Merge branch 'stable_ids' of code-repo.d4science.org:D-Net/dnet-hadoop into stable_ids

This commit is contained in:
miconis 2021-04-14 18:06:34 +02:00
commit 176a5e493d
20 changed files with 905 additions and 862 deletions

757
100.patch
View File

@ -1,757 +0,0 @@
From c5fbad8093ca27deebf1b5fd5ffd39e1877c533d Mon Sep 17 00:00:00 2001
From: antleb <antleb@di.uoa.gr>
Date: Thu, 4 Mar 2021 00:42:21 +0200
Subject: [PATCH 1/8] Contexts are now downloaded instead of using the
stats_ext db
---
.../dhp/oa/graph/stats/oozie_app/contexts.sh | 33 +++++++++++++++++++
.../graph/stats/oozie_app/scripts/step10.sql | 13 --------
.../dhp/oa/graph/stats/oozie_app/workflow.xml | 17 ++++++++++
3 files changed, 50 insertions(+), 13 deletions(-)
create mode 100644 dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh
diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh
new file mode 100644
index 00000000..f06a43bb
--- /dev/null
+++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh
@@ -0,0 +1,33 @@
+#!/usr/bin/env bash
+
+CONTEXT_API=$1
+TARGET_DB=$2
+
+TMP=/tmp/stats-update-`tr -dc A-Za-z0-9 </dev/urandom | head -c 6`
+
+echo "Downloading context data"
+curl ${CONTEXT_API}/contexts?all=true -H "accept: application/json" | /usr/local/sbin/jq -r '.[] | "\(.id),\(.label)"' > contexts.csv
+cat contexts.csv | cut -d , -f1 | xargs -I {} curl ${CONTEXT_API}/context/{}/?all=true | /usr/local/sbin/jq -r '.[]|"\(.id|split(":")[0]),\(.id),\(.label)"' > categories.csv
+cat categories.csv | cut -d , -f2 | sed 's/:/%3A/g'| xargs -I {} curl ${CONTEXT_API}/context/category/{}/?all=true | /usr/local/sbin/jq -r '.[]|"\(.id|split("::")[0])::\(.id|split("::")[1]),\(.id),\(.label)"' > concepts.csv
+cat contexts.csv | cut -f1 -d, | sed 's/\(.*\)/\1,\1::other,other/' >> categories.csv
+cat categories.csv | cut -d, -f2 | sed 's/\(.*\)/\1,\1::other,other/' >> concepts.csv
+
+echo "uploading context data to hdfs"
+hdfs dfs -mkdir ${TMP}
+hdfs dfs -copyFromLocal contexts.csv ${TMP}
+hdfs dfs -copyFromLocal categories.csv ${TMP}
+hdfs dfs -copyFromLocal concepts.csv ${TMP}
+hdfs dfs -chmod -R 777 ${TMP}
+
+echo "Creating and populating impala tables"
+impala-shell -c "create table ${TARGET_DB}.context (id string, name string) row format delimited fields terminated by ',';"
+impala-shell -c "create table ${TARGET_DB}.category (context string, id string, name string) row format delimited fields terminated by ',';"
+impala-shell -c "create table ${TARGET_DB}.concept (category string, id string, name string) row format delimited fields terminated by ',';"
+impala-shell -c "load data inpath '${TMP}/contexts.csv' into table ${TARGET_DB}.context;"
+impala-shell -c "load data inpath '${TMP}/categories.csv' into table ${TARGET_DB}.category;"
+impala-shell -c "load data inpath '${TMP}/concepts.csv' into table ${TARGET_DB}.concept;"
+
+echo "Cleaning up"
+hdfs dfs -rm -f -r -skipTrash ${TMP}
+
+echo "Finito!"
\ No newline at end of file
diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql
index 6c96317e..77fbd3b1 100644
--- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql
+++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step10.sql
@@ -23,19 +23,6 @@ CREATE OR REPLACE VIEW ${stats_db_name}.rndexpediture AS
SELECT *
FROM ${external_stats_db_name}.rndexpediture;
-CREATE OR REPLACE VIEW ${stats_db_name}.context AS
-SELECT *
-FROM ${external_stats_db_name}.context;
-
-CREATE OR REPLACE VIEW ${stats_db_name}.category AS
-SELECT *
-FROM ${external_stats_db_name}.category;
-
-CREATE OR REPLACE VIEW ${stats_db_name}.concept AS
-SELECT *
-FROM ${external_stats_db_name}.concept;
-
-
------------------------------------------------------------------------------------------------
------------------------------------------------------------------------------------------------
-- Creation date of the database
diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml
index 9c16f149..afb10c41 100644
--- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml
+++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml
@@ -41,6 +41,10 @@
<name>hive_timeout</name>
<description>the time period, in seconds, after which Hive fails a transaction if a Hive client has not sent a hearbeat. The default value is 300 seconds.</description>
</property>
+ <property>
+ <name>context_api_url</name>
+ <description>the base url of the context api (https://services.openaire.eu/openaire)</description>
+ </property>
</parameters>
<global>
@@ -263,6 +267,19 @@
<ok to="Step19"/>
<error to="Kill"/>
</action>
+
+ <action name="Step17">
+ <shell xmlns="uri:oozie:shell-action:0.1">
+ <job-tracker>${jobTracker}</job-tracker>
+ <name-node>${nameNode}</name-node>
+ <exec>contexts.sh</exec>
+ <argument>${context_api_url}</argument>
+ <argument>${stats_db_name}</argument>
+ <file>contexts.sh</file>
+ </shell>
+ <ok to="step20-createMonitorDB"/>
+ <error to="Kill"/>
+ </action>
<action name="Step19">
<shell xmlns="uri:oozie:shell-action:0.1">
--
2.17.1
From 6147ee495053634436abe822aaf9ba909813d8c4 Mon Sep 17 00:00:00 2001
From: antleb <antleb@di.uoa.gr>
Date: Fri, 5 Mar 2021 14:12:18 +0200
Subject: [PATCH 2/8] assigning correctly hive contexts to concepts
---
.../eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh | 7 +++++--
.../dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step2.sql | 5 ++++-
.../dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step3.sql | 5 ++++-
.../dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step4.sql | 5 ++++-
.../dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step5.sql | 5 ++++-
5 files changed, 21 insertions(+), 6 deletions(-)
diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh
index f06a43bb..6788f88b 100644
--- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh
+++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh
@@ -9,8 +9,8 @@ echo "Downloading context data"
curl ${CONTEXT_API}/contexts?all=true -H "accept: application/json" | /usr/local/sbin/jq -r '.[] | "\(.id),\(.label)"' > contexts.csv
cat contexts.csv | cut -d , -f1 | xargs -I {} curl ${CONTEXT_API}/context/{}/?all=true | /usr/local/sbin/jq -r '.[]|"\(.id|split(":")[0]),\(.id),\(.label)"' > categories.csv
cat categories.csv | cut -d , -f2 | sed 's/:/%3A/g'| xargs -I {} curl ${CONTEXT_API}/context/category/{}/?all=true | /usr/local/sbin/jq -r '.[]|"\(.id|split("::")[0])::\(.id|split("::")[1]),\(.id),\(.label)"' > concepts.csv
-cat contexts.csv | cut -f1 -d, | sed 's/\(.*\)/\1,\1::other,other/' >> categories.csv
-cat categories.csv | cut -d, -f2 | sed 's/\(.*\)/\1,\1::other,other/' >> concepts.csv
+cat contexts.csv | sed 's/^\(.*\),\(.*\)/\1,\1::other,\2/' >> categories.csv
+cat categories.csv | grep -v ::other | sed 's/^.*,\(.*\),\(.*\)/\1,\1::other,\2/' >> concepts.csv
echo "uploading context data to hdfs"
hdfs dfs -mkdir ${TMP}
@@ -29,5 +29,8 @@ impala-shell -c "load data inpath '${TMP}/concepts.csv' into table ${TARGET_DB}.
echo "Cleaning up"
hdfs dfs -rm -f -r -skipTrash ${TMP}
+rm concepts.csv
+rm categories.csv
+rm contexts.csv
echo "Finito!"
\ 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/step2.sql b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/step2.sql
index 62a15856..75b24b18 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
@@ -47,7 +47,10 @@ from ${openaire_db_name}.publication p
where p.datainfo.deletedbyinference = false;
CREATE TABLE ${stats_db_name}.publication_concepts AS
-SELECT substr(p.id, 4) as id, contexts.context.id as concept
+SELECT substr(p.id, 4) as id, case
+ when contexts.context.id RLIKE '^[^::]+::[^::]+::.+$' then contexts.context.id
+ when contexts.context.id RLIKE '^[^::]+::[^::]+$' then concat(contexts.context.id, '::other')
+ when contexts.context.id RLIKE '^[^::]+$' then concat(contexts.context.id, '::other::other') END as concept
from ${openaire_db_name}.publication p
LATERAL VIEW explode(p.context) contexts as context
where p.datainfo.deletedbyinference = false;
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 dcd5ad85..540cc03a 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
@@ -54,7 +54,10 @@ FROM ${openaire_db_name}.dataset p
where p.datainfo.deletedbyinference = false;
CREATE TABLE ${stats_db_name}.dataset_concepts AS
-SELECT substr(p.id, 4) as id, contexts.context.id as concept
+SELECT substr(p.id, 4) as id, case
+ when contexts.context.id RLIKE '^[^::]+::[^::]+::.+$' then contexts.context.id
+ when contexts.context.id RLIKE '^[^::]+::[^::]+$' then concat(contexts.context.id, '::other')
+ when contexts.context.id RLIKE '^[^::]+$' then concat(contexts.context.id, '::other::other') END as concept
from ${openaire_db_name}.dataset p
LATERAL VIEW explode(p.context) contexts as context
where p.datainfo.deletedbyinference = false;
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 fd5390e6..54345e07 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
@@ -54,7 +54,10 @@ FROM ${openaire_db_name}.software p
where p.datainfo.deletedbyinference = false;
CREATE TABLE ${stats_db_name}.software_concepts AS
-SELECT substr(p.id, 4) AS id, contexts.context.id AS concept
+SELECT substr(p.id, 4) as id, case
+ when contexts.context.id RLIKE '^[^::]+::[^::]+::.+$' then contexts.context.id
+ when contexts.context.id RLIKE '^[^::]+::[^::]+$' then concat(contexts.context.id, '::other')
+ when contexts.context.id RLIKE '^[^::]+$' then concat(contexts.context.id, '::other::other') END as concept
FROM ${openaire_db_name}.software p
LATERAL VIEW explode(p.context) contexts AS context
where p.datainfo.deletedbyinference = false;
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 b359b596..36ad5d92 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
@@ -52,7 +52,10 @@ FROM ${openaire_db_name}.otherresearchproduct p LATERAL VIEW explode(p.instance.
where p.datainfo.deletedbyinference = false;
CREATE TABLE ${stats_db_name}.otherresearchproduct_concepts AS
-SELECT substr(p.id, 4) AS id, contexts.context.id AS concept
+SELECT substr(p.id, 4) as id, case
+ when contexts.context.id RLIKE '^[^::]+::[^::]+::.+$' then contexts.context.id
+ when contexts.context.id RLIKE '^[^::]+::[^::]+$' then concat(contexts.context.id, '::other')
+ when contexts.context.id RLIKE '^[^::]+$' then concat(contexts.context.id, '::other::other') END as concept
FROM ${openaire_db_name}.otherresearchproduct p LATERAL VIEW explode(p.context) contexts AS context
where p.datainfo.deletedbyinference = false;
--
2.17.1
From f40c150a0d549e2dbcfd42ecf81e17ad4b505391 Mon Sep 17 00:00:00 2001
From: antleb <antleb@di.uoa.gr>
Date: Sat, 6 Mar 2021 00:35:57 +0200
Subject: [PATCH 3/8] fixed steps...
---
.../eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml
index afb10c41..2184cb8a 100644
--- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml
+++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml
@@ -264,7 +264,7 @@
<param>stats_db_name=${stats_db_name}</param>
<param>openaire_db_name=${openaire_db_name}</param>
</hive2>
- <ok to="Step19"/>
+ <ok to="Step17"/>
<error to="Kill"/>
</action>
@@ -277,7 +277,7 @@
<argument>${stats_db_name}</argument>
<file>contexts.sh</file>
</shell>
- <ok to="step20-createMonitorDB"/>
+ <ok to="step19"/>
<error to="Kill"/>
</action>
--
2.17.1
From fa1ec5b5e9b6038b3b565422af5c6406f21220d3 Mon Sep 17 00:00:00 2001
From: antleb <antleb@di.uoa.gr>
Date: Wed, 10 Mar 2021 14:05:58 +0200
Subject: [PATCH 4/8] fixed typo...
---
.../eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
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 2184cb8a..321500e2 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
@@ -277,7 +277,7 @@
<argument>${stats_db_name}</argument>
<file>contexts.sh</file>
</shell>
- <ok to="step19"/>
+ <ok to="Step19"/>
<error to="Kill"/>
</action>
--
2.17.1
From 3c75a050443942b632cf8469b5af16a8c61e7569 Mon Sep 17 00:00:00 2001
From: antleb <antleb@di.uoa.gr>
Date: Fri, 12 Mar 2021 13:47:04 +0200
Subject: [PATCH 5/8] fixed a ton of typos
---
.../scripts/computeProductionStats.sql | 8 -------
.../stats/oozie_app/updateProductionViews.sh | 18 ++++++++++++++++
.../dhp/oa/graph/stats/oozie_app/contexts.sh | 21 ++++++++++++-------
3 files changed, 32 insertions(+), 15 deletions(-)
delete mode 100644 dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/computeProductionStats.sql
create mode 100644 dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/updateProductionViews.sh
diff --git a/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/computeProductionStats.sql b/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/computeProductionStats.sql
deleted file mode 100644
index 34e48a18..00000000
--- a/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/computeProductionStats.sql
+++ /dev/null
@@ -1,8 +0,0 @@
-------------------------------------------------------
-------------------------------------------------------
--- Impala table statistics - Needed to make the tables
--- visible for impala
-------------------------------------------------------
-------------------------------------------------------
-
-INVALIDATE METADATA ${stats_db_name};
diff --git a/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/updateProductionViews.sh b/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/updateProductionViews.sh
new file mode 100644
index 00000000..57acb2ee
--- /dev/null
+++ b/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/updateProductionViews.sh
@@ -0,0 +1,18 @@
+export PYTHON_EGG_CACHE=/home/$(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 -d ${SOURCE} -q "invalidate metadata"
+impala-shell -d ${SOURCE} -q "show tables" --delimited | sed "s/^\(.*\)/compute stats ${SOURCE}.\1;/" | impala-shell -c -f -
+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 -c -f -
+impala-shell -d ${SOURCE} -q "show tables" --delimited | sed "s/\(.*\)/create view ${SHADOW}.\1 as select * from ${SOURCE}.\1;/" | impala-shell -c -f -
+echo "Shadow db ready!"
\ No newline at end of file
diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh
index 6788f88b..c28be50d 100644
--- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh
+++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh
@@ -1,4 +1,10 @@
-#!/usr/bin/env bash
+export PYTHON_EGG_CACHE=/home/$(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
CONTEXT_API=$1
TARGET_DB=$2
@@ -20,12 +26,13 @@ hdfs dfs -copyFromLocal concepts.csv ${TMP}
hdfs dfs -chmod -R 777 ${TMP}
echo "Creating and populating impala tables"
-impala-shell -c "create table ${TARGET_DB}.context (id string, name string) row format delimited fields terminated by ',';"
-impala-shell -c "create table ${TARGET_DB}.category (context string, id string, name string) row format delimited fields terminated by ',';"
-impala-shell -c "create table ${TARGET_DB}.concept (category string, id string, name string) row format delimited fields terminated by ',';"
-impala-shell -c "load data inpath '${TMP}/contexts.csv' into table ${TARGET_DB}.context;"
-impala-shell -c "load data inpath '${TMP}/categories.csv' into table ${TARGET_DB}.category;"
-impala-shell -c "load data inpath '${TMP}/concepts.csv' into table ${TARGET_DB}.concept;"
+impala-shell -q "create table ${TARGET_DB}.context (id string, name string) row format delimited fields terminated by ','"
+impala-shell -q "create table ${TARGET_DB}.category (context string, id string, name string) row format delimited fields terminated by ','"
+impala-shell -q "create table ${TARGET_DB}.concept (category string, id string, name string) row format delimited fields terminated by ','"
+impala-shell -d ${TARGET_DB} -q "invalidate metadata"
+impala-shell -q "load data inpath '${TMP}/contexts.csv' into table ${TARGET_DB}.context"
+impala-shell -q "load data inpath '${TMP}/categories.csv' into table ${TARGET_DB}.category"
+impala-shell -q "load data inpath '${TMP}/concepts.csv' into table ${TARGET_DB}.concept"
echo "Cleaning up"
hdfs dfs -rm -f -r -skipTrash ${TMP}
--
2.17.1
From 236435b47010ea1ab94c3f018dcf278f5d2c44aa Mon Sep 17 00:00:00 2001
From: antleb <antleb@di.uoa.gr>
Date: Fri, 12 Mar 2021 14:11:21 +0200
Subject: [PATCH 6/8] following redirects
---
.../eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh
index c28be50d..29b225e3 100644
--- a/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh
+++ b/dhp-workflows/dhp-stats-update/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/contexts.sh
@@ -12,9 +12,9 @@ TARGET_DB=$2
TMP=/tmp/stats-update-`tr -dc A-Za-z0-9 </dev/urandom | head -c 6`
echo "Downloading context data"
-curl ${CONTEXT_API}/contexts?all=true -H "accept: application/json" | /usr/local/sbin/jq -r '.[] | "\(.id),\(.label)"' > contexts.csv
-cat contexts.csv | cut -d , -f1 | xargs -I {} curl ${CONTEXT_API}/context/{}/?all=true | /usr/local/sbin/jq -r '.[]|"\(.id|split(":")[0]),\(.id),\(.label)"' > categories.csv
-cat categories.csv | cut -d , -f2 | sed 's/:/%3A/g'| xargs -I {} curl ${CONTEXT_API}/context/category/{}/?all=true | /usr/local/sbin/jq -r '.[]|"\(.id|split("::")[0])::\(.id|split("::")[1]),\(.id),\(.label)"' > concepts.csv
+curl -L ${CONTEXT_API}/contexts?all=true -H "accept: application/json" | /usr/local/sbin/jq -r '.[] | "\(.id),\(.label)"' > contexts.csv
+cat contexts.csv | cut -d , -f1 | xargs -I {} curl -L ${CONTEXT_API}/context/{}/?all=true | /usr/local/sbin/jq -r '.[]|"\(.id|split(":")[0]),\(.id),\(.label)"' > categories.csv
+cat categories.csv | cut -d , -f2 | sed 's/:/%3A/g'| xargs -I {} curl -L ${CONTEXT_API}/context/category/{}/?all=true | /usr/local/sbin/jq -r '.[]|"\(.id|split("::")[0])::\(.id|split("::")[1]),\(.id),\(.label)"' > concepts.csv
cat contexts.csv | sed 's/^\(.*\),\(.*\)/\1,\1::other,\2/' >> categories.csv
cat categories.csv | grep -v ::other | sed 's/^.*,\(.*\),\(.*\)/\1,\1::other,\2/' >> concepts.csv
--
2.17.1
From 60ebdf2dbe704733809f401df70bffcf49cede29 Mon Sep 17 00:00:00 2001
From: antleb <antleb@di.uoa.gr>
Date: Fri, 12 Mar 2021 16:34:53 +0200
Subject: [PATCH 7/8] update promote wf to support monitor&production
---
.../oa/graph/stats/oozie_app/impala-shell.sh | 18 --
.../scripts/updateProductionViews.sql | 207 ------------------
2 files changed, 225 deletions(-)
delete mode 100644 dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/impala-shell.sh
delete mode 100644 dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/updateProductionViews.sql
diff --git a/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/impala-shell.sh b/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/impala-shell.sh
deleted file mode 100644
index 70112dc7..00000000
--- a/dhp-workflows/dhp-stats-promote/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-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/updateProductionViews.sql b/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/updateProductionViews.sql
deleted file mode 100644
index 48f8d58f..00000000
--- a/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/scripts/updateProductionViews.sql
+++ /dev/null
@@ -1,207 +0,0 @@
-------------------------------------------------------
-------------------------------------------------------
--- Shadow schema table exchange
-------------------------------------------------------
-------------------------------------------------------
-
--- Dropping old views
-DROP VIEW IF EXISTS ${stats_db_production_name}.category;
-DROP VIEW IF EXISTS ${stats_db_production_name}.concept;
-DROP VIEW IF EXISTS ${stats_db_production_name}.context;
-DROP VIEW IF EXISTS ${stats_db_production_name}.country;
-DROP VIEW IF EXISTS ${stats_db_production_name}.countrygdp;
-DROP VIEW IF EXISTS ${stats_db_production_name}.creation_date;
-DROP VIEW IF EXISTS ${stats_db_production_name}.dataset;
-DROP VIEW IF EXISTS ${stats_db_production_name}.dataset_citations;
-DROP VIEW IF EXISTS ${stats_db_production_name}.dataset_classifications;
-DROP VIEW IF EXISTS ${stats_db_production_name}.dataset_concepts;
-DROP VIEW IF EXISTS ${stats_db_production_name}.dataset_datasources;
-DROP VIEW IF EXISTS ${stats_db_production_name}.dataset_languages;
-DROP VIEW IF EXISTS ${stats_db_production_name}.dataset_licenses;
-DROP VIEW IF EXISTS ${stats_db_production_name}.dataset_oids;
-DROP VIEW IF EXISTS ${stats_db_production_name}.dataset_pids;
-DROP VIEW IF EXISTS ${stats_db_production_name}.dataset_refereed;
-DROP VIEW IF EXISTS ${stats_db_production_name}.dataset_sources;
-DROP VIEW IF EXISTS ${stats_db_production_name}.dataset_topics;
-DROP VIEW IF EXISTS ${stats_db_production_name}.datasource;
-DROP VIEW IF EXISTS ${stats_db_production_name}.datasource_languages;
-DROP VIEW IF EXISTS ${stats_db_production_name}.datasource_oids;
-DROP VIEW IF EXISTS ${stats_db_production_name}.datasource_organizations;
-DROP VIEW IF EXISTS ${stats_db_production_name}.datasource_results;
-DROP VIEW IF EXISTS ${stats_db_production_name}.datasource_sources;
-DROP VIEW IF EXISTS ${stats_db_production_name}.funder;
-DROP VIEW IF EXISTS ${stats_db_production_name}.fundref;
-DROP VIEW IF EXISTS ${stats_db_production_name}.numbers_country;
-DROP VIEW IF EXISTS ${stats_db_production_name}.organization;
-DROP VIEW IF EXISTS ${stats_db_production_name}.organization_datasources;
-DROP VIEW IF EXISTS ${stats_db_production_name}.organization_pids;
-DROP VIEW IF EXISTS ${stats_db_production_name}.organization_projects;
-DROP VIEW IF EXISTS ${stats_db_production_name}.organization_sources;
-DROP VIEW IF EXISTS ${stats_db_production_name}.otherresearchproduct;
-DROP VIEW IF EXISTS ${stats_db_production_name}.otherresearchproduct_citations;
-DROP VIEW IF EXISTS ${stats_db_production_name}.otherresearchproduct_classifications;
-DROP VIEW IF EXISTS ${stats_db_production_name}.otherresearchproduct_concepts;
-DROP VIEW IF EXISTS ${stats_db_production_name}.otherresearchproduct_datasources;
-DROP VIEW IF EXISTS ${stats_db_production_name}.otherresearchproduct_languages;
-DROP VIEW IF EXISTS ${stats_db_production_name}.otherresearchproduct_licenses;
-DROP VIEW IF EXISTS ${stats_db_production_name}.otherresearchproduct_oids;
-DROP VIEW IF EXISTS ${stats_db_production_name}.otherresearchproduct_pids;
-DROP VIEW IF EXISTS ${stats_db_production_name}.otherresearchproduct_refereed;
-DROP VIEW IF EXISTS ${stats_db_production_name}.otherresearchproduct_sources;
-DROP VIEW IF EXISTS ${stats_db_production_name}.otherresearchproduct_topics;
-DROP VIEW IF EXISTS ${stats_db_production_name}.project;
-DROP VIEW IF EXISTS ${stats_db_production_name}.project_oids;
-DROP VIEW IF EXISTS ${stats_db_production_name}.project_organizations;
-DROP VIEW IF EXISTS ${stats_db_production_name}.project_results;
-DROP VIEW IF EXISTS ${stats_db_production_name}.project_resultcount;
-DROP VIEW IF EXISTS ${stats_db_production_name}.project_results_publication;
-DROP VIEW IF EXISTS ${stats_db_production_name}.publication;
-DROP VIEW IF EXISTS ${stats_db_production_name}.publication_citations;
-DROP VIEW IF EXISTS ${stats_db_production_name}.publication_classifications;
-DROP VIEW IF EXISTS ${stats_db_production_name}.publication_concepts;
-DROP VIEW IF EXISTS ${stats_db_production_name}.publication_datasources;
-DROP VIEW IF EXISTS ${stats_db_production_name}.publication_languages;
-DROP VIEW IF EXISTS ${stats_db_production_name}.publication_licenses;
-DROP VIEW IF EXISTS ${stats_db_production_name}.publication_oids;
-DROP VIEW IF EXISTS ${stats_db_production_name}.publication_pids;
-DROP VIEW IF EXISTS ${stats_db_production_name}.publication_refereed;
-DROP VIEW IF EXISTS ${stats_db_production_name}.publication_sources;
-DROP VIEW IF EXISTS ${stats_db_production_name}.publication_topics;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_affiliated_country;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_citations;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_classifications;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_concepts;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_datasources;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_deposited_country;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_fundercount;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_gold;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_greenoa;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_languages;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_licenses;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_oids;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_organization;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_peerreviewed;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_pids;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_projectcount;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_projects;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_refereed;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_sources;
-DROP VIEW IF EXISTS ${stats_db_production_name}.result_topics;
-DROP VIEW IF EXISTS ${stats_db_production_name}.rndexpediture;
-DROP VIEW IF EXISTS ${stats_db_production_name}.roarmap;
-DROP VIEW IF EXISTS ${stats_db_production_name}.software;
-DROP VIEW IF EXISTS ${stats_db_production_name}.software_citations;
-DROP VIEW IF EXISTS ${stats_db_production_name}.software_classifications;
-DROP VIEW IF EXISTS ${stats_db_production_name}.software_concepts;
-DROP VIEW IF EXISTS ${stats_db_production_name}.software_datasources;
-DROP VIEW IF EXISTS ${stats_db_production_name}.software_languages;
-DROP VIEW IF EXISTS ${stats_db_production_name}.software_licenses;
-DROP VIEW IF EXISTS ${stats_db_production_name}.software_oids;
-DROP VIEW IF EXISTS ${stats_db_production_name}.software_pids;
-DROP VIEW IF EXISTS ${stats_db_production_name}.software_refereed;
-DROP VIEW IF EXISTS ${stats_db_production_name}.software_sources;
-DROP VIEW IF EXISTS ${stats_db_production_name}.software_topics;
-
-
--- Creating the shadow database, in case it doesn't exist
-CREATE database IF NOT EXISTS ${stats_db_production_name};
-
--- Creating new views
