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

Library for creating and modifying PDF files in JavaScript

import { PDFXRef } from '../pdf-structures';
import { arrayToString, trimArray } from '../../utils';
/**
 * Accepts an string as input. Repeatedly applies a regex to the input that matches
 * against entries of PDF Cross Reference Table subsections.
 *
 * If entries are found, then an array of Entry will be returned.
 *
 * If not, null is returned.
 */
var parseEntries = function (input) {
    var trimmed = input.trim();
    var entryRegex = /^(\d{10}) (\d{5}) (n|f)/;
    var entriesArr = [];
    var remainder = trimmed;
    while (remainder.length > 0) {
        var result = remainder.match(entryRegex);
        if (!result)
            return undefined;
        var fullMatch = result[0], offset = result[1], genNum = result[2], isInUse = result[3];
        entriesArr.push(PDFXRef.Entry.create()
            .setOffset(Number(offset))
            .setGenerationNum(Number(genNum))
            .setIsInUse(isInUse === 'n'));
        remainder = remainder.substring(fullMatch.length).trim();
    }
    return entriesArr;
};
/**
 * Accepts an string as input. Repeatedly applies a regex to the input that matches
 * against subsections of PDF Cross Reference Tables.
 *
 * If subsections are found, then an array of Subsection will be returned.
 *
 * If not, null is returned.
 */
var parseSubsections = function (input) {
    var trimmed = input.trim();
    var sectionsRegex = /^(\d+) (\d+)((\n|\r| )*(\d{10} \d{5} (n|f)(\n|\r| )*)+)/;
    var sectionsArr = [];
    var remainder = trimmed;
    while (remainder.length > 0) {
        var result = remainder.match(sectionsRegex);
        if (!result)
            return undefined;
        var fullMatch = result[0], firstObjNum = result[1], _objCount = result[2], entriesStr = result[3];
        var entries = parseEntries(entriesStr);
        if (!entries)
            return undefined;
        sectionsArr.push(PDFXRef.Subsection.from(entries).setFirstObjNum(Number(firstObjNum)));
        remainder = remainder.substring(fullMatch.length).trim();
    }
    return sectionsArr;
};
/**
 * Accepts an array of bytes as input. Checks to see if the first characters in the
 * trimmed input make up a PDF Cross Reference Table.
 *
 * If so, returns a tuple containing (1) an object representing the parsed PDF
 * Cross Reference Table and (2) a subarray of the input with the characters making
 * up the parsed cross reference table removed. The "onParseXRefTable" parse
 * handler will also be called with the Table object.
 *
 * If not, null is returned.
 */
var parseXRefTable = function (input, _a) {
    var onParseXRefTable = (_a === void 0 ? {} : _a).onParseXRefTable;
    var trimmed = trimArray(input);
    var xRefTableRegex = /^xref[\n|\r| ]*([\d|\n|\r| |f|n]+)/;
    // Search for first character that isn't part of an xref table
    var idx = 0;
    while (String.fromCharCode(trimmed[idx]).match(/^[xref \n\r\dfn]/))
        idx += 1;
    // Try to match the regex up to that character to see if we've got an xref table
    var result1 = arrayToString(trimmed, 0, idx).match(xRefTableRegex);
    if (!result1)
        return undefined;
    // Parse the subsections of the xref table
    var fullMatch = result1[0], contents = result1[1];
    var subsections = parseSubsections(contents);
    if (!subsections)
        return undefined;
    var xRefTable = PDFXRef.Table.from(subsections);
    if (onParseXRefTable)
        onParseXRefTable(xRefTable);
    return [xRefTable, trimmed.subarray(fullMatch.length)];
};
export default parseXRefTable;