org.thymeleaf.templateparser.html.AbstractHtmlTemplateParser Maven / Gradle / Ivy

Go to download
/*
 * =============================================================================
 * 
 *   Copyright (c) 2011-2012, The THYMELEAF team (http://www.thymeleaf.org)
 * 
 *   Licensed under the Apache License, Version 2.0 (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.apache.org/licenses/LICENSE-2.0
 * 
 *   Unless required by applicable law or agreed to in writing, software
 *   distributed under the License is distributed on an "AS IS" BASIS,
 *   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 *   See the License for the specific language governing permissions and
 *   limitations under the License.
 * 
 * =============================================================================
 */
package org.thymeleaf.templateparser.html;

import java.io.Reader;
import java.io.StringReader;
import java.util.List;

import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import org.thymeleaf.Configuration;
import org.thymeleaf.dom.Document;
import org.thymeleaf.dom.Node;
import org.thymeleaf.exceptions.ConfigurationException;
import org.thymeleaf.exceptions.TemplateInputException;
import org.thymeleaf.exceptions.TemplateProcessingException;
import org.thymeleaf.templateparser.EntityResolver;
import org.thymeleaf.templateparser.ErrorHandler;
import org.thymeleaf.templateparser.ITemplateParser;
import org.thymeleaf.templateparser.TemplatePreprocessingReader;
import org.thymeleaf.util.ClassLoaderUtils;
import org.thymeleaf.util.ResourcePool;
import org.thymeleaf.util.StandardDOMTranslator;
import org.xml.sax.InputSource;

/**
 * 
 *   Document parser implementation for non-XML HTML documents.
 * 
 * 
 * @since 2.0.0
 * 
 * @author Daniel Fernández
 */
public abstract class AbstractHtmlTemplateParser implements ITemplateParser {

    private static final int BUFFER_SIZE = 8192;

    private final String templateModeName;
    private final boolean nekoInClasspath;
    private final NekoBasedHtmlParser parser;


    protected AbstractHtmlTemplateParser(final String templateModeName, int poolSize) {
        
        super();

        boolean nekoFound = true;
        try {
            ClassLoaderUtils.getClassLoader(AbstractHtmlTemplateParser.class).
                    loadClass("org.cyberneko.html.parsers.DOMParser");
        } catch (final ClassNotFoundException ignored) {
            nekoFound = false;
        } catch (final NoClassDefFoundError ignored) {
            nekoFound = false;
        }
        this.nekoInClasspath = nekoFound;
        this.templateModeName = templateModeName;
        if (this.nekoInClasspath) {
            this.parser = new NekoBasedHtmlParser(poolSize);
        } else {
            this.parser = null;
        }
        
    }



    
    
    public final Document parseTemplate(final Configuration configuration, final String documentName, final Reader reader) {
        if (!this.nekoInClasspath) {
            throw new ConfigurationException(
                    "Cannot perform conversion to XML from legacy HTML: The nekoHTML library " +
                    "is not in classpath. nekoHTML 1.9.15 or newer is required for processing templates in " +
                    "\"" + this.templateModeName + "\" mode [http://nekohtml.sourceforge.net]. Maven spec: " +
                    "\"net.sourceforge.nekohtml::nekohtml::1.9.15\". IMPORTANT: DO NOT use versions of " +
                    "nekoHTML older than 1.9.15.");
        }
        return this.parser.parseTemplate(configuration, documentName, getTemplatePreprocessingReader(reader));
    }




    public final List parseFragment(final Configuration configuration, final String fragment) {
        final String wrappedFragment = wrapFragment(fragment);
        final Document document = 
                parseTemplate(
                        configuration, 
                        null, // documentName 
                        new StringReader(wrappedFragment));
        return unwrapFragment(document);
    }
    
    
    protected abstract String wrapFragment(final String fragment);
    protected abstract List unwrapFragment(final Document document);


    
    

    /*
     * This is defined in a class apart so that the classloader does not always try to load
     * neko and xerces classes that might not be in the classpath.
     */
    private static class NekoBasedHtmlParser {
        
        
        private final Logger logger = LoggerFactory.getLogger(this.getClass());
        // The org.apache.xerces.parsers.DOMParser is not used here as a type
        // parameter to avoid the class loader to try to load this xerces class
        // (and fail) before we control the error at the constructor.
        private final ResourcePool