glin-profanity/dist/multimodal/ocr.d.ts

Glin-Profanity is a lightweight and efficient npm package designed to detect and filter profane language in text inputs across multiple languages. Whether you’re building a chat application, a comment section, or any platform where user-generated content

import { F as Filter } from '../Filter-BGcyIAvO.js';
import { L as Language, F as FilterConfig, C as CheckProfanityResult } from '../types-B9c_ik4k.js';

/**
 * OCR (Optical Character Recognition) Integration for glin-profanity
 *
 * Extracts text from images and checks for profanity.
 * Uses Tesseract.js as an optional peer dependency.
 *
 * @example
 * ```typescript
 * import { createOCRChecker, checkImageForProfanity } from 'glin-profanity/ocr';
 *
 * // Quick check
 * const result = await checkImageForProfanity(imageBuffer);
 * console.log(result.containsProfanity);
 *
 * // With custom config
 * const checker = createOCRChecker({
 *   languages: ['english', 'spanish'],
 *   tesseractLangs: ['eng', 'spa'],
 *   detectLeetspeak: true,
 * });
 * const result = await checker.checkImage(imageBuffer);
 * ```
 *
 * @packageDocumentation
 * @module glin-profanity/ocr
 */

type ImageLike = string | Buffer | Uint8Array | Blob | File | HTMLImageElement | HTMLCanvasElement;
/**
 * OCR checker configuration
 */
interface OCRCheckerConfig {
    /** Languages for profanity detection */
    languages?: Language[];
    /** Tesseract language codes (e.g., 'eng', 'spa', 'fra') */
    tesseractLangs?: string[];
    /** Enable leetspeak detection */
    detectLeetspeak?: boolean;
    /** Enable Unicode normalization */
    normalizeUnicode?: boolean;
    /** Minimum OCR confidence to process text (0-100) */
    minConfidence?: number;
    /** Custom filter configuration */
    filterConfig?: Partial<FilterConfig>;
}
/**
 * OCR check result
 */
interface OCRCheckResult {
    /** Whether profanity was found in the extracted text */
    containsProfanity: boolean;
    /** Extracted text from the image */
    extractedText: string;
    /** OCR confidence score (0-100) */
    ocrConfidence: number;
    /** Profane words found */
    profaneWords: string[];
    /** Full profanity check result */
    profanityResult: CheckProfanityResult;
    /** Processing time in milliseconds */
    processingTimeMs: number;
}
/**
 * Creates an OCR profanity checker
 *
 * @example
 * ```typescript
 * const checker = createOCRChecker({
 *   languages: ['english'],
 *   tesseractLangs: ['eng'],
 *   detectLeetspeak: true,
 * });
 *
 * // Check an image
 * const result = await checker.checkImage('./screenshot.png');
 *
 * // Check multiple images
 * const results = await checker.checkImages([image1, image2, image3]);
 *
 * // Clean up when done
 * await checker.terminate();
 * ```
 */
declare function createOCRChecker(config?: OCRCheckerConfig): {
    /**
     * Check a single image for profanity
     */
    checkImage(image: ImageLike): Promise<OCRCheckResult>;
    /**
     * Check multiple images for profanity
     */
    checkImages(images: ImageLike[]): Promise<OCRCheckResult[]>;
    /**
     * Extract text from image without profanity check
     */
    extractText(image: ImageLike): Promise<{
        text: string;
        confidence: number;
    }>;
    /**
     * Check extracted text (if you already have text from another OCR)
     */
    checkText(text: string): CheckProfanityResult;
    /**
     * Terminate the Tesseract worker (clean up resources)
     */
    terminate(): Promise<void>;
    /**
     * Get the underlying filter instance
     */
    getFilter(): Filter;
};
/**
 * Quick function to check an image for profanity
 * Creates a temporary worker, checks the image, and terminates
 *
 * @example
 * ```typescript
 * import { checkImageForProfanity } from 'glin-profanity/ocr';
 *
 * const result = await checkImageForProfanity('./meme.png');
 * if (result.containsProfanity) {
 *   console.log('Found profanity:', result.profaneWords);
 * }
 * ```
 */
declare function checkImageForProfanity(image: ImageLike, config?: OCRCheckerConfig): Promise<OCRCheckResult>;
/**
 * Batch check multiple images for profanity
 * More efficient than calling checkImageForProfanity multiple times
 *
 * @example
 * ```typescript
 * import { batchCheckImages } from 'glin-profanity/ocr';
 *
 * const images = ['./img1.png', './img2.png', './img3.png'];
 * const results = await batchCheckImages(images);
 *
 * const flagged = results.filter(r => r.containsProfanity);
 * console.log(`${flagged.length} images contain profanity`);
 * ```
 */
declare function batchCheckImages(images: ImageLike[], config?: OCRCheckerConfig): Promise<OCRCheckResult[]>;
/**
 * Supported Tesseract language codes
 * Map from glin-profanity language to Tesseract code
 */
declare const LANGUAGE_TO_TESSERACT: Record<Language, string>;
/**
 * Helper to convert glin-profanity languages to Tesseract codes
 */
declare function languagesToTesseract(languages: Language[]): string[];

export { CheckProfanityResult, FilterConfig, LANGUAGE_TO_TESSERACT, Language, type OCRCheckResult, type OCRCheckerConfig, batchCheckImages, checkImageForProfanity, createOCRChecker, languagesToTesseract };