Compare commits
71 Commits
Author | SHA1 | Date |
---|---|---|
Claudio Atzori | 9a5b134ddf | |
Claudio Atzori | 069803f34a | |
Claudio Atzori | 71c1f81b54 | |
Claudio Atzori | c3c9bdb59c | |
Claudio Atzori | 91b61687fa | |
Claudio Atzori | 63067d4b24 | |
Claudio Atzori | e0c315b07b | |
Claudio Atzori | 54936b7f42 | |
Michele Artini | e1149eb5c4 | |
Michele Artini | 3f174ad90f | |
Michele Artini | 6ffb1faf09 | |
Giambattista Bloisi | 3f22c101d9 | |
Giambattista Bloisi | 0ff7faad72 | |
Michele Artini | 7faa115ba0 | |
Michele Artini | f9c74c98fa | |
Claudio Atzori | 7ae7e8aa06 | |
Giambattista Bloisi | 664a381d31 | |
Michele Artini | cb29b9773c | |
Michele Artini | 85b844d57e | |
Michele Artini | 455f2e1e07 | |
Michele Artini | 88fef367b9 | |
Giambattista Bloisi | 9092075760 | |
Miriam Baglioni | 5180b6ec8a | |
Miriam Baglioni | 7827a2d66b | |
Giambattista Bloisi | 3cd5590f3b | |
Giambattista Bloisi | 56dd05f85c | |
Sandro La Bruzzo | 7d806a434c | |
Sandro La Bruzzo | e468e99100 | |
Sandro La Bruzzo | b63994dcc4 | |
Sandro La Bruzzo | 915a76a796 | |
Giambattista Bloisi | 773e856550 | |
Sandro La Bruzzo | a712df1e1d | |
Sandro La Bruzzo | b32a9d1994 | |
Michele Artini | 3268570b2c | |
Miriam Baglioni | 72bae7af76 | |
Serafeim Chatzopoulos | f0dc12634b | |
Claudio Atzori | 753c2a72bd | |
Claudio Atzori | a63b091bae | |
Giambattista Bloisi | 85aeff72f1 | |
Giambattista Bloisi | d65285da7f | |
Giambattista Bloisi | 29194472a7 | |
Miriam Baglioni | eca021f4d6 | |
Miriam Baglioni | bdb6bbb365 | |
Claudio Atzori | d85d2df6ad | |
Giambattista Bloisi | b19643f6eb | |
Claudio Atzori | e6bdee86d1 | |
Claudio Atzori | 38c9001147 | |
Claudio Atzori | fd17c1f17c | |
Claudio Atzori | 009dcf6aea | |
Claudio Atzori | bb82052c40 | |
Claudio Atzori | 42f5506306 | |
Alessia Bardi | f2a08d8cc2 | |
Miriam Baglioni | 07a373a0bd | |
Miriam Baglioni | ead08b0dd4 | |
Miriam Baglioni | a5995ab557 | |
Sandro La Bruzzo | 9aebca77a0 | |
Sandro La Bruzzo | 0386f36385 | |
Sandro La Bruzzo | 43e0bba7ed | |
Miriam Baglioni | f7d06dc661 | |
Miriam Baglioni | 6e58d79623 | |
Miriam Baglioni | e0ec800d7e | |
Sandro La Bruzzo | e0753f19da | |
sandro.labruzzo | e328bc0ade | |
Sandro La Bruzzo | 859babf722 | |
Sandro La Bruzzo | 39ebb60b38 | |
Sandro La Bruzzo | 9d5a7c3b22 | |
Sandro La Bruzzo | 8f61063201 | |
Sandro La Bruzzo | 1a42a5c10d | |
Miriam Baglioni | 624f5f3f21 | |
Miriam Baglioni | 354e02e6a9 | |
Miriam Baglioni | b00771c7cc |
|
@ -0,0 +1,53 @@
|
|||
|
||||
package eu.dnetlib.dhp.common.api;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.io.InputStream;
|
||||
|
||||
import okhttp3.MediaType;
|
||||
import okhttp3.RequestBody;
|
||||
import okhttp3.internal.Util;
|
||||
import okio.BufferedSink;
|
||||
import okio.Okio;
|
||||
import okio.Source;
|
||||
|
||||
public class InputStreamRequestBody extends RequestBody {
|
||||
|
||||
private final InputStream inputStream;
|
||||
private final MediaType mediaType;
|
||||
private final long lenght;
|
||||
|
||||
public static RequestBody create(final MediaType mediaType, final InputStream inputStream, final long len) {
|
||||
|
||||
return new InputStreamRequestBody(inputStream, mediaType, len);
|
||||
}
|
||||
|
||||
private InputStreamRequestBody(InputStream inputStream, MediaType mediaType, long len) {
|
||||
this.inputStream = inputStream;
|
||||
this.mediaType = mediaType;
|
||||
this.lenght = len;
|
||||
}
|
||||
|
||||
@Override
|
||||
public MediaType contentType() {
|
||||
return mediaType;
|
||||
}
|
||||
|
||||
@Override
|
||||
public long contentLength() {
|
||||
|
||||
return lenght;
|
||||
|
||||
}
|
||||
|
||||
@Override
|
||||
public void writeTo(BufferedSink sink) throws IOException {
|
||||
Source source = null;
|
||||
try {
|
||||
source = Okio.source(inputStream);
|
||||
sink.writeAll(source);
|
||||
} finally {
|
||||
Util.closeQuietly(source);
|
||||
}
|
||||
}
|
||||
}
|
|
@ -0,0 +1,8 @@
|
|||
|
||||
package eu.dnetlib.dhp.common.api;
|
||||
|
||||
public class MissingConceptDoiException extends Throwable {
|
||||
public MissingConceptDoiException(String message) {
|
||||
super(message);
|
||||
}
|
||||
}
|
|
@ -0,0 +1,365 @@
|
|||
|
||||
package eu.dnetlib.dhp.common.api;
|
||||
|
||||
import java.io.*;
|
||||
import java.io.IOException;
|
||||
import java.net.HttpURLConnection;
|
||||
import java.net.URL;
|
||||
import java.util.concurrent.TimeUnit;
|
||||
|
||||
import org.apache.http.HttpHeaders;
|
||||
import org.apache.http.entity.ContentType;
|
||||
import org.jetbrains.annotations.NotNull;
|
||||
|
||||
import com.google.gson.Gson;
|
||||
|
||||
import eu.dnetlib.dhp.common.api.zenodo.ZenodoModel;
|
||||
import eu.dnetlib.dhp.common.api.zenodo.ZenodoModelList;
|
||||
import okhttp3.*;
|
||||
|
||||
public class ZenodoAPIClient implements Serializable {
|
||||
|
||||
String urlString;
|
||||
String bucket;
|
||||
|
||||
String deposition_id;
|
||||
String access_token;
|
||||
|
||||
public static final MediaType MEDIA_TYPE_JSON = MediaType.parse("application/json; charset=utf-8");
|
||||
|
||||
private static final MediaType MEDIA_TYPE_ZIP = MediaType.parse("application/zip");
|
||||
|
||||
public String getUrlString() {
|
||||
return urlString;
|
||||
}
|
||||
|
||||
public void setUrlString(String urlString) {
|
||||
this.urlString = urlString;
|
||||
}
|
||||
|
||||
public String getBucket() {
|
||||
return bucket;
|
||||
}
|
||||
|
||||
public void setBucket(String bucket) {
|
||||
this.bucket = bucket;
|
||||
}
|
||||
|
||||
public void setDeposition_id(String deposition_id) {
|
||||
this.deposition_id = deposition_id;
|
||||
}
|
||||
|
||||
public ZenodoAPIClient(String urlString, String access_token) {
|
||||
|
||||
this.urlString = urlString;
|
||||
this.access_token = access_token;
|
||||
}
|
||||
|
||||
/**
|
||||
* Brand new deposition in Zenodo. It sets the deposition_id and the bucket where to store the files to upload
|
||||
*
|
||||
* @return response code
|
||||
* @throws IOException
|
||||
*/
|
||||
public int newDeposition() throws IOException {
|
||||
String json = "{}";
|
||||
|
||||
URL url = new URL(urlString);
|
||||
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
|
||||
conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString());
|
||||
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
|
||||
conn.setRequestMethod("POST");
|
||||
conn.setDoOutput(true);
|
||||
try (OutputStream os = conn.getOutputStream()) {
|
||||
byte[] input = json.getBytes("utf-8");
|
||||
os.write(input, 0, input.length);
|
||||
}
|
||||
|
||||
String body = getBody(conn);
|
||||
|
||||
int responseCode = conn.getResponseCode();
|
||||
conn.disconnect();
|
||||
|
||||
if (!checkOKStatus(responseCode))
|
||||
throw new IOException("Unexpected code " + responseCode + body);
|
||||
|
||||
ZenodoModel newSubmission = new Gson().fromJson(body, ZenodoModel.class);
|
||||
this.bucket = newSubmission.getLinks().getBucket();
|
||||
this.deposition_id = newSubmission.getId();
|
||||
|
||||
return responseCode;
|
||||
}
|
||||
|
||||
/**
|
||||
* Upload files in Zenodo.
|
||||
*
|
||||
* @param is the inputStream for the file to upload
|
||||
* @param file_name the name of the file as it will appear on Zenodo
|
||||
* @return the response code
|
||||
*/
|
||||
public int uploadIS(InputStream is, String file_name) throws IOException {
|
||||
|
||||
URL url = new URL(bucket + "/" + file_name);
|
||||
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
|
||||
conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, "application/zip");
|
||||
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
|
||||
conn.setDoOutput(true);
|
||||
conn.setRequestMethod("PUT");
|
||||
|
||||
byte[] buf = new byte[8192];
|
||||
int length;
|
||||
try (OutputStream os = conn.getOutputStream()) {
|
||||
while ((length = is.read(buf)) != -1) {
|
||||
os.write(buf, 0, length);
|
||||
}
|
||||
|
||||
}
|
||||
int responseCode = conn.getResponseCode();
|
||||
if (!checkOKStatus(responseCode)) {
|
||||
throw new IOException("Unexpected code " + responseCode + getBody(conn));
|
||||
}
|
||||
|
||||
return responseCode;
|
||||
}
|
||||
|
||||
@NotNull
|
||||
private String getBody(HttpURLConnection conn) throws IOException {
|
||||
String body = "{}";
|
||||
try (BufferedReader br = new BufferedReader(
|
||||
new InputStreamReader(conn.getInputStream(), "utf-8"))) {
|
||||
StringBuilder response = new StringBuilder();
|
||||
String responseLine = null;
|
||||
while ((responseLine = br.readLine()) != null) {
|
||||
response.append(responseLine.trim());
|
||||
}
|
||||
|
||||
body = response.toString();
|
||||
|
||||
}
|
||||
return body;
|
||||
}
|
||||
|
||||
/**
|
||||
* Associates metadata information to the current deposition
|
||||
*
|
||||
* @param metadata the metadata
|
||||
* @return response code
|
||||
* @throws IOException
|
||||
*/
|
||||
public int sendMretadata(String metadata) throws IOException {
|
||||
|
||||
URL url = new URL(urlString + "/" + deposition_id);
|
||||
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
|
||||
conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString());
|
||||
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
|
||||
conn.setDoOutput(true);
|
||||
conn.setRequestMethod("PUT");
|
||||
|
||||
try (OutputStream os = conn.getOutputStream()) {
|
||||
byte[] input = metadata.getBytes("utf-8");
|
||||
os.write(input, 0, input.length);
|
||||
|
||||
}
|
||||
|
||||
final int responseCode = conn.getResponseCode();
|
||||
conn.disconnect();
|
||||
if (!checkOKStatus(responseCode))
|
||||
throw new IOException("Unexpected code " + responseCode + getBody(conn));
|
||||
|
||||
return responseCode;
|
||||
|
||||
}
|
||||
|
||||
private boolean checkOKStatus(int responseCode) {
|
||||
|
||||
if (HttpURLConnection.HTTP_OK != responseCode ||
|
||||
HttpURLConnection.HTTP_CREATED != responseCode)
|
||||
return true;
|
||||
return false;
|
||||
}
|
||||
|
||||
/**
|
||||
* To publish the current deposition. It works for both new deposition or new version of an old deposition
|
||||
*
|
||||
* @return response code
|
||||
* @throws IOException
|
||||
*/
|
||||
@Deprecated
|
||||
public int publish() throws IOException {
|
||||
|
||||
String json = "{}";
|
||||
|
||||
OkHttpClient httpClient = new OkHttpClient.Builder().connectTimeout(600, TimeUnit.SECONDS).build();
|
||||
|
||||
RequestBody body = RequestBody.create(json, MEDIA_TYPE_JSON);
|
||||
|
||||
Request request = new Request.Builder()
|
||||
.url(urlString + "/" + deposition_id + "/actions/publish")
|
||||
.addHeader("Authorization", "Bearer " + access_token)
|
||||
.post(body)
|
||||
.build();
|
||||
|
||||
try (Response response = httpClient.newCall(request).execute()) {
|
||||
|
||||
if (!response.isSuccessful())
|
||||
throw new IOException("Unexpected code " + response + response.body().string());
|
||||
|
||||
return response.code();
|
||||
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* To create a new version of an already published deposition. It sets the deposition_id and the bucket to be used
|
||||
* for the new version.
|
||||
*
|
||||
* @param concept_rec_id the concept record id of the deposition for which to create a new version. It is the last
|
||||
* part of the url for the DOI Zenodo suggests to use to cite all versions: DOI: 10.xxx/zenodo.656930
|
||||
* concept_rec_id = 656930
|
||||
* @return response code
|
||||
* @throws IOException
|
||||
* @throws MissingConceptDoiException
|
||||
*/
|
||||
public int newVersion(String concept_rec_id) throws IOException, MissingConceptDoiException {
|
||||
setDepositionId(concept_rec_id, 1);
|
||||
String json = "{}";
|
||||
|
||||
URL url = new URL(urlString + "/" + deposition_id + "/actions/newversion");
|
||||
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
|
||||
|
||||
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
|
||||
conn.setDoOutput(true);
|
||||
conn.setRequestMethod("POST");
|
||||
|
||||
try (OutputStream os = conn.getOutputStream()) {
|
||||
byte[] input = json.getBytes("utf-8");
|
||||
os.write(input, 0, input.length);
|
||||
|
||||
}
|
||||
|
||||
String body = getBody(conn);
|
||||
|
||||
int responseCode = conn.getResponseCode();
|
||||
|
||||
conn.disconnect();
|
||||
if (!checkOKStatus(responseCode))
|
||||
throw new IOException("Unexpected code " + responseCode + body);
|
||||
|
||||
ZenodoModel zenodoModel = new Gson().fromJson(body, ZenodoModel.class);
|
||||
String latest_draft = zenodoModel.getLinks().getLatest_draft();
|
||||
deposition_id = latest_draft.substring(latest_draft.lastIndexOf("/") + 1);
|
||||
bucket = getBucket(latest_draft);
|
||||
|
||||
return responseCode;
|
||||
|
||||
}
|
||||
|
||||
/**
|
||||
* To finish uploading a version or new deposition not published
|
||||
* It sets the deposition_id and the bucket to be used
|
||||
*
|
||||
*
|
||||
* @param deposition_id the deposition id of the not yet published upload
|
||||
* concept_rec_id = 656930
|
||||
* @return response code
|
||||
* @throws IOException
|
||||
* @throws MissingConceptDoiException
|
||||
*/
|
||||
public int uploadOpenDeposition(String deposition_id) throws IOException, MissingConceptDoiException {
|
||||
|
||||
this.deposition_id = deposition_id;
|
||||
|
||||
String json = "{}";
|
||||
|
||||
URL url = new URL(urlString + "/" + deposition_id);
|
||||
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
|
||||
|
||||
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
|
||||
conn.setRequestMethod("POST");
|
||||
conn.setDoOutput(true);
|
||||
try (OutputStream os = conn.getOutputStream()) {
|
||||
byte[] input = json.getBytes("utf-8");
|
||||
os.write(input, 0, input.length);
|
||||
}
|
||||
|
||||
String body = getBody(conn);
|
||||
|
||||
int responseCode = conn.getResponseCode();
|
||||
conn.disconnect();
|
||||
|
||||
if (!checkOKStatus(responseCode))
|
||||
throw new IOException("Unexpected code " + responseCode + body);
|
||||
|
||||
ZenodoModel zenodoModel = new Gson().fromJson(body, ZenodoModel.class);
|
||||
bucket = zenodoModel.getLinks().getBucket();
|
||||
|
||||
return responseCode;
|
||||
|
||||
}
|
||||
|
||||
private void setDepositionId(String concept_rec_id, Integer page) throws IOException, MissingConceptDoiException {
|
||||
|
||||
ZenodoModelList zenodoModelList = new Gson()
|
||||
.fromJson(getPrevDepositions(String.valueOf(page)), ZenodoModelList.class);
|
||||
|
||||
for (ZenodoModel zm : zenodoModelList) {
|
||||
if (zm.getConceptrecid().equals(concept_rec_id)) {
|
||||
deposition_id = zm.getId();
|
||||
return;
|
||||
}
|
||||
}
|
||||
if (zenodoModelList.size() == 0)
|
||||
throw new MissingConceptDoiException(
|
||||
"The concept record id specified was missing in the list of depositions");
|
||||
setDepositionId(concept_rec_id, page + 1);
|
||||
|
||||
}
|
||||
|
||||
private String getPrevDepositions(String page) throws IOException {
|
||||
|
||||
HttpUrl.Builder urlBuilder = HttpUrl.parse(urlString).newBuilder();
|
||||
urlBuilder.addQueryParameter("page", page);
|
||||
|
||||
URL url = new URL(urlBuilder.build().toString());
|
||||
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
|
||||
conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString());
|
||||
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
|
||||
conn.setDoOutput(true);
|
||||
conn.setRequestMethod("GET");
|
||||
|
||||
String body = getBody(conn);
|
||||
|
||||
int responseCode = conn.getResponseCode();
|
||||
|
||||
conn.disconnect();
|
||||
if (!checkOKStatus(responseCode))
|
||||
throw new IOException("Unexpected code " + responseCode + body);
|
||||
|
||||
return body;
|
||||
|
||||
}
|
||||
|
||||
private String getBucket(String inputUurl) throws IOException {
|
||||
|
||||
URL url = new URL(inputUurl);
|
||||
HttpURLConnection conn = (HttpURLConnection) url.openConnection();
|
||||
conn.setRequestProperty(HttpHeaders.CONTENT_TYPE, ContentType.APPLICATION_JSON.toString());
|
||||
conn.setRequestProperty(HttpHeaders.AUTHORIZATION, "Bearer " + access_token);
|
||||
conn.setDoOutput(true);
|
||||
conn.setRequestMethod("GET");
|
||||
|
||||
String body = getBody(conn);
|
||||
|
||||
int responseCode = conn.getResponseCode();
|
||||
|
||||
conn.disconnect();
|
||||
if (!checkOKStatus(responseCode))
|
||||
throw new IOException("Unexpected code " + responseCode + body);
|
||||
|
||||
ZenodoModel zenodoModel = new Gson().fromJson(body, ZenodoModel.class);
|
||||
|
||||
return zenodoModel.getLinks().getBucket();
|
||||
|
||||
}
|
||||
|
||||
}
|
|
@ -0,0 +1,14 @@
|
|||
|
||||
package eu.dnetlib.dhp.common.api.zenodo;
|
||||
|
||||
public class Community {
|
||||
private String identifier;
|
||||
|
||||
public String getIdentifier() {
|
||||
return identifier;
|
||||
}
|
||||
|
||||
public void setIdentifier(String identifier) {
|
||||
this.identifier = identifier;
|
||||
}
|
||||
}
|
|
@ -0,0 +1,47 @@
|
|||
|
||||
package eu.dnetlib.dhp.common.api.zenodo;
|
||||
|
||||
public class Creator {
|
||||
private String affiliation;
|
||||
private String name;
|
||||
private String orcid;
|
||||
|
||||
public String getAffiliation() {
|
||||
return affiliation;
|
||||
}
|
||||
|
||||
public void setAffiliation(String affiliation) {
|
||||
this.affiliation = affiliation;
|
||||
}
|
||||
|
||||
public String getName() {
|
||||
return name;
|
||||
}
|
||||
|
||||
public void setName(String name) {
|
||||
this.name = name;
|
||||
}
|
||||
|
||||
public String getOrcid() {
|
||||
return orcid;
|
||||
}
|
||||
|
||||
public void setOrcid(String orcid) {
|
||||
this.orcid = orcid;
|
||||
}
|
||||
|
||||
public static Creator newInstance(String name, String affiliation, String orcid) {
|
||||
Creator c = new Creator();
|
||||
if (name != null) {
|
||||
c.name = name;
|
||||
}
|
||||
if (affiliation != null) {
|
||||
c.affiliation = affiliation;
|
||||
}
|
||||
if (orcid != null) {
|
||||
c.orcid = orcid;
|
||||
}
|
||||
|
||||
return c;
|
||||
}
|
||||
}
|
|
@ -0,0 +1,44 @@
|
|||
|
||||
package eu.dnetlib.dhp.common.api.zenodo;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
public class File implements Serializable {
|
||||
private String checksum;
|
||||
private String filename;
|
||||
private long filesize;
|
||||
private String id;
|
||||
|
||||
public String getChecksum() {
|
||||
return checksum;
|
||||
}
|
||||
|
||||
public void setChecksum(String checksum) {
|
||||
this.checksum = checksum;
|
||||
}
|
||||
|
||||
public String getFilename() {
|
||||
return filename;
|
||||
}
|
||||
|
||||
public void setFilename(String filename) {
|
||||
this.filename = filename;
|
||||
}
|
||||
|
||||
public long getFilesize() {
|
||||
return filesize;
|
||||
}
|
||||
|
||||
public void setFilesize(long filesize) {
|
||||
this.filesize = filesize;
|
||||
}
|
||||
|
||||
public String getId() {
|
||||
return id;
|
||||
}
|
||||
|
||||
public void setId(String id) {
|
||||
this.id = id;
|
||||
}
|
||||
|
||||
}
|
|
@ -0,0 +1,23 @@
|
|||
|
||||
package eu.dnetlib.dhp.common.api.zenodo;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
public class Grant implements Serializable {
|
||||
private String id;
|
||||
|
||||
public String getId() {
|
||||
return id;
|
||||
}
|
||||
|
||||
public void setId(String id) {
|
||||
this.id = id;
|
||||
}
|
||||
|
||||
public static Grant newInstance(String id) {
|
||||
Grant g = new Grant();
|
||||
g.id = id;
|
||||
|
||||
return g;
|
||||
}
|
||||
}
|
|
@ -0,0 +1,92 @@
|
|||
|
||||
package eu.dnetlib.dhp.common.api.zenodo;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
public class Links implements Serializable {
|
||||
|
||||
private String bucket;
|
||||
|
||||
private String discard;
|
||||
|
||||
private String edit;
|
||||
private String files;
|
||||
private String html;
|
||||
private String latest_draft;
|
||||
private String latest_draft_html;
|
||||
private String publish;
|
||||
|
||||
private String self;
|
||||
|
||||
public String getBucket() {
|
||||
return bucket;
|
||||
}
|
||||
|
||||
public void setBucket(String bucket) {
|
||||
this.bucket = bucket;
|
||||
}
|
||||
|
||||
public String getDiscard() {
|
||||
return discard;
|
||||
}
|
||||
|
||||
public void setDiscard(String discard) {
|
||||
this.discard = discard;
|
||||
}
|
||||
|
||||
public String getEdit() {
|
||||
return edit;
|
||||
}
|
||||
|
||||
public void setEdit(String edit) {
|
||||
this.edit = edit;
|
||||
}
|
||||
|
||||
public String getFiles() {
|
||||
return files;
|
||||
}
|
||||
|
||||
public void setFiles(String files) {
|
||||
this.files = files;
|
||||
}
|
||||
|
||||
public String getHtml() {
|
||||
return html;
|
||||
}
|
||||
|
||||
public void setHtml(String html) {
|
||||
this.html = html;
|
||||
}
|
||||
|
||||
public String getLatest_draft() {
|
||||
return latest_draft;
|
||||
}
|
||||
|
||||
public void setLatest_draft(String latest_draft) {
|
||||
this.latest_draft = latest_draft;
|
||||
}
|
||||
|
||||
public String getLatest_draft_html() {
|
||||
return latest_draft_html;
|
||||
}
|
||||
|
||||
public void setLatest_draft_html(String latest_draft_html) {
|
||||
this.latest_draft_html = latest_draft_html;
|
||||
}
|
||||
|
||||
public String getPublish() {
|
||||
return publish;
|
||||
}
|
||||
|
||||
public void setPublish(String publish) {
|
||||
this.publish = publish;
|
||||
}
|
||||
|
||||
public String getSelf() {
|
||||
return self;
|
||||
}
|
||||
|
||||
public void setSelf(String self) {
|
||||
this.self = self;
|
||||
}
|
||||
}
|
|
@ -0,0 +1,153 @@
|
|||
|
||||
package eu.dnetlib.dhp.common.api.zenodo;
|
||||
|
||||
import java.io.Serializable;
|
||||
import java.util.List;
|
||||
|
||||
public class Metadata implements Serializable {
|
||||
|
||||
private String access_right;
|
||||
private List<Community> communities;
|
||||
private List<Creator> creators;
|
||||
private String description;
|
||||
private String doi;
|
||||
private List<Grant> grants;
|
||||
private List<String> keywords;
|
||||
private String language;
|
||||
private String license;
|
||||
private PrereserveDoi prereserve_doi;
|
||||
private String publication_date;
|
||||
private List<String> references;
|
||||
private List<RelatedIdentifier> related_identifiers;
|
||||
private String title;
|
||||
private String upload_type;
|
||||
private String version;
|
||||
|
||||
public String getUpload_type() {
|
||||
return upload_type;
|
||||
}
|
||||
|
||||
public void setUpload_type(String upload_type) {
|
||||
this.upload_type = upload_type;
|
||||
}
|
||||
|
||||
public String getVersion() {
|
||||
return version;
|
||||
}
|
||||
|
||||
public void setVersion(String version) {
|
||||
this.version = version;
|
||||
}
|
||||
|
||||
public String getAccess_right() {
|
||||
return access_right;
|
||||
}
|
||||
|
||||
public void setAccess_right(String access_right) {
|
||||
this.access_right = access_right;
|
||||
}
|
||||
|
||||
public List<Community> getCommunities() {
|
||||
return communities;
|
||||
}
|
||||
|
||||
public void setCommunities(List<Community> communities) {
|
||||
this.communities = communities;
|
||||
}
|
||||
|
||||
public List<Creator> getCreators() {
|
||||
return creators;
|
||||
}
|
||||
|
||||
public void setCreators(List<Creator> creators) {
|
||||
this.creators = creators;
|
||||
}
|
||||
|
||||
public String getDescription() {
|
||||
return description;
|
||||
}
|
||||
|
||||
public void setDescription(String description) {
|
||||
this.description = description;
|
||||
}
|
||||
|
||||
public String getDoi() {
|
||||
return doi;
|
||||
}
|
||||
|
||||
public void setDoi(String doi) {
|
||||
this.doi = doi;
|
||||
}
|
||||
|
||||
public List<Grant> getGrants() {
|
||||
return grants;
|
||||
}
|
||||
|
||||
public void setGrants(List<Grant> grants) {
|
||||
this.grants = grants;
|
||||
}
|
||||
|
||||
public List<String> getKeywords() {
|
||||
return keywords;
|
||||
}
|
||||
|
||||
public void setKeywords(List<String> keywords) {
|
||||
this.keywords = keywords;
|
||||
}
|
||||
|
||||
public String getLanguage() {
|
||||
return language;
|
||||
}
|
||||
|
||||
public void setLanguage(String language) {
|
||||
this.language = language;
|
||||
}
|
||||
|
||||
public String getLicense() {
|
||||
return license;
|
||||
}
|
||||
|
||||
public void setLicense(String license) {
|
||||
this.license = license;
|
||||
}
|
||||
|
||||
public PrereserveDoi getPrereserve_doi() {
|
||||
return prereserve_doi;
|
||||
}
|
||||
|
||||
public void setPrereserve_doi(PrereserveDoi prereserve_doi) {
|
||||
this.prereserve_doi = prereserve_doi;
|
||||
}
|
||||
|
||||
public String getPublication_date() {
|
||||
return publication_date;
|
||||
}
|
||||
|
||||
public void setPublication_date(String publication_date) {
|
||||
this.publication_date = publication_date;
|
||||
}
|
||||
|
||||
public List<String> getReferences() {
|
||||
return references;
|
||||
}
|
||||
|
||||
public void setReferences(List<String> references) {
|
||||
this.references = references;
|
||||
}
|
||||
|
||||
public List<RelatedIdentifier> getRelated_identifiers() {
|
||||
return related_identifiers;
|
||||
}
|
||||
|
||||
public void setRelated_identifiers(List<RelatedIdentifier> related_identifiers) {
|
||||
this.related_identifiers = related_identifiers;
|
||||
}
|
||||
|
||||
public String getTitle() {
|
||||
return title;
|
||||
}
|
||||
|
||||
public void setTitle(String title) {
|
||||
this.title = title;
|
||||
}
|
||||
}
|
|
@ -0,0 +1,25 @@
|
|||
|
||||
package eu.dnetlib.dhp.common.api.zenodo;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
public class PrereserveDoi implements Serializable {
|
||||
private String doi;
|
||||
private String recid;
|
||||
|
||||
public String getDoi() {
|
||||
return doi;
|
||||
}
|
||||
|
||||
public void setDoi(String doi) {
|
||||
this.doi = doi;
|
||||
}
|
||||
|
||||
public String getRecid() {
|
||||
return recid;
|
||||
}
|
||||
|
||||
public void setRecid(String recid) {
|
||||
this.recid = recid;
|
||||
}
|
||||
}
|
|
@ -0,0 +1,43 @@
|
|||
|
||||
package eu.dnetlib.dhp.common.api.zenodo;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
public class RelatedIdentifier implements Serializable {
|
||||
private String identifier;
|
||||
private String relation;
|
||||
private String resource_type;
|
||||
private String scheme;
|
||||
|
||||
public String getIdentifier() {
|
||||
return identifier;
|
||||
}
|
||||
|
||||
public void setIdentifier(String identifier) {
|
||||
this.identifier = identifier;
|
||||
}
|
||||
|
||||
public String getRelation() {
|
||||
return relation;
|
||||
}
|
||||
|
||||
public void setRelation(String relation) {
|
||||
this.relation = relation;
|
||||
}
|
||||
|
||||
public String getResource_type() {
|
||||
return resource_type;
|
||||
}
|
||||
|
||||
public void setResource_type(String resource_type) {
|
||||
this.resource_type = resource_type;
|
||||
}
|
||||
|
||||
public String getScheme() {
|
||||
return scheme;
|
||||
}
|
||||
|
||||
public void setScheme(String scheme) {
|
||||
this.scheme = scheme;
|
||||
}
|
||||
}
|
|
@ -0,0 +1,118 @@
|
|||
|
||||
package eu.dnetlib.dhp.common.api.zenodo;
|
||||
|
||||
import java.io.Serializable;
|
||||
import java.util.List;
|
||||
|
||||
public class ZenodoModel implements Serializable {
|
||||
|
||||
private String conceptrecid;
|
||||
private String created;
|
||||
|
||||
private List<File> files;
|
||||
private String id;
|
||||
private Links links;
|
||||
private Metadata metadata;
|
||||
private String modified;
|
||||
private String owner;
|
||||
private String record_id;
|
||||
private String state;
|
||||
private boolean submitted;
|
||||
private String title;
|
||||
|
||||
public String getConceptrecid() {
|
||||
return conceptrecid;
|
||||
}
|
||||
|
||||
public void setConceptrecid(String conceptrecid) {
|
||||
this.conceptrecid = conceptrecid;
|
||||
}
|
||||
|
||||
public String getCreated() {
|
||||
return created;
|
||||
}
|
||||
|
||||
public void setCreated(String created) {
|
||||
this.created = created;
|
||||
}
|
||||
|
||||
public List<File> getFiles() {
|
||||
return files;
|
||||
}
|
||||
|
||||
public void setFiles(List<File> files) {
|
||||
this.files = files;
|
||||
}
|
||||
|
||||
public String getId() {
|
||||
return id;
|
||||
}
|
||||
|
||||
public void setId(String id) {
|
||||
this.id = id;
|
||||
}
|
||||
|
||||
public Links getLinks() {
|
||||
return links;
|
||||
}
|
||||
|
||||
public void setLinks(Links links) {
|
||||
this.links = links;
|
||||
}
|
||||
|
||||
public Metadata getMetadata() {
|
||||
return metadata;
|
||||
}
|
||||
|
||||
public void setMetadata(Metadata metadata) {
|
||||
this.metadata = metadata;
|
||||
}
|
||||
|
||||
public String getModified() {
|
||||
return modified;
|
||||
}
|
||||
|
||||
public void setModified(String modified) {
|
||||
this.modified = modified;
|
||||
}
|
||||
|
||||
public String getOwner() {
|
||||
return owner;
|
||||
}
|
||||
|
||||
public void setOwner(String owner) {
|
||||
this.owner = owner;
|
||||
}
|
||||
|
||||
public String getRecord_id() {
|
||||
return record_id;
|
||||
}
|
||||
|
||||
public void setRecord_id(String record_id) {
|
||||
this.record_id = record_id;
|
||||
}
|
||||
|
||||
public String getState() {
|
||||
return state;
|
||||
}
|
||||
|
||||
public void setState(String state) {
|
||||
this.state = state;
|
||||
}
|
||||
|
||||
public boolean isSubmitted() {
|
||||
return submitted;
|
||||
}
|
||||
|
||||
public void setSubmitted(boolean submitted) {
|
||||
this.submitted = submitted;
|
||||
}
|
||||
|
||||
public String getTitle() {
|
||||
return title;
|
||||
}
|
||||
|
||||
public void setTitle(String title) {
|
||||
this.title = title;
|
||||
}
|
||||
}
|
|
@ -0,0 +1,7 @@
|
|||
|
||||
package eu.dnetlib.dhp.common.api.zenodo;
|
||||
|
||||
import java.util.ArrayList;
|
||||
|
||||
public class ZenodoModelList extends ArrayList<ZenodoModel> {
|
||||
}
|
|
@ -145,105 +145,6 @@ public class AuthorMerger {
|
|||
return null;
|
||||
}
|
||||
|
||||
/**
|
||||
* This method tries to figure out when two author are the same in the contest
|
||||
* of ORCID enrichment
|
||||
*
|
||||
* @param left Author in the OAF entity
|
||||
* @param right Author ORCID
|
||||
* @return based on a heuristic on the names of the authors if they are the same.
|
||||
*/
|
||||
public static boolean checkORCIDSimilarity(final Author left, final Author right) {
|
||||
final Person pl = parse(left);
|
||||
final Person pr = parse(right);
|
||||
|
||||
// If one of them didn't have a surname we verify if they have the fullName not empty
|
||||
// and verify if the normalized version is equal
|
||||
if (!(pl.getSurname() != null && pl.getSurname().stream().anyMatch(StringUtils::isNotBlank) &&
|
||||
pr.getSurname() != null && pr.getSurname().stream().anyMatch(StringUtils::isNotBlank))) {
|
||||
|
||||
if (pl.getFullname() != null && !pl.getFullname().isEmpty() && pr.getFullname() != null
|
||||
&& !pr.getFullname().isEmpty()) {
|
||||
return pl
|
||||
.getFullname()
|
||||
.stream()
|
||||
.anyMatch(
|
||||
fl -> pr.getFullname().stream().anyMatch(fr -> normalize(fl).equalsIgnoreCase(normalize(fr))));
|
||||
} else {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
// The Authors have one surname in common
|
||||
if (pl.getSurname().stream().anyMatch(sl -> pr.getSurname().stream().anyMatch(sr -> sr.equalsIgnoreCase(sl)))) {
|
||||
|
||||
// If one of them has only a surname and is the same we can say that they are the same author
|
||||
if ((pl.getName() == null || pl.getName().stream().allMatch(StringUtils::isBlank)) ||
|
||||
(pr.getName() == null || pr.getName().stream().allMatch(StringUtils::isBlank)))
|
||||
return true;
|
||||
// The authors have the same initials of Name in common
|
||||
if (pl
|
||||
.getName()
|
||||
.stream()
|
||||
.anyMatch(
|
||||
nl -> pr
|
||||
.getName()
|
||||
.stream()
|
||||
.anyMatch(nr -> nr.equalsIgnoreCase(nl))))
|
||||
return true;
|
||||
}
|
||||
|
||||
// Sometimes we noticed that publication have author wrote in inverse order Surname, Name
|
||||
// We verify if we have an exact match between name and surname
|
||||
if (pl.getSurname().stream().anyMatch(sl -> pr.getName().stream().anyMatch(nr -> nr.equalsIgnoreCase(sl))) &&
|
||||
pl.getName().stream().anyMatch(nl -> pr.getSurname().stream().anyMatch(sr -> sr.equalsIgnoreCase(nl))))
|
||||
return true;
|
||||
else
|
||||
return false;
|
||||
}
|
||||
//
|
||||
|
||||
/**
|
||||
* Method to enrich ORCID information in one list of authors based on another list
|
||||
*
|
||||
* @param baseAuthor the Author List in the OAF Entity
|
||||
* @param orcidAuthor The list of ORCID Author intersected
|
||||
* @return The Author List of the OAF Entity enriched with the orcid Author
|
||||
*/
|
||||
public static List<Author> enrichOrcid(List<Author> baseAuthor, List<Author> orcidAuthor) {
|
||||
|
||||
if (baseAuthor == null || baseAuthor.isEmpty())
|
||||
return orcidAuthor;
|
||||
|
||||
if (orcidAuthor == null || orcidAuthor.isEmpty())
|
||||
return baseAuthor;
|
||||
|
||||
if (baseAuthor.size() == 1 && orcidAuthor.size() > 10)
|
||||
return baseAuthor;
|
||||
|
||||
final List<Author> oAuthor = new ArrayList<>();
|
||||
oAuthor.addAll(orcidAuthor);
|
||||
|
||||
baseAuthor.forEach(ba -> {
|
||||
Optional<Author> aMatch = oAuthor.stream().filter(oa -> checkORCIDSimilarity(ba, oa)).findFirst();
|
||||
if (aMatch.isPresent()) {
|
||||
final Author sameAuthor = aMatch.get();
|
||||
addPid(ba, sameAuthor.getPid());
|
||||
oAuthor.remove(sameAuthor);
|
||||
}
|
||||
});
|
||||
return baseAuthor;
|
||||
}
|
||||
|
||||
private static void addPid(final Author a, final List<StructuredProperty> pids) {
|
||||
|
||||
if (a.getPid() == null) {
|
||||
a.setPid(new ArrayList<>());
|
||||
}
|
||||
|
||||
a.getPid().addAll(pids);
|
||||
|
||||
}
|
||||
|
||||
public static String pidToComparableString(StructuredProperty pid) {
|
||||
final String classid = pid.getQualifier().getClassid() != null ? pid.getQualifier().getClassid().toLowerCase()
|
||||
: "";
|
||||
|
|
|
@ -1,24 +1,6 @@
|
|||
|
||||
package eu.dnetlib.dhp.oa.merge;
|
||||
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
import static org.apache.spark.sql.functions.col;
|
||||
import static org.apache.spark.sql.functions.when;
|
||||
|
||||
import java.util.Map;
|
||||
import java.util.Optional;
|
||||
import java.util.concurrent.ExecutionException;
|
||||
import java.util.concurrent.ForkJoinPool;
|
||||
import java.util.stream.Collectors;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.function.MapFunction;
|
||||
import org.apache.spark.api.java.function.ReduceFunction;
|
||||
import org.apache.spark.sql.*;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.common.HdfsSupport;
|
||||
import eu.dnetlib.dhp.common.vocabulary.VocabularyGroup;
|
||||
|
@ -26,169 +8,186 @@ import eu.dnetlib.dhp.schema.common.EntityType;
|
|||
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.GraphCleaningFunctions;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.OafMapperUtils;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
|
||||
import eu.dnetlib.dhp.utils.ISLookupClientFactory;
|
||||
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
|
||||
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpService;
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.function.MapFunction;
|
||||
import org.apache.spark.api.java.function.ReduceFunction;
|
||||
import org.apache.spark.sql.*;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
import scala.Tuple2;
|
||||
|
||||
import java.util.Map;
|
||||
import java.util.Optional;
|
||||
import java.util.concurrent.ExecutionException;
|
||||
import java.util.concurrent.ForkJoinPool;
|
||||
import java.util.stream.Collectors;
|
||||
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
import static org.apache.spark.sql.functions.col;
|
||||
import static org.apache.spark.sql.functions.when;
|
||||
|
||||
/**
|
||||
* Groups the graph content by entity identifier to ensure ID uniqueness
|
||||
*/
|
||||
public class GroupEntitiesSparkJob {
|
||||
private static final Logger log = LoggerFactory.getLogger(GroupEntitiesSparkJob.class);
|
||||
private static final Logger log = LoggerFactory.getLogger(GroupEntitiesSparkJob.class);
|
||||
|
||||
private static final Encoder<OafEntity> OAFENTITY_KRYO_ENC = Encoders.kryo(OafEntity.class);
|
||||
private static final Encoder<OafEntity> OAFENTITY_KRYO_ENC = Encoders.kryo(OafEntity.class);
|
||||
|
||||
private ArgumentApplicationParser parser;
|
||||
private ArgumentApplicationParser parser;
|
||||
|
||||
public GroupEntitiesSparkJob(ArgumentApplicationParser parser) {
|
||||
this.parser = parser;
|
||||
}
|
||||
public GroupEntitiesSparkJob(ArgumentApplicationParser parser) {
|
||||
this.parser = parser;
|
||||
}
|
||||
|
||||
public static void main(String[] args) throws Exception {
|
||||
public static void main(String[] args) throws Exception {
|
||||
|
||||
String jsonConfiguration = IOUtils
|
||||
.toString(
|
||||
GroupEntitiesSparkJob.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/oa/merge/group_graph_entities_parameters.json"));
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
|
||||
parser.parseArgument(args);
|
||||
String jsonConfiguration = IOUtils
|
||||
.toString(
|
||||
GroupEntitiesSparkJob.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/oa/merge/group_graph_entities_parameters.json"));
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
|
||||
parser.parseArgument(args);
|
||||
|
||||
Boolean isSparkSessionManaged = Optional
|
||||
.ofNullable(parser.get("isSparkSessionManaged"))
|
||||
.map(Boolean::valueOf)
|
||||
.orElse(Boolean.TRUE);
|
||||
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||
Boolean isSparkSessionManaged = Optional
|
||||
.ofNullable(parser.get("isSparkSessionManaged"))
|
||||
.map(Boolean::valueOf)
|
||||
.orElse(Boolean.TRUE);
|
||||
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||
|
||||
final String isLookupUrl = parser.get("isLookupUrl");
|
||||
log.info("isLookupUrl: {}", isLookupUrl);
|
||||
final String isLookupUrl = parser.get("isLookupUrl");
|
||||
log.info("isLookupUrl: {}", isLookupUrl);
|
||||
|
||||
final ISLookUpService isLookupService = ISLookupClientFactory.getLookUpService(isLookupUrl);
|
||||
final ISLookUpService isLookupService = ISLookupClientFactory.getLookUpService(isLookupUrl);
|
||||
|
||||
new GroupEntitiesSparkJob(parser).run(isSparkSessionManaged, isLookupService);
|
||||
}
|
||||
new GroupEntitiesSparkJob(parser).run(isSparkSessionManaged, isLookupService);
|
||||
}
|
||||
|
||||
public void run(Boolean isSparkSessionManaged, ISLookUpService isLookUpService)
|
||||
throws ISLookUpException {
|
||||
public void run(Boolean isSparkSessionManaged, ISLookUpService isLookUpService)
|
||||
throws ISLookUpException {
|
||||
|
||||
String graphInputPath = parser.get("graphInputPath");
|
||||
log.info("graphInputPath: {}", graphInputPath);
|
||||
String graphInputPath = parser.get("graphInputPath");
|
||||
log.info("graphInputPath: {}", graphInputPath);
|
||||
|
||||
String checkpointPath = parser.get("checkpointPath");
|
||||
log.info("checkpointPath: {}", checkpointPath);
|
||||
String checkpointPath = parser.get("checkpointPath");
|
||||
log.info("checkpointPath: {}", checkpointPath);
|
||||
|
||||
String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath: {}", outputPath);
|
||||
String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath: {}", outputPath);
|
||||
|
||||
boolean filterInvisible = Boolean.parseBoolean(parser.get("filterInvisible"));
|
||||
log.info("filterInvisible: {}", filterInvisible);
|
||||
boolean filterInvisible = Boolean.parseBoolean(parser.get("filterInvisible"));
|
||||
log.info("filterInvisible: {}", filterInvisible);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
conf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer");
|
||||
conf.registerKryoClasses(ModelSupport.getOafModelClasses());
|
||||
SparkConf conf = new SparkConf();
|
||||
conf.set("spark.serializer", "org.apache.spark.serializer.KryoSerializer");
|
||||
conf.registerKryoClasses(ModelSupport.getOafModelClasses());
|
||||
|
||||
final VocabularyGroup vocs = VocabularyGroup.loadVocsFromIS(isLookUpService);
|
||||
final VocabularyGroup vocs = VocabularyGroup.loadVocsFromIS(isLookUpService);
|
||||
|
||||
runWithSparkSession(
|
||||
conf,
|
||||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
HdfsSupport.remove(checkpointPath, spark.sparkContext().hadoopConfiguration());
|
||||
groupEntities(spark, graphInputPath, checkpointPath, outputPath, filterInvisible, vocs);
|
||||
});
|
||||
}
|
||||
runWithSparkSession(
|
||||
conf,
|
||||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
HdfsSupport.remove(checkpointPath, spark.sparkContext().hadoopConfiguration());
|
||||
groupEntities(spark, graphInputPath, checkpointPath, outputPath, filterInvisible, vocs);
|
||||
});
|
||||
}
|
||||
|
||||
private static void groupEntities(
|
||||
SparkSession spark,
|
||||
String inputPath,
|
||||
String checkpointPath,
|
||||
String outputPath,
|
||||
boolean filterInvisible, VocabularyGroup vocs) {
|
||||
private static void groupEntities(
|
||||
SparkSession spark,
|
||||
String inputPath,
|
||||
String checkpointPath,
|
||||
String outputPath,
|
||||
boolean filterInvisible, VocabularyGroup vocs) {
|
||||
|
||||
Dataset<OafEntity> allEntities = spark.emptyDataset(OAFENTITY_KRYO_ENC);
|
||||
Dataset<OafEntity> allEntities = spark.emptyDataset(OAFENTITY_KRYO_ENC);
|
||||
|
||||
for (Map.Entry<EntityType, Class> e : ModelSupport.entityTypes.entrySet()) {
|
||||
String entity = e.getKey().name();
|
||||
Class<? extends OafEntity> entityClass = e.getValue();
|
||||
String entityInputPath = inputPath + "/" + entity;
|
||||
for (Map.Entry<EntityType, Class> e : ModelSupport.entityTypes.entrySet()) {
|
||||
String entity = e.getKey().name();
|
||||
Class<? extends OafEntity> entityClass = e.getValue();
|
||||
String entityInputPath = inputPath + "/" + entity;
|
||||
|
||||
if (!HdfsSupport.exists(entityInputPath, spark.sparkContext().hadoopConfiguration())) {
|
||||
continue;
|
||||
}
|
||||
if (!HdfsSupport.exists(entityInputPath, spark.sparkContext().hadoopConfiguration())) {
|
||||
continue;
|
||||
}
|
||||
|
||||
allEntities = allEntities
|
||||
.union(
|
||||
((Dataset<OafEntity>) spark
|
||||
.read()
|
||||
.schema(Encoders.bean(entityClass).schema())
|
||||
.json(entityInputPath)
|
||||
.filter("length(id) > 0")
|
||||
.as(Encoders.bean(entityClass)))
|
||||
.map((MapFunction<OafEntity, OafEntity>) r -> r, OAFENTITY_KRYO_ENC));
|
||||
}
|
||||
allEntities = allEntities
|
||||
.union(
|
||||
((Dataset<OafEntity>) spark
|
||||
.read()
|
||||
.schema(Encoders.bean(entityClass).schema())
|
||||
.json(entityInputPath)
|
||||
.filter("length(id) > 0")
|
||||
.as(Encoders.bean(entityClass)))
|
||||
.map((MapFunction<OafEntity, OafEntity>) r -> r, OAFENTITY_KRYO_ENC));
|
||||
}
|
||||
|
||||
Dataset<?> groupedEntities = allEntities
|
||||
.map(
|
||||
(MapFunction<OafEntity, OafEntity>) entity -> GraphCleaningFunctions
|
||||
.applyCoarVocabularies(entity, vocs),
|
||||
OAFENTITY_KRYO_ENC)
|
||||
.groupByKey((MapFunction<OafEntity, String>) OafEntity::getId, Encoders.STRING())
|
||||
.reduceGroups((ReduceFunction<OafEntity>) OafMapperUtils::mergeEntities)
|
||||
.map(
|
||||
(MapFunction<Tuple2<String, OafEntity>, Tuple2<String, OafEntity>>) t -> new Tuple2<>(
|
||||
t._2().getClass().getName(), t._2()),
|
||||
Encoders.tuple(Encoders.STRING(), OAFENTITY_KRYO_ENC));
|
||||
Dataset<?> groupedEntities = allEntities
|
||||
.map(
|
||||
(MapFunction<OafEntity, OafEntity>) entity -> GraphCleaningFunctions
|
||||
.applyCoarVocabularies(entity, vocs),
|
||||
OAFENTITY_KRYO_ENC)
|
||||
.groupByKey((MapFunction<OafEntity, String>) OafEntity::getId, Encoders.STRING())
|
||||
.reduceGroups((ReduceFunction<OafEntity>) MergeUtils::checkedMerge)
|
||||
.map(
|
||||
(MapFunction<Tuple2<String, OafEntity>, Tuple2<String, OafEntity>>) t -> new Tuple2<>(
|
||||
t._2().getClass().getName(), t._2()),
|
||||
Encoders.tuple(Encoders.STRING(), OAFENTITY_KRYO_ENC));
|
||||
|
||||
// pivot on "_1" (classname of the entity)
|
||||
// created columns containing only entities of the same class
|
||||
for (Map.Entry<EntityType, Class> e : ModelSupport.entityTypes.entrySet()) {
|
||||
String entity = e.getKey().name();
|
||||
Class<? extends OafEntity> entityClass = e.getValue();
|
||||
// pivot on "_1" (classname of the entity)
|
||||
// created columns containing only entities of the same class
|
||||
for (Map.Entry<EntityType, Class> e : ModelSupport.entityTypes.entrySet()) {
|
||||
String entity = e.getKey().name();
|
||||
Class<? extends OafEntity> entityClass = e.getValue();
|
||||
|
||||
groupedEntities = groupedEntities
|
||||
.withColumn(
|
||||
entity,
|
||||
when(col("_1").equalTo(entityClass.getName()), col("_2")));
|
||||
}
|
||||
groupedEntities = groupedEntities
|
||||
.withColumn(
|
||||
entity,
|
||||
when(col("_1").equalTo(entityClass.getName()), col("_2")));
|
||||
}
|
||||
|
||||
groupedEntities
|
||||
.drop("_1", "_2")
|
||||
.write()
|
||||
.mode(SaveMode.Overwrite)
|
||||
.option("compression", "gzip")
|
||||
.save(checkpointPath);
|
||||
groupedEntities
|
||||
.drop("_1", "_2")
|
||||
.write()
|
||||
.mode(SaveMode.Overwrite)
|
||||
.option("compression", "gzip")
|
||||
.save(checkpointPath);
|
||||
|
||||
ForkJoinPool parPool = new ForkJoinPool(ModelSupport.entityTypes.size());
|
||||
ForkJoinPool parPool = new ForkJoinPool(ModelSupport.entityTypes.size());
|
||||
|
||||
ModelSupport.entityTypes
|
||||
.entrySet()
|
||||
.stream()
|
||||
.map(e -> parPool.submit(() -> {
|
||||
String entity = e.getKey().name();
|
||||
Class<? extends OafEntity> entityClass = e.getValue();
|
||||
ModelSupport.entityTypes
|
||||
.entrySet()
|
||||
.stream()
|
||||
.map(e -> parPool.submit(() -> {
|
||||
String entity = e.getKey().name();
|
||||
Class<? extends OafEntity> entityClass = e.getValue();
|
||||
|
||||
spark
|
||||
.read()
|
||||
.load(checkpointPath)
|
||||
.select(col(entity).as("value"))
|
||||
.filter("value IS NOT NULL")
|
||||
.as(OAFENTITY_KRYO_ENC)
|
||||
.map((MapFunction<OafEntity, OafEntity>) r -> r, (Encoder<OafEntity>) Encoders.bean(entityClass))
|
||||
.filter(filterInvisible ? "dataInfo.invisible != TRUE" : "TRUE")
|
||||
.write()
|
||||
.mode(SaveMode.Overwrite)
|
||||
.option("compression", "gzip")
|
||||
.json(outputPath + "/" + entity);
|
||||
}))
|
||||
.collect(Collectors.toList())
|
||||
.forEach(t -> {
|
||||
try {
|
||||
t.get();
|
||||
} catch (InterruptedException | ExecutionException e) {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
});
|
||||
}
|
||||
spark
|
||||
.read()
|
||||
.load(checkpointPath)
|
||||
.select(col(entity).as("value"))
|
||||
.filter("value IS NOT NULL")
|
||||
.as(OAFENTITY_KRYO_ENC)
|
||||
.map((MapFunction<OafEntity, OafEntity>) r -> r, (Encoder<OafEntity>) Encoders.bean(entityClass))
|
||||
.filter(filterInvisible ? "dataInfo.invisible != TRUE" : "TRUE")
|
||||
.write()
|
||||
.mode(SaveMode.Overwrite)
|
||||
.option("compression", "gzip")
|
||||
.json(outputPath + "/" + entity);
|
||||
}))
|
||||
.collect(Collectors.toList())
|
||||
.forEach(t -> {
|
||||
try {
|
||||
t.get();
|
||||
} catch (InterruptedException | ExecutionException e) {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
});
|
||||
}
|
||||
}
|
||||
|
|
|
@ -0,0 +1,79 @@
|
|||
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||
|
||||
//
|
||||
// Source code recreated from a .class file by IntelliJ IDEA
|
||||
// (powered by FernFlower decompiler)
|
||||
//
|
||||
|
||||
|
||||
import eu.dnetlib.dhp.schema.common.EntityType;
|
||||
import eu.dnetlib.dhp.schema.oaf.KeyValue;
|
||||
import eu.dnetlib.dhp.schema.oaf.Oaf;
|
||||
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
||||
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||
|
||||
import java.util.Comparator;
|
||||
import java.util.HashSet;
|
||||
import java.util.Optional;
|
||||
import java.util.stream.Collectors;
|
||||
|
||||
public class MergeComparator implements Comparator<Oaf> {
|
||||
public MergeComparator() {
|
||||
}
|
||||
|
||||
public int compare(Oaf left, Oaf right) {
|
||||
// nulls at the end
|
||||
if (left == null && right == null) {
|
||||
return 0;
|
||||
} else if (left == null) {
|
||||
return -1;
|
||||
} else if (right == null) {
|
||||
return 1;
|
||||
}
|
||||
|
||||
// invisible
|
||||
if (left.getDataInfo() != null && left.getDataInfo().getInvisible() == true) {
|
||||
if (right.getDataInfo() != null && right.getDataInfo().getInvisible() == false) {
|
||||
return -1;
|
||||
}
|
||||
}
|
||||
|
||||
// collectedfrom
|
||||
HashSet<String> lCf = getCollectedFromIds(left);
|
||||
HashSet<String> rCf = getCollectedFromIds(right);
|
||||
if (lCf.contains("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2") && !rCf.contains("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2")) {
|
||||
return -1;
|
||||
} else if (!lCf.contains("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2") && rCf.contains("10|openaire____::081b82f96300b6a6e3d282bad31cb6e2")) {
|
||||
return 1;
|
||||
}
|
||||
|
||||
|
||||
|
||||
SubEntityType lClass = SubEntityType.fromClass(left.getClass());
|
||||
SubEntityType rClass = SubEntityType.fromClass(right.getClass());
|
||||
return lClass.ordinal() - rClass.ordinal();
|
||||
|
||||
}
|
||||
|
||||
protected HashSet<String> getCollectedFromIds(Oaf left) {
|
||||
return (HashSet) Optional.ofNullable(left.getCollectedfrom()).map((cf) -> {
|
||||
return (HashSet) cf.stream().map(KeyValue::getKey).collect(Collectors.toCollection(HashSet::new));
|
||||
}).orElse(new HashSet());
|
||||
}
|
||||
|
||||
enum SubEntityType {
|
||||
publication, dataset, software, otherresearchproduct, datasource, organization, project;
|
||||
|
||||
/**
|
||||
* Resolves the EntityType, given the relative class name
|
||||
*
|
||||
* @param clazz the given class name
|
||||
* @param <T> actual OafEntity subclass
|
||||
* @return the EntityType associated to the given class
|
||||
*/
|
||||
public static <T extends Oaf> SubEntityType fromClass(Class<T> clazz) {
|
||||
return valueOf(clazz.getSimpleName().toLowerCase());
|
||||
}
|
||||
}
|
||||
|
||||
}
|
|
@ -0,0 +1,707 @@
|
|||
|
||||
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||
|
||||
import eu.dnetlib.dhp.schema.common.AccessRightComparator;
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||
import eu.dnetlib.dhp.schema.oaf.*;
|
||||
import org.apache.commons.lang3.StringUtils;
|
||||
import org.apache.commons.lang3.tuple.ImmutablePair;
|
||||
import org.apache.commons.lang3.tuple.Pair;
|
||||
|
||||
import java.text.ParseException;
|
||||
import java.util.*;
|
||||
import java.util.stream.Collectors;
|
||||
import java.util.stream.Stream;
|
||||
|
||||
import static com.google.common.base.Objects.firstNonNull;
|
||||
import static com.google.common.base.Preconditions.checkArgument;
|
||||
|
||||
public class MergeUtils {
|
||||
|
||||
public static <T extends Oaf> T checkedMerge(final T left, final T right) {
|
||||
return (T) merge(left, right, false);
|
||||
}
|
||||
|
||||
public static Oaf merge(final Oaf left, final Oaf right) {
|
||||
return merge(left, right, false);
|
||||
}
|
||||
|
||||
public static Oaf merge(final Oaf left, final Oaf right, boolean checkDelegatedAuthority) {
|
||||
if (sameClass(left, right, OafEntity.class)) {
|
||||
return mergeEntities(left, right, checkDelegatedAuthority);
|
||||
} else if (sameClass(left, right, Relation.class)) {
|
||||
return mergeRelation((Relation) left, (Relation) right);
|
||||
} else {
|
||||
throw new RuntimeException(
|
||||
String
|
||||
.format(
|
||||
"MERGE_FROM_AND_GET incompatible types: %s, %s",
|
||||
left.getClass().getCanonicalName(), right.getClass().getCanonicalName()));
|
||||
}
|
||||
}
|
||||
|
||||
private static <T extends Oaf> boolean sameClass(Object left, Object right, Class<T> cls) {
|
||||
return cls.isAssignableFrom(left.getClass()) && cls.isAssignableFrom(right.getClass());
|
||||
}
|
||||
|
||||
private static Oaf mergeEntities(Oaf left, Oaf right, boolean checkDelegatedAuthority) {
|
||||
|
||||
if (sameClass(left, right, Result.class)) {
|
||||
if (!left.getClass().equals(right.getClass()) || checkDelegatedAuthority) {
|
||||
return mergeResultsOfDifferentTypes((Result)left, (Result) right);
|
||||
}
|
||||
|
||||
if (sameClass(left, right, Publication.class)) {
|
||||
return mergePublication((Publication) left, (Publication) right);
|
||||
}
|
||||
if (sameClass(left, right, Dataset.class)) {
|
||||
return mergeDataset((Dataset) left, (Dataset) right);
|
||||
}
|
||||
if (sameClass(left, right, OtherResearchProduct.class)) {
|
||||
return mergeORP((OtherResearchProduct) left, (OtherResearchProduct) right);
|
||||
}
|
||||
if (sameClass(left, right, Software.class)) {
|
||||
return mergeSoftware((Software) left, (Software) right);
|
||||
}
|
||||
|
||||
return mergeResult((Result) left, (Result) right);
|
||||
} else if (sameClass(left, right, Datasource.class)) {
|
||||
// TODO
|
||||
final int trust = compareTrust(left, right);
|
||||
return mergeOafEntityFields((Datasource) left, (Datasource) right, trust);
|
||||
} else if (sameClass(left, right, Organization.class)) {
|
||||
return mergeOrganization((Organization) left, (Organization) right);
|
||||
} else if (sameClass(left, right, Project.class)) {
|
||||
return mergeProject((Project) left, (Project) right);
|
||||
} else {
|
||||
throw new RuntimeException(
|
||||
String
|
||||
.format(
|
||||
"MERGE_FROM_AND_GET incompatible types: %s, %s",
|
||||
left.getClass().getCanonicalName(), right.getClass().getCanonicalName()));
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* This method is used in the global result grouping phase. It checks if one of the two is from a delegated authority
|
||||
* https://graph.openaire.eu/docs/data-model/pids-and-identifiers#delegated-authorities and in that case it prefers
|
||||
* such version.