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.category AS SELECT * FROM ${stats_db_name}.category;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.concept AS SELECT * FROM ${stats_db_name}.concept;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.context AS SELECT * FROM ${stats_db_name}.context;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.country AS SELECT * FROM ${stats_db_name}.country;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.countrygdp AS SELECT * FROM ${stats_db_name}.countrygdp;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.creation_date AS SELECT * FROM ${stats_db_name}.creation_date;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.dataset AS SELECT * FROM ${stats_db_name}.dataset;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.dataset_citations AS SELECT * FROM ${stats_db_name}.dataset_citations;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.dataset_classifications AS SELECT * FROM ${stats_db_name}.dataset_classifications;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.dataset_concepts AS SELECT * FROM ${stats_db_name}.dataset_concepts;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.dataset_datasources AS SELECT * FROM ${stats_db_name}.dataset_datasources;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.dataset_languages AS SELECT * FROM ${stats_db_name}.dataset_languages;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.dataset_licenses AS SELECT * FROM ${stats_db_name}.dataset_licenses;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.dataset_oids AS SELECT * FROM ${stats_db_name}.dataset_oids;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.dataset_pids AS SELECT * FROM ${stats_db_name}.dataset_pids;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.dataset_refereed AS SELECT * FROM ${stats_db_name}.dataset_refereed;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.dataset_sources AS SELECT * FROM ${stats_db_name}.dataset_sources;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.dataset_topics AS SELECT * FROM ${stats_db_name}.dataset_topics;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.datasource AS SELECT * FROM ${stats_db_name}.datasource;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.datasource_languages AS SELECT * FROM ${stats_db_name}.datasource_languages;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.datasource_oids AS SELECT * FROM ${stats_db_name}.datasource_oids;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.datasource_organizations AS SELECT * FROM ${stats_db_name}.datasource_organizations;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.datasource_results AS SELECT * FROM ${stats_db_name}.datasource_results;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.datasource_sources AS SELECT * FROM ${stats_db_name}.datasource_sources;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.funder AS SELECT * FROM ${stats_db_name}.funder;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.fundref AS SELECT * FROM ${stats_db_name}.fundref;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.numbers_country AS SELECT * FROM ${stats_db_name}.numbers_country;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.organization AS SELECT * FROM ${stats_db_name}.organization;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.organization_datasources AS SELECT * FROM ${stats_db_name}.organization_datasources;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.organization_pids AS SELECT * FROM ${stats_db_name}.organization_pids;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.organization_projects AS SELECT * FROM ${stats_db_name}.organization_projects;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.organization_sources AS SELECT * FROM ${stats_db_name}.organization_sources;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.otherresearchproduct AS SELECT * FROM ${stats_db_name}.otherresearchproduct;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.otherresearchproduct_citations AS SELECT * FROM ${stats_db_name}.otherresearchproduct_citations;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.otherresearchproduct_classifications AS SELECT * FROM ${stats_db_name}.otherresearchproduct_classifications;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.otherresearchproduct_concepts AS SELECT * FROM ${stats_db_name}.otherresearchproduct_concepts;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.otherresearchproduct_datasources AS SELECT * FROM ${stats_db_name}.otherresearchproduct_datasources;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.otherresearchproduct_languages AS SELECT * FROM ${stats_db_name}.otherresearchproduct_languages;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.otherresearchproduct_licenses AS SELECT * FROM ${stats_db_name}.otherresearchproduct_licenses;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.otherresearchproduct_oids AS SELECT * FROM ${stats_db_name}.otherresearchproduct_oids;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.otherresearchproduct_pids AS SELECT * FROM ${stats_db_name}.otherresearchproduct_pids;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.otherresearchproduct_refereed AS SELECT * FROM ${stats_db_name}.otherresearchproduct_refereed;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.otherresearchproduct_sources AS SELECT * FROM ${stats_db_name}.otherresearchproduct_sources;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.otherresearchproduct_topics AS SELECT * FROM ${stats_db_name}.otherresearchproduct_topics;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.project AS SELECT * FROM ${stats_db_name}.project;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.project_oids AS SELECT * FROM ${stats_db_name}.project_oids;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.project_organizations AS SELECT * FROM ${stats_db_name}.project_organizations;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.project_results AS SELECT * FROM ${stats_db_name}.project_results;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.project_resultcount AS SELECT * FROM ${stats_db_name}.project_resultcount;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.project_results_publication AS SELECT * FROM ${stats_db_name}.project_results_publication;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.publication AS SELECT * FROM ${stats_db_name}.publication;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.publication_citations AS SELECT * FROM ${stats_db_name}.publication_citations;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.publication_classifications AS SELECT * FROM ${stats_db_name}.publication_classifications;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.publication_concepts AS SELECT * FROM ${stats_db_name}.publication_concepts;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.publication_datasources AS SELECT * FROM ${stats_db_name}.publication_datasources;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.publication_languages AS SELECT * FROM ${stats_db_name}.publication_languages;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.publication_licenses AS SELECT * FROM ${stats_db_name}.publication_licenses;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.publication_oids AS SELECT * FROM ${stats_db_name}.publication_oids;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.publication_pids AS SELECT * FROM ${stats_db_name}.publication_pids;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.publication_refereed AS SELECT * FROM ${stats_db_name}.publication_refereed;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.publication_sources AS SELECT * FROM ${stats_db_name}.publication_sources;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.publication_topics AS SELECT * FROM ${stats_db_name}.publication_topics;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result AS SELECT * FROM ${stats_db_name}.result;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_affiliated_country AS SELECT * FROM ${stats_db_name}.result_affiliated_country;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_citations AS SELECT * FROM ${stats_db_name}.result_citations;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_classifications AS SELECT * FROM ${stats_db_name}.result_classifications;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_concepts AS SELECT * FROM ${stats_db_name}.result_concepts;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_datasources AS SELECT * FROM ${stats_db_name}.result_datasources;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_deposited_country AS SELECT * FROM ${stats_db_name}.result_deposited_country;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_fundercount AS SELECT * FROM ${stats_db_name}.result_fundercount;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_gold AS SELECT * FROM ${stats_db_name}.result_gold;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_greenoa AS SELECT * FROM ${stats_db_name}.result_greenoa;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_languages AS SELECT * FROM ${stats_db_name}.result_languages;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_licenses AS SELECT * FROM ${stats_db_name}.result_licenses;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_oids AS SELECT * FROM ${stats_db_name}.result_oids;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_organization AS SELECT * FROM ${stats_db_name}.result_organization;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_peerreviewed AS SELECT * FROM ${stats_db_name}.result_peerreviewed;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_pids AS SELECT * FROM ${stats_db_name}.result_pids;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_projectcount AS SELECT * FROM ${stats_db_name}.result_projectcount;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_projects AS SELECT * FROM ${stats_db_name}.result_projects;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_refereed AS SELECT * FROM ${stats_db_name}.result_refereed;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_sources AS SELECT * FROM ${stats_db_name}.result_sources;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.result_topics AS SELECT * FROM ${stats_db_name}.result_topics;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.rndexpediture AS SELECT * FROM ${stats_db_name}.rndexpediture;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.roarmap AS SELECT * FROM ${stats_db_name}.roarmap;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.software AS SELECT * FROM ${stats_db_name}.software;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.software_citations AS SELECT * FROM ${stats_db_name}.software_citations;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.software_classifications AS SELECT * FROM ${stats_db_name}.software_classifications;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.software_concepts AS SELECT * FROM ${stats_db_name}.software_concepts;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.software_datasources AS SELECT * FROM ${stats_db_name}.software_datasources;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.software_languages AS SELECT * FROM ${stats_db_name}.software_languages;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.software_licenses AS SELECT * FROM ${stats_db_name}.software_licenses;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.software_oids AS SELECT * FROM ${stats_db_name}.software_oids;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.software_pids AS SELECT * FROM ${stats_db_name}.software_pids;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.software_refereed AS SELECT * FROM ${stats_db_name}.software_refereed;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.software_sources AS SELECT * FROM ${stats_db_name}.software_sources;
-CREATE VIEW IF NOT EXISTS ${stats_db_production_name}.software_topics AS SELECT * FROM ${stats_db_name}.software_topics;
--
2.17.1
From 0ba0a6b9dac25f5ec73e8eafefbf7f91442ad1c5 Mon Sep 17 00:00:00 2001
From: antleb <antleb@di.uoa.gr>
Date: Fri, 12 Mar 2021 16:42:59 +0200
Subject: [PATCH 8/8] update promote wf to support monitor&production
---
.../stats/oozie_app/updateProductionViews.sh | 14 +++----
.../dhp/oa/graph/stats/oozie_app/workflow.xml | 37 ++++++++++++-------
2 files changed, 29 insertions(+), 22 deletions(-)
diff --git a/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/updateProductionViews.sh b/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/updateProductionViews.sh
index 57acb2ee..3e510e87 100644
--- a/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/updateProductionViews.sh
+++ b/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/updateProductionViews.sh
@@ -7,12 +7,10 @@ then
fi
export SOURCE=$1
-export SHADOW=$2
+export PRODUCTION=$2
-echo "Updating shadow database"
-impala-shell -d ${SOURCE} -q "invalidate metadata"
-impala-shell -d ${SOURCE} -q "show tables" --delimited | sed "s/^\(.*\)/compute stats ${SOURCE}.\1;/" | impala-shell -c -f -
-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 -c -f -
-impala-shell -d ${SOURCE} -q "show tables" --delimited | sed "s/\(.*\)/create view ${SHADOW}.\1 as select * from ${SOURCE}.\1;/" | impala-shell -c -f -
-echo "Shadow db ready!"
\ No newline at end of file
+echo "Updating ${PRODUCTION} database"
+impala-shell -q "create database if not exists ${PRODUCTION}"
+impala-shell -d ${PRODUCTION} -q "show tables" --delimited | sed "s/^/drop view if exists ${PRODUCTION}./" | sed "s/$/;/" | impala-shell -c -f -
+impala-shell -d ${SOURCE} -q "show tables" --delimited | sed "s/\(.*\)/create view ${PRODUCTION}.\1 as select * from ${SOURCE}.\1;/" | impala-shell -c -f -
+echo "Production db ready!"
\ No newline at end of file
diff --git a/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml b/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml
index d744f18d..0d8ff7ee 100644
--- a/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml
+++ b/dhp-workflows/dhp-stats-promote/src/main/resources/eu/dnetlib/dhp/oa/graph/stats/oozie_app/workflow.xml
@@ -6,7 +6,15 @@
</property>
<property>
<name>stats_db_production_name</name>
- <description>the name of the production schema</description>
+ <description>the name of the public production schema</description>
+ </property>
+ <property>
+ <name>monitor_db_name</name>
+ <description>the monitor database name</description>
+ </property>
+ <property>
+ <name>monitor_db_production_name</name>
+ <description>the name of the monitor public database</description>
</property>
<property>
<name>stats_tool_api_url</name>
@@ -48,25 +56,26 @@
</kill>
<action name="updateProductionViews">
- <hive2 xmlns="uri:oozie:hive2-action:0.1">
- <jdbc-url>${hive_jdbc_url}</jdbc-url>
- <script>scripts/updateProductionViews.sql</script>
- <param>stats_db_name=${stats_db_name}</param>
- <param>stats_db_production_name=${stats_db_production_name}</param>
- </hive2>
- <ok to="computeProductionStats"/>
+ <shell xmlns="uri:oozie:shell-action:0.1">
+ <job-tracker>${jobTracker}</job-tracker>
+ <name-node>${nameNode}</name-node>
+ <exec>updateProductionViews.sh</exec>
+ <argument>${stats_db_name}</argument>
+ <argument>${stats_db_production_name}</argument>
+ <file>updateProductionViews.sh</file>
+ </shell>
+ <ok to="updateMonitorViews"/>
<error to="Kill"/>
</action>
- <action name="computeProductionStats">
+ <action name="updateMonitorViews">
<shell xmlns="uri:oozie:shell-action:0.1">
<job-tracker>${jobTracker}</job-tracker>
<name-node>${nameNode}</name-node>
- <exec>impala-shell.sh</exec>
- <argument>${stats_db_production_name}</argument>
- <argument>computeProductionStats.sql</argument>
- <argument>${wf:appPath()}/scripts/computeProductionStats.sql</argument>
- <file>impala-shell.sh</file>
+ <exec>updateProductionViews.sh</exec>
+ <argument>${monitor_db_name}</argument>
+ <argument>${monitor_db_production_name}</argument>
+ <file>updateProductionViews.sh</file>
</shell>
<ok to="promoteCache"/>
<error to="Kill"/>
--
2.17.1

