Merge pull request 'task_2234' (!5) from task_2234 into master

Reviewed-on: #5
Fabio Sinibaldi 2 years ago
commit 6e8ea70e1c

@ -2,6 +2,9 @@ This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.htm
# Changelog for org.gcube.data-publishing.gFeed.DataMinerAlgorithmsCrawler
## [v1.0.5] - 2020-12-15
- Fixes [#22344](https://support.d4science.org/issues/22344#change-128440) : publish DM algorithms as Methods
## [v1.0.4] - 2020-12-15
- Dependency management
- Naming Convention

@ -8,7 +8,7 @@
</parent>
<artifactId>DataMinerAlgorithmsCrawler</artifactId>
<name>DataMinerAlgorithmsCrawler</name>
<version>1.0.4</version>
<version>1.0.5</version>
<description>Plugin for gCat-Feeder for DataMiner Algorithms publishing</description>
<!-- <properties> -->
@ -56,6 +56,18 @@
<artifactId>jersey-media-json-jackson</artifactId>
</dependency>
<dependency>
<groupId>org.gcube.data-catalogue</groupId>
<artifactId>gcat-client</artifactId>
<version>[2.0.0,3.0.0)</version>
</dependency>
<dependency>
<groupId>org.gcube.portlets.user</groupId>
<artifactId>uri-resolver-manager</artifactId>
<version>[1.5.0-SNAPSHOT,2.0.0)</version>
</dependency>
<dependency>
<groupId>org.projectlombok</groupId>
<artifactId>lombok</artifactId>

@ -11,7 +11,8 @@ public class Constants {
// ENVIRONMENT EXPECTED PARAMETERS
public static final String GUI_BASE_URL=ENVIRONMENT_PROPERTIES_BASE+"GUI_BASE_URL";
public static final String GATEWAY_NAME=ENVIRONMENT_PROPERTIES_BASE+"GATEWAY_NAME";
public static final String DEFAULT_AUTHOR=ENVIRONMENT_PROPERTIES_BASE+"DEFAULT_AUTHOR";
public static final String DEFAULT_MAINTAINER=ENVIRONMENT_PROPERTIES_BASE+"DEFAULT_MAINTAINER";