|
||||
* <p>
|
||||
* Otherwise, it considers a resulttype priority order implemented in {@link ResultTypeComparator}
|
||||
* and proceeds with the canonical property merging.
|
||||
*
|
||||
* @param left
|
||||
* @param right
|
||||
* @return
|
||||
*/
|
||||
private static <T extends Result> T mergeResultsOfDifferentTypes(T left, T right) {
|
||||
|
||||
final boolean leftFromDelegatedAuthority = isFromDelegatedAuthority(left);
|
||||
final boolean rightFromDelegatedAuthority = isFromDelegatedAuthority(right);
|
||||
|
||||
if (leftFromDelegatedAuthority && !rightFromDelegatedAuthority) {
|
||||
return left;
|
||||
}
|
||||
if (!leftFromDelegatedAuthority && rightFromDelegatedAuthority) {
|
||||
return right;
|
||||
}
|
||||
//TODO: raise trust to have preferred fields from one or the other??
|
||||
if (new ResultTypeComparator().compare(left, right) < 0) {
|
||||
return mergeResult(left, right);
|
||||
} else {
|
||||
return mergeResult(right, left);
|
||||
}
|
||||
}
|
||||
|
||||
private static DataInfo chooseDataInfo(DataInfo left, DataInfo right, int trust) {
|
||||
if (trust > 0) {
|
||||
return left;
|
||||
} else if (trust == 0) {
|
||||
if (left == null || (left.getInvisible() != null && left.getInvisible().equals(Boolean.TRUE))) {
|
||||
return right;
|
||||
} else {
|
||||
return left;
|
||||
}
|
||||
} else {
|
||||
return right;
|
||||
}
|
||||
}
|
||||
|
||||
private static String chooseString(String left, String right, int trust) {
|
||||
if (trust > 0) {
|
||||
return left;
|
||||
} else if (trust == 0) {
|
||||
return StringUtils.isNotBlank(left) ? left : right;
|
||||
} else {
|
||||
return right;
|
||||
}
|
||||
}
|
||||
|
||||
private static <T> T chooseReference(T left, T right, int trust) {
|
||||
if (trust > 0) {
|
||||
return left;
|
||||
} else if (trust == 0) {
|
||||
return left != null ? left : right;
|
||||
} else {
|
||||
return right;
|
||||
}
|
||||
}
|
||||
|
||||
private static Long max(Long left, Long right) {
|
||||
if (left == null)
|
||||
return right;
|
||||
if (right == null)
|
||||
return left;
|
||||
|
||||
return Math.max(left, right);
|
||||
}
|
||||
|
||||
// trust ??
|
||||
private static Boolean booleanOR(Boolean a, Boolean b) {
|
||||
if (a == null) {
|
||||
return b;
|
||||
} else if (b == null) {
|
||||
return a;
|
||||
}
|
||||
|
||||
return a || b;
|
||||
}
|
||||
|
||||
|
||||
private static <T> List<T> unionDistinctLists(final List<T> left, final List<T> right, int trust) {
|
||||
if (left == null) {
|
||||
return right;
|
||||
} else if (right == null) {
|
||||
return left;
|
||||
}
|
||||
|
||||
List<T> h = trust >= 0 ? left : right;
|
||||
List<T> l = trust >= 0 ? right : left;
|
||||
|
||||
return Stream.concat(h.stream(), l.stream())
|
||||
.filter(Objects::nonNull)
|
||||
.distinct()
|
||||
.collect(Collectors.toList());
|
||||
}
|
||||
|
||||
private static List<String> unionDistinctListOfString(final List<String> l, final List<String> r) {
|
||||
if (l == null) {
|
||||
return r;
|
||||
} else if (r == null) {
|
||||
return l;
|
||||
}
|
||||
|
||||
return Stream.concat(l.stream(), r.stream())
|
||||
.filter(StringUtils::isNotBlank)
|
||||
.distinct()
|
||||
.collect(Collectors.toList());
|
||||
}
|
||||
|
||||
//TODO review
|
||||
private static List<KeyValue> mergeKeyValue(List<KeyValue> left, List<KeyValue> right, int trust) {
|
||||
if (trust < 0) {
|
||||
List<KeyValue> s = left;
|
||||
left = right;
|
||||
right = s;
|
||||
}
|
||||
|
||||
HashMap<String, KeyValue> values = new HashMap<>();
|
||||
left.forEach(kv -> values.put(kv.getKey(), kv));
|
||||
right.forEach(kv -> values.putIfAbsent(kv.getKey(), kv));
|
||||
|
||||
return new ArrayList<>(values.values());
|
||||
}
|
||||
|
||||
private static List<StructuredProperty> unionTitle(List<StructuredProperty> left, List<StructuredProperty> right, int trust) {
|
||||
if (left == null) {
|
||||
return right;
|
||||
} else if (right == null) {
|
||||
return left;
|
||||
}
|
||||
|
||||
List<StructuredProperty> h = trust >= 0 ? left : right;
|
||||
List<StructuredProperty> l = trust >= 0 ? right : left;
|
||||
|
||||
return Stream.concat(h.stream(), l.stream())
|
||||
.filter(Objects::isNull)
|
||||
.distinct()
|
||||
.collect(Collectors.toList());
|
||||
}
|
||||
|
||||
/**
|
||||
* Internal utility that merges the common OafEntity fields
|
||||
*
|
||||
* @param merged
|
||||
* @param enrich
|
||||
* @param <T>
|
||||
* @return
|
||||
*/
|
||||
private static <T extends Oaf> T mergeOafFields(T merged, T enrich, int trust) {
|
||||
|
||||
//TODO: union of all values, but what does it mean with KeyValue pairs???
|
||||
merged.setCollectedfrom(mergeKeyValue(merged.getCollectedfrom(), enrich.getCollectedfrom(), trust));
|
||||
merged.setDataInfo(chooseDataInfo(merged.getDataInfo(), enrich.getDataInfo(), trust));
|
||||
merged.setLastupdatetimestamp(max(merged.getLastupdatetimestamp(), enrich.getLastupdatetimestamp()));
|
||||
|
||||
return merged;
|
||||
}
|
||||
|
||||
/**
|
||||
* Internal utility that merges the common OafEntity fields
|
||||
*
|
||||
* @param original
|
||||
* @param enrich
|
||||
* @param <T>
|
||||
* @return
|
||||
*/
|
||||
private static <T extends OafEntity> T mergeOafEntityFields(T original, T enrich, int trust) {
|
||||
final T merged = mergeOafFields(original, enrich, trust);
|
||||
|
||||
merged.setOriginalId(unionDistinctListOfString(merged.getOriginalId(), enrich.getOriginalId()));
|
||||
merged.setPid(unionDistinctLists(merged.getPid(), enrich.getPid(), trust));
|
||||
// dateofcollection mettere today quando si fa merge
|
||||
merged.setDateofcollection(chooseString(merged.getDateofcollection(), enrich.getDateofcollection(), trust));
|
||||
// setDateoftransformation mettere vuota in dedup, nota per Claudio
|
||||
merged.setDateoftransformation(chooseString(merged.getDateoftransformation(), enrich.getDateoftransformation(), trust));
|
||||
// TODO: was missing in OafEntity.merge
|
||||
merged.setExtraInfo(unionDistinctLists(merged.getExtraInfo(), enrich.getExtraInfo(), trust));
|
||||
//oaiprovenanze da mettere a null quando si genera merge
|
||||
merged.setOaiprovenance(chooseReference(merged.getOaiprovenance(), enrich.getOaiprovenance(), trust));
|
||||
merged.setMeasures(unionDistinctLists(merged.getMeasures(), enrich.getMeasures(), trust));
|
||||
|
||||
return merged;
|
||||
}
|
||||
|
||||
|
||||
public static <T extends Relation> T mergeRelation(T original, T enrich) {
|
||||
int trust = compareTrust(original, enrich);
|
||||
T merge = mergeOafFields(original, enrich, trust);
|
||||
|
||||
checkArgument(Objects.equals(merge.getSource(), enrich.getSource()), "source ids must be equal");
|
||||
checkArgument(Objects.equals(merge.getTarget(), enrich.getTarget()), "target ids must be equal");
|
||||
checkArgument(Objects.equals(merge.getRelType(), enrich.getRelType()), "relType(s) must be equal");
|
||||
checkArgument(
|
||||
Objects.equals(merge.getSubRelType(), enrich.getSubRelType()), "subRelType(s) must be equal");
|
||||
checkArgument(Objects.equals(merge.getRelClass(), enrich.getRelClass()), "relClass(es) must be equal");
|
||||
|
||||
//merge.setProvenance(mergeLists(merge.getProvenance(), enrich.getProvenance()));
|
||||
|
||||
//TODO: trust ??
|
||||
merge.setValidated(booleanOR(merge.getValidated(), enrich.getValidated()));
|
||||
try {
|
||||
merge.setValidationDate(ModelSupport.oldest(merge.getValidationDate(), enrich.getValidationDate()));
|
||||
} catch (ParseException e) {
|
||||
throw new IllegalArgumentException(String
|
||||
.format(
|
||||
"invalid validation date format in relation [s:%s, t:%s]: %s", merge.getSource(),
|
||||
merge.getTarget(),
|
||||
merge.getValidationDate()));
|
||||
}
|
||||
|
||||
// TODO keyvalue merge
|
||||
merge.setProperties(mergeKeyValue(merge.getProperties(), enrich.getProperties(), trust));
|
||||
|
||||
return merge;
|
||||
}
|
||||
|
||||
public static <T extends Result> T mergeResult(T original, T enrich) {
|
||||
final int trust = compareTrust(original, enrich);
|
||||
T merge = mergeOafEntityFields(original, enrich, trust);
|
||||
|
||||
if (merge.getProcessingchargeamount() == null || StringUtils.isBlank(merge.getProcessingchargeamount().getValue())) {
|
||||
merge.setProcessingchargeamount(enrich.getProcessingchargeamount());
|
||||
merge.setProcessingchargecurrency(enrich.getProcessingchargecurrency());
|
||||
}
|
||||
|
||||
// author = usare la stessa logica che in dedup
|
||||
merge.setAuthor(chooseReference(merge.getAuthor(), enrich.getAuthor(), trust));
|
||||
// il primo che mi arriva secondo l'ordinamento per priorita'
|
||||
merge.setResulttype(chooseReference(merge.getResulttype(), enrich.getResulttype(), trust));
|
||||
// gestito come il resulttype perche' e' un subtype
|
||||
merge.setMetaResourceType(chooseReference(merge.getMetaResourceType(), enrich.getMetaResourceType(), trust));
|
||||
// spostiamo nell'instance e qui prendo il primo che arriva
|
||||
merge.setLanguage(chooseReference(merge.getLanguage(), enrich.getLanguage(), trust));
|
||||
// country lasicamo,o cosi' -> parentesi sul datainfo
|
||||
merge.setCountry(unionDistinctLists(merge.getCountry(), enrich.getCountry(), trust));
|
||||
//ok
|
||||
merge.setSubject(unionDistinctLists(merge.getSubject(), enrich.getSubject(), trust));
|
||||
// union per priority quindi vanno in append
|
||||
merge.setTitle(unionTitle(merge.getTitle(), enrich.getTitle(), trust));
|
||||
//ok
|
||||
merge.setRelevantdate(unionDistinctLists(merge.getRelevantdate(), enrich.getRelevantdate(), trust));
|
||||
// prima trust e poi longest list
|
||||
merge.setDescription(longestLists(merge.getDescription(), enrich.getDescription()));
|
||||
// trust piu' alto e poi piu' vecchia
|
||||
merge.setDateofacceptance(chooseReference(merge.getDateofacceptance(), enrich.getDateofacceptance(), trust));
|
||||
// ok, ma publisher va messo ripetibile
|
||||
merge.setPublisher(chooseReference(merge.getPublisher(), enrich.getPublisher(), trust));
|
||||
// ok
|
||||
merge.setEmbargoenddate(chooseReference(merge.getEmbargoenddate(), enrich.getEmbargoenddate(), trust));
|
||||
// ok
|
||||
merge.setSource(unionDistinctLists(merge.getSource(), enrich.getSource(), trust));
|
||||
// ok
|
||||
merge.setFulltext(unionDistinctLists(merge.getFulltext(), enrich.getFulltext(), trust));
|
||||
// ok
|
||||
merge.setFormat(unionDistinctLists(merge.getFormat(), enrich.getFormat(), trust));
|
||||
// ok
|
||||
merge.setContributor(unionDistinctLists(merge.getContributor(), enrich.getContributor(), trust));
|
||||
|
||||
// prima prendo l'higher trust, su questo prendo il valore migliore nelle istanze TODO
|
||||
// trust maggiore ma a parita' di trust il piu' specifico (base del vocabolario)
|
||||
// vedi note
|
||||
merge.setResourcetype(firstNonNull(merge.getResourcetype(), enrich.getResourcetype()));
|
||||
|
||||
// ok
|
||||
merge.setCoverage(unionDistinctLists(merge.getCoverage(), enrich.getCoverage(), trust));
|
||||
|
||||
// most open ok
|
||||
if (enrich.getBestaccessright() != null
|
||||
&& new AccessRightComparator<>()
|
||||
.compare(enrich.getBestaccessright(), merge.getBestaccessright()) < 0) {
|
||||
merge.setBestaccessright(enrich.getBestaccessright());
|
||||
}
|
||||
|
||||
// TODO merge of datainfo given same id
|
||||
merge.setContext(unionDistinctLists(merge.getContext(), enrich.getContext(), trust));
|
||||
|
||||
//ok
|
||||
merge.setExternalReference(unionDistinctLists(merge.getExternalReference(), enrich.getExternalReference(), trust));
|
||||
|
||||
//instance enrichment or union
|
||||
// review instance equals => add pid to comparision
|
||||
if (!isAnEnrichment(merge) && !isAnEnrichment(enrich))
|
||||
merge.setInstance(unionDistinctLists(merge.getInstance(), enrich.getInstance(), trust));
|
||||
else {
|
||||
final List<Instance> enrichmentInstances = isAnEnrichment(merge) ? merge.getInstance()
|
||||
: enrich.getInstance();
|
||||
final List<Instance> enrichedInstances = isAnEnrichment(merge) ? enrich.getInstance()
|
||||
: merge.getInstance();
|
||||
if (isAnEnrichment(merge))
|
||||
merge.setDataInfo(enrich.getDataInfo());
|
||||
merge.setInstance(enrichInstances(enrichedInstances, enrichmentInstances));
|
||||
}
|
||||
|
||||
merge.setEoscifguidelines(unionDistinctLists(merge.getEoscifguidelines(), enrich.getEoscifguidelines(), trust));
|
||||
merge.setIsGreen(booleanOR(merge.getIsGreen(), enrich.getIsGreen()));
|
||||
// OK but should be list of values
|
||||
merge.setOpenAccessColor(chooseReference(merge.getOpenAccessColor(), enrich.getOpenAccessColor(), trust));
|
||||
merge.setIsInDiamondJournal(booleanOR(merge.getIsInDiamondJournal(), enrich.getIsInDiamondJournal()));
|
||||
merge.setPubliclyFunded(booleanOR(merge.getPubliclyFunded(), enrich.getPubliclyFunded()));
|
||||
|
||||
return merge;
|
||||
}
|
||||
|
||||
private static <T extends OtherResearchProduct> T mergeORP(T original, T enrich) {
|
||||
int trust = compareTrust(original, enrich);
|
||||
final T merge = mergeResult(original, enrich);
|
||||
|
||||
merge.setContactperson(unionDistinctLists(merge.getContactperson(), enrich.getContactperson(), trust));
|
||||
merge.setContactgroup(unionDistinctLists(merge.getContactgroup(), enrich.getContactgroup(), trust));
|
||||
merge.setTool(unionDistinctLists(merge.getTool(), enrich.getTool(), trust));
|
||||
|
||||
return merge;
|
||||
}
|
||||
|
||||
private static <T extends Software> T mergeSoftware(T original, T enrich) {
|
||||
int trust = compareTrust(original, enrich);
|
||||
final T merge = mergeResult(original, enrich);
|
||||
|
||||
merge.setDocumentationUrl(unionDistinctLists(merge.getDocumentationUrl(), enrich.getDocumentationUrl(), trust));
|
||||
merge.setLicense(unionDistinctLists(merge.getLicense(), enrich.getLicense(), trust));
|
||||
merge.setCodeRepositoryUrl(chooseReference(merge.getCodeRepositoryUrl(), enrich.getCodeRepositoryUrl(), trust));
|
||||
merge.setProgrammingLanguage(chooseReference(merge.getProgrammingLanguage(), enrich.getProgrammingLanguage(), trust));
|
||||
|
||||
return merge;
|
||||
}
|
||||
|
||||
private static <T extends Dataset> T mergeDataset(T original, T enrich) {
|
||||
int trust = compareTrust(original, enrich);
|
||||
T merge = mergeResult(original, enrich);
|
||||
|
||||
merge.setStoragedate(chooseReference(merge.getStoragedate(), enrich.getStoragedate(), trust));
|
||||
merge.setDevice(chooseReference(merge.getDevice(), enrich.getDevice(), trust));
|
||||
merge.setSize(chooseReference(merge.getSize(), enrich.getSize(), trust));
|
||||
merge.setVersion(chooseReference(merge.getVersion(), enrich.getVersion(), trust));
|
||||
merge.setLastmetadataupdate(chooseReference(merge.getLastmetadataupdate(), enrich.getLastmetadataupdate(), trust));
|
||||
merge.setMetadataversionnumber(chooseReference(merge.getMetadataversionnumber(), enrich.getMetadataversionnumber(), trust));
|
||||
merge.setGeolocation(unionDistinctLists(merge.getGeolocation(), enrich.getGeolocation(), trust));
|
||||
|
||||
return merge;
|
||||
}
|
||||
|
||||
public static <T extends Publication> T mergePublication(T original, T enrich) {
|
||||
final int trust = compareTrust(original, enrich);
|
||||
T merged = mergeResult(original, enrich);
|
||||
|
||||
merged.setJournal(chooseReference(merged.getJournal(), enrich.getJournal(), trust));
|
||||
|
||||
return merged;
|
||||
}
|
||||
|
||||
private static <T extends Organization> T mergeOrganization(T left, T enrich) {
|
||||
int trust = compareTrust(left, enrich);
|
||||
T merged = mergeOafEntityFields(left, enrich, trust);
|
||||
|
||||
merged.setLegalshortname(chooseReference(merged.getLegalshortname(), enrich.getLegalshortname(), trust));
|
||||
merged.setLegalname(chooseReference(merged.getLegalname(), enrich.getLegalname(), trust));
|
||||
merged.setAlternativeNames(unionDistinctLists(enrich.getAlternativeNames(), merged.getAlternativeNames(), trust));
|
||||
merged.setWebsiteurl(chooseReference(merged.getWebsiteurl(), enrich.getWebsiteurl(), trust));
|
||||
merged.setLogourl(chooseReference(merged.getLogourl(), enrich.getLogourl(), trust));
|
||||
merged.setEclegalbody(chooseReference(merged.getEclegalbody(), enrich.getEclegalbody(), trust));
|
||||
merged.setEclegalperson(chooseReference(merged.getEclegalperson(), enrich.getEclegalperson(), trust));
|
||||
merged.setEcnonprofit(chooseReference(merged.getEcnonprofit(), enrich.getEcnonprofit(), trust));
|
||||
merged.setEcresearchorganization(chooseReference(merged.getEcresearchorganization(), enrich.getEcresearchorganization(), trust));
|
||||
merged.setEchighereducation(chooseReference(merged.getEchighereducation(), enrich.getEchighereducation(), trust));
|
||||
merged.setEcinternationalorganizationeurinterests(chooseReference(merged.getEcinternationalorganizationeurinterests(), enrich.getEcinternationalorganizationeurinterests(), trust));
|
||||
merged.setEcinternationalorganization(chooseReference(merged.getEcinternationalorganization(), enrich.getEcinternationalorganization(), trust));
|
||||
merged.setEcenterprise(chooseReference(merged.getEcenterprise(), enrich.getEcenterprise(), trust));
|
||||
merged.setEcsmevalidated(chooseReference(merged.getEcsmevalidated(), enrich.getEcsmevalidated(), trust));
|
||||
merged.setEcnutscode(chooseReference(merged.getEcnutscode(), enrich.getEcnutscode(), trust));
|
||||
merged.setCountry(chooseReference(merged.getCountry(), enrich.getCountry(), trust));
|
||||
|
||||
return merged;
|
||||
}
|
||||
|
||||
public static <T extends Project> T mergeProject(T original, T enrich) {
|
||||
int trust = compareTrust(original, enrich);
|
||||
T merged = mergeOafEntityFields(original, enrich, trust);
|
||||
|
||||
merged.setWebsiteurl(chooseReference(merged.getWebsiteurl(), enrich.getWebsiteurl(), trust));
|
||||
merged.setCode(chooseReference(merged.getCode(), enrich.getCode(), trust));
|
||||
merged.setAcronym(chooseReference(merged.getAcronym(), enrich.getAcronym(), trust));
|
||||
merged.setTitle(chooseReference(merged.getTitle(), enrich.getTitle(), trust));
|
||||
merged.setStartdate(chooseReference(merged.getStartdate(), enrich.getStartdate(), trust));
|
||||
merged.setEnddate(chooseReference(merged.getEnddate(), enrich.getEnddate(), trust));
|
||||
merged.setCallidentifier(chooseReference(merged.getCallidentifier(), enrich.getCallidentifier(), trust));
|
||||
merged.setKeywords(chooseReference(merged.getKeywords(), enrich.getKeywords(), trust));
|
||||
merged.setDuration(chooseReference(merged.getDuration(), enrich.getDuration(), trust));
|
||||
merged.setEcsc39(chooseReference(merged.getEcsc39(), enrich.getEcsc39(), trust));
|
||||
merged.setOamandatepublications(chooseReference(merged.getOamandatepublications(), enrich.getOamandatepublications(), trust));
|
||||
merged.setEcarticle29_3(chooseReference(merged.getEcarticle29_3(), enrich.getEcarticle29_3(), trust));
|
||||
merged.setSubjects(unionDistinctLists(merged.getSubjects(), enrich.getSubjects(), trust));
|
||||
merged.setFundingtree(unionDistinctLists(merged.getFundingtree(), enrich.getFundingtree(), trust));
|
||||
merged.setContracttype(chooseReference(merged.getContracttype(), enrich.getContracttype(), trust));
|
||||
merged.setOptional1(chooseReference(merged.getOptional1(), enrich.getOptional1(), trust));
|
||||
merged.setOptional2(chooseReference(merged.getOptional2(), enrich.getOptional2(), trust));
|
||||
merged.setJsonextrainfo(chooseReference(merged.getJsonextrainfo(), enrich.getJsonextrainfo(), trust));
|
||||
merged.setContactfullname(chooseReference(merged.getContactfullname(), enrich.getContactfullname(), trust));
|
||||
merged.setContactfax(chooseReference(merged.getContactfax(), enrich.getContactfax(), trust));
|
||||
merged.setContactphone(chooseReference(merged.getContactphone(), enrich.getContactphone(), trust));
|
||||
merged.setContactemail(chooseReference(merged.getContactemail(), enrich.getContactemail(), trust));
|
||||
merged.setSummary(chooseReference(merged.getSummary(), enrich.getSummary(), trust));
|
||||
merged.setCurrency(chooseReference(merged.getCurrency(), enrich.getCurrency(), trust));
|
||||
|
||||
//missin in Project.merge
|
||||
merged.setTotalcost(chooseReference(merged.getTotalcost(), enrich.getTotalcost(), trust));
|
||||
merged.setFundedamount(chooseReference(merged.getFundedamount(), enrich.getFundedamount(), trust));
|
||||
|
||||
// trust ??
|
||||
if (enrich.getH2020topiccode() != null && StringUtils.isEmpty(merged.getH2020topiccode())) {
|
||||
merged.setH2020topiccode(enrich.getH2020topiccode());
|
||||
merged.setH2020topicdescription(enrich.getH2020topicdescription());
|
||||
}
|
||||
|
||||
merged.setH2020classification(unionDistinctLists(merged.getH2020classification(), enrich.getH2020classification(), trust));
|
||||
|
||||
return merged;
|
||||
}
|
||||
|
||||
|
||||
/**
|
||||
* Longest lists list.
|
||||
*
|
||||
* @param a the a
|
||||
* @param b the b
|
||||
* @return the list
|
||||
*/
|
||||
public static List<Field<String>> longestLists(List<Field<String>> a, List<Field<String>> b) {
|
||||
if (a == null || b == null)
|
||||
return a == null ? b : a;
|
||||
|
||||
return a.size() >= b.size() ? a : b;
|
||||
}
|
||||
|
||||
/**
|
||||
* This main method apply the enrichment of the instances
|
||||
*
|
||||
* @param toEnrichInstances the instances that could be enriched
|
||||
* @param enrichmentInstances the enrichment instances
|
||||
* @return list of instances possibly enriched
|
||||
*/
|
||||
private static List<Instance> enrichInstances(final List<Instance> toEnrichInstances,
|
||||
final List<Instance> enrichmentInstances) {
|
||||
final List<Instance> enrichmentResult = new ArrayList<>();
|
||||
|
||||
if (toEnrichInstances == null) {
|
||||
return enrichmentResult;
|
||||
}
|
||||
if (enrichmentInstances == null) {
|
||||
return enrichmentResult;
|
||||
}
|
||||
Map<String, Instance> ri = toInstanceMap(enrichmentInstances);
|
||||
|
||||
toEnrichInstances.forEach(i -> {
|
||||
final List<Instance> e = findEnrichmentsByPID(i.getPid(), ri);
|
||||
if (e != null && e.size() > 0) {
|
||||
e.forEach(enr -> applyEnrichment(i, enr));
|
||||
} else {
|
||||
final List<Instance> a = findEnrichmentsByPID(i.getAlternateIdentifier(), ri);
|
||||
if (a != null && a.size() > 0) {
|
||||
a.forEach(enr -> applyEnrichment(i, enr));
|
||||
}
|
||||
}
|
||||
enrichmentResult.add(i);
|
||||
});
|
||||
return enrichmentResult;
|
||||
}
|
||||
|
||||
/**
|
||||
* This method converts the list of instance enrichments
|
||||
* into a Map where the key is the normalized identifier
|
||||
* and the value is the instance itself
|
||||
*
|
||||
* @param ri the list of enrichment instances
|
||||
* @return the result map
|
||||
*/
|
||||
private static Map<String, Instance> toInstanceMap(final List<Instance> ri) {
|
||||
return ri
|
||||
.stream()
|
||||
.filter(i -> i.getPid() != null || i.getAlternateIdentifier() != null)
|
||||
.flatMap(i -> {
|
||||
final List<Pair<String, Instance>> result = new ArrayList<>();
|
||||
if (i.getPid() != null)
|
||||
i
|
||||
.getPid()
|
||||
.stream()
|
||||
.filter(MergeUtils::validPid)
|
||||
.forEach(p -> result.add(new ImmutablePair<>(extractKeyFromPid(p), i)));
|
||||
if (i.getAlternateIdentifier() != null)
|
||||
i
|
||||
.getAlternateIdentifier()
|
||||
.stream()
|
||||
.filter(MergeUtils::validPid)
|
||||
.forEach(p -> result.add(new ImmutablePair<>(extractKeyFromPid(p), i)));
|
||||
return result.stream();
|
||||
})
|
||||
.collect(
|
||||
Collectors
|
||||
.toMap(
|
||||
Pair::getLeft,
|
||||
Pair::getRight,
|
||||
(a, b) -> a));
|
||||
}
|
||||
|
||||
private static boolean isFromDelegatedAuthority(Result r) {
|
||||
return Optional
|
||||
.ofNullable(r.getInstance())
|
||||
.map(
|
||||
instance -> instance
|
||||
.stream()
|
||||
.filter(i -> Objects.nonNull(i.getCollectedfrom()))
|
||||
.map(i -> i.getCollectedfrom().getKey())
|
||||
.anyMatch(cfId -> IdentifierFactory.delegatedAuthorityDatasourceIds().contains(cfId)))
|
||||
.orElse(false);
|
||||
}
|
||||
|
||||
/**
|
||||
* Valid pid boolean.
|
||||
*
|
||||
* @param p the p
|
||||
* @return the boolean
|
||||
*/
|
||||
private static boolean validPid(final StructuredProperty p) {
|
||||
return p.getValue() != null && p.getQualifier() != null && p.getQualifier().getClassid() != null;
|
||||
}
|
||||
|
||||
/**
|
||||
* Normalize pid string.
|
||||
*
|
||||
* @param pid the pid
|
||||
* @return the string
|
||||
*/
|
||||
private static String extractKeyFromPid(final StructuredProperty pid) {
|
||||
if (pid == null)
|
||||
return null;
|
||||
final StructuredProperty normalizedPid = CleaningFunctions.normalizePidValue(pid);
|
||||
|
||||
return String.format("%s::%s", normalizedPid.getQualifier().getClassid(), normalizedPid.getValue());
|
||||
}
|
||||
|
||||
/**
|
||||
* This utility method finds the list of enrichment instances
|
||||
* that match one or more PIDs in the input list
|
||||
*
|
||||
* @param pids the list of PIDs
|
||||
* @param enrichments the List of enrichment instances having the same pid
|
||||
* @return the list
|
||||
*/
|
||||
private static List<Instance> findEnrichmentsByPID(final List<StructuredProperty> pids,
|
||||
final Map<String, Instance> enrichments) {
|
||||
if (pids == null || enrichments == null)
|
||||
return null;
|
||||
return pids
|
||||
.stream()
|
||||
.map(MergeUtils::extractKeyFromPid)
|
||||
.map(enrichments::get)
|
||||
.filter(Objects::nonNull)
|
||||
.collect(Collectors.toList());
|
||||
}
|
||||
|
||||
/**
|
||||
* Is an enrichment boolean.
