From ffabd85b6d997c08d4c4ee6b2dbe204f1c3f8d89 Mon Sep 17 00:00:00 2001 From: Aaron Po Date: Sun, 19 Jul 2026 04:10:32 -0400 Subject: [PATCH] Formatted includes/data_model --- .../includes/data_model/generated_models.h | 112 ++++---- tooling/pipeline/includes/data_model/models.h | 250 +++++++++--------- 2 files changed, 181 insertions(+), 181 deletions(-) diff --git a/tooling/pipeline/includes/data_model/generated_models.h b/tooling/pipeline/includes/data_model/generated_models.h index e47def6e..c2e62377 100644 --- a/tooling/pipeline/includes/data_model/generated_models.h +++ b/tooling/pipeline/includes/data_model/generated_models.h @@ -17,64 +17,64 @@ * @brief Generated brewery payload. */ struct BreweryResult { - /** - * @brief Brewery display name in English. - */ - std::string name_en; + /** + * @brief Brewery display name in English. + */ + std::string name_en; - /** - * @brief Brewery description text in English. - */ - std::string description_en; + /** + * @brief Brewery description text in English. + */ + std::string description_en; - /** - * @brief Brewery display name in the local language. - */ - std::string name_local; + /** + * @brief Brewery display name in the local language. + */ + std::string name_local; - /** - * @brief Brewery description text in the local language. - */ - std::string description_local; + /** + * @brief Brewery description text in the local language. + */ + std::string description_local; }; /** * @brief Generated user profile payload. */ struct UserResult { - /** - * @brief First (given) name, copied from the sampled Name -- not - * LLM-invented. - */ - std::string first_name{}; + /** + * @brief First (given) name, copied from the sampled Name -- not + * LLM-invented. + */ + std::string first_name{}; - /** - * @brief Last (family) name, copied from the sampled Name -- not - * LLM-invented. - */ - std::string last_name{}; + /** + * @brief Last (family) name, copied from the sampled Name -- not + * LLM-invented. + */ + std::string last_name{}; - /** - * @brief Gender associated with the sampled first name, copied from the - * sampled Name -- not LLM-invented. - */ - std::string gender{}; + /** + * @brief Gender associated with the sampled first name, copied from the + * sampled Name -- not LLM-invented. + */ + std::string gender{}; - /** - * @brief Username handle. - */ - std::string username{}; + /** + * @brief Username handle. + */ + std::string username{}; - /** - * @brief Short user biography. - */ - std::string bio{}; + /** + * @brief Short user biography. + */ + std::string bio{}; - /** - * @brief Relative check-in/activity weight for this user, used to drive - * a J-curve activity profile in later pipeline phases. - */ - float activity_weight{}; + /** + * @brief Relative check-in/activity weight for this user, used to drive + * a J-curve activity profile in later pipeline phases. + */ + float activity_weight{}; }; // Pipeline Data Models @@ -83,8 +83,8 @@ struct UserResult { * @brief Enriched city data with Wikipedia context. */ struct EnrichedCity { - City location; - std::string region_context{}; + City location; + std::string region_context{}; }; /** @@ -92,8 +92,8 @@ struct EnrichedCity { * from that city's curated postal-code examples. */ struct BreweryAddress { - City city; - std::string postal_code{}; + City city; + std::string postal_code{}; }; /** @@ -101,16 +101,16 @@ struct BreweryAddress { * postal code selected from that city's curated postal-code examples. */ struct UserAddress { - City city; - std::string postal_code{}; + City city; + std::string postal_code{}; }; /** * @brief Helper struct to store generated brewery data. */ struct BreweryRecord { - BreweryAddress address; - BreweryResult brewery; + BreweryAddress address; + BreweryResult brewery; }; /** @@ -121,10 +121,10 @@ struct BreweryRecord { * consumer can register real accounts from the pipeline's SQLite export. */ struct UserRecord { - UserAddress address; - UserResult user; - std::string email{}; - std::string date_of_birth{}; + UserAddress address; + UserResult user; + std::string email{}; + std::string