@ -1,14 +1,18 @@
package org.gcube.data.publishing.gCatFeeder.collectors.dm;
import java.util.Collections;
import java.util.HashSet;
import java.util.List;
import java.util.Map;
import java.util.Set;
import java.time.LocalDateTime;
import java.time.Month;
import java.time.ZoneId;
import java.time.chrono.IsoChronology;
import java.time.format.DateTimeFormatter;
import java.time.format.DateTimeFormatterBuilder;
import java.time.format.ResolverStyle;
import java.time.temporal.ChronoField;
import java.util.*;
import java.util.regex.Matcher;
import java.util.regex.Pattern;
import org.gcube.common.resources.gcore.ServiceEndpoint;
import org.gcube.data.analysis.dataminermanagercl.server.DataMinerService;
import org.gcube.data.analysis.dataminermanagercl.server.dmservice.SClient;
import org.gcube.data.analysis.dataminermanagercl.shared.process.Operator;
@ -23,16 +27,49 @@ import org.gcube.data.publishing.gCatfeeder.collectors.DataCollector;
import org.gcube.data.publishing.gCatfeeder.collectors.model.faults.CollectorFault;
import lombok.extern.slf4j.Slf4j;
import org.gcube.portlets.user.uriresolvermanager.exception.IllegalArgumentException;
import org.gcube.portlets.user.uriresolvermanager.exception.UriResolverMapException;
@Slf4j
public class DMAlgorithmsInfoCollector implements DataCollector<InternalAlgorithmDescriptor> {
private static final Pattern p = Pattern.compile("\\{Published by (.*)\\((.*(\\.)?.*\\)).*\\}$");
/*
* i.e. "Basic statistic max min average {Published by Giancarlo Panichi (giancarlo.panichi) on 2018/07/20 10:24 GMT}"
*/
private static final Pattern descriptionPattern = Pattern.compile("\\{Published by (.*)\\((.*(\\.)?.*\\)) on (.*)\\}$");
static final DateTimeFormatter versionDateParser= DateTimeFormatter.ofPattern("uuuu/MM/dd HH:mm 'GMT'[Z]")
.withResolverStyle(ResolverStyle.STRICT)
.withLocale(Locale.getDefault())
.withZone(ZoneId.systemDefault());
/* static final DateTimeFormatter versionDateParser=new DateTimeFormatterBuilder()
.parseCaseInsensitive().parseLenient()
.appendValue(ChronoField.YEAR,4)
.appendLiteral('/')
.appendValue(ChronoField.MONTH_OF_YEAR,2)
.appendLiteral('/')
.appendValue(ChronoField.DAY_OF_MONTH,2)
.appendLiteral(' ')
.appendValue(ChronoField.HOUR_OF_DAY,2)
.appendLiteral(':')
.appendValue(ChronoField.MINUTE_OF_HOUR,2)
.appendLiteral(' ')
.appendOffset("+HHMM", "GMT")
.toFormatter().withChronology(IsoChronology.INSTANCE)
.withResolverStyle(ResolverStyle.SMART); */
private Map<String,String> env=null;
public void setEnvironmentConfiguration(EnvironmentConfiguration envConfig) {
if(envConfig!=null) {
log.debug("Current Environment Configuration is : "+envConfig.getCurrentConfiguration());
@ -74,7 +111,7 @@ public class DMAlgorithmsInfoCollector implements DataCollector<InternalAlgorith
String categoryID=cat.getId();
String categoryName=cat.getName();
desc.setCategoryBriefDescription(categoryBriefDescription);
desc.setCategoryID(categoryID);
desc.setCategoryName(categoryName);
@ -83,7 +120,7 @@ public class DMAlgorithmsInfoCollector implements DataCollector<InternalAlgorith
// Operator info
String opBriefDescription=op.getBriefDescription();
String opDescription=op.getDescription();
String opID=op.getId();
@ -99,7 +136,20 @@ public class DMAlgorithmsInfoCollector implements DataCollector<InternalAlgorith
desc.setAuthor(parseUser(getAuthor(opDescription)));
desc.setMaintainer(parseUser(getAuthor(opDescription)));
desc.setVersion(parseDescriptionForDate(opDescription));
// Try to use version as creation time
