mirror of
https://github.com/aaronpo97/the-biergarten-app.git
synced 2026-10-14 17:54:42 +00:00
Formatting
This commit is contained in:
Aaron Po
@@ -24,98 +24,98 @@
|
||||
* Handles location loading, city enrichment, and brewery/user generation.
|
||||
*/
|
||||
class BiergartenPipelineOrchestrator {
|
||||
public:
|
||||
/**
|
||||
* @brief Constructs the orchestrator with injected pipeline dependencies.
|
||||
*
|
||||
* @param logger Sink for pipeline diagnostics.
|
||||
* @param context_service Provides regional context for locations.
|
||||
* @param generator Implementation (Llama or Mock) for brewery/user
|
||||
* generation.
|
||||
* @param exporter Database backend for persisting generated records.
|
||||
* @param curated_data_service Loads curated location, persona, and name
|
||||
* data used to seed generation.
|
||||
* @param postal_code_service Resolves a postal code for a city from its
|
||||
* curated postal-code data.
|
||||
* @param application_options CLI configuration and paths.
|
||||
*/
|
||||
BiergartenPipelineOrchestrator(
|
||||
std::shared_ptr<ILogger> logger,
|
||||
std::unique_ptr<IEnrichmentService> context_service,
|
||||
std::unique_ptr<DataGenerator> generator,
|
||||
std::unique_ptr<IExportService> exporter,
|
||||
std::unique_ptr<ICuratedDataService> curated_data_service,
|
||||
std::unique_ptr<IPostalCodeService> postal_code_service,
|
||||
const ApplicationOptions& application_options);
|
||||
public:
|
||||
/**
|
||||
* @brief Constructs the orchestrator with injected pipeline dependencies.
|
||||
*
|
||||
* @param logger Sink for pipeline diagnostics.
|
||||
* @param context_service Provides regional context for locations.
|
||||
* @param generator Implementation (Llama or Mock) for brewery/user
|
||||
* generation.
|
||||
* @param exporter Database backend for persisting generated records.
|
||||
* @param curated_data_service Loads curated location, persona, and name
|
||||
* data used to seed generation.
|
||||
* @param postal_code_service Resolves a postal code for a city from its
|
||||
* curated postal-code data.
|
||||
* @param application_options CLI configuration and paths.
|
||||
*/
|
||||
BiergartenPipelineOrchestrator(
|
||||
std::shared_ptr<ILogger> logger,
|
||||
std::unique_ptr<IEnrichmentService> context_service,
|
||||
std::unique_ptr<DataGenerator> generator,
|
||||
std::unique_ptr<IExportService> exporter,
|
||||
std::unique_ptr<ICuratedDataService> curated_data_service,
|
||||
std::unique_ptr<IPostalCodeService> postal_code_service,
|
||||
const ApplicationOptions& application_options);
|
||||
|
||||
/**
|
||||
* @brief Run the data generation pipeline.
|
||||
*
|
||||
* Performs the following steps:
|
||||
* 1. Load curated locations from JSON
|
||||
* 2. Resolve context for each city using the injected context service
|
||||
* 3. Generate brewery and user data for sampled cities
|
||||
*
|
||||
* @note STRUCTURAL CONCURRENCY REQUIREMENT:
|
||||
* When transitioned to a multithreaded design, this method MUST
|
||||
* structurally enforce that all deployed worker threads are joined before
|
||||
* returning (e.g. by using std::jthread or a structured concurrency
|
||||
* primitive). This ensures workers do not attempt to log to a closed
|
||||
* channel during application teardown.
|
||||
*
|
||||
* @return true if successful, false if not
|
||||
*/
|
||||
bool Run();
|
||||
/**
|
||||
* @brief Run the data generation pipeline.
|
||||
*
|
||||
* Performs the following steps:
|
||||
* 1. Load curated locations from JSON
|
||||
* 2. Resolve context for each city using the injected context service
|
||||
* 3. Generate brewery and user data for sampled cities
|
||||
*
|
||||
* @note STRUCTURAL CONCURRENCY REQUIREMENT:
|
||||
* When transitioned to a multithreaded design, this method MUST
|
||||
* structurally enforce that all deployed worker threads are joined before
|
||||
* returning (e.g. by using std::jthread or a structured concurrency
|
||||
* primitive). This ensures workers do not attempt to log to a closed
|
||||
* channel during application teardown.
|
||||
*
|
||||
* @return true if successful, false if not
|
||||
*/
|
||||
bool Run();
|
||||
|
||||
private:
|
||||
std::shared_ptr<ILogger> logger_;
|
||||
std::unique_ptr<IEnrichmentService> context_service_;
|
||||
private:
|
||||
std::shared_ptr<ILogger> logger_;
|
||||
std::unique_ptr<IEnrichmentService> context_service_;
|
||||
|
||||
/**
|
||||
* @brief Generator implementation selected at the composition root (Llama
|
||||
* or Mock).
|
||||
*/
|
||||
std::unique_ptr<DataGenerator> generator_;
|
||||
/**
|
||||
* @brief Generator implementation selected at the composition root (Llama
|
||||
* or Mock).
|
||||
*/
|
||||
std::unique_ptr<DataGenerator> generator_;
|
||||
|
||||
/**
|
||||
* @brief Storage backend for generated brewery and user records.
|
||||
*/
|
||||
std::unique_ptr<IExportService> exporter_;
|
||||
std::unique_ptr<ICuratedDataService> curated_data_service_;
|
||||
std::unique_ptr<IPostalCodeService> postal_code_service_;
|
||||
/**
|
||||
* @brief Storage backend for generated brewery and user records.
|
||||
*/
|
||||
std::unique_ptr<IExportService> exporter_;
|
||||
std::unique_ptr<ICuratedDataService> curated_data_service_;
|
||||
std::unique_ptr<IPostalCodeService> postal_code_service_;
|
||||
|
||||
ApplicationOptions application_options_;
|
||||
ApplicationOptions application_options_;
|
||||
|
||||
/**
|
||||
* @brief Load locations from JSON and sample cities.
|
||||
*
|
||||
* @return Vector of locations randomly sampled per
|
||||
* PipelineOptions::location_count.
|
||||
*/
|
||||
std::vector<City> QueryLocations();
|
||||
/**
|
||||
* @brief Load locations from JSON and sample cities.
|
||||
*
|
||||
* @return Vector of locations randomly sampled per
|
||||
* PipelineOptions::location_count.
|
||||
*/
|
||||
std::vector<City> QueryLocations();
|
||||
|
||||
/**
|
||||
* @brief Generate breweries for enriched cities.
|
||||
*
|
||||
* @param cities Span of enriched city data.
|
||||
*/
|
||||
void GenerateBreweries(std::span<const EnrichedCity> cities);
|
||||
/**
|
||||
* @brief Generate breweries for enriched cities.
|
||||
*
|
||||
* @param cities Span of enriched city data.
|
||||
*/
|
||||
void GenerateBreweries(std::span<const EnrichedCity> cities);
|
||||
|
||||
/**
|
||||
* @brief Generate users grounded in sampled names and personas for
|
||||
* enriched cities.
|
||||
*
|
||||
* @param cities Span of enriched city data.
|
||||
*/
|
||||
void GenerateUsers(std::span<const EnrichedCity> cities);
|
||||
/**
|
||||
* @brief Generate users grounded in sampled names and personas for
|
||||
* enriched cities.
|
||||
*
|
||||
* @param cities Span of enriched city data.
|
||||
*/
|
||||
void GenerateUsers(std::span<const EnrichedCity> cities);
|
||||
|
||||
/**
|
||||
* @brief Log the generated brewery and user results.
|
||||
*/
|
||||
void LogResults() const;
|
||||
/**
|
||||
* @brief Log the generated brewery and user results.
|
||||
*/
|
||||
void LogResults() const;
|
||||
|
||||
std::vector<BreweryRecord> generated_breweries_;
|
||||
std::vector<UserRecord> generated_users_;
|
||||
std::vector<BreweryRecord> generated_breweries_;
|
||||
std::vector<UserRecord> generated_users_;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_BIERGARTEN_PIPELINE_ORCHESTRATOR_H_
|
||||
|
||||
@@ -26,45 +26,45 @@
|
||||
*/
|
||||
template <typename T>
|
||||
class BoundedChannel {
|
||||
// Internal state — all access must be guarded by mutex_.
|
||||
// Internal state — all access must be guarded by mutex_.
|
||||
|
||||
std::queue<T> queue_;
|
||||
std::queue<T> queue_;
|
||||
|
||||
std::mutex mutex_;
|
||||
std::mutex mutex_;
|
||||
|
||||
std::condition_variable not_full_;
|
||||
std::condition_variable not_full_;
|
||||
|
||||
std::condition_variable not_empty_;
|
||||
std::condition_variable not_empty_;
|
||||
|
||||
std::size_t capacity_;
|
||||
std::size_t capacity_;
|
||||
|
||||
bool closed_ = false;
|
||||
bool closed_ = false;
|
||||
|
||||
public:
|
||||
/**
|
||||
* @brief Construct a bounded channel with the given capacity.
|
||||
* @param capacity Maximum number of items the channel may hold.
|
||||
*/
|
||||
explicit BoundedChannel(std::size_t capacity) : capacity_(capacity) {}
|
||||
public:
|
||||
/**
|
||||
* @brief Construct a bounded channel with the given capacity.
|
||||
* @param capacity Maximum number of items the channel may hold.
|
||||
*/
|
||||
explicit BoundedChannel(std::size_t capacity) : capacity_(capacity) {}
|
||||
|
||||
/**
|
||||
* @brief Send an item into the channel. Blocks when the channel is full.
|
||||
* @param item Move-only item to enqueue.
|
||||
*/
|
||||
void Send(T item);
|
||||
/**
|
||||
* @brief Send an item into the channel. Blocks when the channel is full.
|
||||
* @param item Move-only item to enqueue.
|
||||
*/
|
||||
void Send(T item);
|
||||
|
||||
/**
|
||||
* @brief Receive an item from the channel. Blocks when the channel is
|
||||
* empty.
|
||||
* @return std::optional<T> containing the item, or std::nullopt when the
|
||||
* channel is closed and drained.
|
||||
*/
|
||||
std::optional<T> Receive();
|
||||
/**
|
||||
* @brief Receive an item from the channel. Blocks when the channel is
|
||||
* empty.
|
||||
* @return std::optional<T> containing the item, or std::nullopt when the
|
||||
* channel is closed and drained.
|
||||
*/
|
||||
std::optional<T> Receive();
|
||||
|
||||
/**
|
||||
* @brief Close the channel and unblock all waiting threads. Idempotent.
|
||||
*/
|
||||
void Close();
|
||||
/**
|
||||
* @brief Close the channel and unblock all waiting threads. Idempotent.
|
||||
*/
|
||||
void Close();
|
||||
};
|
||||
|
||||
// Include the template implementation
|
||||
|
||||
@@ -14,28 +14,28 @@
|
||||
* @brief Interface for data generator implementations.
|
||||
*/
|
||||
class DataGenerator {
|
||||
public:
|
||||
virtual ~DataGenerator() = default;
|
||||
public:
|
||||
virtual ~DataGenerator() = default;
|
||||
|
||||
/**
|
||||
* @brief Generates brewery data for a location.
|
||||
*
|
||||
* @param city Enriched city the brewery is associated with.
|
||||
* @return Brewery generation result.
|
||||
*/
|
||||
virtual BreweryResult GenerateBrewery(const EnrichedCity& city) = 0;
|
||||
/**
|
||||
* @brief Generates brewery data for a location.
|
||||
*
|
||||
* @param city Enriched city the brewery is associated with.
|
||||
* @return Brewery generation result.
|
||||
*/
|
||||
virtual BreweryResult GenerateBrewery(const EnrichedCity& city) = 0;
|
||||
|
||||
/**
|
||||
* @brief Generates a user profile grounded in a sampled name and persona.
|
||||
*
|
||||
* @param city Enriched city the user is associated with.
|
||||
* @param persona Persona archetype grounding the generated bio.
|
||||
* @param name Sampled first/last name (and gender)
|
||||
* @return User generation result.
|
||||
*/
|
||||
virtual UserResult GenerateUser(const EnrichedCity& city,
|
||||
const UserPersona& persona,
|
||||
const Name& name) = 0;
|
||||
/**
|
||||
* @brief Generates a user profile grounded in a sampled name and persona.
|
||||
*
|
||||
* @param city Enriched city the user is associated with.
|
||||
* @param persona Persona archetype grounding the generated bio.
|
||||
* @param name Sampled first/last name (and gender)
|
||||
* @return User generation result.
|
||||
*/
|
||||
virtual UserResult GenerateUser(const EnrichedCity& city,
|
||||
const UserPersona& persona,
|
||||
const Name& name) = 0;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_DATA_GENERATOR_H_
|
||||
|
||||
@@ -26,110 +26,112 @@ struct llama_context;
|
||||
* @brief Data generator implementation backed by llama.cpp.
|
||||
*/
|
||||
class LlamaGenerator final : public DataGenerator {
|
||||
public:
|
||||
/**
|
||||
* @brief Constructs a generator using parsed application options and loads
|
||||
* the configured model immediately.
|
||||
*
|
||||
* @param options Parsed application options.
