cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/specimen/abcd206/in/AbcdParseUtility.java

   1 /**
   2 * Copyright (C) 2015 EDIT
   3 * European Distributed Institute of Taxonomy
   4 * http://www.e-taxonomy.eu
   5 *
   6 * The contents of this file are subject to the Mozilla Public License Version 1.1
   7 * See LICENSE.TXT at the top of this package for the full license terms.
   8 */
   9 package eu.etaxonomy.cdm.io.specimen.abcd206.in;
  10
  11 import java.io.InputStream;
  12 import java.net.URI;
  13 import java.util.Date;
  14 import java.util.List;
  15
  16 import javax.xml.parsers.DocumentBuilder;
  17 import javax.xml.parsers.DocumentBuilderFactory;
  18
  19 import org.apache.log4j.Logger;
  20 import org.joda.time.DateTime;
  21 import org.w3c.dom.Document;
  22 import org.w3c.dom.Element;
  23 import org.w3c.dom.Node;
  24 import org.w3c.dom.NodeList;
  25
  26 import eu.etaxonomy.cdm.api.application.ICdmRepository;
  27 import eu.etaxonomy.cdm.common.CdmUtils;
  28 import eu.etaxonomy.cdm.model.reference.Reference;
  29 import eu.etaxonomy.cdm.model.reference.ReferenceFactory;
  30 import eu.etaxonomy.cdm.persistence.query.MatchMode;
  31
  32 /**
  33  * @author pplitzner
  34  * @since 16.06.2015
  35  *
  36  */
  37 public class AbcdParseUtility {
  38
  39     private static final Logger logger = Logger.getLogger(AbcdParseUtility.class);
  40
  41
  42     public static URI parseFirstUri(NodeList nodeList, SpecimenImportReport report){
  43         URI uri = null;
  44         String textContent = parseFirstTextContent(nodeList);
  45         if(textContent!=null){
  46             try {
  47                 uri = URI.create(textContent);
  48             } catch (IllegalArgumentException e) {
  49                 if(report!=null){
  50                     report.addException("Exception during URI parsing!", e);
  51                 }
  52             }
  53         }
  54         return uri;
  55     }
  56
  57     public static String parseFirstTextContent(NodeList nodeList){
  58         return parseFirstTextContent(nodeList, true);
  59     }
  60
  61     public static String parseFirstTextContent(NodeList nodeList, boolean cleanUpWhiteSpaces){
  62         String string = null;
  63         if(nodeList!=null && nodeList.getLength()>0){
  64             string = nodeList.item(0).getTextContent();
  65             if(cleanUpWhiteSpaces){
  66                 string = string.replace("\n", "").replaceAll("( )+", " ").trim();
  67             }
  68         }
  69         return string;
  70     }
  71
  72     public static Double parseFirstDouble(NodeList nodeList, SpecimenImportReport report){
  73         if(nodeList.getLength()>0){
  74             return parseDouble(nodeList.item(0), report);
  75         }
  76         return null;
  77     }
  78
  79     public static Double parseDouble(Node node, SpecimenImportReport report){
  80         String message = "Could not parse double value for node " + node.getNodeName();
  81         Double doubleValue = null;
  82         try{
  83             String textContent = node.getTextContent();
  84             //remove 1000 dots
  85             textContent = textContent.replace(".","");
  86             //convert commmas
  87             textContent = textContent.replace(",",".");
  88             if (!CdmUtils.isBlank(textContent)){
  89                 doubleValue = Double.parseDouble(textContent);
  90             }
  91         } catch (NullPointerException npe){
  92             logger.error(message, npe);
  93             if(report!=null){
  94                 report.addException(message, npe);
  95             }
  96         } catch (NumberFormatException nfe){
  97             logger.error(message, nfe);
  98             if(report!=null){
  99                 report.addException(message, nfe);
 100             }
 101         }
 102         return doubleValue;
 103     }
 104
 105     public static DateTime parseFirstDateTime(NodeList nodeList) {
 106         DateTime dateTime = null;
 107         String textContent = parseFirstTextContent(nodeList);
 108         if(textContent!=null){
 109             dateTime = DateTime.parse(textContent);
 110         }
 111         return dateTime;
 112     }
 113
 114     public static Date parseFirstDate(NodeList nodeList) {
 115         Date date = null;
 116         DateTime dateTime = parseFirstDateTime(nodeList);
 117         if(dateTime!=null){
 118             date = dateTime.toDate();
 119         }
 120         return date;
 121     }
 122
 123     public static Reference parseFirstReference(NodeList referenceNodeList, ICdmRepository cdmAppController){
 124         String referenceCitation = AbcdParseUtility.parseFirstTextContent(referenceNodeList);
 125         //check if reference already exists
 126         List<Reference> matchingReferences = cdmAppController.getReferenceService().findByTitleWithRestrictions(Reference.class, referenceCitation, MatchMode.EXACT, null, null, null, null, null).getRecords();
 127         Reference reference;
 128         if(matchingReferences.size()==1){
 129             reference = matchingReferences.iterator().next();
 130         }
 131         else{
 132             reference = ReferenceFactory.newGeneric();
 133             reference.setTitle(referenceCitation);
 134             cdmAppController.getReferenceService().saveOrUpdate(reference);
 135         }
 136         return reference;
 137     }
 138
 139     /**
 140      * Return the wrapper with the list of root nodes for an ABCD XML file
 141      * @param fileName: the file's location
 142      * @return a wrapper with a list of root nodes ("Unit")
 143      */
 144     public static UnitAssociationWrapper parseUnitsNodeList(InputStream inputStream, SpecimenImportReport report) {
 145         UnitAssociationWrapper unitAssociationWrapper = new UnitAssociationWrapper();
 146         NodeList unitList = null;
 147         try {
 148             DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
 149             DocumentBuilder builder = factory.newDocumentBuilder();
 150
 151             Document document = builder.parse(inputStream);
 152             Element root = document.getDocumentElement();
 153             unitList = root.getElementsByTagName("Unit");
 154             if (unitList.getLength()>0) {
 155                 unitAssociationWrapper.setPrefix("");
 156                 unitAssociationWrapper.setAssociatedUnits(unitList);
 157                 return unitAssociationWrapper;
 158             }
 159             unitList = root.getElementsByTagName("abcd:Unit");
 160             if (unitList.getLength()>0) {
 161                 unitAssociationWrapper.setPrefix("abcd:");
 162                 unitAssociationWrapper.setAssociatedUnits(unitList);
 163                 return unitAssociationWrapper;
 164             }
 165             unitList = root.getElementsByTagName("abcd21:Unit");
 166             if (unitList.getLength()>0) {
 167                 unitAssociationWrapper.setPrefix("abcd21:");
 168                 unitAssociationWrapper.setAssociatedUnits(unitList);
 169             }
 170         } catch (Exception e) {
 171             logger.warn(e);
 172             if(report!=null){
 173                 report.addException("Exception during parsing of nodeList!", e);
 174             }
 175         }
 176         return unitAssociationWrapper;
 177     }
 178
 179 }