Update string concatenations to use std::format

add pretty print log
This commit is contained in:
Aaron Po
2026-05-20 00:44:17 -04:00
parent 54a46458a3
commit 20742bb613
22 changed files with 502 additions and 298 deletions

View File

@@ -138,7 +138,8 @@ 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

View File

@@ -38,8 +38,7 @@ 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, const std::string& model_path, std::shared_ptr<ILogger> logger,
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

@@ -0,0 +1,109 @@
#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_CONSUMER_H_ #ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_
#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_CONSUMER_H_ #define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_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_CONSUMER_H_ #endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_

View File

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

View File

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

View File

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

View File

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

View File

@@ -4,6 +4,7 @@
* inference, and validates structured JSON output for brewery records. * inference, and validates structured JSON output for brewery records.
*/ */
#include <chrono>
#include <format> #include <format>
#include <optional> #include <optional>
#include <stdexcept> #include <stdexcept>
@@ -99,9 +100,11 @@ BreweryResult LlamaGenerator::GenerateBrewery(
raw = this->Infer(system_prompt, user_prompt, max_tokens, raw = this->Infer(system_prompt, user_prompt, max_tokens,
kBreweryJsonGrammar); kBreweryJsonGrammar);
if (logger_) { if (logger_) {
logger_->Log(LogLevel::Debug, PipelinePhase::BreweryAndBeerGeneration, logger_->Log(
std::string("LlamaGenerator: raw output (attempt ") + {.level = LogLevel::Debug,
std::to_string(attempt + 1) + "): " + raw); .phase = PipelinePhase::BreweryAndBeerGeneration,
.message = std::format("LlamaGenerator: raw output (attempt {}): {}",
attempt + 1, raw)});
} }
// Validate output: parse JSON and check required fields // Validate output: parse JSON and check required fields
@@ -114,10 +117,11 @@ BreweryResult LlamaGenerator::GenerateBrewery(
// Success: return parsed brewery data // Success: return parsed brewery data
if (logger_) { if (logger_) {
logger_->Log(LogLevel::Info, PipelinePhase::BreweryAndBeerGeneration, logger_->Log(
std::string( {.level = LogLevel::Info,
"LlamaGenerator: successfully generated brewery data on attempt ") + .phase = PipelinePhase::BreweryAndBeerGeneration,
std::to_string(attempt + 1)); .message = std::format("LlamaGenerator: successfully generated brewery data on attempt {}",
attempt + 1)});
} }
return brewery; return brewery;
@@ -127,9 +131,12 @@ BreweryResult LlamaGenerator::GenerateBrewery(
last_error = *validation_error; last_error = *validation_error;
if (logger_) { if (logger_) {
logger_->Log(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration, logger_->Log(
std::string("LlamaGenerator: malformed brewery JSON (attempt ") + {.level = LogLevel::Warn,
std::to_string(attempt + 1) + "): " + *validation_error); .phase = PipelinePhase::BreweryAndBeerGeneration,
.message =
std::format("LlamaGenerator: malformed brewery JSON (attempt {}): {}",
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.
@@ -148,10 +155,12 @@ BreweryResult LlamaGenerator::GenerateBrewery(
// All retry attempts exhausted: log failure and throw exception // All retry attempts exhausted: log failure and throw exception
if (logger_) { if (logger_) {
logger_->Log(LogLevel::Error, PipelinePhase::BreweryAndBeerGeneration, logger_->Log(
std::string("LlamaGenerator: malformed brewery response after ") + {.level = LogLevel::Error,
std::to_string(max_attempts) + " attempts: " + .phase = PipelinePhase::BreweryAndBeerGeneration,
(last_error.empty() ? raw : last_error)); .message = std::format(
"LlamaGenerator: malformed brewery response after {} attempts: {}",
max_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

@@ -5,6 +5,7 @@
*/ */
#include <format>
#include <string> #include <string>
#include "data_generation/llama_generator.h" #include "data_generation/llama_generator.h"
@@ -19,5 +20,5 @@
// 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 = "This is a test user profile from " + locale + "."}; .bio = std::format("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
*/ */
static std::string Trim(std::string_view value) { 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 @@ static 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
*/ */
static std::string CondenseWhitespace(std::string_view text) { std::string CondenseWhitespace(std::string_view text) {
std::string out; std::string out;
out.reserve(text.size()); out.reserve(text.size());
@@ -61,7 +61,37 @@ static 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.
static constexpr size_t kTruncationGuardDivisor = 2; 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
@@ -121,47 +151,6 @@ 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;
@@ -209,7 +198,7 @@ std::optional<std::string> ValidateBreweryJson(const std::string& raw,
return validation_error; return validation_error;
} }
const std::array<std::string*, 4> schema_placeholders = { const std::array 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