date_of_birth{}; }; #endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_MODEL_GENERATED_MODELS_H_ diff --git a/tooling/pipeline/includes/data_model/models.h b/tooling/pipeline/includes/data_model/models.h index 25e7b976..3705e134 100644 --- a/tooling/pipeline/includes/data_model/models.h +++ b/tooling/pipeline/includes/data_model/models.h @@ -28,54 +28,54 @@ namespace prog_opts = boost::program_options; * `postal_code` object in the locations dataset. */ struct PostalCodeSpec { - /** - * @brief Permissive country-wide postal-code format regex, used as the - * validation fallback for a selected example. - */ - std::string country_format_regex{}; + /** + * @brief Permissive country-wide postal-code format regex, used as the + * validation fallback for a selected example. + */ + std::string country_format_regex{}; - /** - * @brief City-specific postal-code regexes (more precise than the country - * format). - */ - std::vector city_regexes{}; + /** + * @brief City-specific postal-code regexes (more precise than the country + * format). + */ + std::vector city_regexes{}; - /** - * @brief Concrete example postal codes for this city. The postal code - * service selects from these rather than synthesizing codes. - */ - std::vector examples{}; + /** + * @brief Concrete example postal codes for this city. The postal code + * service selects from these rather than synthesizing codes. + */ + std::vector examples{}; }; /** * @brief Canonical city record for city-level generation. */ struct City { - std::string city{}; - std::string state_province{}; + std::string city{}; + std::string state_province{}; - /** - * @brief ISO 3166-2 subdivision code. - */ - std::string iso3166_2{}; + /** + * @brief ISO 3166-2 subdivision code. + */ + std::string iso3166_2{}; - std::string country{}; + std::string country{}; - /** - * @brief ISO 3166-1 country code. - */ - std::string iso3166_1{}; + /** + * @brief ISO 3166-1 country code. + */ + std::string iso3166_1{}; - /** - * @brief Local language codes in priority order. - */ - std::vector local_languages{}; + /** + * @brief Local language codes in priority order. + */ + std::vector local_languages{}; - /** - * @brief Postal-code metadata (format regex, city regexes, and concrete - * examples) sourced directly from the curated locations dataset. - */ - PostalCodeSpec postal_code{}; + /** + * @brief Postal-code metadata (format regex, city regexes, and concrete + * examples) sourced directly from the curated locations dataset. + */ + PostalCodeSpec postal_code{}; }; // Name / Persona Models @@ -86,44 +86,44 @@ struct City { * Produced by the SampleName() helper in generate_users.cc. */ struct Name { - std::string first_name{}; - std::string last_name{}; + std::string first_name{}; + std::string last_name{}; - /** - * @brief Gender associated with the sampled forename (e.g. "M", "F"), as - * reported by the source dataset. - */ - std::string gender{}; + /** + * @brief Gender associated with the sampled forename (e.g. "M", "F"), as + * reported by the source dataset. + */ + std::string gender{}; }; /** * @brief A single forename entry from the names-by-country fixture data. */ struct ForenameEntry { - /** - * @brief Romanized forename. - */ - std::string name{}; + /** + * @brief Romanized forename. + */ + std::string name{}; - /** - * @brief Gender associated with this forename, as reported by the source - * dataset (e.g. "M", "F"). - */ - std::string gender{}; + /** + * @brief Gender associated with this forename, as reported by the source + * dataset (e.g. "M", "F"). + */ + std::string gender{}; - bool operator==(const ForenameEntry& other) const { - return name == other.name && gender == other.gender; - } + bool operator==(const ForenameEntry& other) const { + return name == other.name && gender == other.gender; + } }; namespace std { template <> struct hash { - size_t operator()(const ForenameEntry& entry) const noexcept { - const size_t name_hash = std::hash{}(entry.name); - const size_t gender_hash = std::hash{}(entry.gender); - return name_hash ^ (gender_hash << 