|
||||
*
|
||||
* @param e the e
|
||||
* @return the boolean
|
||||
*/
|
||||
private static boolean isAnEnrichment(OafEntity e) {
|
||||
return e.getDataInfo() != null &&
|
||||
e.getDataInfo().getProvenanceaction() != null
|
||||
&& ModelConstants.PROVENANCE_ENRICH.equalsIgnoreCase(e.getDataInfo().getProvenanceaction().getClassid());
|
||||
}
|
||||
|
||||
/**
|
||||
* This method apply enrichment on a single instance
|
||||
* The enrichment consists of replacing values on
|
||||
* single attribute only if in the current instance is missing
|
||||
* The only repeatable field enriched is measures
|
||||
*
|
||||
* @param merge the current instance
|
||||
* @param enrichment the enrichment instance
|
||||
*/
|
||||
private static void applyEnrichment(final Instance merge, final Instance enrichment) {
|
||||
if (merge == null || enrichment == null)
|
||||
return;
|
||||
|
||||
merge.setLicense(firstNonNull(merge.getLicense(), enrichment.getLicense()));
|
||||
merge.setAccessright(firstNonNull(merge.getAccessright(), enrichment.getAccessright()));
|
||||
merge.setInstancetype(firstNonNull(merge.getInstancetype(), enrichment.getInstancetype()));
|
||||
merge.setInstanceTypeMapping(firstNonNull(merge.getInstanceTypeMapping(), enrichment.getInstanceTypeMapping()));
|
||||
merge.setHostedby(firstNonNull(merge.getHostedby(), enrichment.getHostedby()));
|
||||
merge.setUrl(unionDistinctLists(merge.getUrl(), enrichment.getUrl(), 0));
|
||||
merge.setDistributionlocation(firstNonNull(merge.getDistributionlocation(), enrichment.getDistributionlocation()));
|
||||
merge.setCollectedfrom(firstNonNull(merge.getCollectedfrom(), enrichment.getCollectedfrom()));
|
||||
// pid and alternateId are used for matching
|
||||
merge.setDateofacceptance(firstNonNull(merge.getDateofacceptance(), enrichment.getDateofacceptance()));
|
||||
merge.setProcessingchargeamount(firstNonNull(merge.getProcessingchargeamount(), enrichment.getProcessingchargeamount()));
|
||||
merge.setProcessingchargecurrency(firstNonNull(merge.getProcessingchargecurrency(), enrichment.getProcessingchargecurrency()));
|
||||
merge.setRefereed(firstNonNull(merge.getRefereed(), enrichment.getRefereed()));
|
||||
merge.setMeasures(unionDistinctLists(merge.getMeasures(), enrichment.getMeasures(), 0));
|
||||
merge.setFulltext(firstNonNull(merge.getFulltext(), enrichment.getFulltext()));
|
||||
}
|
||||
|
||||
private static int compareTrust(Oaf a, Oaf b) {
|
||||
String left = Optional
|
||||
.ofNullable(a.getDataInfo())
|
||||
.map(DataInfo::getTrust)
|
||||
.orElse("0.0");
|
||||
|
||||
String right = Optional
|
||||
.ofNullable(b.getDataInfo())
|
||||
.map(DataInfo::getTrust)
|
||||
.orElse("0.0");
|
||||
|
||||
return left.compareTo(right);
|
||||
}
|
||||
|
||||
}
|
|
@ -14,7 +14,6 @@ import java.util.stream.Collectors;
|
|||
import org.apache.commons.lang3.StringUtils;
|
||||
|
||||
import eu.dnetlib.dhp.schema.common.AccessRightComparator;
|
||||
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||
import eu.dnetlib.dhp.schema.oaf.*;
|
||||
|
||||
public class OafMapperUtils {
|
||||
|
@ -22,65 +21,6 @@ public class OafMapperUtils {
|
|||
private OafMapperUtils() {
|
||||
}
|
||||
|
||||
public static Oaf merge(final Oaf left, final Oaf right) {
|
||||
if (ModelSupport.isSubClass(left, OafEntity.class)) {
|
||||
return mergeEntities((OafEntity) left, (OafEntity) right);
|
||||
} else if (ModelSupport.isSubClass(left, Relation.class)) {
|
||||
((Relation) left).mergeFrom((Relation) right);
|
||||
} else {
|
||||
throw new IllegalArgumentException("invalid Oaf type:" + left.getClass().getCanonicalName());
|
||||
}
|
||||
return left;
|
||||
}
|
||||
|
||||
public static OafEntity mergeEntities(OafEntity left, OafEntity right) {
|
||||
if (ModelSupport.isSubClass(left, Result.class)) {
|
||||
return mergeResults((Result) left, (Result) right);
|
||||
} else if (ModelSupport.isSubClass(left, Datasource.class)) {
|
||||
left.mergeFrom(right);
|
||||
} else if (ModelSupport.isSubClass(left, Organization.class)) {
|
||||
left.mergeFrom(right);
|
||||
} else if (ModelSupport.isSubClass(left, Project.class)) {
|
||||
left.mergeFrom(right);
|
||||
} else {
|
||||
throw new IllegalArgumentException("invalid OafEntity subtype:" + left.getClass().getCanonicalName());
|
||||
}
|
||||
return left;
|
||||
}
|
||||
|
||||
public static Result mergeResults(Result left, Result right) {
|
||||
|
||||
final boolean leftFromDelegatedAuthority = isFromDelegatedAuthority(left);
|
||||
final boolean rightFromDelegatedAuthority = isFromDelegatedAuthority(right);
|
||||
|
||||
if (leftFromDelegatedAuthority && !rightFromDelegatedAuthority) {
|
||||
return left;
|
||||
}
|
||||
if (!leftFromDelegatedAuthority && rightFromDelegatedAuthority) {
|
||||
return right;
|
||||
}
|
||||
|
||||
if (new ResultTypeComparator().compare(left, right) < 0) {
|
||||
left.mergeFrom(right);
|
||||
return left;
|
||||
} else {
|
||||
right.mergeFrom(left);
|
||||
return right;
|
||||
}
|
||||
}
|
||||
|
||||
private static boolean isFromDelegatedAuthority(Result r) {
|
||||
return Optional
|
||||
.ofNullable(r.getInstance())
|
||||
.map(
|
||||
instance -> instance
|
||||
.stream()
|
||||
.filter(i -> Objects.nonNull(i.getCollectedfrom()))
|
||||
.map(i -> i.getCollectedfrom().getKey())
|
||||
.anyMatch(cfId -> IdentifierFactory.delegatedAuthorityDatasourceIds().contains(cfId)))
|
||||
.orElse(false);
|
||||
}
|
||||
|
||||
public static KeyValue keyValue(final String k, final String v) {
|
||||
final KeyValue kv = new KeyValue();
|
||||
kv.setKey(k);
|
||||
|
|
|
@ -0,0 +1,109 @@
|
|||
|
||||
package eu.dnetlib.dhp.common.api;
|
||||
|
||||
import java.io.File;
|
||||
import java.io.FileInputStream;
|
||||
import java.io.IOException;
|
||||
import java.io.InputStream;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.junit.jupiter.api.Assertions;
|
||||
import org.junit.jupiter.api.Disabled;
|
||||
import org.junit.jupiter.api.Test;
|
||||
|
||||
@Disabled
|
||||
class ZenodoAPIClientTest {
|
||||
|
||||
private final String URL_STRING = "https://sandbox.zenodo.org/api/deposit/depositions";
|
||||
private final String ACCESS_TOKEN = "";
|
||||
|
||||
private final String CONCEPT_REC_ID = "657113";
|
||||
|
||||
private final String depositionId = "674915";
|
||||
|
||||
@Test
|
||||
void testUploadOldDeposition() throws IOException, MissingConceptDoiException {
|
||||
ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
|
||||
ACCESS_TOKEN);
|
||||
Assertions.assertEquals(200, client.uploadOpenDeposition(depositionId));
|
||||
|
||||
File file = new File(getClass()
|
||||
.getResource("/eu/dnetlib/dhp/common/api/COVID-19.json.gz")
|
||||
.getPath());
|
||||
|
||||
InputStream is = new FileInputStream(file);
|
||||
|
||||
Assertions.assertEquals(200, client.uploadIS(is, "COVID-19.json.gz"));
|
||||
|
||||
String metadata = IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/common/api/metadata.json"));
|
||||
|
||||
Assertions.assertEquals(200, client.sendMretadata(metadata));
|
||||
|
||||
Assertions.assertEquals(202, client.publish());
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
void testNewDeposition() throws IOException {
|
||||
|
||||
ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
|
||||
ACCESS_TOKEN);
|
||||
Assertions.assertEquals(201, client.newDeposition());
|
||||
|
||||
File file = new File(getClass()
|
||||
.getResource("/eu/dnetlib/dhp/common/api/COVID-19.json.gz")
|
||||
.getPath());
|
||||
|
||||
InputStream is = new FileInputStream(file);
|
||||
|
||||
Assertions.assertEquals(200, client.uploadIS(is, "COVID-19.json.gz"));
|
||||
|
||||
String metadata = IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/common/api/metadata.json"));
|
||||
|
||||
Assertions.assertEquals(200, client.sendMretadata(metadata));
|
||||
|
||||
Assertions.assertEquals(202, client.publish());
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
void testNewVersionNewName() throws IOException, MissingConceptDoiException {
|
||||
|
||||
ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
|
||||
ACCESS_TOKEN);
|
||||
|
||||
Assertions.assertEquals(201, client.newVersion(CONCEPT_REC_ID));
|
||||
|
||||
File file = new File(getClass()
|
||||
.getResource("/eu/dnetlib/dhp/common/api/newVersion")
|
||||
.getPath());
|
||||
|
||||
InputStream is = new FileInputStream(file);
|
||||
|
||||
Assertions.assertEquals(200, client.uploadIS(is, "newVersion_deposition"));
|
||||
|
||||
Assertions.assertEquals(202, client.publish());
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
void testNewVersionOldName() throws IOException, MissingConceptDoiException {
|
||||
|
||||
ZenodoAPIClient client = new ZenodoAPIClient(URL_STRING,
|
||||
ACCESS_TOKEN);
|
||||
|
||||
Assertions.assertEquals(201, client.newVersion(CONCEPT_REC_ID));
|
||||
|
||||
File file = new File(getClass()
|
||||
.getResource("/eu/dnetlib/dhp/common/api/newVersion2")
|
||||
.getPath());
|
||||
|
||||
InputStream is = new FileInputStream(file);
|
||||
|
||||
Assertions.assertEquals(200, client.uploadIS(is, "newVersion_deposition"));
|
||||
|
||||
Assertions.assertEquals(202, client.publish());
|
||||
|
||||
}
|
||||
|
||||
}
|
|
@ -0,0 +1,111 @@
|
|||
|
||||
package eu.dnetlib.dhp.schema.oaf.utils;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.*;
|
||||
import static org.junit.jupiter.api.Assertions.assertEquals;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.util.HashSet;
|
||||
import java.util.List;
|
||||
import java.util.stream.Collectors;
|
||||
|
||||
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.junit.jupiter.api.Test;
|
||||
|
||||
import com.fasterxml.jackson.databind.DeserializationFeature;
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||
import eu.dnetlib.dhp.schema.oaf.Dataset;
|
||||
import eu.dnetlib.dhp.schema.oaf.KeyValue;
|
||||
import eu.dnetlib.dhp.schema.oaf.Publication;
|
||||
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||
|
||||
public class MergeUtilsTest {
|
||||
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper()
|
||||
.configure(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES, false);
|
||||
|
||||
@Test
|
||||
void testMergePubs() throws IOException {
|
||||
Publication p1 = read("publication_1.json", Publication.class);
|
||||
Publication p2 = read("publication_2.json", Publication.class);
|
||||
Dataset d1 = read("dataset_1.json", Dataset.class);
|
||||
Dataset d2 = read("dataset_2.json", Dataset.class);
|
||||
|
||||
assertEquals(1, p1.getCollectedfrom().size());
|
||||
assertEquals(ModelConstants.CROSSREF_ID, p1.getCollectedfrom().get(0).getKey());
|
||||
assertEquals(1, d2.getCollectedfrom().size());
|
||||
assertFalse(cfId(d2.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
|
||||
|
||||
assertEquals(1, p2.getCollectedfrom().size());
|
||||
assertFalse(cfId(p2.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
|
||||
assertEquals(1, d1.getCollectedfrom().size());
|
||||
assertTrue(cfId(d1.getCollectedfrom()).contains(ModelConstants.CROSSREF_ID));
|
||||
|
||||
final Result p1d2 = MergeUtils.checkedMerge(p1, d2);
|
||||
assertEquals(ModelConstants.PUBLICATION_RESULTTYPE_CLASSID, p1d2.getResulttype().getClassid());
|
||||
assertTrue(p1d2 instanceof Publication);
|
||||
assertEquals(p1.getId(), p1d2.getId());
|
||||
}
|
||||
|
||||
@Test
|
||||
void testMergePubs_1() throws IOException {
|
||||
Publication p2 = read("publication_2.json", Publication.class);
|
||||
Dataset d1 = read("dataset_1.json", Dataset.class);
|
||||
|
||||
final Result p2d1 = MergeUtils.checkedMerge(p2, d1);
|
||||
assertEquals((ModelConstants.DATASET_RESULTTYPE_CLASSID), p2d1.getResulttype().getClassid());
|
||||
assertTrue(p2d1 instanceof Dataset);
|
||||
assertEquals(d1.getId(), p2d1.getId());
|
||||
assertEquals(2, p2d1.getCollectedfrom().size());
|
||||
}
|
||||
|
||||
@Test
|
||||
void testMergePubs_2() throws IOException {
|
||||
Publication p1 = read("publication_1.json", Publication.class);
|
||||
Publication p2 = read("publication_2.json", Publication.class);
|
||||
|
||||
Result p1p2 = MergeUtils.checkedMerge(p1, p2);
|
||||
assertTrue(p1p2 instanceof Publication);
|
||||
assertEquals(p1.getId(), p1p2.getId());
|
||||
assertEquals(2, p1p2.getCollectedfrom().size());
|
||||
}
|
||||
|
||||
@Test
|
||||
void testDelegatedAuthority_1() throws IOException {
|
||||
Dataset d1 = read("dataset_2.json", Dataset.class);
|
||||
Dataset d2 = read("dataset_delegated.json", Dataset.class);
|
||||
|
||||
assertEquals(1, d2.getCollectedfrom().size());
|
||||
assertTrue(cfId(d2.getCollectedfrom()).contains(ModelConstants.ZENODO_OD_ID));
|
||||
|
||||
Result res = (Result) MergeUtils.merge(d1, d2, true);
|
||||
|
||||
assertEquals(d2, res);
|
||||
}
|
||||
|
||||
@Test
|
||||
void testDelegatedAuthority_2() throws IOException {
|
||||
Dataset p1 = read("publication_1.json", Dataset.class);
|
||||
Dataset d2 = read("dataset_delegated.json", Dataset.class);
|
||||
|
||||
assertEquals(1, d2.getCollectedfrom().size());
|
||||
assertTrue(cfId(d2.getCollectedfrom()).contains(ModelConstants.ZENODO_OD_ID));
|
||||
|
||||
Result res = (Result) MergeUtils.merge(p1, d2, true);
|
||||
|
||||
assertEquals(d2, res);
|
||||
}
|
||||
|
||||
protected HashSet<String> cfId(List<KeyValue> collectedfrom) {
|
||||
return collectedfrom.stream().map(KeyValue::getKey).collect(Collectors.toCollection(HashSet::new));
|
||||
}
|
||||
|
||||
protected <T extends Result> T read(String filename, Class<T> clazz) throws IOException {
|
||||
final String json = IOUtils.toString(getClass().getResourceAsStream(filename));
|
||||
return OBJECT_MAPPER.readValue(json, clazz);
|
||||
}
|
||||
|
||||
}
|
|
@ -149,7 +149,7 @@ class OafMapperUtilsTest {
|
|||
void testDate() {
|
||||
final String date = GraphCleaningFunctions.cleanDate("23-FEB-1998");
|
||||
assertNotNull(date);
|
||||
System.out.println(date);
|
||||
assertEquals("1998-02-23", date);
|
||||
}
|
||||
|
||||
@Test
|
||||
|
@ -166,8 +166,8 @@ class OafMapperUtilsTest {
|
|||
|
||||
assertEquals(
|
||||
ModelConstants.PUBLICATION_RESULTTYPE_CLASSID,
|
||||
OafMapperUtils
|
||||
.mergeResults(p1, d2)
|
||||
MergeUtils
|
||||
.mergeResult(p1, d2)
|
||||
.getResulttype()
|
||||
.getClassid());
|
||||
|
||||
|
@ -178,8 +178,8 @@ class OafMapperUtilsTest {
|
|||
|
||||
assertEquals(
|
||||
ModelConstants.DATASET_RESULTTYPE_CLASSID,
|
||||
OafMapperUtils
|
||||
.mergeResults(p2, d1)
|
||||
MergeUtils
|
||||
.mergeResult(p2, d1)
|
||||
.getResulttype()
|
||||
.getClassid());
|
||||
}
|
||||
|
@ -192,7 +192,7 @@ class OafMapperUtilsTest {
|
|||
assertEquals(1, d2.getCollectedfrom().size());
|
||||
assertTrue(cfId(d2.getCollectedfrom()).contains(ModelConstants.ZENODO_OD_ID));
|
||||
|
||||
Result res = OafMapperUtils.mergeResults(d1, d2);
|
||||
Result res = MergeUtils.mergeResult(d1, d2);
|
||||
|
||||
assertEquals(d2, res);
|
||||
|
||||
|
|
|
@ -23,15 +23,18 @@ public class InstanceTypeMatch extends AbstractListComparator {
|
|||
|
||||
// jolly types
|
||||
translationMap.put("Conference object", "*");
|
||||
translationMap.put("Research", "*");
|
||||
translationMap.put("Other literature type", "*");
|
||||
translationMap.put("Unknown", "*");
|
||||
translationMap.put("UNKNOWN", "*");
|
||||
|
||||
// article types
|
||||
translationMap.put("Article", "Article");
|
||||
translationMap.put("Journal", "Article");
|
||||
translationMap.put("Data Paper", "Article");
|
||||
translationMap.put("Software Paper", "Article");
|
||||
translationMap.put("Preprint", "Article");
|
||||
translationMap.put("Part of book or chapter of book", "Article");
|
||||
|
||||
// thesis types
|
||||
translationMap.put("Thesis", "Thesis");
|
||||
|
|
|
@ -1,14 +1,13 @@
|
|||
|
||||
package eu.dnetlib.dhp.actionmanager.promote;
|
||||
|
||||
import static eu.dnetlib.dhp.schema.common.ModelSupport.isSubClass;
|
||||
import eu.dnetlib.dhp.common.FunctionalInterfaceSupport.SerializableSupplier;
|
||||
import eu.dnetlib.dhp.schema.oaf.Oaf;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
|
||||
|
||||
import java.util.function.BiFunction;
|
||||
|
||||
import eu.dnetlib.dhp.common.FunctionalInterfaceSupport.SerializableSupplier;
|
||||
import eu.dnetlib.dhp.schema.oaf.Oaf;
|
||||
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
||||
import eu.dnetlib.dhp.schema.oaf.Relation;
|
||||
import static eu.dnetlib.dhp.schema.common.ModelSupport.isSubClass;
|
||||
|
||||
/** OAF model merging support. */
|
||||
public class MergeAndGet {
|
||||
|
@ -46,20 +45,7 @@ public class MergeAndGet {
|
|||
}
|
||||
|
||||
private static <G extends Oaf, A extends Oaf> G mergeFromAndGet(G x, A y) {
|
||||
if (isSubClass(x, Relation.class) && isSubClass(y, Relation.class)) {
|
||||
((Relation) x).mergeFrom((Relation) y);
|
||||
return x;
|
||||
} else if (isSubClass(x, OafEntity.class)
|
||||
&& isSubClass(y, OafEntity.class)
|
||||
&& isSubClass(x, y)) {
|
||||
((OafEntity) x).mergeFrom((OafEntity) y);
|
||||
return x;
|
||||
}
|
||||
throw new RuntimeException(
|
||||
String
|
||||
.format(
|
||||
"MERGE_FROM_AND_GET incompatible types: %s, %s",
|
||||
x.getClass().getCanonicalName(), y.getClass().getCanonicalName()));
|
||||
return (G) MergeUtils.merge(x, y);
|
||||
}
|
||||
|
||||
@SuppressWarnings("unchecked")
|
||||
|
|
|
@ -64,6 +64,9 @@ public class PrepareAffiliationRelations implements Serializable {
|
|||
final String pubmedInputPath = parser.get("pubmedInputPath");
|
||||
log.info("pubmedInputPath: {}", pubmedInputPath);
|
||||
|
||||
final String openapcInputPath = parser.get("openapcInputPath");
|
||||
log.info("openapcInputPath: {}", openapcInputPath);
|
||||
|
||||
final String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath: {}", outputPath);
|
||||
|
||||
|
@ -85,8 +88,14 @@ public class PrepareAffiliationRelations implements Serializable {
|
|||
JavaPairRDD<Text, Text> pubmedRelations = prepareAffiliationRelations(
|
||||
spark, pubmedInputPath, collectedFromPubmed);
|
||||
|
||||
List<KeyValue> collectedFromOpenAPC = OafMapperUtils
|
||||
.listKeyValues(ModelConstants.OPEN_APC_ID, "OpenAPC");
|
||||
JavaPairRDD<Text, Text> openAPCRelations = prepareAffiliationRelations(
|
||||
spark, openapcInputPath, collectedFromOpenAPC);
|
||||
|
||||
crossrefRelations
|
||||
.union(pubmedRelations)
|
||||
.union(openAPCRelations)
|
||||
.saveAsHadoopFile(
|
||||
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
|
||||
|
||||
|
|
|
@ -95,7 +95,7 @@ public class SparkAtomicActionScoreJob implements Serializable {
|
|||
|
||||
return projectScores.map((MapFunction<BipProjectModel, Project>) bipProjectScores -> {
|
||||
Project project = new Project();
|
||||
project.setId(bipProjectScores.getProjectId());
|
||||
//project.setId(bipProjectScores.getProjectId());
|
||||
project.setMeasures(bipProjectScores.toMeasures());
|
||||
return project;
|
||||
}, Encoders.bean(Project.class))
|
||||
|
|
|
@ -34,6 +34,11 @@ public class BipProjectModel {
|
|||
|
||||
String totalCitationCount;
|
||||
|
||||
public String getProjectId() {
|
||||
return projectId;
|
||||
}
|
||||
|
||||
|
||||
// each project bip measure has exactly one value, hence one key-value pair
|
||||
private Measure createMeasure(String measureId, String measureValue) {
|
||||
|
||||
|
|
|
@ -75,6 +75,7 @@ public class GetFOSSparkJob implements Serializable {
|
|||
fosData.map((MapFunction<Row, FOSDataModel>) r -> {
|
||||
FOSDataModel fosDataModel = new FOSDataModel();
|
||||
fosDataModel.setDoi(r.getString(0).toLowerCase());
|
||||
fosDataModel.setOaid(r.getString(1).toLowerCase());
|
||||
fosDataModel.setLevel1(r.getString(2));
|
||||
fosDataModel.setLevel2(r.getString(3));
|
||||
fosDataModel.setLevel3(r.getString(4));
|
||||
|
|
|
@ -16,12 +16,14 @@ 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.jetbrains.annotations.NotNull;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel;
|
||||
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.Result;
|
||||
import eu.dnetlib.dhp.schema.oaf.StructuredProperty;
|
||||
import eu.dnetlib.dhp.schema.oaf.Subject;
|
||||
|
@ -52,62 +54,90 @@ public class PrepareFOSSparkJob implements Serializable {
|
|||
final String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath: {}", outputPath);
|
||||
|
||||
final Boolean distributeDOI = Optional
|
||||
.ofNullable(parser.get("distributeDoi"))
|
||||
.map(Boolean::valueOf)
|
||||
.orElse(Boolean.TRUE);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
runWithSparkSession(
|
||||
conf,
|
||||
isSparkSessionManaged,
|
||||
spark -> {
|
||||
distributeFOSdois(
|
||||
spark,
|
||||
sourcePath,
|
||||
if (distributeDOI)
|
||||
distributeFOSdois(
|
||||
spark,
|
||||
sourcePath,
|
||||
|
||||
outputPath);
|
||||
outputPath);
|
||||
else
|
||||
distributeFOSoaid(spark, sourcePath, outputPath);
|
||||
});
|
||||
}
|
||||
|
||||
private static void distributeFOSoaid(SparkSession spark, String sourcePath, String outputPath) {
|
||||
Dataset<FOSDataModel> fosDataset = readPath(spark, sourcePath, FOSDataModel.class);
|
||||
|
||||
fosDataset
|
||||
.groupByKey((MapFunction<FOSDataModel, String>) v -> v.getOaid().toLowerCase(), Encoders.STRING())
|
||||
.mapGroups((MapGroupsFunction<String, FOSDataModel, Result>) (k, it) -> {
|
||||
return getResult(ModelSupport.getIdPrefix(Result.class) + "|" + k, it);
|
||||
}, Encoders.bean(Result.class))
|
||||
.write()
|
||||
.mode(SaveMode.Overwrite)
|
||||
.option("compression", "gzip")
|
||||
.json(outputPath + "/fos");
|
||||
}
|
||||
|
||||
@NotNull
|
||||
private static Result getResult(String k, Iterator<FOSDataModel> it) {
|
||||
Result r = new Result();
|
||||
FOSDataModel first = it.next();
|
||||
r.setId(k);
|
||||
|
||||
HashSet<String> level1 = new HashSet<>();
|
||||
HashSet<String> level2 = new HashSet<>();
|
||||
HashSet<String> level3 = new HashSet<>();
|
||||
HashSet<String> level4 = new HashSet<>();
|
||||
addLevels(level1, level2, level3, level4, first);
|
||||
it.forEachRemaining(v -> addLevels(level1, level2, level3, level4, v));
|
||||
List<Subject> sbjs = new ArrayList<>();
|
||||
level1
|
||||
.forEach(l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
|
||||
level2
|
||||
.forEach(l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
|
||||
level3
|
||||
.forEach(
|
||||
l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID, true)));
|
||||
level4
|
||||
.forEach(
|
||||
l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID, true)));
|
||||
r.setSubject(sbjs);
|
||||
r
|
||||
.setDataInfo(
|
||||
OafMapperUtils
|
||||
.dataInfo(
|
||||
false, null, true,
|
||||
false,
|
||||
OafMapperUtils
|
||||
.qualifier(
|
||||
ModelConstants.PROVENANCE_ENRICH,
|
||||
null,
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS,
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS),
|
||||
null));
|
||||
return r;
|
||||
}
|
||||
|
||||
private static void distributeFOSdois(SparkSession spark, String sourcePath, String outputPath) {
|
||||
Dataset<FOSDataModel> fosDataset = readPath(spark, sourcePath, FOSDataModel.class);
|
||||
|
||||
fosDataset
|
||||
.groupByKey((MapFunction<FOSDataModel, String>) v -> v.getDoi().toLowerCase(), Encoders.STRING())
|
||||
.mapGroups((MapGroupsFunction<String, FOSDataModel, Result>) (k, it) -> {
|
||||
Result r = new Result();
|
||||
FOSDataModel first = it.next();
|
||||
r.setId(DHPUtils.generateUnresolvedIdentifier(k, DOI));
|
||||
|
||||
HashSet<String> level1 = new HashSet<>();
|
||||
HashSet<String> level2 = new HashSet<>();
|
||||
HashSet<String> level3 = new HashSet<>();
|
||||
HashSet<String> level4 = new HashSet<>();
|
||||
addLevels(level1, level2, level3, level4, first);
|
||||
it.forEachRemaining(v -> addLevels(level1, level2, level3, level4, v));
|
||||
List<Subject> sbjs = new ArrayList<>();
|
||||
level1
|
||||
.forEach(l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
|
||||
level2
|
||||
.forEach(l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID)));
|
||||
level3
|
||||
.forEach(
|
||||
l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID, true)));
|
||||
level4
|
||||
.forEach(
|
||||
l -> add(sbjs, getSubject(l, FOS_CLASS_ID, FOS_CLASS_NAME, UPDATE_SUBJECT_FOS_CLASS_ID, true)));
|
||||
r.setSubject(sbjs);
|
||||
r
|
||||
.setDataInfo(
|
||||
OafMapperUtils
|
||||
.dataInfo(
|
||||
false, null, true,
|
||||
false,
|
||||
OafMapperUtils
|
||||
.qualifier(
|
||||
ModelConstants.PROVENANCE_ENRICH,
|
||||
null,
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS,
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS),
|
||||
null));
|
||||
return r;
|
||||
}, Encoders.bean(Result.class))
|
||||
.mapGroups(
|
||||
(MapGroupsFunction<String, FOSDataModel, Result>) (k,
|
||||
it) -> getResult(DHPUtils.generateUnresolvedIdentifier(k, DOI), it),
|
||||
Encoders.bean(Result.class))
|
||||
.write()
|
||||
.mode(SaveMode.Overwrite)
|
||||
.option("compression", "gzip")
|
||||
|
|
|
@ -0,0 +1,92 @@
|
|||
|
||||
package eu.dnetlib.dhp.actionmanager.fosnodoi;
|
||||
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.io.Serializable;
|
||||
import java.util.*;
|
||||
|
||||
import org.apache.commons.cli.ParseException;
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.hadoop.io.Text;
|
||||
import org.apache.hadoop.io.compress.GzipCodec;
|
||||
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.JavaPairRDD;
|
||||
import org.apache.spark.api.java.function.FilterFunction;
|
||||
import org.apache.spark.api.java.function.FlatMapFunction;
|
||||
import org.apache.spark.api.java.function.MapFunction;
|
||||
import org.apache.spark.sql.Encoders;
|
||||
import org.apache.spark.sql.SparkSession;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
import eu.dnetlib.dhp.actionmanager.opencitations.model.COCI;
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.schema.action.AtomicAction;
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||
import eu.dnetlib.dhp.schema.oaf.Relation;
|
||||
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.*;
|
||||
import scala.Tuple2;
|
||||
|
||||
public class CreateActionSetSparkJob implements Serializable {
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
|
||||
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
public static void main(final String[] args) throws IOException, ParseException {
|
||||
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
|
||||
IOUtils
|
||||
.toString(
|
||||
Objects
|
||||
.requireNonNull(
|
||||
CreateActionSetSparkJob.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/actionmanager/fosnodoi/as_parameters.json"))));
|
||||
|
||||
parser.parseArgument(args);
|
||||
|
||||
Boolean isSparkSessionManaged = Optional
|
||||
.ofNullable(parser.get("isSparkSessionManaged"))
|
||||
.map(Boolean::valueOf)
|
||||
.orElse(Boolean.TRUE);
|
||||
|
||||
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||
|
||||
final 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 -> createActionSet(spark, inputPath, outputPath));
|
||||
|
||||
}
|
||||
|
||||
private static void createActionSet(SparkSession spark, String inputPath, String outputPath) {
|
||||
spark
|
||||
.read()
|
||||
.textFile(inputPath)
|
||||
.map(
|
||||
(MapFunction<String, Result>) value -> OBJECT_MAPPER.readValue(value, Result.class),
|
||||
Encoders.bean(Result.class))
|
||||
.toJavaRDD()
|
||||
.map(p -> new AtomicAction(p.getClass(), p))
|
||||
.mapToPair(
|
||||
aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
|
||||
new Text(OBJECT_MAPPER.writeValueAsString(aa))))
|
||||
.saveAsHadoopFile(
|
||||
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
|
||||
}
|
||||
|
||||
}
|
|
@ -1,12 +1,20 @@
|
|||
|
||||
package eu.dnetlib.dhp.actionmanager.project;
|
||||
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
import java.util.Arrays;
|
||||
import java.util.Objects;
|
||||
import java.util.Optional;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProgramme;
|
||||
import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProject;
|
||||
import eu.dnetlib.dhp.actionmanager.project.utils.model.JsonTopic;
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.common.HdfsSupport;
|
||||
import eu.dnetlib.dhp.schema.action.AtomicAction;
|
||||
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||
import eu.dnetlib.dhp.schema.oaf.H2020Classification;
|
||||
import eu.dnetlib.dhp.schema.oaf.H2020Programme;
|
||||
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
||||
import eu.dnetlib.dhp.schema.oaf.Project;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
|
||||
import eu.dnetlib.dhp.utils.DHPUtils;
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.hadoop.io.Text;
|
||||
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
|
||||
|
@ -18,24 +26,14 @@ import org.apache.spark.sql.Encoders;
|
|||
import org.apache.spark.sql.SparkSession;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProgramme;
|
||||
import eu.dnetlib.dhp.actionmanager.project.utils.model.CSVProject;
|
||||
import eu.dnetlib.dhp.actionmanager.project.utils.model.EXCELTopic;
|
||||
import eu.dnetlib.dhp.actionmanager.project.utils.model.JsonTopic;
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.common.HdfsSupport;
|
||||
import eu.dnetlib.dhp.schema.action.AtomicAction;
|
||||
import eu.dnetlib.dhp.schema.common.ModelSupport;
|
||||
import eu.dnetlib.dhp.schema.oaf.H2020Classification;
|
||||
import eu.dnetlib.dhp.schema.oaf.H2020Programme;
|
||||
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
||||
import eu.dnetlib.dhp.schema.oaf.Project;
|
||||
import eu.dnetlib.dhp.utils.DHPUtils;
|
||||
import scala.Tuple2;
|
||||
|
||||
import java.util.Arrays;
|
||||
import java.util.Objects;
|
||||
import java.util.Optional;
|
||||
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
/**
|
||||
* Class that makes the ActionSet. To prepare the AS two joins are needed
|
||||
*
|
||||
|
@ -160,9 +158,11 @@ public class SparkAtomicActionJob {
|
|||
(MapFunction<Project, String>) OafEntity::getId,
|
||||
Encoders.STRING())
|
||||
.mapGroups((MapGroupsFunction<String, Project, Project>) (s, it) -> {
|
||||
Project first = it.next();
|
||||
it.forEachRemaining(first::mergeFrom);
|
||||
return first;
|
||||
Project merge = it.next();
|
||||
while (it.hasNext()) {
|
||||
merge = MergeUtils.mergeProject(merge, it.next());
|
||||
}
|
||||
return merge;
|
||||
}, Encoders.bean(Project.class))
|
||||
.toJavaRDD()
|
||||
.map(p -> new AtomicAction(Project.class, p))
|
||||
|
|
|
@ -0,0 +1,195 @@
|
|||
|
||||
package eu.dnetlib.dhp.actionmanager.transformativeagreement;
|
||||
|
||||
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.io.Serializable;
|
||||
import java.util.*;
|
||||
|
||||
import org.apache.commons.cli.ParseException;
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.hadoop.io.Text;
|
||||
import org.apache.hadoop.io.compress.GzipCodec;
|
||||
import org.apache.hadoop.mapred.SequenceFileOutputFormat;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.JavaRDD;
|
||||
import org.apache.spark.api.java.function.FilterFunction;
|
||||
import org.apache.spark.api.java.function.FlatMapFunction;
|
||||
import org.apache.spark.api.java.function.MapFunction;
|
||||
import org.apache.spark.sql.Encoders;
|
||||
import org.apache.spark.sql.SparkSession;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
import eu.dnetlib.dhp.actionmanager.transformativeagreement.model.TransformativeAgreementModel;
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.schema.action.AtomicAction;
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||
import eu.dnetlib.dhp.schema.oaf.Country;
|
||||
import eu.dnetlib.dhp.schema.oaf.Relation;
|
||||
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.*;
|
||||
import scala.Tuple2;
|
||||
|
||||
public class CreateActionSetSparkJob implements Serializable {
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(CreateActionSetSparkJob.class);
|
||||
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
private static final String IREL_PROJECT = "40|100018998___::1e5e62235d094afd01cd56e65112fc63";
|
||||
private static final String TRANSFORMATIVE_AGREEMENT = "openapc::transformativeagreement";
|
||||
|
||||
public static void main(final String[] args) throws IOException, ParseException {
|
||||
|
||||
final ArgumentApplicationParser parser = new ArgumentApplicationParser(
|
||||
IOUtils
|
||||
.toString(
|
||||
Objects
|
||||
.requireNonNull(
|
||||
CreateActionSetSparkJob.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/actionmanager/transformativeagreement/as_parameters.json"))));
|
||||
|
||||
parser.parseArgument(args);
|
||||
|
||||
Boolean isSparkSessionManaged = Optional
|
||||
.ofNullable(parser.get("isSparkSessionManaged"))
|
||||
.map(Boolean::valueOf)
|
||||
.orElse(Boolean.TRUE);
|
||||
|
||||
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
|
||||
|
||||
final String inputPath = parser.get("inputPath");
|
||||
log.info("inputPath {}", inputPath);
|
||||
|
||||
final String outputPath = parser.get("outputPath");
|
||||
log.info("outputPath {}", outputPath);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
runWithSparkSession(
|
||||
conf,
|
||||
isSparkSessionManaged,
|
||||
spark -> createActionSet(spark, inputPath, outputPath));
|
||||
|
||||
}
|
||||
|
||||
private static void createActionSet(SparkSession spark, String inputPath, String outputPath) {
|
||||
JavaRDD<AtomicAction> relations = spark
|
||||
.read()
|
||||
.textFile(inputPath)
|
||||
.map(
|
||||
(MapFunction<String, TransformativeAgreementModel>) value -> OBJECT_MAPPER
|
||||
.readValue(value, TransformativeAgreementModel.class),
|
||||
Encoders.bean(TransformativeAgreementModel.class))
|
||||
.flatMap(
|
||||
(FlatMapFunction<TransformativeAgreementModel, Relation>) value -> createRelation(
|
||||
value)
|
||||
.iterator(),
|
||||
Encoders.bean(Relation.class))
|
||||
.filter((FilterFunction<Relation>) Objects::nonNull)
|
||||
.toJavaRDD()
|
||||
.map(p -> new AtomicAction(p.getClass(), p));
|
||||
//TODO relations in stand-by waiting to know if we need to create them or not In case we need just make a union before saving the sequence file
|
||||
spark
|
||||
.read()
|
||||
.textFile(inputPath)
|
||||
.map(
|
||||
(MapFunction<String, TransformativeAgreementModel>) value -> OBJECT_MAPPER
|
||||
.readValue(value, TransformativeAgreementModel.class),
|
||||
Encoders.bean(TransformativeAgreementModel.class))
|
||||
.map(
|
||||
(MapFunction<TransformativeAgreementModel, Result>) value -> createResult(
|
||||
value),
|
||||
Encoders.bean(Result.class))
|
||||
.filter((FilterFunction<Result>) r -> r != null)
|
||||
.toJavaRDD()
|
||||
.map(p -> new AtomicAction(p.getClass(), p))
|
||||
.mapToPair(
|
||||
aa -> new Tuple2<>(new Text(aa.getClazz().getCanonicalName()),
|
||||
new Text(OBJECT_MAPPER.writeValueAsString(aa))))
|
||||
.saveAsHadoopFile(
|
||||
outputPath, Text.class, Text.class, SequenceFileOutputFormat.class, GzipCodec.class);
|
||||
|
||||
}
|
||||
|
||||
private static Result createResult(TransformativeAgreementModel value) {
|
||||
Result r = new Result();
|
||||
r
|
||||
.setId(
|
||||
"50|doi_________::"
|
||||
+ IdentifierFactory
|
||||
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getDoi())));
|
||||
r.setTransformativeAgreement(value.getAgreement());
|
||||
Country country = new Country();
|
||||
country.setClassid(value.getCountry());
|
||||
country.setClassname(value.getCountry());
|
||||
country
|
||||
.setDataInfo(
|
||||
OafMapperUtils
|
||||
.dataInfo(
|
||||
false, ModelConstants.SYSIMPORT_ACTIONSET, false, false,
|
||||
OafMapperUtils
|
||||
.qualifier(
|
||||
"openapc::transformativeagreement",
|
||||
"Harvested from Trnasformative Agreement file from OpenAPC",
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
|
||||
"0.9"));
|
||||
country.setSchemeid(ModelConstants.DNET_COUNTRY_TYPE);
|
||||
country.setSchemename(ModelConstants.DNET_COUNTRY_TYPE);
|
||||
r.setCountry(Arrays.asList(country));
|
||||
return r;
|
||||
}
|
||||
|
||||
private static List<Relation> createRelation(TransformativeAgreementModel value) {
|
||||
|
||||
List<Relation> relationList = new ArrayList<>();
|
||||
|
||||
if (value.getAgreement().startsWith("IReL")) {
|
||||
String paper;
|
||||
|
||||
paper = "50|doi_________::"
|
||||
+ IdentifierFactory
|
||||
.md5(PidCleaner.normalizePidValue(PidType.doi.toString(), value.getDoi()));
|
||||
|
||||
relationList
|
||||
.add(
|
||||
getRelation(
|
||||
paper,
|
||||
IREL_PROJECT, ModelConstants.IS_PRODUCED_BY));
|
||||
|
||||
relationList.add(getRelation(IREL_PROJECT, paper, ModelConstants.PRODUCES));
|
||||
}
|
||||
return relationList;
|
||||
}
|
||||
|
||||
public static Relation getRelation(
|
||||
String source,
|
||||
String target,
|
||||
String relClass) {
|
||||
|
||||
return OafMapperUtils
|
||||
.getRelation(
|
||||
source,
|
||||
target,
|
||||
ModelConstants.RESULT_PROJECT,
|
||||
ModelConstants.OUTCOME,
|
||||
relClass,
|
||||
Arrays
|
||||
.asList(
|
||||
OafMapperUtils.keyValue(ModelConstants.OPEN_APC_ID, ModelConstants.OPEN_APC_NAME)),
|
||||
OafMapperUtils
|
||||
.dataInfo(
|
||||
false, null, false, false,
|
||||
OafMapperUtils
|
||||
.qualifier(
|
||||
TRANSFORMATIVE_AGREEMENT, "Transformative Agreement",
|
||||
ModelConstants.DNET_PROVENANCE_ACTIONS, ModelConstants.DNET_PROVENANCE_ACTIONS),
|
||||
"0.9"),
|
||||
null);
|
||||
}
|
||||
|
||||
}
|
|
@ -0,0 +1,51 @@
|
|||
|
||||
package eu.dnetlib.dhp.actionmanager.transformativeagreement.model;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
import com.fasterxml.jackson.annotation.JsonIgnoreProperties;
|
||||
|
||||
/**
|
||||
* @author miriam.baglioni
|
||||
* @Date 18/12/23
|
||||
*/
|
||||
@JsonIgnoreProperties(ignoreUnknown = true)
|
||||
|
||||
public class TransformativeAgreementModel implements Serializable {
|
||||
private String institution;
|
||||
private String doi;
|
||||
private String agreement;
|
||||
private String country;
|
||||
|
||||
public String getCountry() {
|
||||
return country;
|
||||
}
|
||||
|
||||
public void setCountry(String country) {
|
||||
this.country = country;
|
||||
}
|
||||
|
||||
public String getInstitution() {
|
||||
return institution;
|
||||
}
|
||||
|
||||
public void setInstitution(String institution) {
|
||||
this.institution = institution;
|
||||
}
|
||||
|
||||
public String getDoi() {
|
||||
return doi;
|
||||
}
|
||||
|
||||
public void setDoi(String doi) {
|
||||
this.doi = doi;
|
||||
}
|
||||
|
||||
public String getAgreement() {
|
||||
return agreement;
|
||||
}
|
||||
|
||||
public void setAgreement(String agreement) {
|
||||
this.agreement = agreement;
|
||||
}
|
||||
}
|
|
@ -0,0 +1,244 @@
|
|||
|
||||
package eu.dnetlib.dhp.collection.orcid;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.io.InputStream;
|
||||
import java.net.HttpURLConnection;
|
||||
import java.net.URL;
|
||||
import java.util.concurrent.BlockingQueue;
|
||||
|
||||
import javax.swing.*;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.commons.lang3.StringUtils;
|
||||
import org.apache.hadoop.io.SequenceFile;
|
||||
import org.apache.hadoop.io.Text;
|
||||
import org.apache.http.HttpHeaders;
|
||||
import org.jetbrains.annotations.NotNull;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import eu.dnetlib.dhp.common.collection.HttpClientParams;
|
||||
|
||||
public class ORCIDWorker extends Thread {
|
||||
|
||||
final static Logger log = LoggerFactory.getLogger(ORCIDWorker.class);
|
||||
|
||||
public static String JOB_COMPLETE = "JOB_COMPLETE";
|
||||
|
||||
private static final String userAgent = "Mozilla/5.0 (compatible; OAI; +http://www.openaire.eu)";
|
||||
|
||||
private final BlockingQueue<String> queue;
|
||||
|
||||
private boolean hasComplete = false;
|
||||
|
||||
private final SequenceFile.Writer employments;
|
||||
|
||||
private final SequenceFile.Writer summary;
|
||||
private final SequenceFile.Writer works;
|
||||
|
||||
private final String token;
|
||||
|
||||
private final String id;
|
||||
|
||||
public static ORCIDWorkerBuilder builder() {
|
||||
return new ORCIDWorkerBuilder();
|
||||
}
|
||||
|
||||
public ORCIDWorker(String id, BlockingQueue<String> myqueue, SequenceFile.Writer employments,
|
||||
SequenceFile.Writer summary, SequenceFile.Writer works, String token) {
|
||||
this.id = id;
|
||||
this.queue = myqueue;
|
||||
this.employments = employments;
|
||||
this.summary = summary;
|
||||
this.works = works;
|
||||
this.token = token;
|
||||
}
|
||||
|
||||
public static String retrieveURL(final String id, final String apiUrl, String token) {
|
||||
try {
|
||||
final HttpURLConnection urlConn = getHttpURLConnection(apiUrl, token);
|
||||
if (urlConn.getResponseCode() > 199 && urlConn.getResponseCode() < 300) {
|
||||
InputStream input = urlConn.getInputStream();
|
||||
return IOUtils.toString(input);
|
||||
} else {
|
||||
log
|
||||
.error(
|
||||
"Thread {} UNABLE TO DOWNLOAD FROM THIS URL {} , status code {}", id, apiUrl,
|
||||
urlConn.getResponseCode());
|
||||
}
|
||||
} catch (Exception e) {
|
||||
log.error("Thread {} Error on retrieving URL {} {}", id, apiUrl, e);
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
@NotNull
|
||||
private static HttpURLConnection getHttpURLConnection(String apiUrl, String token) throws IOException {
|
||||
final HttpURLConnection urlConn = (HttpURLConnection) new URL(apiUrl).openConnection();
|
||||
final HttpClientParams clientParams = new HttpClientParams();
|
||||
urlConn.setInstanceFollowRedirects(false);
|
||||
urlConn.setReadTimeout(clientParams.getReadTimeOut() * 1000);
|
||||
urlConn.setConnectTimeout(clientParams.getConnectTimeOut() * 1000);
|
||||
urlConn.addRequestProperty(HttpHeaders.USER_AGENT, userAgent);
|
||||
urlConn.addRequestProperty(HttpHeaders.AUTHORIZATION, String.format("Bearer %s", token));
|
||||
return urlConn;
|
||||
}
|
||||
|
||||
private static String generateSummaryURL(final String orcidId) {
|
||||
return "https://api.orcid.org/v3.0/" + orcidId + "/record";
|
||||
}
|
||||
|
||||
private static String generateWorksURL(final String orcidId) {
|
||||
return "https://api.orcid.org/v3.0/" + orcidId + "/works";
|
||||
}
|
||||
|
||||
private static String generateEmploymentsURL(final String orcidId) {
|
||||
return "https://api.orcid.org/v3.0/" + orcidId + "/employments";
|
||||
}
|
||||
|
||||
private static void writeResultToSequenceFile(String id, String url, String token, String orcidId,
|
||||
SequenceFile.Writer file) throws IOException {
|
||||
final String response = retrieveURL(id, url, token);
|
||||
if (response != null) {
|
||||
if (orcidId == null) {
|
||||
log.error("Thread {} {} {}", id, orcidId, response);
|
||||
throw new RuntimeException("null items ");
|
||||
}
|
||||
|
||||
if (file == null) {
|
||||
log.error("Thread {} file is null for {} URL:{}", id, url, orcidId);
|
||||
} else {
|
||||
file.append(new Text(orcidId), new Text(response));
|
||||
file.hflush();
|
||||
}
|
||||
|
||||
} else
|
||||
log.error("Thread {} response is null for {} URL:{}", id, url, orcidId);
|
||||
|
||||
}
|
||||
|
||||
@Override
|
||||
public void run() {
|
||||
final Text key = new Text();
|
||||
final Text value = new Text();
|
||||
long start;
|
||||
long total_time;
|
||||
String orcidId = "";
|
||||
int requests = 0;
|
||||
if (summary == null || employments == null || works == null)
|
||||
throw new RuntimeException("Null files");
|
||||
|
||||
while (!hasComplete) {
|
||||
try {
|
||||
|
||||
orcidId = queue.take();
|
||||
|
||||
if (orcidId.equalsIgnoreCase(JOB_COMPLETE)) {
|
||||
hasComplete = true;
|
||||
} else {
|
||||
start = System.currentTimeMillis();
|
||||
writeResultToSequenceFile(id, generateSummaryURL(orcidId), token, orcidId, summary);
|
||||
total_time = System.currentTimeMillis() - start;
|
||||
requests++;
|
||||
if (total_time < 1000) {
|
||||
// I know making a sleep on a thread is bad, but we need to stay to 24 requests per seconds,
|
||||
// hence
|
||||
// the time between two http request in a thread must be 1 second
|
||||
Thread.sleep(1000L - total_time);
|
||||
}
|
||||
start = System.currentTimeMillis();
|
||||
writeResultToSequenceFile(id, generateWorksURL(orcidId), token, orcidId, works);
|
||||
total_time = System.currentTimeMillis() - start;
|
||||
requests++;
|
||||
if (total_time < 1000) {
|
||||
// I know making a sleep on a thread is bad, but we need to stay to 24 requests per seconds,
|
||||
// hence
|
||||
// the time between two http request in a thread must be 1 second
|
||||
Thread.sleep(1000L - total_time);
|
||||
}
|
||||
start = System.currentTimeMillis();
|
||||
writeResultToSequenceFile(id, generateEmploymentsURL(orcidId), token, orcidId, employments);
|
||||
total_time = System.currentTimeMillis() - start;
|
||||
requests++;
|
||||
if (total_time < 1000) {
|
||||
// I know making a sleep on a thread is bad, but we need to stay to 24 requests per seconds,
|
||||
// hence
|
||||
// the time between two http request in a thread must be 1 second
|
||||
Thread.sleep(1000L - total_time);
|
||||
}
|
||||
if (requests % 30 == 0) {
|
||||
log.info("Thread {} Downloaded {}", id, requests);
|
||||
}
|
||||
}
|
||||
|
||||
} catch (Throwable e) {
|
||||
|
||||
log.error("Thread {} Unable to save ORICD: {} item error", id, orcidId, e);
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
try {
|
||||
works.close();
|
||||
summary.close();
|
||||
employments.close();
|
||||
} catch (Throwable e) {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
|
||||
log.info("Thread {} COMPLETE ", id);
|
||||
log.info("Thread {} Downloaded {}", id, requests);
|
||||
|
||||
}
|
||||
|
||||
public static class ORCIDWorkerBuilder {
|
||||
|
||||
private String id;
|
||||
private SequenceFile.Writer employments;
|
||||
private SequenceFile.Writer summary;
|
||||
private SequenceFile.Writer works;
|
||||
private BlockingQueue<String> queue;
|
||||
|
||||
private String token;
|
||||
|
||||
public ORCIDWorkerBuilder withId(final String id) {
|
||||
this.id = id;
|
||||
return this;
|
||||
}
|
||||
|
||||
public ORCIDWorkerBuilder withEmployments(final SequenceFile.Writer sequenceFile) {
|
||||
this.employments = sequenceFile;
|
||||
return this;
|
||||
}
|
||||
|
||||
public ORCIDWorkerBuilder withSummary(final SequenceFile.Writer sequenceFile) {
|
||||
this.summary = sequenceFile;
|
||||
return this;
|
||||
}
|
||||
|
||||
public ORCIDWorkerBuilder withWorks(final SequenceFile.Writer sequenceFile) {
|
||||
this.works = sequenceFile;
|
||||
return this;
|
||||
}
|
||||
|
||||
public ORCIDWorkerBuilder withAccessToken(final String accessToken) {
|
||||
this.token = accessToken;
|
||||
return this;
|
||||
}
|
||||
|
||||
public ORCIDWorkerBuilder withBlockingQueue(final BlockingQueue<String> queue) {
|
||||
this.queue = queue;
|
||||
return this;
|
||||
}
|
||||
|
||||
public ORCIDWorker build() {
|
||||
if (this.summary == null || this.works == null || this.employments == null || StringUtils.isEmpty(token)
|
||||
|| queue == null)
|
||||
throw new RuntimeException("Unable to build missing required params");
|
||||
return new ORCIDWorker(id, queue, employments, summary, works, token);
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
}
|
|
@ -0,0 +1,171 @@
|
|||
|
||||
package eu.dnetlib.dhp.collection.orcid;
|
||||
|
||||
import static eu.dnetlib.dhp.utils.DHPUtils.getHadoopConfiguration;
|
||||
|
||||
import java.io.*;
|
||||