@@ -6,6 +6,8 @@
*/ */
#include <algorithm> #include <algorithm>
#include <chrono>
#include <format>
#include <memory> #include <memory>
#include <stdexcept> #include <stdexcept>
#include <string> #include <string>
@@ -105,7 +107,7 @@ 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_()),
}; };
auto sampler = MakeSamplerChain(vocab, sampler_config, grammar); const 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)
@@ -170,12 +172,12 @@ 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( logger_->Log({.level = LogLevel::Warn,
LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration, .phase = PipelinePhase::BreweryAndBeerGeneration,
std::string("LlamaGenerator: prompt too long (") + .message = std::format(
std::to_string(token_count) + ") tokens, truncating to " + "LlamaGenerator: prompt too long ({} tokens), "
std::to_string(prompt_budget) + "truncating to {} tokens to fit n_batch/n_ctx limits",
" tokens to fit n_batch/n_ctx limits"); token_count, prompt_budget)});
} }
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

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

View File

@@ -6,6 +6,7 @@
#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>
@@ -20,8 +21,8 @@ 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(std::string("Missing or invalid string field: ") + throw std::runtime_error(
key); std::format("Missing or invalid string field: {}", 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);
@@ -31,8 +32,8 @@ 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(std::string("Missing or invalid numeric field: ") + throw std::runtime_error(
key); std::format("Missing or invalid numeric field: {}", key));
} }
return value->to_number<double>(); return value->to_number<double>();
} }
@@ -42,7 +43,7 @@ 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::string("Missing or invalid string array field: ") + key); std::format("Missing or invalid string array field: {}", key));
} }
const auto& array = value->as_array(); const auto& array = value->as_array();
@@ -51,7 +52,7 @@ 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::string("Missing or invalid string array field: ") + key); std::format("Missing or invalid string array field: {}", key));
} }
items.emplace_back(item.as_string()); items.emplace_back(item.as_string());
} }

