diff --git a/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/SparkDownloadOrcidAuthors.java b/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/SparkDownloadOrcidAuthors.java index 2b8e42bf6..c549beb03 100644 --- a/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/SparkDownloadOrcidAuthors.java +++ b/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/SparkDownloadOrcidAuthors.java @@ -12,10 +12,6 @@ import org.apache.commons.io.IOUtils; import org.apache.commons.lang3.StringUtils; import org.apache.hadoop.io.Text; import org.apache.hadoop.mapreduce.lib.output.SequenceFileOutputFormat; -import org.apache.http.client.methods.CloseableHttpResponse; -import org.apache.http.client.methods.HttpGet; -import org.apache.http.impl.client.CloseableHttpClient; -import org.apache.http.impl.client.HttpClients; import org.apache.spark.SparkConf; import org.apache.spark.api.java.JavaPairRDD; import org.apache.spark.api.java.JavaSparkContext; @@ -25,8 +21,12 @@ import org.slf4j.Logger; import org.slf4j.LoggerFactory; import eu.dnetlib.dhp.application.ArgumentApplicationParser; +import eu.dnetlib.dhp.common.collection.CollectorException; +import eu.dnetlib.dhp.common.collection.HttpClientParams; import eu.dnetlib.doiboost.orcid.model.DownloadedRecordData; +import eu.dnetlib.doiboost.orcid.util.DownloadsReport; import eu.dnetlib.doiboost.orcid.util.HDFSUtil; +import eu.dnetlib.doiboost.orcid.util.MultiAttemptsHttpConnector; import scala.Tuple2; public class SparkDownloadOrcidAuthors { @@ -72,16 +72,12 @@ public class SparkDownloadOrcidAuthors { LongAccumulator parsedRecordsAcc = spark.sparkContext().longAccumulator("parsed_records"); LongAccumulator modifiedRecordsAcc = spark.sparkContext().longAccumulator("to_download_records"); LongAccumulator downloadedRecordsAcc = spark.sparkContext().longAccumulator("downloaded_records"); - LongAccumulator errorHTTP403Acc = spark.sparkContext().longAccumulator("error_HTTP_403"); - LongAccumulator errorHTTP404Acc = spark.sparkContext().longAccumulator("error_HTTP_404"); - LongAccumulator errorHTTP409Acc = spark.sparkContext().longAccumulator("error_HTTP_409"); - LongAccumulator errorHTTP503Acc = spark.sparkContext().longAccumulator("error_HTTP_503"); - LongAccumulator errorHTTP525Acc = spark.sparkContext().longAccumulator("error_HTTP_525"); - LongAccumulator errorHTTPGenericAcc = spark.sparkContext().longAccumulator("error_HTTP_Generic"); + LongAccumulator errorsAcc = spark.sparkContext().longAccumulator("errors"); - logger.info("Retrieving data from lamda sequence file"); + String lambdaFilePath = workingPath + lambdaFileName; + logger.info("Retrieving data from lamda sequence file: " + lambdaFilePath); JavaPairRDD lamdaFileRDD = sc - .sequenceFile(workingPath + lambdaFileName, Text.class, Text.class); + .sequenceFile(lambdaFilePath, Text.class, Text.class); final long lamdaFileRDDCount = lamdaFileRDD.count(); logger.info("Data retrieved: {}", lamdaFileRDDCount); @@ -102,47 +98,44 @@ public class SparkDownloadOrcidAuthors { final DownloadedRecordData downloaded = new DownloadedRecordData(); downloaded.setOrcidId(orcidId); downloaded.setLastModifiedDate(lastModifiedDate); - CloseableHttpClient client = HttpClients.createDefault(); - HttpGet httpGet = new HttpGet("https://api.orcid.org/v3.0/" + orcidId + "/record"); - httpGet.addHeader("Accept", "application/vnd.orcid+xml"); - httpGet.addHeader("Authorization", String.format("Bearer %s", token)); + final HttpClientParams clientParams = new HttpClientParams(); + MultiAttemptsHttpConnector httpConnector = new MultiAttemptsHttpConnector(clientParams); + httpConnector.setAuthMethod(MultiAttemptsHttpConnector.BEARER); + httpConnector.setAcceptHeaderValue("application/vnd.orcid+xml"); + httpConnector.setAuthToken(token); + String apiUrl = "https://api.orcid.org/v3.0/" + orcidId + "/record"; + DownloadsReport report = new DownloadsReport(); long startReq = System.currentTimeMillis(); - CloseableHttpResponse response = client.execute(httpGet); + boolean downloadCompleted = false; + String record = ""; + try { + record = httpConnector.getInputSource(apiUrl, report); + downloadCompleted = true; + } catch (CollectorException ce) { + if (!report.isEmpty()) { + int errCode = report.keySet().stream().findFirst().get(); + report.forEach((k, v) -> { + logger.error(k + " " + v); + }); + downloaded.setStatusCode(errCode); + } else { + downloaded.setStatusCode(-4); + } + errorsAcc.add(1); + } long endReq = System.currentTimeMillis(); long reqTime = endReq - startReq; if (reqTime < 1000) { Thread.sleep(1000 - reqTime); } - int statusCode = response.getStatusLine().getStatusCode(); - downloaded.setStatusCode(statusCode); - if (statusCode != 200) { - switch (statusCode) { - case 403: - errorHTTP403Acc.add(1); - break; - case 404: - errorHTTP404Acc.add(1); - break; - case 409: - errorHTTP409Acc.add(1); - break; - case 503: - errorHTTP503Acc.add(1); - break; - case 525: - errorHTTP525Acc.add(1); - break; - default: - errorHTTPGenericAcc.add(1); - } - return downloaded.toTuple2(); + if (downloadCompleted) { + downloaded.setStatusCode(200); + downloadedRecordsAcc.add(1); + downloaded + .setCompressedData( + ArgumentApplicationParser + .compressArgument(record)); } - downloadedRecordsAcc.add(1); - downloaded - .setCompressedData( - ArgumentApplicationParser - .compressArgument(IOUtils.toString(response.getEntity().getContent()))); - client.close(); return downloaded.toTuple2(); }; @@ -153,26 +146,17 @@ public class SparkDownloadOrcidAuthors { long authorsModifiedCount = authorsModifiedRDD.count(); logger.info("Authors modified count: {}", authorsModifiedCount); - logger.info("Start downloading ..."); - final JavaPairRDD pairRDD = authorsModifiedRDD .repartition(100) .map(downloadRecordFn) .mapToPair(t -> new Tuple2<>(new Text(t._1()), new Text(t._2()))); - saveAsSequenceFile(workingPath, outputPath, sc, pairRDD); logger.info("parsedRecordsAcc: {}", parsedRecordsAcc.value()); logger.info("modifiedRecordsAcc: {}", modifiedRecordsAcc.value()); logger.info("downloadedRecordsAcc: {}", downloadedRecordsAcc.value()); - logger.info("errorHTTP403Acc: {}", errorHTTP403Acc.value()); - logger.info("errorHTTP404Acc: {}", errorHTTP404Acc.value()); - logger.info("errorHTTP409Acc: {}", errorHTTP409Acc.value()); - logger.info("errorHTTP503Acc: {}", errorHTTP503Acc.value()); - logger.info("errorHTTP525Acc: {}", errorHTTP525Acc.value()); - logger.info("errorHTTPGenericAcc: {}", errorHTTPGenericAcc.value()); + logger.info("errorsAcc: {}", errorsAcc.value()); }); - } private static void saveAsSequenceFile(String workingPath, String outputPath, JavaSparkContext sc, diff --git a/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/SparkDownloadOrcidWorks.java b/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/SparkDownloadOrcidWorks.java index cab538783..0569bacfd 100644 --- a/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/SparkDownloadOrcidWorks.java +++ b/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/SparkDownloadOrcidWorks.java @@ -11,10 +11,6 @@ import org.apache.commons.io.IOUtils; import org.apache.commons.lang3.StringUtils; import org.apache.hadoop.io.Text; import org.apache.hadoop.io.compress.GzipCodec; -import org.apache.http.client.methods.CloseableHttpResponse; -import org.apache.http.client.methods.HttpGet; -import org.apache.http.impl.client.CloseableHttpClient; -import org.apache.http.impl.client.HttpClients; import org.apache.spark.SparkConf; import org.apache.spark.api.java.JavaPairRDD; import org.apache.spark.api.java.JavaSparkContext; @@ -28,8 +24,12 @@ import com.google.gson.JsonElement; import com.google.gson.JsonParser; import eu.dnetlib.dhp.application.ArgumentApplicationParser; +import eu.dnetlib.dhp.common.collection.CollectorException; +import eu.dnetlib.dhp.common.collection.HttpClientParams; import eu.dnetlib.doiboost.orcid.model.DownloadedRecordData; +import eu.dnetlib.doiboost.orcid.util.DownloadsReport; import eu.dnetlib.doiboost.orcid.util.HDFSUtil; +import eu.dnetlib.doiboost.orcid.util.MultiAttemptsHttpConnector; import eu.dnetlib.doiboost.orcid.xml.XMLRecordParser; import scala.Tuple2; @@ -90,12 +90,7 @@ public class SparkDownloadOrcidWorks { .sparkContext() .longAccumulator("error_parsing_xml_found"); LongAccumulator downloadedRecordsAcc = spark.sparkContext().longAccumulator("downloaded_records"); - LongAccumulator errorHTTP403Acc = spark.sparkContext().longAccumulator("error_HTTP_403"); - LongAccumulator errorHTTP404Acc = spark.sparkContext().longAccumulator("error_HTTP_404"); - LongAccumulator