qlever 0.5.2__py3-none-any.whl → 0.5.4__py3-none-any.whl

qlever/Qleverfiles/Qleverfile.dblp

@@ -1,13 +1,13 @@
 # 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 ~3 mins (on an AMD Ryzen 9 5900X)
+# qlever index     # takes ~4 mins (on an AMD Ryzen 9 5900X)
 # qlever start     # takes a few seconds
 
 [data]
 NAME         = dblp
-GET_DATA_URL = https://dblp.org/rdf/${index:INPUT_FILES}
-GET_DATA_CMD = curl -LRC - O ${GET_DATA_URL} 2>&1 | tee ${data:NAME}.download-log.txt
+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
 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})
 
@@ -19,7 +19,7 @@ SETTINGS_JSON   = { "ascii-prefixes-only": false, "num-triples-per-batch": 10000
 [server]
 PORT               = 7015
 ACCESS_TOKEN       = ${data:NAME}
-MEMORY_FOR_QUERIES = 30G
+MEMORY_FOR_QUERIES = 10G
 CACHE_MAX_SIZE     = 5G
 
 [runtime]

qlever/Qleverfiles/Qleverfile.dbpedia

@@ -0,0 +1,30 @@
+# Qleverfile for DBpedia, use with https://github.com/ad-freiburg/qlever-control
+#
+# qlever get-data  # ~14 GB, ~850 M triples (as of 30.07.2024)
+# qlever index     # ~20 min (on an AMD Ryzen 9 5900X)
+# qlever start     # ~3 sec
+
+[data]
+NAME         = dbpedia
+DATABUS_URL  = https://databus.dbpedia.org/dbpedia/collections/latest-core
+GET_DATA_CMD = curl -X POST -H "Accept: text/csv" --data-urlencode "query=$$(curl -s -H "Accept:text/sparql" https://databus.dbpedia.org/dbpedia/collections/latest-core)" https://databus.dbpedia.org/sparql | tail -n+2 | sed 's/\r$$//' | sed 's/"//g' | while read -r file; do wget -P rdf-input $$file; done
+DESCRIPTION  = RDF data from ${DATABUS_URL}
+
+[index]
+INPUT_FILES     = rdf-input/*
+CAT_INPUT_FILES = (cat rdf-input/*.nt; lbzcat -n2 rdf-input/*.bzip2 rdf-input/*.bz2)
+SETTINGS_JSON   = { "ascii-prefixes-only": true, "num-triples-per-batch": 1000000, "prefixes-external": [""] }
+WITH_TEXT_INDEX = false
+
+[server]
+PORT               = 7012
+ACCESS_TOKEN       = ${data:NAME}
+MEMORY_FOR_QUERIES = 10G
+CACHE_MAX_SIZE     = 5G
+
+[runtime]
+SYSTEM = docker
+IMAGE  = docker.io/adfreiburg/qlever:latest
+
+[ui]
+UI_CONFIG = dbpedia

qlever/Qleverfiles/Qleverfile.default

@@ -1,47 +1,51 @@
-# Automatically created by the "qlever" script
+# Default Qleverfile, use with https://github.com/ad-freiburg/qlever-control
 #
-# Modify as you see fit. Beware that some of the values below are executed as
-# commands  by the script.
-#
-# If you have never seen a Qleverfile before, we recommend that you look at the
-# pre-filled Qleverfiles on http://qlever.cs.uni-freiburg.de/qlever-control/
-# Qleverfiles first to get some inspiration. Or execute `qlever setup-config
-# <config name>` with a config name of your choice.
+# If you have never seen a Qleverfile before, we recommend that you first look
+# at the example Qleverfiles on http://qlever.cs.uni-freiburg.de/qlever-control/
+# src/qlever/Qleverfiles . Or execute `qlever setup-config <dataset>` on the
+# command line to obtain the example Qleverfiles for <dataset>.
 
 # As a minimum, each dataset needs a name. If you want `qlever get-data` to do
-# something meaningful, you need to define GET_DATA_CMD. If you want to use the
-# QLever UI, you should define DESCRIPTION (and if you have a text index,
-# also TEXT_DESCRIPTION).
+# something meaningful, you need to define GET_DATA_CMD. Otherwise, you need to 
+# generate (or download or copy from somewhere) the input files yourself. Each
+# dataset should have a short DESCRIPTION, ideally with a date.
 [data]
-NAME              =
-# GET_DATA_CMD      =
-# DESCRIPTION = 
-# TEXT_DESCRIPTION  =
+NAME         =
+GET_DATA_CMD =
+DESCRIPTION  = 
 
