feat: resolve geof:distance issues (#1)

* feat: trying to get metric distance calculation to work

* feat: added even more dependencies

* feat: use pom file and maven

* fixed

* Update Dockerfile

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

Author: MathiasVDA

.gitignore

@@ -0,0 +1,3 @@
+data/
+lib/
+.vscode/

Dockerfile

@@ -1,14 +1,20 @@
 # Based on https://github.com/SemanticComputing/fuseki-docker/blob/master/Dockerfile
-# Optimized to download JAR files from Apache repositories
 
 FROM eclipse-temurin:21-jre-alpine AS base
 
-# Allow version to be overridden during build
+# Allow versions to be overridden during build
 ARG JENA_VERSION=5.4.0
 ENV JENA_VERSION=${JENA_VERSION}
 
-# jq needed for tdb2.xloader, wget for downloading files, unzip for SIS datasets
-RUN apk add --update bash ca-certificates coreutils findutils jq pwgen ruby wget unzip && rm -rf /var/cache/apk/*
+ARG SIS_VERSION=1.4
+ENV SIS_VERSION=${SIS_VERSION}
+
+ARG DERBY_VERSION=10.15.2.0
+ENV DERBY_VERSION=${DERBY_VERSION}
+
+# Install Maven and required tools
+# jq needed for tdb2.xloader, unzip for SIS datasets
+RUN apk add --no-cache --update bash ca-certificates coreutils findutils jq pwgen ruby unzip maven && rm -rf /var/cache/apk/*
 
 # Config and data
 ENV FUSEKI_BASE=/fuseki-base
@@ -20,64 +26,24 @@ ENV JENA_HOME=/jena
 ENV JENA_BIN=$JENA_HOME/bin
 
 WORKDIR /tmp
-# Download, extract and install Fuseki
-RUN echo "Downloading Apache Jena Fuseki ${JENA_VERSION}..." && \
-    wget -O fuseki.tar.gz "https://dlcdn.apache.org/jena/binaries/apache-jena-fuseki-${JENA_VERSION}.tar.gz" && \
-    echo "Extracting Fuseki..." && \
-    tar zxf fuseki.tar.gz && \
-    mv apache-jena-fuseki* $FUSEKI_HOME && \
-    rm fuseki.tar.gz && \
-    cd $FUSEKI_HOME && rm -rf fuseki.war && \
-    echo "Fuseki installation completed"
-
-# Download the GeoSPARQL extension JAR
-RUN echo "Downloading GeoSPARQL extension ${JENA_VERSION}..." && \
-    wget -O $FUSEKI_HOME/jena-fuseki-geosparql-${JENA_VERSION}.jar \
-    "https://repo1.maven.org/maven2/org/apache/jena/jena-fuseki-geosparql/${JENA_VERSION}/jena-fuseki-geosparql-${JENA_VERSION}.jar" && \
-    echo "GeoSPARQL extension downloaded"
 
 # Download and install Apache SIS binary distribution
 ENV SIS_HOME=/apache-sis
-ENV SIS_VERSION=1.4
-ENV SIS_DATA=$FUSEKI_BASE/SIS_DATA
-RUN echo "Downloading Apache SIS binary distribution ${SIS_VERSION}..." && \
-    wget -O /tmp/apache-sis-${SIS_VERSION}-bin.zip \
-    "https://dlcdn.apache.org/sis/${SIS_VERSION}/apache-sis-${SIS_VERSION}-bin.zip" && \
-    echo "Extracting Apache SIS..." && \
-    cd /tmp && \
-    unzip -q apache-sis-${SIS_VERSION}-bin.zip && \
-    mv apache-sis-${SIS_VERSION} $SIS_HOME && \
-    rm apache-sis-${SIS_VERSION}-bin.zip && \
-    mkdir -p $SIS_DATA && \
-    echo "Apache SIS binary distribution installed"
+ENV SIS_DATA=$FUSEKI_BASE/sis_data
+RUN mkdir -p $SIS_DATA && mkdir -p $SIS_HOME && mkdir -p $SIS_HOME/log
 