1); - } + size_t operator()(const ForenameEntry& entry) const noexcept { + const size_t name_hash = std::hash{}(entry.name); + const size_t gender_hash = std::hash{}(entry.gender); + return name_hash ^ (gender_hash << 1); + } }; } // namespace std @@ -131,20 +131,20 @@ struct hash { * @brief A persona archetype used to ground LLM-generated user bios. */ struct UserPersona { - /** - * @brief Persona display name (e.g. "Hophead Explorer"). - */ - std::string name{}; + /** + * @brief Persona display name (e.g. "Hophead Explorer"). + */ + std::string name{}; - /** - * @brief Short description of the persona's interests and voice. - */ - std::string description{}; + /** + * @brief Short description of the persona's interests and voice. + */ + std::string description{}; - /** - * @brief Beer styles this persona gravitates toward. - */ - std::vector style_affinities{}; + /** + * @brief Beer styles this persona gravitates toward. + */ + std::vector style_affinities{}; }; // Configuration Models @@ -153,88 +153,88 @@ struct UserPersona { * @brief LLM sampling parameters. */ struct SamplingOptions { - /** - * @brief LLM sampling temperature (higher = more random). - */ - float temperature = 1.0F; + /** + * @brief LLM sampling temperature (higher = more random). + */ + float temperature = 1.0F; - /** - * @brief LLM nucleus sampling top-p parameter. - */ - float top_p = 0.95F; + /** + * @brief LLM nucleus sampling top-p parameter. + */ + float top_p = 0.95F; - /** - * @brief LLM top-k sampling parameter. - */ - uint32_t top_k = 64; + /** + * @brief LLM top-k sampling parameter. + */ + uint32_t top_k = 64; - /** - * @brief Context window size (tokens). - */ - uint32_t n_ctx = 8192; + /** + * @brief Context window size (tokens). + */ + uint32_t n_ctx = 8192; - /** - * @brief Random seed (-1 for random, otherwise non-negative). - */ - int seed = -1; + /** + * @brief Random seed (-1 for random, otherwise non-negative). + */ + int seed = -1; - /** - * @brief Number of layers to offload to GPU. - */ - int n_gpu_layers = 0; + /** + * @brief Number of layers to offload to GPU. + */ + int n_gpu_layers = 0; }; /** * @brief Configuration for the LLM generator component. */ struct GeneratorOptions { - /** - * @brief Path to the LLM model file (gguf format). - */ - std::filesystem::path model_path; + /** + * @brief Path to the LLM model file (gguf format). + */ + std::filesystem::path model_path; - /** - * @brief Use mocked generator instead of actual LLM inference. - */ - bool use_mocked = false; + /** + * @brief Use mocked generator instead of actual LLM inference. + */ + bool use_mocked = false; - /** - * @brief Specific sampling parameters for this generator. - * If nullopt, the application should use global defaults. - */ - std::optional sampling; + /** + * @brief Specific sampling parameters for this generator. + * If nullopt, the application should use global defaults. + */ + std::optional sampling; }; /** * @brief Configuration for the pipeline execution and output. */ struct PipelineOptions { - /** - * @brief Directory for generated artifacts. - */ - std::filesystem::path output_path; + /** + * @brief Directory for generated artifacts. + */ + std::filesystem::path output_path; - /** - * @brief Directory that contains named prompt files (e.g. - * BREWERY_GENERATION.md). - */ - std::filesystem::path prompt_dir; + /** + * @brief Directory that contains named prompt files (e.g. + * BREWERY_GENERATION.md). + */ + std::filesystem::path prompt_dir; - std::filesystem::path log_path; + std::filesystem::path log_path; - /** - * @brief Number of locations to sample from the dataset - * More locations -> more users/more breweries - */ - uint32_t location_count; + /** + * @brief Number of locations to sample from the dataset + * More locations -> more users/more breweries + */ + uint32_t location_count; }; /** * @brief Root configuration object for the Biergarten pipeline. */ struct ApplicationOptions { - GeneratorOptions generator; - PipelineOptions pipeline; + GeneratorOptions generator; + PipelineOptions pipeline; }; // Function Declarations