From 33c85d4e667af80bfe5bbf1642b40a008e082609 Mon Sep 17 00:00:00 2001 From: antleb Date: Thu, 18 Feb 2021 17:23:34 +0200 Subject: [PATCH] moved stats computation in impala instead of hive --- .../oa/graph/stats/oozie_app/finalizedb.sh | 17 ++ .../oa/graph/stats/oozie_app/impala-shell.sh | 18 -- .../graph/stats/oozie_app/scripts/step10.sql | 6 +- .../graph/stats/oozie_app/scripts/step11.sql | 4 +- .../graph/stats/oozie_app/scripts/step12.sql | 24 +- .../graph/stats/oozie_app/scripts/step13.sql | 18 +- .../graph/stats/oozie_app/scripts/step14.sql | 24 +- .../graph/stats/oozie_app/scripts/step15.sql | 18 +- .../graph/stats/oozie_app/scripts/step16.sql | 20 +- .../stats/oozie_app/scripts/step16_5.sql | 6 +- .../stats/oozie_app/scripts/step16_6.sql | 14 +- .../graph/stats/oozie_app/scripts/step17.sql | 207 ------------------ .../graph/stats/oozie_app/scripts/step18.sql | 8 - .../graph/stats/oozie_app/scripts/step19.sql | 8 - .../graph/stats/oozie_app/scripts/step2.sql | 36 +-- .../graph/stats/oozie_app/scripts/step3.sql | 34 +-- .../graph/stats/oozie_app/scripts/step4.sql | 34 +-- .../graph/stats/oozie_app/scripts/step5.sql | 32 +-- .../graph/stats/oozie_app/scripts/step6.sql | 20 +- .../graph/stats/oozie_app/scripts/step7.sql | 8 +- .../graph/stats/oozie_app/scripts/step8.sql | 16 +- .../graph/stats/oozie_app/scripts/step9.sql | 4 +- .../dhp/oa/graph/stats/oozie_app/workflow.xml | 32 +-- 23 files changed, 179 insertions(+), 429 deletions(-) create mode 100644 dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/finalizedb.sh delete mode 100644 dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/impala-shell.sh delete mode 100644 dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step17.sql delete mode 100644 dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step18.sql delete mode 100644 dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step19.sql diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/finalizedb.sh b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/finalizedb.sh new file mode 100644 index 000000000..915faab70 --- /dev/null +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/finalizedb.sh @@ -0,0 +1,17 @@ +export PYTHON_EGG_CACHE=/home/$(whoami)/.python-eggs +export link_folder=/tmp/impala-shell-python-egg-cache-$(whoami) +if ! [ -L $link_folder ] +then + rm -Rf "$link_folder" + ln -sfn ${PYTHON_EGG_CACHE}${link_folder} ${link_folder} +fi + +export SOURCE=$1 +export SHADOW=$2 + +echo "Updating shadow database" +impala-shell -q "invalidate metadata ${SOURCE}" +impala-shell -q "create database if not exists ${SHADOW}" +impala-shell -d ${SHADOW} -q "show tables" --delimited | sed "s/^/drop view if exists ${SHADOW}./" | sed "s/$/;/" | impala-shell -f - +impala-shell -d ${SOURCE} -q "show tables" --delimited | sed "s/\(.*\)/create view ${SHADOW}.\1 as select * from ${SOURCE}.\1;/" | impala-shell -f - +echo "Shadow db ready!" \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/impala-shell.sh b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/impala-shell.sh deleted file mode 100644 index 70112dc7b..000000000 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/impala-shell.sh +++ /dev/null @@ -1,18 +0,0 @@ -export PYTHON_EGG_CACHE=/home/$(whoami)/.python-eggs -export link_folder=/tmp/impala-shell-python-egg-cache-$(whoami) -if ! [ -L $link_folder ] -then - rm -Rf "$link_folder" - ln -sfn ${PYTHON_EGG_CACHE}${link_folder} ${link_folder} -fi - -echo "Getting file from " $3 -hdfs dfs -copyToLocal $3 - -echo "Running impala shell make the new database visible" -impala-shell -q "INVALIDATE METADATA;" - -echo "Running impala shell to compute new table stats" -impala-shell -d $1 -f $2 -echo "Impala shell finished" -rm $2 diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql index d5ae0a5c8..6c96317e6 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql @@ -43,6 +43,6 @@ FROM ${external_stats_db_name}.concept; ------------------------------------------------------------------------------------------------ create table ${stats_db_name}.creation_date as select date_format(current_date(), 'dd-MM-yyyy') as date; - -ANALYZE TABLE ${stats_db_name}.creation_date COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.creation_date COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- +-- ANALYZE TABLE ${stats_db_name}.creation_date COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.creation_date COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step11.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step11.sql index db5fdb1c3..d26169fd6 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step11.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step11.sql @@ -114,5 +114,5 @@ WHERE result_projects.id = result.id AND result.type = 'publication' AND project.id = result_projects.project; -ANALYZE TABLE ${stats_db_name}.project COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.project COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- ANALYZE TABLE ${stats_db_name}.project COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.project COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step12.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step12.sql index 779547a84..51d3a73c9 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step12.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step12.sql @@ -65,15 +65,15 @@ WHERE r.id = rd.id AND r.bestlicence = 'Open Access' GROUP BY org.country; -ANALYZE TABLE ${stats_db_name}.datasource COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.datasource COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.publication COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.publication COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.dataset COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.dataset COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.software COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.software COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.numbers_country COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.numbers_country COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- ANALYZE TABLE ${stats_db_name}.datasource COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.datasource COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.publication COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.publication COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.dataset COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.dataset COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.software COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.software COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.numbers_country COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.numbers_country COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step13.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step13.sql index 41d2000e7..d79396b3b 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step13.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step13.sql @@ -57,12 +57,12 @@ UNION ALL SELECT * FROM ${stats_db_name}.software_sources UNION ALL SELECT * FROM ${stats_db_name}.otherresearchproduct_sources; - -ANALYZE TABLE ${stats_db_name}.publication_sources COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.publication_sources COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.dataset_sources COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.dataset_sources COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.software_sources COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.software_sources COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_sources COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_sources COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- +-- ANALYZE TABLE ${stats_db_name}.publication_sources COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.publication_sources COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.dataset_sources COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.dataset_sources COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.software_sources COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.software_sources COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_sources COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_sources COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step14.