summaryrefslogtreecommitdiff
path: root/searx
diff options
context:
space:
mode:
Diffstat (limited to 'searx')
-rw-r--r--searx/engines/searx_engine.py2
-rw-r--r--searx/metrics/__init__.py12
-rw-r--r--searx/metrics/error_recorder.py6
-rw-r--r--searx/metrics/models.py17
-rw-r--r--searx/network/client.py105
-rw-r--r--searx/network/network.py45
-rw-r--r--searx/search/__init__.py4
-rw-r--r--searx/settings.yml7
-rw-r--r--searx/settings_defaults.py3
-rw-r--r--searx/webadapter.py2
-rwxr-xr-xsearx/webapp.py2
11 files changed, 80 insertions, 125 deletions
diff --git a/searx/engines/searx_engine.py b/searx/engines/searx_engine.py
index 3e9035d6f..84a8e6449 100644
--- a/searx/engines/searx_engine.py
+++ b/searx/engines/searx_engine.py
@@ -10,7 +10,7 @@ from searx.engines import categories as searx_categories
about = {
"website": 'https://github.com/searxng/searxng',
"wikidata_id": 'Q17639196',
- "official_api_documentation": 'https://searxng.github.io/searxng/dev/search_api.html',
+ "official_api_documentation": 'https://docs.searxng.org/dev/search_api.html',
"use_official_api": True,
"require_api_key": False,
"results": 'JSON',
diff --git a/searx/metrics/__init__.py b/searx/metrics/__init__.py
index 37f0ba121..bc755b96b 100644
--- a/searx/metrics/__init__.py
+++ b/searx/metrics/__init__.py
@@ -9,7 +9,7 @@ from timeit import default_timer
from operator import itemgetter
from searx.engines import engines
-from .models import HistogramStorage, CounterStorage
+from .models import HistogramStorage, CounterStorage, VoidHistogram, VoidCounterStorage
from .error_recorder import count_error, count_exception, errors_per_engines
__all__ = [
@@ -69,14 +69,18 @@ def counter(*args):
return counter_storage.get(*args)
-def initialize(engine_names=None):
+def initialize(engine_names=None, enabled=True):
"""
Initialize metrics
"""
global counter_storage, histogram_storage # pylint: disable=global-statement
- counter_storage = CounterStorage()
- histogram_storage = HistogramStorage()
+ if enabled:
+ counter_storage = CounterStorage()
+ histogram_storage = HistogramStorage()
+ else:
+ counter_storage = VoidCounterStorage()
+ histogram_storage = HistogramStorage(histogram_class=VoidHistogram)
# max_timeout = max of all the engine.timeout
max_timeout = 2
diff --git a/searx/metrics/error_recorder.py b/searx/metrics/error_recorder.py
index 76d27f64f..1d0d6e7a3 100644
--- a/searx/metrics/error_recorder.py
+++ b/searx/metrics/error_recorder.py
@@ -9,7 +9,7 @@ from searx.exceptions import (
SearxEngineAPIException,
SearxEngineAccessDeniedException,
)
-from searx import searx_parent_dir
+from searx import searx_parent_dir, settings
from searx.engines import engines
@@ -165,6 +165,8 @@ def get_error_context(framerecords, exception_classname, log_message, log_parame
def count_exception(engine_name: str, exc: Exception, secondary: bool = False) -> None:
+ if not settings['general']['enable_metrics']:
+ return
framerecords = inspect.trace()
try:
exception_classname = get_exception_classname(exc)
@@ -178,6 +180,8 @@ def count_exception(engine_name: str, exc: Exception, secondary: bool = False) -
def count_error(
engine_name: str, log_message: str, log_parameters: typing.Optional[typing.Tuple] = None, secondary: bool = False
) -> None:
+ if not settings['general']['enable_metrics']:
+ return
framerecords = list(reversed(inspect.stack()[1:]))
try:
error_context = get_error_context(framerecords, None, log_message, log_parameters or (), secondary)
diff --git a/searx/metrics/models.py b/searx/metrics/models.py
index d42569b7f..900a7fa93 100644
--- a/searx/metrics/models.py
+++ b/searx/metrics/models.py
@@ -102,16 +102,17 @@ class Histogram:
class HistogramStorage:
- __slots__ = 'measures'
+ __slots__ = 'measures', 'histogram_class'
- def __init__(self):
+ def __init__(self, histogram_class=Histogram):
self.clear()
+ self.histogram_class = histogram_class
def clear(self):
self.measures = {}
def configure(self, width, size, *args):
- measure = Histogram(width, size)
+ measure = self.histogram_class(width, size)
self.measures[args] = measure
return measure
@@ -154,3 +155,13 @@ class CounterStorage:
logger.debug("Counters:")
for k in ks:
logger.debug("- %-60s %s", '|'.join(k), self.counters[k])
+
+
+class VoidHistogram(Histogram):
+ def observe(self, value):
+ pass
+
+