import java.net.HttpURLConnection;
|
||||
import java.net.URL;
|
||||
import java.util.ArrayList;
|
||||
import java.util.List;
|
||||
import java.util.Objects;
|
||||
import java.util.concurrent.ArrayBlockingQueue;
|
||||
import java.util.concurrent.BlockingQueue;
|
||||
|
||||
import org.apache.commons.compress.archivers.tar.TarArchiveEntry;
|
||||
import org.apache.commons.compress.archivers.tar.TarArchiveInputStream;
|
||||
import org.apache.commons.compress.compressors.gzip.GzipCompressorInputStream;
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.commons.lang3.StringUtils;
|
||||
import org.apache.hadoop.fs.FSDataInputStream;
|
||||
import org.apache.hadoop.fs.FSDataOutputStream;
|
||||
import org.apache.hadoop.fs.FileSystem;
|
||||
import org.apache.hadoop.fs.Path;
|
||||
import org.apache.hadoop.io.SequenceFile;
|
||||
import org.apache.hadoop.io.Text;
|
||||
import org.apache.spark.sql.SparkSession;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
|
||||
import eu.dnetlib.dhp.common.collection.HttpClientParams;
|
||||
|
||||
public class OrcidGetUpdatesFile {
|
||||
|
||||
private static Logger log = LoggerFactory.getLogger(OrcidGetUpdatesFile.class);
|
||||
|
||||
public static void main(String[] args) throws Exception {
|
||||
|
||||
ArgumentApplicationParser parser = new ArgumentApplicationParser(
|
||||
IOUtils
|
||||
.toString(
|
||||
Objects
|
||||
.requireNonNull(
|
||||
OrcidGetUpdatesFile.class
|
||||
.getResourceAsStream(
|
||||
"/eu/dnetlib/dhp/collection/orcid/download_orcid_update_parameter.json")))
|
||||
|
||||
);
|
||||
parser.parseArgument(args);
|
||||
|
||||
final String namenode = parser.get("namenode");
|
||||
log.info("got variable namenode: {}", namenode);
|
||||
|
||||
final String master = parser.get("master");
|
||||
log.info("got variable master: {}", master);
|
||||
|
||||
final String targetPath = parser.get("targetPath");
|
||||
log.info("got variable targetPath: {}", targetPath);
|
||||
|
||||
final String apiURL = parser.get("apiURL");
|
||||
log.info("got variable apiURL: {}", apiURL);
|
||||
|
||||
final String accessToken = parser.get("accessToken");
|
||||
log.info("got variable accessToken: {}", accessToken);
|
||||
|
||||
final String graphPath = parser.get("graphPath");
|
||||
log.info("got variable graphPath: {}", graphPath);
|
||||
|
||||
final SparkSession spark = SparkSession
|
||||
.builder()
|
||||
.appName(OrcidGetUpdatesFile.class.getName())
|
||||
.master(master)
|
||||
.getOrCreate();
|
||||
|
||||
final String latestDate = spark
|
||||
.read()
|
||||
.load(graphPath + "/Authors")
|
||||
.selectExpr("max(lastModifiedDate)")
|
||||
.first()
|
||||
.getString(0);
|
||||
|
||||
log.info("latest date is {}", latestDate);
|
||||
|
||||
final FileSystem fileSystem = FileSystem.get(getHadoopConfiguration(namenode));
|
||||
|
||||
new OrcidGetUpdatesFile().readTar(fileSystem, accessToken, apiURL, targetPath, latestDate);
|
||||
|
||||
}
|
||||
|
||||
private SequenceFile.Writer createFile(Path aPath, FileSystem fileSystem) throws IOException {
|
||||
return SequenceFile
|
||||
.createWriter(
|
||||
fileSystem.getConf(),
|
||||
SequenceFile.Writer.file(aPath),
|
||||
SequenceFile.Writer.keyClass(Text.class),
|
||||
SequenceFile.Writer.valueClass(Text.class));
|
||||
}
|
||||
|
||||
private ORCIDWorker createWorker(final String id, final String targetPath, final BlockingQueue<String> queue,
|
||||
final String accessToken, FileSystem fileSystem) throws Exception {
|
||||
return ORCIDWorker
|
||||
.builder()
|
||||
.withId(id)
|
||||
.withEmployments(createFile(new Path(String.format("%s/employments_%s", targetPath, id)), fileSystem))
|
||||
.withSummary(createFile(new Path(String.format("%s/summary_%s", targetPath, id)), fileSystem))
|
||||
.withWorks(createFile(new Path(String.format("%s/works_%s", targetPath, id)), fileSystem))
|
||||
.withAccessToken(accessToken)
|
||||
.withBlockingQueue(queue)
|
||||
.build();
|
||||
}
|
||||
|
||||
public void readTar(FileSystem fileSystem, final String accessToken, final String apiURL, final String targetPath,
|
||||
final String startDate) throws Exception {
|
||||
final HttpURLConnection urlConn = (HttpURLConnection) new URL(apiURL).openConnection();
|
||||
final HttpClientParams clientParams = new HttpClientParams();
|
||||
urlConn.setInstanceFollowRedirects(false);
|
||||
urlConn.setReadTimeout(clientParams.getReadTimeOut() * 1000);
|
||||
urlConn.setConnectTimeout(clientParams.getConnectTimeOut() * 1000);
|
||||
if (urlConn.getResponseCode() > 199 && urlConn.getResponseCode() < 300) {
|
||||
InputStream input = urlConn.getInputStream();
|
||||
|
||||
Path hdfsWritePath = new Path("/tmp/orcid_updates.tar.gz");
|
||||
final FSDataOutputStream fsDataOutputStream = fileSystem.create(hdfsWritePath, true);
|
||||
IOUtils.copy(input, fsDataOutputStream);
|
||||
fsDataOutputStream.flush();
|
||||
fsDataOutputStream.close();
|
||||
FSDataInputStream updateFile = fileSystem.open(hdfsWritePath);
|
||||
TarArchiveInputStream tais = new TarArchiveInputStream(new GzipCompressorInputStream(
|
||||
new BufferedInputStream(
|
||||
updateFile.getWrappedStream())));
|
||||
TarArchiveEntry entry;
|
||||
|
||||
BlockingQueue<String> queue = new ArrayBlockingQueue<String>(3000);
|
||||
final List<ORCIDWorker> workers = new ArrayList<>();
|
||||
for (int i = 0; i < 22; i++) {
|
||||
workers.add(createWorker("" + i, targetPath, queue, accessToken, fileSystem));
|
||||
}
|
||||
workers.forEach(Thread::start);
|
||||
|
||||
while ((entry = tais.getNextTarEntry()) != null) {
|
||||
|
||||
if (entry.isFile()) {
|
||||
|
||||
BufferedReader br = new BufferedReader(new InputStreamReader(tais));
|
||||
System.out.println(br.readLine());
|
||||
br
|
||||
.lines()
|
||||
.map(l -> l.split(","))
|
||||
.filter(s -> StringUtils.compare(s[3].substring(0, 10), startDate) > 0)
|
||||
.map(s -> s[0])
|
||||
.forEach(s -> {
|
||||
try {
|
||||
queue.put(s);
|
||||
} catch (InterruptedException e) {
|
||||
throw new RuntimeException(e);
|
||||
}
|
||||
});
|
||||
|
||||
}
|
||||
}
|
||||
|
||||
for (int i = 0; i < 22; i++) {
|
||||
queue.put(ORCIDWorker.JOB_COMPLETE);
|
||||
}
|
||||
for (ORCIDWorker worker : workers) {
|
||||
worker.join();
|
||||
}
|
||||
}
|
||||
|
||||
}
|
||||
}
|
|
@ -1,11 +1,15 @@
|
|||
|
||||
package eu.dnetlib.dhp.collection.orcid;
|
||||
|
||||
import java.util.Arrays;
|
||||
import java.util.Collections;
|
||||
import java.util.List;
|
||||
import java.util.*;
|
||||
import java.util.stream.Collectors;
|
||||
|
||||
import org.apache.commons.lang3.StringUtils;
|
||||
import org.dom4j.Document;
|
||||
import org.dom4j.DocumentFactory;
|
||||
import org.dom4j.DocumentHelper;
|
||||
import org.dom4j.Node;
|
||||
import org.jetbrains.annotations.NotNull;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
|
@ -40,8 +44,8 @@ public class OrcidParser {
|
|||
private static final String NS_ERROR = "error";
|
||||
private static final String NS_HISTORY = "history";
|
||||
private static final String NS_HISTORY_URL = "http://www.orcid.org/ns/history";
|
||||
private static final String NS_BULK_URL = "http://www.orcid.org/ns/bulk";
|
||||
private static final String NS_BULK = "bulk";
|
||||
private static final String NS_EMPLOYMENT = "employment";
|
||||
private static final String NS_EMPLOYMENT_URL = "http://www.orcid.org/ns/employment";
|
||||
private static final String NS_EXTERNAL = "external-identifier";
|
||||
private static final String NS_EXTERNAL_URL = "http://www.orcid.org/ns/external-identifier";
|
||||
|
||||
|
@ -61,6 +65,7 @@ public class OrcidParser {
|
|||
ap.declareXPathNameSpace(NS_WORK, NS_WORK_URL);
|
||||
ap.declareXPathNameSpace(NS_EXTERNAL, NS_EXTERNAL_URL);
|
||||
ap.declareXPathNameSpace(NS_ACTIVITIES, NS_ACTIVITIES_URL);
|
||||
ap.declareXPathNameSpace(NS_EMPLOYMENT, NS_EMPLOYMENT_URL);
|
||||
}
|
||||
|
||||
public Author parseSummary(final String xml) {
|
||||
|
@ -70,13 +75,15 @@ public class OrcidParser {
|
|||
generateParsedDocument(xml);
|
||||
List<VtdUtilityParser.Node> recordNodes = VtdUtilityParser
|
||||
.getTextValuesWithAttributes(
|
||||
ap, vn, "//record:record", Arrays.asList("path"));
|
||||
ap, vn, "//record:record", Collections.singletonList("path"));
|
||||
if (!recordNodes.isEmpty()) {
|
||||
final String oid = (recordNodes.get(0).getAttributes().get("path")).substring(1);
|
||||
author.setOrcid(oid);
|
||||
} else {
|
||||
return null;
|
||||
}
|
||||
final String ltm = VtdUtilityParser.getSingleValue(ap, vn, "//common:last-modified-date");
|
||||
author.setLastModifiedDate(ltm);
|
||||
List<VtdUtilityParser.Node> personNodes = VtdUtilityParser
|
||||
.getTextValuesWithAttributes(
|
||||
ap, vn, "//person:name", Arrays.asList("visibility"));
|
||||
|
@ -129,6 +136,64 @@ public class OrcidParser {
|
|||
}
|
||||
}
|
||||
|
||||
public List<Work> parseWorks(final String xml) {
|
||||
|
||||
try {
|
||||
String oid;
|
||||
|
||||
generateParsedDocument(xml);
|
||||
List<VtdUtilityParser.Node> workNodes = VtdUtilityParser
|
||||
.getTextValuesWithAttributes(ap, vn, "//activities:works", Arrays.asList("path", "visibility"));
|
||||
if (!workNodes.isEmpty()) {
|
||||
oid = (workNodes.get(0).getAttributes().get("path")).split("/")[1];
|
||||
|
||||
} else {
|
||||
return null;
|
||||
}
|
||||
final List<Work> works = new ArrayList<>();
|
||||
ap.selectXPath("//work:work-summary");
|
||||
|
||||
while (ap.evalXPath() != -1) {
|
||||
final Work work = new Work();
|
||||
work.setOrcid(oid);
|
||||
final AutoPilot ap1 = new AutoPilot(ap.getNav());
|
||||
ap1.selectXPath("./work:title/common:title");
|
||||
while (ap1.evalXPath() != -1) {
|
||||
int it = vn.getText();
|
||||
work.setTitle(vn.toNormalizedString(it));
|
||||
}
|
||||
ap1.selectXPath(".//common:external-id");
|
||||
while (ap1.evalXPath() != -1) {
|
||||
final Pid pid = new Pid();
|
||||
|
||||
final AutoPilot ap2 = new AutoPilot(ap1.getNav());
|
||||
|
||||
ap2.selectXPath("./common:external-id-type");
|
||||
while (ap2.evalXPath() != -1) {
|
||||
int it = vn.getText();
|
||||
pid.setSchema(vn.toNormalizedString(it));
|
||||
}
|
||||
ap2.selectXPath("./common:external-id-value");
|
||||
while (ap2.evalXPath() != -1) {
|
||||
int it = vn.getText();
|
||||
pid.setValue(vn.toNormalizedString(it));
|
||||
}
|
||||
|
||||
work.addPid(pid);
|
||||
}
|
||||
|
||||
works.add(work);
|
||||
}
|
||||
return works;
|
||||
|
||||
} catch (Throwable e) {
|
||||
log.error("Error on parsing {}", xml);
|
||||
log.error(e.getMessage());
|
||||
return null;
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
public Work parseWork(final String xml) {
|
||||
|
||||
try {
|
||||
|
@ -176,11 +241,15 @@ public class OrcidParser {
|
|||
}
|
||||
|
||||
private String extractEmploymentDate(final String xpath) throws Exception {
|
||||
return extractEmploymentDate(xpath, ap);
|
||||
}
|
||||
|
||||
ap.selectXPath(xpath);
|
||||
private String extractEmploymentDate(final String xpath, AutoPilot pp) throws Exception {
|
||||
|
||||
pp.selectXPath(xpath);
|
||||
StringBuilder sb = new StringBuilder();
|
||||
while (ap.evalXPath() != -1) {
|
||||
final AutoPilot ap1 = new AutoPilot(ap.getNav());
|
||||
while (pp.evalXPath() != -1) {
|
||||
final AutoPilot ap1 = new AutoPilot(pp.getNav());
|
||||
ap1.selectXPath("./common:year");
|
||||
while (ap1.evalXPath() != -1) {
|
||||
int it = vn.getText();
|
||||
|
@ -203,6 +272,104 @@ public class OrcidParser {
|
|||
|
||||
}
|
||||
|
||||
public List<Employment> parseEmployments(final String xml) {
|
||||
try {
|
||||
String oid;
|
||||
Map<String, String> nsContext = getNameSpaceMap();
|
||||
DocumentFactory.getInstance().setXPathNamespaceURIs(nsContext);
|
||||
Document doc = DocumentHelper.parseText(xml);
|
||||
oid = doc.valueOf("//activities:employments/@path");
|
||||
if (oid == null || StringUtils.isEmpty(oid))
|
||||
return null;
|
||||
final String orcid = oid.split("/")[1];
|
||||
|
||||
List<Node> nodes = doc.selectNodes("//employment:employment-summary");
|
||||
return nodes.stream().map(n -> {
|
||||
final Employment e = new Employment();
|
||||
e.setOrcid(orcid);
|
||||
|
||||
final String depName = n.valueOf(".//common:department-name");
|
||||
if (StringUtils.isNotBlank(depName))
|
||||
e.setDepartmentName(depName);
|
||||
final String roleTitle = n.valueOf(".//common:role-title");
|
||||
e.setRoleTitle(roleTitle);
|
||||
final String organizationName = n.valueOf(".//common:organization/common:name");
|
||||
if (StringUtils.isEmpty(e.getDepartmentName()))
|
||||
e.setDepartmentName(organizationName);
|
||||
final Pid p = new Pid();
|
||||
final String pid = n
|
||||
.valueOf(
|
||||
"./common:organization/common:disambiguated-organization/common:disambiguated-organization-identifier");
|
||||
p.setValue(pid);
|
||||
final String pidType = n
|
||||
.valueOf("./common:organization/common:disambiguated-organization/common:disambiguation-source");
|
||||
p.setSchema(pidType);
|
||||
e.setAffiliationId(p);
|
||||
|
||||
final StringBuilder aDate = new StringBuilder();
|
||||
final String sy = n.valueOf("./common:start-date/common:year");
|
||||
if (StringUtils.isNotBlank(sy)) {
|
||||
aDate.append(sy);
|
||||
final String sm = n.valueOf("./common:start-date/common:month");
|
||||
final String sd = n.valueOf("./common:start-date/common:day");
|
||||
aDate.append("-");
|
||||
if (StringUtils.isNotBlank(sm))
|
||||
aDate.append(sm);
|
||||
else
|
||||
aDate.append("01");
|
||||
aDate.append("-");
|
||||
if (StringUtils.isNotBlank(sd))
|
||||
aDate.append(sd);
|
||||
else
|
||||
aDate.append("01");
|
||||
e.setEndDate(aDate.toString());
|
||||
}
|
||||
|
||||
final String ey = n.valueOf("./common:end-date/common:year");
|
||||
if (StringUtils.isNotBlank(ey)) {
|
||||
aDate.append(ey);
|
||||
final String em = n.valueOf("./common:end-date/common:month");
|
||||
final String ed = n.valueOf("./common:end-date/common:day");
|
||||
aDate.append("-");
|
||||
if (StringUtils.isNotBlank(em))
|
||||
aDate.append(em);
|
||||
else
|
||||
aDate.append("01");
|
||||
aDate.append("-");
|
||||
if (StringUtils.isNotBlank(ed))
|
||||
aDate.append(ed);
|
||||
else
|
||||
aDate.append("01");
|
||||
e.setEndDate(aDate.toString());
|
||||
}
|
||||
|
||||
return e;
|
||||
|
||||
}).collect(Collectors.toList());
|
||||
} catch (Throwable e) {
|
||||
log.error("Error on parsing {}", xml);
|
||||
log.error(e.getMessage());
|
||||
return null;
|
||||
}
|
||||
}
|
||||
|
||||
@NotNull
|
||||
private static Map<String, String> getNameSpaceMap() {
|
||||
Map<String, String> nsContext = new HashMap<>();
|
||||
nsContext.put(NS_COMMON, NS_COMMON_URL);
|
||||
nsContext.put(NS_PERSON, NS_PERSON_URL);
|
||||
nsContext.put(NS_DETAILS, NS_DETAILS_URL);
|
||||
nsContext.put(NS_OTHER, NS_OTHER_URL);
|
||||
nsContext.put(NS_RECORD, NS_RECORD_URL);
|
||||
nsContext.put(NS_ERROR, NS_ERROR_URL);
|
||||
nsContext.put(NS_HISTORY, NS_HISTORY_URL);
|
||||
nsContext.put(NS_WORK, NS_WORK_URL);
|
||||
nsContext.put(NS_EXTERNAL, NS_EXTERNAL_URL);
|
||||
nsContext.put(NS_ACTIVITIES, NS_ACTIVITIES_URL);
|
||||
nsContext.put(NS_EMPLOYMENT, NS_EMPLOYMENT_URL);
|
||||
return nsContext;
|
||||
}
|
||||
|
||||
public Employment parseEmployment(final String xml) {
|
||||
try {
|
||||
final Employment employment = new Employment();
|
||||
|
|
|
@ -18,6 +18,8 @@ public class Author extends ORCIDItem {
|
|||
|
||||
private String biography;
|
||||
|
||||
private String lastModifiedDate;
|
||||
|
||||
public String getBiography() {
|
||||
return biography;
|
||||
}
|
||||
|
@ -74,6 +76,14 @@ public class Author extends ORCIDItem {
|
|||
this.otherPids = otherPids;
|
||||
}
|
||||
|
||||
public String getLastModifiedDate() {
|
||||
return lastModifiedDate;
|
||||
}
|
||||
|
||||
public void setLastModifiedDate(String lastModifiedDate) {
|
||||
this.lastModifiedDate = lastModifiedDate;
|
||||
}
|
||||
|
||||
public void addOtherPid(final Pid pid) {
|
||||
|
||||
if (otherPids == null)
|
||||
|
|
|
@ -52,8 +52,6 @@ public class RestIterator implements Iterator<String> {
|
|||
|
||||
private final String BASIC = "basic";
|
||||
|
||||
private final JsonUtils jsonUtils;
|
||||
|
||||
private final String baseUrl;
|
||||
private final String resumptionType;
|
||||
private final String resumptionParam;
|
||||
|
@ -106,7 +104,6 @@ public class RestIterator implements Iterator<String> {
|
|||
final String resultOutputFormat) {
|
||||
|
||||
this.clientParams = clientParams;
|
||||
this.jsonUtils = new JsonUtils();
|
||||
this.baseUrl = baseUrl;
|
||||
this.resumptionType = resumptionType;
|
||||
this.resumptionParam = resumptionParam;
|
||||
|
@ -126,6 +123,7 @@ public class RestIterator implements Iterator<String> {
|
|||
} catch (Exception e) {
|
||||
throw new IllegalStateException("xml transformation init failed: " + e.getMessage());
|
||||
}
|
||||
|
||||
initQueue();
|
||||
}
|
||||
|
||||
|
@ -190,7 +188,7 @@ public class RestIterator implements Iterator<String> {
|
|||
String resultJson;
|
||||
String resultXml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>";
|
||||
String nextQuery = "";
|
||||
String emptyXml = resultXml + "<" + JsonUtils.wrapName + "></" + JsonUtils.wrapName + ">";
|
||||
String emptyXml = resultXml + "<" + JsonUtils.XML_WRAP_TAG + "></" + JsonUtils.XML_WRAP_TAG + ">";
|
||||
Node resultNode = null;
|
||||
NodeList nodeList = null;
|
||||
String qUrlArgument = "";
|
||||
|
@ -231,7 +229,7 @@ public class RestIterator implements Iterator<String> {
|
|||
resultStream = theHttpInputStream;
|
||||
if ("json".equals(resultOutputFormat)) {
|
||||
resultJson = IOUtils.toString(resultStream, StandardCharsets.UTF_8);
|
||||
resultXml = jsonUtils.convertToXML(resultJson);
|
||||
resultXml = JsonUtils.convertToXML(resultJson);
|
||||
resultStream = IOUtils.toInputStream(resultXml, UTF_8);
|
||||
}
|
||||
|
||||
|
|
|
@ -3,82 +3,142 @@ package eu.dnetlib.dhp.collection.plugin.utils;
|
|||
|
||||
import org.apache.commons.logging.Log;
|
||||
import org.apache.commons.logging.LogFactory;
|
||||
import org.json.JSONArray;
|
||||
import org.json.JSONObject;
|
||||
|
||||
public class JsonUtils {
|
||||
public static final String XML_WRAP_TAG = "recordWrap";
|
||||
private static final String XML_HEADER = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>";
|
||||
private static final String INVALID_XMLTAG_CHARS = "!\"#$%&'()*+,/;<=>?@[\\]^`{|}~,";
|
||||
|
||||
private static final Log log = LogFactory.getLog(JsonUtils.class);
|
||||
|
||||
public static final String wrapName = "recordWrap";
|
||||
|
||||
/**
|
||||
* convert in JSON-KeyName 'whitespace(s)' to '_' and '/' to '_', '(' and ')' to ''
|
||||
* cleanup in JSON-KeyName
|
||||
* check W3C XML syntax: https://www.w3.org/TR/2006/REC-xml11-20060816/#sec-starttags for valid tag names
|
||||
* and work-around for the JSON to XML converting of org.json.XML-package.
|
||||
*
|
||||
* known bugs: doesn't prevent "key name":" ["sexy name",": penari","erotic dance"],
|
||||
*
|
||||
* @param jsonInput
|
||||
* @return convertedJsonKeynameOutput
|
||||
* @param input
|
||||
* @return converted json object
|
||||
*/
|
||||
public String syntaxConvertJsonKeyNames(String jsonInput) {
|
||||
|
||||
log.trace("before convertJsonKeyNames: " + jsonInput);
|
||||
// pre-clean json - rid spaces of element names (misinterpreted as elements with attributes in xml)
|
||||
// replace ' 's in JSON Namens with '_'
|
||||
while (jsonInput.matches(".*\"([^\"]*)\\s+([^\"]*)\":.*")) {
|
||||
jsonInput = jsonInput.replaceAll("\"([^\"]*)\\s+([^\"]*)\":", "\"$1_$2\":");
|
||||
public static JSONObject cleanJsonObject(final JSONObject input) {
|
||||
if (null == input) {
|
||||
return null;
|
||||
}
|
||||
|
||||
// replace forward-slash (sign '/' ) in JSON Names with '_'
|
||||
while (jsonInput.matches(".*\"([^\"]*)/([^\"]*)\":.*")) {
|
||||
jsonInput = jsonInput.replaceAll("\"([^\"]*)/([^\"]*)\":", "\"$1_$2\":");
|
||||
JSONObject result = new JSONObject();
|
||||
|
||||
for (String key : input.keySet()) {
|
||||
Object value = input.opt(key);
|
||||
if (value != null) {
|
||||
result.put(cleanKey(key), cleanValue(value));
|
||||
}
|
||||
}
|
||||
|
||||
// replace '(' in JSON Names with ''
|
||||
while (jsonInput.matches(".*\"([^\"]*)[(]([^\"]*)\":.*")) {
|
||||
jsonInput = jsonInput.replaceAll("\"([^\"]*)[(]([^\"]*)\":", "\"$1$2\":");
|
||||
}
|
||||
|
||||
// replace ')' in JSON Names with ''
|
||||
while (jsonInput.matches(".*\"([^\"]*)[)]([^\"]*)\":.*")) {
|
||||
jsonInput = jsonInput.replaceAll("\"([^\"]*)[)]([^\"]*)\":", "\"$1$2\":");
|
||||
}
|
||||
|
||||
// add prefix of startNumbers in JSON Keynames with 'n_'
|
||||
while (jsonInput.matches(".*\"([^\"][0-9])([^\"]*)\":.*")) {
|
||||
jsonInput = jsonInput.replaceAll("\"([^\"][0-9])([^\"]*)\":", "\"n_$1$2\":");
|
||||
}
|
||||
// add prefix of only numbers in JSON Keynames with 'm_'
|
||||
while (jsonInput.matches(".*\"([0-9]+)\":.*")) {
|
||||
jsonInput = jsonInput.replaceAll("\"([0-9]+)\":", "\"m_$1\":");
|
||||
}
|
||||
|
||||
// replace ':' between number like '2018-08-28T11:05:00Z' in JSON keynames with ''
|
||||
while (jsonInput.matches(".*\"([^\"]*[0-9]):([0-9][^\"]*)\":.*")) {
|
||||
jsonInput = jsonInput.replaceAll("\"([^\"]*[0-9]):([0-9][^\"]*)\":", "\"$1$2\":");
|
||||
}
|
||||
|
||||
// replace ',' in JSON Keynames with '.' to prevent , in xml tagnames.
|
||||
// while (jsonInput.matches(".*\"([^\"]*),([^\"]*)\":.*")) {
|
||||
// jsonInput = jsonInput.replaceAll("\"([^\"]*),([^\"]*)\":", "\"$1.$2\":");
|
||||
// }
|
||||
|
||||
// replace '=' in JSON Keynames with '-'
|
||||
while (jsonInput.matches(".*\"([^\"]*)=([^\"]*)\":.*")) {
|
||||
jsonInput = jsonInput.replaceAll("\"([^\"]*)=([^\"]*)\":", "\"$1-$2\":");
|
||||
}
|
||||
|
||||
log.trace("after syntaxConvertJsonKeyNames: " + jsonInput);
|
||||
return jsonInput;
|
||||
return result;
|
||||
}
|
||||
|
||||
public String convertToXML(final String jsonRecord) {
|
||||
String resultXml = "<?xml version=\"1.0\" encoding=\"UTF-8\"?>";
|
||||
org.json.JSONObject jsonObject = new org.json.JSONObject(syntaxConvertJsonKeyNames(jsonRecord));
|
||||
resultXml += org.json.XML.toString(jsonObject, wrapName); // wrap xml in single root element
|
||||
log.trace("before inputStream: " + resultXml);
|
||||
resultXml = XmlCleaner.cleanAllEntities(resultXml);
|
||||
log.trace("after cleaning: " + resultXml);
|
||||
return resultXml;
|
||||
private static Object cleanValue(Object object) {
|
||||
if (object instanceof JSONObject) {
|
||||
return cleanJsonObject((JSONObject) object);
|
||||
} else if (object instanceof JSONArray) {
|
||||
JSONArray array = (JSONArray) object;
|
||||
JSONArray res = new JSONArray();
|
||||
|
||||
for (int i = array.length() - 1; i >= 0; i--) {
|
||||
res.put(i, cleanValue(array.opt(i)));
|
||||
}
|
||||
return res;
|
||||
} else if (object instanceof String) {
|
||||
String value = (String) object;
|
||||
|
||||
// XML 1.0 Allowed characters
|
||||
// Char ::= #x9 | #xA | #xD | [#x20-#xD7FF] | [#xE000-#xFFFD] | [#x10000-#x10FFFF]
|
||||
|
||||
return value
|
||||
.codePoints()
|
||||
.filter(
|
||||
cp -> cp == 0x9 || cp == 0xA || cp == 0xD || (cp >= 0x20 && cp <= 0xD7FF)
|
||||
|| (cp >= 0xE000 && cp <= 0xFFFD)
|
||||
|| (cp >= 0x10000 && cp <= 0x10FFFF))
|
||||
.collect(
|
||||
StringBuilder::new,
|
||||
StringBuilder::appendCodePoint,
|
||||
StringBuilder::append)
|
||||
.toString();
|
||||
}
|
||||
|
||||
return object;
|
||||
}
|
||||
|
||||
private static String cleanKey(String key) {
|
||||
if (key == null || key.isEmpty()) {
|
||||
return key;
|
||||
}
|
||||
|
||||
// xml tag cannot begin with "-", ".", or a numeric digit.
|
||||
switch (key.charAt(0)) {
|
||||
case '-':
|
||||
case '.':
|
||||
key = "_" + key.substring(1);
|
||||
break;
|
||||
}
|
||||
|
||||
if (Character.isDigit(key.charAt(0))) {
|
||||
if (key.matches("^[0-9]+$")) {
|
||||
// add prefix of only numbers in JSON Keynames with 'm_'
|
||||
key = "m_" + key;
|
||||
} else {
|
||||
// add prefix of startNumbers in JSON Keynames with 'n_'
|
||||
key = "n_" + key;
|
||||
}
|
||||
}
|
||||
|
||||
StringBuilder res = new StringBuilder(key.length());
|
||||
for (int i = 0; i < key.length(); i++) {
|
||||
char c = key.charAt(i);
|
||||
|
||||
// sequence of whitespaces are rendered as a single '_'
|
||||
if (Character.isWhitespace(c)) {
|
||||
while (i + 1 < key.length() && Character.isWhitespace(key.charAt(i + 1))) {
|
||||
i++;
|
||||
}
|
||||
res.append('_');
|
||||
}
|
||||
// remove invalid chars for xml tags with the expception of '=' and '/'
|
||||
else if (INVALID_XMLTAG_CHARS.indexOf(c) >= 0) {
|
||||
switch (c) {
|
||||
case '=':
|
||||
res.append('-');
|
||||
break;
|
||||
case '/':
|
||||
res.append('_');
|
||||
break;
|
||||
default:
|
||||
break;
|
||||
}
|
||||
// nothing
|
||||
}
|
||||
// all other chars are kept
|
||||
else {
|
||||
res.append(c);
|
||||
}
|
||||
}
|
||||
|
||||
return res.toString();
|
||||
}
|
||||
|
||||
static public String convertToXML(final String jsonRecord) {
|
||||
if (log.isTraceEnabled()) {
|
||||
log.trace("input json: " + jsonRecord);
|
||||
}
|
||||
|
||||
JSONObject jsonObject = cleanJsonObject(new org.json.JSONObject(jsonRecord));
|
||||
String res = XML_HEADER + org.json.XML.toString(jsonObject, XML_WRAP_TAG); // wrap xml in single root element
|
||||
|
||||
if (log.isTraceEnabled()) {
|
||||
log.trace("outout xml: " + res);
|
||||
}
|
||||
return res;
|
||||
}
|
||||
}
|
||||
|
|
|
@ -48,7 +48,7 @@ public class XSLTTransformationFunction implements MapFunction<MetadataRecord, M
|
|||
@Override
|
||||
public MetadataRecord call(MetadataRecord value) {
|
||||
aggregationCounter.getTotalItems().add(1);
|
||||
try {
|
||||
|
||||
Processor processor = new Processor(false);
|
||||
|
||||
processor.registerExtensionFunction(cleanFunction);
|
||||
|
@ -60,11 +60,18 @@ public class XSLTTransformationFunction implements MapFunction<MetadataRecord, M
|
|||
comp.setParameter(datasourceIDParam, new XdmAtomicValue(value.getProvenance().getDatasourceId()));
|
||||
QName datasourceNameParam = new QName(DATASOURCE_NAME_PARAM);
|
||||
comp.setParameter(datasourceNameParam, new XdmAtomicValue(value.getProvenance().getDatasourceName()));
|
||||
XsltExecutable xslt = comp
|
||||
.compile(new StreamSource(IOUtils.toInputStream(transformationRule, StandardCharsets.UTF_8)));
|
||||
XdmNode source = processor
|
||||
.newDocumentBuilder()
|
||||
.build(new StreamSource(IOUtils.toInputStream(value.getBody(), StandardCharsets.UTF_8)));
|
||||
XsltExecutable xslt;
|
||||
XdmNode source;
|
||||
try {
|
||||
xslt = comp
|
||||
.compile(new StreamSource(IOUtils.toInputStream(transformationRule, StandardCharsets.UTF_8)));
|
||||
source = processor
|
||||
.newDocumentBuilder()
|
||||
.build(new StreamSource(IOUtils.toInputStream(value.getBody(), StandardCharsets.UTF_8)));
|
||||
} catch (Throwable e) {
|
||||
throw new RuntimeException("Error on parsing xslt", e);
|
||||
}
|
||||
try {
|
||||
XsltTransformer trans = xslt.load();
|
||||
trans.setInitialContextNode(source);
|
||||
final StringWriter output = new StringWriter();
|
||||
|
|
|
@ -17,6 +17,12 @@
|
|||
"paramDescription": "the path to get the input data from Pubmed",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "oip",
|
||||
"paramLongName": "openapcInputPath",
|
||||
"paramDescription": "the path to get the input data from OpenAPC",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "o",
|
||||
"paramLongName": "outputPath",
|
||||
|
|
|
@ -31,6 +31,7 @@ spark2SqlQueryExecutionListeners=com.cloudera.spark.lineage.NavigatorQueryListen
|
|||
# The following is needed as a property of a workflow
|
||||
oozie.wf.application.path=${oozieTopWfApplicationPath}
|
||||
|
||||
crossrefInputPath=/data/bip-affiliations/data.json
|
||||
crossrefInputPath=/data/bip-affiliations/crossref-data.json
|
||||
pubmedInputPath=/data/bip-affiliations/pubmed-data.json
|
||||
openapcInputPath=/data/bip-affiliations/openapc-data.json
|
||||
outputPath=/tmp/crossref-affiliations-output-v5
|
||||
|
|
|
@ -9,6 +9,10 @@
|
|||
<name>pubmedInputPath</name>
|
||||
<description>the path where to find the inferred affiliation relations from Pubmed</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>openapcInputPath</name>
|
||||
<description>the path where to find the inferred affiliation relations from OpenAPC</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>outputPath</name>
|
||||
<description>the path where to store the actionset</description>
|
||||
|
@ -102,6 +106,7 @@
|
|||
</spark-opts>
|
||||
<arg>--crossrefInputPath</arg><arg>${crossrefInputPath}</arg>
|
||||
<arg>--pubmedInputPath</arg><arg>${pubmedInputPath}</arg>
|
||||
<arg>--openapcInputPath</arg><arg>${openapcInputPath}</arg>
|
||||
<arg>--outputPath</arg><arg>${outputPath}</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
|
|
|
@ -16,5 +16,10 @@
|
|||
"paramLongName": "outputPath",
|
||||
"paramDescription": "the path of the new ActionSet",
|
||||
"paramRequired": true
|
||||
}
|
||||
}, {
|
||||
"paramName": "fd",
|
||||
"paramLongName": "distributeDoi",
|
||||
"paramDescription": "the path of the new ActionSet",
|
||||
"paramRequired": false
|
||||
}
|
||||
]
|
|
@ -0,0 +1,20 @@
|
|||
[
|
||||
{
|
||||
"paramName": "sp",
|
||||
"paramLongName": "sourcePath",
|
||||
"paramDescription": "the zipped opencitations file",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "op",
|
||||
"paramLongName": "outputPath",
|
||||
"paramDescription": "the working path",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "issm",
|
||||
"paramLongName": "isSparkSessionManaged",
|
||||
"paramDescription": "the hdfs name node",
|
||||
"paramRequired": false
|
||||
}
|
||||
]
|
|
@ -0,0 +1,30 @@
|
|||
<configuration>
|
||||
<property>
|
||||
<name>jobTracker</name>
|
||||
<value>yarnRM</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>nameNode</name>
|
||||
<value>hdfs://nameservice1</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozie.use.system.libpath</name>
|
||||
<value>true</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveMetastoreUris</name>
|
||||
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveJdbcUrl</name>
|
||||
<value>jdbc:hive2://iis-cdh5-test-m3.ocean.icm.edu.pl:10000</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveDbName</name>
|
||||
<value>openaire</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozie.launcher.mapreduce.user.classpath.first</name>
|
||||
<value>true</value>
|
||||
</property>
|
||||
</configuration>
|
|
@ -0,0 +1,153 @@
|
|||
|
||||
<workflow-app name="FOS no doi" xmlns="uri:oozie:workflow:0.5">
|
||||
<parameters>
|
||||
<property>
|
||||
<name>fosPath</name>
|
||||
<description>the input path of the resources to be extended</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>outputPath</name>
|
||||
<description>the path where to store the actionset</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkDriverMemory</name>
|
||||
<description>memory for driver process</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkExecutorMemory</name>
|
||||
<description>memory for individual executor</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkExecutorCores</name>
|
||||
<description>number of cores used by single executor</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozieActionShareLibForSpark2</name>
|
||||
<description>oozie action sharelib for spark 2.*</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2ExtraListeners</name>
|
||||
<value>com.cloudera.spark.lineage.NavigatorAppListener</value>
|
||||
<description>spark 2.* extra listeners classname</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2SqlQueryExecutionListeners</name>
|
||||
<value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
|
||||
<description>spark 2.* sql query execution listeners classname</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2YarnHistoryServerAddress</name>
|
||||
<description>spark 2.* yarn history server address</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2EventLogDir</name>
|
||||
<description>spark 2.* event log dir location</description>
|
||||
</property>
|
||||
</parameters>
|
||||
|
||||
<global>
|
||||
<job-tracker>${jobTracker}</job-tracker>
|
||||
<name-node>${nameNode}</name-node>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>mapreduce.job.queuename</name>
|
||||
<value>${queueName}</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozie.launcher.mapred.job.queue.name</name>
|
||||
<value>${oozieLauncherQueueName}</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozie.action.sharelib.for.spark</name>
|
||||
<value>${oozieActionShareLibForSpark2}</value>
|
||||
</property>
|
||||
|
||||
</configuration>
|
||||
</global>
|
||||
<start to="getFOS"/>
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
||||
|
||||
|
||||
<action name="getFOS">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Gets Data from FOS csv file</name>
|
||||
<class>eu.dnetlib.dhp.actionmanager.createunresolvedentities.GetFOSSparkJob</class>
|
||||
<jar>dhp-aggregation-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--executor-cores=${sparkExecutorCores}
|
||||
--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.sql.warehouse.dir=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${fosPath}</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/input/fos</arg>
|
||||
<arg>--delimiter</arg><arg>${delimiter}</arg>
|
||||
</spark>
|
||||
<ok to="prepareFos"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
<action name="prepareFos">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Produces the results from FOS</name>
|
||||
<class>eu.dnetlib.dhp.actionmanager.createunresolvedentities.PrepareFOSSparkJob</class>
|
||||
<jar>dhp-aggregation-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--executor-cores=${sparkExecutorCores}
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${workingDir}/input/fos</arg>
|
||||
<arg>--outputPath</arg><arg>${workingDir}/prepared</arg>
|
||||
<arg>--distributeDoi</arg><arg>false</arg>
|
||||
</spark>
|
||||
<ok to="produceActionSet"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
|
||||
<action name="produceActionSet">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Save the action set grouping results with the same id</name>
|
||||
<class>eu.dnetlib.dhp.actionmanager.fosnodoi.CreateActionSetSparkJob</class>
|
||||
<jar>dhp-aggregation-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--executor-cores=${sparkExecutorCores}
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${workingDir}/prepared/fos</arg>
|
||||
<arg>--outputPath</arg><arg>${outputPath}</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<end name="End"/>
|
||||
</workflow-app>
|
|
@ -0,0 +1,20 @@
|
|||
[
|
||||
{
|
||||
"paramName": "ip",
|
||||
"paramLongName": "inputPath",
|
||||
"paramDescription": "the zipped opencitations file",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "op",
|
||||
"paramLongName": "outputPath",
|
||||
"paramDescription": "the working path",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "issm",
|
||||
"paramLongName": "isSparkSessionManaged",
|
||||
"paramDescription": "the hdfs name node",
|
||||
"paramRequired": false
|
||||
}
|
||||
]
|
|
@ -0,0 +1,30 @@
|
|||
[
|
||||
|
||||
{
|
||||
"paramName": "issm",
|
||||
"paramLongName": "isSparkSessionManaged",
|
||||
"paramDescription": "the hdfs name node",
|
||||
"paramRequired": false
|
||||
},
|
||||
{
|
||||
"paramName": "d",
|
||||
"paramLongName": "delimiter",
|
||||
"paramDescription": "the hdfs name node",
|
||||
"paramRequired": false
|
||||
},
|
||||
{
|
||||
"paramName": "op",
|
||||
"paramLongName": "outputPath",
|
||||
"paramDescription": "the hdfs name node",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "if",
|
||||
"paramLongName": "inputFile",
|
||||
"paramDescription": "the hdfs name node",
|
||||
"paramRequired": true
|
||||
}
|
||||
]
|
||||
|
||||
|
||||
|
|
@ -0,0 +1,58 @@
|
|||
<configuration>
|
||||
<property>
|
||||
<name>jobTracker</name>
|
||||
<value>yarnRM</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>nameNode</name>
|
||||
<value>hdfs://nameservice1</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozie.use.system.libpath</name>
|
||||
<value>true</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozie.action.sharelib.for.spark</name>
|
||||
<value>spark2</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>hive_metastore_uris</name>
|
||||
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2YarnHistoryServerAddress</name>
|
||||
<value>http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2ExtraListeners</name>
|
||||
<value>com.cloudera.spark.lineage.NavigatorAppListener</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2SqlQueryExecutionListeners</name>
|
||||
<value>com.cloudera.spark.lineage.NavigatorQueryListener</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozie.launcher.mapreduce.user.classpath.first</name>
|
||||
<value>true</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkExecutorNumber</name>
|
||||
<value>4</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>spark2EventLogDir</name>
|
||||
<value>/user/spark/spark2ApplicationHistory</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkDriverMemory</name>
|
||||
<value>15G</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkExecutorMemory</name>
|
||||
<value>6G</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkExecutorCores</name>
|
||||
<value>1</value>
|
||||
</property>
|
||||
</configuration>
|
|
@ -0,0 +1,2 @@
|
|||
#!/bin/bash
|
||||
curl -L $1 | hdfs dfs -put - $2
|
|
@ -0,0 +1,82 @@
|
|||
<workflow-app name="Transfomative Agreement Integration" xmlns="uri:oozie:workflow:0.5">
|
||||
|
||||
<global>
|
||||
<job-tracker>${jobTracker}</job-tracker>
|
||||
<name-node>${nameNode}</name-node>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>mapreduce.job.queuename</name>
|
||||
<value>${queueName}</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozie.launcher.mapred.job.queue.name</name>
|
||||
<value>${oozieLauncherQueueName}</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozie.action.sharelib.for.spark</name>
|
||||
<value>${oozieActionShareLibForSpark2}</value>
|
||||
</property>
|
||||
|
||||
</configuration>
|
||||
</global>
|
||||
|
||||
<start to="resume_from"/>
|
||||
|
||||
<decision name="resume_from">
|
||||
<switch>
|
||||
<case to="download">${wf:conf('resumeFrom') eq 'DownloadDump'}</case>
|
||||
<default to="create_actionset"/> <!-- first action to be done when downloadDump is to be performed -->
|
||||
</switch>
|
||||
</decision>
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
||||
<action name="download">
|
||||
<shell xmlns="uri:oozie:shell-action:0.2">
|
||||
<job-tracker>${jobTracker}</job-tracker>
|
||||
<name-node>${nameNode}</name-node>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>mapred.job.queue.name</name>
|
||||
<value>${queueName}</value>
|
||||
</property>
|
||||
</configuration>
|
||||
<exec>download.sh</exec>
|
||||
<argument>${inputFile}</argument>
|
||||
<argument>${workingDir}/transformativeagreement/transformativeAgreement.json</argument>
|
||||
<env-var>HADOOP_USER_NAME=${wf:user()}</env-var>
|
||||
<file>download.sh</file>
|
||||
<capture-output/>
|
||||
</shell>
|
||||
<ok to="create_actionset"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
<action name="create_actionset">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Produces the AS for the Transformative Agreement</name>
|
||||
<class>eu.dnetlib.dhp.actionmanager.transformativeagreement.CreateActionSetSparkJob</class>
|
||||
<jar>dhp-aggregation-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--executor-cores=${sparkExecutorCores}
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
|
||||
</spark-opts>
|
||||
<arg>--inputPath</arg><arg>${workingDir}/transformativeagreement/</arg>
|
||||
<arg>--outputPath</arg><arg>${outputPath}</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
<end name="End"/>
|
||||
</workflow-app>
|
|
@ -0,0 +1,26 @@
|
|||
[
|
||||
{
|
||||
"paramName": "m",
|
||||
"paramLongName": "master",
|
||||
"paramDescription": "the master name",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "t",
|
||||
"paramLongName": "targetPath",
|
||||
"paramDescription": "the target PATH of the DF tables",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "g",
|
||||
"paramLongName": "graphPath",
|
||||
"paramDescription": "the PATH of the current graph path",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "u",
|
||||
"paramLongName": "updatePath",
|
||||
"paramDescription": "the PATH of the current graph update path",
|
||||
"paramRequired": true
|
||||
}
|
||||
]
|
|
@ -0,0 +1,37 @@
|
|||
[ {
|
||||
"paramName": "n",
|
||||
"paramLongName": "namenode",
|
||||
"paramDescription": "the Name Node URI",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "m",
|
||||
"paramLongName": "master",
|
||||
"paramDescription": "the master name",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "t",
|
||||
"paramLongName": "targetPath",
|
||||
"paramDescription": "the target PATH where download the files",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "a",
|
||||
"paramLongName": "apiURL",
|
||||
"paramDescription": "the URL to download the tar file",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "g",
|
||||
"paramLongName": "graphPath",
|
||||
"paramDescription": "the path of the input graph",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "at",
|
||||
"paramLongName": "accessToken",
|
||||
"paramDescription": "the accessToken to contact API",
|
||||
"paramRequired": true
|
||||
}
|
||||
]
|
|
@ -16,6 +16,12 @@
|
|||
"paramLongName": "sourcePath",
|
||||
"paramDescription": "the PATH of the ORCID sequence file",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "fu",
|
||||
"paramLongName": "fromUpdate",
|
||||
"paramDescription": "whether we have to generate table from dump or from update",
|
||||
"paramRequired": false
|
||||
}
|
||||
|
||||
]
|
|
@ -0,0 +1,23 @@
|
|||
<configuration>
|
||||
<property>
|
||||
<name>jobTracker</name>
|
||||
<value>yarnRM</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>nameNode</name>
|
||||
<value>hdfs://nameservice1</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozie.use.system.libpath</name>
|
||||
<value>true</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>oozie.action.sharelib.for.spark</name>
|
||||
<value>spark2</value>
|
||||
</property>
|
||||
|
||||
<property>
|
||||
<name>oozie.launcher.mapreduce.user.classpath.first</name>
|
||||
<value>true</value>
|
||||
</property>
|
||||
</configuration>
|
|
@ -0,0 +1,114 @@
|
|||
<workflow-app name="download_Update_ORCID" xmlns="uri:oozie:workflow:0.5">
|
||||
<parameters>
|
||||
<property>
|
||||
<name>graphPath</name>
|
||||
<description>the path to store the original ORCID dump</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>targetPath</name>
|
||||
<description>the path to store the original ORCID dump</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>apiURL</name>
|
||||
<value>http://74804fb637bd8e2fba5b-e0a029c2f87486cddec3b416996a6057.r3.cf1.rackcdn.com/last_modified.csv.tar</value>
|
||||
<description>The URL of the update CSV list </description>
|
||||
</property>
|
||||
<property>
|
||||
<name>accessToken</name>
|
||||
<description>The access token</description>
|
||||
</property>
|
||||
|
||||
|
||||
</parameters>
|
||||
|
||||
<start to="startUpdate"/>
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
||||
<action name="startUpdate">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Check Latest Orcid and Download updates</name>
|
||||
<class>eu.dnetlib.dhp.collection.orcid.OrcidGetUpdatesFile</class>
|
||||
<jar>dhp-aggregation-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--executor-cores=${sparkExecutorCores}
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.executor.memoryOverhead=2g
|
||||
--conf spark.sql.shuffle.partitions=3000
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||
</spark-opts>
|
||||
<arg>--master</arg><arg>yarn</arg>
|
||||
<arg>--namenode</arg><arg>${nameNode}</arg>
|
||||
<arg>--graphPath</arg><arg>${graphPath}</arg>
|
||||
<arg>--targetPath</arg><arg>${targetPath}</arg>
|
||||
<arg>--apiURL</arg><arg>${apiURL}</arg>
|
||||
<arg>--accessToken</arg><arg>${accessToken}</arg>
|
||||
</spark>
|
||||
<ok to="generateTables"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
<action name="generateTables">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Generate ORCID Tables</name>
|
||||
<class>eu.dnetlib.dhp.collection.orcid.SparkGenerateORCIDTable</class>
|
||||
<jar>dhp-aggregation-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--executor-cores=${sparkExecutorCores}
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.executor.memoryOverhead=2g
|
||||
--conf spark.sql.shuffle.partitions=3000
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${targetPath}</arg>
|
||||
<arg>--targetPath</arg><arg>${targetPath}/updateTable</arg>
|
||||
<arg>--fromUpdate</arg><arg>true</arg>
|
||||
<arg>--master</arg><arg>yarn</arg>
|
||||
</spark>
|
||||
<ok to="updateTable"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="updateTable">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
<mode>cluster</mode>
|
||||
<name>Update ORCID Tables</name>
|
||||
<class>eu.dnetlib.dhp.collection.orcid.SparkApplyUpdate</class>
|
||||
<jar>dhp-aggregation-${projectVersion}.jar</jar>
|
||||
<spark-opts>
|
||||
--executor-memory=${sparkExecutorMemory}
|
||||
--executor-cores=${sparkExecutorCores}
|
||||
--driver-memory=${sparkDriverMemory}
|
||||
--conf spark.executor.memoryOverhead=2g
|
||||
--conf spark.sql.shuffle.partitions=3000
|
||||
--conf spark.extraListeners=${spark2ExtraListeners}
|
||||
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
|
||||
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
|
||||
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
|
||||
</spark-opts>
|
||||
<arg>--graphPath</arg><arg>${graphPath}</arg>
|
||||
<arg>--updatePath</arg><arg>${targetPath}/updateTable</arg>
|
||||
<arg>--targetPath</arg><arg>${targetPath}/newTable</arg>
|
||||
<arg>--master</arg><arg>yarn</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
<end name="End"/>
|
||||
</workflow-app>
|
|
@ -108,7 +108,7 @@ INSERT INTO dsm_apiparams(
|
|||
'api_________::openaire____::base_search::dump@@acceptedNormTypes',
|
||||
'api_________::openaire____::base_search::dump',
|
||||
'acceptedNormTypes',
|
||||
'1,11,111,121,13,14,15,18,181,182,183,1A,6,7'
|
||||
'1,11,111,121,14,15,18,181,182,183,1A,6,7'
|
||||
);
|
||||
|
||||
COMMIT;
|
|
@ -66,10 +66,6 @@ dc:language (I used base_dc:lang)
|
|||
base_dc:link (I used dc:identifier)
|
||||
-->
|
||||
|
||||
|
||||
<xsl:variable name="varBaseNormType" select="vocabulary:clean(//base_dc:typenorm, 'base:normalized_types')" />
|
||||
|
||||
|
||||
<metadata>
|
||||
<xsl:call-template name="allElements">
|
||||
<xsl:with-param name="sourceElement" select="//dc:title" />
|
||||
|
@ -112,9 +108,13 @@ base_dc:link (I used dc:identifier)
|
|||
<xsl:with-param name="targetElement" select="'dc:format'" />
|
||||
</xsl:call-template>
|
||||
|
||||
<dc:type>
|
||||
<xsl:value-of select="$varBaseNormType" />
|
||||
</dc:type>
|
||||
|
||||
<xsl:for-each select="//base_dc:typenorm">
