diff --git a/tooling/pipeline/CMakeLists.txt b/tooling/pipeline/CMakeLists.txt index c2d907b..12df845 100644 --- a/tooling/pipeline/CMakeLists.txt +++ b/tooling/pipeline/CMakeLists.txt @@ -138,7 +138,8 @@ FetchContent_MakeAvailable(cpp-httplib) # 5. Executable & Sources add_executable(${PROJECT_NAME} - includes/services/enrichment/mock_enrichment.h) + includes/services/enrichment/mock_enrichment.h + includes/json_handling/pretty_print.h) # --- Entry point --- target_sources(${PROJECT_NAME} PRIVATE diff --git a/tooling/pipeline/includes/data_generation/llama_generator.h b/tooling/pipeline/includes/data_generation/llama_generator.h index 40b5a11..ef33b0c 100644 --- a/tooling/pipeline/includes/data_generation/llama_generator.h +++ b/tooling/pipeline/includes/data_generation/llama_generator.h @@ -38,8 +38,7 @@ class LlamaGenerator final : public DataGenerator { * @param prompt_directory Directory service for loading named prompt files. */ LlamaGenerator(const ApplicationOptions& options, - const std::string& model_path, - std::shared_ptr logger, + const std::string& model_path, std::shared_ptr logger, std::unique_ptr prompt_formatter, std::unique_ptr prompt_directory); diff --git a/tooling/pipeline/includes/json_handling/pretty_print.h b/tooling/pipeline/includes/json_handling/pretty_print.h new file mode 100644 index 0000000..51e7486 --- /dev/null +++ b/tooling/pipeline/includes/json_handling/pretty_print.h @@ -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 +#include +#include + +/** + * @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 diff --git a/tooling/pipeline/includes/services/logging/log_dispatcher.h b/tooling/pipeline/includes/services/logging/log_dispatcher.h index 823a37e..c2104bf 100644 --- a/tooling/pipeline/includes/services/logging/log_dispatcher.h +++ b/tooling/pipeline/includes/services/logging/log_dispatcher.h @@ -6,8 +6,8 @@ * them to spdlog on a dedicated thread. */ -#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_CONSUMER_H_ -#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_CONSUMER_H_ +#ifndef BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_ +#define BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_ #include @@ -23,31 +23,31 @@ */ class LogDispatcher { public: - /** - * @brief Construct a log dispatcher. - * - * @param channel Reference to the bounded channel used for log retrieval. - */ - explicit LogDispatcher(BoundedChannel& channel); + /** + * @brief Construct a log dispatcher. + * + * @param channel Reference to the bounded channel used for log retrieval. + */ + explicit LogDispatcher(BoundedChannel& channel); - LogDispatcher(const LogDispatcher&) = delete; - LogDispatcher& operator=(const LogDispatcher&) = delete; - LogDispatcher(LogDispatcher&&) = delete; - LogDispatcher& operator=(LogDispatcher&&) = delete; - ~LogDispatcher() = default; + LogDispatcher(const LogDispatcher&) = delete; + LogDispatcher& operator=(const LogDispatcher&) = delete; + LogDispatcher(LogDispatcher&&) = delete; + LogDispatcher& operator=(LogDispatcher&&) = delete; + ~LogDispatcher() = default; - /** - * @brief Drain the channel and forward entries to spdlog. - * - * 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. - */ - void Run(); + /** + * @brief Drain the channel and forward entries to spdlog. + * + * 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. + */ + void Run(); private: - BoundedChannel& channel_; + BoundedChannel& 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_ diff --git a/tooling/pipeline/src/biergarten_pipeline_orchestrator/generate_breweries.cc b/tooling/pipeline/src/biergarten_pipeline_orchestrator/generate_breweries.cc index b80861a..09dfa82 100644 --- a/tooling/pipeline/src/biergarten_pipeline_orchestrator/generate_breweries.cc +++ b/tooling/pipeline/src/biergarten_pipeline_orchestrator/generate_breweries.cc @@ -3,13 +3,17 @@ * @brief BiergartenDataGenerator::GenerateBreweries() implementation. */ -#include "services/logging/logger.h" +#include +#include + #include "biergarten_pipeline_orchestrator.h" +#include "services/logging/logger.h" void BiergartenPipelineOrchestrator::GenerateBreweries( std::span cities) { - logger_->Log(LogLevel::Info, PipelinePhase::BreweryAndBeerGeneration, - "=== SAMPLE BREWERY GENERATION ==="); + logger_->Log({.level = LogLevel::Info, + .phase = PipelinePhase::BreweryAndBeerGeneration, + .message = "=== SAMPLE BREWERY GENERATION ==="}); generated_breweries_.clear(); size_t skipped_count = 0; @@ -29,33 +33,36 @@ void BiergartenPipelineOrchestrator::GenerateBreweries( } catch (const std::exception& export_exception) { ++export_failed_count; - logger_->Log(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration, - std::string("[Pipeline] Generated brewery for '") + - location.city + "' (" + location.country + - ") but SQLite export failed: " + - export_exception.what()); + logger_->Log( + {.level = LogLevel::Warn, + .phase = PipelinePhase::BreweryAndBeerGeneration, + .message = + std::format("[Pipeline] Generated brewery for '{}' ({}) but SQLite export failed: {}", + location.city, location.country, export_exception.what())}); } } catch (const std::exception& e) { ++skipped_count; - logger_->Log(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration, - std::string("[Pipeline] Skipping