@flatfile/plugin-xlsx-extractor/dist/index.d.ts

A plugin for parsing xlsx files in Flatfile.

import * as _flatfile_listener from '@flatfile/listener';
import { WorkbookCapture } from '@flatfile/util-extractor';

interface DefaultOptions {
    algorithm: 'default';
    rowsToSearch?: number;
}
interface ExplicitHeadersOptions {
    algorithm: 'explicitHeaders';
    headers: string[];
    skip?: number;
}
interface SpecificRowsOptions {
    algorithm: 'specificRows';
    rowNumbers: number[];
    skip?: number;
}
interface DataRowAndSubHeaderDetectionOptions {
    algorithm: 'dataRowAndSubHeaderDetection';
    rowsToSearch?: number;
}
interface NewfangledOptions {
    algorithm: 'newfangled';
}
interface AIDetectionOptions {
    algorithm: 'aiDetection';
    rowsToSearch?: number;
}
type GetHeadersOptions = DefaultOptions | ExplicitHeadersOptions | SpecificRowsOptions | DataRowAndSubHeaderDetectionOptions | NewfangledOptions | AIDetectionOptions;
interface GetHeadersResult {
    header: string[];
    headerRow: number;
    letters: string[];
}

type ParseBufferOptions = Omit<ExcelExtractorOptions, 'chunkSize' | 'parallel'> & {
    readonly headerSelectionEnabled?: boolean;
    getHeaders: (options: any, data: string[][]) => Promise<GetHeadersResult>;
    rowsToSearch?: number;
};
declare function parseBuffer(buffer: Buffer, options?: ParseBufferOptions): Promise<WorkbookCapture>;

/**
 * Plugin config options.
 *
 * @property {boolean} raw - if true, return raw data; if false, return formatted text.
 * @property {boolean} rawNumbers - if true, return raw numbers; if false, return formatted numbers.
 * @property {string} dateNF - the date format.
 * @property {number} chunkSize - the size of chunk to process when inserting records.
 * @property {number} parallel - the quantity of parallel process when inserting records.
 * @property {GetHeadersOptions} headerDetectionOptions - the options for header detection.
 * @property {boolean} skipEmptyLines - if true, skip empty lines; if false, include empty lines.
 * @property {boolean} debug - if true, display helpful console logs.
 * @property {object} mergedCellOptions - the options for merged cell handling.
 * @property {boolean} cascadeRowValues - if true, cascade values down the dataset until a blank row, new value, or end of dataset.
 * @property {boolean} cascadeHeaderValues - if true, cascade values across the header rows until a blank column, new value, or end of dataset.
 */
interface ExcelExtractorOptions {
    readonly raw?: boolean;
    readonly rawNumbers?: boolean;
    readonly dateNF?: string;
    readonly headerDetectionOptions?: GetHeadersOptions;
    readonly skipEmptyLines?: boolean;
    readonly chunkSize?: number;
    readonly parallel?: number;
    readonly debug?: boolean;
    readonly mergedCellOptions?: {
        acrossColumns?: {
            treatment: 'applyToAll' | 'applyToTopLeft' | 'coalesce' | 'concatenate';
            separator?: string;
        };
        acrossRows?: {
            treatment: 'applyToAll' | 'applyToTopLeft' | 'coalesce' | 'concatenate';
            separator?: string;
        };
        acrossRanges?: {
            treatment: 'applyToAll' | 'applyToTopLeft';
        };
    };
    readonly cascadeRowValues?: boolean;
    readonly cascadeHeaderValues?: boolean;
}
declare const ExcelExtractor: (options?: ExcelExtractorOptions) => (listener: _flatfile_listener.FlatfileListener) => void;
declare const excelParser: typeof parseBuffer;
declare const xlsxExtractorPlugin: (options?: ExcelExtractorOptions) => (listener: _flatfile_listener.FlatfileListener) => void;

export { ExcelExtractor, type ExcelExtractorOptions, excelParser, xlsxExtractorPlugin };