LocalDateTime toSetCreationDate=null;
try{
toSetCreationDate=LocalDateTime.parse(desc.getVersion(),versionDateParser);
}catch(Throwable t){
log.debug("Version {} is not a date. Using 1900-01-01 as Creation date..",desc.getVersion());
toSetCreationDate = LocalDateTime.of(1900, Month.JANUARY,1,0,0);
}
desc.setCreationDate(toSetCreationDate);
// Parameters info
for(org.gcube.data.analysis.dataminermanagercl.shared.parameters.Parameter param:client.getInputParameters(op)) {
@ -132,11 +182,17 @@ public class DMAlgorithmsInfoCollector implements DataCollector<InternalAlgorith
if(guiBasePath!=null)
desc.setGuiLink(getGUIBasePath()+"?"+
DataMinerCollectorProperties.getProperty(DataMinerCollectorProperties.GUI_PARAM_NAME)+"="+opID);
desc.setGatewayName(env.get(Constants.GATEWAY_NAME));
if(wpsbaseUrl!=null) {
desc.setWpsLink(wpsbaseUrl+"?Request=DescribeProcess&Version=1.0.0&Service=WPS"+"&Identifier="+opID);
}
desc.setPrivateFlag(Boolean.parseBoolean(env.get(Constants.PRIVATE)));
toReturn.add(desc);
@ -164,7 +220,7 @@ public class DMAlgorithmsInfoCollector implements DataCollector<InternalAlgorith
}
private String getAuthor(String algorithmDescription) {
String toReturn=parseDescription(algorithmDescription);
String toReturn=parseDescriptionForUser(algorithmDescription);
if(toReturn==null)
toReturn=env.get(Constants.DEFAULT_AUTHOR);
if(toReturn==null)
@ -173,35 +229,48 @@ public class DMAlgorithmsInfoCollector implements DataCollector<InternalAlgorith
}
private static final UserIdentity parseUser(String userString) {
String splitter=null;
if(userString.contains(" "))
splitter=" ";
else if (userString.contains(".")) splitter="\\.";
String[] splitted=userString.split(splitter);
return new UserIdentity(splitted[0], splitted[1], null, null);
static final UserIdentity parseUser(String userString) {
try{
String splitter=null;
if(userString.contains(" "))
splitter=" ";
else if (userString.contains(".")) splitter="\\.";
String[] splitted=userString.split(splitter);
return new UserIdentity(splitted[0], splitted[1], null, null);
}catch(NullPointerException e){
System.err.println("Error with userString "+userString);
e.printStackTrace(System.err);
throw e;
}
}
/*
* i.e. "Basic statistic max min average {Published by Giancarlo Panichi (giancarlo.panichi) on 2018/07/20 10:24 GMT}"
* e.g. "Basic statistic max min average {Published by Giancarlo Panichi (giancarlo.panichi) on 2018/07/20 10:24 GMT}"
*/
private static final String parseDescription(String description) {
Matcher m=p.matcher(description);
static final String parseDescriptionForUser(String description) {
Matcher m=descriptionPattern.matcher(description);
if(m.find())
return m.group(1); // group 0 == {...}, group 1 == Giancarlo Panichi, group 2 == giancarlo.panichi
else return null;
}
static final String parseDescriptionForDate(String description) {
Matcher m=descriptionPattern.matcher(description);
if(m.find())
return m.group(4); // group 0 == {...}, group 1 == Giancarlo Panichi, group 2 == giancarlo.panichi, group 4 == 2018/07/20 10:24 GMT
else return "n.d.";
}
private final String getWPSBasePath() {
static final String getWPSBasePath() {
try{
ServiceEndpoint se=ISUtils.queryForServiceEndpoints("DataAnalysis", "DataMiner").get(0);
return se.profile().accessPoints().iterator().next().address();
return ISUtils.queryForServiceEndpointsByName("DataAnalysis", "DataMiner").get(0).profile().
accessPoints().iterator().next().address();
}catch(Throwable t) {
log.warn("Unable to find DM proxy. No WPS URL will be provided",t);
return null;
}
}
}

