mirror of
https://github.com/searxng/searxng.git
synced 2025-07-22 12:49:22 +02:00
[mod] engines: migration of the individual cache solutions to EngineCache
The EngineCache class replaces all previously individual solutions for caches in the context of the engines. - demo_offline.py - duckduckgo.py - radio_browser.py - soundcloud.py - startpage.py - wolframalpha_api.py - wolframalpha_noapi.py Search term to test most of the modified engines:: !ddg !rb !sc !sp !wa test !ddg !rb !sc !sp !wa foo For introspection of the DB, jump into developer environment and run command to show cache state:: $ ./manage pyenv.cmd bash --norc --noprofile (py3) python -m searx.enginelib cache state cache tables and key/values =========================== [demo_offline ] 2025-04-22 11:32:50 count --> (int) 4 [startpage ] 2025-04-22 12:32:30 SC_CODE --> (str) fSOBnhEMlDfE20 [duckduckgo ] 2025-04-22 12:32:31 4dff493e.... --> (str) 4-128634958369380006627592672385352473325 [duckduckgo ] 2025-04-22 12:40:06 3e2583e2.... --> (str) 4-263126175288871260472289814259666848451 [radio_browser ] 2025-04-23 11:33:08 servers --> (list) ['https://de2.api.radio-browser.info', ...] [soundcloud ] 2025-04-29 11:40:06 guest_client_id --> (str) EjkRJG0BLNEZquRiPZYdNtJdyGtTuHdp [wolframalpha ] 2025-04-22 12:40:06 code --> (str) 5aa79f86205ad26188e0e26e28fb7ae7 number of tables: 6 number of key/value pairs: 7 In the "cache tables and key/values" section, the table name (engine name) is at first position on the second there is the calculated expire date and on the third and fourth position the key/value is shown. About duckduckgo: The *vqd coode* of ddg depends on the query term and therefore the key is a hash value of the query term (to not to store the raw query term). In the "properties of ENGINES_CACHE" section all properties of the SQLiteAppl / ExpireCache and their last modification date are shown:: properties of ENGINES_CACHE =========================== [last modified: 2025-04-22 11:32:27] DB_SCHEMA : 1 [last modified: 2025-04-22 11:32:27] LAST_MAINTENANCE : [last modified: 2025-04-22 11:32:27] crypt_hash : ca612e3566fdfd7cf7efe2b1c9349f461158d07cb78a3750e5c5be686aa8ebdc [last modified: 2025-04-22 11:32:30] CACHE-TABLE--demo_offline: demo_offline [last modified: 2025-04-22 11:32:30] CACHE-TABLE--startpage: startpage [last modified: 2025-04-22 11:32:31] CACHE-TABLE--duckduckgo: duckduckgo [last modified: 2025-04-22 11:33:08] CACHE-TABLE--radio_browser: radio_browser [last modified: 2025-04-22 11:40:06] CACHE-TABLE--soundcloud: soundcloud [last modified: 2025-04-22 11:40:06] CACHE-TABLE--wolframalpha: wolframalpha These properties provide information about the state of the ExpireCache and control the behavior. For example, the maintenance intervals are controlled by the last modification date of the LAST_MAINTENANCE property and the hash value of the password can be used to detect whether the password has been changed (in this case the DB entries can no longer be decrypted and the entire cache must be discarded). Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
This commit is contained in:
parent
4cbfba9d7b
commit
bdfe1c2a15
7 changed files with 169 additions and 103 deletions
|
@ -84,7 +84,6 @@ from typing import TYPE_CHECKING, Any
|
|||
from collections import OrderedDict
|
||||
import re
|
||||
from unicodedata import normalize, combining
|
||||
from time import time
|
||||
from datetime import datetime, timedelta
|
||||
from json import loads
|
||||
|
||||
|
@ -97,6 +96,7 @@ from searx.network import get # see https://github.com/searxng/searxng/issues/7
|
|||
from searx.exceptions import SearxEngineCaptchaException
|
||||
from searx.locales import region_tag
|
||||
from searx.enginelib.traits import EngineTraits
|
||||
from searx.enginelib import EngineCache
|
||||
|
||||
if TYPE_CHECKING:
|
||||
import logging
|
||||
|
@ -159,10 +159,21 @@ search_form_xpath = '//form[@id="search"]'
|
|||
</form>
|
||||
"""
|
||||
|
||||
# timestamp of the last fetch of 'sc' code
|
||||
sc_code_ts = 0
|
||||
sc_code = ''
|
||||
sc_code_cache_sec = 30
|
||||
|
||||
CACHE: EngineCache
|
||||
"""Persistent (SQLite) key/value cache that deletes its values after ``expire``
|
||||
seconds."""
|
||||
|
||||
|
||||
def init(_):
|
||||
global CACHE # pylint: disable=global-statement
|
||||
|
||||
# hint: all three startpage engines (WEB, Images & News) can/should use the
|
||||
# same sc_code ..
|
||||
CACHE = EngineCache("startpage") # type:ignore
|
||||
|
||||
|
||||
sc_code_cache_sec = 3600
|
||||
"""Time in seconds the sc-code is cached in memory :py:obj:`get_sc_code`."""
|
||||
|
||||
|
||||
|
@ -176,14 +187,10 @@ def get_sc_code(searxng_locale, params):
|
|||
|
||||
Startpage's search form generates a new sc-code on each request. This
|
||||
function scrap a new sc-code from Startpage's home page every
|
||||
:py:obj:`sc_code_cache_sec` seconds.
|
||||
:py:obj:`sc_code_cache_sec` seconds."""
|
||||
|
||||
"""
|
||||
|
||||
global sc_code_ts, sc_code # pylint: disable=global-statement
|
||||
|
||||
if sc_code and (time() < (sc_code_ts + sc_code_cache_sec)):
|
||||
logger.debug("get_sc_code: reuse '%s'", sc_code)
|
||||
sc_code = CACHE.get("SC_CODE", "")
|
||||
if sc_code:
|
||||
return sc_code
|
||||
|
||||
headers = {**params['headers']}
|
||||
|
@ -233,8 +240,9 @@ def get_sc_code(searxng_locale, params):
|
|||
message="get_sc_code: [PR-695] query new sc time-stamp failed! (%s)" % resp.url, # type: ignore
|
||||
) from exc
|
||||
|
||||
sc_code_ts = time()
|
||||
sc_code = str(sc_code)
|
||||
logger.debug("get_sc_code: new value is: %s", sc_code)
|
||||
CACHE.set(key="SC_CODE", value=sc_code, expire=sc_code_cache_sec)
|
||||
return sc_code
|
||||
|
||||
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue