qlever 0.5.28__tar.gz → 0.5.31__tar.gz

{qlever-0.5.28/src/qlever.egg-info → qlever-0.5.31}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: qlever
-Version: 0.5.28
+Version: 0.5.31
 Summary: Command-line tool for using the QLever graph database
 Author-email: Hannah Bast <bast@cs.uni-freiburg.de>
 License: Apache-2.0

{qlever-0.5.28 → qlever-0.5.31}/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 = "0.5.28"
+version = "0.5.31"
 authors = [
     { name = "Hannah Bast", email = "bast@cs.uni-freiburg.de" }
 ]

{qlever-0.5.28 → qlever-0.5.31}/src/qlever/Qleverfiles/Qleverfile.dblp

@@ -18,7 +18,8 @@ FORMAT       = ttl
 [index]
 INPUT_FILES      = *.gz
 MULTI_INPUT_JSON = { "cmd": "zcat {}", "for-each": "*.gz" }
-SETTINGS_JSON    = { "ascii-prefixes-only": false, "num-triples-per-batch": 5000000, "prefixes-external": [""] }
+SETTINGS_JSON    = { "num-triples-per-batch": 5000000 }
+STXXL_MEMORY     = 5G
 
 [server]
 PORT               = 7015

{qlever-0.5.28 → qlever-0.5.31}/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-0.5.28 → qlever-0.5.31}/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-0.5.28 → qlever-0.5.31}/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-0.5.31/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-0.5.28 → qlever-0.5.31}/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-0.5.28 → qlever-0.5.31}/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-0.5.28 → qlever-0.5.31}/src/qlever/commands/index.py

@@ -219,8 +219,8 @@ class IndexCommand(QleverCommand):
         if args.encode_as_id:
             index_cmd += f" --encode-as-id {args.encode_as_id}"
         if args.only_pso_and_pos_permutations:
-            index_cmd += " --only-pso-and-pos-permutations --no-patterns"
-        if not args.use_patterns:
+            index_cmd += " --only-pso-and-pos-permutations"
+        if args.use_patterns == "no":
             index_cmd += " --no-patterns"
         if args.text_index in [
             "from_text_records",

{qlever-0.5.28 → qlever-0.5.31}/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-0.5.28 → qlever-0.5.31}/src/qlever/commands/start.py

@@ -34,7 +34,7 @@ def construct_command(args) -> str:
         start_cmd += " --persist-updates"
     if args.only_pso_and_pos_permutations:
         start_cmd += " --only-pso-and-pos-permutations"
-    if not args.use_patterns:
+    if args.use_patterns == "no":
         start_cmd += " --no-patterns"
     if args.use_text_index == "yes":
         start_cmd += " -t"

{qlever-0.5.28 → qlever-0.5.31}/src/qlever/qleverfile.py

@@ -61,7 +61,7 @@ class Qleverfile:
             "--text-description",
             type=str,
             default=None,
-            help="A concise description of the additional text data" " if any",
+            help="A concise description of the additional text data if any",
         )
         data_args["format"] = arg(
             "--format",
@@ -167,10 +167,10 @@ class Qleverfile:
         )
         index_args["use_patterns"] = arg(
             "--use-patterns",
-            action="store_true",
-            default=True,
-            help="Precompute so-called patterns needed for fast processing"
-            " of queries like SELECT ?p (COUNT(DISTINCT ?s) AS ?c) "
+            choices=["yes", "no"],
+            default="yes",
+            help="Whether to precompute the so-called patterns used for fast "
+            "processing of queries like SELECT ?p (COUNT(DISTINCT ?s) AS ?c) "
             "WHERE { ?s ?p [] ... } GROUP BY ?p",
         )
         index_args["text_index"] = arg(
@@ -283,10 +283,10 @@ class Qleverfile:
         )
         server_args["use_patterns"] = arg(
             "--use-patterns",
-            action="store_true",
-            default=True,
-            help="Use the patterns precomputed during the index build"
-            " (see `qlever index --help` for their utility)",
+            choices=["yes", "no"],
+            default="yes",
+            help="Whether to use the patterns precomputed during the index "
+            "build (see `qlever index --help` for their utility)",
         )
         server_args["use_text_index"] = arg(
             "--use-text-index",
@@ -438,6 +438,10 @@ class Qleverfile:
             server = config["server"]
         if index.get("text_index", "none") != "none":
             server["use_text_index"] = "yes"
+        if index.get("only_pso_and_pos_permutations", "false") == "true":
+            index["use_patterns"] = "no"
+        if index.get("use_patterns", None) == "no":
+            server["use_patterns"] = "no"
 
         # Add other non-trivial default values.
         try:

{qlever-0.5.28 → qlever-0.5.31/src/qlever.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: qlever
-Version: 0.5.28
+Version: 0.5.31
 Summary: Command-line tool for using the QLever graph database
 Author-email: Hannah Bast <bast@cs.uni-freiburg.de>
 License: Apache-2.0

{qlever-0.5.28 → qlever-0.5.31}/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-0.5.31/src/qlever.egg-info/top_level.txt

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

qlever-0.5.28/src/qlever.egg-info/top_level.txt

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