ -34,31 +34,12 @@ class ILogger {
/**
* @brief Submit a log message to the logging subsystem.
*
* @param payload User-provided log data (level, phase, message).
* @param origin Auto-captured source location of the call site.
* @param level Severity of the message.
* @param phase Pipeline execution phase associated with the message.
* @param message Log message text.
*/
void Log(LogDTO payload,
std::source_location origin = std::source_location::current(),
std::chrono::system_clock::time_point timestamp = std::chrono::system_clock::now(),
std::thread::id thread_id = std::this_thread::get_id()) {
LogEntry entry;
entry.timestamp = timestamp;
entry.thread_id = thread_id;
entry.level = payload.level;
entry.phase = payload.phase;
entry.message = std::move(payload.message);
entry.origin = origin;
DoLog(std::move(entry));
}
protected:
/**
* @brief Underlying implementation to transport the log entry.
*
* Implementations must be thread-safe as DoLog can be called concurrently
* from multiple worker threads.
*/
virtual void DoLog(LogEntry log_entry) = 0;
virtual void Log(LogLevel level, PipelinePhase phase,
std::string_view message) = 0;
};
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_

View File

@@ -1,15 +1,14 @@
#include <chrono>
#include <format>
#include "services/logging/logger.h"
#include <iostream>
#include <optional>
#include <sstream>
#include <string>
#include "data_model/models.h"
#include "services/logging/logger.h"
std::optional<ApplicationOptions> ParseArguments(
const int argc, char** argv, std::shared_ptr<ILogger> logger) {
std::optional<ApplicationOptions> ParseArguments(const int argc, char** argv,
std::shared_ptr<ILogger> logger) {
prog_opts::options_description desc("Pipeline Options");
auto opt = desc.add_options();
@@ -71,12 +70,10 @@ std::optional<ApplicationOptions> ParseArguments(
return usage_stream.str();
})();
if (logger) {
logger->Log(LogDTO{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = title});
logger->Log(LogDTO{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = usage});
logger->Log(LogLevel::Info, PipelinePhase::Startup, title);
logger->Log(LogLevel::Info, PipelinePhase::Startup, usage);
} else {
std::cout << title << std::endl << usage << std::endl;
}
return std::nullopt;
}
@@ -90,9 +87,9 @@ std::optional<ApplicationOptions> ParseArguments(
std::stringstream help_stream;
help_stream << "\n" << desc;
if (logger) {
logger->Log(LogDTO{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = help_stream.str()});
logger->Log(LogLevel::Info, PipelinePhase::Startup, help_stream.str());
} else {
std::cout << help_stream.str() << std::endl;
}
return std::nullopt;
}
@@ -102,7 +99,8 @@ std::optional<ApplicationOptions> ParseArguments(
options.pipeline.output_path = var_map["output"].as<std::string>();
options.pipeline.log_path = var_map["log-path"].as<std::string>();
options.pipeline.prompt_dir = var_map["prompt-dir"].as<std::string>();
options.pipeline.location_count = var_map["location-count"].as<uint32_t>();
options.pipeline.location_count =
var_map["location-count"].as<uint32_t>();
const bool use_mocked = var_map["mocked"].as<bool>();
const std::string model_path = var_map["model"].as<std::string>();
@@ -113,9 +111,7 @@ std::optional<ApplicationOptions> ParseArguments(
const std::string msg =
"Invalid arguments: --mocked and --model are mutually exclusive";
if (logger) {
logger->Log(LogDTO{.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = msg});
logger->Log(LogLevel::Error, PipelinePhase::Startup, msg);
} else {
std::cerr << msg << std::endl;
}
@@ -126,9 +122,7 @@ std::optional<ApplicationOptions> ParseArguments(
const std::string msg =
"Invalid arguments: either --mocked or --model must be specified";
if (logger) {
logger->Log(LogDTO{.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = msg});
logger->Log(LogLevel::Error, PipelinePhase::Startup, msg);
} else {
std::cerr << msg << std::endl;
}
@@ -141,9 +135,7 @@ std::optional<ApplicationOptions> ParseArguments(
const std::string msg =
"Invalid arguments: --prompt-dir is required when not using --mocked";
if (logger) {
logger->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = msg});
logger->Log(LogLevel::Error, PipelinePhase::Startup, msg);
} else {
std::cerr << msg << std::endl;
}
@@ -170,9 +162,7 @@ std::optional<ApplicationOptions> ParseArguments(
const std::string msg =
"Sampling parameters are ignored when using --mocked";
if (logger) {
logger->Log(LogDTO{.level = LogLevel::Warn,
.phase = PipelinePhase::Startup,
.message = msg});
logger->Log(LogLevel::Warn, PipelinePhase::Startup, msg);
} else {
std::cerr << msg << std::endl;
}
@@ -196,18 +186,17 @@ std::optional<ApplicationOptions> ParseArguments(
std::string("Failed to parse command-line arguments: ") +
exception.what();
if (logger) {
logger->Log(LogDTO{.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = msg});
logger->Log(LogLevel::Error, PipelinePhase::Startup, msg);
} else {
std::cerr << msg << std::endl;
}
return std::nullopt;
} catch (...) {
const std::string msg =
"Failed to parse command-line arguments: unknown error";
const std::string msg = "Failed to parse command-line arguments: unknown error";
if (logger) {
logger->Log(LogDTO{.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = msg});
logger->Log(LogLevel::Error, PipelinePhase::Startup, msg);
} else {
std::cerr << msg << std::endl;
}
return std::nullopt;
}