city '") + location.city + - " (" + location.country + "): brewery generation failed: " + - e.what()); + logger_->Log({.level = LogLevel::Warn, + .phase = PipelinePhase::BreweryAndBeerGeneration, + .message = std::format("[Pipeline] Skipping city '{}' ({}): brewery generation failed: {}", + location.city, location.country, e.what())}); } } if (skipped_count > 0) { - logger_->Log(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration, - std::string("[Pipeline] Skipped ") + - std::to_string(skipped_count) + - " city/cities due to generation errors"); + logger_->Log({.level = LogLevel::Warn, + .phase = PipelinePhase::BreweryAndBeerGeneration, + .message = std::format( + "[Pipeline] Skipped {} city/cities due to generation errors", + skipped_count)}); } if (export_failed_count > 0) { - logger_->Log(LogLevel::Warn, PipelinePhase::Teardown, - std::string("[Pipeline] Failed to export ") + - std::to_string(export_failed_count) + - " generated brewery/breweries to SQLite"); + logger_->Log({.level = LogLevel::Warn, + .phase = PipelinePhase::Teardown, + .message = std::format( + "[Pipeline] Failed to export {} generated brewery/breweries to SQLite", + export_failed_count)}); } } diff --git a/tooling/pipeline/src/biergarten_pipeline_orchestrator/log_results.cc b/tooling/pipeline/src/biergarten_pipeline_orchestrator/log_results.cc index 7206426..8843502 100644 --- a/tooling/pipeline/src/biergarten_pipeline_orchestrator/log_results.cc +++ b/tooling/pipeline/src/biergarten_pipeline_orchestrator/log_results.cc @@ -3,29 +3,35 @@ * @brief BiergartenDataGenerator::LogResults() implementation. */ -#include "services/logging/logger.h" +#include +#include +#include +#include "../../includes/json_handling/pretty_print.h" #include "biergarten_pipeline_orchestrator.h" -#include - +#include "services/logging/logger.h" void BiergartenPipelineOrchestrator::LogResults() const { - std::ostringstream msg; - 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"; + boost::json::array output; - msg << " brewery_name_en=\"" << brewery.name_en << "\"\n"; - msg << " brewery_description_en=\"" << brewery.description_en - << "\"\n"; - msg << " brewery_name_local=\"" << brewery.name_local << "\"\n"; - msg << " brewery_description_local=\"" << brewery.description_local - << "\"\n"; - ++index; + for (const auto& [location, brewery] : generated_breweries_) { + output.push_back(boost::json::object{ + {"name_en", brewery.name_en}, + {"description_en", brewery.description_en}, + {"name_local", brewery.name_local}, + {"description_local", brewery.description_local}, + {"location", boost::json::object{ + {"city", location.city}, + {"country", location.country}, + {"state_province", location.state_province}, + {"iso3166_2", location.iso3166_2}, + {"latitude", location.latitude}, + {"longitude", location.longitude}, + }}}); } - 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()}); +} \ No newline at end of file diff --git a/tooling/pipeline/src/biergarten_pipeline_orchestrator/query_cities_with_countries.cc b/tooling/pipeline/src/biergarten_pipeline_orchestrator/query_cities_with_countries.cc index 3ee644a..6c1b62b 100644 --- a/tooling/pipeline/src/biergarten_pipeline_orchestrator/query_cities_with_countries.cc +++ b/tooling/pipeline/src/biergarten_pipeline_orchestrator/query_cities_with_countries.cc @@ -3,9 +3,8 @@ * @brief BiergartenDataGenerator::QueryCitiesWithCountries() implementation. */ -#include "services/logging/logger.h" - #include +#include #include #include #include @@ -13,16 +12,18 @@ #include "biergarten_pipeline_orchestrator.h" #include "json_handling/json_loader.h" +#include "services/logging/logger.h" -std::vector BiergartenPipelineOrchestrator::QueryCitiesWithCountries() { - logger_->Log(LogLevel::Info, PipelinePhase::Startup, - "=== GEOGRAPHIC DATA OVERVIEW ==="); +std::vector +BiergartenPipelineOrchestrator::QueryCitiesWithCountries() { + logger_->Log({.level = LogLevel::Info, + .phase = PipelinePhase::Startup, + .message = "=== GEOGRAPHIC DATA OVERVIEW ==="}); const std::filesystem::path locations_path = "locations.json"; auto all_locations = JsonLoader::LoadLocations(locations_path, logger_); - const size_t sample_count = std::min( static_cast(application_options_.pipeline.location_count), all_locations.size()); @@ -38,9 +39,13 @@ std::vector BiergartenPipelineOrchestrator::QueryCitiesWithCountries() std::ranges::sample(all_locations, std::back_inserter(sampled_locations), sample_count_signed, random_generator); - logger_->Log(LogLevel::Info, PipelinePhase::Startup, - std::format(" Locations available: {}", all_locations.size())); - logger_->Log(LogLevel::Info, PipelinePhase::Startup, - std::format(" Sampled locations: {}", sampled_locations.size())); + logger_->Log({.level = LogLevel::Info, + .phase = PipelinePhase::Startup, + .message = std::format(" Locations available: {}", + all_locations.size())}); + logger_->Log({.level = LogLevel::Info, + .phase = PipelinePhase::Startup, + .message = std::format(" Sampled locations: {}", + sampled_locations.size())}); return sampled_locations; } diff --git a/tooling/pipeline/src/biergarten_pipeline_orchestrator/run.cc b/tooling/pipeline/src/biergarten_pipeline_orchestrator/run.cc index 