From 8d0ed7d4141d051677e75dc038e879e63cf7d062 Mon Sep 17 00:00:00 2001
From: LSmyrnaios <lsmyrnaios@gmail.com>
Date: Thu, 25 Jan 2024 18:23:14 +0200
Subject: [PATCH] Continuous-Validation updates: - Update the
 "uoa-validator-engine2" dependency. - Update the "installProject.sh" script
 to account for potential conflict with previous builds. - Add documentation.

---
 dhp-workflows/dhp-continuous-validation/README.md         | 8 ++++++++
 dhp-workflows/dhp-continuous-validation/installProject.sh | 8 ++++++++
 .../dhp-continuous-validation/runOozieWorkflow.sh         | 6 ++++--
 pom.xml                                                   | 2 +-
 4 files changed, 21 insertions(+), 3 deletions(-)

diff --git a/dhp-workflows/dhp-continuous-validation/README.md b/dhp-workflows/dhp-continuous-validation/README.md
index 7dc65f8e8..7905a0e55 100644
--- a/dhp-workflows/dhp-continuous-validation/README.md
+++ b/dhp-workflows/dhp-continuous-validation/README.md
@@ -1,3 +1,11 @@
 # Continuous Validation
 
+This module is responsible for deploying an **Oozie Workflow** (on the desired cluster), which executes a **Spark** action.<br>
+This action takes the HDFS-path of a directory of parquet files containing metadata records, and applies the validation process on all of them, in parallel. Then it outputs the results, in json-format, in the given directory.<br>
+The validation process is powered by the [**uoa-validator-engine2**](https://code-repo.d4science.org/MaDgIK/uoa-validator-engine2) software.<br>
+
+### Install and run
+
+Run the **./installProject.sh** script and then the **./runOozieWorkflow.sh** script.<br>
+
 [...]
\ No newline at end of file
diff --git a/dhp-workflows/dhp-continuous-validation/installProject.sh b/dhp-workflows/dhp-continuous-validation/installProject.sh
index 7f5f8f134..afd95578d 100755
--- a/dhp-workflows/dhp-continuous-validation/installProject.sh
+++ b/dhp-workflows/dhp-continuous-validation/installProject.sh
@@ -1,9 +1,17 @@
+# Install the whole "dnet-hadoop" project.
+
+# Delete this module's previous build-files in order to avoid any conflicts.
+rm -rf target/ ||
+
+# Go to the root directory of this project.
 cd ../../
 
+# Select the build profile.
 DEFAULT_PROFILE=''  # It's the empty profile.
 NEWER_VERSIONS_PROFILE='-Pscala-2.12'
 CHOSEN_MAVEN_PROFILE=${DEFAULT_PROFILE}
 
+# Install the project.
 mvn clean install -U ${CHOSEN_MAVEN_PROFILE} -Dmaven.test.skip=true
 
 # We skip tests for all modules, since the take a big amount of time and some of them fail.
diff --git a/dhp-workflows/dhp-continuous-validation/runOozieWorkflow.sh b/dhp-workflows/dhp-continuous-validation/runOozieWorkflow.sh
index 665619b49..8ab67a39b 100755
--- a/dhp-workflows/dhp-continuous-validation/runOozieWorkflow.sh
+++ b/dhp-workflows/dhp-continuous-validation/runOozieWorkflow.sh
@@ -1,12 +1,14 @@
-# This script deploys and runs the oozie workflow.
+# This script deploys and runs the oozie workflow on the cluster, defined in the "~/.dhp/application.properties" file.
 
+# Select the build profile.
 DEFAULT_PROFILE=''  # It's the empty profile.
 NEWER_VERSIONS_PROFILE='-Pscala-2.12'
 CHOSEN_MAVEN_PROFILE=${DEFAULT_PROFILE}
 
-
+# Build and deploy this module.
 mvn clean package -U ${CHOSEN_MAVEN_PROFILE} -Poozie-package,deploy,run \
       -Dworkflow.source.dir=eu/dnetlib/dhp/continuous_validator
 
+# Show the Oozie-job-ID.
 echo -e "\n\nShowing the contents of \"extract-and-run-on-remote-host.log\":\n"
 cat ./target/extract-and-run-on-remote-host.log
diff --git a/pom.xml b/pom.xml
index c84ab8ff4..addc4cfec 100644
--- a/pom.xml
+++ b/pom.xml
@@ -207,7 +207,7 @@
 			<dependency>
 				<groupId>eu.dnetlib</groupId>
 				<artifactId>uoa-validator-engine2</artifactId>
-				<version>0.9.3</version>
+				<version>2.0.0-SNAPSHOT</version>
 			</dependency>
 
 			<dependency>