@ -8,7 +8,9 @@ public class DataMinerCollectorProperties {
public static final String DEFAULT_AUTHOR="default_author";
public static final String GUI_PARAM_NAME="gui_param_name";
public static final String CKAN_RESOURCE_TYPE="ckan_resource_type";

@ -13,7 +13,7 @@ public class GCATTransformer implements DataTransformer<GCatModel,InternalAlgori
@Override
public Set<GCatModel> transform(Collection<InternalAlgorithmDescriptor> collectedData) {
HashSet<GCatModel> toReturn=new HashSet<>();
boolean specifyProfile=true;
boolean specifyProfile=false; //never
for(InternalAlgorithmDescriptor desc:collectedData) {
toReturn.add(desc.asCKANModel(specifyProfile));
specifyProfile=false; //only once

@ -0,0 +1,123 @@
package org.gcube.data.publishing.gCatFeeder.collectors.dm;
import java.io.BufferedReader;
import java.io.IOException;
import java.io.InputStream;
import java.io.InputStreamReader;
import java.util.HashMap;
import java.util.Map;
import org.gcube.com.fasterxml.jackson.databind.ObjectMapper;
import org.gcube.data.publishing.gCatFeeder.utils.ContextUtils;
import org.gcube.portlets.user.uriresolvermanager.UriResolverManager;
import org.gcube.portlets.user.uriresolvermanager.exception.IllegalArgumentException;
import org.gcube.portlets.user.uriresolvermanager.exception.UriResolverMapException;
public class URIResolver {
private static final String CTLG_RESOLVER_NAME="CTLG";
// private static final String CATALOGUE_CONTEXT = "gcube_scope";
private static final String ENTITY_CONTEXT = "entity_context";
private static final String ENTITY_NAME = "entity_name";
private static final String DATASET = "dataset";
protected ObjectMapper mapper;
public URIResolver() {
this.mapper = new ObjectMapper();
}
protected StringBuilder getStringBuilder(InputStream inputStream) throws IOException {
StringBuilder result = new StringBuilder();
try(BufferedReader reader = new BufferedReader(new InputStreamReader(inputStream))) {
String line;
while((line = reader.readLine()) != null) {
result.append(line);
}
}
return result;
}
/*
{
"gcube_scope" : "/gcube/devsec/devVRE",
"entity_context" : "dataset",
"entity_name" : "sarda-sarda"
}
*/
public String getCatalogueItemURL(String name) throws UriResolverMapException, IllegalArgumentException {
UriResolverManager resolver = new UriResolverManager(CTLG_RESOLVER_NAME);
Map<String, String> params = new HashMap<String, String>();
params.put(ENTITY_NAME, name);
params.put(ENTITY_CONTEXT,DATASET);
params.put("gcube_scope", ContextUtils.getCurrentScope());
String shortLink = resolver.getLink(params, false);
return shortLink;
}
/*public String getCatalogueItemURL(String name) {
try {
String uriResolverURL = getConfigurationFromIS();
ObjectNode requestContent = mapper.createObjectNode();
requestContent.put(CATALOGUE_CONTEXT, ContextUtils.getCurrentScope());
requestContent.put(ENTITY_TYPE, DATASET);
requestContent.put(ENTITY_NAME, name);
GXHTTPStringRequest gxhttpStringRequest = GXHTTPStringRequest.newRequest(uriResolverURL);
gxhttpStringRequest.from(CTLG_RESOLVER_NAME);
gxhttpStringRequest.header(HttpHeaders.CONTENT_TYPE, MediaType.APPLICATION_JSON);
gxhttpStringRequest.isExternalCall(true);
String body = mapper.writeValueAsString(requestContent);
HttpURLConnection httpURLConnection = gxhttpStringRequest.post(body);
if(httpURLConnection.getResponseCode() != 200) {
try{
IOUtils.copy(httpURLConnection.getInputStream(),System.out);
}catch(Throwable t){
System.out.println("No message");
}
throw new InternalServerErrorException("Unable to get Item URL via URI Resolver. Code : "+
httpURLConnection.getResponseCode());
}
String url = getStringBuilder(httpURLConnection.getInputStream()).toString();
return url;
} catch(WebApplicationException e) {
throw e;
} catch(Exception e) {
throw new WebApplicationException(e);
}
}*/
/*
static String getConfigurationFromIS() {
try {
StringBuilder toReturn=new StringBuilder();
ServiceEndpoint serviceEndpoint = ISUtils.queryForServiceEndpointsByName("Service","HTTP-URI-Resolver").get(0);
serviceEndpoint.profile().accessPoints().
forEach(a->{
if(a.name().equals(CTLG_RESOLVER_NAME))
toReturn.append(a.address());
});
if(toReturn.length()>0) return toReturn.toString();
else throw new Exception("Access point for "+CTLG_RESOLVER_NAME+" not found ");
} catch(WebApplicationException e) {
throw e;
} catch(Exception e) {
throw new InternalServerErrorException("Error while getting configuration on IS", e);
}
}
*/
}

