qlever 0.5.27__tar.gz → 0.5.29__tar.gz

{qlever-0.5.27/src/qlever.egg-info → qlever-0.5.29}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: qlever
-Version: 0.5.27
+Version: 0.5.29
 Summary: Command-line tool for using the QLever graph database
 Author-email: Hannah Bast <bast@cs.uni-freiburg.de>
 License: Apache-2.0

{qlever-0.5.27 → qlever-0.5.29}/pyproject.toml

@@ -5,7 +5,7 @@ build-backend = "setuptools.build_meta"
 [project]
 name = "qlever"
 description = "Command-line tool for using the QLever graph database"
-version = "0.5.27"
+version = "0.5.29"
 authors = [
     { name = "Hannah Bast", email = "bast@cs.uni-freiburg.de" }
 ]

{qlever-0.5.27 → qlever-0.5.29}/src/qlever/Qleverfiles/Qleverfile.ohm-planet

@@ -22,7 +22,7 @@ MULTI_INPUT_JSON   = { "cmd": "zcat ${INPUT_FILES}", "parallel": "true" }
 STXXL_MEMORY       = 5G
 PARSER_BUFFER_SIZE = 50M
 SETTINGS_JSON      = { "num-triples-per-batch": 5000000 }
-ENCODE_AS_IDS      = https://www.openhistoricalmap.org/node/ http://www.openhistoricalmap.org/node/ https://www.openhistoricalmap.org/way/ https://www.openhistoricalmap.org/relation/ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_node_tagged_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_node_untagged_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_way_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_relation_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_wayarea_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_relationarea_ https://www.openstreetmap.org/changeset/
+ENCODE_AS_ID       = https://www.openhistoricalmap.org/node/ http://www.openhistoricalmap.org/node/ https://www.openhistoricalmap.org/way/ https://www.openhistoricalmap.org/relation/ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#ohmnode_tagged_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#ohmnode_untagged_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#ohmway_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#ohmrel_ https://www.openstreetmap.org/changeset/
 
 [server]
 PORT                        = 7037

{qlever-0.5.27 → qlever-0.5.29}/src/qlever/Qleverfiles/Qleverfile.osm-country

@@ -25,13 +25,13 @@ INPUT_FILES       = ${data:NAME}.ttl.bz2
 CAT_INPUT_FILES   = bzcat ${data:NAME}.ttl.bz2
 STXXL_MEMORY      = 10G
 SETTINGS_JSON      = { "num-triples-per-batch": 10000000 }
-ENCODE_AS_IDS      = https://www.openstreetmap.org/node/ http://www.openstreetmap.org/node/ https://www.openstreetmap.org/way/ https://www.openstreetmap.org/relation/ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_node_tagged_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_node_untagged_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_way_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_relation_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_wayarea_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_relationarea_ https://www.openstreetmap.org/changeset/
+ENCODE_AS_ID       = https://www.openstreetmap.org/node/ http://www.openstreetmap.org/node/ https://www.openstreetmap.org/way/ https://www.openstreetmap.org/relation/ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osmnode_tagged_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osmnode_untagged_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osmway_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osmrel_ https://www.openstreetmap.org/changeset/
 
 # Server settings
 [server]
 HOSTNAME                    = localhost
 PORT                        = 7025
-ACCESS_TOKEN                = ${data:NAME}_%RANDOM%
+ACCESS_TOKEN                = ${data:NAME}
 MEMORY_FOR_QUERIES          = 20G
 CACHE_MAX_SIZE              = 10G
 CACHE_MAX_SIZE_SINGLE_ENTRY = 5G

{qlever-0.5.27 → qlever-0.5.29}/src/qlever/Qleverfiles/Qleverfile.osm-planet

@@ -15,13 +15,13 @@ DESCRIPTION  = OSM from ${GET_DATA_URL} (converted to RDF using osm2rdf, enhance
 