View File

@ -42,6 +42,8 @@ public class Constants {
public static final String RETRY_DELAY = "retryDelay";
public static final String CONNECT_TIMEOUT = "connectTimeOut";
public static final String READ_TIMEOUT = "readTimeOut";
public static final String FROM_DATE_OVERRIDE = "fromDateOverride";
public static final String UNTIL_DATE_OVERRIDE = "untilDateOverride";
public static final String CONTENT_TOTALITEMS = "TotalItems";
public static final String CONTENT_INVALIDRECORDS = "InvalidRecords";

View File

@ -4,6 +4,7 @@ package eu.dnetlib.dhp.schema.oaf;
import java.util.*;
import java.util.function.Function;
import java.util.stream.Collectors;
import java.util.stream.Stream;
import org.apache.commons.lang3.StringUtils;
@ -22,6 +23,9 @@ public class CleaningFunctions {
public static final String CLEANING_REGEX = "(?:\\n|\\r|\\t)";
public static final Set<String> PID_BLACKLIST = new HashSet<>();
public static final String INVALID_AUTHOR_REGEX = ".*deactivated.*";
public static final String TITLE_FILTER_REGEX = "[.*test.*\\W\\d]";
public static final int TITLE_FILTER_RESIDUAL_LENGTH = 10;
static {
PID_BLACKLIST.add("none");
@ -80,6 +84,36 @@ public class CleaningFunctions {
return value;
}
public static <T extends Oaf> boolean filter(T value) {
if (value instanceof Datasource) {
// nothing to evaluate here
} else if (value instanceof Project) {
// nothing to evaluate here
} else if (value instanceof Organization) {
// nothing to evaluate here
} else if (value instanceof Relation) {
// nothing to clean here
} else if (value instanceof Result) {
Result r = (Result) value;
if (Objects.nonNull(r.getTitle()) && r.getTitle().isEmpty()) {
return false;
}
if (value instanceof Publication) {
} else if (value instanceof eu.dnetlib.dhp.schema.oaf.Dataset) {
} else if (value instanceof OtherResearchProduct) {
} else if (value instanceof Software) {
}
}
return true;
}
public static <T extends Oaf> T cleanup(T value) {
if (value instanceof Datasource) {
// nothing to clean here
@ -124,6 +158,12 @@ public class CleaningFunctions {
.stream()
.filter(Objects::nonNull)
.filter(sp -> StringUtils.isNotBlank(sp.getValue()))
.filter(
sp -> sp
.getValue()
.toLowerCase()
.replaceAll(TITLE_FILTER_REGEX, "")
.length() > TITLE_FILTER_RESIDUAL_LENGTH)
.map(CleaningFunctions::cleanValue)
.collect(Collectors.toList()));
}
@ -199,16 +239,7 @@ public class CleaningFunctions {
}
}
if (Objects.nonNull(r.getAuthor())) {
boolean nullRank = r
.getAuthor()
.stream()
.anyMatch(a -> Objects.isNull(a.getRank()));
if (nullRank) {
int i = 1;
for (Author author : r.getAuthor()) {
author.setRank(i++);
}
}
final List<Author> authors = Lists.newArrayList();
for (Author a : r.getAuthor()) {
if (Objects.isNull(a.getPid())) {
a.setPid(Lists.newArrayList());
@ -235,7 +266,26 @@ public class CleaningFunctions {
.stream()
.collect(Collectors.toList()));
}
if (StringUtils.isBlank(a.getFullname())) {
if (StringUtils.isNotBlank(a.getName()) && StringUtils.isNotBlank(a.getSurname())) {
a.setFullname(a.getSurname() + ", " + a.getName());
}
}
if (StringUtils.isNotBlank(a.getFullname()) && isValidAuthorName(a)) {
authors.add(a);
}
}
boolean nullRank = authors
.stream()
.anyMatch(a -> Objects.isNull(a.getRank()));
if (nullRank) {
int i = 1;
for (Author author : authors) {
author.setRank(i++);
}
}
r.setAuthor(authors);
}
if (value instanceof Publication) {
@ -252,6 +302,15 @@ public class CleaningFunctions {
return value;
}
private static boolean isValidAuthorName(Author a) {
return !Stream
.of(a.getFullname(), a.getName(), a.getSurname())
.filter(s -> s != null && !s.isEmpty())
.collect(Collectors.joining(""))
.toLowerCase()
.matches(INVALID_AUTHOR_REGEX);
}
private static List<StructuredProperty> processPidCleaning(List<StructuredProperty> pids) {
return pids
.stream()

