Enhancement: allow regex timeout configuration

docs/configuration.md

@@ -1209,6 +1209,14 @@ left unassigned, preventing low-confidence guesses from being applied.
 
     Defaults to 0.6.
 
+#### [`PAPERLESS_MATCH_REGEX_TIMEOUT_SECONDS=<float>`](#PAPERLESS_MATCH_REGEX_TIMEOUT_SECONDS) {#PAPERLESS_MATCH_REGEX_TIMEOUT_SECONDS}
+
+: Sets the timeout, in seconds, for regular expression matching. Increase this
+value if date parsing or user-defined matching rules time out when processing
+long documents, especially on slower hardware.
+
+    Defaults to 0.1 seconds.
+
 #### [`PAPERLESS_DATE_PARSER_LANGUAGES=<lang>`](#PAPERLESS_DATE_PARSER_LANGUAGES) {#PAPERLESS_DATE_PARSER_LANGUAGES}
 
 : Specifies which language Paperless should use when parsing dates from documents.

src/documents/tests/test_regex.py

@@ -1,5 +1,6 @@
 import pytest
 import regex
+from django.conf import settings
 from pytest_mock import MockerFixture
 
 from documents.regex import safe_regex_finditer
@@ -9,6 +10,12 @@ from documents.regex import safe_regex_sub
 from documents.regex import validate_regex_pattern
 
 
+def test_regex_timeout_uses_configured_setting() -> None:
+    from documents.regex import REGEX_TIMEOUT_SECONDS
+
+    assert REGEX_TIMEOUT_SECONDS == settings.MATCH_REGEX_TIMEOUT_SECONDS
+
+
 class TestValidateRegexPattern:
     def test_valid_pattern(self) -> None:
         validate_regex_pattern(r"\d+")

src/paperless/settings/__init__.py

@@ -102,6 +102,10 @@ CLASSIFIER_MATCH_THRESHOLD: Final[float] = get_float_from_env(
     "PAPERLESS_CLASSIFIER_MATCH_THRESHOLD",
     0.6,
 )
+MATCH_REGEX_TIMEOUT_SECONDS: Final[float] = get_float_from_env(
+    "PAPERLESS_MATCH_REGEX_TIMEOUT_SECONDS",
+    0.1,
+)
 LLM_INDEX_DIR = DATA_DIR / "llm_index"
 LLM_INDEX_LOCK = LLM_INDEX_DIR / "index.lock"
 # Cross-process read/write lock guarding the LLM index compaction/migration