 ENV PATH=$PATH:$SIS_HOME/bin
 
-# Download, extract and install Jena tools
-RUN echo "Downloading Apache Jena ${JENA_VERSION}..." && \
-    wget -O jena.tar.gz "https://dlcdn.apache.org/jena/binaries/apache-jena-${JENA_VERSION}.tar.gz" && \
-    echo "Extracting Jena tools..." && \
-    tar zxf jena.tar.gz && \
-    mkdir -p $JENA_BIN && \
-    mv apache-jena*/lib $JENA_HOME && \
-    mv apache-jena*/bin/tdb1.xloader apache-jena*/bin/xload-* $JENA_BIN && \
-    mv apache-jena*/bin/tdb2.xloader $JENA_BIN && \
-    rm -rf apache-jena* && \
-    rm jena.tar.gz && \
-    echo "Jena tools installation completed"
-
-# As "localhost" is often inaccessible within Docker container,
-# we'll enable basic-auth with a random admin password
-# (which we'll generate on start-up)
+# Use Maven to download all dependencies as JARs
+COPY pom.xml /tmp/pom.xml
+RUN mkdir -p /javalibs && \
+    mvn dependency:copy-dependencies -DoutputDirectory=/javalibs -f /tmp/pom.xml && \
+    echo "All dependencies downloaded to /javalibs"
+
 COPY config/shiro.ini /jena-fuseki/shiro.ini
 COPY config/docker-entrypoint.sh /
 RUN chmod 755 /docker-entrypoint.sh
 
-# SeCo extensions (commented out - file not found in current setup)
-# If you need this extension, place the JAR file in a bin/ directory and uncomment the line below
-# COPY bin/silk-arq-1.0.0-SNAPSHOT-with-dependencies.jar /javalibs/
-RUN mkdir -p /javalibs
-
 # Fuseki config
 ENV ASSEMBLER=$FUSEKI_BASE/configuration/assembler.ttl
 COPY config/assembler.ttl $ASSEMBLER
@@ -90,7 +56,10 @@ RUN chgrp -R 0 $FUSEKI_BASE \
     && chmod -R g+rwX $FUSEKI_BASE \
     && chgrp -R 0 $SIS_HOME \
     && chmod -R g+rX $SIS_HOME \
-    && chmod -R g+rwX $SIS_HOME/log
+    && chmod -R g+rwX $SIS_HOME/log \
+    && mkdir -p $FUSEKI_BASE/derby-logs \
+    && chgrp -R 0 $FUSEKI_BASE/derby-logs \
+    && chmod -R g+rwX $FUSEKI_BASE/derby-logs
 
 # Tools for loading data
 ENV JAVA_CMD='java -cp "$FUSEKI_HOME/fuseki-server.jar:/javalibs/*"'
@@ -106,5 +75,12 @@ WORKDIR /jena-fuseki
 EXPOSE 3030
 USER 9008
 
+# Healthcheck: check if Fuseki is responding on port 3030
+HEALTHCHECK --interval=30s --timeout=5s --start-period=30s --retries=3 \
+    CMD wget --spider --no-verbose http://localhost:3030/ || exit 1
+
 ENTRYPOINT ["/docker-entrypoint.sh"]
-CMD ["java", "-cp", "*:/javalibs/*", "org.apache.jena.fuseki.main.cmds.FusekiServerCmd"]
+CMD ["java", "-cp", "*:/javalibs/*", "org.apache.jena.fuseki.main.cmds.FusekiServerCmd"]
+#CMD ["java", "-cp", "*:/javalibs/*", "-Dlog4j.configurationFile=/fuseki-base/log4j2.properties", "org.apache.jena.fuseki.main.cmds.FusekiServerCmd"]
+#CMD ["java", "-cp", "*:/javalibs/*", "-Dlog4j.configurationFile=/fuseki-base/log4j2.properties", "-DSIS_DATA=/fuseki-base/SIS_DATA", "-Dorg.apache.sis.referencing.factory.sql.EPSG.embedded=true", "-Dderby.stream.error.file=/fuseki-base/derby-logs/derby.log", "-Dderby.system.home=/fuseki-base/derby-logs", "org.apache.jena.fuseki.main.cmds.FusekiServerCmd"]
+#CMD ["java", "-cp", "*:/javalibs/*", "-Dlog4j.configurationFile=/fuseki-base/log4j2.properties", "-Dderby.stream.error.file=/fuseki-base/derby-logs/derby.log", "-DSIS_DATA=/fuseki-base/sis_data", "org.apache.jena.fuseki.main.cmds.FusekiServerCmd"]

README.md

@@ -27,7 +27,9 @@ This Docker container provides Apache Jena Fuseki with built-in GeoSPARQL suppor
 
 More information about the GeoSPARQL implementation of Apache Jena Fuseki can be found in the [official documentation](https://jena.apache.org/documentation/geosparql/).
 
-**Note**: This container includes Apache SIS command line tools to enable download of EPSG datasets. The SIS_DATA environment variable is configured to a directory inside /fuseki-base (recommended to as docker volume). It seems that this is insufficient for Jena Fuseki to properly transform coordinates or calculate metric distances for WGS84 coordinates.
+**Note**: This container includes Apache SIS command line tools to enable download of EPSG datasets. The SIS_DATA environment variable is configured to a directory inside /fuseki-base (recommended to mount as a docker volume).
+
+**Note 2**: The GeoSPARQL extension of Apache Jena Fuseki 5.4.0 currently does not support geof:distance with a metric unit from a source EPSG that is not metric. You still need to use the vendor function spatialF:distance for this. Please see the example queries.
 
