8 Commits

Author SHA1 Message Date
Aaron Po
366cb99e1d logging updates 2026-05-17 02:58:47 -04:00
Aaron Po
5d80b53351 Update main.cc 2026-05-17 01:29:32 -04:00
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
29 changed files with 255 additions and 484 deletions

View File

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

View File

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

View File

@@ -138,8 +138,7 @@ FetchContent_MakeAvailable(cpp-httplib)
# 5. Executable & Sources # 5. Executable & Sources
add_executable(${PROJECT_NAME} add_executable(${PROJECT_NAME}
includes/services/enrichment/mock_enrichment.h includes/services/enrichment/mock_enrichment.h)
includes/json_handling/pretty_print.h)
# --- Entry point --- # --- Entry point ---
target_sources(${PROJECT_NAME} PRIVATE target_sources(${PROJECT_NAME} PRIVATE
@@ -249,11 +248,6 @@ target_compile_definitions(${PROJECT_NAME} PRIVATE
$<$<CONFIG:Debug>:DEBUG> $<$<CONFIG:Debug>:DEBUG>
) )
target_compile_options(biergarten-pipeline PRIVATE
-fmacro-prefix-map=${CMAKE_SOURCE_DIR}/tooling/pipeline/src/=
)
# 7. Runtime Assets # 7. Runtime Assets
configure_file( configure_file(
${CMAKE_SOURCE_DIR}/locations.json ${CMAKE_SOURCE_DIR}/locations.json
@@ -265,4 +259,3 @@ add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD
${CMAKE_SOURCE_DIR}/prompts ${CMAKE_SOURCE_DIR}/prompts
${CMAKE_BINARY_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 * 2. Resolve context for each city using the injected context service
* 3. Generate brewery data for sampled cities * 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 * @return true if successful, false if not
*/ */
bool Run(); bool Run();

View File

@@ -38,7 +38,8 @@ class LlamaGenerator final : public DataGenerator {
* @param prompt_directory Directory service for loading named prompt files. * @param prompt_directory Directory service for loading named prompt files.
*/ */
LlamaGenerator(const ApplicationOptions& options, 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<IPromptFormatter> prompt_formatter,
std::unique_ptr<IPromptDirectory> prompt_directory); 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. * them to spdlog on a dedicated thread.
*/ */
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_ #ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_CONSUMER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_ #define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_CONSUMER_H_
#include <spdlog/spdlog.h> #include <spdlog/spdlog.h>
@@ -23,31 +23,31 @@
*/ */
class LogDispatcher { class LogDispatcher {
public: public:
/** /**
* @brief Construct a log dispatcher. * @brief Construct a log dispatcher.
* *
* @param channel Reference to the bounded channel used for log retrieval. * @param channel Reference to the bounded channel used for log retrieval.
*/ */
explicit LogDispatcher(BoundedChannel<LogEntry>& channel); explicit LogDispatcher(BoundedChannel<LogEntry>& channel);
LogDispatcher(const LogDispatcher&) = delete; LogDispatcher(const LogDispatcher&) = delete;
LogDispatcher& operator=(const LogDispatcher&) = delete; LogDispatcher& operator=(const LogDispatcher&) = delete;
LogDispatcher(LogDispatcher&&) = delete; LogDispatcher(LogDispatcher&&) = delete;
LogDispatcher& operator=(LogDispatcher&&) = delete; LogDispatcher& operator=(LogDispatcher&&) = delete;
~LogDispatcher() = default; ~LogDispatcher() = default;
/** /**
* @brief Drain the channel and forward entries to spdlog. * @brief Drain the channel and forward entries to spdlog.
* *
* Intended to be called once on a dedicated thread. The loop returns after * Intended to be called once on a dedicated thread. The loop returns after
* the channel has been closed and all queued entries have been processed. * the channel has been closed and all queued entries have been processed.
*/ */
void Run(); void Run();
private: private:
BoundedChannel<LogEntry>& channel_; BoundedChannel<LogEntry>& channel_;
static spdlog::level::level_enum ToSpdlogLevel(LogLevel level); 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_ #define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
#include <chrono> #include <chrono>
#include <source_location>
#include <string>
#include <thread> #include <thread>
#include <vector> #include <string>
/** /**
* @enum LogLevel * @enum LogLevel
@@ -43,35 +41,17 @@ enum class PipelinePhase {
Teardown, ///< Finalization and cleanup. 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 * @struct LogEntry
* @brief Single structured log event. * @brief Single structured log event.
* *
* All fields are value types, which keeps transfer across the bounded channel * All fields are value types, which keeps transfer across the bounded channel
* simple and avoids shared ownership. * simple and avoids shared ownership.
*
* NOTE: timestamp, thread_id, and origin must be populated by ILogger::Log()
* before the entry is dispatched.
*/ */
struct LogEntry { struct LogEntry {
/// @brief Timestamp when the entry was created. /// @brief Timestamp when the entry was created.
std::chrono::system_clock::time_point timestamp{}; std::chrono::system_clock::time_point timestamp =
std::chrono::system_clock::now();
/// @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{};
/// @brief Severity level of this entry. /// @brief Severity level of this entry.