@ -1,5 +1,6 @@
package org.gcube.data.publishing.gCatFeeder.collectors.dm.model;
import java.time.LocalDateTime;
import java.util.ArrayList;
import java.util.HashSet;
import java.util.List;
@ -25,7 +26,10 @@ public class InternalAlgorithmDescriptor implements CustomData {
private UserIdentity author;
private UserIdentity maintainer;
private String version;
private LocalDateTime creationDate;
//category info
private String categoryBriefDescription;
@ -38,8 +42,10 @@ public class InternalAlgorithmDescriptor implements CustomData {
private Set<Parameter> outputParameters=new HashSet<>();
private String guiLink;
private String gatewayName;
private String wpsLink;
private Boolean privateFlag;

@ -2,9 +2,14 @@ package org.gcube.data.publishing.gCatFeeder.collectors.dm.model.ckan;
import java.io.ByteArrayOutputStream;
import java.net.URL;
import java.text.SimpleDateFormat;
import java.time.LocalDateTime;
import java.time.format.DateTimeFormatter;
import java.time.format.DateTimeFormatterBuilder;
import java.util.ArrayList;
import org.gcube.data.publishing.gCatFeeder.collectors.dm.DataMinerCollectorProperties;
import org.gcube.data.publishing.gCatFeeder.collectors.dm.URIResolver;
import org.gcube.data.publishing.gCatFeeder.collectors.dm.model.InternalAlgorithmDescriptor;
import org.gcube.data.publishing.gCatFeeder.collectors.dm.model.Parameter;
import org.gcube.data.publishing.gCatFeeder.collectors.dm.model.UserIdentity;
@ -25,6 +30,9 @@ import lombok.extern.slf4j.Slf4j;
@Slf4j
public class GCatModel implements CatalogueFormatData {
private static final DateTimeFormatter dateFormatter=DateTimeFormatter.ISO_DATE;
private static ObjectMapper mapper=new ObjectMapper();
private static String profileXML=null;
@ -35,13 +43,29 @@ public class GCatModel implements CatalogueFormatData {
profileXML=toSet;
}
public static String getItemUrl(String name) {
try{
URIResolver uriResolver = new URIResolver();
log.debug("Evaluating item url for {}",name);
String catalogueItemURL = uriResolver.getCatalogueItemURL(name);
log.info("Item URL for {} is {}",name,catalogueItemURL);
return catalogueItemURL;
}catch(Exception e){
log.warn("Unable to evaluate item URL for "+name,e);
return null;
}
}
public GCatModel(InternalAlgorithmDescriptor desc) {
item=new CkanItem();
// item.setAuthor(desc.getAuthor());
item.setAuthor(desc.getAuthor().getFirstName()+" "+desc.getAuthor().getLastName());
item.setTitle(desc.getName()+" in "+ContextUtils.getCurrentScopeName());
item.setLicense_id("CC-BY-NC-SA-4.0");
// item.setMaintainer(desc.getMaintainer());
item.setMaintainer(desc.getMaintainer().getFirstName()+" "+desc.getMaintainer().getLastName());
item.setName(item.getTitle().toLowerCase().toLowerCase().replaceAll(" ", "_"));
for(String tag:desc.getTags()) {
item.getTags().add(new CkanItem.Tag(fixTag(tag)));
@ -54,21 +78,53 @@ public class GCatModel implements CatalogueFormatData {
item.setPrivateFlag(desc.getPrivateFlag());
for(Parameter param: desc.getInputParameters())
item.getExtras().add(new CKanExtraField(profileID+":Input Parameter",
String.format("%1$s [%2$s] %3$s : %4$s",
item.getExtras().add(new CKanExtraField("TechnicalDetails:input",
String.format("%1$s [%2$s] %3$s : %4$s",
param.getName(),param.getType(),
((param.getValue()!=null&&!param.getValue().isEmpty())?"default : "+param.getValue():""),
param.getDescription())));
for(Parameter param: desc.getOutputParameters())
item.getExtras().add(new CKanExtraField(profileID+":Output Parameter",
String.format("%1$s [%2$s] %3$s : %4$s",
item.getExtras().add(new CKanExtraField("TechnicalDetails:output",
String.format("%1$s [%2$s] %3$s : %4$s",
param.getName(),param.getType(),
((param.getValue()!=null&&!param.getValue().isEmpty())?"default : "+param.getValue():""),
param.getDescription())));
item.getExtras().add(new CKanExtraField("Identity:Creator", desc.getAuthor().asStringValue()));
item.getExtras().add(new CKanExtraField("Identity:CreationDate", dateFormatter.format(desc.getCreationDate())));
item.getExtras().add(new CKanExtraField("AccessMode:UsageMode", "as-a-Service via Blue-Cloud Infrastructure"));
item.getExtras().add(new CKanExtraField("AccessMode:Availability", "On-Line"));
item.getExtras().add(new CKanExtraField("TechnicalDetails:Hosting Environment", "gCube SmartGear"));
item.getExtras().add(new CKanExtraField("TechnicalDetails:Dependencies on Other SW", "gCube DataMiner"));
item.getExtras().add(new CKanExtraField("Rights:Field/Scope of use", "Any use"));
item.getExtras().add(new CKanExtraField("Rights:Basic rights", "Communication"));
item.getExtras().add(new CKanExtraField("Rights:Basic rights", "Making available to the public"));
item.getExtras().add(new CKanExtraField("Rights:Basic rights", "Distribution"));
item.getExtras().add(new CKanExtraField("Attribution:Attribution requirements",
String.format("Cite as: %1$s (%2$d): %3$s. %4$s. %5$s. %6$s. %7$s. Retrieved from the %8$s (%9$s) operated by D4Science.org www.d4science.org",
desc.getAuthor().asStringValue(),
LocalDateTime.now().getYear(),
desc.getName(),
desc.getVersion(),
"Blue-Cloud",
"DataMiner Process",
getItemUrl(item.getName()),
desc.getGatewayName(),
desc.getGuiLink())));
//Algorithm Description
// item.getExtras().add(new CKanExtraField(profileID+":Process Description", desc.getDescription()));
@ -77,8 +133,8 @@ public class GCatModel implements CatalogueFormatData {
// Algorithm Users
item.getExtras().add(new CKanExtraField(profileID+":Process Author",desc.getAuthor().asStringValue()));
item.getExtras().add(new CKanExtraField(profileID+":Process Maintainer",desc.getAuthor().asStringValue()));
//item.getExtras().add(new CKanExtraField(profileID+":Process Author",desc.getAuthor().asStringValue()));
//item.getExtras().add(new CKanExtraField(profileID+":Process Maintainer",desc.getAuthor().asStringValue()));
if(desc.getGuiLink()!=null) {
try {
@ -112,23 +168,6 @@ public class GCatModel implements CatalogueFormatData {
}
/**
* (Common) Title
* (Common) Description
* (Common) Tags: free list of keywords
* (Common) License
* (Common) Visibility: either public or private
* (Common) Version
* (Common) Author: the creator of metadata. Only one occurrence is supported;
* (Common) Maintainer:
* (Method specific) Creator: the author of the method (with email and ORCID). Repeatable field;
* (Method specific) Creation date: when the method has been released;
* (Method specific) Input: Repeatable field;
* (Method specific) Output: Repeatable field;
* (Method specific) RelatedPaper: a reference to an associated paper;
* (Method specific) Restrictions On Use: an optional text
* (Method specific) Attribution requirements: the text to use to acknowledge method usage;
*/
static final String fixTag(String toFix) {

