refactors to use lod_storage endpoint manager

Author: WolfgangFahl

pyproject.toml

@@ -26,7 +26,7 @@ dependencies = [
 	# https://github.com/WolfgangFahl/nicegui_widgets
 	"ngwidgets>=0.30.0",
     # https://pypi.org/project/pyLodStorage/
-    "pyLodStorage>=0.18.0",
+    "pyLodStorage>=0.18.1",
     # https://pypi.org/project/py-3rdparty-mediawiki/
     "py-3rdparty-mediawiki>=0.18.1",
     "wikitextparser",

snapquery/endpoint.py

@@ -0,0 +1,94 @@
+"""
+Created 2024
+
+@author: tholzheim
+
+Move to separate module in 2025-12-01 by wf
+"""
+from enum import Enum
+
+from lodstorage.query import Query
+from snapquery.endpoint import Endpoint
+from snapquery.snapquery_core import NamedQuery
+from snapquery.sparql_analyzer import SparqlAnalyzer
+
+
+class QueryPrefixMerger(Enum):
+    """
+    SPARQL Query prefix merger
+    """
+
+    RAW = "raw"
+    SIMPLE_MERGER = "simple merger"
+    ANALYSIS_MERGER = "analysis merger"
+
+    @classmethod
+    def _missing_(cls, key):
+        return cls.default_merger()
+
+    @classmethod
+    def default_merger(cls) -> "QueryPrefixMerger":
+        return cls.SIMPLE_MERGER
+
+    @classmethod
+    def get_by_name(cls, name: str) -> "QueryPrefixMerger":
+        merger_map = {merger.name: merger.value for merger in QueryPrefixMerger}
+        merger_value = merger_map.get(name, None)
+        merger = QueryPrefixMerger(merger_value)
+        return merger
+
+    @classmethod
+    def merge_prefixes(
+        cls,
+        named_query: NamedQuery,
+        query: Query,
+        endpoint: Endpoint,
+        merger: "QueryPrefixMerger",
+    ) -> str:
+        """
+        Merge prefixes with the given merger
+        Args:
+            named_query (NamedQuery):
+            query (Query):
+            endpoint (Endpoint):
+            merger (QueryPrefixMerger):
+
+        Returns:
+            merged query
+        """
+        if merger == QueryPrefixMerger.SIMPLE_MERGER:
+            return cls.simple_prefix_merger(query.query, endpoint)
+        elif merger == QueryPrefixMerger.ANALYSIS_MERGER:
+            return cls.analysis_prefix_merger(query.query)
+        else:
+            return query.query
+
+    @classmethod
+    def simple_prefix_merger(cls, query_str: str, endpoint: Endpoint) -> str:
+        """
+        Simple prefix merger
+        Args:
+            query_str (str): the query string
+            endpoint (Endpoint): the endpoint
+
+        Returns:
+            merged query
+        """
+        prefixes = endpoint.prefixes if hasattr(endpoint, "prefixes") else None
+        merged_query = query_str
+        if prefixes:
+            merged_query = f"{prefixes}\n{merged_query}"
+        return merged_query
+
+    @classmethod
+    def analysis_prefix_merger(cls, query_str: str) -> str:
+        """
+        Analysis prefix merger
+        Args:
+            query_str
+
+        Returns:
+            merged query
+        """
+        merged_query = SparqlAnalyzer.add_missing_prefixes(query_str)
+        return merged_query

snapquery/prefix_merger.py

@@ -0,0 +1,98 @@
+# Optional SPARQL endpoints for snapquery
+# WF 2025-12-01 - new format
+# state nees to be checked
+endpoints:
+  wikidata-openlinksw:
+    description: OpenLink Virtuoso demo (unstable).
+    lang: sparql
+    endpoint: https://wikidata.demo.openlinksw.com/sparql
+    website: https://wikidata.demo.openlinksw.com/sparql
+    database: virtuoso
+    method: POST
+    calls_per_minute: 20
+    prefix_sets:
+      - rdf
+      - wikidata
+
+  wikidata-triply:
+    description: TriplyDB mirror.
+    lang: sparql
+    method: POST
+    database: TriplyDB
+    endpoint: https://api.triplydb.com/datasets/wikimedia/wikidata/sparql
+    website: https://triplydb.com/wikimedia/wikidata/sparql
+    calls_per_minute: 30
+    prefix_sets:
+      - rdf
+      - wikidata
+
+  wikidata-qlever:
+    description: QLever Freiburg Wikidata.
+    lang: sparql
+    method: POST
+    database: qlever
+    endpoint: https://qlever.cs.uni-freiburg.de/api/wikidata
+    website: https://qlever.cs.uni-freiburg.de/wikidata
+    calls_per_minute: 60
+    prefix_sets:
+      - rdf
+      - wikidata
+      - commons
+
+  wikidata-qlever-dbis:
+    description: QLever RWTH Wikidata.
+    lang: sparql
+    method: POST
+    database: qlever
+    endpoint: https://qlever-api.wikidata.dbis.rwth-aachen.de/
+    website: https://qlever.wikidata.dbis.rwth-aachen.de/wikidata
+    calls_per_minute: 60
+    prefix_sets:
+      - rdf
+      - wikidata
+
+  wikidata-scatter:
+    description: Scatter experimental.
+    lang: sparql
+    endpoint: https://query-direct2.orbopengraph.com/bigdata/namespace/wdq/sparql
+    website: https://scatter.red/
+    database: blazegraph
+    method: GET
+    calls_per_minute: 20
+    prefix_sets:
+      - rdf
+      - wikidata
+
+  orkg:
+    description: ORKG (rate-limited).
+    lang: sparql
+    endpoint: https://orkg.org/triplestore
+    website: https://orkg.org/sparql
+    database: virtuoso
+    prefix_sets:
+      - rdf
+      - orkg
+
+  dblp-qlever:
+    description: DBLP QLever Freiburg.
+    lang: sparql
+    method: POST
+    database: qlever
+    endpoint: https://qlever.cs.uni-freiburg.de/api/dblp
+    website: https://qlever.cs.uni-freiburg.de/dblp
+    calls_per_minute: 60
+    prefix_sets:
+      - rdf
+      - dblp
+
+  dblp-trier:
+    description: DBLP Trier mirror.
+    lang: sparql
+    method: POST
+    database: qlever
+    endpoint: https://archimedes.uni-trier.de/sparql
+    website: https://archimedes.uni-trier.de
+    calls_per_minute: 30
+    prefix_sets:
+      - rdf
+      - dblp