View File

@@ -41,10 +41,9 @@ class LogProducer final : public ILogger {
/** /**
* @brief Queue a log message for asynchronous processing. * @brief Queue a log message for asynchronous processing.
* *
* Blocks while the channel applies backpressure. This blocking behavior * Blocks while the channel applies backpressure.
* under heavy load is an accepted trade-off for simplicity.
*/ */
void DoLog(LogEntry log_entry) override; void Log(LogEntry const& entry) override;
private: private:
BoundedChannel<LogEntry>& channel_; BoundedChannel<LogEntry>& channel_;

View File

@@ -9,9 +9,9 @@
#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_ #ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_ #define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
#include <source_location> #include <optional>
#include <string> #include <string>
#include <utility> #include <string_view>
#include "services/logging/log_entry.h" #include "services/logging/log_entry.h"
@@ -34,31 +34,10 @@ class ILogger {
/** /**
* @brief Submit a log message to the logging subsystem. * @brief Submit a log message to the logging subsystem.
* *
* @param payload User-provided log data (level, phase, message). * @param entry Structured log record containing message and metadata.
* @param origin Auto-captured source location of the call site.
*/
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(const LogEntry& entry) = 0;
}; };
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_ #endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_

View File

@@ -1,5 +1,4 @@
#include <chrono> #include <chrono>
#include <format>
#include <iostream> #include <iostream>
#include <optional> #include <optional>
#include <sstream> #include <sstream>
@@ -71,12 +70,14 @@ std::optional<ApplicationOptions> ParseArguments(
return usage_stream.str(); return usage_stream.str();
})(); })();
if (logger) { if (logger) {
logger->Log(LogDTO{.level = LogLevel::Info, logger->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = title}); .message = title});
logger->Log(LogDTO{.level = LogLevel::Info, logger->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = usage}); .message = usage});
} else {
std::cout << title << std::endl << usage << std::endl;
} }
return std::nullopt; return std::nullopt;
} }
@@ -90,9 +91,11 @@ std::optional<ApplicationOptions> ParseArguments(
std::stringstream help_stream; std::stringstream help_stream;
help_stream << "\n" << desc; help_stream << "\n" << desc;
if (logger) { if (logger) {
logger->Log(LogDTO{.level = LogLevel::Info, logger->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = help_stream.str()}); .message = help_stream.str()});
} else {
std::cout << help_stream.str() << std::endl;
} }
return std::nullopt; return std::nullopt;
} }
@@ -113,7 +116,7 @@ std::optional<ApplicationOptions> ParseArguments(
const std::string msg = const std::string msg =
"Invalid arguments: --mocked and --model are mutually exclusive"; "Invalid arguments: --mocked and --model are mutually exclusive";
if (logger) { if (logger) {
logger->Log(LogDTO{.level = LogLevel::Error, logger->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = msg}); .message = msg});
} else { } else {
@@ -126,7 +129,7 @@ std::optional<ApplicationOptions> ParseArguments(
const std::string msg = const std::string msg =
"Invalid arguments: either --mocked or --model must be specified"; "Invalid arguments: either --mocked or --model must be specified";
if (logger) { if (logger) {
logger->Log(LogDTO{.level = LogLevel::Error, logger->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = msg}); .message = msg});
} else { } else {
@@ -170,7 +173,7 @@ std::optional<ApplicationOptions> ParseArguments(
const std::string msg = const std::string msg =
"Sampling parameters are ignored when using --mocked"; "Sampling parameters are ignored when using --mocked";
if (logger) { if (logger) {
logger->Log(LogDTO{.level = LogLevel::Warn, logger->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = msg}); .message = msg});
} else { } else {
@@ -196,18 +199,22 @@ std::optional<ApplicationOptions> ParseArguments(
std::string("Failed to parse command-line arguments: ") + std::string("Failed to parse command-line arguments: ") +
exception.what(); exception.what();
if (logger) { if (logger) {
logger->Log(LogDTO{.level = LogLevel::Error, logger->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = msg}); .message = msg});
} else {
std::cerr << msg << std::endl;
} }
return std::nullopt; return std::nullopt;
} catch (...) { } catch (...) {
const std::string msg = const std::string msg =
"Failed to parse command-line arguments: unknown error"; "Failed to parse command-line arguments: unknown error";
if (logger) { if (logger) {
logger->Log(LogDTO{.level = LogLevel::Error, logger->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = msg}); .message = msg});
} else {
std::cerr << msg << std::endl;
} }
return std::nullopt; return std::nullopt;
} }

View File

@@ -4,7 +4,6 @@
*/ */
#include <chrono> #include <chrono>
#include <format>
#include "biergarten_pipeline_orchestrator.h" #include "biergarten_pipeline_orchestrator.h"
#include "services/logging/logger.h" #include "services/logging/logger.h"
@@ -37,32 +36,34 @@ void BiergartenPipelineOrchestrator::GenerateBreweries(
{.level = LogLevel::Warn, {.level = LogLevel::Warn,
.phase = PipelinePhase::BreweryAndBeerGeneration, .phase = PipelinePhase::BreweryAndBeerGeneration,
.message = .message =
std::format("[Pipeline] Generated brewery for '{}' ({}) but SQLite export failed: {}", std::string("[Pipeline] Generated brewery for '") +
location.city, location.country, export_exception.what())}); location.city + "' (" + location.country +
") but SQLite export failed: " + export_exception.what()});
} }
} catch (const std::exception& e) { } catch (const std::exception& e) {
++skipped_count; ++skipped_count;
logger_->Log({.level = LogLevel::Warn, logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::BreweryAndBeerGeneration, .phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::format("[Pipeline] Skipping city '{}' ({}): brewery generation failed: {}", .message = std::string("[Pipeline] Skipping city '") +
location.city, location.country, e.what())}); location.city + " (" + location.country +
"): brewery generation failed: " + e.what()});
} }
} }
if (skipped_count > 0) { if (skipped_count > 0) {
logger_->Log({.level = LogLevel::Warn, logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::BreweryAndBeerGeneration, .phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::format( .message = std::string("[Pipeline] Skipped ") +
"[Pipeline] Skipped {} city/cities due to generation errors", std::to_string(skipped_count) +
skipped_count)}); " city/cities due to generation errors"});
} }
if (export_failed_count > 0) { if (export_failed_count > 0) {
logger_->Log({.level = LogLevel::Warn, logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::Teardown, .phase = PipelinePhase::Teardown,
.message = std::format( .message = std::string("[Pipeline] Failed to export ") +
"[Pipeline] Failed to export {} generated brewery/breweries to SQLite", std::to_string(export_failed_count) +
export_failed_count)}); " generated brewery/breweries to SQLite"});
} }
} }