-# CAT_INPUT_FILES produces the data that is piped into QLever's index builder.
-# Use SETTINGS_JSON for more advanced configuration settings (see the other
-# Qleverfiles for examples).
+# The format for INPUT_FILES should be such that `ls ${INPUT_FILES}` lists all
+# input files. CAT_INPUT_FILES should write a concatenation of all input files
+# to stdout. For example, if your input files are gzipped, you can write `zcat
+# ${INPUT_FILES}`. Regarding SETTINGS_JSON, look at the other Qleverfiles for
+# examples. Several batches of size `num-triples-per-batch` are kept in RAM at 
+# the same time; increasing this, increases the memory usage but speeds up the
+# loading process.
 [index]
-# INPUT_FILES     = 
-# CAT_INPUT_FILES = cat ${INPUT_FILES}
-# SETTINGS_JSON   = {}
+INPUT_FILES     = *.ttl
+CAT_INPUT_FILES = cat ${INPUT_FILES}
+SETTINGS_JSON   = { "num-triples-per-batch": 1000000 }
 
-# As a minimum, you need to specify the PORT, where QLever will listen for
-# SPARQL queries. If you want to send priviledged commands to the server, you
-# need to specify an ACCESS_TOKEN (modify the random number below).
+# The server listens on PORT. If you want to send privileged commands to the
+# server, you need to specify an ACCESS_TOKEN, which you then have to set via a
+# URL parameter `access_token`. It should not be easily guessable, unless you
+# don't mind others to get privileged access to your server.
 [server]
-PORT = 7001
-# ACCESS_TOKEN = ${data:NAME}_1234567890
+PORT         =
+ACCESS_TOKEN = 
 
-# With USE_DOCKER = true, the qlever script will download the docker image for
-# you and run QLever inside docker containers. With USE_DOCKER = false, you need 
-# the QLever binaries in the PATH of your sheel.
+# Use SYSTEM = docker to run QLever inside a docker container; the Docker image
+# will be downloaded automatically. Use SYSTEM = native to use self-compiled
+# binaries `IndexBuilderMain` and `ServerMain` (which should be in you PATH).
 [runtime]
-SYSTEM = true
+SYSTEM = docker
 IMAGE  = docker.io/adfreiburg/qlever:latest
 
+# UI_PORT specifies the port of the QLever UI web app, when you run `qlever ui`.
 # The UI_CONFIG must be one of the slugs from http://qlever.cs.uni-freiburg.de
 # (see the dropdown menu on the top right, the slug is the last part of the URL).
-# In partiular, this determines the example queries.
+# It determines the example queries and which SPARQL queries are launched to
+# obtain suggestions as you type a query.
 [ui]
+UI_PORT   = 8176
 UI_CONFIG = default

qlever/Qleverfiles/Qleverfile.dnb

@@ -17,14 +17,14 @@
 [data]
 NAME              = dnb
 BASE_URL          = https://data.dnb.de/opendata
-GET_DATA_CMD      = curl -L -C - --remote-name-all ${BASE_URL}/authorities-gnd_lds.nt.gz ${BASE_URL}/dnb-all_lds.nt.gz ${BASE_URL}/dnb-all_ldsprov.nt.gz ${BASE_URL}/zdb_lds.nt.gz 2>&1 | tee ${data:NAME}.getdata-log.txt
+GET_DATA_CMD      = curl -L -C - --remote-name-all --remote-time ${BASE_URL}/authorities-gnd_lds.nt.gz ${BASE_URL}/dnb-all_lds.nt.gz ${BASE_URL}/dnb-all_ldsprov.nt.gz ${BASE_URL}/zdb_lds.nt.gz 2>&1 | tee ${data:NAME}.getdata-log.txt
 VERSION           = $$(date -r dnb-all_lds.nt.gz +%d.%m.%Y || echo "NO_DATE")
 DESCRIPTION       = DNB data from ${BASE_URL} (authoritities-gnd_lds, dnb_all_lds, dnb-all_ldsprov, zdb_lds), version ${VERSION}
 
 [index]
 INPUT_FILES     = *.nt.gz
-CAT_INPUT_FILES = zcat ${INPUT_FILES}
-SETTINGS_JSON   = { "ascii-prefixes-only": true, "num-triples-per-batch": 1000000 }
+CAT_INPUT_FILES = zcat ${INPUT_FILES} | sed '/"\$$R0"/d;/"0\.03013\$$D"/d'
+SETTINGS_JSON   = { "ascii-prefixes-only": false, "num-triples-per-batch": 1000000 }
 
