From f02fc236f205a1012854d264aa068ca4c736665e Mon Sep 17 00:00:00 2001 From: Dimitris Date: Mon, 10 May 2021 16:53:29 +0300 Subject: [PATCH] Commit 100520201 --- pom.xml | 2 +- .../repositories/UsageStatsRepository.java | 925 +++--------------- src/main/resources/log4j.properties | 6 +- 3 files changed, 159 insertions(+), 774 deletions(-) diff --git a/pom.xml b/pom.xml index 26961b5..2bd23d2 100755 --- a/pom.xml +++ b/pom.xml @@ -116,7 +116,7 @@ com.cloudera ImpalaJDBC41 2.6.3 - runtime + jar diff --git a/src/main/java/eu/dnetlib/usagestats/repositories/UsageStatsRepository.java b/src/main/java/eu/dnetlib/usagestats/repositories/UsageStatsRepository.java index b93ef0a..8d47b1a 100755 --- a/src/main/java/eu/dnetlib/usagestats/repositories/UsageStatsRepository.java +++ b/src/main/java/eu/dnetlib/usagestats/repositories/UsageStatsRepository.java @@ -35,7 +35,6 @@ import java.security.MessageDigest; import java.sql.Connection; import java.sql.PreparedStatement; import java.sql.ResultSet; -import java.sql.SQLException; import java.text.SimpleDateFormat; import java.util.ArrayList; import java.util.Calendar; @@ -828,775 +827,6 @@ public class UsageStatsRepository { DbUtils.closeQuietly(connection); } } -// -// private void executeOpenaire(List reportItems, String openaire, -// String repositoryIdentifier, String itemDataType, Date beginDate, -// Date endDate, String granularity) { -// SimpleDateFormat report_dateFormat = new SimpleDateFormat("yyyy-MM-dd"); -// SimpleDateFormat postgresFormat = new SimpleDateFormat("yyyy/MM"); -// String beginDateStr = postgresFormat.format(beginDate); -// String endDateStr = postgresFormat.format(endDate); -// -// Connection connection = null; -// PreparedStatement st = null; -// ResultSet rs = null; -// -// /* -// Calendar startCalendar = Calendar.getInstance(); -// startCalendar.setTime(beginDate); -// Calendar endCalendar = Calendar.getInstance(); -// endCalendar.setTime(endDate); -// int diffYear = endCalendar.get(Calendar.YEAR) - startCalendar.get(Calendar.YEAR); -// int diffMonth = diffYear * 12 + endCalendar.get(Calendar.MONTH) - startCalendar.get(Calendar.MONTH); -// */ -// try { -// connection = usageStatsDB.getConnection(); -// if (repositoryIdentifier.equals("")) { -// if (itemDataType.equals("")) { -// //st = connection.prepareStatement("SELECT res.repository_id, r.title, r.publisher, r.source, rc.type, pids.pid, d.name, res.ddate, oids.orid, res.downloads, res.views FROM (SELECT coalesce(ds.repository_id, vs.repository_id) AS repository_id, coalesce(ds.result_id, vs.result_id) AS result_id, coalesce(ds.date, vs.date) AS ddate, coalesce(ds.sum, 0) AS downloads, coalesce(vs.sum,0) AS views FROM (SELECT s.repository_id, s.result_id, s.date, sum(s.count) FROM public.downloads_stats s WHERE s.date>=? AND s.date<=? AND s.result_id=? GROUP BY s.repository_id, s.result_id, s.date) AS ds FULL OUTER JOIN (SELECT s.repository_id, s.result_id, s.date, sum(s.count) FROM public.views_stats s WHERE s.date>=? AND s.date<=? AND s.result_id=? GROUP BY s.repository_id, s.result_id, s.date) AS vs ON ds.result_id=vs.result_id AND ds.date=vs.date) AS res JOIN public.result r ON res.result_id=r.id JOIN public.datasource d ON d.id=res.repository_id JOIN public.result_classifications rc ON rc.id=r.id LEFT JOIN (SELECT pids.id, string_agg(pids.pid, '#!#') AS pid FROM public.result_pids pids WHERE pids.id=? AND type='doi' GROUP BY pids.id) AS pids ON pids.id=r.id LEFT JOIN (SELECT oids.id, string_agg(oids.orid, '#!#') AS orid FROM public.result_oids oids WHERE oids.id=? GROUP BY oids.id) AS oids ON oids.id=r.id ORDER BY res.repository_id, res.ddate;"); -// //st = connection.prepareStatement("SELECT res.repository_id, r.title, r.publisher, r.source, rc.type, pids.pid, d.name, res.date, oids.orid, res.downloads, res.views FROM (SELECT us.repository_id, us.result_id, us.date, us.downloads, us.views FROM usage_stats us WHERE us.date>=? AND us.date<=? AND us.result_id=?) AS res JOIN public.result r ON res.result_id=r.id JOIN public.datasource d ON d.id=res.repository_id JOIN public.result_classifications rc ON rc.id=r.id LEFT JOIN (SELECT pids.id, string_agg(pids.pid, '#!#') AS pid FROM public.result_pids pids WHERE pids.id=? AND type='doi' GROUP BY pids.id) AS pids ON pids.id=r.id LEFT JOIN (SELECT oids.id, string_agg(oids.orid, '#!#') AS orid FROM public.result_oids oids WHERE oids.id=? GROUP BY oids.id) AS oids ON oids.id=r.id ORDER BY res.repository_id, res.date;"); -// st = connection.prepareStatement("SELECT distinct res.repository_id, r.title, r.publisher, r.source, rc.type, pids.pid, d.name, res.`date`, oids.oid, res.downloads, res.views " -// + "FROM (SELECT us.repository_id, us.result_id, us.`date`, us.downloads, us.views FROM " + usagestatsImpalaDB + ".usage_stats us " -// + "WHERE us.`date`>=? AND us.`date`<=? AND us.result_id=?) AS res " -// + "JOIN " + statsDB + ".result r ON res.result_id=r.id " -// + "JOIN " + statsDB + ".datasource d ON d.id=res.repository_id " -// + "JOIN (select id, group_concat(type,',') as type FROM " + statsDB + ".result_classifications where id=? " -// + "GROUP by id) rc ON rc.id=r.id " -// + "LEFT JOIN (SELECT pids.id, group_concat(pids.pid, '#!#') AS pid FROM " + statsDB + ".result_pids pids " -// + "WHERE pids.id=? AND type='Digital Object Identifier' GROUP BY pids.id) AS pids ON pids.id=r.id " -// + "LEFT JOIN (SELECT id, group_concat(oids.oid, '#!#') AS oid FROM " + statsDB + ".result_oids oids " -// + "WHERE oids.id=? GROUP BY oids.id) AS oids ON oids.id=r.id ORDER BY res.repository_id, res.`date`;"); -// st.setString(1, beginDateStr); -// st.setString(2, endDateStr); -// st.setString(3, openaire); -// //st.setString(4, beginDateStr); -// //st.setString(5, endDateStr); -// //st.setString(6, openaire); -// st.setString(4, openaire); -// st.setString(5, openaire); -// st.setString(6, openaire); -// } else { -// //st = connection.prepareStatement("SELECT res.repository_id, r.title, r.publisher, r.source, rc.type, pids.pid, d.name, res.ddate, oids.orid, res.downloads, res.views FROM (SELECT coalesce(ds.repository_id, vs.repository_id) AS repository_id, coalesce(ds.result_id, vs.result_id) AS result_id, coalesce(ds.date, vs.date) AS ddate, coalesce(ds.sum, 0) AS downloads, coalesce(vs.sum,0) AS views FROM (SELECT s.repository_id, s.result_id, s.date, sum(s.count) FROM public.downloads_stats s WHERE s.date>=? AND s.date<=? AND s.result_id=? GROUP BY s.repository_id, s.result_id, s.date) AS ds FULL OUTER JOIN (SELECT s.repository_id, s.result_id, s.date, sum(s.count) FROM public.views_stats s WHERE s.date>=? AND s.date<=? AND s.result_id=? GROUP BY s.repository_id, s.result_id, s.date) AS vs ON ds.result_id=vs.result_id AND ds.date=vs.date) AS res JOIN public.result r ON res.result_id=r.id JOIN public.datasource d ON d.id=res.repository_id JOIN public.result_classifications rc ON rc.id=r.id AND rc.type=? LEFT JOIN (SELECT pids.id, string_agg(pids.pid, '#!#') AS pid FROM public.result_pids pids WHERE pids.id=? AND type='doi' GROUP BY pids.id) AS pids ON pids.id=r.id LEFT JOIN (SELECT oids.id, string_agg(oids.orid, '#!#') AS orid FROM public.result_oids oids WHERE oids.id=? GROUP BY oids.id) AS oids ON oids.id=r.id ORDER BY res.repository_id, res.ddate;"); -// st = connection.prepareStatement("SELECT distinct res.repository_id, r.title, r.publisher, r.source, rc.type, pids.pid, d.name, res.`date`, oids.oid, res.downloads, " -// + "res.views FROM (SELECT us.repository_id, us.result_id, us.`date`, us.downloads, us.views FROM " + usagestatsImpalaDB + ".usage_stats us " -// + "WHERE us.`date`>=? AND us.`date`<=? AND us.result_id=?) AS res " -// + "JOIN " + statsDB + ".result r ON res.result_id=r.id " -// + "JOIN " + statsDB + ".datasource d ON d.id=res.repository_id " -// + "JOIN " + statsDB + ".result_classifications rc ON rc.id=r.id AND rc.type=? " -// + "LEFT JOIN (SELECT pids.id, group_concat(pids.pid, '#!#') AS pid " -// + "FROM " + statsDB + ".result_pids pids WHERE pids.id=? " -// + "AND type='Digital Object Identifier' GROUP BY pids.id) AS pids ON pids.id=r.id " -// + "LEFT JOIN (SELECT oids.id, group_concat(oids.oid, '#!#') AS oid " -// + "FROM " + statsDB + ".result_oids oids WHERE oids.id=? " -// + "GROUP BY oids.id) AS oids ON oids.id=r.id ORDER BY res.repository_id, res.`date`;"); -// st.setString(1, beginDateStr); -// st.setString(2, endDateStr); -// st.setString(3, openaire); -// //st.setString(4, beginDateStr); -// //st.setString(5, endDateStr); -// //st.setString(6, openaire); -// st.setString(4, itemDataType); -// st.setString(5, openaire); -// st.setString(6, openaire); -// } -// } else { -// if (itemDataType.equals("")) { -// //st = connection.prepareStatement("SELECT res.repository_id, r.title, r.publisher, r.source, rc.type, pids.pid, d.name, res.ddate, oids.orid, res.downloads, res.views FROM (SELECT coalesce(ds.repository_id, vs.repository_id) AS repository_id, coalesce(ds.result_id, vs.result_id) AS result_id, coalesce(ds.date, vs.date) AS ddate, coalesce(ds.sum, 0) AS downloads, coalesce(vs.sum,0) AS views FROM (SELECT s.repository_id, s.result_id, s.date, sum(s.count) FROM public.downloads_stats s WHERE s.date>=? AND s.date<=? AND s.result_id=? AND s.repository_id=? GROUP BY s.repository_id, s.result_id, s.date) AS ds FULL OUTER JOIN (SELECT s.repository_id, s.result_id, s.date, sum(s.count) FROM public.views_stats s WHERE s.date>=? AND s.date<=? AND s.result_id=? AND s.repository_id=? GROUP BY s.repository_id, s.result_id, s.date) AS vs ON ds.result_id=vs.result_id AND ds.date=vs.date) AS res JOIN public.result r ON res.result_id=r.id JOIN public.datasource d ON d.id=res.repository_id JOIN public.result_classifications rc ON rc.id=r.id LEFT JOIN (SELECT pids.id, string_agg(pids.pid, '#!