View File

@@ -3,35 +3,31 @@
* @brief BiergartenDataGenerator::LogResults() implementation. * @brief BiergartenDataGenerator::LogResults() implementation.
*/ */
#include <boost/json/array.hpp>
#include <chrono> #include <chrono>
#include <format> #include <sstream>
#include "../../includes/json_handling/pretty_print.h"
#include "biergarten_pipeline_orchestrator.h" #include "biergarten_pipeline_orchestrator.h"
#include "services/logging/logger.h" #include "services/logging/logger.h"
void BiergartenPipelineOrchestrator::LogResults() const {
boost::json::array output;
void BiergartenPipelineOrchestrator::LogResults() const {
std::ostringstream msg;
msg << "GENERATED DATA DUMP\n";
size_t index = 1;
for (const auto& [location, brewery] : generated_breweries_) { for (const auto& [location, brewery] : generated_breweries_) {
output.push_back(boost::json::object{ msg << index << ". city=\"" << location.city << "\" country=\""
{"name_en", brewery.name_en}, << location.country << "\" state=\"" << location.state_province
{"description_en", brewery.description_en}, << "\" iso3166_2=" << location.iso3166_2 << " lat=" << location.latitude
{"name_local", brewery.name_local}, << " lon=" << location.longitude << "\n";
{"description_local", brewery.description_local},
{"location", boost::json::object{ msg << " brewery_name_en=\"" << brewery.name_en << "\"\n";
{"city", location.city}, msg << " brewery_description_en=\"" << brewery.description_en << "\"\n";
{"country", location.country}, msg << " brewery_name_local=\"" << brewery.name_local << "\"\n";
{"state_province", location.state_province}, msg << " brewery_description_local=\"" << brewery.description_local
{"iso3166_2", location.iso3166_2}, << "\"\n";
{"latitude", location.latitude}, ++index;
{"longitude", location.longitude},
}}});
} }
std::ostringstream oss;
PrettyPrint(oss, output);
logger_->Log({.level = LogLevel::Info, logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Teardown, .phase = PipelinePhase::Teardown,
.message = oss.str()}); .message = msg.str()});
} }

View File

@@ -4,7 +4,6 @@
*/ */
#include <chrono> #include <chrono>
#include <format>
#include <utility> #include <utility>
#include "biergarten_pipeline_orchestrator.h" #include "biergarten_pipeline_orchestrator.h"
@@ -34,18 +33,18 @@ bool BiergartenPipelineOrchestrator::Run() {
logger_->Log( logger_->Log(
{.level = LogLevel::Warn, {.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration, .phase = PipelinePhase::UserGeneration,
.message = std::format( .message = std::string("[Pipeline] Skipping city '") + city.city +
"[Pipeline] Skipping city '{}' ({}): context lookup failed: {}", " (" + city.country +
city.city, city.country, exception.what())}); "): context lookup failed: " + exception.what()});
} }
} }
if (skipped_count > 0) { if (skipped_count > 0) {
logger_->Log({.level = LogLevel::Warn, logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration, .phase = PipelinePhase::UserGeneration,
.message = std::format( .message = std::string("[Pipeline] Skipped ") +
"[Pipeline] Skipped {} city/cities due to context lookup errors", std::to_string(skipped_count) +
skipped_count)}); " city/cities due to context lookup errors"});
} }
this->GenerateBreweries(enriched); this->GenerateBreweries(enriched);
@@ -57,7 +56,7 @@ bool BiergartenPipelineOrchestrator::Run() {
{.level = LogLevel::Error, {.level = LogLevel::Error,
.phase = PipelinePhase::Teardown, .phase = PipelinePhase::Teardown,
.message = .message =
std::format("Pipeline execution failed with error: {}", e.what())}); std::string("Pipeline execution failed with error: ") + e.what()});
return false; return false;
} }
} }

