add ld setup

.github/workflows/ci.yaml

@@ -140,6 +140,23 @@ jobs:
           echo 'file unchanged, skipping.'
         fi;
 
+    - name: "Generate linked data: DE_ZHV"
+      # todo: do not run if processing the dataset failed
+      if: ${{ success() }} # this should allow the other steps to run, but should still mark the workflow as failing
+      env:
+        DO_SPACES_BUCKET_NAME: ${{ secrets.DO_SPACES_BUCKET_NAME }}
+      run: |
+        set -e;
+        ./src/linked-data/zhv-de/index.sh
+        currentobj=$(aws s3api head-object --bucket $DO_SPACES_BUCKET_NAME --key de/zhv.ttl.gz || echo 'not-yet-existing');
+        newhash=$(cat ./src/linked-data/zhv-de/data/output.ttl.gz | md5sum);
+        if [ $(echo $currentobj | grep $newhash | wc -l) -ne 1 ]
+        then
+          aws s3 cp --acl public-read ./src/linked-data/zhv-de/data/output.ttl.gz s3://"$DO_SPACES_BUCKET_NAME"/de/zhv.ttl.gz
+        else
+          echo 'file unchanged, skipping.'
+        fi;
+
     - name: "Fetch and upload feed: DE_NRW_GTFS"
       if: ${{ success() || failure() }} # this should allow the other steps to run, but should still mark the workflow as failing
       env:

.gitignore

@@ -10,4 +10,5 @@ shrinkwrap.yaml
 pnpm-lock.yaml
 dist
 
+data
 *.zip

src/linked-data/.bin/.gitignore

@@ -0,0 +1,2 @@
+*
+!.gitignore

src/linked-data/zhv-de/index.sh

@@ -0,0 +1,27 @@
+#!/usr/bin/env bash
+set -e
+DIR=$(dirname "$0")
+BASE_IRI="https://lod.codefor.de/"
+BIN_DIR="$DIR/../.bin"
+DATA_DIR="$DIR/data"
+
+echo 'Fetching rmlmapper'
+wget -q --show-progress --progress=dot:mega -c -N -O "$BIN_DIR/rmlmapper.jar" https://github.com/RMLio/rmlmapper-java/releases/download/v7.0.0/rmlmapper-7.0.0-r374-all.jar
+
+rm -rf "$DATA_DIR"
+mkdir -p "$DATA_DIR"
+
+echo 'Preparing data…'
+cp "$DIR/../../../de-zhv.zip" "$DATA_DIR/source.zip"
+unzip "$DATA_DIR/source.zip" -d "$DATA_DIR/unzipped"
+find "$DATA_DIR/unzipped/" -name "*.csv" -exec mv '{}' "$DATA_DIR/source.csv" \;
+
+pnpx csvtojson --delimiter=";" "$DATA_DIR/source.csv" > "$DATA_DIR/source.json"
+
+echo 'Applying mapping…'
+java -jar "$BIN_DIR/rmlmapper.jar" -m "$DIR/mapping.ttl" -s turtle --strict --base-iri "$BASE_IRI" > "$DATA_DIR/output.ttl"
+
+echo 'Compressing output…'
+cat "$DATA_DIR/source.csv" | gzip > "$DATA_DIR/output.ttl.gz"
+
+# echo 'Done.'

src/linked-data/zhv-de/mapping.ttl

@@ -0,0 +1,56 @@
+@prefix bahnhof: <https://lod.bahnhof.de/vocabulary/db/>.
+@prefix codeforde: <https://lod.codefor.de/vocabulary/codeforde/>.
+@prefix dct: <http://purl.org/dc/terms/>.
+@prefix dbo: <https://dbpedia.org/ontology/>.
+@prefix foaf: <http://xmlns.com/foaf/0.1/>.
+@prefix geo: <http://www.opengis.net/ont/geosparql#>.
+@prefix gn: <http://www.geonames.org/ontology#>.
+@prefix juso: <http://rdfs.co/juso/>.
+@prefix netex: <https://lod.bahnhof.de/vocabulary/netex/>.
+@prefix owl: <http://www.w3.org/2002/07/owl#>.
+@prefix ql: <http://semweb.mmlab.be/ns/ql#>.
+@prefix rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>.
+@prefix rdfs: <http://www.w3.org/2000/01/rdf-schema#>.
+@prefix rml: <http://semweb.mmlab.be/ns/rml#>.
+@prefix rr: <http://www.w3.org/ns/r2rml#>.
+@prefix schema: <http://schema.org/>.
+@prefix status: <http://www.w3.org/2003/06/sw-vocab-status/ns#>.
+@prefix wdt: <http://www.wikidata.org/prop/direct/>.
+@prefix xsd: <http://www.w3.org/2001/XMLSchema#>.
+
+# level 1 (stop place)
+
+[ a rr:TriplesMap ]
+  rml:logicalSource [
+    rml:source "data/source.json";
+    rml:referenceFormulation ql:JSONPath;
+    rml:iterator "$[?(@.Type == 'S')]"
+  ];
+  rr:subjectMap [
+    rr:template "resource/by-key/ifopt/{.DHID}";
+    rr:class netex:StopPlace
+  ];
+	rr:predicateObjectMap [
+    rr:predicate netex:topographicPlace;
+    rr:objectMap [
+      rr:termType rr:IRI;
+      rr:template "resource/by-key/ags/{.MunicipalityCode}"
+    ]
+  ], [
+    rr:predicate bahnhof:ifoptStopId;
+    rr:objectMap [
+      rr:datatype xsd:string;
+      rr:termType rr:Literal;
+      rml:reference "$.DHID"
+    ]
+  ], [
+		rr:predicate netex:name;
+    rr:objectMap [
+      rr:datatype xsd:string;
+      rr:termType rr:Literal;
+      rml:reference "$.Name"
+    ]
+	].
+	# todo: other attributes
+
+# todo: level 2 (quay - platform), level 3 (quay - platform edge)