tag-soup/tokenizeMarkup.d.ts

The fastest pure JS SAX/DOM XML/HTML parser.

/**
 * The error thrown by a parser if a {@link ParserError.input input} is malformed.
 *
 * @group Parser
 */
export declare class ParserError extends SyntaxError {
    input: string;
    startIndex: number;
    endIndex: number;
    /**
     * Creates a new {@link ParserError} instance.
     *
     * @param message The error message.
     * @param input The text where an error was detected.
     * @param startIndex The index of the first char in text where an error was detected, inclusive.
     * @param endIndex The index of the last char in text where an error was detected, exclusive.
     */
    constructor(message: string, input: string, startIndex?: number, endIndex?: number);
}
/**
 * A token that can be read from a text.
 *
 * @group Tokenizer
 */
export type Token = 'TEXT' | 'START_TAG_NAME' | 'START_TAG_CLOSING' | 'START_TAG_SELF_CLOSING' | 'END_TAG_NAME' | 'ATTRIBUTE_NAME' | 'ATTRIBUTE_VALUE' | 'COMMENT' | 'PROCESSING_INSTRUCTION_TARGET' | 'PROCESSING_INSTRUCTION_DATA' | 'CDATA_SECTION' | 'DOCTYPE_NAME';
/**
 * A callback that is invoked when a token is read from a text.
 *
 * @param token The token that was read.
 * @param startIndex The start index of the first meaningful token char, inclusive.
 * @param endIndex The end index of the last meaningful token char, exclusive.
 * @group Tokenizer
 */
export type TokenCallback = (token: Token, startIndex: number, endIndex: number) => void;
/**
 * Options of {@link tokenizeMarkup}.
 */
export interface ResolvedTokenizerOptions extends TokenReaderOptions {
    voidTags?: Set<number>;
    implicitlyClosedTags?: Map<number, Set<number>>;
    implicitlyOpenedTags?: Set<number>;
    areUnbalancedStartTagsImplicitlyClosed?: boolean;
    areUnbalancedEndTagsIgnored?: boolean;
}
/**
 * Reads tokens from text and returns them by invoking a callback.
 *
 * Tokens are _guaranteed_ to be returned in correct order. Missing tokens are inserted to restore the correct order if
 * needed.
 *
 * @example
 * tokenizeMarkup(
 *   'Hello, <b>Bob</b>!',
 *   (token, startIndex, endIndex) => {
 *     // Handle token here
 *   },
 *   resolveTokenizerOptions(htmlTokenizerOptions)
 * );
 *
 * @param input The text to read tokens from.
 * @param callback The callback that is invoked when a token is read.
 * @param options Tokenizer options prepared by {@link resolveTokenizerOptions}.
 */
export declare function tokenizeMarkup(input: string, callback: TokenCallback, options?: ResolvedTokenizerOptions): void;
export interface ContextualTokenReaderOptions {
    parentOptions?: ContextualTokenReaderOptions;
    foreignTags?: Map<number, ContextualTokenReaderOptions>;
    areSelfClosingTagsRecognized?: boolean;
    areCDATASectionsRecognized?: boolean;
    areProcessingInstructionsRecognized?: boolean;
}
export interface TokenReaderOptions extends ContextualTokenReaderOptions {
    readTag?: (input: string, startIndex: number, endIndex: number) => number;
    rawTextTags?: Set<number>;
    isFragment?: boolean;
    isStrict?: boolean;
}
/**
 * Reads tokens from the text and returns tokens by invoking a callback.
 *
 * Tokens returned in the same order they are listed in text.
 */
export declare function readTokens(input: string, callback: TokenCallback, options?: TokenReaderOptions): void;
/**
 * Returns case-insensitive djb2 hash of a substring.
 */
export declare function getCaseInsensitiveHashCode(input: string, startIndex: number, endIndex: number): number;
/**
 * Returns case-sensitive djb2 hash of a substring.
 */
export declare function getCaseSensitiveHashCode(input: string, startIndex: number, endIndex: number): number;