View File

@@ -103,8 +103,8 @@ BreweryResult LlamaGenerator::GenerateBrewery(
logger_->Log( logger_->Log(
{.level = LogLevel::Debug, {.level = LogLevel::Debug,
.phase = PipelinePhase::BreweryAndBeerGeneration, .phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::format("LlamaGenerator: raw output (attempt {}): {}", .message = std::string("LlamaGenerator: raw output (attempt ") +
attempt + 1, raw)}); std::to_string(attempt + 1) + "): " + raw});
} }
// Validate output: parse JSON and check required fields // Validate output: parse JSON and check required fields
@@ -120,8 +120,9 @@ BreweryResult LlamaGenerator::GenerateBrewery(
logger_->Log( logger_->Log(
{.level = LogLevel::Info, {.level = LogLevel::Info,
.phase = PipelinePhase::BreweryAndBeerGeneration, .phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::format("LlamaGenerator: successfully generated brewery data on attempt {}", .message = std::string("LlamaGenerator: successfully generated "
attempt + 1)}); "brewery data on attempt ") +
std::to_string(attempt + 1)});
} }
return brewery; return brewery;
@@ -135,8 +136,8 @@ BreweryResult LlamaGenerator::GenerateBrewery(
{.level = LogLevel::Warn, {.level = LogLevel::Warn,
.phase = PipelinePhase::BreweryAndBeerGeneration, .phase = PipelinePhase::BreweryAndBeerGeneration,
.message = .message =
std::format("LlamaGenerator: malformed brewery JSON (attempt {}): {}", std::string("LlamaGenerator: malformed brewery JSON (attempt ") +
attempt + 1, *validation_error)}); std::to_string(attempt + 1) + "): " + *validation_error});
} }
// Update prompt with error details to guide LLM toward correct output. // Update prompt with error details to guide LLM toward correct output.
@@ -158,9 +159,10 @@ BreweryResult LlamaGenerator::GenerateBrewery(
logger_->Log( logger_->Log(
{.level = LogLevel::Error, {.level = LogLevel::Error,
.phase = PipelinePhase::BreweryAndBeerGeneration, .phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::format( .message =
"LlamaGenerator: malformed brewery response after {} attempts: {}", std::string("LlamaGenerator: malformed brewery response after ") +
max_attempts, last_error.empty() ? raw : last_error)}); std::to_string(max_attempts) +
" attempts: " + (last_error.empty() ? raw : last_error)});
} }
throw std::runtime_error("LlamaGenerator: malformed brewery response"); throw std::runtime_error("LlamaGenerator: malformed brewery response");
} }

View File

@@ -5,7 +5,6 @@
*/ */
#include <format>
#include <string> #include <string>
#include "data_generation/llama_generator.h" #include "data_generation/llama_generator.h"
@@ -20,5 +19,5 @@
// 4. Return locale-aware username and biography // 4. Return locale-aware username and biography
UserResult LlamaGenerator::GenerateUser(const std::string& locale) { UserResult LlamaGenerator::GenerateUser(const std::string& locale) {
return {.username = "test_user", 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 "data_generation/llama_generator_helpers.h"
#include "llama.h" #include "llama.h"
namespace {
/** /**
* String trimming: removes leading and trailing whitespace * 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"; constexpr std::string_view whitespace = " \t\n\r\f\v";
const size_t first_index = value.find_first_not_of(whitespace); const size_t first_index = value.find_first_not_of(whitespace);
if (first_index == std::string_view::npos) { 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 * Normalize whitespace: collapses multiple spaces/tabs/newlines into single
* spaces * spaces
*/ */
std::string CondenseWhitespace(std::string_view text) { static std::string CondenseWhitespace(std::string_view text) {
std::string out; std::string out;
out.reserve(text.size()); 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. // Guard against truncating in the first half of the string.
// This preserves the critical opening content and avoids cutting critical // This preserves the critical opening content and avoids cutting critical
// context words early in the region description. // context words early in the region description.
constexpr size_t kTruncationGuardDivisor = 2; static 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
/** /**
* Truncate region context to fit within max length while preserving word * 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"); "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, std::optional<std::string> ValidateBreweryJson(const std::string& raw,
BreweryResult& brewery_out) { BreweryResult& brewery_out) {
boost::system::error_code error_code; boost::system::error_code error_code;
@@ -198,7 +209,7 @@ std::optional<std::string> ValidateBreweryJson(const std::string& raw,
return validation_error; 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_en, &brewery_out.description_en,
&brewery_out.name_local, &brewery_out.description_local}; &brewery_out.name_local, &brewery_out.description_local};
if (HasSchemaPlaceholder(schema_placeholders)) { if (HasSchemaPlaceholder(schema_placeholders)) {

View File

@@ -7,7 +7,6 @@
#include <algorithm> #include <algorithm>
#include <chrono> #include <chrono>
#include <format>
#include <memory> #include <memory>
#include <stdexcept> #include <stdexcept>
#include <string> #include <string>
@@ -107,7 +106,7 @@ std::string LlamaGenerator::InferFormatted(const std::string& formatted_prompt,
.top_p = sampling_top_p_, .top_p = sampling_top_p_,
.seed = static_cast<uint32_t>(rng_()), .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) * Clear KV cache to ensure clean inference state (no residual context)
@@ -172,12 +171,13 @@ std::string LlamaGenerator::InferFormatted(const std::string& formatted_prompt,
prompt_tokens.resize(static_cast<size_t>(token_count)); prompt_tokens.resize(static_cast<size_t>(token_count));
if (token_count > prompt_budget) { if (token_count > prompt_budget) {
if (logger_) { if (logger_) {
logger_->Log({.level = LogLevel::Warn, logger_->Log(
.phase = PipelinePhase::BreweryAndBeerGeneration, {.level = LogLevel::Warn,
.message = std::format( .phase = PipelinePhase::BreweryAndBeerGeneration,
"LlamaGenerator: prompt too long ({} tokens), " .message = std::string("LlamaGenerator: prompt too long (") +
"truncating to {} tokens to fit n_batch/n_ctx limits", std::to_string(token_count) + ") tokens, truncating to " +
token_count, prompt_budget)}); std::to_string(prompt_budget) +
" tokens to fit n_batch/n_ctx limits"});
} }
prompt_tokens.resize(static_cast<size_t>(prompt_budget)); prompt_tokens.resize(static_cast<size_t>(prompt_budget));
token_count = prompt_budget; token_count = prompt_budget;