|
||||
* @param model_path Filesystem path to GGUF model assets.
|
||||
* @param prompt_formatter Formatter that produces model-specific prompts.
|
||||
* @param prompt_directory Directory service for loading named prompt files.
|
||||
*/
|
||||
LlamaGenerator(const ApplicationOptions& options,
|
||||
const std::string& model_path, std::shared_ptr<ILogger> logger,
|
||||
std::unique_ptr<IPromptFormatter> prompt_formatter,
|
||||
std::unique_ptr<IPromptDirectory> prompt_directory);
|
||||
public:
|
||||
/**
|
||||
* @brief Constructs a generator using parsed application options and loads
|
||||
* the configured model immediately.
|
||||
*
|
||||
* @param options Parsed application options.
|
||||
* @param model_path Filesystem path to GGUF model assets.
|
||||
* @param prompt_formatter Formatter that produces model-specific prompts.
|
||||
* @param prompt_directory Directory service for loading named prompt files.
|
||||
*/
|
||||
LlamaGenerator(const ApplicationOptions& options,
|
||||
const std::string& model_path,
|
||||
std::shared_ptr<ILogger> logger,
|
||||
std::unique_ptr<IPromptFormatter> prompt_formatter,
|
||||
std::unique_ptr<IPromptDirectory> prompt_directory);
|
||||
|
||||
~LlamaGenerator() override;
|
||||
~LlamaGenerator() override;
|
||||
|
||||
LlamaGenerator(const LlamaGenerator&) = delete;
|
||||
LlamaGenerator& operator=(const LlamaGenerator&) = delete;
|
||||
LlamaGenerator(LlamaGenerator&&) = delete;
|
||||
LlamaGenerator& operator=(LlamaGenerator&&) = delete;
|
||||
LlamaGenerator(const LlamaGenerator&) = delete;
|
||||
LlamaGenerator& operator=(const LlamaGenerator&) = delete;
|
||||
LlamaGenerator(LlamaGenerator&&) = delete;
|
||||
LlamaGenerator& operator=(LlamaGenerator&&) = delete;
|
||||
|
||||
/**
|
||||
* @brief Generates brewery data for a specific location.
|
||||
*
|
||||
* @param location City object.
|
||||
* @param region_context Additional regional context.
|
||||
* @return Generated brewery result.
|
||||
*/
|
||||
BreweryResult GenerateBrewery(const EnrichedCity&) override;
|
||||
/**
|
||||
* @brief Generates brewery data for a specific location.
|
||||
*
|
||||
* @param location City object.
|
||||
* @param region_context Additional regional context.
|
||||
* @return Generated brewery result.
|
||||
*/
|
||||
BreweryResult GenerateBrewery(const EnrichedCity&) override;
|
||||
|
||||
/**
|
||||
* @brief Generates a user profile grounded in a sampled name and persona.
|
||||
*
|
||||
* @param city Enriched city the user is associated with.
|
||||
* @param persona Persona archetype grounding the generated bio.
|
||||
* @param name Sampled first/last name -- not LLM-invented.
|
||||
* @return Generated user profile.
|
||||
*/
|
||||
UserResult GenerateUser(const EnrichedCity& city, const UserPersona& persona,
|
||||
const Name& name) override;
|
||||
/**
|
||||
* @brief Generates a user profile grounded in a sampled name and persona.
|
||||
*
|
||||
* @param city Enriched city the user is associated with.
|
||||
* @param persona Persona archetype grounding the generated bio.
|
||||
* @param name Sampled first/last name -- not LLM-invented.
|
||||
* @return Generated user profile.
|
||||
*/
|
||||
UserResult GenerateUser(const EnrichedCity& city, const UserPersona& persona,
|
||||
const Name& name) override;
|
||||
|
||||
private:
|
||||
static constexpr int32_t kDefaultMaxTokens = 10000;
|
||||
static constexpr float kDefaultSamplingTopP = 0.95F;
|
||||
static constexpr uint32_t kDefaultSamplingTopK = 64;
|
||||
static constexpr uint32_t kDefaultContextSize = 8192;
|
||||
private:
|
||||
static constexpr int32_t kDefaultMaxTokens = 10000;
|
||||
static constexpr float kDefaultSamplingTopP = 0.95F;
|
||||
static constexpr uint32_t kDefaultSamplingTopK = 64;
|
||||
static constexpr uint32_t kDefaultContextSize = 8192;
|
||||
|
||||
struct ModelDeleter {
|
||||
void operator()(llama_model* model) const noexcept;
|
||||
};
|
||||
struct ContextDeleter {
|
||||
void operator()(llama_context* context) const noexcept;
|
||||
};
|
||||
struct ModelDeleter {
|
||||
void operator()(llama_model* model) const noexcept;
|
||||
};
|
||||
struct ContextDeleter {
|
||||
void operator()(llama_context* context) const noexcept;
|
||||
};
|
||||
|
||||
using ModelHandle = std::unique_ptr<llama_model, ModelDeleter>;
|
||||
using ContextHandle = std::unique_ptr<llama_context, ContextDeleter>;
|
||||
using ModelHandle = std::unique_ptr<llama_model, ModelDeleter>;
|
||||
using ContextHandle = std::unique_ptr<llama_context, ContextDeleter>;
|
||||
|
||||
/**
|
||||
* @brief Loads model and prepares inference context.
|
||||
*
|
||||
* @param model_path Filesystem path to GGUF model.
|
||||
*/
|
||||
void Load(const std::string& model_path);
|
||||
/**
|
||||
* @brief Loads model and prepares inference context.
|
||||
*
|
||||
* @param model_path Filesystem path to GGUF model.
|
||||
*/
|
||||
void Load(const std::string& model_path);
|
||||
|
||||
/**
|
||||
* @brief Infers text from separate system and user prompts.
|
||||
*
|
||||
* This helps chat-capable models preserve system-role behavior instead of
|
||||
* concatenating system text into user input.
|
||||
*
|
||||
* @param system_prompt System role prompt.
|
||||
* @param prompt User prompt.
|
||||
* @param max_tokens Maximum tokens to generate.
|
||||
* @param grammar Optional GBNF grammar constraining generated output.
|
||||
* @return Generated text.
|
||||
*/
|
||||
std::string Infer(const std::string& system_prompt, const std::string& prompt,
|
||||
int max_tokens = kDefaultMaxTokens,
|
||||
std::string_view grammar = {});
|
||||
/**
|
||||
* @brief Infers text from separate system and user prompts.
|
||||
*
|
||||
* This helps chat-capable models preserve system-role behavior instead of
|
||||
* concatenating system text into user input.
|
||||
*
|
||||
* @param system_prompt System role prompt.
|
||||
* @param prompt User prompt.
|
||||
* @param max_tokens Maximum tokens to generate.
|
||||
* @param grammar Optional GBNF grammar constraining generated output.
|
||||
* @return Generated text.
|
||||
*/
|
||||
std::string Infer(const std::string& system_prompt,
|
||||
const std::string& prompt,
|
||||
int max_tokens = kDefaultMaxTokens,
|
||||
std::string_view grammar = {});
|
||||
|
||||
/**
|
||||
* @brief Runs inference on an already-formatted prompt.
|
||||
*
|
||||
* @param formatted_prompt Prompt preformatted for model chat template.
|
||||
* @param max_tokens Maximum tokens to generate.
|
||||
* @param grammar Optional GBNF grammar constraining generated output.
|
||||
* @return Generated text.
|
||||
*/
|
||||
std::string InferFormatted(const std::string& formatted_prompt,
|
||||
int max_tokens = kDefaultMaxTokens,
|
||||
std::string_view grammar = {});
|
||||
/**
|
||||
* @brief Runs inference on an already-formatted prompt.
|
||||
*
|
||||
* @param formatted_prompt Prompt preformatted for model chat template.
|
||||
* @param max_tokens Maximum tokens to generate.
|
||||
* @param grammar Optional GBNF grammar constraining generated output.
|
||||
* @return Generated text.
|
||||
*/
|
||||
std::string InferFormatted(const std::string& formatted_prompt,
|
||||
int max_tokens = kDefaultMaxTokens,
|
||||
std::string_view grammar = {});
|
||||
|
||||
ModelHandle model_;
|
||||
ContextHandle context_;
|
||||
float sampling_temperature_ = 1.0F;
|
||||
float sampling_top_p_ = kDefaultSamplingTopP;
|
||||
uint32_t sampling_top_k_ = kDefaultSamplingTopK;
|
||||
std::mt19937 rng_;
|
||||
uint32_t n_ctx_ = kDefaultContextSize;
|
||||
int n_gpu_layers_ = 0;
|
||||
std::shared_ptr<ILogger> logger_;
|
||||
std::unique_ptr<IPromptFormatter> prompt_formatter_;
|
||||
std::unique_ptr<IPromptDirectory> prompt_directory_;
|
||||
ModelHandle model_;
|
||||
ContextHandle context_;
|
||||
float sampling_temperature_ = 1.0F;
|
||||
float sampling_top_p_ = kDefaultSamplingTopP;
|
||||
uint32_t sampling_top_k_ = kDefaultSamplingTopK;
|
||||
std::mt19937 rng_;
|
||||
uint32_t n_ctx_ = kDefaultContextSize;
|
||||
int n_gpu_layers_ = 0;
|
||||
std::shared_ptr<ILogger> logger_;
|
||||
std::unique_ptr<IPromptFormatter> prompt_formatter_;
|
||||
std::unique_ptr<IPromptDirectory> prompt_directory_;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_LLAMA_GENERATOR_H_
|
||||
|
||||
@@ -16,128 +16,129 @@
|
||||
* @brief Mock generator used for deterministic, model-free outputs.
|
||||
*/
|
||||
class MockGenerator final : public DataGenerator {
|
||||
public:
|
||||
/**
|
||||
* @brief Generates deterministic brewery data for a location.
|
||||
*
|
||||
* @param enriched_city
|
||||
* @return Generated brewery result.
|
||||
*/
|
||||
public:
|
||||
/**
|
||||
* @brief Generates deterministic brewery data for a location.
|
||||
*
|
||||
* @param enriched_city
|
||||
* @return Generated brewery result.
|
||||
*/
|
||||
|
||||
BreweryResult GenerateBrewery(const EnrichedCity& enriched_city) override;
|
||||
/**
|
||||
* @brief Generates deterministic user data grounded in a sampled name and
|
||||
* persona.
|
||||
BreweryResult GenerateBrewery(const EnrichedCity& enriched_city) override;
|
||||
/**
|
||||
* @brief Generates deterministic user data grounded in a sampled name and
|
||||
* persona.
|
||||
|
||||
* @return Generated user result.
|
||||
*/
|
||||
UserResult GenerateUser(const EnrichedCity& city, const UserPersona& persona,
|
||||
const Name& name) override;
|
||||
* @return Generated user result.
|
||||
*/
|
||||
UserResult GenerateUser(const EnrichedCity& city, const UserPersona& persona,
|
||||
const Name& name) override;
|
||||
|
||||
private:
|
||||
/**
|
||||
* @brief Combines two strings into a stable hash value.
|
||||
*
|
||||
* @param location City and country names.
|
||||
* @return Deterministic hash value.
|
||||
*/
|
||||
static size_t DeterministicHash(const City& location);
|
||||
private:
|
||||
/**
|
||||
* @brief Combines two strings into a stable hash value.
|
||||
*
|
||||
* @param location City and country names.
|
||||
* @return Deterministic hash value.
|
||||
*/
|
||||
static size_t DeterministicHash(const City& location);
|
||||
|
||||
/**
|
||||
* @brief Combines city, persona, and name into a stable hash value.
|
||||
*
|
||||
* @param location City and country names.
|
||||
* @param persona Persona archetype.
|
||||
* @param name Sampled first/last name.
|
||||
* @return Deterministic hash value.
|
||||
*/
|
||||
static size_t DeterministicHash(const City& location,
|
||||
const UserPersona& persona, const Name& name);
|
||||
/**
|
||||
* @brief Combines city, persona, and name into a stable hash value.
|
||||
*
|
||||
* @param location City and country names.
|
||||
* @param persona Persona archetype.
|
||||
* @param name Sampled first/last name.
|
||||
* @return Deterministic hash value.
|
||||
*/
|
||||
static size_t DeterministicHash(const City& location,
|
||||
const UserPersona& persona,
|
||||
const Name& name);
|
||||
|
||||
// Hash stride constants for deterministic distribution across fixed-size
|
||||
// arrays. These coprime strides spread hash values uniformly without
|
||||
// clustering, ensuring diverse output across different hash inputs.
|
||||
static constexpr size_t kNounHashStride = 7;
|
||||
static constexpr size_t kDescriptionHashStride = 13;
|
||||
static constexpr size_t kBioHashStride = 11;
|
||||
static constexpr size_t kActivityWeightHashStride = 17;
|
||||
static constexpr size_t kActivityWeightHashRange = 1000;
|
||||
// Hash stride constants for deterministic distribution across fixed-size
|
||||
// arrays. These coprime strides spread hash values uniformly without
|
||||
// clustering, ensuring diverse output across different hash inputs.
