156 lines
4.9 KiB
Python
156 lines
4.9 KiB
Python
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import base64
|
|
import json
|
|
from typing import Any, Protocol
|
|
|
|
import httpx
|
|
from rdflib import Graph
|
|
|
|
from .settings import Settings
|
|
|
|
|
|
class SparqlEngine(Protocol):
|
|
name: str
|
|
|
|
async def startup(self) -> None: ...
|
|
|
|
async def shutdown(self) -> None: ...
|
|
|
|
async def query_json(self, query: str) -> dict[str, Any]: ...
|
|
|
|
|
|
class RdflibEngine:
|
|
name = "rdflib"
|
|
|
|
def __init__(self, *, ttl_path: str):
|
|
self.ttl_path = ttl_path
|
|
self.graph: Graph | None = None
|
|
|
|
async def startup(self) -> None:
|
|
g = Graph()
|
|
g.parse(self.ttl_path, format="turtle")
|
|
self.graph = g
|
|
|
|
async def shutdown(self) -> None:
|
|
# Nothing to close for in-memory rdflib graph.
|
|
return None
|
|
|
|
async def query_json(self, query: str) -> dict[str, Any]:
|
|
if self.graph is None:
|
|
raise RuntimeError("RdflibEngine not started")
|
|
|
|
result = self.graph.query(query)
|
|
payload = result.serialize(format="json")
|
|
if isinstance(payload, bytes):
|
|
payload = payload.decode("utf-8")
|
|
return json.loads(payload)
|
|
|
|
|
|
class AnzoGraphEngine:
|
|
name = "anzograph"
|
|
|
|
def __init__(self, *, settings: Settings):
|
|
self.endpoint = settings.effective_sparql_endpoint()
|
|
self.timeout_s = settings.sparql_timeout_s
|
|
self.ready_retries = settings.sparql_ready_retries
|
|
self.ready_delay_s = settings.sparql_ready_delay_s
|
|
|
|
self.user = settings.sparql_user
|
|
self.password = settings.sparql_pass
|
|
self.data_file = settings.sparql_data_file
|
|
self.graph_iri = settings.sparql_graph_iri
|
|
self.load_on_start = settings.sparql_load_on_start
|
|
self.clear_on_start = settings.sparql_clear_on_start
|
|
|
|
self._client: httpx.AsyncClient | None = None
|
|
self._auth_header = self._build_auth_header(self.user, self.password)
|
|
|
|
@staticmethod
|
|
def _build_auth_header(user: str | None, password: str | None) -> str | None:
|
|
if not user or not password:
|
|
return None
|
|
token = base64.b64encode(f"{user}:{password}".encode("utf-8")).decode("ascii")
|
|
return f"Basic {token}"
|
|
|
|
async def startup(self) -> None:
|
|
self._client = httpx.AsyncClient(timeout=self.timeout_s)
|
|
|
|
await self._wait_ready()
|
|
|
|
if self.clear_on_start:
|
|
await self._update("CLEAR ALL")
|
|
await self._wait_ready()
|
|
|
|
if self.load_on_start:
|
|
if not self.data_file:
|
|
raise RuntimeError("SPARQL_LOAD_ON_START=true but SPARQL_DATA_FILE is not set")
|
|
|
|
if self.graph_iri:
|
|
await self._update(f"LOAD <{self.data_file}> INTO GRAPH <{self.graph_iri}>")
|
|
else:
|
|
await self._update(f"LOAD <{self.data_file}>")
|
|
|
|
# AnzoGraph may still be indexing after LOAD.
|
|
await self._wait_ready()
|
|
|
|
async def shutdown(self) -> None:
|
|
if self._client is not None:
|
|
await self._client.aclose()
|
|
self._client = None
|
|
|
|
async def query_json(self, query: str) -> dict[str, Any]:
|
|
if self._client is None:
|
|
raise RuntimeError("AnzoGraphEngine not started")
|
|
|
|
headers = {
|
|
"Content-Type": "application/x-www-form-urlencoded",
|
|
"Accept": "application/sparql-results+json",
|
|
}
|
|
if self._auth_header:
|
|
headers["Authorization"] = self._auth_header
|
|
|
|
# AnzoGraph expects x-www-form-urlencoded with `query=...`.
|
|
resp = await self._client.post(
|
|
self.endpoint,
|
|
headers=headers,
|
|
data={"query": query},
|
|
)
|
|
resp.raise_for_status()
|
|
return resp.json()
|
|
|
|
async def _update(self, update: str) -> None:
|
|
if self._client is None:
|
|
raise RuntimeError("AnzoGraphEngine not started")
|
|
|
|
headers = {
|
|
"Content-Type": "application/sparql-update",
|
|
"Accept": "application/json",
|
|
}
|
|
if self._auth_header:
|
|
headers["Authorization"] = self._auth_header
|
|
|
|
resp = await self._client.post(self.endpoint, headers=headers, content=update)
|
|
resp.raise_for_status()
|
|
|
|
async def _wait_ready(self) -> None:
|
|
last_err: Exception | None = None
|
|
for _ in range(self.ready_retries):
|
|
try:
|
|
# Keep it cheap and JSON-parseable.
|
|
await self.query_json("ASK WHERE { ?s ?p ?o }")
|
|
return
|
|
except Exception as e:
|
|
last_err = e
|
|
await asyncio.sleep(self.ready_delay_s)
|
|
raise RuntimeError(f"AnzoGraph not ready at {self.endpoint}") from last_err
|
|
|
|
|
|
def create_sparql_engine(settings: Settings) -> SparqlEngine:
|
|
if settings.graph_backend == "rdflib":
|
|
return RdflibEngine(ttl_path=settings.ttl_path)
|
|
if settings.graph_backend == "anzograph":
|
|
return AnzoGraphEngine(settings=settings)
|
|
raise RuntimeError(f"Unsupported GRAPH_BACKEND={settings.graph_backend!r}")
|