View File

@@ -28,10 +28,8 @@ void LlamaGenerator::Load(const std::string& model_path) {
llama_model_params model_params = llama_model_default_params(); llama_model_params model_params = llama_model_default_params();
model_params.n_gpu_layers = n_gpu_layers_; model_params.n_gpu_layers = n_gpu_layers_;
LlamaGenerator::ModelHandle loaded_model(
ModelHandle loaded_model(
llama_model_load_from_file(model_path.c_str(), model_params)); llama_model_load_from_file(model_path.c_str(), model_params));
if (!loaded_model) { if (!loaded_model) {
throw std::runtime_error( throw std::runtime_error(
"LlamaGenerator: failed to load model from path: " + model_path); "LlamaGenerator: failed to load model from path: " + model_path);
@@ -41,9 +39,8 @@ void LlamaGenerator::Load(const std::string& model_path) {
context_params.n_ctx = n_ctx_; context_params.n_ctx = n_ctx_;
context_params.n_batch = std::min(n_ctx_, kMaxBatchSize); 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)); llama_init_from_model(loaded_model.get(), context_params));
if (!loaded_context) { if (!loaded_context) {
throw std::runtime_error("LlamaGenerator: failed to create context"); throw std::runtime_error("LlamaGenerator: failed to create context");
} }
@@ -54,7 +51,7 @@ void LlamaGenerator::Load(const std::string& model_path) {
if (logger_) { if (logger_) {
logger_->Log({.level = LogLevel::Info, logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = std::format("[LlamaGenerator] Loaded model: {} ", .message = std::string("[LlamaGenerator] Loaded model: ") +
model_path)}); model_path});
} }
} }