|
||||
static constexpr size_t kNounHashStride = 7;
|
||||
static constexpr size_t kDescriptionHashStride = 13;
|
||||
static constexpr size_t kBioHashStride = 11;
|
||||
static constexpr size_t kActivityWeightHashStride = 17;
|
||||
static constexpr size_t kActivityWeightHashRange = 1000;
|
||||
|
||||
static constexpr std::array<std::string_view, 18> kBreweryAdjectives = {
|
||||
"Craft", "Heritage", "Local", "Artisan", "Pioneer", "Golden",
|
||||
"Modern", "Classic", "Summit", "Northern", "Riverstone", "Barrel",
|
||||
"Hinterland", "Harbor", "Wild", "Granite", "Copper", "Maple"};
|
||||
static constexpr std::array<std::string_view, 18> kBreweryAdjectives = {
|
||||
"Craft", "Heritage", "Local", "Artisan", "Pioneer", "Golden",
|
||||
"Modern", "Classic", "Summit", "Northern", "Riverstone", "Barrel",
|
||||
"Hinterland", "Harbor", "Wild", "Granite", "Copper", "Maple"};
|
||||
|
||||
static constexpr std::array<std::string_view, 18> kBreweryNouns = {
|
||||
"Brewing Co.", "Brewery", "Bier Haus", "Taproom", "Works",
|
||||
"House", "Fermentery", "Ale Co.", "Cellars", "Collective",
|
||||
"Project", "Foundry", "Malthouse", "Public House", "Co-op",
|
||||
"Lab", "Beer Hall", "Guild"};
|
||||
static constexpr std::array<std::string_view, 18> kBreweryNouns = {
|
||||
"Brewing Co.", "Brewery", "Bier Haus", "Taproom", "Works",
|
||||
"House", "Fermentery", "Ale Co.", "Cellars", "Collective",
|
||||
"Project", "Foundry", "Malthouse", "Public House", "Co-op",
|
||||
"Lab", "Beer Hall", "Guild"};
|
||||
|
||||
static constexpr std::array<std::string_view, 18> kBreweryDescriptions = {
|
||||
"Handcrafted pale ales and seasonal IPAs with local ingredients.",
|
||||
"Traditional lagers and experimental sours in small batches.",
|
||||
"Award-winning stouts and wildly hoppy blonde ales.",
|
||||
"Craft brewery specializing in Belgian-style triples and dark "
|
||||
"porters.",
|
||||
"Modern brewery blending tradition with bold experimental flavors.",
|
||||
"Neighborhood-focused taproom pouring crisp pilsners and citrusy "
|
||||
"pale "
|
||||
"ales.",
|
||||
"Small-batch brewery known for barrel-aged releases and smoky "
|
||||
"lagers.",
|
||||
"Independent brewhouse pairing farmhouse ales with rotating food "
|
||||
"pop-ups.",
|
||||
"Community brewpub making balanced bitters, saisons, and hazy IPAs.",
|
||||
"Experimental nanobrewery exploring local yeast and regional "
|
||||
"grains.",
|
||||
"Family-run brewery producing smooth amber ales and robust porters.",
|
||||
"Urban brewery crafting clean lagers and bright, fruit-forward "
|
||||
"sours.",
|
||||
"Riverfront brewhouse featuring oak-matured ales and seasonal "
|
||||
"blends.",
|
||||
"Modern taproom focused on sessionable lagers and classic pub "
|
||||
"styles.",
|
||||
"Brewery rooted in tradition with a lineup of malty reds and crisp "
|
||||
"lagers.",
|
||||
"Creative brewery offering rotating collaborations and limited "
|
||||
"draft-only "
|
||||
"pours.",
|
||||
"Locally inspired brewery serving approachable ales with bold hop "
|
||||
"character.",
|
||||
"Destination taproom known for balanced IPAs and cocoa-rich "
|
||||
"stouts."};
|
||||
static constexpr std::array<std::string_view, 18> kBreweryDescriptions = {
|
||||
"Handcrafted pale ales and seasonal IPAs with local ingredients.",
|
||||
"Traditional lagers and experimental sours in small batches.",
|
||||
"Award-winning stouts and wildly hoppy blonde ales.",
|
||||
"Craft brewery specializing in Belgian-style triples and dark "
|
||||
"porters.",
|
||||
"Modern brewery blending tradition with bold experimental flavors.",
|
||||
"Neighborhood-focused taproom pouring crisp pilsners and citrusy "
|
||||
"pale "
|
||||
"ales.",
|
||||
"Small-batch brewery known for barrel-aged releases and smoky "
|
||||
"lagers.",
|
||||
"Independent brewhouse pairing farmhouse ales with rotating food "
|
||||
"pop-ups.",
|
||||
"Community brewpub making balanced bitters, saisons, and hazy IPAs.",
|
||||
"Experimental nanobrewery exploring local yeast and regional "
|
||||
"grains.",
|
||||
"Family-run brewery producing smooth amber ales and robust porters.",
|
||||
"Urban brewery crafting clean lagers and bright, fruit-forward "
|
||||
"sours.",
|
||||
"Riverfront brewhouse featuring oak-matured ales and seasonal "
|
||||
"blends.",
|
||||
"Modern taproom focused on sessionable lagers and classic pub "
|
||||
"styles.",
|
||||
"Brewery rooted in tradition with a lineup of malty reds and crisp "
|
||||
"lagers.",
|
||||
"Creative brewery offering rotating collaborations and limited "
|
||||
"draft-only "
|
||||
"pours.",
|
||||
"Locally inspired brewery serving approachable ales with bold hop "
|
||||
"character.",
|
||||
"Destination taproom known for balanced IPAs and cocoa-rich "
|
||||
"stouts."};
|
||||
|
||||
static constexpr std::array<std::string_view, 18> kUsernames = {
|
||||
"hopseeker", "malttrail", "yeastwhisper", "lagerlane",
|
||||
"barrelbound", "foamfinder", "taphunter", "graingeist",
|
||||
"brewscout", "aleatlas", "caskcompass", "hopsandmaps",
|
||||
"mashpilot", "pintnomad", "fermentfriend", "stoutsignal",
|
||||
"sessionwander", "kettlekeeper"};
|
||||
static constexpr std::array<std::string_view, 18> kUsernames = {
|
||||
"hopseeker", "malttrail", "yeastwhisper", "lagerlane",
|
||||
"barrelbound", "foamfinder", "taphunter", "graingeist",
|
||||
"brewscout", "aleatlas", "caskcompass", "hopsandmaps",
|
||||
"mashpilot", "pintnomad", "fermentfriend", "stoutsignal",
|
||||
"sessionwander", "kettlekeeper"};
|
||||
|
||||
static constexpr std::array<std::string_view, 18> kBios = {
|
||||
"Always chasing balanced IPAs and crisp lagers across local taprooms.",
|
||||
"Weekend brewery explorer with a soft spot for dark, roasty stouts.",
|
||||
"Documenting tiny brewpubs, fresh pours, and unforgettable beer "
|
||||
"gardens.",
|
||||
"Fan of farmhouse ales, food pairings, and long tasting flights.",
|
||||
"Collecting favorite pilsners one city at a time.",
|
||||
"Hops-first drinker who still saves room for classic malt-forward "
|
||||
"styles.",
|
||||
"Finding hidden tap lists and sharing the best seasonal releases.",
|
||||
"Brewery road-tripper focused on local ingredients and clean "
|
||||
"fermentation.",
|
||||
"Always comparing house lagers and ranking patio pint vibes.",
|
||||
"Curious about yeast strains, barrel programs, and cellar experiments.",
|
||||
"Believes every neighborhood deserves a great community taproom.",
|
||||
"Looking for session beers that taste great from first sip to last.",
|
||||
"Belgian ale enthusiast who never skips a new saison.",
|
||||
"Hazy IPA critic with deep respect for a perfectly clear pilsner.",
|
||||
"Visits breweries for the stories, stays for the flagship pours.",
|
||||
"Craft beer fan mapping tasting notes and favorite brew routes.",
|
||||
"Always ready to trade recommendations for underrated local breweries.",
|
||||
"Keeping a running list of must-try collab releases and tap "
|
||||
"takeovers."};
|
||||
static constexpr std::array<std::string_view, 18> kBios = {
|
||||
"Always chasing balanced IPAs and crisp lagers across local taprooms.",
|
||||
"Weekend brewery explorer with a soft spot for dark, roasty stouts.",
|
||||
"Documenting tiny brewpubs, fresh pours, and unforgettable beer "
|
||||
"gardens.",
|
||||
"Fan of farmhouse ales, food pairings, and long tasting flights.",
|
||||
"Collecting favorite pilsners one city at a time.",
|
||||
"Hops-first drinker who still saves room for classic malt-forward "
|
||||
"styles.",
|
||||
"Finding hidden tap lists and sharing the best seasonal releases.",
|
||||
"Brewery road-tripper focused on local ingredients and clean "
|
||||
"fermentation.",
|
||||
"Always comparing house lagers and ranking patio pint vibes.",
|
||||
"Curious about yeast strains, barrel programs, and cellar experiments.",
|
||||
"Believes every neighborhood deserves a great community taproom.",
|
||||
"Looking for session beers that taste great from first sip to last.",
|
||||
"Belgian ale enthusiast who never skips a new saison.",
|
||||
"Hazy IPA critic with deep respect for a perfectly clear pilsner.",
|
||||
"Visits breweries for the stories, stays for the flagship pours.",
|
||||
"Craft beer fan mapping tasting notes and favorite brew routes.",
|
||||
"Always ready to trade recommendations for underrated local breweries.",
|
||||
"Keeping a running list of must-try collab releases and tap "
|
||||
"takeovers."};
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_MOCK_GENERATOR_H_
|
||||
|
||||
@@ -7,12 +7,13 @@
|
||||
#include "data_generation/prompt_formatting/prompt_formatter.h"
|
||||
|
||||
class Gemma4JinjaPromptFormatter final : public IPromptFormatter {
|
||||
public:
|
||||
Gemma4JinjaPromptFormatter() = default;
|
||||
~Gemma4JinjaPromptFormatter() override = default;
|
||||
public:
|
||||
Gemma4JinjaPromptFormatter() = default;
|
||||
~Gemma4JinjaPromptFormatter() override = default;
|
||||
|
||||
[[nodiscard]] std::string Format(std::string_view system_prompt,
|
||||
std::string_view user_prompt) const override;
|
||||
[[nodiscard]] std::string Format(
|
||||
std::string_view system_prompt,
|
||||
std::string_view user_prompt) const override;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_GEMMA4_JINJA_PROMPT_FORMATTER_H_
|
||||
|
||||
@@ -5,16 +5,16 @@
|
||||
#include <string_view>
|
||||
|
||||
class IPromptFormatter {
|
||||
public:
|
||||
IPromptFormatter() = default;
|
||||
IPromptFormatter(const IPromptFormatter&) = delete;
|
||||
IPromptFormatter& operator=(const IPromptFormatter&) = delete;
|
||||
IPromptFormatter(IPromptFormatter&&) = delete;
|
||||
IPromptFormatter& operator=(IPromptFormatter&&) = delete;
|
||||
virtual ~IPromptFormatter() = default;
|
||||
public:
|
||||
IPromptFormatter() = default;
|
||||
IPromptFormatter(const IPromptFormatter&) = delete;
|
||||
IPromptFormatter& operator=(const IPromptFormatter&) = delete;
|
||||
IPromptFormatter(IPromptFormatter&&) = delete;
|
||||
IPromptFormatter& operator=(IPromptFormatter&&) = delete;
|
||||
virtual ~IPromptFormatter() = default;
|
||||
|
||||
[[nodiscard]] virtual std::string Format(
|
||||
std::string_view system_prompt, std::string_view user_prompt) const = 0;
|
||||
[[nodiscard]] virtual std::string Format(
|
||||
std::string_view system_prompt, std::string_view user_prompt) const = 0;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_DATA_GENERATION_PROMPT_FORMATTING_PROMPT_FORMATTER_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_
|
||||
|
||||
@@ -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<std::string> city_regexes{};
|
||||
/**
|
||||
* @brief City-specific postal-code regexes (more precise than the country
|
||||
* format).
|
||||
*/
|
||||
std::vector<std::string> city_regexes{};
|
||||
|
||||
/**
|
||||
* @brief Concrete example postal codes for this city. The postal code
|
||||
* service selects from these rather than synthesizing codes.
|
||||
*/
|
||||
std::vector<std::string> examples{};
|
||||
/**
|
||||
* @brief Concrete example postal codes for this city. The postal code
|
||||
* service selects from these rather than synthesizing codes.
|
||||
*/
|
||||
std::vector<std::string> 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<std::string> local_languages{};
|
||||
/**
|
||||
* @brief Local language codes in priority order.
|
||||
*/
|
||||
std::vector<std::string> 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<ForenameEntry> {
|
||||
size_t operator()(const ForenameEntry& entry) const noexcept {
|
||||
const size_t name_hash = std::hash<std::string>{}(entry.name);
|
||||
const size_t gender_hash = std::hash<std::string>{}(entry.gender);
|
||||
return name_hash ^ (gender_hash << 1);
|
||||
}
|
||||
size_t operator()(const ForenameEntry& entry) const noexcept {
|
||||
const size_t name_hash = std::hash<std::string>{}(entry.name);
|
||||
const size_t gender_hash = std::hash<std::string>{}(entry.gender);
|
||||
return name_hash ^ (gender_hash << 1);
|
||||
}
|
||||
};
|
||||
} // namespace std
|
||||
|
||||
@@ -131,20 +131,20 @@ struct hash<ForenameEntry> {
|
||||
* @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<std::string> style_affinities{};
|
||||
/**
|
||||
* @brief Beer styles this persona gravitates toward.
