qlever 0.5.7__py3-none-any.whl → 0.5.8__py3-none-any.whl

qlever/Qleverfiles/Qleverfile.dblp

@@ -1,20 +1,20 @@
 # Qleverfile for DBLP, use with https://github.com/ad-freiburg/qlever-control
 #
-# qlever get-data  # takes ~3 mins (downloads .ttl.gz file of size ~3 GB)
-# qlever index     # takes ~4 mins (on an AMD Ryzen 9 5900X)
-# qlever start     # takes a few seconds
+# qlever get-data  # ~5 GB compressed, 1.3 B triples
+# qlever index     # ~30 min (on an AMD Ryzen 9 5900X)
+# qlever start     # ~1 sec
 
 [data]
 NAME         = dblp
-GET_DATA_URL = https://dblp.org/rdf/dblp.ttl.gz
-GET_DATA_CMD = curl -LRC - -O ${GET_DATA_URL} 2>&1 | tee ${data:NAME}.download-log.txt
+GET_DATA_URL = https://sparql.dblp.org/download/dblp_KG_with_associated_data.tar
+GET_DATA_CMD = (curl -LRC - -o dblp+citations.tar ${GET_DATA_URL} && tar -xf dblp+citations.tar) 2>&1 | tee ${NAME}.download-log.txt
 VERSION      = $$(date -r dblp.ttl.gz +"%d.%m.%Y %H:%M" || echo "NO_DATE")
-DESCRIPTION  = DBLP computer science bibliography, data from ${GET_DATA_URL} (version ${VERSION})
+DESCRIPTION  = DBLP computer science bibliography + citations from OpenCitations, data from ${GET_DATA_URL} (version ${VERSION})
 
 [index]
-INPUT_FILES     = dblp.ttl.gz
+INPUT_FILES     = *.gz
 CAT_INPUT_FILES = zcat ${INPUT_FILES}
-SETTINGS_JSON   = { "ascii-prefixes-only": false, "num-triples-per-batch": 1000000, "prefixes-external": [""] }
+SETTINGS_JSON   = { "ascii-prefixes-only": false, "num-triples-per-batch": 1000000, "languages-internal": [], "prefixes-external": [""] }
 
 [server]
 PORT               = 7015

qlever/commands/index.py

@@ -41,7 +41,7 @@ class IndexCommand(QleverCommand):
     def execute(self, args) -> bool:
         # Construct the command line.
         index_cmd = (f"{args.cat_input_files} | {args.index_binary}"
-                     f" -F {args.format} -"
+                     f" -F {args.format} -f -"
                      f" -i {args.name}"
                      f" -s {args.name}.settings.json")
         if args.only_pso_and_pos_permutations:

{qlever-0.5.7.dist-info → qlever-0.5.8.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: qlever
-Version: 0.5.7
+Version: 0.5.8
 Summary: Script for using the QLever SPARQL engine.
 Author-email: Hannah Bast <bast@cs.uni-freiburg.de>
 License: Apache-2.0

