diff --git a/CODE_OF_CONDUCT.md b/CODE_OF_CONDUCT.md new file mode 100644 index 000000000..aff151f94 --- /dev/null +++ b/CODE_OF_CONDUCT.md @@ -0,0 +1,43 @@ +# Contributor Code of Conduct + +Openness, transparency and our community-driven participatory approach guide us in our day-to-day interactions and decision-making. Our open source projects are no exception. Trust, respect, collaboration and transparency are core values we believe should live and breathe within our projects. Our community welcomes participants from around the world with different experiences, unique perspectives, and great ideas to share. + +## Our Pledge + +In the interest of fostering an open and welcoming environment, we as contributors and maintainers pledge to making participation in our project and our community a harassment-free experience for everyone, regardless of age, body size, disability, ethnicity, sex characteristics, gender identity and expression, level of experience, education, socio-economic status, nationality, personal appearance, race, religion, or sexual identity and orientation. + +## Our Standards + +Examples of behavior that contributes to creating a positive environment include: + +- Using welcoming and inclusive language +- Being respectful of differing viewpoints and experiences +- Gracefully accepting constructive criticism +- Attempting collaboration before conflict +- Focusing on what is best for the community +- Showing empathy towards other community members + +Examples of unacceptable behavior by participants include: + +- Violence, threats of violence, or inciting others to commit self-harm +- The use of sexualized language or imagery and unwelcome sexual attention or advances +- Trolling, intentionally spreading misinformation, insulting/derogatory comments, and personal or political attacks +- Public or private harassment +- Publishing others' private information, such as a physical or electronic address, without explicit permission +- Abuse of the reporting process to intentionally harass or exclude others +- Advocating for, or encouraging, any of the above behavior +- Other conduct which could reasonably be considered inappropriate in a professional setting + +## Our Responsibilities + +Project maintainers are responsible for clarifying the standards of acceptable behavior and are expected to take appropriate and fair corrective action in response to any instances of unacceptable behavior. + +Project maintainers have the right and responsibility to remove, edit, or reject comments, commits, code, wiki edits, issues, and other contributions that are not aligned to this Code of Conduct, or to ban temporarily or permanently any contributor for other behaviors that they deem inappropriate, threatening, offensive, or harmful. + +## Scope + +This Code of Conduct applies both within project spaces and in public spaces when an individual is representing the project or its community. Examples of representing a project or community include using an official project e-mail address, posting via an official social media account, or acting as an appointed representative at an online or offline event. Representation of a project may be further defined and clarified by project maintainers. + +## Attribution + +This Code of Conduct is adapted from the [Contributor Covenant](https://www.contributor-covenant.org/), [version 1.4](https://www.contributor-covenant.org/version/1/4/code-of-conduct.html). \ No newline at end of file diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md new file mode 100644 index 000000000..13a359c86 --- /dev/null +++ b/CONTRIBUTING.md @@ -0,0 +1,10 @@ +# Contributing to D-Net Hadoop + +:+1::tada: First off, thanks for taking the time to contribute! :tada::+1: + +This project and everyone participating in it is governed by our [Code of Conduct](CODE_OF_CONDUCT.md). By participating, you are expected to uphold this code. Please report unacceptable behavior to [dnet-team@isti.cnr.it](mailto:dnet-team@isti.cnr.it). + +The following is a set of guidelines for contributing to this project and its packages. These are mostly guidelines, not rules, which applies to this project as a while, including all its sub-modules. +Use your best judgment, and feel free to propose changes to this document in a pull request. + +All contributions are welcome, all contributions will be considered to be contributed under the [project license](LICENSE.md). diff --git a/LICENSE b/LICENSE.md similarity index 100% rename from LICENSE rename to LICENSE.md diff --git a/README.md b/README.md index 2c1440f44..b6575814d 100644 --- a/README.md +++ b/README.md @@ -2,6 +2,11 @@ Dnet-hadoop is the project that defined all the [OOZIE workflows](https://oozie.apache.org/) for the OpenAIRE Graph construction, processing, provisioning. +This project adheres to the Contributor Covenant [code of conduct](CODE_OF_CONDUCT.md). +By participating, you are expected to uphold this code. Please report unacceptable behavior to [dnet-team@isti.cnr.it](mailto:dnet-team@isti.cnr.it). + +This project is licensed under the [AGPL v3 or later version](#LICENSE.md). + How to build, package and run oozie workflows ==================== diff --git a/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/CategorySummary.java b/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/CategorySummary.java new file mode 100644 index 000000000..fff28dbdf --- /dev/null +++ b/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/CategorySummary.java @@ -0,0 +1,39 @@ + +package eu.dnetlib.dhp.common.api.context; + +public class CategorySummary { + + private String id; + + private String label; + + private boolean hasConcept; + + public String getId() { + return id; + } + + public String getLabel() { + return label; + } + + public boolean isHasConcept() { + return hasConcept; + } + + public CategorySummary setId(final String id) { + this.id = id; + return this; + } + + public CategorySummary setLabel(final String label) { + this.label = label; + return this; + } + + public CategorySummary setHasConcept(final boolean hasConcept) { + this.hasConcept = hasConcept; + return this; + } + +} diff --git a/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/CategorySummaryList.java b/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/CategorySummaryList.java new file mode 100644 index 000000000..7213a945a --- /dev/null +++ b/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/CategorySummaryList.java @@ -0,0 +1,7 @@ + +package eu.dnetlib.dhp.common.api.context; + +import java.util.ArrayList; + +public class CategorySummaryList extends ArrayList { +} diff --git a/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/ConceptSummary.java b/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/ConceptSummary.java new file mode 100644 index 000000000..a576f9a1e --- /dev/null +++ b/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/ConceptSummary.java @@ -0,0 +1,52 @@ + +package eu.dnetlib.dhp.common.api.context; + +import java.util.List; + +public class ConceptSummary { + + private String id; + + private String label; + + public boolean hasSubConcept; + + private List concepts; + + public String getId() { + return id; + } + + public String getLabel() { + return label; + } + + public List getConcepts() { + return concepts; + } + + public ConceptSummary setId(final String id) { + this.id = id; + return this; + } + + public ConceptSummary setLabel(final String label) { + this.label = label; + return this; + } + + public boolean isHasSubConcept() { + return hasSubConcept; + } + + public ConceptSummary setHasSubConcept(final boolean hasSubConcept) { + this.hasSubConcept = hasSubConcept; + return this; + } + + public ConceptSummary setConcept(final List concepts) { + this.concepts = concepts; + return this; + } + +} diff --git a/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/ConceptSummaryList.java b/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/ConceptSummaryList.java new file mode 100644 index 000000000..45ccd2810 --- /dev/null +++ b/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/ConceptSummaryList.java @@ -0,0 +1,7 @@ + +package eu.dnetlib.dhp.common.api.context; + +import java.util.ArrayList; + +public class ConceptSummaryList extends ArrayList { +} diff --git a/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/ContextSummary.java b/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/ContextSummary.java new file mode 100644 index 000000000..46a0d0d5a --- /dev/null +++ b/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/ContextSummary.java @@ -0,0 +1,50 @@ + +package eu.dnetlib.dhp.common.api.context; + +public class ContextSummary { + + private String id; + + private String label; + + private String type; + + private String status; + + public String getId() { + return id; + } + + public String getLabel() { + return label; + } + + public String getType() { + return type; + } + + public String getStatus() { + return status; + } + + public ContextSummary setId(final String id) { + this.id = id; + return this; + } + + public ContextSummary setLabel(final String label) { + this.label = label; + return this; + } + + public ContextSummary setType(final String type) { + this.type = type; + return this; + } + + public ContextSummary setStatus(final String status) { + this.status = status; + return this; + } + +} diff --git a/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/ContextSummaryList.java b/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/ContextSummaryList.java new file mode 100644 index 000000000..618600007 --- /dev/null +++ b/dhp-common/src/main/java/eu/dnetlib/dhp/common/api/context/ContextSummaryList.java @@ -0,0 +1,7 @@ + +package eu.dnetlib.dhp.common.api.context; + +import java.util.ArrayList; + +public class ContextSummaryList extends ArrayList { +} diff --git a/dhp-common/src/main/java/eu/dnetlib/dhp/common/collection/HttpConnector2.java b/dhp-common/src/main/java/eu/dnetlib/dhp/common/collection/HttpConnector2.java index 905457bcd..342d73cdc 100644 --- a/dhp-common/src/main/java/eu/dnetlib/dhp/common/collection/HttpConnector2.java +++ b/dhp-common/src/main/java/eu/dnetlib/dhp/common/collection/HttpConnector2.java @@ -8,10 +8,13 @@ import java.io.InputStream; import java.net.*; import java.util.List; import java.util.Map; +import java.util.concurrent.TimeUnit; import org.apache.commons.io.IOUtils; import org.apache.commons.lang3.math.NumberUtils; +import org.apache.commons.lang3.time.DateUtils; import org.apache.http.HttpHeaders; +import org.joda.time.Instant; import org.slf4j.Logger; import org.slf4j.LoggerFactory; @@ -94,14 +97,16 @@ public class HttpConnector2 { throw new CollectorException(msg); } - log.info("Request attempt {} [{}]", retryNumber, requestUrl); - InputStream input = null; + long start = System.currentTimeMillis(); try { if (getClientParams().getRequestDelay() > 0) { backoffAndSleep(getClientParams().getRequestDelay()); } + + log.info("Request attempt {} [{}]", retryNumber, requestUrl); + final HttpURLConnection urlConn = (HttpURLConnection) new URL(requestUrl).openConnection(); urlConn.setInstanceFollowRedirects(false); urlConn.setReadTimeout(getClientParams().getReadTimeOut() * 1000); @@ -115,9 +120,8 @@ public class HttpConnector2 { urlConn.addRequestProperty(headerEntry.getKey(), headerEntry.getValue()); } } - if (log.isDebugEnabled()) { - logHeaderFields(urlConn); - } + + logHeaderFields(urlConn); int retryAfter = obtainRetryAfter(urlConn.getHeaderFields()); String rateLimit = urlConn.getHeaderField(Constants.HTTPHEADER_IETF_DRAFT_RATELIMIT_LIMIT); @@ -132,9 +136,7 @@ public class HttpConnector2 { } if (is2xx(urlConn.getResponseCode())) { - input = urlConn.getInputStream(); - responseType = urlConn.getContentType(); - return input; + return getInputStream(urlConn, start); } if (is3xx(urlConn.getResponseCode())) { // REDIRECTS @@ -144,6 +146,7 @@ public class HttpConnector2 { .put( REPORT_PREFIX + urlConn.getResponseCode(), String.format("Moved to: %s", newUrl)); + logRequestTime(start); urlConn.disconnect(); if (retryAfter > 0) { backoffAndSleep(retryAfter); @@ -159,26 +162,50 @@ public class HttpConnector2 { if (retryAfter > 0) { log .warn( - "{} - waiting and repeating request after suggested retry-after {} sec.", - requestUrl, retryAfter); + "waiting and repeating request after suggested retry-after {} sec for URL {}", + retryAfter, requestUrl); backoffAndSleep(retryAfter * 1000); } else { log .warn( - "{} - waiting and repeating request after default delay of {} sec.", - requestUrl, getClientParams().getRetryDelay()); - backoffAndSleep(retryNumber * getClientParams().getRetryDelay() * 1000); + "waiting and repeating request after default delay of {} sec for URL {}", + getClientParams().getRetryDelay(), requestUrl); + backoffAndSleep(retryNumber * getClientParams().getRetryDelay()); } report.put(REPORT_PREFIX + urlConn.getResponseCode(), requestUrl); + + logRequestTime(start); + urlConn.disconnect(); + return attemptDownload(requestUrl, retryNumber + 1, report); + case 422: // UNPROCESSABLE ENTITY + report.put(REPORT_PREFIX + urlConn.getResponseCode(), requestUrl); + log.warn("waiting and repeating request after 10 sec for URL {}", requestUrl); + backoffAndSleep(10000); + urlConn.disconnect(); + logRequestTime(start); + try { + return getInputStream(urlConn, start); + } catch (IOException e) { + log + .error( + "server returned 422 and got IOException accessing the response body from URL {}", + requestUrl); + log.error("IOException:", e); + return attemptDownload(requestUrl, retryNumber + 1, report); + } default: + log.error("gor error {} from URL: {}", urlConn.getResponseCode(), urlConn.getURL()); + log.error("response message: {}", urlConn.getResponseMessage()); report .put( REPORT_PREFIX + urlConn.getResponseCode(), String .format( "%s Error: %s", requestUrl, urlConn.getResponseMessage())); + logRequestTime(start); + urlConn.disconnect(); throw new CollectorException(urlConn.getResponseCode() + " error " + report); } } @@ -199,13 +226,27 @@ public class HttpConnector2 { } } + private InputStream getInputStream(HttpURLConnection urlConn, long start) throws IOException { + InputStream input = urlConn.getInputStream(); + responseType = urlConn.getContentType(); + logRequestTime(start); + return input; + } + + private static void logRequestTime(long start) { + log + .info( + "request time elapsed: {}sec", + TimeUnit.MILLISECONDS.toSeconds(System.currentTimeMillis() - start)); + } + private void logHeaderFields(final HttpURLConnection urlConn) throws IOException { - log.debug("StatusCode: {}", urlConn.getResponseMessage()); + log.info("Response: {} - {}", urlConn.getResponseCode(), urlConn.getResponseMessage()); for (Map.Entry> e : urlConn.getHeaderFields().entrySet()) { if (e.getKey() != null) { for (String v : e.getValue()) { - log.debug(" key: {} - value: {}", e.getKey(), v); + log.info(" key: {} - value: {}", e.getKey(), v); } } } @@ -225,7 +266,7 @@ public class HttpConnector2 { for (String key : headerMap.keySet()) { if ((key != null) && key.equalsIgnoreCase(HttpHeaders.RETRY_AFTER) && (!headerMap.get(key).isEmpty()) && NumberUtils.isCreatable(headerMap.get(key).get(0))) { - return Integer.parseInt(headerMap.get(key).get(0)) + 10; + return Integer.parseInt(headerMap.get(key).get(0)); } } return -1; diff --git a/dhp-common/src/main/java/eu/dnetlib/dhp/oozie/RunSQLSparkJob.java b/dhp-common/src/main/java/eu/dnetlib/dhp/oozie/RunSQLSparkJob.java new file mode 100644 index 000000000..027bf0735 --- /dev/null +++ b/dhp-common/src/main/java/eu/dnetlib/dhp/oozie/RunSQLSparkJob.java @@ -0,0 +1,77 @@ + +package eu.dnetlib.dhp.oozie; + +import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession; + +import java.net.URL; +import java.nio.charset.StandardCharsets; +import java.util.HashMap; +import java.util.Map; +import java.util.Optional; + +import org.apache.commons.lang3.time.DurationFormatUtils; +import org.apache.commons.text.StringSubstitutor; +import org.apache.spark.SparkConf; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import com.google.common.io.Resources; + +import eu.dnetlib.dhp.application.ArgumentApplicationParser; + +public class RunSQLSparkJob { + private static final Logger log = LoggerFactory.getLogger(RunSQLSparkJob.class); + + private final ArgumentApplicationParser parser; + + public RunSQLSparkJob(ArgumentApplicationParser parser) { + this.parser = parser; + } + + public static void main(String[] args) throws Exception { + + Map params = new HashMap<>(); + for (int i = 0; i < args.length - 1; i++) { + if (args[i].startsWith("--")) { + params.put(args[i].substring(2), args[++i]); + } + } + + /* + * String jsonConfiguration = IOUtils .toString( Objects .requireNonNull( RunSQLSparkJob.class + * .getResourceAsStream( "/eu/dnetlib/dhp/oozie/run_sql_parameters.json"))); final ArgumentApplicationParser + * parser = new ArgumentApplicationParser(jsonConfiguration); parser.parseArgument(args); + */ + + Boolean isSparkSessionManaged = Optional + .ofNullable(params.get("isSparkSessionManaged")) + .map(Boolean::valueOf) + .orElse(Boolean.TRUE); + log.info("isSparkSessionManaged: {}", isSparkSessionManaged); + + URL url = com.google.common.io.Resources.getResource(params.get("sql")); + String raw_sql = Resources.toString(url, StandardCharsets.UTF_8); + + String sql = StringSubstitutor.replace(raw_sql, params); + log.info("sql: {}", sql); + + SparkConf conf = new SparkConf(); + conf.set("hive.metastore.uris", params.get("hiveMetastoreUris")); + + runWithSparkHiveSession( + conf, + isSparkSessionManaged, + spark -> { + for (String statement : sql.split(";\\s*/\\*\\s*EOS\\s*\\*/\\s*")) { + log.info("executing: {}", statement); + long startTime = System.currentTimeMillis(); + spark.sql(statement).show(); + log + .info( + "executed in {}", + DurationFormatUtils.formatDuration(System.currentTimeMillis() - startTime, "HH:mm:ss.S")); + } + }); + } + +} diff --git a/dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/GraphCleaningFunctions.java b/dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/GraphCleaningFunctions.java index 0124e96fc..f01f90fe4 100644 --- a/dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/GraphCleaningFunctions.java +++ b/dhp-common/src/main/java/eu/dnetlib/dhp/schema/oaf/utils/GraphCleaningFunctions.java @@ -312,7 +312,8 @@ public class GraphCleaningFunctions extends CleaningFunctions { } if (value instanceof Datasource) { - // nothing to evaluate here + final Datasource d = (Datasource) value; + return Objects.nonNull(d.getOfficialname()) && StringUtils.isNotBlank(d.getOfficialname().getValue()); } else if (value instanceof Project) { final Project p = (Project) value; return Objects.nonNull(p.getCode()) && StringUtils.isNotBlank(p.getCode().getValue()); diff --git a/dhp-common/src/main/resources/eu/dnetlib/dhp/oozie/run_sql_parameters.json b/dhp-common/src/main/resources/eu/dnetlib/dhp/oozie/run_sql_parameters.json new file mode 100644 index 000000000..355f38e2f --- /dev/null +++ b/dhp-common/src/main/resources/eu/dnetlib/dhp/oozie/run_sql_parameters.json @@ -0,0 +1,20 @@ +[ + { + "paramName": "issm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "when true will stop SparkSession after job execution", + "paramRequired": false + }, + { + "paramName": "hmu", + "paramLongName": "hiveMetastoreUris", + "paramDescription": "the hive metastore uris", + "paramRequired": true + }, + { + "paramName": "sql", + "paramLongName": "sql", + "paramDescription": "sql script to execute", + "paramRequired": true + } +] \ No newline at end of file diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/AbstractClusteringFunction.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/AbstractClusteringFunction.java index 3da8eb490..e971ec5bb 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/AbstractClusteringFunction.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/AbstractClusteringFunction.java @@ -14,9 +14,9 @@ import eu.dnetlib.pace.config.Config; public abstract class AbstractClusteringFunction extends AbstractPaceFunctions implements ClusteringFunction { - protected Map params; + protected Map params; - public AbstractClusteringFunction(final Map params) { + public AbstractClusteringFunction(final Map params) { this.params = params; } @@ -27,7 +27,7 @@ public abstract class AbstractClusteringFunction extends AbstractPaceFunctions i return fields .stream() .filter(f -> !f.isEmpty()) - .map(this::normalize) + .map(s -> normalize(s)) .map(s -> filterAllStopWords(s)) .map(s -> doApply(conf, s)) .map(c -> filterBlacklisted(c, ngramBlacklist)) @@ -36,11 +36,24 @@ public abstract class AbstractClusteringFunction extends AbstractPaceFunctions i .collect(Collectors.toCollection(HashSet::new)); } - public Map getParams() { + public Map getParams() { return params; } protected Integer param(String name) { - return params.get(name); + Object val = params.get(name); + if (val == null) + return null; + if (val instanceof Number) { + return ((Number) val).intValue(); + } + return Integer.parseInt(val.toString()); + } + + protected int paramOrDefault(String name, int i) { + Integer res = param(name); + if (res == null) + res = i; + return res; } } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/Acronyms.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/Acronyms.java index 9072fbb4b..b5db27106 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/Acronyms.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/Acronyms.java @@ -13,7 +13,7 @@ import eu.dnetlib.pace.config.Config; @ClusteringClass("acronyms") public class Acronyms extends AbstractClusteringFunction { - public Acronyms(Map params) { + public Acronyms(Map params) { super(params); } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/ClusteringFunction.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/ClusteringFunction.java index 8b7852418..269de867d 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/ClusteringFunction.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/ClusteringFunction.java @@ -11,6 +11,6 @@ public interface ClusteringFunction { public Collection apply(Config config, List fields); - public Map getParams(); + public Map getParams(); } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/ImmutableFieldValue.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/ImmutableFieldValue.java index bc8844aee..cbfcde266 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/ImmutableFieldValue.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/ImmutableFieldValue.java @@ -12,7 +12,7 @@ import eu.dnetlib.pace.config.Config; @ClusteringClass("immutablefieldvalue") public class ImmutableFieldValue extends AbstractClusteringFunction { - public ImmutableFieldValue(final Map params) { + public ImmutableFieldValue(final Map params) { super(params); } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/JSONListClustering.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/JSONListClustering.java new file mode 100644 index 000000000..e00092bd0 --- /dev/null +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/JSONListClustering.java @@ -0,0 +1,69 @@ + +package eu.dnetlib.pace.clustering; + +import java.util.Collection; +import java.util.HashSet; +import java.util.List; +import java.util.Map; +import java.util.stream.Collectors; + +import org.apache.commons.lang3.StringUtils; + +import com.jayway.jsonpath.Configuration; +import com.jayway.jsonpath.DocumentContext; +import com.jayway.jsonpath.JsonPath; +import com.jayway.jsonpath.Option; + +import eu.dnetlib.pace.common.AbstractPaceFunctions; +import eu.dnetlib.pace.config.Config; +import eu.dnetlib.pace.util.MapDocumentUtil; + +@ClusteringClass("jsonlistclustering") +public class JSONListClustering extends AbstractPaceFunctions implements ClusteringFunction { + + private Map params; + + public JSONListClustering(Map params) { + this.params = params; + } + + @Override + public Map getParams() { + return params; + } + + @Override + public Collection apply(Config conf, List fields) { + return fields + .stream() + .filter(f -> !f.isEmpty()) + .map(s -> doApply(conf, s)) + .filter(StringUtils::isNotBlank) + .collect(Collectors.toCollection(HashSet::new)); + } + + private String doApply(Config conf, String json) { + StringBuilder st = new StringBuilder(); // to build the string used for comparisons basing on the jpath into + // parameters + final DocumentContext documentContext = JsonPath + .using(Configuration.defaultConfiguration().addOptions(Option.SUPPRESS_EXCEPTIONS)) + .parse(json); + + // for each path in the param list + for (String key : params.keySet().stream().filter(k -> k.contains("jpath")).collect(Collectors.toList())) { + String path = params.get(key).toString(); + String value = MapDocumentUtil.getJPathString(path, documentContext); + if (value == null || value.isEmpty()) + value = ""; + st.append(value); + st.append(" "); + } + + st.setLength(st.length() - 1); + + if (StringUtils.isBlank(st)) { + return "1"; + } + return st.toString(); + } +} diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/KeywordsClustering.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/KeywordsClustering.java index 38299adb4..fdd8d1fb1 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/KeywordsClustering.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/KeywordsClustering.java @@ -11,7 +11,7 @@ import eu.dnetlib.pace.config.Config; @ClusteringClass("keywordsclustering") public class KeywordsClustering extends AbstractClusteringFunction { - public KeywordsClustering(Map params) { + public KeywordsClustering(Map params) { super(params); } @@ -19,8 +19,8 @@ public class KeywordsClustering extends AbstractClusteringFunction { protected Collection doApply(final Config conf, String s) { // takes city codes and keywords codes without duplicates - Set keywords = getKeywords(s, conf.translationMap(), params.getOrDefault("windowSize", 4)); - Set cities = getCities(s, params.getOrDefault("windowSize", 4)); + Set keywords = getKeywords(s, conf.translationMap(), paramOrDefault("windowSize", 4)); + Set cities = getCities(s, paramOrDefault("windowSize", 4)); // list of combination to return as result final Collection combinations = new LinkedHashSet(); @@ -28,7 +28,7 @@ public class KeywordsClustering extends AbstractClusteringFunction { for (String keyword : keywordsToCodes(keywords, conf.translationMap())) { for (String city : citiesToCodes(cities)) { combinations.add(keyword + "-" + city); - if (combinations.size() >= params.getOrDefault("max", 2)) { + if (combinations.size() >= paramOrDefault("max", 2)) { return combinations; } } @@ -42,8 +42,8 @@ public class KeywordsClustering extends AbstractClusteringFunction { return fields .stream() .filter(f -> !f.isEmpty()) - .map(this::cleanup) - .map(this::normalize) + .map(KeywordsClustering::cleanup) + .map(KeywordsClustering::normalize) .map(s -> filterAllStopWords(s)) .map(s -> doApply(conf, s)) .map(c -> filterBlacklisted(c, ngramBlacklist)) diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/LastNameFirstInitial.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/LastNameFirstInitial.java index 5a385961a..9692f5762 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/LastNameFirstInitial.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/LastNameFirstInitial.java @@ -16,7 +16,7 @@ public class LastNameFirstInitial extends AbstractClusteringFunction { private boolean DEFAULT_AGGRESSIVE = true; - public LastNameFirstInitial(final Map params) { + public LastNameFirstInitial(final Map params) { super(params); } @@ -25,7 +25,7 @@ public class LastNameFirstInitial extends AbstractClusteringFunction { return fields .stream() .filter(f -> !f.isEmpty()) - .map(this::normalize) + .map(LastNameFirstInitial::normalize) .map(s -> doApply(conf, s)) .map(c -> filterBlacklisted(c, ngramBlacklist)) .flatMap(c -> c.stream()) @@ -33,8 +33,7 @@ public class LastNameFirstInitial extends AbstractClusteringFunction { .collect(Collectors.toCollection(HashSet::new)); } - @Override - protected String normalize(final String s) { + public static String normalize(final String s) { return fixAliases(transliterate(nfd(unicodeNormalization(s)))) // do not compact the regexes in a single expression, would cause StackOverflowError in case of large input // strings diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/LowercaseClustering.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/LowercaseClustering.java index a3a6c4881..807f41dd5 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/LowercaseClustering.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/LowercaseClustering.java @@ -15,7 +15,7 @@ import eu.dnetlib.pace.config.Config; @ClusteringClass("lowercase") public class LowercaseClustering extends AbstractClusteringFunction { - public LowercaseClustering(final Map params) { + public LowercaseClustering(final Map params) { super(params); } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/NgramPairs.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/NgramPairs.java index aa06aa408..bcc9667a8 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/NgramPairs.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/NgramPairs.java @@ -12,11 +12,11 @@ import eu.dnetlib.pace.config.Config; @ClusteringClass("ngrampairs") public class NgramPairs extends Ngrams { - public NgramPairs(Map params) { + public NgramPairs(Map params) { super(params, false); } - public NgramPairs(Map params, boolean sorted) { + public NgramPairs(Map params, boolean sorted) { super(params, sorted); } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/Ngrams.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/Ngrams.java index 96c305a16..7b862c729 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/Ngrams.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/Ngrams.java @@ -10,11 +10,11 @@ public class Ngrams extends AbstractClusteringFunction { private final boolean sorted; - public Ngrams(Map params) { + public Ngrams(Map params) { this(params, false); } - public Ngrams(Map params, boolean sorted) { + public Ngrams(Map params, boolean sorted) { super(params); this.sorted = sorted; } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/NumAuthorsTitleSuffixPrefixChain.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/NumAuthorsTitleSuffixPrefixChain.java new file mode 100644 index 000000000..f1d1e17b9 --- /dev/null +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/NumAuthorsTitleSuffixPrefixChain.java @@ -0,0 +1,113 @@ + +package eu.dnetlib.pace.clustering; + +import java.util.*; +import java.util.stream.Collectors; +import java.util.stream.StreamSupport; + +import com.google.common.base.Splitter; +import com.google.common.collect.Sets; + +import eu.dnetlib.pace.config.Config; + +@ClusteringClass("numAuthorsTitleSuffixPrefixChain") +public class NumAuthorsTitleSuffixPrefixChain extends AbstractClusteringFunction { + + public NumAuthorsTitleSuffixPrefixChain(Map params) { + super(params); + } + + @Override + public Collection apply(Config conf, List fields) { + + try { + int num_authors = Math.min(Integer.parseInt(fields.get(0)), 21); // SIZE threshold is 20, +1 + + if (num_authors > 0) { + return super.apply(conf, fields.subList(1, fields.size())) + .stream() + .map(s -> num_authors + "-" + s) + .collect(Collectors.toList()); + } + } catch (NumberFormatException e) { + // missing or null authors array + } + + return Collections.emptyList(); + } + + @Override + protected Collection doApply(Config conf, String s) { + return suffixPrefixChain(cleanup(s), param("mod")); + } + + private Collection suffixPrefixChain(String s, int mod) { + // create the list of words from the string (remove short words) + List wordsList = Arrays + .stream(s.split(" ")) + .filter(si -> si.length() > 3) + .collect(Collectors.toList()); + + final int words = wordsList.size(); + final int letters = s.length(); + + // create the prefix: number of words + number of letters/mod + String prefix = words / mod + "-"; + + return doSuffixPrefixChain(wordsList, prefix); + + } + + private Collection doSuffixPrefixChain(List wordsList, String prefix) { + + Set set = Sets.newLinkedHashSet(); + switch (wordsList.size()) { + case 0: + break; + case 1: + set.add(wordsList.get(0)); + break; + case 2: + set + .add( + prefix + + suffix(wordsList.get(0), 3) + + prefix(wordsList.get(1), 3)); + + set + .add( + prefix + + prefix(wordsList.get(0), 3) + + suffix(wordsList.get(1), 3)); + + break; + default: + set + .add( + prefix + + suffix(wordsList.get(0), 3) + + prefix(wordsList.get(1), 3) + + suffix(wordsList.get(2), 3)); + + set + .add( + prefix + + prefix(wordsList.get(0), 3) + + suffix(wordsList.get(1), 3) + + prefix(wordsList.get(2), 3)); + break; + } + + return set; + + } + + private String suffix(String s, int len) { + return s.substring(s.length() - len); + } + + private String prefix(String s, int len) { + return s.substring(0, len); + } + +} diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/PersonClustering.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/PersonClustering.java index b4a04ce65..91b51bebb 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/PersonClustering.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/PersonClustering.java @@ -17,11 +17,11 @@ import eu.dnetlib.pace.model.Person; @ClusteringClass("personClustering") public class PersonClustering extends AbstractPaceFunctions implements ClusteringFunction { - private Map params; + private Map params; private static final int MAX_TOKENS = 5; - public PersonClustering(final Map params) { + public PersonClustering(final Map params) { this.params = params; } @@ -77,7 +77,7 @@ public class PersonClustering extends AbstractPaceFunctions implements Clusterin // } @Override - public Map getParams() { + public Map getParams() { return params; } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/PersonHash.