 ## Usage
 
@@ -164,6 +166,27 @@ SELECT ?relation ?geometry1_label ?geometry2_label ?result WHERE {
 ORDER BY ?relation ?geometry1_label
 ```
 
+```sparql
+PREFIX geo: <http://www.opengis.net/ont/geosparql#>
+PREFIX geof: <http://www.opengis.net/def/function/geosparql/>
+PREFIX uom: <http://www.opengis.net/def/uom/OGC/1.0/>
+PREFIX spatialf: <http://jena.apache.org/function/spatial#>
+
+# Test GeoSPARQL distance calculation between two cities
+SELECT ?city1 ?city2 ?distance_km WHERE {
+  VALUES (?city1 ?point1 ?city2 ?point2) {
+    ("London" "<http://www.opengis.net/def/crs/EPSG/0/4326> POINT(-0.1276 51.5074)"^^geo:wktLiteral "Paris" "<http://www.opengis.net/def/crs/EPSG/0/4326> POINT(2.3522 48.8566)"^^geo:wktLiteral)
+    ("New York" "<http://www.opengis.net/def/crs/EPSG/0/4326> POINT(-74.0060 40.7128)"^^geo:wktLiteral "Boston" "<http://www.opengis.net/def/crs/EPSG/0/4326> POINT(-71.0588 42.3601)"^^geo:wktLiteral)
+    ("Amsterdam" "<http://www.opengis.net/def/crs/EPSG/0/4326> POINT(4.9041 52.3676)"^^geo:wktLiteral "Brussels" "<http://www.opengis.net/def/crs/EPSG/0/4326> POINT(4.3517 50.8503)"^^geo:wktLiteral)
+  }
+
+  # Calculate distance in kilometers
+  # implementation of geof:distance in v5.4 does not support coordinate transformation to uom:metre for non-metric EPSG, so we use spatialf:distance
+  BIND(spatialf:distance(?point1, ?point2, uom:metre) / 1000 AS ?distance_km)
+}
+ORDER BY ?distance_km
+```
+
 ## Building from Source
 
 ```bash

example-queries/test-geosparql-basic-functions.sparql

@@ -0,0 +1,22 @@
+PREFIX geo: <http://www.opengis.net/ont/geosparql#>
+PREFIX geof: <http://www.opengis.net/def/function/geosparql/>
+PREFIX uom: <http://www.opengis.net/def/uom/OGC/1.0/>
+
+# Test basic GeoSPARQL geometry functions without UOM
+SELECT ?test_name ?point ?buffer_geom ?envelope_geom WHERE {
+  
+  VALUES (?test_name ?lat ?lon ?buffer_distance) {
+    ("Amsterdam Central" 52.3791 4.9003 0.01)
+    ("Rotterdam Port" 51.9225 4.4792 0.02)
+    ("Utrecht Center" 52.0907 5.1214 0.015)
+  }
+    # Create point geometry from coordinates
+  BIND(STRDT(CONCAT("<http://www.opengis.net/def/crs/EPSG/0/4326> POINT(", STR(?lon), " ", STR(?lat), ")"), geo:wktLiteral) AS ?point)
+  
+  # Create a buffer around the point (simple circular buffer)
+  BIND(geof:buffer(?point, ?buffer_distance, uom:degree) AS ?buffer_geom)
+  
+  # Get the envelope (bounding box) of the buffered geometry
+  BIND(geof:envelope(?buffer_geom) AS ?envelope_geom)
+}
+ORDER BY ?test_name

example-queries/test-geosparql-distance.sparql

@@ -0,0 +1,17 @@
+PREFIX geo: <http://www.opengis.net/ont/geosparql#>
+PREFIX geof: <http://www.opengis.net/def/function/geosparql/>
+PREFIX uom: <http://www.opengis.net/def/uom/OGC/1.0/>
+PREFIX spatialf: <http://jena.apache.org/function/spatial#>
+
+# Test GeoSPARQL distance calculation between two cities
+SELECT ?city1 ?city2 ?distance_km WHERE {  
+  VALUES (?city1 ?point1 ?city2 ?point2) {
+    ("London" "<http://www.opengis.net/def/crs/EPSG/0/4326> POINT(-0.1276 51.5074)"^^geo:wktLiteral "Paris" "<http://www.opengis.net/def/crs/EPSG/0/4326> POINT(2.3522 48.8566)"^^geo:wktLiteral)
+    ("New York" "<http://www.opengis.net/def/crs/EPSG/0/4326> POINT(-74.0060 40.7128)"^^geo:wktLiteral "Boston" "<http://www.opengis.net/def/crs/EPSG/0/4326> POINT(-71.0588 42.3601)"^^geo:wktLiteral)
+    ("Amsterdam" "<http://www.opengis.net/def/crs/EPSG/0/4326> POINT(4.9041 52.3676)"^^geo:wktLiteral "Brussels" "<http://www.opengis.net/def/crs/EPSG/0/4326> POINT(4.3517 50.8503)"^^geo:wktLiteral)
+  }
+  
+  # Calculate distance in kilometers
+  BIND(spatialf:distance(?point1, ?point2, uom:metre) / 1000 AS ?distance_km)
+}
+ORDER BY ?distance_km

