Try set utf-8 on console

Author: bact

.github/workflows/unittest.yml

@@ -72,6 +72,8 @@ jobs:
         SKLEARN_ALLOW_DEPRECATED_SKLEARN_PACKAGE_INSTALL: True
       run: pip install -r docker_requirements.txt
     - name: Install PyThaiNLP
+      env:
+        PYTHONIOENCODING: utf-8
       run: pip install .
       # If you want to install a safe small set of optional dependencies, use:
       # pip install .[compact]

pythainlp/cli/__init__.py

@@ -3,9 +3,13 @@
 # SPDX-License-Identifier: Apache-2.0
 """Command line helpers."""
 
+import io
 import sys
 from argparse import ArgumentParser
 
+sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding="utf-8")
+sys.stderr = io.TextIOWrapper(sys.stderr.buffer, encoding="utf-8")
+
 # a command should start with a verb when possible
 COMMANDS = sorted(["data", "soundex", "tag", "tokenize", "benchmark"])