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/PersonHash.java index a3d58a9be..09a112c37 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/PersonHash.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/PersonHash.java @@ -15,7 +15,7 @@ public class PersonHash extends AbstractClusteringFunction { private boolean DEFAULT_AGGRESSIVE = false; - public PersonHash(final Map params) { + public PersonHash(final Map params) { super(params); } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/RandomClusteringFunction.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/RandomClusteringFunction.java index 2aab926da..3733dfc74 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/RandomClusteringFunction.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/RandomClusteringFunction.java @@ -8,7 +8,7 @@ import eu.dnetlib.pace.config.Config; public class RandomClusteringFunction extends AbstractClusteringFunction { - public RandomClusteringFunction(Map params) { + public RandomClusteringFunction(Map params) { super(params); } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/SortedNgramPairs.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/SortedNgramPairs.java index b085ae26d..ca1b4189b 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/SortedNgramPairs.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/SortedNgramPairs.java @@ -1,7 +1,10 @@ package eu.dnetlib.pace.clustering; -import java.util.*; +import java.util.Collection; +import java.util.Collections; +import java.util.List; +import java.util.Map; import com.google.common.base.Joiner; import com.google.common.base.Splitter; @@ -12,7 +15,7 @@ import eu.dnetlib.pace.config.Config; @ClusteringClass("sortedngrampairs") public class SortedNgramPairs extends NgramPairs { - public SortedNgramPairs(Map params) { + public SortedNgramPairs(Map params) { super(params, false); } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/SpaceTrimmingFieldValue.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/SpaceTrimmingFieldValue.java index 392aecc79..048380f7e 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/SpaceTrimmingFieldValue.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/SpaceTrimmingFieldValue.java @@ -15,7 +15,7 @@ import eu.dnetlib.pace.config.Config; @ClusteringClass("spacetrimmingfieldvalue") public class SpaceTrimmingFieldValue extends AbstractClusteringFunction { - public SpaceTrimmingFieldValue(final Map params) { + public SpaceTrimmingFieldValue(final Map params) { super(params); } @@ -25,7 +25,7 @@ public class SpaceTrimmingFieldValue extends AbstractClusteringFunction { res .add( - StringUtils.isBlank(s) ? RandomStringUtils.random(getParams().get("randomLength")) + StringUtils.isBlank(s) ? RandomStringUtils.random(param("randomLength")) : s.toLowerCase().replaceAll("\\s+", "")); return res; diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/SuffixPrefix.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/SuffixPrefix.java index 2a1c023a9..b6921e9f1 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/SuffixPrefix.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/SuffixPrefix.java @@ -12,7 +12,7 @@ import eu.dnetlib.pace.config.Config; @ClusteringClass("suffixprefix") public class SuffixPrefix extends AbstractClusteringFunction { - public SuffixPrefix(Map params) { + public SuffixPrefix(Map params) { super(params); } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/UrlClustering.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/UrlClustering.java index 5b267ad10..34f41085b 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/UrlClustering.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/UrlClustering.java @@ -15,12 +15,17 @@ import eu.dnetlib.pace.config.Config; @ClusteringClass("urlclustering") public class UrlClustering extends AbstractPaceFunctions implements ClusteringFunction { - protected Map params; + protected Map params; - public UrlClustering(final Map params) { + public UrlClustering(final Map params) { this.params = params; } + @Override + public Map getParams() { + return params; + } + @Override public Collection apply(final Config conf, List fields) { try { @@ -35,11 +40,6 @@ public class UrlClustering extends AbstractPaceFunctions implements ClusteringFu } } - @Override - public Map getParams() { - return null; - } - private URL asUrl(String value) { try { return new URL(value); diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/WordsStatsSuffixPrefixChain.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/WordsStatsSuffixPrefixChain.java index c8e02f8f0..22351cf8f 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/WordsStatsSuffixPrefixChain.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/WordsStatsSuffixPrefixChain.java @@ -11,7 +11,7 @@ import eu.dnetlib.pace.config.Config; @ClusteringClass("wordsStatsSuffixPrefixChain") public class WordsStatsSuffixPrefixChain extends AbstractClusteringFunction { - public WordsStatsSuffixPrefixChain(Map params) { + public WordsStatsSuffixPrefixChain(Map params) { super(params); } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/WordsSuffixPrefix.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/WordsSuffixPrefix.java index e606590a5..f9fef376b 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/WordsSuffixPrefix.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/clustering/WordsSuffixPrefix.java @@ -12,7 +12,7 @@ import eu.dnetlib.pace.config.Config; @ClusteringClass("wordssuffixprefix") public class WordsSuffixPrefix extends AbstractClusteringFunction { - public WordsSuffixPrefix(Map params) { + public WordsSuffixPrefix(Map params) { super(params); } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/common/AbstractPaceFunctions.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/common/AbstractPaceFunctions.java index b440686de..ba7639ada 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/common/AbstractPaceFunctions.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/common/AbstractPaceFunctions.java @@ -16,7 +16,6 @@ import org.apache.commons.lang3.StringUtils; import com.google.common.base.Joiner; import com.google.common.base.Splitter; import com.google.common.collect.Iterables; -import com.google.common.collect.Lists; import com.google.common.collect.Sets; import com.ibm.icu.text.Transliterator; @@ -27,7 +26,7 @@ import eu.dnetlib.pace.clustering.NGramUtils; * * @author claudio */ -public abstract class AbstractPaceFunctions { +public class AbstractPaceFunctions { // city map to be used when translating the city names into codes private static Map cityMap = AbstractPaceFunctions @@ -62,11 +61,14 @@ public abstract class AbstractPaceFunctions { private static Pattern hexUnicodePattern = Pattern.compile("\\\\u(\\p{XDigit}{4})"); - protected String concat(final List l) { + private static Pattern romanNumberPattern = Pattern + .compile("^M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})$"); + + protected static String concat(final List l) { return Joiner.on(" ").skipNulls().join(l); } - protected String cleanup(final String s) { + public static String cleanup(final String s) { final String s1 = HTML_REGEX.matcher(s).replaceAll(""); final String s2 = unicodeNormalization(s1.toLowerCase()); final String s3 = nfd(s2); @@ -82,7 +84,7 @@ public abstract class AbstractPaceFunctions { return s12; } - protected String fixXML(final String a) { + protected static String fixXML(final String a) { return a .replaceAll("–", " ") @@ -91,7 +93,7 @@ public abstract class AbstractPaceFunctions { .replaceAll("−", " "); } - protected boolean checkNumbers(final String a, final String b) { + protected static boolean checkNumbers(final String a, final String b) { final String numbersA = getNumbers(a); final String numbersB = getNumbers(b); final String romansA = getRomans(a); @@ -99,7 +101,7 @@ public abstract class AbstractPaceFunctions { return !numbersA.equals(numbersB) || !romansA.equals(romansB); } - protected String getRomans(final String s) { + protected static String getRomans(final String s) { final StringBuilder sb = new StringBuilder(); for (final String t : s.split(" ")) { sb.append(isRoman(t) ? t : ""); @@ -107,13 +109,12 @@ public abstract class AbstractPaceFunctions { return sb.toString(); } - protected boolean isRoman(final String s) { - return s - .replaceAll("^M{0,4}(CM|CD|D?C{0,3})(XC|XL|L?X{0,3})(IX|IV|V?I{0,3})$", "qwertyuiop") - .equals("qwertyuiop"); + protected static boolean isRoman(final String s) { + Matcher m = romanNumberPattern.matcher(s); + return m.matches() && m.hitEnd(); } - protected String getNumbers(final String s) { + protected static String getNumbers(final String s) { final StringBuilder sb = new StringBuilder(); for (final String t : s.split(" ")) { sb.append(isNumber(t) ? t : ""); @@ -121,7 +122,7 @@ public abstract class AbstractPaceFunctions { return sb.toString(); } - public boolean isNumber(String strNum) { + public static boolean isNumber(String strNum) { if (strNum == null) { return false; } @@ -147,7 +148,7 @@ public abstract class AbstractPaceFunctions { } } - protected String removeSymbols(final String s) { + protected static String removeSymbols(final String s) { final StringBuilder sb = new StringBuilder(); s.chars().forEach(ch -> { @@ -157,11 +158,11 @@ public abstract class AbstractPaceFunctions { return sb.toString().replaceAll("\\s+", " "); } - protected boolean notNull(final String s) { + protected static boolean notNull(final String s) { return s != null; } - protected String normalize(final String s) { + public static String normalize(final String s) { return fixAliases(transliterate(nfd(unicodeNormalization(s)))) .toLowerCase() // do not compact the regexes in a single expression, would cause StackOverflowError in case of large input @@ -174,16 +175,16 @@ public abstract class AbstractPaceFunctions { .trim(); } - public String nfd(final String s) { + public static String nfd(final String s) { return Normalizer.normalize(s, Normalizer.Form.NFD); } - public String utf8(final String s) { + public static String utf8(final String s) { byte[] bytes = s.getBytes(StandardCharsets.UTF_8); return new String(bytes, StandardCharsets.UTF_8); } - public String unicodeNormalization(final String s) { + public static String unicodeNormalization(final String s) { Matcher m = hexUnicodePattern.matcher(s); StringBuffer buf = new StringBuffer(s.length()); @@ -195,7 +196,7 @@ public abstract class AbstractPaceFunctions { return buf.toString(); } - protected String filterStopWords(final String s, final Set stopwords) { + protected static String filterStopWords(final String s, final Set stopwords) { final StringTokenizer st = new StringTokenizer(s); final StringBuilder sb = new StringBuilder(); while (st.hasMoreTokens()) { @@ -208,7 +209,7 @@ public abstract class AbstractPaceFunctions { return sb.toString().trim(); } - public String filterAllStopWords(String s) { + public static String filterAllStopWords(String s) { s = filterStopWords(s, stopwords_en); s = filterStopWords(s, stopwords_de); @@ -221,7 +222,8 @@ public abstract class AbstractPaceFunctions { return s; } - protected Collection filterBlacklisted(final Collection set, final Set ngramBlacklist) { + protected static Collection filterBlacklisted(final Collection set, + final Set ngramBlacklist) { final Set newset = Sets.newLinkedHashSet(); for (final String s : set) { if (!ngramBlacklist.contains(s)) { @@ -268,7 +270,7 @@ public abstract class AbstractPaceFunctions { return m; } - public String removeKeywords(String s, Set keywords) { + public static String removeKeywords(String s, Set keywords) { s = " " + s + " "; for (String k : keywords) { @@ -278,39 +280,39 @@ public abstract class AbstractPaceFunctions { return s.trim(); } - public double commonElementsPercentage(Set s1, Set s2) { + public static double commonElementsPercentage(Set s1, Set s2) { double longer = Math.max(s1.size(), s2.size()); return (double) s1.stream().filter(s2::contains).count() / longer; } // convert the set of keywords to codes - public Set toCodes(Set keywords, Map translationMap) { + public static Set toCodes(Set keywords, Map translationMap) { return keywords.stream().map(s -> translationMap.get(s)).collect(Collectors.toSet()); } - public Set keywordsToCodes(Set keywords, Map translationMap) { + public static Set keywordsToCodes(Set keywords, Map translationMap) { return toCodes(keywords, translationMap); } - public Set citiesToCodes(Set keywords) { + public static Set citiesToCodes(Set keywords) { return toCodes(keywords, cityMap); } - protected String firstLC(final String s) { + protected static String firstLC(final String s) { return StringUtils.substring(s, 0, 1).toLowerCase(); } - protected Iterable tokens(final String s, final int maxTokens) { + protected static Iterable tokens(final String s, final int maxTokens) { return Iterables.limit(Splitter.on(" ").omitEmptyStrings().trimResults().split(s), maxTokens); } - public String normalizePid(String pid) { + public static String normalizePid(String pid) { return DOI_PREFIX.matcher(pid.toLowerCase()).replaceAll(""); } // get the list of keywords into the input string - public Set getKeywords(String s1, Map translationMap, int windowSize) { + public static Set getKeywords(String s1, Map translationMap, int windowSize) { String s = s1; @@ -340,7 +342,7 @@ public abstract class AbstractPaceFunctions { return codes; } - public Set getCities(String s1, int windowSize) { + public static Set getCities(String s1, int windowSize) { return getKeywords(s1, cityMap, windowSize); } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/model/ClusteringDef.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/model/ClusteringDef.java index d9ad81d42..5ede2c380 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/model/ClusteringDef.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/model/ClusteringDef.java @@ -18,7 +18,7 @@ public class ClusteringDef implements Serializable { private List fields; - private Map params; + private Map params; public ClusteringDef() { } @@ -43,11 +43,11 @@ public class ClusteringDef implements Serializable { this.fields = fields; } - public Map getParams() { + public Map getParams() { return params; } - public void setParams(final Map params) { + public void setParams(final Map params) { this.params = params; } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/model/FieldDef.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/model/FieldDef.java index f34545e6d..7ad9b7445 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/model/FieldDef.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/model/FieldDef.java @@ -2,6 +2,7 @@ package eu.dnetlib.pace.model; import java.io.Serializable; +import java.util.HashSet; import java.util.List; import com.fasterxml.jackson.core.JsonProcessingException; @@ -36,6 +37,16 @@ public class FieldDef implements Serializable { */ private int length = -1; + private HashSet filter; + + private boolean sorted; + + public boolean isSorted() { + return sorted; + } + + private String clean; + public FieldDef() { } @@ -91,6 +102,30 @@ public class FieldDef implements Serializable { this.path = path; } + public HashSet getFilter() { + return filter; + } + + public void setFilter(HashSet filter) { + this.filter = filter; + } + + public boolean getSorted() { + return sorted; + } + + public void setSorted(boolean sorted) { + this.sorted = sorted; + } + + public String getClean() { + return clean; + } + + public void setClean(String clean) { + this.clean = clean; + } + @Override public String toString() { try { diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/model/SparkDeduper.scala b/dhp-pace-core/src/main/java/eu/dnetlib/pace/model/SparkDeduper.scala index b3f56bcdb..bc702b9e2 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/model/SparkDeduper.scala +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/model/SparkDeduper.scala @@ -5,9 +5,9 @@ import eu.dnetlib.pace.util.{BlockProcessor, SparkReporter} import org.apache.spark.SparkContext import org.apache.spark.sql.catalyst.expressions.Literal import org.apache.spark.sql.expressions._ -import org.apache.spark.sql.functions.{col, lit, udf} +import org.apache.spark.sql.functions.{col, desc, expr, lit, udf} import org.apache.spark.sql.types._ -import org.apache.spark.sql.{Column, Dataset, Row, functions} +import org.apache.spark.sql.{Column, Dataset, Row, SaveMode, functions} import java.util.function.Predicate import java.util.stream.Collectors @@ -80,6 +80,8 @@ case class SparkDeduper(conf: DedupConfig) extends Serializable { .withColumn("key", functions.explode(clusterValuesUDF(cd).apply(functions.array(inputColumns: _*)))) // Add position column having the position of the row within the set of rows having the same key value ordered by the sorting value .withColumn("position", functions.row_number().over(Window.partitionBy("key").orderBy(col(model.orderingFieldName), col(model.identifierFieldName)))) + // .withColumn("count", functions.max("position").over(Window.partitionBy("key").orderBy(col(model.orderingFieldName), col(model.identifierFieldName)).rowsBetween(Window.unboundedPreceding,Window.unboundedFollowing) )) + // .filter("count > 1") if (df_with_clustering_keys == null) df_with_clustering_keys = ds @@ -88,20 +90,44 @@ case class SparkDeduper(conf: DedupConfig) extends Serializable { } //TODO: analytics + /*df_with_clustering_keys.groupBy(col("clustering"), col("key")) + .agg(expr("max(count) AS size")) + .orderBy(desc("size")) + .show*/ val df_with_blocks = df_with_clustering_keys - // filter out rows with position exceeding the maxqueuesize parameter - .filter(col("position").leq(conf.getWf.getQueueMaxSize)) - .groupBy("clustering", "key") + // split the clustering block into smaller blocks of queuemaxsize + .groupBy(col("clustering"), col("key"), functions.floor(col("position").divide(lit(conf.getWf.getQueueMaxSize)))) .agg(functions.collect_set(functions.struct(model.schema.fieldNames.map(col): _*)).as("block")) .filter(functions.size(new Column("block")).gt(1)) + .union( + //adjacency blocks + df_with_clustering_keys + // filter out leading and trailing elements + .filter(col("position").gt(conf.getWf.getSlidingWindowSize/2)) + //.filter(col("position").lt(col("count").minus(conf.getWf.getSlidingWindowSize/2))) + // create small blocks of records on "the border" of maxqueuesize: getSlidingWindowSize/2 elements before and after + .filter( + col("position").mod(conf.getWf.getQueueMaxSize).lt(conf.getWf.getSlidingWindowSize/2) // slice of the start of block + || col("position").mod(conf.getWf.getQueueMaxSize).gt(conf.getWf.getQueueMaxSize - (conf.getWf.getSlidingWindowSize/2)) //slice of the end of the block + ) + .groupBy(col("clustering"), col("key"), functions.floor((col("position") + lit(conf.getWf.getSlidingWindowSize/2)).divide(lit(conf.getWf.getQueueMaxSize)))) + .agg(functions.collect_set(functions.struct(model.schema.fieldNames.map(col): _*)).as("block")) + .filter(functions.size(new Column("block")).gt(1)) + ) df_with_blocks } def clusterValuesUDF(cd: ClusteringDef) = { udf[mutable.WrappedArray[String], mutable.WrappedArray[Any]](values => { - values.flatMap(f => cd.clusteringFunction().apply(conf, Seq(f.toString).asJava).asScala) + val valueList = values.flatMap { + case a: mutable.WrappedArray[Any] => a.map(_.toString) + case s: Any => Seq(s.toString) + }.asJava; + + mutable.WrappedArray.make(cd.clusteringFunction().apply(conf, valueList).toArray()) + }) } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/model/SparkModel.scala b/dhp-pace-core/src/main/java/eu/dnetlib/pace/model/SparkModel.scala index aa997c6e9..aa04188da 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/model/SparkModel.scala +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/model/SparkModel.scala @@ -1,13 +1,16 @@ package eu.dnetlib.pace.model import com.jayway.jsonpath.{Configuration, JsonPath} +import eu.dnetlib.pace.common.AbstractPaceFunctions import eu.dnetlib.pace.config.{DedupConfig, Type} import eu.dnetlib.pace.util.MapDocumentUtil +import org.apache.commons.lang3.StringUtils import org.apache.spark.sql.catalyst.encoders.RowEncoder import org.apache.spark.sql.catalyst.expressions.GenericRowWithSchema import org.apache.spark.sql.types.{DataTypes, Metadata, StructField, StructType} import org.apache.spark.sql.{Dataset, Row} +import java.util.Locale import java.util.regex.Pattern import scala.collection.JavaConverters._ @@ -60,7 +63,7 @@ case class SparkModel(conf: DedupConfig) { values(identityFieldPosition) = MapDocumentUtil.getJPathString(conf.getWf.getIdPath, documentContext) schema.fieldNames.zipWithIndex.foldLeft(values) { - case ((res, (fname, index))) => { + case ((res, (fname, index))) => val fdef = conf.getPace.getModelMap.get(fname) if (fdef != null) { @@ -96,13 +99,52 @@ case class SparkModel(conf: DedupConfig) { case Type.DoubleArray => MapDocumentUtil.getJPathArray(fdef.getPath, json) } + + val filter = fdef.getFilter + + if (StringUtils.isNotBlank(fdef.getClean)) { + res(index) = res(index) match { + case x: Seq[String] => x.map(clean(_, fdef.getClean)).toSeq + case _ => clean(res(index).toString, fdef.getClean) + } + } + + if (filter != null && !filter.isEmpty) { + res(index) = res(index) match { + case x: String if filter.contains(x.toLowerCase(Locale.ROOT)) => null + case x: Seq[String] => x.filter(s => !filter.contains(s.toLowerCase(Locale.ROOT))).toSeq + case _ => res(index) + } + } + + if (fdef.getSorted) { + res(index) = res(index) match { + case x: Seq[String] => x.sorted.toSeq + case _ => res(index) + } + } } res - } } new GenericRowWithSchema(values, schema) } + + def clean(value: String, cleantype: String) : String = { + val res = cleantype match { + case "title" => AbstractPaceFunctions.cleanup(value) + case _ => value + } + +// if (!res.equals(AbstractPaceFunctions.normalize(value))) { +// println(res) +// println(AbstractPaceFunctions.normalize(value)) +// println() +// } + + res + } + } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/AuthorsMatch.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/AuthorsMatch.java index 5c6939e60..edad0ae2e 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/AuthorsMatch.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/AuthorsMatch.java @@ -23,7 +23,6 @@ public class AuthorsMatch extends AbstractListComparator { private String MODE; // full or surname private int SIZE_THRESHOLD; private String TYPE; // count or percentage - private int common; public AuthorsMatch(Map params) { super(params, new com.wcohen.ss.JaroWinkler()); @@ -35,7 +34,6 @@ public class AuthorsMatch extends AbstractListComparator { FULLNAME_THRESHOLD = Double.parseDouble(params.getOrDefault("fullname_th", "0.9")); SIZE_THRESHOLD = Integer.parseInt(params.getOrDefault("size_th", "20")); TYPE = params.getOrDefault("type", "percentage"); - common = 0; } protected AuthorsMatch(double w, AbstractStringDistance ssalgo) { @@ -44,22 +42,27 @@ public class AuthorsMatch extends AbstractListComparator { @Override public double compare(final List a, final List b, final Config conf) { - if (a.isEmpty() || b.isEmpty()) return -1; if (a.size() > SIZE_THRESHOLD || b.size() > SIZE_THRESHOLD) return 1.0; - List aList = a.stream().map(author -> new Person(author, false)).collect(Collectors.toList()); + int maxMiss = Integer.MAX_VALUE; List bList = b.stream().map(author -> new Person(author, false)).collect(Collectors.toList()); - common = 0; + Double threshold = getDoubleParam("threshold"); + + if (threshold != null && threshold >= 0.0 && threshold <= 1.0 && a.size() == b.size()) { + maxMiss = (int) Math.floor((1 - threshold) * Math.max(a.size(), b.size())); + } + + int common = 0; // compare each element of List1 with each element of List2 - for (Person p1 : aList) + for (int i = 0; i < a.size(); i++) { + Person p1 = new Person(a.get(i), false); for (Person p2 : bList) { - // both persons are inaccurate if (!p1.isAccurate() && !p2.isAccurate()) { // compare just normalized fullnames @@ -118,11 +121,15 @@ public class AuthorsMatch extends AbstractListComparator { } } - } + if (i - common > maxMiss) { + return 0.0; + } + } + // normalization factor to compute the score - int normFactor = aList.size() == bList.size() ? aList.size() : (aList.size() + bList.size() - common); + int normFactor = a.size() == b.size() ? a.size() : (a.size() + b.size() - common); if (TYPE.equals("percentage")) { return (double) common / normFactor; diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/InstanceTypeMatch.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/InstanceTypeMatch.java index 238cb16ce..34ebcf7a7 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/InstanceTypeMatch.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/InstanceTypeMatch.java @@ -25,6 +25,7 @@ public class InstanceTypeMatch extends AbstractListComparator { translationMap.put("Conference object", "*"); translationMap.put("Other literature type", "*"); translationMap.put("Unknown", "*"); + translationMap.put("UNKNOWN", "*"); // article types translationMap.put("Article", "Article"); @@ -76,5 +77,4 @@ public class InstanceTypeMatch extends AbstractListComparator { protected double normalize(final double d) { return d; } - } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/LevensteinTitle.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/LevensteinTitle.java index 877cb95ab..e2ee062b5 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/LevensteinTitle.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/LevensteinTitle.java @@ -3,6 +3,7 @@ package eu.dnetlib.pace.tree; import java.util.Map; +import org.apache.commons.lang3.StringUtils; import org.apache.commons.logging.Log; import org.apache.commons.logging.LogFactory; @@ -30,16 +31,25 @@ public class LevensteinTitle extends AbstractStringComparator { } @Override - public double distance(final String a, final String b, final Config conf) { - final String ca = cleanup(a); - final String cb = cleanup(b); - + public double distance(final String ca, final String cb, final Config conf) { final boolean check = checkNumbers(ca, cb); if (check) return 0.5; - return normalize(ssalgo.score(ca, cb), ca.length(), cb.length()); + Double threshold = getDoubleParam("threshold"); + + // reduce Levenshtein algo complexity when target threshold is known + if (threshold != null && threshold >= 0.0 && threshold <= 1.0) { + int maxdistance = (int) Math.floor((1 - threshold) * Math.max(ca.length(), cb.length())); + int score = StringUtils.getLevenshteinDistance(ca, cb, maxdistance); + if (score == -1) { + return 0; + } + return normalize(score, ca.length(), cb.length()); + } else { + return normalize(StringUtils.getLevenshteinDistance(ca, cb), ca.length(), cb.length()); + } } private double normalize(final double score, final int la, final int lb) { diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/MaxLengthMatch.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/MaxLengthMatch.java new file mode 100644 index 000000000..8f525c6d5 --- /dev/null +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/MaxLengthMatch.java @@ -0,0 +1,29 @@ + +package eu.dnetlib.pace.tree; + +import java.util.Map; + +import eu.dnetlib.pace.config.Config; +import eu.dnetlib.pace.tree.support.AbstractStringComparator; +import eu.dnetlib.pace.tree.support.ComparatorClass; + +@ComparatorClass("maxLengthMatch") +public class MaxLengthMatch extends AbstractStringComparator { + + private final int limit; + + public MaxLengthMatch(Map params) { + super(params); + + limit = Integer.parseInt(params.getOrDefault("limit", "200")); + } + + @Override + public double compare(String a, String b, final Config conf) { + return a.length() < limit && b.length() < limit ? 1.0 : -1.0; + } + + protected String toString(final Object object) { + return toFirstString(object); + } +} diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/support/AbstractComparator.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/support/AbstractComparator.java index 8a957c5e3..cde73fd2b 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/support/AbstractComparator.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/tree/support/AbstractComparator.java @@ -127,4 +127,14 @@ public abstract class AbstractComparator extends AbstractPaceFunctions implem return this.weight; } + public Double getDoubleParam(String name) { + String svalue = params.get(name); + + try { + return Double.parseDouble(svalue); + } catch (Throwable t) { + } + + return null; + } } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/util/BlockProcessor.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/util/BlockProcessor.java index c2b0ddda7..177ad73df 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/util/BlockProcessor.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/util/BlockProcessor.java @@ -67,8 +67,10 @@ public class BlockProcessor { private void processRows(final List queue, final Reporter context) { - for (int pivotPos = 0; pivotPos < queue.size(); pivotPos++) { - final Row pivot = queue.get(pivotPos); + IncrementalConnectedComponents icc = new IncrementalConnectedComponents(queue.size()); + + for (int i = 0; i < queue.size(); i++) { + final Row pivot = queue.get(i); final String idPivot = pivot.getString(identifierFieldPos); // identifier final Object fieldsPivot = getJavaValue(pivot, orderFieldPos); @@ -76,9 +78,9 @@ public class BlockProcessor { final WfConfig wf = dedupConf.getWf(); if (fieldPivot != null) { - int i = 0; - for (int windowPos = pivotPos + 1; windowPos < queue.size(); windowPos++) { - final Row curr = queue.get(windowPos); + for (int j = icc.nextUnconnected(i, i + 1); j >= 0 + && j < queue.size(); j = icc.nextUnconnected(i, j + 1)) { + final Row curr = queue.get(j); final String idCurr = curr.getString(identifierFieldPos); // identifier if (mustSkip(idCurr)) { @@ -86,7 +88,7 @@ public class BlockProcessor { break; } - if (++i > wf.getSlidingWindowSize()) { + if (wf.getSlidingWindowSize() > 0 && (j - i) > wf.getSlidingWindowSize()) { break; } @@ -97,7 +99,9 @@ public class BlockProcessor { final TreeProcessor treeProcessor = new TreeProcessor(dedupConf); - emitOutput(treeProcessor.compare(pivot, curr), idPivot, idCurr, context); + if (emitOutput(treeProcessor.compare(pivot, curr), idPivot, idCurr, context)) { + icc.connect(i, j); + } } } } @@ -115,7 +119,8 @@ public class BlockProcessor { return null; } - private void emitOutput(final boolean result, final String idPivot, final String idCurr, final Reporter context) { + private boolean emitOutput(final boolean result, final String idPivot, final String idCurr, + final Reporter context) { if (result) { if (idPivot.compareTo(idCurr) <= 0) { @@ -127,6 +132,8 @@ public class BlockProcessor { } else { context.incrementCounter(dedupConf.getWf().getEntityType(), "d < " + dedupConf.getWf().getThreshold(), 1); } + + return result; } private boolean mustSkip(final String idPivot) { @@ -142,5 +149,4 @@ public class BlockProcessor { context.emit(type, from, to); } - } diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/util/IncrementalConnectedComponents.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/util/IncrementalConnectedComponents.java new file mode 100644 index 000000000..ed35239a8 --- /dev/null +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/util/IncrementalConnectedComponents.java @@ -0,0 +1,50 @@ + +package eu.dnetlib.pace.util; + +import java.util.BitSet; + +public class IncrementalConnectedComponents { + final private int size; + + final private BitSet[] indexes; + + IncrementalConnectedComponents(int size) { + this.size = size; + this.indexes = new BitSet[size]; + } + + public void connect(int i, int j) { + if (indexes[i] == null) { + if (indexes[j] == null) { + indexes[i] = new BitSet(size); + } else { + indexes[i] = indexes[j]; + } + } else { + if (indexes[j] != null && indexes[i] != indexes[j]) { + // merge adjacency lists for i and j + indexes[i].or(indexes[j]); + } + } + + indexes[i].set(i); + indexes[i].set(j); + indexes[j] = indexes[i]; + } + + public int nextUnconnected(int i, int j) { + if (indexes[i] == null) { + return j; + } + int result = indexes[i].nextClearBit(j); + + return (result >= size) ? -1 : result; + } + + public BitSet getConnections(int i) { + if (indexes[i] == null) { + return null; + } + return indexes[i]; + } +} diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/util/MapDocumentUtil.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/util/MapDocumentUtil.java index 28244cb3b..7dc340663 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/util/MapDocumentUtil.