example-queries/test-geosparql-spatial-relations.sparql

@@ -0,0 +1,31 @@
+PREFIX geo: <http://www.opengis.net/ont/geosparql#>
+PREFIX geof: <http://www.opengis.net/def/function/geosparql/>
+
+# Test GeoSPARQL spatial relationships without UOM namespace
+# This query tests contains, intersects, and within relationships
+SELECT ?relation ?geometry1_label ?geometry2_label ?result WHERE {
+  
+  # Define test geometries
+  VALUES (?geometry1_label ?geometry1 ?geometry2_label ?geometry2 ?relation) {
+    # Point within polygon test
+    ("City Center" "POINT(4.9041 52.3676)"^^geo:wktLiteral "Amsterdam Bounds" "POLYGON((4.8 52.3, 5.0 52.3, 5.0 52.4, 4.8 52.4, 4.8 52.3))"^^geo:wktLiteral "within")
+    
+    # Line intersects polygon test  
+    ("Highway" "LINESTRING(4.85 52.32, 4.95 52.38)"^^geo:wktLiteral "Amsterdam Bounds" "POLYGON((4.8 52.3, 5.0 52.3, 5.0 52.4, 4.8 52.4, 4.8 52.3))"^^geo:wktLiteral "intersects")
+    
+    # Polygon contains point test
+    ("Large Area" "POLYGON((4.7 52.2, 5.1 52.2, 5.1 52.5, 4.7 52.5, 4.7 52.2))"^^geo:wktLiteral "Small Point" "POINT(4.9 52.35)"^^geo:wktLiteral "contains")
+    
+    # Buffer test (point with buffer intersects line)
+    ("Station" "POINT(4.9 52.37)"^^geo:wktLiteral "Train Line" "LINESTRING(4.88 52.36, 4.92 52.38)"^^geo:wktLiteral "intersects")
+  }
+  
+  # Test the spatial relationship based on the relation type
+  BIND(
+    IF(?relation = "within", geof:sfWithin(?geometry1, ?geometry2),
+    IF(?relation = "intersects", geof:sfIntersects(?geometry1, ?geometry2),
+    IF(?relation = "contains", geof:sfContains(?geometry1, ?geometry2),
+    false))) AS ?result
+  )
+}
+ORDER BY ?relation ?geometry1_label

pom.xml

@@ -0,0 +1,51 @@
+<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>
+    <groupId>org.example</groupId>
+    <artifactId>jena-fuseki-geosparql</artifactId>
+    <version>1.0-SNAPSHOT</version>
+    <dependencies>
+        <dependency>
+            <groupId>org.apache.jena</groupId>
+            <artifactId>apache-jena-fuseki</artifactId>
+            <type>pom</type>
+            <version>${jena.version}</version>
+        </dependency>        
+        <dependency>
+            <groupId>org.apache.jena</groupId>
+            <artifactId>jena-fuseki-geosparql</artifactId>
+            <version>${jena.version}</version>
+        </dependency>
+		<dependency>
+			<groupId>org.apache.jena</groupId>
+			<artifactId>jena-geosparql</artifactId>
+            <version>${jena.version}</version>
+		</dependency>
+		<dependency>
+			<groupId>org.apache.jena</groupId>
+			<artifactId>jena-core</artifactId>
+            <version>${jena.version}</version>
+		</dependency>
+
+		<dependency>
+			<groupId>org.apache.jena</groupId>
+			<artifactId>jena-arq</artifactId>
+            <version>${jena.version}</version>
+		</dependency>
+        <dependency>
+            <groupId>org.apache.sis.non-free</groupId>
+            <artifactId>sis-embedded-data</artifactId>
+            <version>${sis.version}</version>
+        </dependency>
+		<dependency>
+			<groupId>org.apache.sis.core</groupId>
+			<artifactId>sis-referencing</artifactId>
+            <version>${sis.version}</version>
+		</dependency>
+	</dependencies>
+	<properties>
+		<jena.version>5.4.0</jena.version>
+		<sis.version>1.4</sis.version>
+	</properties>
+</project>