View File

@@ -3,17 +3,13 @@
* @brief BiergartenDataGenerator::GenerateBreweries() implementation.
*/
#include <chrono>
#include <format>
#include "biergarten_pipeline_orchestrator.h"
#include "services/logging/logger.h"
#include "biergarten_pipeline_orchestrator.h"
void BiergartenPipelineOrchestrator::GenerateBreweries(
std::span<const EnrichedCity> cities) {
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message = "=== SAMPLE BREWERY GENERATION ==="});
logger_->Log(LogLevel::Info, PipelinePhase::BreweryAndBeerGeneration,
"=== SAMPLE BREWERY GENERATION ===");
generated_breweries_.clear();
size_t skipped_count = 0;
@@ -33,36 +29,33 @@ void BiergartenPipelineOrchestrator::GenerateBreweries(
} catch (const std::exception& export_exception) {
++export_failed_count;
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message =
std::format("[Pipeline] Generated brewery for '{}' ({}) but SQLite export failed: {}",
location.city, location.country, export_exception.what())});
logger_->Log(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration,
std::string("[Pipeline] Generated brewery for '") +
location.city + "' (" + location.country +
") but SQLite export failed: " +
export_exception.what());
}
} catch (const std::exception& e) {
++skipped_count;
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::format("[Pipeline] Skipping city '{}' ({}): brewery generation failed: {}",
location.city, location.country, e.what())});
logger_->Log(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration,
std::string("[Pipeline] Skipping city '") + location.city +
" (" + location.country + "): brewery generation failed: " +
e.what());
}
}
if (skipped_count > 0) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::format(
"[Pipeline] Skipped {} city/cities due to generation errors",
skipped_count)});
logger_->Log(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration,
std::string("[Pipeline] Skipped ") +
std::to_string(skipped_count) +
" city/cities due to generation errors");
}
if (export_failed_count > 0) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Teardown,
.message = std::format(
"[Pipeline] Failed to export {} generated brewery/breweries to SQLite",
export_failed_count)});
logger_->Log(LogLevel::Warn, PipelinePhase::Teardown,
std::string("[Pipeline] Failed to export ") +
std::to_string(export_failed_count) +
" generated brewery/breweries to SQLite");
}
}

View File

@@ -3,35 +3,29 @@
* @brief BiergartenDataGenerator::LogResults() implementation.
*/
#include <boost/json/array.hpp>
#include <chrono>
#include <format>
#include "../../includes/json_handling/pretty_print.h"
#include "biergarten_pipeline_orchestrator.h"
#include "services/logging/logger.h"
#include "biergarten_pipeline_orchestrator.h"
#include <sstream>
void BiergartenPipelineOrchestrator::LogResults() const {
boost::json::array output;
std::ostringstream msg;
msg << "GENERATED DATA DUMP\n";
size_t index = 1;
for (const auto& [location, brewery] : generated_breweries_) {
output.push_back(boost::json::object{
{"name_en", brewery.name_en},
{"description_en", brewery.description_en},
{"name_local", brewery.name_local},
{"description_local", brewery.description_local},
{"location", boost::json::object{
{"city", location.city},
{"country", location.country},
{"state_province", location.state_province},
{"iso3166_2", location.iso3166_2},
{"latitude", location.latitude},
{"longitude", location.longitude},
}}});
msg << index << ". city=\"" << location.city << "\" country=\""
<< location.country << "\" state=\"" << location.state_province
<< "\" iso3166_2=" << location.iso3166_2 << " lat="
<< location.latitude << " lon=" << location.longitude << "\n";
msg << " brewery_name_en=\"" << brewery.name_en << "\"\n";
msg << " brewery_description_en=\"" << brewery.description_en
<< "\"\n";
msg << " brewery_name_local=\"" << brewery.name_local << "\"\n";
msg << " brewery_description_local=\"" << brewery.description_local
<< "\"\n";
++index;
}
std::ostringstream oss;
PrettyPrint(oss, output);
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Teardown,
.message = oss.str()});
logger_->Log(LogLevel::Debug, PipelinePhase::Teardown, msg.str());
}

