Merge branch 'release-0.8'

.dockerignore

@@ -0,0 +1,7 @@
+.github
+.git
+.idea
+*/logs
+**/target
+**/node_modules
+**/build

.env

@@ -0,0 +1,8 @@
+REACT_APP_REST_HOST=rest
+REACT_APP_REST_PORT=8080
+REST_API_HOST=rest
+REST_API_PORT=8080
+FITS_HOST=fits
+FITS_PORT=8080
+DB_HOST=db
+DB_PORT=8080

.github/workflows/docker-image.yml

@@ -0,0 +1,69 @@
+name: Docker Image CI
+
+on:
+  push:
+    branches: [main, dev, release/*]
+  pull_request:
+    branches: [main]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+      - name: Login to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+      - name: Cache local Maven repository
+        uses: actions/cache@v3
+        with:
+          path: ~/.m2/repository
+          key: ${{ runner.os }}-maven-${{ hashFiles('**/pom.xml') }}
+          restore-keys: |
+            ${{ runner.os }}-maven-
+      - name: Build and push FITSInn REST
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: artourkin/fitsinn-rest:${{ github.ref_name }}
+      - name: Cache node modules
+        id: cache-npm
+        uses: actions/cache@v3
+        env:
+          cache-name: cache-node-modules
+        with:
+          # npm cache files are stored in `~/.npm` on Linux/macOS
+          path: ~/.npm
+          key: ${{ runner.os }}-build-${{ env.cache-name }}-${{ hashFiles('**/package-lock.json') }}
+          restore-keys: |
+            ${{ runner.os }}-build-${{ env.cache-name }}-
+            ${{ runner.os }}-build-
+            ${{ runner.os }}-
+      - if: ${{ steps.cache-npm.outputs.cache-hit != 'true' }}
+        name: List the state of node modules
+        continue-on-error: true
+        run: npm list
+      - name: Build and push FITSInn WEB
+        uses: docker/build-push-action@v5
+        with:
+          file: ./web/Dockerfile
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: artourkin/fitsinn-web:${{ github.ref_name }}
+      - name: Build and push FITS WEB
+        uses: docker/build-push-action@v5
+        with:
+          file: ./fits/Dockerfile
+          platforms: linux/amd64,linux/arm64/v8
+          push: true
+          tags: artourkin/fits-web:${{ github.ref_name }}

.gitignore

@@ -22,3 +22,63 @@
 # virtual machine crash logs, see http://www.java.com/en/download/help/error_hotspot.xml
 hs_err_pid*
 replay_pid*
+
+
+**/build/
+**/yarn.lock
+*.lock
+.classpath
+.project
+.settings/
+.DS_Store
+target/
+bin/
+c3po-core/output.xml
+c3po-webapi/war/
+*/profiles/*
+*/exports/*
+*/*.csv
+*/logs/
+*/log
+.idea/
+*.iml
+# vagrant related local settings, should never end up in the repo
+.vagrant_settings/maven_settings.xml
+.vagrant_settings/proxy_settings.conf
+# Eclipse
+.project
+.classpath
+.settings/
+bin/
+
+# IntelliJ
+.idea
+*.ipr
+*.iml
+*.iws
+
+# NetBeans
+nb-configuration.xml
+
+# Visual Studio Code
+.vscode
+
+# OSX
+.DS_Store
+
+# Vim
+*.swp
+*.swo
+
+# patch
+*.orig
+*.rej
+
+# Maven
+target/
+pom.xml.tag
+pom.xml.releaseBackup
+pom.xml.versionsBackup
+release.properties
+
+**/node_modules

Dockerfile

@@ -0,0 +1,16 @@
+FROM maven:3.9.0 as builder
+COPY . /app
+WORKDIR /app
+RUN mvn -pl !web clean install -Pprod
+
+FROM openjdk:21-jdk-slim
+WORKDIR /app
+RUN printenv
+COPY --from=builder /app/main/target/fitsinn-main-*.jar ./app.jar
+
+RUN chown 1001 ./app.jar \
+    && chmod "g+rwX" ./app.jar
+
+USER 1001
+EXPOSE 8080
+ENTRYPOINT ["java", "-jar", "app.jar"]

README.md

@@ -1,2 +1,53 @@
-# fitsinn
-Place where your FITS files feel good
+# FITSInn
+Place where your FITS files feel good.
+## Purpose
+
+FITSInn is a tool to store and analyse technical metadata extracted by characterisation tools such as [FITS](https://projects.iq.harvard.edu/fits/).
+![img.png](docs/img.png)
+
+The features include:
+* Improved user experience through an intuitive UI.
+* Running file characterisation using FITS on the uploaded files.
+  * The original files are not stored.
+* Slice and dice:
+  * Filtering,
+  * Drill-down,
+  * Property value aggregations,
+  * Distribution visualisations,
+  * Sampling.
+* Built-in metadata conflict resolution.
+* REST API for workflow automation.
+
+
+## Installation
+
+### Deployment
+
+The artifacts are released as Docker images. You can install FITSInn using Docker-compose:
+
+```
+docker-compose -f docker-compose.yaml up --pull
+```
+
+Installation of FITSInn to Docker Swarm or K8S is possible, but is not currently addressed. 
+
+
+### Local build
+
+Building the Docker images from scratch and starting FITSInn is executed via: 
+
+```
+docker-compose -f docker-compose.dev.yaml up --build
+```
+
+File uploading using bash:
+
+bash fileupload.sh http://localhost:8082 ~/rnd/data/govdocs_fits/govdocs1/000/
+
+## Issues
+
+If you have any issue regarding FITSInn, please use [https://github.com/datascience/fitsinn/issues](https://github.com/datascience/fitsinn/issues).
+
+## License
+
+FITSInn is released under MIT license. See the [LICENSE](LICENSE) for details.

