char-encoding-detector/dist/encoding/mbcs.d.ts

Character encoding detector

import { Recognizer, Context, Match } from '../type';
/**
 * Asian double or multi-byte - charsets.
 * Match is determined mostly by the input data adhering to the
 * encoding scheme for the charset, and, optionally,
 * frequency-of-occurence of characters.
 */
declare class mbcs implements Recognizer {
    commonChars: any;
    name(): string;
    /**
     * Test the match of this charset with the input text data
     *      which is obtained via the CharsetDetector object.
     *
     * @param det  The CharsetDetector, which contains the input text
     *             to be checked for being in this charset.
     * @return     Two values packed into one int  (Damn java, anyhow)
     *             bits 0-7:  the match confidence, ranging from 0-100
     *             bits 8-15: The match reason, an enum-like value.
     */
    match(det: Context): Match;
    /**
     * Get the next character (however many bytes it is) from the input data
     *    Subclasses for specific charset encodings must implement this function
     *    to get characters according to the rules of their encoding scheme.
     *
     *  This function is not a method of class iteratedChar only because
     *   that would require a lot of extra derived classes, which is awkward.
     * @param it  The iteratedChar 'struct' into which the returned char is placed.
     * @param det The charset detector, which is needed to get at the input byte data
     *            being iterated over.
     * @return    True if a character was returned, false at end of input.
     */
    nextChar(iter: any, det: any): boolean;
}
/**
 * Shift-JIS charset recognizer.
 */
export declare class sjis extends mbcs {
    name(): string;
    language(): string;
    commonChars: number[];
    nextChar(iter: any, det: any): boolean;
}
/**
 *   Big5 charset recognizer.
 */
export declare class big5 extends mbcs {
    name(): string;
    language(): string;
    commonChars: number[];
    nextChar(iter: any, det: any): boolean;
}
/**
 * The charset recognize for EUC-JP.  A singleton instance of this class
 *    is created and kept by the public CharsetDetector class
 */
export declare class euc_jp extends mbcs {
    name(): string;
    language(): string;
    commonChars: number[];
    nextChar(iter: any, det: any): boolean;
}
/**
 * The charset recognize for EUC-KR.  A singleton instance of this class
 *    is created and kept by the public CharsetDetector class
 */
export declare class euc_kr extends mbcs {
    name(): string;
    language(): string;
    commonChars: number[];
    nextChar(iter: any, det: any): boolean;
}
/**
 *   GB-18030 recognizer. Uses simplified Chinese statistics.
 */
export declare class gb_18030 extends mbcs {
    name(): string;
    language(): string;
    nextChar(iter: any, det: any): boolean;
    commonChars: number[];
}
export {};