View File

@@ -3,8 +3,9 @@
* @brief BiergartenDataGenerator::QueryCitiesWithCountries() implementation.
*/
#include "services/logging/logger.h"
#include <algorithm>
#include <chrono>
#include <filesystem>
#include <format>
#include <iterator>
@@ -12,18 +13,16 @@
#include "biergarten_pipeline_orchestrator.h"
#include "json_handling/json_loader.h"
#include "services/logging/logger.h"
std::vector<Location>
BiergartenPipelineOrchestrator::QueryCitiesWithCountries() {
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "=== GEOGRAPHIC DATA OVERVIEW ==="});
std::vector<Location> BiergartenPipelineOrchestrator::QueryCitiesWithCountries() {
logger_->Log(LogLevel::Info, PipelinePhase::Startup,
"=== GEOGRAPHIC DATA OVERVIEW ===");
const std::filesystem::path locations_path = "locations.json";
auto all_locations = JsonLoader::LoadLocations(locations_path, logger_);
const size_t sample_count = std::min(
static_cast<size_t>(application_options_.pipeline.location_count),
all_locations.size());
@@ -39,13 +38,9 @@ BiergartenPipelineOrchestrator::QueryCitiesWithCountries() {
std::ranges::sample(all_locations, std::back_inserter(sampled_locations),
sample_count_signed, random_generator);
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = std::format(" Locations available: {}",
all_locations.size())});
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = std::format(" Sampled locations: {}",
sampled_locations.size())});
logger_->Log(LogLevel::Info, PipelinePhase::Startup,
std::format(" Locations available: {}", all_locations.size()));
logger_->Log(LogLevel::Info, PipelinePhase::Startup,
std::format(" Sampled locations: {}", sampled_locations.size()));
return sampled_locations;
}

View File

@@ -3,12 +3,11 @@
* @brief BiergartenDataGenerator::Run() implementation.
*/
#include <chrono>
#include <format>
#include "services/logging/logger.h"
#include <utility>
#include "biergarten_pipeline_orchestrator.h"
#include "services/logging/logger.h"
bool BiergartenPipelineOrchestrator::Run() {
try {
@@ -31,21 +30,18 @@ bool BiergartenPipelineOrchestrator::Run() {
.region_context = std::move(region_context)});
} catch (const std::exception& exception) {
++skipped_count;
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::format(
"[Pipeline] Skipping city '{}' ({}): context lookup failed: {}",
city.city, city.country, exception.what())});
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("[Pipeline] Skipping city '") + city.city +
" (" + city.country + "): context lookup failed: " +
exception.what());
}
}
if (skipped_count > 0) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::format(
"[Pipeline] Skipped {} city/cities due to context lookup errors",
skipped_count)});
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("[Pipeline] Skipped ") +
std::to_string(skipped_count) +
" city/cities due to context lookup errors");
}
this->GenerateBreweries(enriched);
@@ -53,11 +49,9 @@ bool BiergartenPipelineOrchestrator::Run() {
this->LogResults();
return true;
} catch (const std::exception& e) {
logger_->Log(
{.level = LogLevel::Error,
.phase = PipelinePhase::Teardown,
.message =
std::format("Pipeline execution failed with error: {}", e.what())});
logger_->Log(LogLevel::Error, PipelinePhase::Teardown,
std::string("Pipeline execution failed with error: ") +
e.what());
return false;
}
}

View File

@@ -4,7 +4,6 @@
* inference, and validates structured JSON output for brewery records.
*/
#include <chrono>
#include <format>
#include <optional>
#include <stdexcept>
@@ -100,11 +99,9 @@ BreweryResult LlamaGenerator::GenerateBrewery(
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)});
logger_->Log(LogLevel::Debug, PipelinePhase::BreweryAndBeerGeneration,
std::string("LlamaGenerator: raw output (attempt ") +
std::to_string(attempt + 1) + "): " + raw);
}
// Validate output: parse JSON and check required fields
@@ -117,11 +114,10 @@ BreweryResult LlamaGenerator::GenerateBrewery(
// 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)});
logger_->Log(LogLevel::Info, PipelinePhase::BreweryAndBeerGeneration,
std::string(
"LlamaGenerator: successfully generated brewery data on attempt ") +
std::to_string(attempt + 1));
}
return brewery;
@@ -131,12 +127,9 @@ BreweryResult LlamaGenerator::GenerateBrewery(
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)});
logger_->Log(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration,
std::string("LlamaGenerator: malformed brewery JSON (attempt ") +
std::to_string(attempt + 1) + "): " + *validation_error);
}
// Update prompt with error details to guide LLM toward correct output.
@@ -155,12 +148,10 @@ BreweryResult LlamaGenerator::GenerateBrewery(
// 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)});
logger_->Log(LogLevel::Error, PipelinePhase::BreweryAndBeerGeneration,
std::string("LlamaGenerator: malformed brewery response after ") +
std::to_string(max_attempts) + " attempts: " +
(last_error.empty() ? raw : last_error));
}
throw std::runtime_error("LlamaGenerator: malformed brewery response");
}

