Commit datasets changes

This commit is contained in:
dimitrispie 2021-06-04 15:47:32 +03:00
parent ac5b7f89b5
commit 533bde3228
25 changed files with 463 additions and 350 deletions

View File

@ -1,107 +0,0 @@
<?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">
<!-- <parent>
<artifactId>dhp-workflows</artifactId >
<groupId>eu.dnetlib.dhp</groupId>
<version>1.1.7-SNAPSHOT</version>
</parent>
<groupId>eu.dnetlib</groupId> -->
<!-- <parent>
<groupId>eu.dnetlib.dhp</groupId>
<artifactId>dhp-workflows</artifactId>
<version>1.1.7-SNAPSHOT</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<artifactId>dhp-usage-stats-update</artifactId> -->
<parent>
<artifactId>dhp-workflows</artifactId>
<groupId>eu.dnetlib.dhp</groupId>
<version>1.1.7-SNAPSHOT</version>
</parent>
<modelVersion>4.0.0</modelVersion>
<artifactId>dhp-indicators</artifactId>
<build>
<plugins>
<plugin>
<groupId>pl.project13.maven</groupId>
<artifactId>git-commit-id-plugin</artifactId>
<version>2.1.15</version>
<executions>
<execution>
<goals>
<goal>revision</goal>
</goals>
</execution>
</executions>
<configuration>
<dotGitDirectory>${project.basedir}/../.git</dotGitDirectory>
<!-- more config here as you see fit -->
</configuration>
</plugin>
<plugin>
<groupId>org.apache.maven.plugins</groupId>
<artifactId>maven-compiler-plugin</artifactId>
<version>3.6.1</version>
<configuration>
<source>1.8</source>
<target>1.8</target>
</configuration>
</plugin>
</plugins>
</build>
<properties>
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
<project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
<cdh.hive.version>0.13.1-cdh5.2.1</cdh.hive.version>
<cdh.hadoop.version>2.5.0-cdh5.2.1</cdh.hadoop.version>
</properties>
<dependencies>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-core_2.11</artifactId>
<version>2.2.0</version>
</dependency>
<dependency>
<groupId>org.apache.spark</groupId>
<artifactId>spark-sql_2.11</artifactId>
<version>2.4.5</version>
</dependency>
<dependency>
<groupId>com.googlecode.json-simple</groupId>
<artifactId>json-simple</artifactId>
<version>1.1.1</version>
</dependency>
<dependency>
<groupId>org.json</groupId>
<artifactId>json</artifactId>
<version>20180130</version>
<type>jar</type>
</dependency>
<dependency>
<groupId>org.apache.hive</groupId>
<artifactId>hive-jdbc</artifactId>
<version>${cdh.hive.version}</version>
</dependency>
<dependency>
<groupId>org.apache.hadoop</groupId>
<artifactId>hadoop-common</artifactId>
<version>${cdh.hadoop.version}</version>
</dependency>
<dependency>
<groupId>eu.dnetlib.dhp</groupId>
<artifactId>dhp-common</artifactId>
<version>${project.version}</version>
</dependency>
<dependency>
<groupId>c3p0</groupId>
<artifactId>c3p0</artifactId>
<version>0.9.1.2</version>
<type>jar</type>
</dependency>
</dependencies>
<name>dhp-indicators</name>
</project>

View File

@ -1 +0,0 @@
mvn clean package -Poozie-package,deploy,run -Dworkflow.source.dir=eu/dnetlib/dhp/oa/graph/indicators

View File

@ -1,35 +0,0 @@
/*
* To change this license header, choose License Headers in Project Properties.
* To change this template file, choose Tools | Templates
* and open the template in the editor.
*/
package eu.dnetlib.oa.graph.indicators.export;
import java.text.SimpleDateFormat;
import java.util.Calendar;
import java.util.Date;
import org.apache.commons.io.IOUtils;
import org.apache.log4j.BasicConfigurator;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;
import eu.dnetlib.dhp.application.ArgumentApplicationParser;
/**
* @author D. Pierrakos
*/
public class ExecuteWorkflow {
private static final Logger logger = LoggerFactory.getLogger(ExecuteWorkflow.class);
public static void main(String args[]) throws Exception {
// Sending the logs to the console
BasicConfigurator.configure();
logger.info("Workflow Executed");
}
}

View File

@ -1,38 +0,0 @@
<configuration>
<property>
<name>jobTracker</name>
<value>${jobTracker}</value>
</property>
<property>
<name>nameNode</name>
<value>${nameNode}</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
<property>
<name>oozie.action.sharelib.for.spark</name>
<value>spark2</value>
</property>
<property>
<name>hiveMetastoreUris</name>
<value>thrift://iis-cdh5-test-m3.ocean.icm.edu.pl:9083</value>
</property>
<property>
<name>hiveJdbcUrl</name>
<value>jdbc:hive2://iis-cdh5-test-m3.ocean.icm.edu.pl:10000/;UseNativeQuery=1</value>
</property>
<property>
<name>impalaJdbcUrl</name>
<value>jdbc:hive2://iis-cdh5-test-gw.ocean.icm.edu.pl:21050/;auth=noSasl;</value>
</property>
<property>
<name>oozie.wf.workflow.notification.url</name>
<value>{serviceUrl}/v1/oozieNotification/jobUpdate?jobId=$jobId%26status=$status</value>
</property>
<property>
<name>oozie.use.system.libpath</name>
<value>true</value>
</property>
</configuration>

View File

@ -1,5 +0,0 @@
#! /usr/bin/env python
import sys
print "this is a Python script"
print "Python Interpreter Version: " + sys.version

