qlever 0.5.5__py3-none-any.whl → 0.5.6__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of qlever might be problematic. Click here for more details.
- qlever/Qleverfiles/Qleverfile.wikimedia-commons +37 -0
- qlever/__main__.py +1476 -0
- qlever/qleverfile.py +1 -1
- qlever/util.py +16 -2
- {qlever-0.5.5.dist-info → qlever-0.5.6.dist-info}/METADATA +1 -1
- {qlever-0.5.5.dist-info → qlever-0.5.6.dist-info}/RECORD +10 -8
- {qlever-0.5.5.dist-info → qlever-0.5.6.dist-info}/LICENSE +0 -0
- {qlever-0.5.5.dist-info → qlever-0.5.6.dist-info}/WHEEL +0 -0
- {qlever-0.5.5.dist-info → qlever-0.5.6.dist-info}/entry_points.txt +0 -0
- {qlever-0.5.5.dist-info → qlever-0.5.6.dist-info}/top_level.txt +0 -0
|
@@ -0,0 +1,37 @@
|
|
|
1
|
+
# Qleverfile for Wikimedia Commons, TODO: add to https://github.com/ad-freiburg/qlever-control
|
|
2
|
+
#
|
|
3
|
+
# qlever get-data # takes ~3 hours to download .bz2 file of size ~40 GB
|
|
4
|
+
# qlever index # takes ~2 hours and ~40 GB RAM (on an AMD Ryzen 9 5900X)
|
|
5
|
+
# qlever start # starts the server (takes around 15 seconds)
|
|
6
|
+
|
|
7
|
+
[data]
|
|
8
|
+
NAME = wikimedia-commons
|
|
9
|
+
MAIN_RDF_FILE = latest-mediainfo.ttl.gz
|
|
10
|
+
DATA_URL_BASE = https://dumps.wikimedia.org/other/wikibase/commonswiki
|
|
11
|
+
GET_TTL_CMD = wget -nc ${DATA_URL_BASE}/${MAIN_RDF_FILE}
|
|
12
|
+
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
|
|
13
|
+
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
|
|
14
|
+
GET_DATA_CMD = ${GET_TTL_CMD} && ${GET_PROPS_CMD} && ${GET_LABELS_CMD}
|
|
15
|
+
INDEX_DESCRIPTION = Wikimedia Commons from ${DATA_URL_BASE}, version 09.11.2023 + Wikidata triples for rdfs:label and wikibase:claim etc.
|
|
16
|
+
|
|
17
|
+
[index]
|
|
18
|
+
INPUT_FILES = ${data:MAIN_RDF_FILE} labels.nt properties.nt
|
|
19
|
+
CAT_INPUT_FILES = zcat -f ${INPUT_FILES}
|
|
20
|
+
WITH_TEXT_INDEX = from_literals
|
|
21
|
+
STXXL_MEMORY_GB = 5
|
|
22
|
+
SETTINGS_JSON = { "languages-internal": [], "prefixes-external": [""], "locale": { "language": "en", "country": "US", "ignore-punctuation": true }, "ascii-prefixes-only": true, "num-triples-per-batch": 5000000 }
|
|
23
|
+
|
|
24
|
+
[server]
|
|
25
|
+
PORT = 7033
|
|
26
|
+
ACCESS_TOKEN = ${data:NAME}_2511328747
|
|
27
|
+
MEMORY_FOR_QUERIES_GB = 20
|
|
28
|
+
CACHE_MAX_SIZE_GB = 10
|
|
29
|
+
CACHE_MAX_SIZE_GB_SINGLE_ENTRY = 5
|
|
30
|
+
|
|
31
|
+
[runtime]
|
|
32
|
+
SYSTEM = native
|
|
33
|
+
IMAGE = docker.io/adfreiburg/qlever:latest
|
|
34
|
+
|
|
35
|
+
[ui]
|
|
36
|
+
PORT = 7000
|
|
37
|
+
CONFIG = wikimedia-commons
|