1888d76..c98805f 100644 --- a/tooling/pipeline/src/biergarten_pipeline_orchestrator/run.cc +++ b/tooling/pipeline/src/biergarten_pipeline_orchestrator/run.cc @@ -3,11 +3,12 @@ * @brief BiergartenDataGenerator::Run() implementation. */ -#include "services/logging/logger.h" - +#include +#include #include #include "biergarten_pipeline_orchestrator.h" +#include "services/logging/logger.h" bool BiergartenPipelineOrchestrator::Run() { try { @@ -30,18 +31,21 @@ bool BiergartenPipelineOrchestrator::Run() { .region_context = std::move(region_context)}); } catch (const std::exception& exception) { ++skipped_count; - logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration, - std::string("[Pipeline] Skipping city '") + city.city + - " (" + city.country + "): context lookup failed: " + - exception.what()); + logger_->Log( + {.level = LogLevel::Warn, + .phase = PipelinePhase::UserGeneration, + .message = std::format( + "[Pipeline] Skipping city '{}' ({}): context lookup failed: {}", + city.city, city.country, exception.what())}); } } if (skipped_count > 0) { - logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration, - std::string("[Pipeline] Skipped ") + - std::to_string(skipped_count) + - " city/cities due to context lookup errors"); + logger_->Log({.level = LogLevel::Warn, + .phase = PipelinePhase::UserGeneration, + .message = std::format( + "[Pipeline] Skipped {} city/cities due to context lookup errors", + skipped_count)}); } this->GenerateBreweries(enriched); @@ -49,9 +53,11 @@ bool BiergartenPipelineOrchestrator::Run() { this->LogResults(); return true; } catch (const std::exception& e) { - logger_->Log(LogLevel::Error, PipelinePhase::Teardown, - std::string("Pipeline execution failed with error: ") + - e.what()); + logger_->Log( + {.level = LogLevel::Error, + .phase = PipelinePhase::Teardown, + .message = + std::format("Pipeline execution failed with error: {}", e.what())}); return false; } } diff --git a/tooling/pipeline/src/data_generation/llama/generate_brewery.cc b/tooling/pipeline/src/data_generation/llama/generate_brewery.cc index c7d5022..f6d5159 100644 --- a/tooling/pipeline/src/data_generation/llama/generate_brewery.cc +++ b/tooling/pipeline/src/data_generation/llama/generate_brewery.cc @@ -4,6 +4,7 @@ * inference, and validates structured JSON output for brewery records. */ +#include #include #include #include @@ -99,9 +100,11 @@ BreweryResult LlamaGenerator::GenerateBrewery( raw = this->Infer(system_prompt, user_prompt, max_tokens, kBreweryJsonGrammar); if (logger_) { - logger_->Log(LogLevel::Debug, PipelinePhase::BreweryAndBeerGeneration, - std::string("LlamaGenerator: raw output (attempt ") + - std::to_string(attempt + 1) + "): " + raw); + logger_->Log( + {.level = LogLevel::Debug, + .phase = PipelinePhase::BreweryAndBeerGeneration, + .message = std::format("LlamaGenerator: raw output (attempt {}): {}", + attempt + 1, raw)}); } // Validate output: parse JSON and check required fields @@ -114,10 +117,11 @@ BreweryResult LlamaGenerator::GenerateBrewery( // Success: return parsed brewery data if (logger_) { - logger_->Log(LogLevel::Info, PipelinePhase::BreweryAndBeerGeneration, - std::string( - "LlamaGenerator: successfully generated brewery data on attempt ") + - std::to_string(attempt + 1)); + logger_->Log( + {.level = LogLevel::Info, + .phase = PipelinePhase::BreweryAndBeerGeneration, + .message = std::format("LlamaGenerator: successfully generated brewery data on attempt {}", + attempt + 1)}); } return brewery; @@ -127,9 +131,12 @@ BreweryResult LlamaGenerator::GenerateBrewery( last_error = *validation_error; if (logger_) { - logger_->Log(LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration, - std::string("LlamaGenerator: malformed brewery JSON (attempt ") + - std::to_string(attempt + 1) + "): " + *validation_error); + logger_->Log( + {.level = LogLevel::Warn, + .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. @@ -148,10 +155,12 @@ BreweryResult LlamaGenerator::GenerateBrewery( // All retry attempts exhausted: log failure and throw exception if (logger_) { - logger_->Log(LogLevel::Error, PipelinePhase::BreweryAndBeerGeneration, - std::string("LlamaGenerator: malformed brewery response after ") + - std::to_string(max_attempts) + " attempts: " + - (last_error.empty() ? raw : last_error)); + logger_->Log( + {.level = LogLevel::Error, + .phase = PipelinePhase::BreweryAndBeerGeneration, + .message = std::format( + "LlamaGenerator: malformed brewery response after {} attempts: {}", + max_attempts, last_error.empty() ? raw : last_error)}); } throw std::runtime_error("LlamaGenerator: malformed brewery response"); } diff --git a/tooling/pipeline/src/data_generation/llama/generate_user.cc b/tooling/pipeline/src/data_generation/llama/generate_user.cc index 9013282..8afc776 100644 --- a/tooling/pipeline/src/data_generation/llama/generate_user.cc +++ b/tooling/pipeline/src/data_generation/llama/generate_user.cc @@ -5,6 +5,7 @@ */ +#include #include #include "data_generation/llama_generator.h" @@ -19,5 +20,5 @@ // 4. Return locale-aware username and biography UserResult LlamaGenerator::GenerateUser(const std::string& locale) { return {.username = "test_user", - .bio = "This is a test user profile from " + locale + "."