errorHTTP409Acc = spark.sparkContext().longAccumulator("error_HTTP_409"); - LongAccumulator errorHTTP503Acc = spark.sparkContext().longAccumulator("error_HTTP_503"); - LongAccumulator errorHTTP525Acc = spark.sparkContext().longAccumulator("error_HTTP_525"); - LongAccumulator errorHTTPGenericAcc = spark.sparkContext().longAccumulator("error_HTTP_Generic"); + LongAccumulator errorsAcc = spark.sparkContext().longAccumulator("errors"); JavaPairRDD updatedAuthorsRDD = sc .sequenceFile(workingPath + "downloads/updated_authors/*", Text.class, Text.class); @@ -149,51 +144,44 @@ public class SparkDownloadOrcidWorks { final DownloadedRecordData downloaded = new DownloadedRecordData(); downloaded.setOrcidId(orcidId); downloaded.setLastModifiedDate(lastUpdateValue); - CloseableHttpClient client = HttpClients.createDefault(); - HttpGet httpGet = new HttpGet("https://api.orcid.org/v3.0/" + relativeWorkUrl); - httpGet.addHeader("Accept", "application/vnd.orcid+xml"); - httpGet.addHeader("Authorization", String.format("Bearer %s", token)); + final HttpClientParams clientParams = new HttpClientParams(); + MultiAttemptsHttpConnector httpConnector = new MultiAttemptsHttpConnector(clientParams); + httpConnector.setAuthMethod(MultiAttemptsHttpConnector.BEARER); + httpConnector.setAcceptHeaderValue("application/vnd.orcid+xml"); + httpConnector.setAuthToken(token); + String apiUrl = "https://api.orcid.org/v3.0/" + relativeWorkUrl; + DownloadsReport report = new DownloadsReport(); long startReq = System.currentTimeMillis(); - CloseableHttpResponse response = client.execute(httpGet); + boolean downloadCompleted = false; + String record = ""; + try { + record = httpConnector.getInputSource(apiUrl, report); + downloadCompleted = true; + } catch (CollectorException ce) { + if (!report.isEmpty()) { + int errCode = report.keySet().stream().findFirst().get(); + report.forEach((k, v) -> { + logger.error(k + " " + v); + }); + downloaded.setStatusCode(errCode); + } else { + downloaded.setStatusCode(-4); + } + errorsAcc.add(1); + } long endReq = System.currentTimeMillis(); long reqTime = endReq - startReq; if (reqTime < 1000) { Thread.sleep(1000 - reqTime); } - int statusCode = response.getStatusLine().getStatusCode(); - downloaded.setStatusCode(statusCode); - if (statusCode != 200) { - switch (statusCode) { - case 403: - errorHTTP403Acc.add(1); - break; - case 404: - errorHTTP404Acc.add(1); - break; - case 409: - errorHTTP409Acc.add(1); - break; - case 503: - errorHTTP503Acc.add(1); - break; - case 525: - errorHTTP525Acc.add(1); - break; - default: - errorHTTPGenericAcc.add(1); - logger - .info( - "Downloading {} status code: {}", orcidId, - response.getStatusLine().getStatusCode()); - } - return downloaded.toTuple2(); + if (downloadCompleted) { + downloaded.setStatusCode(200); + downloadedRecordsAcc.add(1); + downloaded + .setCompressedData( + ArgumentApplicationParser + .compressArgument(record)); } - downloadedRecordsAcc.add(1); - downloaded - .setCompressedData( - ArgumentApplicationParser - .compressArgument(IOUtils.toString(response.getEntity().getContent()))); - client.close(); return downloaded.toTuple2(); }; @@ -214,11 +202,7 @@ public class SparkDownloadOrcidWorks { logger.info("errorLoadingXMLFoundAcc: {}", errorLoadingXMLFoundAcc.value()); logger.info("errorParsingXMLFoundAcc: {}", errorParsingXMLFoundAcc.value()); logger.info("downloadedRecordsAcc: {}", downloadedRecordsAcc.value()); - logger.info("errorHTTP403Acc: {}", errorHTTP403Acc.value()); - logger.info("errorHTTP409Acc: {}", errorHTTP409Acc.value()); - logger.info("errorHTTP503Acc: {}", errorHTTP503Acc.value()); - logger.info("errorHTTP525Acc: {}", errorHTTP525Acc.value()); - logger.info("errorHTTPGenericAcc: {}", errorHTTPGenericAcc.value()); + logger.info("errorsAcc: {}", errorsAcc.value()); }); } diff --git a/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/util/DownloadsReport.java b/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/util/DownloadsReport.java new file mode 100644 index 000000000..b06b0af90 --- /dev/null +++ b/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/util/DownloadsReport.java @@ -0,0 +1,10 @@ + +package eu.dnetlib.doiboost.orcid.util; + +import java.util.LinkedHashMap; + +public class DownloadsReport extends LinkedHashMap { + + public DownloadsReport() { + } +} diff --git a/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/util/MultiAttemptsHttpConnector.java b/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/util/MultiAttemptsHttpConnector.java new file mode 100644 index 000000000..5ef6efa26 --- /dev/null +++ b/dhp-workflows/dhp-doiboost/src/main/java/eu/dnetlib/doiboost/orcid/util/MultiAttemptsHttpConnector.java @@ -0,0 +1,272 @@ + +package eu.dnetlib.doiboost.orcid.util; + +import static eu.dnetlib.dhp.utils.DHPUtils.MAPPER; + +import java.io.IOException; +import java.io.InputStream; +import java.net.*; +import java.util.List; +import java.util.Map; + +import org.apache.commons.io.IOUtils; +import org.apache.commons.lang3.math.NumberUtils; +import org.apache.http.HttpHeaders; +import org.slf4j.Logger; +import org.slf4j.LoggerFactory; + +import eu.dnetlib.dhp.common.collection.CollectorException; +import eu.dnetlib.dhp.common.collection.HttpClientParams; + +/** + * Derived from eu.dnetlib.dhp.common.collection.HttpConnector2 with custom report and Bearer auth + * + * @author enrico + */ +public class MultiAttemptsHttpConnector { + + private static final Logger log = LoggerFactory.getLogger(MultiAttemptsHttpConnector.class); + + private HttpClientParams clientParams; + + private String responseType = null; + + private static final String userAgent = "Mozilla/5.0 (compatible; OAI; +http://www.openaire.eu)"; + + private String authToken = ""; + private String acceptHeaderValue = ""; + private String authMethod = ""; + public final static String BEARER = "BEARER"; + + public MultiAttemptsHttpConnector() { + this(new HttpClientParams()); + } + + public MultiAttemptsHttpConnector(HttpClientParams clientParams) { + this.clientParams = clientParams; + CookieHandler.setDefault(new CookieManager(null, CookiePolicy.ACCEPT_ALL)); + } + + /** + * Given the URL returns the content via HTTP GET + * + * @param requestUrl the URL + * @param report the list of errors + * @return the content of the downloaded resource + * @throws CollectorException when retrying more than maxNumberOfRetry times + */ + public String getInputSource(final String requestUrl, DownloadsReport report) + throws CollectorException { + return attemptDownloadAsString(requestUrl, 1, report); + } + + private String attemptDownloadAsString(final String requestUrl, final int retryNumber, + final DownloadsReport report) throws CollectorException { + + try (InputStream s = attemptDownload(requestUrl, retryNumber, report)) { + return IOUtils.toString(s); + } catch (IOException e) { + log.error(e.getMessage(), e); + throw new CollectorException(e); + } + } + + private InputStream attemptDownload(final String requestUrl, final int retryNumber, + final DownloadsReport report) throws CollectorException, IOException { + + if (retryNumber > getClientParams().getMaxNumberOfRetry()) { + final String msg = String + .format( + "Max number of retries (%s/%s) exceeded, failing.", + retryNumber, getClientParams().getMaxNumberOfRetry()); + log.error(msg); + throw new CollectorException(msg); + } + + log.info("Request attempt {} [{}]", retryNumber, requestUrl); + + InputStream input = null; + + try { + if (getClientParams().getRequestDelay() > 0) { + backoffAndSleep(getClientParams().getRequestDelay()); + } + final HttpURLConnection urlConn = (HttpURLConnection) new URL(requestUrl).openConnection(); + urlConn.setInstanceFollowRedirects(false); + urlConn.setReadTimeout(getClientParams().getReadTimeOut() * 1000); + urlConn.setConnectTimeout(getClientParams().getConnectTimeOut() * 1000); + urlConn.addRequestProperty(HttpHeaders.USER_AGENT, userAgent); + + if (!getAcceptHeaderValue().isEmpty()) { + urlConn.addRequestProperty(HttpHeaders.ACCEPT, getAcceptHeaderValue()); + } + if (!getAuthToken().isEmpty() && getAuthMethod().equals(BEARER)) { + urlConn.addRequestProperty(HttpHeaders.AUTHORIZATION, String.format("Bearer %s", getAuthToken())); + } + + if (log.isDebugEnabled()) { + logHeaderFields(urlConn); + } + + int retryAfter = obtainRetryAfter(urlConn.getHeaderFields()); + if (is2xx(urlConn.getResponseCode())) { + input = urlConn.getInputStream(); + responseType = urlConn.getContentType(); + return input; + } + if (is3xx(urlConn.getResponseCode())) { + // REDIRECTS + final String newUrl = obtainNewLocation(urlConn.getHeaderFields()); + log.info("The requested url has been moved to {}", newUrl); + report + .put( + urlConn.getResponseCode(), + String.format("Moved to: %s", newUrl)); + urlConn.disconnect(); + if (retryAfter > 0) { + backoffAndSleep(retryAfter); + } + return attemptDownload(newUrl, retryNumber + 1, report); + } + if (is4xx(urlConn.getResponseCode()) || is5xx(urlConn.getResponseCode())) { + switch (urlConn.getResponseCode()) { + case HttpURLConnection.HTTP_NOT_FOUND: + case HttpURLConnection.HTTP_BAD_GATEWAY: + case HttpURLConnection.HTTP_UNAVAILABLE: + case HttpURLConnection.HTTP_GATEWAY_TIMEOUT: + if (retryAfter > 0) { + log + .warn( + "{} - waiting and repeating request after suggested retry-after {} sec.", + requestUrl, retryAfter); + backoffAndSleep(retryAfter * 1000); + } else { + log + .warn( + "{} - waiting and repeating request after default delay of {} sec.", + requestUrl, getClientParams().getRetryDelay()); + backoffAndSleep(retryNumber * getClientParams().getRetryDelay() * 1000); + } + report.put(urlConn.getResponseCode(), requestUrl); + urlConn.disconnect(); + return attemptDownload(requestUrl, retryNumber + 1, report); + default: + report + .put( + urlConn.getResponseCode(), + String + .format( + "%s Error: %s", requestUrl, urlConn.getResponseMessage())); + throw new CollectorException(urlConn.getResponseCode() + " error " + report); + } + } + throw new CollectorException( + String + .format( + "Unexpected status code: %s errors: %s", urlConn.getResponseCode(), + MAPPER.writeValueAsString(report))); + } catch (MalformedURLException | UnknownHostException e) { + log.error(e.getMessage(), e); + report.put(-2, e.getMessage()); + throw new CollectorException(e.getMessage(), e); + } catch (SocketTimeoutException | SocketException e) { + log.error(e.getMessage(), e); + report.put(-3, e.getMessage()); + backoffAndSleep(getClientParams().getRetryDelay() * retryNumber * 1000); + return attemptDownload(requestUrl, retryNumber + 1, report); + } + } + + private void logHeaderFields(final HttpURLConnection urlConn) throws IOException { + log.debug("StatusCode: {}", urlConn.getResponseMessage()); + + for (Map.Entry> e : urlConn.getHeaderFields().entrySet()) { + if (e.getKey() != null) { + for (String v : e.getValue()) { + log.debug(" key: {} - value: {}", e.getKey(), v); + } + } + } + } + + private void backoffAndSleep(int sleepTimeMs) throws CollectorException { + log.info("I'm going to sleep for {}ms", sleepTimeMs); + try { + Thread.sleep(sleepTimeMs); + } catch (InterruptedException e) { + log.error(e.getMessage(), e); + throw new CollectorException(e); + } + } + + private int obtainRetryAfter(final Map> headerMap) { + for (String key : headerMap.keySet()) { + if ((key != null) && key.equalsIgnoreCase(HttpHeaders.RETRY_AFTER) && (!headerMap.get(key).isEmpty()) + && NumberUtils.isCreatable(headerMap.get(key).get(0))) { + return Integer.parseInt(headerMap.get(key).get(0)) + 10; + } + } + return -1; + } + + private String obtainNewLocation(final Map> headerMap) throws CollectorException { + for (String key : headerMap.keySet()) { + if ((key != null) && key.equalsIgnoreCase(HttpHeaders.LOCATION) && (headerMap.get(key).size() > 0)) { + return headerMap.get(key).get(0); + } + } + throw new CollectorException("The requested url has been MOVED, but 'location' param is MISSING"); + } + + private boolean is2xx(final int statusCode) { + return statusCode >= 200 && statusCode <= 299; + } + + private boolean is4xx(final int statusCode) { + return statusCode >= 400 && statusCode <= 499; + } + + private boolean is3xx(final int statusCode) { + return statusCode >= 300 && statusCode <= 399; + } + + private boolean is5xx(final int statusCode) { + return statusCode >= 500 && statusCode <= 599; + } + + public String getResponseType() { + return responseType; + } + + public HttpClientParams getClientParams() { + return clientParams; + } + + public void setClientParams(HttpClientParams clientParams) { + this.clientParams = clientParams; + } + + public void setAuthToken(String authToken) { + this.authToken = authToken; + } + + private String getAuthToken() { + return authToken; + } + + public String getAcceptHeaderValue() { + return acceptHeaderValue; + } + + public void setAcceptHeaderValue(String acceptHeaderValue) { + this.acceptHeaderValue = acceptHeaderValue; + } + + public String getAuthMethod() { + return authMethod; + } + + public void setAuthMethod(String authMethod) { + this.authMethod = authMethod; + } +} diff --git a/dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/doiboost/orcid/OrcidClientTest.java b/dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/doiboost/orcid/OrcidClientTest.java index 9ea7c6959..d4079058e 100644 --- a/dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/doiboost/orcid/OrcidClientTest.java +++ b/dhp-workflows/dhp-doiboost/src/test/java/eu/dnetlib/doiboost/orcid/OrcidClientTest.java @@ -1,13 +1,11 @@ package eu.dnetlib.doiboost.orcid; -import static org.junit.jupiter.api.Assertions.assertEquals; -import static org.junit.jupiter.api.Assertions.assertTrue; +import static org.junit.jupiter.api.Assertions.*; import java.io.*; import java.nio.file.Files; import java.nio.file.Path; -import java.nio.file.Paths; import java.nio.file.StandardOpenOption; import java.text.ParseException; import java.text.SimpleDateFormat; @@ -17,7 +15,6 @@ 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.compress.utils.Lists; -import org.apache.commons.io.FileUtils; import org.apache.commons.io.IOUtils; import org.apache.http.client.methods.CloseableHttpResponse; import org.apache.http.client.methods.HttpGet; @@ -28,8 +25,11 @@ import org.junit.jupiter.api.Disabled; import org.junit.jupiter.api.Test; import eu.dnetlib.dhp.application.ArgumentApplicationParser; +import eu.dnetlib.dhp.common.collection.CollectorException; +import eu.dnetlib.dhp.common.collection.HttpClientParams; import eu.dnetlib.dhp.schema.orcid.AuthorData; -import eu.dnetlib.doiboost.orcid.xml.XMLRecordParserTest; +import eu.dnetlib.doiboost.orcid.util.DownloadsReport; +import eu.dnetlib.doiboost.orcid.util.MultiAttemptsHttpConnector; import jdk.nashorn.internal.ir.annotations.Ignore; public class OrcidClientTest { @@ -49,7 +49,7 @@ public class OrcidClientTest { @BeforeAll private static void setUp() throws IOException { - testPath = Files.createTempDirectory(XMLRecordParserTest.class.getName()); + testPath = Files.createTempDirectory(OrcidClientTest.class.getName()); System.out.println("using test path: " + testPath); } @@ -349,4 +349,84 @@ public class OrcidClientTest { final String work = ArgumentApplicationParser.decompressValue(base64CompressedWork); logToFile(testPath, "\n\nwork updated \n\n" + work); } + + @Test + void downloadUnknownHostExceptionTest() throws Exception { + logToFile(testPath, "downloadUnknownHostExceptionTest"); + final String orcid = "0000-0001-7291-3210"; + final HttpClientParams clientParams = new HttpClientParams(); + clientParams.setMaxNumberOfRetry(2); + MultiAttemptsHttpConnector httpConnector = new MultiAttemptsHttpConnector(clientParams); + httpConnector.setAuthMethod(MultiAttemptsHttpConnector.BEARER); + httpConnector.setAcceptHeaderValue("application/vnd.orcid+xml"); + httpConnector.setAuthToken("78fdb232-7105-4086-8570-e153f4198e3d"); + String wrongApiUrl = "https://api.orcid_UNKNOWN.org/v3.0/" + orcid + "/" + REQUEST_TYPE_RECORD; + String url = "UNKNOWN"; + DownloadsReport report = new DownloadsReport(); + try { + httpConnector.getInputSource(wrongApiUrl, report); + } catch (CollectorException ce) { + logToFile(testPath, "CollectorException downloading: " + ce.getMessage()); + } catch (Throwable t) { + logToFile(testPath, "Throwable downloading: " + t.getMessage()); + } + } + + @Test + void downloadAttemptSuccessTest() throws Exception { + logToFile(testPath, "downloadAttemptSuccessTest"); + final String orcid = "0000-0001-7291-3210"; + final HttpClientParams clientParams = new HttpClientParams(); + clientParams.setMaxNumberOfRetry(2); + MultiAttemptsHttpConnector httpConnector = new MultiAttemptsHttpConnector(clientParams); + httpConnector.setAuthMethod(MultiAttemptsHttpConnector.BEARER); + httpConnector.setAcceptHeaderValue("application/vnd.orcid+xml"); + httpConnector.setAuthToken("78fdb232-7105-4086-8570-e153f4198e3d"); + String apiUrl = "https://api.orcid.org/v3.0/" + orcid + "/" + REQUEST_TYPE_RECORD; + String url = "UNKNOWN"; + DownloadsReport report = new DownloadsReport(); + String record = httpConnector.getInputSource(apiUrl, report); + logToFile(testPath, "Downloaded at first attempt record: " + record); + } + + @Test + void downloadAttemptNotFoundTest() throws Exception { + logToFile(testPath, "downloadAttemptNotFoundTest"); + final HttpClientParams clientParams = new HttpClientParams(); + clientParams.setMaxNumberOfRetry(2); + MultiAttemptsHttpConnector httpConnector = new MultiAttemptsHttpConnector(clientParams); + httpConnector.setAuthMethod(MultiAttemptsHttpConnector.BEARER); + httpConnector.setAcceptHeaderValue("application/vnd.orcid+xml"); + httpConnector.setAuthToken("78fdb232-7105-4086-8570-e153f4198e3d"); + String apiUrl = "https://api.orcid.org/v3.0/NOTFOUND/" + REQUEST_TYPE_RECORD; + DownloadsReport report = new DownloadsReport(); + try { + httpConnector.getInputSource(apiUrl, report); + } catch (CollectorException ce) { + + } + report.forEach((k, v) -> { + try { + logToFile(testPath, k + " " + v); + } catch (IOException e) { + e.printStackTrace(); + } + }); + } + + @Test + @Ignore + void testDownloadedAuthor() throws Exception { + final String base64CompressedWork = "H4sIAAAAAAAAAI2Yy26jMBSG932KiD0hIe1MiwiVZjGLkWbX2XRHsFOsgs3YJmnefszFFy4+mUhtVPz9P/gcH/vQ9PWrrjYXzAVh9Bjst7tgg2nBEKEfx+DP28/wOdgImVOUV4ziY3DDInjNHlKOC8ZRMnxtmlyWxyDaqU+ofg7h/uX7IYwfn+Ngo25ARUKoxJzm1TEopWySKLper1vGC4LU74+IikgTWoFRW+SyfyyfxCBag4iQhBawyoGMDjdqJrnECJAZRquYLDEPaV5jv8oyWlXj+qTiXZLGr7KMiQbnjAOR6IY1W7C6hgIwjGt6SKGfHsY13ajHYipLIcIyJ5Xw6+akdvjEtyt4wxEwM6+VGph5N2zYr2ENhQRhKsmZYChmS1j7nFs6VIBPOwImKhyfMVeFg6GAWEjrcoQ4FoBmBGwVXYhagGHDBIEX+ZzUDiqyn35VN6rJUpUJ4zc/PAI2T03FbrUKJZQszWjV3zavVOjvVfoE01qB+YUUQPGNwHTt3luxJjdqh1AxJFBKLWOrSeCcF13RtxxYtlPOPqH6m+MLwVfoMQ2kdae2ArLajc6fTxkI1nIoegs0yB426pMO+0fSw07xDKMu0XKSde5C2VvrlVMijRzFwqY7XTJI1QMLWcmEzMxtDdxfHiYSgTNJnYJ1K9y5k0tUrMgrnGGaRiuXxxuClulYUbr0nBvpkYLjvgTCGsuSoex3f1CEvRPHKI184NJKtKeaiO7cD5E61bJ4F+9DFd7d01u8Tw6H5BBvvz8f3q3nXLGIeJULGdaqeVBBRK7rS7h/fNvvk/gpedxt4923dxP7Fc3KtKuc1BhlkrfYmeN4dcmrhmbw60+HmWw2CKgbTuqc32CXKTTmeTWT6bDBjPsQ0DTpnchdaYO0ayQ2FyLIiVREqs25aU8VKYLRbK0BsyZuqvr1MU2Sm/rDdhe/2CRN6FU/b+oBVyj1zqRtC5F8kAumfTclsl+s7EoNQu64nfOaVLeezX60Z3XCULLi6GI2IZGTEeey7fec9lBAuXawIHKcpifE7GABHWfoxLVfpUNPBXoMbZWrHFsR3bPAk9J9i2sw9nW6AQT1mpk++7JhW+v44Hmt8PomJqfD13jRnvFOSxCKtu6qHoyBbQ7cMFo750UEfGaXm6bEeplXIXj2hvL6mA7tzvIwmM9pbJFBG834POZdLGi2gH2u9u0K9HMwn5PTioFWLufzmrS4oNuU9Pkt2rf/2jMs7fMdm2rQTTM+j+49AzToAVuXYA1mD2k0+XdE9vAP+JYR5NcQAAA="; + final String work = ArgumentApplicationParser.decompressValue(base64CompressedWork); + logToFile(testPath, "\n\ndownloaded author \n\n" + work); + } + + @Test + @Ignore + void testDownloadedWork() throws Exception { + final String base64CompressedWork = "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"; + final String work = ArgumentApplicationParser.decompressValue(base64CompressedWork); + logToFile(testPath, "\n\ndownloaded work \n\n" + work); + } } diff --git a/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/IndexRecordTransformerTest.java b/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/IndexRecordTransformerTest.java index cd07cfcb1..8daf318be 100644 --- a/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/IndexRecordTransformerTest.java +++ b/dhp-workflows/dhp-graph-provision/src/test/java/eu/dnetlib/dhp/oa/provision/IndexRecordTransformerTest.java @@ -76,6 +76,18 @@ public class IndexRecordTransformerTest { testRecordTransformation(record); } + @Test + public void testForEOSCFutureDataTransferPilot() throws IOException, TransformerException { + final String record = IOUtils.toString(getClass().getResourceAsStream("eosc-future/data-transfer-pilot.xml")); + testRecordTransformation(record); + } + + @Test + public void testForEOSCFutureTraining() throws IOException, TransformerException { + final String record = IOUtils.toString(getClass().getResourceAsStream("eosc-future/training-notebooks-seadatanet.xml")); + testRecordTransformation(record); + } + private void testRecordTransformation(final String record) throws IOException, TransformerException { final String fields = IOUtils.toString(getClass().getResourceAsStream("fields.xml")); final String xslt = IOUtils.toString(getClass().getResourceAsStream("layoutToRecordTransformer.xsl")); diff --git a/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/eosc-future/data-transfer-pilot.xml b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/eosc-future/data-transfer-pilot.xml new file mode 100644 index 000000000..23dd6c6ed --- /dev/null +++ b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/eosc-future/data-transfer-pilot.xml @@ -0,0 +1,72 @@ + + +
+ r37b0ad08687::dec0d8520e726f2adda9a51280ac7299 + 2021-09-22T08:53:16Z + under curation + +
+ + + + EGI-Foundation/data-transfer-pilot: Include libraries in environment.yml + Giuseppe La Rocca + Enol Fernández + Andrea Manzi + + + + This notebook is used to demonstrate how a scientist from one of the PaNOSC RIs can use the resources provided by EGI to perform analysis on the data sets obtained during an expirement. + + EOSC Jupyter Notebook + + Zenodo + + + + + + + + + + + + + + + + + + + oai:zenodo.org:4218562 + + oai:zenodo.org:4218562 + 10.5281/zenodo.4218562 + + + false + false + 0.9 + + + + + + + + + + + + + https://zenodo.org/record/4218562 + + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/eosc-future/training-notebooks-seadatanet.xml b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/eosc-future/training-notebooks-seadatanet.xml new file mode 100644 index 000000000..9995b902f --- /dev/null +++ b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/eosc-future/training-notebooks-seadatanet.xml @@ -0,0 +1,71 @@ + + +
+ r37b0ad08687::eb430fb7438e1533ba95d6aa50a477eb + 2021-09-22T08:53:13Z + under curation + +
+ + + + + EGI-Foundation/training-notebooks-seadatanet: Version 0.4 + Enol Fernández + + + + A sample notebook using SeaDataNet data to plot a map that shows surface temperature of Black Sea, Arctic Sea and Baltic Sea. The data is available at EGI DataHub with PID http://hdl.handle.net/21.T15999/qVk6JWQ (run at EGI Notebooks service for easy access to data).This release updates the PID for the data. + + EOSC Jupyter Notebook + + Zenodo + + + + + + + + + + + + + + + + + + + oai:zenodo.org:3561323 + + oai:zenodo.org:3561323 + 10.5281/zenodo.3561323 + + + false + false + 0.9 + + + + + + + + + + + + + https://zenodo.org/record/3561323 + + + + + + + + \ No newline at end of file diff --git a/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/fields.xml b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/fields.xml index c47975c9d..910a366f6 100644 --- a/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/fields.xml +++ b/dhp-workflows/dhp-graph-provision/src/test/resources/eu/dnetlib/dhp/oa/provision/fields.xml @@ -15,7 +15,13 @@ - + + + + + + + @@ -28,7 +34,8 @@ - + + @@ -79,6 +86,7 @@ + @@ -105,7 +113,7 @@ - + @@ -130,7 +138,7 @@ - + diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh index 6c5823b0c..6d42ab13d 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh @@ -16,7 +16,7 @@ curl -L ${CONTEXT_API}/contexts/?type=ri,community -H "accept: application/json" cat contexts.csv | cut -d , -f1 | xargs -I {} curl -L ${CONTEXT_API}/context/{}/?all=true | /usr/local/sbin/jq -r '.[]|"\(.id|split(":")[0]),\(.id),\(.label)"' > categories.csv cat categories.csv | cut -d , -f2 | sed 's/:/%3A/g'| xargs -I {} curl -L ${CONTEXT_API}/context/category/{}/?all=true | /usr/local/sbin/jq -r '.[]|"\(.id|split("::")[0])::\(.id|split("::")[1]),\(.id),\(.label)"' > concepts.csv cat contexts.csv | sed 's/^\(.*\),\(.*\)/\1,\1::other,\2/' >> categories.csv -cat categories.csv | grep -v ::other | sed 's/^.*,\(.*\),\(.*\)/\1,\1::other,\2/' >> concepts.csv +cat categories.csv | sed 's/^.*,\(.*\),\(.*\)/\1,\1::other,\2/' >> concepts.csv echo "uploading context data to hdfs" hdfs dfs -mkdir ${TMP} diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/indicators.sh b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/indicators.sh index fb944f4ff..93faa43d6 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/indicators.sh +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/indicators.sh @@ -15,5 +15,5 @@ hdfs dfs -copyToLocal $SCRIPT_PATH echo "Creating indicators" impala-shell -q "invalidate metadata" impala-shell -d ${TARGET} -q "show tables" --delimited | sed "s/^\(.*\)/compute stats ${TARGET}.