|
||||
*/
|
||||
std::vector<std::string> 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<SamplingOptions> sampling;
|
||||
/**
|
||||
* @brief Specific sampling parameters for this generator.
|
||||
* If nullopt, the application should use global defaults.
|
||||
*/
|
||||
std::optional<SamplingOptions> 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
|
||||
|
||||
@@ -27,83 +27,84 @@
|
||||
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;
|
||||
}
|
||||
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";
|
||||
}
|
||||
}
|
||||
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";
|
||||
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 // BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_PRETTY_PRINT_H_
|
||||
|
||||
@@ -15,12 +15,12 @@
|
||||
* it alive for application lifetime.
|
||||
*/
|
||||
class LlamaBackendState {
|
||||
public:
|
||||
LlamaBackendState() { llama_backend_init(); }
|
||||
~LlamaBackendState() { llama_backend_free(); }
|
||||
public:
|
||||
LlamaBackendState() { llama_backend_init(); }
|
||||
~LlamaBackendState() { llama_backend_free(); }
|
||||
|
||||
LlamaBackendState(const LlamaBackendState&) = delete;
|
||||
LlamaBackendState& operator=(const LlamaBackendState&) = delete;
|
||||
LlamaBackendState(const LlamaBackendState&) = delete;
|
||||
LlamaBackendState& operator=(const LlamaBackendState&) = delete;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_LLAMA_BACKEND_STATE_H_
|
||||
|
||||
@@ -25,26 +25,26 @@ using SurnamesByCountryMap = std::unordered_map<std::string, SurnameList>;
|
||||
* brewery/user generation.
|
||||
*/
|
||||
class ICuratedDataService {
|
||||
public:
|
||||
ICuratedDataService() = default;
|
||||
virtual ~ICuratedDataService() = default;
|
||||
public:
|
||||
ICuratedDataService() = default;
|
||||
virtual ~ICuratedDataService() = default;
|
||||
|
||||
ICuratedDataService(const ICuratedDataService&) = delete;
|
||||
ICuratedDataService& operator=(const ICuratedDataService&) = delete;
|
||||
ICuratedDataService(ICuratedDataService&&) = delete;
|
||||
ICuratedDataService& operator=(ICuratedDataService&&) = delete;
|
||||
ICuratedDataService(const ICuratedDataService&) = delete;
|
||||
ICuratedDataService& operator=(const ICuratedDataService&) = delete;
|
||||
ICuratedDataService(ICuratedDataService&&) = delete;
|
||||
ICuratedDataService& operator=(ICuratedDataService&&) = delete;
|
||||
|
||||
/**
|
||||
* @brief Loads all curated location records.
|
||||
*/
|
||||
virtual const LocationsList& LoadLocations() = 0;
|
||||
/**
|
||||
* @brief Loads all curated location records.
|
||||
*/
|
||||
virtual const LocationsList& LoadLocations() = 0;
|
||||
|
||||
/**
|
||||
* @brief Loads all curated persona records.
|
||||
*/
|
||||
virtual const PersonasList& LoadPersonas() = 0;
|
||||
virtual const ForenamesByCountryMap& LoadForenamesByCountry() = 0;
|
||||
virtual const SurnamesByCountryMap& LoadSurnamesByCountry() = 0;
|
||||
/**
|
||||
* @brief Loads all curated persona records.
|
||||
*/
|
||||
virtual const PersonasList& LoadPersonas() = 0;
|
||||
virtual const ForenamesByCountryMap& LoadForenamesByCountry() = 0;
|
||||
virtual const SurnamesByCountryMap& LoadSurnamesByCountry() = 0;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_CURATED_DATA_CURATED_DATA_SERVICE_H_
|
||||
|
||||
@@ -16,48 +16,48 @@
|
||||
* CuratedJsonDataService.
|
||||
*/
|
||||
struct CuratedDataFilePaths {
|
||||
std::filesystem::path locations_path;
|
||||
std::filesystem::path personas_path;
|
||||
std::filesystem::path forenames_path;
|
||||
std::filesystem::path surnames_path;
|
||||
std::filesystem::path locations_path;
|
||||
std::filesystem::path personas_path;
|
||||
std::filesystem::path forenames_path;
|
||||
std::filesystem::path surnames_path;
|
||||
};
|
||||
|
||||
/**
|
||||
* @brief Loads curated location, persona, and name data from JSON files.
|
||||
*/
|
||||
class CuratedJsonDataService final : public ICuratedDataService {
|
||||
struct cache {
|
||||
LocationsList locations;
|
||||
PersonasList personas;
|
||||
ForenamesByCountryMap forenames_by_country;
|
||||
SurnamesByCountryMap surnames_by_country;
|
||||
struct cache {
|
||||
LocationsList locations;
|
||||
PersonasList personas;
|
||||
ForenamesByCountryMap forenames_by_country;
|
||||
SurnamesByCountryMap surnames_by_country;
|
||||
|
||||
cache() = default;
|
||||
~cache() = default;
|
||||
};
|
||||
cache() = default;
|
||||
~cache() = default;
|
||||
};
|
||||
|
||||
CuratedDataFilePaths filepaths_;
|
||||
cache cache_;
|
||||
CuratedDataFilePaths filepaths_;
|
||||
cache cache_;
|
||||
|
||||
public:
|
||||
explicit CuratedJsonDataService(CuratedDataFilePaths filepaths);
|
||||
public:
|
||||
explicit CuratedJsonDataService(CuratedDataFilePaths filepaths);
|
||||
|
||||
/**
|
||||
* @brief Parses a JSON array file and returns all location records.
|
||||
*/
|
||||
const LocationsList& LoadLocations() override;
|
||||
/**
|
||||
* @brief Parses a JSON array file and returns all location records.
|
||||
*/
|
||||
const LocationsList& LoadLocations() override;
|
||||
|
||||
/**
|
||||
* @brief Parses a JSON array file and returns all persona records.
|
||||
*/
|
||||
const PersonasList& LoadPersonas() override;
|
||||
/**
|
||||
* @brief Parses a JSON array file and returns all persona records.
|
||||
*/
|
||||
const PersonasList& LoadPersonas() override;
|
||||
|
||||
const ForenamesByCountryMap& LoadForenamesByCountry() override;
|
||||
const ForenamesByCountryMap& LoadForenamesByCountry() override;
|
||||
|
||||
/**
|
||||
* @brief Parses a JSON file and returns all the forenames per country.
|
||||
*/
|
||||
const SurnamesByCountryMap& LoadSurnamesByCountry() override;
|
||||
/**
|
||||
* @brief Parses a JSON file and returns all the forenames per country.
|
||||
*/
|
||||
const SurnamesByCountryMap& LoadSurnamesByCountry() override;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_JSON_HANDLING_JSON_LOADER_H_
|
||||
|
||||
@@ -17,22 +17,22 @@
|
||||
* place of the JSON fixture files used by JsonLoader.
|
||||
*/
|
||||
class MockCuratedDataService final : public ICuratedDataService {
|
||||
public:
|
||||
MockCuratedDataService();
|
||||
public:
|
||||
MockCuratedDataService();
|
||||
|
||||
const LocationsList& LoadLocations() override;
|
||||
const LocationsList& LoadLocations() override;
|
||||
|
||||
const PersonasList& LoadPersonas() override;
|
||||
const PersonasList& LoadPersonas() override;
|
||||
|
||||
const ForenamesByCountryMap& LoadForenamesByCountry() override;
|
||||
const ForenamesByCountryMap& LoadForenamesByCountry() override;
|
||||
|
||||
const SurnamesByCountryMap& LoadSurnamesByCountry() override;
|
||||
const SurnamesByCountryMap& LoadSurnamesByCountry() override;
|
||||
|
||||
private:
|
||||
LocationsList locations_;
|
||||
PersonasList personas_;
|
||||
ForenamesByCountryMap forenames_by_country_;
|
||||
SurnamesByCountryMap surnames_by_country_;
|
||||
private:
|
||||
LocationsList locations_;
|
||||
PersonasList personas_;
|
||||
ForenamesByCountryMap forenames_by_country_;
|
||||
SurnamesByCountryMap surnames_by_country_;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_CURATED_DATA_MOCK_CURATED_DATA_SERVICE_H_
|
||||
|
||||
@@ -14,38 +14,38 @@
|
||||
* @brief Interface for services that persist generated brewery records.
|
||||
*/
|
||||
class IExportService {
|
||||
public:
|
||||
IExportService() = default;
|
||||
virtual ~IExportService() = default;
|
||||
public:
|
||||
IExportService() = default;
|
||||
virtual ~IExportService() = default;
|
||||
|
||||
IExportService(const IExportService&) = delete;
|
||||
IExportService& operator=(const IExportService&) = delete;
|
||||
IExportService(IExportService&&) = delete;
|
||||
IExportService& operator=(IExportService&&) = delete;
|
||||
IExportService(const IExportService&) = delete;
|
||||
IExportService& operator=(const IExportService&) = delete;
|
||||
IExportService(IExportService&&) = delete;
|
||||
IExportService& operator=(IExportService&&) = delete;
|
||||
|
||||
/**
|
||||
* @brief Prepares the export destination for a new run.
|
||||
*/
|
||||
virtual void Initialize() = 0;
|
||||
/**
|
||||
* @brief Prepares the export destination for a new run.
|
||||
*/
|
||||
virtual void Initialize() = 0;
|
||||
|
||||
/**
|
||||
* @brief Persists one generated brewery record.
|
||||
*
|
||||
* @param brewery Generated brewery payload to store.
|
||||
*/
|
||||
virtual uint64_t ProcessRecord(const BreweryRecord& brewery) = 0;
|
||||
/**
|
||||
* @brief Persists one generated brewery record.
|
||||
*
|
||||
* @param brewery Generated brewery payload to store.
|
||||
*/
|
||||
virtual uint64_t ProcessRecord(const BreweryRecord& brewery) = 0;
|
||||
|
||||
/**
|
||||
* @brief Persists one generated user record.
|
||||
*
|
||||
* @param user Generated user payload to store.
|
||||
*/
|
||||
virtual uint64_t ProcessRecord(const UserRecord& user) = 0;
|
||||
/**
|
||||
* @brief Persists one generated user record.
|
||||
*
|
||||
* @param user Generated user payload to store.
|
||||
*/
|
||||
virtual uint64_t ProcessRecord(const UserRecord& user) = 0;
|
||||
|
||||
/**
|
||||
* @brief Finalizes the export destination.
|
||||
*/
|
||||
virtual void Finalize() = 0;
|
||||
/**
|
||||
* @brief Finalizes the export destination.
|
||||
*/
|
||||
virtual void Finalize() = 0;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_EXPORT_SERVICE_H_
|
||||
|
||||
@@ -20,54 +20,54 @@
|
||||
* @brief Persists generated brewery records into a fresh SQLite database.
|
||||
*/
|
||||
class SqliteExportService final : public IExportService {
|
||||
public:
|
||||
explicit SqliteExportService(const ApplicationOptions& options);
|
||||
~SqliteExportService() override;
|
||||
public:
|
||||
explicit SqliteExportService(const ApplicationOptions& options);
|
||||
~SqliteExportService() override;
|
||||
|
||||
SqliteExportService(const SqliteExportService&) = delete;
|
||||
SqliteExportService& operator=(const SqliteExportService&) = delete;
|
||||
SqliteExportService(SqliteExportService&&) = delete;
|
||||
SqliteExportService& operator=(SqliteExportService&&) = delete;
|
||||
SqliteExportService(const SqliteExportService&) = delete;
|
||||
SqliteExportService& operator=(const SqliteExportService&) = delete;
|
||||
SqliteExportService(SqliteExportService&&) = delete;
|
||||
SqliteExportService& operator=(SqliteExportService&&) = delete;
|
||||
|
||||
void Initialize() override;
|
||||
uint64_t ProcessRecord(const BreweryRecord& brewery) override;
|
||||
uint64_t ProcessRecord(const UserRecord& user) override;
|
||||
void Finalize() override;
|
||||
void Initialize() override;
|
||||
uint64_t ProcessRecord(const BreweryRecord& brewery) override;
|
||||
uint64_t ProcessRecord(const UserRecord& user) override;
|
||||
void Finalize() override;
|
||||
|
||||
private:
|
||||
using SqliteDatabaseHandle =
|
||||
sqlite_export_service_internal::SqliteDatabaseHandle;
|
||||
using SqliteStatementHandle =
|
||||
sqlite_export_service_internal::SqliteStatementHandle;
|
||||
private:
|
||||
using SqliteDatabaseHandle =
|
||||
sqlite_export_service_internal::SqliteDatabaseHandle;
|
||||
using SqliteStatementHandle =
|
||||
sqlite_export_service_internal::SqliteStatementHandle;
|
||||
|
||||
void InitializeSchema() const;
|
||||
void PrepareStatements();
|
||||
void RollbackAndCloseNoThrow() noexcept;
|
||||
void InitializeSchema() const;
|
||||
void PrepareStatements();
|
||||
void RollbackAndCloseNoThrow() noexcept;
|
||||
|
||||
[[nodiscard]] std::filesystem::path BuildDatabasePath() const;
|
||||
[[nodiscard]] static std::string BuildCityKey(const City& city);
|
||||
[[nodiscard]] std::filesystem::path BuildDatabasePath() const;
|
||||
[[nodiscard]] static std::string BuildCityKey(const City& city);
|
||||
|
||||
/**
|
||||
* @brief Returns the row id for @p city, inserting it first if it has
|
||||
* not already been seen during this run.