+class VoidCounterStorage(CounterStorage):
+ def add(self, value, *args):
+ pass
diff --git a/searx/network/client.py b/searx/network/client.py
index cd1e41460..6858ac05b 100644
--- a/searx/network/client.py
+++ b/searx/network/client.py
@@ -6,8 +6,6 @@ import asyncio
import logging
import threading
-import anyio
-import httpcore
import httpx
from httpx_socks import AsyncProxyTransport
from python_socks import parse_proxy_url, ProxyConnectionError, ProxyTimeoutError, ProxyError
@@ -27,31 +25,10 @@ logger = logger.getChild('searx.network.client')
LOOP = None
SSLCONTEXTS = {}
TRANSPORT_KWARGS = {
- # use anyio :
- # * https://github.com/encode/httpcore/issues/344
- # * https://github.com/encode/httpx/discussions/1511
- 'backend': 'anyio',
'trust_env': False,
}
-# pylint: disable=protected-access
-async def close_connections_for_url(connection_pool: httpcore.AsyncConnectionPool, url: httpcore._utils.URL):
-
- origin = httpcore._utils.url_to_origin(url)
- logger.debug('Drop connections for %r', origin)
- connections_to_close = connection_pool._connections_for_origin(origin)
- for connection in connections_to_close:
- await connection_pool._remove_from_pool(connection)
- try:
- await connection.aclose()
- except httpx.NetworkError as e:
- logger.warning('Error closing an existing connection', exc_info=e)
-
-
-# pylint: enable=protected-access
-
-
def get_sslcontexts(proxy_url=None, cert=None, verify=True, trust_env=True, http2=False):
key = (proxy_url, cert, verify, trust_env, http2)
if key not in SSLCONTEXTS:
@@ -62,75 +39,25 @@ def get_sslcontexts(proxy_url=None, cert=None, verify=True, trust_env=True, http
class AsyncHTTPTransportNoHttp(httpx.AsyncHTTPTransport):
"""Block HTTP request"""
- async def handle_async_request(self, method, url, headers=None, stream=None, extensions=None):
+ async def handle_async_request(self, request):
raise httpx.UnsupportedProtocol('HTTP protocol is disabled')
class AsyncProxyTransportFixed(AsyncProxyTransport):
"""Fix httpx_socks.AsyncProxyTransport
- Map python_socks exceptions to httpx.ProxyError / httpx.ConnectError
-
- Map socket.gaierror to httpx.ConnectError
-
- Note: AsyncProxyTransport inherit from AsyncConnectionPool
+ Map python_socks exceptions to httpx.ProxyError exceptions
"""
- async def handle_async_request(self, method, url, headers=None, stream=None, extensions=None):
- retry = 2
- while retry > 0:
- retry -= 1
- try:
- return await super().handle_async_request(
- method, url, headers=headers, stream=stream, extensions=extensions
- )
- except (ProxyConnectionError, ProxyTimeoutError, ProxyError) as e:
- raise httpx.ProxyError from e
- except OSError as e:
- # socket.gaierror when DNS resolution fails
- raise httpx.ConnectError from e
- except httpx.NetworkError as e:
- # httpx.WriteError on HTTP/2 connection leaves a new opened stream
- # then each new request creates a new stream and raise the same WriteError
- await close_connections_for_url(self, url)
- raise e
- except anyio.ClosedResourceError as e:
- await close_connections_for_url(self, url)
- raise httpx.CloseError from e
- except httpx.RemoteProtocolError as e:
- # in case of httpx.RemoteProtocolError: Server disconnected
- await close_connections_for_url(self, url)
- logger.warning('httpx.RemoteProtocolError: retry', exc_info=e)
- # retry
-
-
-class AsyncHTTPTransportFixed(httpx.AsyncHTTPTransport):
- """Fix httpx.AsyncHTTPTransport"""
-
- async def handle_async_request(self, method, url, headers=None, stream=None, extensions=None):
- retry = 2
- while retry > 0:
- retry -= 1
- try:
- return await super().handle_async_request(
- method, url, headers=headers, stream=stream, extensions=extensions
- )
- except OSError as e:
- # socket.gaierror when DNS resolution fails
- raise httpx.ConnectError from e
- except httpx.NetworkError as e:
- # httpx.WriteError on HTTP/2 connection leaves a new opened stream
- # then each new request creates a new stream and raise the same WriteError
- await close_connections_for_url(self._pool, url)
- raise e
- except anyio.ClosedResourceError as e:
- await close_connections_for_url(self._pool, url)
- raise httpx.CloseError from e
- except httpx.RemoteProtocolError as e:
- # in case of httpx.RemoteProtocolError: Server disconnected
- await close_connections_for_url(self._pool, url)
- logger.warning('httpx.RemoteProtocolError: retry', exc_info=e)