View File

@ -1,58 +0,0 @@
<workflow-app name="Python sample" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>hiveMetastoreUris</name>
<description>Hive server metastore URIs</description>
</property>
<property>
<name>hiveJdbcUrl</name>
<description>Hive server jdbc url</description>
</property>
<property>
<name>impalaJdbcUrl</name>
<description>Impala server jdbc url</description>
</property>
</parameters>
<global>
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>hive.metastore.uris</name>
<value>${hiveMetastoreUris}</value>
</property>
<property>
<name>mapreduce.job.queuename</name>
<value>${queueName}</value>
</property>
<property>
<name>oozie.launcher.mapred.job.queue.name</name>
<value>${oozieLauncherQueueName}</value>
</property>
</configuration>
</global>
<start to="python-check"/>
<action name="python-check">
<shell xmlns="uri:oozie:shell-action:0.2">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
<configuration>
<property>
<name>mapred.job.queue.name</name>
<value>${queueName}</value>
</property>
</configuration>
<exec>testpython.py</exec>
<file>python/testpython.py</file>
<capture-output/>
</shell>
<ok to="end"/>
<error to="fail"/>
</action>
<kill name="fail">
<message>Python action failed, error message[${wf:errorMessage(wf:lastErrorNode())}]</message>
</kill>
<end name="end"/>
</workflow-app>

View File

@ -19,7 +19,7 @@
<parent>
<artifactId>dhp-workflows</artifactId>
<groupId>eu.dnetlib.dhp</groupId>
<version>1.1.7-SNAPSHOT</version>
<version>1.2.4-SNAPSHOT</version>
<relativePath>../</relativePath>
</parent>
<modelVersion>4.0.0</modelVersion>
@ -96,7 +96,7 @@
<dependency>
<groupId>eu.dnetlib.dhp</groupId>
<artifactId>dhp-common</artifactId>
<version>1.1.7-SNAPSHOT</version>
<version>1.2.4-SNAPSHOT</version>
<type>jar</type>
</dependency>
<dependency>

View File

@ -9,6 +9,10 @@ package eu.dnetlib.oa.graph.datasetsusagestats.export;
import java.sql.Connection;
import java.sql.SQLException;
import java.sql.Statement;
import java.text.DateFormat;
import java.text.SimpleDateFormat;
import java.util.Calendar;
import java.util.Date;
import org.apache.log4j.Logger;
@ -28,6 +32,7 @@ public abstract class ConnectDB {
private static String dbHiveUrl;
private static String dbImpalaUrl;
private static String datasetUsageStatsDBSchema;
private static String datasetsUsageStatsPermanentDBSchema;
private static String statsDBSchema;
private final static Logger logger = Logger.getLogger(ConnectDB.class);
private Statement stmt = null;
@ -37,6 +42,7 @@ public abstract class ConnectDB {
dbHiveUrl = ExecuteWorkflow.dbHiveUrl;
dbImpalaUrl = ExecuteWorkflow.dbImpalaUrl;
datasetUsageStatsDBSchema = ExecuteWorkflow.datasetUsageStatsDBSchema;
datasetsUsageStatsPermanentDBSchema = ExecuteWorkflow.datasetsUsageStatsPermanentDBSchema;
statsDBSchema = ExecuteWorkflow.statsDBSchema;
Class.forName("org.apache.hive.jdbc.HiveDriver");
@ -63,14 +69,25 @@ public abstract class ConnectDB {
}
public static String getDataSetUsageStatsDBSchema() {
return ConnectDB.datasetUsageStatsDBSchema;
String datePattern = "YYYYMMdd";
DateFormat df = new SimpleDateFormat(datePattern);
// Get the today date using Calendar object.
Date today = Calendar.getInstance().getTime();
String todayAsString = df.format(today);
return ConnectDB.datasetUsageStatsDBSchema + "_" + todayAsString;
}
public static String getStatsDBSchema() {
return ConnectDB.statsDBSchema;
}
public static String getDatasetsUsagestatsPermanentDBSchema() {
return ConnectDB.datasetsUsageStatsPermanentDBSchema;
}
private static Connection connectHive() throws SQLException {
logger.info("trying to open Hive connection...");
ComboPooledDataSource cpds = new ComboPooledDataSource();
cpds.setJdbcUrl(dbHiveUrl);
@ -90,14 +107,18 @@ public abstract class ConnectDB {
cpds.setPreferredTestQuery("SELECT 1");
cpds.setIdleConnectionTestPeriod(60);
logger.info("Opened database successfully");
logger.info("Opened HIVE successfully");
return cpds.getConnection();
// Connection connection = DriverManager.getConnection(dbHiveUrl);
// logger.debug("Opened Hive successfully");
//
// return connection;
}
private static Connection connectImpala() throws SQLException {
logger.info("trying to open Impala connection...");
ComboPooledDataSource cpds = new ComboPooledDataSource();
cpds.setJdbcUrl(dbImpalaUrl);
cpds.setUser("dimitris.pierrakos");
@ -116,8 +137,12 @@ public abstract class ConnectDB {
cpds.setPreferredTestQuery("SELECT 1");
cpds.setIdleConnectionTestPeriod(60);
logger.info("Opened database successfully");
logger.info("Opened Impala successfully");
return cpds.getConnection();
// Connection connection = DriverManager.getConnection(dbHiveUrl);
// logger.debug("Opened Impala successfully");
//
// return connection;
}
}

