Add collecting software code repository URLs

This commit is contained in:
Serafeim Chatzopoulos 2023-09-14 18:43:25 +03:00
parent 8a6892cc63
commit 9d44418d38
7 changed files with 508 additions and 0 deletions

View File

@ -0,0 +1,104 @@
<?xml version="1.0" encoding="UTF-8"?>
<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<parent>
<groupId>eu.dnetlib.dhp</groupId>
<artifactId>dhp-workflows</artifactId>
<version>1.2.5-SNAPSHOT</version>
</parent>
<artifactId>dhp-swh</artifactId>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_${scala.binary.version}</artifactId>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_${scala.binary.version}</artifactId>
</dependency>
<dependency>
<groupId>eu.dnetlib.dhp</groupId>
<artifactId>dhp-common</artifactId>
<version>${project.version}</version>
<exclusions>
<exclusion>
<groupId>net.sf.saxon</groupId>
<artifactId>Saxon-HE</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>dom4j</groupId>
<artifactId>dom4j</artifactId>
</dependency>
<dependency>
<groupId>xml-apis</groupId>
<artifactId>xml-apis</artifactId>
</dependency>
<dependency>
<groupId>jaxen</groupId>
<artifactId>jaxen</artifactId>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-distcp</artifactId>
</dependency>
<dependency>
<groupId>eu.dnetlib</groupId>
<artifactId>dnet-actionmanager-api</artifactId>
</dependency>
<dependency>
<groupId>eu.dnetlib</groupId>
<artifactId>dnet-actionmanager-common</artifactId>
<exclusions>
<exclusion>
<groupId>eu.dnetlib</groupId>
<artifactId>dnet-openaireplus-mapping-utils</artifactId>
</exclusion>
<exclusion>
<groupId>saxonica</groupId>
<artifactId>saxon</artifactId>
</exclusion>
<exclusion>
<groupId>saxonica</groupId>
<artifactId>saxon-dom</artifactId>
</exclusion>
<exclusion>
<groupId>jgrapht</groupId>
<artifactId>jgrapht</artifactId>
</exclusion>
<exclusion>
<groupId>net.sf.ehcache</groupId>
<artifactId>ehcache</artifactId>
</exclusion>
<exclusion>
<groupId>org.springframework</groupId>
<artifactId>spring-test</artifactId>
</exclusion>
<exclusion>
<groupId>org.apache.*</groupId>
<artifactId>*</artifactId>
</exclusion>
<exclusion>
<groupId>apache</groupId>
<artifactId>*</artifactId>
</exclusion>
</exclusions>
</dependency>
<dependency>
<groupId>org.apache.httpcomponents</groupId>
<artifactId>httpclient</artifactId>
<version>4.5.13</version>
</dependency>
</dependencies>
</project>