- # retry
+ async def handle_async_request(self, request):
+ try:
+ return await super().handle_async_request(request)
+ except ProxyConnectionError as e:
+ raise httpx.ProxyError("ProxyConnectionError: " + e.strerror, request=request) from e
+ except ProxyTimeoutError as e:
+ raise httpx.ProxyError("ProxyTimeoutError: " + e.args[0], request=request) from e
+ except ProxyError as e:
+ raise httpx.ProxyError("ProxyError: " + e.args[0], request=request) from e
def get_transport_for_socks_proxy(verify, http2, local_address, proxy_url, limit, retries):
@@ -157,9 +84,7 @@ def get_transport_for_socks_proxy(verify, http2, local_address, proxy_url, limit
verify=verify,
http2=http2,
local_address=local_address,
- max_connections=limit.max_connections,
- max_keepalive_connections=limit.max_keepalive_connections,
- keepalive_expiry=limit.keepalive_expiry,
+ limits=limit,
retries=retries,
**TRANSPORT_KWARGS,
)
@@ -167,13 +92,13 @@ def get_transport_for_socks_proxy(verify, http2, local_address, proxy_url, limit
def get_transport(verify, http2, local_address, proxy_url, limit, retries):
verify = get_sslcontexts(None, None, True, False, http2) if verify is True else verify
- return AsyncHTTPTransportFixed(
+ return httpx.AsyncHTTPTransport(
# pylint: disable=protected-access
verify=verify,
http2=http2,
- local_address=local_address,
- proxy=httpx._config.Proxy(proxy_url) if proxy_url else None,
limits=limit,
+ proxy=httpx._config.Proxy(proxy_url) if proxy_url else None,
+ local_address=local_address,
retries=retries,
**TRANSPORT_KWARGS,
)
diff --git a/searx/network/network.py b/searx/network/network.py
index 9e14e14bd..43140b44d 100644
--- a/searx/network/network.py
+++ b/searx/network/network.py
@@ -213,15 +213,18 @@ class Network:
await asyncio.gather(*[close_client(client) for client in self._clients.values()], return_exceptions=False)
@staticmethod
- def get_kwargs_clients(kwargs):
+ def extract_kwargs_clients(kwargs):
kwargs_clients = {}
if 'verify' in kwargs:
kwargs_clients['verify'] = kwargs.pop('verify')
if 'max_redirects' in kwargs:
kwargs_clients['max_redirects'] = kwargs.pop('max_redirects')
+ if 'allow_redirects' in kwargs:
+ # see https://github.com/encode/httpx/pull/1808
+ kwargs['follow_redirects'] = kwargs.pop('allow_redirects')
return kwargs_clients
- def is_valid_respones(self, response):
+ def is_valid_response(self, response):
# pylint: disable=too-many-boolean-expressions
if (
(self.retry_on_http_error is True and 400 <= response.status_code <= 599)
@@ -231,34 +234,40 @@ class Network:
return False
return True
- async def request(self, method, url, **kwargs):
+ async def call_client(self, stream, method, url, **kwargs):
retries = self.retries
+ was_disconnected = False
+ kwargs_clients = Network.extract_kwargs_clients(kwargs)
while retries >= 0: # pragma: no cover
- kwargs_clients = Network.get_kwargs_clients(kwargs)
client = await self.get_client(**kwargs_clients)
try:
- response = await client.request(method, url, **kwargs)
- if self.is_valid_respones(response) or retries <= 0:
+ if stream:
+ response = client.stream(method, url, **kwargs)
+ else:
+ response = await client.request(method, url, **kwargs)
+ if self.is_valid_response(response) or retries <= 0:
return response
- except (httpx.RequestError, httpx.HTTPStatusError) as e:
+ except httpx.RemoteProtocolError as e:
+ if not was_disconnected:
+ # the server has closed the connection:
+ # try again without decreasing the retries variable & with a new HTTP client
+ was_disconnected = True
+ await client.aclose()
+ self._logger.warning('httpx.RemoteProtocolError: the server has disconnected, retrying')
+ continue
if retries <= 0:
raise e
- retries -= 1
-
- async def stream(self, method, url, **kwargs):
- retries = self.retries
- while retries >= 0: # pragma: no cover
- kwargs_clients = Network.get_kwargs_clients(kwargs)
- client = await self.get_client(**kwargs_clients)
- try:
- response = client.stream(method, url, **kwargs)
- if self.is_valid_respones(response) or retries <= 0:
- return response
except (httpx.RequestError, httpx.HTTPStatusError) as e:
if retries <= 0:
raise e
retries -= 1
+ async def request(self, method, url, **kwargs):
+ return await self.call_client(False, method, url, **kwargs)
+
+ async def stream(self, method, url, **kwargs):