#') AS pid FROM public.result_pids pids WHERE pids.id=? AND type='doi' GROUP BY pids.id) AS pids ON pids.id=r.id LEFT JOIN (SELECT oids.id, string_agg(oids.orid, '#!#') AS orid FROM public.result_oids oids WHERE oids.id=? GROUP BY oids.id) AS oids ON oids.id=r.id ORDER BY res.repository_id, res.ddate;"); -// st = connection.prepareStatement("SELECT distinct res.repository_id, r.title, r.publisher, r.source, rc.type, pids.pid, d.name, res.`date`, oids.oid, res.downloads, res.views " -// + "FROM (SELECT us.repository_id, us.result_id, us.`date`, us.downloads, us.views " -// + "FROM " + usagestatsImpalaDB + ".usage_stats us WHERE us.`date`>=? AND us.`date`<=? AND us.result_id=? AND us.repository_id=?) AS res " -// + "JOIN " + statsDB + ".result r ON res.result_id=r.id JOIN " + statsDB + ".datasource d ON d.id=res.repository_id " -// + "JOIN (select id, group_concat(type,',') as type from " + statsDB + ".result_classifications where id=? group by id) rc ON rc.id=r.id " -// + "LEFT JOIN (SELECT pids.id, group_concat(pids.pid, '#!#') AS pid FROM " + statsDB + ".result_pids pids " -// + "WHERE pids.id=? AND type='Digital Object Identifier' GROUP BY pids.id) AS pids ON pids.id=r.id " -// + "LEFT JOIN (SELECT oids.id, group_concat(oids.oid, '#!#') AS oid FROM " + statsDB + ".result_oids oids " -// + "WHERE oids.id=? GROUP BY oids.id) AS oids ON oids.id=r.id ORDER BY res.repository_id, res.`date`;"); -// st.setString(1, beginDateStr); -// st.setString(2, endDateStr); -// st.setString(3, openaire); -// st.setString(4, repositoryIdentifier); -// //st.setString(5, beginDateStr); -// //st.setString(6, endDateStr); -// //st.setString(7, openaire); -// //st.setString(8, repositoryIdentifier); -// st.setString(5, openaire); -// st.setString(6, openaire); -// st.setString(7, openaire); -// } else { -// //st = connection.prepareStatement("SELECT res.repository_id, r.title, r.publisher, r.source, rc.type, pids.pid, d.name, res.ddate, oids.orid, res.downloads, res.views FROM (SELECT coalesce(ds.repository_id, vs.repository_id) AS repository_id, coalesce(ds.result_id, vs.result_id) AS result_id, coalesce(ds.date, vs.date) AS ddate, coalesce(ds.sum, 0) AS downloads, coalesce(vs.sum,0) AS views FROM (SELECT s.repository_id, s.result_id, s.date, sum(s.count) FROM public.downloads_stats s WHERE s.date>=? AND s.date<=? AND s.result_id=? AND s.repository_id=? GROUP BY s.repository_id, s.result_id, s.date) AS ds FULL OUTER JOIN (SELECT s.repository_id, s.result_id, s.date, sum(s.count) FROM public.views_stats s WHERE s.date>=? AND s.date<=? AND s.result_id=? AND s.repository_id=? GROUP BY s.repository_id, s.result_id, s.date) AS vs ON ds.result_id=vs.result_id AND ds.date=vs.date) AS res JOIN public.result r ON res.result_id=r.id JOIN public.datasource d ON d.id=res.repository_id JOIN public.result_classifications rc ON rc.id=r.id AND rc.type=? LEFT JOIN (SELECT pids.id, string_agg(pids.pid, '#!#') AS pid FROM public.result_pids pids WHERE pids.id=? AND type='doi' GROUP BY pids.id) AS pids ON pids.id=r.id LEFT JOIN (SELECT oids.id, string_agg(oids.orid, '#!#') AS orid FROM public.result_oids oids WHERE oids.id=? GROUP BY oids.id) AS oids ON oids.id=r.id ORDER BY res.repository_id, res.ddate;"); -// st = connection.prepareStatement("SELECT distinct res.repository_id, r.title, r.publisher, r.source, rc.type, pids.pid, d.name, res.`date`, oids.oid, res.downloads,res.views " -// + "FROM (SELECT us.repository_id, us.result_id, us.`date`, us.downloads, us.views FROM " + usagestatsImpalaDB + ".usage_stats us " -// + "WHERE us.`date`>=? AND us.`date`<=? AND us.result_id=? AND us.repository_id=?) AS res " -// + "JOIN " + statsDB + ".result r ON res.result_id=r.id JOIN " + statsDB + ".datasource d ON d.id=res.repository_id " -// + "JOIN " + statsDB + ".result_classifications rc ON rc.id=r.id AND rc.type=?' " -// + "LEFT JOIN (SELECT pids.id, group_concat(pids.pid, '#!#') AS pid FROM " + statsDB + ".result_pids pids " -// + "WHERE pids.id=? AND type='Digital Object Identifier' GROUP BY pids.id) AS pids ON pids.id=r.id " -// + "LEFT JOIN (SELECT oids.id, group_concat(oids.oid, '#!#') AS oid " -// + "FROM " + statsDB + ".result_oids oids WHERE oids.id=? " -// + "GROUP BY oids.id) AS oids ON oids.id=r.id ORDER BY res.repository_id, res.`date`;"); -// st.setString(1, beginDateStr); -// st.setString(2, endDateStr); -// st.setString(3, openaire); -// st.setString(4, repositoryIdentifier); -// //st.setString(5, beginDateStr); -// //st.setString(6, endDateStr); -// //st.setString(7, openaire); -// //st.setString(8, repositoryIdentifier); -// st.setString(5, itemDataType); -// st.setString(6, openaire); -// st.setString(7, openaire); -// } -// } -// -// rs = st.executeQuery(); -// String repository = ""; -// String lastDate = ""; -// COUNTER_Platform_Usage reportItem = null; -// int ft_total = 0; -// int abstr = 0; -// -// if (granularity.equalsIgnoreCase("totals")) { -// while (rs.next()) { -// if (!rs.getString(1).equals(repository)) { -// if (reportItem != null) { -// reportItem.addPerformance(new COUNTER_Item_Performance(report_dateFormat.format(beginDate), report_dateFormat.format(endDate), Integer.toString(ft_total), Integer.toString(abstr))); -// reportItems.add(reportItem); -// } -// repository = rs.getString(1); -// reportItem = new COUNTER_Platform_Usage(rs.getString(3), rs.getString(7), rs.getString(5), rs.getString(2), ""); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OpenAIRE", openaire)); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("URLs", rs.getString(4))); -// if (rs.getString(9) != null && !rs.getString(9).equals("")) { -// if (rs.getString(9).contains("#!#")) { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OAI", rs.getString(9).substring(0, rs.getString(9).indexOf("#!#")))); -// } else { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OAI", rs.getString(9))); -// } -// } -// if (rs.getString(6) != null && !rs.getString(6).equals("")) { -// if (rs.getString(6).contains("#!#")) { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("DOI", rs.getString(6).substring(0, rs.getString(6).indexOf("#!#")))); -// } else { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("DOI", rs.getString(6))); -// } -// } -// ft_total = 0; -// abstr = 0; -// } -// ft_total += rs.getInt(10); -// abstr += rs.getInt(11); -// } -// if (reportItem != null) { -// reportItem.addPerformance(new COUNTER_Item_Performance(report_dateFormat.format(beginDate), report_dateFormat.format(endDate), Integer.toString(ft_total), Integer.toString(abstr))); -// reportItems.add(reportItem); -// } -// } else if (granularity.equalsIgnoreCase("monthly")) { -// Calendar endCal = Calendar.getInstance(); -// endCal.setTime(postgresFormat.parse(endDateStr)); -// endCal.add(Calendar.MONTH, 1); -// Date endDateForZeros = endCal.getTime(); -// while (rs.next()) { -// if (!rs.getString(1).equals(repository)) { -// if (reportItem != null) { -// fillWithZeros(postgresFormat.parse(lastDate), endDateForZeros, reportItem); -// reportItems.add(reportItem); -// } -// repository = rs.getString(1); -// lastDate = beginDateStr; -// reportItem = new COUNTER_Platform_Usage(rs.getString(3), rs.getString(7), rs.getString(5), rs.getString(2), ""); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OpenAIRE", openaire)); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("URLs", rs.getString(4))); -// if (rs.getString(9) != null && !rs.getString(9).equals("")) { -// if (rs.getString(9).contains("#!#")) { -// String allOAIs = rs.getString(9); -// String[] oaiArray = allOAIs.split("#!#"); -// for (int i = 0; i < oaiArray.length; i++) { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OAI", oaiArray[i])); -// } -// //reportItem.addIdentifier(new COUNTER_Item_Identifier("OAI", rs.getString(9).substring(0, rs.getString(9).indexOf("#!#")))); -// -// //reportItem.addIdentifier(new COUNTER_Item_Identifier("OAI", rs.getString(9).substring(0, rs.getString(9).indexOf("#!#")))); -// } else { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OAI", rs.getString(9))); -// } -// } -// if (rs.getString(6) != null && !rs.getString(6).equals("")) { -// if (rs.getString(6).contains("#!#")) { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("DOI", rs.getString(6).substring(0, rs.getString(6).indexOf("#!