View File

@ -0,0 +1,211 @@
package eu.dnetlib.dhp.swh;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkHiveSession;
import static eu.dnetlib.dhp.common.SparkSessionSupport.runWithSparkSession;
import java.io.IOException;
import java.io.Serializable;
import java.util.ArrayList;
import java.util.Iterator;
import java.util.List;
import java.util.Optional;
import java.util.concurrent.TimeUnit;
import org.apache.commons.io.IOUtils;
import org.apache.http.Header;
import org.apache.http.HttpEntity;
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.http.util.EntityUtils;
import org.apache.spark.SparkConf;
import org.apache.spark.api.java.function.FlatMapFunction;
import org.apache.spark.sql.*;
import org.apache.spark.sql.Dataset;
import org.apache.spark.sql.types.DataTypes;
import org.apache.spark.sql.types.StructType;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import com.fasterxml.jackson.databind.ObjectMapper;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
import eu.dnetlib.dhp.schema.common.ModelConstants;
import eu.dnetlib.dhp.schema.oaf.*;
/**
* Creates action sets for Crossref affiliation relations inferred by BIP!
*/
public class CollectSoftwareRepositoryURLs implements Serializable {
private static final Logger log = LoggerFactory.getLogger(CollectSoftwareRepositoryURLs.class);
// public static final String BIP_AFFILIATIONS_CLASSID = "result:organization:bipinference";
// public static final String BIP_AFFILIATIONS_CLASSNAME = "Affiliation relation inferred by BIP!";
// public static final String BIP_INFERENCE_PROVENANCE = "bip:affiliation:crossref";
private static final String DEFAULT_VISIT_TYPE = "git";
private static final int CONCURRENT_API_CALLS = 1;
private static final String SWH_LATEST_VISIT_URL = "https://archive.softwareheritage.org/api/1/origin/%s/visit/latest/";
public static <I extends Result> void main(String[] args) throws Exception {
String jsonConfiguration = IOUtils
.toString(
CollectSoftwareRepositoryURLs.class
.getResourceAsStream("/eu/dnetlib/dhp/swh/input_parameters.json"));
final ArgumentApplicationParser parser = new ArgumentApplicationParser(jsonConfiguration);
parser.parseArgument(args);
final Boolean isSparkSessionManaged = Optional
.ofNullable(parser.get("isSparkSessionManaged"))
.map(Boolean::valueOf)
.orElse(Boolean.TRUE);
log.info("isSparkSessionManaged: {}", isSparkSessionManaged);
final String hiveDbName = parser.get("hiveDbName");
log.info("hiveDbName {}: ", hiveDbName);
final String outputPath = parser.get("softwareCodeRepositoryURLs");
log.info("softwareCodeRepositoryURLs {}: ", outputPath);
final String hiveMetastoreUris = parser.get("hiveMetastoreUris");
log.info("hiveMetastoreUris: {}", hiveMetastoreUris);
SparkConf conf = new SparkConf();
conf.set("hive.metastore.uris", hiveMetastoreUris);
runWithSparkHiveSession(
conf,
isSparkSessionManaged,
spark -> {
doRun(spark, hiveDbName, outputPath);
});
}
private static <I extends Result> void doRun(SparkSession spark, String hiveDbName, String outputPath) {
String queryTemplate = "SELECT distinct coderepositoryurl.value " +
"FROM %s.software " +
"WHERE coderepositoryurl.value IS NOT NULL";
String query = String.format(queryTemplate, hiveDbName);
log.info("Hive query to fetch software code URLs: {}", query);
Dataset<Row> df = spark.sql(query);
// write distinct repository URLs
df
.write()
.mode(SaveMode.Overwrite)
// .option("compression", "gzip")
.csv(outputPath);
}
private static Dataset<Row> readSoftware(SparkSession spark, String inputPath) {
return spark
.read()
.json(inputPath)
.select(
new Column("codeRepositoryUrl.value").as("codeRepositoryUrl"),
new Column("dataInfo.deletedbyinference"),
new Column("dataInfo.invisible"));
}
private static Dataset<Row> filterSoftware(Dataset<Row> softwareDF, Integer limit) {
Dataset<Row> df = softwareDF
.where(softwareDF.col("codeRepositoryUrl").isNotNull())
.where("deletedbyinference = false")
.where("invisible = false")
.drop("deletedbyinference")
.drop("invisible");
// TODO remove when done
df = df.limit(limit);
return df;
}
public static Dataset<Row> makeParallelRequests(SparkSession spark, Dataset<Row> softwareDF) {
// TODO replace with coalesce ?
Dataset<Row> df = softwareDF.repartition(CONCURRENT_API_CALLS);
log.info("Number of partitions: {}", df.rdd().getNumPartitions());
ObjectMapper objectMapper = new ObjectMapper();
List<Row> collectedRows = df
.javaRDD()
// max parallelism should be equal to the number of partitions here
.mapPartitions((FlatMapFunction<Iterator<Row>, Row>) partition -> {
List<Row> resultRows = new ArrayList<>();
while (partition.hasNext()) {
Row row = partition.next();
String url = String.format(SWH_LATEST_VISIT_URL, row.getString(0));
// String snapshotId = null;
// String type = null;
// String date = null;
String responseBody = makeAPICall(url);
TimeUnit.SECONDS.sleep(1);
// Thread.sleep(500);
// if (responseBody != null) {
// LastVisitResponse visitResponse = objectMapper.readValue(responseBody, LastVisitResponse.class);
// snapshotId = visitResponse.getSnapshot();
// type = visitResponse.getType();
// date = visitResponse.getDate();
// }
// resultRows.add(RowFactory.create(url, snapshotId, type, date));
resultRows.add(RowFactory.create(url, responseBody));
}
return resultRows.iterator();
})
.collect();
StructType resultSchema = new StructType()
.add("codeRepositoryUrl", DataTypes.StringType)
.add("response", DataTypes.StringType);
// .add("snapshotId", DataTypes.StringType)
// .add("type", DataTypes.StringType)
// .add("date", DataTypes.StringType);
// create a DataFrame from the collected rows
return spark.createDataFrame(collectedRows, resultSchema);
}
private static String makeAPICall(String url) throws IOException {
System.out.println(java.time.LocalDateTime.now());
try (CloseableHttpClient httpClient = HttpClients.createDefault()) {
HttpGet httpGet = new HttpGet(url);
httpGet
.setHeader(
"Authorization",
"Bearer eyJhbGciOiJIUzI1NiIsInR5cCIgOiAiSldUIiwia2lkIiA6ICJhMTMxYTQ1My1hM2IyLTQwMTUtODQ2Ny05MzAyZjk3MTFkOGEifQ.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.XHj1VIZu1dZ4Ej32-oU84mFmaox9cLNjXosNxwZM0Xs");
try (CloseableHttpResponse response = httpClient.execute(httpGet)) {
int statusCode = response.getStatusLine().getStatusCode();
// if (statusCode != 200)
// return null;
Header[] headers = response.getHeaders("X-RateLimit-Remaining");
for (Header header : headers) {
System.out
.println(
"Key : " + header.getName()
+ " ,Value : " + header.getValue());
}
HttpEntity entity = response.getEntity();
if (entity != null) {
return EntityUtils.toString(entity);
}
}
}
return null;
}
}