View File

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

View File

@@ -12,7 +12,6 @@
#include <chrono> #include <chrono>
#include <exception> #include <exception>
#include <format> #include <format>
#include <iostream>
#include <memory> #include <memory>
#include <optional> #include <optional>
#include <string> #include <string>
@@ -66,15 +65,15 @@ int main(const int argc, char** argv) {
const LlamaBackendState llama_backend_state; const LlamaBackendState llama_backend_state;
#endif #endif
log_producer->Log({.level = LogLevel::Info, log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = "STARTING PIPELINE"}); .message = "STARTING PIPELINE"});
const std::optional<ApplicationOptions> parsed_options = const std::optional<ApplicationOptions> parsed_options =
ParseArguments(argc, argv, log_producer); ParseArguments(argc, argv, log_producer);
if (!parsed_options.has_value()) { if (!parsed_options.has_value()) {
return shutdown(EXIT_FAILURE); return shutdown(0);
} }
const auto options = *parsed_options; const auto options = *parsed_options;
@@ -89,12 +88,12 @@ int main(const int argc, char** argv) {
prompt_directory = std::make_unique<PromptDirectory>( prompt_directory = std::make_unique<PromptDirectory>(
options.pipeline.prompt_dir, log_producer); options.pipeline.prompt_dir, log_producer);
} catch (const std::exception& dir_error) { } catch (const std::exception& dir_error) {
log_producer->Log({.level = LogLevel::Error, log_producer->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = std::format("Invalid --prompt-dir: {}", .message = std::format("Invalid --prompt-dir: {}",
dir_error.what())}); dir_error.what())});
return shutdown(EXIT_FAILURE); return shutdown(1);
} }
} }
@@ -108,7 +107,7 @@ int main(const int argc, char** argv) {
{ {
log_producer->Log( log_producer->Log(
{.level = LogLevel::Info, {.level = LogLevel::Info,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = "Prompt formatter: none (mock mode)"}); .message = "Prompt formatter: none (mock mode)"});
} }
return std::unique_ptr<IPromptFormatter>(nullptr); return std::unique_ptr<IPromptFormatter>(nullptr);
@@ -116,7 +115,7 @@ int main(const int argc, char** argv) {
{ {
log_producer->Log( log_producer->Log(
{.level = LogLevel::Info, {.level = LogLevel::Info,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = "Prompt formatter: Gemma4JinjaPromptFormatter"}); .message = "Prompt formatter: Gemma4JinjaPromptFormatter"});
} }
return std::unique_ptr<IPromptFormatter>( return std::unique_ptr<IPromptFormatter>(
@@ -125,15 +124,15 @@ int main(const int argc, char** argv) {
di::bind<WebClient>().to([options, log_producer] { di::bind<WebClient>().to([options, log_producer] {
if (options.generator.use_mocked) { if (options.generator.use_mocked) {
{ {
log_producer->Log({.level = LogLevel::Info, log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = "Web client: none (mock mode)"}); .message = "Web client: none (mock mode)"});
} }
return std::unique_ptr<WebClient>(nullptr); return std::unique_ptr<WebClient>(nullptr);
} }
{ {
log_producer->Log({.level = LogLevel::Info, log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = "Web client: HttpWebClient"}); .message = "Web client: HttpWebClient"});
} }
return std::unique_ptr<WebClient>( return std::unique_ptr<WebClient>(
@@ -144,15 +143,15 @@ int main(const int argc, char** argv) {
const auto& inj) -> std::unique_ptr<IEnrichmentService> { const auto& inj) -> std::unique_ptr<IEnrichmentService> {
if (options.generator.use_mocked) { if (options.generator.use_mocked) {
{ {
log_producer->Log({.level = LogLevel::Info, log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = "Enrichment: mock"}); .message = "Enrichment: mock"});
} }
return std::make_unique<MockEnrichmentService>(); return std::make_unique<MockEnrichmentService>();
} }
{ {
log_producer->Log({.level = LogLevel::Info, log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = "Enrichment: Wikipedia"}); .message = "Enrichment: Wikipedia"});
} }
return std::make_unique<WikipediaEnrichmentService>( return std::make_unique<WikipediaEnrichmentService>(
@@ -164,8 +163,8 @@ int main(const int argc, char** argv) {
&log_producer](const auto& inj) -> std::unique_ptr<DataGenerator> { &log_producer](const auto& inj) -> std::unique_ptr<DataGenerator> {
if (options.generator.use_mocked) { if (options.generator.use_mocked) {
{ {
log_producer->Log({.level = LogLevel::Info, log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = "Generator: mock"}); .message = "Generator: mock"});
} }
return std::make_unique<MockGenerator>(); return std::make_unique<MockGenerator>();
@@ -173,8 +172,8 @@ int main(const int argc, char** argv) {
{ {
log_producer->Log( log_producer->Log(
{.level = LogLevel::Info, {.level = LogLevel::Info,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = std::format( .message = fmt::format(
"Generator: LlamaGenerator | model={} | temp={:.2f} " "Generator: LlamaGenerator | model={} | temp={:.2f} "
"top_p={:.2f} top_k={} n_ctx={} seed={}", "top_p={:.2f} top_k={} n_ctx={} seed={}",
model_path, sampling.temperature, sampling.top_p, model_path, sampling.temperature, sampling.top_p,
@@ -190,29 +189,26 @@ int main(const int argc, char** argv) {
injector.create<std::unique_ptr<BiergartenPipelineOrchestrator>>(); injector.create<std::unique_ptr<BiergartenPipelineOrchestrator>>();
if (!orchestrator->Run()) { if (!orchestrator->Run()) {
log_producer->Log({.level = LogLevel::Error, log_producer->Log({.level = LogLevel::Error,
.phase = PipelinePhase::Teardown, .phase = PipelinePhase::Teardown,
.message = "Pipeline execution failed"}); .message = "Pipeline execution failed"});
return shutdown(EXIT_FAILURE); return shutdown(1);
} }
log_producer->Log({.level = LogLevel::Info, log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Teardown, .phase = PipelinePhase::Teardown,
.message = std::format("Pipeline complete in {} ms", .message = fmt::format("Pipeline complete in {} ms",
timer.Elapsed())}); timer.Elapsed())});
return shutdown(EXIT_SUCCESS); return shutdown(0);
} catch (const std::exception& exception) { } catch (const std::exception& exception) {
const LogDTO log_entry{.level = LogLevel::Error,
.phase = PipelinePhase::Teardown,
.message = exception.what()};
if (log_producer) { if (log_producer) {
log_producer->Log(log_entry); log_producer->Log({.level = LogLevel::Error,
} else { .phase = PipelinePhase::Teardown,
std::cerr << log_entry.message << std::endl; .message = fmt::format("Unhandled fatal error: {}",
exception.what())});
} }
return shutdown(1);
return shutdown(EXIT_FAILURE);
} }
} }

