pdfreader.java

处理PDF

/*
 * $Id: PdfReader.java 3537 2008-07-08 08:53:00Z blowagie $
 *
 * Copyright 2001, 2002 Paulo Soares
 *
 * The contents of this file are subject to the Mozilla Public License Version 1.1
 * (the "License"); you may not use this file except in compliance with the License.
 * You may obtain a copy of the License at http://www.mozilla.org/MPL/
 *
 * Software distributed under the License is distributed on an "AS IS" basis,
 * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
 * for the specific language governing rights and limitations under the License.
 *
 * The Original Code is 'iText, a free JAVA-PDF library'.
 *
 * The Initial Developer of the Original Code is Bruno Lowagie. Portions created by
 * the Initial Developer are Copyright (C) 1999, 2000, 2001, 2002 by Bruno Lowagie.
 * All Rights Reserved.
 * Co-Developer of the code is Paulo Soares. Portions created by the Co-Developer
 * are Copyright (C) 2000, 2001, 2002 by Paulo Soares. All Rights Reserved.
 *
 * Contributor(s): all the names of the contributors are added in the source code
 * where applicable.
 *
 * Alternatively, the contents of this file may be used under the terms of the
 * LGPL license (the "GNU LIBRARY GENERAL PUBLIC LICENSE"), in which case the
 * provisions of LGPL are applicable instead of those above.  If you wish to
 * allow use of your version of this file only under the terms of the LGPL
 * License and not to allow others to use your version of this file under
 * the MPL, indicate your decision by deleting the provisions above and
 * replace them with the notice and other provisions required by the LGPL.
 * If you do not delete the provisions above, a recipient may use your version
 * of this file under either the MPL or the GNU LIBRARY GENERAL PUBLIC LICENSE.
 *
 * This library is free software; you can redistribute it and/or modify it
 * under the terms of the MPL as stated above or under the terms of the GNU
 * Library General Public License as published by the Free Software Foundation;
 * either version 2 of the License, or any later version.
 *
 * This library is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
 * FOR A PARTICULAR PURPOSE. See the GNU Library general Public License for more
 * details.
 *
 * If you didn't download this code from the following link, you should check if
 * you aren't using an obsolete version:
 * http://www.lowagie.com/iText/
 */

package com.lowagie.text.pdf;

import java.io.ByteArrayInputStream;
import java.io.ByteArrayOutputStream;
import java.io.DataInputStream;
import java.io.IOException;
import java.io.InputStream;
import java.net.URL;
import java.util.ArrayList;
import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import java.util.Iterator;
import java.util.List;
import java.util.Map;
import java.util.Set;
import java.util.zip.InflaterInputStream;
import java.util.Stack;
import java.security.Key;
import java.security.MessageDigest;
import java.security.cert.Certificate;

import com.lowagie.text.ExceptionConverter;
import com.lowagie.text.PageSize;
import com.lowagie.text.Rectangle;
import com.lowagie.text.pdf.interfaces.PdfViewerPreferences;
import com.lowagie.text.pdf.internal.PdfViewerPreferencesImp;

import org.bouncycastle.cms.CMSEnvelopedData;
import org.bouncycastle.cms.RecipientInformation;

/** Reads a PDF document.
 * @author Paulo Soares ([e-mail])
 * @author Kazuya Ujihara
 */
public class PdfReader implements PdfViewerPreferences {

    static final PdfName pageInhCandidates[] = {
        PdfName.MEDIABOX, PdfName.ROTATE, PdfName.RESOURCES, PdfName.CROPBOX
    };
   