}; + .bio = std::format("This is a test user profile from {}.", locale)}; } diff --git a/tooling/pipeline/src/data_generation/llama/helpers.cc b/tooling/pipeline/src/data_generation/llama/helpers.cc index 1433523..d8b2715 100644 --- a/tooling/pipeline/src/data_generation/llama/helpers.cc +++ b/tooling/pipeline/src/data_generation/llama/helpers.cc @@ -16,11 +16,11 @@ #include "data_generation/llama_generator_helpers.h" #include "llama.h" - +namespace { /** * 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"; const size_t first_index = value.find_first_not_of(whitespace); 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 * spaces */ -static std::string CondenseWhitespace(std::string_view text) { +std::string CondenseWhitespace(std::string_view text) { std::string out; 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. // This preserves the critical opening content and avoids cutting critical // 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& values) { + for (const std::string* value : values) { + std::string lowered = *value; + std::ranges::transform(lowered, lowered.begin(), + [](const unsigned char character) { + return static_cast(std::tolower(character)); + }); + + if (lowered == "string") { + return true; + } + } + + return false; +} +} // namespace /** * 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"); } -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& values) { - for (const std::string* value : values) { - std::string lowered = *value; - std::ranges::transform(lowered, lowered.begin(), - [](unsigned char character) { - return static_cast(std::tolower(character)); - }); - - if (lowered == "string") { - return true; - } - } - - return false; -} - std::optional ValidateBreweryJson(const std::string& raw, BreweryResult& brewery_out) { boost::system::error_code error_code; @@ -209,7 +198,7 @@ std::optional ValidateBreweryJson(const std::string& raw, return validation_error; } - const std::array schema_placeholders = { + const std::array schema_placeholders = { &brewery_out.name_en, &brewery_out.description_en, &brewery_out.name_local, &brewery_out.description_local}; if (HasSchemaPlaceholder(schema_placeholders)) { diff --git a/tooling/pipeline/src/data_generation/llama/infer.cc b/tooling/pipeline/src/data_generation/llama/infer.cc index 03c6f46..fd9f2ee 100644 --- a/tooling/pipeline/src/data_generation/llama/infer.cc +++ b/tooling/pipeline/src/data_generation/llama/infer.cc @@ -6,6 +6,8 @@ */ #include +#include +#include #include #include #include @@ -105,7 +107,7 @@ std::string LlamaGenerator::InferFormatted(const std::string& formatted_prompt, .top_p = sampling_top_p_, .seed = static_cast(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) @@ -170,12 +172,12 @@ std::string LlamaGenerator::InferFormatted(const std::string& formatted_prompt, prompt_tokens.resize(static_cast(token_count)); if (token_count > prompt_budget) { if (logger_) { - logger_->Log( - LogLevel::Warn, PipelinePhase::BreweryAndBeerGeneration, - std::string("LlamaGenerator: prompt too long (") + - std::to_string(token_count) + ") tokens, truncating to " + - std::to_string(prompt_budget) + - " tokens to fit n_batch/n_ctx limits"); + logger_->Log({.level = LogLevel::Warn, + .phase = PipelinePhase::BreweryAndBeerGeneration, + .message = std::format( + "LlamaGenerator: prompt too long ({} tokens), " + "truncating to {} tokens to fit n_batch/n_ctx limits", + token_count, prompt_budget)}); } prompt_tokens.resize(static_cast(prompt_budget)); token_count = prompt_budget; diff --git a/tooling/pipeline/src/data_generation/llama/load.cc b/tooling/pipeline/src/data_generation/llama/load.cc index 7066001..1866b2a 100644 --- a/tooling/pipeline/src/data_generation/llama/load.cc +++ b/tooling/pipeline/src/data_generation/llama/load.cc @@ -5,6 +5,7 @@ */ #include +#include #include #include #include @@ -27,8 +28,10 @@ void LlamaGenerator::Load(const std::string& model_path) { llama_model_params model_params = llama_model_default_params(); model_params.n_gpu_layers = n_gpu_layers_; - LlamaGenerator::ModelHandle loaded_model( + + ModelHandle loaded_model( llama_model_load_from_file(model_path.c_str(), model_params)); + if (!loaded_model) { throw std::runtime_error( "LlamaGenerator: failed to load model from path: " + model_path); @@ -38,8 +41,9 @@ void LlamaGenerator::Load(const std::string& model_path) { context_params.n_ctx = n_ctx_; 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)); + if (!loaded_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); if (logger_) { - logger_->Log(LogLevel::Info, PipelinePhase::Startup, - std::string("[LlamaGenerator] Loaded model: ") + model_path); + logger_->Log({.level = LogLevel::Info, + .phase = PipelinePhase::Startup, + .message = std::format("[LlamaGenerator] Loaded model: {} ", + model_path)}); } } diff --git a/tooling/pipeline/src/json_handling/json_loader.cc b/tooling/pipeline/src/json_handling/json_loader.cc index 3ebdbd4..6311991 100644 --- a/tooling/pipeline/src/json_handling/json_loader.cc +++ b/tooling/pipeline/src/json_handling/json_loader.cc @@ -6,6 +6,7 @@ #include "json_handling/json_loader.h" +#include #include "services/logging/logger.h" #include @@ -20,8 +21,8 @@ static std::string ReadRequiredString(const boost::json::object& object, const