split code into submodules

src/nominatim_api/server/falcon/server.py

@@ -0,0 +1,194 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+#
+# This file is part of Nominatim. (https://nominatim.org)
+#
+# Copyright (C) 2024 by the Nominatim developer community.
+# For a full list of authors see the git log.
+"""
+Server implementation using the falcon webserver framework.
+"""
+from typing import Optional, Mapping, cast, Any, List
+from pathlib import Path
+import datetime as dt
+import asyncio
+
+from falcon.asgi import App, Request, Response
+
+from nominatim_core.config import Configuration
+from ...core import NominatimAPIAsync
+from ... import v1 as api_impl
+from ... import logging as loglib
+
+class HTTPNominatimError(Exception):
+    """ A special exception class for errors raised during processing.
+    """
+    def __init__(self, msg: str, status: int, content_type: str) -> None:
+        self.msg = msg
+        self.status = status
+        self.content_type = content_type
+
+
+async def nominatim_error_handler(req: Request, resp: Response, #pylint: disable=unused-argument
+                                  exception: HTTPNominatimError,
+                                  _: Any) -> None:
+    """ Special error handler that passes message and content type as
+        per exception info.
+    """
+    resp.status = exception.status
+    resp.text = exception.msg
+    resp.content_type = exception.content_type
+
+
+async def timeout_error_handler(req: Request, resp: Response, #pylint: disable=unused-argument
+                                exception: TimeoutError, #pylint: disable=unused-argument
+                                _: Any) -> None:
+    """ Special error handler that passes message and content type as
+        per exception info.
+    """
+    resp.status = 503
+
+    loglib.log().comment('Aborted: Query took too long to process.')
+    logdata = loglib.get_and_disable()
+    if logdata:
+        resp.text = logdata
+        resp.content_type = 'text/html; charset=utf-8'
+    else:
+        resp.text = "Query took too long to process."
+        resp.content_type = 'text/plain; charset=utf-8'
+
+
+class ParamWrapper(api_impl.ASGIAdaptor):
+    """ Adaptor class for server glue to Falcon framework.
+    """
+
+    def __init__(self, req: Request, resp: Response,
+                 config: Configuration) -> None:
+        self.request = req
+        self.response = resp
+        self._config = config
+
+
+    def get(self, name: str, default: Optional[str] = None) -> Optional[str]:
+        return cast(Optional[str], self.request.get_param(name, default=default))
+
+
+    def get_header(self, name: str, default: Optional[str] = None) -> Optional[str]:
+        return cast(Optional[str], self.request.get_header(name, default=default))
+
+
+    def error(self, msg: str, status: int = 400) -> HTTPNominatimError:
+        return HTTPNominatimError(msg, status, self.content_type)
+
+
+    def create_response(self, status: int, output: str, num_results: int) -> None:
+        self.response.context.num_results = num_results
+        self.response.status = status
+        self.response.text = output
+        self.response.content_type = self.content_type
+
+
+    def base_uri(self) -> str:
+        return cast (str, self.request.forwarded_prefix)
+
+    def config(self) -> Configuration:
+        return self._config
+
+
+class EndpointWrapper:
+    """ Converter for server glue endpoint functions to Falcon request handlers.
+    """
+
+    def __init__(self, name: str, func: api_impl.EndpointFunc, api: NominatimAPIAsync) -> None:
+        self.name = name
+        self.func = func
+        self.api = api
+
+
+    async def on_get(self, req: Request, resp: Response) -> None:
+        """ Implementation of the endpoint.
+        """
+        await self.func(self.api, ParamWrapper(req, resp, self.api.config))
+
+
+class FileLoggingMiddleware:
+    """ Middleware to log selected requests into a file.
+    """
+
+    def __init__(self, file_name: str):
+        self.fd = open(file_name, 'a', buffering=1, encoding='utf8') # pylint: disable=R1732
+
+
+    async def process_request(self, req: Request, _: Response) -> None:
+        """ Callback before the request starts timing.
+        """
+        req.context.start = dt.datetime.now(tz=dt.timezone.utc)
+
+
+    async def process_response(self, req: Request, resp: Response,
+                               resource: Optional[EndpointWrapper],
+                               req_succeeded: bool) -> None:
+        """ Callback after requests writes to the logfile. It only
+            writes logs for successful requests for search, reverse and lookup.