{qlever-0.5.7.dist-info → qlever-0.5.8.dist-info}/RECORD

@@ -8,7 +8,7 @@ qlever/qlever_main.py,sha256=tA_xqOs_FjvqlDIvKTprwuysfTwzsUjE7at26gRhCVA,2336
 qlever/qlever_old.py,sha256=X-JxmepFKYeFgSLLp0TRDNqXSxDwIbc8_0Xstiems8c,62026
 qlever/qleverfile.py,sha256=D321zDnWi-ScCefbFGBydKKI7lzzr1CkohHW6KuwVw0,13106
 qlever/util.py,sha256=20NQJquSk_mSqvlK4k0OrSBqWrxKs5SgVshm5ucus5o,7847
-qlever/Qleverfiles/Qleverfile.dblp,sha256=Y6BqAG1GZg-OmEs0HM00yAQuY2TGnSzsOO1LLmGVn2Y,994
+qlever/Qleverfiles/Qleverfile.dblp,sha256=NKkvwgvJss0oEsnPLMcJazYyO-8yV_Or824hz9TlzR8,1083
 qlever/Qleverfiles/Qleverfile.dblp-plus,sha256=Dwd9pK1vPcelKfw6sA-IuyhbZ6yIxOh6_84JgPYnB9Q,1332
 qlever/Qleverfiles/Qleverfile.dbpedia,sha256=aaNZZayE-zVePGSwPzXemkX__Ns8-kP_E7DNNKZPnqg,1160
 qlever/Qleverfiles/Qleverfile.default,sha256=UWDy9ohhbKjE4n5xEYqbOPZOiYDFzsnJ_aNNBMCOlaI,2402
@@ -25,7 +25,6 @@ qlever/Qleverfiles/Qleverfile.scientists,sha256=9eZ2c6P9a3E3VHa3RR7LdOQbF4k3oyyr
 qlever/Qleverfiles/Qleverfile.uniprot,sha256=9kAKseomdUnIt7EAZge39g1MTuaLVaSW9JYLHzIMolM,2338
 qlever/Qleverfiles/Qleverfile.vvz,sha256=ftdMj5dCC9jAlFtNt2WR7kP30w0itT_iYtj5HoUVyWU,931
 qlever/Qleverfiles/Qleverfile.wikidata,sha256=vDkTY3mPSx2C8MvFWfB72zZoc4d-TMJSw3f_-FqnEqs,1275
-qlever/Qleverfiles/Qleverfile.wikimedia-commons,sha256=5JJ1MIp6LoM-ROCDFFIRvLREepCF4i4PnjOT9AFihzQ,2247
 qlever/Qleverfiles/Qleverfile.wikipathways,sha256=UFEVLrtOBiSQfibBN9xc2wDXrnWcnx5f8PY9khcE6bc,1983
 qlever/Qleverfiles/Qleverfile.yago-4,sha256=GikYPqChCtbAyZOVqszmVUwgQxSePTcgM8xw2b_21e4,1849
 qlever/commands/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
@@ -34,7 +33,7 @@ qlever/commands/cache_stats.py,sha256=6JjueQstAqc8dNfgY8TP2EitFMxdUvCwrcyd7KUEb2
 qlever/commands/clear_cache.py,sha256=AnE1MOoj1ZexxrRT8FGeBLlv8rtQIVV4DP8VBn5-X-s,2843
 qlever/commands/example_queries.py,sha256=5-0ln5EkuDcQYPqKKAOcLaTIStMzFhkAogaNedfRc_I,15271
 qlever/commands/get_data.py,sha256=f9kjZI3TKad6JHSuXWNkeoajmW8h0Sx8ShvjauDCtNo,1412
-qlever/commands/index.py,sha256=TwL6o16KZON1hbD8UnXMw_tduLXWcy7D4o6tbsLt1OE,5888
+qlever/commands/index.py,sha256=7tdExYVwJMgBT54gj06oyBPZLR1EraEtPJe86ErV4t4,5891
 qlever/commands/index_stats.py,sha256=_BiUNBhmbYd9RPxrlm4HF0oENO6JmqnRiAkwkyOdN4U,11722
 qlever/commands/log.py,sha256=8Krt3MsTUDapYqVw1zUu5X15SF8mV97Uj0qKOWK8jXk,1861
 qlever/commands/query.py,sha256=_IDH-M8gKL_f1i5wzu0X452pZSUD0_qXl6bPXC85wX0,2750
@@ -44,9 +43,9 @@ qlever/commands/status.py,sha256=5S6EdapZEwFKV9cQZtNYcZhMbAXAY-FP6ggjIhfX8ek,163
 qlever/commands/stop.py,sha256=TZs4bxKHvujlZAU8BZmFjA5eXSZNAa6EeNzvPpEZsuI,4139
 qlever/commands/ui.py,sha256=b7g7Mp6ZWevn8f1kwFr-WR4ZWMq42KEV4cGl2QS7M1E,2828
 qlever/commands/warmup.py,sha256=WOZSxeV8U_F6pEEnAb6YybXLQMxZFTRJXs4BPHUhsmc,1030
-qlever-0.5.7.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-qlever-0.5.7.dist-info/METADATA,sha256=4g8Lf7NVarNL99xbtFGOCRTPky--pHznE7WtwYgYjfk,4582
-qlever-0.5.7.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
-qlever-0.5.7.dist-info/entry_points.txt,sha256=U_gbYYi0wwdsn884eb0XoOXfvhACOsxhlO330dZ9bi0,87
-qlever-0.5.7.dist-info/top_level.txt,sha256=kd3zsYqiFd0--Czh5XTVkfEq6XR-XgRFW35X0v0GT-c,7
-qlever-0.5.7.dist-info/RECORD,,
+qlever-0.5.8.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+qlever-0.5.8.dist-info/METADATA,sha256=Cds_PBvPYvMOqlLAZAFdMF4hKjjaAhuCPJtKCzqZIXg,4582
+qlever-0.5.8.dist-info/WHEEL,sha256=GV9aMThwP_4oNCtvEC2ec3qUYutgWeAzklro_0m4WJQ,91
+qlever-0.5.8.dist-info/entry_points.txt,sha256=U_gbYYi0wwdsn884eb0XoOXfvhACOsxhlO330dZ9bi0,87
+qlever-0.5.8.dist-info/top_level.txt,sha256=kd3zsYqiFd0--Czh5XTVkfEq6XR-XgRFW35X0v0GT-c,7
+qlever-0.5.8.dist-info/RECORD,,

