@overture-stack/lyric/dist/src/utils/fileUtils.d.ts

Data Submission system

import { type Unit } from 'bytes';
import { z } from 'zod';
import { type DataRecord, type ParseSchemaError, type Schema, type UnprocessedDataRecord } from '@overture-stack/lectern-client';
import { type BatchError } from './types.js';
export declare const SUPPORTED_FILE_EXTENSIONS: z.ZodEnum<["tsv", "csv"]>;
export type SupportedFileExtension = z.infer<typeof SUPPORTED_FILE_EXTENSIONS>;
export declare const columnSeparatorValue: {
    readonly tsv: "\t";
    readonly csv: ",";
};
/**
 * Determines the separator character for a given file based on its extension.
 * @param file The name of the file whose extension determines the separator character.
 * @returns The separator character associated with the file extension, or `undefined` if
 *          the file extension is invalid or unrecognized.
 */
export declare const getSeparatorCharacter: (file: Express.Multer.File) => string | undefined;
/**
 * Maps a record array to an object with keys from headers, formatting each value for compatibility.
 * @param headers An array of header names, used as keys for the returned object.
 * @param record An array of values corresponding to each header, to be formatted and mapped.
 * @returns An `UnprocessedDataRecord` object where each header in `headers` is a key,
 *          and each value is the corresponding entry in `record` formatted for compatibility.
 */
export declare const mapRecordToHeaders: (headers: string[], record: string[]) => UnprocessedDataRecord;
/**
 * Reads only first line of the file
 * Usefull when file is too large and we're only interested in column names
 * @param file A file we want to read
 * @returns a string with the content of the first line of the file
 */
export declare const readHeaders: (file: Express.Multer.File) => Promise<string>;
/**
 * Reads a text file and parse it to a JSON format.
 * Records are parsed to match schema field types.
 * Supported files: .tsv and .csv
 * @param {Express.Multer.File} file A file to read
 * @param {Schema} schema Schema to parse data with
 * @returns a JSON format objet
 */
export declare const readTextFile: (file: Express.Multer.File, schema: Schema) => Promise<{
    records: DataRecord[];
    errors?: ParseSchemaError[];
}>;
export declare function getSizeInBytes(size: string | number): number;
/**
 * Formats a file size from bytes to a specified unit with a defined precision.
 *
 * @param sizeInBytes - The file size in bytes to be formatted.
 * @param unit - The unit to which the size should be converted (e.g., 'MB', 'GB').
 * @param precision - The number of decimal places to include in the formatted output.
 * @returns The file size formatted as a string in the specified unit with the given precision. Returns null if sizeInBytes is not a Finite number.
 *
 */
export declare const formatByteSize: (sizeInBytes: number, unit: Unit, precision: number) => string | null;
type FileProcessingResult = {
    validFiles: Express.Multer.File[];
    fileErrors: BatchError[];
};
/**
 * Processes an array of uploaded files, filtering valid `.tsv` files and checking for required headers
 *
 * @param {Express.Multer.File[]} files An array of `Express.Multer.File` objects representing the uploaded files.
 * @returns A `Promise<FileProcessingResult>` that resolves to an object containing two arrays:
 * - `validFiles`: Files that have a `.tsv` extension and contain the `systemId` header.
 * - `fileErrors`: Files that either have an invalid extension or are missing the required `systemId` header.
 */
export declare function processFiles(files: Express.Multer.File[]): Promise<FileProcessingResult>;
export {};