add some examples on indexing preston provenance logs; related to bio…

…-guoda/preston#199 (comment)

query/4fa7b334-ce0d-4e88-aaae-2e0c138d049e.sparql

@@ -0,0 +1,13 @@
+SELECT ?archiveUrl ?seenAt ?contentId  
+WHERE {
+  graph ?g1 {
+   <urn:uuid:4fa7b334-ce0d-4e88-aaae-2e0c138d049e> <http://www.w3.org/ns/prov#hadMember> ?archiveUrl . 
+   ?archiveUrl <http://purl.org/dc/elements/1.1/format> "application/dwca" .
+  }
+  graph ?activity {
+    ?activity <http://www.w3.org/ns/prov#used> ?archiveUrl .
+    ?activity <http://www.w3.org/ns/prov#generatedAtTime> ?seenAt .
+    ?contentId <http://www.w3.org/ns/prov#qualifiedGeneration> ?activity .  
+    }
+} limit 10
+

query/README.md

@@ -0,0 +1,20 @@
+2023-12-15
+Jorrit Poelen
+
+This directory contains examples on how query preston provenance logs using SPARQL:
+
+Step 1. 
+Stream preston provenance logs into a triple-store.
+
+Step 2. 
+Write a query in sparql.
+
+Step 3.
+Execute query.
+
+Step 4. 
+Inspect results. 
+
+
+See https://github.com/bio-guoda/preston/issues/199#issuecomment-1858618208 for context and examples.
+

query/all-versions.sparql

@@ -0,0 +1,8 @@
+
+SELECT ?s ?p ?o
+WHERE {
+  GRAPH ?g { 
+    ?s <http://purl.org/pav/hasVersion> ?o .
+  }
+}
+

query/ebird.sparql

@@ -0,0 +1,32 @@
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+PREFIX foaf: <http://xmlns.com/foaf/0.1/>
+
+SELECT ?contentId ?seenAt ?archiveUrl WHERE
+{ 
+{
+    SELECT ?contentId ?seenAt ?archiveUrl  
+WHERE {
+  graph ?g1 {
+   <urn:uuid:4fa7b334-ce0d-4e88-aaae-2e0c138d049e> <http://www.w3.org/ns/prov#hadMember> ?archiveUrl . 
+   ?archiveUrl <http://purl.org/dc/elements/1.1/format> "application/dwca" .
+  }
+  graph ?activity {
+    ?activity <http://www.w3.org/ns/prov#used> ?archiveUrl .
+    ?activity <http://www.w3.org/ns/prov#generatedAtTime> ?seenAt .
+    ?contentId <http://www.w3.org/ns/prov#qualifiedGeneration> ?activity .  
+    }
+}
+}
+UNION
+{
+    SELECT ?contentId ?seenAt ?archiveUrl  
+WHERE {
+   <urn:uuid:4fa7b334-ce0d-4e88-aaae-2e0c138d049e> <http://www.w3.org/ns/prov#hadMember> ?archiveUrl . 
+   ?archiveUrl <http://purl.org/dc/elements/1.1/format> "application/dwca" .
+    ?activity <http://www.w3.org/ns/prov#used> ?archiveUrl .
+    ?activity <http://www.w3.org/ns/prov#generatedAtTime> ?seenAt .
+    ?contentId <http://www.w3.org/ns/prov#qualifiedGeneration> ?activity .  
+}
+}
+} ORDER BY ?seenAt 
+

query/index-provenance-graph.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+#
+# index provenance graph associated with an anchor
+# into oxigraph  
+#
+
+
+preston ls\
+ --anchor hash://sha256/5b7fa37bf8b64e7c935c4ff3389e36f8dd162f0705410dd719fd089e1ea253cd\
+ --remote https://linker.bio\
+ | sed -E 's/(<)([a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12})([^ ]*)(>)/<urn:uuid:\2>/g'\
+ | pv -l\
+ | ./oxigraph_server_v0.3.22_x86_64_linux_gnu load --lenient --format nq --location preston-gib
+
+

query/versions-of-url.sparql

@@ -0,0 +1,9 @@
+PREFIX rdf: <http://www.w3.org/1999/02/22-rdf-syntax-ns#>
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+
+SELECT ?o
+WHERE {
+  <http://collections.mnhn.fr/ipt/archive.do?r=mnhn-ar> <http://purl.org/pav/hasVersion> ?o .
+} limit 10
+
+