#")))); -// } else { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("DOI", rs.getString(6))); -// } -// } -// } -// fillWithZeros(postgresFormat.parse(lastDate), postgresFormat.parse(rs.getString(8)), reportItem); -// Calendar endC = Calendar.getInstance(); -// endC.setTime(postgresFormat.parse(rs.getString(8))); -// endC.set(Calendar.DATE, endC.getActualMaximum(Calendar.DATE)); -// if (reportItem != null) { -// reportItem.addPerformance(new COUNTER_Item_Performance(report_dateFormat.format(postgresFormat.parse(rs.getString(8))), report_dateFormat.format(endC.getTime()), rs.getString(10), rs.getString(11))); -// } -// endC.setTime(postgresFormat.parse(rs.getString(8))); -// endC.add(Calendar.MONTH, 1); -// lastDate = postgresFormat.format(endC.getTime()); -// } -// if (reportItem != null) { -// fillWithZeros(postgresFormat.parse(lastDate), endDateForZeros, reportItem); -// reportItems.add(reportItem); -// } -// } -// } catch (Exception e) { -// log.error("Single Item Report failed: ", e); -// } finally { -// DbUtils.closeQuietly(rs); -// DbUtils.closeQuietly(st); -// DbUtils.closeQuietly(connection); -// } -// } -// public void executeRepo(List reportItems, -// String repositoryIdentifier, String itemDataType, Date beginDate, -// Date endDate, String granularity) { -// SimpleDateFormat report_dateFormat = new SimpleDateFormat("yyyy-MM-dd"); -// SimpleDateFormat postgresFormat = new SimpleDateFormat("yyyy/MM"); -// String beginDateStr = postgresFormat.format(beginDate); -// String endDateStr = postgresFormat.format(endDate); -// -// Connection connection = null; -// PreparedStatement st = null; -// ResultSet rs = null; -// -// try { -// connection = usageStatsDB.getConnection(); -// -// if (repositoryIdentifier.equals("")) { -// if (itemDataType.equals("")) { -// //st = connection.prepareStatement("SELECT d.id, d.name, d.websiteurl, dois.orid, res.ddate, res.downloads, res.views FROM (SELECT coalesce(ds.source, vs.source), coalesce(ds.repository_id, vs.repository_id) AS repository_id, coalesce(ds.date, vs.date) AS ddate, coalesce(ds.sum, 0) AS downloads, coalesce(vs.sum,0) AS views FROM (SELECT s.source, s.repository_id, s.date, sum(s.count) FROM public.downloads_stats s WHERE s.date>=? AND s.date<=? GROUP BY s.source, s.repository_id, s.date) AS ds FULL OUTER JOIN (SELECT s.source, s.repository_id, s.date, sum(s.count) FROM public.views_stats s WHERE s.date>=? AND s.date<=? GROUP BY s.source, s.repository_id, s.date) AS vs ON ds.source=vs.source AND ds.repository_id=vs.repository_id AND ds.date=vs.date) AS res JOIN public.datasource d ON d.id=res.repository_id JOIN public.datasource_oids dois ON d.id=dois.id WHERE dois.orid LIKE 'opendoar%' ORDER BY d.id, d.name, res.ddate ASC;"); -// st = connection.prepareStatement("SELECT d.id, d.name, d.websiteurl, dois.oid, res.`date`, res.downloads, res.views " -// + "FROM (SELECT us.source, us.repository_id, us.`date`, sum(us.downloads) AS downloads, sum(us.views) AS views " -// + "FROM " + usagestatsImpalaDB + ".usage_stats us WHERE us.`date`>=? AND us.`date`<=? GROUP BY us.source, us.repository_id, us.`date`) " -// + "AS res JOIN " + statsDB + ".datasource d ON d.id=res.repository_id " -// + "JOIN " + statsDB + ".datasource_oids dois ON d.id=dois.id WHERE dois.oid " -// + "LIKE 'opendoar%' ORDER BY d.id, d.name, res.`date` ASC;"); -// st.setString(1, beginDateStr); -// st.setString(2, endDateStr); -// //st.setString(3, beginDateStr); -// //st.setString(4, endDateStr); -// } else { -// //st = connection.prepareStatement("SELECT d.id, d.name, d.websiteurl, dois.orid, res.ddate, res.downloads, res.views FROM (SELECT coalesce(ds.source, vs.source), coalesce(ds.repository_id, vs.repository_id) AS repository_id, coalesce(ds.date, vs.date) AS ddate, coalesce(ds.sum, 0) AS downloads, coalesce(vs.sum,0) AS views FROM (SELECT s.source, s.repository_id, s.date, sum(s.count) FROM public.downloads_stats s, result_classifications rc WHERE rc.id=s.result_id AND s.date>=? AND s.date<=? AND rc.type=? GROUP BY s.source, s.repository_id, s.date) AS ds FULL OUTER JOIN (SELECT s.source, s.repository_id, s.date, sum(s.count) FROM public.views_stats s, public.result_classifications rc WHERE rc.id=s.result_id AND s.date>=? AND s.date<=? AND rc.type=? GROUP BY s.source, s.repository_id, s.date) AS vs ON ds.source=vs.source AND ds.repository_id=vs.repository_id AND ds.date=vs.date) AS res JOIN public.datasource d ON d.id=res.repository_id JOIN public.datasource_oids dois ON d.id=dois.id WHERE dois.orid LIKE 'opendoar%' ORDER BY d.id, d.name, res.ddate ASC;"); -// st = connection.prepareStatement("SELECT d.id, d.name, d.websiteurl, dois.oid, res.`date`, res.downloads, res.views " -// + "FROM (SELECT us.source, us.repository_id, us.`date`, sum(us.downloads) AS downloads, sum(us.views) AS views " -// + "FROM " + usagestatsImpalaDB + ".usage_stats us, " + statsDB + ".result_classifications rc " -// + "WHERE rc.id=us.result_id AND us.`date`>=? AND us.`date`<=? AND rc.type=? " -// + "GROUP BY us.source, us.repository_id, us.`date`) AS res " -// + "JOIN " + statsDB + ".datasource d ON d.id=res.repository_id " -// + "JOIN " + statsDB + ".datasource_oids dois ON d.id=dois.id WHERE dois.oid LIKE 'opendoar%' " -// + "ORDER BY d.id, d.name, res.`date` ASC;"); -// st.setString(1, beginDateStr); -// st.setString(2, endDateStr); -// st.setString(3, itemDataType); -// //st.setString(4, beginDateStr); -// //st.setString(5, endDateStr); -// //st.setString(6, itemDataType); -// } -// } else { -// if (itemDataType.equals("")) { -// //st = connection.prepareStatement("SELECT d.id, d.name, d.websiteurl, dois.orid, res.ddate, res.downloads, res.views FROM (SELECT coalesce(ds.source, vs.source), coalesce(ds.repository_id, vs.repository_id) AS repository_id, coalesce(ds.date, vs.date) AS ddate, coalesce(ds.sum, 0) AS downloads, coalesce(vs.sum,0) AS views FROM (SELECT s.source, s.repository_id, s.date, sum(s.count) FROM public.downloads_stats s WHERE s.date>=? AND s.date<=? AND s.repository_id=? GROUP BY s.source, s.repository_id, s.date) AS ds FULL OUTER JOIN (SELECT s.source, s.repository_id, s.date, sum(s.count) FROM public.views_stats s WHERE s.date>=? AND s.date<=? AND s.repository_id=? GROUP BY s.source, s.repository_id, s.date) AS vs ON ds.source=vs.source AND ds.repository_id=vs.repository_id AND ds.date=vs.date) AS res JOIN public.datasource d ON d.id=res.repository_id JOIN public.datasource_oids dois ON d.id=dois.id WHERE dois.orid LIKE 'opendoar%' ORDER BY d.id, d.name, res.ddate ASC;"); -// st = connection.prepareStatement("SELECT d.id, d.name, d.websiteurl, dois.oid, res.`date`, res.downloads, res.views " -// + "FROM (SELECT us.source, us.repository_id, us.`date`, sum(us.downloads) AS downloads, sum(us.views) AS views " -// + "FROM " + usagestatsImpalaDB + ".usage_stats us WHERE us.`date`>=? AND us.`date`<=? AND us.repository_id=? " -// + "GROUP BY us.source, us.repository_id, us.`date`) AS res " -// + "JOIN " + statsDB + ".datasource d ON d.id=res.repository_id " -// + "JOIN " + statsDB + ".datasource_oids dois ON d.id=dois.id " -// + "WHERE dois.oid LIKE 'opendoar%' ORDER BY d.id, d.name, res.`date` ASC;"); -// st.setString(1, beginDateStr); -// st.setString(2, endDateStr); -// st.setString(3, repositoryIdentifier); -// //st.setString(4, beginDateStr); -// //st.setString(5, endDateStr); -// //st.setString(6, repositoryIdentifier); -// } else { -// //st = connection.prepareStatement("SELECT d.id, d.name, d.websiteurl, dois.orid, res.ddate, res.downloads, res.views FROM (SELECT coalesce(ds.source, vs.source), coalesce(ds.repository_id, vs.repository_id) AS repository_id, coalesce(ds.date, vs.date) AS ddate, coalesce(ds.sum, 0) AS downloads, coalesce(vs.sum,0) AS views FROM (SELECT s.source, s.repository_id, s.date, sum(s.count) FROM public.downloads_stats s, public.result_classifications rc WHERE rc.id=s.result_id AND s.date>=? AND s.date<=? AND rc.type=? AND s.repository_id=? GROUP BY s.source, s.repository_id, s.date) AS ds FULL OUTER JOIN (SELECT s.source, s.repository_id, s.date, sum(s.count) FROM public.views_stats s, public.result_classifications rc WHERE rc.id=s.result_id AND s.date>=? AND s.date<=? AND rc.type=? AND s.repository_id=? GROUP BY s.source, s.repository_id, s.date) AS vs ON ds.source=vs.source AND ds.repository_id=vs.repository_id AND ds.date=vs.date) AS res JOIN public.datasource d ON d.id=res.repository_id JOIN public.datasource_oids dois ON d.id=dois.id WHERE dois.orid LIKE 'opendoar%' ORDER BY d.id, d.name, res.ddate ASC;"); -// st = connection.prepareStatement("SELECT d.id, d.name, d.websiteurl, dois.oid, res.`date`, res.downloads, res.views " -// + "FROM (SELECT us.source, us.repository_id, us.`date`, sum(us.downloads) AS downloads, sum(us.views) AS views " -// + "FROM " + usagestatsImpalaDB + ".usage_stats us, " + statsDB + ".result_classifications rc " -// + "WHERE rc.id=us.result_id AND us.`date`>=? AND us.`date`<=? AND rc.type=? " -// + "AND us.repository_id=? GROUP BY us.source, us.repository_id, us.`date`) AS res " -// + "JOIN " + statsDB + ".datasource d ON d.id=res.repository_id " -// + "JOIN " + statsDB + ".datasource_oids dois ON d.id=dois.id " -// + "WHERE dois.oid LIKE 'opendoar%' ORDER BY d.id, d.name, res.`date` ASC;"); -// st.setString(1, beginDateStr); -// st.setString(2, endDateStr); -// st.setString(3, itemDataType); -// st.setString(4, repositoryIdentifier); -// //st.setString(5, beginDateStr); -// //st.setString(6, endDateStr); -// //st.setString(7, itemDataType); -// //st.setString(8, repositoryIdentifier); -// } -// } -// //log.error("RR STATEMENT: " + st); -// -// /* -// String redis_key = MD5(st.toString()); -// -// if (jedis.hasKey(redis_key, "result")) { -// reportItems.addAll(reportItemsFromJson((String) jedis.get(redis_key, "result"))); -// st.close(); -// connection.close(); -// return; -// } -// */ -// rs = st.executeQuery(); -// String repository = ""; -// String lastDate = ""; -// COUNTER_Platform_Usage reportItem = null; -// -// /* -// Calendar startCalendar = Calendar.getInstance(); -// startCalendar.setTime(beginDate); -// Calendar endCalendar = Calendar.getInstance(); -// endCalendar.setTime(endDate); -// */ -// int ft_total = 0; -// int abstr = 0; -// if (granularity.equalsIgnoreCase("totals")) { -// while (rs.next()) { -// if (!rs.getString(1).equals(repository)) { -// if (reportItem != null) { -// reportItem.addPerformance(new COUNTER_Item_Performance(report_dateFormat.format(beginDate), report_dateFormat.format(endDate), Integer.toString(ft_total), Integer.toString(abstr))); -// reportItems.add(reportItem); -// } -// repository = rs.getString(1); -// reportItem = new COUNTER_Platform_Usage(null, rs.getString(2), "Platform", null, ""); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OpenAIRE", rs.getString(1))); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OpenDOAR", rs.getString(4).substring(rs.getString(4).lastIndexOf(":") + 