org.apache.tika.parser.external.ExternalParsersConfigReader Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of aem-sdk-api Show documentation
The Adobe Experience Manager SDK
There is a newer version: 2024.11.18751.20241128T090041Z-241100
/*
 * Licensed to the Apache Software Foundation (ASF) under one or more
 * contributor license agreements.  See the NOTICE file distributed with
 * this work for additional information regarding copyright ownership.
 * The ASF licenses this file to You 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.apache.tika.parser.external;

import javax.xml.parsers.DocumentBuilder;
import java.io.IOException;
import java.io.InputStream;
import java.util.ArrayList;
import java.util.HashMap;
import java.util.HashSet;
import java.util.List;
import java.util.Map;
import java.util.Set;
import java.util.StringTokenizer;
import java.util.regex.Pattern;

import org.apache.tika.exception.TikaException;
import org.apache.tika.mime.MediaType;
import org.apache.tika.mime.MimeTypeException;
import org.apache.tika.parser.ParseContext;
import org.apache.tika.utils.XMLReaderUtils;
import org.w3c.dom.Document;
import org.w3c.dom.Element;
import org.w3c.dom.Node;
import org.w3c.dom.NodeList;
import org.xml.sax.InputSource;
import org.xml.sax.SAXException;

/**
 * Builds up ExternalParser instances based on XML file(s)
 *  which define what to run, for what, and how to process
 *  any output metadata.
 * Typically used to configure up a series of external programs 
 *  (like catdoc or pdf2txt) to extract text content from documents.
 *  
 *  *  TODO XML DTD Here
 * 
 */
public final class ExternalParsersConfigReader implements ExternalParsersConfigReaderMetKeys {
   
   public static List read(InputStream stream) throws TikaException, IOException {
      try {
          DocumentBuilder builder = XMLReaderUtils.getDocumentBuilder();
          Document document = builder.parse(new InputSource(stream));
          return read(document);
      } catch (SAXException e) {
          throw new TikaException("Invalid parser configuration", e);
      }
   }
   
   public static List read(Document document) throws TikaException, IOException {
      return read(document.getDocumentElement());
   }
   
   public static List read(Element element) throws TikaException, IOException {
      List parsers = new ArrayList();
      
      if (element != null && element.getTagName().equals(EXTERNAL_PARSERS_TAG)) {
         NodeList nodes = element.getChildNodes();
         for (int i = 0; i < nodes.getLength(); i++) {
            Node node = nodes.item(i);
            if (node.getNodeType() == Node.ELEMENT_NODE) {
               Element child = (Element) node;
               if (child.getTagName().equals(PARSER_TAG)) {
                  ExternalParser p = readParser(child);
                  if(p != null) {
                     parsers.add( p );
                  }
               }
            }
         }
      } else {
         throw new MimeTypeException(
               "Not a <" + EXTERNAL_PARSERS_TAG + "/> configuration document: "
               + element.getTagName());
      }
      
      return parsers;
   }
   
   /**
    * Builds and Returns an ExternalParser, or null if a check
    *  command was given that didn't match.
    */
   private static ExternalParser readParser(Element parserDef) throws TikaException {
      ExternalParser parser = new ExternalParser();

      NodeList children = parserDef.getChildNodes();
      for(int i=0; i readMimeTypes(Element mimeTypes) {
      Set types = new HashSet();
      
      NodeList children = mimeTypes.getChildNodes();
      for(int i=0; i readMetadataPatterns(Element metadataDef) {
      Map metadata = new HashMap();
      
      NodeList children = metadataDef.getChildNodes();
      for(int i=0; i errorVals = new ArrayList(); 
      
      NodeList children = checkDef.getChildNodes();
      for(int i=0; i