char* key) { const boost::json::value* value = object.if_contains(key); if (value == nullptr || !value->is_string()) { - throw std::runtime_error(std::string("Missing or invalid string field: ") + - key); + throw std::runtime_error( + std::format("Missing or invalid string field: {}", key)); } const std::string_view text = value->as_string(); return std::string(text); @@ -31,8 +32,8 @@ static double ReadRequiredNumber(const boost::json::object& object, const char* key) { const boost::json::value* value = object.if_contains(key); if (value == nullptr || !value->is_number()) { - throw std::runtime_error(std::string("Missing or invalid numeric field: ") + - key); + throw std::runtime_error( + std::format("Missing or invalid numeric field: {}", key)); } return value->to_number(); } @@ -42,7 +43,7 @@ static std::vector ReadRequiredStringArray( const boost::json::value* value = object.if_contains(key); if (value == nullptr || !value->is_array()) { 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(); @@ -51,7 +52,7 @@ static std::vector ReadRequiredStringArray( for (const auto& item : array) { if (!item.is_string()) { 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()); } diff --git a/tooling/pipeline/src/main.cc b/tooling/pipeline/src/main.cc index f586f4d..b2c7a11 100644 --- a/tooling/pipeline/src/main.cc +++ b/tooling/pipeline/src/main.cc @@ -4,12 +4,15 @@ * initializes shared infrastructure, and executes the pipeline entry flow. */ -#include #include +#include #include #include +#include #include +#include +#include #include #include #include @@ -43,12 +46,13 @@ int main(const int argc, char** argv) { spdlog::set_level(spdlog::level::debug); spdlog::set_pattern("│ %Y-%m-%d %H:%M:%S.%e │ %^%-7l%$ │ %v"); BoundedChannel log_channel(kLogMaxCount); - auto log_dispatcher = std::make_unique(log_channel); - std::thread log_thread([&log_dispatcher] { log_dispatcher->Run(); }); + auto log_dispatcher = // + std::make_unique(log_channel); std::shared_ptr log_producer = std::make_shared(log_channel); + std::thread log_thread([&log_dispatcher] { log_dispatcher->Run(); }); auto shutdown = [&](const int exit_code) { log_channel.Close(); log_thread.join(); @@ -62,18 +66,21 @@ int main(const int argc, char** argv) { const LlamaBackendState llama_backend_state; #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 parsed_options = ParseArguments(argc, argv, log_producer); if (!parsed_options.has_value()) { - return shutdown(0); + return shutdown(EXIT_FAILURE); } const auto options = *parsed_options; 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 prompt_directory; @@ -82,9 +89,12 @@ int main(const int argc, char** argv) { prompt_directory = std::make_unique( options.pipeline.prompt_dir, log_producer); } catch (const std::exception& dir_error) { - log_producer->Log(LogLevel::Error, PipelinePhase::Startup, - fmt::format("Invalid --prompt-dir: {}", dir_error.what())); - return shutdown(1); + log_producer->Log({.level = LogLevel::Error, + .phase = PipelinePhase::Startup, + .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().to(options), di::bind().to(model_path), di::bind().to(), - di::bind().to( - [options, log_producer] { - if (options.generator.use_mocked) { - log_producer->Log(LogLevel::Info, PipelinePhase::Startup, - "Prompt formatter: none (mock mode)"); - return std::unique_ptr(nullptr); - } - log_producer->Log(LogLevel::Info, PipelinePhase::Startup, - "Prompt formatter: Gemma4JinjaPromptFormatter"); - return std::unique_ptr( - std::make_unique()); - }), + di::bind().to([options, log_producer] { + if (options.generator.use_mocked) { + { + log_producer->Log( + {.level = LogLevel::Info, + .phase = PipelinePhase::Startup, + .message = "Prompt formatter: none (mock mode)"}); + } + return std::unique_ptr(nullptr); + } + { + log_producer->Log( + {.level = LogLevel::Info, + .phase = PipelinePhase::Startup, + .message = "Prompt formatter: Gemma4JinjaPromptFormatter"}); + } + return std::unique_ptr( + std::make_unique()); + }), di::bind().to([options, log_producer] { 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(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( std::make_unique(log_producer)); }), @@ -120,12 +143,18 @@ int main(const int argc, char** argv) { [options, &log_producer]( const auto& inj) -> std::unique_ptr { 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(); } - 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( inj.template create>(), log_producer); @@ -134,20 +163,23 @@ int main(const int argc, char** argv) { [&options, &model_path, &sampling, &prompt_directory, &log_producer](const auto& inj) -> std::unique_ptr { 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(); } - log_producer->Log( - LogLevel::Info, PipelinePhase::Startup, - fmt::format( - "Generator: LlamaGenerator | model={} | temp={:.2f} top_p={:.2f} top_k={} n_ctx={} seed={}", - model_path, - sampling.temperature, - sampling.top_p, - sampling.top_k, - sampling.n_ctx, - sampling.seed)); + { + log_producer->Log( + {.level = LogLevel::Info, + .phase = PipelinePhase::Startup, + .message = std::format( + "Generator: LlamaGenerator | model={} | temp={:.2f} " + "top_p={:.2f} top_k={} n_ctx={} seed={}", + model_path, sampling.temperature, sampling.top_p, + sampling.top_k, sampling.n_ctx, sampling.seed)}); + } return