View File

@@ -22,7 +22,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if (logger_) { if (logger_) {
logger_->Log({.level = LogLevel::Debug, logger_->Log({.level = LogLevel::Debug,
.phase = PipelinePhase::UserGeneration, .phase = PipelinePhase::UserGeneration,
.message = std::format("Wikipedia: Cache hit for {}!", cache_key)}); .message = std::string("Wikipedia: Cache hit for ") +
cache_key + "!"});
} }
return cache_it->second; return cache_it->second;
} }
@@ -48,8 +49,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
logger_->Log( logger_->Log(
{.level = LogLevel::Warn, {.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration, .phase = PipelinePhase::UserGeneration,
.message = std::format("WikipediaService: JSON parse error for '{}': {}", .message = std::string("WikipediaService: JSON parse error for '") +
std::string(query), ec.message())}); std::string(query) + "': " + ec.message()});
} }
return {}; return {};
} }
@@ -62,8 +63,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
{.level = LogLevel::Warn, {.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration, .phase = PipelinePhase::UserGeneration,
.message = .message =
std::format("WikipediaService: Expected root object for '{}'", std::string("WikipediaService: Expected root object for '") +
std::string(query))}); std::string(query) + "'"});
} }
return {}; return {};
} }
@@ -80,8 +81,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
{.level = LogLevel::Warn, {.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration, .phase = PipelinePhase::UserGeneration,
.message = .message =
std::format("WikipediaService: Missing query.pages for '{}'", std::string("WikipediaService: Missing query.pages for '") +
std::string(query))}); std::string(query) + "'"});
} }
return {}; return {};
} }
@@ -93,8 +94,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
logger_->Log( logger_->Log(
{.level = LogLevel::Warn, {.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration, .phase = PipelinePhase::UserGeneration,
.message = std::format("WikipediaService: No pages returned for '{}'", .message = std::string("WikipediaService: No pages returned for '") +
std::string(query))}); std::string(query) + "'"});
} }
this->extract_cache_.emplace(cache_key, ""); this->extract_cache_.emplace(cache_key, "");
return {}; return {};
@@ -110,8 +111,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
{.level = LogLevel::Warn, {.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration, .phase = PipelinePhase::UserGeneration,
.message = .message =
std::format("WikipediaService: Unexpected page format for '{}'", std::string("WikipediaService: Unexpected page format for '") +
std::string(query))}); std::string(query) + "'"});
} }
return {}; return {};
} }
@@ -123,8 +124,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if (logger_) { if (logger_) {
logger_->Log({.level = LogLevel::Warn, logger_->Log({.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration, .phase = PipelinePhase::UserGeneration,
.message = std::format("WikipediaService: Page '{}' does not exist", .message = std::string("WikipediaService: Page '") +
std::string(query))}); std::string(query) + "' does not exist"});
} }
this->extract_cache_.emplace(cache_key, ""); this->extract_cache_.emplace(cache_key, "");
return {}; return {};
@@ -138,8 +139,8 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
{.level = LogLevel::Warn, {.level = LogLevel::Warn,
.phase = PipelinePhase::UserGeneration, .phase = PipelinePhase::UserGeneration,
.message = .message =
std::format("WikipediaService: No extract string found for '{}'", std::string("WikipediaService: No extract string found for '") +
std::string(query))}); std::string(query) + "'"});
} }
this->extract_cache_.emplace(cache_key, ""); this->extract_cache_.emplace(cache_key, "");
return {}; return {};
@@ -150,8 +151,9 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) {
if (logger_) { if (logger_) {
logger_->Log({.level = LogLevel::Info, logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::UserGeneration, .phase = PipelinePhase::UserGeneration,
.message = std::format("WikipediaService: Fetched {} chars for '{}'", .message = std::string("WikipediaService: Fetched ") +
extract.size(), std::string(query))}); std::to_string(extract.size()) + " chars for '" +
std::string(query) + "'"});
} }
this->extract_cache_.insert_or_assign(cache_key, extract); this->extract_cache_.insert_or_assign(cache_key, extract);

View File

@@ -52,8 +52,8 @@ std::string WikipediaEnrichmentService::GetLocationContext(
if (logger_) { if (logger_) {
logger_->Log({.level = LogLevel::Info, logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::UserGeneration, .phase = PipelinePhase::UserGeneration,
.message = std::format("Done fetching for {}. Sleeping for 10 seconds.", .message = std::string("Done fetching for ") +
location_query)}); location_query + ". Sleeping for 10 seconds."});
} }
std::this_thread::sleep_for(10s); std::this_thread::sleep_for(10s);
@@ -62,8 +62,8 @@ std::string WikipediaEnrichmentService::GetLocationContext(
logger_->Log( logger_->Log(
{.level = LogLevel::Debug, {.level = LogLevel::Debug,
.phase = PipelinePhase::UserGeneration, .phase = PipelinePhase::UserGeneration,
.message = std::format("WikipediaService lookup failed for '{}': {}", .message = std::string("WikipediaService lookup failed for '") +
location_query, e.what())}); location_query + "': " + e.what()});
} }
} }
return result; return result;

View File

@@ -13,29 +13,6 @@
#include "concurrency/bounded_channel.h" #include "concurrency/bounded_channel.h"
#include "services/logging/log_entry.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) LogDispatcher::LogDispatcher(BoundedChannel<LogEntry>& channel)
: channel_(channel) {} : channel_(channel) {}
@@ -51,11 +28,7 @@ void LogDispatcher::Run() {
const auto& log = entry.value(); const auto& log = entry.value();
logger->log(ToSpdlogLevel(log.level), logger->log(ToSpdlogLevel(log.level), log.message);
"{:<20} │ thread: {:016x} │ [{}:{}] │ {}",
PipelinePhaseToString(log.phase),
std::hash<std::thread::id>{}(log.thread_id),
log.origin.file_name(), log.origin.line(), log.message);
} }
} }

View File

@@ -16,4 +16,4 @@
LogProducer::LogProducer(BoundedChannel<LogEntry>& channel) LogProducer::LogProducer(BoundedChannel<LogEntry>& channel)
: channel_(channel) {} : channel_(channel) {}
void LogProducer::DoLog(LogEntry entry) { channel_.Send(std::move(entry)); } void LogProducer::Log(const LogEntry& entry) { channel_.Send(entry); }