1))); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("URL", rs.getString(3))); -// ft_total = 0; -// abstr = 0; -// } -// ft_total += rs.getInt(6); -// abstr += rs.getInt(7); -// } -// if (reportItem != null) { -// reportItem.addPerformance(new COUNTER_Item_Performance(report_dateFormat.format(beginDate), report_dateFormat.format(endDate), Integer.toString(ft_total), Integer.toString(abstr))); -// reportItems.add(reportItem); -// } -// } else if (granularity.equalsIgnoreCase("monthly")) { -// Calendar endCal = Calendar.getInstance(); -// endCal.setTime(postgresFormat.parse(endDateStr)); -// endCal.add(Calendar.MONTH, 1); -// Date endDateForZeros = endCal.getTime(); -// while (rs.next()) { -// if (!rs.getString(1).equals(repository)) { -// if (reportItem != null) { -// fillWithZeros(postgresFormat.parse(lastDate), endDateForZeros, reportItem); -// reportItems.add(reportItem); -// } -// repository = rs.getString(1); -// lastDate = beginDateStr; -// reportItem = new COUNTER_Platform_Usage(null, rs.getString(2), "Platform", null, ""); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OpenAIRE", rs.getString(1))); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OpenDOAR", rs.getString(4).substring(rs.getString(4).lastIndexOf(":") + 1))); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("URL", rs.getString(3))); -// } -// fillWithZeros(postgresFormat.parse(lastDate), postgresFormat.parse(rs.getString(5)), reportItem); -// Calendar endC = Calendar.getInstance(); -// endC.setTime(postgresFormat.parse(rs.getString(5))); -// endC.set(Calendar.DATE, endC.getActualMaximum(Calendar.DATE)); -// if (reportItem != null) { -// reportItem.addPerformance(new COUNTER_Item_Performance(report_dateFormat.format(postgresFormat.parse(rs.getString(5))), report_dateFormat.format(endC.getTime()), rs.getString(6), rs.getString(7))); -// } -// endC.setTime(postgresFormat.parse(rs.getString(5))); -// endC.add(Calendar.MONTH, 1); -// lastDate = postgresFormat.format(endC.getTime()); -// } -// if (reportItem != null) { -// fillWithZeros(postgresFormat.parse(lastDate), endDateForZeros, reportItem); -// reportItems.add(reportItem); -// } -// } -// -// /* -// jedis.put(redis_key, "persistent", "false"); -// jedis.put(redis_key, "query", st.toString()); -// jedis.put(redis_key, "result", toJson(reportItems)); -// jedis.put(redis_key, "fetchMode", "3"); -// */ -// rs.close(); -// st.close(); -// connection.close(); -// } catch (Exception e) { -// log.error("Repository Report failed: ", e); -// } finally { -// DbUtils.closeQuietly(rs); -// DbUtils.closeQuietly(st); -// DbUtils.closeQuietly(connection); -// } -// } -// public void executeJournal(List reportItems, -// String repositoryIdentifier, String itemDataType, Date beginDate, -// Date endDate, String granularity) { -// SimpleDateFormat report_dateFormat = new SimpleDateFormat("yyyy-MM-dd"); -// SimpleDateFormat postgresFormat = new SimpleDateFormat("yyyy/MM"); -// String beginDateStr = postgresFormat.format(beginDate); -// String endDateStr = postgresFormat.format(endDate); -// -// Connection connection = null; -// PreparedStatement st = null; -// ResultSet rs = null; -// -// try { -// connection = usageStatsDB.getConnection(); -// -// if (repositoryIdentifier.equals("")) { -// if (itemDataType.equals("")) { -// //st = connection.prepareStatement("SELECT d.id, d.name, d.websiteurl, dois.orid, res.ddate, res.downloads, res.views FROM (SELECT coalesce(ds.source, vs.source), coalesce(ds.repository_id, vs.repository_id) AS repository_id, coalesce(ds.date, vs.date) AS ddate, coalesce(ds.sum, 0) AS downloads, coalesce(vs.sum,0) AS views FROM (SELECT s.source, s.repository_id, s.date, sum(s.count) FROM public.downloads_stats s WHERE s.date>=? AND s.date<=? GROUP BY s.source, s.repository_id, s.date) AS ds FULL OUTER JOIN (SELECT s.source, s.repository_id, s.date, sum(s.count) FROM public.views_stats s WHERE s.date>=? AND s.date<=? GROUP BY s.source, s.repository_id, s.date) AS vs ON ds.source=vs.source AND ds.repository_id=vs.repository_id AND ds.date=vs.date) AS res JOIN public.datasource d ON d.id=res.repository_id JOIN public.datasource_oids dois ON d.id=dois.id WHERE (d.type='Journal' OR d.type='Journal Aggregator/Publisher') ORDER BY d.id, d.name, res.ddate ASC;"); -// st = connection.prepareStatement("SELECT d.id, d.name, d.websiteurl, dois.oid, res.`date`, res.downloads, res.views " -// + "FROM (SELECT us.source, us.repository_id, us.`date`, sum(us.downloads) as downloads, sum(us.views) as views " -// + "FROM " + usagestatsImpalaDB + ".usage_stats us WHERE us.`date`>=? AND us.`date`<=? GROUP BY us.source, us.repository_id, us.`date`) AS res " -// + "JOIN " + statsDB + ".datasource d ON d.id=res.repository_id " -// + "JOIN " + statsDB + ".datasource_oids dois ON d.id=dois.id " -// + "WHERE (d.type='Journal' OR d.type='Journal Aggregator/Publisher') ORDER BY d.id, d.name, res.`date` ASC;"); -// st.setString(1, beginDateStr); -// st.setString(2, endDateStr); -// //st.setString(3, beginDateStr); -// //st.setString(4, endDateStr); -// } else { -// //st = connection.prepareStatement("SELECT d.id, d.name, d.websiteurl, dois.orid, res.ddate, res.downloads, res.views FROM (SELECT coalesce(ds.source, vs.source), coalesce(ds.repository_id, vs.repository_id) AS repository_id, coalesce(ds.date, vs.date) AS ddate, coalesce(ds.sum, 0) AS downloads, coalesce(vs.sum,0) AS views FROM (SELECT s.source, s.repository_id, s.date, sum(s.count) FROM public.downloads_stats s, public.result_classifications rc WHERE rc.id=s.result_id AND s.date>=? AND s.date<=? AND rc.type=? GROUP BY s.source, s.repository_id, s.date) AS ds FULL OUTER JOIN (SELECT s.source, s.repository_id, s.date, sum(s.count) FROM public.views_stats s, public.result_classifications rc WHERE rc.id=s.result_id AND s.date>=? AND s.date<=? AND rc.type=? GROUP BY s.source, s.repository_id, s.date) AS vs ON ds.source=vs.source AND ds.repository_id=vs.repository_id AND ds.date=vs.date) AS res JOIN public.datasource d ON d.id=res.repository_id JOIN public.datasource_oids dois ON d.id=dois.id WHERE (d.type='Journal' OR d.type='Journal Aggregator/Publisher') ORDER BY d.id, d.name, res.ddate ASC;"); -// st = connection.prepareStatement("SELECT d.id, d.name, d.websiteurl, dois.oid, res.`date`, res.downloads, res.views " -// + "FROM (SELECT us.source, us.repository_id, us.`date`, sum(us.downloads) as downloads, sum(us.views) as views " -// + "FROM " + usagestatsImpalaDB + ".usage_stats us, " + statsDB + ".result_classifications rc " -// + "WHERE rc.id=us.result_id AND us.`date`>=? AND us.`date`<=? AND rc.type=? " -// + "GROUP BY us.source, us.repository_id, us.`date`) AS res " -// + "JOIN " + statsDB + ".datasource d ON d.id=res.repository_id " -// + "JOIN " + statsDB + ".datasource_oids dois ON d.id=dois.id " -// + "WHERE (d.type='Journal' OR d.type='Journal Aggregator/Publisher') ORDER BY d.id, d.name, res.`date` ASC;"); -// st.setString(1, beginDateStr); -// st.setString(2, endDateStr); -// st.setString(3, itemDataType); -// //st.setString(4, beginDateStr); -// //st.setString(5, endDateStr); -// //st.setString(6, itemDataType); -// } -// } else { -// if (itemDataType.equals("")) { -// //st = connection.prepareStatement("SELECT d.id, d.name, d.websiteurl, dois.orid, res.ddate, res.downloads, res.views FROM (SELECT coalesce(ds.source, vs.source), coalesce(ds.repository_id, vs.repository_id) AS repository_id, coalesce(ds.date, vs.date) AS ddate, coalesce(ds.sum, 0) AS downloads, coalesce(vs.sum,0) AS views FROM (SELECT s.source, s.repository_id, s.date, sum(s.count) FROM public.downloads_stats s WHERE s.date>=? AND s.date<=? AND s.repository_id=? GROUP BY s.source, s.repository_id, s.date) AS ds FULL OUTER JOIN (SELECT s.source, s.repository_id, s.date, sum(s.count) FROM public.views_stats s WHERE s.date>=? AND s.date<=? AND s.repository_id=? GROUP BY s.source, s.repository_id, s.date) AS vs ON ds.source=vs.source AND ds.repository_id=vs.repository_id AND ds.date=vs.date) AS res JOIN public.datasource d ON d.id=res.repository_id JOIN public.datasource_oids dois ON d.id=dois.id WHERE (d.type='Journal' OR d.type='Journal Aggregator/Publisher') ORDER BY d.id, d.name, res.ddate ASC;"); -// st = connection.prepareStatement("SELECT d.id, d.name, d.websiteurl, dois.oid, res.`date`, res.downloads, res.views " -// + "FROM (SELECT us.source, us.repository_id, us.`date`, sum(us.downloads) as downloads, sum(us.views) as views " -// + "FROM " + usagestatsImpalaDB + ".usage_stats us WHERE us.`date`>=? AND us.`date`<=? AND us.repository_id=? " -// + "GROUP BY us.source, us.repository_id, us.`date`) AS res JOIN " + statsDB + ".datasource d ON d.id=res.repository_id " -// + "JOIN " + statsDB + ".datasource_oids dois ON d.id=dois.id " -// + "WHERE (d.type='Journal' OR d.type='Journal Aggregator/Publisher') ORDER BY d.id, d.name, res.`date` ASC;"); -// st.setString(1, beginDateStr); -// st.setString(2, endDateStr); -// st.setString(3, repositoryIdentifier); -// //st.setString(4, beginDateStr); -// //st.setString(5, endDateStr); -// //st.setString(6, repositoryIdentifier); -// } else { -// //st = connection.prepareStatement("SELECT d.id, d.name, d.websiteurl, dois.orid, res.ddate, res.downloads, res.views FROM (SELECT coalesce(ds.source, vs.source), coalesce(ds.repository_id, vs.repository_id) AS repository_id, coalesce(ds.date, vs.date) AS ddate, coalesce(ds.sum, 0) AS downloads, coalesce(vs.sum,0) AS views FROM (SELECT s.source, s.repository_id, s.date, sum(s.count) FROM public.downloads_stats s, public.result_classifications rc WHERE rc.id=s.result_id AND s.date>=? AND s.date<=? AND rc.type=? AND s.repository_id=? GROUP BY s.source, s.repository_id, s.date) AS ds FULL OUTER JOIN (SELECT s.source, s.repository_id, s.date, sum(s.count) FROM public.views_stats s, public.result_classifications rc WHERE rc.id=s.result_id AND s.date>=? AND s.date<=? AND rc.type=? AND s.repository_id=? GROUP BY s.source, s.repository_id, s.date) AS vs ON ds.source=vs.source AND ds.repository_id=vs.repository_id AND ds.date=vs.date) AS res JOIN public.datasource d ON d.id=res.repository_id JOIN public.datasource_oids dois ON d.id=dois.id WHERE (d.type='Journal' OR d.type='Journal Aggregator/Publisher') ORDER BY d.id, d.name, res.ddate ASC;"); -// st = connection.prepareStatement("SELECT d.id, d.name, d.websiteurl, dois.oid, res.