View File

@@ -5,7 +5,6 @@
*/
#include <format>
#include <string>
#include "data_generation/llama_generator.h"
@@ -20,5 +19,5 @@
// 4. Return locale-aware username and biography
UserResult LlamaGenerator::GenerateUser(const std::string& locale) {
return {.username = "test_user",
.bio = std::format("This is a test user profile from {}.", locale)};
.bio = "This is a test user profile from " + locale + "."};
}

View File

@@ -16,11 +16,11 @@
#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) {
@@ -35,7 +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());
@@ -61,37 +61,7 @@ std::string CondenseWhitespace(std::string_view text) {
// 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(const std::array<std::string*, 4>& 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
static constexpr size_t kTruncationGuardDivisor = 2;
/**
* Truncate region context to fit within max length while preserving word
@@ -151,6 +121,47 @@ 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;
@@ -198,7 +209,7 @@ 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)) {

View File

@@ -6,8 +6,6 @@
*/
#include <algorithm>
#include <chrono>
#include <format>
#include <memory>
#include <stdexcept>
#include <string>
@@ -107,7 +105,7 @@ 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)
@@ -172,12 +170,12 @@ 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)});
logger_->Log(
LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration,
std::string("LlamaGenerator: prompt too long (") +
std::to_string(token_count) + ") tokens, truncating to " +
std::to_string(prompt_budget) +
" tokens to fit n_batch/n_ctx limits");
}
prompt_tokens.resize(static_cast<size_t>(prompt_budget));
token_count = prompt_budget;

View File

@@ -5,7 +5,6 @@
*/
#include <algorithm>
#include <chrono>
#include <stdexcept>
#include <string>
#include <utility>
@@ -28,10 +27,8 @@ void LlamaGenerator::Load(const std::string& model_path) {
llama_model_params model_params = llama_model_default_params();
model_params.n_gpu_layers = n_gpu_layers_;
ModelHandle loaded_model(
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);
@@ -41,9 +38,8 @@ void LlamaGenerator::Load(const std::string& model_path) {
context_params.n_ctx = n_ctx_;
context_params.n_batch = std::min(n_ctx_, kMaxBatchSize);
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");
}
@@ -52,9 +48,7 @@ void LlamaGenerator::Load(const std::string& model_path) {
context_ = std::move(loaded_context);
if (logger_) {
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = std::format("[LlamaGenerator] Loaded model: {} ",
model_path)});
logger_->Log(LogLevel::Info, PipelinePhase::Startup,
std::string("[LlamaGenerator] Loaded model: ") + model_path);
}
}

View File

@@ -6,7 +6,6 @@
#include "json_handling/json_loader.h"
#include <format>
#include "services/logging/logger.h"
#include <iostream>
@@ -21,8 +20,8 @@ static std::string ReadRequiredString(const boost::json::object& object,
const char* key) {
const boost::json::value* value = object.if_contains(key);
if (value == nullptr || !value->is_string()) {
throw std::runtime_error(
std::format("Missing or invalid string field: {}", key));
throw std::runtime_error(std::string("Missing or invalid string field: ") +
key);
}
const std::string_view text = value->as_string();
return std::string(text);
@@ -32,8 +31,8 @@ static double ReadRequiredNumber(const boost::json::object& object,
const char* key) {
const boost::json::value* value = object.if_contains(key);
if (value == nullptr || !value->is_number()) {
throw std::runtime_error(
std::format("Missing or invalid numeric field: {}", key));
throw std::runtime_error(std::string("Missing or invalid numeric field: ") +
key);
}
return value->to_number<double>();
}
@@ -43,7 +42,7 @@ static std::vector<std::string> ReadRequiredStringArray(
const boost::json::value* value = object.if_contains(key);
if (value == nullptr || !value->is_array()) {
throw std::runtime_error(
std::format("Missing or invalid string array field: {}", key));
std::string("Missing or invalid string array field: ") + key);
}
const auto& array = value->as_array();
@@ -52,7 +51,7 @@ static std::vector<std::string> ReadRequiredStringArray(
for (const auto& item : array) {
if (!item.is_string()) {
throw std::runtime_error(
std::format("Missing or invalid string array field: {}", key));
std::string("Missing or invalid string array field: ") + key);
}
items.emplace_back(item.as_string());
}

