Revision 786696e3
Added by Andreas Müller over 10 years ago
| .gitattributes | ||
|---|---|---|
| 10 | 10 |
cdmlib-commons/src/main/java/eu/etaxonomy/cdm/common/DoubleResult.java -text |
| 11 | 11 |
cdmlib-commons/src/main/java/eu/etaxonomy/cdm/common/ExcelUtils.java -text |
| 12 | 12 |
cdmlib-commons/src/main/java/eu/etaxonomy/cdm/common/FileCopy.java -text |
| 13 |
cdmlib-commons/src/main/java/eu/etaxonomy/cdm/common/GeneralParser.java -text |
|
| 13 | 14 |
cdmlib-commons/src/main/java/eu/etaxonomy/cdm/common/ResultWrapper.java -text |
| 14 | 15 |
cdmlib-commons/src/main/java/eu/etaxonomy/cdm/common/StreamUtils.java -text |
| 15 | 16 |
cdmlib-commons/src/main/java/eu/etaxonomy/cdm/common/Tree.java -text |
| ... | ... | |
| 31 | 32 |
cdmlib-commons/src/main/resources/MUST-EXIST.txt -text |
| 32 | 33 |
cdmlib-commons/src/main/resources/log4j.properties -text |
| 33 | 34 |
cdmlib-commons/src/test/java/eu/etaxonomy/cdm/common/CdmUtilsTest.java -text |
| 35 |
cdmlib-commons/src/test/java/eu/etaxonomy/cdm/common/GeneralParserTest.java -text |
|
| 34 | 36 |
cdmlib-commons/src/test/java/eu/etaxonomy/cdm/common/UriUtilsTest.java -text |
| 35 | 37 |
cdmlib-commons/src/test/java/eu/etaxonomy/cdm/common/UuidGenerator.java -text |
| 36 | 38 |
cdmlib-commons/src/test/java/eu/etaxonomy/cdm/common/XmlHelpTest.java -text |
| ... | ... | |
| 65 | 67 |
cdmlib-ext/src/main/java/eu/etaxonomy/cdm/ext/openurl/MobotOpenUrlResponseSchemaAdapter.java -text |
| 66 | 68 |
cdmlib-ext/src/main/java/eu/etaxonomy/cdm/ext/openurl/MobotOpenUrlServiceWrapper.java -text |
| 67 | 69 |
cdmlib-ext/src/main/java/eu/etaxonomy/cdm/ext/openurl/OpenUrlReference.java -text |
| 70 |
cdmlib-ext/src/main/java/eu/etaxonomy/cdm/ext/scratchpads/ScratchpadsService.java -text |
|
| 68 | 71 |
cdmlib-ext/src/main/java/eu/etaxonomy/cdm/ext/sru/SruServiceWrapper.java -text |
| 69 | 72 |
cdmlib-ext/src/main/resources/eu/etaxonomy/cdm/ext/geo/mapServices_v10.xsd -text |
| 70 | 73 |
cdmlib-ext/src/test/java/eu/etaxonomy/cdm/ext/bci/BciServiceTest.java -text |
| ... | ... | |
| 418 | 421 |
cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/LookAheadEventReader.java -text |
| 419 | 422 |
cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/MarkupDocumentImport.java -text |
| 420 | 423 |
cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/MarkupDocumentImportNoComponent.java -text |
| 424 |
cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/MarkupFeatureImport.java -text |
|
| 421 | 425 |
cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/MarkupImportBase.java -text |
| 422 | 426 |
cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/MarkupImportConfigurator.java -text |
| 423 | 427 |
cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/MarkupImportState.java -text |
| 424 | 428 |
cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/MarkupInputStream.java -text |
| 425 | 429 |
cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/MarkupKeyImport.java -text |
| 430 |
cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/MarkupModsImport.java -text |
|
| 426 | 431 |
cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/MarkupNomenclatureImport.java -text |
| 427 | 432 |
cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/MarkupSpecimenImport.java -text |
| 428 | 433 |
cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/MarkupTransformer.java -text |
| ... | ... | |
| 683 | 688 |
cdmlib-model/src/main/java/eu/etaxonomy/cdm/hibernate/UUIDUserType.java -text |
| 684 | 689 |
cdmlib-model/src/main/java/eu/etaxonomy/cdm/hibernate/WSDLDefinitionUserType.java -text |
| 685 | 690 |
cdmlib-model/src/main/java/eu/etaxonomy/cdm/hibernate/search/AbstractClassBridge.java -text |
| 691 |
cdmlib-model/src/main/java/eu/etaxonomy/cdm/hibernate/search/AcceptedTaxonBridge.java -text |
|
| 692 |
cdmlib-model/src/main/java/eu/etaxonomy/cdm/hibernate/search/ClassInfoBridge.java -text |
|
| 686 | 693 |
cdmlib-model/src/main/java/eu/etaxonomy/cdm/hibernate/search/DateTimeBridge.java -text |
| 687 | 694 |
cdmlib-model/src/main/java/eu/etaxonomy/cdm/hibernate/search/DefinedTermBaseClassBridge.java -text |
| 688 | 695 |
cdmlib-model/src/main/java/eu/etaxonomy/cdm/hibernate/search/DescriptionBaseClassBridge.java -text |
| ... | ... | |
| 2116 | 2123 |
cdmlib-services/src/main/java/eu/etaxonomy/cdm/api/service/pager/impl/DefaultPagerImpl.java -text |
| 2117 | 2124 |
cdmlib-services/src/main/java/eu/etaxonomy/cdm/api/service/pager/impl/StringLabelPagerImpl.java -text |
| 2118 | 2125 |
cdmlib-services/src/main/java/eu/etaxonomy/cdm/api/service/search/CdmMassIndexer.java -text |
| 2126 |
cdmlib-services/src/main/java/eu/etaxonomy/cdm/api/service/search/DocumentSearchResult.java -text |
|
| 2119 | 2127 |
cdmlib-services/src/main/java/eu/etaxonomy/cdm/api/service/search/ICdmMassIndexer.java -text |
| 2120 | 2128 |
cdmlib-services/src/main/java/eu/etaxonomy/cdm/api/service/search/ISearchResultBuilder.java -text |
| 2121 | 2129 |
cdmlib-services/src/main/java/eu/etaxonomy/cdm/api/service/search/LuceneMultiSearch.java -text |
| cdmlib-commons/src/main/java/eu/etaxonomy/cdm/common/GeneralParser.java | ||
|---|---|---|
| 1 |
/** |
|
| 2 |
* |
|
| 3 |
*/ |
|
| 4 |
package eu.etaxonomy.cdm.common; |
|
| 5 |
|
|
| 6 |
import java.util.regex.Pattern; |
|
| 7 |
|
|
| 8 |
import org.apache.log4j.Logger; |
|
| 9 |
|
|
| 10 |
/** |
|
| 11 |
* @author a.mueller |
|
| 12 |
* @created 2013-Aug-02 |
|
| 13 |
* |
|
| 14 |
*/ |
|
| 15 |
public class GeneralParser {
|
|
| 16 |
@SuppressWarnings("unused")
|
|
| 17 |
private static final Logger logger = Logger.getLogger(GeneralParser.class); |
|
| 18 |
|
|
| 19 |
static String isbnPatternStr = "^(ISBN\\s*)?(\\d-?){9}((\\d-?){3})?(\\d|X)$";
|
|
| 20 |
static Pattern isbnPattern; |
|
| 21 |
|
|
| 22 |
/** |
|
| 23 |
* Checks if a string follows the ISBN pattern (10 and 13 digits). It does not check the |
|
| 24 |
* checksum of an isbn (http://en.wikipedia.org/wiki/International_Standard_Book_Number#ISBN-13_check_digit_calculation). |
|
| 25 |
* We may implement this separately as sometimes additional checksum validation is unwanted. |
|
| 26 |
* @param isbn |
|
| 27 |
* @return |
|
| 28 |
*/ |
|
| 29 |
public static boolean isIsbn(String isbn){
|
|
| 30 |
// if (isbnPattern == null){
|
|
| 31 |
// isbnPattern = Pattern.compile(isbnPatternStr); |
|
| 32 |
// } |
|
| 33 |
// Matcher matcher = isbnPattern.matcher(isbn); |
|
| 34 |
if (isbn == null){
|
|
| 35 |
return false; |
|
| 36 |
}else{
|
|
| 37 |
return isbn.matches(isbnPatternStr); |
|
| 38 |
} |
|
| 39 |
|
|
| 40 |
|
|
| 41 |
|
|
| 42 |
} |
|
| 43 |
|
|
| 44 |
} |
|
| cdmlib-commons/src/main/java/eu/etaxonomy/cdm/common/monitor/ProgressMonitorWrapper.java | ||
|---|---|---|
| 90 | 90 |
* This implementation of a <code>IProgressMonitor</code> |
| 91 | 91 |
* method forwards to the wrapped progress monitor. |
| 92 | 92 |
* Clients may override this method to do additional |
| 93 |
* processing. |
|
| 93 |
* processing.<BR> |
|
| 94 |
* As the {@link IProgressMonitor interface} documentation for
|
|
| 95 |
* {@link IProgressMonitor#internalWorked(double) this method}
|
|
| 96 |
* says the method must not be called by a client. |
|
| 97 |
* Clients should always use the method </code>worked(int)</code>. |
|
| 94 | 98 |
* |
| 95 | 99 |
* @see IProgressMonitor#internalWorked(double) |
| 96 | 100 |
*/ |
| cdmlib-commons/src/main/java/eu/etaxonomy/cdm/common/monitor/SubProgressMonitor.java | ||
|---|---|---|
| 147 | 147 |
sentToParent = 0; |
| 148 | 148 |
} |
| 149 | 149 |
|
| 150 |
/* (Intentionally not javadoc'd) |
|
| 151 |
* Implements the internal method <code>IProgressMonitor.internalWorked</code>. |
|
| 150 |
|
|
| 151 |
/* (non-Javadoc) |
|
| 152 |
* @see eu.etaxonomy.cdm.common.monitor.ProgressMonitorWrapper#internalWorked(double) |
|
| 152 | 153 |
*/ |
| 154 |
@Override |
|
| 153 | 155 |
public void internalWorked(double work) {
|
| 154 | 156 |
if (usedUp || nestedBeginTasks != 1) {
|
| 155 | 157 |
return; |
| cdmlib-commons/src/test/java/eu/etaxonomy/cdm/common/GeneralParserTest.java | ||
|---|---|---|
| 1 |
/** |
|
| 2 |
* |
|
| 3 |
*/ |
|
| 4 |
package eu.etaxonomy.cdm.common; |
|
| 5 |
|
|
| 6 |
import static org.junit.Assert.*; |
|
| 7 |
|
|
| 8 |
import org.junit.Assert; |
|
| 9 |
import org.junit.Before; |
|
| 10 |
import org.junit.Test; |
|
| 11 |
|
|
| 12 |
/** |
|
| 13 |
* @author a.mueller |
|
| 14 |
* |
|
| 15 |
*/ |
|
| 16 |
public class GeneralParserTest {
|
|
| 17 |
|
|
| 18 |
/** |
|
| 19 |
* @throws java.lang.Exception |
|
| 20 |
*/ |
|
| 21 |
@Before |
|
| 22 |
public void setUp() throws Exception {
|
|
| 23 |
} |
|
| 24 |
|
|
| 25 |
@Test |
|
| 26 |
public void test() {
|
|
| 27 |