+        """
+        if not req_succeeded or resource is None or resp.status != 200\
+            or resource.name not in ('reverse', 'search', 'lookup', 'details'):
+            return
+
+        finish = dt.datetime.now(tz=dt.timezone.utc)
+        duration = (finish - req.context.start).total_seconds()
+        params = req.scope['query_string'].decode('utf8')
+        start = req.context.start.replace(tzinfo=None)\
+                                 .isoformat(sep=' ', timespec='milliseconds')
+
+        self.fd.write(f"[{start}] "
+                      f"{duration:.4f} {getattr(resp.context, 'num_results', 0)} "
+                      f'{resource.name} "{params}"\n')
+
+
+class APIShutdown:
+    """ Middleware that closes any open database connections.
+    """
+
+    def __init__(self, api: NominatimAPIAsync) -> None:
+        self.api = api
+
+    async def process_shutdown(self, *_: Any) -> None:
+        """Process the ASGI lifespan shutdown event.
+        """
+        await self.api.close()
+
+
+def get_application(project_dir: Path,
+                    environ: Optional[Mapping[str, str]] = None) -> App:
+    """ Create a Nominatim Falcon ASGI application.
+    """
+    api = NominatimAPIAsync(project_dir, environ)
+
+    middleware: List[object] = [APIShutdown(api)]
+    log_file = api.config.LOG_FILE
+    if log_file:
+        middleware.append(FileLoggingMiddleware(log_file))
+
+    app = App(cors_enable=api.config.get_bool('CORS_NOACCESSCONTROL'),
+              middleware=middleware)
+    app.add_error_handler(HTTPNominatimError, nominatim_error_handler)
+    app.add_error_handler(TimeoutError, timeout_error_handler)
+    # different from TimeoutError in Python <= 3.10
+    app.add_error_handler(asyncio.TimeoutError, timeout_error_handler)
+
+    legacy_urls = api.config.get_bool('SERVE_LEGACY_URLS')
+    for name, func in api_impl.ROUTES:
+        endpoint = EndpointWrapper(name, func, api)
+        app.add_route(f"/{name}", endpoint)
+        if legacy_urls:
+            app.add_route(f"/{name}.php", endpoint)
+
+    return app
+
+
+def run_wsgi() -> App:
+    """ Entry point for uvicorn.
+
+        Make sure uvicorn is run from the project directory.
+    """
+    return get_application(Path('.'))

src/nominatim_api/server/starlette/server.py

@@ -0,0 +1,174 @@
+# SPDX-License-Identifier: GPL-3.0-or-later
+#
+# This file is part of Nominatim. (https://nominatim.org)
+#
+# Copyright (C) 2024 by the Nominatim developer community.
+# For a full list of authors see the git log.
+"""
+Server implementation using the starlette webserver framework.
+"""
+from typing import Any, Optional, Mapping, Callable, cast, Coroutine, Dict, Awaitable
+from pathlib import Path
+import datetime as dt
+import asyncio
+
+from starlette.applications import Starlette
+from starlette.routing import Route
+from starlette.exceptions import HTTPException
+from starlette.responses import Response, PlainTextResponse, HTMLResponse
+from starlette.requests import Request
+from starlette.middleware import Middleware
+from starlette.middleware.base import BaseHTTPMiddleware, RequestResponseEndpoint
+from starlette.middleware.cors import CORSMiddleware
+
+from nominatim_core.config import Configuration
+from ...core import NominatimAPIAsync
+from ... import v1 as api_impl
+from ... import logging as loglib
+
+class ParamWrapper(api_impl.ASGIAdaptor):
+    """ Adaptor class for server glue to Starlette framework.
