qlever 0.5.7__py3-none-any.whl → 0.5.9__py3-none-any.whl

qlever/util.py

@@ -29,8 +29,9 @@ def get_total_file_size(patterns: list[str]) -> int:
     return total_size
 
 
-def run_command(cmd: str, return_output: bool = False,
-                show_output: bool = False) -> Optional[str]:
+def run_command(
+    cmd: str, return_output: bool = False, show_output: bool = False
+) -> Optional[str]:
     """
     Run the given command and throw an exception if the exit code is non-zero.
     If `return_output` is `True`, return what the command wrote to `stdout`.
@@ -45,7 +46,7 @@ def run_command(cmd: str, return_output: bool = False,
         "shell": True,
         "text": True,
         "stdout": None if show_output else subprocess.PIPE,
-        "stderr": subprocess.PIPE
+        "stderr": subprocess.PIPE,
     }
     result = subprocess.run(f"set -o pipefail; {cmd}", **subprocess_args)
     # If the exit code is non-zero, throw an exception. If something was
@@ -63,17 +64,20 @@ def run_command(cmd: str, return_output: bool = False,
             raise Exception(result.stderr.replace("\n", " ").strip())
         else:
             raise Exception(
-                    f"Command failed with exit code {result.returncode}"
-                    f" but nothing written to stderr")
+                f"Command failed with exit code {result.returncode}"
+                f" but nothing written to stderr"
+            )
     # Optionally, return what was written to `stdout`.
     if return_output:
         return result.stdout
 
 
-def run_curl_command(url: str,
-                     headers: dict[str, str] = {},
-                     params: dict[str, str] = {},
-                     result_file: Optional[str] = None) -> str:
+def run_curl_command(
+    url: str,
+    headers: dict[str, str] = {},
+    params: dict[str, str] = {},
+    result_file: Optional[str] = None,
+) -> str:
     """
     Run `curl` with the given `url`, `headers`, and `params`. If `result_file`
     is `None`, return the output, otherwise, write the output to the given file
@@ -83,22 +87,29 @@ def run_curl_command(url: str,
     # Construct and run the `curl` command.
     default_result_file = "/tmp/qlever.curl.result"
     actual_result_file = result_file if result_file else default_result_file
-    curl_cmd = (f"curl -s -o \"{actual_result_file}\""
-                f" -w \"%{{http_code}}\n\" {url}"
-                + "".join([f" -H \"{key}: {value}\""
-                           for key, value in headers.items()])
-                + "".join([f" --data-urlencode {key}={shlex.quote(value)}"
-                           for key, value in params.items()]))
-    result = subprocess.run(curl_cmd, shell=True, text=True,
-                            stdout=subprocess.PIPE,
-                            stderr=subprocess.PIPE)
+    curl_cmd = (
+        f'curl -s -o "{actual_result_file}"'
+        f' -w "%{{http_code}}\n" {url}'
+        + "".join([f' -H "{key}: {value}"' for key, value in headers.items()])
+        + "".join(
+            [
+                f" --data-urlencode {key}={shlex.quote(value)}"
+                for key, value in params.items()
+            ]
+        )
+    )
+    result = subprocess.run(
+        curl_cmd, shell=True, text=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE
+    )
     # Case 1: An error occurred, raise an exception.
     if result.returncode != 0:
         if len(result.stderr) > 0:
             raise Exception(result.stderr)
         else:
-            raise Exception(f"curl command failed with exit code "
-                            f"{result.returncode}, stderr is empty")
+            raise Exception(
+                f"curl command failed with exit code "
+                f"{result.returncode}, stderr is empty"
+            )
     # Case 2: Return output (read from `default_result_file`).
     if result_file is None:
         result_file_path = Path(default_result_file)
@@ -117,9 +128,9 @@ def is_qlever_server_alive(port: str) -> bool:
 
     message = "from the qlever script".replace(" ", "%20")
     curl_cmd = f"curl -s http://localhost:{port}/ping?msg={message}"
-    exit_code = subprocess.call(curl_cmd, shell=True,
-                                stdout=subprocess.DEVNULL,
-                                stderr=subprocess.DEVNULL)
+    exit_code = subprocess.call(
+        curl_cmd, shell=True, stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL
+    )
     return exit_code == 0
 
