From d29cf64ce4932916affd68232aed19d01c6758b5 Mon Sep 17 00:00:00 2001
From: Markus Heiser <markus.heiser@darmarIT.de>
Date: Thu, 22 May 2025 16:23:30 +0200
Subject: [PATCH] [mod] searx.data: lazy load of the data objects (databases)
 (#4834)

In the previous implementation, all databases were loaded into memory when
importing the searx.data package, regardless of whether they were ever needed.

Regardless of this, it is an antipattern to load entire databases into memory
when importing a package or module; databases should be loaded when needed.

Lazy loading is a first step toward improving memory usage and also improves
performance when setting up the runtime environment.  Building on this,
subsequent PRs will be able to further optimize memory behavior, e.g., by using
a real database application such as the one already available via

    searx.cache.ExpireCache

Related:

- https://github.com/searxng/searxng/discussions/1892
- https://github.com/searxng/searxng/pull/3458
- https://github.com/searxng/searxng/pull/4650

Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>
---
 searx/data/__init__.py | 81 ++++++++++++++++++++++++++++--------------
 1 file changed, 55 insertions(+), 26 deletions(-)

diff --git a/searx/data/__init__.py b/searx/data/__init__.py
index 28a3974fa..48455ebe3 100644
--- a/searx/data/__init__.py
+++ b/searx/data/__init__.py
@@ -5,28 +5,68 @@
 
 """
 
-__all__ = [
-    'ENGINE_TRAITS',
-    'CURRENCIES',
-    'USER_AGENTS',
-    'EXTERNAL_URLS',
-    'WIKIDATA_UNITS',
-    'EXTERNAL_BANGS',
-    'OSM_KEYS_TAGS',
-    'ENGINE_DESCRIPTIONS',
-    'LOCALES',
-    'ahmia_blacklist_loader',
-]
+
+__all__ = ["ahmia_blacklist_loader"]
 
 import json
 from pathlib import Path
+import typing
+
+from searx import logger
+
+log = logger.getChild("data")
 
 data_dir = Path(__file__).parent
 
+CURRENCIES: dict[str, typing.Any]
+USER_AGENTS: dict[str, typing.Any]
+EXTERNAL_URLS: dict[str, typing.Any]
+WIKIDATA_UNITS: dict[str, typing.Any]
+EXTERNAL_BANGS: dict[str, typing.Any]
+OSM_KEYS_TAGS: dict[str, typing.Any]
+ENGINE_DESCRIPTIONS: dict[str, typing.Any]
+ENGINE_TRAITS: dict[str, typing.Any]
+LOCALES: dict[str, typing.Any]
 
-def _load(filename):
-    with open(data_dir / filename, encoding='utf-8') as f:
-        return json.load(f)
+lazy_globals = {
+    "CURRENCIES": None,
+    "USER_AGENTS": None,
+    "EXTERNAL_URLS": None,
+    "WIKIDATA_UNITS": None,
+    "EXTERNAL_BANGS": None,
+    "OSM_KEYS_TAGS": None,
+    "ENGINE_DESCRIPTIONS": None,
+    "ENGINE_TRAITS": None,
+    "LOCALES": None,
+}
+
+data_json_files = {
+    "CURRENCIES": "currencies.json",
+    "USER_AGENTS": "useragents.json",
+    "EXTERNAL_URLS": "external_urls.json",
+    "WIKIDATA_UNITS": "wikidata_units.json",
+    "EXTERNAL_BANGS": "external_bangs.json",
+    "OSM_KEYS_TAGS": "osm_keys_tags.json",
+    "ENGINE_DESCRIPTIONS": "engine_descriptions.json",
+    "ENGINE_TRAITS": "engine_traits.json",
+    "LOCALES": "locales.json",
+}
+
+
+def __getattr__(name):
+    # lazy init of the global objects
+    if name not in lazy_globals:
+        raise AttributeError(f"module {__name__!r} has no attribute {name!r}")
+
+    data = lazy_globals[name]
+    if data is not None:
+        return data
+
+    log.debug("init searx.data.%s", name)
+    with open(data_dir / data_json_files[name], encoding='utf-8') as f:
+        lazy_globals[name] = json.load(f)
+
+    return lazy_globals[name]
 
 
 def ahmia_blacklist_loader():
@@ -40,14 +80,3 @@ def ahmia_blacklist_loader():
     """
     with open(data_dir / 'ahmia_blacklist.txt', encoding='utf-8') as f:
         return f.read().split()
-
-
-CURRENCIES = _load('currencies.json')
-USER_AGENTS = _load('useragents.json')
-EXTERNAL_URLS = _load('external_urls.json')
-WIKIDATA_UNITS = _load('wikidata_units.json')
-EXTERNAL_BANGS = _load('external_bangs.json')
-OSM_KEYS_TAGS = _load('osm_keys_tags.json')
-ENGINE_DESCRIPTIONS = _load('engine_descriptions.json')
-ENGINE_TRAITS = _load('engine_traits.json')
-LOCALES = _load('locales.json')