View File

@@ -4,15 +4,11 @@
* initializes shared infrastructure, and executes the pipeline entry flow.
*/
#include <spdlog/fmt/fmt.h>
#include <spdlog/spdlog.h>
#include <boost/di.hpp>
#include <boost/program_options.hpp>
#include <chrono>
#include <exception>
#include <format>
#include <iostream>
#include <memory>
#include <optional>
#include <string>
@@ -46,19 +42,11 @@ int main(const int argc, char** argv) {
spdlog::set_level(spdlog::level::debug);
spdlog::set_pattern("│ %Y-%m-%d %H:%M:%S.%e │ %^%-7l%$ │ %v");
BoundedChannel<LogEntry> log_channel(kLogMaxCount);
auto log_dispatcher = std::make_unique<LogDispatcher>(log_channel);
std::thread log_thread([&log_dispatcher] { log_dispatcher->Run(); });
auto log_dispatcher = //
std::make_unique<LogDispatcher>(log_channel);
std::shared_ptr<ILogger> log_producer =
std::make_shared<LogProducer>(log_channel);
std::thread log_thread([&log_dispatcher] { log_dispatcher->Run(); });
auto shutdown = [&](const int exit_code) {
log_channel.Close();
log_thread.join();
return exit_code;
};
try {
Timer timer;
@@ -66,15 +54,15 @@ int main(const int argc, char** argv) {
const LlamaBackendState llama_backend_state;
#endif
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "STARTING PIPELINE"});
log_producer->Log(LogLevel::Info, PipelinePhase::Startup,
"STARTING PIPELINE");
const std::optional<ApplicationOptions> parsed_options =
ParseArguments(argc, argv, log_producer);
if (!parsed_options.has_value()) {
return shutdown(EXIT_FAILURE);
log_channel.Close();
log_thread.join();
return 0;
}
const auto options = *parsed_options;
@@ -82,79 +70,41 @@ int main(const int argc, char** argv) {
const auto sampling =
options.generator.sampling.value_or(SamplingOptions{});
// -----------------------------------------------------------------------
// Prompt directory
// Conditionally constructed before the injector; moved into LlamaGenerator.
// -----------------------------------------------------------------------
std::unique_ptr<IPromptDirectory> prompt_directory;
if (!options.generator.use_mocked) {
try {
prompt_directory = std::make_unique<PromptDirectory>(
options.pipeline.prompt_dir, log_producer);
} catch (const std::exception& dir_error) {
log_producer->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Startup,
.message = std::format("Invalid --prompt-dir: {}",
dir_error.what())});
return shutdown(EXIT_FAILURE);
log_producer->Log(
LogLevel::Error, PipelinePhase::Startup,
std::string("Invalid --prompt-dir: ") + dir_error.what());
log_channel.Close();
log_thread.join();
return 1;
}
}
// -----------------------------------------------------------------------
// Dependency injection
// -----------------------------------------------------------------------
const auto injector = di::make_injector(
di::bind<ILogger>().to(log_producer),
di::bind<ApplicationOptions>().to(options),
di::bind<std::string>().to(model_path),
di::bind<WebClient>().to<HttpWebClient>(),
di::bind<IExportService>().to<SqliteExportService>(),
di::bind<IPromptFormatter>().to([options, log_producer] {
if (options.generator.use_mocked) {
{
log_producer->Log(
{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Prompt formatter: none (mock mode)"});
}
return std::unique_ptr<IPromptFormatter>(nullptr);
}
{
log_producer->Log(
{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Prompt formatter: Gemma4JinjaPromptFormatter"});
}
return std::unique_ptr<IPromptFormatter>(
std::make_unique<Gemma4JinjaPromptFormatter>());
}),
di::bind<WebClient>().to([options, log_producer] {
if (options.generator.use_mocked) {
{
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Web client: none (mock mode)"});
}
return std::unique_ptr<WebClient>(nullptr);
}
{
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Web client: HttpWebClient"});
}
return std::unique_ptr<WebClient>(
std::make_unique<HttpWebClient>(log_producer));
}),
di::bind<IPromptFormatter>().to<Gemma4JinjaPromptFormatter>(),
di::bind<IEnrichmentService>().to(
[options, &log_producer](
const auto& inj) -> std::unique_ptr<IEnrichmentService> {
if (options.generator.use_mocked) {
{
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Enrichment: mock"});
}
return std::make_unique<MockEnrichmentService>();
}
{
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Enrichment: Wikipedia"});
}
// if (options.generator.use_mocked) {
// return std::make_unique<MockEnrichmentService>();
// }
return std::make_unique<WikipediaEnrichmentService>(
inj.template create<std::unique_ptr<WebClient>>(),
log_producer);
@@ -163,56 +113,57 @@ int main(const int argc, char** argv) {
[&options, &model_path, &sampling, &prompt_directory,
&log_producer](const auto& inj) -> std::unique_ptr<DataGenerator> {
if (options.generator.use_mocked) {
{
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Generator: mock"});
}
log_producer->Log(
LogLevel::Info, PipelinePhase::Startup,
"Using MockGenerator (no model path provided)");
return std::make_unique<MockGenerator>();
}
{
log_producer->Log(
{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = std::format(
"Generator: LlamaGenerator | model={} | temp={:.2f} "
"top_p={:.2f} top_k={} n_ctx={} seed={}",
model_path, sampling.temperature, sampling.top_p,
sampling.top_k, sampling.n_ctx, sampling.seed)});
}
LogLevel::Info, PipelinePhase::Startup,
"Using LlamaGenerator: " + model_path +
" (temperature=" + std::to_string(sampling.temperature) +
", top-p=" + std::to_string(sampling.top_p) +
", top-k=" + std::to_string(sampling.top_k) +
", n_ctx=" + std::to_string(sampling.n_ctx) +
", seed=" + std::to_string(sampling.seed) + ")");
return std::make_unique<LlamaGenerator>(
options, model_path, log_producer,
inj.template create<std::unique_ptr<IPromptFormatter>>(),
std::move(prompt_directory));
}));
// -----------------------------------------------------------------------
// Pipeline execution
// -----------------------------------------------------------------------
const auto orchestrator =
injector.create<std::unique_ptr<BiergartenPipelineOrchestrator>>();
if (!orchestrator->Run()) {
log_producer->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Teardown,
.message = "Pipeline execution failed"});
return shutdown(EXIT_FAILURE);
log_producer->Log(LogLevel::Error, PipelinePhase::Teardown,
"Pipeline execution failed");
log_channel.Close();
log_thread.join();
return 1;
}
log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Teardown,
.message = std::format("Pipeline complete in {} ms",
timer.Elapsed())});
log_producer->Log(LogLevel::Info, PipelinePhase::Teardown,
"Pipeline executed successfully in " +
std::to_string(timer.Elapsed()) + " ms");
return shutdown(EXIT_SUCCESS);
log_channel.Close();
log_thread.join();
return 0;
} catch (const std::exception& exception) {
const LogDTO log_entry{.level = LogLevel::Error,
.phase = PipelinePhase::Teardown,
.message = exception.what()};
// Attempt to use the logging infrastructure; if channel/dispatcher are
// compromised this is a best-effort fallback.
if (log_producer) {
log_producer->Log(log_entry);
} else {
std::cerr << log_entry.message << std::endl;
log_producer->Log(
LogLevel::Error, PipelinePhase::Teardown,
std::string("Unhandled fatal error in main: ") + exception.what());
}
return shutdown(EXIT_FAILURE);
log_channel.Close();
log_thread.join();
return 1;
}
}

