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 public class AbcdParseUtility {
  37
  38     private static final Logger logger = Logger.getLogger(AbcdParseUtility.class);
  39
  40     public static URI parseFirstUri(NodeList nodeList, SpecimenImportReport report){
  41         URI uri = null;
  42         String textContent = parseFirstTextContent(nodeList);
  43         if(textContent!=null){
  44             try {
  45                 uri = URI.create(textContent);
  46             } catch (IllegalArgumentException e) {
  47                 if(report!=null){
  48                     report.addException("Exception during URI parsing!", e);
  49                 }
  50             }
  51         }
  52         return uri;
  53     }
  54
  55     public static String parseFirstTextContent(NodeList nodeList){
  56         return parseFirstTextContent(nodeList, true);
  57     }
  58
  59     public static String parseFirstTextContent(NodeList nodeList, boolean cleanUpWhiteSpaces){
  60         String string = null;
  61         if(nodeList!=null && nodeList.getLength()>0){
  62             string = nodeList.item(0).getTextContent();
  63             if(cleanUpWhiteSpaces){
  64                 string = string.replace("\n", "").replaceAll("( )+", " ").trim();
  65             }
  66         }
  67         return string;
  68     }
  69
  70     public static Double parseFirstDouble(NodeList nodeList, SpecimenImportReport report){
  71         if(nodeList.getLength()>0){
  72             return parseDouble(nodeList.item(0), report);
  73         }
  74         return null;
  75     }
  76
  77     public static Double parseDouble(Node node, SpecimenImportReport report){
  78         String message = "Could not parse double value for node " + node.getNodeName();
  79         Double doubleValue = null;
  80         try{
  81             String textContent = node.getTextContent();
  82             //remove 1000 dots
  83             textContent = textContent.replace(".","");
  84             //convert commmas
  85             textContent = textContent.replace(",",".");
  86             if (!CdmUtils.isBlank(textContent)){
  87                 doubleValue = Double.parseDouble(textContent);
  88             }
  89         } catch (NullPointerException npe){
  90             logger.error(message, npe);
  91             if(report!=null){
  92                 report.addException(message, npe);
  93             }
  94         } catch (NumberFormatException nfe){
  95             logger.error(message, nfe);
  96             if(report!=null){
  97                 report.addException(message, nfe);
  98             }
  99         }
 100         return doubleValue;
 101     }
 102
 103     public static DateTime parseFirstDateTime(NodeList nodeList) {
 104         DateTime dateTime = null;
 105         String textContent = parseFirstTextContent(nodeList);
 106         if(textContent!=null){
 107             dateTime = DateTime.parse(textContent);
 108         }
 109         return dateTime;
 110     }
 111
 112     public static Date parseFirstDate(NodeList nodeList) {
 113         Date date = null;
 114         DateTime dateTime = parseFirstDateTime(nodeList);
 115         if(dateTime!=null){
 116             date = dateTime.toDate();
 117         }
 118         return date;
 119     }
 120
 121     public static Reference parseFirstReference(NodeList referenceNodeList, ICdmRepository cdmAppController){
 122         String referenceCitation = AbcdParseUtility.parseFirstTextContent(referenceNodeList);
 123         //check if reference already exists
 124         List<Reference> matchingReferences = cdmAppController.getReferenceService().findByTitleWithRestrictions(Reference.class, referenceCitation, MatchMode.EXACT, null, null, null, null, null).getRecords();
 125         Reference reference;
 126         if(matchingReferences.size()==1){
 127             reference = matchingReferences.iterator().next();
 128         }
 129         else{
 130             reference = ReferenceFactory.newGeneric();
 131             reference.setTitle(referenceCitation);
 132             cdmAppController.getReferenceService().saveOrUpdate(reference);
 133         }
 134         return reference;
 135     }
 136
 137     /**
 138      * Return the wrapper with the list of root nodes for an ABCD XML file
 139      * @param fileName: the file's location
 140      * @return a wrapper with a list of root nodes ("Unit")
 141      */
 142     public static UnitAssociationWrapper parseUnitsNodeList(InputStream inputStream, SpecimenImportReport report) {
 143         UnitAssociationWrapper unitAssociationWrapper = new UnitAssociationWrapper();
 144         NodeList unitList = null;
 145         try {
 146             DocumentBuilderFactory factory = DocumentBuilderFactory.newInstance();
 147             DocumentBuilder builder = factory.newDocumentBuilder();
 148
 149             Document document = builder.parse(inputStream);
 150             Element root = document.getDocumentElement();
 151             unitList = root.getElementsByTagName("Unit");
 152             if (unitList.getLength()>0) {
 153                 unitAssociationWrapper.setPrefix("");
 154                 unitAssociationWrapper.setAssociatedUnits(unitList);
 155                 return unitAssociationWrapper;
 156             }
 157             unitList = root.getElementsByTagName("abcd:Unit");
 158             if (unitList.getLength()>0) {
 159                 unitAssociationWrapper.setPrefix("abcd:");
 160                 unitAssociationWrapper.setAssociatedUnits(unitList);
 161                 return unitAssociationWrapper;
 162             }
 163             unitList = root.getElementsByTagName("abcd21:Unit");
 164             if (unitList.getLength()>0) {
 165                 unitAssociationWrapper.setPrefix("abcd21:");
 166                 unitAssociationWrapper.setAssociatedUnits(unitList);
 167             }
 168         } catch (Exception e) {
 169             logger.warn(e);
 170             if(report!=null){
 171                 report.addException("Exception during parsing of nodeList!", e);
 172             }
 173         }
 174         return unitAssociationWrapper;
 175     }
 176 }