@startuml indexer
!define COMPONENT_INTERFACE <<Component Interface>>
!define INTERNAL <<Internal>>
!define ASYNC <<async>>
package "mcp_server.indexer" <<Component>> {
' ========================================
' Component Interfaces (Public)
' ========================================
interface IIndexEngine COMPONENT_INTERFACE #LightGreen {
+ASYNC index_file(file_path: str, force: bool): IndexResult
+ASYNC index_directory(directory: str, recursive: bool, patterns: List<str>): BatchIndexResult
+ASYNC update_index(file_path: str): UpdateResult
+ASYNC remove_from_index(file_path: str): void
+get_index_status(path: str): IndexStatus
+ASYNC rebuild_index(): void
}
interface IIndexCoordinator COMPONENT_INTERFACE #LightGreen {
+ASYNC coordinate_indexing(paths: List<str], options: IndexOptions): CoordinationResult
+ASYNC schedule_reindex(path: str, priority: int): void
+get_pending_tasks(): List<IndexTask]
+cancel_task(task_id: str): bool
+get_progress(): IndexProgress
}
interface IParserCoordinator COMPONENT_INTERFACE #LightGreen {
+ASYNC parse_file(file_path: str): ParseResult
+ASYNC parse_content(content: str, language: str): ParseResult
+get_parser_for_language(language: str): IParser
+register_parser(language: str, parser: IParser): void
}
interface IParseOrchestrator COMPONENT_INTERFACE #LightGreen {
+ASYNC orchestrate_parsing(files: List<str]): List<ParseResult]
+ASYNC parse_with_fallback(file_path: str): ParseResult
+get_parse_statistics(): ParseStatistics
+clear_parse_cache(): void
}
interface IQueryOptimizer COMPONENT_INTERFACE #LightGreen {
+optimize_query(query: Query): OptimizedQuery
+estimate_cost(query: Query): QueryCost
+suggest_indexes(query_patterns: List<Query]): List<IndexSuggestion]
+analyze_query_performance(query: Query, results: QueryResults): PerformanceReport
}
interface ISearchPlanner COMPONENT_INTERFACE #LightGreen {
+plan_search(query: SearchQuery): SearchPlan
+ASYNC execute_plan(plan: SearchPlan): SearchResults
+optimize_plan(plan: SearchPlan): SearchPlan
+get_search_statistics(): SearchStatistics
}
interface IFuzzyIndexer COMPONENT_INTERFACE #LightGreen {
+ASYNC index_for_fuzzy(text: str, metadata: Dict): void
+ASYNC search_fuzzy(query: str, threshold: float): List<FuzzyMatch]
+update_fuzzy_index(id: str, text: str): void
+remove_from_fuzzy_index(id: str): void
}
interface ITrigramSearcher COMPONENT_INTERFACE #LightGreen {
+generate_trigrams(text: str): Set<str]
+ASYNC search_trigrams(trigrams: Set<str], limit: int): List<TrigramMatch]
+calculate_similarity(text1: str, text2: str): float
+get_trigram_statistics(): TrigramStats
}
interface ISemanticIndexer COMPONENT_INTERFACE #LightGreen {
+ASYNC generate_embeddings(text: str): Embedding
+ASYNC index_semantic(text: str, metadata: Dict): void
+ASYNC search_semantic(query: str, k: int): List<SemanticMatch]
+ASYNC find_similar(embedding: Embedding, k: int): List<SemanticMatch]
}
interface IEmbeddingGenerator COMPONENT_INTERFACE #LightGreen {
+ASYNC generate(text: str): Embedding
+ASYNC batch_generate(texts: List<str]): List<Embedding]
+get_embedding_dimension(): int
+get_model_info(): ModelInfo
}
' ========================================
' Main Implementation Classes
' ========================================
class IndexEngine implements IIndexEngine, IIndexCoordinator {
-parser_coordinator: IParserCoordinator
-storage: IIndexStorage
-graph_builder: IGraphBuilder
-fuzzy_indexer: IFuzzyIndexer
-semantic_indexer: ISemanticIndexer
-task_queue: ITaskQueue
-cache: ICache
-logger: ILogger
-metrics: IMetrics
+ASYNC index_file(file_path: str, force: bool): IndexResult
+ASYNC index_directory(directory: str, recursive: bool, patterns: List<str]): BatchIndexResult
+ASYNC update_index(file_path: str): UpdateResult
+ASYNC remove_from_index(file_path: str): void
+get_index_status(path: str): IndexStatus
+ASYNC rebuild_index(): void
+ASYNC coordinate_indexing(paths: List<str], options: IndexOptions): CoordinationResult