View File

@@ -4,12 +4,15 @@
* initializes shared infrastructure, and executes the pipeline entry flow. * initializes shared infrastructure, and executes the pipeline entry flow.
*/ */
#include <spdlog/spdlog.h>
#include <spdlog/fmt/fmt.h> #include <spdlog/fmt/fmt.h>
#include <spdlog/spdlog.h>
#include <boost/di.hpp> #include <boost/di.hpp>
#include <boost/program_options.hpp> #include <boost/program_options.hpp>
#include <chrono>
#include <exception> #include <exception>
#include <format>
#include <iostream>
#include <memory> #include <memory>
#include <optional> #include <optional>
#include <string> #include <string>
@@ -43,12 +46,13 @@ int main(const int argc, char** argv) {
spdlog::set_level(spdlog::level::debug); spdlog::set_level(spdlog::level::debug);
spdlog::set_pattern("│ %Y-%m-%d %H:%M:%S.%e │ %^%-7l%$ │ %v"); spdlog::set_pattern("│ %Y-%m-%d %H:%M:%S.%e │ %^%-7l%$ │ %v");
BoundedChannel<LogEntry> log_channel(kLogMaxCount); 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::shared_ptr<ILogger> log_producer =
std::make_shared<LogProducer>(log_channel); std::make_shared<LogProducer>(log_channel);
std::thread log_thread([&log_dispatcher] { log_dispatcher->Run(); });
auto shutdown = [&](const int exit_code) { auto shutdown = [&](const int exit_code) {
log_channel.Close(); log_channel.Close();
log_thread.join(); log_thread.join();
@@ -62,18 +66,21 @@ int main(const int argc, char** argv) {
const LlamaBackendState llama_backend_state; const LlamaBackendState llama_backend_state;
#endif #endif
log_producer->Log(LogLevel::Info, PipelinePhase::Startup, "STARTING PIPELINE"); log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.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(0); return shutdown(EXIT_FAILURE);
} }
const auto options = *parsed_options; const auto options = *parsed_options;
const std::string model_path = options.generator.model_path.string(); const std::string model_path = options.generator.model_path.string();
const auto sampling = options.generator.sampling.value_or(SamplingOptions{}); const auto sampling =
options.generator.sampling.value_or(SamplingOptions{});
std::unique_ptr<IPromptDirectory> prompt_directory; std::unique_ptr<IPromptDirectory> prompt_directory;
@@ -82,9 +89,12 @@ 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(LogLevel::Error, PipelinePhase::Startup, log_producer->Log({.level = LogLevel::Error,
fmt::format("Invalid --prompt-dir: {}", dir_error.what())); .phase = PipelinePhase::Startup,
return shutdown(1); .message = std::format("Invalid --prompt-dir: {}",
dir_error.what())});
return shutdown(EXIT_FAILURE);
} }
} }
@@ -93,26 +103,39 @@ int main(const int argc, char** argv) {
di::bind<ApplicationOptions>().to(options), di::bind<ApplicationOptions>().to(options),
di::bind<std::string>().to(model_path), di::bind<std::string>().to(model_path),
di::bind<IExportService>().to<SqliteExportService>(), di::bind<IExportService>().to<SqliteExportService>(),
di::bind<IPromptFormatter>().to( di::bind<IPromptFormatter>().to([options, log_producer] {
[options, log_producer] { if (options.generator.use_mocked) {
if (options.generator.use_mocked) { {
log_producer->Log(LogLevel::Info, PipelinePhase::Startup, log_producer->Log(
"Prompt formatter: none (mock mode)"); {.level = LogLevel::Info,
return std::unique_ptr<IPromptFormatter>(nullptr); .phase = PipelinePhase::Startup,
} .message = "Prompt formatter: none (mock mode)"});
log_producer->Log(LogLevel::Info, PipelinePhase::Startup, }
"Prompt formatter: Gemma4JinjaPromptFormatter"); return std::unique_ptr<IPromptFormatter>(nullptr);
return std::unique_ptr<IPromptFormatter>( }
std::make_unique<Gemma4JinjaPromptFormatter>()); {
}), 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] { di::bind<WebClient>().to([options, log_producer] {
if (options.generator.use_mocked) { if (options.generator.use_mocked) {
log_producer->Log(LogLevel::Info, PipelinePhase::Startup, {
"Web client: none (mock mode)"); log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Web client: none (mock mode)"});
}
return std::unique_ptr<WebClient>(nullptr); return std::unique_ptr<WebClient>(nullptr);
} }
log_producer->Log(LogLevel::Info, PipelinePhase::Startup, {
"Web client: HttpWebClient"); log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Web client: HttpWebClient"});
}
return std::unique_ptr<WebClient>( return std::unique_ptr<WebClient>(
std::make_unique<HttpWebClient>(log_producer)); std::make_unique<HttpWebClient>(log_producer));
}), }),
@@ -120,12 +143,18 @@ int main(const int argc, char** argv) {
[options, &log_producer]( [options, &log_producer](
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(LogLevel::Info, PipelinePhase::Startup, {
"Enrichment: mock"); log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Enrichment: mock"});
}
return std::make_unique<MockEnrichmentService>(); return std::make_unique<MockEnrichmentService>();
} }
log_producer->Log(LogLevel::Info, PipelinePhase::Startup, {
"Enrichment: Wikipedia"); log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Enrichment: Wikipedia"});
}
return std::make_unique<WikipediaEnrichmentService>( return std::make_unique<WikipediaEnrichmentService>(
inj.template create<std::unique_ptr<WebClient>>(), inj.template create<std::unique_ptr<WebClient>>(),
log_producer); log_producer);
@@ -134,20 +163,23 @@ int main(const int argc, char** argv) {
[&options, &model_path, &sampling, &prompt_directory, [&options, &model_path, &sampling, &prompt_directory,
&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(LogLevel::Info, PipelinePhase::Startup, {
"Generator: mock"); log_producer->Log({.level = LogLevel::Info,
.phase = PipelinePhase::Startup,
.message = "Generator: mock"});
}
return std::make_unique<MockGenerator>(); return std::make_unique<MockGenerator>();
} }
log_producer->Log( {
LogLevel::Info, PipelinePhase::Startup, log_producer->Log(
fmt::format( {.level = LogLevel::Info,
"Generator: LlamaGenerator | model={} | temp={:.2f} top_p={:.2f} top_k={} n_ctx={} seed={}", .phase = PipelinePhase::Startup,
model_path, .message = std::format(
sampling.temperature, "Generator: LlamaGenerator | model={} | temp={:.2f} "
sampling.top_p, "top_p={:.2f} top_k={} n_ctx={} seed={}",
sampling.top_k, model_path, sampling.temperature, sampling.top_p,
sampling.n_ctx, sampling.top_k, sampling.n_ctx, sampling.seed)});
sampling.seed)); }
return std::make_unique<LlamaGenerator>( return std::make_unique<LlamaGenerator>(
options, model_path, log_producer, options, model_path, log_producer,
inj.template create<std::unique_ptr<IPromptFormatter>>(), inj.template create<std::unique_ptr<IPromptFormatter>>(),
@@ -158,21 +190,29 @@ 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(LogLevel::Error, PipelinePhase::Teardown, log_producer->Log({.level = LogLevel::Error,
"Pipeline execution failed"); .phase = PipelinePhase::Teardown,
return shutdown(1); .message = "Pipeline execution failed"});
return shutdown(EXIT_FAILURE);
} }
log_producer->Log(LogLevel::Info, PipelinePhase::Teardown, log_producer->Log({.level = LogLevel::Info,
fmt::format("Pipeline complete in {} ms", timer.Elapsed())); .phase = PipelinePhase::Teardown,
.message = std::format("Pipeline complete in {} ms",
timer.Elapsed())});
return shutdown(0); return shutdown(EXIT_SUCCESS);
} catch (const std::exception& exception) { } catch (const std::exception& exception) {
const LogEntry log_entry{.level = LogLevel::Error,
.phase = PipelinePhase::Teardown,
.message = exception.what()};
if (log_producer) { if (log_producer) {
log_producer->Log(LogLevel::Error, PipelinePhase::Teardown, log_producer->Log(log_entry);
fmt::format("Unhandled fatal error: {}", exception.what())); } else {
std::cerr << log_entry.message << std::endl;
} }
return shutdown(1);
return shutdown(EXIT_FAILURE);
} }
} }