qlever/Qleverfiles/Qleverfile.wikimedia-commons

@@ -1,37 +0,0 @@
-# Qleverfile for Wikimedia Commons, TODO: add to https://github.com/ad-freiburg/qlever-control
-#
-# qlever get-data  # takes ~3 hours to download .bz2 file of size ~40 GB
-# qlever index     # takes ~2 hours and ~40 GB RAM (on an AMD Ryzen 9 5900X)
-# qlever start     # starts the server (takes around 15 seconds)
-
-[data]
-NAME              = wikimedia-commons
-MAIN_RDF_FILE     = latest-mediainfo.ttl.gz
-DATA_URL_BASE     = https://dumps.wikimedia.org/other/wikibase/commonswiki
-GET_TTL_CMD       = wget -nc ${DATA_URL_BASE}/${MAIN_RDF_FILE}
-GET_PROPS_CMD     = curl -s https://qlever.cs.uni-freiburg.de/api/wikidata -H "Accept: text/turtle" -H "Content-type: application/sparql-query" --data "PREFIX wikibase: <http://wikiba.se/ontology#> CONSTRUCT { ?s ?p ?o } WHERE { VALUES ?p { wikibase:claim wikibase:directClaim wikibase:novalue wikibase:propertyType wikibase:qualifier wikibase:qualifierValue wikibase:reference wikibase:referenceValue wikibase:statementProperty wikibase:statementValue } ?s ?p ?o }" > properties.nt
-GET_LABELS_CMD    = curl -s https://qlever.cs.uni-freiburg.de/api/wikidata -H "Accept: text/turtle" -H "Content-type: application/sparql-query" --data "PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#> CONSTRUCT { ?subject rdfs:label ?label } WHERE { ?subject @en@rdfs:label ?label }" > labels.nt
-GET_DATA_CMD      = ${GET_TTL_CMD} && ${GET_PROPS_CMD} && ${GET_LABELS_CMD}
-INDEX_DESCRIPTION = Wikimedia Commons from ${DATA_URL_BASE}, version 09.11.2023 + Wikidata triples for rdfs:label and wikibase:claim etc.
-
-[index]
-INPUT_FILES     = ${data:MAIN_RDF_FILE} labels.nt properties.nt
-CAT_INPUT_FILES = zcat -f ${INPUT_FILES}
-WITH_TEXT_INDEX = from_literals
-STXXL_MEMORY_GB = 5
-SETTINGS_JSON   = { "languages-internal": [], "prefixes-external": [""], "locale": { "language": "en", "country": "US", "ignore-punctuation": true }, "ascii-prefixes-only": true, "num-triples-per-batch": 5000000 }
-
-[server]
-PORT                           = 7033
-ACCESS_TOKEN                   = ${data:NAME}_2511328747
-MEMORY_FOR_QUERIES_GB          = 20
-CACHE_MAX_SIZE_GB              = 10
-CACHE_MAX_SIZE_GB_SINGLE_ENTRY = 5
-
-[runtime]
-SYSTEM = native
-IMAGE  = docker.io/adfreiburg/qlever:latest
-
-[ui]
-PORT   = 7000
-CONFIG = wikimedia-commons