|
||||
*
|
||||
* Shared by both ProcessRecord() overloads so brewery and user addresses
|
||||
* referencing the same city resolve to the same row.
|
||||
*/
|
||||
[[nodiscard]] sqlite3_int64 ResolveCityId(const City& city);
|
||||
/**
|
||||
* @brief Returns the row id for @p city, inserting it first if it has
|
||||
* not already been seen during this run.
|
||||
*
|
||||
* Shared by both ProcessRecord() overloads so brewery and user addresses
|
||||
* referencing the same city resolve to the same row.
|
||||
*/
|
||||
[[nodiscard]] sqlite3_int64 ResolveCityId(const City& city);
|
||||
|
||||
std::unique_ptr<IDateTimeProvider> date_time_provider_;
|
||||
std::filesystem::path output_path_;
|
||||
std::string run_timestamp_utc_;
|
||||
std::filesystem::path database_path_;
|
||||
SqliteDatabaseHandle db_handle_;
|
||||
SqliteStatementHandle insert_city_stmt_;
|
||||
SqliteStatementHandle insert_brewery_stmt_;
|
||||
SqliteStatementHandle insert_brewery_address_stmt_;
|
||||
SqliteStatementHandle insert_user_stmt_;
|
||||
SqliteStatementHandle insert_user_address_stmt_;
|
||||
bool transaction_open_ = false;
|
||||
std::unordered_map<std::string, sqlite3_int64> city_cache_;
|
||||
std::unique_ptr<IDateTimeProvider> date_time_provider_;
|
||||
std::filesystem::path output_path_;
|
||||
std::string run_timestamp_utc_;
|
||||
std::filesystem::path database_path_;
|
||||
SqliteDatabaseHandle db_handle_;
|
||||
SqliteStatementHandle insert_city_stmt_;
|
||||
SqliteStatementHandle insert_brewery_stmt_;
|
||||
SqliteStatementHandle insert_brewery_address_stmt_;
|
||||
SqliteStatementHandle insert_user_stmt_;
|
||||
SqliteStatementHandle insert_user_address_stmt_;
|
||||
bool transaction_open_ = false;
|
||||
std::unordered_map<std::string, sqlite3_int64> city_cache_;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATABASE_SQLITE_EXPORT_SERVICE_H_
|
||||
|
||||
@@ -13,11 +13,11 @@
|
||||
namespace sqlite_export_service_internal {
|
||||
|
||||
struct SqliteDatabaseDeleter {
|
||||
void operator()(sqlite3* handle) const noexcept;
|
||||
void operator()(sqlite3* handle) const noexcept;
|
||||
};
|
||||
|
||||
struct SqliteStatementDeleter {
|
||||
void operator()(sqlite3_stmt* statement) const noexcept;
|
||||
void operator()(sqlite3_stmt* statement) const noexcept;
|
||||
};
|
||||
|
||||
using SqliteDatabaseHandle = std::unique_ptr<sqlite3, SqliteDatabaseDeleter>;
|
||||
@@ -28,9 +28,9 @@ using SqliteStatementHandle =
|
||||
// N.B. indices are 1 based.
|
||||
template <typename T>
|
||||
struct BoundParam {
|
||||
int index;
|
||||
T value;
|
||||
std::string_view action;
|
||||
int index;
|
||||
T value;
|
||||
std::string_view action;
|
||||
};
|
||||
|
||||
} // namespace sqlite_export_service_internal
|
||||
|
||||
@@ -152,44 +152,44 @@ INSERT INTO user_addresses (
|
||||
// sqlite3_bind_*() parameter indices are 1-based, matching the "?"
|
||||
// placeholder order in the SQL above.
|
||||
enum CityBindIndex {
|
||||
kCityCityBindIndex = 1,
|
||||
kCityStateProvinceBindIndex,
|
||||
kCityIso31662BindIndex,
|
||||
kCityCountryBindIndex,
|
||||
kCityIso31661BindIndex,
|
||||
kCityLanguagesBindIndex,
|
||||
kCityPostalCodeCountryFormatRegexBindIndex,
|
||||
kCityPostalCodeCityRegexJsonBindIndex,
|
||||
kCityCityBindIndex = 1,
|
||||
kCityStateProvinceBindIndex,
|
||||
kCityIso31662BindIndex,
|
||||
kCityCountryBindIndex,
|
||||
kCityIso31661BindIndex,
|
||||
kCityLanguagesBindIndex,
|
||||
kCityPostalCodeCountryFormatRegexBindIndex,
|
||||
kCityPostalCodeCityRegexJsonBindIndex,
|
||||
};
|
||||
|
||||
enum BreweryBindIndex {
|
||||
kBreweryEnglishNameBindIndex = 1,
|
||||
kBreweryEnglishDescriptionBindIndex,
|
||||
kBreweryLocalNameBindIndex,
|
||||
kBreweryLocalDescriptionBindIndex,
|
||||
kBreweryEnglishNameBindIndex = 1,
|
||||
kBreweryEnglishDescriptionBindIndex,
|
||||
kBreweryLocalNameBindIndex,
|
||||
kBreweryLocalDescriptionBindIndex,
|
||||
};
|
||||
|
||||
enum BreweryAddressBindIndex {
|
||||
kBreweryAddressBreweryIdBindIndex = 1,
|
||||
kBreweryAddressCityIdBindIndex,
|
||||
kBreweryAddressPostalCodeBindIndex,
|
||||
kBreweryAddressBreweryIdBindIndex = 1,
|
||||
kBreweryAddressCityIdBindIndex,
|
||||
kBreweryAddressPostalCodeBindIndex,
|
||||
};
|
||||
|
||||
enum UserBindIndex {
|
||||
kUserFirstNameBindIndex = 1,
|
||||
kUserLastNameBindIndex,
|
||||
kUserGenderBindIndex,
|
||||
kUserUsernameBindIndex,
|
||||
kUserBioBindIndex,
|
||||
kUserActivityWeightBindIndex,
|
||||
kUserEmailBindIndex,
|
||||
kUserDateOfBirthBindIndex,
|
||||
kUserFirstNameBindIndex = 1,
|
||||
kUserLastNameBindIndex,
|
||||
kUserGenderBindIndex,
|
||||
kUserUsernameBindIndex,
|
||||
kUserBioBindIndex,
|
||||
kUserActivityWeightBindIndex,
|
||||
kUserEmailBindIndex,
|
||||
kUserDateOfBirthBindIndex,
|
||||
};
|
||||
|
||||
enum UserAddressBindIndex {
|
||||
kUserAddressUserIdBindIndex = 1,
|
||||
kUserAddressCityIdBindIndex,
|
||||
kUserAddressPostalCodeBindIndex,
|
||||
kUserAddressUserIdBindIndex = 1,
|
||||
kUserAddressCityIdBindIndex,
|
||||
kUserAddressPostalCodeBindIndex,
|
||||
};
|
||||
|
||||
SqliteStatementHandle PrepareStatement(const SqliteDatabaseHandle& db_handle,
|
||||
|
||||
@@ -20,49 +20,49 @@
|
||||
* directly
|
||||
*/
|
||||
class IDateTimeProvider {
|
||||
public:
|
||||
virtual ~IDateTimeProvider() = default;
|
||||
public:
|
||||
virtual ~IDateTimeProvider() = default;
|
||||
|
||||
IDateTimeProvider() = default;
|
||||
IDateTimeProvider(const IDateTimeProvider&) = delete;
|
||||
IDateTimeProvider& operator=(const IDateTimeProvider&) = delete;
|
||||
IDateTimeProvider(IDateTimeProvider&&) = delete;
|
||||
IDateTimeProvider& operator=(IDateTimeProvider&&) = delete;
|
||||
IDateTimeProvider() = default;
|
||||
IDateTimeProvider(const IDateTimeProvider&) = delete;
|
||||
IDateTimeProvider& operator=(const IDateTimeProvider&) = delete;
|
||||
IDateTimeProvider(IDateTimeProvider&&) = delete;
|
||||
IDateTimeProvider& operator=(IDateTimeProvider&&) = delete;
|
||||
|
||||
/**
|
||||
* @brief Returns the current UTC timestamp in a file-safe format.
|
||||
*
|
||||
* @return UTC timestamp string.
|
||||
*/
|
||||
virtual std::string GetUtcTimestamp() = 0;
|
||||
/**
|
||||
* @brief Returns the current UTC timestamp in a file-safe format.
|
||||
*
|
||||
* @return UTC timestamp string.
|
||||
*/
|
||||
virtual std::string GetUtcTimestamp() = 0;
|
||||
};
|
||||
|
||||
/**
|
||||
* @brief Timestamp provider backed by the system clock.
|
||||
*/
|
||||
class SystemDateTimeProvider final : public IDateTimeProvider {
|
||||
public:
|
||||
std::string GetUtcTimestamp() override {
|
||||
constexpr int kFractionalSecondWidth = 6;
|
||||
public:
|
||||
std::string GetUtcTimestamp() override {
|
||||
constexpr int kFractionalSecondWidth = 6;
|
||||
|
||||
const auto now = std::chrono::system_clock::now();
|
||||
const auto now_time = std::chrono::system_clock::to_time_t(now);
|
||||
const std::tm* utc_time_ptr = std::gmtime(&now_time);
|
||||
if (utc_time_ptr == nullptr) {
|
||||
throw std::runtime_error("Failed to format UTC timestamp");
|
||||
}
|
||||
const auto now = std::chrono::system_clock::now();
|
||||
const auto now_time = std::chrono::system_clock::to_time_t(now);
|
||||
const std::tm* utc_time_ptr = std::gmtime(&now_time);
|
||||
if (utc_time_ptr == nullptr) {
|
||||
throw std::runtime_error("Failed to format UTC timestamp");
|
||||
}
|
||||
|
||||
const auto fractional_seconds =
|
||||
std::chrono::duration_cast<std::chrono::microseconds>(
|
||||
now.time_since_epoch()) %
|
||||
std::chrono::seconds(1);
|
||||
const auto fractional_seconds =
|
||||
std::chrono::duration_cast<std::chrono::microseconds>(
|
||||
now.time_since_epoch()) %
|
||||
std::chrono::seconds(1);
|
||||
|
||||
std::ostringstream output;
|
||||
output << std::put_time(utc_time_ptr, "%Y-%m-%dT%H-%M-%S");
|
||||
output << '.' << std::setw(kFractionalSecondWidth) << std::setfill('0')
|
||||
<< fractional_seconds.count() << 'Z';
|
||||
return output.str();
|
||||
}
|
||||
std::ostringstream output;
|
||||
output << std::put_time(utc_time_ptr, "%Y-%m-%dT%H-%M-%S");
|
||||
output << '.' << std::setw(kFractionalSecondWidth) << std::setfill('0')
|
||||
<< fractional_seconds.count() << 'Z';
|
||||
return output.str();
|
||||
}
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_DATE_TIME_PROVIDER_H_
|
||||
|
||||
@@ -8,28 +8,28 @@
|
||||
* @brief Simple timer utility for measuring elapsed time.
|
||||
*/
|
||||
class Timer {
|
||||
std::chrono::steady_clock::time_point start_time =
|
||||
std::chrono::steady_clock::now();
|
||||
std::chrono::steady_clock::time_point start_time =
|
||||
std::chrono::steady_clock::now();
|
||||
|
||||
public:
|
||||
Timer(const Timer&) = delete;
|
||||
Timer& operator=(const Timer&) = delete;
|
||||
Timer(Timer&&) = delete;
|
||||
Timer& operator=(Timer&&) = delete;
|
||||
Timer() = default;
|
||||
~Timer() = default;
|
||||
public:
|
||||
Timer(const Timer&) = delete;
|
||||
Timer& operator=(const Timer&) = delete;
|
||||
Timer(Timer&&) = delete;
|
||||
Timer& operator=(Timer&&) = delete;
|
||||
Timer() = default;
|
||||
~Timer() = default;
|
||||
|
||||
[[nodiscard]] int64_t Elapsed() const {
|
||||
return std::chrono::duration_cast<std::chrono::milliseconds>(
|
||||
std::chrono::steady_clock::now() - start_time)
|
||||
.count();
|
||||
}
|
||||
[[nodiscard]] int64_t Elapsed() const {
|
||||
return std::chrono::duration_cast<std::chrono::milliseconds>(
|
||||
std::chrono::steady_clock::now() - start_time)
|
||||
.count();
|
||||
}
|
||||
|
||||
[[nodiscard]] int64_t Reset() {
|
||||
auto previous_elapsed = Elapsed();
|
||||
start_time = std::chrono::steady_clock::now();
|
||||
return previous_elapsed;
|
||||
}
|
||||
[[nodiscard]] int64_t Reset() {
|
||||
auto previous_elapsed = Elapsed();
|
||||
start_time = std::chrono::steady_clock::now();
|
||||
return previous_elapsed;
|
||||
}
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_DATETIME_TIMER_H_
|
||||
|
||||
@@ -14,16 +14,16 @@
|
||||
* @brief Interface for services that can enrich a location with context.