View File

@ -1,8 +1,6 @@
package eu.dnetlib.oa.graph.datasetsusagestats.export;
import java.sql.Connection;
import java.sql.SQLException;
import java.sql.Statement;
import org.slf4j.Logger;
@ -47,7 +45,7 @@ public class DatasetsStatsDB {
try {
stmt = ConnectDB.getHiveConnection().createStatement();
logger.info("Creating usagestats DB: " + ConnectDB.getDataSetUsageStatsDBSchema());
logger.info("Creating datacite usagestats DB: " + ConnectDB.getDataSetUsageStatsDBSchema());
String createDatabase = "CREATE DATABASE IF NOT EXISTS " + ConnectDB.getDataSetUsageStatsDBSchema();
stmt.executeUpdate(createDatabase);
@ -55,6 +53,23 @@ public class DatasetsStatsDB {
logger.error("Failed to create database: " + e);
throw new Exception("Failed to create database: " + e.toString(), e);
}
try {
stmt = ConnectDB.getHiveConnection().createStatement();
logger
.info(
"Creating permanent datasets usagestats DB: " + ConnectDB.getDatasetsUsagestatsPermanentDBSchema());
String createPermanentDatabase = "CREATE DATABASE IF NOT EXISTS "
+ ConnectDB.getDatasetsUsagestatsPermanentDBSchema();
stmt.executeUpdate(createPermanentDatabase);
logger
.info(
"Created permanent datasets usagestats DB: " + ConnectDB.getDatasetsUsagestatsPermanentDBSchema());
} catch (Exception e) {
logger.error("Failed to create database: " + e);
throw new Exception("Failed to create database: " + e.toString(), e);
}
}
private void createTables() throws Exception {
@ -62,10 +77,10 @@ public class DatasetsStatsDB {
stmt = ConnectDB.getHiveConnection().createStatement();
// Create Reports table - This table should exist
logger.info("Creating Reports Table");
logger.info("Creating Reports Tmp Table");
String sqlCreateTableDataciteReports = "CREATE TABLE IF NOT EXISTS "
+ ConnectDB.getDataSetUsageStatsDBSchema()
+ ".datacitereports(reportid STRING, \n"
+ ".datacitereports_tmp(reportid STRING, \n"
+ " name STRING, \n"
+ " source STRING,\n"
+ " release STRING,\n"
@ -79,10 +94,10 @@ public class DatasetsStatsDB {
logger.info("Reports Table Created");
// Create Datasets Performance Table
logger.info("Creating DataSetsPerformance Table");
logger.info("Creating DataSetsPerformance Tmp Table");
String sqlCreateTableDataSetsPerformance = "CREATE TABLE IF NOT EXISTS "
+ ConnectDB.getDataSetUsageStatsDBSchema()
+ ".datasetsperformance(ds_type STRING,\n"
+ ".datasetsperformance_tmp(ds_type STRING,\n"
+ " ds_title STRING,\n"
+ " yop STRING,\n"
+ " dataset_type STRING, \n"
@ -100,7 +115,22 @@ public class DatasetsStatsDB {
+ " CLUSTERED BY (ds_type)\n"
+ " into 100 buckets stored as orc tblproperties('transactional'='true')";
stmt.executeUpdate(sqlCreateTableDataSetsPerformance);
logger.info("DataSetsPerformance Table Created");
logger.info("DataSetsPerformance Tmp Table Created");
logger.info("Creating Datacite Reports table");
String createDataciteReportsTable = "CREATE TABLE IF NOT EXISTS " + ConnectDB.getDataSetUsageStatsDBSchema()
+ ".datacitereports LIKE " + ConnectDB.getDataSetUsageStatsDBSchema()
+ ".datacitereports_tmp STORED AS PARQUET";
stmt.executeUpdate(createDataciteReportsTable);
logger.info("Datacite Reports Table created");
logger.info("Creating Datasets Performance table");
String createDatasetPerformanceTable = "CREATE TABLE IF NOT EXISTS "
+ ConnectDB.getDataSetUsageStatsDBSchema()
+ ".datasetsperformance LIKE " + ConnectDB.getDataSetUsageStatsDBSchema()
+ ".datasetsperformance_tmp STORED AS PARQUET";
stmt.executeUpdate(createDatasetPerformanceTable);
logger.info("DatasetsPerformance Table created");
stmt.close();
ConnectDB.getHiveConnection().close();

View File

@ -21,6 +21,7 @@ public class ExecuteWorkflow {
static String dbHiveUrl;
static String dbImpalaUrl;
static String datasetUsageStatsDBSchema;
static String datasetsUsageStatsPermanentDBSchema;
static String statsDBSchema;
static boolean recreateDbAndTables;
static boolean datasetsEmptyDirs;
@ -45,6 +46,7 @@ public class ExecuteWorkflow {
dbHiveUrl = parser.get("dbHiveUrl");
dbImpalaUrl = parser.get("dbImpalaUrl");
datasetUsageStatsDBSchema = parser.get("datasetUsageStatsDBSchema");
datasetsUsageStatsPermanentDBSchema = parser.get("datasetsUsageStatsPermanentDBSchema");
statsDBSchema = parser.get("statsDBSchema");
if (parser.get("recreateDbAndTables").toLowerCase().equals("true"))
@ -57,11 +59,11 @@ public class ExecuteWorkflow {
else
datasetsEmptyDirs = false;
// if (parser.get("finalTablesVisibleToImpala").toLowerCase().equals("true"))
// finalTablesVisibleToImpala = true;
// else
// finalTablesVisibleToImpala = false;
//
if (parser.get("finalTablesVisibleToImpala").toLowerCase().equals("true"))
finalTablesVisibleToImpala = true;
else
finalTablesVisibleToImpala = false;
UsageStatsExporter usagestatsExport = new UsageStatsExporter();
usagestatsExport.export();
}