 [server]
 PORT               = 7035

qlever/Qleverfiles/Qleverfile.imdb

@@ -9,8 +9,8 @@
 [data]
 NAME             = imdb
 IMDB_DATA_URL    = https://datasets.imdbws.com
-GET_PREFIXES     = echo "@prefix imdb: <https://www.imdb.com/> .\n"
-GET_IMDB_BASICS  = FILE=title.basics.tsv.gz; curl -sLO -C - ${IMDB_DATA_URL}/$${FILE}; zcat $${FILE} | sed 1d | awk -F'\t' '{ gsub("\"", "\\\"", $$3); printf "imdb:%s imdb:id \"%s\" ; imdb:type \"%s\" ; imdb:title \"%s\" .\n", $$1, $$1, $$2, $$3 }'; rm -f $${FILE}
+GET_PREFIXES     = echo "@prefix imdb: <https://www.imdb.com/> ."
+GET_IMDB_BASICS  = FILE=title.basics.tsv.gz; curl -sLO -C - ${IMDB_DATA_URL}/$${FILE}; zcat $${FILE} | sed 1d | awk -F'\t' '{ gsub("\\\\", "\\\\", $$3); gsub("\"", "\\\"", $$3); printf "imdb:%s imdb:id \"%s\" ; imdb:type \"%s\" ; imdb:title \"%s\" .\n", $$1, $$1, $$2, $$3 }'; rm -f $${FILE}
 GET_IMDB_RATINGS = FILE=title.ratings.tsv.gz; curl -sLO -C - ${IMDB_DATA_URL}/$${FILE}; zcat $${FILE} | sed 1d | awk -F'\t' '{ printf "imdb:%s imdb:averageRating %s ; imdb:numVotes %s .\n", $$1, $$2, $$3 }'; rm -f $${FILE}
 GET_DATA_CMD     = (${GET_PREFIXES}; ${GET_IMDB_BASICS}; ${GET_IMDB_RATINGS}) > ${NAME}.ttl
 DESCRIPTION      = RDF data derived from ${IMDB_DATA_URL}
@@ -18,17 +18,17 @@ TEXT_DESCRIPTION = All literals, search with FILTER CONTAINS(?var, "...")
 
 [index]
 INPUT_FILES     = ${data:NAME}.ttl
-CAT_INPUT_FILES = cat ${FILE_NAMES}
+CAT_INPUT_FILES = cat ${INPUT_FILES}
 SETTINGS_JSON   = { "ascii-prefixes-only": false, "num-triples-per-batch": 1000000 }
 TEXT_INDEX      = from_literals
 
 [server]
 PORT               = 7029
-ACCESS_TOKEN       = ${data:NAME}_1234567890
+ACCESS_TOKEN       = ${data:NAME}
 MEMORY_FOR_QUERIES = 5G
 
 [runtime]
-SYSTEM = docker
+SYSTEM = native
 IMAGE  = docker.io/adfreiburg/qlever:latest
 
 [ui]

qlever/Qleverfiles/Qleverfile.pubchem

@@ -48,7 +48,7 @@ DESCRIPTION       = PubChem RDF from ${GET_DATA_URL}, version ${DATE} (all folde
 
 [index]
 INPUT_FILES     = pubchem.additional-ontologies.nt.gz nt.${DATE}/*.nt.gz
-CAT_INPUT_FILES = zcat ${FILE_NAMES}
+CAT_INPUT_FILES = zcat ${INPUT_FILES}
 SETTINGS_JSON   = { "languages-internal": [], "prefixes-external": [""], "ascii-prefixes-only": false, "num-triples-per-batch": 1000000 }
 STXXL_MEMORY    = 10G
 

qlever/Qleverfiles/Qleverfile.uniprot

@@ -1,37 +1,38 @@
 # Qleverfile for UniProt, use with https://github.com/ad-freiburg/qlever-control
 #
-# qlever get-data  # download RDFXML and convert to NT (around 1 TB each)
-# qlever index     # takes ~ 1.5 days and ~40 GB RAM (on an AMD Ryzen 9 5900X)
-# qlever start     # starts the server (takes a few second)
+# qlever get-data  # takes ~ 30 hours and ~ 2 TB of disk (for the NT files)
+# qlever index     # takes ~ 40 hours and ~ 60 GB RAM (on an AMD Ryzen 9 5900X)
+# qlever start     # starts the server (takes a few seconds)
 #
 # Install packages: sudo apt install -y libxml2-utils parallel xz-utils pv
 # Install manually: Apache Jena binaries (https://dlcdn.apache.org/jena/binaries)
 #
-# Set DATE to the date of the latest release
-#
-# IMPORTANT: Build on SSD, disk space required: ~ 10 T. For running the server,
-# the uniprot.index.???.meta files can be on HDD.
+# Set DATE to the date of the latest release. Build on SSD (requires ~ 7 TB
+# during build, ~ 3 TB after build). The uniprot.index.???.meta files can be on
+# HDD without significant performance loss (when running the server).
 