View File

@@ -8,7 +8,6 @@
#include <chrono> #include <chrono>
#include <filesystem> #include <filesystem>
#include <format>
#include <fstream> #include <fstream>
#include <stdexcept> #include <stdexcept>
#include <string> #include <string>
@@ -45,8 +44,8 @@ PromptDirectory::PromptDirectory(const std::filesystem::path& prompt_dir,
std::filesystem::directory_iterator probe(prompt_dir_, ec); std::filesystem::directory_iterator probe(prompt_dir_, ec);
if (ec) { if (ec) {
throw std::runtime_error( throw std::runtime_error(
std::format("PromptDirectory: prompt directory is not readable: {} ({})", "PromptDirectory: prompt directory is not readable: " +
prompt_dir_.string(), ec.message())); prompt_dir_.string() + " (" + ec.message() + ")");
} }
if (logger_) { if (logger_) {
@@ -70,13 +69,13 @@ std::string PromptDirectory::Load(std::string_view key) {
// Scenario 3: resolve <prompt_dir>/<key>.md and require it to exist. // Scenario 3: resolve <prompt_dir>/<key>.md and require it to exist.
const std::filesystem::path file_path = 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); std::ifstream file(file_path);
if (!file.is_open()) { if (!file.is_open()) {
throw std::runtime_error( throw std::runtime_error(
std::format("PromptDirectory: prompt file not found for key '{}': {}", "PromptDirectory: prompt file not found for key '" + key_str +
key_str, file_path.string())); "': " + file_path.string());
} }
std::string content((std::istreambuf_iterator<char>(file)), std::string content((std::istreambuf_iterator<char>(file)),
@@ -84,15 +83,16 @@ std::string PromptDirectory::Load(std::string_view key) {
file.close(); file.close();
if (content.empty()) { if (content.empty()) {
throw std::runtime_error(std::format("PromptDirectory: prompt file for key '{}' is empty: {}", throw std::runtime_error("PromptDirectory: prompt file for key '" +
key_str, file_path.string())); key_str + "' is empty: " + file_path.string());
} }
if (logger_) { if (logger_) {
logger_->Log({.level = LogLevel::Info, logger_->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup, .phase = PipelinePhase::Startup,
.message = std::format("[PromptDirectory] Loaded prompt '{}' from '{}' ({} chars)", .message = std::string("[PromptDirectory] Loaded prompt '") +
key_str, file_path.string(), content.size())}); key_str + "' from '" + file_path.string() + "' (" +
std::to_string(content.size()) + " chars)"});
} }
cache_.emplace(key_str, content); cache_.emplace(key_str, content);

View File

@@ -1,6 +1,5 @@
#include "services/database/sqlite_connection_helpers.h" #include "services/database/sqlite_connection_helpers.h"
#include <format>
#include <stdexcept> #include <stdexcept>
namespace sqlite_export_service_internal { namespace sqlite_export_service_internal {
@@ -21,7 +20,7 @@ void SqliteStatementDeleter::operator()(
void ThrowSqliteError(sqlite3* db_handle, std::string_view action) { void ThrowSqliteError(sqlite3* db_handle, std::string_view action) {
const std::string message = const std::string message =
db_handle != nullptr ? sqlite3_errmsg(db_handle) : "unknown SQLite error"; 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) { SqliteDatabaseHandle OpenDatabase(const std::filesystem::path& path) {
@@ -51,7 +50,7 @@ void ExecSql(const SqliteDatabaseHandle& db_handle, std::string_view sql,
? error_message ? error_message
: sqlite3_errmsg(db_handle.get()); : sqlite3_errmsg(db_handle.get());
sqlite3_free(error_message); 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 <filesystem>
#include <format>
#include <memory> #include <memory>
#include <stdexcept> #include <stdexcept>
#include <string> #include <string>
@@ -19,8 +18,8 @@ std::filesystem::path SqliteExportService::BuildDatabasePath() const {
for (int suffix = 1; std::filesystem::exists(candidate); ++suffix) { for (int suffix = 1; std::filesystem::exists(candidate); ++suffix) {
candidate = output_path_ / candidate = output_path_ /
std::filesystem::path(std::format("biergarten_seed_{}-{}.sqlite", std::filesystem::path("biergarten_seed_" + run_timestamp_utc_ +
run_timestamp_utc_, suffix)); "-" + std::to_string(suffix) + ".sqlite");
} }
return candidate; return candidate;

View File

@@ -8,7 +8,6 @@
#include <httplib.h> #include <httplib.h>
#include <chrono> #include <chrono>
#include <format>
#include <regex> #include <regex>
#include <stdexcept> #include <stdexcept>
#include <string> #include <string>
@@ -48,9 +47,8 @@ std::string HttpWebClient::Get(const std::string& url) {
const httplib::Result result = client.Get(path); const httplib::Result result = client.Get(path);
if (!result) { if (!result) {
throw std::runtime_error(std::format( throw std::runtime_error("[HttpWebClient] Request failed for URL: " + url +
"[HttpWebClient] Request failed for URL: {} — {}", url, "" + httplib::to_string(result.error()));
httplib::to_string(result.error())));
} }
if (result->status < kSuccessMin || result->status >= kSuccessMax) { if (result->status < kSuccessMin || result->status >= kSuccessMax) {
@@ -58,11 +56,12 @@ std::string HttpWebClient::Get(const std::string& url) {
logger_->Log( logger_->Log(
{.level = LogLevel::Error, {.level = LogLevel::Error,
.phase = PipelinePhase::UserGeneration, .phase = PipelinePhase::UserGeneration,
.message = .message =
std::format("[HttpWebClient] Request failed for URL: {}", url)}); std::string("[HttpWebClient] Request failed for URL: ") + url});
} }
throw std::runtime_error(std::format("[HttpWebClient] HTTP {} for URL: {}", throw std::runtime_error("[HttpWebClient] HTTP " +
result->status, url)); std::to_string(result->status) +
" for URL: " + url);
} }
return result->body; return result->body;