 
@@ -152,15 +163,15 @@ def show_process_info(psutil_process, cmdline_regex, show_heading=True):
 
     try:
         pinfo = psutil_process.as_dict(
-                attrs=['pid', 'username', 'create_time',
-                       'memory_info', 'cmdline'])
+            attrs=["pid", "username", "create_time", "memory_info", "cmdline"]
+        )
         # Note: pinfo[`cmdline`] is `None` if the process is a zombie.
-        cmdline = " ".join(pinfo['cmdline'] or [])
+        cmdline = " ".join(pinfo["cmdline"] or [])
         if len(cmdline) == 0 or not re.search(cmdline_regex, cmdline):
             return False
-        pid = pinfo['pid']
-        user = pinfo['username'] if pinfo['username'] else ""
-        start_time = datetime.fromtimestamp(pinfo['create_time'])
+        pid = pinfo["pid"]
+        user = pinfo["username"] if pinfo["username"] else ""
+        start_time = datetime.fromtimestamp(pinfo["create_time"])
         if start_time.date() == date.today():
             start_time = start_time.strftime("%H:%M")
         else:
@@ -193,10 +204,24 @@ def is_port_used(port: int) -> bool:
         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.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
+
+
+def format_size(bytes, suffix="B"):
+    """
+    Scale bytes to its proper format
+    e.g:
+        1253656 => '1.20MB'
+        1253656678 => '1.17GB'
+    """
+    factor = 1024
+    for unit in ["", "K", "M", "G", "T", "P"]:
+        if bytes < factor:
+            return f"{bytes:.2f} {unit}{suffix}"
+        bytes /= factor

{qlever-0.5.7.dist-info → qlever-0.5.9.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: qlever
-Version: 0.5.7
+Version: 0.5.9
 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-0.5.9.dist-info}/RECORD

