@harryjwang/simplewordcloud/dist/browser-tokenizers.d.ts

A simple word cloud generator supporting English and Chinese text

/**
 * Simple tokenizers for browser usage
 * These are simplified versions that don't rely on Node.js dependencies
 */
/**
 * Simple English tokenizer for browser usage
 */
export declare class SimplifiedEnglishTokenizer {
    private stopwords;
    constructor();
    /**
     * Tokenize English text into words and count their frequencies
     * @param text The input English text
     * @returns A map of words to their frequencies
     */
    tokenize(text: string): Map<string, number>;
}
/**
 * Simple Chinese tokenizer for browser usage
 * This is a very basic implementation that splits by characters
 * and combines common character pairs
 */
export declare class SimplifiedChineseTokenizer {
    private stopwords;
    constructor();
    /**
     * Tokenize Chinese text into words and count their frequencies
     * This is a simplified approach that works in the browser
     * @param text The input Chinese text
     * @returns A map of words to their frequencies
     */
    tokenize(text: string): Map<string, number>;
}
/**
 * Get a simplified tokenizer for browser usage
 */
export declare function getSimplifiedTokenizer(language: 'english' | 'chinese'): SimplifiedEnglishTokenizer | SimplifiedChineseTokenizer;
//# sourceMappingURL=browser-tokenizers.d.ts.map