String isbn1 = "ISBN 90-71236-61-7"; |
|
| 28 |
Assert.assertTrue("isbn1 should be an ISBN", GeneralParser.isIsbn(isbn1));
|
|
| 29 |
|
|
| 30 |
String isbn2 = "90-71236-61-7"; |
|
| 31 |
Assert.assertTrue("'ISBN' string should not be required", GeneralParser.isIsbn(isbn2));
|
|
| 32 |
|
|
| 33 |
String isbnToShort = "ISBN 90-7123-61-7"; |
|
| 34 |
Assert.assertFalse("ISBN must have 10 or 13 numbers, 9 numbered string should not be an ISBN", GeneralParser.isIsbn(isbnToShort));
|
|
| 35 |
|
|
| 36 |
String isbn3 = "ISBN 123-456-789-112-3"; |
|
| 37 |
Assert.assertTrue("isbn3 (with 13 numbers) should be an ISBN", GeneralParser.isIsbn(isbn3));
|
|
| 38 |
|
|
| 39 |
String isbn4 = "ISBN 123-456-789-112-3-"; |
|
| 40 |
Assert.assertFalse("- at the end of ISBN is not allowed", GeneralParser.isIsbn(isbn4));
|
|
| 41 |
|
|
| 42 |
String isbn5 = "ISBN 123-456-789-12-3"; |
|
| 43 |
Assert.assertFalse("12 numbers are not allowed, either 10 or 13", GeneralParser.isIsbn(isbn5));
|
|
| 44 |
|
|
| 45 |
String isbn6 = "ISBN 123-456-789-112-X"; |
|
| 46 |
Assert.assertTrue("X should be allowed as a final digit", GeneralParser.isIsbn(isbn6));
|
|
| 47 |
|
|
| 48 |
} |
|
| 49 |
|
|
| 50 |
} |
|
| cdmlib-ext/pom.xml | ||
|---|---|---|
| 92 | 92 |
<groupId>org.apache.httpcomponents</groupId> |
| 93 | 93 |
<artifactId>httpclient</artifactId> |
| 94 | 94 |
</dependency> |
| 95 |
<dependency> |
|
| 96 |
<groupId>net.sf.json-lib</groupId> |
|
| 97 |
<artifactId>json-lib</artifactId> |
|
| 98 |
<classifier>jdk15</classifier> |
|
| 99 |
</dependency> |
|
| 100 |
<dependency> |
|
| 101 |
<groupId>net.sf.ezmorph</groupId> |
|
| 102 |
<artifactId>ezmorph</artifactId> |
|
| 103 |
</dependency> |
|
| 95 | 104 |
|
| 96 | 105 |
</dependencies> |
| 97 | 106 |
</project> |
| cdmlib-ext/src/main/java/eu/etaxonomy/cdm/ext/scratchpads/ScratchpadsService.java | ||
|---|---|---|
| 1 |
// $Id$ |
|
| 2 |
/** |
|
| 3 |
* Copyright (C) 2009 EDIT |
|
| 4 |
* European Distributed Institute of Taxonomy |
|
| 5 |
* http://www.e-taxonomy.eu |
|
| 6 |
* |
|
| 7 |
* The contents of this file are subject to the Mozilla Public License Version 1.1 |
|
| 8 |
* See LICENSE.TXT at the top of this package for the full license terms. |
|
| 9 |
*/ |
|
| 10 |
package eu.etaxonomy.cdm.ext.scratchpads; |
|
| 11 |
|
|
| 12 |
import java.io.BufferedReader; |
|
| 13 |
import java.io.FileNotFoundException; |
|
| 14 |
import java.io.FileOutputStream; |
|
| 15 |
import java.io.IOException; |
|
| 16 |
import java.io.InputStream; |
|
| 17 |
import java.io.InputStreamReader; |
|
| 18 |
import java.net.URI; |
|
| 19 |
import java.net.URISyntaxException; |
|
| 20 |
import java.net.URL; |
|
| 21 |
import java.util.Iterator; |
|
| 22 |
import java.util.zip.ZipEntry; |
|
| 23 |
import java.util.zip.ZipInputStream; |
|
| 24 |
|
|
| 25 |
import org.apache.http.HttpException; |
|
| 26 |
import org.apache.http.HttpResponse; |
|
| 27 |
import org.apache.log4j.Logger; |
|
| 28 |
import org.codehaus.jackson.JsonNode; |
|
| 29 |
import org.codehaus.jackson.map.ObjectMapper; |
|
| 30 |
|
|
| 31 |
import eu.etaxonomy.cdm.common.UriUtils; |
|
| 32 |
|
|
| 33 |
|
|
| 34 |
/** |
|
| 35 |
* @author l.morris |
|
| 36 |
* @date Jul 2, 2013 |
|
| 37 |
* |
|
| 38 |
*/ |
|
| 39 |
public class ScratchpadsService {
|
|
| 40 |
|
|
| 41 |
private static final Logger logger = Logger.getLogger(ScratchpadsService.class); |
|
| 42 |
|
|
| 43 |
public static final String SCRATCHPADS_JSON_ENDPOINT = "http://scratchpads.eu/explore/sites-list/json"; |
|
| 44 |
|
|
| 45 |
private static final char[] ILLEGAL_CHARACTERS = { '/', '\n', '\r', '\t', '\0', '\f', '`', '?', '*', '\\', '<', '>', '|', '\"', ':', '.' };
|
|
| 46 |
|
|
| 47 |
private static final String dir = "C:\\Users\\l.morris\\Downloads\\dwca_scratchpads\\"; |
|
| 48 |
|
|
| 49 |
public void harvest(){
|
|
| 50 |
|
|
| 51 |
InputStream inputStream = null; |
|
| 52 |
|
|
| 53 |
try {
|
|
| 54 |
URL url = new URL(SCRATCHPADS_JSON_ENDPOINT); |
|
| 55 |
boolean isAvailable = UriUtils.isServiceAvailable(url.toURI()); |
|
| 56 |
|
|
| 57 |
if (isAvailable) {
|
|
| 58 |
inputStream = UriUtils.getInputStream(url.toURI()); |
|
| 59 |
} |
|
| 60 |
|
|
| 61 |
BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream, "iso-8859-1"), 8); |
|
| 62 |
StringBuilder sb = new StringBuilder(); |
|
| 63 |
String line = null; |
|
| 64 |
while ((line = reader.readLine()) != null) {
|
|
| 65 |
sb.append(line + "\n"); |
|
| 66 |
logger.debug(line); |
|
| 67 |
|
|
| 68 |
} |
|
| 69 |
|
|
| 70 |
ObjectMapper m = new ObjectMapper(); |
|
| 71 |
|
|
| 72 |
JsonNode rootNode = m.readTree(sb.toString()); |
|
| 73 |
logger.debug(rootNode.toString()); |
|
| 74 |
logger.debug(rootNode.isArray()); |
|
| 75 |
|
|
| 76 |
int num = 0; |
|
| 77 |
if (rootNode.isArray()) {
|
|
| 78 |
Iterator<JsonNode> arrayElements = rootNode.getElements(); |
|
| 79 |
while (arrayElements.hasNext()) {
|
|
| 80 |
JsonNode element = arrayElements.next(); |
|
| 81 |
JsonNode website = element.path("field_website");
|
|
| 82 |
//logger.debug(website.getValueAsText()); |
|
| 83 |
String fieldWebsite = website.getValueAsText(); |
|
| 84 |
|
|
| 85 |
if (fieldWebsite.startsWith("http")) {
|
|
| 86 |
|
|
| 87 |
url = new URL(fieldWebsite + "/dwca.zip"); |
|
| 88 |
URI uri = url.toURI(); |
|
| 89 |
isAvailable = UriUtils.isServiceAvailable(uri); |
|
| 90 |
logger.debug("Is " + fieldWebsite + " available :" + isAvailable);
|
|
| 91 |
|
|
| 92 |
String websiteName = ""; |
|
| 93 |
//websiteName = (fieldWebsite.toString().split("//")[1]).split(".*")[0];
|
|
| 94 |
websiteName = websiteName + fieldWebsite.split("//")[1];
|
|
| 95 |
//if (websiteName.contains(".")){
|
|
| 96 |
//websiteName = websiteName.substring(0, websiteName.indexOf("."));
|
|
| 97 |
websiteName = websiteName.replaceAll("\\.", "_");
|
|
| 98 |
//websiteName = websiteName.substring(0, websiteName.indexOf("."));
|
|
| 99 |
|
|
| 100 |
//} |
|
| 101 |
|
|
| 102 |
//logger.debug("the website name " + websiteName);
|
|
| 103 |
|
|
| 104 |
for (int j = 0; j < ILLEGAL_CHARACTERS.length; j++) {
|
|
| 105 |
|
|
| 106 |
char ch = '_'; |
|
| 107 |
websiteName.replace(ILLEGAL_CHARACTERS[j], ch); |
|
| 108 |
} |
|
| 109 |
|
|
| 110 |
websiteName = websiteName.substring(0, websiteName.length()); |
|
| 111 |
|
|
| 112 |
if (isAvailable) {
|
|
| 113 |
|
|
| 114 |
HttpResponse response = UriUtils.getResponse(uri, null); |
|
| 115 |
if (UriUtils.isOk(response)) {
|
|
| 116 |
|
|
| 117 |
|
|
| 118 |
logger.debug("There is a dwca " + websiteName);
|
|
| 119 |
|
|
| 120 |
try {
|
|
| 121 |
inputStream = UriUtils.getInputStream(url.toURI()); |
|
| 122 |
|
|
| 123 |
num++; |
|
| 124 |
|
|
| 125 |
if (inputStream != null) {
|
|
| 126 |
|
|
| 127 |
copyDwcaZip(inputStream, websiteName); |
|
| 128 |
//createDwcaZip(inputStream); |
|
| 129 |
} |
|
| 130 |
|
|
| 131 |
} catch (HttpException e) {
|
|
| 132 |
// TODO Auto-generated catch block |
|
| 133 |
logger.error("Failed to get dwca for " + websiteName + " as there was an error " + e);
|
|
| 134 |
} |
|
| 135 |
|
|
| 136 |
} |
|
| 137 |
|
|
| 138 |
} |
|
| 139 |
} |
|
| 140 |
} |
|
| 141 |
} |
|
| 142 |
|
|
| 143 |
inputStream.close(); |
|
| 144 |
|
|
| 145 |
|
|
| 146 |
} catch (URISyntaxException e) {
|
|
| 147 |
// TODO Auto-generated catch block |
|
| 148 |
e.printStackTrace(); |
|
| 149 |
} catch (IOException ie) {
|
|
| 150 |
ie.printStackTrace(); |
|
| 151 |
} catch (HttpException e) {
|
|
| 152 |
// TODO Auto-generated catch block |
|
| 153 |
e.printStackTrace(); |
|
| 154 |
} |
|
| 155 |
} |
|
| 156 |
|
|
| 157 |
/** |
|
| 158 |
* FIXME |
|
| 159 |
* This is a hack as dwca.zip files from Scratchpads sites have an extra directory when unzipped. i.e. all the text |
|
| 160 |
* and meta.xml are in the sub-directory dwca, but the should be directly in the top-level unzipped directory |
|
| 161 |
*/ |
|
| 162 |
private void createDwcaZip (InputStream inputStream, String websiteName) {
|
|
| 163 |
|
|
| 164 |
ZipInputStream zis = new ZipInputStream(inputStream); |
|
| 165 |
|
|
| 166 |
byte[] buffer = new byte[4096]; |
|
| 167 |
ZipEntry ze; |
|
| 168 |
try {
|
|
| 169 |
while ((ze = zis.getNextEntry()) != null) |
|
| 170 |
{
|
|
| 171 |
System.out.println("Extracting: " + ze);
|
|
| 172 |
|
|
| 173 |
FileOutputStream fos = new FileOutputStream(ze.getName()); |
|
| 174 |
{
|
|
| 175 |
int numBytes; |
|
| 176 |
while ((numBytes = zis.read(buffer, 0, buffer.length)) != -1) |
|
| 177 |
fos.write(buffer, 0, numBytes); |
|
| 178 |
} |
|
| 179 |
zis.closeEntry(); |
|
| 180 |
} |
|
| 181 |
} catch (FileNotFoundException e) {
|
|
| 182 |
// TODO Auto-generated catch block |
|
| 183 |
e.printStackTrace(); |
|
| 184 |
} catch (IOException e) {
|
|
