remove restriction on frequent one word names

[nominatim.git] / nominatim / server / falcon / server.py

diff --git a/nominatim/server/falcon/server.py b/nominatim/server/falcon/server.py
index c11cf4a845de734f1f68319990ebb6b179ca40d1..bdae350744e6774ff927f8bec597da8b05ee90e6 100644 (file)
--- a/nominatim/server/falcon/server.py
+++ b/nominatim/server/falcon/server.py
@@ -7,13 +7,16 @@
 """
 Server implementation using the falcon webserver framework.
 """
-from typing import Optional, Mapping, cast, Any
+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.api import NominatimAPIAsync
 import nominatim.api.v1 as api_impl
+import nominatim.api.logging as loglib
 from nominatim.config import Configuration
 
 class HTTPNominatimError(Exception):
@@ -36,6 +39,24 @@ async def nominatim_error_handler(req: Request, resp: Response, #pylint: disable
     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.
     """
@@ -59,12 +80,16 @@ class ParamWrapper(api_impl.ASGIAdaptor):
         return HTTPNominatimError(msg, status, self.content_type)
 
 
-    def create_response(self, status: int, output: str) -> None:
+    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
 
@@ -73,7 +98,8 @@ class EndpointWrapper:
     """ Converter for server glue endpoint functions to Falcon request handlers.
     """
 
-    def __init__(self, func: api_impl.EndpointFunc, api: NominatimAPIAsync) -> None:
+    def __init__(self, name: str, func: api_impl.EndpointFunc, api: NominatimAPIAsync) -> None:
+        self.name = name
         self.func = func
         self.api = api
 
@@ -84,18 +110,75 @@ class EndpointWrapper:
         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)
 
-    app = App(cors_enable=api.config.get_bool('CORS_NOACCESSCONTROL'))
+    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(func, api)
+        endpoint = EndpointWrapper(name, func, api)
         app.add_route(f"/{name}", endpoint)
         if legacy_urls:
             app.add_route(f"/{name}.php", endpoint)