View File

@ -0,0 +1,206 @@
package eu.dnetlib.dhp.transformation.xslt;
import static eu.dnetlib.dhp.transformation.xslt.XSLTTransformationFunction.QNAME_BASE_URI;
import java.io.Serializable;
// import java.nio.charset.Charset;
import java.nio.charset.StandardCharsets;
import java.text.Normalizer;
import java.util.List;
import java.util.Set;
import com.google.common.base.Joiner;
import com.google.common.base.Splitter;
import com.google.common.collect.Iterables;
import com.google.common.collect.Lists;
import com.google.common.hash.Hashing;
import eu.dnetlib.dhp.transformation.xslt.utils.Capitalize;
import eu.dnetlib.dhp.transformation.xslt.utils.DotAbbreviations;
import net.sf.saxon.s9api.ExtensionFunction;
import net.sf.saxon.s9api.ItemType;
import net.sf.saxon.s9api.OccurrenceIndicator;
import net.sf.saxon.s9api.QName;
import net.sf.saxon.s9api.SaxonApiException;
import net.sf.saxon.s9api.SequenceType;
import net.sf.saxon.s9api.XdmValue;
//import eu.dnetlib.pace.clustering.NGramUtils;
//import eu.dnetlib.pace.util.Capitalise;
//import eu.dnetlib.pace.util.DotAbbreviations;
public class PersonCleaner implements ExtensionFunction, Serializable {
/**
*
*/
private static final long serialVersionUID = 1L;
private List<String> firstname = Lists.newArrayList();
private List<String> surname = Lists.newArrayList();
private List<String> fullname = Lists.newArrayList();
private static Set<String> particles = null;
public PersonCleaner() {
}
public String normalize(String s) {
s = Normalizer.normalize(s, Normalizer.Form.NFD); // was NFD
s = s.replaceAll("\\(.+\\)", "");
s = s.replaceAll("\\[.+\\]", "");
s = s.replaceAll("\\{.+\\}", "");
s = s.replaceAll("\\s+-\\s+", "-");
// s = s.replaceAll("[\\W&&[^,-]]", " ");
// System.out.println("class Person: s: " + s);
// s = s.replaceAll("[\\p{InCombiningDiacriticalMarks}&&[^,-]]", " ");
s = s.replaceAll("[\\p{Punct}&&[^-,]]", " ");
s = s.replace("\\d", " ");
s = s.replace("\\n", " ");
s = s.replace("\\.", " ");
s = s.replaceAll("\\s+", " ");
if (s.contains(",")) {
// System.out.println("class Person: s: " + s);
String[] arr = s.split(",");
if (arr.length == 1) {
fullname = splitTerms(arr[0]);
} else if (arr.length > 1) {
surname = splitTerms(arr[0]);
firstname = splitTermsFirstName(arr[1]);
// System.out.println("class Person: surname: " + surname);
// System.out.println("class Person: firstname: " + firstname);
fullname.addAll(surname);
fullname.addAll(firstname);
}
} else {
fullname = splitTerms(s);
int lastInitialPosition = fullname.size();
boolean hasSurnameInUpperCase = false;
for (int i = 0; i < fullname.size(); i++) {
String term = fullname.get(i);
if (term.length() == 1) {
lastInitialPosition = i;
} else if (term.equals(term.toUpperCase())) {
hasSurnameInUpperCase = true;
}
}
if (lastInitialPosition < fullname.size() - 1) { // Case: Michele G. Artini
firstname = fullname.subList(0, lastInitialPosition + 1);
System.out.println("name: " + firstname);
surname = fullname.subList(lastInitialPosition + 1, fullname.size());
} else if (hasSurnameInUpperCase) { // Case: Michele ARTINI
for (String term : fullname) {
if (term.length() > 1 && term.equals(term.toUpperCase())) {
surname.add(term);
} else {
firstname.add(term);
}
}
} else if (lastInitialPosition == fullname.size()) {
surname = fullname.subList(lastInitialPosition - 1, fullname.size());
firstname = fullname.subList(0, lastInitialPosition - 1);
}
}
return null;
}
private List<String> splitTermsFirstName(String s) {
List<String> list = Lists.newArrayList();
for (String part : Splitter.on(" ").omitEmptyStrings().split(s)) {
if (s.trim().matches("\\p{Lu}{2,3}")) {
String[] parts = s.trim().split("(?=\\p{Lu})"); // (Unicode UpperCase)
for (String p : parts) {
if (p.length() > 0)
list.add(p);
}
} else {
list.add(part);
}
}
return list;
}
private List<String> splitTerms(String s) {
if (particles == null) {
// particles = NGramUtils.loadFromClasspath("/eu/dnetlib/pace/config/name_particles.txt");
}
List<String> list = Lists.newArrayList();
for (String part : Splitter.on(" ").omitEmptyStrings().split(s)) {
// if (!particles.contains(part.toLowerCase())) {
list.add(part);
// }
}
return list;
}
public List<String> getFirstname() {
return firstname;
}
public List<String> getSurname() {
return surname;
}
public List<String> getFullname() {
return fullname;
}
public String hash() {
return Hashing.murmur3_128().hashString(getNormalisedFullname(), StandardCharsets.UTF_8).toString();
}
public String getNormalisedFullname() {
return isAccurate() ? Joiner.on(" ").join(getSurname()) + ", " + Joiner.on(" ").join(getNameWithAbbreviations())
: Joiner.on(" ").join(fullname);
// return isAccurate() ?
// Joiner.on(" ").join(getCapitalSurname()) + ", " + Joiner.on(" ").join(getNameWithAbbreviations()) :
// Joiner.on(" ").join(fullname);
}
public List<String> getCapitalSurname() {
return Lists.newArrayList(Iterables.transform(surname, new Capitalize()));
}
public List<String> getNameWithAbbreviations() {
return Lists.newArrayList(Iterables.transform(firstname, new DotAbbreviations()));
}
public boolean isAccurate() {
return (firstname != null && surname != null && !firstname.isEmpty() && !surname.isEmpty());
}
@Override
public QName getName() {
return new QName(QNAME_BASE_URI + "/person", "person");
}
@Override
public SequenceType getResultType() {
return SequenceType.makeSequenceType(ItemType.STRING, OccurrenceIndicator.ZERO_OR_ONE);
}
@Override
public SequenceType[] getArgumentTypes() {
// TODO Auto-generated method stub
return null;
}
@Override
public XdmValue call(XdmValue[] arguments) throws SaxonApiException {
// TODO Auto-generated method stub
return null;
}
}

View File

@ -46,6 +46,7 @@ public class XSLTTransformationFunction implements MapFunction<MetadataRecord, M
Processor processor = new Processor(false);
processor.registerExtensionFunction(cleanFunction);
processor.registerExtensionFunction(new DateCleaner());
processor.registerExtensionFunction(new PersonCleaner());
final XsltCompiler comp = processor.newXsltCompiler();
XsltExecutable xslt = comp

View File

@ -0,0 +1,14 @@
package eu.dnetlib.dhp.transformation.xslt.utils;
// import org.apache.commons.text.WordUtils;
// import org.apache.commons.text.WordUtils;
import com.google.common.base.Function;
public class Capitalize implements Function<String, String> {
@Override
public String apply(String s) {
return org.apache.commons.lang3.text.WordUtils.capitalize(s.toLowerCase());
}
}

View File

@ -0,0 +1,12 @@
package eu.dnetlib.dhp.transformation.xslt.utils;
import com.google.common.base.Function;
public class DotAbbreviations implements Function<String, String> {
@Override
public String apply(String s) {
return s.length() == 1 ? s + "." : s;
}
}

View File

@ -92,15 +92,18 @@ public class TransformationJobTest extends AbstractVocabularyTest {
}
@Test
@DisplayName("Test Transform Inst.&Them.v4 record XML with xslt_cleaning_oaiOpenaire_datacite_ExchangeLandingpagePid")
public void testTransformITGv4() throws Exception {
@DisplayName("Test Transform record XML with xslt_cleaning_datarepo_datacite/oaiOpenAIRE")
public void testTransformMostlyUsedScript() throws Exception {
String xslTransformationScript = "";
xslTransformationScript = "/eu/dnetlib/dhp/transform/scripts/xslt_cleaning_datarepo_datacite.xsl";
xslTransformationScript = "/eu/dnetlib/dhp/transform/scripts/xslt_cleaning_oaiOpenaire_datacite_ExchangeLandingpagePid.xsl";
// We Set the input Record getting the XML from the classpath
final MetadataRecord mr = new MetadataRecord();
mr.setBody(IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/transform/input_itgv4.xml")));
// We Load the XSLT transformation Rule from the classpath
XSLTTransformationFunction tr = loadTransformationRule(
"/eu/dnetlib/dhp/transform/scripts/xslt_cleaning_oaiOpenaire_datacite_ExchangeLandingpagePid.xsl");
XSLTTransformationFunction tr = loadTransformationRule(xslTransformationScript);
MetadataRecord result = tr.call(mr);
@ -110,15 +113,17 @@ public class TransformationJobTest extends AbstractVocabularyTest {
}
@Test
@DisplayName("Test Transform record XML with xslt_cleaning_datarepo_datacite")
public void testTransformMostlyUsedScript() throws Exception {
@DisplayName("Test Transform record XML with xslt_cleaning_REST_OmicsDI")
public void testTransformRestScript() throws Exception {
String xslTransformationScript = "";
xslTransformationScript = "/eu/dnetlib/dhp/transform/scripts/xslt_cleaning_REST_OmicsDI.xsl";
// We Set the input Record getting the XML from the classpath
final MetadataRecord mr = new MetadataRecord();
mr.setBody(IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/transform/input_itgv4.xml")));
mr.setBody(IOUtils.toString(getClass().getResourceAsStream("/eu/dnetlib/dhp/transform/input_omicsdi.xml")));
// We Load the XSLT transformation Rule from the classpath
XSLTTransformationFunction tr = loadTransformationRule(
"/eu/dnetlib/dhp/transform/scripts/xslt_cleaning_datarepo_datacite.xsl");
XSLTTransformationFunction tr = loadTransformationRule(xslTransformationScript);
MetadataRecord result = tr.call(mr);