|
||||
*/
|
||||
class IEnrichmentService {
|
||||
public:
|
||||
virtual ~IEnrichmentService() = default;
|
||||
public:
|
||||
virtual ~IEnrichmentService() = default;
|
||||
|
||||
/**
|
||||
* @brief Resolves contextual enrichment for a location.
|
||||
*
|
||||
* @param loc City to enrich.
|
||||
* @return Context text, or an empty string if unavailable.
|
||||
*/
|
||||
virtual std::string GetLocationContext(const City& loc) = 0;
|
||||
/**
|
||||
* @brief Resolves contextual enrichment for a location.
|
||||
*
|
||||
* @param loc City to enrich.
|
||||
* @return Context text, or an empty string if unavailable.
|
||||
*/
|
||||
virtual std::string GetLocationContext(const City& loc) = 0;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_ENRICHMENT_SERVICE_H_
|
||||
|
||||
@@ -14,9 +14,7 @@
|
||||
* @brief Enrichment service that returns no context for any location.
|
||||
*/
|
||||
class MockEnrichmentService final : public IEnrichmentService {
|
||||
public:
|
||||
std::string GetLocationContext(const City& /*loc*/) override {
|
||||
return {};
|
||||
}
|
||||
public:
|
||||
std::string GetLocationContext(const City& /*loc*/) override { return {}; }
|
||||
};
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_MOCK_ENRICHMENT_H_
|
||||
|
||||
@@ -19,30 +19,30 @@
|
||||
* @brief Provides Wikipedia summary lookups backed by cached raw extracts.
|
||||
*/
|
||||
class WikipediaEnrichmentService final : public IEnrichmentService {
|
||||
public:
|
||||
/**
|
||||
* @brief Creates a new Wikipedia service with the provided web client.
|
||||
*/
|
||||
explicit WikipediaEnrichmentService(std::unique_ptr<WebClient> client,
|
||||
std::shared_ptr<ILogger> logger);
|
||||
public:
|
||||
/**
|
||||
* @brief Creates a new Wikipedia service with the provided web client.
|
||||
*/
|
||||
explicit WikipediaEnrichmentService(std::unique_ptr<WebClient> client,
|
||||
std::shared_ptr<ILogger> logger);
|
||||
|
||||
/**
|
||||
* @brief Returns the Wikipedia-derived context for a location.
|
||||
*/
|
||||
[[nodiscard]] std::string GetLocationContext(const City& loc) override;
|
||||
/**
|
||||
* @brief Returns the Wikipedia-derived context for a location.
|
||||
*/
|
||||
[[nodiscard]] std::string GetLocationContext(const City& loc) override;
|
||||
|
||||
private:
|
||||
std::string FetchExtract(std::string_view query);
|
||||
std::unique_ptr<WebClient> client_;
|
||||
std::shared_ptr<ILogger> logger_;
|
||||
/**
|
||||
* @brief Cache for raw Wikipedia query extracts, keyed by query string.
|
||||
*
|
||||
* GetLocationContext() always queries "brewing" and reuses "beer in
|
||||
* {country}" for every city in that country, so caching avoids refetching
|
||||
* the same extract across locations in a run.
|
||||
*/
|
||||
std::unordered_map<std::string, std::string> extract_cache_;
|
||||
private:
|
||||
std::string FetchExtract(std::string_view query);
|
||||
std::unique_ptr<WebClient> client_;
|
||||
std::shared_ptr<ILogger> logger_;
|
||||
/**
|
||||
* @brief Cache for raw Wikipedia query extracts, keyed by query string.
|
||||
*
|
||||
* GetLocationContext() always queries "brewing" and reuses "beer in
|
||||
* {country}" for every city in that country, so caching avoids refetching
|
||||
* the same extract across locations in a run.
|
||||
*/
|
||||
std::unordered_map<std::string, std::string> extract_cache_;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_ENRICHMENT_WIKIPEDIA_SERVICE_H_
|
||||
|
||||
@@ -22,32 +22,32 @@
|
||||
* and exit once the channel has been closed and drained.
|
||||
*/
|
||||
class LogDispatcher {
|
||||
public:
|
||||
/**
|
||||
* @brief Construct a log dispatcher.
|
||||
*
|
||||
* @param channel Reference to the bounded channel used for log retrieval.
|
||||
*/
|
||||
explicit LogDispatcher(BoundedChannel<LogEntry>& channel);
|
||||
public:
|
||||
/**
|
||||
* @brief Construct a log dispatcher.
|
||||
*
|
||||
* @param channel Reference to the bounded channel used for log retrieval.
|
||||
*/
|
||||
explicit LogDispatcher(BoundedChannel<LogEntry>& 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<LogEntry>& channel_;
|
||||
private:
|
||||
BoundedChannel<LogEntry>& channel_;
|
||||
|
||||
static spdlog::level::level_enum ToSpdlogLevel(LogLevel level);
|
||||
static spdlog::level::level_enum ToSpdlogLevel(LogLevel level);
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_DISPATCHER_H_
|
||||
|
||||
@@ -20,22 +20,22 @@
|
||||
* @brief Severity levels supported by the logging infra.
|
||||
*/
|
||||
enum class LogLevel {
|
||||
/**
|
||||
* @brief Development/debugging information.
|
||||
*/
|
||||
Debug,
|
||||
/**
|
||||
* @brief General informational messages.
|
||||
*/
|
||||
Info,
|
||||
/**
|
||||
* @brief Warning conditions.
|
||||
*/
|
||||
Warn,
|
||||
/**
|
||||
* @brief Error conditions.
|
||||
*/
|
||||
Error,
|
||||
/**
|
||||
* @brief Development/debugging information.
|
||||
*/
|
||||
Debug,
|
||||
/**
|
||||
* @brief General informational messages.
|
||||
*/
|
||||
Info,
|
||||
/**
|
||||
* @brief Warning conditions.
|
||||
*/
|
||||
Warn,
|
||||
/**
|
||||
* @brief Error conditions.
|
||||
*/
|
||||
Error,
|
||||
};
|
||||
|
||||
/**
|
||||
@@ -46,38 +46,38 @@ enum class LogLevel {
|
||||
* pipeline that emitted it.
|
||||
*/
|
||||
enum class PipelinePhase {
|
||||
/**
|
||||
* @brief Initialization and validation.
|
||||
*/
|
||||
Startup,
|
||||
/**
|
||||
* @brief City/context enrichment (e.g. Wikipedia lookups).
|
||||
*/
|
||||
Enrichment,
|
||||
/**
|
||||
* @brief User profile generation.
|
||||
*/
|
||||
UserGeneration,
|
||||
/**
|
||||
* @brief Brewery and beer data generation.
|
||||
*/
|
||||
BreweryAndBeerGeneration,
|
||||
/**
|
||||
* @brief Checkin (visit) record generation.
|
||||
*/
|
||||
CheckinGeneration,
|
||||
/**
|
||||
* @brief Rating and review generation.
|
||||
*/
|
||||
RatingGeneration,
|
||||
/**
|
||||
* @brief Follow relationship generation.
|
||||
*/
|
||||
FollowGeneration,
|
||||
/**
|
||||
* @brief Finalization and cleanup.
|
||||
*/
|
||||
Teardown,
|
||||
/**
|
||||
* @brief Initialization and validation.
|
||||
*/
|
||||
Startup,
|
||||
/**
|
||||
* @brief City/context enrichment (e.g. Wikipedia lookups).
|
||||
*/
|
||||
Enrichment,
|
||||
/**
|
||||
* @brief User profile generation.
|
||||
*/
|
||||
UserGeneration,
|
||||
/**
|
||||
* @brief Brewery and beer data generation.
|
||||
*/
|
||||
BreweryAndBeerGeneration,
|
||||
/**
|
||||
* @brief Checkin (visit) record generation.
|
||||
*/
|
||||
CheckinGeneration,
|
||||
/**
|
||||
* @brief Rating and review generation.
|
||||
*/
|
||||
RatingGeneration,
|
||||
/**
|
||||
* @brief Follow relationship generation.
|
||||
*/
|
||||
FollowGeneration,
|
||||
/**
|
||||
* @brief Finalization and cleanup.
|
||||
*/
|
||||
Teardown,
|
||||
};
|
||||
|
||||
/**
|
||||
@@ -86,9 +86,9 @@ enum class PipelinePhase {
|
||||
* transparently.
|
||||
*/
|
||||
struct LogDTO {
|
||||
LogLevel level;
|
||||
PipelinePhase phase;
|
||||
std::string message;
|
||||
LogLevel level;
|
||||
PipelinePhase phase;
|
||||
std::string message;
|
||||
};
|
||||
|
||||
/**
|
||||
@@ -102,35 +102,35 @@ struct LogDTO {
|
||||
* before the entry is dispatched.
|
||||
*/
|
||||
struct LogEntry {
|
||||
/**
|
||||
* @brief Timestamp when the entry was created.
|
||||
*/
|
||||
std::chrono::system_clock::time_point timestamp{};
|
||||
/**
|
||||
* @brief Timestamp when the entry was created.
|
||||
*/
|
||||
std::chrono::system_clock::time_point timestamp{};
|
||||
|
||||
/**
|
||||
* @brief Source location where the log call was made.
|
||||
*/
|
||||
std::source_location origin{};
|
||||
/**
|
||||
* @brief Source location where the log call was made.
|
||||
*/
|
||||
std::source_location origin{};
|
||||
|
||||
/**
|
||||
* @brief Thread responsible for emitting the log.
|
||||
*/
|
||||
std::thread::id thread_id{};
|
||||
/**
|
||||
* @brief Thread responsible for emitting the log.
|
||||
*/
|
||||
std::thread::id thread_id{};
|
||||
|
||||
/**
|
||||
* @brief Severity level of this entry.
|
||||
*/
|
||||
LogLevel level;
|
||||
/**
|
||||
* @brief Severity level of this entry.
|
||||
*/
|
||||
LogLevel level;
|
||||
|
||||
/**
|
||||
* @brief Pipeline phase associated with the entry.
|
||||
*/
|
||||
PipelinePhase phase;
|
||||
/**
|
||||
* @brief Pipeline phase associated with the entry.
|
||||
*/
|
||||
PipelinePhase phase;
|
||||
|
||||
/**
|
||||
* @brief Log message text.
|
||||
*/
|
||||
std::string message;
|
||||
/**
|
||||
* @brief Log message text.
|
||||
*/
|
||||
std::string message;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_ENTRY_H_
|
||||
|
||||
@@ -23,31 +23,31 @@
|
||||
* remain valid for the lifetime of the producer.
|
||||
*/
|
||||
class LogProducer final : public ILogger {
|
||||
public:
|
||||
/**
|
||||
* @brief Construct a channel-backed producer.
|
||||
*
|
||||
* @param channel Reference to the bounded channel used for log transfer.
|
||||
*/
|
||||
explicit LogProducer(BoundedChannel<LogEntry>& channel);
|
||||
public:
|
||||
/**
|
||||
* @brief Construct a channel-backed producer.
|
||||
*
|
||||
* @param channel Reference to the bounded channel used for log transfer.
|
||||
*/
|
||||
explicit LogProducer(BoundedChannel<LogEntry>& channel);
|
||||
|
||||
LogProducer(const LogProducer&) = delete;
|
||||
LogProducer& operator=(const LogProducer&) = delete;
|
||||
LogProducer(LogProducer&&) = delete;
|
||||
LogProducer& operator=(LogProducer&&) = delete;
|
||||
LogProducer(const LogProducer&) = delete;
|
||||
LogProducer& operator=(const LogProducer&) = delete;
|
||||
LogProducer(LogProducer&&) = delete;
|
||||
LogProducer& operator=(LogProducer&&) = delete;
|
||||
|
||||
~LogProducer() override = default;
|
||||
~LogProducer() override = default;
|
||||
|
||||
/**
|
||||
* @brief Queue a log message for asynchronous processing.
|
||||
*
|
||||
* Blocks while the channel applies backpressure. This blocking behavior
|
||||
* under heavy load is an accepted trade-off for simplicity.
|
||||
*/
|
||||
void DoLog(LogEntry log_entry) override;
|
||||
/**
|
||||
* @brief Queue a log message for asynchronous processing.
|
||||
*
|
||||
* Blocks while the channel applies backpressure. This blocking behavior
|
||||
* under heavy load is an accepted trade-off for simplicity.
|
||||
*/
|
||||
void DoLog(LogEntry log_entry) override;
|
||||
|
||||
private:
|
||||
BoundedChannel<LogEntry>& channel_;
|
||||
private:
|
||||
BoundedChannel<LogEntry>& channel_;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOG_PRODUCER_H_
|
||||
|
||||
@@ -23,43 +23,43 @@
|
||||
* by the composition root and injected into services that emit diagnostics.