|
||||
<dc:type>
|
||||
<xsl:value-of select="vocabulary:clean(., 'base:normalized_types')" />
|
||||
</dc:type>
|
||||
</xsl:for-each>
|
||||
|
||||
<xsl:call-template name="allElements">
|
||||
<xsl:with-param name="sourceElement" select="//dc:type" />
|
||||
<xsl:with-param name="targetElement" select="'dc:type'" />
|
||||
|
@ -162,16 +162,150 @@ base_dc:link (I used dc:identifier)
|
|||
</xsl:if>
|
||||
</xsl:for-each>
|
||||
|
||||
<dr:CobjCategory>
|
||||
<xsl:variable name="varCobjCategory" select="vocabulary:clean($varBaseNormType, 'dnet:publication_resource')" />
|
||||
<xsl:variable name="varSuperType" select="vocabulary:clean($varCobjCategory, 'dnet:result_typologies')" />
|
||||
<xsl:attribute name="type" select="$varSuperType" />
|
||||
<xsl:value-of select="$varCobjCategory" />
|
||||
</dr:CobjCategory>
|
||||
<xsl:choose>
|
||||
<!-- I used an inline mapping because the field typenorm could be repeated and I have to specify a list of priority -->
|
||||
|
||||
<!-- Book part -->
|
||||
<xsl:when test="//base_dc:typenorm = '111'">
|
||||
<dr:CobjCategory type="publication">0013</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Book -->
|
||||
<xsl:when test="//base_dc:typenorm = '11'">
|
||||
<dr:CobjCategory type="publication">0002</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Article contribution -->
|
||||
<xsl:when test="//base_dc:typenorm = '121'">
|
||||
<dr:CobjCategory type="publication">0001</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
|
||||
<!-- Journal/Newspaper -->
|
||||
<xsl:when test="//base_dc:typenorm = '12'">
|
||||
<dr:CobjCategory type="publication">0043</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Report -->
|
||||
<xsl:when test="//base_dc:typenorm = '14'">
|
||||
<dr:CobjCategory type="publication">0017</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Review -->
|
||||
<xsl:when test="//base_dc:typenorm = '15'">
|
||||
<dr:CobjCategory type="publication">0015</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Lecture -->
|
||||
<xsl:when test="//base_dc:typenorm = '17'">
|
||||
<dr:CobjCategory type="publication">0010</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Bachelor's thesis -->
|
||||
<xsl:when test="//base_dc:typenorm = '181'">
|
||||
<dr:CobjCategory type="publication">0008</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Master's thesis -->
|
||||
<xsl:when test="//base_dc:typenorm = '182'">
|
||||
<dr:CobjCategory type="publication">0007</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Doctoral and postdoctoral thesis -->
|
||||
<xsl:when test="//base_dc:typenorm = '183'">
|
||||
<dr:CobjCategory type="publication">0006</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Thesis -->
|
||||
<xsl:when test="//base_dc:typenorm = '18'">
|
||||
<dr:CobjCategory type="publication">0044</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Patent -->
|
||||
<xsl:when test="//base_dc:typenorm = '1A'">
|
||||
<dr:CobjCategory type="publication">0019</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Text -->
|
||||
<xsl:when test="//base_dc:typenorm = '1'">
|
||||
<dr:CobjCategory type="publication">0001</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Software -->
|
||||
<xsl:when test="//base_dc:typenorm = '6'">
|
||||
<dr:CobjCategory type="software">0029</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Dataset -->
|
||||
<xsl:when test="//base_dc:typenorm = '7'">
|
||||
<dr:CobjCategory type="dataset">0021</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Still image -->
|
||||
<xsl:when test="//base_dc:typenorm = '51'">
|
||||
<dr:CobjCategory type="other">0025</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Moving image/Video -->
|
||||
<xsl:when test="//base_dc:typenorm = '52'">
|
||||
<dr:CobjCategory type="other">0024</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Image/Video -->
|
||||
<xsl:when test="//base_dc:typenorm = '5'">
|
||||
<dr:CobjCategory type="other">0033</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Audio -->
|
||||
<xsl:when test="//base_dc:typenorm = '4'">
|
||||
<dr:CobjCategory type="other">0030</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Musical notation -->
|
||||
<xsl:when test="//base_dc:typenorm = '2'">
|
||||
<dr:CobjCategory type="other">0020</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Map -->
|
||||
<xsl:when test="//base_dc:typenorm = '3'">
|
||||
<dr:CobjCategory type="other">0020</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Other non-article -->
|
||||
<xsl:when test="//base_dc:typenorm = '122'">
|
||||
<dr:CobjCategory type="publication">0038</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Course material -->
|
||||
<xsl:when test="//base_dc:typenorm = '16'">
|
||||
<dr:CobjCategory type="publication">0038</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Manuscript -->
|
||||
<xsl:when test="//base_dc:typenorm = '19'">
|
||||
<dr:CobjCategory type="publication">0038</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Conference object -->
|
||||
<xsl:when test="//base_dc:typenorm = '13'">
|
||||
<dr:CobjCategory type="publication">0004</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Unknown -->
|
||||
<xsl:when test="//base_dc:typenorm = 'F'">
|
||||
<dr:CobjCategory type="other">0000</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
<xsl:otherwise>
|
||||
<dr:CobjCategory type="other">0000</dr:CobjCategory>
|
||||
</xsl:otherwise>
|
||||
</xsl:choose>
|
||||
|
||||
|
||||
<oaf:accessrights>
|
||||
<xsl:choose>
|
||||
<xsl:when test="//base_dc:oa[.='0']">CLOSED</xsl:when>
|
||||
<xsl:when test="//base_dc:oa[.='1']">OPEN</xsl:when>
|
||||
<xsl:when test="//base_dc:oa[.='2']">UNKNOWN</xsl:when>
|
||||
<xsl:when test="//base_dc:rightsnorm">
|
||||
<xsl:value-of select="vocabulary:clean(//base_dc:rightsnorm, 'dnet:access_modes')" />
|
||||
</xsl:when>
|
||||
|
@ -208,7 +342,7 @@ base_dc:link (I used dc:identifier)
|
|||
|
||||
<oaf:identifier identifierType="oai-original">
|
||||
<xsl:value-of
|
||||
select="//*[local-name() = 'about']/*[local-name() = 'provenance']//*[local-name() = 'originDescription' and not(./*[local-name() = 'originDescription'])]/*[local-name() = 'identifier']" />
|
||||
select="//oai:header/oai:identifier" />
|
||||
</oaf:identifier>
|
||||
|
||||
<oaf:hostedBy>
|
||||
|
|
|
@ -51,10 +51,6 @@
|
|||
base_dc:link (I used dc:identifier)
|
||||
-->
|
||||
|
||||
|
||||
<xsl:variable name="varBaseNormType" select="vocabulary:clean(//base_dc:typenorm, 'base:normalized_types')" />
|
||||
|
||||
|
||||
<metadata>
|
||||
<datacite:resource>
|
||||
|
||||
|
@ -86,14 +82,17 @@
|
|||
|
||||
<datacite:identifier alternateIdentifierType="oai-original">
|
||||
<xsl:value-of
|
||||
select="//*[local-name() = 'about']/*[local-name() = 'provenance']//*[local-name() = 'originDescription' and not(./*[local-name() = 'originDescription'])]/*[local-name() = 'identifier']" />
|
||||
select="//oai:header/oai:identifier" />
|
||||
</datacite:identifier>
|
||||
|
||||
</datacite:alternateIdentifiers>
|
||||
|
||||
<datacite:relatedIdentifiers />
|
||||
|
||||
|
||||
<datacite:resourceType><xsl:value-of select="$varBaseNormType" /></datacite:resourceType>
|
||||
<xsl:for-each select="//base_dc:typenorm">
|
||||
<datacite:resourceType><xsl:value-of select="vocabulary:clean(., 'base:normalized_types')" /></datacite:resourceType>
|
||||
</xsl:for-each>
|
||||
|
||||
<datacite:titles>
|
||||
<xsl:for-each select="//dc:title">
|
||||
|
@ -154,14 +153,18 @@
|
|||
</xsl:for-each>
|
||||
</datacite:subjects>
|
||||
|
||||
<datacite:publisher>
|
||||
<xsl:value-of select="normalize-space(//dc:publisher)" />
|
||||
</datacite:publisher>
|
||||
|
||||
<datacite:publicationYear>
|
||||
<xsl:value-of select="normalize-space(//base_dc:year)" />
|
||||
</datacite:publicationYear>
|
||||
<xsl:for-each select="//dc:publisher">
|
||||
<datacite:publisher>
|
||||
<xsl:value-of select="normalize-space(.)" />
|
||||
</datacite:publisher>
|
||||
</xsl:for-each>
|
||||
|
||||
<xsl:for-each select="//base_dc:year">
|
||||
<datacite:publicationYear>
|
||||
<xsl:value-of select="normalize-space(.)" />
|
||||
</datacite:publicationYear>
|
||||
</xsl:for-each>
|
||||
|
||||
<datacite:formats>
|
||||
<xsl:for-each select="//dc:format">
|
||||
<datacite:format>
|
||||
|
@ -175,6 +178,9 @@
|
|||
</datacite:language>
|
||||
|
||||
<oaf:accessrights>
|
||||
<xsl:if test="//base_dc:oa[.='0']">
|
||||
<datacite:rights rightsURI="http://purl.org/coar/access_right/c_16ec">restricted access</datacite:rights>
|
||||
</xsl:if>
|
||||
<xsl:if test="//base_dc:oa[.='1']">
|
||||
<datacite:rights rightsURI="http://purl.org/coar/access_right/c_abf2">open access</datacite:rights>
|
||||
</xsl:if>
|
||||
|
@ -185,29 +191,162 @@
|
|||
|
||||
</datacite:resource>
|
||||
|
||||
<xsl:for-each select="//dc:relation">
|
||||
<xsl:if test="matches(normalize-space(.), '(info:eu-repo/grantagreement/ec/fp7/)(\d\d\d\d\d\d)(.*)', 'i')">
|
||||
<oaf:projectid>
|
||||
<xsl:value-of select="concat($varFP7, replace(normalize-space(.), '(info:eu-repo/grantagreement/ec/fp7/)(\d\d\d\d\d\d)(.*)', '$2', 'i'))" />
|
||||
</oaf:projectid>
|
||||
</xsl:if>
|
||||
<xsl:if test="matches(normalize-space(.), '(info:eu-repo/grantagreement/ec/h2020/)(\d\d\d\d\d\d)(.*)', 'i')">
|
||||
<oaf:projectid>
|
||||
<xsl:value-of select="concat($varH2020, replace(normalize-space(.), '(info:eu-repo/grantagreement/ec/h2020/)(\d\d\d\d\d\d)(.*)', '$2', 'i'))" />
|
||||
</oaf:projectid>
|
||||
</xsl:if>
|
||||
</xsl:for-each>
|
||||
<xsl:for-each select="//dc:relation">
|
||||
<xsl:if test="matches(normalize-space(.), '(info:eu-repo/grantagreement/ec/fp7/)(\d\d\d\d\d\d)(.*)', 'i')">
|
||||
<oaf:projectid>
|
||||
<xsl:value-of select="concat($varFP7, replace(normalize-space(.), '(info:eu-repo/grantagreement/ec/fp7/)(\d\d\d\d\d\d)(.*)', '$2', 'i'))" />
|
||||
</oaf:projectid>
|
||||
</xsl:if>
|
||||
<xsl:if test="matches(normalize-space(.), '(info:eu-repo/grantagreement/ec/h2020/)(\d\d\d\d\d\d)(.*)', 'i')">
|
||||
<oaf:projectid>
|
||||
<xsl:value-of select="concat($varH2020, replace(normalize-space(.), '(info:eu-repo/grantagreement/ec/h2020/)(\d\d\d\d\d\d)(.*)', '$2', 'i'))" />
|
||||
</oaf:projectid>
|
||||
</xsl:if>
|
||||
</xsl:for-each>
|
||||
|
||||
<dr:CobjCategory>
|
||||
<xsl:variable name="varCobjCategory" select="vocabulary:clean($varBaseNormType, 'dnet:publication_resource')" />
|
||||
<xsl:variable name="varSuperType" select="vocabulary:clean($varCobjCategory, 'dnet:result_typologies')" />
|
||||
<xsl:attribute name="type" select="$varSuperType" />
|
||||
<xsl:value-of select="$varCobjCategory" />
|
||||
</dr:CobjCategory>
|
||||
<xsl:choose>
|
||||
<!-- I used an inline mapping because the field typenorm could be repeated and I have to specify a list of priority -->
|
||||
|
||||
<!-- Book part -->
|
||||
<xsl:when test="//base_dc:typenorm = '111'">
|
||||
<dr:CobjCategory type="publication">0013</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Book -->
|
||||
<xsl:when test="//base_dc:typenorm = '11'">
|
||||
<dr:CobjCategory type="publication">0002</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Article contribution -->
|
||||
<xsl:when test="//base_dc:typenorm = '121'">
|
||||
<dr:CobjCategory type="publication">0001</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
|
||||
<!-- Journal/Newspaper -->
|
||||
<xsl:when test="//base_dc:typenorm = '12'">
|
||||
<dr:CobjCategory type="publication">0043</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Report -->
|
||||
<xsl:when test="//base_dc:typenorm = '14'">
|
||||
<dr:CobjCategory type="publication">0017</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Review -->
|
||||
<xsl:when test="//base_dc:typenorm = '15'">
|
||||
<dr:CobjCategory type="publication">0015</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Lecture -->
|
||||
<xsl:when test="//base_dc:typenorm = '17'">
|
||||
<dr:CobjCategory type="publication">0010</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Bachelor's thesis -->
|
||||
<xsl:when test="//base_dc:typenorm = '181'">
|
||||
<dr:CobjCategory type="publication">0008</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Master's thesis -->
|
||||
<xsl:when test="//base_dc:typenorm = '182'">
|
||||
<dr:CobjCategory type="publication">0007</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Doctoral and postdoctoral thesis -->
|
||||
<xsl:when test="//base_dc:typenorm = '183'">
|
||||
<dr:CobjCategory type="publication">0006</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Thesis -->
|
||||
<xsl:when test="//base_dc:typenorm = '18'">
|
||||
<dr:CobjCategory type="publication">0044</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Patent -->
|
||||
<xsl:when test="//base_dc:typenorm = '1A'">
|
||||
<dr:CobjCategory type="publication">0019</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Text -->
|
||||
<xsl:when test="//base_dc:typenorm = '1'">
|
||||
<dr:CobjCategory type="publication">0001</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Software -->
|
||||
<xsl:when test="//base_dc:typenorm = '6'">
|
||||
<dr:CobjCategory type="software">0029</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Dataset -->
|
||||
<xsl:when test="//base_dc:typenorm = '7'">
|
||||
<dr:CobjCategory type="dataset">0021</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Still image -->
|
||||
<xsl:when test="//base_dc:typenorm = '51'">
|
||||
<dr:CobjCategory type="other">0025</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Moving image/Video -->
|
||||
<xsl:when test="//base_dc:typenorm = '52'">
|
||||
<dr:CobjCategory type="other">0024</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Image/Video -->
|
||||
<xsl:when test="//base_dc:typenorm = '5'">
|
||||
<dr:CobjCategory type="other">0033</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Audio -->
|
||||
<xsl:when test="//base_dc:typenorm = '4'">
|
||||
<dr:CobjCategory type="other">0030</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Musical notation -->
|
||||
<xsl:when test="//base_dc:typenorm = '2'">
|
||||
<dr:CobjCategory type="other">0020</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Map -->
|
||||
<xsl:when test="//base_dc:typenorm = '3'">
|
||||
<dr:CobjCategory type="other">0020</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Other non-article -->
|
||||
<xsl:when test="//base_dc:typenorm = '122'">
|
||||
<dr:CobjCategory type="publication">0038</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Course material -->
|
||||
<xsl:when test="//base_dc:typenorm = '16'">
|
||||
<dr:CobjCategory type="publication">0038</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Manuscript -->
|
||||
<xsl:when test="//base_dc:typenorm = '19'">
|
||||
<dr:CobjCategory type="publication">0038</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Conference object -->
|
||||
<xsl:when test="//base_dc:typenorm = '13'">
|
||||
<dr:CobjCategory type="publication">0004</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
|
||||
<!-- Unknown -->
|
||||
<xsl:when test="//base_dc:typenorm = 'F'">
|
||||
<dr:CobjCategory type="other">0000</dr:CobjCategory>
|
||||
</xsl:when>
|
||||
<xsl:otherwise>
|
||||
<dr:CobjCategory type="other">0000</dr:CobjCategory>
|
||||
</xsl:otherwise>
|
||||
</xsl:choose>
|
||||
|
||||
<oaf:accessrights>
|
||||
<xsl:choose>
|
||||
<xsl:when test="//base_dc:oa[.='0']">CLOSED</xsl:when>
|
||||
<xsl:when test="//base_dc:oa[.='1']">OPEN</xsl:when>
|
||||
<xsl:when test="//base_dc:oa[.='2']">UNKNOWN</xsl:when>
|
||||
<xsl:when test="//base_dc:rightsnorm">
|
||||
<xsl:value-of select="vocabulary:clean(//base_dc:rightsnorm, 'dnet:access_modes')" />
|
||||
</xsl:when>
|
||||
|
@ -245,7 +384,7 @@
|
|||
|
||||
<oaf:identifier identifierType="oai-original">
|
||||
<xsl:value-of
|
||||
select="//*[local-name() = 'about']/*[local-name() = 'provenance']//*[local-name() = 'originDescription' and not(./*[local-name() = 'originDescription'])]/*[local-name() = 'identifier']" />
|
||||
select="//oai:header/oai:identifier" />
|
||||
</oaf:identifier>
|
||||
|
||||
<oaf:hostedBy>
|
||||
|
|
|
@ -1048,10 +1048,5 @@
|
|||
"openaire_id": "re3data_____::r3d100010399",
|
||||
"datacite_name": "ZEW Forschungsdatenzentrum",
|
||||
"official_name": "ZEW Forschungsdatenzentrum"
|
||||
},
|
||||
"HBP.NEUROINF": {
|
||||
"openaire_id": "fairsharing_::2975",
|
||||
"datacite_name": "EBRAINS",
|
||||
"official_name": "EBRAINS"
|
||||
}
|
||||
}
|
|
@ -1,4 +1,4 @@
|
|||
<workflow-app name="Transform_BioEntity_Workflow" xmlns="uri:oozie:workflow:0.5">
|
||||
<workflow-app name="Transform_BioEntity_Workflow" xmlns="uri:oozie:workflow:0.5">
|
||||
<parameters>
|
||||
<property>
|
||||
<name>sourcePath</name>
|
||||
|
@ -8,40 +8,19 @@
|
|||
<name>database</name>
|
||||
<description>the PDB Database Working Path</description>
|
||||
</property>
|
||||
|
||||
<property>
|
||||
<name>mdStoreOutputId</name>
|
||||
<description>the identifier of the cleaned MDStore</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>mdStoreManagerURI</name>
|
||||
<description>the path of the cleaned mdstore</description>
|
||||
<name>targetPath</name>
|
||||
<description>the Target Working dir path</description>
|
||||
</property>
|
||||
</parameters>
|
||||
|
||||
<start to="StartTransaction"/>
|
||||
|
||||
<start to="ConvertDB"/>
|
||||
|
||||
<kill name="Kill">
|
||||
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
|
||||
</kill>
|
||||
|
||||
<action name="StartTransaction">
|
||||
<java>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>oozie.launcher.mapreduce.user.classpath.first</name>
|
||||
<value>true</value>
|
||||
</property>
|
||||
</configuration>
|
||||
<main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
|
||||
<arg>--action</arg><arg>NEW_VERSION</arg>
|
||||
<arg>--mdStoreID</arg><arg>${mdStoreOutputId}</arg>
|
||||
<arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
|
||||
<capture-output/>
|
||||
</java>
|
||||
<ok to="ConvertDB"/>
|
||||
<error to="RollBack"/>
|
||||
</action>
|
||||
<action name="ConvertDB">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn</master>
|
||||
|
@ -62,48 +41,11 @@
|
|||
<arg>--master</arg><arg>yarn</arg>
|
||||
<arg>--dbPath</arg><arg>${sourcePath}</arg>
|
||||
<arg>--database</arg><arg>${database}</arg>
|
||||
<arg>--mdstoreOutputVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
|
||||
<arg>--targetPath</arg><arg>${targetPath}</arg>
|
||||
</spark>
|
||||
<ok to="CommitVersion"/>
|
||||
<error to="RollBack"/>
|
||||
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
<action name="CommitVersion">
|
||||
<java>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>oozie.launcher.mapreduce.user.classpath.first</name>
|
||||
<value>true</value>
|
||||
</property>
|
||||
</configuration>
|
||||
<main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
|
||||
<arg>--action</arg><arg>COMMIT</arg>
|
||||
<arg>--namenode</arg><arg>${nameNode}</arg>
|
||||
<arg>--mdStoreVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
|
||||
<arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
|
||||
</java>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="RollBack">
|
||||
<java>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>oozie.launcher.mapreduce.user.classpath.first</name>
|
||||
<value>true</value>
|
||||
</property>
|
||||
</configuration>
|
||||
<main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
|
||||
<arg>--action</arg><arg>ROLLBACK</arg>
|
||||
<arg>--mdStoreVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
|
||||
<arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
|
||||
</java>
|
||||
<ok to="Kill"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
<end name="End"/>
|
||||
<end name="End"/>
|
||||
|
||||
</workflow-app>
|
|
@ -2,5 +2,5 @@
|
|||
{"paramName":"mt", "paramLongName":"master", "paramDescription": "should be local or yarn", "paramRequired": true},
|
||||
{"paramName":"db", "paramLongName":"database", "paramDescription": "should be PDB or UNIPROT", "paramRequired": true},
|
||||
{"paramName":"p", "paramLongName":"dbPath", "paramDescription": "the path of the database to transform", "paramRequired": true},
|
||||
{"paramName":"mo", "paramLongName":"mdstoreOutputVersion", "paramDescription": "the oaf path ", "paramRequired": true}
|
||||
{"paramName":"t", "paramLongName":"targetPath", "paramDescription": "the OAF target path ", "paramRequired": true}
|
||||
]
|
|
@ -1,20 +1,5 @@
|
|||
[
|
||||
{
|
||||
"paramName": "mt",
|
||||
"paramLongName": "master",
|
||||
"paramDescription": "should be local or yarn",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "s",
|
||||
"paramLongName": "sourcePath",
|
||||
"paramDescription": "the source Path",
|
||||
"paramRequired": true
|
||||
},
|
||||
{
|
||||
"paramName": "mo",
|
||||
"paramLongName": "mdstoreOutputVersion",
|
||||
"paramDescription": "the oaf path ",
|
||||
"paramRequired": true
|
||||
}
|
||||
{"paramName":"mt", "paramLongName":"master", "paramDescription": "should be local or yarn", "paramRequired": true},
|
||||
{"paramName":"s", "paramLongName":"sourcePath","paramDescription": "the source Path", "paramRequired": true},
|
||||
{"paramName":"t", "paramLongName":"targetPath","paramDescription": "the oaf path ", "paramRequired": true}
|
||||
]
|
|
@ -9,26 +9,34 @@
|
|||
<description>the Working Path</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>mdStoreOutputId</name>
|
||||
<description>the identifier of the cleaned MDStore</description>
|
||||
<name>targetPath</name>
|
||||
<description>the OAF MDStore Path</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>mdStoreManagerURI</name>
|
||||
<description>the path of the cleaned mdstore</description>
|
||||
<name>sparkDriverMemory</name>
|
||||
<description>memory for driver process</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkExecutorMemory</name>
|
||||
<description>memory for individual executor</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>sparkExecutorCores</name>
|
||||
<description>number of cores used by single executor</description>
|
||||
</property>
|
||||
<property>
|
||||
<name>resumeFrom</name>
|
||||
<value>CreateEBIDataSet</value>
|
||||
<value>DownloadEBILinks</value>
|
||||
<description>node to start</description>
|
||||
</property>
|
||||
</parameters>
|
||||
|
||||
<start to="StartTransaction"/>
|
||||
<start to="resume_from"/>
|
||||
|
||||
<decision name="resume_from">
|
||||
<switch>
|
||||
<case to="DownloadEBILinks">${wf:conf('resumeFrom') eq 'DownloadEBILinks'}</case>
|
||||
<case to="StartTransaction">${wf:conf('resumeFrom') eq 'CreateEBIDataSet'}</case>
|
||||
<case to="CreateEBIDataSet">${wf:conf('resumeFrom') eq 'CreateEBIDataSet'}</case>
|
||||
<default to="DownloadEBILinks"/>
|
||||
</switch>
|
||||
</decision>
|
||||
|
@ -69,29 +77,9 @@
|
|||
<move source="${sourcePath}/ebi_links_dataset" target="${sourcePath}/ebi_links_dataset_old"/>
|
||||
<move source="${workingPath}/links_final" target="${sourcePath}/ebi_links_dataset"/>
|
||||
</fs>
|
||||
<ok to="StartTransaction"/>
|
||||
<ok to="CreateEBIDataSet"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="StartTransaction">
|
||||
<java>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>oozie.launcher.mapreduce.user.classpath.first</name>
|
||||
<value>true</value>
|
||||
</property>
|
||||
</configuration>
|
||||
<main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
|
||||
<arg>--action</arg><arg>NEW_VERSION</arg>
|
||||
<arg>--mdStoreID</arg><arg>${mdStoreOutputId}</arg>
|
||||
<arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
|
||||
<capture-output/>
|
||||
</java>
|
||||
<ok to="CreateEBIDataSet"/>
|
||||
<error to="RollBack"/>
|
||||
</action>
|
||||
|
||||
|
||||
<action name="CreateEBIDataSet">
|
||||
<spark xmlns="uri:oozie:spark-action:0.2">
|
||||
<master>yarn-cluster</master>
|
||||
|
@ -107,49 +95,11 @@
|
|||
${sparkExtraOPT}
|
||||
</spark-opts>
|
||||
<arg>--sourcePath</arg><arg>${sourcePath}/ebi_links_dataset</arg>
|
||||
<arg>--mdstoreOutputVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
|
||||
<arg>--targetPath</arg><arg>${targetPath}</arg>
|
||||
<arg>--master</arg><arg>yarn</arg>
|
||||
</spark>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
|
||||
<action name="CommitVersion">
|
||||
<java>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>oozie.launcher.mapreduce.user.classpath.first</name>
|
||||
<value>true</value>
|
||||
</property>
|
||||
</configuration>
|
||||
<main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
|
||||
<arg>--action</arg><arg>COMMIT</arg>
|
||||
<arg>--namenode</arg><arg>${nameNode}</arg>
|
||||
<arg>--mdStoreVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
|
||||
<arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
|
||||
</java>
|
||||
<ok to="End"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<action name="RollBack">
|
||||
<java>
|
||||
<configuration>
|
||||
<property>
|
||||
<name>oozie.launcher.mapreduce.user.classpath.first</name>
|
||||
<value>true</value>
|
||||
</property>
|
||||
</configuration>
|
||||
<main-class>eu.dnetlib.dhp.aggregation.mdstore.MDStoreActionNode</main-class>
|
||||
<arg>--action</arg><arg>ROLLBACK</arg>
|
||||
<arg>--mdStoreVersion</arg><arg>${wf:actionData('StartTransaction')['mdStoreVersion']}</arg>
|
||||
<arg>--mdStoreManagerURI</arg><arg>${mdStoreManagerURI}</arg>
|
||||
</java>
|
||||
<ok to="Kill"/>
|
||||
<error to="Kill"/>
|
||||
</action>
|
||||
|
||||
<end name="End"/>
|
||||
|
||||
</workflow-app>
|
|
@ -0,0 +1,120 @@
|
|||
package eu.dnetlib.dhp.collection.orcid
|
||||
|
||||
import eu.dnetlib.dhp.application.AbstractScalaApplication
|
||||
import org.apache.spark.sql.{DataFrame, SaveMode, SparkSession}
|
||||
import org.slf4j.{Logger, LoggerFactory}
|
||||
|
||||
class SparkApplyUpdate(propertyPath: String, args: Array[String], log: Logger)
|
||||
extends AbstractScalaApplication(propertyPath, args, log: Logger) {
|
||||
|
||||
/** Here all the spark applications runs this method
|
||||
* where the whole logic of the spark node is defined
|
||||
*/
|
||||
override def run(): Unit = {
|
||||
|
||||
val graphPath: String = parser.get("graphPath")
|
||||
log.info("found parameters graphPath: {}", graphPath)
|
||||
val updatePath: String = parser.get("updatePath")
|
||||
log.info("found parameters updatePath: {}", updatePath)
|
||||
val targetPath: String = parser.get("targetPath")
|
||||
log.info("found parameters targetPath: {}", targetPath)
|
||||
applyTableUpdate(spark, graphPath, updatePath, targetPath)
|
||||
checkUpdate(spark, graphPath, targetPath)
|
||||
moveTable(spark, graphPath, targetPath)
|
||||
|
||||
}
|
||||
|
||||
private def moveTable(spark: SparkSession, graphPath: String, updatePath: String): Unit = {
|
||||
spark.read
|
||||
.load(s"$updatePath/Authors")
|
||||
.repartition(1000)
|
||||
.write
|
||||
.mode(SaveMode.Overwrite)
|
||||
.save(s"$graphPath/Authors")
|
||||
spark.read
|
||||
.load(s"$updatePath/Works")
|
||||
.repartition(1000)
|
||||
.write
|
||||
.mode(SaveMode.Overwrite)
|
||||
.save(s"$graphPath/Works")
|
||||
spark.read
|
||||
.load(s"$updatePath/Employments")
|
||||
.repartition(1000)
|
||||
.write
|
||||
.mode(SaveMode.Overwrite)
|
||||
.save(s"$graphPath/Employments")
|
||||
|
||||
}
|
||||
|
||||
private def updateDataset(
|
||||
inputDataset: DataFrame,
|
||||
idUpdate: DataFrame,
|
||||
updateDataframe: DataFrame,
|
||||
targetPath: String
|
||||
): Unit = {
|
||||
inputDataset
|
||||
.join(idUpdate, inputDataset("orcid").equalTo(idUpdate("orcid")), "leftanti")
|
||||
.select(inputDataset("*"))
|
||||
.unionByName(updateDataframe)
|
||||
.write
|
||||
.mode(SaveMode.Overwrite)
|
||||
.save(targetPath)
|
||||
}
|
||||
|
||||
private def checkUpdate(spark: SparkSession, graphPath: String, updatePath: String): Unit = {
|
||||
val totalOriginalAuthors = spark.read.load(s"$graphPath/Authors").count
|
||||
val totalOriginalWorks = spark.read.load(s"$graphPath/Works").count
|
||||
val totalOriginalEmployments = spark.read.load(s"$graphPath/Employments").count
|
||||
val totalUpdateAuthors = spark.read.load(s"$updatePath/Authors").count
|
||||
val totalUpdateWorks = spark.read.load(s"$updatePath/Works").count
|
||||
val totalUpdateEmployments = spark.read.load(s"$updatePath/Employments").count
|
||||
|
||||
log.info("totalOriginalAuthors: {}", totalOriginalAuthors)
|
||||
log.info("totalOriginalWorks: {}", totalOriginalWorks)
|
||||
log.info("totalOriginalEmployments: {}", totalOriginalEmployments)
|
||||
log.info("totalUpdateAuthors: {}", totalUpdateAuthors)
|
||||
log.info("totalUpdateWorks: {}", totalUpdateWorks)
|
||||
log.info("totalUpdateEmployments: {}", totalUpdateEmployments)
|
||||
if (
|
||||
totalUpdateAuthors < totalOriginalAuthors || totalUpdateEmployments < totalOriginalEmployments || totalUpdateWorks < totalOriginalWorks
|
||||
)
|
||||
throw new RuntimeException("The updated Graph contains less elements of the original one")
|
||||
|
||||
}
|
||||
|
||||
private def applyTableUpdate(spark: SparkSession, graphPath: String, updatePath: String, targetPath: String): Unit = {
|
||||
val orcidIDUpdate = spark.read.load(s"$updatePath/Authors").select("orcid")
|
||||
updateDataset(
|
||||
spark.read.load(s"$graphPath/Authors"),
|
||||
orcidIDUpdate,
|
||||
spark.read.load(s"$updatePath/Authors"),
|
||||
s"$targetPath/Authors"
|
||||
)
|
||||
updateDataset(
|
||||
spark.read.load(s"$graphPath/Employments"),
|
||||
orcidIDUpdate,
|
||||
spark.read.load(s"$updatePath/Employments"),
|
||||
s"$targetPath/Employments"
|
||||
)
|
||||
updateDataset(
|
||||
spark.read.load(s"$graphPath/Works"),
|
||||
orcidIDUpdate,
|
||||
spark.read.load(s"$updatePath/Works"),
|
||||
s"$targetPath/Works"
|
||||
)
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
object SparkApplyUpdate {
|
||||
|
||||
val log: Logger = LoggerFactory.getLogger(SparkGenerateORCIDTable.getClass)
|
||||
|
||||
def main(args: Array[String]): Unit = {
|
||||
|
||||
new SparkApplyUpdate("/eu/dnetlib/dhp/collection/orcid/apply_orcid_table_parameter.json", args, log)
|
||||
.initialize()
|
||||
.run()
|
||||
|
||||
}
|
||||
}
|
|
@ -6,6 +6,7 @@ import org.apache.hadoop.io.Text
|
|||
import org.apache.spark.SparkContext
|
||||
import org.apache.spark.sql.{Encoder, Encoders, SaveMode, SparkSession}
|
||||
import org.slf4j.{Logger, LoggerFactory}
|
||||
import scala.collection.JavaConverters._
|
||||
|
||||
class SparkGenerateORCIDTable(propertyPath: String, args: Array[String], log: Logger)
|
||||
extends AbstractScalaApplication(propertyPath, args, log: Logger) {
|
||||
|
@ -18,12 +19,16 @@ class SparkGenerateORCIDTable(propertyPath: String, args: Array[String], log: Lo
|
|||
log.info("found parameters sourcePath: {}", sourcePath)
|
||||
val targetPath: String = parser.get("targetPath")
|
||||
log.info("found parameters targetPath: {}", targetPath)
|
||||
extractORCIDTable(spark, sourcePath, targetPath)
|
||||
extractORCIDEmploymentsTable(spark, sourcePath, targetPath)
|
||||
extractORCIDWorksTable(spark, sourcePath, targetPath)
|
||||
val fromUpdate = "true".equals(parser.get("fromUpdate"))
|
||||
val sourceSummaryPath = if (fromUpdate) s"$sourcePath/summary*" else sourcePath
|
||||
val sourceEmploymentsPath = if (fromUpdate) s"$sourcePath/employments*" else sourcePath
|
||||
val sourceWorksPath = if (fromUpdate) s"$sourcePath/works*" else sourcePath
|
||||
extractORCIDTable(spark, sourceSummaryPath, targetPath, fromUpdate)
|
||||
extractORCIDEmploymentsTable(spark, sourceEmploymentsPath, targetPath, fromUpdate)
|
||||
extractORCIDWorksTable(spark, sourceWorksPath, targetPath, fromUpdate)
|
||||
}
|
||||
|
||||
def extractORCIDTable(spark: SparkSession, sourcePath: String, targetPath: String): Unit = {
|
||||
def extractORCIDTable(spark: SparkSession, sourcePath: String, targetPath: String, skipFilterByKey: Boolean): Unit = {
|
||||
val sc: SparkContext = spark.sparkContext
|
||||
import spark.implicits._
|
||||
val df = sc
|
||||
|
@ -32,8 +37,8 @@ class SparkGenerateORCIDTable(propertyPath: String, args: Array[String], log: Lo
|
|||
.toDF
|
||||
.as[(String, String)]
|
||||
implicit val orcidAuthor: Encoder[Author] = Encoders.bean(classOf[Author])
|
||||
// implicit val orcidPID:Encoder[Pid] = Encoders.bean(classOf[Pid])
|
||||
df.filter(r => r._1.contains("summaries"))
|
||||
val newDf = if (!skipFilterByKey) df.filter(r => r._1.contains("summaries")) else df
|
||||
newDf
|
||||
.map { r =>
|
||||
val p = new OrcidParser
|
||||
p.parseSummary(r._2)
|
||||
|
@ -44,7 +49,12 @@ class SparkGenerateORCIDTable(propertyPath: String, args: Array[String], log: Lo
|
|||
.save(s"$targetPath/Authors")
|
||||
}
|
||||
|
||||
def extractORCIDWorksTable(spark: SparkSession, sourcePath: String, targetPath: String): Unit = {
|
||||
def extractORCIDWorksTable(
|
||||
spark: SparkSession,
|
||||
sourcePath: String,
|
||||
targetPath: String,
|
||||
skipFilterByKey: Boolean
|
||||
): Unit = {
|
||||
val sc: SparkContext = spark.sparkContext
|
||||
import spark.implicits._
|
||||
val df = sc
|
||||
|
@ -53,19 +63,37 @@ class SparkGenerateORCIDTable(propertyPath: String, args: Array[String], log: Lo
|
|||
.toDF
|
||||
.as[(String, String)]
|
||||
implicit val orcidWorkAuthor: Encoder[Work] = Encoders.bean(classOf[Work])
|
||||
implicit val orcidPID: Encoder[Pid] = Encoders.bean(classOf[Pid])
|
||||
df.filter(r => r._1.contains("works"))
|
||||
.map { r =>
|
||||
|
||||
//We are in the case of parsing ORCID UPDATE
|
||||
if (skipFilterByKey) {
|
||||
df.flatMap { r =>
|
||||
val p = new OrcidParser
|
||||
p.parseWork(r._2)
|
||||
}
|
||||
.filter(p => p != null)
|
||||
.write
|
||||
.mode(SaveMode.Overwrite)
|
||||
.save(s"$targetPath/Works")
|
||||
p.parseWorks(r._2).asScala
|
||||
}.filter(p => p != null)
|
||||
.write
|
||||
.mode(SaveMode.Overwrite)
|
||||
.save(s"$targetPath/Works")
|
||||
}
|
||||
//We are in the case of parsing ORCID DUMP
|
||||
else {
|
||||
df.filter(r => r._1.contains("works"))
|
||||
.map { r =>
|
||||
val p = new OrcidParser
|
||||
p.parseWork(r._2)
|
||||
}
|
||||
.filter(p => p != null)
|
||||
.write
|
||||
.mode(SaveMode.Overwrite)
|
||||
.save(s"$targetPath/Works")
|
||||
}
|
||||
}
|
||||
|
||||
def extractORCIDEmploymentsTable(spark: SparkSession, sourcePath: String, targetPath: String): Unit = {
|
||||
def extractORCIDEmploymentsTable(
|
||||
spark: SparkSession,
|
||||
sourcePath: String,
|
||||
targetPath: String,
|
||||
skipFilterByKey: Boolean
|
||||
): Unit = {
|
||||
val sc: SparkContext = spark.sparkContext
|
||||
import spark.implicits._
|
||||
val df = sc
|
||||
|
@ -74,16 +102,27 @@ class SparkGenerateORCIDTable(propertyPath: String, args: Array[String], log: Lo
|
|||
.toDF
|
||||
.as[(String, String)]
|
||||
implicit val orcidEmploymentAuthor: Encoder[Employment] = Encoders.bean(classOf[Employment])
|
||||
implicit val orcidPID: Encoder[Pid] = Encoders.bean(classOf[Pid])
|
||||
df.filter(r => r._1.contains("employments"))
|
||||
.map { r =>
|
||||
if (skipFilterByKey) {
|
||||
df.flatMap { r =>
|
||||
val p = new OrcidParser
|
||||
p.parseEmployment(r._2)
|
||||
}
|
||||
.filter(p => p != null)
|
||||
.write
|
||||
.mode(SaveMode.Overwrite)
|
||||
.save(s"$targetPath/Employments")
|
||||
p.parseEmployments(r._2).asScala
|
||||
}.filter(p => p != null)
|
||||
.write
|
||||
.mode(SaveMode.Overwrite)
|
||||
.save(s"$targetPath/Employments")
|
||||
}
|
||||
//We are in the case of parsing ORCID DUMP
|
||||
else {
|
||||
df.filter(r => r._1.contains("employments"))
|
||||
.map { r =>
|
||||
val p = new OrcidParser
|
||||
p.parseEmployment(r._2)
|
||||
}
|
||||
.filter(p => p != null)
|
||||
.write
|
||||
.mode(SaveMode.Overwrite)
|
||||
.save(s"$targetPath/Employments")
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
|
|
|
@ -231,7 +231,7 @@ object BioDBToOAF {
|
|||
def uniprotToOAF(input: String): List[Oaf] = {
|
||||
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
|
||||
lazy val json = parse(input)
|
||||
val pid = (json \ "pid").extract[String].trim()
|
||||
val pid = (json \ "pid").extract[String]
|
||||
|
||||
val d = new Dataset
|
||||
|
||||
|
|
|
@ -2,15 +2,12 @@ package eu.dnetlib.dhp.sx.bio
|
|||
|
||||
import eu.dnetlib.dhp.application.ArgumentApplicationParser
|
||||
import eu.dnetlib.dhp.collection.CollectionUtils
|
||||
import eu.dnetlib.dhp.common.Constants.{MDSTORE_DATA_PATH, MDSTORE_SIZE_PATH}
|
||||
import eu.dnetlib.dhp.schema.mdstore.MDStoreVersion
|
||||
import eu.dnetlib.dhp.schema.oaf.Oaf
|
||||
import eu.dnetlib.dhp.sx.bio.BioDBToOAF.ScholixResolved
|
||||
import org.apache.commons.io.IOUtils
|
||||
import org.apache.spark.SparkConf
|
||||
import org.apache.spark.sql.{Encoder, Encoders, SparkSession}
|
||||
import org.slf4j.{Logger, LoggerFactory}
|
||||
import eu.dnetlib.dhp.utils.DHPUtils.{MAPPER, writeHdfsFile}
|
||||
|
||||
object SparkTransformBioDatabaseToOAF {
|
||||
|
||||
|
@ -28,13 +25,8 @@ object SparkTransformBioDatabaseToOAF {
|
|||
|
||||
val dbPath: String = parser.get("dbPath")
|
||||
log.info("dbPath: {}", database)
|
||||
|
||||
val mdstoreOutputVersion = parser.get("mdstoreOutputVersion")
|
||||
log.info("mdstoreOutputVersion: {}", mdstoreOutputVersion)
|
||||
|
||||
val cleanedMdStoreVersion = MAPPER.readValue(mdstoreOutputVersion, classOf[MDStoreVersion])
|
||||
val outputBasePath = cleanedMdStoreVersion.getHdfsPath
|
||||
log.info("outputBasePath: {}", outputBasePath)
|
||||
val targetPath: String = parser.get("targetPath")
|
||||
log.info("targetPath: {}", database)
|
||||
|
||||
val spark: SparkSession =
|
||||
SparkSession
|
||||
|
@ -51,28 +43,24 @@ object SparkTransformBioDatabaseToOAF {
|
|||
case "UNIPROT" =>
|
||||
CollectionUtils.saveDataset(
|
||||
spark.createDataset(sc.textFile(dbPath).flatMap(i => BioDBToOAF.uniprotToOAF(i))),
|
||||
s"$outputBasePath/$MDSTORE_DATA_PATH"
|
||||
targetPath
|
||||
)
|
||||
case "PDB" =>
|
||||
CollectionUtils.saveDataset(
|
||||
spark.createDataset(sc.textFile(dbPath).flatMap(i => BioDBToOAF.pdbTOOaf(i))),
|
||||
s"$outputBasePath/$MDSTORE_DATA_PATH"
|
||||
targetPath
|
||||
)
|
||||
case "SCHOLIX" =>
|
||||
CollectionUtils.saveDataset(
|
||||
spark.read.load(dbPath).as[ScholixResolved].map(i => BioDBToOAF.scholixResolvedToOAF(i)),
|
||||
s"$outputBasePath/$MDSTORE_DATA_PATH"
|
||||
targetPath
|
||||
)
|
||||
case "CROSSREF_LINKS" =>
|
||||
CollectionUtils.saveDataset(
|
||||
spark.createDataset(sc.textFile(dbPath).map(i => BioDBToOAF.crossrefLinksToOaf(i))),
|
||||
s"$outputBasePath/$MDSTORE_DATA_PATH"
|
||||
targetPath
|
||||
)
|
||||
}
|
||||
|
||||
val df = spark.read.text(s"$outputBasePath/$MDSTORE_DATA_PATH")
|
||||
val mdStoreSize = df.count
|
||||
writeHdfsFile(spark.sparkContext.hadoopConfiguration, s"$mdStoreSize", s"$outputBasePath/$MDSTORE_SIZE_PATH")
|
||||
}
|
||||
|
||||
}
|
||||
|
|
|
@ -9,9 +9,6 @@ import org.apache.commons.io.IOUtils
|
|||
import org.apache.spark.SparkConf
|
||||
import org.apache.spark.sql._
|
||||
import org.slf4j.{Logger, LoggerFactory}
|
||||
import eu.dnetlib.dhp.common.Constants.{MDSTORE_DATA_PATH, MDSTORE_SIZE_PATH}
|
||||
import eu.dnetlib.dhp.schema.mdstore.MDStoreVersion
|
||||
import eu.dnetlib.dhp.utils.DHPUtils.{MAPPER, writeHdfsFile}
|
||||
|
||||
object SparkEBILinksToOaf {
|
||||
|
||||
|
@ -35,13 +32,8 @@ object SparkEBILinksToOaf {
|
|||
import spark.implicits._
|
||||
val sourcePath = parser.get("sourcePath")
|
||||
log.info(s"sourcePath -> $sourcePath")
|
||||
val mdstoreOutputVersion = parser.get("mdstoreOutputVersion")
|
||||
log.info("mdstoreOutputVersion: {}", mdstoreOutputVersion)
|
||||
|
||||
val cleanedMdStoreVersion = MAPPER.readValue(mdstoreOutputVersion, classOf[MDStoreVersion])
|
||||
val outputBasePath = cleanedMdStoreVersion.getHdfsPath
|
||||
log.info("outputBasePath: {}", outputBasePath)
|
||||
|
||||
val targetPath = parser.get("targetPath")
|
||||
log.info(s"targetPath -> $targetPath")
|
||||
implicit val PMEncoder: Encoder[Oaf] = Encoders.kryo(classOf[Oaf])
|
||||
|
||||
val ebLinks: Dataset[EBILinkItem] = spark.read
|
||||
|
@ -54,10 +46,7 @@ object SparkEBILinksToOaf {
|
|||
.flatMap(j => BioDBToOAF.parse_ebi_links(j.links))
|
||||
.filter(p => BioDBToOAF.EBITargetLinksFilter(p))
|
||||
.flatMap(p => BioDBToOAF.convertEBILinksToOaf(p)),
|
||||
s"$outputBasePath/$MDSTORE_DATA_PATH"
|
||||
targetPath
|
||||
)
|
||||
val df = spark.read.text(s"$outputBasePath/$MDSTORE_DATA_PATH")
|
||||
val mdStoreSize = df.count
|
||||
writeHdfsFile(spark.sparkContext.hadoopConfiguration, s"$mdStoreSize", s"$outputBasePath/$MDSTORE_SIZE_PATH")
|
||||
}
|
||||
}
|
||||
|
|
|
@ -78,10 +78,6 @@ public class PrepareAffiliationRelationsTest {
|
|||
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/doi_to_ror.json")
|
||||
.getPath();
|
||||
|
||||
String pubmedAffiliationRelationsPath = getClass()
|
||||
.getResource("/eu/dnetlib/dhp/actionmanager/bipaffiliations/doi_to_ror.json")
|
||||
.getPath();
|
||||
|
||||
String outputPath = workingDir.toString() + "/actionSet";
|
||||
|
||||
PrepareAffiliationRelations
|
||||
|
@ -89,7 +85,8 @@ public class PrepareAffiliationRelationsTest {
|
|||
new String[] {
|
||||
"-isSparkSessionManaged", Boolean.FALSE.toString(),
|
||||
"-crossrefInputPath", crossrefAffiliationRelationPath,
|
||||
"-pubmedInputPath", pubmedAffiliationRelationsPath,
|
||||
"-pubmedInputPath", crossrefAffiliationRelationPath,
|
||||
"-openapcInputPath", crossrefAffiliationRelationPath,
|
||||
"-outputPath", outputPath
|
||||
});
|
||||
|
||||
|
@ -106,7 +103,7 @@ public class PrepareAffiliationRelationsTest {
|
|||
// );
|
||||
// }
|
||||
// count the number of relations
|
||||
assertEquals(40, tmp.count());
|
||||
assertEquals(60, tmp.count());
|
||||
|
||||
Dataset<Relation> dataset = spark.createDataset(tmp.rdd(), Encoders.bean(Relation.class));
|
||||
dataset.createOrReplaceTempView("result");
|
||||
|
@ -117,7 +114,7 @@ public class PrepareAffiliationRelationsTest {
|
|||
// verify that we have equal number of bi-directional relations
|
||||
Assertions
|
||||
.assertEquals(
|
||||
20, execVerification
|
||||
30, execVerification
|
||||
.filter(
|
||||
"relClass='" + ModelConstants.HAS_AUTHOR_INSTITUTION + "'")
|
||||
.collectAsList()
|
||||
|
@ -125,7 +122,7 @@ public class PrepareAffiliationRelationsTest {
|
|||
|
||||
Assertions
|
||||
.assertEquals(
|
||||
20, execVerification
|
||||
30, execVerification
|
||||
.filter(
|
||||
"relClass='" + ModelConstants.IS_AUTHOR_INSTITUTION_OF + "'")
|
||||
.collectAsList()
|
||||
|
|
|
@ -0,0 +1,104 @@
|
|||
|
||||
package eu.dnetlib.dhp.actionmanager.fosnodoi;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.nio.file.Files;
|
||||
import java.nio.file.Path;
|
||||
|
||||
import org.apache.commons.io.FileUtils;
|
||||
import org.apache.hadoop.conf.Configuration;
|
||||
import org.apache.hadoop.fs.FileSystem;
|
||||
import org.apache.hadoop.fs.LocalFileSystem;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.JavaRDD;
|
||||
import org.apache.spark.api.java.JavaSparkContext;
|
||||
import org.apache.spark.sql.SparkSession;
|
||||
import org.junit.jupiter.api.*;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.GetFOSSparkJob;
|
||||
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.PrepareTest;
|
||||
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.ProduceTest;
|
||||
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.model.FOSDataModel;
|
||||
|
||||
/**
|
||||
* @author miriam.baglioni
|
||||
* @Date 13/02/23
|
||||
*/
|
||||
public class GetFosTest {
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(ProduceTest.class);
|
||||
|
||||
private static Path workingDir;
|
||||
private static SparkSession spark;
|
||||
private static LocalFileSystem fs;
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
@BeforeAll
|
||||
public static void beforeAll() throws IOException {
|
||||
workingDir = Files.createTempDirectory(PrepareTest.class.getSimpleName());
|
||||
|
||||
fs = FileSystem.getLocal(new Configuration());
|
||||
log.info("using work dir {}", workingDir);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
conf.setAppName(ProduceTest.class.getSimpleName());
|
||||
|
||||
conf.setMaster("local[*]");
|
||||
conf.set("spark.driver.host", "localhost");
|
||||
conf.set("hive.metastore.local", "true");
|
||||
conf.set("spark.ui.enabled", "false");
|
||||
conf.set("spark.sql.warehouse.dir", workingDir.toString());
|
||||
conf.set("hive.metastore.warehouse.dir", workingDir.resolve("warehouse").toString());
|
||||
|
||||
spark = SparkSession
|
||||
.builder()
|
||||
.appName(PrepareTest.class.getSimpleName())
|
||||
.config(conf)
|
||||
.getOrCreate();
|
||||
}
|
||||
|
||||
@AfterAll
|
||||
public static void afterAll() throws IOException {
|
||||
FileUtils.deleteDirectory(workingDir.toFile());
|
||||
spark.stop();
|
||||
}
|
||||
|
||||
@Test
|
||||
@Disabled
|
||||
void test3() throws Exception {
|
||||
final String sourcePath = getClass()
|
||||
.getResource("/eu/dnetlib/dhp/actionmanager/fosnodoi/fosnodoi.csv")
|
||||
.getPath();
|
||||
|
||||
final String outputPath = workingDir.toString() + "/fos.json";
|
||||
GetFOSSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"--isSparkSessionManaged", Boolean.FALSE.toString(),
|
||||
"--sourcePath", sourcePath,
|
||||
|
||||
"-outputPath", outputPath,
|
||||
"-delimiter", ","
|
||||
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<FOSDataModel> tmp = sc
|
||||
.textFile(outputPath)
|
||||
.map(item -> OBJECT_MAPPER.readValue(item, FOSDataModel.class));
|
||||
|
||||
tmp.foreach(t -> Assertions.assertTrue(t.getOaid() != null));
|
||||
tmp.foreach(t -> Assertions.assertTrue(t.getLevel1() != null));
|
||||
tmp.foreach(t -> Assertions.assertTrue(t.getLevel2() != null));
|
||||
tmp.foreach(t -> Assertions.assertTrue(t.getLevel3() != null));
|
||||
|
||||
tmp.foreach(t -> System.out.println(new ObjectMapper().writeValueAsString(t)));
|
||||
|
||||
}
|
||||
|
||||
}
|
|
@ -0,0 +1,99 @@
|
|||
|
||||
package eu.dnetlib.dhp.actionmanager.fosnodoi;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.assertEquals;
|
||||
import static org.junit.jupiter.api.Assertions.assertTrue;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.nio.file.Files;
|
||||
import java.nio.file.Path;
|
||||
|
||||
import org.apache.commons.io.FileUtils;
|
||||
import org.apache.hadoop.conf.Configuration;
|
||||
import org.apache.hadoop.fs.FileSystem;
|
||||
import org.apache.hadoop.fs.LocalFileSystem;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.JavaRDD;
|
||||
import org.apache.spark.api.java.JavaSparkContext;
|
||||
import org.apache.spark.sql.SparkSession;
|
||||
import org.junit.jupiter.api.AfterAll;
|
||||
import org.junit.jupiter.api.Assertions;
|
||||
import org.junit.jupiter.api.BeforeAll;
|
||||
import org.junit.jupiter.api.Test;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.PrepareFOSSparkJob;
|
||||
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.PrepareSDGSparkJob;
|
||||
import eu.dnetlib.dhp.actionmanager.createunresolvedentities.ProduceTest;
|
||||
import eu.dnetlib.dhp.schema.oaf.Result;
|
||||
|
||||
public class PrepareTest {
|
||||
|
||||
private static final Logger log = LoggerFactory.getLogger(ProduceTest.class);
|
||||
|
||||
private static Path workingDir;
|
||||