@ -1,3 +1,3 @@
default_author=Gianpaolo Coro
default_author=Gianpaolo.Coro
gui_param_name=OperatorId
ckan_resource_type=DataMiner Process
ckan_resource_type=Method

@ -1,41 +1,196 @@
<metadataformat type="DataMiner Process">
<metadatafield categoryref="DataMiner Process">
<fieldName>Input Parameter</fieldName>
<metadataformat type="Method">
<metadatafield categoryref="Identity">
<fieldName>External Identifier</fieldName>
<mandatory>false</mandatory>
<dataType>String</dataType>
<note>Input parameter expected for the execution of the process</note>
</metadatafield>
<metadatafield categoryref="DataMiner Process">
<fieldName>Output Parameter</fieldName>
<maxOccurs>*</maxOccurs>
<note>This applies only to methods that have been already published. Insert here a DOI, an handle, and any other Identifier assigned when publishing the dataset alsewhere.</note>
</metadatafield>
<metadatafield categoryref="Identity">
<fieldName>Creator</fieldName>
<mandatory>true</mandatory>
<dataType>String</dataType>
<maxOccurs>*</maxOccurs>
<note>The name of the creator, with email and ORCID. The format should be: family, given[, email][, ORCID]. Example: Smith, John, js@acme.org, orcid.org/0000-0002-1825-0097</note>
<validator>
<regularExpression>^[a-zA-ZÀ-ÿ .'-]+, [a-zA-ZÀ-ÿ .'-]+[, ]*([a-zA-Z0-9_!#$%*+=?`{|}~^.-]+@[a-zA-Z0-9À-ÿ.-]+)?[, ]*(orcid.org\/0000-000(1-[5-9]|2-[0-9]|3-[0-4])\d\d\d-\d\d\d[\dX])?$</regularExpression>
</validator>
</metadatafield>
<metadatafield categoryref="Identity">
<fieldName>CreationDate</fieldName>
<mandatory>true</mandatory>
<dataType>Time</dataType>
<maxOccurs>1</maxOccurs>
<note>The date of creation of the dataset (different from the date of registration of the dataset automatically added by the system). Use ISO 8601 Date Format: YYYY-MM-DD[ HH:MM] Ex. 1998-11-10 or 2015-05-29 11:55</note>
<validator>
<regularExpression>^(\d{4}\-(0?[1-9]|1[012])\-(0?[1-9]|[12][0-9]|3[01]))+([ ]+(\d{2}(:?\d{2})?)?)?$</regularExpression>
</validator>
</metadatafield>
<metadatafield categoryref="Identity">
<fieldName>Owner</fieldName>
<mandatory>false</mandatory>
<dataType>String</dataType>
<note>Output parameter expected from the execution of the process
</note>
<maxOccurs>*</maxOccurs>
<note>The owner of the method (free text).</note>
</metadatafield>
<metadatafield categoryref="DataMiner Process">
<fieldName>Process Author</fieldName>
<metadatafield categoryref="Identity">
<fieldName>RelatedPaper</fieldName>
<mandatory>false</mandatory>
<dataType>String</dataType>
<maxOccurs>1</maxOccurs>
<note>Insert a complete reference to an associated work.</note>
</metadatafield>
<metadatafield categoryref="Coverage">
<fieldName>Semantic Coverage</fieldName>
<mandatory>false</mandatory>
<dataType>String</dataType>
<maxOccurs>*</maxOccurs>
<defaultValue />
<note>The name of the author, with email and ORCID. The format should
be: family, given[, email][, ORCID]. Example: Smith, John,
js@acme.org, orcid.org/0000-0002-1825-0097</note>
<validator>
<regularExpression>^[a-zA-ZÀ-ÿ .'-]+, [a-zA-ZÀ-ÿ .'-]+[,]*([a-zA-Z0-9_!#$%*+=?`{|}~^.-]+@[a-zA-Z0-9À-ÿ.-]+)?[,]*(orcid.org\/0000-000(1-[5-9]|2-[0-9]|3-[0-4])\d\d\d-\d\d\d[\dX])?$</regularExpression>
</validator>
<note>Tagging e.g. Functional analysis, Environment analysis and visualisation, ...</note>
</metadatafield>
<metadatafield categoryref="AccessMode">
<fieldName>UsageMode</fieldName>
<mandatory>true</mandatory>
<dataType>String</dataType>
<maxOccurs>1</maxOccurs>
<note>How the method is expected to be exploited.</note>
<vocabulary isMultiSelection="true">
<vocabularyField>Download</vocabularyField>
<vocabularyField>as-a-Application via Blue-Cloud Infrastructure</vocabularyField>
<vocabularyField>as-a-Application via third-party Infrastructure</vocabularyField>
<vocabularyField>as-a-Service via Blue-Cloud Infrastructure</vocabularyField>
<vocabularyField>as-a-Service via third-party Infrastructure</vocabularyField>
</vocabulary>
</metadatafield>
<metadatafield categoryref="AccessMode">
<fieldName>Availability</fieldName>
<mandatory>false</mandatory>
<dataType>String</dataType>
<maxOccurs>1</maxOccurs>
<note>How the availability to the resource is offered. On-line means that the method can be executed through the Virtual Laboratory Gateway. On-site means that the method can only be executed by visiting the hosting provider.</note>
<vocabulary>
<vocabularyField>On-Line</vocabularyField>
<vocabularyField>On-Site</vocabularyField>
</vocabulary>
</metadatafield>
<metadatafield categoryref="DataMiner Process">
<fieldName>Process Maintainer</fieldName>
<metadatafield categoryref="TechnicalDetails">
<fieldName>Hosting Environment</fieldName>
<mandatory>false</mandatory>
<dataType>String</dataType>
<maxOccurs>1</maxOccurs>
<note>E.g. Linux, Microsoft Azure, Amazon EC2</note>
</metadatafield>
<metadatafield categoryref="TechnicalDetails">