View File

@@ -14,15 +14,15 @@
using namespace boost;
std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
const std::string cache_key(query);
// 1. Cache Lookup
if (const auto cache_it = this->extract_cache_.find(cache_key);
cache_it != this->extract_cache_.end()) {
if (logger_) {
logger_->Log({.level = LogLevel::Debug,
.phase = PipelinePhase::UserGeneration,
.message = std::format("Wikipedia: Cache hit for {}!", cache_key)});
logger_->Log(LogLevel::Debug, PipelinePhase::UserGeneration,
std::string("Wikipedia: Cache hit for ") + cache_key + "!");
}
return cache_it->second;
}
@@ -33,6 +33,7 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
"api.php?action=query&titles={}&prop=extracts&explaintext=1&format=json",
encoded);
const std::string body = this->client_->Get(url);
{
using namespace std::literals::chrono_literals;
@@ -45,11 +46,9 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if (ec) {
if (logger_) {
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::format("WikipediaService: JSON parse error for '{}': {}",
std::string(query), ec.message())});
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("WikipediaService: JSON parse error for '") +
std::string(query) + "': " + ec.message());
}
return {};
}
@@ -58,12 +57,9 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
const json::object* obj = doc.if_object();
if (obj == nullptr) {
if (logger_) {
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message =
std::format("WikipediaService: Expected root object for '{}'",
std::string(query))});
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("WikipediaService: Expected root object for '") +
std::string(query) + "'");
}
return {};
}
@@ -76,12 +72,9 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if ((pages_ptr == nullptr) || !pages_ptr->is_object()) {
if (logger_) {
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message =
std::format("WikipediaService: Missing query.pages for '{}'",
std::string(query))});
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("WikipediaService: Missing query.pages for '") +
std::string(query) + "'");
}
return {};
}
@@ -90,11 +83,9 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if (pages.empty()) {
if (logger_) {
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::format("WikipediaService: No pages returned for '{}'",
std::string(query))});
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("WikipediaService: No pages returned for '") +
std::string(query) + "'");
}
this->extract_cache_.emplace(cache_key, "");
return {};
@@ -106,12 +97,9 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if (!page_val.is_object()) {
if (logger_) {
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message =
std::format("WikipediaService: Unexpected page format for '{}'",
std::string(query))});
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("WikipediaService: Unexpected page format for '") +
std::string(query) + "'");
}
return {};
}
@@ -121,10 +109,9 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
// Handle 404/Missing status
if (page.contains("missing")) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = std::format("WikipediaService: Page '{}' does not exist",
std::string(query))});
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("WikipediaService: Page '") + std::string(query) +
"' does not exist");
}
this->extract_cache_.emplace(cache_key, "");
return {};
@@ -134,12 +121,9 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if ((extract_ptr == nullptr) || !extract_ptr->is_string()) {
if (logger_) {
logger_->Log(
{.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message =
std::format("WikipediaService: No extract string found for '{}'",
std::string(query))});
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
std::string("WikipediaService: No extract string found for '") +
std::string(query) + "'");
}
this->extract_cache_.emplace(cache_key, "");
return {};
@@ -148,10 +132,10 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
// 4. Success
std::string extract(extract_ptr->as_string());
if (logger_) {
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::UserGeneration,
.message = std::format("WikipediaService: Fetched {} chars for '{}'",
extract.size(), std::string(query))});
logger_->Log(LogLevel::Info, PipelinePhase::UserGeneration,
std::string("WikipediaService: Fetched ") +
std::to_string(extract.size()) + " chars for '" +
std::string(query) + "'");
}
this->extract_cache_.insert_or_assign(cache_key, extract);