private static SparkSession spark;
|
||||
private static LocalFileSystem fs;
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
@BeforeAll
|
||||
public static void beforeAll() throws IOException {
|
||||
workingDir = Files.createTempDirectory(PrepareTest.class.getSimpleName());
|
||||
|
||||
fs = FileSystem.getLocal(new Configuration());
|
||||
log.info("using work dir {}", workingDir);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
conf.setAppName(ProduceTest.class.getSimpleName());
|
||||
|
||||
conf.setMaster("local[*]");
|
||||
conf.set("spark.driver.host", "localhost");
|
||||
conf.set("hive.metastore.local", "true");
|
||||
conf.set("spark.ui.enabled", "false");
|
||||
conf.set("spark.sql.warehouse.dir", workingDir.toString());
|
||||
conf.set("hive.metastore.warehouse.dir", workingDir.resolve("warehouse").toString());
|
||||
|
||||
spark = SparkSession
|
||||
.builder()
|
||||
.appName(PrepareTest.class.getSimpleName())
|
||||
.config(conf)
|
||||
.getOrCreate();
|
||||
}
|
||||
|
||||
@AfterAll
|
||||
public static void afterAll() throws IOException {
|
||||
FileUtils.deleteDirectory(workingDir.toFile());
|
||||
spark.stop();
|
||||
}
|
||||
|
||||
@Test
|
||||
void fosPrepareTest() throws Exception {
|
||||
final String sourcePath = getClass()
|
||||
.getResource("/eu/dnetlib/dhp/actionmanager/fosnodoi/fosnodoi.json")
|
||||
.getPath();
|
||||
|
||||
PrepareFOSSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"--isSparkSessionManaged", Boolean.FALSE.toString(),
|
||||
"--sourcePath", sourcePath,
|
||||
|
||||
"-outputPath", workingDir.toString() + "/work",
|
||||
"-distributeDoi", Boolean.FALSE.toString()
|
||||
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = JavaSparkContext.fromSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Result> tmp = sc
|
||||
.textFile(workingDir.toString() + "/work/fos")
|
||||
.map(item -> OBJECT_MAPPER.readValue(item, Result.class));
|
||||
|
||||
tmp.foreach(t -> System.out.println(new ObjectMapper().writeValueAsString(t)));
|
||||
|
||||
}
|
||||
|
||||
}
|
|
@ -0,0 +1,324 @@
|
|||
|
||||
package eu.dnetlib.dhp.actionmanager.transformativeagreement;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.assertEquals;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.nio.file.Files;
|
||||
import java.nio.file.Path;
|
||||
|
||||
import org.apache.commons.io.FileUtils;
|
||||
import org.apache.hadoop.io.Text;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.JavaRDD;
|
||||
import org.apache.spark.api.java.JavaSparkContext;
|
||||
import org.apache.spark.sql.SparkSession;
|
||||
import org.junit.jupiter.api.AfterAll;
|
||||
import org.junit.jupiter.api.BeforeAll;
|
||||
import org.junit.jupiter.api.Test;
|
||||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import com.fasterxml.jackson.databind.ObjectMapper;
|
||||
|
||||
import eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob;
|
||||
import eu.dnetlib.dhp.actionmanager.opencitations.CreateOpenCitationsASTest;
|
||||
import eu.dnetlib.dhp.schema.action.AtomicAction;
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants;
|
||||
import eu.dnetlib.dhp.schema.oaf.Relation;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.CleaningFunctions;
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory;
|
||||
|
||||
/**
|
||||
* @author miriam.baglioni
|
||||
* @Date 13/02/24
|
||||
*/
|
||||
public class CreateTAActionSetTest {
|
||||
private static final ObjectMapper OBJECT_MAPPER = new ObjectMapper();
|
||||
|
||||
private static SparkSession spark;
|
||||
|
||||
private static Path workingDir;
|
||||
private static final Logger log = LoggerFactory
|
||||
.getLogger(CreateOpenCitationsASTest.class);
|
||||
|
||||
@BeforeAll
|
||||
public static void beforeAll() throws IOException {
|
||||
workingDir = Files
|
||||
.createTempDirectory(CreateTAActionSetTest.class.getSimpleName());
|
||||
log.info("using work dir {}", workingDir);
|
||||
|
||||
SparkConf conf = new SparkConf();
|
||||
conf.setAppName(CreateTAActionSetTest.class.getSimpleName());
|
||||
|
||||
conf.setMaster("local[*]");
|
||||
conf.set("spark.driver.host", "localhost");
|
||||
conf.set("hive.metastore.local", "true");
|
||||
conf.set("spark.ui.enabled", "false");
|
||||
conf.set("spark.sql.warehouse.dir", workingDir.toString());
|
||||
conf.set("hive.metastore.warehouse.dir", workingDir.resolve("warehouse").toString());
|
||||
|
||||
spark = SparkSession
|
||||
.builder()
|
||||
.appName(CreateTAActionSetTest.class.getSimpleName())
|
||||
.config(conf)
|
||||
.getOrCreate();
|
||||
}
|
||||
|
||||
@AfterAll
|
||||
public static void afterAll() throws IOException {
|
||||
FileUtils.deleteDirectory(workingDir.toFile());
|
||||
spark.stop();
|
||||
}
|
||||
|
||||
@Test
|
||||
void createActionSet() throws Exception {
|
||||
|
||||
String inputPath = getClass()
|
||||
.getResource(
|
||||
"/eu/dnetlib/dhp/actionmanager/transformativeagreement/facts.json")
|
||||
.getPath();
|
||||
|
||||
eu.dnetlib.dhp.actionmanager.transformativeagreement.CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet1"
|
||||
});
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
void testNumberofRelations2() throws Exception {
|
||||
|
||||
String inputPath = getClass()
|
||||
.getResource(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
|
||||
.getPath();
|
||||
|
||||
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet2"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet2", Text.class, Text.class)
|
||||
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
|
||||
.map(aa -> ((Relation) aa.getPayload()));
|
||||
|
||||
assertEquals(23, tmp.count());
|
||||
|
||||
// tmp.foreach(r -> System.out.println(OBJECT_MAPPER.writeValueAsString(r)));
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
void testRelationsCollectedFrom() throws Exception {
|
||||
|
||||
String inputPath = getClass()
|
||||
.getResource(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
|
||||
.getPath();
|
||||
|
||||
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet3"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet3", Text.class, Text.class)
|
||||
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
|
||||
.map(aa -> ((Relation) aa.getPayload()));
|
||||
|
||||
tmp.foreach(r -> {
|
||||
assertEquals(ModelConstants.OPENOCITATIONS_NAME, r.getCollectedfrom().get(0).getValue());
|
||||
assertEquals(ModelConstants.OPENOCITATIONS_ID, r.getCollectedfrom().get(0).getKey());
|
||||
});
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
void testRelationsDataInfo() throws Exception {
|
||||
|
||||
String inputPath = getClass()
|
||||
.getResource(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
|
||||
.getPath();
|
||||
|
||||
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet4"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet4", Text.class, Text.class)
|
||||
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
|
||||
.map(aa -> ((Relation) aa.getPayload()));
|
||||
|
||||
tmp.foreach(r -> {
|
||||
assertEquals(false, r.getDataInfo().getInferred());
|
||||
assertEquals(false, r.getDataInfo().getDeletedbyinference());
|
||||
assertEquals("0.91", r.getDataInfo().getTrust());
|
||||
assertEquals(
|
||||
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob.OPENCITATIONS_CLASSID,
|
||||
r.getDataInfo().getProvenanceaction().getClassid());
|
||||
assertEquals(
|
||||
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob.OPENCITATIONS_CLASSNAME,
|
||||
r.getDataInfo().getProvenanceaction().getClassname());
|
||||
assertEquals(ModelConstants.DNET_PROVENANCE_ACTIONS, r.getDataInfo().getProvenanceaction().getSchemeid());
|
||||
assertEquals(ModelConstants.DNET_PROVENANCE_ACTIONS, r.getDataInfo().getProvenanceaction().getSchemename());
|
||||
});
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
void testRelationsSemantics() throws Exception {
|
||||
|
||||
String inputPath = getClass()
|
||||
.getResource(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
|
||||
.getPath();
|
||||
|
||||
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet5"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet5", Text.class, Text.class)
|
||||
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
|
||||
.map(aa -> ((Relation) aa.getPayload()));
|
||||
|
||||
tmp.foreach(r -> {
|
||||
assertEquals("citation", r.getSubRelType());
|
||||
assertEquals("resultResult", r.getRelType());
|
||||
});
|
||||
assertEquals(23, tmp.filter(r -> r.getRelClass().equals("Cites")).count());
|
||||
assertEquals(0, tmp.filter(r -> r.getRelClass().equals("IsCitedBy")).count());
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
void testRelationsSourceTargetPrefix() throws Exception {
|
||||
|
||||
String inputPath = getClass()
|
||||
.getResource(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
|
||||
.getPath();
|
||||
|
||||
eu.dnetlib.dhp.actionmanager.opencitations.CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet6"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet6", Text.class, Text.class)
|
||||
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
|
||||
.map(aa -> ((Relation) aa.getPayload()));
|
||||
|
||||
tmp.foreach(r -> {
|
||||
assertEquals("50|doi_________::", r.getSource().substring(0, 17));
|
||||
assertEquals("50|doi_________::", r.getTarget().substring(0, 17));
|
||||
});
|
||||
|
||||
}
|
||||
|
||||
@Test
|
||||
void testRelationsSourceTargetCouple() throws Exception {
|
||||
final String doi1 = "50|doi_________::"
|
||||
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1007/s10854-015-3684-x"));
|
||||
final String doi2 = "50|doi_________::"
|
||||
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1111/j.1551-2916.2008.02408.x"));
|
||||
final String doi3 = "50|doi_________::"
|
||||
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1007/s10854-014-2114-9"));
|
||||
final String doi4 = "50|doi_________::"
|
||||
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1016/j.ceramint.2013.09.069"));
|
||||
final String doi5 = "50|doi_________::"
|
||||
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1007/s10854-009-9913-4"));
|
||||
final String doi6 = "50|doi_________::"
|
||||
+ IdentifierFactory.md5(CleaningFunctions.normalizePidValue("doi", "10.1016/0038-1098(72)90370-5"));
|
||||
|
||||
String inputPath = getClass()
|
||||
.getResource(
|
||||
"/eu/dnetlib/dhp/actionmanager/opencitations/COCI")
|
||||
.getPath();
|
||||
|
||||
CreateActionSetSparkJob
|
||||
.main(
|
||||
new String[] {
|
||||
"-isSparkSessionManaged",
|
||||
Boolean.FALSE.toString(),
|
||||
"-inputPath",
|
||||
inputPath,
|
||||
"-outputPath",
|
||||
workingDir.toString() + "/actionSet7"
|
||||
});
|
||||
|
||||
final JavaSparkContext sc = new JavaSparkContext(spark.sparkContext());
|
||||
|
||||
JavaRDD<Relation> tmp = sc
|
||||
.sequenceFile(workingDir.toString() + "/actionSet7", Text.class, Text.class)
|
||||
.map(value -> OBJECT_MAPPER.readValue(value._2().toString(), AtomicAction.class))
|
||||
.map(aa -> ((Relation) aa.getPayload()));
|
||||
|
||||
JavaRDD<Relation> check = tmp.filter(r -> r.getSource().equals(doi1) || r.getTarget().equals(doi1));
|
||||
|
||||
assertEquals(5, check.count());
|
||||
|
||||
// check.foreach(r -> {
|
||||
// if (r.getSource().equals(doi2) || r.getSource().equals(doi3) || r.getSource().equals(doi4) ||
|
||||
// r.getSource().equals(doi5) || r.getSource().equals(doi6)) {
|
||||
// assertEquals(ModelConstants.IS_CITED_BY, r.getRelClass());
|
||||
// assertEquals(doi1, r.getTarget());
|
||||
// }
|
||||
// });
|
||||
|
||||
assertEquals(5, check.filter(r -> r.getSource().equals(doi1)).count());
|
||||
check.filter(r -> r.getSource().equals(doi1)).foreach(r -> assertEquals(ModelConstants.CITES, r.getRelClass()));
|
||||
|
||||
}
|
||||
}
|
|
@ -2,6 +2,7 @@
|
|||
package eu.dnetlib.dhp.collection.orcid;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.net.URI;
|
||||
import java.util.Arrays;
|
||||
import java.util.List;
|
||||
import java.util.Objects;
|
||||
|
@ -9,7 +10,12 @@ import java.util.Objects;
|
|||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.hadoop.conf.Configuration;
|
||||
import org.apache.hadoop.fs.FileSystem;
|
||||
import org.apache.hadoop.fs.LocalFileSystem;
|
||||
import org.apache.hadoop.fs.Path;
|
||||
import org.apache.hadoop.io.SequenceFile;
|
||||
import org.apache.hadoop.io.Text;
|
||||
import org.apache.hadoop.io.compress.CompressionCodec;
|
||||
import org.apache.hadoop.io.compress.CompressionCodecFactory;
|
||||
import org.apache.spark.SparkContext;
|
||||
import org.apache.spark.api.java.JavaSparkContext;
|
||||
import org.apache.spark.sql.Encoders;
|
||||
|
@ -27,6 +33,7 @@ import com.ximpleware.XPathParseException;
|
|||
|
||||
import eu.dnetlib.dhp.collection.orcid.model.Author;
|
||||
import eu.dnetlib.dhp.collection.orcid.model.ORCIDItem;
|
||||
import eu.dnetlib.dhp.collection.orcid.model.Work;
|
||||
import eu.dnetlib.dhp.parser.utility.VtdException;
|
||||
|
||||
public class DownloadORCIDTest {
|
||||
|
@ -82,6 +89,34 @@ public class DownloadORCIDTest {
|
|||
});
|
||||
}
|
||||
|
||||
@Test
|
||||
public void testParsingOrcidUpdateEmployments() throws Exception {
|
||||
final String xml = IOUtils
|
||||
.toString(
|
||||
Objects
|
||||
.requireNonNull(
|
||||
getClass().getResourceAsStream("/eu/dnetlib/dhp/collection/orcid/update_employments.xml")));
|
||||
|
||||
final OrcidParser parser = new OrcidParser();
|
||||
final ObjectMapper mapper = new ObjectMapper();
|
||||
System.out.println(mapper.writeValueAsString(parser.parseEmployments(xml)));
|
||||
}
|
||||
|
||||
@Test
|
||||
public void testParsingOrcidUpdateWorks() throws Exception {
|
||||
final String xml = IOUtils
|
||||
.toString(
|
||||
Objects
|
||||
.requireNonNull(
|
||||
getClass().getResourceAsStream("/eu/dnetlib/dhp/collection/orcid/update_work.xml")));
|
||||
|
||||
final OrcidParser parser = new OrcidParser();
|
||||
final List<Work> works = parser.parseWorks(xml);
|
||||
|
||||
final ObjectMapper mapper = new ObjectMapper();
|
||||
System.out.println(mapper.writeValueAsString(works));
|
||||
}
|
||||
|
||||
@Test
|
||||
public void testParsingEmployments() throws Exception {
|
||||
|
||||
|
|
|
@ -1,6 +1,8 @@
|
|||
|
||||
package eu.dnetlib.dhp.collection.plugin.base;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.assertThrows;
|
||||
|
||||
import java.io.IOException;
|
||||
|
||||
import org.apache.commons.io.IOUtils;
|
||||
|
@ -8,7 +10,6 @@ import org.apache.spark.SparkConf;
|
|||
import org.apache.spark.util.LongAccumulator;
|
||||
import org.dom4j.io.SAXReader;
|
||||
import org.junit.jupiter.api.BeforeEach;
|
||||
import org.junit.jupiter.api.Disabled;
|
||||
import org.junit.jupiter.api.Test;
|
||||
import org.junit.jupiter.api.extension.ExtendWith;
|
||||
import org.mockito.junit.jupiter.MockitoExtension;
|
||||
|
@ -20,7 +21,7 @@ import eu.dnetlib.dhp.schema.mdstore.Provenance;
|
|||
import eu.dnetlib.dhp.transformation.xslt.XSLTTransformationFunction;
|
||||
import eu.dnetlib.enabling.is.lookup.rmi.ISLookUpException;
|
||||
|
||||
@Disabled
|
||||
// @Disabled
|
||||
@ExtendWith(MockitoExtension.class)
|
||||
public class BaseTransfomationTest extends AbstractVocabularyTest {
|
||||
|
||||
|
@ -64,11 +65,26 @@ public class BaseTransfomationTest extends AbstractVocabularyTest {
|
|||
System.out.println(result.getBody());
|
||||
}
|
||||
|
||||
@Test
|
||||
void testBase2ODF_wrong_date() throws Exception {
|
||||
|
||||
final MetadataRecord mr = new MetadataRecord();
|
||||
mr.setProvenance(new Provenance("DSID", "DSNAME", "PREFIX"));
|
||||
mr.setBody(IOUtils.toString(getClass().getResourceAsStream("record_wrong_1.xml")));
|
||||
|
||||
final XSLTTransformationFunction tr = loadTransformationRule("xml/base2oaf.transformationRule.xml");
|
||||
|
||||
assertThrows(NullPointerException.class, () -> {
|
||||
final MetadataRecord result = tr.call(mr);
|
||||
System.out.println(result.getBody());
|
||||
});
|
||||
}
|
||||
|
||||
private XSLTTransformationFunction loadTransformationRule(final String path) throws Exception {
|
||||
final String xslt = new SAXReader()
|
||||
.read(this.getClass().getResourceAsStream(path))
|
||||
.selectSingleNode("//CODE/*")
|
||||
.asXML();
|
||||
.read(this.getClass().getResourceAsStream(path))
|
||||
.selectSingleNode("//CODE/*")
|
||||
.asXML();
|
||||
|
||||
final LongAccumulator la = new LongAccumulator();
|
||||
|
||||
|
|
|
@ -9,6 +9,7 @@ import org.junit.jupiter.api.Test;
|
|||
import org.slf4j.Logger;
|
||||
import org.slf4j.LoggerFactory;
|
||||
|
||||
import eu.dnetlib.dhp.common.collection.CollectorException;
|
||||
import eu.dnetlib.dhp.common.collection.HttpClientParams;
|
||||
|
||||
/**
|
||||
|
@ -37,7 +38,7 @@ public class RestIteratorTest {
|
|||
|
||||
@Disabled
|
||||
@Test
|
||||
public void test() {
|
||||
public void test() throws CollectorException {
|
||||
|
||||
HttpClientParams clientParams = new HttpClientParams();
|
||||
|
||||
|
|
|
@ -0,0 +1,48 @@
|
|||
|
||||
package eu.dnetlib.dhp.collection.plugin.utils;
|
||||
|
||||
import static org.junit.jupiter.api.Assertions.assertEquals;
|
||||
|
||||
import org.junit.jupiter.api.Test;
|
||||
|
||||
class JsonUtilsTest {
|
||||
|
||||
static private String wrapped(String xml) {
|
||||
return "<?xml version=\"1.0\" encoding=\"UTF-8\"?><recordWrap>" + xml + "</recordWrap>";
|
||||
}
|
||||
|
||||
@Test
|
||||
void keyStartWithDigit() {
|
||||
assertEquals(
|
||||
wrapped("<m_100><n_200v>null</n_200v></m_100>"),
|
||||
JsonUtils.convertToXML("{\"100\" : {\"200v\" : null}}"));
|
||||
}
|
||||
|
||||
@Test
|
||||
void keyStartWithSpecialchars() {
|
||||
assertEquals(
|
||||
wrapped("<_parent><_nest1><_nest2>null</_nest2></_nest1></_parent>"),
|
||||
JsonUtils.convertToXML("{\" parent\" : {\"-nest1\" : {\".nest2\" : null}}}"));
|
||||
}
|
||||
|
||||
@Test
|
||||
void encodeArray() {
|
||||
assertEquals(
|
||||
wrapped("<_parent.child>1</_parent.child><_parent.child>2</_parent.child>"),
|
||||
JsonUtils.convertToXML("{\" parent.child\":[1, 2]}"));
|
||||
}
|
||||
|
||||
@Test
|
||||
void arrayOfObjects() {
|
||||
assertEquals(
|
||||
wrapped("<parent><id>1</id></parent><parent><id>2</id></parent>"),
|
||||
JsonUtils.convertToXML("{\"parent\": [{\"id\": 1}, {\"id\": 2}]}"));
|
||||
}
|
||||
|
||||
@Test
|
||||
void removeControlCharacters() {
|
||||
assertEquals(
|
||||
wrapped("<m_100><n_200v>Test</n_200v></m_100>"),
|
||||
JsonUtils.convertToXML("{\"100\" : {\"200v\" : \"\\u0000\\u000cTest\"}}"));
|
||||
}
|
||||
}
|
|
@ -3,6 +3,7 @@ package eu.dnetlib.dhp.transformation;
|
|||
|
||||
import static eu.dnetlib.dhp.common.Constants.MDSTORE_DATA_PATH;
|
||||
import static org.junit.jupiter.api.Assertions.assertEquals;
|
||||
import static org.junit.jupiter.api.Assertions.assertThrows;
|
||||
|
||||
import java.io.IOException;
|
||||
import java.nio.file.Path;
|
||||
|
@ -279,6 +280,19 @@ class TransformationJobTest extends AbstractVocabularyTest {
|
|||
// TODO Create significant Assert
|
||||
}
|
||||
|
||||
@Test
|
||||
public void testInvalidXSLT() throws Exception{
|
||||
final MetadataRecord mr = new MetadataRecord();
|
||||
|
||||
mr.setProvenance(new Provenance("openaire____::cnr_explora", "CNR ExploRA", "cnr_________"));
|
||||
mr.setBody(IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/transform/input_cnr_explora.xml")));
|
||||
// We Load the XSLT transformation Rule from the classpath
|
||||
final XSLTTransformationFunction tr = loadTransformationRule("/eu/dnetlib/dhp/transform/invalid.xslt");
|
||||
|
||||
assertThrows(RuntimeException.class,()->tr.call(mr));
|
||||
|
||||
}
|
||||
|
||||
private XSLTTransformationFunction loadTransformationRule(final String path) throws Exception {
|
||||
final String trValue = IOUtils.toString(this.getClass().getResourceAsStream(path));
|
||||
final LongAccumulator la = new LongAccumulator();
|
||||
|
|
|
@ -0,0 +1,19 @@
|
|||
DOI,OAID,level1,level2,level3,level4,score_for_L3,score_for_L4
|
||||
N/A,78975075580c::e680668c98366c9cd6349afc62486a7f,03 medical and health sciences,0301 basic medicine,030104 developmental biology,N/A,0.5,0.0
|
||||
N/A,78975075580c::e680668c98366c9cd6349afc62486a7f,03 medical and health sciences,0303 health sciences,030304 developmental biology,N/A,0.5,0.0
|
||||
N/A,od______2806::a1da9d2678b12969a9ab5f50b5e71d0a,05 social sciences,0501 psychology and cognitive sciences,050109 social psychology,05010904 Group processes/Collective identity,0.5589094161987305,0.5166763067245483
|
||||
N/A,od______2806::a1da9d2678b12969a9ab5f50b5e71d0a,05 social sciences,0501 psychology and cognitive sciences,050105 experimental psychology,05010501 Emotion/Affective science,0.44109055399894714,0.4833236634731293
|
||||
N/A,doajarticles::76535d77fd2a5fe9810aefafffb8ef6c,05 social sciences,0502 economics and business,050203 business & management,05020302 Supply chain management/Business terms,0.5459638833999634,0.5460261106491089
|
||||
N/A,doajarticles::76535d77fd2a5fe9810aefafffb8ef6c,05 social sciences,0502 economics and business,050211 marketing,05021102 Services marketing/Retailing,0.4540362060070038,0.4539738595485687
|
||||
N/A,od_______156::a3a0119c6d9d3a66943f8da042e97a5e,01 natural sciences,0105 earth and related environmental sciences,010504 meteorology & atmospheric sciences,01050407 Geomagnetism/Ionosphere,0.5131047964096069,0.4990350902080536
|
||||
N/A,od_______156::a3a0119c6d9d3a66943f8da042e97a5e,01 natural sciences,0105 earth and related environmental sciences,010502 geochemistry & geophysics,01050203 Seismology/Seismology measurement,0.4868951737880707,0.500964879989624
|
||||
N/A,od______2806::4b9a664dd6b8b04204cb613e7bc9c873,03 medical and health sciences,0302 clinical medicine,030220 oncology & carcinogenesis,03022002 Medical imaging/Medical physics,0.5068133473396301,0.10231181626910052
|
||||
N/A,od______2806::4b9a664dd6b8b04204cb613e7bc9c873,03 medical and health sciences,0302 clinical medicine,030204 cardiovascular system & hematology,N/A,0.49318668246269226,0.0
|
||||
N/A,od______3341::ef754de29464abf9bc9b99664630ce74,03 medical and health sciences,0302 clinical medicine,030220 oncology & carcinogenesis,03022012 Oncology/Infectious causes of cancer,0.5,0.5
|
||||
N/A,od______3341::ef754de29464abf9bc9b99664630ce74,03 medical and health sciences,0302 clinical medicine,030220 oncology & carcinogenesis,03022012 Oncology/Infectious causes of cancer,0.5,0.5
|
||||
N/A,od______3978::6704dcced0fe3dd6fbf985dc2507f61c,03 medical and health sciences,0302 clinical medicine,030217 neurology & neurosurgery,03021702 Aging-associated diseases/Cognitive disorders,0.5134317874908447,0.09614889098529535
|
||||
N/A,od______3978::6704dcced0fe3dd6fbf985dc2507f61c,03 medical and health sciences,0301 basic medicine,030104 developmental biology,N/A,0.48656824231147766,0.0
|
||||
N/A,dedup_wf_001::b77264819800b90c0328c4d17eea5c1a,02 engineering and technology,0209 industrial biotechnology,020901 industrial engineering & automation,02090105 Control theory/Advanced driver assistance systems,0.5178514122962952,0.5198937654495239
|
||||
N/A,dedup_wf_001::b77264819800b90c0328c4d17eea5c1a,02 engineering and technology,"0202 electrical engineering, electronic engineering, information engineering",020201 artificial intelligence & image processing,02020108 Fuzzy logic/Artificial neural networks/Computational neuroscience,0.48214852809906006,0.4801062345504761
|
||||
N/A,od______2806::a938609e9f36ada6629a1bcc50c88230,03 medical and health sciences,0302 clinical medicine,030217 neurology & neurosurgery,03021708 Neurotrauma/Stroke,0.5014800429344177,0.5109656453132629
|
||||
N/A,od______2806::a938609e9f36ada6629a1bcc50c88230,02 engineering and technology,0206 medical engineering,020601 biomedical engineering,02060102 Medical terminology/Patient,0.4985199570655823,0.4890343248844147
|
|
|
@ -0,0 +1,18 @@
|
|||
{"doi":"n/a","oaid":"od______3341::ef754de29464abf9bc9b99664630ce74","level1":"03 medical and health sciences","level2":"0302 clinical medicine","level3":"030220 oncology & carcinogenesis","level4":"03022012 Oncology/Infectious causes of cancer","scoreL3":"0.5","scoreL4":"0.5"}
|
||||
{"doi":"n/a","oaid":"78975075580c::e680668c98366c9cd6349afc62486a7f","level1":"03 medical and health sciences","level2":"0301 basic medicine","level3":"030104 developmental biology","level4":"N/A","scoreL3":"0.5","scoreL4":"0.0"}
|
||||
{"doi":"n/a","oaid":"od______3341::ef754de29464abf9bc9b99664630ce74","level1":"03 medical and health sciences","level2":"0302 clinical medicine","level3":"030220 oncology & carcinogenesis","level4":"03022012 Oncology/Infectious causes of cancer","scoreL3":"0.5","scoreL4":"0.5"}
|
||||
{"doi":"n/a","oaid":"78975075580c::e680668c98366c9cd6349afc62486a7f","level1":"03 medical and health sciences","level2":"0303 health sciences","level3":"030304 developmental biology","level4":"N/A","scoreL3":"0.5","scoreL4":"0.0"}
|
||||
{"doi":"n/a","oaid":"od______3978::6704dcced0fe3dd6fbf985dc2507f61c","level1":"03 medical and health sciences","level2":"0302 clinical medicine","level3":"030217 neurology & neurosurgery","level4":"03021702 Aging-associated diseases/Cognitive disorders","scoreL3":"0.5134317874908447","scoreL4":"0.09614889098529535"}
|
||||
{"doi":"n/a","oaid":"od______2806::a1da9d2678b12969a9ab5f50b5e71d0a","level1":"05 social sciences","level2":"0501 psychology and cognitive sciences","level3":"050109 social psychology","level4":"05010904 Group processes/Collective identity","scoreL3":"0.5589094161987305","scoreL4":"0.5166763067245483"}
|
||||
{"doi":"n/a","oaid":"od______3978::6704dcced0fe3dd6fbf985dc2507f61c","level1":"03 medical and health sciences","level2":"0301 basic medicine","level3":"030104 developmental biology","level4":"N/A","scoreL3":"0.48656824231147766","scoreL4":"0.0"}
|
||||
{"doi":"n/a","oaid":"od______2806::a1da9d2678b12969a9ab5f50b5e71d0a","level1":"05 social sciences","level2":"0501 psychology and cognitive sciences","level3":"050105 experimental psychology","level4":"05010501 Emotion/Affective science","scoreL3":"0.44109055399894714","scoreL4":"0.4833236634731293"}
|
||||
{"doi":"n/a","oaid":"dedup_wf_001::b77264819800b90c0328c4d17eea5c1a","level1":"02 engineering and technology","level2":"0209 industrial biotechnology","level3":"020901 industrial engineering & automation","level4":"02090105 Control theory/Advanced driver assistance systems","scoreL3":"0.5178514122962952","scoreL4":"0.5198937654495239"}
|
||||
{"doi":"n/a","oaid":"doajarticles::76535d77fd2a5fe9810aefafffb8ef6c","level1":"05 social sciences","level2":"0502 economics and business","level3":"050203 business & management","level4":"05020302 Supply chain management/Business terms","scoreL3":"0.5459638833999634","scoreL4":"0.5460261106491089"}
|
||||
{"doi":"n/a","oaid":"doajarticles::76535d77fd2a5fe9810aefafffb8ef6c","level1":"05 social sciences","level2":"0502 economics and business","level3":"050211 marketing","level4":"05021102 Services marketing/Retailing","scoreL3":"0.4540362060070038","scoreL4":"0.4539738595485687"}
|
||||
{"doi":"n/a","oaid":"dedup_wf_001::b77264819800b90c0328c4d17eea5c1a","level1":"02 engineering and technology","level2":"0202 electrical engineering, electronic engineering, information engineering","level3":"020201 artificial intelligence & image processing","level4":"02020108 Fuzzy logic/Artificial neural networks/Computational neuroscience","scoreL3":"0.48214852809906006","scoreL4":"0.4801062345504761"}
|
||||
{"doi":"n/a","oaid":"od_______156::a3a0119c6d9d3a66943f8da042e97a5e","level1":"01 natural sciences","level2":"0105 earth and related environmental sciences","level3":"010504 meteorology & atmospheric sciences","level4":"01050407 Geomagnetism/Ionosphere","scoreL3":"0.5131047964096069","scoreL4":"0.4990350902080536"}
|
||||
{"doi":"n/a","oaid":"od______2806::a938609e9f36ada6629a1bcc50c88230","level1":"03 medical and health sciences","level2":"0302 clinical medicine","level3":"030217 neurology & neurosurgery","level4":"03021708 Neurotrauma/Stroke","scoreL3":"0.5014800429344177","scoreL4":"0.5109656453132629"}
|
||||
{"doi":"n/a","oaid":"od_______156::a3a0119c6d9d3a66943f8da042e97a5e","level1":"01 natural sciences","level2":"0105 earth and related environmental sciences","level3":"010502 geochemistry & geophysics","level4":"01050203 Seismology/Seismology measurement","scoreL3":"0.4868951737880707","scoreL4":"0.500964879989624"}
|
||||
{"doi":"n/a","oaid":"od______2806::a938609e9f36ada6629a1bcc50c88230","level1":"02 engineering and technology","level2":"0206 medical engineering","level3":"020601 biomedical engineering","level4":"02060102 Medical terminology/Patient","scoreL3":"0.4985199570655823","scoreL4":"0.4890343248844147"}
|
||||
{"doi":"n/a","oaid":"od______2806::4b9a664dd6b8b04204cb613e7bc9c873","level1":"03 medical and health sciences","level2":"0302 clinical medicine","level3":"030220 oncology & carcinogenesis","level4":"03022002 Medical imaging/Medical physics","scoreL3":"0.5068133473396301","scoreL4":"0.10231181626910052"}
|
||||
{"doi":"n/a","oaid":"od______2806::4b9a664dd6b8b04204cb613e7bc9c873","level1":"03 medical and health sciences","level2":"0302 clinical medicine","level3":"030204 cardiovascular system & hematology","level4":"N/A","scoreL3":"0.49318668246269226","scoreL4":"0.0"}
|
File diff suppressed because one or more lines are too long
File diff suppressed because it is too large
Load Diff
|
@ -0,0 +1,966 @@
|
|||
<record:record path="/0000-0001-6816-8350" xmlns:internal="http://www.orcid.org/ns/internal" xmlns:education="http://www.orcid.org/ns/education" xmlns:distinction="http://www.orcid.org/ns/distinction" xmlns:deprecated="http://www.orcid.org/ns/deprecated" xmlns:other-name="http://www.orcid.org/ns/other-name" xmlns:membership="http://www.orcid.org/ns/membership" xmlns:error="http://www.orcid.org/ns/error" xmlns:common="http://www.orcid.org/ns/common" xmlns:record="http://www.orcid.org/ns/record" xmlns:personal-details="http://www.orcid.org/ns/personal-details" xmlns:keyword="http://www.orcid.org/ns/keyword" xmlns:email="http://www.orcid.org/ns/email" xmlns:external-identifier="http://www.orcid.org/ns/external-identifier" xmlns:funding="http://www.orcid.org/ns/funding" xmlns:preferences="http://www.orcid.org/ns/preferences" xmlns:address="http://www.orcid.org/ns/address" xmlns:invited-position="http://www.orcid.org/ns/invited-position" xmlns:work="http://www.orcid.org/ns/work" xmlns:history="http://www.orcid.org/ns/history" xmlns:employment="http://www.orcid.org/ns/employment" xmlns:qualification="http://www.orcid.org/ns/qualification" xmlns:service="http://www.orcid.org/ns/service" xmlns:person="http://www.orcid.org/ns/person" xmlns:activities="http://www.orcid.org/ns/activities" xmlns:researcher-url="http://www.orcid.org/ns/researcher-url" xmlns:peer-review="http://www.orcid.org/ns/peer-review" xmlns:bulk="http://www.orcid.org/ns/bulk" xmlns:research-resource="http://www.orcid.org/ns/research-resource">
|
||||
<common:orcid-identifier>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:orcid-identifier>
|
||||
<preferences:preferences>
|
||||
<preferences:locale>en</preferences:locale>
|
||||
</preferences:preferences>
|
||||
<history:history>
|
||||
<history:creation-method>Direct</history:creation-method>
|
||||
<history:submission-date>2016-01-06T05:08:45.720Z</history:submission-date>
|
||||
<common:last-modified-date>2024-01-02T20:07:05.186Z</common:last-modified-date>
|
||||
<history:claimed>true</history:claimed>
|
||||
<history:verified-email>true</history:verified-email>
|
||||
<history:verified-primary-email>true</history:verified-primary-email>
|
||||
</history:history>
|
||||
<person:person path="/0000-0001-6816-8350/person">
|
||||
<common:last-modified-date>2023-12-02T13:32:05.269Z</common:last-modified-date>
|
||||
<other-name:other-names path="/0000-0001-6816-8350/other-names"/>
|
||||
<researcher-url:researcher-urls path="/0000-0001-6816-8350/researcher-urls">
|
||||
<common:last-modified-date>2016-02-09T09:18:18.417Z</common:last-modified-date>
|
||||
<researcher-url:researcher-url put-code="633431" visibility="public" path="/0000-0001-6816-8350/researcher-urls/633431" display-index="0">
|
||||
<common:created-date>2016-02-09T09:18:18.416Z</common:created-date>
|
||||
<common:last-modified-date>2016-02-09T09:18:18.417Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<researcher-url:url-name>Dr Michael Muchiri</researcher-url:url-name>
|
||||
<researcher-url:url>http://www.rmit.edu.au/contact/staff-contacts/academic-staff/m/muchiri-dr-michael</researcher-url:url>
|
||||
</researcher-url:researcher-url>
|
||||
</researcher-url:researcher-urls>
|
||||
<email:emails path="/0000-0001-6816-8350/email"/>
|
||||
<address:addresses path="/0000-0001-6816-8350/address">
|
||||
<common:last-modified-date>2023-12-02T13:32:05.269Z</common:last-modified-date>
|
||||
<address:address put-code="897528" visibility="public" path="/0000-0001-6816-8350/address/897528" display-index="2">
|
||||
<common:created-date>2018-02-13T02:32:04.094Z</common:created-date>
|
||||
<common:last-modified-date>2023-12-02T13:32:05.269Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<address:country>AU</address:country>
|
||||
</address:address>
|
||||
<address:address put-code="3191142" visibility="public" path="/0000-0001-6816-8350/address/3191142" display-index="1">
|
||||
<common:created-date>2023-12-02T13:32:05.260Z</common:created-date>
|
||||
<common:last-modified-date>2023-12-02T13:32:05.260Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<address:country>SA</address:country>
|
||||
</address:address>
|
||||
</address:addresses>
|
||||
<keyword:keywords path="/0000-0001-6816-8350/keywords">
|
||||
<common:last-modified-date>2023-12-02T13:31:16.269Z</common:last-modified-date>
|
||||
<keyword:keyword put-code="368304" visibility="public" path="/0000-0001-6816-8350/keywords/368304" display-index="4">
|
||||
<common:created-date>2016-02-09T09:16:44.001Z</common:created-date>
|
||||
<common:last-modified-date>2023-12-02T13:31:16.269Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<keyword:content>Organizational Behavior</keyword:content>
|
||||
</keyword:keyword>
|
||||
<keyword:keyword put-code="368303" visibility="public" path="/0000-0001-6816-8350/keywords/368303" display-index="3">
|
||||
<common:created-date>2016-02-09T09:16:27.374Z</common:created-date>
|
||||
<common:last-modified-date>2023-12-02T13:31:16.269Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<keyword:content>Organizational Leadership</keyword:content>
|
||||
</keyword:keyword>
|
||||
<keyword:keyword put-code="368306" visibility="public" path="/0000-0001-6816-8350/keywords/368306" display-index="2">
|
||||
<common:created-date>2016-02-09T09:17:08.998Z</common:created-date>
|
||||
<common:last-modified-date>2023-12-02T13:31:16.269Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<keyword:content>Organizational performance</keyword:content>
|
||||
</keyword:keyword>
|
||||
<keyword:keyword put-code="3590814" visibility="public" path="/0000-0001-6816-8350/keywords/3590814" display-index="1">
|
||||
<common:created-date>2023-12-02T13:31:16.259Z</common:created-date>
|
||||
<common:last-modified-date>2023-12-02T13:31:16.259Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<keyword:content>Thriving at work</keyword:content>
|
||||
</keyword:keyword>
|
||||
</keyword:keywords>
|
||||
<external-identifier:external-identifiers path="/0000-0001-6816-8350/external-identifiers">
|
||||
<common:last-modified-date>2018-04-10T00:49:55.386Z</common:last-modified-date>
|
||||
<external-identifier:external-identifier put-code="998076" visibility="public" path="/0000-0001-6816-8350/external-identifiers/998076" display-index="0">
|
||||
<common:created-date>2018-04-10T00:49:55.385Z</common:created-date>
|
||||
<common:last-modified-date>2018-04-10T00:49:55.386Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-client-id>
|
||||
<common:uri>https://orcid.org/client/0000-0003-1377-5676</common:uri>
|
||||
<common:path>0000-0003-1377-5676</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-client-id>
|
||||
<common:source-name>ResearcherID</common:source-name>
|
||||
<common:assertion-origin-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:assertion-origin-orcid>
|
||||
</common:source>
|
||||
<common:external-id-type>ResearcherID</common:external-id-type>
|
||||
<common:external-id-value>D-1929-2018</common:external-id-value>
|
||||
<common:external-id-url>http://www.researcherid.com/rid/D-1929-2018</common:external-id-url>
|
||||
<common:external-id-relationship>self</common:external-id-relationship>
|
||||
</external-identifier:external-identifier>
|
||||
</external-identifier:external-identifiers>
|
||||
</person:person>
|
||||
<activities:activities-summary path="/0000-0001-6816-8350/activities">
|
||||
<common:last-modified-date>2023-12-02T13:28:26.051Z</common:last-modified-date>
|
||||
<activities:distinctions path="/0000-0001-6816-8350/distinctions"/>
|
||||
<activities:educations path="/0000-0001-6816-8350/educations">
|
||||
<common:last-modified-date>2018-02-13T02:33:38.225Z</common:last-modified-date>
|
||||
<activities:affiliation-group>
|
||||
<common:last-modified-date>2016-02-09T06:55:21.838Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<education:education-summary put-code="1549986" display-index="0" path="/0000-0001-6816-8350/education/1549986" visibility="public">
|
||||
<common:created-date>2016-02-09T06:54:39.199Z</common:created-date>
|
||||
<common:last-modified-date>2016-02-09T06:55:21.838Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<common:department-name>Management</common:department-name>
|
||||
<common:role-title>PhD</common:role-title>
|
||||
<common:start-date>
|
||||
<common:year>2021</common:year>
|
||||
</common:start-date>
|
||||
<common:end-date>
|
||||
<common:year>2022</common:year>
|
||||
<common:month>02</common:month>
|
||||
<common:day>12</common:day>
|
||||
</common:end-date>
|
||||
<common:start-date>
|
||||
<common:year>2003</common:year>
|
||||
<common:month>03</common:month>
|
||||
</common:start-date>
|
||||
<common:end-date>
|
||||
<common:year>2007</common:year>
|
||||
<common:month>03</common:month>
|
||||
</common:end-date>
|
||||
<common:organization>
|
||||
<common:name>University of New England</common:name>
|
||||
<common:address>
|
||||
<common:city>Armidale</common:city>
|
||||
<common:region>NSW</common:region>
|
||||
<common:country>AU</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>1319</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</common:organization>
|
||||
</education:education-summary>
|
||||
</activities:affiliation-group>
|
||||
<activities:affiliation-group>
|
||||
<common:last-modified-date>2018-02-13T02:33:38.225Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<education:education-summary put-code="1549990" display-index="0" path="/0000-0001-6816-8350/education/1549990" visibility="public">
|
||||
<common:created-date>2016-02-09T06:57:04.181Z</common:created-date>
|
||||
<common:last-modified-date>2018-02-13T02:33:38.225Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<common:department-name>Psychology</common:department-name>
|
||||
<common:role-title>Master of Science (Industrial and Organizational) Psychology</common:role-title>
|
||||
<common:start-date>
|
||||
<common:year>1998</common:year>
|
||||
<common:month>01</common:month>
|
||||
</common:start-date>
|
||||
<common:end-date>
|
||||
<common:year>2000</common:year>
|
||||
<common:month>01</common:month>
|
||||
</common:end-date>
|
||||
<common:organization>
|
||||
<common:name>Universitas Gadjah Mada</common:name>
|
||||
<common:address>
|
||||
<common:city>Yogyakarta</common:city>
|
||||
<common:region>Daerah Istimewa Yogyakart</common:region>
|
||||
<common:country>ID</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>59166</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</common:organization>
|
||||
</education:education-summary>
|
||||
</activities:affiliation-group>
|
||||
<activities:affiliation-group>
|
||||
<common:last-modified-date>2018-02-13T02:33:35.821Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<education:education-summary put-code="1549998" display-index="0" path="/0000-0001-6816-8350/education/1549998" visibility="public">
|
||||
<common:created-date>2016-02-09T06:58:59.869Z</common:created-date>
|
||||
<common:last-modified-date>2018-02-13T02:33:35.821Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<common:department-name>Education</common:department-name>
|
||||
<common:role-title>Bachelor of Education (Honors)</common:role-title>
|
||||
<common:start-date>
|
||||
<common:year>1988</common:year>
|
||||
<common:month>03</common:month>
|
||||
</common:start-date>
|
||||
<common:end-date>
|
||||
<common:year>1991</common:year>
|
||||
<common:month>03</common:month>
|
||||
</common:end-date>
|
||||
<common:organization>
|
||||
<common:name>Kenyatta University</common:name>
|
||||
<common:address>
|
||||
<common:city>Nairobi</common:city>
|
||||
<common:region>Nairobi</common:region>
|
||||
<common:country>KE</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>107864</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</common:organization>
|
||||
</education:education-summary>
|
||||
</activities:affiliation-group>
|
||||
</activities:educations>
|
||||
<activities:employments path="/0000-0001-6816-8350/employments">
|
||||
<common:last-modified-date>2023-12-02T13:28:26.051Z</common:last-modified-date>
|
||||
<activities:affiliation-group>
|
||||
<common:last-modified-date>2023-12-02T13:28:26.051Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<employment:employment-summary put-code="21884863" display-index="1" path="/0000-0001-6816-8350/employment/21884863" visibility="public">
|
||||
<common:created-date>2023-12-02T13:28:26.051Z</common:created-date>
|
||||
<common:last-modified-date>2023-12-02T13:28:26.051Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<common:department-name>Management</common:department-name>
|
||||
<common:role-title>Associate Professor in Management</common:role-title>
|
||||
<common:start-date>
|
||||
<common:year>2023</common:year>
|
||||
<common:month>08</common:month>
|
||||
<common:day>20</common:day>
|
||||
</common:start-date>
|
||||
<common:organization>
|
||||
<common:name>Alfaisal University</common:name>
|
||||
<common:address>
|
||||
<common:city>Riyadh</common:city>
|
||||
<common:country>SA</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>https://ror.org/00cdrtq48</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>ROR</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</common:organization>
|
||||
<common:url>https://faculty.alfaisal.edu/user/mmuchiri</common:url>
|
||||
</employment:employment-summary>
|
||||
</activities:affiliation-group>
|
||||
<activities:affiliation-group>
|
||||
<common:last-modified-date>2016-02-09T07:00:06.052Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<employment:employment-summary put-code="1550002" display-index="0" path="/0000-0001-6816-8350/employment/1550002" visibility="public">
|
||||
<common:created-date>2016-02-09T07:00:06.052Z</common:created-date>
|
||||
<common:last-modified-date>2016-02-09T07:00:06.052Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<common:department-name>Management</common:department-name>
|
||||
<common:role-title>Senior Lecturer</common:role-title>
|
||||
<common:start-date>
|
||||
<common:year>2014</common:year>
|
||||
<common:month>02</common:month>
|
||||
</common:start-date>
|
||||
<common:organization>
|
||||
<common:name>RMIT University</common:name>
|
||||
<common:address>
|
||||
<common:city>Melbourne</common:city>
|
||||
<common:region>VIC</common:region>
|
||||
<common:country>AU</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>5376</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</common:organization>
|
||||
</employment:employment-summary>
|
||||
</activities:affiliation-group>
|
||||
<activities:affiliation-group>
|
||||
<common:last-modified-date>2016-02-09T07:01:08.398Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<employment:employment-summary put-code="1550007" display-index="0" path="/0000-0001-6816-8350/employment/1550007" visibility="public">
|
||||
<common:created-date>2016-02-09T07:01:08.398Z</common:created-date>
|
||||
<common:last-modified-date>2016-02-09T07:01:08.398Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<common:department-name>Management</common:department-name>
|
||||
<common:role-title>Senior Lecturer in Human Resource Management</common:role-title>
|
||||
<common:start-date>
|
||||
<common:year>2010</common:year>
|
||||
<common:month>01</common:month>
|
||||
</common:start-date>
|
||||
<common:end-date>
|
||||
<common:year>2014</common:year>
|
||||
<common:month>02</common:month>
|
||||
</common:end-date>
|
||||
<common:organization>
|
||||
<common:name>Central Queensland University</common:name>
|
||||
<common:address>
|
||||
<common:city>Rockhampton</common:city>
|
||||
<common:region>QLD</common:region>
|
||||
<common:country>AU</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>273488</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</common:organization>
|
||||
</employment:employment-summary>
|
||||
</activities:affiliation-group>
|
||||
<activities:affiliation-group>
|
||||
<common:last-modified-date>2016-02-09T07:01:47.814Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<employment:employment-summary put-code="1550010" display-index="0" path="/0000-0001-6816-8350/employment/1550010" visibility="public">
|
||||
<common:created-date>2016-02-09T07:01:47.814Z</common:created-date>
|
||||
<common:last-modified-date>2016-02-09T07:01:47.814Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<common:department-name>Management</common:department-name>
|
||||
<common:role-title>Lecturer in Management</common:role-title>
|
||||
<common:start-date>
|
||||
<common:year>2007</common:year>
|
||||
<common:month>01</common:month>
|
||||
</common:start-date>
|
||||
<common:end-date>
|
||||
<common:year>2010</common:year>
|
||||
<common:month>01</common:month>
|
||||
</common:end-date>
|
||||
<common:organization>
|
||||
<common:name>Central Queensland University</common:name>
|
||||
<common:address>
|
||||
<common:city>Rockhampton</common:city>
|
||||
<common:region>QLD</common:region>
|
||||
<common:country>AU</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>273488</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</common:organization>
|
||||
</employment:employment-summary>
|
||||
</activities:affiliation-group>
|
||||
<activities:affiliation-group>
|
||||
<common:last-modified-date>2018-02-13T02:33:13.213Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<employment:employment-summary put-code="1550017" display-index="0" path="/0000-0001-6816-8350/employment/1550017" visibility="public">
|
||||
<common:created-date>2016-02-09T07:03:42.180Z</common:created-date>
|
||||
<common:last-modified-date>2018-02-13T02:33:13.213Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<common:department-name>Human Resource Development Division</common:department-name>
|
||||
<common:role-title>Chief Human Resource Development Officer</common:role-title>
|
||||
<common:start-date>