<fieldName>ProgrammingLanguage</fieldName>
<mandatory>false</mandatory>
<dataType>String</dataType>
<maxOccurs>1</maxOccurs>
<note>The primary language used to implement the method. </note>
</metadatafield>
<metadatafield categoryref="TechnicalDetails">
<fieldName>Dependencies on Other SW</fieldName>
<mandatory>false</mandatory>
<dataType>String</dataType>
<maxOccurs>*</maxOccurs>
<defaultValue />
<note>The name of the author, with email and ORCID. The format should
be: family, given[, email][, ORCID]. Example: Smith, John,
js@acme.org, orcid.org/0000-0002-1825-0097</note>
<note>E.g. this sowftware requires an Hadoop cluster to run</note>
</metadatafield>
<metadatafield categoryref="TechnicalDetails">
<fieldName>input</fieldName>
<mandatory>false</mandatory>
<dataType>String</dataType>
<maxOccurs>*</maxOccurs>
<note>inputParametersType. See WPS specifications</note>
</metadatafield>
<metadatafield categoryref="TechnicalDetails">
<fieldName>output</fieldName>
<mandatory>false</mandatory>
<dataType>String</dataType>
<maxOccurs>*</maxOccurs>
<note>outputType. See WPS specifications </note>
</metadatafield>
<metadatafield categoryref="Rights">
<fieldName>IP/Copyrights</fieldName>
<mandatory>false</mandatory>
<dataType>String</dataType>
<maxOccurs>1</maxOccurs>
<note>Whether software is covered by any rights: copyright, related rights, know how, proprietary, etc.</note>
</metadatafield>
<metadatafield categoryref="Rights">
<fieldName>Field/Scope of use</fieldName>
<mandatory>true</mandatory>
<dataType>String</dataType>
<maxOccurs>1</maxOccurs>
<vocabulary isMultiSelection="true">
<vocabularyField>Any use</vocabularyField>
<vocabularyField>Non-commercial only</vocabularyField>
<vocabularyField>Research only</vocabularyField>
<vocabularyField>Non-commercial research only</vocabularyField>
<vocabularyField>Private use</vocabularyField>
<vocabularyField>Use for developing and providing a service</vocabularyField>
</vocabulary>
</metadatafield>
<metadatafield categoryref="Rights">
<fieldName>Basic rights</fieldName>
<mandatory>true</mandatory>
<dataType>String</dataType>
<maxOccurs>1</maxOccurs>
<vocabulary isMultiSelection="true">
<vocabularyField>Temporary download of a single copy only</vocabularyField>
<vocabularyField>Download</vocabularyField>
<vocabularyField>Copying</vocabularyField>
<vocabularyField>Distribution</vocabularyField>
<vocabularyField>Modification</vocabularyField>
<vocabularyField>Communication</vocabularyField>
<vocabularyField>Making available to the public</vocabularyField>
<vocabularyField>Other rights</vocabularyField>
</vocabulary>
</metadatafield>
<metadatafield categoryref="Rights">
<fieldName>Restrictions on use</fieldName>
<mandatory>false</mandatory>
<dataType>String</dataType>
<maxOccurs>1</maxOccurs>
<note>Any restrictions on how where the dataset may be used </note>
</metadatafield>
<metadatafield categoryref="Rights">
<fieldName>Sublicense rights</fieldName>
<mandatory>false</mandatory>
<dataType>String</dataType>
<maxOccurs>1</maxOccurs>
<note>Any restrictions on how where the dataset may be used</note>
<vocabulary>
<vocabularyField>No</vocabularyField>
<vocabularyField>Yes</vocabularyField>
</vocabulary>
</metadatafield>
<metadatafield categoryref="Rights">
<fieldName>Requirement of non-disclosure (confidentiality mark)</fieldName>
<mandatory>false</mandatory>
<dataType>String</dataType>
<maxOccurs>1</maxOccurs>
<note>Requirement of non-disclosure (confidentiality mark). Whether the dataset bears confidentiality mark/may be used and shared subject to the obligation of non-disclosure</note>
</metadatafield>
<metadatafield categoryref="Rights">
<fieldName>Embargo period</fieldName>
<mandatory>false</mandatory>
<dataType>Time_Interval</dataType>
<maxOccurs>1</maxOccurs>
<note>Period of time during which the resource may be used. Use ISO 8601 Date Format: YYYY-MM-DD[ HH:MM] Ex. 2016-07-31 or 2015-05-10 12:00</note>
<validator>
<regularExpression>^[a-zA-ZÀ-ÿ .'-]+, [a-zA-ZÀ-ÿ .'-]+[,]*([a-zA-Z0-9_!#$%*+=?`{|}~^.-]+@[a-zA-Z0-9À-ÿ.-]+)?[,]*(orcid.org\/0000-000(1-[5-9]|2-[0-9]|3-[0-4])\d\d\d-\d\d\d[\dX])?$</regularExpression>
<regularExpression>^(\d{4}\-(0?[1-9]|1[012])\-(0?[1-9]|[12][0-9]|3[01]))+([ ]+(\d{2}(:?\d{2})?)?)?$</regularExpression>
</validator>
</metadatafield>
<metadatafield categoryref="Attribution">
<fieldName>Attribution requirements</fieldName>
<mandatory>false</mandatory>
<dataType>String</dataType>
<maxOccurs>1</maxOccurs>
<note>The text to acknowledge the resource when using it</note>
</metadatafield>
<metadatafield categoryref="Attribution">
<fieldName>Distribution requirements</fieldName>
<mandatory>false</mandatory>
<dataType>String</dataType>
<maxOccurs>1</maxOccurs>
<note>The text to acknowledge the resource when distributing it</note>
</metadatafield>
</metadataformat>