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step14.sql index c46012c02..00a6913bc 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step14.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step14.sql @@ -48,15 +48,15 @@ FROM ( from ${openaire_db_name}.datasource d WHERE d.datainfo.deletedbyinference=false) d on o.datasource = d.id; -ANALYZE TABLE ${stats_db_name}.publication_licenses COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.publication_licenses COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.dataset_licenses COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.dataset_licenses COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.software_licenses COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.software_licenses COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_licenses COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_licenses COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.organization_pids COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.organization_pids COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.organization_sources COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.organization_sources COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- ANALYZE TABLE ${stats_db_name}.publication_licenses COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.publication_licenses COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.dataset_licenses COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.dataset_licenses COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.software_licenses COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.software_licenses COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_licenses COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_licenses COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.organization_pids COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.organization_pids COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.organization_sources COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.organization_sources COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step15.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step15.sql index ee9e04e97..8f364d747 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step15.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step15.sql @@ -34,12 +34,12 @@ union all select * from ${stats_db_name}.software_refereed union all select * from ${stats_db_name}.otherresearchproduct_refereed; - -ANALYZE TABLE ${stats_db_name}.publication_refereed COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.publication_refereed COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.dataset_refereed COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.dataset_refereed COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.software_refereed COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.software_refereed COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_refereed COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_refereed COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- +-- ANALYZE TABLE ${stats_db_name}.publication_refereed COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.publication_refereed COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.dataset_refereed COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.dataset_refereed COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.software_refereed COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.software_refereed COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_refereed COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_refereed COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16.sql index a7e6c74e4..833deff73 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16.sql @@ -79,13 +79,13 @@ join ${stats_db_name}.datasource_organizations dor on dor.id=d.id join ${stats_db_name}.organization o on o.id=dor.organization where o.country is not null and o.country!=''; -ANALYZE TABLE ${stats_db_name}.result_peerreviewed COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.result_peerreviewed COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.result_greenoa COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.result_greenoa COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.result_gold COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.result_gold COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.result_affiliated_country COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.result_affiliated_country COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.result_deposited_country COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.result_deposited_country COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- ANALYZE TABLE ${stats_db_name}.result_peerreviewed COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.result_peerreviewed COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.result_greenoa COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.result_greenoa COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.result_gold COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.result_gold COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.result_affiliated_country COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.result_affiliated_country COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.result_deposited_country COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.result_deposited_country COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_5.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_5.sql index 52b7a58fa..2bdc263ef 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_5.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_5.sql @@ -53,6 +53,6 @@ drop table if exists ${stats_db_name}.result; drop view if exists ${stats_db_name}.result; create table ${stats_db_name}.result stored as parquet as select * from ${stats_db_name}.result_tmp; drop table ${stats_db_name}.result_tmp; - -ANALYZE TABLE ${stats_db_name}.result COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.result COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- +-- ANALYZE TABLE ${stats_db_name}.result COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.result COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_6.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_6.sql index 8b55e83b5..528aaff52 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_6.