std::make_unique( options, model_path, log_producer, inj.template create>(), @@ -158,21 +190,29 @@ int main(const int argc, char** argv) { injector.create>(); if (!orchestrator->Run()) { - log_producer->Log(LogLevel::Error, PipelinePhase::Teardown, - "Pipeline execution failed"); - return shutdown(1); + log_producer->Log({.level = LogLevel::Error, + .phase = PipelinePhase::Teardown, + .message = "Pipeline execution failed"}); + return shutdown(EXIT_FAILURE); } - log_producer->Log(LogLevel::Info, PipelinePhase::Teardown, - fmt::format("Pipeline complete in {} ms", timer.Elapsed())); + log_producer->Log({.level = LogLevel::Info, + .phase = PipelinePhase::Teardown, + .message = std::format("Pipeline complete in {} ms", + timer.Elapsed())}); - return shutdown(0); + return shutdown(EXIT_SUCCESS); } catch (const std::exception& exception) { + const LogEntry log_entry{.level = LogLevel::Error, + .phase = PipelinePhase::Teardown, + .message = exception.what()}; if (log_producer) { - log_producer->Log(LogLevel::Error, PipelinePhase::Teardown, - fmt::format("Unhandled fatal error: {}", exception.what())); + log_producer->Log(log_entry); + } else { + std::cerr << log_entry.message << std::endl; } - return shutdown(1); + + return shutdown(EXIT_FAILURE); } -} \ No newline at end of file +} diff --git a/tooling/pipeline/src/services/enrichment/wikipedia/fetch_extract.cc b/tooling/pipeline/src/services/enrichment/wikipedia/fetch_extract.cc index 281db66..0afd490 100644 --- a/tooling/pipeline/src/services/enrichment/wikipedia/fetch_extract.cc +++ b/tooling/pipeline/src/services/enrichment/wikipedia/fetch_extract.cc @@ -14,15 +14,15 @@ using namespace boost; std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) { - const std::string cache_key(query); // 1. Cache Lookup if (const auto cache_it = this->extract_cache_.find(cache_key); cache_it != this->extract_cache_.end()) { if (logger_) { - logger_->Log(LogLevel::Debug, PipelinePhase::UserGeneration, - std::string("Wikipedia: Cache hit for ") + cache_key + "!"); + logger_->Log({.level = LogLevel::Debug, + .phase = PipelinePhase::UserGeneration, + .message = std::format("Wikipedia: Cache hit for {}!", cache_key)}); } 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", encoded); - const std::string body = this->client_->Get(url); { using namespace std::literals::chrono_literals; @@ -46,9 +45,11 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) { if (ec) { if (logger_) { - logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration, - std::string("WikipediaService: JSON parse error for '") + - std::string(query) + "': " + ec.message()); + logger_->Log( + {.level = LogLevel::Warn, + .phase = PipelinePhase::UserGeneration, + .message = std::format("WikipediaService: JSON parse error for '{}': {}", + std::string(query), ec.message())}); } return {}; } @@ -57,9 +58,12 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) { const json::object* obj = doc.if_object(); if (obj == nullptr) { if (logger_) { - logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration, - std::string("WikipediaService: Expected root object for '") + - std::string(query) + "'"); + logger_->Log( + {.level = LogLevel::Warn, + .phase = PipelinePhase::UserGeneration, + .message = + std::format("WikipediaService: Expected root object for '{}'", + std::string(query))}); } return {}; } @@ -72,9 +76,12 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) { if ((pages_ptr == nullptr) || !pages_ptr->is_object()) { if (logger_) { - logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration, - std::string("WikipediaService: Missing query.pages for '") + - std::string(query) + "'"); + logger_->Log( + {.level = LogLevel::Warn, + .phase = PipelinePhase::UserGeneration, + .message = + std::format("WikipediaService: Missing query.pages for '{}'", + std::string(query))}); } return {}; } @@ -83,9 +90,11 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) { if (pages.empty()) { if (logger_) { - logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration, - std::string("WikipediaService: No pages returned for '") + - std::string(query) + "'"); + logger_->Log( + {.level = LogLevel::Warn, + .phase = PipelinePhase::UserGeneration, + .message = std::format("WikipediaService: No pages returned for '{}'", + std::string(query))}); } this->extract_cache_.emplace(cache_key, ""); return {}; @@ -97,9 +106,12 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) { if (!page_val.is_object()) { if (logger_) { - logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration, - std::string("WikipediaService: Unexpected page format for '") + - std::string(query) + "'"); + logger_->Log( + {.level = LogLevel::Warn, + .phase = PipelinePhase::UserGeneration, + .message = + std::format("WikipediaService: Unexpected page format for '{}'", + std::string(query))}); } return {}; } @@ -109,9 +121,10 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) { // Handle 404/Missing status if (page.contains("missing")) { if (logger_) { - logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration, - std::string("WikipediaService: Page '") + std::string(query) + - "' does not exist"); + logger_->Log({.level = LogLevel::Warn, + .phase = PipelinePhase::UserGeneration, + .message = std::format("WikipediaService: Page '{}' does not exist", + std::string(query))}); } this->extract_cache_.emplace(cache_key, ""); return {}; @@ -121,9 +134,12 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) { if ((extract_ptr == nullptr) || !extract_ptr->is_string()) { if (logger_) { - logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration, - std::string("WikipediaService: No extract string found for '") + - std::string(query) + "'"); + logger_->Log( + {.level = LogLevel::Warn, + .phase = PipelinePhase::UserGeneration, + .message = + std::format("WikipediaService: No extract string found for '{}'", + std::string(query))}); } this->extract_cache_.emplace(cache_key, ""); return {}; @@ -132,13 +148,13 @@ std::string WikipediaEnrichmentService::FetchExtract(std::string_view query) { // 4. Success std::string extract(extract_ptr->as_string()); if (logger_) { - logger_->Log(LogLevel::Info, PipelinePhase::UserGeneration, - std::string("WikipediaService: Fetched ") + - std::to_string(extract.size()) + " chars for '" + - std::string(query) + "'"); + logger_->Log({.level = LogLevel::Info, + .phase = PipelinePhase::UserGeneration, + .message = std::format("WikipediaService: Fetched {} chars for '{}'", + extract.size(), std::string(query))}); } this->extract_cache_.insert_or_assign(cache_key, extract); return extract; -} \ No newline at end of file +} diff --git a/tooling/pipeline/src/services/enrichment/wikipedia/get_summary.cc b/tooling/pipeline/src/services/enrichment/wikipedia/get_summary.cc index ac22d19..1df272f 100644 --- a/tooling/pipeline/src/services/enrichment/wikipedia/get_summary.cc +++ b/tooling/pipeline/src/services/enrichment/wikipedia/get_summary.cc @@ -10,12 +10,14 @@ #include "services/enrichment/wikipedia_service.h" -std::string WikipediaEnrichmentService::GetLocationContext(const Location& loc) { +std::string WikipediaEnrichmentService::GetLocationContext( + const Location& loc) { using namespace std::literals::chrono_literals; if (!this->client_) { if (logger_) { - logger_->Log(LogLevel::Warn, PipelinePhase::UserGeneration, - "Wikipedia client is nullptr."); + logger_->Log({.level = LogLevel::Warn, + .phase = PipelinePhase::UserGeneration, + .message = "Wikipedia client is nullptr."}); } return {}; } @@ -48,17 +50,20 @@ std::string WikipediaEnrichmentService::GetLocationContext(const Location& loc) append_extract(FetchExtract(brewing_query)); append_extract(FetchExtract(beer_query)); if (logger_) { - logger_->Log(LogLevel::Info, PipelinePhase::UserGeneration, - std::string("Done fetching for ") + location_query + - ". Sleeping for 10 seconds."); + logger_->Log({.level = LogLevel::Info, + .phase = PipelinePhase::UserGeneration, + .message = std::format("Done fetching for {}. Sleeping for 10 seconds.", + location_query)}); } std::this_thread::sleep_for(10s); } catch (const std::runtime_error& e) { if (logger_) { - logger_->Log(LogLevel::Debug, PipelinePhase::UserGeneration, - std::string("WikipediaService lookup failed for '") + - location_query + "': " + e.what()); + logger_->Log( + {.level = LogLevel::Debug, + .phase = PipelinePhase::UserGeneration, + .message = std::format("WikipediaService lookup failed for '{}': {}", + location_query, e.what())}); } } return result; diff --git a/tooling/pipeline/src/services/logging/log_producer.cc b/tooling/pipeline/src/services/logging/log_producer.cc index c15d592..6c24069 100644 --- a/tooling/pipeline/src/services/logging/log_producer.cc +++ b/tooling/pipeline/src/services/logging/log_producer.cc @@ -16,10 +16,4 @@ LogProducer::LogProducer(BoundedChannel& channel) : channel_(channel) {} -void LogProducer::Log(LogLevel level, PipelinePhase phase, - const std::string_view message) { - channel_.Send(LogEntry{.timestamp = std::chrono::system_clock::now(), - .level = level, - .phase = phase, - .message = std::string(message)}); -} +void LogProducer::Log(const LogEntry& entry) { channel_.Send(entry); } diff --git a/tooling/pipeline/src/services/prompt_directory.cc b/tooling/pipeline/src/services/prompt_directory.cc index 40b0423..ded77b4 100644 --- a/tooling/pipeline/src/services/prompt_directory.cc +++ b/tooling/pipeline/src/services/prompt_directory.cc @@ -6,7 +6,9 @@ #include "services/prompting/prompt_directory.h" +#include #include +#include #include #include #include @@ -43,14 +45,17 @@ PromptDirectory::PromptDirectory(const std::filesystem::path& prompt_dir, std::filesystem::directory_iterator probe(prompt_dir_, ec); if (ec) { throw std::runtime_error( - "PromptDirectory: prompt directory is not readable: " + - prompt_dir_.string() + " (" + ec.message() + ")"); + std::format("PromptDirectory: prompt directory is not readable: {} ({})", + prompt_dir_.string(), ec.message())); } if (logger_) { - logger_->Log(LogLevel::Info, PipelinePhase::Startup, - std::string("[PromptDirectory] Resolved prompt directory: ") + - prompt_dir_.string()); + logger_->Log( + {.level = LogLevel::Info, + .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 /.md and require it to exist. 