@akira108sys/html-rewriter-readability
Version:
A library to extract readable content with Mozilla/Readability algorithm using Cloudflare HTMLRewriter.
23 lines (22 loc) • 1.35 kB
TypeScript
/** Set of HTML void elements */
export declare const VOID_ELEMENTS: Set<string>;
/** Default tag names that Readability considers for scoring */
export declare const DEFAULT_TAGS_TO_SCORE: Set<string>;
/** Regular expression for class/ID names that receive positive weight in Readability scoring */
export declare const POSITIVE_REGEX: RegExp;
/** Regular expression for class/ID names that receive negative weight in Readability scoring */
export declare const NEGATIVE_REGEX: RegExp;
/** Regular expression for class/ID names that Readability is likely to consider unnecessary */
export declare const UNLIKELY_CANDIDATES_REGEX: RegExp;
/** Regular expression for class/ID names that might be kept even if marked as unlikely candidates */
export declare const OK_MAYBE_ITS_A_CANDIDATE_REGEX: RegExp;
/** Role attribute values that Readability is likely to consider unnecessary */
export declare const UNLIKELY_ROLES: Set<string>;
/** Regular expression for commas (and similar symbols) used in score calculation */
export declare const COMMAS_REGEX: RegExp;
/** Number of top candidates in Readability */
export declare const NB_TOP_CANDIDATES = 5;
/** Minimum character threshold for Readability */
export declare const CHAR_THRESHOLD = 500;
/** Link density adjustment value for Readability */
export declare const LINK_DENSITY_MODIFIER = 0;