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step16_6.sql @@ -30,10 +30,10 @@ from rcount group by rcount.pid; create view ${stats_db_name}.rndexpenditure as select * from stats_ext.rndexpediture; - -ANALYZE TABLE ${stats_db_name}.result_projectcount COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.result_projectcount COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.result_fundercount COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.result_fundercount COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.project_resultcount COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.project_resultcount COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- +-- ANALYZE TABLE ${stats_db_name}.result_projectcount COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.result_projectcount COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.result_fundercount COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.result_fundercount COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.project_resultcount COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.project_resultcount COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step17.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step17.sql deleted file mode 100644 index 5c102d014..000000000 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step17.sql +++ /dev/null @@ -1,207 +0,0 @@ ------------------------------------------------------- ------------------------------------------------------- --- Shadow schema table exchange ------------------------------------------------------- ------------------------------------------------------- - --- Dropping old views -DROP VIEW IF EXISTS ${stats_db_shadow_name}.category; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.concept; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.context; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.country; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.countrygdp; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.creation_date; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.dataset; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.dataset_citations; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.dataset_classifications; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.dataset_concepts; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.dataset_datasources; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.dataset_languages; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.dataset_licenses; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.dataset_oids; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.dataset_pids; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.dataset_refereed; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.dataset_sources; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.dataset_topics; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.datasource; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.datasource_languages; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.datasource_oids; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.datasource_organizations; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.datasource_results; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.datasource_sources; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.funder; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.fundref; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.numbers_country; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.organization; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.organization_datasources; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.organization_pids; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.organization_projects; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.organization_sources; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.otherresearchproduct; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.otherresearchproduct_citations; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.otherresearchproduct_classifications; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.otherresearchproduct_concepts; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.otherresearchproduct_datasources; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.otherresearchproduct_languages; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.otherresearchproduct_licenses; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.otherresearchproduct_oids; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.otherresearchproduct_pids; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.otherresearchproduct_refereed; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.otherresearchproduct_sources; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.otherresearchproduct_topics; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.project; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.project_oids; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.project_organizations; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.project_results; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.project_resultcount; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.project_results_publication; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.publication; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.publication_citations; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.publication_classifications; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.publication_concepts; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.publication_datasources; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.publication_languages; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.publication_licenses; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.publication_oids; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.publication_pids; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.publication_refereed; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.publication_sources; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.publication_topics; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_affiliated_country; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_citations; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_classifications; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_concepts; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_datasources; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_deposited_country; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_fundercount; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_gold; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_greenoa; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_languages; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_licenses; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_oids; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_organization; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_peerreviewed; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_pids; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_projectcount; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_projects; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_refereed; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_sources; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.result_topics; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.rndexpediture; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.roarmap; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.software; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.software_citations; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.software_classifications; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.software_concepts; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.software_datasources; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.software_languages; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.software_licenses; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.software_oids; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.software_pids; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.software_refereed; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.software_sources; -DROP