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); if (!file.is_open()) { throw std::runtime_error( - "PromptDirectory: prompt file not found for key '" + key_str + - "': " + file_path.string()); + std::format("PromptDirectory: prompt file not found for key '{}': {}", + key_str, file_path.string())); } std::string content((std::istreambuf_iterator(file)), @@ -79,15 +84,15 @@ std::string PromptDirectory::Load(std::string_view key) { file.close(); if (content.empty()) { - throw std::runtime_error("PromptDirectory: prompt file for key '" + - key_str + "' is empty: " + file_path.string()); + throw std::runtime_error(std::format("PromptDirectory: prompt file for key '{}' is empty: {}", + key_str, file_path.string())); } if (logger_) { - logger_->Log(LogLevel::Info, PipelinePhase::Startup, - std::string("[PromptDirectory] Loaded prompt '") + key_str + - "' from '" + file_path.string() + "' (" + - std::to_string(content.size()) + " chars)"); + logger_->Log({.level = LogLevel::Info, + .phase = PipelinePhase::Startup, + .message = std::format("[PromptDirectory] Loaded prompt '{}' from '{}' ({} chars)", + key_str, file_path.string(), content.size())}); } cache_.emplace(key_str, content); diff --git a/tooling/pipeline/src/services/sqlite/helpers/sqlite_connection_helpers.cc b/tooling/pipeline/src/services/sqlite/helpers/sqlite_connection_helpers.cc index c527aa3..3602002 100644 --- a/tooling/pipeline/src/services/sqlite/helpers/sqlite_connection_helpers.cc +++ b/tooling/pipeline/src/services/sqlite/helpers/sqlite_connection_helpers.cc @@ -1,5 +1,6 @@ #include "services/database/sqlite_connection_helpers.h" +#include #include namespace sqlite_export_service_internal { @@ -20,7 +21,7 @@ void SqliteStatementDeleter::operator()( void ThrowSqliteError(sqlite3* db_handle, std::string_view action) { const std::string message = db_handle != nullptr ? sqlite3_errmsg(db_handle) : "unknown SQLite error"; - throw std::runtime_error(std::string(action) + ": " + message); + throw std::runtime_error(std::format("{}: {}", action, message)); } SqliteDatabaseHandle OpenDatabase(const std::filesystem::path& path) { @@ -50,7 +51,7 @@ void ExecSql(const SqliteDatabaseHandle& db_handle, std::string_view sql, ? error_message : sqlite3_errmsg(db_handle.get()); sqlite3_free(error_message); - throw std::runtime_error(std::string(action) + ": " + message); + throw std::runtime_error(std::format("{}: {}", action, message)); } } diff --git a/tooling/pipeline/src/services/sqlite/initialize.cc b/tooling/pipeline/src/services/sqlite/initialize.cc index fb66bc9..b7da162 100644 --- a/tooling/pipeline/src/services/sqlite/initialize.cc +++ b/tooling/pipeline/src/services/sqlite/initialize.cc @@ -4,6 +4,7 @@ */ #include +#include #include #include #include @@ -18,8 +19,8 @@ std::filesystem::path SqliteExportService::BuildDatabasePath() const { for (int suffix = 1; std::filesystem::exists(candidate); ++suffix) { candidate = output_path_ / - std::filesystem::path("biergarten_seed_" + run_timestamp_utc_ + - "-" + std::to_string(suffix) + ".sqlite"); + std::filesystem::path(std::format("biergarten_seed_{}-{}.sqlite", + run_timestamp_utc_, suffix)); } return candidate; diff --git a/tooling/pipeline/src/web_client/http_web_client.cc b/tooling/pipeline/src/web_client/http_web_client.cc index d5dc076..dabd669 100644 --- a/tooling/pipeline/src/web_client/http_web_client.cc +++ b/tooling/pipeline/src/web_client/http_web_client.cc @@ -1,5 +1,5 @@ /** -* @file web_client/http_web_client.cc + * @file web_client/http_web_client.cc * @brief cpp-httplib implementation of WebClient. */ @@ -7,6 +7,8 @@ #include +#include +#include #include #include #include @@ -31,7 +33,7 @@ std::pair SplitUrl(const std::string& url) { return {match[1].str(), match[2].matched ? match[2].str() : "/"}; } -} // namespace +} // namespace std::string HttpWebClient::Get(const std::string& 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_connection_timeout(kConnectionTimeoutSeconds); client.set_read_timeout(kReadTimeoutSeconds); - client.set_default_headers({ - {"Accept", "application/json"}, - {"User-Agent", "biergarten-pipeline/1.0"} - }); + client.set_default_headers({{"Accept", "application/json"}, + {"User-Agent", "biergarten-pipeline/1.0"}}); const httplib::Result result = client.Get(path); if (!result) { - throw std::runtime_error( - "[HttpWebClient] Request failed for URL: " + url + - " — " + httplib::to_string(result.error())); + throw std::runtime_error(std::format( + "[HttpWebClient] Request failed for URL: {} — {}", url, + httplib::to_string(result.error()))); } if (result->status < kSuccessMin || result->status >= kSuccessMax) { if (logger_) { - logger_->Log(LogLevel::Error, PipelinePhase::UserGeneration, - std::string("[HttpWebClient] Request failed for URL: ") + - url); + logger_->Log( + {.level = LogLevel::Error, + .phase = PipelinePhase::UserGeneration, + .message = + std::format("[HttpWebClient] Request failed for URL: {}", url)}); } - throw std::runtime_error( - "[HttpWebClient] HTTP " + std::to_string(result->status) + - " for URL: " + url); + throw std::runtime_error(std::format("[HttpWebClient] HTTP {} for URL: {}", + result->status, url)); } return result->body; @@ -69,4 +70,4 @@ std::string HttpWebClient::Get(const std::string& url) { std::string HttpWebClient::EncodeURL(const std::string& value) { return httplib::encode_uri_component(value); -} \ No newline at end of file +}