[mod] ExpireCacheSQLite - implement .setmany() for bulk loading

[1] https://github.com/searxng/searxng/issues/5223#issuecomment-3328597147

Suggested-by: Ivan G <igabaldon@inetol.net> [1]
Signed-off-by: Markus Heiser <markus.heiser@darmarit.de>

3 files changed, 52 insertions, 24 deletions

diff --git a/searx/data/__main__.py b/searx/data/__main__.py
new file mode 100644
index 000000000..8e7852751
--- /dev/null
+++ b/searx/data/__main__.py
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: AGPL-3.0-or-later
+"""Command line implementation"""
+
+import typer
+
+from .core import get_cache
+
+app = typer.Typer()
+
+
+@app.command()
+def state():
+    """show state of the cache"""
+    cache = get_cache()
+    for table in cache.table_names:
+        for row in cache.DB.execute(f"SELECT count(*) FROM {table}"):
+            print(f"cache table {table} holds {row[0]} key/value pairs")
+
+
+app()
diff --git a/searx/data/currencies.py b/searx/data/currencies.py
index 33aa9530c..538900762 100644
--- a/searx/data/currencies.py
+++ b/searx/data/currencies.py
@@ -6,10 +6,12 @@ __all__ = ["CurrenciesDB"]
 import typing as t
 import json
 import pathlib
-import time
 
 from .core import get_cache, log
 
+if t.TYPE_CHECKING:
+    from searx.cache import CacheRowType
+
 
 @t.final
 class CurrenciesDB:
@@ -33,19 +35,14 @@ class CurrenciesDB:
         #     in /tmp and will be rebuild during the reboot anyway
 
     def load(self):
-        _start = time.time()
         log.debug("init searx.data.CURRENCIES")
         with open(self.json_file, encoding="utf-8") as f:
             data_dict: dict[str, dict[str, str]] = json.load(f)
-        for key, value in data_dict["names"].items():
-            self.cache.set(key=key, value=value, ctx=self.ctx_names, expire=None)
-        for key, value in data_dict["iso4217"].items():
-            self.cache.set(key=key, value=value, ctx=self.ctx_iso4217, expire=None)
-        log.debug(
-            "init searx.data.CURRENCIES added %s items in %s sec.",
-            len(data_dict["names"]) + len(data_dict["iso4217"]),
-            time.time() - _start,
-        )
+
+        rows: "list[CacheRowType]" = [(k, v, None) for k, v in data_dict["names"].items()]
+        self.cache.setmany(rows, ctx=self.ctx_names)
+        rows = [(k, v, None) for k, v in data_dict["iso4217"].items()]
+        self.cache.setmany(rows, ctx=self.ctx_iso4217)
 
     def name_to_iso4217(self, name: str) -> str | None:
         self.init()
diff --git a/searx/data/tracker_patterns.py b/searx/data/tracker_patterns.py
index 2966c0f31..fd4746e5c 100644
--- a/searx/data/tracker_patterns.py
+++ b/searx/data/tracker_patterns.py
@@ -1,7 +1,7 @@
 # SPDX-License-Identifier: AGPL-3.0-or-later
 """Simple implementation to store TrackerPatterns data in a SQL database."""
 
-import typing
+import typing as t
 
 __all__ = ["TrackerPatternsDB"]
 
@@ -14,9 +14,14 @@ from httpx import HTTPError
 from searx.data.core import get_cache, log
 from searx.network import get as http_get
 
+if t.TYPE_CHECKING:
+    from searx.cache import CacheRowType
+
+
 RuleType = tuple[str, list[str], list[str]]
 
 
+@t.final
 class TrackerPatternsDB:
     # pylint: disable=missing-class-docstring
 
@@ -31,9 +36,9 @@ class TrackerPatternsDB:
 
     class Fields:
         # pylint: disable=too-few-public-methods, invalid-name
-        url_regexp: typing.Final = 0  # URL (regular expression) match condition of the link
-        url_ignore: typing.Final = 1  # URL (regular expression) to ignore
-        del_args: typing.Final = 2  # list of URL arguments (regular expression) to delete
+        url_regexp: t.Final = 0  # URL (regular expression) match condition of the link
+        url_ignore: t.Final = 1  # URL (regular expression) to ignore
+        del_args: t.Final = 2  # list of URL arguments (regular expression) to delete
 
     def __init__(self):
         self.cache = get_cache()
@@ -49,19 +54,25 @@ class TrackerPatternsDB:
 
     def load(self):
         log.debug("init searx.data.TRACKER_PATTERNS")
-        for rule in self.iter_clear_list():
-            self.add(rule)
+        rows: "list[CacheRowType]" = []
 
-    def add(self, rule: RuleType):
-        self.cache.set(
-            key=rule[self.Fields.url_regexp],
-            value=(
+        for rule in self.iter_clear_list():
+            key = rule[self.Fields.url_regexp]
+            value = (
                 rule[self.Fields.url_ignore],
                 rule[self.Fields.del_args],
-            ),
-            ctx=self.ctx_name,
-            expire=None,
+            )
+            rows.append((key, value, None))
+
+        self.cache.setmany(rows, ctx=self.ctx_name)
+
+    def add(self, rule: RuleType):
+        key = rule[self.Fields.url_regexp]
+        value = (
+            rule[self.Fields.url_ignore],
+            rule[self.Fields.del_args],
         )
+        self.cache.set(key=key, value=value, ctx=self.ctx_name, expire=None)
 
     def rules(self) -> Iterator[RuleType]:
         self.init()