\1;/" | impala-shell -c -f - -cat step16_7-createIndicatorsTables.sql | impala-shell -d $TARGET -f - +cat step16-createIndicatorsTables.sql | impala-shell -d $TARGET -f - echo "Indicators created" \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/observatory.sh b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/observatory-post.sh similarity index 58% rename from dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/observatory.sh rename to dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/observatory-post.sh index ff03bca03..db8d39af2 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/observatory.sh +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/observatory-post.sh @@ -9,16 +9,9 @@ fi export SOURCE=$1 export TARGET=$2 export SHADOW=$3 -export SCRIPT_PATH=$4 -echo "Getting file from " $4 -hdfs dfs -copyToLocal $4 - -echo "Creating observatory database" -impala-shell -q "drop database if exists ${TARGET} cascade" -impala-shell -q "create database if not exists ${TARGET}" -impala-shell -d ${SOURCE} -q "show tables" --delimited | sed "s/\(.*\)/create view ${TARGET}.\1 as select * from ${SOURCE}.\1;/" | impala-shell -f - -cat step21-createObservatoryDB.sql | sed s/SOURCE/$1/g | sed s/TARGET/$2/g1 | impala-shell -f - +impala-shell -q "invalidate metadata;" +impala-shell -d ${TARGET} -q "show tables" --delimited | sed "s/\(.*\)/compute stats ${TARGET}.\1;/" | impala-shell -f - echo "Impala shell finished" echo "Updating shadow observatory database" diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/observatory-pre.sh b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/observatory-pre.sh new file mode 100644 index 000000000..92543b8b8 --- /dev/null +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/observatory-pre.sh @@ -0,0 +1,16 @@ +export PYTHON_EGG_CACHE=/home/$(whoami)/.python-eggs +export link_folder=/tmp/impala-shell-python-egg-cache-$(whoami) +if ! [ -L $link_folder ] +then + rm -Rf "$link_folder" + ln -sfn ${PYTHON_EGG_CACHE}${link_folder} ${link_folder} +fi + +export SOURCE=$1 +export TARGET=$2 +export SHADOW=$3 + +echo "Creating observatory database" +impala-shell -q "drop database if exists ${TARGET} cascade" +impala-shell -q "create database if not exists ${TARGET}" +impala-shell -d ${SOURCE} -q "show tables" --delimited | sed "s/\(.*\)/create view ${TARGET}.\1 as select * from ${SOURCE}.\1;/" | impala-shell -f - \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql index 77fbd3b18..fc0162a9c 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql @@ -23,6 +23,11 @@ CREATE OR REPLACE VIEW ${stats_db_name}.rndexpediture AS SELECT * FROM ${external_stats_db_name}.rndexpediture; +CREATE OR REPLACE VIEW ${stats_db_name}.licenses_normalized AS +SELECT * +FROM ${external_stats_db_name}.licenses_normalized; + + ------------------------------------------------------------------------------------------------ ------------------------------------------------------------------------------------------------ -- Creation date of the database diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_6.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step15_5.sql similarity index 100% rename from dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_6.sql rename to dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step15_5.sql diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_7-createIndicatorsTables.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16-createIndicatorsTables.sql similarity index 100% rename from dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_7-createIndicatorsTables.sql rename to dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16-createIndicatorsTables.sql diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16.sql deleted file mode 100644 index 481fd9e8c..000000000 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16.sql +++ /dev/null @@ -1,62 +0,0 @@ ----------------------------------------------------- --- Shortcuts for various definitions in stats db --- ----------------------------------------------------- - --- Peer reviewed: --- Results that have been collected from Crossref -create table ${stats_db_name}.result_peerreviewed as -with peer_reviewed as ( - select distinct r.id as id - from ${stats_db_name}.result r - join ${stats_db_name}.result_sources rs on rs.id=r.id - join ${stats_db_name}.datasource d on d.id=rs.datasource - where d.name='Crossref') -select distinct peer_reviewed.id as id, true as peer_reviewed -from peer_reviewed -union all -select distinct r.id as id, false as peer_reviewed -from ${stats_db_name}.result r -left outer join peer_reviewed pr on pr.id=r.id -where pr.id is null; - --- Green OA: --- OA results that are hosted by an Institutional repository and have NOT been harvested from a DOAJ journal. -create table ${stats_db_name}.result_greenoa as -with result_green as ( - select distinct r.id as id - from ${stats_db_name}.result r - join ${stats_db_name}.result_datasources rd on rd.id=r.id - join ${stats_db_name}.datasource d on d.id=rd.datasource - left outer join ( - select rd.id from ${stats_db_name}.result_datasources rd - join ${stats_db_name}.datasource d on rd.datasource=d.id - join ${stats_db_name}.datasource_sources sds on sds.id=d.id - join ${stats_db_name}.datasource sd on sd.id=sds.datasource - where sd.name='DOAJ-ARTICLES' - ) as doaj on doaj.id=r.id - where r.bestlicence in ('Open Access', 'Open Source') and d.type='Institutional Repository' and doaj.id is null) -select distinct result_green.id, true as green -from result_green -union all -select distinct r.id as id, false as green -from ${stats_db_name}.result r -left outer join result_green rg on rg.id=r.id -where rg.id is null; - --- GOLD OA: --- OA results that have been harvested from a DOAJ journal. -create table ${stats_db_name}.result_gold as -with result_gold as ( - select distinct r.id as id - from ${stats_db_name}.result r - join ${stats_db_name}.result_datasources rd on rd.id=r.id - join ${stats_db_name}.datasource d on d.id=rd.datasource - join ${stats_db_name}.datasource_sources sds on sds.id=d.id - join ${stats_db_name}.datasource sd on sd.id=sds.datasource - where r.type='publication' and r.bestlicence='Open Access' and sd.name='DOAJ-Articles') -select distinct result_gold.id, true as gold -from result_gold -union all -select distinct r.id, false as gold -from ${stats_db_name}.result r -where r.id not in (select id from result_gold); \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_1-definitions.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_1-definitions.sql new file mode 100644 index 000000000..6b4d9b1b0 --- /dev/null +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_1-definitions.sql @@ -0,0 +1,22 @@ +---------------------------------------------------- +-- Shortcuts for various definitions in stats db --- +---------------------------------------------------- + +-- Peer reviewed: +create table ${stats_db_name}.result_peerreviewed as +select r.id as id, case when doi.doi_from_crossref=1 and grey.grey_lit=0 then true else false end as peer_reviewed +from ${stats_db_name}.result r +left outer join ${stats_db_name}.indi_pub_doi_from_crossref doi on doi.id=r.id +left outer join ${stats_db_name}.indi_pub_grey_lit grey on grey.id=r.id; + +-- Green OA: +create table ${stats_db_name}.result_greenoa as +select r.id, case when green.green_oa=1 then true else false end as green +from ${stats_db_name}.result r +left outer join ${stats_db_name}.indi_pub_green_oa green on green.id=r.id; + +-- GOLD OA: +create table ${stats_db_name}.result_gold as +select r.id, case when gold.gold_oa=1 then true else false end as gold +from ${stats_db_name}.result r + left outer join ${stats_db_name}.indi_pub_gold_oa gold on gold.id=r.id; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step20-createMonitorDB.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step20-createMonitorDB.sql index 5da028304..9ea50d488 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step20-createMonitorDB.