 [data]
 NAME           = uniprot
-DATE           = 2024-01-24
+DATE           = 2024-05-29
 DOWNLOAD_URL   = https://ftp.uniprot.org/pub/databases/uniprot/current_release/rdf
 GET_RDFXML_CMD = mkdir -p rdf.${DATE} && curl -s ${DOWNLOAD_URL}/RELEASE.meta4 | sed "s/<metalink.*/<metalink>/" | xmllint --xpath "/metalink/files/file/url[@location=\"ch\"]/text()" - | while read URL; do wget --no-verbose -P rdf.${DATE} $$URL 2>&1 | tee -a uniprot.download-log; done
-RDFXML2NT_CMD  = mkdir -p nt.${DATE} && for RDFXML in rdf.${DATE}/*.{owl,owl.xz,rdf,rdf.xz}; do echo "xzcat -f $$RDFXML | rdfxml --output=nt 2> /dev/null | xz -c > nt.${DATE}/$$(basename $$RDFXML | sed 's/\(rdf\|rdf.xz\|owl\|owl.xz\)$$/nt.xz/') && echo 'DONE converting $$RDFXML'"; done | parallel
+RDFXML2NT_CMD  = mkdir -p nt.${DATE} && for RDFXML in rdf.${DATE}/*.{owl,owl.xz,rdf,rdf.xz}; do echo "xzcat -f $$RDFXML | rdfxml --output=nt 2> /dev/null | gzip -c > nt.${DATE}/$$(basename $$RDFXML | sed 's/\(rdf\|rdf.xz\|owl\|owl.xz\)$$/nt.gz/') && echo 'DONE converting $$RDFXML'"; done | parallel
 GET_DATA_CMD   = rdfxml --help && date > ${NAME}.get-data.begin-date && ${GET_RDFXML_CMD} && ${RDFXML2NT_CMD} && date > ${NAME}.get-data.end-date
 DESCRIPTION    = Complete UniProt data from ${DOWNLOAD_URL}, version ${DATE}
 
 [index]
-INPUT_FILES     = nt.${data:DATE}/*.nt.xz
-CAT_INPUT_FILES = parallel --tmpdir . -j 4 'xzcat -f {}' ::: nt.${data:DATE}/*.nt.xz | pv -q -B 5G 
+INPUT_FILES     = nt.${data:DATE}/*.nt.gz
+CAT_INPUT_FILES = parallel --tmpdir . -j 4 'zcat -f {}' ::: ${INPUT_FILES} | pv -q -B 5G
 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
 
 [server]
-PORT               = 7018
-ACCESS_TOKEN       = ${data:NAME}_1369924040
-MEMORY_FOR_QUERIES = 20G
-CACHE_MAX_SIZE     = 10G
+PORT                        = 7018
+ACCESS_TOKEN                = ${data:NAME}
+MEMORY_FOR_QUERIES          = 20G
+CACHE_MAX_SIZE              = 10G
+CACHE_MAX_SIZE_SINGLE_ENTRY = 5G
+TIMEOUT	                    = 300s
 
 [runtime]
 SYSTEM = docker

qlever/Qleverfiles/Qleverfile.wikidata

@@ -1,24 +1,27 @@
-# Qleverfile for Wikidata, use with https://github.com/ad-freiburg/qlever-control
+# Qleverfile for Wikidata, use with qlever script (`pip install qlever`)
 #
-# qlever get-data    downloads two .bz2 files of total size ~100 GB
-# qlever index       takes ~7 hours and ~40 GB RAM (on an AMD Ryzen 9 5900X)
-# qlever start       starts the server (takes around 30 seconds)
+# qlever get-data  # downloads two .bz2 files of total size ~100 GB
+# qlever index     # takes ~4.5 hours and ~20 GB RAM (on an AMD Ryzen 9 5900X)
+# qlever start     # starts the server (takes a few seconds)
+
+[DEFAULT]
+NAME = wikidata
 
 [data]
-NAME         = wikidata
 GET_DATA_URL = https://dumps.wikimedia.org/wikidatawiki/entities
-GET_DATA_CMD = curl -LO -C - ${GET_DATA_URL}/latest-all.ttl.bz2 ${GET_DATA_URL}/latest-lexemes.ttl.bz2
-DESCRIPTION  = "Full Wikidata dump from ${GET_DATA_URL} (latest-all.ttl.bz2 and latest-lexemes.ttl.bz2)"
+GET_DATA_CMD = curl -LRC - --remote-name-all ${GET_DATA_URL}/latest-all.ttl.bz2 ${GET_DATA_URL}/latest-lexemes.ttl.bz2 2>&1
+VERSION      = $$(date -r latest-all.ttl.bz2 +%d.%m.%Y || echo "NO_DATE")
+DESCRIPTION  = Full Wikidata dump from ${GET_DATA_URL} (latest-all.ttl.bz2 and latest-lexemes.ttl.bz2, version ${VERSION})
 