    static final byte endstream[] = PdfEncodings.convertToBytes("endstream", null);
    static final byte endobj[] = PdfEncodings.convertToBytes("endobj", null);
    protected PRTokeniser tokens;
    // Each xref pair is a position
    // type 0 -> -1, 0
    // type 1 -> offset, 0
    // type 2 -> index, obj num
    protected int xref[];
    protected HashMap objStmMark;
    protected IntHashtable objStmToOffset;
    protected boolean newXrefType;
    private ArrayList xrefObj;
    PdfDictionary rootPages;
    protected PdfDictionary trailer;
    protected PdfDictionary catalog;
    protected PageRefs pageRefs;
    protected PRAcroForm acroForm = null;
    protected boolean acroFormParsed = false;
    protected boolean encrypted = false;
    protected boolean rebuilt = false;
    protected int freeXref;
    protected boolean tampered = false;
    protected int lastXref;
    protected int eofPos;
    protected char pdfVersion;
    protected PdfEncryption decrypt;
    protected byte password[] = null; //added by ujihara for decryption
    protected Key certificateKey = null; //added by Aiken Sam for certificate decryption
    protected Certificate certificate = null; //added by Aiken Sam for certificate decryption
    protected String certificateKeyProvider = null; //added by Aiken Sam for certificate decryption
    private boolean ownerPasswordUsed;
    protected ArrayList strings = new ArrayList();
    protected boolean sharedStreams = true;
    protected boolean consolidateNamedDestinations = false;
    protected int rValue;
    protected int pValue;
    private int objNum;
    private int objGen;
    private int fileLength;
    private boolean hybridXref;
    private int lastXrefPartial = -1;
    private boolean partial;
    private PRIndirectReference cryptoRef;
	private PdfViewerPreferencesImp viewerPreferences = new PdfViewerPreferencesImp();
    private boolean encryptionError;

    /**
     * Holds value of property appendable.
     */
    private boolean appendable;

    protected PdfReader() {
    }

    /** Reads and parses a PDF document.
     * @param filename the file name of the document
     * @throws IOException on error
     */
    public PdfReader(String filename) throws IOException {
        this(filename, null);
    }

    /** Reads and parses a PDF document.
     * @param filename the file name of the document
     * @param ownerPassword the password to read the document
     * @throws IOException on error
     */
    public PdfReader(String filename, byte ownerPassword[]) throws IOException {
        password = ownerPassword;
        tokens = new PRTokeniser(filename);
        readPdf();
    }

    /** Reads and parses a PDF document.
     * @param pdfIn the byte array with the document
     * @throws IOException on error
     */
    public PdfReader(byte pdfIn[]) throws IOException {
        this(pdfIn, null);
    }

    /** Reads and parses a PDF document.
     * @param pdfIn the byte array with the document
     * @param ownerPassword the password to read the document
     * @throws IOException on error
     */
    public PdfReader(byte pdfIn[], byte ownerPassword[]) throws IOException {
        password = ownerPassword;
        tokens = new PRTokeniser(pdfIn);
        readPdf();
    }

    /** Reads and parses a PDF document.
     * @param filename the file name of the document
     * @param certificate the certificate to read the document
     * @param certificateKey the private key of the certificate
     * @param certificateKeyProvider the security provider for certificateKey
     * @throws IOException on error
     */
    public PdfReader(String filename, Certificate certificate, Key certificateKey, String certificateKeyProvider) throws IOException {
        this.certificate = certificate;
        this.certificateKey = certificateKey;
        this.certificateKeyProvider = certificateKeyProvider;
        tokens = new PRTokeniser(filename);
        readPdf();
    }        

    /** Reads and parses a PDF document.
     * @param url the URL of the document
     * @throws IOException on error
     */
    public PdfReader(URL url) throws IOException {
        this(url, null);
    }

    /** Reads and parses a PDF document.
     * @param url the URL of the document
     * @param ownerPassword the password to read the document
     * @throws IOException on error
     */
    public PdfReader(URL url, byte ownerPassword[]) throws IOException {
        password = ownerPassword;
        tokens = new PRTokeniser(new RandomAccessFileOrArray(url));
        readPdf();
    }

    /**
     * Reads and parses a PDF document.
     * @param is the <CODE>InputStream</CODE> containing the document. The stream is read to the
     * end but is not closed
     * @param ownerPassword the password to read the document
     * @throws IOException on error
     */
    public PdfReader(InputStream is, byte ownerPassword[]) throws IOException {
        password = ownerPassword;
        tokens = new PRTokeniser(new RandomAccessFileOrArray(is));
        readPdf();
    }

    /**
     * Reads and parses a PDF document.
     * @param is the <CODE>InputStream</CODE> containing the document. The stream is read to the
     * end but is not closed
     * @throws IOException on error
     */
    public PdfReader(InputStream is) throws IOException {
        this(is, null);
    }