View File

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

View File

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

View File

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

View File

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

View File

@@ -1,5 +1,6 @@
#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 {
@@ -20,7 +21,7 @@ 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::string(action) + ": " + message); throw std::runtime_error(std::format("{}: {}", action, message));
} }
SqliteDatabaseHandle OpenDatabase(const std::filesystem::path& path) { SqliteDatabaseHandle OpenDatabase(const std::filesystem::path& path) {
@@ -50,7 +51,7 @@ 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::string(action) + ": " + message); throw std::runtime_error(std::format("{}: {}", action, message));
} }
} }

View File

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

View File

@@ -1,5 +1,5 @@
/** /**
* @file web_client/http_web_client.cc * @file web_client/http_web_client.cc
* @brief cpp-httplib implementation of WebClient. * @brief cpp-httplib implementation of WebClient.
*/ */
@@ -7,6 +7,8 @@
#include <httplib.h> #include <httplib.h>
#include <chrono>
#include <format>
#include <regex> #include <regex>
#include <stdexcept> #include <stdexcept>
#include <string> #include <string>
@@ -31,7 +33,7 @@ std::pair<std::string, std::string> SplitUrl(const std::string& url) {
return {match[1].str(), match[2].matched ? match[2].str() : "/"}; return {match[1].str(), match[2].matched ? match[2].str() : "/"};
} }
} // namespace } // namespace
std::string HttpWebClient::Get(const std::string& url) { std::string HttpWebClient::Get(const std::string& url) {
const auto [origin, path] = SplitUrl(url); const auto [origin, path] = SplitUrl(url);
@@ -40,28 +42,27 @@ std::string HttpWebClient::Get(const std::string& url) {
client.set_follow_location(true); client.set_follow_location(true);
client.set_connection_timeout(kConnectionTimeoutSeconds); client.set_connection_timeout(kConnectionTimeoutSeconds);
client.set_read_timeout(kReadTimeoutSeconds); client.set_read_timeout(kReadTimeoutSeconds);
client.set_default_headers({ client.set_default_headers({{"Accept", "application/json"},
{"Accept", "application/json"}, {"User-Agent", "biergarten-pipeline/1.0"}});
{"User-Agent", "biergarten-pipeline/1.0"}
});
const httplib::Result result = client.Get(path); const httplib::Result result = client.Get(path);
if (!result) { if (!result) {
throw std::runtime_error( throw std::runtime_error(std::format(
"[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) {
if (logger_) { if (logger_) {
logger_->Log(LogLevel::Error, PipelinePhase::UserGeneration, logger_->Log(
std::string("[HttpWebClient] Request failed for URL: ") + {.level = LogLevel::Error,
url); .phase = PipelinePhase::UserGeneration,
.message =
std::format("[HttpWebClient] Request failed for URL: {}", url)});
} }
throw std::runtime_error( throw std::runtime_error(std::format("[HttpWebClient] HTTP {} for URL: {}",
"[HttpWebClient] HTTP " + std::to_string(result->status) + result->status, url));
" for URL: " + url);
} }
return result->body; return result->body;