+    """
+
+    def __init__(self, request: Request) -> None:
+        self.request = request
+
+
+    def get(self, name: str, default: Optional[str] = None) -> Optional[str]:
+        return self.request.query_params.get(name, default=default)
+
+
+    def get_header(self, name: str, default: Optional[str] = None) -> Optional[str]:
+        return self.request.headers.get(name, default)
+
+
+    def error(self, msg: str, status: int = 400) -> HTTPException:
+        return HTTPException(status, detail=msg,
+                             headers={'content-type': self.content_type})
+
+
+    def create_response(self, status: int, output: str, num_results: int) -> Response:
+        self.request.state.num_results = num_results
+        return Response(output, status_code=status, media_type=self.content_type)
+
+
+    def base_uri(self) -> str:
+        scheme = self.request.url.scheme
+        host = self.request.url.hostname
+        port = self.request.url.port
+        root = self.request.scope['root_path']
+        if (scheme == 'http' and port == 80) or (scheme == 'https' and port == 443):
+            port = None
+        if port is not None:
+            return f"{scheme}://{host}:{port}{root}"
+
+        return f"{scheme}://{host}{root}"
+
+
+    def config(self) -> Configuration:
+        return cast(Configuration, self.request.app.state.API.config)
+
+
+def _wrap_endpoint(func: api_impl.EndpointFunc)\
+        -> Callable[[Request], Coroutine[Any, Any, Response]]:
+    async def _callback(request: Request) -> Response:
+        return cast(Response, await func(request.app.state.API, ParamWrapper(request)))
+
+    return _callback
+
+
+class FileLoggingMiddleware(BaseHTTPMiddleware):
+    """ Middleware to log selected requests into a file.
+    """
+
+    def __init__(self, app: Starlette, file_name: str = ''):
+        super().__init__(app)
+        self.fd = open(file_name, 'a', buffering=1, encoding='utf8') # pylint: disable=R1732
+
+    async def dispatch(self, request: Request,
+                       call_next: RequestResponseEndpoint) -> Response:
+        start = dt.datetime.now(tz=dt.timezone.utc)
+        response = await call_next(request)
+
+        if response.status_code != 200:
+            return response
+
+        finish = dt.datetime.now(tz=dt.timezone.utc)
+
+        for endpoint in ('reverse', 'search', 'lookup', 'details'):
+            if request.url.path.startswith('/' + endpoint):
+                qtype = endpoint
+                break
+        else:
+            return response
+
+        duration = (finish - start).total_seconds()
+        params = request.scope['query_string'].decode('utf8')
+
+        self.fd.write(f"[{start.replace(tzinfo=None).isoformat(sep=' ', timespec='milliseconds')}] "
+                      f"{duration:.4f} {getattr(request.state, 'num_results', 0)} "
+                      f'{qtype} "{params}"\n')
+
+        return response
+
+
+async def timeout_error(request: Request, #pylint: disable=unused-argument
+                        _: Exception) -> Response:
+    """ Error handler for query timeouts.
+    """
+    loglib.log().comment('Aborted: Query took too long to process.')
+    logdata = loglib.get_and_disable()
+
+    if logdata:
+        return HTMLResponse(logdata)
+
+    return PlainTextResponse("Query took too long to process.", status_code=503)
+
+
+def get_application(project_dir: Path,
+                    environ: Optional[Mapping[str, str]] = None,
+                    debug: bool = True) -> Starlette:
+    """ Create a Nominatim falcon ASGI application.
+    """
+    config = Configuration(project_dir, environ)
+
+    routes = []
+    legacy_urls = config.get_bool('SERVE_LEGACY_URLS')
+    for name, func in api_impl.ROUTES:
+        endpoint = _wrap_endpoint(func)
+        routes.append(Route(f"/{name}", endpoint=endpoint))
+        if legacy_urls:
+            routes.append(Route(f"/{name}.php", endpoint=endpoint))
+
+    middleware = []
+    if config.get_bool('CORS_NOACCESSCONTROL'):
+        middleware.append(Middleware(CORSMiddleware,
+                                     allow_origins=['*'],
+                                     allow_methods=['GET', 'OPTIONS'],
+                                     max_age=86400))
+
+    log_file = config.LOG_FILE
+    if log_file:
+        middleware.append(Middleware(FileLoggingMiddleware, file_name=log_file))
+
+    exceptions: Dict[Any, Callable[[Request, Exception], Awaitable[Response]]] = {
+        TimeoutError: timeout_error,
+        asyncio.TimeoutError: timeout_error
+    }
+
+    async def _shutdown() -> None:
+        await app.state.API.close()
+
+    app = Starlette(debug=debug, routes=routes, middleware=middleware,
+                    exception_handlers=exceptions,
+                    on_shutdown=[_shutdown])
+
+    app.state.API = NominatimAPIAsync(project_dir, environ)
+
+    return app
+
+
+def run_wsgi() -> Starlette:
+    """ Entry point for uvicorn.
+    """
+    return get_application(Path('.'), debug=False)