`date`, res.downloads, res.views " -// + "FROM (SELECT us.source, us.repository_id, us.`date`, sum(us.downloads) as downloads, sum(us.views) as views " -// + "FROM " + usagestatsImpalaDB + ".usage_stats us, " + statsDB + ".result_classifications rc WHERE rc.id=us.result_id " -// + "AND us.`date`>=?' AND us.`date`<=? AND rc.type=? AND us.repository_id=? " -// + "GROUP BY us.source, us.repository_id, us.`date`) AS res " -// + "JOIN " + statsDB + ".datasource d ON d.id=res.repository_id " -// + "JOIN " + statsDB + ".datasource_oids dois ON d.id=dois.id " -// + "WHERE (d.type='Journal' OR d.type='Journal Aggregator/Publisher') ORDER BY d.id, d.name, res.`date` ASC;"); -// st.setString(1, beginDateStr); -// st.setString(2, endDateStr); -// st.setString(3, itemDataType); -// st.setString(4, repositoryIdentifier); -// //st.setString(5, beginDateStr); -// //st.setString(6, endDateStr); -// //st.setString(7, itemDataType); -// //st.setString(8, repositoryIdentifier); -// } -// } -// //log.error("RR STATEMENT: " + st); -// -// /* -// String redis_key = MD5(st.toString()); -// -// if (jedis.hasKey(redis_key, "result")) { -// reportItems.addAll(reportItemsFromJson((String) jedis.get(redis_key, "result"))); -// st.close(); -// connection.close(); -// return; -// } -// */ -// rs = st.executeQuery(); -// String repository = ""; -// String lastDate = ""; -// COUNTER_Platform_Usage reportItem = null; -// -// /* -// Calendar startCalendar = Calendar.getInstance(); -// startCalendar.setTime(beginDate); -// Calendar endCalendar = Calendar.getInstance(); -// endCalendar.setTime(endDate); -// */ -// int ft_total = 0; -// int abstr = 0; -// if (granularity.equalsIgnoreCase("totals")) { -// while (rs.next()) { -// if (!rs.getString(1).equals(repository)) { -// if (reportItem != null) { -// reportItem.addPerformance(new COUNTER_Item_Performance(report_dateFormat.format(beginDate), report_dateFormat.format(endDate), Integer.toString(ft_total), Integer.toString(abstr))); -// reportItems.add(reportItem); -// } -// repository = rs.getString(1); -// reportItem = new COUNTER_Platform_Usage(null, rs.getString(2), "Platform", null, ""); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OpenAIRE", rs.getString(1))); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("ISSN", rs.getString(4).substring(rs.getString(4).lastIndexOf(":") + 1))); -// if (rs.getString(3) != null) { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("URL", rs.getString(3))); -// } -// ft_total = 0; -// abstr = 0; -// } -// ft_total += rs.getInt(6); -// abstr += rs.getInt(7); -// } -// if (reportItem != null) { -// reportItem.addPerformance(new COUNTER_Item_Performance(report_dateFormat.format(beginDate), report_dateFormat.format(endDate), Integer.toString(ft_total), Integer.toString(abstr))); -// reportItems.add(reportItem); -// } -// } else if (granularity.equalsIgnoreCase("monthly")) { -// Calendar endCal = Calendar.getInstance(); -// endCal.setTime(postgresFormat.parse(endDateStr)); -// endCal.add(Calendar.MONTH, 1); -// Date endDateForZeros = endCal.getTime(); -// while (rs.next()) { -// if (!rs.getString(1).equals(repository)) { -// if (reportItem != null) { -// fillWithZeros(postgresFormat.parse(lastDate), endDateForZeros, reportItem); -// reportItems.add(reportItem); -// } -// repository = rs.getString(1); -// lastDate = beginDateStr; -// reportItem = new COUNTER_Platform_Usage(null, rs.getString(2), "Platform", null, ""); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OpenAIRE", rs.getString(1))); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("ISSN", rs.getString(4).substring(rs.getString(4).lastIndexOf(":") + 1))); -// if (rs.getString(3) != null) { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("URL", rs.getString(3))); -// } -// } -// fillWithZeros(postgresFormat.parse(lastDate), postgresFormat.parse(rs.getString(5)), reportItem); -// Calendar endC = Calendar.getInstance(); -// endC.setTime(postgresFormat.parse(rs.getString(5))); -// endC.set(Calendar.DATE, endC.getActualMaximum(Calendar.DATE)); -// if (reportItem != null) { -// reportItem.addPerformance(new COUNTER_Item_Performance(report_dateFormat.format(postgresFormat.parse(rs.getString(5))), report_dateFormat.format(endC.getTime()), rs.getString(6), rs.getString(7))); -// } -// endC.setTime(postgresFormat.parse(rs.getString(5))); -// endC.add(Calendar.MONTH, 1); -// lastDate = postgresFormat.format(endC.getTime()); -// } -// if (reportItem != null) { -// fillWithZeros(postgresFormat.parse(lastDate), endDateForZeros, reportItem); -// reportItems.add(reportItem); -// } -// } -// -// /* -// jedis.put(redis_key, "persistent", "false"); -// jedis.put(redis_key, "query", st.toString()); -// jedis.put(redis_key, "result", toJson(reportItems)); -// jedis.put(redis_key, "fetchMode", "3"); -// */ -// rs.close(); -// st.close(); -// connection.close(); -// } catch (Exception e) { -// log.error("Repository Report failed: ", e); -// } finally { -// DbUtils.closeQuietly(rs); -// DbUtils.closeQuietly(st); -// DbUtils.closeQuietly(connection); -// } -// } -// public void executeBatchItems(List reportItems, -// String repositoryIdentifier, String itemDataType, Date beginDate, -// Date endDate, String granularity) { -// SimpleDateFormat report_dateFormat = new SimpleDateFormat("yyyy-MM-dd"); -// SimpleDateFormat postgresFormat = new SimpleDateFormat("yyyy/MM"); -// String beginDateStr = postgresFormat.format(beginDate); -// String endDateStr = postgresFormat.format(endDate); -// -// Connection connection = null; -// PreparedStatement st = null; -// ResultSet rs = null; -// -// try { -// connection = usageStatsDB.getConnection(); -// -// if (itemDataType.equals("")) { -// //st = connection.prepareStatement("SELECT res.result_id, r.title, r.publisher, r.source, rc.type, pids.pid, d.name, res.ddate, oids.orid, res.downloads, res.views FROM (SELECT coalesce(ds.repository_id, vs.repository_id) AS repository_id, coalesce(ds.result_id, vs.result_id) AS result_id, coalesce(ds.date, vs.date) AS ddate, coalesce(ds.sum, 0) AS downloads, coalesce(vs.sum,0) AS views FROM (SELECT s.repository_id, s.result_id, s.date, sum(s.count) FROM public.downloads_stats s WHERE s.date>=? AND s.date<=? AND s.repository_id=? GROUP BY s.repository_id, s.result_id, s.date) AS ds FULL OUTER JOIN (SELECT s.repository_id, s.result_id, s.date, sum(s.count) FROM public.views_stats s WHERE s.date>=? AND s.date<=? AND s.repository_id=? GROUP BY s.repository_id, s.result_id, s.date) AS vs ON ds.result_id=vs.result_id AND ds.date=vs.date) AS res JOIN public.result r ON res.result_id=r.id JOIN public.datasource d ON d.id=res.repository_id JOIN public.result_classifications rc ON rc.id=r.id LEFT JOIN (SELECT pids.id, string_agg(pids.pid, '#!#') AS pid FROM public.result_pids pids, public.result_datasources rd WHERE rd.id=pids.id AND type='doi' AND rd.datasource=? GROUP BY pids.id) AS pids ON pids.id=r.id LEFT JOIN (SELECT oids.id, string_agg(oids.orid, '#!#') AS orid FROM public.result_oids oids, public.result_datasources rd WHERE rd.id=oids.id AND rd.datasource=? GROUP BY oids.id) AS oids ON oids.id=r.id ORDER BY res.result_id, res.ddate;"); -// //st = connection.prepareStatement("SELECT res.result_id, r.title, r.publisher, r.source, rc.type, pids.pid, d.name, res.date, oids.orid, res.downloads, res.views FROM (SELECT us.repository_id, us.result_id, us.date, sum(us.downloads) as downloads, sum(us.views) as views FROM public.usage_stats us WHERE us.date>=? AND us.date<=? AND us.repository_id=? GROUP BY us.repository_id, us.result_id, us.date) AS res JOIN public.result r ON res.result_id=r.id JOIN public.datasource d ON d.id=res.repository_id JOIN public.result_classifications rc ON rc.id=r.id LEFT JOIN (SELECT pids.id, string_agg(pids.pid, '#!#') AS pid FROM public.result_pids pids, public.result_datasources rd WHERE rd.id=pids.id AND type='doi' AND rd.datasource=? GROUP BY pids.id) AS pids ON pids.id=r.id LEFT JOIN (SELECT oids.id, string_agg(oids.orid, '#!#') AS orid FROM public.result_oids oids, public.result_datasources rd WHERE rd.id=oids.id AND rd.datasource=? GROUP BY oids.id) AS oids ON oids.id=r.id ORDER BY res.result_id, res.date;"); -// st = connection.prepareStatement("SELECT distinct res.result_id, r.title, r.publisher, r.source, rc.type, pids.pid, d.name, res.`date`, oids.oid, res.downloads, res.views " -// + "FROM (SELECT us.repository_id, us.result_id, us.`date`, sum(us.downloads) as downloads, sum(us.views) as views FROM " + usagestatsImpalaDB + ".usage_stats us " -// + "WHERE us.`date`>=? AND us.`date`<=? AND us.repository_id=? " -// + "GROUP BY us.repository_id, us.result_id, us.`date`) AS res JOIN " + statsDB + ".result r ON res.result_id=r.id " -// + "JOIN " + statsDB + ".datasource d ON d.id=res.repository_id " -// + "JOIN " + statsDB + ".result_classifications rc ON rc.id=r.id " -// + "LEFT JOIN (SELECT pids.id, group_concat(pids.pid, '#!