@ -0,0 +1,19 @@
package org.gcube.data.publishing.gCatFeeder.collectors.dm;
import org.gcube.common.authorization.library.provider.SecurityTokenProvider;
import org.gcube.data.publishing.gCatFeeder.tests.BaseCollectorTest;
import org.gcube.data.publishing.gCatFeeder.tests.TokenSetter;
import org.gcube.portlets.user.uriresolvermanager.exception.IllegalArgumentException;
import org.gcube.portlets.user.uriresolvermanager.exception.UriResolverMapException;
import org.junit.Test;
public class ItemUrlTests extends BaseCollectorTest {
@Test
public void getItemURL() throws UriResolverMapException, IllegalArgumentException {
//SecurityTokenProvider.instance.set("934d4d59-1c09-490f-96c0-58eeb24586f6-843339462");
TokenSetter.set("/gcube/devsec/devVRE");
String name = "fake";
System.out.println(new URIResolver().getCatalogueItemURL(name));
}
}

@ -1,13 +1,18 @@
package org.gcube.data.publishing.gCatFeeder.collectors.dm;
import java.io.IOException;
import java.time.LocalDateTime;
import java.time.ZonedDateTime;
import java.util.Collection;
import java.util.Set;
import org.gcube.common.authorization.library.provider.SecurityTokenProvider;
import org.gcube.data.publishing.gCatFeeder.collectors.dm.model.InternalAlgorithmDescriptor;
import org.gcube.data.publishing.gCatFeeder.collectors.dm.model.ckan.GCatModel;
import org.gcube.data.publishing.gCatFeeder.model.CatalogueFormatData;
import org.gcube.data.publishing.gCatFeeder.model.InternalConversionException;
import org.gcube.data.publishing.gCatFeeder.tests.BaseCollectorTest;
import org.gcube.data.publishing.gCatFeeder.tests.TokenSetter;
import org.gcube.data.publishing.gCatfeeder.collectors.CollectorPlugin;
import org.gcube.data.publishing.gCatfeeder.collectors.DataCollector;
import org.gcube.data.publishing.gCatfeeder.collectors.DataTransformer;
@ -20,6 +25,8 @@ import com.fasterxml.jackson.core.JsonGenerationException;
import com.fasterxml.jackson.databind.JsonMappingException;
import com.fasterxml.jackson.databind.ObjectMapper;
import static org.junit.Assert.*;
public class TranslationTest extends BaseCollectorTest{
@ -38,12 +45,38 @@ public class TranslationTest extends BaseCollectorTest{
System.out.println(mapper.writeValueAsString(obj)+"\n");
for(String destinationcatalogue : (Set<String>)plugin.getSupportedCatalogueTypes()) {
DataTransformer<? extends CatalogueFormatData, InternalAlgorithmDescriptor> transformer=plugin.getTransformerByCatalogueType(destinationcatalogue);
DataTransformer<? extends CatalogueFormatData, InternalAlgorithmDescriptor> transformer=
plugin.getTransformerByCatalogueType(destinationcatalogue);
System.out.println("Starting Transformation "+transformer.toString());
for(Object data:transformer.transform(collected))
System.out.println(((CatalogueFormatData)data).toCatalogueFormat());
}
}
@Test
public void testParseDescription(){
String s="balablabalba";
assertEquals("n/a",DMAlgorithmsInfoCollector.parseDescriptionForDate(s));
assertEquals(null, DMAlgorithmsInfoCollector.parseDescriptionForUser(s));
s="Basic statistic max min average {Published by Giancarlo Panichi (giancarlo.panichi) on 2018/07/20 10:24 GMT}";
assertEquals("2018/07/20 10:24 GMT",DMAlgorithmsInfoCollector.parseDescriptionForDate(s));
assertEquals("Giancarlo Panichi ",DMAlgorithmsInfoCollector.parseDescriptionForUser(s));
System.out.println(DMAlgorithmsInfoCollector.versionDateParser.format(ZonedDateTime.now()));
System.out.println(DMAlgorithmsInfoCollector.versionDateParser.parse(DMAlgorithmsInfoCollector.parseDescriptionForDate(s)));
}
@Test
public void testEnvironment(){
Assume.assumeTrue(isTestInfrastructureEnabled());
//assertNotNull(DMAlgorithmsInfoCollector.getWPSBasePath());
//assertNotNull(GCatModel.getItemUrl("fake"));
System.out.println(getEnvironmentConfiguration().getCurrentConfiguration());
}
}

@ -10,6 +10,7 @@ import org.gcube.data.publishing.gCatFeeder.model.CatalogueFormatData;
import org.gcube.data.publishing.gCatFeeder.model.CatalogueInstanceDescriptor;
import org.gcube.data.publishing.gCatFeeder.model.InternalConversionException;
import org.gcube.data.publishing.gCatFeeder.tests.BaseCataloguePluginTest;
import org.gcube.data.publishing.gCatFeeder.tests.TokenSetter;
import org.gcube.data.publishing.gCataFeeder.catalogues.gCat.GCatPlugin;
import org.junit.Assert;
import org.junit.Assume;

@ -8,7 +8,7 @@
</encoder>
</appender>
<logger name="org.gcube" level="DEBUG"/>
<logger name="org.gcube.data" level="DEBUG"/>
<root level="WARN">
<appender-ref ref="STDOUT" />

Loading…
Cancel
Save