org.xhtmlrenderer.pdf.HTMLOutline Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of flying-saucer-pdf-itext5 Show documentation
Flying Saucer is a CSS 2.1 renderer written in Java. This artifact supports PDF output with iText 5.x.
There is a newer version: 9.7.2
Show newest version
/*
 * {{{ header & license
 * Copyright (c) 2016 Stanimir Stamenkov
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public License
 * as published by the Free Software Foundation; either version 2.1
 * of the License, or (at your option) any later version.
 *
 * This program 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 Lesser General Public License for more details.
 *
 * You should have received a copy of the GNU Lesser General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA.
 * }}}
 */
package org.xhtmlrenderer.pdf;

import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.w3c.dom.traversal.DocumentTraversal;
import org.w3c.dom.traversal.NodeFilter;
import org.w3c.dom.traversal.NodeIterator;
import org.xhtmlrenderer.pdf.ITextOutputDevice.Bookmark;
import org.xhtmlrenderer.render.Box;

import java.util.IdentityHashMap;
import java.util.List;
import java.util.Map;
import java.util.regex.Matcher;
import java.util.regex.Pattern;

class HTMLOutline {

    private static final Pattern HEADING =
            Pattern.compile("h([1-6])", Pattern.CASE_INSENSITIVE);

    /** sectioning roots */
    private static final Pattern ROOT =
            Pattern.compile("blockquote|details|fieldset|figure|td",
                            Pattern.CASE_INSENSITIVE);

    private static final Pattern WS = Pattern.compile("\\s+");

    private static final int MAX_NAME_LENGTH = 200;

    private final HTMLOutline parent;

    private final int level;

    private final Bookmark bookmark;

    private HTMLOutline() {
        this(0, "root", null);
    }

    private HTMLOutline(int level, String name, HTMLOutline parent) {
        this.level = level;
        this.bookmark = new Bookmark(name, "");
        this.parent = parent;
        if (parent != null) {
            parent.bookmark.addChild(bookmark);
        }
    }

    /**
     * Creates a bookmark list of the document outline generated for the given
     * element context (usually the root document element).
     * 
     * The current algorithm is more simple than the one suggested in the HTML5
     * specification such as it is not affected by
     * sectioning
     * content but just the heading level.  For
     * example:
     *      * <body>
     *   <h1>Foo</h1>
     *   <h3>Bar</h3>
     *   <blockquote>
     *     <h5>Bla</h5>
     *   </blockquote>
     *   <p>Baz</p>
     *   <h2>Quux</h2>
     *   <section>
     *     <h3>Thud</h3>
     *   </section>
     *   <h4>Grunt</h4>
     * </body>
     * 
     * Should generate outline as:
     * 
     * Foo
     *   
     *   Bar
     *   Quux
     *   Thud
     *   Grunt
     *   
     * 
     * 
     * But it generates outline as:
     * 
     * Foo
     *   
     *   Bar
     *   Quux
     *     
     *     Thud
     *       
     *       Grunt
     *       
     *     
     *   
     * 
     *
     * Example document customizations
     *
     * Include non-heading element as bookmark (level 4)
     *      * <strong data-pdf-bookmark="4">Foo bar</strong>
     *
     * Specify bookmark name
     *      * <tr data-pdf-bookmark="5" data-pdf-bookmark-name="Bar baz">...</tr>
     *
     * Exclude individual heading from bookmarks
     *      * <h3 data-pdf-bookmark="none">Baz qux</h3>
     *
     * Prevent automatic bookmarks for the whole of the document
     *      * <html data-pdf-bookmark="exclude">...</html>
     *
     * @param   context  the top element a sectioning outline would be generated for;
     * @param   box  box hierarchy the outline bookmarks would get mapped into.
     * @return  Bookmarks of the outline generated for the given element context.
     * @see     Creating an outline
     */
    public static List generate(Element context, Box box) {
        NodeIterator iterator = NestedSectioningFilter.iterator(context);

        HTMLOutline root = new HTMLOutline();
        HTMLOutline current = root;
        Map map = new IdentityHashMap<>();

        for (Element element = (Element) iterator.nextNode();
                element != null; element = (Element) iterator.nextNode()) {
            int level;
            try {
                level = Integer.parseInt(getOutlineLevel(element));
                if (level < 1) {
                    continue; // Illegal value
                }
            } catch (NumberFormatException e) {
                continue; // Invalid value
            }

            String name = getBookmarkName(element);

            while (current.level >= level) {
                current = current.parent;
            }
            current = new HTMLOutline(level, name, current);
            map.put(element, current.bookmark);
        }
        initBoxRefs(map, box);
        return root.bookmark.getChildren();
    } // generate(Element, Box) : List

    private static void initBoxRefs(Map map, Box box) {
        Bookmark bookmark = map.get(box.getElement());
        if (bookmark != null) {
            bookmark.setBox(box);
        }
        for (int i = 0, len = box.getChildCount(); i < len; i++) {
            initBoxRefs(map, box.getChild(i));
        }
    }

    private static String getBookmarkName(Element element) {
        String name = element.getAttribute("data-pdf-bookmark-name").trim();
        if (name.isEmpty()) {
            name = element.getTextContent();
        }
        name = WS.matcher(name.trim()).replaceAll(" ");
        if (name.length() > MAX_NAME_LENGTH) {
            name = name.substring(0, MAX_NAME_LENGTH);
        }
        return name;
    }

    static String getOutlineLevel(Element element) {
        String bookmark = element.getAttribute("data-pdf-bookmark").trim();
        if (bookmark.isEmpty()) {
            Matcher heading = HEADING.matcher(element.getTagName());
            if (heading.matches()) {
                bookmark = heading.group(1);
            } else if (ROOT.matcher(element.getTagName()).matches()) {
                bookmark = "exclude";
            } else {
                bookmark = "none";
            }
        }
        return bookmark;
    }


    private static class NestedSectioningFilter implements NodeFilter {

        static final NestedSectioningFilter INSTANCE = new NestedSectioningFilter();

        static NodeIterator iterator(Element root) {
            return ((DocumentTraversal) root.getOwnerDocument())
                    .createNodeIterator(root, SHOW_ELEMENT, INSTANCE, true);
        }

        @Override
        public short acceptNode(Node n) {
            String outlineLevel = getOutlineLevel((Element) n);
            if (outlineLevel.equalsIgnoreCase("none")) {
                return FILTER_SKIP;
            }
            return outlineLevel.equalsIgnoreCase("exclude")
                    ? FILTER_REJECT
                    : FILTER_ACCEPT;
        }

    } // class NestedSectioningFilter


} // class HTMLOutline