View File

@ -65,7 +65,7 @@ public class ReadReportsListFromDatacite {
logger.info("Checking report with id " + reportID);
String sqlCheckIfReportExists = "SELECT source FROM " + ConnectDB.getDataSetUsageStatsDBSchema()
+ ".datacitereports where reportid=?";
+ ".datacitereports_tmp where reportid=?";
PreparedStatement stGetReportID = ConnectDB.getHiveConnection().prepareStatement(sqlCheckIfReportExists);
stGetReportID.setString(1, reportID);
@ -76,7 +76,7 @@ public class ReadReportsListFromDatacite {
dropTmpReportsTable();
} else {
String sqlInsertReport = "INSERT INTO " + ConnectDB.getDataSetUsageStatsDBSchema()
+ " .datacitereports "
+ " .datacitereports_tmp "
+ "SELECT\n"
+ " get_json_object(json, '$.report.id') AS reportid,\n"
+ " get_json_object(json, '$.report.report-header.report-name') AS name,\n"
@ -127,7 +127,7 @@ public class ReadReportsListFromDatacite {
public void readDatasetsReport(String prettyDatasetsReports, String reportId) throws Exception {
logger.info("Reading Datasets performance for report " + reportId);
logger.info("Write Performance Report To File");
ConnectDB.getHiveConnection().setAutoCommit(false);
ObjectMapper objectMapper = new ObjectMapper();
JsonNode jsonNode = objectMapper.readValue(prettyDatasetsReports, JsonNode.class);
String datasetsReports = jsonNode.toString();
@ -177,7 +177,7 @@ public class ReadReportsListFromDatacite {
stmt.execute(sqlCreateTempTableForDatasets);
String sqlInsertToDatasetsPerformance = "INSERT INTO " + ConnectDB.getDataSetUsageStatsDBSchema()
+ ".datasetsperformance SELECT dataset.dataset_id[0].value ds_type, "
+ ".datasetsperformance_tmp SELECT dataset.dataset_id[0].value ds_type, "
+ " dataset.dataset_title ds_title, "
+ " dataset.yop yop, "
+ " dataset.data_type dataset_type, "
@ -296,15 +296,25 @@ public class ReadReportsListFromDatacite {
}
public void createUsageStatisticsTable() throws SQLException {
logger.info("Dropping Downloads Stats table");
Statement stmt = ConnectDB.getHiveConnection().createStatement();
String dropDownloadsTable = "DROP TABLE IF EXISTS " + ConnectDB.getDataSetUsageStatsDBSchema()
+ ".datacite_downloads";
stmt.executeUpdate(dropDownloadsTable);
logger.info("Updating Datacite Reports table");
String createDataciteReportsTable = "INSERT INTO " + ConnectDB.getDataSetUsageStatsDBSchema()
+ ".datacitereports "
+ "SELECT * FROM " + ConnectDB.getDataSetUsageStatsDBSchema() + ".datacitereports_tmp";
stmt.executeUpdate(createDataciteReportsTable);
logger.info("Datacite Reports Table updated");
logger.info("Updating Datasets Performance table");
String createDatasetPerformanceTable = "INSERT INTO " + ConnectDB.getDataSetUsageStatsDBSchema()
+ ".datasetsperformance "
+ "SELECT * FROM " + ConnectDB.getDataSetUsageStatsDBSchema() + ".datasetsperformance_tmp";
stmt.executeUpdate(createDatasetPerformanceTable);
logger.info("DatasetsPerformance Table updated");
logger.info("Creating Downloads Stats table");
String createDownloadsTable = "CREATE TABLE " + ConnectDB.getDataSetUsageStatsDBSchema()
+ ".datacite_downloads as "
+ ".datacite_downloads STORED AS PARQUET as "
+ "SELECT 'Datacite' source, d.id repository_id, od.id result_id, regexp_replace(substring(string(period_end),0,7),'-','/') date, count, '0' openaire "
+ "FROM " + ConnectDB.getDataSetUsageStatsDBSchema() + ".datasetsperformance "
+ "JOIN " + ConnectDB.getStatsDBSchema() + ".datasource d on name=platform "
@ -314,7 +324,8 @@ public class ReadReportsListFromDatacite {
logger.info("Downloads Stats table created");
logger.info("Creating Views Stats table");
String createViewsTable = "CREATE TABLE " + ConnectDB.getDataSetUsageStatsDBSchema() + ".datacite_views as "
String createViewsTable = "CREATE TABLE " + ConnectDB.getDataSetUsageStatsDBSchema()
+ ".datacite_views STORED AS PARQUET as "
+ "SELECT 'Datacite' source, d.id repository_id, od.id result_id, regexp_replace(substring(string(period_end),0,7),'-','/') date, count, '0' openaire "
+ "FROM " + ConnectDB.getDataSetUsageStatsDBSchema() + ".datasetsperformance "
+ "JOIN " + ConnectDB.getStatsDBSchema() + ".datasource d on name=platform "
@ -322,6 +333,56 @@ public class ReadReportsListFromDatacite {
+ "where metric_type='total-dataset-investigations' ";
stmt.executeUpdate(createViewsTable);
logger.info("Views Stats table created");
logger.info("Building Permanent Datasets Usage Stats DB");
logger.info("Dropping view datacitereports on permanent datacite usagestats DB");
String sql = "DROP VIEW IF EXISTS " + ConnectDB.getDatasetsUsagestatsPermanentDBSchema() + ".datacitereports";
stmt.executeUpdate(sql);
logger.info("Dropped view datacitereports on permanent datacite usagestats DB");
logger.info("Create view datacitereports on permanent datacite usagestats DB");
sql = "CREATE VIEW IF NOT EXISTS " + ConnectDB.getDatasetsUsagestatsPermanentDBSchema() + ".datacitereports"
+ " AS SELECT * FROM " + ConnectDB.getDataSetUsageStatsDBSchema() + ".datacitereports";
stmt.executeUpdate(sql);
logger.info("Created view datacitereports on permanent datasets usagestats DB");
logger.info("Dropping view datasetsperformance on permanent datacite usagestats DB");
sql = "DROP VIEW IF EXISTS " + ConnectDB.getDatasetsUsagestatsPermanentDBSchema() + ".datasetsperformance";
stmt.executeUpdate(sql);
logger.info("Dropped view datasetsperformance on permanent datacite usagestats DB");
logger.info("Create view datasetsperformance on permanent datacite usagestats DB");
sql = "CREATE VIEW IF NOT EXISTS " + ConnectDB.getDatasetsUsagestatsPermanentDBSchema() + ".datasetsperformance"
+ " AS SELECT * FROM " + ConnectDB.getDataSetUsageStatsDBSchema() + ".datasetsperformance";
stmt.executeUpdate(sql);
logger.info("Created view datasetsperformance on permanent datasets usagestats DB");
logger.info("Dropping view datacite_views on permanent datacite usagestats DB");
sql = "DROP VIEW IF EXISTS " + ConnectDB.getDatasetsUsagestatsPermanentDBSchema() + ".datacite_views";
stmt.executeUpdate(sql);
logger.info("Dropped view datacite_views on permanent datacite usagestats DB");
logger.info("Create view datacite_views on permanent datacite usagestats DB");
sql = "CREATE VIEW IF NOT EXISTS " + ConnectDB.getDatasetsUsagestatsPermanentDBSchema() + ".datacite_views"
+ " AS SELECT * FROM " + ConnectDB.getDataSetUsageStatsDBSchema() + ".datacite_views";
stmt.executeUpdate(sql);
logger.info("Created view datacite_views on permanent datasets usagestats DB");
logger.info("Dropping view datacite_downloads on permanent datacite usagestats DB");
sql = "DROP VIEW IF EXISTS " + ConnectDB.getDatasetsUsagestatsPermanentDBSchema() + ".datacite_downloads";
stmt.executeUpdate(sql);
logger.info("Dropped view datacite_downloads on permanent datacite usagestats DB");
logger.info("Create view datacite_downloads on permanent datacite usagestats DB");
sql = "CREATE VIEW IF NOT EXISTS " + ConnectDB.getDatasetsUsagestatsPermanentDBSchema() + ".datacite_downloads"
+ " AS SELECT * FROM " + ConnectDB.getDataSetUsageStatsDBSchema() + ".datacite_downloads";
stmt.executeUpdate(sql);
logger.info("Created view datacite_downloads on permanent datasets usagestats DB");
stmt.close();
ConnectDB.getHiveConnection().close();
logger.info("Completed Building Permanent Datasets Usage Stats DB");
}
}

