@thi.ng/text-analysis/xform.d.ts

Text tokenization, transformation & analysis transducers, utilities, stop words, porter stemming, vector encodings, similarities

import type { Vocab } from "./api.js";
/**
 * Trnasducer to produce lowercase string.
 */
export declare const lowercase: import("@thi.ng/transducers").Transducer<string, string>;
/**
 * Trnasducer which collapses multiple whitespace chars into one.
 */
export declare const collapseWS: import("@thi.ng/transducers").Transducer<string, string>;
/**
 * Transducer which removes empty or whitespace-only strings/tokens.
 */
export declare const removeEmpty: import("@thi.ng/transducers").Transducer<string, string>;
/**
 * Transducer which removes non-alphabetic chars from input, using
 * {@link RE_NON_ALPHA}.
 */
export declare const removeNonAlpha: import("@thi.ng/transducers").Transducer<string, string>;
/**
 * Transducer which removes non-alphabetic chars from input, using
 * {@link RE_NON_ALPHANUM}.
 */
export declare const removeNonAlphaNum: import("@thi.ng/transducers").Transducer<string, string>;
/**
 * Transducer which removes tokens with their length outside the configured
 * `[min,max]` range.
 *
 * @param min
 * @param max
 */
export declare const minMaxLength: (min: number, max: number) => import("@thi.ng/transducers").Transducer<string, string>;
/**
 * Transducer version of {@link stemWord}.
 */
export declare const stemOnly: import("@thi.ng/transducers").Transducer<string, string>;
/**
 * Transducer which removes tokens which are not present in given `vocab`.
 *
 * @param vocab
 */
export declare const vocabOnly: (vocab: Vocab) => import("@thi.ng/transducers").Transducer<string, string>;
//# sourceMappingURL=xform.d.ts.map