View File

@ -0,0 +1,60 @@
<?xml version="1.0" encoding="UTF-8"?>
<oai:record xmlns="http://namespace.openaire.eu/"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:dri="http://www.driver-repository.eu/namespace/dri"
xmlns:oaf="http://namespace.openaire.eu/oaf"
xmlns:oai="http://www.openarchives.org/OAI/2.0/"
xmlns:prov="http://www.openarchives.org/OAI/2.0/provenance" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">
<oai:header>
<dri:objIdentifier>_____OmicsDI::0000337c02d1b51030675d69407655da</dri:objIdentifier>
<dri:recordIdentifier>PRJNA78295</dri:recordIdentifier>
<dri:dateOfCollection>2020-10-31T15:31:30.725Z</dri:dateOfCollection>
<oaf:datasourceprefix>_____OmicsDI</oaf:datasourceprefix>
</oai:header>
<oai:metadata>
<datasets xmlns="">
<connectionsCountScaled>0.235294117647059</connectionsCountScaled>
<reanalysisCount>0</reanalysisCount>
<keywords>null</keywords>
<citationsCountScaled>0.0</citationsCountScaled>
<viewsCount>0</viewsCount>
<description>Sedimentitalea nanhaiensis DSM 24252 Genome sequencing and assembly</description>
<downloadCountScaled>8.20101314054644E-5</downloadCountScaled>
<source>omics_ena_project</source>
<title>Sedimentitalea nanhaiensis DSM 24252</title>
<connectionsCount>14</connectionsCount>
<citationsCount>0</citationsCount>
<score>null</score>
<omicsType>Genomics</omicsType>
<reanalysisCountScaled>0.0</reanalysisCountScaled>
<organisms>
<acc>571166</acc>
<name>Sedimentitalea nanhaiensis DSM 24252</name>
</organisms>
<viewsCountScaled>0.0</viewsCountScaled>
<claimable>false</claimable>
<id>PRJNA78295</id>
<publicationDate>null</publicationDate>
<downloadCount>13</downloadCount>
</datasets>
</oai:metadata>
<about xmlns="">
<provenance xmlns="http://www.openarchives.org/OAI/2.0/provenance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/provenance http://www.openarchives.org/OAI/2.0/provenance.xsd">
<originDescription altered="true" harvestDate="2020-10-31T15:31:30.725Z">
<baseURL>https%3A%2F%2Fwww.omicsdi.org%2Fws%2Fdataset%2Fsearch</baseURL>
<identifier/>
<datestamp/>
<metadataNamespace/>
</originDescription>
</provenance>
<oaf:datainfo>
<oaf:inferred>false</oaf:inferred>
<oaf:deletedbyinference>false</oaf:deletedbyinference>
<oaf:trust>0.9</oaf:trust>
<oaf:inferenceprovenance/>
<oaf:provenanceaction classid="sysimport:crosswalk:datasetarchive"
classname="sysimport:crosswalk:datasetarchive"
schemeid="dnet:provenanceActions" schemename="dnet:provenanceActions"/>
</oaf:datainfo>
</about>
</oai:record>

View File

@ -0,0 +1,297 @@
<!-- complete literature v4: xslt_cleaning_REST_OmicsDI ; transformation script production , 2021-03-17 -->
<xsl:stylesheet xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
version="2.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xmlns:oaf="http://namespace.openaire.eu/oaf"
xmlns:dr="http://www.driver-repository.eu/namespace/dr"
xmlns:datacite="http://datacite.org/schema/kernel-4"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:dri="http://www.driver-repository.eu/namespace/dri"
xmlns:oaire="http://namespace.openaire.eu/schema/oaire/"
xmlns:xs="http://www.w3.org/2001/XMLSchema"
xmlns:vocabulary="http://eu/dnetlib/transform/clean"
xmlns:dateCleaner="http://eu/dnetlib/transform/dateISO"
xmlns:personCleaner="http://eu/dnetlib/transform/person"
exclude-result-prefixes="xsl vocabulary dateCleaner personCleaner">
<xsl:param name="varOfficialName" />
<xsl:param name="varDsType" />
<xsl:param name="varDataSourceId" />
<xsl:param name="index" select="0"/>
<xsl:param name="transDate" select="current-dateTime()"/>
<xsl:variable name="vCodes">
<codes>
<code source="arrayexpress-repository" id="re3data_____::r3d100010222" name="ArrayExpress Archive of Functional Genomics Data" sourceUrl="https://www.ebi.ac.uk/arrayexpress/" urlTemplate="https://www.ebi.ac.uk/arrayexpress/experiments/" />
<code source="atlas-experiments" id="re3data_____::r3d100010223" name="Expression Atlas Database" sourceUrl="http://www.ebi.ac.uk/gxa/home" urlTemplate="" />
<code source="biomodels" id="re3data_____::r3d100010789" name="BioModels Database" sourceUrl="https://www.ebi.ac.uk/biomodels-main/" urlTemplate="" />
<code source="dbgap" id="re3data_____::r3d100010788" name="dbGaP (database of Genotypes and Phenotypes)" sourceUrl="https://www.ncbi.nlm.nih.gov/gap" urlTemplate="" />
<code source="ega" id="re3data_____::r3d100011242" name="EGA Database (European Genome-phenome Archive)" sourceUrl="https://ega-archive.org" urlTemplate="" />
<code source="eva" id="re3data_____::r3d100011553" name="EVA database (European Variation Archive)" sourceUrl="https://www.ebi.ac.uk/eva/" urlTemplate="" />
<code source="geo" id="re3data_____::r3d100010283" name="GEO (Gene Expression Omnibus)" sourceUrl="https://www.ncbi.nlm.nih.gov/geo/" urlTemplate="https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=" />
<code source="gnps" id="omicsdi_____::gnps" name="GNPS Database (Global Natural Products Social Molecular Networking)" sourceUrl="https://gnps.ucsd.edu/ProteoSAFe/static/gnps-splash2.jsp" urlTemplate="" />
<code source="gpmdb" id="re3data_____::r3d100010883" name="GPMDB (Global Proteome Machine)" sourceUrl="http://gpmdb.thegpm.org/" urlTemplate="http://gpmdb.thegpm.org/~/dblist_gpmnum/gpmnum=" />
<code source="jpost" id="re3data_____::r3d100012349" name="JPOST Repository (Japan ProteOme STandard Repository/Database)" sourceUrl="https://jpostdb.org/" urlTemplate="https://repository.jpostdb.org/entry/JPST000228" />
<code source="lincs" id="re3data_____::r3d100011833" name="LINCS (Big Data to Knowledge / Library of Integrated Network-based Cellular Signatures)" sourceUrl="http://lincsportal.ccs.miami.edu/dcic-portal/" urlTemplate="http://lincsportal.ccs.miami.edu/datasets/#/view/" />
<code source="massive" id="omicsdi_____::massive" name="MassIVE Database (Mass Spectrometry Interactive Virtual Environment)" sourceUrl="https://massive.ucsd.edu/ProteoSAFe/datasets.jsp" urlTemplate="" />
<code source="metabolights_dataset" id="opendoar____::2970" name="MetaboLights Database" sourceUrl="http://www.ebi.ac.uk/metabolights/" urlTemplate="" />
<code source="metabolome_express" id="omicsdi_____::metabolome" name="MetabolomeExpress" sourceUrl="https://www.metabolome-express.org/" urlTemplate="https://www.metabolome-express.org/datasetview.php?datasetid=" />
<code source="metabolomics_workbench" id="re3data_____::r3d100012314" name="Metabolomics Workbench Database" sourceUrl="http://www.metabolomicsworkbench.org/" urlTemplate="http://www.metabolomicsworkbench.org/data/DRCCMetadata.php?StudyID=" />
<code source="NCBI" id="omicsdi_____::ncbi" name="NCBI" sourceUrl="https://www.ncbi.nlm.nih.gov/bioproject/" urlTemplate="https://www.ncbi.nlm.nih.gov/bioproject/" />
<code source="omics_ena_project" id="re3data_____::r3d100010527" name="ENA (European Nucleotide Archive)" sourceUrl="https://www.ebi.ac.uk/ena" urlTemplate="https://www.ebi.ac.uk/ena/data/view/" />
<code source="paxdb" id="omicsdi_____::paxdb" name="PAXDB (protein abundance database)" sourceUrl="http://pax-db.org/" urlTemplate="" />
<code source="peptide_atlas" id="re3data_____::r3d100010889" name="PeptideAtlas Database" sourceUrl="http://www.peptideatlas.org/" urlTemplate="" />
<code source="pride" id="re3data_____::r3d100010137" name="PRIDE Database (PRoteomics IDEntifications)" sourceUrl="http://www.ebi.ac.uk/pride/archive/" urlTemplate="http://www.ebi.ac.uk/pride/archive/projects/PXD008134" />
</codes>
</xsl:variable>
<!--
gnps, jpost, massive, metabolome_express, paxdb: no id/OpenAIRE-entry found
ncbi: several OpenAIRE-entries found - is one the right?
-->
<xsl:key name="kCodeByName" match="code" use="string(@source)"/>
<xsl:template match="/">
<xsl:variable name="datasourcePrefix"
select="normalize-space(//oaf:datasourceprefix)" />
<xsl:call-template name="validRecord" />
</xsl:template>
<xsl:template name="terminate">
<xsl:message terminate="yes">
record is not compliant, transformation is interrupted.
</xsl:message>
</xsl:template>
<xsl:template name="validRecord">
<record>
<xsl:apply-templates select="//*[local-name() = 'header']" />
<metadata>
<!--
<xsl:apply-templates select="//*[local-name() = 'metadata']//*[local-name() = 'datasets']"/>
-->
<datacite:resource>
<!-- OmicsDI does not state: languages, projects,
-->
<!-- landing page -->
<xsl:if test="//*[local-name() = 'datasourceprefix'][.='_____OmicsDI']">
<datacite:alternateIdentifiers>
<datacite:alternateIdentifier>
<xsl:attribute name="alternateIdentifierType">
<xsl:value-of select="'LandingPage'"/>
</xsl:attribute>
<xsl:choose>
<xsl:when test="//*[local-name() = 'source'][. = ('gnps','massive','paxdb','peptide_atlas')]">
<xsl:value-of select="concat('https://www.omicsdi.org/#/dataset/', //*[local-name() = 'source'], '/', //*[local-name() = 'id'])"/>
</xsl:when>
<xsl:when test="//*[local-name() = 'source'][. = 'metabolome_express']">
<xsl:value-of select="concat(key('kCodeByName', string(//*[local-name()='source']), $vCodes)/@urlTemplate, substring-after(//*[local-name()='id'], 'MEX'))"/>
</xsl:when>
<xsl:otherwise>
<xsl:value-of select="concat(key('kCodeByName', string(//*[local-name()='source']), $vCodes)/@urlTemplate, //*[local-name()='id'])"/>
</xsl:otherwise>
</xsl:choose>
</datacite:alternateIdentifier>
<datacite:alternateIdentifier>
<xsl:attribute name="alternateIdentifierType">
<xsl:value-of select="'local'"/>
</xsl:attribute>
<xsl:value-of select="//*[local-name()='id']"/>
</datacite:alternateIdentifier>
</datacite:alternateIdentifiers>
</xsl:if>
<!-- identifier; ... -->
<!-- URL hindered by _et_: https://www.omicsdi.org/ws/dataset/get_acc=E-MTAB-6546_et_database=arrayexpress-repository -->
<xsl:if test="//*[local-name() = 'datasourceprefix'][.='_____OmicsDI']">
<datacite:identifier>
<xsl:attribute name="identifierType">
<xsl:value-of select="'URL'"/>
</xsl:attribute>
<xsl:value-of select="concat('https://www.omicsdi.org/dataset/', //*[local-name() = 'source'], '/', //*[local-name() = 'id'])"/>
</datacite:identifier>
</xsl:if>
<!-- title -->
<xsl:if test="//*[local-name() = 'datasourceprefix'][.='_____OmicsDI']">
<datacite:titles>
<datacite:title>
<xsl:value-of select="//*[local-name() = 'title']"/>
</datacite:title>
</datacite:titles>
</xsl:if>
<!-- no authors in OmicsDI -->
<!--
<xsl:call-template name="authors" />
-->
<!--
<xsl:call-template name="relatedPaper" />
-->
<datacite:descriptions>
<datacite:description>
<xsl:attribute name="descriptionType">
<xsl:value-of select="'Abstract'"/>
</xsl:attribute>
<xsl:value-of select="//*[local-name() = 'description']"/>
</datacite:description>
</datacite:descriptions>
<!-- subject -->
<datacite:subjects>
<xsl:for-each select="distinct-values(//*[local-name()='omicsType'])">
<datacite:subject>
<xsl:value-of select="."/>
</datacite:subject>
</xsl:for-each>
</datacite:subjects>
</datacite:resource>
<xsl:choose>
<xsl:when test="//*[local-name() = 'datasourceprefix'][.='_____OmicsDI']">
<xsl:variable name='varCobjCategory'
select="'0021'" />
<dr:CobjCategory>
<xsl:attribute name="type">
<xsl:value-of select="vocabulary:clean($varCobjCategory, 'dnet:result_typologies')"/>
</xsl:attribute>
<xsl:value-of
select="$varCobjCategory" />
</dr:CobjCategory>
</xsl:when>
<xsl:otherwise>
<!--
<xsl:call-template name="terminate"/>
-->
</xsl:otherwise>
</xsl:choose>
<!--
// review status: no review indications found so far
-->
<!--
OMICSDI is including both open and controlled data source.
-->
<oaf:accessrights>
<xsl:text>UNKNOWN</xsl:text>
</oaf:accessrights>
<xsl:if test="//*[local-name() = 'datasourceprefix'][.='NeuroVault__']">
<oaf:concept>
<xsl:attribute name="id">
<xsl:value-of select="'ni'"/>
</xsl:attribute>
</oaf:concept>
</xsl:if>
<oaf:hostedBy>
<xsl:attribute name="name">
<xsl:value-of select="key('kCodeByName', string(//*[local-name()='source']), $vCodes)/@name"/>
</xsl:attribute>
<xsl:attribute name="id">
<xsl:value-of select="key('kCodeByName', string(//*[local-name()='source']), $vCodes)/@id"/>
</xsl:attribute>
</oaf:hostedBy>
<oaf:collectedFrom>
<xsl:attribute name="name">
<xsl:value-of select="$varOfficialName"/>
</xsl:attribute>
<xsl:attribute name="id">
<xsl:value-of select="$varDataSourceId"/>
</xsl:attribute>
</oaf:collectedFrom>
<!-- date -->
<xsl:if test="//*[local-name() = 'datasourceprefix'][.='_____OmicsDI']">
<oaf:dateAccepted>
<xsl:value-of select="replace(//*[local-name() = 'publicationDate'][not(.='null')],'(\d{4})(\d{2})(\d{2})','$1-$2-$3')"/>
</oaf:dateAccepted>
</xsl:if>
</metadata>
<xsl:copy-of select="//*[local-name() = 'about']" />
</record>
</xsl:template>
<xsl:template match="node()|@*">
<xsl:copy>
<xsl:apply-templates select="node()|@*"/>
</xsl:copy>
</xsl:template>
<xsl:template match="//*[local-name() = 'metadata']//*[local-name() = 'datasets']">
<xsl:copy>
<xsl:apply-templates select="node()|@*"/>
</xsl:copy>
</xsl:template>
<xsl:template match="//*[local-name() = 'header']">
<xsl:copy>
<xsl:apply-templates select="node()|@*"/>
<xsl:element name="dr:dateOfTransformation">
<xsl:value-of select="$transDate"/>
</xsl:element>
</xsl:copy>
</xsl:template>
<!--
no authors findable in OmicsDI">
-->
<!--
<xsl:template match="//*[local-name() = 'authors']">
-->
<xsl:template name="authors">
<xsl:choose>
<xsl:when test="not(//*[local-name() = 'authors'][string-length(normalize-space(.)) > 0 and not(. = 'null')])">
<xsl:call-template name="terminate" />
</xsl:when>
<xsl:otherwise>
<xsl:for-each select="tokenize(//*[local-name() = 'authors'], '(, and |,| and )')">
<xsl:element name="datacite:creator">
<xsl:element name="datacite:creatorName">
<xsl:value-of select="personCleaner:normalize( .)"/>
</xsl:element>
<xsl:element name="datacite:givenName">
<xsl:value-of select="normalize-space(substring-after(personCleaner:normalize(.), ','))"/>
</xsl:element>
<xsl:element name="datacite:familyName">
<xsl:value-of select="substring-before(personCleaner:normalize(.), ',')"/>
</xsl:element>
</xsl:element>
</xsl:for-each>
</xsl:otherwise>
</xsl:choose>
</xsl:template>
<!--
<xsl:template match="//*[local-name() = 'DOI']">
-->
<xsl:template name="relatedPaper">
<xsl:element name="datacite:relatedIdentifier">
<xsl:attribute name="relatedIdentifierType">
<xsl:value-of select="'DOI'"/>
</xsl:attribute>
<xsl:attribute name="relationType">
<xsl:value-of select="'isReferencedBy'"/>
</xsl:attribute>
<xsl:value-of select="//*[local-name() = 'DOI']"/>
</xsl:element>
</xsl:template>
</xsl:stylesheet>