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/util/MapDocumentUtil.java @@ -97,6 +97,8 @@ public class MapDocumentUtil { Object o = json.read(jsonPath); if (o instanceof String) return (String) o; + if (o instanceof Number) + return (String) o.toString(); if (o instanceof JSONArray && ((JSONArray) o).size() > 0) return (String) ((JSONArray) o).get(0); return ""; diff --git a/dhp-pace-core/src/main/java/eu/dnetlib/pace/util/PaceResolver.java b/dhp-pace-core/src/main/java/eu/dnetlib/pace/util/PaceResolver.java index 252205c79..746892f0c 100644 --- a/dhp-pace-core/src/main/java/eu/dnetlib/pace/util/PaceResolver.java +++ b/dhp-pace-core/src/main/java/eu/dnetlib/pace/util/PaceResolver.java @@ -40,7 +40,7 @@ public class PaceResolver implements Serializable { Collectors.toMap(cl -> cl.getAnnotation(ComparatorClass.class).value(), cl -> (Class) cl)); } - public ClusteringFunction getClusteringFunction(String name, Map params) throws PaceException { + public ClusteringFunction getClusteringFunction(String name, Map params) throws PaceException { try { return clusteringFunctions.get(name).getDeclaredConstructor(Map.class).newInstance(params); } catch (InstantiationException | IllegalAccessException | InvocationTargetException diff --git a/dhp-pace-core/src/test/java/eu/dnetlib/pace/clustering/ClusteringFunctionTest.java b/dhp-pace-core/src/test/java/eu/dnetlib/pace/clustering/ClusteringFunctionTest.java index f9a1ea9e2..80e349a3f 100644 --- a/dhp-pace-core/src/test/java/eu/dnetlib/pace/clustering/ClusteringFunctionTest.java +++ b/dhp-pace-core/src/test/java/eu/dnetlib/pace/clustering/ClusteringFunctionTest.java @@ -15,7 +15,7 @@ import eu.dnetlib.pace.config.DedupConfig; public class ClusteringFunctionTest extends AbstractPaceTest { - private static Map params; + private static Map params; private static DedupConfig conf; @BeforeAll @@ -40,10 +40,10 @@ public class ClusteringFunctionTest extends AbstractPaceTest { @Test public void testNgram() { - params.put("ngramLen", 3); - params.put("max", 8); - params.put("maxPerToken", 2); - params.put("minNgramLen", 1); + params.put("ngramLen", "3"); + params.put("max", "8"); + params.put("maxPerToken", "2"); + params.put("minNgramLen", "1"); final ClusteringFunction ngram = new Ngrams(params); @@ -54,8 +54,8 @@ public class ClusteringFunctionTest extends AbstractPaceTest { @Test public void testNgramPairs() { - params.put("ngramLen", 3); - params.put("max", 2); + params.put("ngramLen", "3"); + params.put("max", "2"); final ClusteringFunction np = new NgramPairs(params); @@ -66,8 +66,8 @@ public class ClusteringFunctionTest extends AbstractPaceTest { @Test public void testSortedNgramPairs() { - params.put("ngramLen", 3); - params.put("max", 2); + params.put("ngramLen", "3"); + params.put("max", "2"); final ClusteringFunction np = new SortedNgramPairs(params); @@ -87,9 +87,9 @@ public class ClusteringFunctionTest extends AbstractPaceTest { @Test public void testAcronym() { - params.put("max", 4); - params.put("minLen", 1); - params.put("maxLen", 3); + params.put("max", "4"); + params.put("minLen", "1"); + params.put("maxLen", "3"); final ClusteringFunction acro = new Acronyms(params); @@ -100,8 +100,8 @@ public class ClusteringFunctionTest extends AbstractPaceTest { @Test public void testSuffixPrefix() { - params.put("len", 3); - params.put("max", 4); + params.put("len", "3"); + params.put("max", "4"); final ClusteringFunction sp = new SuffixPrefix(params); @@ -109,8 +109,8 @@ public class ClusteringFunctionTest extends AbstractPaceTest { System.out.println(s); System.out.println(sp.apply(conf, Lists.newArrayList(s))); - params.put("len", 3); - params.put("max", 1); + params.put("len", "3"); + params.put("max", "1"); System.out.println(sp.apply(conf, Lists.newArrayList("Framework for general-purpose deduplication"))); } @@ -118,8 +118,8 @@ public class ClusteringFunctionTest extends AbstractPaceTest { @Test public void testWordsSuffixPrefix() { - params.put("len", 3); - params.put("max", 4); + params.put("len", "3"); + params.put("max", "4"); final ClusteringFunction sp = new WordsSuffixPrefix(params); @@ -130,7 +130,7 @@ public class ClusteringFunctionTest extends AbstractPaceTest { @Test public void testWordsStatsSuffixPrefix() { - params.put("mod", 10); + params.put("mod", "10"); final ClusteringFunction sp = new WordsStatsSuffixPrefixChain(params); @@ -167,7 +167,7 @@ public class ClusteringFunctionTest extends AbstractPaceTest { @Test public void testFieldValue() { - params.put("randomLength", 5); + params.put("randomLength", "5"); final ClusteringFunction sp = new SpaceTrimmingFieldValue(params); diff --git a/dhp-pace-core/src/test/java/eu/dnetlib/pace/util/IncrementalConnectedComponentsTest.java b/dhp-pace-core/src/test/java/eu/dnetlib/pace/util/IncrementalConnectedComponentsTest.java new file mode 100644 index 000000000..b0f105d7c --- /dev/null +++ b/dhp-pace-core/src/test/java/eu/dnetlib/pace/util/IncrementalConnectedComponentsTest.java @@ -0,0 +1,40 @@ + +package eu.dnetlib.pace.util; + +import static org.junit.jupiter.api.Assertions.assertEquals; +import static org.junit.jupiter.api.Assertions.assertNull; + +import org.junit.jupiter.api.Test; + +public class IncrementalConnectedComponentsTest { + + @Test + public void transitiveClosureTest() { + IncrementalConnectedComponents icc = new IncrementalConnectedComponents(10); + + icc.connect(0, 1); + icc.connect(0, 2); + icc.connect(0, 3); + + icc.connect(1, 2); + icc.connect(1, 4); + icc.connect(1, 5); + + icc.connect(6, 7); + icc.connect(6, 9); + + assertEquals(icc.getConnections(0).toString(), "{0, 1, 2, 3, 4, 5}"); + assertEquals(icc.getConnections(1).toString(), "{0, 1, 2, 3, 4, 5}"); + assertEquals(icc.getConnections(2).toString(), "{0, 1, 2, 3, 4, 5}"); + assertEquals(icc.getConnections(3).toString(), "{0, 1, 2, 3, 4, 5}"); + assertEquals(icc.getConnections(4).toString(), "{0, 1, 2, 3, 4, 5}"); + assertEquals(icc.getConnections(5).toString(), "{0, 1, 2, 3, 4, 5}"); + + assertEquals(icc.getConnections(6).toString(), "{6, 7, 9}"); + assertEquals(icc.getConnections(7).toString(), "{6, 7, 9}"); + assertEquals(icc.getConnections(9).toString(), "{6, 7, 9}"); + + assertNull(icc.getConnections(8)); + } + +} diff --git a/dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/PromoteAction.java b/dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/PromoteAction.java new file mode 100644 index 000000000..8fb9c8c95 --- /dev/null +++ b/dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/PromoteAction.java @@ -0,0 +1,39 @@ +/* + * Copyright (c) 2024. + * SPDX-FileCopyrightText: © 2023 Consiglio Nazionale delle Ricerche + * SPDX-License-Identifier: AGPL-3.0-or-later + */ + +package eu.dnetlib.dhp.actionmanager.promote; + +/** Encodes the Actionset promotion strategies */ +public class PromoteAction { + + /** The supported actionset promotion strategies + * + * ENRICH: promotes only records in the actionset matching another record in the + * graph and enriches them applying the given MergeAndGet strategy + * UPSERT: promotes all the records in an actionset, matching records are updated + * using the given MergeAndGet strategy, the non-matching record as inserted as they are. + */ + public enum Strategy { + ENRICH, UPSERT + } + + /** + * Returns the string representation of the join type implementing the given PromoteAction. + * + * @param strategy the strategy to be used to promote the Actionset contents + * @return the join type used to implement the promotion strategy + */ + public static String joinTypeForStrategy(PromoteAction.Strategy strategy) { + switch (strategy) { + case ENRICH: + return "left_outer"; + case UPSERT: + return "full_outer"; + default: + throw new IllegalStateException("unsupported PromoteAction: " + strategy.toString()); + } + } +} diff --git a/dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadForGraphTableJob.java b/dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadForGraphTableJob.java index 7b024bea8..56cbda4d6 100644 --- a/dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadForGraphTableJob.java +++ b/dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadForGraphTableJob.java @@ -67,8 +67,9 @@ public class PromoteActionPayloadForGraphTableJob { String outputGraphTablePath = parser.get("outputGraphTablePath"); logger.info("outputGraphTablePath: {}", outputGraphTablePath); - MergeAndGet.Strategy strategy = MergeAndGet.Strategy.valueOf(parser.get("mergeAndGetStrategy").toUpperCase()); - logger.info("strategy: {}", strategy); + MergeAndGet.Strategy mergeAndGetStrategy = MergeAndGet.Strategy + .valueOf(parser.get("mergeAndGetStrategy").toUpperCase()); + logger.info("mergeAndGetStrategy: {}", mergeAndGetStrategy); Boolean shouldGroupById = Optional .ofNullable(parser.get("shouldGroupById")) @@ -76,6 +77,12 @@ public class PromoteActionPayloadForGraphTableJob { .orElse(true); logger.info("shouldGroupById: {}", shouldGroupById); + PromoteAction.Strategy promoteActionStrategy = Optional + .ofNullable(parser.get("promoteActionStrategy")) + .map(PromoteAction.Strategy::valueOf) + .orElse(PromoteAction.Strategy.UPSERT); + logger.info("promoteActionStrategy: {}", promoteActionStrategy); + @SuppressWarnings("unchecked") Class rowClazz = (Class) Class.forName(graphTableClassName); @SuppressWarnings("unchecked") @@ -97,7 +104,8 @@ public class PromoteActionPayloadForGraphTableJob { inputGraphTablePath, inputActionPayloadPath, outputGraphTablePath, - strategy, + mergeAndGetStrategy, + promoteActionStrategy, rowClazz, actionPayloadClazz, shouldGroupById); @@ -124,14 +132,16 @@ public class PromoteActionPayloadForGraphTableJob { String inputGraphTablePath, String inputActionPayloadPath, String outputGraphTablePath, - MergeAndGet.Strategy strategy, + MergeAndGet.Strategy mergeAndGetStrategy, + PromoteAction.Strategy promoteActionStrategy, Class rowClazz, Class actionPayloadClazz, Boolean shouldGroupById) { Dataset rowDS = readGraphTable(spark, inputGraphTablePath, rowClazz); Dataset actionPayloadDS = readActionPayload(spark, inputActionPayloadPath, actionPayloadClazz); Dataset result = promoteActionPayloadForGraphTable( - rowDS, actionPayloadDS, strategy, rowClazz, actionPayloadClazz, shouldGroupById) + rowDS, actionPayloadDS, mergeAndGetStrategy, promoteActionStrategy, rowClazz, actionPayloadClazz, + shouldGroupById) .map((MapFunction) value -> value, Encoders.bean(rowClazz)); saveGraphTable(result, outputGraphTablePath); @@ -183,7 +193,8 @@ public class PromoteActionPayloadForGraphTableJob { private static Dataset promoteActionPayloadForGraphTable( Dataset rowDS, Dataset actionPayloadDS, - MergeAndGet.Strategy strategy, + MergeAndGet.Strategy mergeAndGetStrategy, + PromoteAction.Strategy promoteActionStrategy, Class rowClazz, Class actionPayloadClazz, Boolean shouldGroupById) { @@ -195,8 +206,9 @@ public class PromoteActionPayloadForGraphTableJob { SerializableSupplier> rowIdFn = ModelSupport::idFn; SerializableSupplier> actionPayloadIdFn = ModelSupport::idFn; - SerializableSupplier> mergeRowWithActionPayloadAndGetFn = MergeAndGet.functionFor(strategy); - SerializableSupplier> mergeRowsAndGetFn = MergeAndGet.functionFor(strategy); + SerializableSupplier> mergeRowWithActionPayloadAndGetFn = MergeAndGet + .functionFor(mergeAndGetStrategy); + SerializableSupplier> mergeRowsAndGetFn = MergeAndGet.functionFor(mergeAndGetStrategy); SerializableSupplier zeroFn = zeroFn(rowClazz); SerializableSupplier> isNotZeroFn = PromoteActionPayloadForGraphTableJob::isNotZeroFnUsingIdOrSourceAndTarget; @@ -207,6 +219,7 @@ public class PromoteActionPayloadForGraphTableJob { rowIdFn, actionPayloadIdFn, mergeRowWithActionPayloadAndGetFn, + promoteActionStrategy, rowClazz, actionPayloadClazz); diff --git a/dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadFunctions.java b/dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadFunctions.java index d799c646b..f0b094240 100644 --- a/dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadFunctions.java +++ b/dhp-workflows/dhp-actionmanager/src/main/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadFunctions.java @@ -34,6 +34,7 @@ public class PromoteActionPayloadFunctions { * @param rowIdFn Function used to get the id of graph table row * @param actionPayloadIdFn Function used to get id of action payload instance * @param mergeAndGetFn Function used to merge graph table row and action payload instance + * @param promoteActionStrategy the Actionset promotion strategy * @param rowClazz Class of graph table * @param actionPayloadClazz Class of action payload * @param Type of graph table row @@ -46,6 +47,7 @@ public class PromoteActionPayloadFunctions { SerializableSupplier> rowIdFn, SerializableSupplier> actionPayloadIdFn, SerializableSupplier> mergeAndGetFn, + PromoteAction.Strategy promoteActionStrategy, Class rowClazz, Class actionPayloadClazz) { if (!isSubClass(rowClazz, actionPayloadClazz)) { @@ -61,7 +63,7 @@ public class PromoteActionPayloadFunctions { .joinWith( actionPayloadWithIdDS, rowWithIdDS.col("_1").equalTo(actionPayloadWithIdDS.col("_1")), - "full_outer") + PromoteAction.joinTypeForStrategy(promoteActionStrategy)) .map( (MapFunction, Tuple2>, G>) value -> { Optional rowOpt = Optional.ofNullable(value._1()).map(Tuple2::_2); diff --git a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/promote/promote_action_payload_for_graph_table_input_parameters.json b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/promote/promote_action_payload_for_graph_table_input_parameters.json index 00c9404ef..81a7c77d7 100644 --- a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/promote/promote_action_payload_for_graph_table_input_parameters.json +++ b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/promote/promote_action_payload_for_graph_table_input_parameters.json @@ -41,6 +41,12 @@ "paramDescription": "strategy for merging graph table objects with action payload instances, MERGE_FROM_AND_GET or SELECT_NEWER_AND_GET", "paramRequired": true }, + { + "paramName": "pas", + "paramLongName": "promoteActionStrategy", + "paramDescription": "strategy for promoting the actionset contents into the graph tables, ENRICH or UPSERT (default)", + "paramRequired": false + }, { "paramName": "sgid", "paramLongName": "shouldGroupById", diff --git a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/dataset/oozie_app/workflow.xml b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/dataset/oozie_app/workflow.xml index 4f374a75a..5401b45ca 100644 --- a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/dataset/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/dataset/oozie_app/workflow.xml @@ -115,6 +115,7 @@ --actionPayloadClassNameeu.dnetlib.dhp.schema.oaf.Dataset --outputGraphTablePath${workingDir}/dataset --mergeAndGetStrategy${mergeAndGetStrategy} + --promoteActionStrategy${promoteActionStrategy} --shouldGroupById${shouldGroupById} @@ -167,6 +168,7 @@ --actionPayloadClassNameeu.dnetlib.dhp.schema.oaf.Result --outputGraphTablePath${outputGraphRootPath}/dataset --mergeAndGetStrategy${mergeAndGetStrategy} + --promoteActionStrategy${promoteActionStrategy} --shouldGroupById${shouldGroupById} diff --git a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/datasource/oozie_app/workflow.xml b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/datasource/oozie_app/workflow.xml index c85ba4ac1..f9bd66ae3 100644 --- a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/datasource/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/datasource/oozie_app/workflow.xml @@ -106,6 +106,7 @@ --actionPayloadClassNameeu.dnetlib.dhp.schema.oaf.Datasource --outputGraphTablePath${outputGraphRootPath}/datasource --mergeAndGetStrategy${mergeAndGetStrategy} + --promoteActionStrategy${promoteActionStrategy} diff --git a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/organization/oozie_app/workflow.xml b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/organization/oozie_app/workflow.xml index 412cad70b..ebfdeee31 100644 --- a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/organization/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/organization/oozie_app/workflow.xml @@ -106,6 +106,7 @@ --actionPayloadClassNameeu.dnetlib.dhp.schema.oaf.Organization --outputGraphTablePath${outputGraphRootPath}/organization --mergeAndGetStrategy${mergeAndGetStrategy} + --promoteActionStrategy${promoteActionStrategy} diff --git a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/otherresearchproduct/oozie_app/workflow.xml b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/otherresearchproduct/oozie_app/workflow.xml index 7bac760e2..02399ed9b 100644 --- a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/otherresearchproduct/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/otherresearchproduct/oozie_app/workflow.xml @@ -114,6 +114,7 @@ --actionPayloadClassNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct --outputGraphTablePath${workingDir}/otherresearchproduct --mergeAndGetStrategy${mergeAndGetStrategy} + --promoteActionStrategy${promoteActionStrategy} --shouldGroupById${shouldGroupById} @@ -166,6 +167,7 @@ --actionPayloadClassNameeu.dnetlib.dhp.schema.oaf.Result --outputGraphTablePath${outputGraphRootPath}/otherresearchproduct --mergeAndGetStrategy${mergeAndGetStrategy} + --promoteActionStrategy${promoteActionStrategy} --shouldGroupById${shouldGroupById} diff --git a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/project/oozie_app/workflow.xml b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/project/oozie_app/workflow.xml index daf48e9d7..57c2357b4 100644 --- a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/project/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/project/oozie_app/workflow.xml @@ -106,6 +106,7 @@ --actionPayloadClassNameeu.dnetlib.dhp.schema.oaf.Project --outputGraphTablePath${outputGraphRootPath}/project --mergeAndGetStrategy${mergeAndGetStrategy} + --promoteActionStrategy${promoteActionStrategy} diff --git a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/publication/oozie_app/workflow.xml b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/publication/oozie_app/workflow.xml index b76dc82f1..92b114776 100644 --- a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/publication/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/publication/oozie_app/workflow.xml @@ -115,6 +115,7 @@ --actionPayloadClassNameeu.dnetlib.dhp.schema.oaf.Publication --outputGraphTablePath${workingDir}/publication --mergeAndGetStrategy${mergeAndGetStrategy} + --promoteActionStrategy${promoteActionStrategy} --shouldGroupById${shouldGroupById} @@ -167,6 +168,7 @@ --actionPayloadClassNameeu.dnetlib.dhp.schema.oaf.Result --outputGraphTablePath${outputGraphRootPath}/publication --mergeAndGetStrategy${mergeAndGetStrategy} + --promoteActionStrategy${promoteActionStrategy} --shouldGroupById${shouldGroupById} diff --git a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/relation/oozie_app/workflow.xml b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/relation/oozie_app/workflow.xml index d3086dbdc..e9e5f0b45 100644 --- a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/relation/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/relation/oozie_app/workflow.xml @@ -107,6 +107,7 @@ --actionPayloadClassNameeu.dnetlib.dhp.schema.oaf.Relation --outputGraphTablePath${outputGraphRootPath}/relation --mergeAndGetStrategy${mergeAndGetStrategy} + --promoteActionStrategy${promoteActionStrategy} diff --git a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/software/oozie_app/workflow.xml b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/software/oozie_app/workflow.xml index b5673b18f..1d36ddf94 100644 --- a/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/software/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-actionmanager/src/main/resources/eu/dnetlib/dhp/actionmanager/wf/software/oozie_app/workflow.xml @@ -114,6 +114,7 @@ --actionPayloadClassNameeu.dnetlib.dhp.schema.oaf.Software --outputGraphTablePath${workingDir}/software --mergeAndGetStrategy${mergeAndGetStrategy} + --promoteActionStrategy${promoteActionStrategy} --shouldGroupById${shouldGroupById} @@ -166,6 +167,7 @@ --actionPayloadClassNameeu.dnetlib.dhp.schema.oaf.Result --outputGraphTablePath${outputGraphRootPath}/software --mergeAndGetStrategy${mergeAndGetStrategy} + --promoteActionStrategy${promoteActionStrategy} --shouldGroupById${shouldGroupById} diff --git a/dhp-workflows/dhp-actionmanager/src/test/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadFunctionsTest.java b/dhp-workflows/dhp-actionmanager/src/test/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadFunctionsTest.java index cbc1bfaba..777e2fa1c 100644 --- a/dhp-workflows/dhp-actionmanager/src/test/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadFunctionsTest.java +++ b/dhp-workflows/dhp-actionmanager/src/test/java/eu/dnetlib/dhp/actionmanager/promote/PromoteActionPayloadFunctionsTest.java @@ -54,7 +54,7 @@ public class PromoteActionPayloadFunctionsTest { RuntimeException.class, () -> PromoteActionPayloadFunctions .joinGraphTableWithActionPayloadAndMerge( - null, null, null, null, null, OafImplSubSub.class, OafImpl.class)); + null, null, null, null, null, null, OafImplSubSub.class, OafImpl.class)); } @Test @@ -104,6 +104,7 @@ public class PromoteActionPayloadFunctionsTest { rowIdFn, actionPayloadIdFn, mergeAndGetFn, + PromoteAction.Strategy.UPSERT, OafImplSubSub.class, OafImplSubSub.class) .collectAsList(); @@ -183,6 +184,7 @@ public class PromoteActionPayloadFunctionsTest { rowIdFn, actionPayloadIdFn, mergeAndGetFn, + PromoteAction.Strategy.UPSERT, OafImplSubSub.class, OafImplSub.class) .collectAsList(); diff --git a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/PrepareFOSSparkJob.java b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/PrepareFOSSparkJob.java index 57ad8b96a..b1ffe7f37 100644 --- a/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/PrepareFOSSparkJob.java +++ b/dhp-workflows/dhp-aggregation/src/main/java/eu/dnetlib/dhp/actionmanager/createunresolvedentities/PrepareFOSSparkJob.java @@ -124,8 +124,19 @@ public class PrepareFOSSparkJob implements Serializable { FOSDataModel first) { level1.add(first.getLevel1()); level2.add(first.getLevel2()); - level3.add(first.getLevel3() + "@@" + first.getScoreL3()); - level4.add(first.getLevel4() + "@@" + first.getScoreL4()); + if (Optional.ofNullable(first.getLevel3()).isPresent() && + !first.getLevel3().equalsIgnoreCase(NA) && !first.getLevel3().equalsIgnoreCase(NULL) + && first.getLevel3() != null) + level3.add(first.getLevel3() + "@@" + first.getScoreL3()); + else + level3.add(NULL); + if (Optional.ofNullable(first.getLevel4()).isPresent() && + !first.getLevel4().equalsIgnoreCase(NA) && + !first.getLevel4().equalsIgnoreCase(NULL) && + first.getLevel4() != null) + level4.add(first.getLevel4() + "@@" + first.getScoreL4()); + else + level4.add(NULL); } } diff --git a/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/pubmed/oozie_app/workflow.xml b/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/pubmed/oozie_app/workflow.xml index 0e4e64842..30eb41469 100644 --- a/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/pubmed/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-aggregation/src/main/resources/eu/dnetlib/dhp/sx/bio/pubmed/oozie_app/workflow.xml @@ -1,4 +1,4 @@ - + baselineWorkingPath @@ -76,42 +76,42 @@ - - - - - oozie.launcher.mapreduce.user.classpath.first - true - - - eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode - --actionCOMMIT - --namenode${nameNode} - --mdStoreVersion${wf:actionData('StartTransaction')['mdStoreVersion']} - --mdStoreManagerURI${mdStoreManagerURI} - - - - + + + + + oozie.launcher.mapreduce.user.classpath.first + true + + + eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode + --actionCOMMIT + --namenode${nameNode} + --mdStoreVersion${wf:actionData('StartTransaction')['mdStoreVersion']} + --mdStoreManagerURI${mdStoreManagerURI} + + + + - - - - - oozie.launcher.mapreduce.user.classpath.first - true - - - eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode - --actionROLLBACK - --mdStoreVersion${wf:actionData('StartTransaction')['mdStoreVersion']} - --mdStoreManagerURI${mdStoreManagerURI} - - - - + + + + + oozie.launcher.mapreduce.user.classpath.first + true + + + eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode + --actionROLLBACK + --mdStoreVersion${wf:actionData('StartTransaction')['mdStoreVersion']} + --mdStoreManagerURI${mdStoreManagerURI} + + + + - + \ No newline at end of file diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/AbstractSparkAction.java b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/AbstractSparkAction.java index 68af3d699..0af7bb6d0 100644 --- a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/AbstractSparkAction.java +++ b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/AbstractSparkAction.java @@ -101,6 +101,10 @@ abstract class AbstractSparkAction implements Serializable { return SparkSession.builder().config(conf).getOrCreate(); } + protected static SparkSession getSparkWithHiveSession(SparkConf conf) { + return SparkSession.builder().enableHiveSupport().config(conf).getOrCreate(); + } + protected static void save(Dataset dataset, String outPath, SaveMode mode) { dataset.write().option("compression", "gzip").mode(mode).json(outPath); } diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/DedupRecordFactory.java b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/DedupRecordFactory.java index 60669106a..d5b106c81 100644 --- a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/DedupRecordFactory.java +++ b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/DedupRecordFactory.java @@ -1,128 +1,212 @@ package eu.dnetlib.dhp.oa.dedup; -import java.lang.reflect.InvocationTargetException; import java.util.*; -import java.util.stream.Collectors; +import java.util.stream.Stream; import org.apache.commons.beanutils.BeanUtils; import org.apache.commons.lang3.StringUtils; +import org.apache.spark.api.java.function.FlatMapFunction; import org.apache.spark.api.java.function.MapFunction; -import org.apache.spark.api.java.function.MapGroupsFunction; -import org.apache.spark.sql.Dataset; -import org.apache.spark.sql.Encoders; -import org.apache.spark.sql.SparkSession; - -import com.fasterxml.jackson.databind.DeserializationFeature; -import com.fasterxml.jackson.databind.ObjectMapper; -import com.google.common.collect.Lists; +import org.apache.spark.api.java.function.ReduceFunction; +import org.apache.spark.sql.*; import eu.dnetlib.dhp.oa.dedup.model.Identifier; import eu.dnetlib.dhp.oa.merge.AuthorMerger; import eu.dnetlib.dhp.schema.common.ModelSupport; -import eu.dnetlib.dhp.schema.oaf.*; +import eu.dnetlib.dhp.schema.oaf.Author; +import eu.dnetlib.dhp.schema.oaf.DataInfo; +import eu.dnetlib.dhp.schema.oaf.OafEntity; +import eu.dnetlib.dhp.schema.oaf.Result; import scala.Tuple2; +import scala.Tuple3; +import scala.collection.JavaConversions; public class DedupRecordFactory { + public static final class DedupRecordReduceState { + public final String dedupId; - protected static final ObjectMapper OBJECT_MAPPER = new ObjectMapper() - .configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false); + public final ArrayList aliases = new ArrayList<>(); + + public final HashSet acceptanceDate = new HashSet<>(); + + public OafEntity entity; + + public DedupRecordReduceState(String dedupId, String id, OafEntity entity) { + this.dedupId = dedupId; + this.entity = entity; + if (entity == null) { + aliases.add(id); + } else { + if (Result.class.isAssignableFrom(entity.getClass())) { + Result result = (Result) entity; + if (result.getDateofacceptance() != null + && StringUtils.isNotBlank(result.getDateofacceptance().getValue())) { + acceptanceDate.add(result.getDateofacceptance().getValue()); + } + } + } + } + + public String getDedupId() { + return dedupId; + } + } + + private static final int MAX_ACCEPTANCE_DATE = 20; private DedupRecordFactory() { } - public static Dataset createDedupRecord( + public static Dataset createDedupRecord( final SparkSession spark, final DataInfo dataInfo, final String mergeRelsInputPath, final String entitiesInputPath, - final Class clazz) { + final Class clazz) { - long ts = System.currentTimeMillis(); + final long ts = System.currentTimeMillis(); + final Encoder beanEncoder = Encoders.bean(clazz); + final Encoder kryoEncoder = Encoders.kryo(clazz); // - Dataset> entities = spark + Dataset entities = spark .read() - .textFile(entitiesInputPath) + .schema(Encoders.bean(clazz).schema()) + .json(entitiesInputPath) + .as(beanEncoder) .map( - (MapFunction>) it -> { - T entity = OBJECT_MAPPER.readValue(it, clazz); + (MapFunction>) entity -> { return new Tuple2<>(entity.getId(), entity); }, - Encoders.tuple(Encoders.STRING(), Encoders.kryo(clazz))); + Encoders.tuple(Encoders.STRING(), kryoEncoder)) + .selectExpr("_1 AS id", "_2 AS kryoObject"); // : source is the dedup_id, target is the id of the mergedIn - Dataset> mergeRels = spark + Dataset mergeRels = spark .read() .load(mergeRelsInputPath) - .as(Encoders.bean(Relation.class)) .where("relClass == 'merges'") - .map( - (MapFunction>) r -> new Tuple2<>(r.getSource(), r.getTarget()), - Encoders.tuple(Encoders.STRING(), Encoders.STRING())); + .selectExpr("source as dedupId", "target as id"); return mergeRels - .joinWith(entities, mergeRels.col("_2").equalTo(entities.col("_1")), "inner") + .join(entities, JavaConversions.asScalaBuffer(Collections.singletonList("id")), "left") + .select("dedupId", "id", "kryoObject") + .as(Encoders.tuple(Encoders.STRING(), Encoders.STRING(), kryoEncoder)) .map( - (MapFunction, Tuple2>, Tuple2>) value -> new Tuple2<>( - value._1()._1(), value._2()._2()), - Encoders.tuple(Encoders.STRING(), Encoders.kryo(clazz))) + (MapFunction, DedupRecordReduceState>) t -> new DedupRecordReduceState( + t._1(), t._2(), t._3()), + Encoders.kryo(DedupRecordReduceState.class)) .groupByKey( - (MapFunction, String>) Tuple2::_1, Encoders.STRING()) - .mapGroups( - (MapGroupsFunction, T>) (key, - values) -> entityMerger(key, values, ts, dataInfo, clazz), - Encoders.bean(clazz)); + (MapFunction) DedupRecordReduceState::getDedupId, Encoders.STRING()) + .reduceGroups( + (ReduceFunction) (t1, t2) -> { + if (t1.entity == null) { + t2.aliases.addAll(t1.aliases); + return t2; + } + if (t1.acceptanceDate.size() < MAX_ACCEPTANCE_DATE) { + t1.acceptanceDate.addAll(t2.acceptanceDate); + } + t1.aliases.addAll(t2.aliases); + t1.entity = reduceEntity(t1.entity, t2.entity); + + return t1; + }) + .flatMap((FlatMapFunction, OafEntity>) t -> { + String dedupId = t._1(); + DedupRecordReduceState agg = t._2(); + + if (agg.acceptanceDate.size() >= MAX_ACCEPTANCE_DATE) { + return Collections.emptyIterator(); + } + + return Stream + .concat( + Stream + .of(agg.getDedupId()) + .map(id -> createDedupOafEntity(id, agg.entity, dataInfo, ts)), + agg.aliases + .stream() + .map(id -> createMergedDedupAliasOafEntity(id, agg.entity, dataInfo, ts))) + .iterator(); + }, beanEncoder); } - public static T entityMerger( - String id, Iterator> entities, long ts, DataInfo dataInfo, Class clazz) - throws IllegalAccessException, InstantiationException, InvocationTargetException { + private static OafEntity createDedupOafEntity(String id, OafEntity base, DataInfo dataInfo, long ts) { + try { + OafEntity res = (OafEntity) BeanUtils.cloneBean(base); + res.setId(id); + res.setDataInfo(dataInfo); + res.setLastupdatetimestamp(ts); + return res; + } catch (Exception e) { + throw new RuntimeException(e); + } + } - final Comparator> idComparator = new IdentifierComparator<>(); + private static OafEntity createMergedDedupAliasOafEntity(String id, OafEntity base, DataInfo dataInfo, long ts) { + try { + OafEntity res = createDedupOafEntity(id, base, dataInfo, ts); + DataInfo ds = (DataInfo) BeanUtils.cloneBean(dataInfo); + ds.setDeletedbyinference(true); + res.setDataInfo(ds); + return res; + } catch (Exception e) { + throw new RuntimeException(e); + } + } - final LinkedList entityList = Lists - .newArrayList(entities) - .stream() - .map(t -> Identifier.newInstance(t._2())) - .sorted(idComparator) - .map(Identifier::getEntity) - .collect(Collectors.toCollection(LinkedList::new)); + private static OafEntity reduceEntity(OafEntity entity, OafEntity duplicate) { - final T entity = clazz.newInstance(); - final T first = entityList.removeFirst(); - - BeanUtils.copyProperties(entity, first); - - final List> authors = Lists.newArrayList(); - - entityList - .forEach( - duplicate -> { - entity.mergeFrom(duplicate); - if (ModelSupport.isSubClass(duplicate, Result.class)) { - Result r1 = (Result) duplicate; - Optional - .ofNullable(r1.getAuthor()) - .ifPresent(a -> authors.add(a)); - } - }); - - // set authors and date - if (ModelSupport.isSubClass(entity, Result.class)) { - Optional - .ofNullable(((Result) entity).getAuthor()) - .ifPresent(a -> authors.add(a)); - - ((Result) entity).setAuthor(AuthorMerger.merge(authors)); + if (duplicate == null) { + return entity; } - entity.setId(id); + int compare = new IdentifierComparator<>() + .compare(Identifier.newInstance(entity), Identifier.newInstance(duplicate)); - entity.setLastupdatetimestamp(ts); - entity.setDataInfo(dataInfo); + if (compare > 0) { + OafEntity swap = duplicate; + duplicate = entity; + entity = swap; + } + + entity.mergeFrom(duplicate); + + if (ModelSupport.isSubClass(duplicate, Result.class)) { + Result re = (Result) entity; + Result rd = (Result) duplicate; + + List> authors = new ArrayList<>(); + if (re.getAuthor() != null) { + authors.add(re.getAuthor()); + } + if (rd.getAuthor() != null) { + authors.add(rd.getAuthor()); + } + + re.setAuthor(AuthorMerger.merge(authors)); + } return entity; } + public static T entityMerger( + String id, Iterator> entities, long ts, DataInfo dataInfo, Class clazz) { + T base = entities.next()._2(); + + while (entities.hasNext()) { + T duplicate = entities.next()._2(); + if (duplicate != null) + base = (T) reduceEntity(base, duplicate); + } + + base.setId(id); + base.setDataInfo(dataInfo); + base.setLastupdatetimestamp(ts); + + return base; + } + } diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/IdGenerator.java b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/IdGenerator.java index 7e0d66062..1d3d4afdd 100644 --- a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/IdGenerator.java +++ b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/IdGenerator.java @@ -1,6 +1,7 @@ package eu.dnetlib.dhp.oa.dedup; +import static eu.dnetlib.dhp.utils.DHPUtils.md5; import static org.apache.commons.lang3.StringUtils.substringAfter; import static org.apache.commons.lang3.StringUtils.substringBefore; @@ -14,33 +15,36 @@ import eu.dnetlib.dhp.schema.oaf.utils.PidType; public class IdGenerator implements Serializable { // pick the best pid from the list (consider date and pidtype) - public static String generate(List> pids, String defaultID) { + public static String generate(List pids, String defaultID) { if (pids == null || pids.isEmpty()) return defaultID; return generateId(pids); } - private static String generateId(List> pids) { - Identifier bp = pids + private static String generateId(List pids) { + Identifier bp = pids .stream() .min(Identifier::compareTo) .orElseThrow(() -> new IllegalStateException("unable to generate id")); - String prefix = substringBefore(bp.getOriginalID(), "|"); - String ns = substringBefore(substringAfter(bp.getOriginalID(), "|"), "::"); - String suffix = substringAfter(bp.getOriginalID(), "::"); + return generate(bp.getOriginalID()); + } + + public static String generate(String originalId) { + String prefix = substringBefore(originalId, "|"); + String ns = substringBefore(substringAfter(originalId, "|"), "::"); + String suffix = substringAfter(originalId, "::"); final String pidType = substringBefore(ns, "_"); if (PidType.isValid(pidType)) { return prefix + "|" + dedupify(ns) + "::" + suffix; } else { - return prefix + "|dedup_wf_001::" + suffix; + return prefix + "|dedup_wf_002::" + md5(originalId); // hash the whole originalId to avoid collisions } } private static String dedupify(String ns) { - StringBuilder prefix; if (PidType.valueOf(substringBefore(ns, "_")) == PidType.openorgs) { prefix = new StringBuilder(substringBefore(ns, "_")); @@ -53,5 +57,4 @@ public class IdGenerator implements Serializable { } return prefix.substring(0, 12); } - } diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkCreateMergeRels.java b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkCreateMergeRels.java index babbaaabd..59626c141 100644 --- a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkCreateMergeRels.java +++ b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkCreateMergeRels.java @@ -3,49 +3,47 @@ package eu.dnetlib.dhp.oa.dedup; import static eu.dnetlib.dhp.schema.common.ModelConstants.DNET_PROVENANCE_ACTIONS; import static eu.dnetlib.dhp.schema.common.ModelConstants.PROVENANCE_DEDUP; +import static org.apache.spark.sql.functions.