#') AS pid " -// + "FROM " + statsDB + ".result_pids pids, " + statsDB + ".result_datasources rd " -// + "WHERE rd.id=pids.id AND type='Digital Object Identifier' AND rd.datasource=? " -// + "GROUP BY pids.id) AS pids ON pids.id=r.id " -// + "LEFT JOIN (SELECT oids.id, group_concat(oids.oid, '#!#') AS oid " -// + "FROM " + statsDB + ".result_oids oids, " + statsDB + ".result_datasources rd " -// + "WHERE rd.id=oids.id AND rd.datasource=? GROUP BY oids.id) " -// + "AS oids ON oids.id=r.id ORDER BY res.result_id, res.`date`;"); -// st.setString(1, beginDateStr); -// st.setString(2, endDateStr); -// st.setString(3, repositoryIdentifier); -// //st.setString(4, beginDateStr); -// //st.setString(5, endDateStr); -// //st.setString(6, repositoryIdentifier); -// st.setString(4, repositoryIdentifier); -// st.setString(5, repositoryIdentifier); -// } else { -// //st = connection.prepareStatement("SELECT res.result_id, r.title, r.publisher, r.source, rc.type, pids.pid, d.name, res.ddate, oids.orid, res.downloads, res.views FROM (SELECT coalesce(ds.repository_id, vs.repository_id) AS repository_id, coalesce(ds.result_id, vs.result_id) AS result_id, coalesce(ds.date, vs.date) AS ddate, coalesce(ds.sum, 0) AS downloads, coalesce(vs.sum,0) AS views FROM (SELECT s.repository_id, s.result_id, s.date, sum(s.count) FROM public.downloads_stats s WHERE s.date>=? AND s.date<=? AND s.repository_id=? GROUP BY s.repository_id, s.result_id, s.date) AS ds FULL OUTER JOIN (SELECT s.repository_id, s.result_id, s.date, sum(s.count) FROM public.views_stats s WHERE s.date>=? AND s.date<=? AND s.repository_id=? GROUP BY s.repository_id, s.result_id, s.date) AS vs ON ds.result_id=vs.result_id AND ds.date=vs.date) AS res JOIN public.result r ON res.result_id=r.id JOIN public.datasource d ON d.id=res.repository_id JOIN public.result_classifications rc ON rc.id=r.id LEFT JOIN (SELECT pids.id, string_agg(pids.pid, '#!#') AS pid FROM public.result_pids pids, result_datasources rd WHERE rd.id=pids.id AND type='doi' AND rd.datasource=? GROUP BY pids.id) AS pids ON pids.id=r.id LEFT JOIN (SELECT oids.id, string_agg(oids.orid, '#!#') AS orid FROM public.result_oids oids, public.result_datasources rd WHERE rd.id=oids.id AND rd.datasource=? GROUP BY oids.id) AS oids ON oids.id=r.id WHERE rc.type=? ORDER BY res.result_id, res.ddate;"); -// st = connection.prepareStatement("SELECT distinct res.result_id, r.title, r.publisher, r.source, rc.type, pids.pid, d.name, res.`date`, oids.oid, res.downloads, res.views " -// + "FROM (SELECT us.repository_id, us.result_id, us.`date`, sum(us.downloads) as downloads, sum(us.views) as views " -// + "FROM " + usagestatsImpalaDB + ".usage_stats us WHERE us.`date`>=? AND us.`date`<=? AND us.repository_id=? " -// + "GROUP BY us.repository_id, us.result_id, us.`date`) AS res " -// + "JOIN " + statsDB + ".result r ON res.result_id=r.id JOIN " + statsDB + ".datasource d ON d.id=res.repository_id " -// + "JOIN " + statsDB + ".result_classifications rc ON rc.id=r.id " -// + "LEFT JOIN (SELECT pids.id, group_concat(pids.pid, '#!#') AS pid " -// + "FROM " + statsDB + ".result_pids pids, " + statsDB + ".result_datasources rd " -// + "WHERE rd.id=pids.id AND type='Digital Object Identifier' " -// + "AND rd.datasource=? GROUP BY pids.id) AS pids ON pids.id=r.id " -// + "LEFT JOIN (SELECT oids.id, group_concat(oids.oid, '#!#') AS oid " -// + "FROM " + statsDB + ".result_oids oids, " + statsDB + ".result_datasources rd " -// + "WHERE rd.id=oids.id AND rd.datasource=? GROUP BY oids.id) AS oids ON oids.id=r.id " -// + "WHERE rc.type=? ORDER BY res.result_id, res.`date`;"); -// st.setString(1, beginDateStr); -// st.setString(2, endDateStr); -// st.setString(3, repositoryIdentifier); -// //st.setString(4, beginDateStr); -// //st.setString(5, endDateStr); -// //st.setString(6, repositoryIdentifier); -// st.setString(4, repositoryIdentifier); -// st.setString(5, repositoryIdentifier); -// st.setString(6, itemDataType); -// } -// //log.error("IR STATEMENT: " + st); -// -// /* -// String redis_key = MD5(st.toString()); -// -// if (jedis.hasKey(redis_key, "result")) { -// reportItems.addAll(reportItemsFromJson((String) jedis.get(redis_key, "result"))); -// st.close(); -// connection.close(); -// return; -// } -// */ -// rs = st.executeQuery(); -// String result = ""; -// String lastDate = ""; -// COUNTER_Platform_Usage reportItem = null; -// -// int ft_total = 0; -// int abstr = 0; -// if (granularity.equalsIgnoreCase("totals")) { -// while (rs.next()) { -// if (!rs.getString(1).equals(result)) { -// if (reportItem != null) { -// reportItem.addPerformance(new COUNTER_Item_Performance(report_dateFormat.format(beginDate), report_dateFormat.format(endDate), Integer.toString(ft_total), Integer.toString(abstr))); -// reportItems.add(reportItem); -// } -// result = rs.getString(1); -// reportItem = new COUNTER_Platform_Usage(rs.getString(3), rs.getString(7), rs.getString(5), rs.getString(2), ""); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OpenAIRE", rs.getString(1))); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("URLs", rs.getString(4))); -// if (rs.getString(9) != null && !rs.getString(9).equals("")) { -// if (rs.getString(9).contains("#!#")) { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OAI", rs.getString(9).substring(0, rs.getString(9).indexOf("#!#")))); -// } else { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OAI", rs.getString(9))); -// } -// } -// if (rs.getString(6) != null && !rs.getString(6).equals("")) { -// if (rs.getString(6).contains("#!#")) { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("DOI", rs.getString(6).substring(0, rs.getString(6).indexOf("#!#")))); -// } else { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("DOI", rs.getString(6))); -// } -// } -// ft_total = 0; -// abstr = 0; -// } -// ft_total += rs.getInt(10); -// abstr += rs.getInt(11); -// } -// if (reportItem != null) { -// reportItem.addPerformance(new COUNTER_Item_Performance(report_dateFormat.format(beginDate), report_dateFormat.format(endDate), Integer.toString(ft_total), Integer.toString(abstr))); -// reportItems.add(reportItem); -// } -// } else if (granularity.equalsIgnoreCase("monthly")) { -// Calendar endCal = Calendar.getInstance(); -// endCal.setTime(postgresFormat.parse(endDateStr)); -// endCal.add(Calendar.MONTH, 1); -// Date endDateForZeros = endCal.getTime(); -// while (rs.next()) { -// if (!rs.getString(1).equals(result)) { -// if (reportItem != null) { -// fillWithZeros(postgresFormat.parse(lastDate), endDateForZeros, reportItem); -// reportItems.add(reportItem); -// } -// result = rs.getString(1); -// lastDate = beginDateStr; -// reportItem = new COUNTER_Platform_Usage(rs.getString(3), rs.getString(7), rs.getString(5), rs.getString(2), ""); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OpenAIRE", rs.getString(1))); -// reportItem.addIdentifier(new COUNTER_Item_Identifier("URLs", rs.getString(4))); -// if (rs.getString(9) != null && !rs.getString(9).equals("")) { -// if (rs.getString(9).contains("#!#")) { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OAI", rs.getString(9).substring(0, rs.getString(9).indexOf("#!#")))); -// } else { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("OAI", rs.getString(9))); -// } -// } -// if (rs.getString(6) != null && !rs.getString(6).equals("")) { -// if (rs.getString(6).contains("#!#")) { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("DOI", rs.getString(6).substring(0, rs.getString(6).indexOf("#!#")))); -// } else { -// reportItem.addIdentifier(new COUNTER_Item_Identifier("DOI", rs.getString(6))); -// } -// } -// } -// fillWithZeros(postgresFormat.parse(lastDate), postgresFormat.parse(rs.getString(8)), reportItem); -// Calendar endC = Calendar.getInstance(); -// endC.setTime(postgresFormat.parse(rs.getString(8))); -// endC.set(Calendar.DATE, endC.getActualMaximum(Calendar.DATE)); -// if (reportItem != null) { -// reportItem.addPerformance(new COUNTER_Item_Performance(report_dateFormat.format(postgresFormat.parse(rs.getString(8))), report_dateFormat.format(endC.getTime()), rs.getString(10), rs.getString(11))); -// } -// endC.setTime(postgresFormat.parse(rs.getString(8))); -// endC.add(Calendar.MONTH, 1); -// lastDate = postgresFormat.format(endC.getTime()); -// } -// if (reportItem != null) { -// fillWithZeros(postgresFormat.parse(lastDate), endDateForZeros, reportItem); -// reportItems.add(reportItem); -// } -// } -// -// /* -// jedis.put(redis_key, "persistent", "false"); -// jedis.put(redis_key, "query", st.toString()); -// jedis.put(redis_key, "result", toJson(reportItems)); -// jedis.put(redis_key, "fetchMode", "3"); -// */ -// } catch (Exception e) { -// log.error("Batch Item Report failed: ", e); -// } finally { -// DbUtils.closeQuietly(rs); -// DbUtils.closeQuietly(st); -// DbUtils.closeQuietly(connection); -// } -// } public void executeBatchItemsPR(List reportItems, String repositoryIdentifier, Date beginDate, @@ -1930,6 +1160,27 @@ public class UsageStatsRepository { + statsDB + ".result_oids ro, tpd " + "WHERE us.`date`>=? AND us.`date`<=? AND us.repository_id=? AND rc.id=us.result_id AND us.result_id=rs.id AND ro.id=us.result_id AND tpd.id=us.result_id " + "GROUP BY rc.type, rs.title, us.result_id, rs.title, rs.year order by rc.type ASC;"); +//WITH tpd as (select distinct id, concat(type,'#-#',pid) type_id from openaire_prod_stats.result_pids) +//select type, downloads, views, resultid, item,yop,group_concat(distinct tpd.type_id,'#!