View File

@ -2,6 +2,7 @@
package eu.dnetlib.oa.graph.datasetsusagestats.export;
import java.io.IOException;
import java.sql.SQLException;
import java.sql.Statement;
import org.apache.hadoop.conf.Configuration;
@ -67,5 +68,50 @@ public class UsageStatsExporter {
readReportsListFromDatacite.readReports();
logger.info("Reports Stored To DB");
readReportsListFromDatacite.createUsageStatisticsTable();
// Make the tables available to Impala
if (ExecuteWorkflow.finalTablesVisibleToImpala) {
logger.info("Making tables visible to Impala");
invalidateMetadata();
}
logger.info("End");
}
private void invalidateMetadata() throws SQLException {
Statement stmt = null;
stmt = ConnectDB.getImpalaConnection().createStatement();
String sql = "INVALIDATE METADATA " + ConnectDB.getDataSetUsageStatsDBSchema() + ".datacite_downloads";
stmt.executeUpdate(sql);
sql = "INVALIDATE METADATA " + ConnectDB.getDataSetUsageStatsDBSchema() + ".datacite_views";
stmt.executeUpdate(sql);
sql = "INVALIDATE METADATA " + ConnectDB.getDataSetUsageStatsDBSchema() + ".datacitereports";
stmt.executeUpdate(sql);
sql = "INVALIDATE METADATA " + ConnectDB.getDataSetUsageStatsDBSchema() + ".datasetsperformance";
stmt.executeUpdate(sql);
sql = "INVALIDATE METADATA " + ConnectDB.getDatasetsUsagestatsPermanentDBSchema() + ".datacite_downloads";
stmt.executeUpdate(sql);
sql = "INVALIDATE METADATA " + ConnectDB.getDatasetsUsagestatsPermanentDBSchema() + ".datacite_views";
stmt.executeUpdate(sql);
sql = "INVALIDATE METADATA " + ConnectDB.getDatasetsUsagestatsPermanentDBSchema() + ".datacitereports";
stmt.executeUpdate(sql);
sql = "INVALIDATE METADATA " + ConnectDB.getDatasetsUsagestatsPermanentDBSchema() + ".datasetsperformance";
stmt.executeUpdate(sql);
stmt.close();
try {
ConnectDB.getHiveConnection().close();
} catch (Exception e) {
logger.info("Message at the end :" + e.getMessage());
}
}
}

View File

@ -29,6 +29,12 @@
"paramDescription": "activate tranform-only mode. Only apply transformation step",
"paramRequired": true
},
{
"paramName": "uspdbs",
"paramLongName": "datasetsUsageStatsPermanentDBSchema",
"paramDescription": "activate tranform-only mode. Only apply transformation step",
"paramRequired": true
},
{
"paramName": "sdbs",
"paramLongName": "statsDBSchema",

View File

@ -1,4 +1,4 @@
<workflow-app name="Usage Datasets Stats" xmlns="uri:oozie:workflow:0.5">
<workflow-app name="Datacite Datasets Usage Stats" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>hiveMetastoreUris</name>
@ -52,6 +52,8 @@
<arg>${impalaJdbcUrl}</arg>
<arg>--datasetUsageStatsDBSchema</arg>
<arg>${datasetUsageStatsDBSchema}</arg>
<arg>--datasetsUsageStatsPermanentDBSchema</arg>
<arg>${datasetsUsageStatsPermanentDBSchema}</arg>
<arg>--statsDBSchema</arg>
<arg>${statsDBSchema}</arg>
<arg>--recreateDbAndTables</arg>

View File

@ -65,6 +65,8 @@ public class ExecuteWorkflow {
static int numberOfDownloadThreads;
static int b2SSHAREID;
public static void main(String args[]) throws Exception {
// Sending the logs to the console
@ -196,6 +198,8 @@ public class ExecuteWorkflow {
numberOfDownloadThreads = Integer.parseInt(parser.get("numberOfDownloadThreads"));
b2SSHAREID = Integer.parseInt(parser.get("b2shareID"));
UsageStatsExporter usagestatsExport = new UsageStatsExporter();
usagestatsExport.export();
// usagestatsExport.createdDBWithTablesOnly();

View File

@ -191,7 +191,7 @@ public class PiwikDownloadLogs {
ResultSet rs = statement
.executeQuery(
"SELECT distinct piwik_id from " + ConnectDB.getStatsDBSchema()
+ ".datasource where piwik_id is not null and piwik_id <> 0 order by piwik_id");
+ ".datasource where piwik_id is not null and piwik_id <> 0 and piwik_id <> 196 order by piwik_id");
// Getting all the piwikids in a list for logging reasons & limitting the list
// to the max number of piwikids