*; import java.io.IOException; -import java.util.*; -import java.util.stream.Collectors; +import java.time.LocalDate; +import java.util.ArrayList; +import java.util.Arrays; +import java.util.Collections; +import java.util.Optional; import org.apache.commons.io.IOUtils; +import org.apache.commons.lang3.StringUtils; import org.apache.spark.SparkConf; -import org.apache.spark.api.java.JavaPairRDD; -import org.apache.spark.api.java.JavaSparkContext; import org.apache.spark.api.java.function.FlatMapFunction; -import org.apache.spark.api.java.function.MapFunction; -import org.apache.spark.api.java.function.MapGroupsFunction; -import org.apache.spark.graphx.Edge; -import org.apache.spark.rdd.RDD; +import org.apache.spark.sql.*; import org.apache.spark.sql.Dataset; -import org.apache.spark.sql.Encoders; -import org.apache.spark.sql.SaveMode; -import org.apache.spark.sql.SparkSession; +import org.apache.spark.sql.catalyst.encoders.RowEncoder; +import org.apache.spark.sql.expressions.UserDefinedFunction; +import org.apache.spark.sql.expressions.Window; +import org.apache.spark.sql.expressions.WindowSpec; +import org.apache.spark.sql.types.DataTypes; +import org.apache.spark.sql.types.StructType; import org.dom4j.DocumentException; import org.slf4j.Logger; import org.slf4j.LoggerFactory; import org.xml.sax.SAXException; -import com.google.common.collect.Lists; import com.google.common.hash.Hashing; +import com.kwartile.lib.cc.ConnectedComponent; import eu.dnetlib.dhp.application.ArgumentApplicationParser; -import eu.dnetlib.dhp.oa.dedup.graph.ConnectedComponent; -import eu.dnetlib.dhp.oa.dedup.graph.GraphProcessor; -import eu.dnetlib.dhp.oa.dedup.model.Identifier; import eu.dnetlib.dhp.schema.common.EntityType; import eu.dnetlib.dhp.schema.common.ModelConstants; import eu.dnetlib.dhp.schema.common.ModelSupport; -import eu.dnetlib.dhp.schema.oaf.DataInfo; -import eu.dnetlib.dhp.schema.oaf.OafEntity; -import eu.dnetlib.dhp.schema.oaf.Qualifier; -import eu.dnetlib.dhp.schema.oaf.Relation; +import eu.dnetlib.dhp.schema.oaf.*; +import eu.dnetlib.dhp.schema.oaf.utils.PidType; import eu.dnetlib.dhp.utils.ISLookupClientFactory; import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException; import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService; import eu.dnetlib.pace.config.DedupConfig; -import eu.dnetlib.pace.util.MapDocumentUtil; -import scala.Tuple2; +import scala.Tuple3; +import scala.collection.JavaConversions; public class SparkCreateMergeRels extends AbstractSparkAction { @@ -68,10 +66,12 @@ public class SparkCreateMergeRels extends AbstractSparkAction { log.info("isLookupUrl {}", isLookUpUrl); SparkConf conf = new SparkConf(); + conf.set("hive.metastore.uris", parser.get("hiveMetastoreUris")); conf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer"); + conf.registerKryoClasses(ModelSupport.getOafModelClasses()); - new SparkCreateMergeRels(parser, getSparkSession(conf)) + new SparkCreateMergeRels(parser, getSparkWithHiveSession(conf)) .run(ISLookupClientFactory.getLookUpService(isLookUpUrl)); } @@ -87,14 +87,15 @@ public class SparkCreateMergeRels extends AbstractSparkAction { .ofNullable(parser.get("cutConnectedComponent")) .map(Integer::valueOf) .orElse(0); + + final String pivotHistoryDatabase = parser.get("pivotHistoryDatabase"); + log.info("connected component cut: '{}'", cut); log.info("graphBasePath: '{}'", graphBasePath); log.info("isLookUpUrl: '{}'", isLookUpUrl); log.info("actionSetId: '{}'", actionSetId); log.info("workingPath: '{}'", workingPath); - final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext()); - for (DedupConfig dedupConf : getConfigurations(isLookUpService, actionSetId)) { final String subEntity = dedupConf.getWf().getSubEntityValue(); final Class clazz = ModelSupport.entityTypes.get(EntityType.valueOf(subEntity)); @@ -106,113 +107,173 @@ public class SparkCreateMergeRels extends AbstractSparkAction { final String mergeRelPath = DedupUtility.createMergeRelPath(workingPath, actionSetId, subEntity); - // - JavaPairRDD vertexes = createVertexes(sc, graphBasePath, subEntity, dedupConf); - - final RDD> edgeRdd = spark + final Dataset simRels = spark .read() .load(DedupUtility.createSimRelPath(workingPath, actionSetId, subEntity)) - .as(Encoders.bean(Relation.class)) - .javaRDD() - .map(it -> new Edge<>(hash(it.getSource()), hash(it.getTarget()), it.getRelClass())) - .rdd(); + .select("source", "target"); - Dataset> rawMergeRels = spark - .createDataset( - GraphProcessor - .findCCs(vertexes.rdd(), edgeRdd, maxIterations, cut) - .toJavaRDD() - .filter(k -> k.getIds().size() > 1) - .flatMap(this::ccToRels) - .rdd(), - Encoders.tuple(Encoders.STRING(), Encoders.STRING())); + UserDefinedFunction hashUDF = functions + .udf( + (String s) -> hash(s), DataTypes.LongType); - Dataset> entities = spark + // + Dataset vertexIdMap = simRels + .selectExpr("source as id") + .union(simRels.selectExpr("target as id")) + .distinct() + .withColumn("vertexId", hashUDF.apply(functions.col("id"))); + + // transform simrels into pairs of numeric ids + final Dataset edges = spark .read() - .textFile(DedupUtility.createEntityPath(graphBasePath, subEntity)) - .map( - (MapFunction>) it -> { - OafEntity entity = OBJECT_MAPPER.readValue(it, clazz); - return new Tuple2<>(entity.getId(), entity); - }, - Encoders.tuple(Encoders.STRING(), Encoders.kryo(clazz))); + .load(DedupUtility.createSimRelPath(workingPath, actionSetId, subEntity)) + .select("source", "target") + .withColumn("source", hashUDF.apply(functions.col("source"))) + .withColumn("target", hashUDF.apply(functions.col("target"))); - Dataset mergeRels = rawMergeRels - .joinWith(entities, rawMergeRels.col("_2").equalTo(entities.col("_1")), "inner") - // , - .map( - (MapFunction, Tuple2>, Tuple2>) value -> new Tuple2<>( - value._1()._1(), value._2()._2()), - Encoders.tuple(Encoders.STRING(), Encoders.kryo(clazz))) - // - .groupByKey( - (MapFunction, String>) Tuple2::_1, Encoders.STRING()) - .mapGroups( - (MapGroupsFunction, ConnectedComponent>) this::generateID, - Encoders.bean(ConnectedComponent.class)) - // + // resolve connected components + // ("vertexId", "groupId") + Dataset cliques = ConnectedComponent + .runOnPairs(edges, 50, spark); + + // transform "vertexId" back to its original string value + // groupId is kept numeric as its string value is not used + // ("id", "groupId") + Dataset rawMergeRels = cliques + .join(vertexIdMap, JavaConversions.asScalaBuffer(Collections.singletonList("vertexId")), "inner") + .drop("vertexId") + .distinct(); + + // empty dataframe if historydatabase is not used + Dataset pivotHistory = spark + .createDataset( + Collections.emptyList(), + RowEncoder + .apply(StructType.fromDDL("id STRING, lastUsage STRING"))); + + if (StringUtils.isNotBlank(pivotHistoryDatabase)) { + pivotHistory = spark + .read() + .table(pivotHistoryDatabase + "." + subEntity) + .selectExpr("id", "lastUsage"); + } + + // depending on resulttype collectefrom and dateofacceptance are evaluated differently + String collectedfromExpr = "false AS collectedfrom"; + String dateExpr = "'' AS date"; + + if (Result.class.isAssignableFrom(clazz)) { + if (Publication.class.isAssignableFrom(clazz)) { + collectedfromExpr = "array_contains(collectedfrom.key, '" + ModelConstants.CROSSREF_ID + + "') AS collectedfrom"; + } else if (eu.dnetlib.dhp.schema.oaf.Dataset.class.isAssignableFrom(clazz)) { + collectedfromExpr = "array_contains(collectedfrom.key, '" + ModelConstants.DATACITE_ID + + "') AS collectedfrom"; + } + + dateExpr = "dateofacceptance.value AS date"; + } + + // cap pidType at w3id as from there on they are considered equal + UserDefinedFunction mapPid = udf( + (String s) -> Math.min(PidType.tryValueOf(s).ordinal(), PidType.w3id.ordinal()), DataTypes.IntegerType); + + UserDefinedFunction validDate = udf((String date) -> { + if (StringUtils.isNotBlank(date) + && date.matches(DatePicker.DATE_PATTERN) && DatePicker.inRange(date)) { + return date; + } + return LocalDate.now().plusWeeks(1).toString(); + }, DataTypes.StringType); + + Dataset pivotingData = spark + .read() + .schema(Encoders.bean(clazz).schema()) + .json(DedupUtility.createEntityPath(graphBasePath, subEntity)) + .selectExpr( + "id", + "regexp_extract(id, '^\\\\d+\\\\|([^_]+).*::', 1) AS pidType", + collectedfromExpr, + dateExpr) + .withColumn("pidType", mapPid.apply(col("pidType"))) // ordinal of pid type + .withColumn("date", validDate.apply(col("date"))); + + // ordering to selected pivot id + WindowSpec w = Window + .partitionBy("groupId") + .orderBy( + col("lastUsage").desc_nulls_last(), + col("pidType").asc_nulls_last(), + col("collectedfrom").desc_nulls_last(), + col("date").asc_nulls_last(), + col("id").asc_nulls_last()); + + Dataset output = rawMergeRels + .join(pivotHistory, JavaConversions.asScalaBuffer(Collections.singletonList("id")), "full") + .join(pivotingData, JavaConversions.asScalaBuffer(Collections.singletonList("id")), "left") + .withColumn("pivot", functions.first("id").over(w)) + .withColumn("position", functions.row_number().over(w)) .flatMap( - (FlatMapFunction) cc -> ccToMergeRel(cc, dedupConf), - Encoders.bean(Relation.class)); + (FlatMapFunction>) (Row r) -> { + String id = r.getAs("id"); + String dedupId = IdGenerator.generate(id); - saveParquet(mergeRels, mergeRelPath, SaveMode.Overwrite); + String pivot = r.getAs("pivot"); + String pivotDedupId = IdGenerator.generate(pivot); + // filter out id == pivotDedupId + // those are caused by claim expressed on pivotDedupId + // information will be merged after creating deduprecord + if (id.equals(pivotDedupId)) { + return Collections.emptyIterator(); + } + + ArrayList> res = new ArrayList<>(); + + // singleton pivots have null groupId as they do not match rawMergeRels + if (r.isNullAt(r.fieldIndex("groupId"))) { + // the record is existing if it matches pivotingData + if (!r.isNullAt(r.fieldIndex("collectedfrom"))) { + // create relation with old dedup id + res.add(new Tuple3<>(id, dedupId, null)); + } + return res.iterator(); + } + + // this was a pivot in a previous graph but it has been merged into a new group with different + // pivot + if (!r.isNullAt(r.fieldIndex("lastUsage")) && !pivot.equals(id) + && !dedupId.equals(pivotDedupId)) { + // materialize the previous dedup record as a merge relation with the new one + res.add(new Tuple3<>(dedupId, pivotDedupId, null)); + } + + // add merge relations + if (cut <= 0 || r. getAs("position") <= cut) { + res.add(new Tuple3<>(id, pivotDedupId, pivot)); + } + + return res.iterator(); + }, Encoders.tuple(Encoders.STRING(), Encoders.STRING(), Encoders.STRING())) + .distinct() + .flatMap( + (FlatMapFunction, Relation>) (Tuple3 r) -> { + String id = r._1(); + String dedupId = r._2(); + String pivot = r._3(); + + ArrayList res = new ArrayList<>(); + res.add(rel(pivot, dedupId, id, ModelConstants.MERGES, dedupConf)); + res.add(rel(pivot, id, dedupId, ModelConstants.IS_MERGED_IN, dedupConf)); + + return res.iterator(); + }, Encoders.bean(Relation.class)); + + saveParquet(output, mergeRelPath, SaveMode.Overwrite); } } - private ConnectedComponent generateID(String key, Iterator> values) { - - List> identifiers = Lists - .newArrayList(values) - .stream() - .map(v -> Identifier.newInstance(v._2())) - .collect(Collectors.toList()); - - String rootID = IdGenerator.generate(identifiers, key); - - if (Objects.equals(rootID, key)) - throw new IllegalStateException("generated default ID: " + rootID); - - return new ConnectedComponent(rootID, - identifiers.stream().map(i -> i.getEntity().getId()).collect(Collectors.toSet())); - } - - private JavaPairRDD createVertexes(JavaSparkContext sc, String graphBasePath, String subEntity, - DedupConfig dedupConf) { - - return sc - .textFile(DedupUtility.createEntityPath(graphBasePath, subEntity)) - .mapToPair(json -> { - String id = MapDocumentUtil.getJPathString(dedupConf.getWf().getIdPath(), json); - return new Tuple2<>(hash(id), id); - }); - } - - private Iterator> ccToRels(ConnectedComponent cc) { - return cc - .getIds() - .stream() - .map(id -> new Tuple2<>(cc.getCcId(), id)) - .iterator(); - } - - private Iterator ccToMergeRel(ConnectedComponent cc, DedupConfig dedupConf) { - return cc - .getIds() - .stream() - .flatMap( - id -> { - List tmp = new ArrayList<>(); - - tmp.add(rel(cc.getCcId(), id, ModelConstants.MERGES, dedupConf)); - tmp.add(rel(id, cc.getCcId(), ModelConstants.IS_MERGED_IN, dedupConf)); - - return tmp.stream(); - }) - .iterator(); - } - - private Relation rel(String source, String target, String relClass, DedupConfig dedupConf) { + private static Relation rel(String pivot, String source, String target, String relClass, DedupConfig dedupConf) { String entityType = dedupConf.getWf().getEntityType(); @@ -238,6 +299,14 @@ public class SparkCreateMergeRels extends AbstractSparkAction { // TODO calculate the trust value based on the similarity score of the elements in the CC r.setDataInfo(info); + + if (pivot != null) { + KeyValue pivotKV = new KeyValue(); + pivotKV.setKey("pivot"); + pivotKV.setValue(pivot); + + r.setProperties(Arrays.asList(pivotKV)); + } return r; } diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkWhitelistSimRels.java b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkWhitelistSimRels.java index 65ad0c327..60752a457 100644 --- a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkWhitelistSimRels.java +++ b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/SparkWhitelistSimRels.java @@ -91,18 +91,12 @@ public class SparkWhitelistSimRels extends AbstractSparkAction { Dataset entities = spark .read() .textFile(DedupUtility.createEntityPath(graphBasePath, subEntity)) - .repartition(numPartitions) - .withColumn("id", functions.get_json_object(new Column("value"), dedupConf.getWf().getIdPath())); + .select(functions.get_json_object(new Column("value"), dedupConf.getWf().getIdPath()).as("id")) + .distinct(); - Dataset whiteListRels1 = whiteListRels - .join(entities, entities.col("id").equalTo(whiteListRels.col("from")), "inner") - .select("from", "to"); - - Dataset whiteListRels2 = whiteListRels1 - .join(entities, whiteListRels1.col("to").equalTo(entities.col("id")), "inner") - .select("from", "to"); - - Dataset whiteListSimRels = whiteListRels2 + Dataset whiteListSimRels = whiteListRels + .join(entities, entities.col("id").equalTo(whiteListRels.col("from")), "leftsemi") + .join(entities, functions.col("to").equalTo(entities.col("id")), "leftsemi") .map( (MapFunction) r -> DedupUtility .createSimRel(r.getString(0), r.getString(1), entity), diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/graph/ConnectedComponent.java b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/graph/ConnectedComponent.java deleted file mode 100644 index 4a39a175d..000000000 --- a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/graph/ConnectedComponent.java +++ /dev/null @@ -1,100 +0,0 @@ - -package eu.dnetlib.dhp.oa.dedup.graph; - -import java.io.IOException; -import java.io.Serializable; -import java.util.Set; -import java.util.stream.Collectors; - -import org.apache.commons.lang3.StringUtils; -import org.codehaus.jackson.annotate.JsonIgnore; - -import com.fasterxml.jackson.databind.ObjectMapper; - -import eu.dnetlib.dhp.utils.DHPUtils; -import eu.dnetlib.pace.util.PaceException; - -public class ConnectedComponent implements Serializable { - - private String ccId; - private Set ids; - - private static final String CONNECTED_COMPONENT_ID_PREFIX = "connect_comp"; - - public ConnectedComponent(Set ids, final int cut) { - this.ids = ids; - - this.ccId = createDefaultID(); - - if (cut > 0 && ids.size() > cut) { - this.ids = ids - .stream() - .filter(id -> !ccId.equalsIgnoreCase(id)) - .limit(cut - 1) - .collect(Collectors.toSet()); -// this.ids.add(ccId); ?? - } - } - - public ConnectedComponent(String ccId, Set ids) { - this.ccId = ccId; - this.ids = ids; - } - - public String createDefaultID() { - if (ids.size() > 1) { - final String s = getMin(); - String prefix = s.split("\\|")[0]; - ccId = prefix + "|" + CONNECTED_COMPONENT_ID_PREFIX + "::" + DHPUtils.md5(s); - return ccId; - } else { - return ids.iterator().next(); - } - } - - @JsonIgnore - public String getMin() { - - final StringBuilder min = new StringBuilder(); - - ids - .forEach( - id -> { - if (StringUtils.isBlank(min.toString())) { - min.append(id); - } else { - if (min.toString().compareTo(id) > 0) { - min.setLength(0); - min.append(id); - } - } - }); - return min.toString(); - } - - @Override - public String toString() { - ObjectMapper mapper = new ObjectMapper(); - try { - return mapper.writeValueAsString(this); - } catch (IOException e) { - throw new PaceException("Failed to create Json: ", e); - } - } - - public Set getIds() { - return ids; - } - - public void setIds(Set ids) { - this.ids = ids; - } - - public String getCcId() { - return ccId; - } - - public void setCcId(String ccId) { - this.ccId = ccId; - } -} diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/graph/GraphProcessor.scala b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/graph/GraphProcessor.scala deleted file mode 100644 index f4dd85d75..000000000 --- a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/graph/GraphProcessor.scala +++ /dev/null @@ -1,37 +0,0 @@ -package eu.dnetlib.dhp.oa.dedup.graph - -import org.apache.spark.graphx._ -import org.apache.spark.rdd.RDD - -import scala.collection.JavaConversions; - -object GraphProcessor { - - def findCCs(vertexes: RDD[(VertexId, String)], edges: RDD[Edge[String]], maxIterations: Int, cut:Int): RDD[ConnectedComponent] = { - val graph: Graph[String, String] = Graph(vertexes, edges).partitionBy(PartitionStrategy.RandomVertexCut) //TODO remember to remove partitionby - val cc = graph.connectedComponents(maxIterations).vertices - - val joinResult = vertexes.leftOuterJoin(cc).map { - case (id, (openaireId, cc)) => { - if (cc.isEmpty) { - (id, openaireId) - } - else { - (cc.get, openaireId) - } - } - } - val connectedComponents = joinResult.groupByKey() - .map[ConnectedComponent](cc => asConnectedComponent(cc, cut)) - connectedComponents - } - - - - def asConnectedComponent(group: (VertexId, Iterable[String]), cut:Int): ConnectedComponent = { - val docs = group._2.toSet[String] - val connectedComponent = new ConnectedComponent(JavaConversions.setAsJavaSet[String](docs), cut); - connectedComponent - } - -} \ No newline at end of file diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/model/Identifier.java b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/model/Identifier.java index 0cba4fc3b..e03c3bf95 100644 --- a/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/model/Identifier.java +++ b/dhp-workflows/dhp-dedup-openaire/src/main/java/eu/dnetlib/dhp/oa/dedup/model/Identifier.java @@ -3,21 +3,21 @@ package eu.dnetlib.dhp.oa.dedup.model; import java.io.Serializable; import java.text.SimpleDateFormat; -import java.util.*; -import java.util.stream.Collectors; +import java.time.LocalDate; +import java.util.Date; +import java.util.List; +import java.util.Objects; import org.apache.commons.lang3.StringUtils; -import com.google.common.collect.Sets; - import eu.dnetlib.dhp.oa.dedup.DatePicker; import eu.dnetlib.dhp.oa.dedup.IdentifierComparator; import eu.dnetlib.dhp.schema.common.EntityType; -import eu.dnetlib.dhp.schema.common.ModelConstants; import eu.dnetlib.dhp.schema.common.ModelSupport; -import eu.dnetlib.dhp.schema.oaf.*; -import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils; -import eu.dnetlib.dhp.schema.oaf.utils.PidComparator; +import eu.dnetlib.dhp.schema.oaf.Field; +import eu.dnetlib.dhp.schema.oaf.KeyValue; +import eu.dnetlib.dhp.schema.oaf.OafEntity; +import eu.dnetlib.dhp.schema.oaf.Result; import eu.dnetlib.dhp.schema.oaf.utils.PidType; public class Identifier implements Serializable, Comparable> { @@ -50,7 +50,7 @@ public class Identifier implements Serializable, Comparable if (Objects.nonNull(date)) { return date; } else { - String sDate = BASE_DATE; + String sDate = LocalDate.now().plusDays(1).toString(); if (ModelSupport.isSubClass(getEntity(), Result.class)) { Result result = (Result) getEntity(); if (isWellformed(result.getDateofacceptance())) { diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/createCC_parameters.json b/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/createCC_parameters.json index b1df08535..4f9f4b0b5 100644 --- a/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/createCC_parameters.json +++ b/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/createCC_parameters.json @@ -28,5 +28,17 @@ "paramLongName": "workingPath", "paramDescription": "path for the working directory", "paramRequired": true + }, + { + "paramName":"h", + "paramLongName":"hiveMetastoreUris", + "paramDescription": "the hive metastore uris", + "paramRequired": true + }, + { + "paramName": "p", + "paramLongName": "pivotHistoryDatabase", + "paramDescription": "Pivot history database", + "paramRequired": false } ] \ No newline at end of file diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/pivothistory/oozie_app/config-default.xml b/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/pivothistory/oozie_app/config-default.xml new file mode 100644 index 000000000..17bb70647 --- /dev/null +++ b/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/pivothistory/oozie_app/config-default.xml @@ -0,0 +1,26 @@ + + + jobTracker + yarnRM + + + nameNode + hdfs://nameservice1 + + + oozie.use.system.libpath + true + + + oozie.action.sharelib.for.spark + spark2 + + + hiveMetastoreUris + thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 + + + sparkSqlWarehouseDir + /user/hive/warehouse + + \ No newline at end of file diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/pivothistory/oozie_app/sql.sql b/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/pivothistory/oozie_app/sql.sql new file mode 100644 index 000000000..86dbda1c9 --- /dev/null +++ b/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/pivothistory/oozie_app/sql.sql @@ -0,0 +1,62 @@ + +CREATE TABLE `${pivot_history_db}`.`dataset_new` STORED AS PARQUET AS +WITH pivots ( + SELECT property.value AS id, '${new_graph_date}' AS usedIn FROM `${new_graph_db}`.`relation` + LEFT SEMI JOIN `${new_graph_db}`.`dataset` ON relation.source = dataset.id + LATERAL VIEW EXPLODE(properties) AS property WHERE relClass = 'isMergedIn' AND property.key = 'pivot' +UNION + SELECT id, usedIn FROM `${pivot_history_db}`.`dataset` LATERAL VIEW EXPLODE(usages) AS usedIn +) +SELECT id, min(usedIn) as firstUsage, max(usedIn) as lastUsage, collect_set(usedIn) as usages + FROM pivots + GROUP BY id; /*EOS*/ +CREATE TABLE `${pivot_history_db}`.`publication_new` STORED AS PARQUET AS +WITH pivots ( + SELECT property.value AS id, '${new_graph_date}' AS usedIn FROM `${new_graph_db}`.`relation` + LEFT SEMI JOIN `${new_graph_db}`.`publication` ON relation.source = publication.id + LATERAL VIEW EXPLODE(properties) AS property WHERE relClass = 'isMergedIn' AND property.key = 'pivot' +UNION + SELECT id, usedIn FROM `${pivot_history_db}`.`publication` LATERAL VIEW EXPLODE(usages) AS usedIn +) +SELECT id, min(usedIn) as firstUsage, max(usedIn) as lastUsage, collect_set(usedIn) as usages + FROM pivots + GROUP BY id; /*EOS*/ +CREATE TABLE `${pivot_history_db}`.`software_new` STORED AS PARQUET AS +WITH pivots ( + SELECT property.value AS id, '${new_graph_date}' AS usedIn FROM `${new_graph_db}`.`relation` + LEFT SEMI JOIN `${new_graph_db}`.`software` ON relation.source = software.id + LATERAL VIEW EXPLODE(properties) AS property WHERE relClass = 'isMergedIn' AND property.key = 'pivot' +UNION + SELECT id, usedIn FROM `${pivot_history_db}`.`software` LATERAL VIEW EXPLODE(usages) AS usedIn +) +SELECT id, min(usedIn) as firstUsage, max(usedIn) as lastUsage, collect_set(usedIn) as usages + FROM pivots + GROUP BY id; /*EOS*/ +CREATE TABLE `${pivot_history_db}`.`otherresearchproduct_new` STORED AS PARQUET AS +WITH pivots ( + SELECT property.value AS id, '${new_graph_date}' AS usedIn FROM `${new_graph_db}`.`relation` + LEFT SEMI JOIN `${new_graph_db}`.`otherresearchproduct` ON relation.source = otherresearchproduct.id + LATERAL VIEW EXPLODE(properties) AS property WHERE relClass = 'isMergedIn' AND property.key = 'pivot' +UNION + SELECT id, usedIn FROM `${pivot_history_db}`.`otherresearchproduct` LATERAL VIEW EXPLODE(usages) AS usedIn +) +SELECT id, min(usedIn) as firstUsage, max(usedIn) as lastUsage, collect_set(usedIn) as usages + FROM pivots + GROUP BY id; /*EOS*/ + + +DROP TABLE IF EXISTS `${pivot_history_db}`.`dataset_old`; /*EOS*/ +ALTER TABLE `${pivot_history_db}`.`dataset` RENAME TO `${pivot_history_db}`.`dataset_old`; /*EOS*/ +ALTER TABLE `${pivot_history_db}`.`dataset_new` RENAME TO `${pivot_history_db}`.`dataset`; /*EOS*/ + +DROP TABLE IF EXISTS `${pivot_history_db}`.`publication_old`; /*EOS*/ +ALTER TABLE `${pivot_history_db}`.`publication` RENAME TO `${pivot_history_db}`.`publication_old`; /*EOS*/ +ALTER TABLE `${pivot_history_db}`.`publication_new` RENAME TO `${pivot_history_db}`.`publication`; /*EOS*/ + +DROP TABLE IF EXISTS `${pivot_history_db}`.`software_old`; /*EOS*/ +ALTER TABLE `${pivot_history_db}`.`software` RENAME TO `${pivot_history_db}`.`software_old`; /*EOS*/ +ALTER TABLE `${pivot_history_db}`.`software_new` RENAME TO `${pivot_history_db}`.`software`; /*EOS*/ + +DROP TABLE IF EXISTS `${pivot_history_db}`.`otherresearchproduct_old`; /*EOS*/ +ALTER TABLE `${pivot_history_db}`.`otherresearchproduct` RENAME TO `${pivot_history_db}`.`otherresearchproduct_old`; /*EOS*/ +ALTER TABLE `${pivot_history_db}`.`otherresearchproduct_new` RENAME TO `${pivot_history_db}`.`otherresearchproduct`; /*EOS*/ diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/pivothistory/oozie_app/workflow.xml b/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/pivothistory/oozie_app/workflow.xml new file mode 100644 index 000000000..d562f088e --- /dev/null +++ b/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/pivothistory/oozie_app/workflow.xml @@ -0,0 +1,95 @@ + + + + + pivot_history_db + + Pivot history DB on hive + + + new_graph_db + + New graph DB on hive + + + new_graph_date + + Creation date of new graph db + + + + + hiveMetastoreUris + hive server metastore URIs + + + sparkSqlWarehouseDir + + + + sparkClusterOpts + --conf spark.network.timeout=600 --conf spark.extraListeners= --conf spark.sql.queryExecutionListeners= --conf spark.yarn.historyServer.address=http://iis-cdh5-test-m3.ocean.icm.edu.pl:18088 --conf spark.eventLog.dir=hdfs://nameservice1/user/spark/applicationHistory + spark cluster-wide options + + + sparkResourceOpts + --executor-memory=3G --conf spark.executor.memoryOverhead=3G --executor-cores=6 --driver-memory=8G --driver-cores=4 + spark resource options + + + sparkApplicationOpts + --conf spark.sql.shuffle.partitions=3840 + spark resource options + + + + + ${jobTracker} + ${nameNode} + + + mapreduce.job.queuename + ${queueName} + + + oozie.launcher.mapred.job.queue.name + ${oozieLauncherQueueName} + + + oozie.action.sharelib.for.spark + ${oozieActionShareLibForSpark2} + + + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + yarn + cluster + Upgrade Pivot History + eu.dnetlib.dhp.oozie.RunSQLSparkJob + dhp-dedup-openaire-${projectVersion}.jar + + --conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir} + ${sparkClusterOpts} + ${sparkResourceOpts} + ${sparkApplicationOpts} + + --hiveMetastoreUris${hiveMetastoreUris} + --sqleu/dnetlib/dhp/oa/dedup/pivothistory/oozie_app/sql.sql + --pivot_history_db${pivot_history_db} + --new_graph_db${new_graph_db} + --new_graph_date${new_graph_date} + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/scan/oozie_app/config-default.xml b/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/scan/oozie_app/config-default.xml index 2e0ed9aee..cd29965e3 100644 --- a/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/scan/oozie_app/config-default.xml +++ b/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/scan/oozie_app/config-default.xml @@ -15,4 +15,8 @@ oozie.action.sharelib.for.spark spark2 + + hiveMetastoreUris + thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 + \ No newline at end of file diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/scan/oozie_app/workflow.xml b/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/scan/oozie_app/workflow.xml index ba2270c8a..49a331def 100644 --- a/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/scan/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-dedup-openaire/src/main/resources/eu/dnetlib/dhp/oa/dedup/scan/oozie_app/workflow.xml @@ -188,6 +188,8 @@ --isLookUpUrl${isLookUpUrl} --actionSetId${actionSetId} --cutConnectedComponent${cutConnectedComponent} + --hiveMetastoreUris${hiveMetastoreUris} + --pivotHistoryDatabase${pivotHistoryDatabase} diff --git a/dhp-workflows/dhp-dedup-openaire/src/main/scala/com/kwartile/lib/cc/ConnectedComponent.scala b/dhp-workflows/dhp-dedup-openaire/src/main/scala/com/kwartile/lib/cc/ConnectedComponent.scala new file mode 100644 index 000000000..4c3362235 --- /dev/null +++ b/dhp-workflows/dhp-dedup-openaire/src/main/scala/com/kwartile/lib/cc/ConnectedComponent.scala @@ -0,0 +1,335 @@ +/** Copyright (c) 2017 Kwartile, Inc., http://www.kwartile.com + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in all + * copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +/** Map-reduce implementation of Connected Component + * Given lists of subgraphs, returns all the nodes that are connected. + */ + +package com.kwartile.lib.cc + +import org.apache.spark.rdd.RDD +import org.apache.spark.sql.