UNPKG

datapilot-cli

Version:

Enterprise-grade streaming multi-format data analysis with comprehensive statistical insights and intelligent relationship detection - supports CSV, JSON, Excel, TSV, Parquet - memory-efficient, cross-platform

67 lines 1.91 kB
/** * Parquet Parser Implementation * Supports .parquet files using hyparquet library */ import type { ParsedRow, ParseOptions, FormatDetectionResult, FormatDetector } from './base/data-parser'; import { BaseParser } from './base/data-parser'; interface ParquetMetadata { numRows: number; schema: any; columnNames: string[]; fileSize: number; compressionType?: string; rowGroups: number; } /** * Parquet Format Detector */ export declare class ParquetDetector implements FormatDetector { getSupportedExtensions(): string[]; getFormatName(): string; detect(filePath: string): Promise<FormatDetectionResult>; private readParquetMetadata; } /** * Parquet Parser Implementation */ export declare class ParquetParser extends BaseParser { private headers; private metadata; getSupportedExtensions(): string[]; getFormatName(): string; detect(filePath: string): Promise<FormatDetectionResult>; parse(filePath: string, options?: ParseOptions): AsyncIterableIterator<ParsedRow>; private readFileMetadata; private formatValue; /** * Get detected headers for column mapping */ getHeaders(): string[]; /** * Get Parquet file metadata */ getMetadata(): ParquetMetadata | null; /** * Get schema information from Parquet file */ getSchema(filePath: string): Promise<any>; /** * Get row group information for optimization */ getRowGroups(filePath: string): Promise<Array<{ index: number; numRows: number; totalByteSize: number; columns: Array<{ name: string; type: string; compression: string; }>; }>>; } /** * Factory function to create Parquet parser */ export declare function createParquetParser(options?: ParseOptions): ParquetParser; export {}; //# sourceMappingURL=parquet-parser.d.ts.map