| 185 |
// TODO Auto-generated catch block |
|
| 186 |
e.printStackTrace(); |
|
| 187 |
} |
|
| 188 |
|
|
| 189 |
} |
|
| 190 |
|
|
| 191 |
/* |
|
| 192 |
* Use this method instead of createDwcaZip, once the dwca.zip structure is fixed in Scratchpads |
|
| 193 |
*/ |
|
| 194 |
private void copyDwcaZip (InputStream inputStream, String websiteName) {
|
|
| 195 |
|
|
| 196 |
FileOutputStream outputStream; |
|
| 197 |
try {
|
|
| 198 |
outputStream = new FileOutputStream("dwca_" + websiteName + ".zip");//dir +
|
|
| 199 |
|
|
| 200 |
byte[] b = new byte[1024]; |
|
| 201 |
int count; |
|
| 202 |
while ((count = inputStream.read(b)) >= 0) {
|
|
| 203 |
outputStream.write(b, 0, count); |
|
| 204 |
} |
|
| 205 |
outputStream.flush(); |
|
| 206 |
outputStream.close(); |
|
| 207 |
inputStream.close(); |
|
| 208 |
} catch (FileNotFoundException e) {
|
|
| 209 |
// TODO Auto-generated catch block |
|
| 210 |
e.printStackTrace(); |
|
| 211 |
} catch (IOException ie) {
|
|
| 212 |
ie.printStackTrace(); |
|
| 213 |
} |
|
| 214 |
} |
|
| 215 |
|
|
| 216 |
/** |
|
| 217 |
* @param args |
|
| 218 |
*/ |
|
| 219 |
public static void main(String[] args) {
|
|
| 220 |
|
|
| 221 |
ScratchpadsService spService = new ScratchpadsService(); |
|
| 222 |
spService.harvest(); |
|
| 223 |
// TODO Auto-generated method stub |
|
| 224 |
|
|
| 225 |
} |
|
| 226 |
|
|
| 227 |
} |
|
| cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/common/ImportStateBase.java | ||
|---|---|---|
| 23 | 23 |
import eu.etaxonomy.cdm.model.common.AnnotationType; |
| 24 | 24 |
import eu.etaxonomy.cdm.model.common.CdmBase; |
| 25 | 25 |
import eu.etaxonomy.cdm.model.common.DefinedTerm; |
| 26 |
import eu.etaxonomy.cdm.model.common.DefinedTermBase; |
|
| 26 | 27 |
import eu.etaxonomy.cdm.model.common.ExtensionType; |
| 27 | 28 |
import eu.etaxonomy.cdm.model.common.Language; |
| 28 | 29 |
import eu.etaxonomy.cdm.model.common.MarkerType; |
| ... | ... | |
| 105 | 106 |
// } |
| 106 | 107 |
setTransformer(newTransformer); |
| 107 | 108 |
} |
| 109 |
|
|
| 108 | 110 |
} |
| 109 | 111 |
|
| 112 |
|
|
| 113 |
|
|
| 114 |
/** |
|
| 115 |
* Resets (empties) all maps which map a uuid to a {@link DefinedTermBase term}.
|
|
| 116 |
* This is usually needed when a a new transaction is opened and user defined terms are reused. |
|
| 117 |
*/ |
|
| 118 |
public void resetUuidTermMaps(){
|
|
| 119 |
extensionTypeMap = new HashMap<UUID, ExtensionType>(); |
|
| 120 |
markerTypeMap = new HashMap<UUID, MarkerType>(); |
|
| 121 |
annotationTypeMap = new HashMap<UUID, AnnotationType>(); |
|
| 122 |
|
|
| 123 |
namedAreaMap = new HashMap<UUID, NamedArea>(); |
|
| 124 |
namedAreaLevelMap = new HashMap<UUID, NamedAreaLevel>(); |
|
| 125 |
featureMap = new HashMap<UUID, Feature>(); |
|
| 126 |
stateTermMap = new HashMap<UUID, State>(); |
|
| 127 |
measurementUnitMap = new HashMap<UUID, MeasurementUnit>(); |
|
| 128 |
statisticalMeasureMap = new HashMap<UUID, StatisticalMeasure>(); |
|
| 129 |
modifierMap = new HashMap<UUID, DefinedTerm>(); |
|
| 130 |
|
|
| 131 |
presenceTermMap = new HashMap<UUID, PresenceTerm>();; |
|
| 132 |
languageMap = new HashMap<UUID, Language>(); |
|
| 133 |
taxonRelationshipTypeMap = new HashMap<UUID, TaxonRelationshipType>(); |
|
| 134 |
|
|
| 135 |
referenceSystemMap = new HashMap<UUID, ReferenceSystem>(); |
|
| 136 |
rankMap = new HashMap<UUID, Rank>(); |
|
| 137 |
} |
|
| 138 |
|
|
| 139 |
|
|
| 110 | 140 |
//different type of stores that are used by the known imports |
| 111 | 141 |
protected Map<String, MapWrapper<? extends CdmBase>> stores = new HashMap<String, MapWrapper<? extends CdmBase>>(); |
| 112 | 142 |
|
| ... | ... | |
| 169 | 199 |
} |
| 170 | 200 |
|
| 171 | 201 |
|
| 172 |
|
|
| 173 |
|
|
| 174 | 202 |
/** |
| 175 | 203 |
* Adds a classification uuid to the classification uuid map, |
| 176 | 204 |
* which maps a key for the classification to its UUID in the CDM |
| cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/common/XmlImportState.java | ||
|---|---|---|
| 11 | 11 |
package eu.etaxonomy.cdm.io.common; |
| 12 | 12 |
|
| 13 | 13 |
import javax.xml.stream.XMLEventReader; |
| 14 |
import javax.xml.stream.XMLStreamException; |
|
| 15 |
import javax.xml.stream.events.XMLEvent; |
|
| 16 | 14 |
|
| 17 | 15 |
import org.apache.log4j.Logger; |
| 18 | 16 |
|
| 19 | 17 |
/** |
| 20 | 18 |
* @author a.mueller |
| 21 | 19 |
* @created 11.05.2009 |
| 22 |
* @version 1.0 |
|
| 23 | 20 |
*/ |
| 24 | 21 |
public class XmlImportState<CONFIG extends XmlImportConfiguratorBase, IO extends XmlImportBase> extends ImportStateBase<CONFIG, IO> {
|
| 25 | 22 |
@SuppressWarnings("unused")
|
| cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/dwca/TermUri.java | ||
|---|---|---|
| 38 | 38 |
DC_LICENSE("http://purl.org/dc/terms/license"),
|
| 39 | 39 |
DC_MODIFIED("http://purl.org/dc/terms/modified"),
|
| 40 | 40 |
DC_PUBLISHER("http://purl.org/dc/terms/publisher"),
|
| 41 |
DC_REFERENCES("http://purl.org/dc/terms/references"),
|
|
| 41 | 42 |
DC_RIGHTS("http://purl.org/dc/terms/rights"),
|
| 42 | 43 |
DC_RIGHTS_HOLDER("http://purl.org/dc/terms/rightsHolder"),
|
| 43 | 44 |
DC_SOURCE("http://purl.org/dc/terms/source"),
|
| cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/dwca/in/DwcTaxonStreamItem2CdmTaxonConverter.java | ||
|---|---|---|
| 9 | 9 |
*/ |
| 10 | 10 |
package eu.etaxonomy.cdm.io.dwca.in; |
| 11 | 11 |
|
| 12 |
import java.net.URI; |
|
| 12 | 13 |
import java.util.ArrayList; |
| 13 | 14 |
import java.util.HashSet; |
| 14 | 15 |
import java.util.List; |
| ... | ... | |
| 27 | 28 |
import eu.etaxonomy.cdm.io.stream.StreamItem; |
| 28 | 29 |
import eu.etaxonomy.cdm.model.common.Annotation; |
| 29 | 30 |
import eu.etaxonomy.cdm.model.common.CdmBase; |
| 31 |
import eu.etaxonomy.cdm.model.common.Extension; |
|
| 32 |
import eu.etaxonomy.cdm.model.common.ExtensionType; |
|
| 30 | 33 |
import eu.etaxonomy.cdm.model.common.IdentifiableSource; |
| 31 | 34 |
import eu.etaxonomy.cdm.model.common.LSID; |
| 32 | 35 |
import eu.etaxonomy.cdm.model.common.Language; |
| ... | ... | |
| 58 | 61 |
* |
| 59 | 62 |
*/ |
| 60 | 63 |
public class DwcTaxonStreamItem2CdmTaxonConverter<CONFIG extends DwcaDataImportConfiguratorBase, STATE extends StreamImportStateBase<CONFIG, StreamImportBase>> extends PartitionableConverterBase<CONFIG, STATE> implements IPartitionableConverter<StreamItem, IReader<CdmBase>, String>{
|
| 61 |
@SuppressWarnings("unused")
|
|
| 62 |
private static Logger logger = Logger.getLogger(DwcTaxonStreamItem2CdmTaxonConverter.class); |
|
| 64 |
private static final Logger logger = Logger.getLogger(DwcTaxonStreamItem2CdmTaxonConverter.class); |
|
| 63 | 65 |
|
| 64 | 66 |
private static final String ID = "id"; |
| 65 | 67 |
// temporary key for the case that no dataset information is supplied, TODO use something better |
| ... | ... | |
| 104 | 106 |
|
| 105 | 107 |
//nameAccordingTo |
| 106 | 108 |
MappedCdmBase<Reference> sec = getNameAccordingTo(csvTaxonRecord, resultList); |
| 109 |
|
|
| 107 | 110 |
if (sec == null && state.getConfig().isUseSourceReferenceAsSec()){
|
| 108 | 111 |
sec = new MappedCdmBase<Reference>(state.getTransactionalSourceReference()); |
| 109 | 112 |
} |
| ... | ... | |
| 187 | 190 |
* @param taxonBase |
| 188 | 191 |
*/ |
| 189 | 192 |
private void handleIdentifiableObjects(StreamItem item,TaxonBase<?> taxonBase) {
|
| 193 |
|
|
| 194 |
|
|
| 195 |
String references = item.get(TermUri.DC_REFERENCES); |
|
| 196 |
|
|
| 197 |
if (references == null || references == "") {
|
|
| 198 |
references = item.get(TermUri.DWC_NAME_PUBLISHED_IN_ID);//lorna temporary until Scratchpads move the reference to the correct place. |
|
| 199 |
} |
|
| 200 |
|
|
| 201 |
if (StringUtils.isNotBlank(references)){
|
|
| 202 |
URI uri = makeUriIfIs(references); |
|
| 203 |
if (uri != null){
|
|
| 204 |
Extension.NewInstance(taxonBase, references, ExtensionType.URL()); |
|
| 205 |
}else{
|
|
| 206 |
String message = "Non-URI Dublin Core References not yet handled for taxa. References is: %s"; |
|
| 207 |
fireWarningEvent(String.format(message, references), item, 6); |
|
| 208 |
} |
|
| 209 |
} |
|
| 210 |
|
|
| 211 |
|
|
| 190 | 212 |
//TODO: Finish properly |
| 191 | 213 |
String id = item.get(TermUri.CDM_SOURCE_IDINSOURCE); |
| 192 | 214 |
String idNamespace = item.get(TermUri.CDM_SOURCE_IDNAMESPACE); |
| ... | ... | |
| 197 | 219 |
Taxon taxon = (Taxon) taxonBase; |
| 198 | 220 |
taxon.addSource(OriginalSourceType.Import, id, idNamespace, ref, null); |
| 199 | 221 |
} |
| 222 |
|
|
| 223 |
|
|
| 224 |
|
|
| 225 |
} |
|
| 226 |
|
|
| 227 |
|
|
| 228 |
/** |
|
| 229 |
* If str is an uri it returns is as an {@link URI}. If not it returns <code>null</code>.