{Dataset, Row, SparkSession} +import org.apache.spark.storage.StorageLevel + +import scala.annotation.tailrec +import scala.collection.mutable + +object ConnectedComponent extends Serializable { + + /** Applies Small Star operation on RDD of nodePairs + * + * @param nodePairs on which to apply Small Star operations + * @return new nodePairs after the operation and conncectivy change count + */ + private def smallStar(nodePairs: RDD[(Long, Long)]): (RDD[(Long, Long)], Long) = { + + /** generate RDD of (self, List(neighbors)) where self > neighbors + * E.g.: nodePairs (1, 4), (6, 1), (3, 2), (6, 5) + * will result into (4, List(1)), (6, List(1)), (3, List(2)), (6, List(5)) + */ + val neighbors = nodePairs.map(x => { + val (self, neighbor) = (x._1, x._2) + if (self > neighbor) + (self, neighbor) + else + (neighbor, self) + }) + + /** reduce on self to get list of all its neighbors. + * E.g: (4, List(1)), (6, List(1)), (3, List(2)), (6, List(5)) + * will result into (4, List(1)), (6, List(1, 5)), (3, List(2)) + * Note: + * (1) you may need to tweak number of partitions. + * (2) also, watch out for data skew. In that case, consider using rangePartitioner + */ + val empty = mutable.HashSet[Long]() + val allNeighbors = neighbors.aggregateByKey(empty)( + (lb, v) => lb += v, + (lb1, lb2) => lb1 ++ lb2 + ) + + /** Apply Small Star operation on (self, List(neighbor)) to get newNodePairs and count the change in connectivity + */ + + val newNodePairsWithChangeCount = allNeighbors + .map(x => { + val self = x._1 + val neighbors = x._2.toList + val minNode = argMin(self :: neighbors) + val newNodePairs = (self :: neighbors) + .map(neighbor => { + (neighbor, minNode) + }) + .filter(x => { + val neighbor = x._1 + val minNode = x._2 + (neighbor <= self && neighbor != minNode) || (self == neighbor) + }) + val uniqueNewNodePairs = newNodePairs.toSet.toList + + /** We count the change by taking a diff of the new node pairs with the old node pairs + */ + val connectivityChangeCount = (uniqueNewNodePairs diff neighbors.map((self, _))).length + (uniqueNewNodePairs, connectivityChangeCount) + }) + .persist(StorageLevel.MEMORY_AND_DISK_SER) + + /** Sum all the changeCounts + */ + val totalConnectivityCountChange = newNodePairsWithChangeCount + .mapPartitions(iter => { + val (v, l) = iter.toSeq.unzip + val sum = l.sum + Iterator(sum) + }) + .sum + .toLong + + val newNodePairs = newNodePairsWithChangeCount.map(x => x._1).flatMap(x => x) + newNodePairsWithChangeCount.unpersist(false) + (newNodePairs, totalConnectivityCountChange) + } + + /** Apply Large Star operation on a RDD of nodePairs + * + * @param nodePairs on which to apply Large Star operations + * @return new nodePairs after the operation and conncectivy change count + */ + private def largeStar(nodePairs: RDD[(Long, Long)]): (RDD[(Long, Long)], Long) = { + + /** generate RDD of (self, List(neighbors)) + * E.g.: nodePairs (1, 4), (6, 1), (3, 2), (6, 5) + * will result into (4, List(1)), (1, List(4)), (6, List(1)), (1, List(6)), (3, List(2)), (2, List(3)), (6, List(5)), (5, List(6)) + */ + + val neighbors = nodePairs.flatMap(x => { + val (self, neighbor) = (x._1, x._2) + if (self == neighbor) + List((self, neighbor)) + else + List((self, neighbor), (neighbor, self)) + }) + + /** reduce on self to get list of all its neighbors. + * E.g: (4, List(1)), (1, List(4)), (6, List(1)), (1, List(6)), (3, List(2)), (2, List(3)), (6, List(5)), (5, List(6)) + * will result into (4, List(1)), (1, List(4, 6)), (6, List(1, 5)), (3, List(2)), (2, List(3)), (5, List(6)) + * Note: + * (1) you may need to tweak number of partitions. + * (2) also, watch out for data skew. In that case, consider using rangePartitioner + */ + + val localAdd = (s: mutable.HashSet[Long], v: Long) => s += v + val partitionAdd = (s1: mutable.HashSet[Long], s2: mutable.HashSet[Long]) => s1 ++= s2 + val allNeighbors = + neighbors.aggregateByKey(mutable.HashSet.empty[Long] /*, rangePartitioner*/ )(localAdd, partitionAdd) + + /** Apply Large Star operation on (self, List(neighbor)) to get newNodePairs and count the change in connectivity + */ + + val newNodePairsWithChangeCount = allNeighbors + .map(x => { + val self = x._1 + val neighbors = x._2.toList + val minNode = argMin(self :: neighbors) + val newNodePairs = (self :: neighbors) + .map(neighbor => { + (neighbor, minNode) + }) + .filter(x => { + val neighbor = x._1 + val minNode = x._2 + neighbor > self || neighbor == minNode + }) + + val uniqueNewNodePairs = newNodePairs.toSet.toList + val connectivityChangeCount = (uniqueNewNodePairs diff neighbors.map((self, _))).length + (uniqueNewNodePairs, connectivityChangeCount) + }) + .persist(StorageLevel.MEMORY_AND_DISK_SER) + + val totalConnectivityCountChange = newNodePairsWithChangeCount + .mapPartitions(iter => { + val (v, l) = iter.toSeq.unzip + val sum = l.sum + Iterator(sum) + }) + .sum + .toLong + + /** Sum all the changeCounts + */ + val newNodePairs = newNodePairsWithChangeCount.map(x => x._1).flatMap(x => x) + newNodePairsWithChangeCount.unpersist(false) + (newNodePairs, totalConnectivityCountChange) + } + + private def argMin(nodes: List[Long]): Long = { + nodes.min(Ordering.by((node: Long) => node)) + } + + /** Build nodePairs given a list of nodes. A list of nodes represents a subgraph. + * + * @param nodes that are part of a subgraph + * @return nodePairs for a subgraph + */ + private def buildPairs(nodes: List[Long]): List[(Long, Long)] = { + buildPairs(nodes.head, nodes.tail, null.asInstanceOf[List[(Long, Long)]]) + } + + @tailrec + private def buildPairs(node: Long, neighbors: List[Long], partialPairs: List[(Long, Long)]): List[(Long, Long)] = { + if (neighbors.isEmpty) { + if (partialPairs != null) + List((node, node)) ::: partialPairs + else + List((node, node)) + } else if (neighbors.length == 1) { + val neighbor = neighbors(0) + if (node > neighbor) + if (partialPairs != null) List((node, neighbor)) ::: partialPairs else List((node, neighbor)) + else if (partialPairs != null) List((neighbor, node)) ::: partialPairs + else List((neighbor, node)) + } else { + val newPartialPairs = neighbors + .map(neighbor => { + if (node > neighbor) + List((node, neighbor)) + else + List((neighbor, node)) + }) + .flatMap(x => x) + + if (partialPairs != null) + buildPairs(neighbors.head, neighbors.tail, newPartialPairs ::: partialPairs) + else + buildPairs(neighbors.head, neighbors.tail, newPartialPairs) + } + } + + /** Implements alternatingAlgo. Converges when the changeCount is either 0 or does not change from the previous iteration + * + * @param nodePairs for a graph + * @param largeStarConnectivityChangeCount change count that resulted from the previous iteration + * @param smallStarConnectivityChangeCount change count that resulted from the previous iteration + * @param didConverge flag to indicate the alorigth converged + * @param currIterationCount counter to capture number of iterations + * @param maxIterationCount maximum number iterations to try before giving up + * @return RDD of nodePairs + */ + + @tailrec + private def alternatingAlgo( + nodePairs: RDD[(Long, Long)], + largeStarConnectivityChangeCount: Long, + smallStarConnectivityChangeCount: Long, + didConverge: Boolean, + currIterationCount: Int, + maxIterationCount: Int + ): (RDD[(Long, Long)], Boolean, Long) = { + + val iterationCount = currIterationCount + 1 + if (didConverge) + (nodePairs, true, currIterationCount) + else if (currIterationCount >= maxIterationCount) { + (nodePairs, false, currIterationCount) + } else { + + val (nodePairsLargeStar, currLargeStarConnectivityChangeCount) = largeStar(nodePairs) + val (nodePairsSmallStar, currSmallStarConnectivityChangeCount) = smallStar(nodePairsLargeStar) + + if ( + (currLargeStarConnectivityChangeCount == largeStarConnectivityChangeCount && + currSmallStarConnectivityChangeCount == smallStarConnectivityChangeCount) || + (currSmallStarConnectivityChangeCount == 0 && currLargeStarConnectivityChangeCount == 0) + ) { + alternatingAlgo( + nodePairsSmallStar, + currLargeStarConnectivityChangeCount, + currSmallStarConnectivityChangeCount, + true, + iterationCount, + maxIterationCount + ) + } else { + alternatingAlgo( + nodePairsSmallStar, + currLargeStarConnectivityChangeCount, + currSmallStarConnectivityChangeCount, + false, + iterationCount, + maxIterationCount + ) + } + } + } + + /** Driver function + * + * @param cliques list of nodes representing subgraphs (or cliques) + * @param maxIterationCount maximum number iterations to try before giving up + * @return Connected Components as nodePairs where second member of the nodePair is the minimum node in the component + */ + def run(cliques: RDD[List[Long]], maxIterationCount: Int): (RDD[(Long, Long)], Boolean, Long) = { + + val nodePairs = cliques + .map(aClique => { + buildPairs(aClique) + }) + .flatMap(x => x) + + val (cc, didConverge, iterCount) = alternatingAlgo(nodePairs, 9999999L, 9999999L, false, 0, maxIterationCount) + + if (didConverge) { + (cc, didConverge, iterCount) + } else { + (null.asInstanceOf[RDD[(Long, Long)]], didConverge, iterCount) + } + } + + def runOnPairs(nodePairs: RDD[(Long, Long)], maxIterationCount: Int): (RDD[(Long, Long)], Boolean, Long) = { + val (cc, didConverge, iterCount) = alternatingAlgo(nodePairs, 9999999L, 9999999L, false, 0, maxIterationCount) + + if (didConverge) { + (cc, didConverge, iterCount) + } else { + (null.asInstanceOf[RDD[(Long, Long)]], didConverge, iterCount) + } + } + + def runOnPairs(nodePairs: Dataset[Row], maxIterationCount: Int)(implicit spark: SparkSession): Dataset[Row] = { + import spark.implicits._ + + val (cc, didConverge, iterCount) = alternatingAlgo( + nodePairs.map(e => (e.getLong(0), e.getLong(1))).rdd, + 9999999L, + 9999999L, + false, + 0, + maxIterationCount + ) + + if (didConverge) { + cc.toDF("vertexId", "groupId") + } else { + null.asInstanceOf[Dataset[Row]] + } + } + +} diff --git a/dhp-workflows/dhp-dedup-openaire/src/test/java/eu/dnetlib/dhp/oa/dedup/SparkDedupTest.java b/dhp-workflows/dhp-dedup-openaire/src/test/java/eu/dnetlib/dhp/oa/dedup/SparkDedupTest.java index 6c4935637..8b3480e60 100644 --- a/dhp-workflows/dhp-dedup-openaire/src/test/java/eu/dnetlib/dhp/oa/dedup/SparkDedupTest.java +++ b/dhp-workflows/dhp-dedup-openaire/src/test/java/eu/dnetlib/dhp/oa/dedup/SparkDedupTest.java @@ -41,9 +41,13 @@ import com.google.common.collect.Sets; import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.schema.common.ModelConstants; +import eu.dnetlib.dhp.schema.common.ModelSupport; import eu.dnetlib.dhp.schema.oaf.*; +import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils; +import eu.dnetlib.dhp.schema.sx.OafUtils; import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException; import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService; +import scala.Tuple2; @ExtendWith(MockitoExtension.class) @TestMethodOrder(MethodOrderer.OrderAnnotation.class) @@ -97,6 +101,7 @@ public class SparkDedupTest implements Serializable { final SparkConf conf = new SparkConf(); conf.set("spark.sql.shuffle.partitions", "200"); + conf.set("spark.sql.warehouse.dir", testOutputBasePath + "/spark-warehouse"); spark = SparkSession .builder() .appName(SparkDedupTest.class.getSimpleName()) @@ -186,11 +191,11 @@ public class SparkDedupTest implements Serializable { System.out.println("ds_simrel = " + ds_simrel); System.out.println("orp_simrel = " + orp_simrel); - assertEquals(1538, orgs_simrel); - assertEquals(3523, pubs_simrel); - assertEquals(168, sw_simrel); - assertEquals(221, ds_simrel); - assertEquals(3392, orp_simrel); + assertEquals(751, orgs_simrel); + assertEquals(546, pubs_simrel); + assertEquals(113, sw_simrel); + assertEquals(148, ds_simrel); + assertEquals(280, orp_simrel); } @@ -235,10 +240,10 @@ public class SparkDedupTest implements Serializable { .count(); // entities simrels supposed to be equal to the number of previous step (no rels in whitelist) - assertEquals(1538, orgs_simrel); - assertEquals(3523, pubs_simrel); - assertEquals(221, ds_simrel); - assertEquals(3392, orp_simrel); + assertEquals(751, orgs_simrel); + assertEquals(546, pubs_simrel); + assertEquals(148, ds_simrel); + assertEquals(280, orp_simrel); // System.out.println("orgs_simrel = " + orgs_simrel); // System.out.println("pubs_simrel = " + pubs_simrel); // System.out.println("ds_simrel = " + ds_simrel); @@ -268,7 +273,7 @@ public class SparkDedupTest implements Serializable { && rel.getTarget().equalsIgnoreCase(whiteList.get(1).split(WHITELIST_SEPARATOR)[1])) .count() > 0); - assertEquals(170, sw_simrel.count()); + assertEquals(115, sw_simrel.count()); // System.out.println("sw_simrel = " + sw_simrel.count()); } @@ -292,7 +297,9 @@ public class SparkDedupTest implements Serializable { "-w", testOutputBasePath, "-cc", - "3" + "3", + "-h", + "" }); new SparkCreateMergeRels(parser, spark).run(isLookUpService); @@ -365,6 +372,113 @@ public class SparkDedupTest implements Serializable { .deleteDirectory(new File(testOutputBasePath + "/" + testActionSetId + "/otherresearchproduct_mergerel")); } + @Test + @Order(3) + void createMergeRelsWithPivotHistoryTest() throws Exception { + + ArgumentApplicationParser parser = new ArgumentApplicationParser( + classPathResourceAsString("/eu/dnetlib/dhp/oa/dedup/createCC_parameters.json")); + + spark.sql("CREATE DATABASE IF NOT EXISTS pivot_history_test"); + ModelSupport.oafTypes.keySet().forEach(entityType -> { + try { + spark + .read() + .json( + Paths + .get(SparkDedupTest.class.getResource("/eu/dnetlib/dhp/dedup/pivot_history").toURI()) + .toFile() + .getAbsolutePath()) + .write() + .mode("overwrite") + .saveAsTable("pivot_history_test." + entityType); + } catch (URISyntaxException e) { + throw new RuntimeException(e); + } + }); + + parser + .parseArgument( + new String[] { + "-i", + testGraphBasePath, + "-asi", + testActionSetId, + "-la", + "lookupurl", + "-w", + testOutputBasePath, + "-h", + "", + "-pivotHistoryDatabase", + "pivot_history_test" + + }); + + new SparkCreateMergeRels(parser, spark).run(isLookUpService); + + long orgs_mergerel = spark + .read() + .load(testOutputBasePath + "/" + testActionSetId + "/organization_mergerel") + .count(); + final Dataset pubs = spark + .read() + .load(testOutputBasePath + "/" + testActionSetId + "/publication_mergerel") + .as(Encoders.bean(Relation.class)); + long sw_mergerel = spark + .read() + .load(testOutputBasePath + "/" + testActionSetId + "/software_mergerel") + .count(); + long ds_mergerel = spark + .read() + .load(testOutputBasePath + "/" + testActionSetId + "/dataset_mergerel") + .count(); + + long orp_mergerel = spark + .read() + .load(testOutputBasePath + "/" + testActionSetId + "/otherresearchproduct_mergerel") + .count(); + + final List merges = pubs + .filter("source == '50|arXiv_dedup_::c93aeb433eb90ed7a86e29be00791b7c'") + .collectAsList(); + assertEquals(3, merges.size()); + Set dups = Sets + .newHashSet( + "50|doi_________::3b1d0d8e8f930826665df9d6b82fbb73", + "50|doi_________::d5021b53204e4fdeab6ff5d5bc468032", + "50|arXiv_______::c93aeb433eb90ed7a86e29be00791b7c"); + merges.forEach(r -> { + assertEquals(ModelConstants.RESULT_RESULT, r.getRelType()); + assertEquals(ModelConstants.DEDUP, r.getSubRelType()); + assertEquals(ModelConstants.MERGES, r.getRelClass()); + assertTrue(dups.contains(r.getTarget())); + }); + + final List mergedIn = pubs + .filter("target == '50|arXiv_dedup_::c93aeb433eb90ed7a86e29be00791b7c'") + .collectAsList(); + assertEquals(3, mergedIn.size()); + mergedIn.forEach(r -> { + assertEquals(ModelConstants.RESULT_RESULT, r.getRelType()); + assertEquals(ModelConstants.DEDUP, r.getSubRelType()); + assertEquals(ModelConstants.IS_MERGED_IN, r.getRelClass()); + assertTrue(dups.contains(r.getSource())); + }); + + assertEquals(1268, orgs_mergerel); + assertEquals(1112, pubs.count()); + assertEquals(292, sw_mergerel); + assertEquals(476, ds_mergerel); + assertEquals(742, orp_mergerel); +// System.out.println("orgs_mergerel = " + orgs_mergerel); +// System.out.println("pubs_mergerel = " + pubs_mergerel); +// System.out.println("sw_mergerel = " + sw_mergerel); +// System.out.println("ds_mergerel = " + ds_mergerel); +// System.out.println("orp_mergerel = " + orp_mergerel); + + } + @Test @Order(4) void createMergeRelsTest() throws Exception { @@ -382,7 +496,9 @@ public class SparkDedupTest implements Serializable { "-la", "lookupurl", "-w", - testOutputBasePath + testOutputBasePath, + "-h", + "" }); new SparkCreateMergeRels(parser, spark).run(isLookUpService); @@ -437,10 +553,10 @@ public class SparkDedupTest implements Serializable { }); assertEquals(1268, orgs_mergerel); - assertEquals(1450, pubs.count()); - assertEquals(286, sw_mergerel); - assertEquals(472, ds_mergerel); - assertEquals(738, orp_mergerel); + assertEquals(1112, pubs.count()); + assertEquals(292, sw_mergerel); + assertEquals(476, ds_mergerel); + assertEquals(742, orp_mergerel); // System.out.println("orgs_mergerel = " + orgs_mergerel); // System.out.println("pubs_mergerel = " + pubs_mergerel); // System.out.println("sw_mergerel = " + sw_mergerel); @@ -492,8 +608,8 @@ public class SparkDedupTest implements Serializable { .count(); assertEquals(86, orgs_deduprecord); - assertEquals(68, pubs.count()); - assertEquals(49, sw_deduprecord); + assertEquals(91, pubs.count()); + assertEquals(47, sw_deduprecord); assertEquals(97, ds_deduprecord); assertEquals(92, orp_deduprecord); @@ -629,11 +745,11 @@ public class SparkDedupTest implements Serializable { .distinct() .count(); - assertEquals(902, publications); + assertEquals(925, publications); assertEquals(839, organizations); assertEquals(100, projects); assertEquals(100, datasource); - assertEquals(198, softwares); + assertEquals(196, softwares); assertEquals(389, dataset); assertEquals(520, otherresearchproduct); diff --git a/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/conf/ds.curr.conf.json b/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/conf/ds.curr.conf.json index fa889d63b..ff6670f1e 100644 --- a/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/conf/ds.curr.conf.json +++ b/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/conf/ds.curr.conf.json @@ -101,7 +101,8 @@ "type" : "String", "path" : "$.title[?(@.qualifier.classid == 'main title')].value", "length" : 250, - "size" : 5 + "size" : 5, + "clean": "title" }, { "name" : "authors", diff --git a/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/conf/orp.curr.conf.json b/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/conf/orp.curr.conf.json index b45b6ae83..a4a3761a3 100644 --- a/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/conf/orp.curr.conf.json +++ b/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/conf/orp.curr.conf.json @@ -101,7 +101,8 @@ "type" : "String", "path" : "$.title[?(@.qualifier.classid == 'main title')].value", "length" : 250, - "size" : 5 + "size" : 5, + "clean": "title" }, { "name" : "authors", diff --git a/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/conf/pub.curr.conf.json b/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/conf/pub.curr.conf.json index 15ebc7a6a..c3a769874 100644 --- a/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/conf/pub.curr.conf.json +++ b/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/conf/pub.curr.conf.json @@ -29,9 +29,8 @@ }, "pace": { "clustering" : [ - { "name" : "ngrampairs", "fields" : [ "title" ], "params" : { "max" : "1", "ngramLen" : "3"} }, - { "name" : "suffixprefix", "fields" : [ "title" ], "params" : { "max" : "1", "len" : "3" } }, - { "name" : "lowercase", "fields" : [ "doi" ], "params" : { } } + { "name" : "numAuthorsTitleSuffixPrefixChain", "fields" : [ "num_authors", "title" ], "params" : { "mod" : "10" } }, + { "name" : "jsonlistclustering", "fields" : [ "pid" ], "params" : { "jpath_value": "$.value", "jpath_classid": "$.qualifier.classid"} } ], "decisionTree": { "start": { @@ -79,13 +78,37 @@ "ignoreUndefined": "false" }, "layer3": { + "fields": [ + { + "field": "authors", + "comparator": "authorsMatch", + "weight": 1.0, + "countIfUndefined": "false", + "params": { + "surname_th": 0.75, + "fullname_th": 0.75, + "threshold": 0.6, + "mode": "full" + } + } + ], + "threshold": 0.6, + "aggregation": "MAX", + "positive": "layer4", + "negative": "NO_MATCH", + "undefined": "MATCH", + "ignoreUndefined": "true" + }, + "layer4": { "fields": [ { "field": "title", "comparator": "levensteinTitle", "weight": 1.0, "countIfUndefined": "true", - "params": {} + "params": { + "threshold": "0.99" + } } ], "threshold": 0.99, @@ -97,23 +120,25 @@ } }, "model": [ - { - "name": "doi", - "type": "String", - "path": "$.pid[?(@.qualifier.classid == 'doi')].value" - }, { "name": "pid", "type": "JSON", "path": "$.pid", "overrideMatch": "true" }, + { + "name": "alternateid", + "type": "JSON", + "path": "$.instance[*].alternateIdentifier[*]", + "overrideMatch": "true" + }, { "name": "title", "type": "String", "path": "$.title[?(@.qualifier.classid == 'main title')].value", "length": 250, - "size": 5 + "size": 5, + "clean": "title" }, { "name": "authors", @@ -122,9 +147,9 @@ "size": 200 }, { - "name": "resulttype", + "name": "num_authors", "type": "String", - "path": "$.resulttype.classid" + "path": "$.author.length()" } ], "blacklists": { diff --git a/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/conf/sw.curr.conf.json b/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/conf/sw.curr.conf.json index f53ff385f..3c6c8aa5f 100644 --- a/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/conf/sw.curr.conf.json +++ b/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/conf/sw.curr.conf.json @@ -75,7 +75,8 @@ "type" : "String", "path" : "$.title[?(@.qualifier.classid == 'main title')].value", "length" : 250, - "size" : 5 + "size" : 5, + "clean": "title" }, { "name" : "url", diff --git a/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/pivot_history/pivot_history.json b/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/pivot_history/pivot_history.json new file mode 100644 index 000000000..8af1a6d06 --- /dev/null +++ b/dhp-workflows/dhp-dedup-openaire/src/test/resources/eu/dnetlib/dhp/dedup/pivot_history/pivot_history.json @@ -0,0 +1 @@ +{"id": "50|arXiv_______::c93aeb433eb90ed7a86e29be00791b7c", "firstUsage": "2022-01-01", "lastUsage": "2022-01-01", "dedupId": "50|arXiv_dedup_::c93aeb433eb90ed7a86e29be00791b7c" } \ No newline at end of file diff --git a/dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/preprocess/oozie_app/workflow.xml b/dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/preprocess/oozie_app/workflow.xml index ed6853229..309031ee4 100644 --- a/dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/preprocess/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-doiboost/src/main/resources/eu/dnetlib/dhp/doiboost/preprocess/oozie_app/workflow.xml @@ -34,18 +34,6 @@ the MAG working path - - - - inputPathOrcid - the ORCID input path - - - - workingPathOrcid - the ORCID working path - - @@ -65,7 +53,6 @@ ${wf:conf('resumeFrom') eq 'ResetMagWorkingPath'} ${wf:conf('resumeFrom') eq 'ConvertMagToDataset'} - ${wf:conf('resumeFrom') eq 'PreProcessORCID'} diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/MoveResult.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/MoveResult.java new file mode 100644 index 000000000..6731f2332 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/MoveResult.java @@ -0,0 +1,84 @@ + +package eu.dnetlib.dhp; + +import static eu.dnetlib.dhp.PropagationConstant.isSparkSessionManaged; +import static eu.dnetlib.dhp.PropagationConstant.readPath; +import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession; + +import java.io.Serializable; + +import org.apache.commons.io.IOUtils; +import org.apache.spark.SparkConf; +import org.apache.spark.sql.Dataset; +import org.apache.spark.sql.SaveMode; +import org.apache.spark.sql.SparkSession; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import eu.dnetlib.dhp.application.ArgumentApplicationParser; +import eu.dnetlib.dhp.resulttocommunityfromorganization.SparkResultToCommunityFromOrganizationJob; +import eu.dnetlib.dhp.schema.common.ModelSupport; +import eu.dnetlib.dhp.schema.oaf.Result; + +/** + * @author miriam.baglioni + * @Date 15/01/24 + */ +public class MoveResult implements Serializable { + private static final Logger log = LoggerFactory.getLogger(MoveResult.class); + + public static void main(String[] args) throws Exception { + String jsonConfiguration = IOUtils + .toString( + MoveResult.class + .getResourceAsStream( + "/eu/dnetlib/dhp/wf/subworkflows/input_moveresult_parameters.json")); + + final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); + + parser.parseArgument(args); + + Boolean isSparkSessionManaged = isSparkSessionManaged(parser); + log.info("isSparkSessionManaged: {}", isSparkSessionManaged); + + String inputPath = parser.get("sourcePath"); + log.info("inputPath: {}", inputPath); + + final String outputPath = parser.get("outputPath"); + log.info("outputPath: {}", outputPath); + + SparkConf conf = new SparkConf(); + + runWithSparkSession( + conf, + isSparkSessionManaged, + spark -> { + moveResults(spark, inputPath, outputPath); + + }); + } + + public static void moveResults(SparkSession spark, String inputPath, String outputPath) { + + ModelSupport.entityTypes + .keySet() + .parallelStream() + .filter(e -> ModelSupport.isResult(e)) + // .parallelStream() + .forEach(e -> { + Class resultClazz = ModelSupport.entityTypes.get(e); + Dataset resultDataset = readPath(spark, inputPath + e.name(), resultClazz); + if (resultDataset.count() > 0) { + + resultDataset + .write() + .mode(SaveMode.Overwrite) + .option("compression", "gzip") + .json(outputPath + e.name()); + } + + }); + + } + +} diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/api/Utils.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/api/Utils.java index d121b8b7e..06d0f95c2 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/api/Utils.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/api/Utils.java @@ -167,4 +167,11 @@ public class Utils implements Serializable { }); return projectMap; } + + public static List getCommunityIdList(String baseURL) throws IOException { + return getValidCommunities(baseURL) + .stream() + .map(community -> community.getId()) + .collect(Collectors.toList()); + } } diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java index 5d1b2b38d..e20fcb081 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/bulktag/SparkBulkTagJob.java @@ -45,7 +45,7 @@ public class SparkBulkTagJob { .toString( SparkBulkTagJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/bulktag/input_bulkTag_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/bulktag/input_bulkTag_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); parser.parseArgument(args); @@ -105,7 +105,6 @@ public class SparkBulkTagJob { Map>> dsm = cc.getEoscDatasourceMap(); for (String ds : datasources.collectAsList()) { - // final String dsId = ds.substring(3); if (!dsm.containsKey(ds)) { ArrayList> eoscList = new ArrayList<>(); dsm.put(ds, eoscList); @@ -116,13 +115,11 @@ public class SparkBulkTagJob { private static boolean isOKDatasource(Datasource ds) { final String compatibility = ds.getOpenairecompatibility().getClassid(); - boolean isOk = (compatibility.equalsIgnoreCase(OPENAIRE_3) || + return (compatibility.equalsIgnoreCase(OPENAIRE_3) || compatibility.equalsIgnoreCase(OPENAIRE_4) || compatibility.equalsIgnoreCase(OPENAIRE_CRIS) || compatibility.equalsIgnoreCase(OPENAIRE_DATA)) && ds.getCollectedfrom().stream().anyMatch(cf -> cf.getKey().equals(EOSC)); - - return isOk; } private static void execBulkTag( @@ -151,7 +148,13 @@ public class SparkBulkTagJob { .write() .mode(SaveMode.Overwrite) .option("compression", "gzip") - .json(outputPath + e.name()); + .json(outputPath + e.name());// writing the tagging in the working dir for entity + + readPath(spark, outputPath + e.name(), resultClazz) // copy the tagging in the actual result output path + .write() + .mode(SaveMode.Overwrite) + .option("compression", "gzip") + .json(inputPath + e.name()); }); } diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java index b9f3bff52..a016509e5 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareDatasourceCountryAssociation.java @@ -45,7 +45,7 @@ public class PrepareDatasourceCountryAssociation { .toString( PrepareDatasourceCountryAssociation.class .getResourceAsStream( - "/eu/dnetlib/dhp/countrypropagation/input_prepareassoc_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareassoc_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); @@ -66,7 +66,7 @@ public class PrepareDatasourceCountryAssociation { conf, isSparkSessionManaged, spark -> { - removeOutputDir(spark, outputPath); + // removeOutputDir(spark, outputPath); prepareDatasourceCountryAssociation( spark, Arrays.asList(parser.get("whitelist").split(";")), @@ -90,7 +90,8 @@ public class PrepareDatasourceCountryAssociation { (FilterFunction) ds -> !ds.getDataInfo().getDeletedbyinference() && Optional.ofNullable(ds.getDatasourcetype()).isPresent() && Optional.ofNullable(ds.getDatasourcetype().getClassid()).isPresent() && - (allowedtypes.contains(ds.getDatasourcetype().getClassid()) || + ((Optional.ofNullable(ds.getJurisdiction()).isPresent() && + allowedtypes.contains(ds.getJurisdiction().getClassid())) || whitelist.contains(ds.getId()))); // filtering of the relations taking the non deleted by inference and those with IsProvidedBy as relclass diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareResultCountrySet.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareResultCountrySet.java index 184d24751..884aa0e47 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareResultCountrySet.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/PrepareResultCountrySet.java @@ -32,7 +32,7 @@ public class PrepareResultCountrySet { .toString( PrepareResultCountrySet.class .getResourceAsStream( - "/eu/dnetlib/dhp/countrypropagation/input_prepareresultcountry_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareresultcountry_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java index 9d553ded3..4e174fddc 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/countrypropagation/SparkCountryPropagationJob.java @@ -36,7 +36,7 @@ public class SparkCountryPropagationJob { .toString( SparkCountryPropagationJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/countrypropagation/input_countrypropagation_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_countrypropagation_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/PrepareInfo.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/PrepareInfo.java index 8d3432f06..bdfdde13b 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/PrepareInfo.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/PrepareInfo.java @@ -60,7 +60,7 @@ public class PrepareInfo implements Serializable { .toString( SparkResultToOrganizationFromIstRepoJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_preparation_parameter.json")); + "/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_preparation_parameter.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkResultToOrganizationFromSemRel.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkEntityToOrganizationFromSemRel.java similarity index 97% rename from dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkResultToOrganizationFromSemRel.java rename to dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkEntityToOrganizationFromSemRel.java index 27e502aba..4e30a6d6a 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkResultToOrganizationFromSemRel.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkEntityToOrganizationFromSemRel.java @@ -27,8 +27,8 @@ import eu.dnetlib.dhp.resulttoorganizationfrominstrepo.SparkResultToOrganization import eu.dnetlib.dhp.schema.common.ModelConstants; import eu.dnetlib.dhp.schema.oaf.Relation; -public class SparkResultToOrganizationFromSemRel implements Serializable { - private static final Logger log = LoggerFactory.getLogger(SparkResultToOrganizationFromSemRel.class); +public class SparkEntityToOrganizationFromSemRel implements Serializable { + private static final Logger log = LoggerFactory.getLogger(SparkEntityToOrganizationFromSemRel.class); private static final int MAX_ITERATION = 5; public static final String NEW_RESULT_RELATION_PATH = "/newResultRelation"; public static final String NEW_PROJECT_RELATION_PATH = "/newProjectRelation"; @@ -39,7 +39,7 @@ public class SparkResultToOrganizationFromSemRel implements Serializable { .toString( SparkResultToOrganizationFromIstRepoJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_propagation_parameter.json")); + "/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_propagation_parameter.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/StepActions.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/StepActions.java index 386ea1a5c..36a7523c5 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/StepActions.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/StepActions.java @@ -3,8 +3,8 @@ package eu.dnetlib.dhp.entitytoorganizationfromsemrel; import static eu.dnetlib.dhp.PropagationConstant.*; import static eu.dnetlib.dhp.PropagationConstant.readPath; -import static eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkResultToOrganizationFromSemRel.NEW_PROJECT_RELATION_PATH; -import static eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkResultToOrganizationFromSemRel.NEW_RESULT_RELATION_PATH; +import static eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkEntityToOrganizationFromSemRel.NEW_PROJECT_RELATION_PATH; +import static eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkEntityToOrganizationFromSemRel.NEW_RESULT_RELATION_PATH; import java.io.Serializable; import java.util.*; @@ -20,7 +20,6 @@ import org.jetbrains.annotations.NotNull; import com.fasterxml.jackson.databind.ObjectMapper; import eu.dnetlib.dhp.KeyValueSet; -import eu.dnetlib.dhp.schema.common.ModelConstants; import eu.dnetlib.dhp.schema.oaf.Relation; import scala.Tuple2; diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep1.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep1.java index 95b870292..bc72a2ae1 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep1.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep1.java @@ -31,7 +31,7 @@ public class PrepareResultOrcidAssociationStep1 { .toString( PrepareResultOrcidAssociationStep1.class .getResourceAsStream( - "/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConf); parser.parseArgument(args); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep2.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep2.java index c60012a74..46894d0e1 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep2.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/PrepareResultOrcidAssociationStep2.java @@ -29,7 +29,7 @@ public class PrepareResultOrcidAssociationStep2 { .toString( PrepareResultOrcidAssociationStep2.class .getResourceAsStream( - "/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json")); + "/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java index a38b4da2e..c5d632658 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/orcidtoresultfromsemrel/SparkOrcidToResultFromSemRelJob.java @@ -2,7 +2,7 @@ package eu.dnetlib.dhp.orcidtoresultfromsemrel; import static eu.dnetlib.dhp.PropagationConstant.