|
||||
<common:year>2005</common:year>
|
||||
<common:month>01</common:month>
|
||||
</common:start-date>
|
||||
<common:end-date>
|
||||
<common:year>2007</common:year>
|
||||
<common:month>01</common:month>
|
||||
</common:end-date>
|
||||
<common:organization>
|
||||
<common:name>Government of Kenya Directorate of Personnel Management</common:name>
|
||||
<common:address>
|
||||
<common:city>Nairobi</common:city>
|
||||
<common:region>Nairobi</common:region>
|
||||
<common:country>KE</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>360256</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</common:organization>
|
||||
</employment:employment-summary>
|
||||
</activities:affiliation-group>
|
||||
<activities:affiliation-group>
|
||||
<common:last-modified-date>2016-02-09T07:05:02.300Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<employment:employment-summary put-code="1550020" display-index="0" path="/0000-0001-6816-8350/employment/1550020" visibility="public">
|
||||
<common:created-date>2016-02-09T07:05:02.300Z</common:created-date>
|
||||
<common:last-modified-date>2016-02-09T07:05:02.300Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<common:department-name>Human Resource Development Division</common:department-name>
|
||||
<common:role-title>Human Resource Development Officer</common:role-title>
|
||||
<common:start-date>
|
||||
<common:year>2001</common:year>
|
||||
<common:month>01</common:month>
|
||||
</common:start-date>
|
||||
<common:end-date>
|
||||
<common:year>2005</common:year>
|
||||
<common:month>01</common:month>
|
||||
</common:end-date>
|
||||
<common:organization>
|
||||
<common:name>Government of Kenya Directorate of Personnel Management</common:name>
|
||||
<common:address>
|
||||
<common:city>Nairobi</common:city>
|
||||
<common:region>Nairobi</common:region>
|
||||
<common:country>KE</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>360256</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</common:organization>
|
||||
</employment:employment-summary>
|
||||
</activities:affiliation-group>
|
||||
<activities:affiliation-group>
|
||||
<common:last-modified-date>2016-02-09T07:36:52.398Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<employment:employment-summary put-code="1550050" display-index="0" path="/0000-0001-6816-8350/employment/1550050" visibility="public">
|
||||
<common:created-date>2016-02-09T07:36:52.398Z</common:created-date>
|
||||
<common:last-modified-date>2016-02-09T07:36:52.398Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<common:department-name>Public Sector Management Technical Assistance Project</common:department-name>
|
||||
<common:role-title>Project Coordinator for Development Learning Centre</common:role-title>
|
||||
<common:start-date>
|
||||
<common:year>2002</common:year>
|
||||
<common:month>08</common:month>
|
||||
</common:start-date>
|
||||
<common:end-date>
|
||||
<common:year>2003</common:year>
|
||||
<common:month>03</common:month>
|
||||
</common:end-date>
|
||||
<common:organization>
|
||||
<common:name>Government of Kenya Directorate of Personnel Management</common:name>
|
||||
<common:address>
|
||||
<common:city>Nairobi</common:city>
|
||||
<common:region>Nairobi</common:region>
|
||||
<common:country>KE</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>360256</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</common:organization>
|
||||
</employment:employment-summary>
|
||||
</activities:affiliation-group>
|
||||
</activities:employments>
|
||||
<activities:fundings path="/0000-0001-6816-8350/fundings">
|
||||
<common:last-modified-date>2016-02-09T09:05:27.100Z</common:last-modified-date>
|
||||
<activities:group>
|
||||
<common:last-modified-date>2016-02-09T09:05:27.100Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<funding:funding-summary put-code="150520" path="/0000-0001-6816-8350/funding/150520" visibility="public" display-index="6">
|
||||
<common:created-date>2016-02-09T09:05:27.100Z</common:created-date>
|
||||
<common:last-modified-date>2016-02-09T09:05:27.100Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<funding:title>
|
||||
<common:title>A cross-country examination of Employee Wellbeing, Leadership, High Performance Work Systems and Innovative Behaviours</common:title>
|
||||
</funding:title>
|
||||
<funding:type>grant</funding:type>
|
||||
<common:start-date>
|
||||
<common:year>2016</common:year>
|
||||
<common:month>01</common:month>
|
||||
</common:start-date>
|
||||
<common:end-date>
|
||||
<common:year>2016</common:year>
|
||||
<common:month>12</common:month>
|
||||
</common:end-date>
|
||||
<common:organization>
|
||||
<common:name>RMIT University</common:name>
|
||||
<common:address>
|
||||
<common:city>VIC</common:city>
|
||||
<common:region>VIC</common:region>
|
||||
<common:country>AU</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>http://dx.doi.org/10.13039/501100001780</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>FUNDREF</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</common:organization>
|
||||
</funding:funding-summary>
|
||||
</activities:group>
|
||||
<activities:group>
|
||||
<common:last-modified-date>2016-02-09T09:03:51.641Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<funding:funding-summary put-code="150518" path="/0000-0001-6816-8350/funding/150518" visibility="public" display-index="5">
|
||||
<common:created-date>2016-02-09T09:03:51.641Z</common:created-date>
|
||||
<common:last-modified-date>2016-02-09T09:03:51.641Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<funding:title>
|
||||
<common:title>Leading Safe and Thriving Organisations: An Investigation of the Relationships between Leadership, Thriving Behaviour, Authentic Followership and Safety Climate in an Australian Multinational Enterprise</common:title>
|
||||
</funding:title>
|
||||
<funding:type>grant</funding:type>
|
||||
<common:start-date>
|
||||
<common:year>2015</common:year>
|
||||
<common:month>01</common:month>
|
||||
</common:start-date>
|
||||
<common:end-date>
|
||||
<common:year>2015</common:year>
|
||||
<common:month>12</common:month>
|
||||
</common:end-date>
|
||||
<common:organization>
|
||||
<common:name>RMIT University</common:name>
|
||||
<common:address>
|
||||
<common:city>VIC</common:city>
|
||||
<common:region>VIC</common:region>
|
||||
<common:country>AU</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>http://dx.doi.org/10.13039/501100001780</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>FUNDREF</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</common:organization>
|
||||
</funding:funding-summary>
|
||||
</activities:group>
|
||||
<activities:group>
|
||||
<common:last-modified-date>2016-02-09T09:02:28.297Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<funding:funding-summary put-code="150516" path="/0000-0001-6816-8350/funding/150516" visibility="public" display-index="4">
|
||||
<common:created-date>2016-02-09T09:02:28.297Z</common:created-date>
|
||||
<common:last-modified-date>2016-02-09T09:02:28.297Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<funding:title>
|
||||
<common:title>A multilevel, cross-country examination of leadership, followership and innovative behaviours in Australia and Indonesia. </common:title>
|
||||
</funding:title>
|
||||
<funding:type>grant</funding:type>
|
||||
<common:start-date>
|
||||
<common:year>2015</common:year>
|
||||
<common:month>01</common:month>
|
||||
</common:start-date>
|
||||
<common:end-date>
|
||||
<common:year>2015</common:year>
|
||||
<common:month>12</common:month>
|
||||
</common:end-date>
|
||||
<common:organization>
|
||||
<common:name>RMIT University</common:name>
|
||||
<common:address>
|
||||
<common:city>VIC</common:city>
|
||||
<common:region>VIC</common:region>
|
||||
<common:country>AU</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>http://dx.doi.org/10.13039/501100001780</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>FUNDREF</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</common:organization>
|
||||
</funding:funding-summary>
|
||||
</activities:group>
|
||||
<activities:group>
|
||||
<common:last-modified-date>2016-02-09T09:00:51.749Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<funding:funding-summary put-code="150514" path="/0000-0001-6816-8350/funding/150514" visibility="public" display-index="3">
|
||||
<common:created-date>2016-02-09T09:00:51.749Z</common:created-date>
|
||||
<common:last-modified-date>2016-02-09T09:00:51.749Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<funding:title>
|
||||
<common:title>Workplace safety and positive leadership: Exploring relationships between leader behaviours, organisational climate, safety climate, safety citizenship behaviours and innovative behaviours within city councils in Victoria </common:title>
|
||||
</funding:title>
|
||||
<funding:type>grant</funding:type>
|
||||
<common:start-date>
|
||||
<common:year>2014</common:year>
|
||||
<common:month>01</common:month>
|
||||
</common:start-date>
|
||||
<common:end-date>
|
||||
<common:year>2014</common:year>
|
||||
<common:month>12</common:month>
|
||||
</common:end-date>
|
||||
<common:organization>
|
||||
<common:name>RMIT University</common:name>
|
||||
<common:address>
|
||||
<common:city>VIC</common:city>
|
||||
<common:region>VIC</common:region>
|
||||
<common:country>AU</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>http://dx.doi.org/10.13039/501100001780</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>FUNDREF</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</common:organization>
|
||||
</funding:funding-summary>
|
||||
</activities:group>
|
||||
<activities:group>
|
||||
<common:last-modified-date>2016-02-09T07:46:44.919Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<funding:funding-summary put-code="150485" path="/0000-0001-6816-8350/funding/150485" visibility="public" display-index="0">
|
||||
<common:created-date>2016-02-09T07:46:44.919Z</common:created-date>
|
||||
<common:last-modified-date>2016-02-09T07:46:44.919Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0001-6816-8350</common:uri>
|
||||
<common:path>0000-0001-6816-8350</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
</common:source>
|
||||
<funding:title>
|
||||
<common:title>Sustainable Business Model for Central Queensland Regional Information Systems.</common:title>
|
||||
</funding:title>
|
||||
<funding:type>grant</funding:type>
|
||||
<common:start-date>
|
||||
<common:year>2008</common:year>
|
||||
<common:month>01</common:month>
|
||||
</common:start-date>
|
||||
<common:end-date>
|
||||
<common:year>2008</common:year>
|
||||
<common:month>12</common:month>
|
||||
</common:end-date>
|
||||
<common:organization>
|
||||
<common:name>Department of Local Government, Planning, Sport and Recreation, Queensland, Australia </common:name>
|
||||
<common:address>
|
||||
<common:city>Rockhampton</common:city>
|
||||
<common:region>Central Queensland</common:region>
|
||||
<common:country>AU</common:country>
|
||||
</common:address>
|
||||
</common:organization>
|
||||
</funding:funding-summary>
|
||||
</activities:group>
|
||||
</activities:fundings>
|
||||
<activities:invited-positions path="/0000-0001-6816-8350/invited-positions"/>
|
||||
<activities:memberships path="/0000-0001-6816-8350/memberships"/>
|
||||
<activities:peer-reviews path="/0000-0001-6816-8350/peer-reviews">
|
||||
<common:last-modified-date>2023-05-31T05:53:44.542Z</common:last-modified-date>
|
||||
<activities:group>
|
||||
<common:last-modified-date>2023-05-31T05:53:44.542Z</common:last-modified-date>
|
||||
<common:external-ids>
|
||||
<common:external-id>
|
||||
<common:external-id-type>peer-review</common:external-id-type>
|
||||
<common:external-id-value>issn:0167-4544</common:external-id-value>
|
||||
</common:external-id>
|
||||
</common:external-ids>
|
||||
<activities:peer-review-group>
|
||||
<common:last-modified-date>2023-02-28T06:51:52.426Z</common:last-modified-date>
|
||||
<common:external-ids>
|
||||
<common:external-id>
|
||||
<common:external-id-type>source-work-id</common:external-id-type>
|
||||
<common:external-id-value>c9bdf086-cfee-4cd9-bcfb-268cc5423248</common:external-id-value>
|
||||
<common:external-id-normalized transient="true">c9bdf086-cfee-4cd9-bcfb-268cc5423248</common:external-id-normalized>
|
||||
<common:external-id-url></common:external-id-url>
|
||||
<common:external-id-relationship>self</common:external-id-relationship>
|
||||
</common:external-id>
|
||||
</common:external-ids>
|
||||
<peer-review:peer-review-summary put-code="8741329" path="/0000-0001-6816-8350/peer-review/8741329" visibility="public" display-index="0">
|
||||
<common:created-date>2023-02-28T06:51:52.426Z</common:created-date>
|
||||
<common:last-modified-date>2023-02-28T06:51:52.426Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-client-id>
|
||||
<common:uri>https://orcid.org/client/APP-945VYTN20C7BZXYT</common:uri>
|
||||
<common:path>APP-945VYTN20C7BZXYT</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-client-id>
|
||||
<common:source-name>Springer Nature @ Editorial Manager</common:source-name>
|
||||
</common:source>
|
||||
<peer-review:reviewer-role>reviewer</peer-review:reviewer-role>
|
||||
<common:external-ids>
|
||||
<common:external-id>
|
||||
<common:external-id-type>source-work-id</common:external-id-type>
|
||||
<common:external-id-value>c9bdf086-cfee-4cd9-bcfb-268cc5423248</common:external-id-value>
|
||||
<common:external-id-normalized transient="true">c9bdf086-cfee-4cd9-bcfb-268cc5423248</common:external-id-normalized>
|
||||
<common:external-id-url></common:external-id-url>
|
||||
<common:external-id-relationship>self</common:external-id-relationship>
|
||||
</common:external-id>
|
||||
</common:external-ids>
|
||||
<peer-review:review-type>review</peer-review:review-type>
|
||||
<peer-review:completion-date>
|
||||
<common:year>2023</common:year>
|
||||
</peer-review:completion-date>
|
||||
<peer-review:review-group-id>issn:0167-4544</peer-review:review-group-id>
|
||||
<peer-review:convening-organization>
|
||||
<common:name>Springer Nature</common:name>
|
||||
<common:address>
|
||||
<common:city>New York</common:city>
|
||||
<common:country>US</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>grid.467660.5</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>GRID</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</peer-review:convening-organization>
|
||||
</peer-review:peer-review-summary>
|
||||
</activities:peer-review-group>
|
||||
<activities:peer-review-group>
|
||||
<common:last-modified-date>2023-05-31T05:53:44.542Z</common:last-modified-date>
|
||||
<common:external-ids>
|
||||
<common:external-id>
|
||||
<common:external-id-type>source-work-id</common:external-id-type>
|
||||
<common:external-id-value>c442840b-5807-459d-802a-303d8ba4e25e</common:external-id-value>
|
||||
<common:external-id-normalized transient="true">c442840b-5807-459d-802a-303d8ba4e25e</common:external-id-normalized>
|
||||
<common:external-id-url></common:external-id-url>
|
||||
<common:external-id-relationship>self</common:external-id-relationship>
|
||||
</common:external-id>
|
||||
</common:external-ids>
|
||||
<peer-review:peer-review-summary put-code="9680570" path="/0000-0001-6816-8350/peer-review/9680570" visibility="public" display-index="0">
|
||||
<common:created-date>2023-05-31T05:53:44.542Z</common:created-date>
|
||||
<common:last-modified-date>2023-05-31T05:53:44.542Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-client-id>
|
||||
<common:uri>https://orcid.org/client/APP-945VYTN20C7BZXYT</common:uri>
|
||||
<common:path>APP-945VYTN20C7BZXYT</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-client-id>
|
||||
<common:source-name>Springer Nature @ Editorial Manager</common:source-name>
|
||||
</common:source>
|
||||
<peer-review:reviewer-role>reviewer</peer-review:reviewer-role>
|
||||
<common:external-ids>
|
||||
<common:external-id>
|
||||
<common:external-id-type>source-work-id</common:external-id-type>
|
||||
<common:external-id-value>c442840b-5807-459d-802a-303d8ba4e25e</common:external-id-value>
|
||||
<common:external-id-normalized transient="true">c442840b-5807-459d-802a-303d8ba4e25e</common:external-id-normalized>
|
||||
<common:external-id-url></common:external-id-url>
|
||||
<common:external-id-relationship>self</common:external-id-relationship>
|
||||
</common:external-id>
|
||||
</common:external-ids>
|
||||
<peer-review:review-type>review</peer-review:review-type>
|
||||
<peer-review:completion-date>
|
||||
<common:year>2023</common:year>
|
||||
</peer-review:completion-date>
|
||||
<peer-review:review-group-id>issn:0167-4544</peer-review:review-group-id>
|
||||
<peer-review:convening-organization>
|
||||
<common:name>Springer Nature</common:name>
|
||||
<common:address>
|
||||
<common:city>New York</common:city>
|
||||
<common:country>US</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>grid.467660.5</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>GRID</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</peer-review:convening-organization>
|
||||
</peer-review:peer-review-summary>
|
||||
</activities:peer-review-group>
|
||||
</activities:group>
|
||||
</activities:peer-reviews>
|
||||
<activities:qualifications path="/0000-0001-6816-8350/qualifications"/>
|
||||
<activities:research-resources path="/0000-0001-6816-8350/research-resources"/>
|
||||
<activities:services path="/0000-0001-6816-8350/services"/>
|
||||
<activities:works path="/0000-0001-6816-8350/works">
|
||||
<common:last-modified-date>2023-06-02T20:12:00.338Z</common:last-modified-date>
|
||||
<activities:group>
|
||||
<common:last-modified-date>2023-06-02T20:12:00.338Z</common:last-modified-date>
|
||||
<common:external-ids>
|
||||
<common:external-id>
|
||||
<common:external-id-type>doi</common:external-id-type>
|
||||
<common:external-id-value>10.4337/9781800881945.00020</common:external-id-value>
|
||||
<common:external-id-normalized transient="true">10.4337/9781800881945.00020</common:external-id-normalized>
|
||||
<common:external-id-url>https://doi.org/10.4337/9781800881945.00020</common:external-id-url>
|
||||
<common:external-id-relationship>self</common:external-id-relationship>
|
||||
</common:external-id>
|
||||
</common:external-ids>
|
||||
<work:work-summary put-code="134891279" path="/0000-0001-6816-8350/work/134891279" visibility="public" display-index="0">
|
||||
<common:created-date>2023-05-11T21:05:54.188Z</common:created-date>
|
||||
<common:last-modified-date>2023-06-02T20:12:00.338Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-client-id>
|
||||
<common:uri>https://orcid.org/client/0000-0001-9884-1913</common:uri>
|
||||
<common:path>0000-0001-9884-1913</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-client-id>
|
||||
<common:source-name>Crossref</common:source-name>
|
||||
</common:source>
|
||||
<work:title>
|
||||
<common:title>Ethical leadership as workplace innovation and enabler for employee commitment and innovative work behaviours in Vietnam</common:title>
|
||||
</work:title>
|
||||
<common:external-ids>
|
||||
<common:external-id>
|
||||
<common:external-id-type>doi</common:external-id-type>
|
||||
<common:external-id-value>10.4337/9781800881945.00020</common:external-id-value>
|
||||
<common:external-id-normalized transient="true">10.4337/9781800881945.00020</common:external-id-normalized>
|
||||
<common:external-id-url>https://doi.org/10.4337/9781800881945.00020</common:external-id-url>
|
||||
<common:external-id-relationship>self</common:external-id-relationship>
|
||||
</common:external-id>
|
||||
</common:external-ids>
|
||||
<common:url>https://doi.org/10.4337/9781800881945.00020</common:url>
|
||||
<work:type>book-chapter</work:type>
|
||||
<common:publication-date>
|
||||
<common:year>2023</common:year>
|
||||
<common:month>05</common:month>
|
||||
<common:day>26</common:day>
|
||||
</common:publication-date>
|
||||
</work:work-summary>
|
||||
</activities:group>
|
||||
<activities:group>
|
||||
<common:last-modified-date>2023-03-01T11:30:31.972Z</common:last-modified-date>
|
||||
<common:external-ids>
|
||||
<common:external-id>
|
||||
<common:external-id-type>doi</common:external-id-type>
|
||||
<common:external-id-value>10.1007/s10551-022-05081-6</common:external-id-value>
|
||||
<common:external-id-normalized transient="true">10.1007/s10551-022-05081-6</common:external-id-normalized>
|
||||
<common:external-id-url>https://doi.org/10.1007/s10551-022-05081-6</common:external-id-url>
|
||||
<common:external-id-relationship>self</common:external-id-relationship>
|
||||
</common:external-id>
|
||||
</common:external-ids>
|
||||
<work:work-summary put-code="110048777" path="/0000-0001-6816-8350/work/110048777" visibility="public" display-index="0">
|
||||
<common:created-date>2022-03-18T03:36:55.927Z</common:created-date>
|
||||
<common:last-modified-date>2023-03-01T11:30:31.972Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-client-id>
|
||||
<common:uri>https://orcid.org/client/0000-0001-9884-1913</common:uri>
|
||||
<common:path>0000-0001-9884-1913</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-client-id>
|
||||
<common:source-name>Crossref</common:source-name>
|
||||
</common:source>
|
||||
<work:title>
|
||||
<common:title>Unethical Leadership: Review, Synthesis and Directions for Future Research</common:title>
|
||||
</work:title>
|
||||
<common:external-ids>
|
||||
<common:external-id>
|
||||
<common:external-id-type>doi</common:external-id-type>
|
||||
<common:external-id-value>10.1007/s10551-022-05081-6</common:external-id-value>
|
||||
<common:external-id-normalized transient="true">10.1007/s10551-022-05081-6</common:external-id-normalized>
|
||||
<common:external-id-url>https://doi.org/10.1007/s10551-022-05081-6</common:external-id-url>
|
||||
<common:external-id-relationship>self</common:external-id-relationship>
|
||||
</common:external-id>
|
||||
</common:external-ids>
|
||||
<common:url>https://doi.org/10.1007/s10551-022-05081-6</common:url>
|
||||
<work:type>journal-article</work:type>
|
||||
<common:publication-date>
|
||||
<common:year>2023</common:year>
|
||||
<common:month>03</common:month>
|
||||
</common:publication-date>
|
||||
<work:journal-title>Journal of Business Ethics</work:journal-title>
|
||||
</work:work-summary>
|
||||
</activities:group>
|
||||
<activities:group>
|
||||
<common:last-modified-date>2022-05-28T18:16:16.575Z</common:last-modified-date>
|
||||
<common:external-ids>
|
||||
<common:external-id>
|
||||
<common:external-id-type>doi</common:external-id-type>
|
||||
<common:external-id-value>10.1017/jmo.2019.33</common:external-id-value>
|
||||
<common:external-id-normalized transient="true">10.1017/jmo.2019.33</common:external-id-normalized>
|
||||
<common:external-id-url>https://doi.org/10.1017/jmo.2019.33</common:external-id-url>
|
||||
<common:external-id-relationship>self</common:external-id-relationship>
|
||||
</common:external-id>
|
||||
</common:external-ids>
|
||||
<work:work-summary put-code="57272180" path="/0000-0001-6816-8350/work/57272180" visibility="public" display-index="0">
|
||||
<common:created-date>2019-05-10T07:23:14.608Z</common:created-date>
|
||||
<common:last-modified-date>2022-05-28T18:16:16.575Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-client-id>
|
||||
<common:uri>https://orcid.org/client/0000-0001-9884-1913</common:uri>
|
||||
<common:path>0000-0001-9884-1913</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-client-id>
|
||||
<common:source-name>Crossref</common:source-name>
|
||||
</common:source>
|
||||
<work:title>
|
||||
<common:title>And now for something completely different: Reframing social processes of leadership theory using positive organisational behaviour</common:title>
|
||||
</work:title>
|
||||
<common:external-ids>
|
||||
<common:external-id>
|
||||
<common:external-id-type>doi</common:external-id-type>
|
||||
<common:external-id-value>10.1017/jmo.2019.33</common:external-id-value>
|
||||
<common:external-id-normalized transient="true">10.1017/jmo.2019.33</common:external-id-normalized>
|
||||
<common:external-id-url>https://doi.org/10.1017/jmo.2019.33</common:external-id-url>
|
||||
<common:external-id-relationship>self</common:external-id-relationship>
|
||||
</common:external-id>
|
||||
</common:external-ids>
|
||||
<common:url>https://doi.org/10.1017/jmo.2019.33</common:url>
|
||||
<work:type>journal-article</work:type>
|
||||
<common:publication-date>
|
||||
<common:year>2019</common:year>
|
||||
<common:month>05</common:month>
|
||||
<common:day>09</common:day>
|
||||
</common:publication-date>
|
||||
<work:journal-title>Journal of Management & Organization</work:journal-title>
|
||||
</work:work-summary>
|
||||
</activities:group>
|
||||
</activities:works>
|
||||
</activities:activities-summary>
|
||||
</record:record>
|
|
@ -0,0 +1,60 @@
|
|||
<?xml version="1.0" encoding="UTF-8" standalone="yes"?>
|
||||
<activities:employments path="/0000-0002-0456-1185/employments" xmlns:internal="http://www.orcid.org/ns/internal" xmlns:education="http://www.orcid.org/ns/education" xmlns:distinction="http://www.orcid.org/ns/distinction" xmlns:deprecated="http://www.orcid.org/ns/deprecated" xmlns:other-name="http://www.orcid.org/ns/other-name" xmlns:membership="http://www.orcid.org/ns/membership" xmlns:error="http://www.orcid.org/ns/error" xmlns:common="http://www.orcid.org/ns/common" xmlns:record="http://www.orcid.org/ns/record" xmlns:personal-details="http://www.orcid.org/ns/personal-details" xmlns:keyword="http://www.orcid.org/ns/keyword" xmlns:email="http://www.orcid.org/ns/email" xmlns:external-identifier="http://www.orcid.org/ns/external-identifier" xmlns:funding="http://www.orcid.org/ns/funding" xmlns:preferences="http://www.orcid.org/ns/preferences" xmlns:address="http://www.orcid.org/ns/address" xmlns:invited-position="http://www.orcid.org/ns/invited-position" xmlns:work="http://www.orcid.org/ns/work" xmlns:history="http://www.orcid.org/ns/history" xmlns:employment="http://www.orcid.org/ns/employment" xmlns:qualification="http://www.orcid.org/ns/qualification" xmlns:service="http://www.orcid.org/ns/service" xmlns:person="http://www.orcid.org/ns/person" xmlns:activities="http://www.orcid.org/ns/activities" xmlns:researcher-url="http://www.orcid.org/ns/researcher-url" xmlns:peer-review="http://www.orcid.org/ns/peer-review" xmlns:bulk="http://www.orcid.org/ns/bulk" xmlns:research-resource="http://www.orcid.org/ns/research-resource">
|
||||
<common:last-modified-date>2024-01-07T23:59:38.869Z</common:last-modified-date>
|
||||
<activities:affiliation-group>
|
||||
<common:last-modified-date>2024-01-07T23:59:38.869Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<employment:employment-summary put-code="22127142" display-index="0" path="/0000-0002-0456-1185/employment/22127142" visibility="public">
|
||||
<common:created-date>2024-01-07T23:59:38.869Z</common:created-date>
|
||||
<common:last-modified-date>2024-01-07T23:59:38.869Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-client-id>
|
||||
<common:uri>https://orcid.org/client/APP-N0TAO4G9BBK9PWHT</common:uri>
|
||||
<common:path>APP-N0TAO4G9BBK9PWHT</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-client-id>
|
||||
<common:source-name>Tampere University</common:source-name>
|
||||
</common:source>
|
||||
<common:organization>
|
||||
<common:name>Tampere University</common:name>
|
||||
<common:address>
|
||||
<common:city>Tampere</common:city>
|
||||
<common:country>FI</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>https://ror.org/033003e23</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>ROR</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</common:organization>
|
||||
</employment:employment-summary>
|
||||
</activities:affiliation-group>
|
||||
<activities:affiliation-group>
|
||||
<common:last-modified-date>2019-01-03T17:00:05.658Z</common:last-modified-date>
|
||||
<common:external-ids/>
|
||||
<employment:employment-summary put-code="3291239" display-index="1" path="/0000-0002-0456-1185/employment/3291239" visibility="public">
|
||||
<common:created-date>2017-02-26T04:46:20.917Z</common:created-date>
|
||||
<common:last-modified-date>2019-01-03T17:00:05.658Z</common:last-modified-date>
|
||||
<common:source>
|
||||
<common:source-orcid>
|
||||
<common:uri>https://orcid.org/0000-0002-0456-1185</common:uri>
|
||||
<common:path>0000-0002-0456-1185</common:path>
|
||||
<common:host>orcid.org</common:host>
|
||||
</common:source-orcid>
|
||||
<common:source-name>Tiina Manninen</common:source-name>
|
||||
</common:source>
|
||||
<common:department-name> Faculty of Medicine and Health Technology</common:department-name>
|
||||
<common:role-title>Academy Research Fellow</common:role-title>
|
||||
<common:organization>
|
||||
<common:name>Tampere University</common:name>
|
||||
<common:address>
|
||||
<common:city>Tampere</common:city>
|
||||
<common:country>FI</common:country>
|
||||
</common:address>
|
||||
<common:disambiguated-organization>
|
||||
<common:disambiguated-organization-identifier>7839</common:disambiguated-organization-identifier>
|
||||
<common:disambiguation-source>RINGGOLD</common:disambiguation-source>
|
||||
</common:disambiguated-organization>
|
||||
</common:organization>
|
||||
</employment:employment-summary>
|
||||
</activities:affiliation-group>
|
||||
</activities:employments>
|
File diff suppressed because it is too large
Load Diff
|
@ -0,0 +1,36 @@
|
|||
<?xml version="1.0" encoding="UTF-8"?>
|
||||
<record>
|
||||
<header xmlns="http://www.openarchives.org/OAI/2.0/">
|
||||
<identifier>ftunivminnesdc:oai:conservancy.umn.edu:11299/109914</identifier>
|
||||
<datestamp>2023-07-18T20:05:40Z</datestamp>
|
||||
</header>
|
||||
<metadata xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:base_dc="http://oai.base-search.net/base_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:dc="http://purl.org/dc/elements/1.1/">
|
||||
<base_dc:dc xsi:schemaLocation="http://oai.base-search.net/base_dc/ http://oai.base-search.net/base_dc/base_dc.xsd">
|
||||
<base_dc:global_id>ftunivminnesdc:oai:conservancy.umn.edu:11299/109914</base_dc:global_id>
|
||||
<base_dc:continent>cna</base_dc:continent>
|
||||
<base_dc:country>us</base_dc:country>
|
||||
<base_dc:collection opendoar_id="1008">ftunivminnesdc</base_dc:collection>
|
||||
<base_dc:collname>University of Minnesota Digital Conservancy</base_dc:collname>
|
||||
<dc:title>An Experimental Investigation of the influence of an air bubble layer on radiated noise and surface pressure fluctuations in a turbulent boundary layer</dc:title>
|
||||
<dc:creator>Killen, John M.</dc:creator>
|
||||
<dc:subject>Boundary layer noise</dc:subject>
|
||||
<dc:subject>Kinetic energy dissipation</dc:subject>
|
||||
<dc:subject>Air bubble layer</dc:subject>
|
||||
<dc:subject>Maximum stable bubble size</dc:subject>
|
||||
<dc:subject>bubble noise spectra</dc:subject>
|
||||
<dc:description>between the noise spectra of a layer of air bubbles in a turbulent flow and' a maximum stable bubble size which can exist in the same flow. An air bubbie layer with individual bubble sizes greater than a maximum stable size was introduced into the boundary layer of water flowing along a smooth flat plate. It was found that the maximum stable bubble size was related to the turbulent kinetic energy dissipation as had been previously shown by other investigators ; Office of Naval Research Arlington, Virginia 22217</dc:description>
|
||||
<dc:date>1981-09-31T21:42:52Z</dc:date>
|
||||
<base_dc:year>1981</base_dc:year>
|
||||
<dc:type>Report</dc:type>
|
||||
<base_dc:typenorm>14</base_dc:typenorm>
|
||||
<dc:identifier>http://purl.umn.edu/109914</dc:identifier>
|
||||
<base_dc:link>http://purl.umn.edu/109914</base_dc:link>
|
||||
<dc:language>en_US</dc:language>
|
||||
<dc:relation>Project Reports</dc:relation>
|
||||
<dc:relation>202</dc:relation>
|
||||
<dc:relation>http://purl.umn.edu/109914</dc:relation>
|
||||
<base_dc:oa>2</base_dc:oa>
|
||||
<base_dc:lang>eng</base_dc:lang>
|
||||
</base_dc:dc>
|
||||
</metadata>
|
||||
</record>
|
|
@ -1,44 +1,15 @@
|
|||
{"classification": "Signaling protein", "pdb": "5NM4", "deposition_date": "2017-04-05", "title": "A2a adenosine receptor room-temperature structure determined by serial Femtosecond crystallography", "Keywords": ["Oom-temperature", " serial crystallography", " signaling protein"], "authors": ["T.weinert", "R.cheng", "D.james", "D.gashi", "P.nogly", "K.jaeger", "M.hennig", "", "J.standfuss"], "pmid": "28912485", "doi": "10.1038/S41467-017-00630-4"}
|
||||
{"classification": "Oxidoreductase/oxidoreductase inhibitor", "pdb": "4KN3", "deposition_date": "2013-05-08", "title": "Structure of the y34ns91g double mutant of dehaloperoxidase from Amphitrite ornata with 2,4,6-trichlorophenol", "Keywords": ["Lobin", " oxygen storage", " peroxidase", " oxidoreductase", " oxidoreductase-", "Oxidoreductase inhibitor complex"], "authors": ["C.wang", "L.lovelace", "L.lebioda"], "pmid": "23952341", "doi": "10.1021/BI400627W"}
|
||||
{"classification": "Transport protein", "pdb": "8HKM", "deposition_date": "2022-11-27", "title": "Ion channel", "Keywords": ["On channel", " transport protein"], "authors": ["D.h.jiang", "J.t.zhang"], "pmid": "37494189", "doi": "10.1016/J.CELREP.2023.112858"}
|
||||
{"classification": "Signaling protein", "pdb": "6JT1", "deposition_date": "2019-04-08", "title": "Structure of human soluble guanylate cyclase in the heme oxidised State", "Keywords": ["Oluble guanylate cyclase", " signaling protein"], "authors": ["L.chen", "Y.kang", "R.liu", "J.-x.wu"], "pmid": "31514202", "doi": "10.1038/S41586-019-1584-6"}
|
||||
{"classification": "Immune system", "pdb": "7OW6", "deposition_date": "2021-06-16", "title": "Crystal structure of a tcr in complex with hla-a*11:01 bound to kras G12d peptide (vvvgadgvgk)", "Keywords": ["La", " kras", " tcr", " immune system"], "authors": ["V.karuppiah", "R.a.robinson"], "doi": "10.1038/S41467-022-32811-1"}
|
||||
{"classification": "Biosynthetic protein", "pdb": "5EQ8", "deposition_date": "2015-11-12", "title": "Crystal structure of medicago truncatula histidinol-phosphate Phosphatase (mthpp) in complex with l-histidinol", "Keywords": ["Istidine biosynthesis", " metabolic pathways", " dimer", " plant", "", "Biosynthetic protein"], "authors": ["M.ruszkowski", "Z.dauter"], "pmid": "26994138", "doi": "10.1074/JBC.M115.708727"}
|
||||
{"classification": "De novo protein", "pdb": "8CWA", "deposition_date": "2022-05-18", "title": "Solution nmr structure of 8-residue rosetta-designed cyclic peptide D8.21 in cdcl3 with cis/trans switching (tc conformation, 53%)", "Keywords": ["Yclic peptide", " non natural amino acids", " cis/trans", " switch peptides", "", "De novo design", "Membrane permeability", "De novo protein"], "authors": ["T.a.ramelot", "R.tejero", "G.t.montelione"], "pmid": "36041435", "doi": "10.1016/J.CELL.2022.07.019"}
|
||||
{"classification": "Hydrolase", "pdb": "3R6M", "deposition_date": "2011-03-21", "title": "Crystal structure of vibrio parahaemolyticus yeaz", "Keywords": ["Ctin/hsp70 nucleotide-binding fold", " bacterial resuscitation", " viable", "But non-culturable state", "Resuscitation promoting factor", "Ygjd", "", "Yjee", "Vibrio parahaemolyticus", "Hydrolase"], "authors": ["A.roujeinikova", "I.aydin"], "pmid": "21858042", "doi": "10.1371/JOURNAL.PONE.0023245"}
|
||||
{"classification": "Hydrolase", "pdb": "2W5J", "deposition_date": "2008-12-10", "title": "Structure of the c14-rotor ring of the proton translocating Chloroplast atp synthase", "Keywords": ["Ydrolase", " chloroplast", " atp synthase", " lipid-binding", " cf(0)", " membrane", "", "Transport", "Formylation", "Energy transduction", "Hydrogen ion transport", "", "Ion transport", "Transmembrane", "Membrane protein"], "authors": ["M.vollmar", "D.schlieper", "M.winn", "C.buechner", "G.groth"], "pmid": "19423706", "doi": "10.1074/JBC.M109.006916"}
|
||||
{"classification": "De novo protein", "pdb": "4GLU", "deposition_date": "2012-08-14", "title": "Crystal structure of the mirror image form of vegf-a", "Keywords": ["-protein", " covalent dimer", " cysteine knot protein", " growth factor", " de", "Novo protein"], "authors": ["K.mandal", "M.uppalapati", "D.ault-riche", "J.kenney", "J.lowitz", "S.sidhu", "", "S.b.h.kent"], "pmid": "22927390", "doi": "10.1073/PNAS.1210483109"}
|
||||
{"classification": "Hydrolase/hydrolase inhibitor", "pdb": "3WYL", "deposition_date": "2014-09-01", "title": "Crystal structure of the catalytic domain of pde10a complexed with 5- Methoxy-3-(1-phenyl-1h-pyrazol-5-yl)-1-(3-(trifluoromethyl)phenyl) Pyridazin-4(1h)-one", "Keywords": ["Ydrolase-hydrolase inhibitor complex"], "authors": ["H.oki", "Y.hayano"], "pmid": "25384088", "doi": "10.1021/JM5013648"}
|
||||
{"classification": "Isomerase", "pdb": "5BOR", "deposition_date": "2015-05-27", "title": "Structure of acetobacter aceti pure-s57c, sulfonate form", "Keywords": ["Cidophile", " pure", " purine biosynthesis", " isomerase"], "authors": ["K.l.sullivan", "T.j.kappock"]}
|
||||
{"classification": "Hydrolase", "pdb": "1X0C", "deposition_date": "2005-03-17", "title": "Improved crystal structure of isopullulanase from aspergillus niger Atcc 9642", "Keywords": ["Ullulan", " glycoside hydrolase family 49", " glycoprotein", " hydrolase"], "authors": ["M.mizuno", "T.tonozuka", "A.yamamura", "Y.miyasaka", "H.akeboshi", "S.kamitori", "", "A.nishikawa", "Y.sakano"], "pmid": "18155243", "doi": "10.1016/J.JMB.2007.11.098"}
|
||||
{"classification": "Oxidoreductase", "pdb": "7CUP", "deposition_date": "2020-08-23", "title": "Structure of 2,5-dihydroxypridine dioxygenase from pseudomonas putida Kt2440", "Keywords": ["On-heme dioxygenase", " oxidoreductase"], "authors": ["G.q.liu", "H.z.tang"]}
|
||||
{"classification": "Ligase", "pdb": "1VCN", "deposition_date": "2004-03-10", "title": "Crystal structure of t.th. hb8 ctp synthetase complex with sulfate Anion", "Keywords": ["Etramer", " riken structural genomics/proteomics initiative", " rsgi", "", "Structural genomics", "Ligase"], "authors": ["M.goto", "Riken structural genomics/proteomics initiative (rsgi)"], "pmid": "15296735", "doi": "10.1016/J.STR.2004.05.013"}
|
||||
{"classification": "Transferase/transferase inhibitor", "pdb": "6C9V", "deposition_date": "2018-01-28", "title": "Mycobacterium tuberculosis adenosine kinase bound to (2r,3s,4r,5r)-2- (hydroxymethyl)-5-(6-(4-phenylpiperazin-1-yl)-9h-purin-9-yl) Tetrahydrofuran-3,4-diol", "Keywords": ["Ucleoside analog", " complex", " inhibitor", " structural genomics", " psi-2", "", "Protein structure initiative", "Tb structural genomics consortium", "", "Tbsgc", "Transferase-transferase inhibitor complex"], "authors": ["R.a.crespo", "Tb structural genomics consortium (tbsgc)"], "pmid": "31002508", "doi": "10.1021/ACS.JMEDCHEM.9B00020"}
|
||||
{"classification": "De novo protein", "pdb": "4LPY", "deposition_date": "2013-07-16", "title": "Crystal structure of tencon variant g10", "Keywords": ["Ibronectin type iii fold", " alternate scaffold", " de novo protein"], "authors": ["A.teplyakov", "G.obmolova", "G.l.gilliland"], "pmid": "24375666", "doi": "10.1002/PROT.24502"}
|
||||
{"classification": "Isomerase", "pdb": "2Y88", "deposition_date": "2011-02-03", "title": "Crystal structure of mycobacterium tuberculosis phosphoribosyl Isomerase (variant d11n) with bound prfar", "Keywords": ["Romatic amino acid biosynthesis", " isomerase", " tim-barrel", " histidine", "Biosynthesis", "Tryptophan biosynthesis"], "authors": ["J.kuper", "A.v.due", "A.geerlof", "M.wilmanns"], "pmid": "21321225", "doi": "10.1073/PNAS.1015996108"}
|
||||
{"classification": "Unknown function", "pdb": "1SR0", "deposition_date": "2004-03-22", "title": "Crystal structure of signalling protein from sheep(sps-40) at 3.0a Resolution using crystal grown in the presence of polysaccharides", "Keywords": ["Ignalling protein", " involution", " unknown function"], "authors": ["D.b.srivastava", "A.s.ethayathulla", "N.singh", "J.kumar", "S.sharma", "T.p.singh"]}
|
||||
{"classification": "Dna binding protein", "pdb": "3RH2", "deposition_date": "2011-04-11", "title": "Crystal structure of a tetr-like transcriptional regulator (sama_0099) From shewanella amazonensis sb2b at 2.42 a resolution", "Keywords": ["Na/rna-binding 3-helical bundle", " structural genomics", " joint center", "For structural genomics", "Jcsg", "Protein structure initiative", "Psi-", "Biology", "Dna binding protein"], "authors": ["Joint center for structural genomics (jcsg)"]}
|
||||
{"classification": "Transferase", "pdb": "2WK5", "deposition_date": "2009-06-05", "title": "Structural features of native human thymidine phosphorylase And in complex with 5-iodouracil", "Keywords": ["Lycosyltransferase", " developmental protein", " angiogenesis", "", "5-iodouracil", "Growth factor", "Enzyme kinetics", "", "Differentiation", "Disease mutation", "Thymidine", "Phosphorylase", "Chemotaxis", "Transferase", "Mutagenesis", "", "Polymorphism"], "authors": ["E.mitsiki", "A.c.papageorgiou", "S.iyer", "N.thiyagarajan", "S.h.prior", "", "D.sleep", "C.finnis", "K.r.acharya"], "pmid": "19555658", "doi": "10.1016/J.BBRC.2009.06.104"}
|
||||
{"classification": "Hydrolase", "pdb": "3P9Y", "deposition_date": "2010-10-18", "title": "Crystal structure of the drosophila melanogaster ssu72-pctd complex", "Keywords": ["Hosphatase", " cis proline", " lmw ptp-like fold", " rna polymerase ii ctd", "", "Hydrolase"], "authors": ["J.w.werner-allen", "P.zhou"], "pmid": "21159777", "doi": "10.1074/JBC.M110.197129"}
|
||||
{"classification": "Recombination/dna", "pdb": "6OEO", "deposition_date": "2019-03-27", "title": "Cryo-em structure of mouse rag1/2 nfc complex (dna1)", "Keywords": ["(d)j recombination", " dna transposition", " rag", " scid", " recombination", "", "Recombination-dna complex"], "authors": ["X.chen", "Y.cui", "Z.h.zhou", "W.yang", "M.gellert"], "pmid": "32015552", "doi": "10.1038/S41594-019-0363-2"}
|
||||
{"classification": "Hydrolase", "pdb": "4ECA", "deposition_date": "1997-02-21", "title": "Asparaginase from e. coli, mutant t89v with covalently bound aspartate", "Keywords": ["Ydrolase", " acyl-enzyme intermediate", " threonine amidohydrolase"], "authors": ["G.j.palm", "J.lubkowski", "A.wlodawer"], "pmid": "8706862", "doi": "10.1016/0014-5793(96)00660-6"}
|
||||
{"classification": "Transcription/protein binding", "pdb": "3UVX", "deposition_date": "2011-11-30", "title": "Crystal structure of the first bromodomain of human brd4 in complex With a diacetylated histone 4 peptide (h4k12ack16ac)", "Keywords": ["Romodomain", " bromodomain containing protein 4", " cap", " hunk1", " mcap", "", "Mitotic chromosome associated protein", "Peptide complex", "Structural", "Genomics consortium", "Sgc", "Transcription-protein binding complex"], "authors": ["P.filippakopoulos", "S.picaud", "T.keates", "E.ugochukwu", "F.von delft", "", "C.h.arrowsmith", "A.m.edwards", "J.weigelt", "C.bountra", "S.knapp", "Structural", "Genomics consortium (sgc)"], "pmid": "22464331", "doi": "10.1016/J.CELL.2012.02.013"}
|
||||
{"classification": "Membrane protein", "pdb": "1TLZ", "deposition_date": "2004-06-10", "title": "Tsx structure complexed with uridine", "Keywords": ["Ucleoside transporter", " beta barrel", " uridine", " membrane", "Protein"], "authors": ["J.ye", "B.van den berg"], "pmid": "15272310", "doi": "10.1038/SJ.EMBOJ.7600330"}
|
||||
{"classification": "Dna binding protein", "pdb": "7AZD", "deposition_date": "2020-11-16", "title": "Dna polymerase sliding clamp from escherichia coli with peptide 20 Bound", "Keywords": ["Ntibacterial drug", " dna binding protein"], "authors": ["C.monsarrat", "G.compain", "C.andre", "I.martiel", "S.engilberge", "V.olieric", "", "P.wolff", "K.brillet", "M.landolfo", "C.silva da veiga", "J.wagner", "G.guichard", "", "D.y.burnouf"], "pmid": "34806883", "doi": "10.1021/ACS.JMEDCHEM.1C00918"}
|
||||
{"classification": "Transferase", "pdb": "5N3K", "deposition_date": "2017-02-08", "title": "Camp-dependent protein kinase a from cricetulus griseus in complex With fragment like molecule o-guanidino-l-homoserine", "Keywords": ["Ragment", " complex", " transferase", " serine threonine kinase", " camp", "", "Kinase", "Pka"], "authors": ["C.siefker", "A.heine", "G.klebe"]}
|
||||
{"classification": "Biosynthetic protein", "pdb": "8H52", "deposition_date": "2022-10-11", "title": "Crystal structure of helicobacter pylori carboxyspermidine Dehydrogenase in complex with nadp", "Keywords": ["Arboxyspermidine dehydrogenase", " biosynthetic protein"], "authors": ["K.y.ko", "S.c.park", "S.y.cho", "S.i.yoon"], "pmid": "36283333", "doi": "10.1016/J.BBRC.2022.10.049"}
|
||||
{"classification": "Metal binding protein", "pdb": "6DYC", "deposition_date": "2018-07-01", "title": "Co(ii)-bound structure of the engineered cyt cb562 variant, ch3", "Keywords": ["Esigned protein", " 4-helix bundle", " electron transport", " metal binding", "Protein"], "authors": ["F.a.tezcan", "J.rittle"], "pmid": "30778140", "doi": "10.1038/S41557-019-0218-9"}
|
||||
{"classification": "Protein fibril", "pdb": "6A6B", "deposition_date": "2018-06-27", "title": "Cryo-em structure of alpha-synuclein fiber", "Keywords": ["Lpha-syn fiber", " parkinson disease", " protein fibril"], "authors": ["Y.w.li", "C.y.zhao", "F.luo", "Z.liu", "X.gui", "Z.luo", "X.zhang", "D.li", "C.liu", "X.li"], "pmid": "30065316", "doi": "10.1038/S41422-018-0075-X"}
|
||||
{"classification": "Dna", "pdb": "7D5E", "deposition_date": "2020-09-25", "title": "Left-handed g-quadruplex containing two bulges", "Keywords": ["-quadruplex", " bulge", " dna", " left-handed"], "authors": ["P.das", "A.maity", "K.h.ngo", "F.r.winnerdy", "B.bakalar", "Y.mechulam", "E.schmitt", "", "A.t.phan"], "pmid": "33503265", "doi": "10.1093/NAR/GKAA1259"}
|
||||
{"classification": "Transferase", "pdb": "3RSY", "deposition_date": "2011-05-02", "title": "Cellobiose phosphorylase from cellulomonas uda in complex with sulfate And glycerol", "Keywords": ["H94", " alpha barrel", " cellobiose phosphorylase", " disaccharide", "Phosphorylase", "Transferase"], "authors": ["A.van hoorebeke", "J.stout", "W.soetaert", "J.van beeumen", "T.desmet", "S.savvides"]}
|
||||
{"classification": "Oxidoreductase", "pdb": "7MCI", "deposition_date": "2021-04-02", "title": "Mofe protein from azotobacter vinelandii with a sulfur-replenished Cofactor", "Keywords": ["Zotobacter vinelandii", " mofe-protein", " nitrogenase", " oxidoreductase"], "authors": ["W.kang", "C.lee", "Y.hu", "M.w.ribbe"], "doi": "10.1038/S41929-022-00782-7"}
|
||||
{"classification": "Dna", "pdb": "1XUW", "deposition_date": "2004-10-26", "title": "Structural rationalization of a large difference in rna affinity Despite a small difference in chemistry between two 2'-o-modified Nucleic acid analogs", "Keywords": ["Na mimetic methylcarbamate amide analog", " dna"], "authors": ["R.pattanayek", "L.sethaphong", "C.pan", "M.prhavc", "T.p.prakash", "M.manoharan", "", "M.egli"], "pmid": "15547979", "doi": "10.1021/JA044637K"}
|
||||
