/**
 * OCR Search - 🔍 Find files that contain some text with OCR
 * Copyright (C) 2021  rigwild <me@rigwild.dev> (https://github.com/rigwild)
 *
 * This program is free software: you can redistribute it and/or modify
 * it under the terms of the GNU Affero General Public License as published
 * by the Free Software Foundation, either version 3 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU Affero General Public License for more details.
 *
 * You should have received a copy of the GNU Affero General Public License
 * along with this program.  If not, see <https://www.gnu.org/licenses/>.
 */
import path from 'path';
import { recognize as tesseractRecognize } from 'node-tesseract-ocr';
import dirTree from 'directory-tree';
import type { ModuleThread, Pool } from 'threads';
export declare type ScanOptions = {
    /**
     * List of words to search (if one is matched, the file is matched)
     *
     * If not provided, every files will get matched (useful to do mass OCR and save the result)
     */
    words?: string[];
    /** Should the OCR scanned content of each file be saved to a txt file (e.g. "file.png.txt") */
    saveOcr?: boolean;
    /** Should the logs be printed to the console? (default = false) */
    shouldConsoleLog?: boolean;
    /** Should the matches file content be printed to the console? (default = true) */
    shouldConsoleLogMatches?: boolean;
    /**
     * If provided, the progress will be saved to a file
     *
     * When stopped, the process will start from where it stopped last time by looking there
     */
    progressFile?: string;
    /** If provided, every file path and their text content that were matched are logged to this file */
    matchesLogFile?: string;
    /** File extensions to ignore when looking for files (e.g. `new Set(['.pdf', '.jpg'])`) */
    ignoreExt?: Set<string>;
    pdfExtractFirst?: number;
    pdfExtractLast?: number;
    /**
     * Amount of worker threads to use (default = your total CPU cores - 2)
     *
     * Note: Using all your available cores may slow down the process!
     */
    workerPoolSize?: number;
    /**
     * Tesseract OCR config, will default `{ lang: 'eng', oem: 1, psm: 1 }`
     *
     * @see https://github.com/tesseract-ocr/tesseract/blob/main/doc/tesseract.1.asc
     */
    tesseractConfig?: TesseractConfig;
};
export declare type Progress = {
    visited: Set<string>;
    matched: Map<string, {
        text: string;
        matches: string[];
    }>;
};
export declare type ProgressJson = {
    visited: string[];
    matched: {
        [path: string]: {
            text: string;
            matches: string[];
        };
    };
};
/** @see https://github.com/tesseract-ocr/tesseract/blob/main/doc/tesseract.1.asc */
export declare type TesseractConfig = Parameters<typeof tesseractRecognize>[1];
export declare type WorkerMethods = {
    scanFile: typeof scanFile;
    pdfToImages: typeof pdfToImages;
};
export declare type WorkerPool = Pool<ModuleThread<WorkerMethods>>;
export declare const cleanStr: (str: string) => string;
export declare const logProgress: (visitedCount: number, totalFilesCount: number, str: string) => void;
/**
 * @param filePath Path to the image to extract text from
 * @param tesseractConfig Tesseract configuration
 * @param shouldCleanStr Should the string be normalized (lowercase, accents removed, whitespace removed)
 * @returns Text content
 */
export declare const ocr: (filePath: string, tesseractConfig?: TesseractConfig, shouldCleanStr?: boolean) => Promise<string>;
/**
 * Does the file `file.pdf-1.png` exist?
 * @param filePath Path to the PDF file
 * @returns The PDF is already extracted
 */
export declare const isPdfAlreadyExtractedToImages: (filePath: string) => Promise<boolean>;
/**
 * Given a PDF file, find its extracted pages images path
 * @param filePath Path to the PDF file
 * @returns Extracted pages path
 */
export declare const getPdfExtractedImages: (filePath: string) => Promise<Array<{
    name: string;
    path: string;
}>>;
/**
 * Extract all the pages of a PDF to PDF images
 *
 * @param filePath Path to the PDF to be converted
 * @returns List of generated output images path
 */
export declare const pdfToImages: (filePath: string, firstPage?: number | undefined, lastPage?: number | undefined) => Promise<Array<{
    name: string;
    path: string;
}>>;
/**
 * Find all words that were matched in text
 *
 * If words is `['MATCH_ALL']`, it will just skip the search as it will match every files
 * @param input
 * @param words
 * @returns List of matched words
 */
export declare const findMatches: (input: string, words: ScanOptions['words']) => string[];
export declare const isSupportedExtension: (ext: string) => boolean;
export declare const scanFile: (file: dirTree.DirectoryTree, words: ScanOptions['words'], tesseractConfig?: TesseractConfig) => Promise<{
    text: string;
    matches: string[];
}>;
export declare const loadProgress: (progressFile?: string | undefined) => Promise<Progress>;
export declare const saveProgress: (progressFile: string, progress: Progress) => Promise<void>;
export declare const getTreeFilesCount: (tree: dirTree.DirectoryTree) => number;
export declare const getTree: (scannedDir: string) => Promise<dirTree.DirectoryTree>;
//# sourceMappingURL=utils.d.ts.map