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step20-createMonitorDB.sql @@ -104,25 +104,42 @@ create table TARGET.project_results as select id as result, project as id from T compute stats TARGET.project_results; -- indicators -create table TARGET.indi_pub_green_oa as select * from SOURCE.indi_pub_green_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id); -compute stats TARGET.indi_pub_green_oa; - -create table TARGET.indi_pub_grey_lit as select * from SOURCE.indi_pub_grey_lit orig where exists (select 1 from TARGET.result r where r.id=orig.id); -compute stats TARGET.indi_pub_grey_lit; - -create table TARGET.indi_pub_doi_from_crossref as select * from SOURCE.indi_pub_doi_from_crossref orig where exists (select 1 from TARGET.result r where r.id=orig.id); -compute stats TARGET.indi_pub_doi_from_crossref; - -create table TARGET.indi_pub_gold_oa as select * from SOURCE.indi_pub_gold_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id); -compute stats TARGET.indi_pub_gold_oa; - +create view TARGET.indi_dataset_avg_year_content_oa as select * from SOURCE.indi_dataset_avg_year_content_oa orig; +create view TARGET.indi_dataset_avg_year_context_oa as select * from SOURCE.indi_dataset_avg_year_context_oa orig; create view TARGET.indi_dataset_avg_year_country_oa as select * from SOURCE.indi_dataset_avg_year_country_oa orig; + +create view TARGET.indi_other_avg_year_content_oa as select * from SOURCE.indi_other_avg_year_content_oa orig; +create view TARGET.indi_other_avg_year_context_oa as select * from SOURCE.indi_other_avg_year_context_oa orig; +create view TARGET.indi_other_avg_year_country_oa as select * from SOURCE.indi_other_avg_year_country_oa orig; + create view TARGET.indi_project_datasets_count as select * from SOURCE.indi_project_datasets_count orig; create view TARGET.indi_project_otherresearch_count as select * from SOURCE.indi_project_otherresearch_count orig; create view TARGET.indi_project_pubs_count as select * from SOURCE.indi_project_pubs_count orig; create view TARGET.indi_project_software_count as select * from SOURCE.indi_project_software_count orig; + +create view TARGET.indi_pub_avg_year_content_oa as select * from SOURCE.indi_pub_avg_year_content_oa orig; +create view TARGET.indi_pub_avg_year_context_oa as select * from SOURCE.indi_pub_avg_year_context_oa orig; create view TARGET.indi_pub_avg_year_country_oa as select * from SOURCE.indi_pub_avg_year_country_oa orig; +create table TARGET.indi_pub_green_oa as select * from SOURCE.indi_pub_green_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.indi_pub_green_oa; +create table TARGET.indi_pub_grey_lit as select * from SOURCE.indi_pub_grey_lit orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.indi_pub_grey_lit; +create table TARGET.indi_pub_doi_from_crossref as select * from SOURCE.indi_pub_doi_from_crossref orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.indi_pub_doi_from_crossref; +create table TARGET.indi_pub_gold_oa as select * from SOURCE.indi_pub_gold_oa orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.indi_pub_gold_oa; +create table TARGET.indi_pub_has_abstract as select * from SOURCE.indi_pub_has_abstract orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.indi_pub_has_abstract; +create table TARGET.indi_pub_has_cc_licence as select * from SOURCE.indi_pub_has_cc_licence orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.indi_pub_has_cc_licence; +create table TARGET.indi_pub_has_cc_licence_url as select * from SOURCE.indi_pub_has_cc_licence_url orig where exists (select 1 from TARGET.result r where r.id=orig.id); +compute stats TARGET.indi_pub_has_cc_licence_url; + +create view TARGET.indi_software_avg_year_content_oa as select * from SOURCE.indi_software_avg_year_content_oa orig; +create view TARGET.indi_software_avg_year_context_oa as select * from SOURCE.indi_software_avg_year_context_oa orig; +create view TARGET.indi_software_avg_year_country_oa as select * from SOURCE.indi_software_avg_year_country_oa orig; + --denorm alter table TARGET.result rename to TARGET.res_tmp; diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step21-createObservatoryDB.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step21-createObservatoryDB.sql index 40cdf3f6d..e24370e7d 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step21-createObservatoryDB.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step21-createObservatoryDB.sql @@ -1,259 +1,561 @@ -create table TARGET.result_affiliated_country stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, - r.peer_reviewed, r.type, c.code as ccode, c.name as cname -from SOURCE.result r -join SOURCE.result_organization ro on ro.id=r.id -join SOURCE.organization o on o.id=ro.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, c.code, c.name; +create table ${observatory_db_name}.result_cc_licence stored as parquet as +select r.id, coalesce(rln.count, 0) > 0 as cc_licence +from ${stats_db_name}.result r + left outer join ( + select rl.id, sum(case when lower(rln.normalized) like 'cc-%' then 1 else 0 end) as count + from ${stats_db_name}.result_licenses rl + left outer join ${stats_db_name}.licenses_normalized rln on rl.type=rln.license + group by rl.id +) rln on rln.id=r.id; -create table TARGET.result_affiliated_year stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, r.peer_reviewed, r.type, r.year -from SOURCE.result r -join SOURCE.result_organization ro on ro.id=r.id -join SOURCE.organization o on o.id=ro.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, r.year; +create table ${observatory_db_name}.result_affiliated_country stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + c.code as ccode, c.name as cname +from ${stats_db_name}.result r + join ${stats_db_name}.result_organization ro on ro.id=r.id + join ${stats_db_name}.organization o on o.id=ro.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, c.code, c.name; -create table TARGET.result_affiliated_year_country stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, - r.peer_reviewed, r.type, r.year, c.code as ccode, c.name as cname -from SOURCE.result r -join SOURCE.result_organization ro on ro.id=r.id -join SOURCE.organization o on o.id=ro.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, r.year, c.code, c.name; +create table ${observatory_db_name}.result_affiliated_year stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + r.year +from ${stats_db_name}.result r + join ${stats_db_name}.result_organization ro on ro.id=r.id + join ${stats_db_name}.organization o on o.id=ro.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, r.year; -create table TARGET.result_affiliated_datasource stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, r.peer_reviewed, r.type, d.name as dname -from SOURCE.result r -join SOURCE.result_organization ro on ro.id=r.id -join SOURCE.organization o on o.id=ro.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -left outer join SOURCE.result_datasources rd on rd.id=r.id -left outer join SOURCE.datasource d on d.id=rd.datasource -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, d.name; +create table ${observatory_db_name}.result_affiliated_year_country stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + r.year, c.code as ccode, c.name as cname +from ${stats_db_name}.result r + join ${stats_db_name}.result_organization ro on ro.id=r.id + join ${stats_db_name}.organization o on o.id=ro.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, r.year, c.code, c.name; -create table TARGET.result_affiliated_datasource_country stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, - r.peer_reviewed, r.type, d.name as dname, c.code as ccode, c.name as cname -from SOURCE.result r -join SOURCE.result_organization ro on ro.id=r.id -join SOURCE.organization o on o.id=ro.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -left outer join SOURCE.result_datasources rd on rd.id=r.id -left outer join SOURCE.datasource d on d.id=rd.datasource -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, d.name, c.code, c.name; +create table ${observatory_db_name}.result_affiliated_datasource stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + d.name as dname +from ${stats_db_name}.result r + join ${stats_db_name}.result_organization ro on ro.id=r.id + join ${stats_db_name}.organization o on o.id=ro.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + left outer join ${stats_db_name}.result_datasources rd on rd.id=r.id + left outer join ${stats_db_name}.datasource d on d.id=rd.datasource + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, d.name; -create table TARGET.result_affiliated_organization stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, - r.peer_reviewed, r.type, o.name as oname -from SOURCE.result r -join SOURCE.result_organization ro on ro.id=r.id -join SOURCE.organization o on o.id=ro.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, o.name; +create table ${observatory_db_name}.result_affiliated_datasource_country stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + d.name as dname, c.code as ccode, c.name as cname +from ${stats_db_name}.result r + join ${stats_db_name}.result_organization ro on ro.id=r.id + join ${stats_db_name}.organization o on o.id=ro.