cdmlib-model/src/main/java/eu/etaxonomy/cdm/jaxb/FormattedTextAdapter.java

   1 package eu.etaxonomy.cdm.jaxb;
   2
   3 import java.io.StringReader;
   4 import java.io.StringWriter;
   5
   6 import javax.xml.bind.annotation.adapters.XmlAdapter;
   7 import javax.xml.parsers.DocumentBuilder;
   8 import javax.xml.parsers.DocumentBuilderFactory;
   9 import javax.xml.transform.OutputKeys;
  10 import javax.xml.transform.Result;
  11 import javax.xml.transform.Source;
  12 import javax.xml.transform.Transformer;
  13 import javax.xml.transform.TransformerFactory;
  14 import javax.xml.transform.dom.DOMSource;
  15 import javax.xml.transform.stream.StreamResult;
  16
  17 import org.apache.commons.lang.StringEscapeUtils;
  18 import org.apache.commons.logging.Log;
  19 import org.apache.commons.logging.LogFactory;
  20 import org.w3c.dom.DOMException;
  21 import org.w3c.dom.Document;
  22 import org.w3c.dom.DocumentFragment;
  23 import org.w3c.dom.NamedNodeMap;
  24 import org.w3c.dom.Node;
  25 import org.w3c.dom.NodeList;
  26 import org.xml.sax.InputSource;
  27
  28 public class FormattedTextAdapter extends XmlAdapter<FormattedText,java.lang.String> {
  29         public static String[] NAMESPACE_PREFIXES = {"xmlns:common",
  30                                                          "xmlns:agent",
  31                                                          "xmlns:description",
  32                                                          "xmlns:location",
  33                                                          "xmlns:media",
  34                                                          "xmlns:molecular",
  35                                                          "xmlns:name",
  36                                                          "xmlns:occurence",
  37                                                          "xmlns:reference",
  38                                                          "xmlns:taxon",
  39                                                          "xmlns:view",
  40                                                          "xmlns:xsi"};
  41
  42         private static final Log log = LogFactory.getLog(FormattedTextAdapter.class);
  43
  44         public FormattedText marshal(String string) throws Exception {
  45                 if(string != null) {
  46
  47                         string = StringEscapeUtils.escapeXml(string);
  48                         String documentString = "<?xml version=\"1.0\"?><Text>"  + string + "</Text>";
  49                         log.debug("Parsing " + documentString);
  50
  51                         FormattedText text = new FormattedText();
  52                     DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
  53                     DocumentBuilder parser = factory.newDocumentBuilder();
  54                     //
  55                    // System.err.println(documentString);
  56                     Document document = parser.parse(new InputSource(new StringReader(documentString)));
  57
  58                     NodeList childNodes = document.getDocumentElement().getChildNodes();
  59
  60                     for(int i = 0; i < childNodes.getLength(); i++) {
  61                         Node node = childNodes.item(i);
  62                         if(node instanceof org.w3c.dom.Text ) {
  63                                 org.w3c.dom.Text textNode = (org.w3c.dom.Text) node;
  64                                 //if (documentString.contains("United Kingdom")){
  65                     //                  System.err.println("w3c..." + textNode.getData());
  66                                 //}
  67
  68                                 text.getContent().add(textNode.getTextContent());
  69                         } else {
  70                             text.getContent().add(node);
  71                                 //System.err.println("no w3c..." + text.toString());
  72                         }
  73                     }
  74                     return text;
  75                 }
  76                 return null;
  77         }
  78
  79         public String unmarshal(FormattedText text) throws Exception {
  80                 DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
  81                 Document document = factory.newDocumentBuilder().newDocument();
  82                 DocumentFragment documentFragment = document.createDocumentFragment();
  83
  84                 for(Object object : text.getContent()) {
  85                         if(object instanceof String) {
  86                                 String string = (String)object;
  87                                 documentFragment.appendChild(document.createTextNode(string));
  88                         } else {
  89                                 Node node = (Node)object;
  90                                 NamedNodeMap attributes = node.getAttributes();
  91                                 for(String prefix : FormattedTextAdapter.NAMESPACE_PREFIXES) {
  92                                         try{
  93                                                 attributes.removeNamedItem(prefix);
  94                                         } catch(DOMException de){
  95                                                 if(de.code != DOMException.NOT_FOUND_ERR) {
  96                                                         System.err.println("no such prefix: " + prefix);
  97                                                         throw de;
  98                                                 }
  99                                         }
 100
 101                                 }
 102
 103                                 documentFragment.appendChild(document.importNode(node,true));
 104                         }
 105
 106                 }
 107
 108                 TransformerFactory transformerFactory  = TransformerFactory.newInstance();
 109                 Transformer transformer = transformerFactory.newTransformer();
 110                 transformer.setOutputProperty(OutputKeys.OMIT_XML_DECLARATION , "yes");
 111
 112                 Source input = new DOMSource(documentFragment);
 113                 StringWriter stringWriter = new StringWriter();
 114                 Result output = new StreamResult(stringWriter);
 115                 transformer.transform(input, output);
 116                 return stringWriter.toString();
 117         }
 118 }