View File

@ -179,6 +179,10 @@ public class PiwikStatsDB {
createPedocsOldUsageData();
logger.info("Pedocs Tables Created");
logger.info("Create Datacite Tables");
createDatasetsUsageData();
logger.info("Datacite Tables Created");
} catch (Exception e) {
logger.error("Failed to process logs: " + e);
throw new Exception("Failed to process logs: " + e.toString(), e);
@ -281,6 +285,7 @@ public class PiwikStatsDB {
// clean view double clicks
logger.info("Cleaning action double clicks");
ConnectDB.getHiveConnection().setAutoCommit(false);
sql = "DELETE from " + ConnectDB.getUsageStatsDBSchema() + ".piwiklogtmp "
+ "WHERE EXISTS (\n"
+ "SELECT DISTINCT p1.source, p1.id_visit, p1.action, p1.entity_id, p1.timestamp \n"
@ -750,6 +755,16 @@ public class PiwikStatsDB {
stmt.executeUpdate(sql);
logger.info("Dropped sarc_sushilogtmp_json_non_array");
logger.info("Dropping piwiklogb2sharetmp");
sql = "DROP TABLE " + ConnectDB.getUsageStatsDBSchema() + ".piwiklogb2sharetmp";
stmt.executeUpdate(sql);
logger.info("Dropped piwiklogb2sharetmp");
logger.info("Dropping piwiklog_b2share_tmp_json");
sql = "DROP TABLE " + ConnectDB.getUsageStatsDBSchema() + ".piwiklog_b2share_tmp_json";
stmt.executeUpdate(sql);
logger.info("Dropped piwiklog_b2share_tmp_json");
stmt.close();
ConnectDB.getHiveConnection().close();
@ -832,4 +847,32 @@ public class PiwikStatsDB {
logger.info("PeDocs Old Downloads Table created");
}
public void createDatasetsUsageData() throws SQLException {
Statement stmt = ConnectDB.getHiveConnection().createStatement();
ConnectDB.getHiveConnection().setAutoCommit(false);
logger.info("Dropping datacite_views");
String sql = "DROP TABLE " + ConnectDB.getUsageStatsDBSchema() + ".datacite_views";
stmt.executeUpdate(sql);
logger.info("Dropped datacite_views");
logger.info("Dropping datacite_downloads");
sql = "DROP TABLE " + ConnectDB.getUsageStatsDBSchema() + ".datacite_downloads";
stmt.executeUpdate(sql);
logger.info("Dropped datacite_downloads");
logger.info("Creating Datasets Views Table");
sql = "Create TABLE IF NOT EXISTS " + ConnectDB.getUsageStatsDBSchema()
+ ".datacite_views as select * from openaire_prod_datacite_usage_stats.datacite_views";
stmt.executeUpdate(sql);
logger.info("Datasets Views Table created");
logger.info("Creating Datasets Downloads Table");
sql = "Create TABLE IF NOT EXISTS " + ConnectDB.getUsageStatsDBSchema()
+ ".datacite_downloads as select * from openaire_prod_datacite_usage_stats.datacite_downloads";
stmt.executeUpdate(sql);
logger.info("Datasets Downloads Table created");
}
}

View File

@ -142,8 +142,20 @@ public class UsageStatsExporter {
sarcStats.updateSarcLogs();
}
logger.info("Sarc done");
// finalize usagestats
PiwikDownloadLogs_B2SHARE b2sharePiwikID = new PiwikDownloadLogs_B2SHARE(ExecuteWorkflow.matomoBaseURL,
ExecuteWorkflow.matomoAuthToken);
b2sharePiwikID.GetOpenAIREB2SHARELogs(ExecuteWorkflow.repoLogPath);
logger.info("B2SHARE done");
PiwikStatsDB_B2SHARE piwikstatsB2SHAREdb = new PiwikStatsDB_B2SHARE(ExecuteWorkflow.repoLogPath,
ExecuteWorkflow.portalLogPath);
piwikstatsB2SHAREdb.setCounterRobotsURL(cRobotsUrl);
logger.info("Processing B2SHARE logs");
piwikstatsB2SHAREdb.processB2SHARELogs();
// finalize usagestats
logger.info("Dropping tmp tables");
if (ExecuteWorkflow.finalizeStats) {
piwikstatsdb.finalizeStats();
@ -161,6 +173,7 @@ public class UsageStatsExporter {
piwikstatsdb.recreateDBAndTables();
piwikstatsdb.createPedocsOldUsageData();
Statement stmt = ConnectDB.getHiveConnection().createStatement();
logger.info("Creating LaReferencia tables");

View File

@ -215,5 +215,11 @@
"paramLongName": "numberOfDownloadThreads",
"paramDescription": "Number of download threads",
"paramRequired": true
},
{
"paramName": "b2shareID",
"paramLongName": "b2shareID",
"paramDescription": "B2SHARE Matomo ID",
"paramRequired": true
}
]

View File

@ -1,4 +1,4 @@
<workflow-app name="Usage Graph Stats" xmlns="uri:oozie:workflow:0.5">
<workflow-app name="Usage Activity Raw Data" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>hiveMetastoreUris</name>
@ -78,6 +78,7 @@
<arg>--sarcNumberOfIssnToDownload</arg><arg>${sarcNumberOfIssnToDownload}</arg>
<arg>--finalizeStats</arg><arg>${finalizeStats}</arg>
<arg>--numberOfDownloadThreads</arg><arg>${numberOfDownloadThreads}</arg>
<arg>--b2shareID</arg><arg>${b2shareID}</arg>
<capture-output/>
</java>
<ok to="End" />

View File

@ -82,7 +82,7 @@ public abstract class ConnectDB {
Date today = Calendar.getInstance().getTime();
String todayAsString = df.format(today);
return ConnectDB.usageStatsDBSchema + "_" + todayAsString;
return ConnectDB.usageStatsDBSchema + todayAsString;
}
public static String getStatsDBSchema() {