 [index]
-INPUT_FILES     = latest-lexemes.ttl.bz2 latest-all.ttl.bz2 
-CAT_INPUT_FILES = bzcat ${FILE_NAMES}
-SETTINGS_JSON   = { "languages-internal": [], "prefixes-external": [""], "locale": { "language": "en", "country": "US", "ignore-punctuation": true }, "ascii-prefixes-only": false, "num-triples-per-batch": 5000000 }
+INPUT_FILES     = latest-all.ttl.bz2 latest-lexemes.ttl.bz2
+CAT_INPUT_FILES = lbzcat -n 4 -f ${INPUT_FILES}
+SETTINGS_JSON   = { "languages-internal": [], "prefixes-external": [""], "locale": { "language": "en", "country": "US", "ignore-punctuation": true }, "ascii-prefixes-only": true, "num-triples-per-batch": 5000000 }
 STXXL_MEMORY    = 10G
 
 [server]
 PORT               = 7001
-ACCESS_TOKEN       = ${data:NAME}_372483264
+ACCESS_TOKEN       = ${data:NAME}
 MEMORY_FOR_QUERIES = 20G
 CACHE_MAX_SIZE     = 10G
 

qlever/Qleverfiles/Qleverfile.wikipathways

@@ -1,16 +1,16 @@
 # Qleverfile for WikiPathways, use with https://github.com/ad-freiburg/qlever-control
 #
-# qlever get-data  # downloads .gz file of size ~100 MB (as of 24.02.2024)
+# qlever get-data  # takes ~3 seconds, generates TTL of size ~600 MB
 # qlever index     # takes ~20 seconds and little RAM (on an AMD Ryzen 9 5900X)
-# qlever start     # starts the server (takes around 2 minutes)
+# qlever start     # instant
 #
 # Limitations: does not include the ontologies (WP, GPML, ChEBI, PW, CLO, ...) yet
 
 [data]
 NAME             = wikipathways
-RELEASE          = 20231210
+RELEASE          = 20240810
 GET_DATA_URL     = https://data.wikipathways.org/${RELEASE}/rdf
-GET_DATA_CMD     = wget -O wikipathways-rdf-void.ttl ${GET_DATA_URL}/wikipathways-${RELEASE}-rdf-void.ttl && \
+GET_DATA_CMD     = wget -O wikipathways-rdf-void.ttl ${GET_DATA_URL}/wikipathways-rdf-void.ttl && \
                     wget ${GET_DATA_URL}/wikipathways-${RELEASE}-rdf-wp.zip && \
                       unzip -qq -c wikipathways-${RELEASE}-rdf-wp.zip -x wp/wpOntology.ttl > wikipathways-rdf-wp.ttl && \
                     wget ${GET_DATA_URL}/wikipathways-${RELEASE}-rdf-gpml.zip && 
@@ -23,13 +23,13 @@ TEXT_DESCRIPTION = All literals, search with FILTER KEYWORDS(?text, "...")
 
 [index]
 INPUT_FILES     = ${data:NAME}.prefix-definitions wikipathways-rdf-wp.ttl wikipathways-rdf-gpml.ttl wikipathways-rdf-void.ttl wikipathways-rdf-authors.ttl
-CAT_INPUT_FILES = cat ${FILE_NAMES}
+CAT_INPUT_FILES = cat ${INPUT_FILES}
 SETTINGS_JSON   = { "ascii-prefixes-only": false, "num-triples-per-batch": 1000000, "prefixes-external": [""] }
 TEXT_INDEX      = from_literals
 
 [server]
 PORT               = 7040
-ACCESS_TOKEN       = ${data:NAME}_7643543846
+ACCESS_TOKEN       = ${data:NAME}
 MEMORY_FOR_QUERIES = 5G
 
 [runtime]

qlever/commands/example_queries.py

@@ -227,6 +227,10 @@ class ExampleQueriesCommand(QleverCommand):
                 except Exception as e:
                     error_msg = str(e)
 
+            # Remove the result file (unless in debug mode).
+            if args.log_level != "DEBUG":
+                Path(result_file).unlink(missing_ok=True)
+
             # Print description, time, result in tabular form.
             if (len(description) > 60):
                 description = description[:57] + "..."
@@ -262,6 +266,4 @@ class ExampleQueriesCommand(QleverCommand):
                 log.info(colored("All queries failed", "red"))
 