|
|
| 230 |
* @param str |
|
| 231 |
* @return the URI. |
|
| 232 |
*/ |
|
| 233 |
private URI makeUriIfIs(String str) {
|
|
| 234 |
if (! str.startsWith("http:")){
|
|
| 235 |
return null; |
|
| 236 |
}else{
|
|
| 237 |
try {
|
|
| 238 |
URI uri = URI.create(str); |
|
| 239 |
return uri; |
|
| 240 |
} catch (Exception e) {
|
|
| 241 |
return null; |
|
| 242 |
} |
|
| 243 |
} |
|
| 244 |
|
|
| 200 | 245 |
} |
| 201 | 246 |
|
| 202 | 247 |
|
| ... | ... | |
| 226 | 271 |
private void handleTdwgArea(StreamItem item, TaxonBase<?> taxonBase) {
|
| 227 | 272 |
// TODO Auto-generated method stub |
| 228 | 273 |
String tdwg_area = item.get(TermUri.DWC_COUNTRY_CODE); |
| 274 |
if (tdwg_area != null){
|
|
| 229 | 275 |
if(taxonBase instanceof Synonym){
|
| 230 | 276 |
Synonym synonym = CdmBase.deproxy(taxonBase, Synonym.class); |
| 231 | 277 |
Set<Taxon> acceptedTaxaList = synonym.getAcceptedTaxa(); |
| ... | ... | |
| 236 | 282 |
for(Taxon taxon : acceptedTaxaList){
|
| 237 | 283 |
TaxonDescription td = getTaxonDescription(taxon, false); |
| 238 | 284 |
NamedArea area = NamedArea.getAreaByTdwgAbbreviation(tdwg_area); |
| 239 |
|
|
| 285 |
|
|
| 240 | 286 |
if (area == null){
|
| 241 | 287 |
area = NamedArea.getAreaByTdwgLabel(tdwg_area); |
| 242 | 288 |
} |
| ... | ... | |
| 251 | 297 |
Taxon taxon = CdmBase.deproxy(taxonBase, Taxon.class); |
| 252 | 298 |
TaxonDescription td = getTaxonDescription(taxon, false); |
| 253 | 299 |
NamedArea area = NamedArea.getAreaByTdwgAbbreviation(tdwg_area); |
| 254 |
|
|
| 300 |
|
|
| 255 | 301 |
if (area == null){
|
| 256 | 302 |
area = NamedArea.getAreaByTdwgLabel(tdwg_area); |
| 257 | 303 |
} |
| ... | ... | |
| 261 | 307 |
} |
| 262 | 308 |
} |
| 263 | 309 |
} |
| 310 |
} |
|
| 264 | 311 |
|
| 265 | 312 |
|
| 266 | 313 |
/** |
| ... | ... | |
| 327 | 374 |
//if not exists, create new |
| 328 | 375 |
if (! classificationExists){
|
| 329 | 376 |
String classificationName = StringUtils.isBlank(datasetName)? datasetId : datasetName; |
| 330 |
if (classificationName.equals(NO_DATASET)){
|
|
| 331 |
classificationName = "Classification (no name)"; //TODO define by config or zipfile or metadata |
|
| 377 |
if (classificationName.equals(NO_DATASET)){
|
|
| 378 |
classificationName = config.getClassificationName(); |
|
| 379 |
//classificationName = "Classification (no name)"; //TODO define by config or zipfile or metadata |
|
| 332 | 380 |
} |
| 333 | 381 |
|
| 334 | 382 |
String classificationId = StringUtils.isBlank(datasetId)? datasetName : datasetId; |
| ... | ... | |
| 497 | 545 |
if (! idIsInternal){
|
| 498 | 546 |
//references should already exist in store if not linking to external links like URLs |
| 499 | 547 |
String message = "External namePublishedInIDs are not yet supported"; |
| 500 |
fireWarningEvent(message, item, 4); |
|
| 548 |
fireWarningEvent(message, item, 4);//set to DEBUG
|
|
| 501 | 549 |
}else{
|
| 502 | 550 |
newRef = ReferenceFactory.newGeneric(); //TODO handle other types if possible |
| 503 | 551 |
newRef.addSource(OriginalSourceType.Import, refId, idTerm.toString(), sourceCitation, null); |
| cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/dwca/in/DwcaZipToStreamConverter.java | ||
|---|---|---|
| 18 | 18 |
import java.net.URI; |
| 19 | 19 |
import java.util.ArrayList; |
| 20 | 20 |
import java.util.Arrays; |
| 21 |
import java.util.Enumeration; |
|
| 21 | 22 |
import java.util.HashMap; |
| 22 | 23 |
import java.util.List; |
| 23 | 24 |
import java.util.Map; |
| ... | ... | |
| 263 | 264 |
throw new IOException(String.format(message, dwcaZip.toString())); |
| 264 | 265 |
} |
| 265 | 266 |
ZipFile zip = new ZipFile(file, ZipFile.OPEN_READ); |
| 267 |
|
|
| 268 |
//Enumeration<? extends ZipEntry> zipEntries = zip.entries(); |
|
| 269 |
//ze = new ZipEntry(name); |
|
| 266 | 270 |
ZipEntry metaEntry = zip.getEntry(name); |
| 271 |
|
|
| 272 |
//Lorna added this to deal with Scratchpads dwca.zip files which when unzipped have a directory dwca/ which contains the files |
|
| 273 |
if (metaEntry == null) {
|
|
| 274 |
metaEntry = zip.getEntry("dwca/" + name);
|
|
| 275 |
} |
|
| 267 | 276 |
if (metaEntry == null){
|
| 268 | 277 |
String message = "Zip entry for %s not available"; |
| 269 | 278 |
throw new IOException(String.format(message, name)); |
| cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/dwca/in/GbifDescriptionCsv2CdmConverter.java | ||
|---|---|---|
| 27 | 27 |
import eu.etaxonomy.cdm.model.description.Feature; |
| 28 | 28 |
import eu.etaxonomy.cdm.model.description.TaxonDescription; |
| 29 | 29 |
import eu.etaxonomy.cdm.model.description.TextData; |
| 30 |
import eu.etaxonomy.cdm.model.media.Rights; |
|
| 30 | 31 |
import eu.etaxonomy.cdm.model.reference.Reference; |
| 31 | 32 |
import eu.etaxonomy.cdm.model.taxon.Taxon; |
| 32 | 33 |
|
| ... | ... | |
| 62 | 63 |
if (taxon != null){
|
| 63 | 64 |
|
| 64 | 65 |
String description = item.get(TermUri.DC_DESCRIPTION); |
| 66 |
//String license = item.get(TermUri.DC_LICENSE);//lorna check - often empty in SP dwca |
|
| 67 |
|
|
| 68 |
//TODO: Create the Language from the TermUri.DC_LANGUAGE in the dwca |
|
| 69 |
Language language = getLanguage(item); |
|
| 70 |
|
|
| 71 |
|
|
| 65 | 72 |
if (StringUtils.isNotBlank(description)){
|
| 66 | 73 |
Feature feature = getFeatureByDcType(item, resultList); |
| 67 | 74 |
|
| 68 | 75 |
TaxonDescription taxonDescription = getTaxonDescription(taxon, false); |
| 76 |
|
|
| 77 |
//deduplicate - if this taxonDescription already got these Rights attached |
|
| 78 |
boolean addRights = true; |
|
| 79 |
String rights = item.get(TermUri.DC_RIGHTS); |
|
| 80 |
Set<Rights> allRights = taxonDescription.getRights(); |
|
| 81 |
for (Rights r : allRights) {
|
|
| 82 |
if (r.getText() == rights) {
|
|
| 83 |
addRights = false; |
|
| 84 |
} |
|
| 85 |
} |
|
| 86 |
|
|
| 87 |
if (addRights && (rights != null || rights != "")) {
|
|
| 88 |
Rights copyright = Rights.NewInstance(rights, language); |
|
| 89 |
taxonDescription.addRights(copyright); |
|
| 90 |
} |
|
| 91 |
|
|
| 69 | 92 |
TextData descElement = TextData.NewInstance(feature); |
| 70 | 93 |
|
| 71 |
Language language = getLanguage(item); //TODO |
|
| 94 |
//Language language = getLanguage(item); //TODO
|
|
| 72 | 95 |
descElement.putText(language,description); |
| 73 | 96 |
taxonDescription.addElement(descElement); |
| 74 | 97 |
}else{
|
| ... | ... | |
| 92 | 115 |
//TODO |
| 93 | 116 |
|
| 94 | 117 |
Language language = Language.DEFAULT(); |
| 118 |
String langString = item.get(TermUri.DC_LANGUAGE); |
|
| 119 |
|
|
| 120 |
/*if (langString != null) {
|
|
| 121 |
if (!langString.equals("")) {
|
|
| 122 |
language = getTermService().getLanguageByIso(langString.substring(0, 2)); |
|
| 123 |
//can getTermService from StreamImportBase which calls GbifDescriptionCsv2CdmConverter.map |
|
| 124 |
} |
|
| 125 |
}*/ |
|
| 95 | 126 |
return language; |
| 96 | 127 |
} |
| 97 | 128 |
|
| cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/FeatureSorter.java | ||
|---|---|---|
| 9 | 9 |
import java.util.HashSet; |
| 10 | 10 |
import java.util.Iterator; |
| 11 | 11 |
import java.util.List; |
| 12 |
import java.util.ListIterator; |
|
| 13 | 12 |
import java.util.Map; |
| 14 | 13 |
import java.util.Set; |
| 15 | 14 |
import java.util.UUID; |
| 16 | 15 |
|
| 17 | 16 |
/** |
| 18 | 17 |
* This class is supposed to find the best sorting order for features (descriptive and other). |
| 18 |
* Currently it is not yet very sophisticated. |
|
| 19 |
* |
|
| 19 | 20 |
* @author a.mueller |
| 20 | 21 |
* |
| 21 | 22 |
*/ |
| ... | ... | |
| 62 | 63 |
Map<UUID,FeatureStatistic> statisticMap = computeStatistic(listMap); |
| 63 | 64 |
FeatureStatistic best = findBest(statisticMap); |
| 64 | 65 |
result.add(best.uuid); |
| 65 |
removeFromLists(listMap, best.uuid); |
|
| 66 |
Map<String, List<FeatureSorterInfo>> subFeatures = removeFromLists(listMap, best.uuid); |
|
| 67 |
List<UUID> subFeatureOrder = getSortOrder(subFeatures); |