View File

@ -35,20 +35,20 @@ public class PiwikStatsDB {
private void createDatabase() throws Exception {
// try {
//
// stmt = ConnectDB.getHiveConnection().createStatement();
//
// logger.info("Dropping usagestats DB: " + ConnectDB.getUsageStatsDBSchema());
// String dropDatabase = "DROP DATABASE IF EXISTS " + ConnectDB.getUsageStatsDBSchema() + " CASCADE";
// stmt.executeUpdate(dropDatabase);
// } catch (Exception e) {
// logger.error("Failed to drop database: " + e);
// throw new Exception("Failed to drop database: " + e.toString(), e);
// }
//
try {
stmt = ConnectDB.getHiveConnection().createStatement();
logger.info("Dropping usagestats DB: " + ConnectDB.getUsageStatsDBSchema());
String dropDatabase = "DROP DATABASE IF EXISTS " + ConnectDB.getUsageStatsDBSchema() + " CASCADE";
stmt.executeUpdate(dropDatabase);
} catch (Exception e) {
logger.error("Failed to drop database: " + e);
throw new Exception("Failed to drop database: " + e.toString(), e);
}
try {
logger.info("Creating usagestats DB: " + ConnectDB.getUsageStatsDBSchema());
String createDatabase = "CREATE DATABASE IF NOT EXISTS " + ConnectDB.getUsageStatsDBSchema();
stmt.executeUpdate(createDatabase);
@ -337,6 +337,96 @@ public class PiwikStatsDB {
}
public void uploadB2SHAREStats() throws Exception {
stmt = ConnectDB.getHiveConnection().createStatement();
ConnectDB.getHiveConnection().setAutoCommit(false);
// Dropping B2SHARE b2share_result_views_monthly_tmp view
logger.info("Dropping B2SHARE b2share_result_views_monthly_tmp view");
String sql = "DROP view IF EXISTS " + ConnectDB.getUsageStatsDBSchema() + ".b2share_result_views_monthly_tmp";
logger.info("Dropped b2share_result_views_monthly_tmp view ");
stmt.executeUpdate(sql);
// Dropping B2SHARE b2share_result_views_monthly_tmp view
logger.info("Dropping b2SHARE b2share_result_downloads_monthly_tmp view");
sql = "DROP view IF EXISTS " + ConnectDB.getUsageStatsDBSchema() + ".b2share_result_downloads_monthly_tmp";
logger.info("Dropped b2share_result_downloads_monthly_tmp view ");
stmt.executeUpdate(sql);
// Dropping B2SHARE b2share_views_stats_tmp table
logger.info("Dropping B2SHARE b2share_views_stats_tmp table");
sql = "DROP TABLE IF EXISTS " + ConnectDB.getUsageStatsDBSchema() + ".b2share_views_stats_tmp";
logger.info("Dropped b2share_views_stats_tmp table ");
stmt.executeUpdate(sql);
// Dropping B2SHARE b2share_downloads_stats_tmp table
logger.info("Dropping B2SHARE b2share_downloads_stats_tmp table");
sql = "DROP TABLE IF EXISTS " + ConnectDB.getUsageStatsDBSchema() + ".b2share_downloads_stats_tmp";
logger.info("Dropped b2share_downloads_stats_tmp table ");
stmt.executeUpdate(sql);
// Creating B2SHARE b2share_result_views_monthly_tmp view
logger.info("Creating B2SHARE b2share_result_views_monthly_tmp view");
sql = "CREATE OR REPLACE VIEW " + ConnectDB.getUsageStatsDBSchema() + ".b2share_result_views_monthly_tmp "
+ "AS SELECT entity_id, reflect('java.net.URLDecoder', 'decode', entity_id) AS id, "
+ "COUNT(entity_id) as views, SUM(CASE WHEN referrer_name LIKE '%openaire%' THEN 1 ELSE 0 END) AS openaire_referrer, "
+ "CONCAT(YEAR(timestamp), '/', LPAD(MONTH(timestamp), 2, '0')) AS month, source "
+ "FROM " + ConnectDB.getUsageRawDataDBSchema() + ".piwiklog "
+ "WHERE action='action' and (source_item_type='oaItem' or source_item_type='repItem') and source=412 "
+ "GROUP BY entity_id, CONCAT(YEAR(timestamp), '/', LPAD(MONTH(timestamp), 2, '0')), source ORDER BY source, entity_id";
stmt.executeUpdate(sql);
logger.info("Created b2share_result_views_monthly_tmp view ");
// Creating B2SHARE b2share_views_stats_tmp table
logger.info("Creating B2SHARE b2share_views_stats_tmp table");
sql = "CREATE TABLE IF NOT EXISTS " + ConnectDB.getUsageStatsDBSchema() + ".b2share_views_stats_tmp AS "
+ "SELECT 'B2SHARE' as source, d.id as repository_id, ro.id as result_id, month as date, "
+ "max(views) AS count, max(openaire_referrer) AS openaire FROM " + ConnectDB.getUsageStatsDBSchema()
+ ".b2share_result_views_monthly_tmp p, "
+ ConnectDB.getStatsDBSchema() + ".datasource d, " + ConnectDB.getStatsDBSchema() + ".result_oids ro "
+ "WHERE p.id=ro.oid and d.id='re3data_____::ad3609c351bd520edf6f10f5e0d9b877' "
+ "GROUP BY d.id, ro.id, month ORDER BY d.id, ro.id";
stmt.executeUpdate(sql);
logger.info("Created B2SHARE b2share_views_stats_tmp table");
// Creating B2SHARE b2share_result_downloads_monthly_tmp view
logger.info("Creating B2SHARE b2share_result_downloads_monthly_tmp view");
sql = "CREATE OR REPLACE VIEW " + ConnectDB.getUsageStatsDBSchema() + ".b2share_result_downloads_monthly_tmp "
+ "AS SELECT entity_id, reflect('java.net.URLDecoder', 'decode', entity_id) AS id, "
+ "COUNT(entity_id) as views, SUM(CASE WHEN referrer_name LIKE '%openaire%' THEN 1 ELSE 0 END) AS openaire_referrer, "
+ "CONCAT(YEAR(timestamp), '/', LPAD(MONTH(timestamp), 2, '0')) AS month, source "
+ "FROM " + ConnectDB.getUsageRawDataDBSchema() + ".piwiklog "
+ "WHERE action='download' and (source_item_type='oaItem' or source_item_type='repItem') and source=412 "