    /**
     * Reads and parses a pdf document. Contrary to the other constructors only the xref is read
     * into memory. The reader is said to be working in "partial" mode as only parts of the pdf
     * are read as needed. The pdf is left open but may be closed at any time with
     * <CODE>PdfReader.close()</CODE>, reopen is automatic.
     * @param raf the document location
     * @param ownerPassword the password or <CODE>null</CODE> for no password
     * @throws IOException on error
     */
    public PdfReader(RandomAccessFileOrArray raf, byte ownerPassword[]) throws IOException {
        password = ownerPassword;
        partial = true;
        tokens = new PRTokeniser(raf);
        readPdfPartial();
    }

    /** Creates an independent duplicate.
     * @param reader the <CODE>PdfReader</CODE> to duplicate
     */
    public PdfReader(PdfReader reader) {
        this.appendable = reader.appendable;
        this.consolidateNamedDestinations = reader.consolidateNamedDestinations;
        this.encrypted = reader.encrypted;
        this.rebuilt = reader.rebuilt;
        this.sharedStreams = reader.sharedStreams;
        this.tampered = reader.tampered;
        this.password = reader.password;
        this.pdfVersion = reader.pdfVersion;
        this.eofPos = reader.eofPos;
        this.freeXref = reader.freeXref;
        this.lastXref = reader.lastXref;
        this.tokens = new PRTokeniser(reader.tokens.getSafeFile());
        if (reader.decrypt != null)
            this.decrypt = new PdfEncryption(reader.decrypt);
        this.pValue = reader.pValue;
        this.rValue = reader.rValue;
        this.xrefObj = new ArrayList(reader.xrefObj);
        for (int k = 0; k < reader.xrefObj.size(); ++k) {
            this.xrefObj.set(k, duplicatePdfObject((PdfObject)reader.xrefObj.get(k), this));
        }
        this.pageRefs = new PageRefs(reader.pageRefs, this);
        this.trailer = (PdfDictionary)duplicatePdfObject(reader.trailer, this);
        this.catalog = (PdfDictionary)getPdfObject(trailer.get(PdfName.ROOT));
        this.rootPages = (PdfDictionary)getPdfObject(catalog.get(PdfName.PAGES));
        this.fileLength = reader.fileLength;
        this.partial = reader.partial;
        this.hybridXref = reader.hybridXref;
        this.objStmToOffset = reader.objStmToOffset;
        this.xref = reader.xref;
        this.cryptoRef = (PRIndirectReference)duplicatePdfObject(reader.cryptoRef, this);
        this.ownerPasswordUsed = reader.ownerPasswordUsed;
    }

    /** Gets a new file instance of the original PDF
     * document.
     * @return a new file instance of the original PDF document
     */
    public RandomAccessFileOrArray getSafeFile() {
        return tokens.getSafeFile();
    }

    protected PdfReaderInstance getPdfReaderInstance(PdfWriter writer) {
        return new PdfReaderInstance(this, writer);
    }

    /** Gets the number of pages in the document.
     * @return the number of pages in the document
     */
    public int getNumberOfPages() {
        return pageRefs.size();
    }

    /** Returns the document's catalog. This dictionary is not a copy,
     * any changes will be reflected in the catalog.
     * @return the document's catalog
     */
    public PdfDictionary getCatalog() {
        return catalog;
    }

    /** Returns the document's acroform, if it has one.
     * @return the document's acroform
     */
    public PRAcroForm getAcroForm() {
        if (!acroFormParsed) {
            acroFormParsed = true;
            PdfObject form = catalog.get(PdfName.ACROFORM);
            if (form != null) {
                try {
                    acroForm = new PRAcroForm(this);
                    acroForm.readAcroForm((PdfDictionary)getPdfObject(form));
                }
                catch (Exception e) {
                    acroForm = null;
                }
            }
        }
        return acroForm;
    }
    /**
     * Gets the page rotation. This value can be 0, 90, 180 or 270.
     * @param index the page number. The first page is 1
     * @return the page rotation
     */
    public int getPageRotation(int index) {
        return getPageRotation(pageRefs.getPageNRelease(index));
    }

    int getPageRotation(PdfDictionary page) {
        PdfNumber rotate = (PdfNumber)getPdfObject(page.get(PdfName.ROTATE));
        if (rotate == null)
            return 0;
        else {