|
| 68 |
result.addAll(subFeatureOrder); |
|
| 66 | 69 |
} |
| 67 | 70 |
return result; |
| 68 | 71 |
} |
| ... | ... | |
| 88 | 91 |
* @param orderLists |
| 89 | 92 |
* @param uuid |
| 90 | 93 |
*/ |
| 91 |
private void removeFromLists(Map<String, List<FeatureSorterInfo>> orderLists, UUID uuid) {
|
|
| 94 |
private Map<String, List<FeatureSorterInfo>> removeFromLists(Map<String, List<FeatureSorterInfo>> orderListsMap, UUID uuid) {
|
|
| 95 |
Map<String, List<FeatureSorterInfo>> childLists = new HashMap<String, List<FeatureSorterInfo>>(); |
|
| 92 | 96 |
|
| 93 |
Set<String> keySet = orderLists.keySet(); |
|
| 97 |
Set<String> keySet = orderListsMap.keySet();
|
|
| 94 | 98 |
Iterator<String> keySetIterator = keySet.iterator(); |
| 95 | 99 |
while (keySetIterator.hasNext()){
|
| 96 | 100 |
String key = keySetIterator.next(); |
| 97 |
List<FeatureSorterInfo> list = orderLists.get(key); |
|
| 101 |
List<FeatureSorterInfo> list = orderListsMap.get(key);
|
|
| 98 | 102 |
Iterator<FeatureSorterInfo> it = list.listIterator(); |
| 99 | 103 |
while (it.hasNext()){
|
| 100 | 104 |
FeatureSorterInfo info = it.next(); |
| 101 | 105 |
if (info.getUuid().equals(uuid)){
|
| 106 |
if (! info.getSubFeatures().isEmpty()){
|
|
| 107 |
childLists.put(key, info.getSubFeatures()); |
|
| 108 |
} |
|
| 102 | 109 |
it.remove(); |
| 103 | 110 |
if (list.isEmpty()){
|
| 104 | 111 |
keySetIterator.remove(); |
| ... | ... | |
| 106 | 113 |
} |
| 107 | 114 |
} |
| 108 | 115 |
} |
| 116 |
return childLists; |
|
| 109 | 117 |
} |
| 110 | 118 |
|
| 111 | 119 |
|
| cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/FeatureSorterInfo.java | ||
|---|---|---|
| 3 | 3 |
*/ |
| 4 | 4 |
package eu.etaxonomy.cdm.io.markup; |
| 5 | 5 |
|
| 6 |
import java.util.ArrayList; |
|
| 7 |
import java.util.List; |
|
| 6 | 8 |
import java.util.UUID; |
| 7 | 9 |
|
| 8 | 10 |
import org.apache.commons.lang.StringUtils; |
| ... | ... | |
| 18 | 20 |
|
| 19 | 21 |
private UUID uuid; |
| 20 | 22 |
private String title; |
| 23 |
private List<FeatureSorterInfo> subFeatures = new ArrayList<FeatureSorterInfo>(); |
|
| 21 | 24 |
|
| 22 | 25 |
public FeatureSorterInfo(Feature feature){
|
| 23 | 26 |
this.setUuid(feature.getUuid()); |
| ... | ... | |
| 35 | 38 |
private void setUuid(UUID uuid) {
|
| 36 | 39 |
this.uuid = uuid; |
| 37 | 40 |
} |
| 41 |
|
|
| 42 |
public List<FeatureSorterInfo> getSubFeatures() {
|
|
| 43 |
return subFeatures; |
|
| 44 |
} |
|
| 45 |
|
|
| 46 |
public void addSubFeature(FeatureSorterInfo subFeature){
|
|
| 47 |
subFeatures.add(subFeature); |
|
| 48 |
} |
|
| 49 |
|
|
| 38 | 50 |
@Override |
| 39 | 51 |
public String toString(){
|
| 40 | 52 |
if (StringUtils.isNotBlank(title)){
|
| cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/MarkupDocumentImport.java | ||
|---|---|---|
| 76 | 76 |
public void doInvoke(MarkupImportState state) {
|
| 77 | 77 |
fireProgressEvent("Start import markup document", "Before start of document");
|
| 78 | 78 |
|
| 79 |
Queue<CdmBase> outputStream = new LinkedList<CdmBase>(); |
|
| 80 |
|
|
| 81 | 79 |
TransactionStatus tx = startTransaction(); |
| 82 | 80 |
// FIXME reset state |
| 83 | 81 |
doAllTheOldOtherStuff(state); |
| cdmlib-io/src/main/java/eu/etaxonomy/cdm/io/markup/MarkupDocumentImportNoComponent.java | ||
|---|---|---|
| 11 | 11 |
|
| 12 | 12 |
import java.net.MalformedURLException; |
| 13 | 13 |
import java.net.URL; |
| 14 |
import java.util.ArrayList; |
|
| 15 |
import java.util.Arrays; |
|
| 16 |
import java.util.HashMap; |
|
| 17 | 14 |
import java.util.HashSet; |
| 18 |
import java.util.List; |
|
| 19 | 15 |
import java.util.Map; |
| 20 | 16 |
import java.util.Set; |
| 21 | 17 |
import java.util.UUID; |
| 22 |
import java.util.regex.Matcher; |
|
| 23 |
import java.util.regex.Pattern; |
|
| 24 | 18 |
|
| 25 | 19 |
import javax.xml.stream.Location; |
| 26 | 20 |
import javax.xml.stream.XMLEventReader; |
| ... | ... | |
| 32 | 26 |
import org.apache.commons.lang.StringUtils; |
| 33 | 27 |
import org.apache.log4j.Logger; |
| 34 | 28 |
|
| 35 |
import eu.etaxonomy.cdm.common.CdmUtils; |
|
| 36 | 29 |
import eu.etaxonomy.cdm.io.common.mapping.UndefinedTransformerMethodException; |
| 37 | 30 |
import eu.etaxonomy.cdm.model.agent.TeamOrPersonBase; |
| 38 |
import eu.etaxonomy.cdm.model.common.AnnotatableEntity; |
|
| 39 |
import eu.etaxonomy.cdm.model.common.Annotation; |
|
| 40 |
import eu.etaxonomy.cdm.model.common.AnnotationType; |
|
| 41 |
import eu.etaxonomy.cdm.model.common.CdmBase; |
|
| 42 |
import eu.etaxonomy.cdm.model.common.Extension; |
|
| 43 | 31 |
import eu.etaxonomy.cdm.model.common.ExtensionType; |
| 44 | 32 |
import eu.etaxonomy.cdm.model.common.Language; |
| 45 | 33 |
import eu.etaxonomy.cdm.model.common.OriginalSourceType; |
| ... | ... | |
| 50 | 38 |
import eu.etaxonomy.cdm.model.description.Feature; |
| 51 | 39 |
import eu.etaxonomy.cdm.model.description.PolytomousKey; |
| 52 | 40 |
import eu.etaxonomy.cdm.model.description.PolytomousKeyNode; |
| 53 |
import eu.etaxonomy.cdm.model.description.PresenceAbsenceTermBase; |
|
| 54 |
import eu.etaxonomy.cdm.model.description.PresenceTerm; |
|
| 55 | 41 |
import eu.etaxonomy.cdm.model.description.TaxonDescription; |
| 56 | 42 |
import eu.etaxonomy.cdm.model.description.TextData; |
| 57 |
import eu.etaxonomy.cdm.model.location.NamedArea; |
|
| 58 |
import eu.etaxonomy.cdm.model.location.NamedAreaLevel; |
|
| 59 |
import eu.etaxonomy.cdm.model.media.IdentifiableMediaEntity; |
|
| 60 |
import eu.etaxonomy.cdm.model.media.Media; |
|
| 61 | 43 |
import eu.etaxonomy.cdm.model.name.CultivarPlantName; |
| 62 | 44 |
import eu.etaxonomy.cdm.model.name.NonViralName; |
| 63 | 45 |
import eu.etaxonomy.cdm.model.name.Rank; |
| 64 |
import eu.etaxonomy.cdm.model.occurrence.SpecimenOrObservationBase; |
|
| 65 | 46 |
import eu.etaxonomy.cdm.model.reference.Reference; |
| 66 | 47 |
import eu.etaxonomy.cdm.model.reference.ReferenceFactory; |
| 67 | 48 |
import eu.etaxonomy.cdm.model.taxon.Classification; |
| 68 | 49 |
import eu.etaxonomy.cdm.model.taxon.Taxon; |
| 69 | 50 |
import eu.etaxonomy.cdm.model.taxon.TaxonNode; |
| 70 |
import eu.etaxonomy.cdm.strategy.parser.NonViralNameParserImpl; |
|
| 71 | 51 |
|
| 72 | 52 |
|
| 73 | 53 |
/** |
| ... | ... | |
| 75 | 55 |
* |
| 76 | 56 |
*/ |
| 77 | 57 |
public class MarkupDocumentImportNoComponent extends MarkupImportBase {
|
| 58 |
@SuppressWarnings("unused")
|
|
| 78 | 59 |
private static final Logger logger = Logger.getLogger(MarkupDocumentImportNoComponent.class); |
| 79 | 60 |
|
| 80 | 61 |
private MarkupKeyImport keyImport; |
| 81 |
private MarkupSpecimenImport specimenImport; |
|
| 82 | 62 |
|
| 63 |
private MarkupModsImport modsImport; |
|
| 64 |
private MarkupFeatureImport featureImport; |
|
| 65 |
private MarkupSpecimenImport specimenImport; |
|
| 83 | 66 |
private MarkupNomenclatureImport nomenclatureImport; |
| 84 |
|
|
| 67 |
|
|
| 85 | 68 |
public MarkupDocumentImportNoComponent(MarkupDocumentImport docImport) {
|
| 86 | 69 |
super(docImport); |
| 87 | 70 |
this.keyImport = new MarkupKeyImport(docImport); |
| 88 | 71 |
this.specimenImport = new MarkupSpecimenImport(docImport); |
| 89 |
nomenclatureImport = new MarkupNomenclatureImport(docImport, keyImport, specimenImport); |
|
| 72 |
this.nomenclatureImport = new MarkupNomenclatureImport(docImport, specimenImport); |
|
| 73 |
this.modsImport = new MarkupModsImport(docImport); |
|
| 74 |
this.featureImport = new MarkupFeatureImport(docImport, specimenImport, nomenclatureImport); |
|
| 90 | 75 |
} |
| 91 | 76 |
|
| 92 | 77 |
public void doInvoke(MarkupImportState state) throws XMLStreamException {
|
| ... | ... | |
| 193 | 178 |
message = String.format(message, baseUrl); |
| 194 | 179 |
fireWarningEvent(message, next, 8); |
| 195 | 180 |
} |
| 196 |
} else if (isStartingElement(next, MODS)){
|
|
| 197 |
handleNotYetImplementedElement(next);
|
|
| 181 |
} else if (isStartingElement(next, MODS)){
|
|
| 182 |
