pdf-lib/es/core/pdf-parser/parseTrailer.js

Library for creating and modifying PDF files in JavaScript

import { PDFDictionary } from '../pdf-objects';
import { PDFTrailer } from '../pdf-structures';
import { arrayIndexOf, arrayToString, charCode, error, trimArrayAndRemoveComments, } from '../../utils';
import parseDict from './parseDict';
import parseNumber from './parseNumber';
/**
 * Accepts an array of bytes as input. Checks to see if the first characters in the
 * trimmed input make up a PDF Trailer.
 *
 * If so, returns a tuple containing (1) an object representing the parsed PDF
 * Trailer and (2) a subarray of the input with the characters making up the parsed
 * trailer removed. The "onParseTrailer" parse handler will be called with the
 * PDFTrailer object. The "onParseDict" parse handler will be called with the
 * dictionary of the PDFTrailer, and the "onParseNumber" parse handler will be
 * called with the "lastXRefOffset" of the PDFTrailer.
 *
 * If not, null is returned.
 */
var parseTrailer = function (input, index, parseHandlers) {
    if (parseHandlers === void 0) { parseHandlers = {}; }
    var trimmed = trimArrayAndRemoveComments(input);
    var trailerRegex = /^trailer[\n|\r| ]*([^]+)startxref[\n|\r| ]+?(\d+)[\n|\r| ]+?%%EOF/;
    // Find the nearest "%%EOF" of the input and match the regex up to that index
    var eofIdx = arrayIndexOf(trimmed, '%%EOF');
    var result = arrayToString(trimmed, 0, eofIdx + 5).match(trailerRegex);
    if (!result)
        return undefined;
    var fullMatch = result[0], dictStr = result[1], lastXRefOffsetStr = result[2];
    // Parse the dictionary string into a PDFDictionary
    var dictBytes = new Uint8Array(dictStr.split('').map(charCode));
    var dict = (parseDict(dictBytes, index, parseHandlers) ||
        error('Failed to parse trailer dictionary'))[0];
    // Parse the xref offset string value into a PDFNumber
    var offsetBytes = new Uint8Array(lastXRefOffsetStr.split('').map(charCode));
    var lastXRefOffset = (parseNumber(offsetBytes, parseHandlers) ||
        error('Failed to parse lastXRefOffset of trailer'))[0];
    var trailer = PDFTrailer.from(lastXRefOffset.number, dict);
    if (parseHandlers.onParseTrailer)
        parseHandlers.onParseTrailer(trailer);
    return [trailer, trimmed.subarray(fullMatch.length)];
};
/**
 * Same as "parseTrailer" function, except does not look for the complete trailer.
 * Specifically, the "trailer" keyword and the trailer's dictionary are not parsed.
 *
 * Documents that use Object Streams do not need the "trailer" keyword or the
 * associated dictionary. (The Object Streams store the trailer's dictionary.)
 */
var parseTrailerWithoutDict = function (input, index, parseHandlers) {
    if (parseHandlers === void 0) { parseHandlers = {}; }
    var trimmed = trimArrayAndRemoveComments(input);
    var trailerRegex = /^startxref[\n|\r| ]+?(\d+)[\n|\r| ]+?%%EOF/;
    // Find the nearest "%%EOF" of the input and match the regex up to that index
    var eofIdx = arrayIndexOf(trimmed, '%%EOF');
    var result = arrayToString(trimmed, 0, eofIdx + 5).match(trailerRegex);
    if (!result)
        return undefined;
    var fullMatch = result[0], lastXRefOffsetStr = result[1];
    // Parse the xref offset string value into a PDFNumber
    var offsetBytes = new Uint8Array(lastXRefOffsetStr.split('').map(charCode));
    var lastXRefOffset = (parseNumber(offsetBytes, parseHandlers) ||
        error('Failed to parse lastXRefOffset of trailer'))[0];
    var trailer = PDFTrailer.from(lastXRefOffset.number, PDFDictionary.from(new Map(), index));
    if (parseHandlers.onParseTrailer)
        parseHandlers.onParseTrailer(trailer);
    return [trailer, trimmed.subarray(fullMatch.length)];
};
export { parseTrailer, parseTrailerWithoutDict };