VIEW IF EXISTS ${stats_db_shadow_name}.software_topics; - - --- Creating the shadow database, in case it doesn't exist -CREATE database IF NOT EXISTS ${stats_db_shadow_name}; - --- Creating new views -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.category AS SELECT * FROM ${stats_db_name}.category; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.concept AS SELECT * FROM ${stats_db_name}.concept; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.context AS SELECT * FROM ${stats_db_name}.context; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.country AS SELECT * FROM ${stats_db_name}.country; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.countrygdp AS SELECT * FROM ${stats_db_name}.countrygdp; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.creation_date AS SELECT * FROM ${stats_db_name}.creation_date; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.dataset AS SELECT * FROM ${stats_db_name}.dataset; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.dataset_citations AS SELECT * FROM ${stats_db_name}.dataset_citations; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.dataset_classifications AS SELECT * FROM ${stats_db_name}.dataset_classifications; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.dataset_concepts AS SELECT * FROM ${stats_db_name}.dataset_concepts; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.dataset_datasources AS SELECT * FROM ${stats_db_name}.dataset_datasources; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.dataset_languages AS SELECT * FROM ${stats_db_name}.dataset_languages; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.dataset_licenses AS SELECT * FROM ${stats_db_name}.dataset_licenses; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.dataset_oids AS SELECT * FROM ${stats_db_name}.dataset_oids; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.dataset_pids AS SELECT * FROM ${stats_db_name}.dataset_pids; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.dataset_refereed AS SELECT * FROM ${stats_db_name}.dataset_refereed; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.dataset_sources AS SELECT * FROM ${stats_db_name}.dataset_sources; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.dataset_topics AS SELECT * FROM ${stats_db_name}.dataset_topics; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.datasource AS SELECT * FROM ${stats_db_name}.datasource; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.datasource_languages AS SELECT * FROM ${stats_db_name}.datasource_languages; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.datasource_oids AS SELECT * FROM ${stats_db_name}.datasource_oids; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.datasource_organizations AS SELECT * FROM ${stats_db_name}.datasource_organizations; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.datasource_results AS SELECT * FROM ${stats_db_name}.datasource_results; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.datasource_sources AS SELECT * FROM ${stats_db_name}.datasource_sources; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.funder AS SELECT * FROM ${stats_db_name}.funder; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.fundref AS SELECT * FROM ${stats_db_name}.fundref; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.numbers_country AS SELECT * FROM ${stats_db_name}.numbers_country; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.organization AS SELECT * FROM ${stats_db_name}.organization; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.organization_datasources AS SELECT * FROM ${stats_db_name}.organization_datasources; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.organization_pids AS SELECT * FROM ${stats_db_name}.organization_pids; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.organization_projects AS SELECT * FROM ${stats_db_name}.organization_projects; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.organization_sources AS SELECT * FROM ${stats_db_name}.organization_sources; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.otherresearchproduct AS SELECT * FROM ${stats_db_name}.otherresearchproduct; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.otherresearchproduct_citations AS SELECT * FROM ${stats_db_name}.otherresearchproduct_citations; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.otherresearchproduct_classifications AS SELECT * FROM ${stats_db_name}.otherresearchproduct_classifications; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.otherresearchproduct_concepts AS SELECT * FROM ${stats_db_name}.otherresearchproduct_concepts; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.otherresearchproduct_datasources AS SELECT * FROM ${stats_db_name}.otherresearchproduct_datasources; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.otherresearchproduct_languages AS SELECT * FROM ${stats_db_name}.otherresearchproduct_languages; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.otherresearchproduct_licenses AS SELECT * FROM ${stats_db_name}.otherresearchproduct_licenses; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.otherresearchproduct_oids AS SELECT * FROM ${stats_db_name}.otherresearchproduct_oids; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.otherresearchproduct_pids AS SELECT * FROM ${stats_db_name}.otherresearchproduct_pids; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.otherresearchproduct_refereed AS SELECT * FROM ${stats_db_name}.otherresearchproduct_refereed; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.otherresearchproduct_sources AS SELECT * FROM ${stats_db_name}.otherresearchproduct_sources; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.otherresearchproduct_topics AS SELECT * FROM ${stats_db_name}.otherresearchproduct_topics; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.project AS SELECT * FROM ${stats_db_name}.project; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.project_oids AS SELECT * FROM ${stats_db_name}.project_oids; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.project_organizations AS SELECT * FROM ${stats_db_name}.project_organizations; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.project_results AS SELECT * FROM ${stats_db_name}.project_results; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.project_resultcount AS SELECT * FROM ${stats_db_name}.project_resultcount; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.project_results_publication AS SELECT * FROM ${stats_db_name}.project_results_publication; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.publication AS SELECT * FROM ${stats_db_name}.publication; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.publication_citations AS SELECT * FROM ${stats_db_name}.publication_citations; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.publication_classifications AS SELECT * FROM ${stats_db_name}.publication_classifications; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.publication_concepts AS SELECT * FROM ${stats_db_name}.publication_concepts; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.publication_datasources AS SELECT * FROM ${stats_db_name}.publication_datasources; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.publication_languages AS SELECT * FROM ${stats_db_name}.publication_languages; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.publication_licenses AS SELECT * FROM ${stats_db_name}.publication_licenses; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.publication_oids AS SELECT * FROM ${stats_db_name}.publication_oids; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.publication_pids AS SELECT * FROM ${stats_db_name}.publication_pids; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.publication_refereed