         # Return success (has nothing to do with how many queries failed).
-        if args.log_level != "DEBUG":
-            Path(result_file).unlink(missing_ok=True)
         return True

qlever/commands/ui.py

@@ -5,6 +5,7 @@ import subprocess
 from qlever.command import QleverCommand
 from qlever.containerize import Containerize
 from qlever.log import log
+from qlever.util import is_port_used
 
 
 class UiCommand(QleverCommand):
@@ -53,6 +54,10 @@ class UiCommand(QleverCommand):
             Containerize.stop_and_remove_container(
                     container_system, args.ui_container)
 
+        # Check if the UI port is already being used.
+        if is_port_used(args.ui_port):
+            log.warning(f"It looks like the specified port for the UI ({args.ui_port}) is already in use. You can set another port in the Qleverfile in the [ui] section with the UI_PORT variable.")
+
         # Try to start the QLever UI.
         try:
             subprocess.run(pull_cmd, shell=True, stdout=subprocess.DEVNULL)
@@ -65,5 +70,5 @@ class UiCommand(QleverCommand):
         # Success.
         log.info(f"The QLever UI should now be up at {ui_url} ..."
                  f"You can log in as QLever UI admin with username and "
-                 f"passwort \"demo\"")
+                 f"password \"demo\"")
         return True

qlever/qlever_old.py

@@ -985,7 +985,7 @@ class Actions:
         log.info(f"The QLever UI should now be up at "
                  f"http://{host_name}:{self.config['ui']['port']}")
         log.info("You can log in as QLever UI admin with username and "
-                 "passwort \"demo\"")
+                 "password \"demo\"")
 
     @track_action_rank
     def action_cache_stats_and_settings(self, only_show=False):

qlever/qleverfile.py

@@ -51,7 +51,7 @@ class Qleverfile:
                 help="A concise description of the dataset")
         data_args["text_description"] = arg(
                 "--text-description", type=str, default=None,
-                help="A concice description of the addtional text data"
+                help="A concise description of the additional text data"
                      " if any")
 
         index_args["input_files"] = arg(
@@ -173,7 +173,7 @@ class Qleverfile:
                 help="The name of the container used by `qlever start`")
 
         ui_args["ui_port"] = arg(
-                "--ui_port", type=int, default=7000,
+                "--ui-port", type=int, default=8176,
                 help="The port of the Qlever UI when running `qlever ui`")
         ui_args["ui_config"] = arg(
                 "--ui-config", type=str, default="default",

qlever/util.py

@@ -1,7 +1,9 @@
 from __future__ import annotations
 
+import errno
 import re
 import secrets
+import socket
 import shlex
 import shutil
 import string
@@ -180,3 +182,21 @@ def get_random_string(length: int) -> str:
     """
     characters = string.ascii_letters + string.digits
     return "".join(secrets.choice(characters) for _ in range(length))
+
+
+def is_port_used(port: int) -> bool:
+    """
+    Try to bind to the port on all interfaces to check if the port is already in use.
+    If the port is already in use, `socket.bind` will raise an `OSError` with errno EADDRINUSE.
+    """
+    try:
+        sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+        # Ensure that the port is not blocked after the check.
+        sock.setsockopt(socket.SOL_SOCKET, socket.SO_REUSEADDR, 1)
+        sock.bind(('', port))
+        sock.close()
+        return False
+    except OSError as err:
+        if err.errno != errno.EADDRINUSE:
+            log.warning(f"Failed to determine if port is used: {err}")
+        return True

{qlever-0.5.2.dist-info → qlever-0.5.4.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: qlever
-Version: 0.5.2
+Version: 0.5.4
 Summary: Script for using the QLever SPARQL engine.
 Author-email: Hannah Bast <bast@cs.uni-freiburg.de>
 License: Apache-2.0