modsImport.handleMods(state, reader, next);
|
|
| 198 | 183 |
} else {
|
| 199 | 184 |
handleUnexpectedElement(next); |
| 200 | 185 |
} |
| ... | ... | |
| 398 | 383 |
nomenclatureImport.handleNomenclature(state, reader, next); |
| 399 | 384 |
hasNomenclature = true; |
| 400 | 385 |
} else if (isStartingElement(next, FEATURE)) {
|
| 401 |
handleFeature(state, reader, next); |
|
| 386 |
featureImport.handleFeature(state, reader, next);
|
|
| 402 | 387 |
} else if (isStartingElement(next, NOTES)) {
|
| 403 | 388 |
// TODO is this the correct way to handle notes? |
| 404 | 389 |
String note = handleNotes(state, reader, next); |
| ... | ... | |
| 425 | 410 |
desc.addElement(textData); |
| 426 | 411 |
} |
| 427 | 412 |
textData = (TextData)desc.getElements().iterator().next(); |
| 428 |
makeFeatureFigureRef(state, reader, desc, false, textData, next); |
|
| 413 |
featureImport.makeFeatureFigureRef(state, reader, desc, false, textData, next);
|
|
| 429 | 414 |
} else if (isStartingElement(next, FIGURE)) {
|
| 430 |
handleFigure(state, reader, next); |
|
| 415 |
handleFigure(state, reader, next, specimenImport, nomenclatureImport);
|
|
| 431 | 416 |
} else if (isStartingElement(next, FOOTNOTE)) {
|
| 432 |
FootnoteDataHolder footnote = handleFootnote(state, reader, next); |
|
| 417 |
FootnoteDataHolder footnote = handleFootnote(state, reader, next, specimenImport, nomenclatureImport);
|
|
| 433 | 418 |
if (footnote.isRef()) {
|
| 434 | 419 |
String message = "Ref footnote not implemented here"; |
| 435 | 420 |
fireWarningEvent(message, next, 4); |
| ... | ... | |
| 458 | 443 |
WriterDataHolder writer = handleWriter(state, reader, next); |
| 459 | 444 |
taxon.addExtension(writer.extension); |
| 460 | 445 |
// TODO what if taxonTitle comes later |
| 461 |
if (StringUtils.isNotBlank(taxonTitle) |
|
| 462 |
&& writer.extension != null) {
|
|
| 446 |
if (StringUtils.isNotBlank(taxonTitle) && writer.extension != null) {
|
|
| 463 | 447 |
Reference<?> sec = ReferenceFactory.newBookSection(); |
| 464 | 448 |
sec.setTitle(taxonTitle); |
| 465 | 449 |
TeamOrPersonBase<?> author = createAuthor(writer.writer); |
| 466 | 450 |
sec.setAuthorTeam(author); |
| 467 |
sec.setInReference(state.getConfig() |
|
| 468 |
.getSourceReference()); |
|
| 451 |
sec.setInReference(state.getConfig().getSourceReference()); |
|
| 469 | 452 |
taxon.setSec(sec); |
| 470 | 453 |
registerFootnotes(state, sec, writer.footnotes); |
| 471 | 454 |
} else {
|
| ... | ... | |
| 645 | 628 |
|
| 646 | 629 |
} |
| 647 | 630 |
|
| 648 |
private WriterDataHolder handleWriter(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent) throws XMLStreamException {
|
|
| 649 |
String text = ""; |
|
| 650 |
checkNoAttributes(parentEvent); |
|
| 651 |
WriterDataHolder dataHolder = new WriterDataHolder(); |
|
| 652 |
List<FootnoteDataHolder> footnotes = new ArrayList<FootnoteDataHolder>(); |
|
| 653 |
|
|
| 654 |
// TODO handle attributes |
|
| 655 |
while (reader.hasNext()) {
|
|
| 656 |
XMLEvent next = readNoWhitespace(reader); |
|
| 657 |
if (isMyEndingElement(next, parentEvent)) {
|
|
| 658 |
text = CdmUtils.removeBrackets(text); |
|
| 659 |
if (checkMandatoryText(text, parentEvent)) {
|
|
| 660 |
text = normalize(text); |
|
| 661 |
dataHolder.writer = text; |
|
| 662 |
dataHolder.footnotes = footnotes; |
|
| 663 |
|
|
| 664 |
// Extension |
|
| 665 |
UUID uuidWriterExtension = MarkupTransformer.uuidWriterExtension; |
|
| 666 |
ExtensionType writerExtensionType = this |
|
| 667 |
.getExtensionType(state, uuidWriterExtension, |
|
| 668 |
"Writer", "writer", "writer"); |
|
| 669 |
Extension extension = Extension.NewInstance(); |
|
| 670 |
extension.setType(writerExtensionType); |
|
| 671 |
extension.setValue(text); |
|
| 672 |
dataHolder.extension = extension; |
|
| 673 |
|
|
| 674 |
// Annotation |
|
| 675 |
UUID uuidWriterAnnotation = MarkupTransformer.uuidWriterAnnotation; |
|
| 676 |
AnnotationType writerAnnotationType = this.getAnnotationType(state, uuidWriterAnnotation, "Writer", "writer", "writer", null); |
|
| 677 |
Annotation annotation = Annotation.NewInstance(text, writerAnnotationType, getDefaultLanguage(state)); |
|
| 678 |
dataHolder.annotation = annotation; |
|
| 679 |
|
|
| 680 |
return dataHolder; |
|
| 681 |
} else {
|
|
| 682 |
return null; |
|
| 683 |
} |
|
| 684 |
} else if (isStartingElement(next, FOOTNOTE_REF)) {
|
|
| 685 |
FootnoteDataHolder footNote = handleFootnoteRef(state, reader, next); |
|
| 686 |
if (footNote.isRef()) {
|
|
| 687 |
footnotes.add(footNote); |
|
| 688 |
} else {
|
|
| 689 |
logger.warn("Non ref footnotes not yet impelemnted");
|
|
| 690 |
} |
|
| 691 |
} else if (next.isCharacters()) {
|
|
| 692 |
text += next.asCharacters().getData(); |
|
| 693 |
|
|
| 694 |
} else {
|
|
| 695 |
handleUnexpectedElement(next); |
|
| 696 |
state.setUnsuccessfull(); |
|
| 697 |
} |
|
| 698 |
} |
|
| 699 |
throw new IllegalStateException("<writer> has no end tag");
|
|
| 700 |
} |
|
| 701 |
|
|
| 702 |
private void registerFootnotes(MarkupImportState state, AnnotatableEntity entity, List<FootnoteDataHolder> footnotes) {
|
|
| 703 |
for (FootnoteDataHolder footNote : footnotes) {
|
|
| 704 |
registerFootnoteDemand(state, entity, footNote); |
|
| 705 |
} |
|
| 706 |
} |
|
| 707 |
|
|
| 708 |
private void registerGivenFootnote(MarkupImportState state, FootnoteDataHolder footnote) {
|
|
| 709 |
state.registerFootnote(footnote); |
|
| 710 |
Set<AnnotatableEntity> demands = state.getFootnoteDemands(footnote.id); |
|
| 711 |
if (demands != null) {
|
|
| 712 |
for (AnnotatableEntity entity : demands) {
|
|
| 713 |
attachFootnote(state, entity, footnote); |
|
| 714 |
} |
|
| 715 |
} |
|
| 716 |
} |
|
| 717 |
|
|
| 718 |
private void registerGivenFigure(MarkupImportState state, XMLEvent next, String id, Media figure) {
|
|
| 719 |
state.registerFigure(id, figure); |
|
| 720 |
Set<AnnotatableEntity> demands = state.getFigureDemands(id); |
|
| 721 |
if (demands != null) {
|
|
| 722 |
for (AnnotatableEntity entity : demands) {
|
|
| 723 |
attachFigure(state, next, entity, figure); |
|
| 724 |
} |
|
| 725 |
} |
|
| 726 |
save(figure, state); |
|
| 727 |
} |
|
| 728 |
|
|
| 729 |
private void registerFootnoteDemand(MarkupImportState state, AnnotatableEntity entity, FootnoteDataHolder footnote) {
|
|
| 730 |
FootnoteDataHolder existingFootnote = state.getFootnote(footnote.ref); |
|
| 731 |
if (existingFootnote != null) {
|
|
| 732 |
attachFootnote(state, entity, existingFootnote); |
|
| 733 |
} else {
|
|
| 734 |
Set<AnnotatableEntity> demands = state.getFootnoteDemands(footnote.ref); |
|
| 735 |
if (demands == null) {
|
|
| 736 |
demands = new HashSet<AnnotatableEntity>(); |
|
| 737 |
state.putFootnoteDemands(footnote.ref, demands); |
|
| 738 |
} |
|
| 739 |
demands.add(entity); |
|
| 740 |
} |
|
| 741 |
} |
|
| 742 |
|
|
| 743 |
private void registerFigureDemand(MarkupImportState state, XMLEvent next, AnnotatableEntity entity, String figureRef) {
|
|
| 744 |
Media existingFigure = state.getFigure(figureRef); |
|
| 745 |
if (existingFigure != null) {
|
|
| 746 |
attachFigure(state, next, entity, existingFigure); |
|
| 747 |
} else {
|
|
| 748 |
Set<AnnotatableEntity> demands = state.getFigureDemands(figureRef); |
|
| 749 |
if (demands == null) {
|
|
| 750 |
demands = new HashSet<AnnotatableEntity>(); |
|
| 751 |
state.putFigureDemands(figureRef, demands); |
|
| 752 |
} |
|
| 753 |
demands.add(entity); |
|
| 754 |
} |
|
| 755 |
} |
|
| 756 |
|
|
| 757 |
private void attachFootnote(MarkupImportState state, AnnotatableEntity entity, FootnoteDataHolder footnote) {
|
|
| 758 |
AnnotationType annotationType = this.getAnnotationType(state, MarkupTransformer.uuidFootnote, "Footnote", "An e-flora footnote", "fn", null); |
|
| 759 |
Annotation annotation = Annotation.NewInstance(footnote.string, annotationType, getDefaultLanguage(state)); |
|
| 760 |
// TODO transient objects |
|
| 761 |
entity.addAnnotation(annotation); |
|
| 762 |
save(entity, state); |
|
| 763 |
} |
|
| 764 |