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + left outer join ${stats_db_name}.result_datasources rd on rd.id=r.id + left outer join ${stats_db_name}.datasource d on d.id=rd.datasource + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, d.name, c.code, c.name; -create table TARGET.result_affiliated_organization_country stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, - r.peer_reviewed, r.type, o.name as oname, c.code as ccode, c.name as cname -from SOURCE.result r -join SOURCE.result_organization ro on ro.id=r.id -join SOURCE.organization o on o.id=ro.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, o.name, c.code, c.name; +create table ${observatory_db_name}.result_affiliated_organization stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + o.name as oname +from ${stats_db_name}.result r + join ${stats_db_name}.result_organization ro on ro.id=r.id + join ${stats_db_name}.organization o on o.id=ro.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, o.name; -create table TARGET.result_affiliated_funder stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, r.peer_reviewed, r.type, p.funder as pfunder -from SOURCE.result r -join SOURCE.result_organization ro on ro.id=r.id -join SOURCE.organization o on o.id=ro.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -join SOURCE.result_projects rp on rp.id=r.id -join SOURCE.project p on p.id=rp.project -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, p.funder; +create table ${observatory_db_name}.result_affiliated_organization_country stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + o.name as oname, c.code as ccode, c.name as cname +from ${stats_db_name}.result r + join ${stats_db_name}.result_organization ro on ro.id=r.id + join ${stats_db_name}.organization o on o.id=ro.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, o.name, c.code, c.name; -create table TARGET.result_affiliated_funder_country stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, - r.peer_reviewed, r.type, p.funder as pfunder, c.code as ccode, c.name as cname -from SOURCE.result r -join SOURCE.result_organization ro on ro.id=r.id -join SOURCE.organization o on o.id=ro.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -join SOURCE.result_projects rp on rp.id=r.id -join SOURCE.project p on p.id=rp.project -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, p.funder, c.code, c.name; +create table ${observatory_db_name}.result_affiliated_funder stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + p.funder as pfunder +from ${stats_db_name}.result r + join ${stats_db_name}.result_organization ro on ro.id=r.id + join ${stats_db_name}.organization o on o.id=ro.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + join ${stats_db_name}.result_projects rp on rp.id=r.id + join ${stats_db_name}.project p on p.id=rp.project + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, p.funder; -create table TARGET.result_deposited_country stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, - r.peer_reviewed, r.type, c.code as ccode, c.name as cname -from SOURCE.result r -join SOURCE.result_datasources rd on rd.id=r.id -join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') -join SOURCE.datasource_organizations dor on dor.id=d.id -join SOURCE.organization o on o.id=dor.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, c.code, c.name; +create table ${observatory_db_name}.result_affiliated_funder_country stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + p.funder as pfunder, c.code as ccode, c.name as cname +from ${stats_db_name}.result r + join ${stats_db_name}.result_organization ro on ro.id=r.id + join ${stats_db_name}.organization o on o.id=ro.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + join ${stats_db_name}.result_projects rp on rp.id=r.id + join ${stats_db_name}.project p on p.id=rp.project + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, p.funder, c.code, c.name; -create table TARGET.result_deposited_year stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, r.peer_reviewed, r.type, r.year -from SOURCE.result r -join SOURCE.result_datasources rd on rd.id=r.id -join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') -join SOURCE.datasource_organizations dor on dor.id=d.id -join SOURCE.organization o on o.id=dor.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, r.year; +create table ${observatory_db_name}.result_deposited_country stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + c.code as ccode, c.name as cname +from ${stats_db_name}.result r + join ${stats_db_name}.result_datasources rd on rd.id=r.id + join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') + join ${stats_db_name}.datasource_organizations dor on dor.id=d.id + join ${stats_db_name}.organization o on o.id=dor.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, c.code, c.name; -create table TARGET.result_deposited_year_country stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, - r.peer_reviewed, r.type, r.year, c.code as ccode, c.name as cname -from SOURCE.result r -join SOURCE.result_datasources rd on rd.id=r.id -join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') -join SOURCE.datasource_organizations dor on dor.id=d.id -join SOURCE.organization o on o.id=dor.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, r.year, c.code, c.name; +create table ${observatory_db_name}.result_deposited_year stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + r.year +from ${stats_db_name}.result r + join ${stats_db_name}.result_datasources rd on rd.id=r.id + join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') + join ${stats_db_name}.datasource_organizations dor on dor.id=d.id + join ${stats_db_name}.organization o on o.id=dor.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, r.year; -create table TARGET.result_deposited_datasource stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, - r.peer_reviewed, r.type, d.name as dname -from SOURCE.result r -join SOURCE.result_datasources rd on rd.id=r.id -join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') -join SOURCE.datasource_organizations dor on dor.id=d.id -join SOURCE.organization o on o.id=dor.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, d.name; +create table ${observatory_db_name}.result_deposited_year_country stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + r.year, c.code as ccode, c.name as cname +from ${stats_db_name}.result r + join ${stats_db_name}.result_datasources rd on rd.id=r.id + join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') + join ${stats_db_name}.datasource_organizations dor on dor.id=d.id + join ${stats_db_name}.organization o on o.id=dor.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, r.year, c.code, c.name; -create table TARGET.result_deposited_datasource_country stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, - r.peer_reviewed, r.type, d.name as dname, c.code as ccode, c.name as cname -from SOURCE.result r -join SOURCE.result_datasources rd on rd.id=r.id -join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') -join SOURCE.datasource_organizations dor on dor.id=d.id -join SOURCE.organization o on o.id=dor.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, d.name, c.code, c.name; +create table ${observatory_db_name}.result_deposited_datasource stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + d.name as dname +from ${stats_db_name}.result r + join ${stats_db_name}.result_datasources rd on rd.id=r.id + join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') + join ${stats_db_name}.datasource_organizations dor on dor.id=d.id + join ${stats_db_name}.organization o on o.id=dor.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, d.name; -create table TARGET.result_deposited_organization stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, r.peer_reviewed, r.type, o.name as oname -from SOURCE.result r -join SOURCE.result_datasources rd on rd.id=r.id -join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') -join SOURCE.datasource_organizations dor on dor.id=d.id -join SOURCE.organization o on o.id=dor.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, o.name; +create table ${observatory_db_name}.result_deposited_datasource_country stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + d.name as dname, c.code as ccode, c.name as cname +from ${stats_db_name}.result r + join ${stats_db_name}.result_datasources rd on rd.id=r.id + join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') + join ${stats_db_name}.datasource_organizations dor on dor.id=d.id + join ${stats_db_name}.organization o on o.id=dor.