{qlever-0.5.2.dist-info → qlever-0.5.4.dist-info}/RECORD

@@ -5,32 +5,33 @@ qlever/config.py,sha256=qYPy-MQ7BwGrvKSazQWhs0lnlOFqm-d47mpZhc3fptc,10254
 qlever/containerize.py,sha256=p8g3O3G8a_0XLzSTzl_e5t9dqjbCQ-ippoA8vI2Z9pI,4193
 qlever/log.py,sha256=2O_RvFymnu_dB10ErBTAOsI8bgjORfdD0tE3USH-siM,1315
 qlever/qlever_main.py,sha256=tA_xqOs_FjvqlDIvKTprwuysfTwzsUjE7at26gRhCVA,2336
-qlever/qlever_old.py,sha256=6sHosOfJzkURpdK4wXLdGl4SUtPnlsNEUwAqUeJiRYA,62026
-qlever/qleverfile.py,sha256=6Ll81xkzel_s2Ju9ZfBXUGlRfikaAzZM6Do-dTrdo3k,12934
-qlever/util.py,sha256=eepj0SY9JJOUQq5kvtoPnWfoLLV9fbw_sTEWKHet66E,7147
-qlever/Qleverfiles/Qleverfile.dblp,sha256=DjeyY0MGNrqEY-_8nRkjSsofGBBSz_wIgQ048KoRQBM,1002
+qlever/qlever_old.py,sha256=X-JxmepFKYeFgSLLp0TRDNqXSxDwIbc8_0Xstiems8c,62026
+qlever/qleverfile.py,sha256=NjY3SFyRTm_igI8Rv87TOvZBiLwn1TgHmRh1jVA51DM,12935
+qlever/util.py,sha256=20NQJquSk_mSqvlK4k0OrSBqWrxKs5SgVshm5ucus5o,7847
+qlever/Qleverfiles/Qleverfile.dblp,sha256=Y6BqAG1GZg-OmEs0HM00yAQuY2TGnSzsOO1LLmGVn2Y,994
 qlever/Qleverfiles/Qleverfile.dblp-plus,sha256=Dwd9pK1vPcelKfw6sA-IuyhbZ6yIxOh6_84JgPYnB9Q,1332
-qlever/Qleverfiles/Qleverfile.default,sha256=mljl6I1RCkpIWOqMQwjzPZIsarYQx1R0mIlc583KuqU,1869
-qlever/Qleverfiles/Qleverfile.dnb,sha256=GgnsbtRUl__yMCqUX2EN5x1oDWpW93bUalMfUxN8534,1751
+qlever/Qleverfiles/Qleverfile.dbpedia,sha256=aaNZZayE-zVePGSwPzXemkX__Ns8-kP_E7DNNKZPnqg,1160
+qlever/Qleverfiles/Qleverfile.default,sha256=UWDy9ohhbKjE4n5xEYqbOPZOiYDFzsnJ_aNNBMCOlaI,2402
+qlever/Qleverfiles/Qleverfile.dnb,sha256=43w_CVi00yf7FHdDvBtHHQR3yU1d-JCNnD_uxYZJOvk,1803
 qlever/Qleverfiles/Qleverfile.fbeasy,sha256=jeztW4gFpWL_w1nCH5qGHeZyZv2lz_kG6f1G3r3DkJ4,974
 qlever/Qleverfiles/Qleverfile.freebase,sha256=k6PqYrtHTBr0EydObm1Hg9QWyAAM9fXkdcjhReDg0fM,1035
-qlever/Qleverfiles/Qleverfile.imdb,sha256=uL5XlPwX01AmH-j6_Bc-PRm2fuPxGSIu8NaDflY525U,1623
+qlever/Qleverfiles/Qleverfile.imdb,sha256=8F6tpEi0uXsMm6lofwjNkLq1X9IEUSoHK8YK_5YCf_g,1638
 qlever/Qleverfiles/Qleverfile.ohm-planet,sha256=Y_yUxdpWpUOSDo_zmVKj3caa8X-Wv-1KmacBMks_4QA,2650
 qlever/Qleverfiles/Qleverfile.olympics,sha256=5w9BOFwEBhdSzPz-0LRxwhv-7Gj6xbF539HOXr3cqD0,1088
 qlever/Qleverfiles/Qleverfile.osm-country,sha256=UnlkckSXJDrknZORlU-Hdj_J82U4kStl1aRctCc5n6M,1953
 qlever/Qleverfiles/Qleverfile.osm-planet,sha256=2RilNix0fplN3GsNNyOu3GzmUss1Pq7586WKOFAQnSs,1400
-qlever/Qleverfiles/Qleverfile.pubchem,sha256=bOhiJKUxzDiAm1UyXFPDQLYTqGc9jM8240fhobYLij0,3898
+qlever/Qleverfiles/Qleverfile.pubchem,sha256=a6EAP8mOfC0V6NnVCLarvRagyoQSQDItR7AnrZqL9iE,3899
 qlever/Qleverfiles/Qleverfile.scientists,sha256=9eZ2c6P9a3E3VHa3RR7LdOQbF4k3oyyrn56Z3u4LZYs,1164
-qlever/Qleverfiles/Qleverfile.uniprot,sha256=FS8QLHvujbjUYyU2Ma0PRgfCWlulviaGLc_1csxpuic,2201
+qlever/Qleverfiles/Qleverfile.uniprot,sha256=9kAKseomdUnIt7EAZge39g1MTuaLVaSW9JYLHzIMolM,2338