@@ -1,52 +1,52 @@
 qlever/__init__.py,sha256=7VKA8tp5iHZQyTXhDOcxUbloZ7WyxDnkruq0iJOzQcE,1403
-qlever/__main__.py,sha256=MqM37bEzQeJEGUXZvuLcilIvnObZiG2eTGIkfKGpdnw,62016
 qlever/command.py,sha256=yOr0Uc8D8-AM7EjwDsVzbc3KNYjPH-FVOZhIHkqO588,2749
 qlever/config.py,sha256=qYPy-MQ7BwGrvKSazQWhs0lnlOFqm-d47mpZhc3fptc,10254
-qlever/containerize.py,sha256=HRtC5jrRRpcBmdrXK2LsEAKiGVq2dWH1Oa2Ps2nvAsE,4643
+qlever/containerize.py,sha256=bnHmjKIFEe-NcuAMRNnXAFjRVLcLnk9f5JspCCyhgt8,5210
 qlever/log.py,sha256=2O_RvFymnu_dB10ErBTAOsI8bgjORfdD0tE3USH-siM,1315
 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-plus,sha256=Dwd9pK1vPcelKfw6sA-IuyhbZ6yIxOh6_84JgPYnB9Q,1332
+qlever/qleverfile.py,sha256=whFQOBCEb7XsCaLwBgI2rleRZaxTVEXe-mDCpgHnvss,13611
+qlever/util.py,sha256=qLxBRyHPT2VTj0xcOCFcP6HV-Lm-g-64QpvOc4V0_a8,8029
+qlever/Qleverfiles/Qleverfile.dblp,sha256=wXZweNfYgEx-IGF1vIJMgqYUSWanQlzPj1EzUOGVuXA,1340
+qlever/Qleverfiles/Qleverfile.dblp-plus,sha256=TJHxp8I1P6JKJjbuAllEpB32-huuY1gH0FlenqPVJ5g,1334
 qlever/Qleverfiles/Qleverfile.dbpedia,sha256=aaNZZayE-zVePGSwPzXemkX__Ns8-kP_E7DNNKZPnqg,1160
-qlever/Qleverfiles/Qleverfile.default,sha256=UWDy9ohhbKjE4n5xEYqbOPZOiYDFzsnJ_aNNBMCOlaI,2402
+qlever/Qleverfiles/Qleverfile.default,sha256=Kj-J1Kkv8PWN7wuMdZU6DUUlEuBIcSNysJCE-R63we8,2407
 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=8F6tpEi0uXsMm6lofwjNkLq1X9IEUSoHK8YK_5YCf_g,1638
+qlever/Qleverfiles/Qleverfile.fbeasy,sha256=9dwCMltT0BIMN4LRmaZFp1a7aV0kh0nJ9XLiQb_NJNo,940
+qlever/Qleverfiles/Qleverfile.freebase,sha256=eFMOxeyuWVbb06Gv2-VFkuKE5tTyckddTDHdw5wbZN8,1028
+qlever/Qleverfiles/Qleverfile.imdb,sha256=1xUBFimgnEHKP_o6tlqwJvIVpEE4Zx6UK_JnnQsG7Ew,1638
 qlever/Qleverfiles/Qleverfile.ohm-planet,sha256=yG6NgW6x6sGTzmCi1wEAkQ-i9goTj2u3PQxvCUwjExs,2122
 qlever/Qleverfiles/Qleverfile.olympics,sha256=5w9BOFwEBhdSzPz-0LRxwhv-7Gj6xbF539HOXr3cqD0,1088
+qlever/Qleverfiles/Qleverfile.orkg,sha256=Uizz-RhlSeExgfckWztewa4l_v3zMN8IR7NaGYKrqt4,937
 qlever/Qleverfiles/Qleverfile.osm-country,sha256=Pb9o5H3b7wVlVRgdiPHWCvrnkIRS1YUhxOazbUmoKZE,1897
-qlever/Qleverfiles/Qleverfile.osm-planet,sha256=2RilNix0fplN3GsNNyOu3GzmUss1Pq7586WKOFAQnSs,1400
+qlever/Qleverfiles/Qleverfile.osm-planet,sha256=555aaMOIzAILvzwpCjucd_GE7TlYxmT2Qh8hME68stU,1418
 qlever/Qleverfiles/Qleverfile.pubchem,sha256=YuDzWQmukSvL1opu7cf1KX9407_P21lmecYZ9cdbuvA,5611
 qlever/Qleverfiles/Qleverfile.scientists,sha256=9eZ2c6P9a3E3VHa3RR7LdOQbF4k3oyyrn56Z3u4LZYs,1164
 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.vvz,sha256=cLzm85erKoFCDllH5eFcSi35MdR6Tahj1MgtvGRxanM,922
+qlever/Qleverfiles/Qleverfile.wikidata,sha256=BB7GHAY-lV0B10BWabPOUKtqWjEHFPn3UQc6f4i2-14,2474
 qlever/Qleverfiles/Qleverfile.wikipathways,sha256=UFEVLrtOBiSQfibBN9xc2wDXrnWcnx5f8PY9khcE6bc,1983
-qlever/Qleverfiles/Qleverfile.yago-4,sha256=GikYPqChCtbAyZOVqszmVUwgQxSePTcgM8xw2b_21e4,1849
+qlever/Qleverfiles/Qleverfile.yago-4,sha256=hAS_2ZmC1zxNsKXip7t1F_iqu3CC-6O7v6HZhuFbnWY,1819
 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=5-0ln5EkuDcQYPqKKAOcLaTIStMzFhkAogaNedfRc_I,15271
+qlever/commands/example_queries.py,sha256=rtMOQw7cJe0Aia_1O7UyKcxHbz7ln9BSZYWUQI9OFA8,16389
 qlever/commands/get_data.py,sha256=f9kjZI3TKad6JHSuXWNkeoajmW8h0Sx8ShvjauDCtNo,1412
-qlever/commands/index.py,sha256=TwL6o16KZON1hbD8UnXMw_tduLXWcy7D4o6tbsLt1OE,5888
+qlever/commands/index.py,sha256=Ebb5dSDJ0u_AElKPgMzQN0YxPgpqbeNT1JscM3xGiMo,10256
 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
-qlever/commands/setup_config.py,sha256=6T0rXrIdejKMKhDbOMEMBKyMF_hAqO5nJaRFb57QPQU,2964
+qlever/commands/setup_config.py,sha256=p0-wJcalzEOrSkIiaicQjOkp_WVNEeLsd0A_WZrlGfs,3345
 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=b7g7Mp6ZWevn8f1kwFr-WR4ZWMq42KEV4cGl2QS7M1E,2828
+qlever/commands/system_info.py,sha256=SShsnEV7QROgdbABeJ6Wk4U_CNjqlYO1J5HrpNCVNMs,4615
+qlever/commands/ui.py,sha256=rZxIYHZr-PqgQKfvVwl8woDnTGR-sFc-f6cPjcORaOk,3611
 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-0.5.9.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+qlever-0.5.9.dist-info/METADATA,sha256=uoi2Wb5N4Co5DdD-gG-uaxgfl1PrWhNY5Twr56clyTk,4582
+qlever-0.5.9.dist-info/WHEEL,sha256=P9jw-gEje8ByB7_hXoICnHtVCrEwMQh-630tKvQWehc,91
+qlever-0.5.9.dist-info/entry_points.txt,sha256=U_gbYYi0wwdsn884eb0XoOXfvhACOsxhlO330dZ9bi0,87
+qlever-0.5.9.dist-info/top_level.txt,sha256=kd3zsYqiFd0--Czh5XTVkfEq6XR-XgRFW35X0v0GT-c,7
+qlever-0.5.9.dist-info/RECORD,,

{qlever-0.5.7.dist-info → qlever-0.5.9.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (75.1.0)
+Generator: setuptools (75.3.0)
 Root-Is-Purelib: true
 Tag: py3-none-any
 

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