From 0ae28f7d3ef33d6bf3650b99bc7646c3234341d1 Mon Sep 17 00:00:00 2001
From: Robert Sachunsky <sachunsky@informatik.uni-leipzig.de>
Date: Sat, 14 Dec 2024 12:15:56 +0000
Subject: [PATCH] switch from stdlib to loky.ProcessPoolExecutor, ensure
 shutdown

---
 requirements.txt         | 1 +
 src/eynollah/eynollah.py | 6 ++++--
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/requirements.txt b/requirements.txt
index d72df29..ef3fe31 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -5,3 +5,4 @@ scikit-learn >= 0.23.2
 tensorflow < 2.13
 imutils >= 0.5.3
 numba <= 0.58.1
+loky
diff --git a/src/eynollah/eynollah.py b/src/eynollah/eynollah.py
index 28cb330..8139b11 100644
--- a/src/eynollah/eynollah.py
+++ b/src/eynollah/eynollah.py
@@ -10,11 +10,12 @@ import math
 import os
 import sys
 import time
+import atexit
 import warnings
 from functools import partial
 from pathlib import Path
 from multiprocessing import cpu_count
-from concurrent.futures import ProcessPoolExecutor
+from loky import ProcessPoolExecutor
 import gc
 from ocrd_utils import getLogger
 import cv2
@@ -257,7 +258,8 @@ class Eynollah:
                 pcgts=pcgts)
         self.logger = logger if logger else getLogger('eynollah')
         # for parallelization of CPU-intensive tasks:
-        self.executor = ProcessPoolExecutor(max_workers=cpu_count())
+        self.executor = ProcessPoolExecutor(max_workers=cpu_count(), timeout=1200)
+        atexit.register(self.executor.shutdown)
         self.dir_models = dir_models
         self.model_dir_of_enhancement = dir_models + "/eynollah-enhancement_20210425"
         self.model_dir_of_binarization = dir_models + "/eynollah-binarization_20210425"