*; -import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession; +import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession; import java.util.List; import java.util.Optional; @@ -36,7 +36,7 @@ public class SparkOrcidToResultFromSemRelJob { .toString( SparkOrcidToResultFromSemRelJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); parser.parseArgument(args); @@ -65,9 +65,8 @@ public class SparkOrcidToResultFromSemRelJob { Class resultClazz = (Class) Class.forName(resultClassName); SparkConf conf = new SparkConf(); - conf.set("hive.metastore.uris", parser.get("hive_metastore_uris")); - runWithSparkHiveSession( + runWithSparkSession( conf, isSparkSessionManaged, spark -> { diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/PrepareProjectResultsAssociation.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/PrepareProjectResultsAssociation.java index ac61e26f9..8f4e2ad9a 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/PrepareProjectResultsAssociation.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/PrepareProjectResultsAssociation.java @@ -28,7 +28,7 @@ public class PrepareProjectResultsAssociation { .toString( PrepareProjectResultsAssociation.class .getResourceAsStream( - "/eu/dnetlib/dhp/projecttoresult/input_prepareprojecttoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_prepareprojecttoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/SparkResultToProjectThroughSemRelJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/SparkResultToProjectThroughSemRelJob.java index 1ec521af1..a6466716a 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/SparkResultToProjectThroughSemRelJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/projecttoresult/SparkResultToProjectThroughSemRelJob.java @@ -33,7 +33,7 @@ public class SparkResultToProjectThroughSemRelJob { .toString( SparkResultToProjectThroughSemRelJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/projecttoresult/input_projecttoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_projecttoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); @@ -64,7 +64,7 @@ public class SparkResultToProjectThroughSemRelJob { removeOutputDir(spark, outputPath); } execPropagation( - spark, outputPath, alreadyLinkedPath, potentialUpdatePath, saveGraph); + spark, outputPath, alreadyLinkedPath, potentialUpdatePath); }); } @@ -72,24 +72,23 @@ public class SparkResultToProjectThroughSemRelJob { SparkSession spark, String outputPath, String alreadyLinkedPath, - String potentialUpdatePath, - Boolean saveGraph) { + String potentialUpdatePath) { Dataset toaddrelations = readPath(spark, potentialUpdatePath, ResultProjectSet.class); Dataset alreadyLinked = readPath(spark, alreadyLinkedPath, ResultProjectSet.class); - if (saveGraph) { - toaddrelations - .joinWith( - alreadyLinked, - toaddrelations.col("resultId").equalTo(alreadyLinked.col("resultId")), - "left_outer") - .flatMap(mapRelationRn(), Encoders.bean(Relation.class)) - .write() - .mode(SaveMode.Append) - .option("compression", "gzip") - .json(outputPath); - } + // if (saveGraph) { + toaddrelations + .joinWith( + alreadyLinked, + toaddrelations.col("resultId").equalTo(alreadyLinked.col("resultId")), + "left_outer") + .flatMap(mapRelationRn(), Encoders.bean(Relation.class)) + .write() + .mode(SaveMode.Append) + .option("compression", "gzip") + .json(outputPath); + // } } private static FlatMapFunction, Relation> mapRelationRn() { diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/PrepareResultCommunitySet.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/PrepareResultCommunitySet.java index 54fa60168..be31cd46c 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/PrepareResultCommunitySet.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/PrepareResultCommunitySet.java @@ -34,7 +34,7 @@ public class PrepareResultCommunitySet { .toString( PrepareResultCommunitySet.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); parser.parseArgument(args); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java index df8ca3805..4f755266a 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromorganization/SparkResultToCommunityFromOrganizationJob.java @@ -36,7 +36,7 @@ public class SparkResultToCommunityFromOrganizationJob { .toString( SparkResultToCommunityFromOrganizationJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttocommunityfromorganization/input_communitytoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_communitytoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); @@ -76,23 +76,41 @@ public class SparkResultToCommunityFromOrganizationJob { ModelSupport.entityTypes .keySet() .parallelStream() + .filter(e -> ModelSupport.isResult(e)) + // .parallelStream() .forEach(e -> { - if (ModelSupport.isResult(e)) { - Class resultClazz = ModelSupport.entityTypes.get(e); - removeOutputDir(spark, outputPath + e.name()); - Dataset result = readPath(spark, inputPath + e.name(), resultClazz); + // if () { + Class resultClazz = ModelSupport.entityTypes.get(e); + removeOutputDir(spark, outputPath + e.name()); + Dataset result = readPath(spark, inputPath + e.name(), resultClazz); - result - .joinWith( - possibleUpdates, - result.col("id").equalTo(possibleUpdates.col("resultId")), - "left_outer") - .map(resultCommunityFn(), Encoders.bean(resultClazz)) - .write() - .mode(SaveMode.Overwrite) - .option("compression", "gzip") - .json(outputPath + e.name()); - } + log.info("executing left join"); + result + .joinWith( + possibleUpdates, + result.col("id").equalTo(possibleUpdates.col("resultId")), + "left_outer") + .map(resultCommunityFn(), Encoders.bean(resultClazz)) + .write() + .mode(SaveMode.Overwrite) + .option("compression", "gzip") + .json(outputPath + e.name()); + +// log +// .info( +// "reading results from " + outputPath + e.name() + " and copying them to " + inputPath +// + e.name()); +// Dataset tmp = readPath(spark, outputPath + e.name(), resultClazz); +// if (tmp.count() > 0){ +// +// tmp +// .write() +// .mode(SaveMode.Overwrite) +// .option("compression", "gzip") +// .json(inputPath + e.name()); +// } + + // } }); } @@ -109,11 +127,11 @@ public class SparkResultToCommunityFromOrganizationJob { .map(Context::getId) .collect(Collectors.toList()); - @SuppressWarnings("unchecked") - R res = (R) ret.getClass().newInstance(); + // @SuppressWarnings("unchecked") + // R res = (R) ret.getClass().newInstance(); - res.setId(ret.getId()); - List propagatedContexts = new ArrayList<>(); + // res.setId(ret.getId()); + // List propagatedContexts = new ArrayList<>(); for (String cId : communitySet) { if (!contextList.contains(cId)) { Context newContext = new Context(); @@ -127,11 +145,11 @@ public class SparkResultToCommunityFromOrganizationJob { PROPAGATION_RESULT_COMMUNITY_ORGANIZATION_CLASS_ID, PROPAGATION_RESULT_COMMUNITY_ORGANIZATION_CLASS_NAME, ModelConstants.DNET_PROVENANCE_ACTIONS))); - propagatedContexts.add(newContext); + ret.getContext().add(newContext); } } - res.setContext(propagatedContexts); - ret.mergeFrom(res); + // res.setContext(propagatedContexts); + // ret.mergeFrom(res); } return ret; }; diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/PrepareResultCommunitySet.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/PrepareResultCommunitySet.java index 467e11a96..512dfa9be 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/PrepareResultCommunitySet.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/PrepareResultCommunitySet.java @@ -38,7 +38,7 @@ public class PrepareResultCommunitySet { .toString( PrepareResultCommunitySet.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); parser.parseArgument(args); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java index 6e298cf94..f9c36d7ca 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromproject/SparkResultToCommunityFromProject.java @@ -44,7 +44,7 @@ public class SparkResultToCommunityFromProject implements Serializable { .toString( SparkResultToCommunityFromProject.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttocommunityfromproject/input_communitytoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_communitytoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); @@ -86,23 +86,30 @@ public class SparkResultToCommunityFromProject implements Serializable { ModelSupport.entityTypes .keySet() .parallelStream() + .filter(e -> ModelSupport.isResult(e)) .forEach(e -> { - if (ModelSupport.isResult(e)) { - removeOutputDir(spark, outputPath + e.name()); - Class resultClazz = ModelSupport.entityTypes.get(e); - Dataset result = readPath(spark, inputPath + e.name(), resultClazz); + // if () { + removeOutputDir(spark, outputPath + e.name()); + Class resultClazz = ModelSupport.entityTypes.get(e); + Dataset result = readPath(spark, inputPath + e.name(), resultClazz); - result - .joinWith( - possibleUpdates, - result.col("id").equalTo(possibleUpdates.col("resultId")), - "left_outer") - .map(resultCommunityFn(), Encoders.bean(resultClazz)) - .write() - .mode(SaveMode.Overwrite) - .option("compression", "gzip") - .json(outputPath + e.name()); - } + result + .joinWith( + possibleUpdates, + result.col("id").equalTo(possibleUpdates.col("resultId")), + "left_outer") + .map(resultCommunityFn(), Encoders.bean(resultClazz)) + .write() + .mode(SaveMode.Overwrite) + .option("compression", "gzip") + .json(outputPath + e.name()); + +// readPath(spark, outputPath + e.name(), resultClazz) +// .write() +// .mode(SaveMode.Overwrite) +// .option("compression", "gzip") +// .json(inputPath + e.name()); + // } }); } diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java index 0c836a3ba..aede9ef05 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep1.java @@ -4,6 +4,7 @@ package eu.dnetlib.dhp.resulttocommunityfromsemrel; import static eu.dnetlib.dhp.PropagationConstant.*; import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession; +import java.io.IOException; import java.util.Arrays; import java.util.List; @@ -15,6 +16,7 @@ import org.slf4j.LoggerFactory; import com.google.gson.Gson; +import eu.dnetlib.dhp.api.Utils; import eu.dnetlib.dhp.application.ArgumentApplicationParser; import eu.dnetlib.dhp.resulttocommunityfromorganization.ResultCommunityList; import eu.dnetlib.dhp.schema.oaf.Relation; @@ -26,11 +28,6 @@ import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService; public class PrepareResultCommunitySetStep1 { private static final Logger log = LoggerFactory.getLogger(PrepareResultCommunitySetStep1.class); - private static final String COMMUNITY_LIST_XQUERY = "for $x in collection('/db/DRIVER/ContextDSResources/ContextDSResourceType')" - + " where $x//CONFIGURATION/context[./@type='community' or ./@type='ri']" - + " and $x//CONFIGURATION/context/param[./@name='status']/text() != 'hidden'" - + " return $x//CONFIGURATION/context/@id/string()"; - /** * associates to each result the set of community contexts they are associated to; associates to each target of a * relation with allowed semantics the set of community context it could possibly inherit from the source of the @@ -64,7 +61,7 @@ public class PrepareResultCommunitySetStep1 { .toString( PrepareResultCommunitySetStep1.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); @@ -88,10 +85,10 @@ public class PrepareResultCommunitySetStep1 { final List allowedsemrel = Arrays.asList(parser.get("allowedsemrels").split(";")); log.info("allowedSemRel: {}", new Gson().toJson(allowedsemrel)); - final String isLookupUrl = parser.get("isLookUpUrl"); - log.info("isLookupUrl: {}", isLookupUrl); + final String baseURL = parser.get("baseURL"); + log.info("baseURL: {}", baseURL); - final List communityIdList = getCommunityList(isLookupUrl); + final List communityIdList = getCommunityList(baseURL); log.info("communityIdList: {}", new Gson().toJson(communityIdList)); final String resultType = resultClassName.substring(resultClassName.lastIndexOf(".") + 1).toLowerCase(); @@ -159,9 +156,8 @@ public class PrepareResultCommunitySetStep1 { .json(outputResultPath); } - public static List getCommunityList(final String isLookupUrl) throws ISLookUpException { - ISLookUpService isLookUp = ISLookupClientFactory.getLookUpService(isLookupUrl); - return isLookUp.quickSearchProfile(COMMUNITY_LIST_XQUERY); + public static List getCommunityList(final String baseURL) throws IOException { + return Utils.getCommunityIdList(baseURL); } } diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep2.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep2.java index 0ddb19a1a..a53d3dfe3 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep2.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/PrepareResultCommunitySetStep2.java @@ -31,7 +31,7 @@ public class PrepareResultCommunitySetStep2 { .toString( PrepareResultCommunitySetStep2.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java index f31a26230..3cf2f73c3 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttocommunityfromsemrel/SparkResultToCommunityThroughSemRelJob.java @@ -33,7 +33,7 @@ public class SparkResultToCommunityThroughSemRelJob { .toString( SparkResultToCommunityThroughSemRelJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_communitytoresult_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_communitytoresult_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); @@ -100,6 +100,7 @@ public class SparkResultToCommunityThroughSemRelJob { .mode(SaveMode.Overwrite) .option("compression", "gzip") .json(outputPath); + } private static MapFunction, R> contextUpdaterFn() { @@ -109,11 +110,11 @@ public class SparkResultToCommunityThroughSemRelJob { if (rcl.isPresent()) { Set contexts = new HashSet<>(); ret.getContext().forEach(c -> contexts.add(c.getId())); - List contextList = rcl + rcl .get() .getCommunityList() .stream() - .map( + .forEach( c -> { if (!contexts.contains(c)) { Context newContext = new Context(); @@ -127,19 +128,11 @@ public class SparkResultToCommunityThroughSemRelJob { PROPAGATION_RESULT_COMMUNITY_SEMREL_CLASS_ID, PROPAGATION_RESULT_COMMUNITY_SEMREL_CLASS_NAME, ModelConstants.DNET_PROVENANCE_ACTIONS))); - return newContext; + ret.getContext().add(newContext); } - return null; - }) - .filter(Objects::nonNull) - .collect(Collectors.toList()); - @SuppressWarnings("unchecked") - R r = (R) ret.getClass().newInstance(); + }); - r.setId(ret.getId()); - r.setContext(contextList); - ret.mergeFrom(r); } return ret; diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/AppendNewRelations.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/AppendNewRelations.java new file mode 100644 index 000000000..11e942142 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/AppendNewRelations.java @@ -0,0 +1,68 @@ + +package eu.dnetlib.dhp.resulttoorganizationfrominstrepo; + +import static eu.dnetlib.dhp.PropagationConstant.*; +import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession; + +import java.io.Serializable; + +import org.apache.commons.io.IOUtils; +import org.apache.spark.SparkConf; +import org.apache.spark.sql.SaveMode; +import org.apache.spark.sql.SparkSession; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import eu.dnetlib.dhp.application.ArgumentApplicationParser; +import eu.dnetlib.dhp.schema.oaf.Relation; + +/** + * @author miriam.baglioni + * @Date 09/12/23 + */ +public class AppendNewRelations implements Serializable { + + private static final Logger log = LoggerFactory.getLogger(AppendNewRelations.class); + + public static void main(String[] args) throws Exception { + + String jsonConfiguration = IOUtils + .toString( + AppendNewRelations.class + .getResourceAsStream( + "/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_newrelation_parameters.json")); + + final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); + + parser.parseArgument(args); + + Boolean isSparkSessionManaged = isSparkSessionManaged(parser); + log.info("isSparkSessionManaged: {}", isSparkSessionManaged); + + String inputPath = parser.get("sourcePath"); + log.info("inputPath: {}", inputPath); + + final String outputPath = parser.get("outputPath"); + log.info("outputPath: {}", outputPath); + + SparkConf conf = new SparkConf(); + + runWithSparkSession( + conf, + isSparkSessionManaged, + spark -> appendNewRelation(spark, inputPath, outputPath)); + } + + private static void appendNewRelation(SparkSession spark, String inputPath, String outputPath) { + + readPath(spark, inputPath + "publication/relation", Relation.class) + .union(readPath(spark, inputPath + "dataset/relation", Relation.class)) + .union(readPath(spark, inputPath + "otherresearchproduct/relation", Relation.class)) + .union(readPath(spark, inputPath + "software/relation", Relation.class)) + .write() + .mode(SaveMode.Append) + .option("compression", "gzip") + .json(outputPath); + } + +} diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/PrepareResultInstRepoAssociation.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/PrepareResultInstRepoAssociation.java index 1663afb32..57488bd20 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/PrepareResultInstRepoAssociation.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/PrepareResultInstRepoAssociation.java @@ -40,7 +40,7 @@ public class PrepareResultInstRepoAssociation { .toString( PrepareResultInstRepoAssociation.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); @@ -52,10 +52,13 @@ public class PrepareResultInstRepoAssociation { String inputPath = parser.get("sourcePath"); log.info("inputPath: {}", inputPath); - final String datasourceOrganizationPath = parser.get("datasourceOrganizationPath"); + final String workingPath = parser.get("workingPath"); + log.info("workingPath : {}", workingPath); + + final String datasourceOrganizationPath = workingPath + "/preparedInfo/datasourceOrganization"; log.info("datasourceOrganizationPath {}: ", datasourceOrganizationPath); - final String alreadyLinkedPath = parser.get("alreadyLinkedPath"); + final String alreadyLinkedPath = workingPath + "/preparedInfo/alreadyLinked"; log.info("alreadyLinkedPath {}: ", alreadyLinkedPath); List blacklist = Optional diff --git a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/SparkResultToOrganizationFromIstRepoJob.java b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/SparkResultToOrganizationFromIstRepoJob.java index 0757ebccd..c8862b10c 100644 --- a/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/SparkResultToOrganizationFromIstRepoJob.java +++ b/dhp-workflows/dhp-enrichment/src/main/java/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/SparkResultToOrganizationFromIstRepoJob.java @@ -47,7 +47,7 @@ public class SparkResultToOrganizationFromIstRepoJob { .toString( SparkResultToOrganizationFromIstRepoJob.class .getResourceAsStream( - "/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json")); + "/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json")); final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration); @@ -119,7 +119,7 @@ public class SparkResultToOrganizationFromIstRepoJob { "left_outer") .flatMap(createRelationFn(), Encoders.bean(Relation.class)) .write() - .mode(SaveMode.Append) + .mode(SaveMode.Overwrite) .option("compression", "gzip") .json(outputPath); } diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/datasourcemaster_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/datasourcemaster_parameters.json deleted file mode 100644 index 9a2eadaa7..000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/datasourcemaster_parameters.json +++ /dev/null @@ -1,32 +0,0 @@ -[ - { - "paramName": "p", - "paramLongName": "hdfsPath", - "paramDescription": "the path where storing the sequential file", - "paramRequired": true - }, - { - "paramName": "nn", - "paramLongName": "hdfsNameNode", - "paramDescription": "the name node on hdfs", - "paramRequired": true - }, - { - "paramName": "pgurl", - "paramLongName": "postgresUrl", - "paramDescription": "postgres url, example: jdbc:postgresql://localhost:5432/testdb", - "paramRequired": true - }, - { - "paramName": "pguser", - "paramLongName": "postgresUser", - "paramDescription": "postgres user", - "paramRequired": false - }, - { - "paramName": "pgpasswd", - "paramLongName": "postgresPassword", - "paramDescription": "postgres password", - "paramRequired": false - } -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_eosc_bulkTag_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_eosc_bulkTag_parameters.json deleted file mode 100644 index 5aace346d..000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_eosc_bulkTag_parameters.json +++ /dev/null @@ -1,41 +0,0 @@ -[ - - { - "paramName":"s", - "paramLongName":"sourcePath", - "paramDescription": "the path of the sequencial file to read", - "paramRequired": true - }, - { - "paramName": "dmp", - "paramLongName":"datasourceMapPath", - "paramDescription": "the path where the association datasource master has been stored", - "paramRequired": true - }, - { - "paramName":"tn", - "paramLongName":"resultTableName", - "paramDescription": "the name of the result table we are currently working on", - "paramRequired": true - }, - { - "paramName": "wp", - "paramLongName": "workingPath", - "paramDescription": "the path used to store temporary output files", - "paramRequired": true - }, - { - "paramName": "ssm", - "paramLongName": "isSparkSessionManaged", - "paramDescription": "true if the spark session is managed, false otherwise", - "paramRequired": false - }, - { - - "paramName": "rt", - "paramLongName": "resultType", - "paramDescription": "the result type", - "paramRequired": true - } - -] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/workflow.xml deleted file mode 100644 index 16c8c4e19..000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/workflow.xml +++ /dev/null @@ -1,197 +0,0 @@ - - - - sourcePath - the source path - - - outputPath - sets the outputPath - - - - - ${jobTracker} - ${nameNode} - - - oozie.action.sharelib.for.spark - ${oozieActionShareLibForSpark2} - - - - - - - - Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - - - - - ${wf:conf('resumeFrom') eq 'PrepareInfo'} - - - - - - - - - - - - - - - - - - - - - - - - - - - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${nameNode}/${sourcePath}/publication - ${nameNode}/${outputPath}/publication - - - - - - - - ${nameNode}/${sourcePath}/dataset - ${nameNode}/${outputPath}/dataset - - - - - - - - ${nameNode}/${sourcePath}/otherresearchproduct - ${nameNode}/${outputPath}/otherresearchproduct - - - - - - - - ${nameNode}/${sourcePath}/software - ${nameNode}/${outputPath}/software - - - - - - - - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - - - - - - yarn - cluster - PrepareResultOrganizationAssociation - eu.dnetlib.dhp.entitytoorganizationfromsemrel.PrepareInfo - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - - --graphPath${sourcePath} - --hive_metastore_uris${hive_metastore_uris} - --leavesPath${workingDir}/preparedInfo/leavesPath - --childParentPath${workingDir}/preparedInfo/childParentPath - --resultOrgPath${workingDir}/preparedInfo/resultOrgPath - --projectOrganizationPath${workingDir}/preparedInfo/projectOrganizationPath - --relationPath${workingDir}/preparedInfo/relation - - - - - - - - yarn - cluster - resultToOrganizationFromSemRel - eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkResultToOrganizationFromSemRel - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --conf spark.sql.shuffle.partitions=3840 - - --relationPath${workingDir}/preparedInfo/relation - --outputPath${outputPath}/relation - --leavesPath${workingDir}/preparedInfo/leavesPath - --childParentPath${workingDir}/preparedInfo/childParentPath - --resultOrgPath${workingDir}/preparedInfo/resultOrgPath - --projectOrganizationPath${workingDir}/preparedInfo/projectOrganizationPath - --hive_metastore_uris${hive_metastore_uris} - --workingDir${workingDir}/working - --iterations${iterations} - - - - - - - - - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/oozie_app/workflow.xml deleted file mode 100644 index 9e91c06fb..000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/oozie_app/workflow.xml +++ /dev/null @@ -1,184 +0,0 @@ - - - - sourcePath - the source path - - - allowedsemrels - the allowed semantics - - - outputPath - the output path - - - - - ${jobTracker} - ${nameNode} - - - oozie.action.sharelib.for.spark - ${oozieActionShareLibForSpark2} - - - - - - - - Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - - - - - - - - - - - - - - - - - - - - - - - - - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${nameNode}/${sourcePath}/publication - ${nameNode}/${outputPath}/publication - - - - - - - - ${nameNode}/${sourcePath}/dataset - ${nameNode}/${outputPath}/dataset - - - - - - - - ${nameNode}/${sourcePath}/otherresearchproduct - ${nameNode}/${outputPath}/otherresearchproduct - - - - - - - - ${nameNode}/${sourcePath}/software - ${nameNode}/${outputPath}/software - - - - - - - - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - - - - - yarn - cluster - PrepareProjectResultsAssociation - eu.dnetlib.dhp.projecttoresult.PrepareProjectResultsAssociation - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - - --sourcePath${sourcePath}/relation - --allowedsemrels${allowedsemrels} - --hive_metastore_uris${hive_metastore_uris} - --potentialUpdatePath${workingDir}/preparedInfo/potentialUpdates - --alreadyLinkedPath${workingDir}/preparedInfo/alreadyLinked - - - - - - - - yarn - cluster - ProjectToResultPropagation - eu.dnetlib.dhp.projecttoresult.SparkResultToProjectThroughSemRelJob - dhp-enrichment-${projectVersion}.jar - - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} - --driver-memory=${sparkDriverMemory} - --conf spark.extraListeners=${spark2ExtraListeners} - --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} - --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} - --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} - --conf spark.dynamicAllocation.enabled=true - --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - - --saveGraph${saveGraph} - --hive_metastore_uris${hive_metastore_uris} - --outputPath${outputPath}/relation - --potentialUpdatePath${workingDir}/preparedInfo/potentialUpdates - --alreadyLinkedPath${workingDir}/preparedInfo/alreadyLinked - - - - - - - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/oozie_app/config-default.xml deleted file mode 100644 index 2744ea92b..000000000 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/oozie_app/config-default.xml +++ /dev/null @@ -1,58 +0,0 @@ - - - jobTracker - yarnRM - - - nameNode - hdfs://nameservice1 - - - oozie.use.system.libpath - true - - - oozie.action.sharelib.for.spark - spark2 - - - hive_metastore_uris - thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 - - - spark2YarnHistoryServerAddress - http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 - - - spark2EventLogDir - /user/spark/spark2ApplicationHistory - - - spark2ExtraListeners - com.cloudera.spark.lineage.NavigatorAppListener - - - spark2SqlQueryExecutionListeners - com.cloudera.spark.lineage.NavigatorQueryListener - - - sparkExecutorNumber - 4 - - - sparkDriverMemory - 15G - - - sparkExecutorMemory - 6G - - - sparkExecutorCores - 1 - - - spark2MaxExecutors - 50 - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties new file mode 100644 index 000000000..05db04090 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/job.properties @@ -0,0 +1,28 @@ +sourcePath=/tmp/beta_provision/graph/10_graph_orcid_enriched +resumeFrom=ResultProject +allowedsemrelsorcidprop=isSupplementedBy;isSupplementTo +allowedsemrelsresultproject=isSupplementedBy;isSupplementTo +allowedsemrelscommunitysemrel=isSupplementedBy;isSupplementTo +datasourceWhitelistForCountryPropagation=10|opendoar____::16e6a3326dd7d868cbc926602a61e4d0;10|openaire____::fdb035c8b3e0540a8d9a561a6c44f4de;10|eurocrisdris::fe4903425d9040f680d8610d9079ea14;10|openaire____::5b76240cc27a58c6f7ceef7d8c36660e;10|openaire____::172bbccecf8fca44ab6a6653e84cb92a;10|openaire____::149c6590f8a06b46314eed77bfca693f;10|eurocrisdris::a6026877c1a174d60f81fd71f62df1c1;10|openaire____::4692342f0992d91f9e705c26959f09e0;10|openaire____::8d529dbb05ec0284662b391789e8ae2a;10|openaire____::345c9d171ef3c5d706d08041d506428c;10|opendoar____::1c1d4df596d01da60385f0bb17a4a9e0;10|opendoar____::7a614fd06c325499f1680b9896beedeb;10|opendoar____::1ee3dfcd8a0645a25a35977997223d22;10|opendoar____::d296c101daa88a51f6ca8cfc1ac79b50;10|opendoar____::798ed7d4ee7138d49b8828958048130a;10|openaire____::c9d2209ecc4d45ba7b4ca7597acb88a2;10|eurocrisdris::c49e0fe4b9ba7b7fab717d1f0f0a674d;10|eurocrisdris::9ae43d14471c4b33661fedda6f06b539;10|eurocrisdris::432ca599953ff50cd4eeffe22faf3e48 +#allowedtypes=pubsrepository::institutional +allowedtypes=Institutional +outputPath=/tmp/miriam/graph/11_graph_orcid +pathMap ={"author":"$['author'][*]['fullname']", \ + "title":"$['title'][*]['value']",\ + "orcid":"$['author'][*]['pid'][*][?(@['qualifier']['classid']=='orcid')]['value']" ,\ + "orcid_pending":"$['author'][*]['pid'][*][?(@['qualifier']['classid']=='orcid_pending')]['value']" ,\ + "contributor" : "$['contributor'][*]['value']",\ + "description" : "$['description'][*]['value']",\ + "subject" :"$['subject'][*]['value']" , \ + "fos" : "$['subject'][?(@['qualifier']['classid']=='FOS')].value" ,\ + "sdg" : "$['subject'][?(@['qualifier']['classid']=='SDG')].value",\ + "journal":"$['journal'].name",\ + "hostedby":"$['instance'][*]['hostedby']['key']",\ + "collectedfrom":"$['instance'][*]['collectedfrom']['key']",\ + "publisher":"$['publisher'].value",\ + "publicationyear":"$['dateofacceptance'].value"} +blacklist=empty +allowedpids=orcid;orcid_pending +baseURL = https://services.openaire.eu/openaire/community/ +iterations=1 + diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/config-default.xml new file mode 100644 index 000000000..d262cb6e0 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/config-default.xml @@ -0,0 +1,30 @@ + + + jobTracker + yarnRM + + + nameNode + hdfs://nameservice1 + + + oozie.use.system.libpath + true + + + hiveMetastoreUris + thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 + + + hiveJdbcUrl + jdbc:hive2://iis-cdh5-test-m3.ocean.icm.edu.pl:10000 + + + hiveDbName + openaire + + + oozie.launcher.mapreduce.user.classpath.first + true + + diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/import.txt b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/import.txt new file mode 100644 index 000000000..b20259414 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/import.txt @@ -0,0 +1,10 @@ +## This is a classpath-based import file (this header is required) +orcid_propagation classpath eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app +bulk_tagging classpath eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app +affiliation_inst_repo classpath eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app +entity_semantic_relation classpath eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app +community_organization classpath eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app +result_project classpath eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app +community_project classpath eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app +community_sem_rel classpath eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app +country_propagation classpath eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml new file mode 100644 index 000000000..8e91707b6 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/main/oozie_app/workflow.xml @@ -0,0 +1,324 @@ + + + + + sourcePath + the source path + + + allowedsemrelsorcidprop + the semantic relationships allowed for propagation + + + allowedsemrelsresultproject + the allowed semantics + + + allowedsemrelscommunitysemrel + the semantic relationships allowed for propagation + + + datasourceWhitelistForCountryPropagation + the white list + + + allowedtypes + the allowed types + + + outputPath + the output path + + + pathMap + the json path associated to each selection field + + + blacklist + list of datasources in blacklist for the affiliation from instrepo propagation + + + + hiveDbName + the target hive database name + + + hiveJdbcUrl + hive server jdbc url + + + hiveMetastoreUris + hive server metastore URIs + + + sparkDriverMemory + memory for driver process + + + sparkExecutorMemory + memory for individual executor + + + sparkExecutorCores + number of cores used by single executor + + + oozieActionShareLibForSpark2 + oozie action sharelib for spark 2.* + + + spark2ExtraListeners + com.cloudera.spark.lineage.NavigatorAppListener + spark 2.* extra listeners classname + + + spark2SqlQueryExecutionListeners + com.cloudera.spark.lineage.NavigatorQueryListener + spark 2.* sql query execution listeners classname + + + spark2YarnHistoryServerAddress + spark 2.* yarn history server address + + + spark2EventLogDir + spark 2.