#') as oid, uniquedownloads,uniqueviews +//FROM (SELECT us.repository_id repo, rc.type type, sum(us.downloads) as downloads, sum(us.views) as views, +//us.result_id as resultid, rs.title as item, rs.year as yop, +//count(case when us.downloads >0 then 1 else null end) as uniquedownloads, count(case when us.views >0 then 1 else null end) as uniqueviews +//FROM openaire_prod_usage_stats.usage_stats us,(select distinct id, type from openaire_prod_stats.result_classifications) rc, openaire_prod_stats.result rs +//WHERE us.`date`>='2020/01' AND us.`date`<='2020/02' +//AND rc.id=us.result_id AND us.result_id=rs.id AND us.repository_id='opendoar____::8e98d81f8217304975ccb23337bb5761' +//GROUP BY rc.type, rs.title, us.result_id, rs.title, rs.year, us.repository_id) tmp1, tpd +//where tpd.id=resultid +//group by repo,type,resultid,item,yop,downloads,views,uniquedownloads,uniqueviews + +//SELECT 'Dataset' as type, sum(case when dp.metric_type='total-dataset-requests' then count else 0 end) as downloads, +//sum(case when dp.metric_type='total-dataset-investigations' then count else 0 end) as views, +//id as resultid,dp.ds_title as item, dp.yop as yop, concat('Digital Object Identifier#-#',dp.ds_type) as oid, +//sum(case when dp.metric_type='unique-dataset-requests' then count else 0 end) as uniquedownloads, +//sum(case when dp.metric_type='unique-dataset-investigations' then count else 0 end) as uniqueviews, +//dp.access_method access_method,dp.platform +//FROM datasetsusagestats_20210312a.datasetsperformance dp, openaire_prod_stats.result_pids +//WHERE dp.period_from>='2020-01-01' AND dp.period_end<='2020-12-01' and pid=ds_type +//GROUP BY dp.ds_title, dp.yop, dp.platform, dp.access_method, dp.ds_type,id st.setString(1, beginDateStr); st.setString(2, endDateStr); @@ -1975,7 +1226,17 @@ public class UsageStatsRepository { + "WHERE us.`date`>=? AND us.`date`<=? AND us.repository_id=? AND rc.type=? AND rc.id=us.result_id " + "AND us.result_id=rs.id AND ro.id=us.result_id AND tpd.id=us.result_id " + "GROUP BY ro.id, rc.type, rs.title, us.result_id, rs.year order by rc.type ASC;"); - +//WITH tpd as (select distinct id, concat(type,'#-#',pid) type_id from openaire_prod_stats.result_pids) +//select type, downloads, views, resultid, item,yop,group_concat(distinct tpd.type_id,'#!#') as oid, uniquedownloads,uniqueviews +//FROM (SELECT us.repository_id repo, us.`date` d1,rc.type type, sum(us.downloads) as downloads, sum(us.views) as views, +//us.result_id as resultid, rs.title as item, rs.year as yop, +//count(case when us.downloads >0 then 1 else null end) as uniquedownloads, count(case when us.views >0 then 1 else null end) as uniqueviews +//FROM openaire_prod_usage_stats.usage_stats us,(select distinct id, type from openaire_prod_stats.result_classifications) rc, openaire_prod_stats.result rs +//WHERE us.`date`>='2020/01' AND us.`date`<='2020/02' +//AND rc.id=us.result_id AND us.result_id=rs.id AND us.repository_id='opendoar____::8e98d81f8217304975ccb23337bb5761' +//GROUP BY us.`date`,rc.type, rs.title, us.result_id, rs.title, rs.year, us.repository_id) tmp1, tpd +//where tpd.id=resultid and type='Article' +//group by repo,d1, type,resultid,item,yop,downloads,views,uniquedownloads,uniqueviews st.setString(1, beginDateStr); st.setString(2, endDateStr); st.setString(3, repositoryIdentifier); @@ -2023,6 +1284,28 @@ public class UsageStatsRepository { + "WHERE us.`date`>=? AND us.`date`<=? AND us.repository_id=? AND rc.id=us.result_id AND us.result_id=rs.id AND ro.id=us.result_id " + "AND tpd.id=us.result_id " + "GROUP BY ro.id, rc.type, rs.title, us.result_id, us.`date`, rs.year order by rc.type, us.`date` ASC;"); + +//WITH tpd as (select distinct id, concat(type,'#-#',pid) type_id from openaire_prod_stats.result_pids) +//select type, `date`,downloads, views, resultid, item,yop,group_concat(distinct tpd.type_id,'#!#') as oid, uniquedownloads,uniqueviews +//FROM (SELECT us.repository_id repo, us.`date` `date`,rc.type type, sum(us.downloads) as downloads, sum(us.views) as views, +//us.result_id as resultid, rs.title as item, rs.year as yop, +//count(case when us.downloads >0 then 1 else null end) as uniquedownloads, count(case when us.views >0 then 1 else null end) as uniqueviews +//FROM openaire_prod_usage_stats.usage_stats us,(select distinct id, type from openaire_prod_stats.result_classifications) rc, openaire_prod_stats.result rs +//WHERE us.`date`>='2020/01' AND us.`date`<='2020/02' +//AND rc.id=us.result_id AND us.result_id=rs.id AND us.repository_id='opendoar____::8e98d81f8217304975ccb23337bb5761' +//GROUP BY us.`date`,rc.type, rs.title, us.result_id, rs.title, rs.year, us.repository_id) tmp1, tpd +//where tpd.id=resultid group by repo,`date`, type,resultid,item,yop,downloads,views,uniquedownloads,uniqueviews + +//SELECT 'Dataset' as type,dp.period_end, sum(case when dp.metric_type='total-dataset-requests' then count else 0 end) as downloads, +//sum(case when dp.metric_type='total-dataset-investigations' then count else 0 end) as views, +//id as resultid,dp.ds_title as item, dp.yop as yop, concat('Digital Object Identifier#-#',dp.ds_type) as oid, +//sum(case when dp.metric_type='unique-dataset-requests' then count else 0 end) as uniquedownloads, +//sum(case when dp.metric_type='unique-dataset-investigations' then count else 0 end) as uniqueviews, +//dp.access_method access_method,dp.platform +//FROM datasetsusagestats_20210312a.datasetsperformance dp, openaire_prod_stats.result_pids +//WHERE dp.period_from>='2020-01-01' AND dp.period_end<='2020-12-01' and pid=ds_type +//GROUP BY dp.period_end,dp.ds_title, dp.yop, dp.platform, dp.access_method, dp.ds_type,id + st.setString(1, beginDateStr); st.setString(2, endDateStr); st.setString(3, repositoryIdentifier); @@ -2091,6 +1374,27 @@ public class UsageStatsRepository { + "WHERE us.`date`>=? AND us.`date`<=? AND us.repository_id=? AND rc.type=? AND rc.id=us.result_id " + "AND us.result_id=rs.id AND ro.id=us.result_id AND tpd.id=us.result_id " + "GROUP BY ro.id, rc.type, rs.title, us.result_id, us.`date`, rs.year order by rc.type, us.`date` ASC;"); + +//WITH tpd as (select distinct id, concat(type,'#-#',pid) type_id from openaire_prod_stats.result_pids) +//select type, `date`,downloads, views, resultid, item,yop,group_concat(distinct tpd.type_id,'#!#') as oid, uniquedownloads,uniqueviews +//FROM (SELECT us.repository_id repo, us.`date` `date`,rc.type type, sum(us.downloads) as downloads, sum(us.views) as views, +//us.result_id as resultid, rs.title as item, rs.year as yop, +//count(case when us.downloads >0 then 1 else null end) as uniquedownloads, count(case when us.views >0 then 1 else null end) as uniqueviews +//FROM openaire_prod_usage_stats.usage_stats us,(select distinct id, type from openaire_prod_stats.result_classifications) rc, openaire_prod_stats.result rs +//WHERE us.`date`>='2020/01' AND us.`date`<='2020/02' +//AND rc.id=us.result_id AND us.result_id=rs.id AND us.repository_id='opendoar____::8e98d81f8217304975ccb23337bb5761' AND rc.type=? +//GROUP BY us.`date`,rc.type, rs.title, us.result_id, rs.title, rs.year, us.repository_id) tmp1, tpd +//where tpd.id=resultid group by repo,`date`, type,resultid,item,yop,downloads,views,uniquedownloads,uniqueviews + +//SELECT 'Dataset' as type,dp.period_end, sum(case when dp.metric_type='total-dataset-requests' then count else 0 end) as downloads, +//sum(case when dp.metric_type='total-dataset-investigations' then count else 0 end) as views, +//id as resultid,dp.ds_title as item, dp.yop as yop, concat('Digital Object Identifier#-#',dp.ds_type) as oid, +//sum(case when dp.metric_type='unique-dataset-requests' then count else 0 end) as uniquedownloads, +//sum(case when dp.metric_type='unique-dataset-investigations' then count else 0 end) as uniqueviews, +//dp.access_method access_method,dp.platform +//FROM datasetsusagestats_20210312a.datasetsperformance dp, openaire_prod_stats.result_pids +//WHERE dp.period_from>='2020-01-01' AND dp.period_end<='2020-12-01' and pid=ds_type +//GROUP BY dp.period_end,dp.ds_title, dp.yop, dp.platform, dp.access_method, dp.ds_type,id st.setString(1, beginDateStr); st.setString(2, endDateStr); st.setString(3, repositoryIdentifier); @@ -2188,7 +1492,27 @@ public class UsageStatsRepository { + statsDB + ".result_oids ro, tpd " + "WHERE us.`date`>=? AND us.`date`<=? AND us.repository_id=? AND us.result_id=? AND rc.id=us.result_id AND us.result_id=rs.id AND ro.id=us.result_id AND tpd.id=us.result_id " + "GROUP BY rc.type, rs.title, us.result_id, rs.title, rs.year order by rc.type ASC;"); +//WITH tpd as (select distinct id, concat(type,'#-#',pid) type_id from openaire_prod_stats.result_pids) +//select type, downloads, views, resultid, item,yop,group_concat(distinct tpd.type_id,'#!#') as oid, uniquedownloads,uniqueviews +//FROM (SELECT us.repository_id repo, rc.type type, sum(us.downloads) as downloads, sum(us.views) as views, +//us.result_id as resultid, rs.title as item, rs.year as yop, +//count(case when us.downloads >0 then 1 else null end) as uniquedownloads, count(case when us.views >0 then 1 else null end) as uniqueviews +//FROM openaire_prod_usage_stats.usage_stats us,(select distinct id, type from openaire_prod_stats.result_classifications) rc, openaire_prod_stats.result rs +//WHERE us.`date`>='2020/01' AND us.