 [index]
 INPUT_FILES        = ${data:NAME}.ttl.bz2
-CAT_INPUT_FILES    = lbzcat -n 2 ${INPUT_FILES}
-PARALLEL_PARSING   = true
+MULTI_INPUT_JSON   = { "cmd": "lbzcat -n 2 ${INPUT_FILES}", "parallel": "true" }
+VOCABULARY_TYPE    = on-disk-compressed-geo-split
 PARSER_BUFFER_SIZE = 100M
-STXXL_MEMORY       = 40G
+STXXL_MEMORY       = 60G
 SETTINGS_JSON      = { "num-triples-per-batch": 10000000 }
-ULIMIT             = 10000
-ENCODE_AS_IDS      = https://www.openstreetmap.org/node/ http://www.openstreetmap.org/node/ https://www.openstreetmap.org/way/ https://www.openstreetmap.org/relation/ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_node_tagged_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_node_untagged_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_way_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_relation_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_wayarea_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osm_relationarea_ https://www.openstreetmap.org/changeset/
+ULIMIT             = 50000
+ENCODE_AS_ID       = https://www.openstreetmap.org/node/ http://www.openstreetmap.org/node/ https://www.openstreetmap.org/way/ https://www.openstreetmap.org/relation/ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osmnode_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osmway_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osmrel_ https://www.openstreetmap.org/changeset/
 
 [server]
 PORT                        = 7007

qlever-0.5.29/src/qlever/Qleverfiles/Qleverfile.osm-planet-from-pbf

@@ -0,0 +1,42 @@
+# Qleverfile for OSM Planet, use with the QLever CLI (`pip install qlever`)
+#
+# qlever get-data  # download ~100 GB (pbf), convert with osm2rdf, ~200B triples
+# qlever index     # ~40 hours, ~60 GB RAM, ~2.5 TB index size on disk
+# qlever start     # a few seconds, adjust MEMORY_FOR_QUERIES as needed
+#
+# Measured on an AMD Ryzen 9 9950X with 128 GB RAM and 4 x 8 TB NVMe (02.10.2025)
+
+[data]
+NAME         = osm-planet
+PLANET_PBF   = planet-250929.osm.pbf
+GET_DATA_URL = https://planet.openstreetmap.org/pbf/${PLANET_PBF}
+GET_PBF_CMD  = unbuffer wget -O ${PLANET_PBF} ${GET_DATA_URL}
+OSM2RDF_CMD  = unbuffer osm2rdf ${PLANET_PBF} -o ${NAME}.ttl --num-threads 20 --output-compression gz --cache . --store-locations disk-dense --iri-prefix-for-untagged-nodes http://www.openstreetmap.org/node/ --split-tag-key-by-semicolon ref --split-tag-key-by-semicolon service
+GET_DATA_CMD = ${GET_PBF_CMD} && ${OSM2RDF_CMD} 2>&1 | tee ${NAME}.osm2rdf-log.txt
+VERSION      = $$(date -r ${PLANET_PBF} +%d.%m.%Y || echo "NO_DATE")
+DESCRIPTION  = OSM from ${GET_DATA_URL}, converted to RDF using osm2rdf, enhanced by GeoSPARQL triples ogc:sfContains, ogc:sfCovers, ogc:sfIntersects, ogc:sfEquals, ogc:sfTouches, ogc:sfCrosses, ogc:sfOverlaps
+
+[index]
+INPUT_FILES        = ${data:NAME}.ttl.gz
+MULTI_INPUT_JSON   = { "cmd": "zcat ${INPUT_FILES}", "parallel": "true" }
+VOCABULARY_TYPE    = on-disk-compressed-geo-split
+PARSER_BUFFER_SIZE = 100M
+STXXL_MEMORY       = 60G
+SETTINGS_JSON      = { "num-triples-per-batch": 10000000 }
+ULIMIT             = 50000
+ENCODE_AS_ID       = https://www.openstreetmap.org/node/ http://www.openstreetmap.org/node/ https://www.openstreetmap.org/way/ https://www.openstreetmap.org/relation/ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osmnode_tagged_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osmnode_untagged_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osmway_ https://osm2rdf.cs.uni-freiburg.de/rdf/geom#osmrel_ https://www.openstreetmap.org/changeset/
+
+[server]
+PORT                        = 7007
+ACCESS_TOKEN                = ${data:NAME}
+MEMORY_FOR_QUERIES          = 40G
+CACHE_MAX_SIZE              = 20G
+CACHE_MAX_SIZE_SINGLE_ENTRY = 10G
+TIMEOUT                     = 600s
+
+[runtime]
+SYSTEM = docker
+IMAGE  = docker.io/adfreiburg/qlever:latest
+
+[ui]
+UI_CONFIG = osm-planet

