Deprecate semfree and don't auto activate it

Instead the standard executor will fall back to threads.

semfree caused test failures  with Py3.14:
https://github.com/ocrmypdf/OCRmyPDF/issues/1558

In retrospect and with emerging Python tech like freethreading, semfree is becoming less necessary. We can use threads for the time being.

A consequence is that performance may be lower on Lambda and Termux when we are using threads and not shelling out work.

src/ocrmypdf/_plugin_manager.py

@@ -73,19 +73,10 @@ class OcrmypdfPluginManager(pluggy.PluginManager):
                 module = importlib.import_module(name)
                 self.register(module)
 
-        # 2. Install semfree if needed
-        try:
-            # pylint: disable=import-outside-toplevel
-            from multiprocessing.synchronize import SemLock
-
-            del SemLock
-        except ImportError:
-            self.register(importlib.import_module('ocrmypdf.extra_plugins.semfree'))
-
-        # 3. Register setuptools plugins
+        # 2. Register setuptools plugins
         self.load_setuptools_entrypoints('ocrmypdf')
 
-        # 4. Register plugins specified on command line
+        # 3. Register plugins specified on command line
         for name in self.__plugins:
             if isinstance(name, Path) or name.endswith('.py'):
                 # Import by filename

src/ocrmypdf/builtin_plugins/concurrency.py

@@ -96,6 +96,31 @@ def thread_init(q: Queue, user_init: UserInit, loglevel) -> None:
     return
 
 
+def setup_executor(use_threads: bool) -> tuple[Queue, Executor, WorkerInit]:
+    if not use_threads:
+        # Some execution environments like AWS Lambda and Termux do not support
+        # semaphores. Check if semaphore support is available, and if not, fall back
+        # to using threads.
+        try:
+            # pylint: disable=import-outside-toplevel
+            from multiprocessing.synchronize import SemLock
+
+            del SemLock
+        except ImportError:
+            use_threads = True
+
+    if use_threads:
+        loq_queue = queue.Queue(-1)
+        executor_class = ThreadPoolExecutor
+        initializer = thread_init
+    else:
+        loq_queue = multiprocessing.Queue(-1)
+        executor_class = ProcessPoolExecutor
+        initializer = process_init
+
+    return loq_queue, executor_class, initializer
+
+
 class StandardExecutor(Executor):
     """Standard OCRmyPDF concurrent task executor."""
 
@@ -110,14 +135,7 @@ class StandardExecutor(Executor):
         task_arguments: Iterable,
         task_finished: Callable,
     ):
-        if use_threads:
-            log_queue: Queue = queue.Queue(-1)
-            executor_class: FuturesExecutorClass = ThreadPoolExecutor
-            initializer: WorkerInit = thread_init
-        else:
-            log_queue = multiprocessing.Queue(-1)
-            executor_class = ProcessPoolExecutor
-            initializer = process_init
+        log_queue, executor_class, initializer = setup_executor(use_threads)
 
         # Regardless of whether we use_threads for worker processes, the log_listener
         # must be a thread. Make sure we create the listener after the worker pool,

src/ocrmypdf/extra_plugins/__init__.py

@@ -2,8 +2,4 @@
 #
 # SPDX-License-Identifier: MPL-2.0
 
-"""Extra plugins. These are not automatically inserted when ocrmypdf is run.
-
-You can use these plugins by specifying them on the command line, e.g.:
-ocrmypdf --plugin ocrmypdf.extra_plugins.semfree ...
-"""
+"""Extra plugins. These are not automatically inserted when ocrmypdf is run."""

src/ocrmypdf/extra_plugins/semfree.py

@@ -13,6 +13,9 @@ worker communicates only with the main process.
 This is not without drawbacks. If the tasks are not "even" in size, which cannot
 be guaranteed, some workers may end up with too much work while others are idle.
 It is less efficient than the standard implementation, so not the default.
+
+This module is deprecated and will be removed in a future release. The standard
+executor will fall back to threads in these environments.
 """
 
 from __future__ import annotations
@@ -20,6 +23,7 @@ from __future__ import annotations
 import logging
 import logging.handlers
 import signal
+import warnings
 from collections.abc import Callable, Iterable, Iterator
 from contextlib import suppress
 from enum import Enum, auto
@@ -32,6 +36,11 @@ from ocrmypdf._concurrent import NullProgressBar
 from ocrmypdf.exceptions import InputFileError
 from ocrmypdf.helpers import remove_all_log_handlers
 
+warnings.warn(
+    "semfree.py is deprecated and will be removed in a future release.",
+    DeprecationWarning,
+)
+
 
 class MessageType(Enum):
     """Implement basic IPC messaging."""

tests/test_semfree.py

@@ -12,15 +12,16 @@ from .conftest import is_linux, run_ocrmypdf_api
 
 @pytest.mark.skipif(not is_linux(), reason='semfree plugin only works on Linux')
 def test_semfree(resources, outpdf):
-    exitcode = run_ocrmypdf_api(
-        resources / 'multipage.pdf',
-        outpdf,
-        '--skip-text',
-        '--skip-big',
-        '2',
-        '--plugin',
-        'ocrmypdf.extra_plugins.semfree',
-        '--plugin',
-        'tests/plugins/tesseract_noop.py',
-    )
-    assert exitcode in (ExitCode.ok, ExitCode.pdfa_conversion_failed)
+    with pytest.warns(DeprecationWarning, match="semfree.py is deprecated"):
+        exitcode = run_ocrmypdf_api(
+            resources / 'multipage.pdf',
+            outpdf,
+            '--skip-text',
+            '--skip-big',
+            '2',
+            '--plugin',
+            'ocrmypdf.extra_plugins.semfree',
+            '--plugin',
+            'tests/plugins/tesseract_noop.py',
+        )
+        assert exitcode in (ExitCode.ok, ExitCode.pdfa_conversion_failed)