View File

@@ -10,14 +10,12 @@
#include "services/enrichment/wikipedia_service.h"
std::string WikipediaEnrichmentService::GetLocationContext(
const Location& loc) {
std::string WikipediaEnrichmentService::GetLocationContext(const Location& loc) {
using namespace std::literals::chrono_literals;
if (!this->client_) {
if (logger_) {
logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration,
.message = "Wikipedia client is nullptr."});
logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration,
"Wikipedia client is nullptr.");
}
return {};
}
@@ -50,20 +48,17 @@ std::string WikipediaEnrichmentService::GetLocationContext(
append_extract(FetchExtract(brewing_query));
append_extract(FetchExtract(beer_query));
if (logger_) {
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::UserGeneration,
.message = std::format("Done fetching for {}. Sleeping for 10 seconds.",
location_query)});
logger_->Log(LogLevel::Info, PipelinePhase::UserGeneration,
std::string("Done fetching for ") + location_query +
". Sleeping for 10 seconds.");
}
std::this_thread::sleep_for(10s);
} catch (const std::runtime_error& e) {
if (logger_) {
logger_->Log(
{.level = LogLevel::Debug,
.phase = PipelinePhase::UserGeneration,
.message = std::format("WikipediaService lookup failed for '{}': {}",
location_query, e.what())});
logger_->Log(LogLevel::Debug, PipelinePhase::UserGeneration,
std::string("WikipediaService lookup failed for '") +
location_query + "': " + e.what());
}
}
return result;

View File

@@ -13,29 +13,6 @@
#include "concurrency/bounded_channel.h"
#include "services/logging/log_entry.h"
namespace {
[[nodiscard]] constexpr std::string_view PipelinePhaseToString(
PipelinePhase phase) {
switch (phase) {
case PipelinePhase::Startup:
return "Startup";
case PipelinePhase::UserGeneration:
return "User Generation";
case PipelinePhase::BreweryAndBeerGeneration:
return "Brewery & Beer Gen";
case PipelinePhase::CheckinGeneration:
return "Checkin Gen";
case PipelinePhase::RatingGeneration:
return "Rating Gen";
case PipelinePhase::FollowGeneration:
return "Follow Gen";
case PipelinePhase::Teardown:
return "Teardown";
}
return "Unknown";
}
} // namespace
LogDispatcher::LogDispatcher(BoundedChannel<LogEntry>& channel)
: channel_(channel) {}
@@ -51,11 +28,7 @@ void LogDispatcher::Run() {
const auto& log = entry.value();
logger->log(ToSpdlogLevel(log.level),
"{:<20} │ thread: {:016x} │ [{}:{}] │ {}",
PipelinePhaseToString(log.phase),
std::hash<std::thread::id>{}(log.thread_id),
log.origin.file_name(), log.origin.line(), log.message);
logger->log(ToSpdlogLevel(log.level), log.message);
}
}

View File

@@ -16,4 +16,10 @@
LogProducer::LogProducer(BoundedChannel<LogEntry>& channel)
: channel_(channel) {}
void LogProducer::DoLog(LogEntry entry) { channel_.Send(std::move(entry)); }
void LogProducer::Log(LogLevel level, PipelinePhase phase,
const std::string_view message) {
channel_.Send(LogEntry{.timestamp = std::chrono::system_clock::now(),
.level = level,
.phase = phase,
.message = std::string(message)});
}