{qlever-0.5.27 → qlever-0.5.29}/src/qlever/Qleverfiles/Qleverfile.uniprot

@@ -55,8 +55,8 @@ MULTI_INPUT_JSON = [{ "cmd": "zcat {}", "graph": "http://sparql.uniprot.org/unip
                     { "cmd": "zcat ${data:TTL_DIR}/examples_uniprot.ttl.gz", "graph": "http://sparql.uniprot.org/.well-known/sparql-examples" },
                     { "cmd": "zcat ${data:TTL_DIR}/core.ttl.gz", "graph": "http://purl.uniprot.org/core" }]
 SETTINGS_JSON    = { "languages-internal": [], "prefixes-external": [""], "locale": { "language": "en", "country": "US", "ignore-punctuation": true }, "ascii-prefixes-only": true, "num-triples-per-batch": 25000000 }
-STXXL_MEMORY     = 60G
-ULIMIT           = 10000
+STXXL_MEMORY     = 80G
+ULIMIT           = 50000
 
 [server]
 PORT                        = 7018

{qlever-0.5.27 → qlever-0.5.29}/src/qlever/commands/benchmark_queries.py

@@ -335,9 +335,7 @@ class BenchmarkQueriesCommand(QleverCommand):
                 )
                 return []
 
-        return [
-            (query['query'], query['sparql']) for query in data["queries"]
-        ]
+        return [(query["query"], query["sparql"]) for query in data["queries"]]
 
     def get_result_size(
         self,
@@ -552,8 +550,7 @@ class BenchmarkQueriesCommand(QleverCommand):
 
         # Show what the command will do.
         example_queries_cmd = (
-            "curl -sv https://qlever.cs.uni-freiburg.de/"
-            f"api/examples/{args.ui_config}"
+            f"curl -sv https://qlever.dev/api/examples/{args.ui_config}"
         )
         sparql_endpoint = (
             args.sparql_endpoint

{qlever-0.5.27 → qlever-0.5.29}/src/qlever/commands/settings.py

@@ -44,6 +44,7 @@ class SettingsCommand(QleverCommand):
             "lazy-result-max-cache-size",
             "query-planning-budget",
             "request-body-limit",
+            "service-max-redirects",
             "service-max-value-rows",
             "sort-estimate-cancellation-factor",
             "spatial-join-prefilter-max-size",

{qlever-0.5.27 → qlever-0.5.29}/src/qlever/commands/update_wikidata.py

@@ -252,46 +252,74 @@ class UpdateWikidataCommand(QleverCommand):
                 # operation = event_data.get("operation")
                 rdf_added_data = event_data.get("rdf_added_data")
                 rdf_deleted_data = event_data.get("rdf_deleted_data")
+                rdf_linked_shared_data = event_data.get(
+                    "rdf_linked_shared_data"
+                )
+                rdf_unlinked_shared_data = event_data.get(
+                    "rdf_unlinked_shared_data"
+                )
 
                 # Process the to-be-deleted triples.
-                if rdf_deleted_data is not None:
-                    try:
-                        rdf_deleted_data = rdf_deleted_data.get("data")
-                        graph = Graph()
-                        log.debug(f"RDF deleted data: {rdf_deleted_data}")
-                        graph.parse(data=rdf_deleted_data, format="turtle")
-                        for s, p, o in graph:
-                            triple = f"{s.n3()} {p.n3()} {o.n3()}"
-                            # NOTE: In case there was a previous `insert` of that
-                            # triple, it is safe to remove that `insert`, but not
-                            # the `delete` (in case the triple is contained in the
-                            # original data).
-                            if triple in insert_triples:
-                                insert_triples.remove(triple)
-                            delete_triples.add(triple)
-                    except Exception as e:
-                        log.error(f"Error reading `rdf_deleted_data`: {e}")
-                        return False
+                for rdf_to_be_deleted in (
+                    rdf_deleted_data,
+                    rdf_unlinked_shared_data,
+                ):
+                    if rdf_to_be_deleted is not None:
+                        try:
+                            rdf_to_be_deleted_data = rdf_to_be_deleted.get(
+                                "data"
+                            )
+                            graph = Graph()
+                            log.debug(
+                                f"RDF to_be_deleted data: {rdf_to_be_deleted_data}"
+                            )
+                            graph.parse(
+                                data=rdf_to_be_deleted_data, format="turtle"
+                            )
+                            for s, p, o in graph:
+                                triple = f"{s.n3()} {p.n3()} {o.n3()}"
+                                # NOTE: In case there was a previous `insert` of that
+                                # triple, it is safe to remove that `insert`, but not
+                                # the `delete` (in case the triple is contained in the
+                                # original data).
+                                if triple in insert_triples:
+                                    insert_triples.remove(triple)
+                                delete_triples.add(triple)
+                        except Exception as e:
+                            log.error(
+                                f"Error reading `rdf_to_be_deleted_data`: {e}"
+                            )
+                            return False
 