`date`<='2020/02' +//AND rc.id=us.result_id AND us.result_id=rs.id AND us.repository_id='opendoar____::8e98d81f8217304975ccb23337bb5761' AND us.result_id=? +//GROUP BY rc.type, rs.title, us.result_id, rs.title, rs.year, us.repository_id) tmp1, tpd +//where tpd.id=resultid +//group by repo,type,resultid,item,yop,downloads,views,uniquedownloads,uniqueviews +//SELECT 'Dataset' as type, sum(case when dp.metric_type='total-dataset-requests' then count else 0 end) as downloads, +//sum(case when dp.metric_type='total-dataset-investigations' then count else 0 end) as views, +//id as resultid,dp.ds_title as item, dp.yop as yop, concat('Digital Object Identifier#-#',dp.ds_type) as oid, +//sum(case when dp.metric_type='unique-dataset-requests' then count else 0 end) as uniquedownloads, +//sum(case when dp.metric_type='unique-dataset-investigations' then count else 0 end) as uniqueviews, +//dp.access_method access_method,dp.platform +//FROM datasetsusagestats_20210312a.datasetsperformance dp, openaire_prod_stats.result_pids +//WHERE dp.period_from>='2020-01-01' AND dp.period_end<='2020-12-01' and pid=ds_type AND ds_type=? +//GROUP BY dp.ds_title, dp.yop, dp.platform, dp.access_method, dp.ds_type,id st.setString(1, beginDateStr); st.setString(2, endDateStr); st.setString(3, repositoryIdentifier); @@ -2232,7 +1556,26 @@ public class UsageStatsRepository { + "WHERE us.`date`>=? AND us.`date`<=? AND us.repository_id=? AND us.result_id=? AND rc.type=? AND rc.id=us.result_id " + "AND us.result_id=rs.id AND ro.id=us.result_id AND tpd.id=us.result_id " + "GROUP BY ro.id, rc.type, rs.title, us.result_id, rs.year order by rc.type ASC;"); +//WITH tpd as (select distinct id, concat(type,'#-#',pid) type_id from openaire_prod_stats.result_pids) +//select type, downloads, views, resultid, item,yop,group_concat(distinct tpd.type_id,'#!#') as oid, uniquedownloads,uniqueviews +//FROM (SELECT us.repository_id repo, us.`date` `date`,rc.type type, sum(us.downloads) as downloads, sum(us.views) as views, +//us.result_id as resultid, rs.title as item, rs.year as yop, +//count(case when us.downloads >0 then 1 else null end) as uniquedownloads, count(case when us.views >0 then 1 else null end) as uniqueviews +//FROM openaire_prod_usage_stats.usage_stats us,(select distinct id, type from openaire_prod_stats.result_classifications) rc, openaire_prod_stats.result rs +//WHERE us.`date`>='2020/01' AND us.`date`<='2020/02' +//AND rc.id=us.result_id AND us.result_id=rs.id AND us.repository_id='opendoar____::8e98d81f8217304975ccb23337bb5761' AND us.result_id=? AND rc.type=? +//GROUP BY rc.type, rs.title, us.result_id, rs.title, rs.year, us.repository_id) tmp1, tpd +//where tpd.id=resultid group by repo, type,resultid,item,yop,downloads,views,uniquedownloads,uniqueviews +//SELECT 'Dataset' as type, sum(case when dp.metric_type='total-dataset-requests' then count else 0 end) as downloads, +//sum(case when dp.metric_type='total-dataset-investigations' then count else 0 end) as views, +//id as resultid,dp.ds_title as item, dp.yop as yop, concat('Digital Object Identifier#-#',dp.ds_type) as oid, +//sum(case when dp.metric_type='unique-dataset-requests' then count else 0 end) as uniquedownloads, +//sum(case when dp.metric_type='unique-dataset-investigations' then count else 0 end) as uniqueviews, +//dp.access_method access_method,dp.platform +//FROM datasetsusagestats_20210312a.datasetsperformance dp, openaire_prod_stats.result_pids +//WHERE dp.period_from>='2020-01-01' AND dp.period_end<='2020-12-01' and pid=ds_type and dp.ds_type=? +//GROUP BY dp.ds_title, dp.yop, dp.platform, dp.access_method, dp.ds_type,id st.setString(1, beginDateStr); st.setString(2, endDateStr); st.setString(3, repositoryIdentifier); @@ -2274,6 +1617,26 @@ public class UsageStatsRepository { + "WHERE us.`date`>=? AND us.`date`<=? AND us.repository_id=? AND us.result_id=? AND rc.id=us.result_id AND us.result_id=rs.id AND ro.id=us.result_id " + "AND tpd.id=us.result_id " + "GROUP BY ro.id, rc.type, rs.title, us.result_id, us.`date`, rs.year order by rc.type, us.`date` ASC;"); +//WITH tpd as (select distinct id, concat(type,'#-#',pid) type_id from openaire_prod_stats.result_pids) +//select type, `date`,downloads, views, resultid, item,yop,group_concat(distinct tpd.type_id,'#!#') as oid, uniquedownloads,uniqueviews +//FROM (SELECT us.repository_id repo, us.`date` `date`,rc.type type, sum(us.downloads) as downloads, sum(us.views) as views, +//us.result_id as resultid, rs.title as item, rs.year as yop, +//count(case when us.downloads >0 then 1 else null end) as uniquedownloads, count(case when us.views >0 then 1 else null end) as uniqueviews +//FROM openaire_prod_usage_stats.usage_stats us,(select distinct id, type from openaire_prod_stats.result_classifications) rc, openaire_prod_stats.result rs +//WHERE us.`date`>='2020/01' AND us.`date`<='2020/02' +//AND rc.id=us.result_id AND us.result_id=rs.id AND us.repository_id='opendoar____::8e98d81f8217304975ccb23337bb5761' AND us.result_id=? +//GROUP BY us.`date`,rc.type, rs.title, us.result_id, rs.title, rs.year, us.repository_id) tmp1, tpd +//where tpd.id=resultid group by repo,`date`, type,resultid,item,yop,downloads,views,uniquedownloads,uniqueviews + +//SELECT 'Dataset' as type,dp.period_end, sum(case when dp.metric_type='total-dataset-requests' then count else 0 end) as downloads, +//sum(case when dp.metric_type='total-dataset-investigations' then count else 0 end) as views, +//id as resultid,dp.ds_title as item, dp.yop as yop, concat('Digital Object Identifier#-#',dp.ds_type) as oid, +//sum(case when dp.metric_type='unique-dataset-requests' then count else 0 end) as uniquedownloads, +//sum(case when dp.metric_type='unique-dataset-investigations' then count else 0 end) as uniqueviews, +//dp.access_method access_method,dp.platform +//FROM datasetsusagestats_20210312a.datasetsperformance dp, openaire_prod_stats.result_pids +//WHERE dp.period_from>='2020-01-01' AND dp.period_end<='2020-12-01' and pid=ds_type and dp.ds_type=? +//GROUP BY dp.period_end,dp.ds_title, dp.yop, dp.platform, dp.access_method, dp.ds_type,id st.setString(1, beginDateStr); st.setString(2, endDateStr); st.setString(3, repositoryIdentifier); @@ -2342,6 +1705,26 @@ public class UsageStatsRepository { + "WHERE us.`date`>=? AND us.`date`<=? AND us.repository_id=? AND us.result_id=? AND rc.type=? AND rc.id=us.result_id " + "AND us.result_id=rs.id AND ro.id=us.result_id AND tpd.id=us.result_id " + "GROUP BY ro.id, rc.type, rs.title, us.result_id, us.`date`, rs.year order by rc.type, us.`date` ASC;"); +//WITH tpd as (select distinct id, concat(type,'#-#',pid) type_id from openaire_prod_stats.result_pids) +//select type, `date`,downloads, views, resultid, item,yop,group_concat(distinct tpd.type_id,'#!#') as oid, uniquedownloads,uniqueviews +//FROM (SELECT us.repository_id repo, us.`date` `date`,rc.type type, sum(us.downloads) as downloads, sum(us.views) as views, +//us.result_id as resultid, rs.title as item, rs.year as yop, +//count(case when us.downloads >0 then 1 else null end) as uniquedownloads, count(case when us.views >0 then 1 else null end) as uniqueviews +//FROM openaire_prod_usage_stats.usage_stats us,(select distinct id, type from openaire_prod_stats.result_classifications) rc, openaire_prod_stats.result rs +//WHERE us.`date`>='2020/01' AND us.`date`<='2020/02' +//AND rc.id=us.result_id AND us.result_id=rs.id AND us.repository_id='opendoar____::8e98d81f8217304975ccb23337bb5761' AND us.result_id=? AND rc.type=? +//GROUP BY us.`date`,rc.type, rs.title, us.result_id, rs.title, rs.year, us.repository_id) tmp1, tpd +//where tpd.id=resultid group by repo,`date`, type,resultid,item,yop,downloads,views,uniquedownloads,uniqueviews + +//SELECT 'Dataset' as type,dp.period_end, sum(case when dp.metric_type='total-dataset-requests' then count else 0 end) as downloads, +//sum(case when dp.metric_type='total-dataset-investigations' then count else 0 end) as views, +//id as resultid,dp.ds_title as item, dp.yop as yop, concat('Digital Object Identifier#-#',dp.ds_type) as oid, +//sum(case when dp.metric_type='unique-dataset-requests' then count else 0 end) as uniquedownloads, +//sum(case when dp.metric_type='unique-dataset-investigations' then count else 0 end) as uniqueviews, +//dp.access_method access_method,dp.platform +//FROM datasetsusagestats_20210312a.datasetsperformance dp, openaire_prod_stats.result_pids +//WHERE dp.period_from>='2020-01-01' AND dp.period_end<='2020-12-01' and pid=ds_type and dp.ds_type=? +//GROUP BY dp.period_end,dp.ds_title, dp.yop, dp.platform, dp.access_method, dp.ds_type,id st.setString(1, beginDateStr); st.setString(2, endDateStr); st.setString(3, repositoryIdentifier); diff --git a/src/main/resources/log4j.properties b/src/main/resources/log4j.properties index 21fdc52..d20fcd2 100755 --- a/src/main/resources/log4j.properties +++ b/src/main/resources/log4j.properties @@ -11,7 +11,8 @@ log4j.appender.R=org.apache.log4j.RollingFileAppender #log4j.appender.R.File=/var/log/dnet/usageStatsAPI/usageStatsAPI_R5.log #log4j.appender.R.File=/home/dimitris.pierrakos/Sushilite_R5/usageStatsAPI_R5.log #log4j.appender.R.File=/Users/dpie/Desktop/usageStatsAPI_R5.log -log4j.appender.R.File=/srv/springboot/9880/usageStatsAPI_R5.log +#log4j.appender.R.File=/srv/springboot/9880/usageStatsAPI_R5.log +log4j.appender.R.File=/home/dpie/Desktop/usageStatsAPI_R5.log loglog4j.appender.R.MaxFileSize=10MB log4j.appender.R.MaxBackupIndex=10 log4j.appender.R.layout=org.apache.log4j.PatternLayout @@ -21,7 +22,8 @@ log4j.appender.S=org.apache.log4j.RollingFileAppender #log4j.appender.S.File=/home/dimitris.pierrakos/Sushilite_R5/usageStatsAPI_R5-spring.log #log4j.appender.S.File=/Users/dpie/Desktop/usageStatsAPI_R5-spring.log #log4j.appender.S.File=/Volumes/Zeus/dpie/Desktop/usageStatsAPI_R5-spring.log -log4j.appender.S.File=/srv/springboot/9880/usageStatsAPI_R5-spring.log +#log4j.appender.S.File=/srv/springboot/9880/usageStatsAPI_R5-spring.log +log4j.appender.S.File=/home/dpie/Desktop/usageStatsAPI_R5-spring.log log4j.appender.S.MaxFileSize=10MB log4j.appender.S.MaxBackupIndex=10 log4j.appender.S.layout=org.apache.log4j.PatternLayout