{"classification": "Lyase", "pdb": "7C0D", "deposition_date": "2020-05-01", "title": "Crystal structure of azospirillum brasilense l-2-keto-3-deoxyarabonate Dehydratase (hydroxypyruvate-bound form)", "Keywords": ["-2-keto-3-deoxyarabonate dehydratase", " lyase"], "authors": ["Y.watanabe", "S.watanabe"], "pmid": "32697085", "doi": "10.1021/ACS.BIOCHEM.0C00515"}
|
||||
{"classification": "Signaling protein", "pdb": "5LYK", "deposition_date": "2016-09-28", "title": "Crystal structure of intracellular b30.2 domain of btn3a1 bound to Citrate", "Keywords": ["30.2", " butyrophilin", " signaling protein"], "authors": ["F.mohammed", "A.t.baker", "M.salim", "B.e.willcox"], "pmid": "28862425", "doi": "10.1021/ACSCHEMBIO.7B00694"}
|
||||
{"classification": "Toxin", "pdb": "4IZL", "deposition_date": "2013-01-30", "title": "Structure of the n248a mutant of the panton-valentine leucocidin s Component from staphylococcus aureus", "Keywords": ["I-component leucotoxin", " staphylococcus aureus", " s component", "Leucocidin", "Beta-barrel pore forming toxin", "Toxin"], "authors": ["L.maveyraud", "B.j.laventie", "G.prevost", "L.mourey"], "pmid": "24643034", "doi": "10.1371/JOURNAL.PONE.0092094"}
|
||||
{"classification": "Dna", "pdb": "6F3C", "deposition_date": "2017-11-28", "title": "The cytotoxic [pt(h2bapbpy)] platinum complex interacting with the Cgtacg hexamer", "Keywords": ["Rug-dna complex", " four-way junction", " dna"], "authors": ["M.ferraroni", "C.bazzicalupi", "P.gratteri", "F.papi"], "pmid": "31046177", "doi": "10.1002/ANIE.201814532"}
|
||||
{"classification": "Signaling protein/inhibitor", "pdb": "4L5M", "deposition_date": "2013-06-11", "title": "Complexe of arno sec7 domain with the protein-protein interaction Inhibitor n-(4-hydroxy-2,6-dimethylphenyl)benzenesulfonamide at ph6.5", "Keywords": ["Ec-7domain", " signaling protein-inhibitor complex"], "authors": ["F.hoh", "J.rouhana"], "pmid": "24112024", "doi": "10.1021/JM4009357"}
|
||||
{"classification": "Signaling protein", "pdb": "5I6J", "deposition_date": "2016-02-16", "title": "Crystal structure of srgap2 f-barx", "Keywords": ["Rgap2", " f-bar", " fx", " signaling protein"], "authors": ["M.sporny", "J.guez-haddad", "M.n.isupov", "Y.opatowsky"], "pmid": "28333212", "doi": "10.1093/MOLBEV/MSX094"}
|
||||
{"classification": "Metal binding protein", "pdb": "1Q80", "deposition_date": "2003-08-20", "title": "Solution structure and dynamics of nereis sarcoplasmic calcium binding Protein", "Keywords": ["Ll-alpha", " metal binding protein"], "authors": ["G.rabah", "R.popescu", "J.a.cox", "Y.engelborghs", "C.t.craescu"], "pmid": "15819893", "doi": "10.1111/J.1742-4658.2005.04629.X"}
|
||||
{"classification": "Transferase", "pdb": "1TW1", "deposition_date": "2004-06-30", "title": "Beta-1,4-galactosyltransferase mutant met344his (m344h-gal-t1) complex With udp-galactose and magnesium", "Keywords": ["Et344his mutation; closed conformation; mn binding", " transferase"], "authors": ["B.ramakrishnan", "E.boeggeman", "P.k.qasba"], "pmid": "15449940", "doi": "10.1021/BI049007+"}
|
||||
{"classification": "Rna", "pdb": "2PN4", "deposition_date": "2007-04-23", "title": "Crystal structure of hepatitis c virus ires subdomain iia", "Keywords": ["Cv", " ires", " subdoamin iia", " rna", " strontium", " hepatitis"], "authors": ["Q.zhao", "Q.han", "C.r.kissinger", "P.a.thompson"], "pmid": "18391410", "doi": "10.1107/S0907444908002011"}
|
||||
{"pdb": "1CW0", "title": "crystal structure analysis of very short patch repair (vsr) endonuclease in complex with a duplex dna", "authors": ["S.E.Tsutakawa", "H.Jingami", "K.Morikawa"], "doi": "10.1016/S0092-8674(00)81550-0", "pmid": "10612397"}
|
||||
{"pdb": "2CWW", "title": "crystal structure of thermus thermophilus ttha1280, a putative sam- dependent rna methyltransferase, in complex with s-adenosyl-l- homocysteine", "authors": ["A.A.Pioszak", "K.Murayama", "N.Nakagawa", "A.Ebihara", "S.Kuramitsu", "M.Shirouzu", "S.Yokoyama", "Riken Structural Genomics/proteomics Initiative (Rsgi)"], "doi": "10.1107/S1744309105029842", "pmid": "16511182"}
|
||||
{"pdb": "6CWE", "title": "structure of alpha-gsa[8,6p] bound by cd1d and in complex with the va14vb8.2 tcr", "authors": ["J.Wang", "D.Zajonc"], "doi": null, "pmid": null}
|
||||
{"pdb": "5CWS", "title": "crystal structure of the intact chaetomium thermophilum nsp1-nup49- nup57 channel nucleoporin heterotrimer bound to its nic96 nuclear pore complex attachment site", "authors": ["C.J.Bley", "S.Petrovic", "M.Paduch", "V.Lu", "A.A.Kossiakoff", "A.Hoelz"], "doi": "10.1126/SCIENCE.AAC9176", "pmid": "26316600"}
|
||||
{"pdb": "5CWE", "title": "structure of cyp107l2 from streptomyces avermitilis with lauric acid", "authors": ["T.-V.Pham", "S.-H.Han", "J.-H.Kim", "D.-H.Kim", "L.-W.Kang"], "doi": null, "pmid": null}
|
||||
{"pdb": "7CW4", "title": "acetyl-coa acetyltransferase from bacillus cereus atcc 14579", "authors": ["J.Hong", "K.J.Kim"], "doi": "10.1016/J.BBRC.2020.09.048", "pmid": "32972748"}
|
||||
{"pdb": "2CWP", "title": "crystal structure of metrs related protein from pyrococcus horikoshii", "authors": ["K.Murayama", "M.Kato-Murayama", "M.Shirouzu", "S.Yokoyama", "Riken StructuralGenomics/proteomics Initiative (Rsgi)"], "doi": null, "pmid": null}
|
||||
{"pdb": "2CW7", "title": "crystal structure of intein homing endonuclease ii", "authors": ["H.Matsumura", "H.Takahashi", "T.Inoue", "H.Hashimoto", "M.Nishioka", "S.Fujiwara", "M.Takagi", "T.Imanaka", "Y.Kai"], "doi": "10.1002/PROT.20858", "pmid": "16493661"}
|
||||
{"pdb": "1CWU", "title": "brassica napus enoyl acp reductase a138g mutant complexed with nad+ and thienodiazaborine", "authors": ["A.Roujeinikova", "J.B.Rafferty", "D.W.Rice"], "doi": "10.1074/JBC.274.43.30811", "pmid": "10521472"}
|
||||
{"pdb": "3CWN", "title": "escherichia coli transaldolase b mutant f178y", "authors": ["T.Sandalova", "G.Schneider", "A.Samland"], "doi": "10.1074/JBC.M803184200", "pmid": "18687684"}
|
||||
{"pdb": "1CWL", "title": "human cyclophilin a complexed with 4 4-hydroxy-meleu cyclosporin", "authors": ["V.Mikol", "J.Kallen", "P.Taylor", "M.D.Walkinshaw"], "doi": "10.1006/JMBI.1998.2108", "pmid": "9769216"}
|
||||
{"pdb": "3CW2", "title": "crystal structure of the intact archaeal translation initiation factor 2 from sulfolobus solfataricus .", "authors": ["E.A.Stolboushkina", "S.V.Nikonov", "A.D.Nikulin", "U.Blaesi", "D.J.Manstein", "R.V.Fedorov", "M.B.Garber", "O.S.Nikonov"], "doi": "10.1016/J.JMB.2008.07.039", "pmid": "18675278"}
|
||||
{"pdb": "3CW9", "title": "4-chlorobenzoyl-coa ligase/synthetase in the thioester-forming conformation, bound to 4-chlorophenacyl-coa", "authors": ["A.S.Reger", "J.Cao", "R.Wu", "D.Dunaway-Mariano", "A.M.Gulick"], "doi": "10.1021/BI800696Y", "pmid": "18620418"}
|
||||
{"pdb": "3CWU", "title": "crystal structure of an alka host/guest complex 2'-fluoro-2'-deoxy-1, n6-ethenoadenine:thymine base pair", "authors": ["B.R.Bowman", "S.Lee", "S.Wang", "G.L.Verdine"], "doi": "10.1016/J.STR.2008.04.012", "pmid": "18682218"}
|
||||
{"pdb": "5CWF", "title": "crystal structure of de novo designed helical repeat protein dhr8", "authors": ["G.Bhabha", "D.C.Ekiert"], "doi": "10.1038/NATURE16162", "pmid": "26675729"}
|
|
@ -1,36 +1,6 @@
|
|||
{"pid": " Q6GZX4", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 43"}], "title": "Putative transcription factor 001R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q6GZX3", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 45"}], "title": "Uncharacterized protein 002L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q197F8", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-02-23", "date_info": "entry version 29"}], "title": "Uncharacterized protein 002R", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
|
||||
{"pid": " Q197F7", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2020-08-12", "date_info": "entry version 23"}], "title": "Uncharacterized protein 003L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
|
||||
{"pid": " Q6GZX2", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 37"}], "title": "Uncharacterized protein 3R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q6GZX1", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 38"}], "title": "Uncharacterized protein 004R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q197F5", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-10-12", "date_info": "entry version 32"}], "title": "Uncharacterized protein 005L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
|
||||
{"pid": " Q6GZX0", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 47"}], "title": "Uncharacterized protein 005R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q91G88", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2001-12-01", "date_info": "sequence version 1"}, {"date": "2023-06-28", "date_info": "entry version 53"}], "title": "Putative KilA-N domain-containing protein 006L", "organism_species": "Invertebrate iridescent virus 6 (IIV-6) (Chilo iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Iridovirus"], "references": [{"PubMed": "17239238"}, {"DOI": "10.1186/1743-422x-4-11"}]}
|
||||
{"pid": " Q6GZW9", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 34"}], "title": "Uncharacterized protein 006R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q6GZW8", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 32"}], "title": "Uncharacterized protein 007R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q197F3", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 28"}], "title": "Uncharacterized protein 007R", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
|
||||
{"pid": " Q197F2", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-02-23", "date_info": "entry version 22"}], "title": "Uncharacterized protein 008L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
|
||||
{"pid": " Q6GZW6", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 67"}], "title": "Putative helicase 009L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q91G85", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2001-12-01", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 38"}], "title": "Uncharacterized protein 009R", "organism_species": "Invertebrate iridescent virus 6 (IIV-6) (Chilo iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Iridovirus"], "references": [{"PubMed": "17239238"}, {"DOI": "10.1186/1743-422x-4-11"}]}
|
||||
{"pid": " Q6GZW5", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 37"}], "title": "Uncharacterized protein 010R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q197E9", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 28"}], "title": "Uncharacterized protein 011L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
|
||||
{"pid": " Q6GZW4", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 37"}], "title": "Uncharacterized protein 011R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q6GZW3", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 35"}], "title": "Uncharacterized protein 012L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q197E7", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 37"}], "title": "Uncharacterized protein IIV3-013L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
|
||||
{"pid": " Q6GZW2", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 30"}], "title": "Uncharacterized protein 013R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q6GZW1", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 35"}], "title": "Uncharacterized protein 014R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q6GZW0", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 50"}], "title": "Uncharacterized protein 015R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q6GZV8", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 35"}], "title": "Uncharacterized protein 017L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q6GZV7", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 33"}], "title": "Uncharacterized protein 018L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q6GZV6", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 87"}], "title": "Putative serine/threonine-protein kinase 019R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q6GZV5", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 40"}], "title": "Uncharacterized protein 020R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q6GZV4", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 35"}], "title": "Uncharacterized protein 021L", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q197D8", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-12-14", "date_info": "entry version 35"}], "title": "Transmembrane protein 022L", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
|
||||
{"pid": " Q6GZV2", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 33"}], "title": "Uncharacterized protein 023R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q197D7", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2023-02-22", "date_info": "entry version 25"}], "title": "Uncharacterized protein 023R", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
|
||||
{"pid": " Q6GZV1", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 37"}], "title": "Uncharacterized protein 024R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q197D5", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2006-07-11", "date_info": "sequence version 1"}, {"date": "2022-10-12", "date_info": "entry version 24"}], "title": "Uncharacterized protein 025R", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus"], "references": [{"PubMed": "16912294"}, {"DOI": "10.1128/jvi.00464-06"}]}
|
||||
{"pid": " Q91G70", "dates": [{"date": "2009-06-16", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2001-12-01", "date_info": "sequence version 1"}, {"date": "2020-08-12", "date_info": "entry version 32"}], "title": "Uncharacterized protein 026R", "organism_species": "Invertebrate iridescent virus 6 (IIV-6) (Chilo iridescent virus)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Iridovirus"], "references": [{"PubMed": "17239238"}, {"DOI": "10.1186/1743-422x-4-11"}]}
|
||||
{"pid": " Q6GZU9", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 49"}], "title": "Uncharacterized protein 027R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": " Q6GZU8", "dates": [{"date": "2011-06-28", "date_info": "integrated into UniProtKB/Swiss-Prot"}, {"date": "2004-07-19", "date_info": "sequence version 1"}, {"date": "2023-09-13", "date_info": "entry version 55"}], "title": "Uncharacterized protein 028R", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3)", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus"], "references": [{"PubMed": "15165820"}, {"DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": "Q6GZX4", "dates": [{"date": "28-JUN-2011", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "19-JUL-2004", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 41."}], "title": "Putative transcription factor 001R;", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus."], "references": [{"PubMed": "15165820"}, {" DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": "Q6GZX3", "dates": [{"date": "28-JUN-2011", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "19-JUL-2004", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 42."}], "title": "Uncharacterized protein 002L;", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus."], "references": [{"PubMed": "15165820"}, {" DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": "Q197F8", "dates": [{"date": "16-JUN-2009", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "11-JUL-2006", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 27."}], "title": "Uncharacterized protein 002R;", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus."], "references": [{"PubMed": "16912294"}, {" DOI": "10.1128/jvi.00464-06"}]}
|
||||
{"pid": "Q197F7", "dates": [{"date": "16-JUN-2009", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "11-JUL-2006", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 23."}], "title": "Uncharacterized protein 003L;", "organism_species": "Invertebrate iridescent virus 3 (IIV-3) (Mosquito iridescent virus).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Betairidovirinae", "Chloriridovirus."], "references": [{"PubMed": "16912294"}, {" DOI": "10.1128/jvi.00464-06"}]}
|
||||
{"pid": "Q6GZX2", "dates": [{"date": "28-JUN-2011", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "19-JUL-2004", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 36."}], "title": "Uncharacterized protein 3R;", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus."], "references": [{"PubMed": "15165820"}, {" DOI": "10.1016/j.virol.2004.02.019"}]}
|
||||
{"pid": "Q6GZX1", "dates": [{"date": "28-JUN-2011", "date_info": " integrated into UniProtKB/Swiss-Prot."}, {"date": "19-JUL-2004", "date_info": " sequence version 1."}, {"date": "12-AUG-2020", "date_info": " entry version 34."}], "title": "Uncharacterized protein 004R;", "organism_species": "Frog virus 3 (isolate Goorha) (FV-3).", "subjects": ["Viruses", "Varidnaviria", "Bamfordvirae", "Nucleocytoviricota", "Megaviricetes", "Pimascovirales", "Iridoviridae", "Alphairidovirinae", "Ranavirus."], "references": [{"PubMed": "15165820"}, {" DOI": "10.1016/j.virol.2004.02.019"}]}
|
|
@ -0,0 +1,185 @@
|
|||
<xsl:stylesheet
|
||||
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
|
||||
xmlns:oaire="http://namespace.openaire.eu/schema/oaire/"
|
||||
xmlns:vocabulary="http://eu/dnetlib/transform/clean"
|
||||
xmlns:dateCleaner="http://eu/dnetlib/transform/dateISO"
|
||||
xmlns:oaf="http://namespace.openaire.eu/oaf"
|
||||
xmlns:oai="http://www.openarchives.org/OAI/2.0/"
|
||||
xmlns:datacite="http://datacite.org/schema/kernel-4"
|
||||
xmlns:dri="http://www.driver-repository.eu/namespace/dri"
|
||||
xmlns:xs="http://www.w3.org/2001/XMLSchema"
|
||||
xmlns:dr="http://www.driver-repository.eu/namespace/dr"
|
||||
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
|
||||
xmlns:dc="http://purl.org/dc/elements/1.1/"
|
||||
exclude-result-prefixes="xsl vocabulary dateCleaner" version="2.0">
|
||||
<xsl:param name="varOfficialName" />
|
||||
<xsl:param name="varDataSourceId" />
|
||||
<xsl:param name="varFP7" select="'corda_______::'" />
|
||||
<xsl:param name="varH2020" select="'corda__h2020::'" />
|
||||
<xsl:param name="repoCode"
|
||||
select="substring-before(//*[local-name() = 'header']/*[local-name()='recordIdentifier'], ':')" />
|
||||
<xsl:param name="index" select="0" />
|
||||
<xsl:param name="transDate" select="current-dateTime()" />
|
||||
asdf;klamsdof'sdn &
|
||||
<xsl:template match="/asdfasdf asdf&">
|
||||
c:format'" />
|
||||
</xsl:call-template>
|
||||
<xsl:call-template name="allElements">
|
||||
<xsl:with-param name="sourceElement" select="//dc:type" />
|
||||
<xsl:with-param name="targetElement" select="'dc:type'" />
|
||||
</xsl:call-template>
|
||||
<xsl:call-template name="allElements">
|
||||
<xsl:with-param name="sourceElement" select="//dc:source" />
|
||||
<xsl:with-param name="targetElement" select="'dc:source'" />
|
||||
</xsl:call-template>
|
||||
<dc:language>
|
||||
<xsl:value-of select="vocabulary:clean( //dc:language, 'dnet:languages')" />
|
||||
</dc:language>
|
||||
<xsl:call-template name="allElements">
|
||||
<xsl:with-param name="sourceElement" select="//dc:rights" />
|
||||
<xsl:with-param name="targetElement" select="'dc:rights'" />
|
||||
</xsl:call-template>
|
||||
<xsl:call-template name="allElements">
|
||||
<xsl:with-param name="sourceElement" select="//dc:relation[not(starts-with(.,'info:cnr-pdr'))]" />
|
||||
<xsl:with-param name="targetElement" select="'dc:relation'" />
|
||||
</xsl:call-template>
|
||||
|
||||
<xsl:call-template name="allElements">
|
||||
<xsl:with-param name="sourceElement" select="//dc:identifier[starts-with(., 'http')]" />
|
||||
<xsl:with-param name="targetElement" select="'dc:identifier'" />
|
||||
</xsl:call-template>
|
||||
<xsl:for-each select="//dc:relation">
|
||||
<xsl:if test="matches(normalize-space(.), '(info:eu-repo/grantagreement/ec/fp7/)(\d\d\d\d\d\d)(.*)', 'i')">
|
||||
<oaf:projectid>
|
||||
<xsl:value-of select="concat($varFP7, replace(normalize-space(.), '(info:eu-repo/grantagreement/ec/fp7/)(\d\d\d\d\d\d)(.*)', '$2', 'i'))" />
|
||||
</oaf:projectid>
|
||||
</xsl:if>
|
||||
<xsl:if test="matches(normalize-space(.), '(info:eu-repo/grantagreement/ec/h2020/)(\d\d\d\d\d\d)(.*)', 'i')">
|
||||
<oaf:projectid>
|
||||
<xsl:value-of select="concat($varH2020, replace(normalize-space(.), '(info:eu-repo/grantagreement/ec/h2020/)(\d\d\d\d\d\d)(.*)', '$2', 'i'))" />
|
||||
</oaf:projectid>
|
||||
</xsl:if>
|
||||
</xsl:for-each>
|
||||
|
||||
<oaf:accessrights>
|
||||
<xsl:value-of select="vocabulary:clean( //dc:rights, 'dnet:access_modes')" />
|
||||
</oaf:accessrights>
|
||||
|
||||
<xsl:variable name="varCobjCategory" select="vocabulary:clean( //dc:type, 'dnet:publication_resource')" />
|
||||
<xsl:variable name="varSuperType" select="vocabulary:clean( $varCobjCategory, 'dnet:result_typologies')" />
|
||||
<dr:CobjCategory type="{$varSuperType}"><xsl:value-of select="$varCobjCategory" /></dr:CobjCategory>
|
||||
|
||||
|
||||
<xsl:variable name="varRefereedConvt" select="for $i in (//dc:type, //dc:description, //oai:setSpec) return vocabulary:clean( normalize-space($i), 'dnet:review_levels')" />
|
||||
<xsl:variable name="varRefereedIdntf" select="(//*[string(node-name(.)) = 'dc:identifier' and matches(lower-case(.), '(^|.*[\.\-_/\s\(\)%\d#])pre[\.\-_/\s\(\)%\d#]?prints?([\.\-_/\s\(\)%\d#].*)?$')][count(//dc:identifier) = 1]/'0002', //*[string(node-name(.)) = 'dc:identifier' and matches(lower-case(.), '(^|.*[\.\-_/\s\(\)%\d#])refereed([\.\-_/\s\(\)\d%\d#].*)?$')]/'0001', //*[string(node-name(.)) = 'dc:identifier' and matches(lower-case(.), '.*-peer-reviewed-(fulltext-)?article-.*')]/'0001')" />
|
||||
<xsl:variable name="varRefereedSourc" select="//*[string(node-name(.)) = ('dc:source', 'dc:publisher') and matches(lower-case(.), '^(.*\s)?pre[\s\-_]*prints?([\s\.,].*)?$')]/'0002'" />
|
||||
<xsl:variable name="varRefereedDescr" select="(//dc:description[matches(lower-case(.), '.*(this\s*book|this\s*volume|it)\s*constitutes\s*the\s*(thoroughly\s*)?refereed') or matches(lower-case(.), '.*peer[\.\-_/\s\(\)]?review\s*under\s*responsibility\s*of.*') or matches(lower-case(.), '(this|a)\s*(article|preprint)\s*(has\s*been\s*)?(peer[\-\s]*)?reviewed\s*and\s*recommended\s*by\s*peer[\-\s]*community')]/'0001', //dc:description[matches(., '^version\s*(préliminaire.*|preliminary.*|0$)')]/'0002')" />
|
||||
<xsl:variable name="varRefereedTitle" select="(//dc:title[matches(lower-case(.), '.*\[.*peer[\s\-\._]*review\s*:.*\]\s*$')]/'0001', //dc:title[matches(lower-case(.), '.*\(\s*pre[\s\-\._]*prints?\s*\)\s*$')]/'0002')" />
|
||||
<xsl:variable name="varRefereedSubjt" select="(//dc:subject[matches(lower-case(.), '^\s*refereed\s*$')][//oaf:datasourceprefix = 'narcis______']/'0001', //dc:subject[matches(lower-case(.), '^\s*no[nt].{0,3}refereed\s*$')][//oaf:datasourceprefix = 'narcis______']/'0002')" />
|
||||
<xsl:variable name="varRefereed" select="($varRefereedConvt, $varRefereedIdntf, $varRefereedSourc, $varRefereedDescr, $varRefereedTitle, $varRefereedSubjt)" />
|
||||
<xsl:choose>
|
||||
<xsl:when test="count($varRefereed[. = '0001']) > 0">
|
||||
<oaf:refereed>
|
||||
<xsl:value-of select="'0001'" />
|
||||
</oaf:refereed>
|
||||
</xsl:when>
|
||||
<xsl:when test="count($varRefereed[. = '0002']) > 0">
|
||||
<oaf:refereed>
|
||||
<xsl:value-of select="'0002'" />
|
||||
</oaf:refereed>
|
||||
</xsl:when>
|
||||
</xsl:choose>
|
||||
|
||||
<oaf:dateAccepted>
|
||||
<xsl:value-of select="dateCleaner:dateISO( //dc:date[1] )" />
|
||||
</oaf:dateAccepted>
|
||||
|
||||
<xsl:if test="//dc:relation[starts-with(., 'http')] and //dc:rights[.='info:eu-repo/semantics/openAccess']">
|
||||
<oaf:fulltext>
|
||||
<xsl:value-of select="//dc:relation[starts-with(., 'http')]" />
|
||||
</oaf:fulltext>
|
||||
</xsl:if>
|
||||
|
||||
<oaf:hostedBy name="{$varOfficialName}" id="{$varDataSourceId}" />
|
||||
<oaf:collectedFrom name="{$varOfficialName}" id="{$varDataSourceId}" />
|
||||
|
||||
<xsl:variable name="varKnownFileEndings" select="('.bmp', '.doc', '.docx', '.epub', '.flv', '.jpeg', '.jpg', '.m4v', '.mp4', '.mpg', '.odp', '.pdf', '.png', '.ppt', '.tiv', '.txt', '.xls', '.xlsx', '.zip')" />
|
||||
<xsl:variable name="varIdDoi" select="distinct-values((//dc:identifier[starts-with(., '10.')][matches(., '(10[.][0-9]{4,}[^\s/>]*/[^\s>]+)')], //dc:identifier[starts-with(., 'http') and (contains(., '://dx.doi.org/10.') or contains(., '://doi.org/10.'))]/substring-after(., 'doi.org/'), //dc:identifier[starts-with(lower-case(.), 'doi:10.')]/substring-after(lower-case(.), 'doi:')))" />
|
||||
<xsl:for-each select="$varIdDoi">
|
||||
<oaf:identifier identifierType="doi">
|
||||
<xsl:value-of select="." />
|
||||
</oaf:identifier>
|
||||
</xsl:for-each>
|
||||
|
||||
<xsl:variable name="varIdHdl" select="distinct-values(//dc:identifier[starts-with(., 'http') and contains(., '://hdl.handle.net/')]/substring-after(., 'hdl.handle.net/'))" />
|
||||
<xsl:for-each select="$varIdHdl" >
|
||||
<oaf:identifier identifierType="handle">
|
||||
<xsl:value-of select="." />
|
||||
</oaf:identifier>
|
||||
</xsl:for-each>
|
||||
|
||||
<xsl:variable name="varIdUrn" select="distinct-values(//dc:identifier[starts-with(., 'urn:nbn:nl:') or starts-with(., 'URN:NBN:NL:')])" />
|
||||
<xsl:for-each select="$varIdUrn">
|
||||
<oaf:identifier identifierType="urn">
|
||||
<xsl:value-of select="." />
|
||||
</oaf:identifier>
|
||||
</xsl:for-each>
|
||||
|
||||
<xsl:variable name="varOrigBaseUrl" select="//*[local-name() = 'about']/*[local-name() = 'provenance']//*[local-name() = 'originDescription' and not(./*[local-name() = 'originDescription'])]/*[local-name() = 'baseURL']" />
|
||||
<xsl:variable name="varIdLdpg" select="distinct-values(//dc:identifier[(contains(substring-after(., '://'), '/') and contains($varOrigBaseUrl, substring-before(substring-after(., '://'), '/'))) or (contains(substring-after(., '://'), ':') and contains($varOrigBaseUrl, substring-before(substring-after(., '://'), ':')))][not(replace(lower-case(.), '.*(\.[a-z]*)$', '$1') = $varKnownFileEndings)])" />
|
||||
<xsl:for-each select="$varIdLdpg">
|
||||
<oaf:identifier identifierType="landingPage">
|
||||
<xsl:value-of select="." />
|
||||
</oaf:identifier>
|
||||
</xsl:for-each>
|
||||
|
||||
<xsl:variable name="varIdUrl" select="distinct-values(//dc:identifier[starts-with(., 'http')][not(contains(., '://dx.doi.org/') or contains(., '://doi.org/') or contains(., '://hdl.handle.net/'))][count(index-of($varIdLdpg, .)) = 0])" />
|
||||
<xsl:for-each select="$varIdUrl">
|
||||
<oaf:identifier identifierType="url">
|
||||
<xsl:value-of select="." />
|
||||
</oaf:identifier>
|
||||
</xsl:for-each>
|
||||
|
||||
<xsl:for-each select="//oai:setSpec">
|
||||
<xsl:variable name="rorDsId" select="vocabulary:clean(., 'cnr:institutes')" />
|
||||
<xsl:if test="contains($rorDsId, '/ror.org/')">
|
||||
<oaf:relation relType="resultOrganization" subRelType="affiliation" relClass="hasAuthorInstitution">
|
||||
<xsl:value-of select="concat('ror_________::', $rorDsId)" />
|
||||
</oaf:relation>
|
||||
</xsl:if>
|
||||
</xsl:for-each>
|
||||
|
||||
</metadata>
|
||||
|
||||
<xsl:copy-of select="//*[local-name() = 'about']" />
|
||||
</record>
|
||||
</xsl:template>
|
||||
|
||||
|
||||
<xsl:template name="allElements">
|
||||
<xsl:param name="sourceElement" />
|
||||
<xsl:param name="targetElement" />
|
||||
|
||||
<xsl:for-each select="$sourceElement">
|
||||
<xsl:element name="{$targetElement}">
|
||||
<xsl:value-of select="normalize-space(.)" />
|
||||
</xsl:element>
|
||||
</xsl:for-each>
|
||||
</xsl:template>
|
||||
|
||||
<xsl:template match="//*[local-name() = 'header']">
|
||||
<xsl:copy>
|
||||
<xsl:apply-templates select="node()|@*" />
|
||||
<xsl:element name="dr:dateOfTransformation">
|
||||
<xsl:value-of select="$transDate" />
|
||||
</xsl:element>
|
||||
</xsl:copy>
|
||||
</xsl:template>
|
||||
|
||||
<xsl:template match="node()|@*">
|
||||
<xsl:copy>
|
||||
<xsl:apply-templates select="node()|@*" />
|
||||
</xsl:copy>
|
||||
</xsl:template>
|
||||
|
||||
</xsl:stylesheet>
|
|
@ -4,6 +4,7 @@ package eu.dnetlib.dhp.oa.dedup;
|
|||
import java.util.*;
|
||||
import java.util.stream.Stream;
|
||||
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
|
||||
import org.apache.commons.beanutils.BeanUtils;
|
||||
import org.apache.commons.lang3.StringUtils;
|
||||
import org.apache.spark.api.java.function.FlatMapFunction;
|
||||
|
@ -14,6 +15,7 @@ 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.utils.MergeUtils;
|
||||
import eu.dnetlib.dhp.schema.oaf.Author;
|
||||
import eu.dnetlib.dhp.schema.oaf.DataInfo;
|
||||
import eu.dnetlib.dhp.schema.oaf.OafEntity;
|
||||
|
@ -23,190 +25,190 @@ import scala.Tuple3;
|
|||
import scala.collection.JavaConversions;
|
||||
|
||||
public class DedupRecordFactory {
|
||||
public static final class DedupRecordReduceState {
|
||||
public final String dedupId;
|
||||
public static final class DedupRecordReduceState {
|
||||
public final String dedupId;
|
||||
|
||||
public final ArrayList<String> aliases = new ArrayList<>();
|
||||
public final ArrayList<String> aliases = new ArrayList<>();
|
||||
|
||||
public final HashSet<String> acceptanceDate = new HashSet<>();
|
||||
public final HashSet<String> acceptanceDate = new HashSet<>();
|
||||
|
||||
public OafEntity entity;
|
||||
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 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;
|
||||
}
|
||||
}
|
||||
public String getDedupId() {
|
||||
return dedupId;
|
||||
}
|
||||
}
|
||||
|
||||
private static final int MAX_ACCEPTANCE_DATE = 20;
|
||||
private static final int MAX_ACCEPTANCE_DATE = 20;
|
||||
|
||||
private DedupRecordFactory() {
|
||||
}
|
||||
private DedupRecordFactory() {
|
||||
}
|
||||
|
||||
public static Dataset<OafEntity> createDedupRecord(
|
||||
final SparkSession spark,
|
||||
final DataInfo dataInfo,
|
||||
final String mergeRelsInputPath,
|
||||
final String entitiesInputPath,
|
||||
final Class<OafEntity> clazz) {
|
||||
public static Dataset<OafEntity> createDedupRecord(
|
||||
final SparkSession spark,
|
||||
final DataInfo dataInfo,
|
||||
final String mergeRelsInputPath,
|
||||
final String entitiesInputPath,
|
||||
final Class<OafEntity> clazz) {
|
||||
|
||||
final long ts = System.currentTimeMillis();
|
||||
final Encoder<OafEntity> beanEncoder = Encoders.bean(clazz);
|
||||
final Encoder<OafEntity> kryoEncoder = Encoders.kryo(clazz);
|
||||
final long ts = System.currentTimeMillis();
|
||||
final Encoder<OafEntity> beanEncoder = Encoders.bean(clazz);
|
||||
final Encoder<OafEntity> kryoEncoder = Encoders.kryo(clazz);
|
||||
|
||||
// <id, json_entity>
|
||||
Dataset<Row> entities = spark
|
||||
.read()
|
||||
.schema(Encoders.bean(clazz).schema())
|
||||
.json(entitiesInputPath)
|
||||
.as(beanEncoder)
|
||||
.map(
|
||||
(MapFunction<OafEntity, Tuple2<String, OafEntity>>) entity -> {
|
||||
return new Tuple2<>(entity.getId(), entity);
|
||||
},
|
||||
Encoders.tuple(Encoders.STRING(), kryoEncoder))
|
||||
.selectExpr("_1 AS id", "_2 AS kryoObject");
|
||||
// <id, json_entity>
|
||||
Dataset<Row> entities = spark
|
||||
.read()
|
||||
.schema(Encoders.bean(clazz).schema())
|
||||
.json(entitiesInputPath)
|
||||
.as(beanEncoder)
|
||||
.map(
|
||||
(MapFunction<OafEntity, Tuple2<String, OafEntity>>) entity -> {
|
||||
return new Tuple2<>(entity.getId(), entity);
|
||||
},
|
||||
Encoders.tuple(Encoders.STRING(), kryoEncoder))
|
||||
.selectExpr("_1 AS id", "_2 AS kryoObject");
|
||||
|
||||
// <source, target>: source is the dedup_id, target is the id of the mergedIn
|
||||
Dataset<Row> mergeRels = spark
|
||||
.read()
|
||||
.load(mergeRelsInputPath)
|
||||
.where("relClass == 'merges'")
|
||||
.selectExpr("source as dedupId", "target as id");
|
||||
// <source, target>: source is the dedup_id, target is the id of the mergedIn
|
||||
Dataset<Row> mergeRels = spark
|
||||
.read()
|
||||
.load(mergeRelsInputPath)
|
||||
.where("relClass == 'merges'")
|
||||
.selectExpr("source as dedupId", "target as id");
|
||||
|
||||
return mergeRels
|
||||
.join(entities, JavaConversions.asScalaBuffer(Collections.singletonList("id")), "left")
|
||||
.select("dedupId", "id", "kryoObject")
|
||||
.as(Encoders.tuple(Encoders.STRING(), Encoders.STRING(), kryoEncoder))
|
||||
.map(
|
||||
(MapFunction<Tuple3<String, String, OafEntity>, DedupRecordReduceState>) t -> new DedupRecordReduceState(
|
||||
t._1(), t._2(), t._3()),
|
||||
Encoders.kryo(DedupRecordReduceState.class))
|
||||
.groupByKey(
|
||||
(MapFunction<DedupRecordReduceState, String>) DedupRecordReduceState::getDedupId, Encoders.STRING())
|
||||
.reduceGroups(
|
||||
(ReduceFunction<DedupRecordReduceState>) (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 mergeRels
|
||||
.join(entities, JavaConversions.asScalaBuffer(Collections.singletonList("id")), "left")
|
||||
.select("dedupId", "id", "kryoObject")
|
||||
.as(Encoders.tuple(Encoders.STRING(), Encoders.STRING(), kryoEncoder))
|
||||
.map(
|
||||
(MapFunction<Tuple3<String, String, OafEntity>, DedupRecordReduceState>) t -> new DedupRecordReduceState(
|
||||
t._1(), t._2(), t._3()),
|
||||
Encoders.kryo(DedupRecordReduceState.class))
|
||||
.groupByKey(
|
||||
(MapFunction<DedupRecordReduceState, String>) DedupRecordReduceState::getDedupId, Encoders.STRING())
|
||||
.reduceGroups(
|
||||
(ReduceFunction<DedupRecordReduceState>) (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<Tuple2<String, DedupRecordReduceState>, OafEntity>) t -> {
|
||||
String dedupId = t._1();
|
||||
DedupRecordReduceState agg = t._2();
|
||||
return t1;
|
||||
})
|
||||
.flatMap((FlatMapFunction<Tuple2<String, DedupRecordReduceState>, OafEntity>) t -> {
|
||||
String dedupId = t._1();
|
||||
DedupRecordReduceState agg = t._2();
|
||||
|
||||
if (agg.acceptanceDate.size() >= MAX_ACCEPTANCE_DATE) {
|
||||
return Collections.emptyIterator();
|
||||
}
|
||||
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);
|
||||
}
|
||||
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);
|
||||
}
|
||||
|
||||
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);
|
||||
}
|
||||
}
|
||||
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);
|
||||
}
|
||||
}
|
||||
|
||||
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);
|
||||
}
|
||||
}
|
||||
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);
|
||||
}
|
||||
}
|
||||
|
||||
private static OafEntity reduceEntity(OafEntity entity, OafEntity duplicate) {
|
||||
private static OafEntity reduceEntity(OafEntity entity, OafEntity duplicate) {
|
||||
|
||||
if (duplicate == null) {
|
||||
return entity;
|
||||
}
|
||||
if (duplicate == null) {
|
||||
return entity;
|
||||
}
|
||||
|
||||
int compare = new IdentifierComparator<>()
|
||||
.compare(Identifier.newInstance(entity), Identifier.newInstance(duplicate));
|
||||
int compare = new IdentifierComparator<>()
|
||||
.compare(Identifier.newInstance(entity), Identifier.newInstance(duplicate));
|
||||
|
||||
if (compare > 0) {
|
||||
OafEntity swap = duplicate;
|
||||
duplicate = entity;
|
||||
entity = swap;
|
||||
}
|
||||
if (compare > 0) {
|
||||
OafEntity swap = duplicate;
|
||||
duplicate = entity;
|
||||
entity = swap;
|
||||
}
|
||||
|
||||
entity.mergeFrom(duplicate);
|
||||
entity = MergeUtils.checkedMerge(entity, duplicate);
|
||||
|
||||
if (ModelSupport.isSubClass(duplicate, Result.class)) {
|
||||
Result re = (Result) entity;
|
||||
Result rd = (Result) duplicate;
|
||||
if (ModelSupport.isSubClass(duplicate, Result.class)) {
|
||||
Result re = (Result) entity;
|
||||
Result rd = (Result) duplicate;
|
||||
|
||||
List<List<Author>> authors = new ArrayList<>();
|
||||
if (re.getAuthor() != null) {
|
||||
authors.add(re.getAuthor());
|
||||
}
|
||||
if (rd.getAuthor() != null) {
|
||||
authors.add(rd.getAuthor());
|
||||
}
|
||||
List<List<Author>> authors = new ArrayList<>();
|
||||
if (re.getAuthor() != null) {
|
||||
authors.add(re.getAuthor());
|
||||
}
|
||||
if (rd.getAuthor() != null) {
|
||||
authors.add(rd.getAuthor());
|
||||
}
|
||||
|
||||
re.setAuthor(AuthorMerger.merge(authors));
|
||||
}
|
||||
re.setAuthor(AuthorMerger.merge(authors));
|
||||
}
|
||||
|
||||
return entity;
|
||||
}
|
||||
return entity;
|
||||
}
|
||||
|
||||
public static <T extends OafEntity> T entityMerger(
|
||||
String id, Iterator<Tuple2<String, T>> entities, long ts, DataInfo dataInfo, Class<T> clazz) {
|
||||
T base = entities.next()._2();
|
||||
public static <T extends OafEntity> T entityMerger(
|
||||
String id, Iterator<Tuple2<String, T>> entities, long ts, DataInfo dataInfo, Class<T> clazz) {
|
||||
T base = entities.next()._2();
|
||||
|
||||
while (entities.hasNext()) {
|
||||
T duplicate = entities.next()._2();
|
||||
if (duplicate != null)
|
||||
base = (T) reduceEntity(base, duplicate);
|
||||
}
|
||||
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);
|
||||
base.setId(id);
|
||||
base.setDataInfo(dataInfo);
|
||||
base.setLastupdatetimestamp(ts);
|
||||
|
||||
return base;
|
||||
}
|
||||
return base;
|
||||
}
|
||||
|
||||
}
|
||||
|
|
|
@ -3,6 +3,7 @@ package eu.dnetlib.dhp.oa.dedup;
|
|||
|
||||
import static org.apache.spark.sql.functions.col;
|
||||
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils;
|
||||
import org.apache.commons.io.IOUtils;
|
||||
import org.apache.spark.SparkConf;
|
||||
import org.apache.spark.api.java.function.MapFunction;
|
||||
|
@ -127,10 +128,8 @@ public class SparkPropagateRelation extends AbstractSparkAction {
|
|||
(MapFunction<Relation, String>) r -> String
|
||||
.join(" ", r.getSource(), r.getTarget(), r.getRelType(), r.getSubRelType(), r.getRelClass()),
|
||||
Encoders.STRING())
|
||||
.reduceGroups((ReduceFunction<Relation>) (b, a) -> {
|
||||
b.mergeFrom(a);
|
||||
return b;
|
||||
})
|
||||
.reduceGroups((ReduceFunction<Relation>) MergeUtils::mergeRelation
|
||||
)
|
||||
.map((MapFunction<Tuple2<String, Relation>, Relation>) Tuple2::_2, REL_BEAN_ENC);
|
||||
|
||||
final String outputRelationPath = graphOutputPath + "/relation";
|
||||
|
|
|
@ -15,12 +15,4 @@
|
|||
<name>oozie.action.sharelib.for.spark</name>
|
||||
<value>spark2</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>hiveMetastoreUris</name>
|
||||
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
|
||||
</property>
|
||||
<property>
|
||||
<name>pivotHistoryDatabase</name>
|
||||
<value>​</value>
|
||||
</property>
|
||||
</configuration>
|
|
@ -198,8 +198,6 @@
|
|||
<arg>--isLookUpUrl</arg><arg>${isLookUpUrl}</arg>
|
||||
<arg>--actionSetId</arg><arg>${actionSetId}</arg>
|
||||
<arg>--cutConnectedComponent</arg><arg>${cutConnectedComponent}</arg>
|
||||
<arg>--hiveMetastoreUris</arg><arg>${hiveMetastoreUris}</arg>
|
||||
<arg>--pivotHistoryDatabase</arg><arg>${pivotHistoryDatabase}</arg>
|
||||
</spark>
|
||||
<ok to="PrepareOrgRels"/>
|
||||
<error to="Kill"/>
|
||||
|
|
|
@ -73,6 +73,12 @@
|
|||
"name": "Irish Nephrology Society",
|
||||
"synonym": []
|
||||
},
|
||||
{
|
||||
"id": "100011062",
|
||||
"uri": "http://dx.doi.org/10.13039/100011062",
|
||||
"name": "Asian Spinal Cord Network",
|
||||
"synonym": []
|
||||
},
|
||||
{
|
||||
"id": "100011096",
|
||||
"uri": "http://dx.doi.org/10.13039/100011096",
|
||||
|
@ -217,6 +223,12 @@
|
|||
"name": "Global Brain Health Institute",
|
||||
"synonym": []
|
||||
},
|
||||
{
|
||||
"id": "100015776",
|
||||
"uri": "http://dx.doi.org/10.13039/100015776",
|
||||
"name": "Health and Social Care Board",
|
||||
"synonym": []
|
||||
},
|
||||
{
|
||||
"id": "100015992",
|
||||
"uri": "http://dx.doi.org/10.13039/100015992",
|
||||
|
@ -391,6 +403,18 @@
|
|||
"name": "Irish Hospice Foundation",
|
||||
"synonym": []
|
||||
},
|
||||
{
|
||||
"id": "501100001596",
|
||||
"uri": "http://dx.doi.org/10.13039/501100001596",
|
||||
"name": "Irish Research Council for Science, Engineering and Technology",
|
||||
"synonym": []
|
||||
},
|
||||
{
|
||||
"id": "501100001597",
|
||||
"uri": "http://dx.doi.org/10.13039/501100001597",
|
||||
"name": "Irish Research Council for the Humanities and Social Sciences",
|
||||
"synonym": []
|
||||
},
|
||||
{
|
||||
"id": "501100001598",
|
||||
"uri": "http://dx.doi.org/10.13039/501100001598",
|
||||
|
@ -491,7 +515,7 @@
|
|||
"id": "501100002081",
|
||||
"uri": "http://dx.doi.org/10.13039/501100002081",
|
||||
"name": "Irish Research Council",
|
||||
"synonym": ["501100001596", "501100001597"]
|
||||
"synonym": []
|
||||
},
|
||||
{
|
||||
"id": "501100002736",
|
||||
|
|
|
@ -3,17 +3,18 @@ package eu.dnetlib.doiboost
|
|||
import eu.dnetlib.dhp.application.ArgumentApplicationParser
|
||||
import eu.dnetlib.dhp.oa.merge.AuthorMerger
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.MergeUtils
|
||||
import eu.dnetlib.dhp.schema.oaf.{Organization, Publication, Relation, Dataset => OafDataset}
|
||||
import eu.dnetlib.doiboost.mag.ConversionUtil
|
||||
import org.apache.commons.io.IOUtils
|
||||
import org.apache.spark.SparkConf
|
||||
import org.apache.spark.sql.expressions.Aggregator
|
||||
import org.apache.spark.sql.functions.col
|
||||
import org.apache.spark.sql._
|
||||
import org.json4s.DefaultFormats
|
||||
import org.json4s.JsonAST.{JField, JObject, JString}
|
||||
import org.json4s.jackson.JsonMethods.parse
|
||||
import org.slf4j.{Logger, LoggerFactory}
|
||||
|
||||
import scala.collection.JavaConverters._
|
||||
|
||||
object SparkGenerateDoiBoost {
|
||||
|
@ -78,8 +79,10 @@ object SparkGenerateDoiBoost {
|
|||
if (item._2 != null) {
|
||||
val otherPub = item._2._2
|
||||
if (otherPub != null) {
|
||||
crossrefPub.mergeFrom(otherPub)
|
||||
crossrefPub.setAuthor(AuthorMerger.mergeAuthor(crossrefPub.getAuthor, otherPub.getAuthor))
|
||||
val mergedAuthor = AuthorMerger.mergeAuthor(crossrefPub.getAuthor, otherPub.getAuthor)
|
||||
val res = MergeUtils.mergePublication(crossrefPub, otherPub)
|
||||
res.setAuthor(mergedAuthor);
|
||||
return res
|
||||
}
|
||||
}
|
||||
crossrefPub
|
||||
|
@ -130,14 +133,13 @@ object SparkGenerateDoiBoost {
|
|||
// So we have to merge
|
||||
val b1 = left._2
|
||||
val b2 = right._2
|
||||
b1.mergeFrom(b2)
|
||||
b1.mergeOAFDataInfo(b2)
|
||||
val authors = AuthorMerger.mergeAuthor(b1.getAuthor, b2.getAuthor)
|
||||
b1.setAuthor(authors)
|
||||
val merged = MergeUtils.mergePublication(b1, b2);
|
||||
merged.setAuthor(authors)
|
||||
if (b2.getId != null && b2.getId.nonEmpty)
|
||||
b1.setId(b2.getId)
|
||||
merged.setId(b2.getId)
|
||||
//Return publication Merged
|
||||
(b1.getId, b1)
|
||||
(merged.getId, merged)
|
||||
}
|
||||
} else {
|
||||
// Left is Null so we return right
|
||||
|
|
|
@ -587,15 +587,7 @@ case object Crossref2Oaf {
|
|||
"10.13039/501100000266" | "10.13039/501100006041" | "10.13039/501100000265" | "10.13039/501100000270" |
|
||||
"10.13039/501100013589" | "10.13039/501100000271" =>
|
||||
generateSimpleRelationFromAward(funder, "ukri________", a => a)
|
||||
//HFRI
|
||||
case "10.13039/501100013209" =>
|
||||
generateSimpleRelationFromAward(funder, "hfri________", a => a)
|
||||
val targetId = getProjectId("hfri________", "1e5e62235d094afd01cd56e65112fc63")
|
||||
queue += generateRelation(sourceId, targetId, ModelConstants.IS_PRODUCED_BY)
|
||||
queue += generateRelation(targetId, sourceId, ModelConstants.PRODUCES)
|
||||
//ERASMUS+
|
||||
case "10.13039/501100010790" =>
|
||||
generateSimpleRelationFromAward(funder, "erasmusplus_", a => a)
|
||||
|
||||
case _ => logger.debug("no match for " + funder.DOI.get)
|
||||
|
||||
}
|
||||
|
|
|
@ -1,8 +1,8 @@
|
|||
package eu.dnetlib.doiboost.mag
|
||||
|
||||
import eu.dnetlib.dhp.schema.common.ModelConstants
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory
|
||||
import eu.dnetlib.dhp.schema.oaf.{Instance, Journal, Publication, StructuredProperty, Subject}
|
||||
import eu.dnetlib.dhp.schema.oaf.utils.{IdentifierFactory, MergeUtils}
|
||||
import eu.dnetlib.dhp.schema.oaf.{Instance, Journal, Publication, Subject}
|
||||
import eu.dnetlib.doiboost.DoiBoostMappingUtil
|
||||
import eu.dnetlib.doiboost.DoiBoostMappingUtil._
|
||||
import org.json4s
|
||||
|
@ -142,8 +142,7 @@ case object ConversionUtil {
|
|||
|
||||
def mergePublication(a: Publication, b: Publication): Publication = {
|
||||
if ((a != null) && (b != null)) {
|
||||
a.mergeFrom(b)
|
||||
a
|
||||
MergeUtils.mergePublication(a, b)
|
||||
} else {
|
||||
if (a == null) b else a
|
||||
}
|
||||
|
|
|
@ -23,10 +23,15 @@ class CrossrefMappingTest {
|
|||
val mapper = new ObjectMapper()
|
||||
|
||||
@Test
|
||||
def testMissingAuthorParser():Unit = {
|
||||
val json: String = Source.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/s41567-022-01757-y.json")).mkString
|
||||
def testMissingAuthorParser(): Unit = {
|
||||
val json: String = Source
|
||||
.fromInputStream(getClass.getResourceAsStream("/eu/dnetlib/doiboost/crossref/s41567-022-01757-y.json"))
|
||||
.mkString
|
||||
val result = Crossref2Oaf.convert(json)
|
||||
result.filter(o => o.isInstanceOf[Publication]).map(p=> p.asInstanceOf[Publication]).foreach(p =>assertTrue(p.getAuthor.size()>0))
|
||||
result
|
||||
.filter(o => o.isInstanceOf[Publication])
|
||||
.map(p => p.asInstanceOf[Publication])
|
||||
.foreach(p => assertTrue(p.getAuthor.size() > 0))
|
||||
}
|
||||
|
||||
@Test
|
||||
|
|
|
@ -0,0 +1,39 @@
|
|||
|
||||
package eu.dnetlib.dhp.bulktag.actions;
|
||||
|
||||
import java.io.Serializable;
|
||||
import java.util.List;
|
||||
|
||||
/**
|
||||
* @author miriam.baglioni
|
||||
* @Date 22/01/24
|
||||
*/
|
||||
public class Action implements Serializable {
|
||||
private String clazz;
|
||||
private String method;
|
||||
private List<Parameters> params;
|
||||
|
||||
public String getClazz() {
|
||||
return clazz;
|
||||
}
|
||||
|
||||
public void setClazz(String clazz) {
|
||||
this.clazz = clazz;
|
||||
}
|
||||
|
||||
public String getMethod() {
|
||||
return method;
|
||||
}
|
||||
|
||||
public void setMethod(String method) {
|
||||
this.method = method;
|
||||
}
|
||||
|
||||
public List<Parameters> getParams() {
|
||||
return params;
|
||||
}
|
||||
|
||||
public void setParams(List<Parameters> params) {
|
||||
this.params = params;
|
||||
}
|
||||
}
|
|
@ -0,0 +1,45 @@
|
|||
|
||||
package eu.dnetlib.dhp.bulktag.actions;
|
||||
|
||||
import java.io.Serializable;
|
||||
|
||||
/**
|
||||
* @author miriam.baglioni
|
||||
* @Date 19/01/24
|
||||
*/
|
||||
public class ExecSubstringAction implements Serializable {
|
||||
|
||||
private String value;
|
||||
private String from;
|
||||
private String to;
|
||||
|
||||
public String getValue() {
|
||||
return value;
|
||||
}
|
||||
|
||||
public void setValue(String value) {
|
||||
this.value = value;
|
||||
}
|
||||
|
||||
public String getFrom() {
|
||||
return from;
|
||||
}
|
||||
|
||||
public void setFrom(String from) {
|
||||
this.from = from;
|
||||
}
|
||||
|
||||
public String getTo() {
|
||||
return to;
|
||||
}
|
||||
|
||||
public void setTo(String to) {
|
||||
this.to = to;
|
||||
}
|
||||
|
||||
public String execSubstring() {
|
||||
|
||||
return this.value.substring(Integer.valueOf(this.from), Integer.valueOf(this.to));
|
||||
|
||||
}
|
||||
}
|
Some files were not shown because too many files have changed in this diff Show More
Loading…
Reference in New Issue