+ASYNC schedule_reindex(path: str, priority: int): void
+get_pending_tasks(): List<IndexTask]
+cancel_task(task_id: str): bool
+get_progress(): IndexProgress
-ASYNC _process_file(file_path: str, options: IndexOptions): IndexResult
-ASYNC _extract_and_store(parse_result: ParseResult, file_path: str): void
-_should_index(file_path: str, force: bool): bool
-_get_file_hash(file_path: str): str
}
class ParserCoordinator implements IParserCoordinator, IParseOrchestrator {
-parsers: Dict<str, IParser]
-plugin_manager: IPluginManager
-cache: IParseCache
-metrics: ParseMetrics
+ASYNC parse_file(file_path: str): ParseResult
+ASYNC parse_content(content: str, language: str): ParseResult
+get_parser_for_language(language: str): IParser
+register_parser(language: str, parser: IParser): void
+ASYNC orchestrate_parsing(files: List<str]): List<ParseResult]
+ASYNC parse_with_fallback(file_path: str): ParseResult
+get_parse_statistics(): ParseStatistics
+clear_parse_cache(): void
-ASYNC _parse_with_timeout(parser: IParser, content: str): ParseResult
-_detect_language(file_path: str, content: str): str
-_normalize_parse_result(result: Any, language: str): ParseResult
}
class QueryOptimizer implements IQueryOptimizer, ISearchPlanner {
-index_stats: IIndexStatistics
-query_cache: IQueryCache
-cost_model: ICostModel
+optimize_query(query: Query): OptimizedQuery
+estimate_cost(query: Query): QueryCost
+suggest_indexes(query_patterns: List<Query]): List<IndexSuggestion]
+analyze_query_performance(query: Query, results: QueryResults): PerformanceReport
+plan_search(query: SearchQuery): SearchPlan
+ASYNC execute_plan(plan: SearchPlan): SearchResults
+optimize_plan(plan: SearchPlan): SearchPlan
+get_search_statistics(): SearchStatistics
-_rewrite_query(query: Query): Query
-_choose_index(query: Query): IndexChoice
-_estimate_selectivity(predicate: Predicate): float
}
class FuzzyIndexer implements IFuzzyIndexer, ITrigramSearcher {
-trigram_index: ITrigramIndex
-storage: IFuzzyStorage
-similarity_threshold: float
+ASYNC index_for_fuzzy(text: str, metadata: Dict): void
+ASYNC search_fuzzy(query: str, threshold: float): List<FuzzyMatch]
+update_fuzzy_index(id: str, text: str): void
+remove_from_fuzzy_index(id: str): void
+generate_trigrams(text: str): Set<str]
+ASYNC search_trigrams(trigrams: Set<str], limit: int): List<TrigramMatch]
+calculate_similarity(text1: str, text2: str): float
+get_trigram_statistics(): TrigramStats
-_normalize_text(text: str): str
-_calculate_jaccard_similarity(set1: Set<str], set2: Set<str]): float
}
class SemanticIndexer implements ISemanticIndexer, IEmbeddingGenerator {
-embedding_model: IEmbeddingModel
-vector_store: IVectorStore
-dimension: int
-batch_size: int
+ASYNC generate_embeddings(text: str): Embedding
+ASYNC index_semantic(text: str, metadata: Dict): void
+ASYNC search_semantic(query: str, k: int): List<SemanticMatch]
+ASYNC find_similar(embedding: Embedding, k: int): List<SemanticMatch]
+ASYNC generate(text: str): Embedding
+ASYNC batch_generate(texts: List<str]): List<Embedding]
+get_embedding_dimension(): int
+get_model_info(): ModelInfo
-ASYNC _chunk_text(text: str): List<str]
-_normalize_embedding(embedding: List<float]): Embedding
}
' ========================================
' Internal Classes and Interfaces
' ========================================
interface IIndexStorage INTERNAL {
+store_file_index(file_path: str, index_data: IndexData): void
+get_file_index(file_path: str): Optional<IndexData]
+update_file_index(file_path: str, updates: Dict): void
+delete_file_index(file_path: str): void
+search_indexes(criteria: SearchCriteria): List<IndexData]
}
interface IParseCache INTERNAL {
+get(file_path: str, hash: str): Optional<ParseResult]
+put(file_path: str, hash: str, result: ParseResult): void
+invalidate(file_path: str): void
+get_stats(): CacheStats
}
interface ICostModel INTERNAL {
+estimate_index_scan_cost(index: str, selectivity: float): float