AS SELECT * FROM ${stats_db_name}.publication_refereed; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.publication_sources AS SELECT * FROM ${stats_db_name}.publication_sources; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.publication_topics AS SELECT * FROM ${stats_db_name}.publication_topics; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result AS SELECT * FROM ${stats_db_name}.result; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_affiliated_country AS SELECT * FROM ${stats_db_name}.result_affiliated_country; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_citations AS SELECT * FROM ${stats_db_name}.result_citations; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_classifications AS SELECT * FROM ${stats_db_name}.result_classifications; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_concepts AS SELECT * FROM ${stats_db_name}.result_concepts; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_datasources AS SELECT * FROM ${stats_db_name}.result_datasources; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_deposited_country AS SELECT * FROM ${stats_db_name}.result_deposited_country; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_fundercount AS SELECT * FROM ${stats_db_name}.result_fundercount; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_gold AS SELECT * FROM ${stats_db_name}.result_gold; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_greenoa AS SELECT * FROM ${stats_db_name}.result_greenoa; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_languages AS SELECT * FROM ${stats_db_name}.result_languages; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_licenses AS SELECT * FROM ${stats_db_name}.result_licenses; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_oids AS SELECT * FROM ${stats_db_name}.result_oids; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_organization AS SELECT * FROM ${stats_db_name}.result_organization; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_peerreviewed AS SELECT * FROM ${stats_db_name}.result_peerreviewed; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_pids AS SELECT * FROM ${stats_db_name}.result_pids; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_projectcount AS SELECT * FROM ${stats_db_name}.result_projectcount; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_projects AS SELECT * FROM ${stats_db_name}.result_projects; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_refereed AS SELECT * FROM ${stats_db_name}.result_refereed; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_sources AS SELECT * FROM ${stats_db_name}.result_sources; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.result_topics AS SELECT * FROM ${stats_db_name}.result_topics; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.rndexpediture AS SELECT * FROM ${stats_db_name}.rndexpediture; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.roarmap AS SELECT * FROM ${stats_db_name}.roarmap; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.software AS SELECT * FROM ${stats_db_name}.software; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.software_citations AS SELECT * FROM ${stats_db_name}.software_citations; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.software_classifications AS SELECT * FROM ${stats_db_name}.software_classifications; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.software_concepts AS SELECT * FROM ${stats_db_name}.software_concepts; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.software_datasources AS SELECT * FROM ${stats_db_name}.software_datasources; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.software_languages AS SELECT * FROM ${stats_db_name}.software_languages; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.software_licenses AS SELECT * FROM ${stats_db_name}.software_licenses; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.software_oids AS SELECT * FROM ${stats_db_name}.software_oids; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.software_pids AS SELECT * FROM ${stats_db_name}.software_pids; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.software_refereed AS SELECT * FROM ${stats_db_name}.software_refereed; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.software_sources AS SELECT * FROM ${stats_db_name}.software_sources; -CREATE VIEW IF NOT EXISTS ${stats_db_shadow_name}.software_topics AS SELECT * FROM ${stats_db_name}.software_topics; diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step18.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step18.sql deleted file mode 100644 index 34e48a18a..000000000 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step18.sql +++ /dev/null @@ -1,8 +0,0 @@ ------------------------------------------------------- ------------------------------------------------------- --- Impala table statistics - Needed to make the tables --- visible for impala ------------------------------------------------------- ------------------------------------------------------- - -INVALIDATE METADATA ${stats_db_name}; diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step19.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step19.sql deleted file mode 100644 index 34e48a18a..000000000 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step19.sql +++ /dev/null @@ -1,8 +0,0 @@ ------------------------------------------------------- ------------------------------------------------------- --- Impala table statistics - Needed to make the tables --- visible for impala ------------------------------------------------------- ------------------------------------------------------- - -INVALIDATE METADATA ${stats_db_name}; diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step2.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step2.sql index d2700f415..62a158560 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step2.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step2.sql @@ -93,21 +93,21 @@ FROM ${openaire_db_name}.publication p WHERE xpath_string(citation.value, "//citation/id[@type='openaire']/@value") != "" and p.datainfo.deletedbyinference = false; -ANALYZE TABLE ${stats_db_name}.publication_tmp COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.publication_tmp COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.publication_classifications COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.publication_classifications COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.publication_concepts COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.publication_concepts COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.publication_datasources COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.publication_datasources COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.publication_languages COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.publication_languages COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.publication_oids COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.publication_oids COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.publication_pids COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.publication_pids COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.publication_topics COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.publication_topics COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.publication_citations COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.publication_citations COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- ANALYZE TABLE ${stats_db_name}.publication_tmp COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.publication_tmp COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.publication_classifications COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.publication_classifications COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.publication_concepts COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.publication_concepts COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.publication_datasources COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.publication_datasources COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.publication_languages COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.publication_languages COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.publication_oids COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.publication_oids COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.publication_pids COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.publication_pids COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.publication_topics COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.publication_topics COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.publication_citations COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.publication_citations COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step3.