|
||||
*/
|
||||
class ILogger {
|
||||
public:
|
||||
ILogger() = default;
|
||||
ILogger(const ILogger&) = delete;
|
||||
ILogger& operator=(const ILogger&) = delete;
|
||||
ILogger(ILogger&&) = delete;
|
||||
ILogger& operator=(ILogger&&) = delete;
|
||||
virtual ~ILogger() = default;
|
||||
public:
|
||||
ILogger() = default;
|
||||
ILogger(const ILogger&) = delete;
|
||||
ILogger& operator=(const ILogger&) = delete;
|
||||
ILogger(ILogger&&) = delete;
|
||||
ILogger& operator=(ILogger&&) = delete;
|
||||
virtual ~ILogger() = default;
|
||||
|
||||
/**
|
||||
* @brief Submit a log message to the logging subsystem.
|
||||
*
|
||||
* @param payload User-provided log data (level, phase, message).
|
||||
* @param origin Auto-captured source location of the call site.
|
||||
*/
|
||||
void Log(LogDTO payload,
|
||||
std::source_location origin = std::source_location::current(),
|
||||
std::chrono::system_clock::time_point timestamp =
|
||||
std::chrono::system_clock::now(),
|
||||
std::thread::id thread_id = std::this_thread::get_id()) {
|
||||
LogEntry entry;
|
||||
entry.timestamp = timestamp;
|
||||
entry.thread_id = thread_id;
|
||||
entry.level = payload.level;
|
||||
entry.phase = payload.phase;
|
||||
entry.message = std::move(payload.message);
|
||||
entry.origin = origin;
|
||||
DoLog(std::move(entry));
|
||||
}
|
||||
/**
|
||||
* @brief Submit a log message to the logging subsystem.
|
||||
*
|
||||
* @param payload User-provided log data (level, phase, message).
|
||||
* @param origin Auto-captured source location of the call site.
|
||||
*/
|
||||
void Log(LogDTO payload,
|
||||
std::source_location origin = std::source_location::current(),
|
||||
std::chrono::system_clock::time_point timestamp =
|
||||
std::chrono::system_clock::now(),
|
||||
std::thread::id thread_id = std::this_thread::get_id()) {
|
||||
LogEntry entry;
|
||||
entry.timestamp = timestamp;
|
||||
entry.thread_id = thread_id;
|
||||
entry.level = payload.level;
|
||||
entry.phase = payload.phase;
|
||||
entry.message = std::move(payload.message);
|
||||
entry.origin = origin;
|
||||
DoLog(std::move(entry));
|
||||
}
|
||||
|
||||
protected:
|
||||
/**
|
||||
* @brief Underlying implementation to transport the log entry.
|
||||
*
|
||||
* Implementations must be thread-safe as DoLog can be called concurrently
|
||||
* from multiple worker threads.
|
||||
*/
|
||||
virtual void DoLog(LogEntry log_entry) = 0;
|
||||
protected:
|
||||
/**
|
||||
* @brief Underlying implementation to transport the log entry.
|
||||
*
|
||||
* Implementations must be thread-safe as DoLog can be called concurrently
|
||||
* from multiple worker threads.
|
||||
*/
|
||||
virtual void DoLog(LogEntry log_entry) = 0;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_LOGGING_LOGGER_H_
|
||||
|
||||
@@ -24,56 +24,57 @@
|
||||
* example that fails validation, throws so the caller can skip the city.
|
||||
*/
|
||||
class MockPostalCodeService final : public IPostalCodeService {
|
||||
public:
|
||||
std::string GeneratePostalCode(const City& city) override {
|
||||
const PostalCodeSpec& spec = city.postal_code;
|
||||
public:
|
||||
std::string GeneratePostalCode(const City& city) override {
|
||||
const PostalCodeSpec& spec = city.postal_code;
|
||||
|
||||
if (spec.examples.empty()) {
|
||||
throw std::runtime_error(std::format(
|
||||
"No postal-code examples available for city '{}'", city.city));
|
||||
}
|
||||
|
||||
const std::string& candidate = spec.examples.front();
|
||||
|
||||
if (!MatchesAnyPattern(candidate, spec)) {
|
||||
throw std::runtime_error(
|
||||
std::format("Postal code '{}' for city '{}' does not match the "
|
||||
"curated postal-code regex",
|
||||
candidate, city.city));
|
||||
}
|
||||
|
||||
return candidate;
|
||||
}
|
||||
|
||||
private:
|
||||
/**
|
||||
* @brief Returns true if @p candidate matches any city regex, or the
|
||||
* country format regex when no city regex matches. When the spec carries no
|
||||
* usable regex at all, validation is skipped (returns true).
|
||||
*/
|
||||
static bool MatchesAnyPattern(const std::string& candidate,
|
||||
const PostalCodeSpec& spec) {
|
||||
bool has_pattern = false;
|
||||
|
||||
for (const std::string& pattern : spec.city_regexes) {
|
||||
if (pattern.empty()) {
|
||||
continue;
|
||||
if (spec.examples.empty()) {
|
||||
throw std::runtime_error(std::format(
|
||||
"No postal-code examples available for city '{}'", city.city));
|
||||
}
|
||||
has_pattern = true;
|
||||
if (std::regex_match(candidate, std::regex(pattern))) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
if (!spec.country_format_regex.empty()) {
|
||||
has_pattern = true;
|
||||
if (std::regex_match(candidate, std::regex(spec.country_format_regex))) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
const std::string& candidate = spec.examples.front();
|
||||
|
||||
return !has_pattern;
|
||||
}
|
||||
if (!MatchesAnyPattern(candidate, spec)) {
|
||||
throw std::runtime_error(
|
||||
std::format("Postal code '{}' for city '{}' does not match the "
|
||||
"curated postal-code regex",
|
||||
candidate, city.city));
|
||||
}
|
||||
|
||||
return candidate;
|
||||
}
|
||||
|
||||
private:
|
||||
/**
|
||||
* @brief Returns true if @p candidate matches any city regex, or the
|
||||
* country format regex when no city regex matches. When the spec carries no
|
||||
* usable regex at all, validation is skipped (returns true).
|
||||
*/
|
||||
static bool MatchesAnyPattern(const std::string& candidate,
|
||||
const PostalCodeSpec& spec) {
|
||||
bool has_pattern = false;
|
||||
|
||||
for (const std::string& pattern : spec.city_regexes) {
|
||||
if (pattern.empty()) {
|
||||
continue;
|
||||
}
|
||||
has_pattern = true;
|
||||
if (std::regex_match(candidate, std::regex(pattern))) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
if (!spec.country_format_regex.empty()) {
|
||||
has_pattern = true;
|
||||
if (std::regex_match(candidate,
|
||||
std::regex(spec.country_format_regex))) {
|
||||
return true;
|
||||
}
|
||||
}
|
||||
|
||||
return !has_pattern;
|
||||
}
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_MOCK_POSTAL_CODE_SERVICE_H_
|
||||
|
||||
@@ -14,22 +14,22 @@
|
||||
* @brief Interface for services that resolve a postal code for a city.
|
||||
*/
|
||||
class IPostalCodeService {
|
||||
public:
|
||||
IPostalCodeService() = default;
|
||||
virtual ~IPostalCodeService() = default;
|
||||
public:
|
||||
IPostalCodeService() = default;
|
||||
virtual ~IPostalCodeService() = default;
|
||||
|
||||
IPostalCodeService(const IPostalCodeService&) = delete;
|
||||
IPostalCodeService& operator=(const IPostalCodeService&) = delete;
|
||||
IPostalCodeService(IPostalCodeService&&) = delete;
|
||||
IPostalCodeService& operator=(IPostalCodeService&&) = delete;
|
||||
IPostalCodeService(const IPostalCodeService&) = delete;
|
||||
IPostalCodeService& operator=(const IPostalCodeService&) = delete;
|
||||
IPostalCodeService(IPostalCodeService&&) = delete;
|
||||
IPostalCodeService& operator=(IPostalCodeService&&) = delete;
|
||||
|
||||
/**
|
||||
* @brief Resolves a postal code for @p city.
|
||||
*
|
||||
* @param city City whose curated postal-code examples supply the result.
|
||||
* @return A postal code string, or an empty string if none is available.
|
||||
*/
|
||||
virtual std::string GeneratePostalCode(const City& city) = 0;
|
||||
/**
|
||||
* @brief Resolves a postal code for @p city.
|
||||
*
|
||||
* @param city City whose curated postal-code examples supply the result.
|
||||
* @return A postal code string, or an empty string if none is available.
|
||||
*/
|
||||
virtual std::string GeneratePostalCode(const City& city) = 0;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_POSTAL_CODE_SERVICE_H_
|
||||
|
||||
@@ -20,13 +20,13 @@
|
||||
* via GenerateStringFromRegex().
|
||||
*/
|
||||
class XegerPostalCodeService final : public IPostalCodeService {
|
||||
public:
|
||||
XegerPostalCodeService();
|
||||
public:
|
||||
XegerPostalCodeService();
|
||||
|
||||
std::string GeneratePostalCode(const City& city) override;
|
||||
std::string GeneratePostalCode(const City& city) override;
|
||||
|
||||
private:
|
||||
std::mt19937 rng_;
|
||||
private:
|
||||
std::mt19937 rng_;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_POSTAL_CODE_XEGER_POSTAL_CODE_SERVICE_H_
|
||||
|
||||
@@ -24,22 +24,22 @@
|
||||
* @brief Interface for loading named prompt files.
|
||||
*/
|
||||
class IPromptDirectory {
|
||||
public:
|
||||
IPromptDirectory() = default;
|
||||
IPromptDirectory(const IPromptDirectory&) = delete;
|
||||
IPromptDirectory& operator=(const IPromptDirectory&) = delete;
|
||||
IPromptDirectory(IPromptDirectory&&) = delete;
|
||||
IPromptDirectory& operator=(IPromptDirectory&&) = delete;
|
||||
virtual ~IPromptDirectory() = default;
|
||||
public:
|
||||
IPromptDirectory() = default;
|
||||
IPromptDirectory(const IPromptDirectory&) = delete;
|
||||
IPromptDirectory& operator=(const IPromptDirectory&) = delete;
|
||||
IPromptDirectory(IPromptDirectory&&) = delete;
|
||||
IPromptDirectory& operator=(IPromptDirectory&&) = delete;
|
||||
virtual ~IPromptDirectory() = default;
|
||||
|
||||
/**
|
||||
* @brief Loads the prompt associated with @p key.
|
||||
*
|
||||
* @param key Logical prompt key, e.g. "BREWERY_GENERATION".
|
||||
* @return Prompt text.
|
||||
* @throws std::runtime_error if the prompt file cannot be found or read.
|
||||
*/
|
||||
[[nodiscard]] virtual std::string Load(std::string_view key) = 0;
|
||||
/**
|
||||
* @brief Loads the prompt associated with @p key.
|
||||
*
|
||||
* @param key Logical prompt key, e.g. "BREWERY_GENERATION".
|
||||
* @return Prompt text.
|
||||
* @throws std::runtime_error if the prompt file cannot be found or read.
|
||||
*/
|
||||
[[nodiscard]] virtual std::string Load(std::string_view key) = 0;
|
||||
};
|
||||
|
||||
/**
|
||||
@@ -50,33 +50,33 @@ class IPromptDirectory {
|
||||
* at construction time; individual file absence is reported lazily at Load().
|
||||
*/
|
||||
class PromptDirectory final : public IPromptDirectory {
|
||||
public:
|
||||
/**
|
||||
* @brief Constructs a PromptDirectory rooted at @p prompt_dir.
|
||||
*
|
||||
* @param prompt_dir Absolute or relative path to the prompt directory.
|
||||
* @throws std::runtime_error if @p prompt_dir does not exist or is not a
|
||||
* directory.
|
||||
*/
|
||||
explicit PromptDirectory(const std::filesystem::path& prompt_dir);
|
||||
PromptDirectory(const std::filesystem::path& prompt_dir,
|
||||
std::shared_ptr<ILogger> logger);
|
||||
public:
|
||||
/**
|
||||
* @brief Constructs a PromptDirectory rooted at @p prompt_dir.
|
||||
*
|
||||
* @param prompt_dir Absolute or relative path to the prompt directory.
|
||||
* @throws std::runtime_error if @p prompt_dir does not exist or is not a
|
||||
* directory.
|
||||
*/
|
||||
explicit PromptDirectory(const std::filesystem::path& prompt_dir);
|
||||
PromptDirectory(const std::filesystem::path& prompt_dir,
|
||||
std::shared_ptr<ILogger> logger);
|
||||
|
||||
/**
|
||||
* @brief Loads the prompt for @p key, caching the result.
|
||||
*
|
||||
* Maps @p key → <prompt_dir>/<key>.md.
|
||||
*
|
||||
* @param key Logical prompt key.
|
||||
* @return Prompt text.
|
||||
* @throws std::runtime_error if the file does not exist or is empty.
|
||||
*/
|
||||
[[nodiscard]] std::string Load(std::string_view key) override;
|
||||
/**
|
||||
* @brief Loads the prompt for @p key, caching the result.
|
||||
*
|
||||
* Maps @p key → <prompt_dir>/<key>.md.
|
||||
*
|
||||
* @param key Logical prompt key.
|
||||
* @return Prompt text.
|
||||
* @throws std::runtime_error if the file does not exist or is empty.