+ return await self.call_client(True, method, url, **kwargs)
+
@classmethod
async def aclose_all(cls):
await asyncio.gather(*[network.aclose() for network in NETWORKS.values()], return_exceptions=False)
diff --git a/searx/search/__init__.py b/searx/search/__init__.py
index d66f3362d..e790bd05e 100644
--- a/searx/search/__init__.py
+++ b/searx/search/__init__.py
@@ -24,13 +24,13 @@ from searx.search.checker import initialize as initialize_checker
logger = logger.getChild('search')
-def initialize(settings_engines=None, enable_checker=False, check_network=False):
+def initialize(settings_engines=None, enable_checker=False, check_network=False, enable_metrics=True):
settings_engines = settings_engines or settings['engines']
load_engines(settings_engines)
initialize_network(settings_engines, settings['outgoing'])
if check_network:
check_network_configuration()
- initialize_metrics([engine['name'] for engine in settings_engines])
+ initialize_metrics([engine['name'] for engine in settings_engines], enable_metrics)
initialize_processors(settings_engines)
if enable_checker:
initialize_checker()
diff --git a/searx/settings.yml b/searx/settings.yml
index 0aa7b99b0..f1d6fa1b1 100644
--- a/searx/settings.yml
+++ b/searx/settings.yml
@@ -2,10 +2,11 @@ general:
debug: false # Debug mode, only for development
instance_name: "SearXNG" # displayed name
contact_url: false # mailto:contact@example.com
+ enable_metrics: true # record stats
brand:
new_issue_url: https://github.com/searxng/searxng/issues/new
- docs_url: https://searxng.github.io/searxng
+ docs_url: https://docs.searxng.org/
public_instances: https://searx.space
wiki_url: https://github.com/searxng/searxng/wiki
issue_url: https://github.com/searxng/searxng/issues
@@ -145,7 +146,7 @@ outgoing:
# - fe80::/126
# External plugin configuration, for more details see
-# https://searxng.github.io/searxng/dev/plugins.html
+# https://docs.searxng.org/dev/plugins.html
#
# plugins:
# - plugin1
@@ -625,7 +626,7 @@ engines:
- name: google
engine: google
shortcut: go
- # see https://searxng.github.io/searxng/src/searx.engines.google.html#module-searx.engines.google
+ # see https://docs.searxng.org/src/searx.engines.google.html#module-searx.engines.google
use_mobile_ui: false
# additional_tests:
# android: *test_android
diff --git a/searx/settings_defaults.py b/searx/settings_defaults.py
index c1154f7ff..e84b442fe 100644
--- a/searx/settings_defaults.py
+++ b/searx/settings_defaults.py
@@ -142,11 +142,12 @@ SCHEMA = {
'debug': SettingsValue(bool, False, 'SEARXNG_DEBUG'),
'instance_name': SettingsValue(str, 'SearXNG'),
'contact_url': SettingsValue((None, False, str), None),
+ 'enable_metrics': SettingsValue(bool, True),
},
'brand': {
'issue_url': SettingsValue(str, 'https://github.com/searxng/searxng/issues'),
'new_issue_url': SettingsValue(str, 'https://github.com/searxng/searxng/issues/new'),
- 'docs_url': SettingsValue(str, 'https://searxng.github.io/searxng'),
+ 'docs_url': SettingsValue(str, 'https://docs.searxng.org'),
'public_instances': SettingsValue(str, 'https://searx.space'),
'wiki_url': SettingsValue(str, 'https://github.com/searxng/searxng/wiki'),
},
diff --git a/searx/webadapter.py b/searx/webadapter.py
index 4fd18cee9..185cb568e 100644
--- a/searx/webadapter.py
+++ b/searx/webadapter.py
@@ -236,7 +236,7 @@ def get_search_query_from_webapp(
external_bang = raw_text_query.external_bang
engine_data = parse_engine_data(form)
- if not is_locked('categories') and raw_text_query.enginerefs and raw_text_query.specific:
+ if not is_locked('categories') and raw_text_query.specific:
# if engines are calculated from query,
# set categories by using that informations
query_engineref_list = raw_text_query.enginerefs
diff --git a/searx/webapp.py b/searx/webapp.py
index f2957a944..46b838b77 100755
--- a/searx/webapp.py
+++ b/searx/webapp.py
@@ -1343,7 +1343,7 @@ werkzeug_reloader = flask_run_development or (searx_debug and __name__ == "__mai
# initialize the engines except on the first run of the werkzeug server.
if not werkzeug_reloader or (werkzeug_reloader and os.environ.get("WERKZEUG_RUN_MAIN") == "true"):
plugin_initialize(app)
- search_initialize(enable_checker=True, check_network=True)
+ search_initialize(enable_checker=True, check_network=True, enable_metrics=settings['general']['enable_metrics'])
def run():