read-gedcom/dist/cjs/parse/decoder.d.ts

Gedcom file reader

/**
 * Supported Gedcom file encoding schemes.
 */
export declare const enum FileEncoding {
    Utf8 = "UTF-8",
    Ansel = "ANSEL",
    Cp1252 = "Cp1252",
    Macintosh = "Macintosh",
    Cp850 = "Cp850",
    Utf16be = "UTF-16be",
    Utf16le = "UTF-16le"
}
/**
 * Early detectable file metadata.
 * Can be used to infer the file encoding with high confidence.
 */
export interface FileMetadata {
    /**
     * The source encoding value, as defined in the header.
     */
    sourceEncoding: string | null;
    /**
     * The source provider value, as defined in the header.
     */
    sourceProvider: string | null;
    /**
     * The source provider's version value, as defined in the header.
     */
    sourceProviderVersion: string | null;
    /**
     * Whether this file contains a byte order marker (BOM).
     */
    fileHasBOM: boolean;
}
/**
 * Extracts the file metadata (see {@link FileMetadata}). The metadata can then be used to guess the actual charset of the file.
 * To circumvent the bootstrapping problem this function restricts its reading to the first lines of the file only, and
 * decodes them as UTF-8.
 * @param buffer The content of the file
 * @param maxPeekBytes Maximum number of bytes to read
 * @param maxPeekLines Maximum number of lines to read
 */
export declare const getFileMetadata: (buffer: ArrayBuffer, maxPeekBytes?: number, maxPeekLines?: number) => FileMetadata;
/**
 * Detects the file charset using a set of heuristics. Has proven to work great in practice.
 * If you encounter a file for which this procedure doesn't work as intended please do open an issue
 * at: https://github.com/arbre-app/read-gedcom/issues.
 * @param buffer The content of the file
 */
export declare const detectCharset: (buffer: ArrayBuffer) => FileEncoding;