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step3.sql index 977d32132..dcd5ad858 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step3.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step3.sql @@ -93,20 +93,20 @@ SELECT substr(p.id, 4) AS id, subjects.subject.qualifier.classname AS type, subj FROM ${openaire_db_name}.dataset p LATERAL VIEW explode(p.subject) subjects AS subject where p.datainfo.deletedbyinference = false; - -ANALYZE TABLE ${stats_db_name}.dataset_tmp COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.dataset_tmp COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.dataset_classifications COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.dataset_classifications COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.dataset_concepts COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.dataset_concepts COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.dataset_datasources COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.dataset_datasources COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.dataset_languages COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.dataset_languages COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.dataset_oids COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.dataset_oids COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.dataset_pids COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.dataset_pids COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.dataset_topics COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.dataset_topics COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- +-- ANALYZE TABLE ${stats_db_name}.dataset_tmp COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.dataset_tmp COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.dataset_classifications COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.dataset_classifications COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.dataset_concepts COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.dataset_concepts COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.dataset_datasources COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.dataset_datasources COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.dataset_languages COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.dataset_languages COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.dataset_oids COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.dataset_oids COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.dataset_pids COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.dataset_pids COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.dataset_topics COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.dataset_topics COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step4.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step4.sql index ace084d23..fd5390e66 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step4.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step4.sql @@ -93,20 +93,20 @@ SELECT substr(p.id, 4) AS id, subjects.subject.qualifier.classname AS type, subj FROM ${openaire_db_name}.software p LATERAL VIEW explode(p.subject) subjects AS subject where p.datainfo.deletedbyinference = false; - -ANALYZE TABLE ${stats_db_name}.software_tmp COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.software_tmp COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.software_classifications COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.software_classifications COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.software_concepts COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.software_concepts COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.software_datasources COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.software_datasources COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.software_languages COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.software_languages COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.software_oids COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.software_oids COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.software_pids COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.software_pids COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.software_topics COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.software_topics COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- +-- ANALYZE TABLE ${stats_db_name}.software_tmp COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.software_tmp COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.software_classifications COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.software_classifications COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.software_concepts COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.software_concepts COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.software_datasources COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.software_datasources COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.software_languages COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.software_languages COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.software_oids COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.software_oids COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.software_pids COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.software_pids COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.software_topics COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.software_topics COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step5.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step5.sql index 0fd8e7189..b359b596f 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step5.