|
|
| 765 |
private void attachFigure(MarkupImportState state, XMLEvent next, AnnotatableEntity entity, Media figure) {
|
|
| 766 |
// IdentifiableEntity<?> toSave; |
|
| 767 |
if (entity.isInstanceOf(TextData.class)) {
|
|
| 768 |
TextData deb = CdmBase.deproxy(entity, TextData.class); |
|
| 769 |
deb.addMedia(figure); |
|
| 770 |
// toSave = ((TaxonDescription)deb.getInDescription()).getTaxon(); |
|
| 771 |
} else if (entity.isInstanceOf(SpecimenOrObservationBase.class)) {
|
|
| 772 |
String message = "figures for specimen should be handled as Textdata"; |
|
| 773 |
fireWarningEvent(message, next, 4); |
|
| 774 |
// toSave = ime; |
|
| 775 |
} else if (entity.isInstanceOf(IdentifiableMediaEntity.class)) {
|
|
| 776 |
IdentifiableMediaEntity<?> ime = CdmBase.deproxy(entity, IdentifiableMediaEntity.class); |
|
| 777 |
ime.addMedia(figure); |
|
| 778 |
// toSave = ime; |
|
| 779 |
} else {
|
|
| 780 |
String message = "Unsupported entity to attach media: %s"; |
|
| 781 |
message = String.format(message, entity.getClass().getName()); |
|
| 782 |
// toSave = null; |
|
| 783 |
} |
|
| 784 |
save(entity, state); |
|
| 785 |
} |
|
| 786 |
|
|
| 787 |
private Media handleFigure(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent) throws XMLStreamException {
|
|
| 788 |
// FigureDataHolder result = new FigureDataHolder(); |
|
| 789 |
|
|
| 790 |
Map<String, Attribute> attributes = getAttributes(parentEvent); |
|
| 791 |
String id = getAndRemoveAttributeValue(attributes, ID); |
|
| 792 |
String type = getAndRemoveAttributeValue(attributes, TYPE); |
|
| 793 |
String urlAttr = getAndRemoveAttributeValue(attributes, URL); |
|
| 794 |
checkNoAttributes(attributes, parentEvent); |
|
| 795 |
|
|
| 796 |
String urlString = null; |
|
| 797 |
String legendString = null; |
|
| 798 |
String titleString = null; |
|
| 799 |
String numString = null; |
|
| 800 |
String text = null; |
|
| 801 |
if (isNotBlank(urlAttr)){
|
|
| 802 |
urlString = CdmUtils.Nz(state.getBaseMediaUrl()) + urlAttr; |
|
| 803 |
} |
|
| 804 |
while (reader.hasNext()) {
|
|
| 805 |
XMLEvent next = readNoWhitespace(reader); |
|
| 806 |
if (isMyEndingElement(next, parentEvent)) {
|
|
| 807 |
if (isNotBlank(text)){
|
|
| 808 |
fireWarningEvent("Text not yet handled for figures: " + text, next, 4);
|
|
| 809 |
} |
|
| 810 |
Media media = makeFigure(state, id, type, urlString, legendString, titleString, numString, next); |
|
| 811 |
return media; |
|
| 812 |
} else if (isStartingElement(next, FIGURE_LEGEND)) {
|
|
| 813 |
// TODO same as figure string ? |
|
| 814 |
legendString = handleFootnoteString(state, reader, next); |
|
| 815 |
} else if (isStartingElement(next, FIGURE_TITLE)) {
|
|
| 816 |
titleString = getCData(state, reader, next); |
|
| 817 |
} else if (isStartingElement(next, URL)) {
|
|
| 818 |
String localUrl = getCData(state, reader, next); |
|
| 819 |
String url = CdmUtils.Nz(state.getBaseMediaUrl()) + localUrl; |
|
| 820 |
if (isBlank(urlString)){
|
|
| 821 |
urlString = url; |
|
| 822 |
} |
|
| 823 |
if (! url.equals(urlString)){
|
|
| 824 |
String message = "URL attribute and URL element differ. Attribute: %s, Element: %s"; |
|
| 825 |
fireWarningEvent(String.format(message, urlString, url), next, 2); |
|
| 826 |
} |
|
| 827 |
} else if (isStartingElement(next, NUM)) {
|
|
| 828 |
numString = getCData(state, reader, next); |
|
| 829 |
} else if (next.isCharacters()) {
|
|
| 830 |
text += CdmUtils.concat("", text, next.asCharacters().getData());
|
|
| 831 |
} else {
|
|
| 832 |
fireUnexpectedEvent(next, 0); |
|
| 833 |
} |
|
| 834 |
} |
|
| 835 |
throw new IllegalStateException("<figure> has no end tag");
|
|
| 836 |
} |
|
| 837 |
|
|
| 838 |
/** |
|
| 839 |
* @param state |
|
| 840 |
* @param id |
|
| 841 |
* @param type |
|
| 842 |
* @param urlString |
|
| 843 |
* @param legendString |
|
| 844 |
* @param titleString |
|
| 845 |
* @param numString |
|
| 846 |
* @param next |
|
| 847 |
*/ |
|
| 848 |
private Media makeFigure(MarkupImportState state, String id, String type, String urlString, |
|
| 849 |
String legendString, String titleString, String numString, XMLEvent next) {
|
|
| 850 |
Media media = null; |
|
| 851 |
boolean isFigure = false; |
|
| 852 |
try {
|
|
| 853 |
//TODO maybe everything is a figure as it is all taken from a book |
|
| 854 |
if ("lineart".equals(type)) {
|
|
| 855 |
isFigure = true; |
|
| 856 |
// media = Figure.NewInstance(url.toURI(), null, null, null); |
|
| 857 |
} else if (type == null || "photo".equals(type) |
|
| 858 |
|| "signature".equals(type) |
|
| 859 |
|| "others".equals(type)) {
|
|
| 860 |
//TODO |
|
| 861 |
} else {
|
|
| 862 |
String message = "Unknown figure type '%s'"; |
|
| 863 |
message = String.format(message, type); |
|
| 864 |
fireWarningEvent(message, next, 2); |
|
| 865 |
} |
|
| 866 |
media = docImport.getImageMedia(urlString, docImport.getReadMediaData(), isFigure); |
|
| 867 |
|
|
| 868 |
if (media != null){
|
|
| 869 |
// title |
|
| 870 |
if (StringUtils.isNotBlank(titleString)) {
|
|
| 871 |
media.putTitle(getDefaultLanguage(state), titleString); |
|
| 872 |
} |
|
| 873 |
// legend |
|
| 874 |
if (StringUtils.isNotBlank(legendString)) {
|
|
| 875 |
media.putDescription(getDefaultLanguage(state), legendString); |
|
| 876 |
} |
|
| 877 |
if (StringUtils.isNotBlank(numString)) {
|
|
| 878 |
// TODO use concrete source (e.g. DAPHNIPHYLLACEAE in FM |
|
| 879 |
// vol.13) |
|
| 880 |
Reference<?> citation = state.getConfig().getSourceReference(); |
|
| 881 |
media.addImportSource( numString, "num", citation, null); |
|
| 882 |
// TODO name used in source if available |
|
| 883 |
} |
|
| 884 |
// TODO which citation |
|
| 885 |
if (StringUtils.isNotBlank(id)) {
|
|
| 886 |
media.addImportSource(id, null, state.getConfig().getSourceReference(), null); |
|
| 887 |
} else {
|
|
| 888 |
String message = "Figure id should never be empty or null"; |
|
| 889 |
fireWarningEvent(message, next, 6); |
|
| 890 |
} |
|
| 891 |
|
|
| 892 |
// text |
|
| 893 |
// do nothing |
|
| 894 |
registerGivenFigure(state, next, id, media); |
|
| 895 |
|
|
| 896 |
}else{
|
|
| 897 |
String message = "No media found: "; |
|
| 898 |
fireWarningEvent(message, next, 4); |
|
| 899 |
} |
|
| 900 |
} catch (MalformedURLException e) {
|
|
| 901 |
String message = "Media uri has incorrect syntax: %s"; |
|
| 902 |
message = String.format(message, urlString); |
|
| 903 |
fireWarningEvent(message, next, 4); |
|
| 904 |
// } catch (URISyntaxException e) {
|
|
| 905 |
// String message = "Media uri has incorrect syntax: %s"; |
|
| 906 |
// message = String.format(message, urlString); |
|
| 907 |
// fireWarningEvent(message, next, 4); |
|
| 908 |
} |
|
| 909 |
|
|
| 910 |
return media; |
|
| 911 |
} |
|
| 912 |
|
|
| 913 |
private FigureDataHolder handleFigureRef(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent) |
|
| 914 |
throws XMLStreamException {
|
|
| 915 |
FigureDataHolder result = new FigureDataHolder(); |
|
| 916 |
Map<String, Attribute> attributes = getAttributes(parentEvent); |
|
| 917 |
result.ref = getAndRemoveAttributeValue(attributes, REF); |
|
| 918 |
checkNoAttributes(attributes, parentEvent); |
|
| 919 |
|
|
| 920 |
// text is not handled, needed only for debugging purposes |
|
| 921 |
String text = ""; |
|
| 922 |
while (reader.hasNext()) {
|
|
| 923 |
XMLEvent next = readNoWhitespace(reader); |
|
| 924 |
if (isMyEndingElement(next, parentEvent)) {
|
|
| 925 |
return result; |
|
| 926 |
} else if (isStartingElement(next, NUM)) {
|
|
| 927 |
String num = getCData(state, reader, next); |
|
| 928 |
result.num = num; // num is not handled during import |
|
| 929 |
} else if (isStartingElement(next, FIGURE_PART)) {
|
|
| 930 |
result.figurePart = getCData(state, reader, next); |
|
| 931 |
} else if (next.isCharacters()) {
|
|
| 932 |
text += next.asCharacters().getData(); |
|
| 933 |
} else {
|
|
| 934 |
fireUnexpectedEvent(next, 0); |
|
| 935 |
} |
|
| 936 |
} |
|
| 937 |