View File

@ -0,0 +1,40 @@
package eu.dnetlib.dhp.swh.models;
import com.cloudera.com.fasterxml.jackson.annotation.JsonProperty;
import com.fasterxml.jackson.annotation.JsonIgnoreProperties;
@JsonIgnoreProperties(ignoreUnknown = true)
public class LastVisitResponse {
private String type;
private String date;
@JsonProperty("snapshot")
private String snapshotId;
public String getType() {
return type;
}
public void setType(String type) {
this.type = type;
}
public String getDate() {
return date;
}
public void setDate(String date) {
this.date = date;
}
public String getSnapshot() {
return snapshotId;
}
public void setSnapshot(String snapshotId) {
this.snapshotId = snapshotId;
}
}

View File

@ -0,0 +1,26 @@
[
{
"paramName": "issm",
"paramLongName": "isSparkSessionManaged",
"paramDescription": "when true will stop SparkSession after job execution",
"paramRequired": false
},
{
"paramName": "ip",
"paramLongName": "softwareCodeRepositoryURLs",
"paramDescription": "the URL where to store software repository URLs",
"paramRequired": true
},
{
"paramName": "db",
"paramLongName": "hiveDbName",
"paramDescription": "the target hive database name",
"paramRequired": true
},
{
"paramName": "hmu",
"paramLongName": "hiveMetastoreUris",
"paramDescription": "the hive metastore uris",
"paramRequired": true
}
]

View File

@ -0,0 +1,25 @@
# hive
hiveDbName=openaire_prod_20230914
hiveMetastoreUris=thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083
# oozie
oozie.action.sharelib.for.spark=spark2
oozie.use.system.libpath=true
oozie.wf.application.path=${oozieTopWfApplicationPath}
oozie.wf.application.path=${oozieTopWfApplicationPath}
oozieActionShareLibForSpark2=spark2
# spark
spark2EventLogDir=/user/spark/spark2ApplicationHistory
spark2ExtraListeners=com.cloudera.spark.lineage.NavigatorAppListener
spark2SqlQueryExecutionListeners=com.cloudera.spark.lineage.NavigatorQueryListener
spark2YarnHistoryServerAddress=http://iis-cdh5-test-gw.ocean.icm.edu.pl:18089
sparkSqlWarehouseDir=/user/hive/warehouse
# misc
wfAppPath=${oozieTopWfApplicationPath}
resourceManager=http://iis-cdh5-test-m2.ocean.icm.edu.pl:8088/cluster
# custom params
softwareCodeRepositoryURLs=${workingDir}/code_repo_urls.csv
resume=collect-software-repository-urls