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step5.sql @@ -85,19 +85,19 @@ SELECT substr(p.id, 4) AS id, subjects.subject.qualifier.classname AS type, subj FROM ${openaire_db_name}.otherresearchproduct p LATERAL VIEW explode(p.subject) subjects AS subject where p.datainfo.deletedbyinference = false; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_tmp COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_tmp COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_classifications COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_classifications COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_concepts COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_concepts COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_datasources COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_datasources COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_languages COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_languages COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_oids COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_oids COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_pids COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_pids COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_topics COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.otherresearchproduct_topics COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_tmp COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_tmp COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_classifications COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_classifications COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_concepts COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_concepts COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_datasources COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_datasources COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_languages COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_languages COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_oids COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_oids COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_pids COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_pids COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_topics COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.otherresearchproduct_topics COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step6.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step6.sql index ade686cf6..23ef03bc9 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step6.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step6.sql @@ -72,13 +72,13 @@ select distinct xpath_string(fund, '//funder/id') as id, xpath_string(fund, '//funder/shortname') as shortname from ${openaire_db_name}.project p lateral view explode(p.fundingtree.value) fundingtree as fund; -ANALYZE TABLE ${stats_db_name}.project_oids COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.project_oids COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.project_organizations COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.project_organizations COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.project_results COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.project_results COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.project_tmp COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.project_tmp COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.funder COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.funder COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- ANALYZE TABLE ${stats_db_name}.project_oids COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.project_oids COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.project_organizations COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.project_organizations COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.project_results COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.project_results COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.project_tmp COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.project_tmp COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.funder COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.funder COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step7.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step7.sql index d330bde46..ae540b9b2 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step7.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step7.sql @@ -135,7 +135,7 @@ FROM ${stats_db_name}.result r JOIN ${stats_db_name}.project_results pr ON r.id = pr.result JOIN ${stats_db_name}.project_tmp p ON p.id = pr.id; -ANALYZE TABLE ${stats_db_name}.result_organization COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.result_organization COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.result_projects COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.result_projects COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- ANALYZE TABLE ${stats_db_name}.result_organization COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.result_organization COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.result_projects COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.result_projects COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step8.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step8.sql index 73ea0c084..de0fedd7e 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step8.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step8.sql @@ -99,11 +99,11 @@ CREATE OR REPLACE VIEW ${stats_db_name}.datasource_results AS SELECT datasource AS id, id AS result FROM ${stats_db_name}.result_datasources; -ANALYZE TABLE ${stats_db_name}.datasource_tmp COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.datasource_tmp COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.datasource_languages COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.datasource_languages COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.datasource_oids COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.datasource_oids COMPUTE STATISTICS FOR COLUMNS; -ANALYZE TABLE ${stats_db_name}.datasource_organizations COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.datasource_organizations COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- ANALYZE TABLE ${stats_db_name}.datasource_tmp COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.datasource_tmp COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.datasource_languages COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.datasource_languages COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.datasource_oids COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.datasource_oids COMPUTE STATISTICS FOR COLUMNS; +-- ANALYZE TABLE ${stats_db_name}.datasource_organizations COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.datasource_organizations COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step9.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step9.sql index 9a581900a..a1cb46185 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step9.sql +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step9.sql @@ -19,5 +19,5 @@ CREATE OR REPLACE VIEW ${stats_db_name}.organization_projects AS SELECT id AS project, organization as id FROM ${stats_db_name}.project_organizations; -ANALYZE TABLE ${stats_db_name}.organization COMPUTE STATISTICS; -ANALYZE TABLE ${stats_db_name}.organization COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file +-- ANALYZE TABLE ${stats_db_name}.organization COMPUTE STATISTICS; +-- ANALYZE TABLE ${stats_db_name}.organization COMPUTE STATISTICS FOR COLUMNS; \ No newline at end of file diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml index 2f195d6d3..95c151c09 100644 --- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml +++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml @@ -260,31 +260,6 @@ stats_db_name=${stats_db_name} openaire_db_name=${openaire_db_name} - - - - - - - ${hive_jdbc_url} - - stats_db_name=${stats_db_name} - stats_db_shadow_name=${stats_db_shadow_name} - - - - - - - - ${jobTracker} - ${nameNode} - impala-shell.sh - ${stats_db_name} - step18.sql - ${wf:appPath()}/scripts/step18.sql - impala-shell.sh - @@ -293,11 +268,10 @@ ${jobTracker} ${nameNode} - impala-shell.sh + finalizedb.sh + stats_db_name ${stats_db_shadow_name} - step19.sql - ${wf:appPath()}/scripts/step19.sql - impala-shell.sh + finalizedb.sh