+ "GROUP BY entity_id, CONCAT(YEAR(timestamp), '/', LPAD(MONTH(timestamp), 2, '0')), source ORDER BY source, entity_id";
stmt.executeUpdate(sql);
logger.info("Created b2share_result_downloads_monthly_tmp view ");
// Creating B2SHARE b2share_downloads_stats_tmp table
logger.info("Creating B2SHARE b2share_downloads_stats_tmp table");
sql = "CREATE TABLE IF NOT EXISTS " + ConnectDB.getUsageStatsDBSchema() + ".b2share_downloads_stats_tmp AS "
+ "SELECT 'B2SHARE' as source, d.id as repository_id, ro.id as result_id, month as date, "
+ "max(views) AS count, max(openaire_referrer) AS openaire FROM " + ConnectDB.getUsageStatsDBSchema()
+ ".b2share_result_downloads_monthly_tmp p, "
+ ConnectDB.getStatsDBSchema() + ".datasource d, " + ConnectDB.getStatsDBSchema() + ".result_oids ro "
+ "WHERE p.id=ro.oid and d.id='re3data_____::ad3609c351bd520edf6f10f5e0d9b877' "
+ "GROUP BY d.id, ro.id, month ORDER BY d.id, ro.id";
stmt.executeUpdate(sql);
logger.info("Created B2SHARE b2share_downloads_stats_tmp table");
// Dropping B2SHARE b2share_result_views_monthly_tmp view
logger.info("Dropping B2SHARE b2share_result_views_monthly_tmp view");
sql = "DROP view IF EXISTS " + ConnectDB.getUsageStatsDBSchema() + ".b2share_result_views_monthly_tmp";
logger.info("Dropped b2share_result_views_monthly_tmp view ");
stmt.executeUpdate(sql);
// Dropping B2SHARE b2share_result_views_monthly_tmp view
logger.info("Dropping B2SHARE b2share_result_downloads_monthly_tmp view");
sql = "DROP view IF EXISTS " + ConnectDB.getUsageStatsDBSchema() + ".b2share_result_downloads_monthly_tmp";
logger.info("Dropped b2share_result_downloads_monthly_tmp view ");
stmt.executeUpdate(sql);
}
public void finalizeStats() throws Exception {
stmt = ConnectDB.getHiveConnection().createStatement();
ConnectDB.getHiveConnection().setAutoCommit(false);
@ -402,6 +492,13 @@ public class PiwikStatsDB {
stmt.executeUpdate(sql);
logger.info("LaReferencia views updated to views_stats");
// Inserting B2SHARE views stats
logger.info("Inserting B2SHARE data to views_stats");
sql = "INSERT INTO " + ConnectDB.getUsageStatsDBSchema() + ".views_stats "
+ "SELECT * FROM " + ConnectDB.getUsageStatsDBSchema() + ".b2share_views_stats_tmp";
stmt.executeUpdate(sql);
logger.info("B2SHARE views updated to views_stats");
logger.info("Creating downloads_stats table");
String createDownloadsStats = "CREATE TABLE IF NOT EXISTS "
+ ConnectDB.getUsageStatsDBSchema()
@ -425,12 +522,18 @@ public class PiwikStatsDB {
logger.info("Inserted Pedocs data to downloads_stats");
// Inserting TUDELFT downloads stats
logger.info("Inserting TUDELFT old data to downloads_stats");
logger.info("Inserting TUDELFT data to downloads_stats");
sql = "INSERT INTO " + ConnectDB.getUsageStatsDBSchema() + ".downloads_stats "
+ "SELECT * FROM " + ConnectDB.getUsageStatsDBSchema() + ".tudelft_downloads_stats_tmp";
stmt.executeUpdate(sql);
logger.info("Inserted TUDELFT data to downloads_stats");
// Inserting B2SHARE downloads stats
logger.info("Inserting B2SHARE data to downloads_stats");
sql = "INSERT INTO " + ConnectDB.getUsageStatsDBSchema() + ".downloads_stats "
+ "SELECT * FROM " + ConnectDB.getUsageStatsDBSchema() + ".b2share_downloads_stats_tmp";
stmt.executeUpdate(sql);
logger.info("Inserted B2SHARE data to downloads_stats");
// Inserting Lareferencia downloads stats
logger.info("Inserting LaReferencia data to downloads_stats");
sql = "INSERT INTO " + ConnectDB.getUsageStatsDBSchema() + ".downloads_stats "
@ -452,6 +555,20 @@ public class PiwikStatsDB {
stmt.executeUpdate(sql);
logger.info("SARC-OJS downloads updated to downloads_stats");
// Inserting Datacite views stats
logger.info("Inserting Datacite views to views_stats");
sql = "INSERT INTO " + ConnectDB.getUsageStatsDBSchema() + ".views_stats "
+ "SELECT * FROM " + ConnectDB.getUsageRawDataDBSchema() + ".datacite_views";
stmt.executeUpdate(sql);
logger.info("Datacite views updated to views_stats");
// Inserting Datacite downloads stats
logger.info("Inserting Datacite downloads to downloads_stats");
sql = "INSERT INTO " + ConnectDB.getUsageStatsDBSchema() + ".downloads_stats "
+ "SELECT * FROM " + ConnectDB.getUsageRawDataDBSchema() + ".datacite_downloads";
stmt.executeUpdate(sql);
logger.info("Datacite downloads updated to downloads_stats");
logger.info("Creating pageviews_stats table");
String create_pageviews_stats = "CREATE TABLE IF NOT EXISTS " + ConnectDB.getUsageStatsDBSchema()
+ ".pageviews_stats "

View File

@ -51,6 +51,9 @@ public class UsageStatsExporter {
logger.info("Processing TUDELFT Stats");
piwikstatsdb.uploadTUDELFTStats();
logger.info("Processing TUDELFT Stats Done");
logger.info("Processing B2SHARE Stats");
piwikstatsdb.uploadB2SHAREStats();
logger.info("Processing B2SHARE Stats Done");
}

View File

@ -1,4 +1,4 @@
<workflow-app name="Usage Graph Stats" xmlns="uri:oozie:workflow:0.5">
<workflow-app name="Usage Stats Update" xmlns="uri:oozie:workflow:0.5">
<parameters>
<property>
<name>hiveMetastoreUris</name>