* event log dir location + + + + + ${jobTracker} + ${nameNode} + + + mapreduce.job.queuename + ${queueName} + + + oozie.launcher.mapred.job.queue.name + ${oozieLauncherQueueName} + + + oozie.action.sharelib.for.spark + ${oozieActionShareLibForSpark2} + + + + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + ${wf:conf('resumeFrom') eq 'BulkTagging'} + ${wf:conf('resumeFrom') eq 'AffiliationInstitutionalRepository'} + ${wf:conf('resumeFrom') eq 'AffiliationSemanticRelation'} + ${wf:conf('resumeFrom') eq 'CommunityOrganization'} + ${wf:conf('resumeFrom') eq 'ResultProject'} + ${wf:conf('resumeFrom') eq 'CommunityProject'} + ${wf:conf('resumeFrom') eq 'CommunitySemanticRelation'} + ${wf:conf('resumeFrom') eq 'CountryPropagation'} + + + + + + + + ${wf:appPath()}/orcid_propagation + + + + + sourcePath + ${sourcePath} + + + allowedsemrels + ${allowedsemrelsorcidprop} + + + outputPath + ${outputPath} + + + + + + + + + + ${wf:appPath()}/bulk_tagging + + + + + sourcePath + ${outputPath} + + + baseURL + ${baseURL} + + + pathMap + ${pathMap} + + + + + + + + + + ${wf:appPath()}/affiliation_inst_repo + + + + + sourcePath + ${outputPath} + + + blacklist + ${blacklist} + + + + + + + + + + ${wf:appPath()}/entity_semantic_relation + + + + + sourcePath + ${outputPath} + + + iterations + ${iterations} + + + + + + + + + + ${wf:appPath()}/community_organization + + + + + sourcePath + ${outputPath} + + + baseURL + ${baseURL} + + + + + + + + + + ${wf:appPath()}/result_project + + + + + sourcePath + ${outputPath} + + + allowedsemrels + ${allowedsemrelsresultproject} + + + + + + + + + + ${wf:appPath()}/community_project + + + + + sourcePath + ${outputPath} + + + + + + + + + + ${wf:appPath()}/community_sem_rel + + + + + sourcePath + ${outputPath} + + + allowedsemrels + ${allowedsemrelscommunitysemrel} + + + baseURL + ${baseURL} + + + + + + + + + + ${wf:appPath()}/country_propagation + + + + + sourcePath + ${outputPath} + + + whitelist + ${datasourceWhitelistForCountryPropagation} + + + allowedtypes + ${allowedtypes} + + + + + + + + + + diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_bulkTag_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/input_bulkTag_parameters.json similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_bulkTag_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/input_bulkTag_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/config-default.xml similarity index 92% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/oozie_app/config-default.xml rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/config-default.xml index c92f559f9..2695253e6 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/oozie_app/config-default.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/config-default.xml @@ -47,9 +47,13 @@ sparkExecutorMemory 5G + + sparkExecutorCores + 4 + memoryOverhead - 3g + 3G partitions diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml similarity index 54% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/oozie_app/workflow.xml rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml index 03373eda0..c7a9e8a26 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/bulktag/oozie_app/workflow.xml @@ -9,13 +9,14 @@ the json path associated to each selection field - outputPath - the output path + baseURL + The URL to access the community APIs - baseURL - the community API base URL + startFrom> + undelete + @@ -29,71 +30,34 @@ - + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + ${wf:conf('startFrom') eq 'undelete'} + + + + + - - + + - + - - - - - - - - - - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - - yarn-cluster cluster - bulkTagging-result + bulkTagging eu.dnetlib.dhp.bulktag.SparkBulkTagJob dhp-enrichment-${projectVersion}.jar @@ -101,13 +65,15 @@ --executor-memory=${sparkExecutorMemory} --executor-cores=${sparkExecutorCores} --driver-memory=${sparkDriverMemory} + --conf spark.executor.memoryOverhead=${memoryOverhead} + --conf spark.sql.shuffle.partitions=${partitions} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --sourcePath${sourcePath}/ - --outputPath${outputPath}/ + --outputPath${workingDir}/bulktag/ --pathMap${pathMap} --baseURL${baseURL} @@ -115,6 +81,8 @@ + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_countrypropagation_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_countrypropagation_parameters.json similarity index 99% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_countrypropagation_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_countrypropagation_parameters.json index f217e2458..d3cde8b74 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_countrypropagation_parameters.json +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_countrypropagation_parameters.json @@ -29,4 +29,4 @@ "paramDescription": "true if the spark session is managed, false otherwise", "paramRequired": false } -] \ No newline at end of file +] diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_prepareassoc_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareassoc_parameters.json similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_prepareassoc_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareassoc_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_prepareresultcountry_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareresultcountry_parameters.json similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/input_prepareresultcountry_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/input_prepareresultcountry_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/config-default.xml new file mode 100644 index 000000000..1cb0b8a5e --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/config-default.xml @@ -0,0 +1,58 @@ + + + jobTracker + yarnRM + + + nameNode + hdfs://nameservice1 + + + oozie.use.system.libpath + true + + + oozie.action.sharelib.for.spark + spark2 + + + hive_metastore_uris + thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083 + + + spark2YarnHistoryServerAddress + http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089 + + + spark2EventLogDir + /user/spark/spark2ApplicationHistory + + + spark2ExtraListeners + com.cloudera.spark.lineage.NavigatorAppListener + + + spark2SqlQueryExecutionListeners + com.cloudera.spark.lineage.NavigatorQueryListener + + + sparkExecutorNumber + 4 + + + sparkDriverMemory + 15G + + + sparkExecutorMemory + 5G + + + sparkExecutorCores + 4 + + + spark2MaxExecutors + 50 + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml similarity index 72% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/oozie_app/workflow.xml rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml index 271ccbf72..b9cf69517 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/countrypropagation/oozie_app/workflow.xml @@ -13,10 +13,9 @@ the allowed types - outputPath - the output path + startFrom + undelete - @@ -30,7 +29,15 @@ - + + + + + ${wf:conf('startFrom') eq 'undelete'} + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] @@ -38,57 +45,13 @@ - - + + - + - - - - - - - - - - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - @@ -110,20 +73,20 @@ --sourcePath${sourcePath} --whitelist${whitelist} --allowedtypes${allowedtypes} - --outputPath${workingDir}/preparedInfo + --outputPath${workingDir}/country/preparedInfo - + - - - - - + + + + + - + yarn cluster @@ -144,16 +107,16 @@ --conf spark.sql.shuffle.partitions=3840 --sourcePath${sourcePath}/publication - --outputPath${workingDir}/publication - --workingPath${workingDir}/workingP + --outputPath${workingDir}/country/publication + --workingPath${workingDir}/country/workingP --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication - --preparedInfoPath${workingDir}/preparedInfo + --preparedInfoPath${workingDir}/country/preparedInfo - + yarn cluster @@ -174,16 +137,16 @@ --conf spark.sql.shuffle.partitions=3840 --sourcePath${sourcePath}/dataset - --outputPath${workingDir}/dataset - --workingPath${workingDir}/workingD + --outputPath${workingDir}/country/dataset + --workingPath${workingDir}/country/workingD --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset - --preparedInfoPath${workingDir}/preparedInfo + --preparedInfoPath${workingDir}/country/preparedInfo - + yarn cluster @@ -204,16 +167,16 @@ --conf spark.sql.shuffle.partitions=3840 --sourcePath${sourcePath}/otherresearchproduct - --outputPath${workingDir}/otherresearchproduct - --workingPath${workingDir}/workingO + --outputPath${workingDir}/country/otherresearchproduct + --workingPath${workingDir}/country/workingO --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct - --preparedInfoPath${workingDir}/preparedInfo + --preparedInfoPath${workingDir}/country/preparedInfo - + yarn cluster @@ -234,25 +197,25 @@ --conf spark.sql.shuffle.partitions=3840 --sourcePath${sourcePath}/software - --outputPath${workingDir}/software - --workingPath${workingDir}/workingS + --outputPath${workingDir}/country/software + --workingPath${workingDir}/country/workingS --resultTableNameeu.dnetlib.dhp.schema.oaf.Software - --preparedInfoPath${workingDir}/preparedInfo + --preparedInfoPath${workingDir}/country/preparedInfo - + - - - - - + + + + + - + yarn cluster @@ -270,18 +233,18 @@ --conf spark.speculation=false --conf spark.hadoop.mapreduce.map.speculative=false --conf spark.hadoop.mapreduce.reduce.speculative=false - --conf spark.sql.shuffle.partitions=3840 + --conf spark.sql.shuffle.partitions=7680 --sourcePath${sourcePath}/publication - --preparedInfoPath${workingDir}/publication + --preparedInfoPath${workingDir}/country/publication --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication - --outputPath${outputPath}/publication + --outputPath${workingDir}/country/country/publication - + yarn cluster @@ -302,15 +265,15 @@ --conf spark.sql.shuffle.partitions=3840 --sourcePath${sourcePath}/dataset - --preparedInfoPath${workingDir}/dataset + --preparedInfoPath${workingDir}/country/dataset --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset - --outputPath${outputPath}/dataset + --outputPath${workingDir}/country/country/dataset - + yarn cluster @@ -331,15 +294,15 @@ --conf spark.sql.shuffle.partitions=3840 --sourcePath${sourcePath}/otherresearchproduct - --preparedInfoPath${workingDir}/otherresearchproduct + --preparedInfoPath${workingDir}/country/otherresearchproduct --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct - --outputPath${outputPath}/otherresearchproduct + --outputPath${workingDir}/country/country/otherresearchproduct - + yarn cluster @@ -360,16 +323,57 @@ --conf spark.sql.shuffle.partitions=3840 --sourcePath${sourcePath}/software - --preparedInfoPath${workingDir}/software + --preparedInfoPath${workingDir}/country/software --resultTableNameeu.dnetlib.dhp.schema.oaf.Software - --outputPath${outputPath}/software - + --outputPath${workingDir}/country/country/software + - + + + + yarn + cluster + community2resultfromorganization - move results + eu.dnetlib.dhp.MoveResult + dhp-enrichment-${projectVersion}.jar + + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${workingDir}/country/country/ + --outputPath${sourcePath}/ + + + + + + + + ${wf:conf('startFrom') eq 'undelete'} + + + + + + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_preparation_parameter.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_preparation_parameter.json similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_preparation_parameter.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_preparation_parameter.json diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_propagation_parameter.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_propagation_parameter.json similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/input_propagation_parameter.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/input_propagation_parameter.json diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/config-default.xml similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/countrypropagation/oozie_app/config-default.xml rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/config-default.xml diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/workflow.xml new file mode 100644 index 000000000..ecec3579b --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/entitytoorganizationfromsemrel/oozie_app/workflow.xml @@ -0,0 +1,112 @@ + + + + sourcePath + the source path + + + startFrom + undelete + + + + + ${jobTracker} + ${nameNode} + + + oozie.action.sharelib.for.spark + ${oozieActionShareLibForSpark2} + + + + + + + + + ${wf:conf('startFrom') eq 'undelete'} + + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + + + + + + + + + + yarn + cluster + PrepareResultProjectOrganizationAssociation + eu.dnetlib.dhp.entitytoorganizationfromsemrel.PrepareInfo + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + + --graphPath${sourcePath} + --hive_metastore_uris${hive_metastore_uris} + --leavesPath${workingDir}/entitiesSemanticRelation/preparedInfo/leavesPath + --childParentPath${workingDir}/entitiesSemanticRelation/preparedInfo/childParentPath + --resultOrgPath${workingDir}/entitiesSemanticRelation/preparedInfo/resultOrgPath + --projectOrganizationPath${workingDir}/entitiesSemanticRelation/preparedInfo/projectOrganizationPath + --relationPath${workingDir}/entitiesSemanticRelation/preparedInfo/relation + + + + + + + + yarn + cluster + entityToOrganizationFromSemRel + eu.dnetlib.dhp.entitytoorganizationfromsemrel.SparkEntityToOrganizationFromSemRel + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + --conf spark.sql.shuffle.partitions=3840 + + --relationPath${workingDir}/entitiesSemanticRelation/preparedInfo/relation + --outputPath${sourcePath}/relation + --leavesPath${workingDir}/entitiesSemanticRelation/preparedInfo/leavesPath + --childParentPath${workingDir}/entitiesSemanticRelation/preparedInfo/childParentPath + --resultOrgPath${workingDir}/entitiesSemanticRelation/preparedInfo/resultOrgPath + --projectOrganizationPath${workingDir}/entitiesSemanticRelation/preparedInfo/projectOrganizationPath + --hive_metastore_uris${hive_metastore_uris} + --workingDir${workingDir}/entitiesSemanticRelation/working + --iterations${iterations} + + + + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_eoscTag_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/input_moveresult_parameters.json similarity index 88% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_eoscTag_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/input_moveresult_parameters.json index 4c25fea01..4645be435 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/bulktag/input_eoscTag_parameters.json +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/input_moveresult_parameters.json @@ -5,9 +5,10 @@ "paramDescription": "the path of the sequencial file to read", "paramRequired": true }, + { - "paramName": "wp", - "paramLongName": "workingPath", + "paramName": "out", + "paramLongName": "outputPath", "paramDescription": "the path used to store temporary output files", "paramRequired": true }, diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json similarity index 88% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json index d8aa7eb9a..3cbaa23bb 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_orcidtoresult_parameters.json @@ -11,12 +11,6 @@ "paramDescription": "true if the new version of the graph must be saved", "paramRequired": false }, - { - "paramName":"h", - "paramLongName":"hive_metastore_uris", - "paramDescription": "the hive metastore uris", - "paramRequired": true - }, { "paramName": "out", "paramLongName": "outputPath", diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/input_prepareorcidtoresult_parameters2.json diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/config-default.xml similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/oozie_app/config-default.xml rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/config-default.xml diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml similarity index 92% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/oozie_app/workflow.xml rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml index 5f52c1658..a9642d637 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/orcidtoresultfromsemrel/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/orcidtoresultfromsemrel/oozie_app/workflow.xml @@ -114,7 +114,7 @@ --sourcePath${sourcePath} --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication - --outputPath${workingDir}/preparedInfo/targetOrcidAssoc + --outputPath${workingDir}/orcid/targetOrcidAssoc --allowedsemrels${allowedsemrels} @@ -142,7 +142,7 @@ --sourcePath${sourcePath} --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset - --outputPath${workingDir}/preparedInfo/targetOrcidAssoc + --outputPath${workingDir}/orcid/targetOrcidAssoc --allowedsemrels${allowedsemrels} @@ -170,7 +170,7 @@ --sourcePath${sourcePath} --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct - --outputPath${workingDir}/preparedInfo/targetOrcidAssoc + --outputPath${workingDir}/orcid/targetOrcidAssoc --allowedsemrels${allowedsemrels} @@ -198,7 +198,7 @@ --sourcePath${sourcePath} --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.Software - --outputPath${workingDir}/preparedInfo/targetOrcidAssoc + --outputPath${workingDir}/orcid/targetOrcidAssoc --allowedsemrels${allowedsemrels} @@ -225,8 +225,8 @@ --conf spark.dynamicAllocation.enabled=true --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --sourcePath${workingDir}/preparedInfo/targetOrcidAssoc - --outputPath${workingDir}/preparedInfo/mergedOrcidAssoc + --sourcePath${workingDir}/orcid/targetOrcidAssoc + --outputPath${workingDir}/orcid/mergedOrcidAssoc @@ -247,9 +247,10 @@ eu.dnetlib.dhp.orcidtoresultfromsemrel.SparkOrcidToResultFromSemRelJob dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=4 + --executor-memory=4G --driver-memory=${sparkDriverMemory} + --conf spark.executor.memoryOverhead=5G --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} @@ -259,11 +260,10 @@ --conf spark.speculation=false --conf spark.hadoop.mapreduce.map.speculative=false --conf spark.hadoop.mapreduce.reduce.speculative=false - --conf spark.sql.shuffle.partitions=3840 + --conf spark.sql.shuffle.partitions=15000 - --possibleUpdatesPath${workingDir}/preparedInfo/mergedOrcidAssoc + --possibleUpdatesPath${workingDir}/orcid/mergedOrcidAssoc --sourcePath${sourcePath}/publication - --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication --outputPath${outputPath}/publication @@ -292,9 +292,8 @@ --conf spark.hadoop.mapreduce.map.speculative=false --conf spark.hadoop.mapreduce.reduce.speculative=false - --possibleUpdatesPath${workingDir}/preparedInfo/mergedOrcidAssoc + --possibleUpdatesPath${workingDir}/orcid/mergedOrcidAssoc --sourcePath${sourcePath}/dataset - --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset --outputPath${outputPath}/dataset @@ -323,9 +322,8 @@ --conf spark.hadoop.mapreduce.map.speculative=false --conf spark.hadoop.mapreduce.reduce.speculative=false - --possibleUpdatesPath${workingDir}/preparedInfo/mergedOrcidAssoc + --possibleUpdatesPath${workingDir}/orcid/mergedOrcidAssoc --sourcePath${sourcePath}/otherresearchproduct - --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct --outputPath${outputPath}/otherresearchproduct @@ -354,9 +352,8 @@ --conf spark.hadoop.mapreduce.map.speculative=false --conf spark.hadoop.mapreduce.reduce.speculative=false - --possibleUpdatesPath${workingDir}/preparedInfo/mergedOrcidAssoc + --possibleUpdatesPath${workingDir}/orcid/mergedOrcidAssoc --sourcePath${sourcePath}/software - --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.Software --outputPath${outputPath}/software @@ -365,6 +362,15 @@ + + + + + + + + + diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/input_prepareprojecttoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_prepareprojecttoresult_parameters.json similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/input_prepareprojecttoresult_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_prepareprojecttoresult_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/input_projecttoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_projecttoresult_parameters.json similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/input_projecttoresult_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/input_projecttoresult_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/config-default.xml similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/projecttoresult/oozie_app/config-default.xml rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/config-default.xml diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/workflow.xml new file mode 100644 index 000000000..287ee4ba8 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/projecttoresult/oozie_app/workflow.xml @@ -0,0 +1,104 @@ + + + + sourcePath + the source path + + + allowedsemrels + the allowed semantics + + + startFrom + undelete + + + + + ${jobTracker} + ${nameNode} + + + oozie.action.sharelib.for.spark + ${oozieActionShareLibForSpark2} + + + + + + + + + ${wf:conf('startFrom') eq 'undelete'} + + + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] + + + + + + + + + + + + + + yarn + cluster + PrepareProjectResultsAssociation + eu.dnetlib.dhp.projecttoresult.PrepareProjectResultsAssociation + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + + --sourcePath${sourcePath}/relation + --allowedsemrels${allowedsemrels} + --hive_metastore_uris${hive_metastore_uris} + --potentialUpdatePath${workingDir}/resultproject/preparedInfo/potentialUpdates + --alreadyLinkedPath${workingDir}/resultproject/preparedInfo/alreadyLinked + + + + + + + + yarn + cluster + ProjectToResultPropagation + eu.dnetlib.dhp.projecttoresult.SparkResultToProjectThroughSemRelJob + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --hive_metastore_uris${hive_metastore_uris} + --outputPath${sourcePath}/relation + --potentialUpdatePath${workingDir}/resultproject/preparedInfo/potentialUpdates + --alreadyLinkedPath${workingDir}/resultproject/preparedInfo/alreadyLinked + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/input_communitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_communitytoresult_parameters.json similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/input_communitytoresult_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_communitytoresult_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/input_preparecommunitytoresult_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/config-default.xml similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/entitytoorganizationfromsemrel/oozie_app/config-default.xml rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/config-default.xml diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/workflow.xml similarity index 61% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/workflow.xml rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/workflow.xml index e342bce23..aa5357eea 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromorganization/oozie_app/workflow.xml @@ -5,12 +5,12 @@ the source path - outputPath - the output path + baseURL + the baseURL from where to reach the community APIs - baseURL - the community API base URL + startFrom + undelete @@ -25,7 +25,15 @@ - + + + + + ${wf:conf('startFrom') eq 'undelete'} + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] @@ -33,58 +41,13 @@ - - + + - + - - - - - - - - - - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - - yarn @@ -102,10 +65,11 @@ --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --sourcePath${sourcePath}/relation - --outputPath${workingDir}/preparedInfo/resultCommunityList + --outputPath${workingDir}/communityorganization/preparedInfo/resultCommunityList --hive_metastore_uris${hive_metastore_uris} --baseURL${baseURL} @@ -132,16 +96,41 @@ --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --preparedInfoPath${workingDir}/preparedInfo/resultCommunityList + --preparedInfoPath${workingDir}/communityorganization/preparedInfo/resultCommunityList --sourcePath${sourcePath}/ - --outputPath${outputPath}/ + --outputPath${workingDir}/communityorganization/resulttocommunityfromorganization/ + + + + + + + + yarn + cluster + community2resultfromorganization - move results + eu.dnetlib.dhp.MoveResult + dhp-enrichment-${projectVersion}.jar + + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${workingDir}/communityorganization/resulttocommunityfromorganization/ + --outputPath${sourcePath}/ + - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/input_communitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_communitytoresult_parameters.json similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/input_communitytoresult_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_communitytoresult_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/input_preparecommunitytoresult_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/config-default.xml similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromorganization/oozie_app/config-default.xml rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/config-default.xml diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/workflow.xml similarity index 61% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/workflow.xml rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/workflow.xml index d0784c94d..0ceee5a7e 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromproject/oozie_app/workflow.xml @@ -5,12 +5,12 @@ the source path - outputPath - the output path + baseURL + the base URL to use to select the right community APIs - baseURL - the community API base URL + startFrom + undelete @@ -25,66 +25,28 @@ - + + + + + ${wf:conf('startFrom') eq 'undelete'} + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] - - - + + - + - - - - - - - - - - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - - yarn @@ -106,7 +68,7 @@ --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --sourcePath${sourcePath}/relation - --outputPath${workingDir}/preparedInfo/resultCommunityList + --outputPath${workingDir}/communitythroughproject/preparedInfo/resultCommunityList --baseURL${baseURL} @@ -132,16 +94,41 @@ --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --preparedInfoPath${workingDir}/preparedInfo/resultCommunityList + --preparedInfoPath${workingDir}/communitythroughproject/preparedInfo/resultCommunityList --sourcePath${sourcePath}/ - --outputPath${outputPath}/ + --outputPath${workingDir}/communitythroughproject/ + + + + + + + + yarn + cluster + move results + eu.dnetlib.dhp.MoveResult + dhp-enrichment-${projectVersion}.jar + + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${workingDir}/communitythroughproject/ + --outputPath${sourcePath}/ + - - \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_communitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_communitytoresult_parameters.json similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_communitytoresult_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_communitytoresult_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult2_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json similarity index 80% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json index 8c99da673..c6389ec8d 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/input_preparecommunitytoresult_parameters.json @@ -1,7 +1,7 @@ [ { - "paramName":"is", - "paramLongName":"isLookUpUrl", + "paramName":"bu", + "paramLongName":"baseURL", "paramDescription": "URL of the isLookUp Service", "paramRequired": true }, @@ -36,9 +36,9 @@ "paramRequired": true }, { - "paramName":"tn", - "paramLongName":"resultTableName", - "paramDescription": "the name of the result table we are currently working on", - "paramRequired": true - } + "paramName":"tn", + "paramLongName":"resultTableName", + "paramDescription": "the name of the result table we are currently working on", + "paramRequired": true + } ] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/config-default.xml similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromproject/oozie_app/config-default.xml rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/config-default.xml diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/workflow.xml similarity index 71% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/workflow.xml rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/workflow.xml index 58d5bb26d..b5e6fbf05 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttocommunityfromsemrel/oozie_app/workflow.xml @@ -9,16 +9,28 @@ the semantic relationships allowed for propagation - isLookUpUrl + baseURL the isLookup service endpoint outputPath the output path + + startFrom + undelete + - + + + + + ${wf:conf('startFrom') eq 'undelete'} + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] @@ -26,66 +38,13 @@ - - + + - + - - - - - - - - - - ${jobTracker} - ${nameNode} - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${jobTracker} - ${nameNode} - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${jobTracker} - ${nameNode} - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${jobTracker} - ${nameNode} - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - - @@ -101,8 +60,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1 dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -114,9 +75,9 @@ --sourcePath${sourcePath} --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication - --outputPath${workingDir}/preparedInfo/targetCommunityAssoc + --outputPath${workingDir}/communitysemrel/preparedInfo/targetCommunityAssoc --allowedsemrels${allowedsemrels} - --isLookUpUrl${isLookUpUrl} + --baseURL${baseURL} @@ -130,8 +91,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1 dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -143,9 +106,9 @@ --sourcePath${sourcePath} --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset - --outputPath${workingDir}/preparedInfo/targetCommunityAssoc + --outputPath${workingDir}/communitysemrel/preparedInfo/targetCommunityAssoc --allowedsemrels${allowedsemrels} - --isLookUpUrl${isLookUpUrl} + --baseURL${baseURL} @@ -159,8 +122,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1 dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -172,9 +137,9 @@ --sourcePath${sourcePath} --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct - --outputPath${workingDir}/preparedInfo/targetCommunityAssoc + --outputPath${workingDir}/communitysemrel/preparedInfo/targetCommunityAssoc --allowedsemrels${allowedsemrels} - --isLookUpUrl${isLookUpUrl} + --baseURL${baseURL} @@ -188,8 +153,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep1 dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -201,9 +168,9 @@ --sourcePath${sourcePath} --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.Software - --outputPath${workingDir}/preparedInfo/targetCommunityAssoc + --outputPath${workingDir}/communitysemrel/preparedInfo/targetCommunityAssoc --allowedsemrels${allowedsemrels} - --isLookUpUrl${isLookUpUrl} + --baseURL${baseURL} @@ -219,8 +186,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.PrepareResultCommunitySetStep2 dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -229,8 +198,8 @@ --conf spark.dynamicAllocation.enabled=true --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --sourcePath${workingDir}/preparedInfo/targetCommunityAssoc - --outputPath${workingDir}/preparedInfo/mergedCommunityAssoc + --sourcePath${workingDir}/communitysemrel/preparedInfo/targetCommunityAssoc + --outputPath${workingDir}/communitysemrel/preparedInfo/mergedCommunityAssoc @@ -251,8 +220,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=4G + --conf spark.executor.memoryOverhead=5G + --conf spark.sql.shuffle.partitions=15000 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -260,14 +231,13 @@ --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.dynamicAllocation.enabled=true --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --conf spark.sql.shuffle.partitions=10000 - --preparedInfoPath${workingDir}/preparedInfo/mergedCommunityAssoc + --preparedInfoPath${workingDir}/communitysemrel/preparedInfo/mergedCommunityAssoc --sourcePath${sourcePath}/publication --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication - --outputPath${outputPath}/publication - --saveGraph${saveGraph} + --outputPath${workingDir}/communitysemrel/publication + @@ -281,8 +251,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -290,14 +262,13 @@ --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.dynamicAllocation.enabled=true --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --conf spark.sql.shuffle.partitions=5000 - --preparedInfoPath${workingDir}/preparedInfo/mergedCommunityAssoc + --preparedInfoPath${workingDir}/communitysemrel/preparedInfo/mergedCommunityAssoc --sourcePath${sourcePath}/dataset --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset - --outputPath${outputPath}/dataset - --saveGraph${saveGraph} + --outputPath${workingDir}/communitysemrel/dataset + @@ -311,8 +282,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -320,14 +293,13 @@ --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.dynamicAllocation.enabled=true --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --conf spark.sql.shuffle.partitions=2000 - --preparedInfoPath${workingDir}/preparedInfo/mergedCommunityAssoc + --preparedInfoPath${workingDir}/communitysemrel/preparedInfo/mergedCommunityAssoc --sourcePath${sourcePath}/otherresearchproduct --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct - --outputPath${outputPath}/otherresearchproduct - --saveGraph${saveGraph} + --outputPath${workingDir}/communitysemrel/otherresearchproduct + @@ -341,8 +313,10 @@ eu.dnetlib.dhp.resulttocommunityfromsemrel.SparkResultToCommunityThroughSemRelJob dhp-enrichment-${projectVersion}.jar - --executor-cores=${sparkExecutorCores} - --executor-memory=${sparkExecutorMemory} + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 --driver-memory=${sparkDriverMemory} --conf spark.extraListeners=${spark2ExtraListeners} --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} @@ -350,20 +324,46 @@ --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --conf spark.dynamicAllocation.enabled=true --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} - --conf spark.sql.shuffle.partitions=1000 - --preparedInfoPath${workingDir}/preparedInfo/mergedCommunityAssoc + --preparedInfoPath${workingDir}/communitysemrel/preparedInfo/mergedCommunityAssoc --sourcePath${sourcePath}/software --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.Software - --outputPath${outputPath}/software - --saveGraph${saveGraph} + --outputPath${workingDir}/communitysemrel/software + - + + + + + yarn + cluster + move results + eu.dnetlib.dhp.MoveResult + dhp-enrichment-${projectVersion}.jar + + --executor-cores=6 + --executor-memory=5G + --conf spark.executor.memoryOverhead=3g + --conf spark.sql.shuffle.partitions=3284 + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --sourcePath${workingDir}/communitysemrel/ + --outputPath${sourcePath}/ + + + + + diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_newrelation_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_newrelation_parameters.json new file mode 100644 index 000000000..5fe92cff1 --- /dev/null +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_newrelation_parameters.json @@ -0,0 +1,20 @@ +[ + { + "paramName":"s", + "paramLongName":"sourcePath", + "paramDescription": "the path of the sequencial file to read", + "paramRequired": true + }, + + { + "paramName": "ssm", + "paramLongName": "isSparkSessionManaged", + "paramDescription": "the path where prepared info have been stored", + "paramRequired": false + },{ + "paramName": "o", + "paramLongName": "outputPath", + "paramDescription": "institutional repositories that should not be considered for the propagation", + "paramRequired": false +} +] \ No newline at end of file diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json similarity index 66% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json index 2f00bacae..3f4b1d151 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_prepareresultorg_parameters.json @@ -11,16 +11,11 @@ "paramDescription": "the hive metastore uris", "paramRequired": true }, + { - "paramName":"dop", - "paramLongName":"datasourceOrganizationPath", - "paramDescription": "path where to store/find association from datasource and organization", - "paramRequired": true - }, - { - "paramName":"alp", - "paramLongName":"alreadyLinkedPath", - "paramDescription": "path where to store/find already linked results and organizations", + "paramName":"wp", + "paramLongName":"workingPath", + "paramDescription": "the working path", "paramRequired": true }, { diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/input_propagationresulaffiliationfrominstrepo_parameters.json diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/config-default.