View File

@@ -6,9 +6,7 @@
#include "services/prompting/prompt_directory.h"
#include <chrono>
#include <filesystem>
#include <format>
#include <fstream>
#include <stdexcept>
#include <string>
@@ -45,17 +43,14 @@ PromptDirectory::PromptDirectory(const std::filesystem::path& prompt_dir,
std::filesystem::directory_iterator probe(prompt_dir_, ec);
if (ec) {
throw std::runtime_error(
std::format("PromptDirectory: prompt directory is not readable: {} ({})",
prompt_dir_.string(), ec.message()));
"PromptDirectory: prompt directory is not readable: " +
prompt_dir_.string() + " (" + ec.message() + ")");
}
if (logger_) {
logger_->Log(
{.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message =
logger_->Log(LogLevel::Info, PipelinePhase::Startup,
std::string("[PromptDirectory] Resolved prompt directory: ") +
prompt_dir_.string()});
prompt_dir_.string());
}
}
@@ -70,13 +65,13 @@ std::string PromptDirectory::Load(std::string_view key) {
// Scenario 3: resolve <prompt_dir>/<key>.md and require it to exist.
const std::filesystem::path file_path =
prompt_dir_ / std::filesystem::path(std::format("{}.md", key_str));
prompt_dir_ / std::filesystem::path(key_str + ".md");
std::ifstream file(file_path);
if (!file.is_open()) {
throw std::runtime_error(
std::format("PromptDirectory: prompt file not found for key '{}': {}",
key_str, file_path.string()));
"PromptDirectory: prompt file not found for key '" + key_str +
"': " + file_path.string());
}
std::string content((std::istreambuf_iterator<char>(file)),
@@ -84,15 +79,15 @@ std::string PromptDirectory::Load(std::string_view key) {
file.close();
if (content.empty()) {
throw std::runtime_error(std::format("PromptDirectory: prompt file for key '{}' is empty: {}",
key_str, file_path.string()));
throw std::runtime_error("PromptDirectory: prompt file for key '" +
key_str + "' is empty: " + file_path.string());
}
if (logger_) {
logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = std::format("[PromptDirectory] Loaded prompt '{}' from '{}' ({} chars)",
key_str, file_path.string(), content.size())});
logger_->Log(LogLevel::Info, PipelinePhase::Startup,
std::string("[PromptDirectory] Loaded prompt '") + key_str +
"' from '" + file_path.string() + "' (" +
std::to_string(content.size()) + " chars)");
}
cache_.emplace(key_str, content);

View File

@@ -1,6 +1,5 @@
#include "services/database/sqlite_connection_helpers.h"
#include <format>
#include <stdexcept>
namespace sqlite_export_service_internal {
@@ -21,7 +20,7 @@ void SqliteStatementDeleter::operator()(
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::format("{}: {}", action, message));
throw std::runtime_error(std::string(action) + ": " + message);
}
SqliteDatabaseHandle OpenDatabase(const std::filesystem::path& path) {
@@ -51,7 +50,7 @@ void ExecSql(const SqliteDatabaseHandle& db_handle, std::string_view sql,
? error_message
: sqlite3_errmsg(db_handle.get());
sqlite3_free(error_message);
throw std::runtime_error(std::format("{}: {}", action, message));
throw std::runtime_error(std::string(action) + ": " + message);
}
}

View File

@@ -4,7 +4,6 @@
*/
#include <filesystem>
#include <format>
#include <memory>
#include <stdexcept>
#include <string>
@@ -19,8 +18,8 @@ std::filesystem::path SqliteExportService::BuildDatabasePath() const {
for (int suffix = 1; std::filesystem::exists(candidate); ++suffix) {
candidate = output_path_ /
std::filesystem::path(std::format("biergarten_seed_{}-{}.sqlite",
run_timestamp_utc_, suffix));
std::filesystem::path("biergarten_seed_" + run_timestamp_utc_ +
"-" + std::to_string(suffix) + ".sqlite");
}
return candidate;

View File

@@ -7,8 +7,6 @@
#include <httplib.h>
#include <chrono>
#include <format>
#include <regex>
#include <stdexcept>
#include <string>
@@ -42,27 +40,28 @@ std::string HttpWebClient::Get(const std::string& url) {
client.set_follow_location(true);
client.set_connection_timeout(kConnectionTimeoutSeconds);
client.set_read_timeout(kReadTimeoutSeconds);
client.set_default_headers({{"Accept", "application/json"},
{"User-Agent", "biergarten-pipeline/1.0"}});
client.set_default_headers({
{"Accept", "application/json"},
{"User-Agent", "biergarten-pipeline/1.0"}
});
const httplib::Result result = client.Get(path);
if (!result) {
throw std::runtime_error(std::format(
"[HttpWebClient] Request failed for URL: {} — {}", url,
httplib::to_string(result.error())));
throw std::runtime_error(
"[HttpWebClient] Request failed for URL: " + url +
"" + httplib::to_string(result.error()));
}
if (result->status < kSuccessMin || result->status >= kSuccessMax) {
if (logger_) {
logger_->Log(
{.level = LogLevel::Error,
.phase = PipelinePhase::UserGeneration,
.message =
std::format("[HttpWebClient] Request failed for URL: {}", url)});
logger_->Log(LogLevel::Error, PipelinePhase::UserGeneration,
std::string("[HttpWebClient] Request failed for URL: ") +
url);
}
throw std::runtime_error(std::format("[HttpWebClient] HTTP {} for URL: {}",
result->status, url));
throw std::runtime_error(
"[HttpWebClient] HTTP " + std::to_string(result->status) +
" for URL: " + url);
}
return result->body;