View File

@ -0,0 +1,101 @@
<workflow-app name="Software-Heritage-Integration-Workflow" xmlns="uri:oozie:workflow:0.5">
<!-- <parameters>-->
<!-- <property>-->
<!-- <name>apiDescription</name>-->
<!-- <description>A json encoding of the API Description class</description>-->
<!-- </property>-->
<!-- <property>-->
<!-- <name>dataSourceInfo</name>-->
<!-- <description>A json encoding of the Datasource Info</description>-->
<!-- </property>-->
<!-- <property>-->
<!-- <name>identifierPath</name>-->
<!-- <description>An xpath to retrieve the metadata identifier for the generation of DNet Identifier </description>-->
<!-- </property>-->
<!-- <property>-->
<!-- <name>metadataEncoding</name>-->
<!-- <description> The type of the metadata XML/JSON</description>-->
<!-- </property>-->
<!-- <property>-->
<!-- <name>timestamp</name>-->
<!-- <description>The timestamp of the collection date</description>-->
<!-- </property>-->
<!-- <property>-->
<!-- <name>workflowId</name>-->
<!-- <description>The identifier of the workflow</description>-->
<!-- </property>-->
<!-- <property>-->
<!-- <name>mdStoreID</name>-->
<!-- <description>The identifier of the mdStore</description>-->
<!-- </property>-->
<!-- <property>-->
<!-- <name>mdStoreManagerURI</name>-->
<!-- <description>The URI of the MDStore Manager</description>-->
<!-- </property>-->
<!-- <property>-->
<!-- <name>dnetMessageManagerURL</name>-->
<!-- <description>The URI of the Dnet Message Manager</description>-->
<!-- </property>-->
<!-- <property>-->
<!-- <name>collectionMode</name>-->
<!-- <description>Should be REFRESH or INCREMENTAL</description>-->
<!-- </property>-->
<!-- <property>-->
<!-- <name>collection_java_xmx</name>-->
<!-- <value>-Xmx200m</value>-->
<!-- <description>Used to configure the heap size for the map JVM process. Should be 80% of mapreduce.map.memory.mb.</description>-->
<!-- </property>-->
<!-- </parameters>-->
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
</global>
<start to="startFrom"/>
<kill name="Kill">
<message>Action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<decision name="startFrom">
<switch>
<case to="collect-software-repository-urls">${wf:conf('startFrom') eq 'collect-software-repository-urls'}</case>
<default to="collect-software-repository-urls"/>
</switch>
</decision>
<action name="collect-software-repository-urls">
<spark xmlns="uri:oozie:spark-action:0.2">
<master>yarn</master>
<mode>cluster</mode>
<name>Collect software repository URLs</name>
<class>eu.dnetlib.dhp.swh.CollectSoftwareRepositoryURLs</class>
<jar>dhp-swh-${projectVersion}.jar</jar>
<spark-opts>
--executor-memory=${sparkExecutorMemory}
--executor-cores=${sparkExecutorCores}
--driver-memory=${sparkDriverMemory}
--conf spark.extraListeners=${spark2ExtraListeners}
--conf spark.sql.queryExecutionListeners=${spark2SqlQueryExecutionListeners}
--conf spark.yarn.historyServer.address=${spark2YarnHistoryServerAddress}
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
--conf spark.sql.warehouse.dir=${sparkSqlWarehouseDir}
</spark-opts>
<arg>--softwareCodeRepositoryURLs</arg><arg>${softwareCodeRepositoryURLs}</arg>
<arg>--hiveDbName</arg><arg>${hiveDbName}</arg>
<arg>--hiveMetastoreUris</arg><arg>${hiveMetastoreUris}</arg>
</spark>
<ok to="End"/>
<error to="Kill"/>
</action>
<end name="End"/>
</workflow-app>

View File

@ -39,6 +39,7 @@
<module>dhp-broker-events</module> <module>dhp-broker-events</module>
<module>dhp-doiboost</module> <module>dhp-doiboost</module>
<module>dhp-impact-indicators</module> <module>dhp-impact-indicators</module>
<module>dhp-swh</module>
</modules> </modules>
<pluginRepositories> <pluginRepositories>