View File

@ -4,16 +4,23 @@ import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.schema.common.ModelConstants
import eu.dnetlib.dhp.schema.oaf.utils.IdentifierFactory
import eu.dnetlib.dhp.schema.oaf.{Author, DataInfo, Publication}
import eu.dnetlib.dhp.schema.orcid.OrcidDOI
import eu.dnetlib.dhp.schema.orcid.{AuthorData, OrcidDOI}
import eu.dnetlib.doiboost.DoiBoostMappingUtil
import eu.dnetlib.doiboost.DoiBoostMappingUtil.{createSP, generateDataInfo}
import org.apache.commons.lang.StringUtils
import org.slf4j.{Logger, LoggerFactory}
import scala.collection.JavaConverters._
import org.json4s
import org.json4s.DefaultFormats
import org.json4s.JsonAST._
import org.json4s.jackson.JsonMethods._
case class ORCIDItem(oid:String,name:String,surname:String,creditName:String,errorCode:String){}
case class ORCIDItem(doi:String, authors:List[OrcidAuthor]){}
case class OrcidAuthor(oid:String, name:Option[String], surname:Option[String], creditName:Option[String], otherNames:Option[List[String]], errorCode:Option[String]){}
case class OrcidWork(oid:String, doi:String)
@ -46,8 +53,52 @@ object ORCIDToOAF {
}
def convertTOOAF(input:OrcidDOI) :Publication = {
val doi = input.getDoi
def strValid(s:Option[String]) : Boolean = {
s.isDefined && s.get.nonEmpty
}
def authorValid(author:OrcidAuthor): Boolean ={
if (strValid(author.name) && strValid(author.surname)) {
return true
}
if (strValid(author.surname)) {
return true
}
if (strValid(author.creditName)) {
return true
}
false
}
def extractDOIWorks(input:String): List[OrcidWork] = {
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
lazy val json: json4s.JValue = parse(input)
val oid = (json \ "workDetail" \"oid").extract[String]
val doi:List[(String, String)] = for {
JObject(extIds) <- json \ "workDetail" \"extIds"
JField("type", JString(typeValue)) <- extIds
JField("value", JString(value)) <- extIds
if "doi".equalsIgnoreCase(typeValue)
} yield (typeValue, value)
if (doi.nonEmpty) {
return doi.map(l =>OrcidWork(oid, l._2))
}
List()
}
def convertORCIDAuthor(input:String): OrcidAuthor = {
implicit lazy val formats: DefaultFormats.type = org.json4s.DefaultFormats
lazy val json: json4s.JValue = parse(input)
(json \"authorData" ).extractOrElse[OrcidAuthor](null)
}
def convertTOOAF(input:ORCIDItem) :Publication = {
val doi = input.doi
val pub:Publication = new Publication
pub.setPid(List(createSP(doi.toLowerCase, "doi", ModelConstants.DNET_PID_TYPES)).asJava)
pub.setDataInfo(generateDataInfo())
@ -58,8 +109,8 @@ object ORCIDToOAF {
try{
val l:List[Author]= input.getAuthors.asScala.map(a=> {
generateAuthor(a.getName, a.getSurname, a.getCreditName, a.getOid)
val l:List[Author]= input.authors.map(a=> {
generateAuthor(a)
})(collection.breakOut)
pub.setAuthor(l.asJava)
@ -80,16 +131,20 @@ object ORCIDToOAF {
di
}
def generateAuthor(given: String, family: String, fullName:String, orcid: String): Author = {
def generateAuthor(o : OrcidAuthor): Author = {
val a = new Author
a.setName(given)
a.setSurname(family)
if (fullName!= null && fullName.nonEmpty)
a.setFullname(fullName)
else
a.setFullname(s"$given $family")
if (StringUtils.isNotBlank(orcid))
a.setPid(List(createSP(orcid, ModelConstants.ORCID, ModelConstants.DNET_PID_TYPES, generateOricPIDDatainfo())).asJava)
if (strValid(o.name)) {
a.setName(o.name.get.capitalize)
}
if (strValid(o.surname)) {
a.setSurname(o.surname.get.capitalize)
}
if(strValid(o.name) && strValid(o.surname))
a.setFullname(s"${o.name.get.capitalize} ${o.surname.get.capitalize}")
else if (strValid(o.creditName))
a.setFullname(o.creditName.get)
if (StringUtils.isNotBlank(o.oid))
a.setPid(List(createSP(o.oid, ModelConstants.ORCID, ModelConstants.DNET_PID_TYPES, generateOricPIDDatainfo())).asJava)
a
}

View File

@ -5,68 +5,48 @@ import eu.dnetlib.dhp.application.ArgumentApplicationParser
import eu.dnetlib.dhp.oa.merge.AuthorMerger
import eu.dnetlib.dhp.schema.oaf.Publication
import eu.dnetlib.dhp.schema.orcid.OrcidDOI
import eu.dnetlib.doiboost.mag.ConversionUtil
import org.apache.commons.io.IOUtils
import org.apache.spark.SparkConf
import org.apache.spark.rdd.RDD
import org.apache.spark.sql.expressions.Aggregator
import org.apache.spark.sql.functions._
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SaveMode, SparkSession}
import org.slf4j.{Logger, LoggerFactory}
object SparkConvertORCIDToOAF {
val logger: Logger = LoggerFactory.getLogger(SparkConvertORCIDToOAF.getClass)
def getPublicationAggregator(): Aggregator[(String, Publication), Publication, Publication] = new Aggregator[(String, Publication), Publication, Publication]{
override def zero: Publication = new Publication()
override def reduce(b: Publication, a: (String, Publication)): Publication = {
b.mergeFrom(a._2)
b.setAuthor(AuthorMerger.mergeAuthor(a._2.getAuthor, b.getAuthor))
if (b.getId == null)
b.setId(a._2.getId)
b
}
override def merge(wx: Publication, wy: Publication): Publication = {
wx.mergeFrom(wy)
wx.setAuthor(AuthorMerger.mergeAuthor(wy.getAuthor, wx.getAuthor))
if(wx.getId == null && wy.getId.nonEmpty)
wx.setId(wy.getId)
wx
}
override def finish(reduction: Publication): Publication = reduction
override def bufferEncoder: Encoder[Publication] =
Encoders.kryo(classOf[Publication])
override def outputEncoder: Encoder[Publication] =
Encoders.kryo(classOf[Publication])
}
def run(spark:SparkSession,sourcePath:String, targetPath:String):Unit = {
def run(spark:SparkSession,sourcePath:String,workingPath:String, targetPath:String):Unit = {
import spark.implicits._
implicit val mapEncoderPubs: Encoder[Publication] = Encoders.kryo[Publication]
implicit val mapOrcid: Encoder[OrcidDOI] = Encoders.kryo[OrcidDOI]
implicit val tupleForJoinEncoder: Encoder[(String, Publication)] = Encoders.tuple(Encoders.STRING, mapEncoderPubs)
val mapper = new ObjectMapper()
mapper.getDeserializationConfig.withFeatures(DeserializationFeature.FAIL_ON_UNKNOWN_PROPERTIES)
val inputRDD:RDD[OrcidAuthor] = spark.sparkContext.textFile(s"$sourcePath/authors").map(s => ORCIDToOAF.convertORCIDAuthor(s)).filter(s => s!= null).filter(s => ORCIDToOAF.authorValid(s))
val dataset:Dataset[OrcidDOI] = spark.createDataset(spark.sparkContext.textFile(sourcePath).map(s => mapper.readValue(s,classOf[OrcidDOI])))
spark.createDataset(inputRDD).as[OrcidAuthor].write.mode(SaveMode.Overwrite).save(s"$workingPath/author")
val res = spark.sparkContext.textFile(s"$sourcePath/works").flatMap(s => ORCIDToOAF.extractDOIWorks(s)).filter(s => s!= null)
spark.createDataset(res).as[OrcidWork].write.mode(SaveMode.Overwrite).save(s"$workingPath/works")
val authors :Dataset[OrcidAuthor] = spark.read.load(s"$workingPath/author").as[OrcidAuthor]
val works :Dataset[OrcidWork] = spark.read.load(s"$workingPath/works").as[OrcidWork]
works.joinWith(authors, authors("oid").equalTo(works("oid")))
.map(i =>{
val doi = i._1.doi
val author = i._2
(doi, author)
}).groupBy(col("_1").alias("doi"))
.agg(collect_list(col("_2")).alias("authors"))
.write.mode(SaveMode.Overwrite).save(s"$workingPath/orcidworksWithAuthor")
val dataset: Dataset[ORCIDItem] =spark.read.load(s"$workingPath/orcidworksWithAuthor").as[ORCIDItem]
logger.info("Converting ORCID to OAF")
dataset.map(o => ORCIDToOAF.convertTOOAF(o)).filter(p=>p!=null)
.map(d => (d.getId, d))
.groupByKey(_._1)(Encoders.STRING)
.agg(getPublicationAggregator().toColumn)
.map(p => p._2)
.write.mode(SaveMode.Overwrite).save(targetPath)
dataset.map(o => ORCIDToOAF.convertTOOAF(o)).write.mode(SaveMode.Overwrite).save(targetPath)
}
def main(args: Array[String]): Unit = {
val conf: SparkConf = new SparkConf()
val parser = new ArgumentApplicationParser(IOUtils.toString(SparkConvertORCIDToOAF.getClass.getResourceAsStream("/eu/dnetlib/dhp/doiboost/convert_map_to_oaf_params.json")))
parser.parseArgument(args)
@ -78,10 +58,10 @@ object SparkConvertORCIDToOAF {
.master(parser.get("master")).getOrCreate()
val sourcePath = parser.get("sourcePath")
val workingPath = parser.get("workingPath")
val targetPath = parser.get("targetPath")
run(spark, sourcePath, targetPath)
run(spark, sourcePath, workingPath, targetPath)
}

View File

@ -1,5 +1,6 @@
[
{"paramName":"s", "paramLongName":"sourcePath", "paramDescription": "the path of the sequencial file to read", "paramRequired": true},
{"paramName":"s", "paramLongName":"sourcePath", "paramDescription": "the path of the Orcid Input file", "paramRequired": true},
{"paramName":"w", "paramLongName":"workingPath", "paramDescription": "the working path ", "paramRequired": true},
{"paramName":"t", "paramLongName":"targetPath", "paramDescription": "the working dir path", "paramRequired": true},
{"paramName":"m", "paramLongName":"master", "paramDescription": "the master name", "paramRequired": true}

View File

@ -74,6 +74,11 @@
<!-- ORCID Parameters -->
<property>
<name>inputPathOrcid</name>
<description>the ORCID input path</description>
</property>
<property>
<name>workingPathOrcid</name>
<description>the ORCID working path</description>
</property>
@ -295,6 +300,7 @@
--conf spark.eventLog.dir=${nameNode}${spark2EventLogDir}
</spark-opts>
<arg>--sourcePath</arg><arg>${inputPathOrcid}</arg>
<arg>--workingPath</arg><arg>${workingPathOrcid}</arg>
<arg>--targetPath</arg><arg>${workingPath}/orcidPublication</arg>
<arg>--master</arg><arg>yarn-cluster</arg>
</spark>

View File

@ -2,12 +2,14 @@ package eu.dnetlib.doiboost.orcid
import com.fasterxml.jackson.databind.ObjectMapper
import eu.dnetlib.dhp.schema.oaf.Publication
import eu.dnetlib.doiboost.orcid.SparkConvertORCIDToOAF.getClass
import org.apache.spark.sql.{Encoder, Encoders, SparkSession}
import org.apache.spark.SparkConf
import org.apache.spark.sql.{Dataset, Encoder, Encoders, SparkSession}
import org.junit.jupiter.api.Assertions._
import org.junit.jupiter.api.Test
import org.junit.jupiter.api.io.TempDir
import org.slf4j.{Logger, LoggerFactory}
import java.nio.file.Path
import scala.io.Source
class MappingORCIDToOAFTest {
@ -24,27 +26,41 @@ class MappingORCIDToOAFTest {
})
}
// @Test
// def testOAFConvert():Unit ={
//
// val spark: SparkSession =
// SparkSession
// .builder()
// .appName(getClass.getSimpleName)
// .master("local[*]").getOrCreate()
//
//
// SparkConvertORCIDToOAF.run( spark,"/Users/sandro/Downloads/orcid", "/Users/sandro/Downloads/orcid_oaf")
// implicit val mapEncoderPubs: Encoder[Publication] = Encoders.kryo[Publication]
//
// val df = spark.read.load("/Users/sandro/Downloads/orcid_oaf").as[Publication]
// println(df.first.getId)
// println(mapper.writeValueAsString(df.first()))
//
//
//
//
// }
@Test
def testOAFConvert(@TempDir testDir: Path):Unit ={
val sourcePath:String = getClass.getResource("/eu/dnetlib/doiboost/orcid/datasets").getPath
val targetPath: String =s"${testDir.toString}/output/orcidPublication"
val workingPath =s"${testDir.toString}/wp/"
val conf = new SparkConf()
conf.setMaster("local[*]")
conf.set("spark.driver.host", "localhost")
val spark: SparkSession =
SparkSession
.builder()
.appName(getClass.getSimpleName)
.config(conf)
.getOrCreate()
implicit val mapEncoderPubs: Encoder[Publication] = Encoders.kryo[Publication]
import spark.implicits._
SparkConvertORCIDToOAF.run( spark,sourcePath, workingPath, targetPath)
val mapper = new ObjectMapper()
val oA = spark.read.load(s"$workingPath/orcidworksWithAuthor").as[ORCIDItem].count()
val p: Dataset[Publication] = spark.read.load(targetPath).as[Publication]
assertTrue(oA == p.count())
println(mapper.writerWithDefaultPrettyPrinter().writeValueAsString(p.first()))
}

File diff suppressed because one or more lines are too long

View File

@ -90,6 +90,7 @@ public class CleanGraphSparkJob {
.map((MapFunction<T, T>) value -> fixVocabularyNames(value), Encoders.bean(clazz))
.map((MapFunction<T, T>) value -> OafCleaner.apply(value, mapping), Encoders.bean(clazz))
.map((MapFunction<T, T>) value -> cleanup(value), Encoders.bean(clazz))
.filter((FilterFunction<T>) value -> filter(value))
.write()
.mode(SaveMode.Overwrite)
.option("compression", "gzip")

View File

@ -67,6 +67,7 @@ public class CleaningFunctionTest {
assertNotNull(p_out.getPublisher());
assertNull(p_out.getPublisher().getValue());
assertEquals("und", p_out.getLanguage().getClassid());
assertEquals("Undetermined", p_out.getLanguage().getClassname());
@ -120,6 +121,9 @@ public class CleaningFunctionTest {
.isPresent());
Publication p_cleaned = CleaningFunctions.cleanup(p_out);
assertEquals(1, p_cleaned.getTitle().size());
assertEquals("CLOSED", p_cleaned.getBestaccessright().getClassid());
assertNull(p_out.getPublisher());

View File

@ -865,6 +865,28 @@
"schemename": "dnet:dataCite_title"
},
"value": "Optical response of strained- and unstrained-silicon cold-electron bolometers"
},
{
"dataInfo": {
"deletedbyinference": false,
"inferenceprovenance": "",
"inferred": false,
"invisible": false,
"provenanceaction": {
"classid": "sysimport:crosswalk:datasetarchive",
"classname": "sysimport:crosswalk:datasetarchive",
"schemeid": "dnet:provenanceActions",
"schemename": "dnet:provenanceActions"
},
"trust": "0.9"
},
"qualifier": {
"classid": "main title",
"classname": "main title",
"schemeid": "dnet:dataCite_title",
"schemename": "dnet:dataCite_title"
},
"value": "test test 123 test"
}
]
}