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, d.name, c.code, c.name; -create table TARGET.result_deposited_organization_country stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, - r.peer_reviewed, r.type, o.name as oname, c.code as ccode, c.name as cname -from SOURCE.result r -join SOURCE.result_datasources rd on rd.id=r.id -join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') -join SOURCE.datasource_organizations dor on dor.id=d.id -join SOURCE.organization o on o.id=dor.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, o.name, c.code, c.name; +create table ${observatory_db_name}.result_deposited_organization stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + o.name as oname +from ${stats_db_name}.result r + join ${stats_db_name}.result_datasources rd on rd.id=r.id + join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') + join ${stats_db_name}.datasource_organizations dor on dor.id=d.id + join ${stats_db_name}.organization o on o.id=dor.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, o.name; -create table TARGET.result_deposited_funder stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, - r.peer_reviewed, r.type, p.funder as pfunder -from SOURCE.result r -join SOURCE.result_datasources rd on rd.id=r.id -join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') -join SOURCE.datasource_organizations dor on dor.id=d.id -join SOURCE.organization o on o.id=dor.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -join SOURCE.result_projects rp on rp.id=r.id -join SOURCE.project p on p.id=rp.project -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, p.funder; +create table ${observatory_db_name}.result_deposited_organization_country stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + o.name as oname, c.code as ccode, c.name as cname +from ${stats_db_name}.result r + join ${stats_db_name}.result_datasources rd on rd.id=r.id + join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') + join ${stats_db_name}.datasource_organizations dor on dor.id=d.id + join ${stats_db_name}.organization o on o.id=dor.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, o.name, c.code, c.name; -create table TARGET.result_deposited_funder_country stored as parquet as -select count(distinct r.id) as total, r.green, r.gold, case when rl.type is not null then true else false end as licence, - case when pids.pid is not null then true else false end as pid, case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, - r.peer_reviewed, r.type, p.funder as pfunder, c.code as ccode, c.name as cname -from SOURCE.result r -join SOURCE.result_datasources rd on rd.id=r.id -join SOURCE.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') -join SOURCE.datasource_organizations dor on dor.id=d.id -join SOURCE.organization o on o.id=dor.organization -join SOURCE.country c on c.code=o.country and c.continent_name='Europe' -join SOURCE.result_projects rp on rp.id=r.id -join SOURCE.project p on p.id=rp.project -left outer join SOURCE.result_licenses rl on rl.id=r.id -left outer join SOURCE.result_pids pids on pids.id=r.id -group by r.green, r.gold, licence, pid, oa, r.peer_reviewed, r.type, p.funder, c.code, c.name; +create table ${observatory_db_name}.result_deposited_funder stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + p.funder as pfunder +from ${stats_db_name}.result r + join ${stats_db_name}.result_datasources rd on rd.id=r.id + join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') + join ${stats_db_name}.datasource_organizations dor on dor.id=d.id + join ${stats_db_name}.organization o on o.id=dor.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + join ${stats_db_name}.result_projects rp on rp.id=r.id + join ${stats_db_name}.project p on p.id=rp.project + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, p.funder; -compute stats TARGET.result_affiliated_country; -compute stats TARGET.result_affiliated_year; -compute stats TARGET.result_affiliated_year_country; -compute stats TARGET.result_affiliated_datasource; -compute stats TARGET.result_affiliated_datasource_country; -compute stats TARGET.result_affiliated_organization; -compute stats TARGET.result_affiliated_organization_country; -compute stats TARGET.result_affiliated_funder; -compute stats TARGET.result_affiliated_funder_country; -compute stats TARGET.result_deposited_country; -compute stats TARGET.result_deposited_year; -compute stats TARGET.result_deposited_year_country; -compute stats TARGET.result_deposited_datasource; -compute stats TARGET.result_deposited_datasource_country; -compute stats TARGET.result_deposited_organization; -compute stats TARGET.result_deposited_organization_country; -compute stats TARGET.result_deposited_funder; -compute stats TARGET.result_deposited_funder_country; +create table ${observatory_db_name}.result_deposited_funder_country stored as parquet as +select + count(distinct r.id) as total, + r.green, + r.gold, + case when rl.type is not null then true else false end as licence, + case when pids.pid is not null then true else false end as pid, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end as oa, + r.peer_reviewed, + rln.cc_licence, + r.abstract as abstract, + r.authors > 1 as multiple_authors, + rpc.count > 1 as multiple_projects, + rfc.count > 1 as multiple_funders, + r.type, + p.funder as pfunder, c.code as ccode, c.name as cname +from ${stats_db_name}.result r + join ${stats_db_name}.result_datasources rd on rd.id=r.id + join ${stats_db_name}.datasource d on d.id=rd.datasource and d.type in ('Institutional Repository','Data Repository', 'Repository', 'Publication Repository') + join ${stats_db_name}.datasource_organizations dor on dor.id=d.id + join ${stats_db_name}.organization o on o.id=dor.organization + join ${stats_db_name}.country c on c.code=o.country and c.continent_name='Europe' + join ${stats_db_name}.result_projects rp on rp.id=r.id + join ${stats_db_name}.project p on p.id=rp.project + left outer join ${stats_db_name}.result_licenses rl on rl.id=r.id + left outer join ${stats_db_name}.result_pids pids on pids.id=r.id + left outer join ${observatory_db_name}.result_cc_licence rln on rln.id=r.id + left outer join ${stats_db_name}.result_projectcount rpc on rpc.id=r.id + left outer join ${stats_db_name}.result_fundercount rfc on rfc.id=r.id +group by r.green, r.gold, case when rl.type is not null then true else false end, case when pids.pid is not null then true else false end, + case when r.access_mode in ('Open Access', 'Open Source') then true else false end, r.peer_reviewed, r.type, abstract, + cc_licence, r.authors > 1, rpc.count > 1, rfc.count > 1, p.funder, c.code, c.name; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml index a329ca4bf..08d33f4e8 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml @@ -239,14 +239,51 @@ stats_db_name=${stats_db_name} openaire_db_name=${openaire_db_name} - + - + ${hive_jdbc_url} - + + stats_db_name=${stats_db_name} + openaire_db_name=${openaire_db_name} + + + + + + + + ${jobTracker} + ${nameNode} + contexts.sh + ${context_api_url} + ${stats_db_name} + contexts.sh + + + + + + + + ${jobTracker} + ${nameNode} + indicators.sh + ${stats_db_name} + ${wf:appPath()}/scripts/step16-createIndicatorsTables.sql + indicators.sh + + + + + + + + ${hive_jdbc_url} + stats_db_name=${stats_db_name} openaire_db_name=${openaire_db_name} @@ -261,48 +298,11 @@ stats_db_name=${stats_db_name} openaire_db_name=${openaire_db_name} - - - - - - - ${hive_jdbc_url} - - stats_db_name=${stats_db_name} - openaire_db_name=${openaire_db_name} - - - - - - - - ${jobTracker} - ${nameNode} - indicators.sh - ${stats_db_name} - ${wf:appPath()}/scripts/step16_7-createIndicatorsTables.sql - indicators.sh - - - - - - - - ${jobTracker} - ${nameNode} - contexts.sh - ${context_api_url} - ${stats_db_name} - contexts.sh - - + - + ${jobTracker} ${nameNode} @@ -326,20 +326,44 @@ ${wf:appPath()}/scripts/step20-createMonitorDB.sql monitor.sh + + + + + + + ${jobTracker} + ${nameNode} + observatory-pre.sh + ${stats_db_name} + ${observatory_db_name} + ${observatory_db_shadow_name} + observatory-pre.sh + + + ${hive_jdbc_url} + + stats_db_name=${stats_db_name} + observatory_db_name=${observatory_db_name} + + + + + + ${jobTracker} ${nameNode} - observatory.sh + observatory-post.sh ${stats_db_name} ${observatory_db_name} ${observatory_db_shadow_name} - ${wf:appPath()}/scripts/step21-createObservatoryDB.sql - observatory.sh + observatory-post.sh