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/config-default.xml similarity index 100% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttocommunityfromsemrel/oozie_app/config-default.xml rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/config-default.xml diff --git a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/oozie_app/workflow.xml b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/workflow.xml similarity index 67% rename from dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/oozie_app/workflow.xml rename to dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/workflow.xml index edfff8817..ca76a0e85 100644 --- a/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/resulttoorganizationfrominstrepo/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-enrichment/src/main/resources/eu/dnetlib/dhp/wf/subworkflows/resulttoorganizationfrominstrepo/oozie_app/workflow.xml @@ -5,8 +5,12 @@ the source path - outputPath - sets the outputPath + blacklist + The list of institutional repositories that should not be used for the propagation + + + startFrom + undelete @@ -21,7 +25,15 @@ - + + + + + ${wf:conf('startFrom') eq 'undelete'} + + + + Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}] @@ -29,97 +41,13 @@ - - + + - + - - - - - - - - - - - - - - ${nameNode}/${sourcePath}/relation - ${nameNode}/${outputPath}/relation - - - - - - - - ${nameNode}/${sourcePath}/publication - ${nameNode}/${outputPath}/publication - - - - - - - - ${nameNode}/${sourcePath}/dataset - ${nameNode}/${outputPath}/dataset - - - - - - - - ${nameNode}/${sourcePath}/otherresearchproduct - ${nameNode}/${outputPath}/otherresearchproduct - - - - - - - - ${nameNode}/${sourcePath}/software - ${nameNode}/${outputPath}/software - - - - - - - - ${nameNode}/${sourcePath}/organization - ${nameNode}/${outputPath}/organization - - - - - - - - ${nameNode}/${sourcePath}/project - ${nameNode}/${outputPath}/project - - - - - - - - ${nameNode}/${sourcePath}/datasource - ${nameNode}/${outputPath}/datasource - - - - - - @@ -138,10 +66,9 @@ --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} --sourcePath${sourcePath} - --hive_metastore_uris${hive_metastore_uris} - --datasourceOrganizationPath${workingDir}/preparedInfo/datasourceOrganization - --alreadyLinkedPath${workingDir}/preparedInfo/alreadyLinked + --workingPath${workingDir}/affiliationInstRepo --blacklist${blacklist} + --hive_metastore_uris${hive_metastore_uris} @@ -173,9 +100,9 @@ --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --sourcePath${sourcePath}/publication - --outputPath${outputPath}/relation - --datasourceOrganizationPath${workingDir}/preparedInfo/datasourceOrganization - --alreadyLinkedPath${workingDir}/preparedInfo/alreadyLinked + --outputPath${workingDir}/affiliationInstRepo/publication/relation + --datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization + --alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.Publication @@ -202,9 +129,9 @@ --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --sourcePath${sourcePath}/dataset - --outputPath${outputPath}/relation - --datasourceOrganizationPath${workingDir}/preparedInfo/datasourceOrganization - --alreadyLinkedPath${workingDir}/preparedInfo/alreadyLinked + --outputPath${workingDir}/affiliationInstRepo/dataset/relation + --datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization + --alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.Dataset @@ -231,9 +158,9 @@ --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --sourcePath${sourcePath}/otherresearchproduct - --outputPath${outputPath}/relation - --datasourceOrganizationPath${workingDir}/preparedInfo/datasourceOrganization - --alreadyLinkedPath${workingDir}/preparedInfo/alreadyLinked + --outputPath${workingDir}/affiliationInstRepo/otherresearchproduct/relation + --datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization + --alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.OtherResearchProduct @@ -260,9 +187,9 @@ --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} --sourcePath${sourcePath}/software - --outputPath${outputPath}/relation - --datasourceOrganizationPath${workingDir}/preparedInfo/datasourceOrganization - --alreadyLinkedPath${workingDir}/preparedInfo/alreadyLinked + --outputPath${workingDir}/affiliationInstRepo/software/relation + --datasourceOrganizationPath${workingDir}/affiliationInstRepo/preparedInfo/datasourceOrganization + --alreadyLinkedPath${workingDir}/affiliationInstRepo/preparedInfo/alreadyLinked --hive_metastore_uris${hive_metastore_uris} --resultTableNameeu.dnetlib.dhp.schema.oaf.Software @@ -270,7 +197,32 @@ - + + + + + yarn + cluster + append new relations + eu.dnetlib.dhp.resulttoorganizationfrominstrepo.AppendNewRelations + dhp-enrichment-${projectVersion}.jar + + --executor-cores=${sparkExecutorCores} + --executor-memory=${sparkExecutorMemory} + --driver-memory=${sparkDriverMemory} + --conf spark.extraListeners=${spark2ExtraListeners} + --conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners} + --conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress} + --conf spark.eventLog.dir=${nameNode}${spark2EventLogDir} + --conf spark.dynamicAllocation.enabled=true + --conf spark.dynamicAllocation.maxExecutors=${spark2MaxExecutors} + + --outputPath${sourcePath}/relation + --sourcePath${workingDir}/affiliationInstRepo/ + + + + diff --git a/dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkJobTest.java b/dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkJobTest.java index 517a20cd9..db917658a 100644 --- a/dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkJobTest.java +++ b/dhp-workflows/dhp-enrichment/src/test/java/eu/dnetlib/dhp/entitytoorganizationfromsemrel/SparkJobTest.java @@ -114,7 +114,7 @@ public class SparkJobTest { .option("compression", "gzip") .json(workingDir.toString() + "/projectInput"); - SparkResultToOrganizationFromSemRel + SparkEntityToOrganizationFromSemRel .main( new String[] { @@ -395,7 +395,7 @@ public class SparkJobTest { .option("compression", "gzip") .json(workingDir.toString() + "/projectInput"); - SparkResultToOrganizationFromSemRel + SparkEntityToOrganizationFromSemRel .main( new String[] { @@ -678,7 +678,7 @@ public class SparkJobTest { .option("compression", "gzip") .json(workingDir.toString() + "/projectInput"); - SparkResultToOrganizationFromSemRel + SparkEntityToOrganizationFromSemRel .main( new String[] { diff --git a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/OafToOafMapper.java b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/OafToOafMapper.java index a63296d18..eee518353 100644 --- a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/OafToOafMapper.java +++ b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/OafToOafMapper.java @@ -11,6 +11,7 @@ import java.util.List; import java.util.Set; import java.util.stream.Collectors; +import org.apache.commons.lang3.ObjectUtils; import org.apache.commons.lang3.StringUtils; import org.dom4j.Document; import org.dom4j.Element; @@ -27,6 +28,15 @@ import eu.dnetlib.dhp.schema.oaf.utils.ModelHardLimits; public class OafToOafMapper extends AbstractMdRecordToOafMapper { + private static Set DC_TYPE_PUBLICATION_VERSION = new HashSet<>(); + + static { + DC_TYPE_PUBLICATION_VERSION.add("info:eu-repo/semantics/submittedVersion"); + DC_TYPE_PUBLICATION_VERSION.add("info:eu-repo/semantics/acceptedVersion"); + DC_TYPE_PUBLICATION_VERSION.add("info:eu-repo/semantics/publishedVersion"); + DC_TYPE_PUBLICATION_VERSION.add("info:eu-repo/semantics/updatedVersion"); + } + public OafToOafMapper(final VocabularyGroup vocs, final boolean invisible, final boolean shouldHashId, final boolean forceOrginalId) { super(vocs, invisible, shouldHashId, forceOrginalId); @@ -192,24 +202,40 @@ public class OafToOafMapper extends AbstractMdRecordToOafMapper { /** * The Dublin Core element dc:type can be repeated, but we need to base our mapping on a single value * So this method tries to give precedence to the COAR resource type, when available. Otherwise, it looks for the - * openaire's info:eu-repo type, and as last resort picks the 1st type text available + * openaire's info:eu-repo type, but excluding the following + * + * info:eu-repo/semantics/draft + * info:eu-repo/semantics/submittedVersion + * info:eu-repo/semantics/acceptedVersion + * info:eu-repo/semantics/publishedVersion + * info:eu-repo/semantics/updatedVersion + * + * Then, it picks the 1st dc:type text available and, in case there is no dc:type element, as last resort it tries + * to extract the type from the dr:CobjCategory element + * + * Examples: * * http://purl.org/coar/resource_type/c_5794 * info:eu-repo/semantics/article * Conference article + * 0006 * * @param doc the input document * @return the chosen resource type */ @Override protected String findOriginalType(Document doc) { - return (String) doc + final String dcType = (String) doc .selectNodes("//dc:type") .stream() .map(o -> "" + ((Node) o).getText().trim()) + .filter(t -> !DC_TYPE_PUBLICATION_VERSION.contains(t)) .sorted(new OriginalTypeComparator()) .findFirst() .orElse(null); + + final String drCobjCategory = doc.valueOf("//dr:CobjCategory/text()"); + return ObjectUtils.firstNonNull(dcType, drCobjCategory); } @Override diff --git a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/OdfToOafMapper.java b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/OdfToOafMapper.java index e63b01a00..57e0d2955 100644 --- a/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/OdfToOafMapper.java +++ b/dhp-workflows/dhp-graph-mapper/src/main/java/eu/dnetlib/dhp/oa/graph/raw/OdfToOafMapper.java @@ -221,27 +221,48 @@ public class OdfToOafMapper extends AbstractMdRecordToOafMapper { } /** - * The Datacite element + * Extracts the resource type from The Datacite element * - * journal article + * journal article * * @param doc the input document * @return the chosen resource type */ @Override protected String findOriginalType(Document doc) { - return Optional + final String resourceType = Optional .ofNullable( (Element) doc .selectSingleNode( "//*[local-name()='metadata']/*[local-name() = 'resource']/*[local-name() = 'resourceType']")) - .map(element -> { - final String resourceTypeURI = element.attributeValue("anyURI"); - final String resourceTypeTxt = element.getText(); + .map(e -> { + final String resourceTypeURI = Optional + .ofNullable(e.attributeValue("uri")) + .filter(StringUtils::isNotBlank) + .orElse(null); + final String resourceTypeAnyURI = Optional + .ofNullable(e.attributeValue("anyURI")) + .filter(StringUtils::isNotBlank) + .orElse(null); + final String resourceTypeTxt = Optional + .ofNullable(e.getText()) + .filter(StringUtils::isNotBlank) + .orElse(null); + final String resourceTypeGeneral = Optional + .ofNullable(e.attributeValue("resourceTypeGeneral")) + .filter(StringUtils::isNotBlank) + .orElse(null); - return ObjectUtils.firstNonNull(resourceTypeURI, resourceTypeTxt); + return ObjectUtils + .firstNonNull(resourceTypeURI, resourceTypeAnyURI, resourceTypeTxt, resourceTypeGeneral); }) .orElse(null); + + final String drCobjCategory = doc.valueOf("//dr:CobjCategory/text()"); + return ObjectUtils.firstNonNull(resourceType, drCobjCategory); } @Override diff --git a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/enrich/orcid/oozie_app/workflow.xml b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/enrich/orcid/oozie_app/workflow.xml index ce117b5e9..3493ecb2f 100644 --- a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/enrich/orcid/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/enrich/orcid/oozie_app/workflow.xml @@ -43,6 +43,17 @@ --graphPath${graphPath} --masteryarn + + + + + + + + + + + diff --git a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/hostedbymap/oozie_app/download.sh b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/hostedbymap/oozie_app/download.sh index 35220bd8c..9877fe7de 100644 --- a/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/hostedbymap/oozie_app/download.sh +++ b/dhp-workflows/dhp-graph-mapper/src/main/resources/eu/dnetlib/dhp/oa/graph/hostedbymap/oozie_app/download.sh @@ -1,3 +1,3 @@ #!/bin/bash curl -LSs $1 | hdfs dfs -put - $2/$3 -curl -LSs http://api.crossref.org/works/10.1099/jgv.0.001453 > prova.txt \ No newline at end of file +#curl -LSs http://api.crossref.org/works/10.1099/jgv.0.001453 > prova.txt \ No newline at end of file diff --git a/dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/oa/graph/raw/CopyHdfsOafSparkApplication.scala b/dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/oa/graph/raw/CopyHdfsOafSparkApplication.scala index 533948289..9d7cca7dd 100644 --- a/dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/oa/graph/raw/CopyHdfsOafSparkApplication.scala +++ b/dhp-workflows/dhp-graph-mapper/src/main/scala/eu/dnetlib/dhp/oa/graph/raw/CopyHdfsOafSparkApplication.scala @@ -93,8 +93,8 @@ object CopyHdfsOafSparkApplication { hasSource != null && hasTarget != null } else { val hasId = (json \ "id").extractOrElse[String](null) - val resultType = (json \ "resulttype" \ "classid").extractOrElse[String](null) - hasId != null && oafType.equalsIgnoreCase(resultType) + val resultType = (json \ "resulttype" \ "classid").extractOrElse[String]("") + hasId != null && oafType.startsWith(resultType) } } diff --git a/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/CopyHdfsOafSparkApplicationTest.java b/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/CopyHdfsOafSparkApplicationTest.java index 85cb551bc..1f5559377 100644 --- a/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/CopyHdfsOafSparkApplicationTest.java +++ b/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/CopyHdfsOafSparkApplicationTest.java @@ -59,7 +59,19 @@ public class CopyHdfsOafSparkApplicationTest { .getResourceAsStream( "/eu/dnetlib/dhp/oa/graph/raw/publication_2_unknownProperty.json")), "publication")); + } + @Test + void isOafType_Datacite_ORP() throws IOException { + assertTrue( + CopyHdfsOafSparkApplication + .isOafType( + IOUtils + .toString( + getClass() + .getResourceAsStream( + "/eu/dnetlib/dhp/oa/graph/raw/datacite_orp.json")), + "otherresearchproduct")); } } diff --git a/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/MappersTest.java b/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/MappersTest.java index ac0435ce2..1f2952b75 100644 --- a/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/MappersTest.java +++ b/dhp-workflows/dhp-graph-mapper/src/test/java/eu/dnetlib/dhp/oa/graph/raw/MappersTest.java @@ -1171,6 +1171,34 @@ class MappersTest { } + @Test + void test_Zenodo2() throws IOException { + final String xml = IOUtils.toString(Objects.requireNonNull(getClass().getResourceAsStream("odf_zenodo2.xml"))); + final List list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml); + + assertEquals(3, list.size()); + Publication p = cleanup((Publication) list.get(0), vocs); + + assertNotNull(p.getInstance()); + assertEquals(1, p.getInstance().size()); + + final Instance instance = p.getInstance().get(0); + + assertNotNull(instance.getInstanceTypeMapping()); + assertEquals(1, instance.getInstanceTypeMapping().size()); + + Optional coarType = instance + .getInstanceTypeMapping() + .stream() + .filter(itm -> ModelConstants.OPENAIRE_COAR_RESOURCE_TYPES_3_1.equals(itm.getVocabularyName())) + .findFirst(); + + assertTrue(coarType.isPresent()); + assertNotNull(coarType.get().getOriginalType()); + assertNull(coarType.get().getTypeCode()); + assertNull(coarType.get().getTypeLabel()); + } + @Test void testROHub2() throws IOException { final String xml = IOUtils @@ -1229,7 +1257,7 @@ class MappersTest { } @Test - public void testD4ScienceTraining() throws IOException { + void testD4ScienceTraining() throws IOException { final String xml = IOUtils .toString(Objects.requireNonNull(getClass().getResourceAsStream("d4science-1-training.xml"))); final List list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml); @@ -1240,7 +1268,7 @@ class MappersTest { } @Test - public void testD4ScienceDataset() throws IOException { + void testD4ScienceDataset() throws IOException { final String xml = IOUtils .toString(Objects.requireNonNull(getClass().getResourceAsStream("d4science-2-dataset.xml"))); final List list = new OdfToOafMapper(vocs, false, true).processMdRecord(xml); diff --git a/dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/datacite_orp.json b/dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/datacite_orp.json new file mode 100644 index 000000000..abf44b49c --- /dev/null +++ b/dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/datacite_orp.json @@ -0,0 +1 @@ +{"collectedfrom":[{"key":"10|openaire____::9e3be59865b2c1c335d32dae2fe7b254","value":"Datacite","dataInfo":null}],"dataInfo":{"invisible":false,"inferred":false,"deletedbyinference":false,"trust":"0.9","inferenceprovenance":null,"provenanceaction":{"classid":"sysimport:actionset","classname":"sysimport:actionset","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}},"lastupdatetimestamp":null,"id":"50|doi_________::0a2763977bb76876aff2d3b33a874552","originalId":["50|datacite____::0a2763977bb76876aff2d3b33a874552","10.25935/nhb2-wy29"],"pid":[{"value":"10.25935/nhb2-wy29","qualifier":{"classid":"doi","classname":"doi","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"dataInfo":{"invisible":false,"inferred":false,"deletedbyinference":false,"trust":"0.9","inferenceprovenance":null,"provenanceaction":{"classid":"sysimport:actionset","classname":"sysimport:actionset","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}],"dateofcollection":"2024-01-15T18:00:35+0000","dateoftransformation":"2024-01-15T18:00:35+0000","extraInfo":null,"oaiprovenance":null,"measures":null,"processingchargeamount":null,"processingchargecurrency":null,"author":[{"fullname":"Louis, Corentin","name":"Corentin","surname":"Louis","rank":1,"pid":[{"value":"https://orcid.org/0000-0002-9552-8822","qualifier":{"classid":"orcid","classname":"Open Researcher and Contributor ID","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"dataInfo":{"invisible":false,"inferred":false,"deletedbyinference":false,"trust":"0.9","inferenceprovenance":null,"provenanceaction":{"classid":"sysimport:actionset","classname":"sysimport:actionset","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}],"affiliation":[{"value":"Dublin Institute For Advanced Studies","dataInfo":{"invisible":false,"inferred":false,"deletedbyinference":false,"trust":"0.9","inferenceprovenance":null,"provenanceaction":{"classid":"sysimport:actionset","classname":"sysimport:actionset","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}]},{"fullname":"Zarka, Philippe","name":"Philippe","surname":"Zarka","rank":2,"pid":[{"value":"https://orcid.org/0000-0003-1672-9878","qualifier":{"classid":"orcid","classname":"Open Researcher and Contributor ID","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"dataInfo":{"invisible":false,"inferred":false,"deletedbyinference":false,"trust":"0.9","inferenceprovenance":null,"provenanceaction":{"classid":"sysimport:actionset","classname":"sysimport:actionset","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}],"affiliation":[{"value":"Laboratory of Space Studies and Instrumentation in Astrophysics","dataInfo":{"invisible":false,"inferred":false,"deletedbyinference":false,"trust":"0.9","inferenceprovenance":null,"provenanceaction":{"classid":"sysimport:actionset","classname":"sysimport:actionset","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}]},{"fullname":"Cecconi, Baptiste","name":"Baptiste","surname":"Cecconi","rank":3,"pid":[{"value":"https://orcid.org/0000-0001-7915-5571","qualifier":{"classid":"orcid","classname":"Open Researcher and Contributor ID","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"dataInfo":{"invisible":false,"inferred":false,"deletedbyinference":false,"trust":"0.9","inferenceprovenance":null,"provenanceaction":{"classid":"sysimport:actionset","classname":"sysimport:actionset","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}],"affiliation":[{"value":"Laboratory of Space Studies and Instrumentation in Astrophysics","dataInfo":{"invisible":false,"inferred":false,"deletedbyinference":false,"trust":"0.9","inferenceprovenance":null,"provenanceaction":{"classid":"sysimport:actionset","classname":"sysimport:actionset","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}]},{"fullname":"Kurth, William","name":"William","surname":"Kurth","rank":4,"pid":[{"value":"https://orcid.org/0000-0002-5471-6202","qualifier":{"classid":"orcid","classname":"Open Researcher and Contributor ID","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"dataInfo":{"invisible":false,"inferred":false,"deletedbyinference":false,"trust":"0.9","inferenceprovenance":null,"provenanceaction":{"classid":"sysimport:actionset","classname":"sysimport:actionset","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}],"affiliation":[{"value":"University of Iowa","dataInfo":{"invisible":false,"inferred":false,"deletedbyinference":false,"trust":"0.9","inferenceprovenance":null,"provenanceaction":{"classid":"sysimport:actionset","classname":"sysimport:actionset","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}]}],"resulttype":{"classid":"other","classname":"other","schemeid":"dnet:result_typologies","schemename":"dnet:result_typologies"},"metaResourceType":null,"language":null,"country":null,"subject":[],"title":[{"value":"Catalogue of Jupiter radio emissions identified in the Juno/Waves observations","qualifier":{"classid":"main title","classname":"main title","schemeid":"dnet:dataCite_title","schemename":"dnet:dataCite_title"},"dataInfo":null}],"relevantdate":[{"value":"2021-01-01","qualifier":{"classid":"issued","classname":"issued","schemeid":"dnet:dataCite_date","schemename":"dnet:dataCite_date"},"dataInfo":null}],"description":[],"dateofacceptance":{"value":"2021-01-01","dataInfo":null},"publisher":{"value":"PADC/MASER","dataInfo":null},"embargoenddate":null,"source":null,"fulltext":null,"format":null,"contributor":null,"resourcetype":null,"coverage":null,"bestaccessright":null,"context":null,"externalReference":null,"instance":[{"license":{"value":"https://creativecommons.org/licenses/by/4.0/legalcode","dataInfo":null},"accessright":{"classid":"UNKNOWN","classname":"not available","schemeid":"dnet:access_modes","schemename":"dnet:access_modes","openAccessRoute":null},"instancetype":{"classid":"0022","classname":"Collection","schemeid":"dnet:publication_resource","schemename":"dnet:publication_resource"},"instanceTypeMapping":[{"originalType":"Collection","typeCode":null,"typeLabel":null,"vocabularyName":"openaire::coar_resource_types_3_1"}],"hostedby":{"key":"10|openaire____::55045bd2a65019fd8e6741a755395c8c","value":"Unknown Repository","dataInfo":null},"url":["https://dx.doi.org/10.25935/nhb2-wy29"],"distributionlocation":null,"collectedfrom":{"key":"10|openaire____::9e3be59865b2c1c335d32dae2fe7b254","value":"Datacite","dataInfo":null},"pid":[{"value":"10.25935/nhb2-wy29","qualifier":{"classid":"doi","classname":"doi","schemeid":"dnet:pid_types","schemename":"dnet:pid_types"},"dataInfo":{"invisible":false,"inferred":false,"deletedbyinference":false,"trust":"0.9","inferenceprovenance":null,"provenanceaction":{"classid":"sysimport:actionset","classname":"sysimport:actionset","schemeid":"dnet:provenanceActions","schemename":"dnet:provenanceActions"}}}],"alternateIdentifier":null,"dateofacceptance":{"value":"2021-01-01","dataInfo":null},"processingchargeamount":null,"processingchargecurrency":null,"refereed":null,"measures":null,"fulltext":null}],"eoscifguidelines":null,"openAccessColor":null,"publiclyFunded":null,"contactperson":null,"contactgroup":null,"tool":null,"isGreen":null,"isInDiamondJournal":null} \ No newline at end of file diff --git a/dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/odf_zenodo2.xml b/dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/odf_zenodo2.xml new file mode 100644 index 000000000..ebe105de8 --- /dev/null +++ b/dhp-workflows/dhp-graph-mapper/src/test/resources/eu/dnetlib/dhp/oa/graph/raw/odf_zenodo2.xml @@ -0,0 +1,59 @@ + + +
+ oai:zenodo.org:1596086 + 2020-01-20T13:50:28Z + openaire + 2024-02-08T11:03:10.994Z + od______2659::036d5555a6688ed00c8d0da97bdece3b + 2024-02-08T11:03:10.994Z + 2024-02-08T11:03:10.994Z +
+ + + https://zenodo.org/record/1596086 + + + + Bonney, T. G. + T. G. + Bonney + + + + Ice Blocks on a Moraine + + Zenodo + 1889 + + 1889-08-22 + + + + 10.1038/040391a0 + + + Creative Commons Zero v1.0 Universal + Open Access + + + n/a + + + 0001 + 1889-08-22 + OPEN + http://creativecommons.org/publicdomain/zero/1.0/legalcode + + + + + diff --git a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/XmlConverterJob.java b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/XmlConverterJob.java index 518f41120..6f43ca3f7 100644 --- a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/XmlConverterJob.java +++ b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/XmlConverterJob.java @@ -62,8 +62,8 @@ public class XmlConverterJob { final String outputPath = parser.get("outputPath"); log.info("outputPath: {}", outputPath); - final String isLookupUrl = parser.get("isLookupUrl"); - log.info("isLookupUrl: {}", isLookupUrl); + final String contextApiBaseUrl = parser.get("contextApiBaseUrl"); + log.info("contextApiBaseUrl: {}", contextApiBaseUrl); final SparkConf conf = new SparkConf(); conf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer"); @@ -71,7 +71,7 @@ public class XmlConverterJob { runWithSparkSession(conf, isSparkSessionManaged, spark -> { removeOutputDir(spark, outputPath); - convertToXml(spark, inputPath, outputPath, ContextMapper.fromIS(isLookupUrl)); + convertToXml(spark, inputPath, outputPath, ContextMapper.fromAPI(contextApiBaseUrl)); }); } diff --git a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/ContextMapper.java b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/ContextMapper.java index bcaf40603..083dbe988 100644 --- a/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/ContextMapper.java +++ b/dhp-workflows/dhp-graph-provision/src/main/java/eu/dnetlib/dhp/oa/provision/utils/ContextMapper.java @@ -1,18 +1,22 @@ package eu.dnetlib.dhp.oa.provision.utils; -import java.io.Serializable; -import java.io.StringReader; +import java.io.*; +import java.net.HttpURLConnection; +import java.net.URL; import java.util.HashMap; import org.dom4j.Document; import org.dom4j.DocumentException; import org.dom4j.Node; import org.dom4j.io.SAXReader; +import org.jetbrains.annotations.NotNull; import org.xml.sax.SAXException; import com.google.common.base.Joiner; +import eu.dnetlib.dhp.common.api.context.*; +import eu.dnetlib.dhp.common.rest.DNetRestClient; import eu.dnetlib.dhp.utils.ISLookupClientFactory; import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException; import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService; @@ -23,6 +27,45 @@ public class ContextMapper extends HashMap implements Serial private static final String XQUERY = "for $x in //RESOURCE_PROFILE[.//RESOURCE_TYPE/@value='ContextDSResourceType']//*[name()='context' or name()='category' or name()='concept'] return "; + public static ContextMapper fromAPI(final String baseURL) throws Exception { + + final ContextMapper contextMapper = new ContextMapper(); + + for (ContextSummary ctx : DNetRestClient + .doGET(String.format("%s/contexts", baseURL), ContextSummaryList.class)) { + + contextMapper.put(ctx.getId(), new ContextDef(ctx.getId(), ctx.getLabel(), "context", ctx.getType())); + + for (CategorySummary cat : DNetRestClient + .doGET(String.format("%s/context/%s?all=true", baseURL, ctx.getId()), CategorySummaryList.class)) { + contextMapper.put(cat.getId(), new ContextDef(cat.getId(), cat.getLabel(), "category", "")); + if (cat.isHasConcept()) { + for (ConceptSummary c : DNetRestClient + .doGET( + String.format("%s/context/category/%s?all=true", baseURL, cat.getId()), + ConceptSummaryList.class)) { + contextMapper.put(c.getId(), new ContextDef(c.getId(), c.getLabel(), "concept", "")); + if (c.isHasSubConcept()) { + for (ConceptSummary cs : c.getConcepts()) { + contextMapper.put(cs.getId(), new ContextDef(cs.getId(), cs.getLabel(), "concept", "")); + if (cs.isHasSubConcept()) { + for (ConceptSummary css : cs.getConcepts()) { + contextMapper + .put( + css.getId(), + new ContextDef(css.getId(), css.getLabel(), "concept", "")); + } + } + } + } + } + } + } + } + return contextMapper; + } + + @Deprecated public static ContextMapper fromIS(final String isLookupUrl) throws DocumentException, ISLookUpException, SAXException { ISLookUpService isLookUp = ISLookupClientFactory.getLookUpService(isLookupUrl); @@ -32,6 +75,7 @@ public class ContextMapper extends HashMap implements Serial return fromXml(sb.toString()); } + @Deprecated public static ContextMapper fromXml(final String xml) throws DocumentException, SAXException { final ContextMapper contextMapper = new ContextMapper(); diff --git a/dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/oa/provision/input_params_xml_converter.json b/dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/oa/provision/input_params_xml_converter.json index eda6154d7..653a69ed1 100644 --- a/dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/oa/provision/input_params_xml_converter.json +++ b/dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/oa/provision/input_params_xml_converter.json @@ -12,9 +12,9 @@ "paramRequired": true }, { - "paramName": "ilu", - "paramLongName": "isLookupUrl", - "paramDescription": "URL of the isLookUp Service", + "paramName": "cau", + "paramLongName": "contextApiBaseUrl", + "paramDescription": "URL of the context API", "paramRequired": true } ] diff --git a/dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/oa/provision/oozie_app/workflow.xml b/dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/oa/provision/oozie_app/workflow.xml index 2e7b11dde..9eab960f0 100644 --- a/dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/oa/provision/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-graph-provision/src/main/resources/eu/dnetlib/dhp/oa/provision/oozie_app/workflow.xml @@ -9,6 +9,10 @@ isLookupUrl URL for the isLookup service + + contextApiBaseUrl + context API URL + relPartitions number or partitions for the relations Dataset @@ -589,7 +593,7 @@ --inputPath${workingDir}/join_entities --outputPath${workingDir}/xml - --isLookupUrl${isLookupUrl} + --contextApiBaseUrl${contextApiBaseUrl} diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml index cbf97944d..f15f22320 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml @@ -78,6 +78,10 @@ hive.txn.timeout ${hive_timeout} + + hive.mapjoin.followby.gby.localtask.max.memory.usage + 0.80 + mapred.job.queue.name analytics diff --git a/pom.xml b/pom.xml index 3fd351c1d..6ef320253 100644 --- a/pom.xml +++ b/pom.xml @@ -931,5 +931,25 @@ --> + + + + arm-silicon-mac + + + aarch64 + mac + + + + + + org.xerial.snappy + snappy-java + 1.1.8.4 + + + + \ No newline at end of file