                 # Process the to-be-added triples.
-                if rdf_added_data is not None:
-                    try:
-                        rdf_added_data = rdf_added_data.get("data")
-                        graph = Graph()
-                        log.debug("RDF added data: {rdf_added_data}")
-                        graph.parse(data=rdf_added_data, format="turtle")
-                        for s, p, o in graph:
-                            triple = f"{s.n3()} {p.n3()} {o.n3()}"
-                            # NOTE: In case there was a previous `delete` of that
-                            # triple, it is safe to remove that `delete`, but not
-                            # the `insert` (in case the triple is not contained in
-                            # the original data).
-                            if triple in delete_triples:
-                                delete_triples.remove(triple)
-                            insert_triples.add(triple)
-                    except Exception as e:
-                        log.error(f"Error reading `rdf_added_data`: {e}")
-                        return False
+                for rdf_to_be_added in (
+                    rdf_added_data,
+                    rdf_linked_shared_data,
+                ):
+                    if rdf_to_be_added is not None:
+                        try:
+                            rdf_to_be_added_data = rdf_to_be_added.get("data")
+                            graph = Graph()
+                            log.debug(
+                                "RDF to be added data: {rdf_to_be_added_data}"
+                            )
+                            graph.parse(
+                                data=rdf_to_be_added_data, format="turtle"
+                            )
+                            for s, p, o in graph:
+                                triple = f"{s.n3()} {p.n3()} {o.n3()}"
+                                # NOTE: In case there was a previous `delete` of that
+                                # triple, it is safe to remove that `delete`, but not
+                                # the `insert` (in case the triple is not contained in
+                                # the original data).
+                                if triple in delete_triples:
+                                    delete_triples.remove(triple)
+                                insert_triples.add(triple)
+                        except Exception as e:
+                            log.error(
+                                f"Error reading `rdf_to_be_added_data`: {e}"
+                            )
+                            return False
 
             except Exception as e:
                 log.error(f"Error reading data from message: {e}")

{qlever-0.5.27 → qlever-0.5.29/src/qlever.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: qlever
-Version: 0.5.27
+Version: 0.5.29
 Summary: Command-line tool for using the QLever graph database
 Author-email: Hannah Bast <bast@cs.uni-freiburg.de>
 License: Apache-2.0

{qlever-0.5.27 → qlever-0.5.29}/src/qlever.egg-info/SOURCES.txt

@@ -28,6 +28,7 @@ src/qlever/Qleverfiles/Qleverfile.olympics
 src/qlever/Qleverfiles/Qleverfile.orkg
 src/qlever/Qleverfiles/Qleverfile.osm-country
 src/qlever/Qleverfiles/Qleverfile.osm-planet
+src/qlever/Qleverfiles/Qleverfile.osm-planet-from-pbf
 src/qlever/Qleverfiles/Qleverfile.pubchem
 src/qlever/Qleverfiles/Qleverfile.scientists
 src/qlever/Qleverfiles/Qleverfile.uniprot

qlever-0.5.29/src/qlever.egg-info/top_level.txt

@@ -0,0 +1,6 @@
+qblazegraph
+qjena
+qlever
+qmdb
+qoxigraph
+qvirtuoso

qlever-0.5.27/src/qlever.egg-info/top_level.txt

@@ -1 +0,0 @@
-qlever