+estimate_join_cost(left_size: int, right_size: int): float
+estimate_sort_cost(size: int): float
+estimate_filter_cost(size: int, selectivity: float): float
}
class IndexStorage INTERNAL implements IIndexStorage {
-db: ISQLiteConnection
-serializer: ISerializer
+store_file_index(file_path: str, index_data: IndexData): void
+get_file_index(file_path: str): Optional<IndexData]
+update_file_index(file_path: str, updates: Dict): void
+delete_file_index(file_path: str): void
+search_indexes(criteria: SearchCriteria): List<IndexData]
-_serialize_index_data(data: IndexData): bytes
-_deserialize_index_data(data: bytes): IndexData
}
class BatchIndexer INTERNAL {
-engine: IIndexEngine
-batch_size: int
-parallelism: int
+ASYNC index_batch(files: List<str], options: IndexOptions): BatchResult
+ASYNC parallel_index(files: List<str], workers: int): BatchResult
-ASYNC _process_batch(batch: List<str]): List<IndexResult]
-_partition_files(files: List<str], partitions: int): List<List<str]]
}
class IndexStatistics INTERNAL implements IIndexStatistics {
-stats_cache: Dict<str, Stats]
-update_interval: int
+get_table_stats(table: str): TableStats
+get_index_stats(index: str): IndexStats
+get_cardinality(column: str): int
+update_statistics(): void
}
class ProgressTracker INTERNAL {
-total_files: int
-processed_files: int
-failed_files: int
-start_time: datetime
+update_progress(processed: int, failed: int): void
+get_progress(): IndexProgress
+estimate_time_remaining(): Optional<timedelta]
+get_throughput(): float
}
' ========================================
' Supporting Types
' ========================================
class IndexResult {
+file_path: str
+success: bool
+symbols_count: int
+references_count: int
+duration_ms: float
+error: Optional<str]
}
class BatchIndexResult {
+total_files: int
+successful: int
+failed: int
+results: List<IndexResult]
+total_duration_ms: float
}
class ParseResult {
+ast: AST
+symbols: List<Symbol]
+imports: List<Import]
+references: List<Reference]
+language: str
+parse_time_ms: float
}
class IndexOptions {
+force_reindex: bool
+include_patterns: List<str]
+exclude_patterns: List<str]
+max_file_size: int
+follow_symlinks: bool
+extract_graph: bool
+generate_embeddings: bool
}
class SearchPlan {
+query: SearchQuery
+index_choice: str
+filter_order: List<Filter]
+use_cache: bool
+estimated_cost: float
}
class FuzzyMatch {
+text: str
+score: float
+metadata: Dict
+location: Location
}
class SemanticMatch {
+text: str
+score: float
+embedding: Embedding
+metadata: Dict
+location: Location
}
class IndexProgress {
+total: int
+completed: int
+failed: int
+current_file: Optional<str]
+elapsed_time: timedelta
+estimated_remaining: Optional<timedelta]
}
' ========================================
' Relationships
' ========================================
IndexEngine --> IParserCoordinator : coordinates parsing
IndexEngine --> IIndexStorage : stores indexes
IndexEngine --> IFuzzyIndexer : fuzzy indexing
IndexEngine --> ISemanticIndexer : semantic indexing
IndexEngine --> IGraphBuilder : builds graph
ParserCoordinator --> IPluginManager : gets parsers
ParserCoordinator --> IParseCache : caches results
QueryOptimizer --> IIndexStatistics : uses stats
QueryOptimizer --> ICostModel : estimates costs
FuzzyIndexer --> ITrigramIndex : stores trigrams
SemanticIndexer --> IVectorStore : stores embeddings
' External dependencies
IndexEngine ..> ITaskQueue : queues tasks
IndexEngine ..> ICache : caches
IndexEngine ..> ILogger : logs
IndexEngine ..> IMetrics : reports
}
' Exceptions
class IndexError <<exception>> {
+file_path: str
+operation: str
+cause: Exception
}
class ParseError <<exception>> {
+file_path: str
+line: int
+column: int
+message: str
}
class QueryError <<exception>> {
+query: str
+reason: str
}
IIndexEngine ..> IndexError : throws
IParserCoordinator ..> ParseError : throws
IQueryOptimizer ..> QueryError : throws
@enduml