core/pom.xml

@@ -0,0 +1,36 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project xmlns="http://maven.apache.org/POM/4.0.0"
+         xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+         xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+    <modelVersion>4.0.0</modelVersion>
+    <dependencies>
+        <dependency>
+            <groupId>junit</groupId>
+            <artifactId>junit</artifactId>
+            <version>${junit.version}</version>
+            <scope>test</scope>
+        </dependency>
+        <dependency>
+            <groupId>org.springframework.boot</groupId>
+            <artifactId>spring-boot-starter-test</artifactId>
+            <scope>test</scope>
+            <exclusions>
+                <exclusion>
+                    <groupId>org.junit.vintage</groupId>
+                    <artifactId>junit-vintage-engine</artifactId>
+                </exclusion>
+            </exclusions>
+        </dependency>
+    </dependencies>
+
+    <parent>
+        <groupId>rocks.artur</groupId>
+        <artifactId>fitsinn</artifactId>
+        <version>0.1.0</version>
+    </parent>
+
+    <groupId>rocks.artur</groupId>
+    <artifactId>fitsinn-core</artifactId>
+
+
+</project>

core/src/main/java/rocks/artur/api/AnalyzePersistFile.java

@@ -0,0 +1,13 @@
+package rocks.artur.api;
+
+import java.io.File;
+
+/**
+ * This interface enables the following actions:
+ * - to analyze a digital object using a characterisation tool,
+ * - to persist a characterisation result in a db.
+ */
+public interface AnalyzePersistFile {
+    Long uploadCharacterisationResults(File file);
+    Long uploadCharacterisationResults(byte[] file, String filename);
+}

core/src/main/java/rocks/artur/api/CharacterisationResultProducer.java

@@ -0,0 +1,41 @@
+package rocks.artur.api;
+
+import rocks.artur.domain.CharacterisationResult;
+
+import java.io.File;
+import java.io.IOException;
+import java.util.List;
+
+/**
+ * this interface helps to build a wrapper for a characterisation tool.
+ */
+public interface CharacterisationResultProducer {
+    /***
+     * This method returns the version of the used tool
+     * @return A version of the tool
+     * @throws IOException
+     */
+    String getVersion() throws IOException;
+
+    /***
+     *
+     * This method extracts metadata properties from a given digital object.
+     *
+     * @param file Input File
+     * @return A list of @CharacterisationResult
+     * @throws IOException
+     */
+    List<CharacterisationResult> processFile(File file) throws IOException;
+
+
+    /***
+     *
+     * This method extracts metadata properties from a given digital object passed as a byte array.
+     *
+     * @param file Input File
+     * @param filename
+     * @return A list of @CharacterisationResult
+     * @throws IOException
+     */
+    List<CharacterisationResult> processFile(byte[] file, String filename) throws IOException;
+}

core/src/main/java/rocks/artur/api/GetCollectionStatistics.java

@@ -0,0 +1,10 @@
+package rocks.artur.api;
+
+import rocks.artur.domain.FilterCriteria;
+
+import java.util.Map;
+
+public interface GetCollectionStatistics {
+    Map<String, Double> getStatistics(FilterCriteria filterCriteria);
+
+}

core/src/main/java/rocks/artur/api/GetObjects.java

@@ -0,0 +1,17 @@
+package rocks.artur.api;
+
+import rocks.artur.domain.CharacterisationResult;
+import rocks.artur.domain.FilterCriteria;
+import rocks.artur.domain.statistics.PropertiesPerObjectStatistic;
+
+import java.util.List;
+
+/**
+ * This interface enables getting characterisation results.
+ */
+public interface GetObjects {
+    List<PropertiesPerObjectStatistic> getObjects(FilterCriteria filterCriteria);
+    Iterable<CharacterisationResult> getObject(String filePath);
+
+    List<CharacterisationResult> getConflictsFromObject(String filePath);
+}

core/src/main/java/rocks/artur/api/GetProperties.java

@@ -0,0 +1,14 @@
+package rocks.artur.api;
+
+import rocks.artur.domain.FilterCriteria;
+import rocks.artur.domain.statistics.PropertyStatistic;
+
+import java.util.List;
+
+/**
+ * This interface enables getting a property distribution.
+ */
+public interface GetProperties {
+    List<PropertyStatistic> getProperties();
+    List<PropertyStatistic> getProperties(FilterCriteria filter);
+}

core/src/main/java/rocks/artur/api/GetPropertyValueDistribution.java

@@ -0,0 +1,15 @@
+package rocks.artur.api;
+
+import rocks.artur.domain.CharacterisationResult;
+import rocks.artur.domain.FilterCriteria;
+import rocks.artur.domain.Property;
+import rocks.artur.domain.statistics.PropertyValueStatistic;
+
+import java.util.List;
+
+/**
+ * This interface enables getting a property value distribution given a property name.
+ */
+public interface GetPropertyValueDistribution {
+    List<PropertyValueStatistic> getPropertyValueDistribution(Property propertyName, FilterCriteria<CharacterisationResult> filterCriteria);
+}

core/src/main/java/rocks/artur/api/GetPropertyValueDistributionWithFilter.java

@@ -0,0 +1,12 @@
+package rocks.artur.api;
+
+import rocks.artur.domain.statistics.PropertyValueStatistic;
+
+import java.util.List;
+
+/**
+ * This interface enables getting a property value distribution given a filter.
+ */
+public interface GetPropertyValueDistributionWithFilter {
+    List<PropertyValueStatistic> getPropertyValueDistributionWithFilter(String propertyName, String filter);
+}