|
||||
*/
|
||||
[[nodiscard]] std::string Load(std::string_view key) override;
|
||||
|
||||
private:
|
||||
std::filesystem::path prompt_dir_;
|
||||
std::shared_ptr<ILogger> logger_;
|
||||
std::unordered_map<std::string, std::string> cache_;
|
||||
private:
|
||||
std::filesystem::path prompt_dir_;
|
||||
std::shared_ptr<ILogger> logger_;
|
||||
std::unordered_map<std::string, std::string> cache_;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_SERVICES_PROMPTING_PROMPT_DIRECTORY_H_
|
||||
|
||||
@@ -55,33 +55,33 @@ struct Alternation;
|
||||
struct Repeat;
|
||||
|
||||
struct Visitor {
|
||||
virtual void Visit(const Literal&) = 0;
|
||||
virtual void Visit(const AnyChar&) = 0;
|
||||
virtual void Visit(const CharClass&) = 0;
|
||||
virtual void Visit(const Concat&) = 0;
|
||||
virtual void Visit(const Alternation&) = 0;
|
||||
virtual void Visit(const Repeat&) = 0;
|
||||
virtual ~Visitor() = default;
|
||||
virtual void Visit(const Literal&) = 0;
|
||||
virtual void Visit(const AnyChar&) = 0;
|
||||
virtual void Visit(const CharClass&) = 0;
|
||||
virtual void Visit(const Concat&) = 0;
|
||||
virtual void Visit(const Alternation&) = 0;
|
||||
virtual void Visit(const Repeat&) = 0;
|
||||
virtual ~Visitor() = default;
|
||||
};
|
||||
|
||||
struct Node {
|
||||
virtual void Accept(Visitor&) const = 0;
|
||||
virtual ~Node() = default;
|
||||
virtual void Accept(Visitor&) const = 0;
|
||||
virtual ~Node() = default;
|
||||
};
|
||||
|
||||
using NodePtr = std::unique_ptr<Node>;
|
||||
|
||||
template <typename Derived>
|
||||
struct Visitable : Node {
|
||||
void Accept(Visitor& visitor) const override {
|
||||
visitor.Visit(static_cast<const Derived&>(*this));
|
||||
}
|
||||
void Accept(Visitor& visitor) const override {
|
||||
visitor.Visit(static_cast<const Derived&>(*this));
|
||||
}
|
||||
};
|
||||
|
||||
// One fixed character, e.g. 'a'.
|
||||
struct Literal : Visitable<Literal> {
|
||||
char ch;
|
||||
explicit Literal(const char c) : ch(c) {}
|
||||
char ch;
|
||||
explicit Literal(const char c) : ch(c) {}
|
||||
};
|
||||
|
||||
// The "." wildcard: any single printable character.
|
||||
@@ -91,18 +91,18 @@ struct AnyChar : Visitable<AnyChar> {};
|
||||
// character 'x' is the range {'x', 'x'}. `negated` flips the meaning to
|
||||
// "any character NOT listed" (i.e. `[^...]`).
|
||||
struct CharClass : Visitable<CharClass> {
|
||||
std::vector<std::pair<char, char>> ranges;
|
||||
bool negated = false;
|
||||
std::vector<std::pair<char, char>> ranges;
|
||||
bool negated = false;
|
||||
};
|
||||
|
||||
// "Do these children one after another."
|
||||
struct Concat : Visitable<Concat> {
|
||||
std::vector<NodePtr> parts;
|
||||
std::vector<NodePtr> parts;
|
||||
};
|
||||
|
||||
// "Pick exactly one of these options at random" -- the `|` operator.
|
||||
struct Alternation : Visitable<Alternation> {
|
||||
std::vector<NodePtr> options;
|
||||
std::vector<NodePtr> options;
|
||||
};
|
||||
|
||||
// "Repeat one child between min and max times."
|
||||
@@ -111,9 +111,9 @@ struct Alternation : Visitable<Alternation> {
|
||||
// a? -> min 0, max 1
|
||||
// a{2,5} -> min 2, max 5
|
||||
struct Repeat : Visitable<Repeat> {
|
||||
NodePtr child;
|
||||
unsigned int min = 0;
|
||||
std::optional<unsigned int> max; // std::nullopt means "no upper bound"
|
||||
NodePtr child;
|
||||
unsigned int min = 0;
|
||||
std::optional<unsigned int> max; // std::nullopt means "no upper bound"
|
||||
};
|
||||
|
||||
// Parser (recursive descent)
|
||||
@@ -125,75 +125,75 @@ struct Repeat : Visitable<Repeat> {
|
||||
// ParseAtom ::= a . [..] (..) \d
|
||||
|
||||
class Parser {
|
||||
public:
|
||||
explicit Parser(std::string_view pattern);
|
||||
public:
|
||||
explicit Parser(std::string_view pattern);
|
||||
|
||||
NodePtr Parse();
|
||||
NodePtr Parse();
|
||||
|
||||
private:
|
||||
std::string src_;
|
||||
size_t pos_ = 0;
|
||||
private:
|
||||
std::string src_;
|
||||
size_t pos_ = 0;
|
||||
|
||||
// Strips anchors (leading '^' and trailing '$') as they are not needed for
|
||||
// generation.
|
||||
static std::string StripAnchors(std::string_view pattern);
|
||||
// Strips anchors (leading '^' and trailing '$') as they are not needed for
|
||||
// generation.
|
||||
static std::string StripAnchors(std::string_view pattern);
|
||||
|
||||
[[nodiscard]] bool AtEnd() const;
|
||||
[[nodiscard]] char Peek() const;
|
||||
char Advance();
|
||||
bool Match(char c);
|
||||
void Expect(char c);
|
||||
[[nodiscard]] bool AtEnd() const;
|
||||
[[nodiscard]] char Peek() const;
|
||||
char Advance();
|
||||
bool Match(char c);
|
||||
void Expect(char c);
|
||||
|
||||
// Level 1: alternation -- ( concat | concat | concat )
|
||||
NodePtr ParseAlternation();
|
||||
// Level 1: alternation -- ( concat | concat | concat )
|
||||
NodePtr ParseAlternation();
|
||||
|
||||
// Level 2: concatenation -- a run of items back to back
|
||||
NodePtr ParseConcat();
|
||||
// Level 2: concatenation -- a run of items back to back
|
||||
NodePtr ParseConcat();
|
||||
|
||||
// Level 3: an atom plus an optional quantifier
|
||||
NodePtr ParseRepeat();
|
||||
// Level 3: an atom plus an optional quantifier
|
||||
NodePtr ParseRepeat();
|
||||
|
||||
// Curly-brace quantifiers: {n}, {n,}, {n,m}
|
||||
NodePtr ParseBrace(NodePtr atom);
|
||||
// Curly-brace quantifiers: {n}, {n,}, {n,m}
|
||||
NodePtr ParseBrace(NodePtr atom);
|
||||
|
||||
// Level 4: an atom -- the smallest standalone unit
|
||||
NodePtr ParseAtom();
|
||||
// Level 4: an atom -- the smallest standalone unit
|
||||
NodePtr ParseAtom();
|
||||
|
||||
static NodePtr MakeClass(std::vector<std::pair<char, char>> ranges,
|
||||
bool negated);
|
||||
static NodePtr MakeClass(std::vector<std::pair<char, char>> ranges,
|
||||
bool negated);
|
||||
|
||||
NodePtr ParseEscape();
|
||||
NodePtr ParseEscape();
|
||||
|
||||
NodePtr ParseCharClass();
|
||||
NodePtr ParseCharClass();
|
||||
|
||||
// Reads one character inside [ ], turning \] \n etc. into the real
|
||||
// character they represent.
|
||||
char ClassChar();
|
||||
// Reads one character inside [ ], turning \] \n etc. into the real
|
||||
// character they represent.
|
||||
char ClassChar();
|
||||
};
|
||||
|
||||
// Generator -- a Visitor that emits a random matching string
|
||||
|
||||
class XegerGenerator final : public Visitor {
|
||||
public:
|
||||
XegerGenerator(std::mt19937& rng, int unbounded_cap);
|
||||
public:
|
||||
XegerGenerator(std::mt19937& rng, int unbounded_cap);
|
||||
|
||||
std::string Run(const Node& root);
|
||||
std::string Run(const Node& root);
|
||||
|
||||
void Visit(const Literal& node) override;
|
||||
void Visit(const AnyChar&) override;
|
||||
void Visit(const CharClass& node) override;
|
||||
void Visit(const Concat& node) override;
|
||||
void Visit(const Alternation& node) override;
|
||||
void Visit(const Repeat& node) override;
|
||||
void Visit(const Literal& node) override;
|
||||
void Visit(const AnyChar&) override;
|
||||
void Visit(const CharClass& node) override;
|
||||
void Visit(const Concat& node) override;
|
||||
void Visit(const Alternation& node) override;
|
||||
void Visit(const Repeat& node) override;
|
||||
|
||||
private:
|
||||
std::mt19937& rng_;
|
||||
int unbounded_cap_;
|
||||
std::string out_;
|
||||
private:
|
||||
std::mt19937& rng_;
|
||||
int unbounded_cap_;
|
||||
std::string out_;
|
||||
|
||||
static bool InRanges(const CharClass& node, char c);
|
||||
static bool InRanges(const CharClass& node, char c);
|
||||
|
||||
char PickFromClass(const CharClass& node);
|
||||
char PickFromClass(const CharClass& node);
|
||||
};
|
||||
|
||||
} // namespace xeger_internal
|
||||
|
||||
@@ -25,31 +25,31 @@
|
||||
* bound to a single origin at construction time.
|
||||
*/
|
||||
class HttpWebClient final : public WebClient {
|
||||
public:
|
||||
explicit HttpWebClient(std::shared_ptr<ILogger> logger)
|
||||
: logger_(std::move(logger)) {}
|
||||
~HttpWebClient() override = default;
|
||||
public:
|
||||
explicit HttpWebClient(std::shared_ptr<ILogger> logger)
|
||||
: logger_(std::move(logger)) {}
|
||||
~HttpWebClient() override = default;
|
||||
|
||||
/**
|
||||
* @brief Executes a blocking HTTP/HTTPS GET request against a full URL.
|
||||
*
|
||||
* @param url Fully-qualified URL, e.g.
|
||||
* "https://en.wikipedia.org/api/rest_v1/page/summary/Berlin"
|
||||
* @return Response body on HTTP 2xx; throws std::runtime_error otherwise.
|
||||
*/
|
||||
std::string Get(const std::string& url) override;
|
||||
/**
|
||||
* @brief Executes a blocking HTTP/HTTPS GET request against a full URL.
|
||||
*
|
||||
* @param url Fully-qualified URL, e.g.
|
||||
* "https://en.wikipedia.org/api/rest_v1/page/summary/Berlin"
|
||||
* @return Response body on HTTP 2xx; throws std::runtime_error otherwise.
|
||||
*/
|
||||
std::string Get(const std::string& url) override;
|
||||
|
||||
/**
|
||||
* @brief Percent-encodes a single URI component (query parameter value or
|
||||
* path segment). Delegates to httplib::encode_uri_component().
|
||||
*
|
||||
* @param value Raw string to encode.
|
||||
* @return Percent-encoded string safe for use in a URL.
|
||||
*/
|
||||
std::string EncodeURL(const std::string& value) override;
|
||||
/**
|
||||
* @brief Percent-encodes a single URI component (query parameter value or
|
||||
* path segment). Delegates to httplib::encode_uri_component().
|
||||
*
|
||||
* @param value Raw string to encode.
|
||||
* @return Percent-encoded string safe for use in a URL.
|
||||
*/
|
||||
std::string EncodeURL(const std::string& value) override;
|
||||
|
||||
private:
|
||||
std::shared_ptr<ILogger> logger_;
|
||||
private:
|
||||
std::shared_ptr<ILogger> logger_;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_HTTP_WEB_CLIENT_H_
|
||||
|
||||
@@ -12,24 +12,24 @@
|
||||
* @brief Abstract web client interface.
|
||||
*/
|
||||
class WebClient {
|
||||
public:
|
||||
virtual ~WebClient() = default;
|
||||
public:
|
||||
virtual ~WebClient() = default;
|
||||
|
||||
/**
|
||||
* @brief Executes an HTTP GET request.
|
||||
*
|
||||
* @param url Request URL.
|
||||
* @return Response body.
|
||||
*/
|
||||
virtual std::string Get(const std::string& url) = 0;
|
||||
/**
|
||||
* @brief Executes an HTTP GET request.
|
||||
*
|
||||
* @param url Request URL.
|
||||
* @return Response body.
|
||||
*/
|
||||
virtual std::string Get(const std::string& url) = 0;
|
||||
|
||||
/**
|
||||
* @brief URL-encodes a string value.
|
||||
*
|
||||
* @param value Raw string value.
|
||||
* @return Encoded value safe for URL usage.
|
||||
*/
|
||||
virtual std::string EncodeURL(const std::string& value) = 0;
|
||||
/**
|
||||
* @brief URL-encodes a string value.
|
||||
*
|
||||
* @param value Raw string value.
|
||||
* @return Encoded value safe for URL usage.
|
||||
*/
|
||||
virtual std::string EncodeURL(const std::string& value) = 0;
|
||||
};
|
||||
|
||||
#endif // BIERGARTEN_PIPELINE_INCLUDES_WEB_CLIENT_WEB_CLIENT_H_
|
||||
|
||||
Reference in New Issue
Block a user