 qlever/Qleverfiles/Qleverfile.vvz,sha256=ftdMj5dCC9jAlFtNt2WR7kP30w0itT_iYtj5HoUVyWU,931
-qlever/Qleverfiles/Qleverfile.wikidata,sha256=fhWSChZTH3c2y14kgP1P5Duq1SsewTOK3wETf6RRmI8,1172
-qlever/Qleverfiles/Qleverfile.wikipathways,sha256=qWjfT-CVQCgRfN6fXPwBORMbjzXS_xsJ2DoCamQI7Rs,2045
+qlever/Qleverfiles/Qleverfile.wikidata,sha256=vDkTY3mPSx2C8MvFWfB72zZoc4d-TMJSw3f_-FqnEqs,1275
+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
 qlever/commands/add_text_index.py,sha256=dkqYtwgOhgnXiei_eyhBWYCtdAiQUEmjWoa3JMlMb4c,3641
 qlever/commands/cache_stats.py,sha256=6JjueQstAqc8dNfgY8TP2EitFMxdUvCwrcyd7KUEb2o,4157
 qlever/commands/clear_cache.py,sha256=AnE1MOoj1ZexxrRT8FGeBLlv8rtQIVV4DP8VBn5-X-s,2843
-qlever/commands/example_queries.py,sha256=2rYTd35t0r7et0i-IBBcCpmVlYZya9kvwSI-gdTpNdE,12326
+qlever/commands/example_queries.py,sha256=L32gVKdvb7MwZNqphF1K_gK6WARiwno6oiNDBgZuj1Y,12396
 qlever/commands/get_data.py,sha256=f9kjZI3TKad6JHSuXWNkeoajmW8h0Sx8ShvjauDCtNo,1412
 qlever/commands/index.py,sha256=lJhDnweknFZQm1czqPzNyz33EvbjIvOrS4j0wDaJ98o,5663
 qlever/commands/index_stats.py,sha256=_BiUNBhmbYd9RPxrlm4HF0oENO6JmqnRiAkwkyOdN4U,11722
@@ -40,11 +41,11 @@ qlever/commands/setup_config.py,sha256=6T0rXrIdejKMKhDbOMEMBKyMF_hAqO5nJaRFb57QP
 qlever/commands/start.py,sha256=2rOtk3NmhEs28D5csL_a1BdjSWU9VkcH6AqYT0vdww0,9285
 qlever/commands/status.py,sha256=5S6EdapZEwFKV9cQZtNYcZhMbAXAY-FP6ggjIhfX8ek,1631
 qlever/commands/stop.py,sha256=TZs4bxKHvujlZAU8BZmFjA5eXSZNAa6EeNzvPpEZsuI,4139
-qlever/commands/ui.py,sha256=rV8u017WLbfz0zVT_c9GC4d9v1WWwrTM3kfGONbeCvQ,2499
+qlever/commands/ui.py,sha256=b7g7Mp6ZWevn8f1kwFr-WR4ZWMq42KEV4cGl2QS7M1E,2828
 qlever/commands/warmup.py,sha256=WOZSxeV8U_F6pEEnAb6YybXLQMxZFTRJXs4BPHUhsmc,1030
-qlever-0.5.2.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-qlever-0.5.2.dist-info/METADATA,sha256=MHlNH1mplzq3hJ0ETmjUqM4Zw6zLqvends9IT60M4Io,4146
-qlever-0.5.2.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-qlever-0.5.2.dist-info/entry_points.txt,sha256=U_gbYYi0wwdsn884eb0XoOXfvhACOsxhlO330dZ9bi0,87
-qlever-0.5.2.dist-info/top_level.txt,sha256=kd3zsYqiFd0--Czh5XTVkfEq6XR-XgRFW35X0v0GT-c,7
-qlever-0.5.2.dist-info/RECORD,,
+qlever-0.5.4.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+qlever-0.5.4.dist-info/METADATA,sha256=sL8oC3NhgnRmUMEMIqfqozI_RTcHkaFYUWeailPrB8g,4146
+qlever-0.5.4.dist-info/WHEEL,sha256=HiCZjzuy6Dw0hdX5R3LCFPDmFS4BWl8H-8W39XfmgX4,91
+qlever-0.5.4.dist-info/entry_points.txt,sha256=U_gbYYi0wwdsn884eb0XoOXfvhACOsxhlO330dZ9bi0,87
+qlever-0.5.4.dist-info/top_level.txt,sha256=kd3zsYqiFd0--Czh5XTVkfEq6XR-XgRFW35X0v0GT-c,7
+qlever-0.5.4.dist-info/RECORD,,

{qlever-0.5.2.dist-info → qlever-0.5.4.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: bdist_wheel (0.43.0)
+Generator: setuptools (72.2.0)
 Root-Is-Purelib: true
 Tag: py3-none-any