fix(utils): remove distutils boolean parser

.github/workflows/test-text-postprocessing.yml

@@ -3,6 +3,8 @@ name: Validate text postprocessing
 on:
   pull_request:
     paths:
+      - "funasr/utils/type_utils.py"
+      - "tests/test_type_utils_compat.py"
       - "funasr/utils/postprocess_hotwords.py"
       - "funasr/utils/postprocess_utils.py"
       - "runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py"
@@ -14,6 +16,8 @@ on:
   push:
     branches: [main]
     paths:
+      - "funasr/utils/type_utils.py"
+      - "tests/test_type_utils_compat.py"
       - "funasr/utils/postprocess_hotwords.py"
       - "funasr/utils/postprocess_utils.py"
       - "runtime/python/onnxruntime/funasr_onnx/utils/postprocess_utils.py"
@@ -52,6 +56,7 @@ jobs:
       - name: Check hotword and rich transcription behavior without model weights
         run: |
           python -m pytest -q \
+            tests/test_type_utils_compat.py \
             tests/test_postprocess_hotwords.py \
             tests/test_rich_transcription_postprocess.py \
             tests/test_sentence_postprocess_timestamps.py \

funasr/utils/type_utils.py

@@ -1,4 +1,3 @@
-from distutils.util import strtobool
 from typing import Optional
 from typing import Tuple
 from typing import Union
@@ -15,7 +14,12 @@ def str2bool(value: str) -> bool:
         Args:
             value: TODO.
         """
-    return bool(strtobool(value))
+    normalized = value.lower()
+    if normalized in ("y", "yes", "t", "true", "on", "1"):
+        return True
+    if normalized in ("n", "no", "f", "false", "off", "0"):
+        return False
+    raise ValueError(f"invalid truth value {normalized!r}")
 
 
 def remove_parenthesis(value: str):

tests/test_type_utils_compat.py

@@ -0,0 +1,65 @@
+"""Keep the command-line boolean parser compatible without distutils."""
+import importlib.util
+from pathlib import Path
+import subprocess
+import sys
+
+import pytest
+
+
+SOURCE = Path(__file__).resolve().parents[1] / "funasr/utils/type_utils.py"
+
+
+@pytest.fixture(scope="module")
+def parser():
+    spec = importlib.util.spec_from_file_location("boolean_parser_under_test", SOURCE)
+    module = importlib.util.module_from_spec(spec)
+    spec.loader.exec_module(module)
+    return module.str2bool
+
+
+@pytest.mark.parametrize(
+    ("value", "expected"),
+    [("y", True), ("yes", True), ("t", True), ("true", True), ("on", True),
+     ("1", True), ("n", False), ("no", False), ("f", False), ("false", False),
+     ("off", False), ("0", False), ("YeS", True), ("TRUE", True),
+     ("nO", False), ("OFF", False)],
+)
+def test_boolean_argument_preserves_values_and_boolean_type(parser, value, expected):
+    assert parser(value) is expected
+
+
+@pytest.mark.parametrize(
+    ("value", "message"),
+    [("MAYBE", "invalid truth value 'maybe'"),
+     ("FaLsE!", "invalid truth value 'false!'"),
+     (" TRUE ", "invalid truth value ' true '"),
+     ("", "invalid truth value ''"),
+     ("2", "invalid truth value '2'"),
+     ("false!", "invalid truth value 'false!'")],
+)
+def test_invalid_boolean_argument_preserves_normalized_error(parser, value, message):
+    with pytest.raises(ValueError) as caught:
+        parser(value)
+    assert str(caught.value) == message
+
+
+def test_boolean_parser_imports_when_distutils_is_unavailable():
+    code = """
+import importlib.abc
+import runpy
+import sys
+
+class MissingDistutils(importlib.abc.MetaPathFinder):
+    def find_spec(self, fullname, path=None, target=None):
+        if fullname == 'distutils' or fullname.startswith('distutils.'):
+            raise ImportError('distutils is unavailable')
+
+sys.meta_path.insert(0, MissingDistutils())
+parse = runpy.run_path(sys.argv[1])['str2bool']
+assert parse('yes') is True
+assert parse('no') is False
+"""
+    result = subprocess.run([sys.executable, "-c", code, str(SOURCE)],
+                            text=True, capture_output=True, timeout=20)
+    assert result.returncode == 0, result.stdout + result.stderr