throw new IllegalStateException("<figureRef> has no end tag");
|
|
| 938 |
} |
|
| 939 |
|
|
| 940 |
private FootnoteDataHolder handleFootnote(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent) throws XMLStreamException {
|
|
| 941 |
FootnoteDataHolder result = new FootnoteDataHolder(); |
|
| 942 |
Map<String, Attribute> attributes = getAttributes(parentEvent); |
|
| 943 |
result.id = getAndRemoveAttributeValue(attributes, ID); |
|
| 944 |
// result.ref = getAndRemoveAttributeValue(attributes, REF); |
|
| 945 |
checkNoAttributes(attributes, parentEvent); |
|
| 946 |
|
|
| 947 |
while (reader.hasNext()) {
|
|
| 948 |
XMLEvent next = readNoWhitespace(reader); |
|
| 949 |
if (isStartingElement(next, FOOTNOTE_STRING)) {
|
|
| 950 |
String string = handleFootnoteString(state, reader, next); |
|
| 951 |
result.string = string; |
|
| 952 |
} else if (isMyEndingElement(next, parentEvent)) {
|
|
| 953 |
return result; |
|
| 954 |
} else {
|
|
| 955 |
fireUnexpectedEvent(next, 0); |
|
| 956 |
} |
|
| 957 |
} |
|
| 958 |
return result; |
|
| 959 |
} |
|
| 960 |
|
|
| 961 |
private FootnoteDataHolder handleFootnoteRef(MarkupImportState state, |
|
| 962 |
XMLEventReader reader, XMLEvent parentEvent) |
|
| 963 |
throws XMLStreamException {
|
|
| 964 |
FootnoteDataHolder result = new FootnoteDataHolder(); |
|
| 965 |
Map<String, Attribute> attributes = getAttributes(parentEvent); |
|
| 966 |
result.ref = getAndRemoveAttributeValue(attributes, REF); |
|
| 967 |
checkNoAttributes(attributes, parentEvent); |
|
| 968 |
|
|
| 969 |
// text is not handled, needed only for debugging purposes |
|
| 970 |
String text = ""; |
|
| 971 |
while (reader.hasNext()) {
|
|
| 972 |
XMLEvent next = readNoWhitespace(reader); |
|
| 973 |
// if (isStartingElement(next, FOOTNOTE_STRING)){
|
|
| 974 |
// String string = handleFootnoteString(state, reader, next); |
|
| 975 |
// result.string = string; |
|
| 976 |
// }else |
|
| 977 |
if (isMyEndingElement(next, parentEvent)) {
|
|
| 978 |
return result; |
|
| 979 |
} else if (next.isCharacters()) {
|
|
| 980 |
text += next.asCharacters().getData(); |
|
| 981 |
|
|
| 982 |
} else {
|
|
| 983 |
fireUnexpectedEvent(next, 0); |
|
| 984 |
} |
|
| 985 |
} |
|
| 986 |
return result; |
|
| 987 |
} |
|
| 988 |
|
|
| 989 |
|
|
| 990 |
|
|
| 991 |
private String handleFootnoteString(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent) throws XMLStreamException {
|
|
| 992 |
boolean isTextMode = true; |
|
| 993 |
String text = ""; |
|
| 994 |
while (reader.hasNext()) {
|
|
| 995 |
XMLEvent next = readNoWhitespace(reader); |
|
| 996 |
if (isMyEndingElement(next, parentEvent)) {
|
|
| 997 |
return text; |
|
| 998 |
} else if (next.isEndElement()) {
|
|
| 999 |
if (isEndingElement(next, FULL_NAME)) {
|
|
| 1000 |
popUnimplemented(next.asEndElement()); |
|
| 1001 |
} else if (isEndingElement(next, BR)) {
|
|
| 1002 |
isTextMode = true; |
|
| 1003 |
} else if (isHtml(next)) {
|
|
| 1004 |
text += getXmlTag(next); |
|
| 1005 |
} else {
|
|
| 1006 |
handleUnexpectedEndElement(next.asEndElement()); |
|
| 1007 |
} |
|
| 1008 |
} else if (next.isStartElement()) {
|
|
| 1009 |
if (isStartingElement(next, FULL_NAME)) {
|
|
| 1010 |
handleNotYetImplementedElement(next); |
|
| 1011 |
} else if (isStartingElement(next, GATHERING)) {
|
|
| 1012 |
text += specimenImport.handleInLineGathering(state, reader, next); |
|
| 1013 |
} else if (isStartingElement(next, REFERENCES)) {
|
|
| 1014 |
text += " " + handleInLineReferences(state, reader, next)+ " "; |
|
| 1015 |
} else if (isStartingElement(next, BR)) {
|
|
| 1016 |
text += "<br/>"; |
|
| 1017 |
isTextMode = false; |
|
| 1018 |
} else if (isStartingElement(next, NOMENCLATURE)) {
|
|
| 1019 |
handleNotYetImplementedElement(next); |
|
| 1020 |
} else if (isHtml(next)) {
|
|
| 1021 |
text += getXmlTag(next); |
|
| 1022 |
} else {
|
|
| 1023 |
handleUnexpectedStartElement(next.asStartElement()); |
|
| 1024 |
} |
|
| 1025 |
} else if (next.isCharacters()) {
|
|
| 1026 |
if (!isTextMode) {
|
|
| 1027 |
String message = "footnoteString is not in text mode"; |
|
| 1028 |
fireWarningEvent(message, next, 6); |
|
| 1029 |
} else {
|
|
| 1030 |
text += next.asCharacters().getData().trim(); |
|
| 1031 |
// getCData(state, reader, next); does not work as we have inner tags like <references> |
|
| 1032 |
} |
|
| 1033 |
} else {
|
|
| 1034 |
handleUnexpectedEndElement(next.asEndElement()); |
|
| 1035 |
} |
|
| 1036 |
} |
|
| 1037 |
throw new IllegalStateException("<footnoteString> has no closing tag");
|
|
| 1038 |
|
|
| 1039 |
} |
|
| 1040 |
|
|
| 1041 |
private String handleInLineReferences(MarkupImportState state,XMLEventReader reader, XMLEvent parentEvent) throws XMLStreamException {
|
|
| 1042 |
checkNoAttributes(parentEvent); |
|
| 1043 |
|
|
| 1044 |
boolean hasReference = false; |
|
| 1045 |
String text = ""; |
|
| 1046 |
while (reader.hasNext()) {
|
|
| 1047 |
XMLEvent next = readNoWhitespace(reader); |
|
| 1048 |
if (isMyEndingElement(next, parentEvent)) {
|
|
| 1049 |
checkMandatoryElement(hasReference, parentEvent.asStartElement(), REFERENCE); |
|
| 1050 |
return text; |
|
| 1051 |
} else if (isStartingElement(next, REFERENCE)) {
|
|
| 1052 |
text += handleInLineReference(state, reader, next); |
|
| 1053 |
hasReference = true; |
|
| 1054 |
} else {
|
|
| 1055 |
handleUnexpectedElement(next); |
|
| 1056 |
} |
|
| 1057 |
} |
|
| 1058 |
throw new IllegalStateException("<References> has no closing tag");
|
|
| 1059 |
} |
|
| 1060 |
|
|
| 1061 |
private String handleInLineReference(MarkupImportState state,XMLEventReader reader, XMLEvent parentEvent)throws XMLStreamException {
|
|
| 1062 |
Reference<?> reference = nomenclatureImport.handleReference(state, reader, parentEvent); |
|
| 1063 |
String result = "<cdm:ref uuid='%s'>%s</ref>"; |
|
| 1064 |
result = String.format(result, reference.getUuid(), reference.getTitleCache()); |
|
| 1065 |
save(reference, state); |
|
| 1066 |
return result; |
|
| 1067 |
} |
|
| 1068 |
|
|
| 1069 |
private void handleFeature(MarkupImportState state, XMLEventReader reader, XMLEvent parentEvent) throws XMLStreamException {
|
|
| 1070 |
Map<String, Attribute> attrs = getAttributes(parentEvent); |
|
| 1071 |
Boolean isFreetext = getAndRemoveBooleanAttributeValue(parentEvent, attrs, IS_FREETEXT, false); |
|
| 1072 |
String classValue =getAndRemoveRequiredAttributeValue(parentEvent, attrs, CLASS); |
|
| 1073 |
checkNoAttributes(attrs, parentEvent); |
|
| 1074 |
|
|
| 1075 |
|
|
| 1076 |
Feature feature = makeFeature(classValue, state, parentEvent, null); |
|
| 1077 |
Taxon taxon = state.getCurrentTaxon(); |
|
| 1078 |
TaxonDescription taxonDescription = getTaxonDescription(taxon, state.getConfig().getSourceReference(), NO_IMAGE_GALLERY, CREATE_NEW); |
|
| 1079 |
// TextData figureHolderTextData = null; //for use with one TextData for |
|
| 1080 |
// all figure only |
|
| 1081 |
|
|
| 1082 |
boolean isDescription = feature.equals(Feature.DESCRIPTION()); |
|
| 1083 |
DescriptionElementBase lastDescriptionElement = null; |
|
| 1084 |
|
|
| 1085 |
while (reader.hasNext()) {
|
|
| 1086 |
XMLEvent next = readNoWhitespace(reader); |
|
| 1087 |
if (isMyEndingElement(next, parentEvent)) {
|
|
| 1088 |
state.putFeatureToGeneralSorterList(feature); |
|
| 1089 |
return; |
|
| 1090 |
} else if (isEndingElement(next, DISTRIBUTION_LIST) || isEndingElement(next, HABITAT_LIST)) {
|
|
| 1091 |
// only handle list elements |
|
| 1092 |
} else if (isStartingElement(next, HEADING)) {
|
|
| 1093 |
makeFeatureHeading(state, reader, classValue, feature, next); |
|
| 1094 |
} else if (isStartingElement(next, WRITER)) {
|
|
| 1095 |
makeFeatureWriter(state, reader, feature, taxon, next); |
|
| 1096 |
// } else if (isStartingElement(next, DISTRIBUTION_LOCALITY)) {
|
|
| 1097 |
// if (!feature.equals(Feature.DISTRIBUTION())) {
|
|
| 1098 |
// String message = "Distribution locality only allowed for feature of type 'distribution'"; |
|
Also available in: Unified diff
merge trunk into cdm3.3 branch