aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/Lib/test/test_codecs.py
diff options
context:
space:
mode:
Diffstat (limited to 'Lib/test/test_codecs.py')
-rw-r--r--Lib/test/test_codecs.py105
1 files changed, 73 insertions, 32 deletions
diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py
index e51f7e0ee12..d8666f7290e 100644
--- a/Lib/test/test_codecs.py
+++ b/Lib/test/test_codecs.py
@@ -1,12 +1,15 @@
import codecs
import contextlib
import copy
+import importlib
import io
import pickle
+import os
import sys
import unittest
import encodings
from unittest import mock
+import warnings
from test import support
from test.support import os_helper
@@ -20,13 +23,12 @@ try:
except ImportError:
_testinternalcapi = None
-try:
- import ctypes
-except ImportError:
- ctypes = None
- SIZEOF_WCHAR_T = -1
-else:
- SIZEOF_WCHAR_T = ctypes.sizeof(ctypes.c_wchar)
+
+def codecs_open_no_warn(*args, **kwargs):
+ """Call codecs.open(*args, **kwargs) ignoring DeprecationWarning."""
+ with warnings.catch_warnings():
+ warnings.simplefilter("ignore")
+ return codecs.open(*args, **kwargs)
def coding_checker(self, coder):
def check(input, expect):
@@ -35,13 +37,13 @@ def coding_checker(self, coder):
# On small versions of Windows like Windows IoT or Windows Nano Server not all codepages are present
def is_code_page_present(cp):
- from ctypes import POINTER, WINFUNCTYPE, WinDLL
+ from ctypes import POINTER, WINFUNCTYPE, WinDLL, Structure
from ctypes.wintypes import BOOL, BYTE, WCHAR, UINT, DWORD
MAX_LEADBYTES = 12 # 5 ranges, 2 bytes ea., 0 term.
MAX_DEFAULTCHAR = 2 # single or double byte
MAX_PATH = 260
- class CPINFOEXW(ctypes.Structure):
+ class CPINFOEXW(Structure):
_fields_ = [("MaxCharSize", UINT),
("DefaultChar", BYTE*MAX_DEFAULTCHAR),
("LeadByte", BYTE*MAX_LEADBYTES),
@@ -719,19 +721,19 @@ class UTF16Test(ReadTest, unittest.TestCase):
self.addCleanup(os_helper.unlink, os_helper.TESTFN)
with open(os_helper.TESTFN, 'wb') as fp:
fp.write(s)
- with codecs.open(os_helper.TESTFN, 'r',
+ with codecs_open_no_warn(os_helper.TESTFN, 'r',
encoding=self.encoding) as reader:
self.assertEqual(reader.read(), s1)
def test_invalid_modes(self):
for mode in ('U', 'rU', 'r+U'):
with self.assertRaises(ValueError) as cm:
- codecs.open(os_helper.TESTFN, mode, encoding=self.encoding)
+ codecs_open_no_warn(os_helper.TESTFN, mode, encoding=self.encoding)
self.assertIn('invalid mode', str(cm.exception))
for mode in ('rt', 'wt', 'at', 'r+t'):
with self.assertRaises(ValueError) as cm:
- codecs.open(os_helper.TESTFN, mode, encoding=self.encoding)
+ codecs_open_no_warn(os_helper.TESTFN, mode, encoding=self.encoding)
self.assertIn("can't have text and binary mode at once",
str(cm.exception))
@@ -1196,23 +1198,39 @@ class EscapeDecodeTest(unittest.TestCase):
check(br"[\1010]", b"[A0]")
check(br"[\x41]", b"[A]")
check(br"[\x410]", b"[A0]")
+
+ def test_warnings(self):
+ decode = codecs.escape_decode
+ check = coding_checker(self, decode)
for i in range(97, 123):
b = bytes([i])
if b not in b'abfnrtvx':
- with self.assertWarns(DeprecationWarning):
+ with self.assertWarnsRegex(DeprecationWarning,
+ r'"\\%c" is an invalid escape sequence' % i):
check(b"\\" + b, b"\\" + b)
- with self.assertWarns(DeprecationWarning):
+ with self.assertWarnsRegex(DeprecationWarning,
+ r'"\\%c" is an invalid escape sequence' % (i-32)):
check(b"\\" + b.upper(), b"\\" + b.upper())
- with self.assertWarns(DeprecationWarning):
+ with self.assertWarnsRegex(DeprecationWarning,
+ r'"\\8" is an invalid escape sequence'):
check(br"\8", b"\\8")
with self.assertWarns(DeprecationWarning):
check(br"\9", b"\\9")
- with self.assertWarns(DeprecationWarning):
+ with self.assertWarnsRegex(DeprecationWarning,
+ r'"\\\xfa" is an invalid escape sequence') as cm:
check(b"\\\xfa", b"\\\xfa")
for i in range(0o400, 0o1000):
- with self.assertWarns(DeprecationWarning):
+ with self.assertWarnsRegex(DeprecationWarning,
+ r'"\\%o" is an invalid octal escape sequence' % i):
check(rb'\%o' % i, bytes([i & 0o377]))
+ with self.assertWarnsRegex(DeprecationWarning,
+ r'"\\z" is an invalid escape sequence'):
+ self.assertEqual(decode(br'\x\z', 'ignore'), (b'\\z', 4))
+ with self.assertWarnsRegex(DeprecationWarning,
+ r'"\\501" is an invalid octal escape sequence'):
+ self.assertEqual(decode(br'\x\501', 'ignore'), (b'A', 6))
+
def test_errors(self):
decode = codecs.escape_decode
self.assertRaises(ValueError, decode, br"\x")
@@ -1844,9 +1862,9 @@ class CodecsModuleTest(unittest.TestCase):
def test_open(self):
self.addCleanup(os_helper.unlink, os_helper.TESTFN)
for mode in ('w', 'r', 'r+', 'w+', 'a', 'a+'):
- with self.subTest(mode), \
- codecs.open(os_helper.TESTFN, mode, 'ascii') as file:
- self.assertIsInstance(file, codecs.StreamReaderWriter)
+ with self.subTest(mode), self.assertWarns(DeprecationWarning):
+ with codecs.open(os_helper.TESTFN, mode, 'ascii') as file:
+ self.assertIsInstance(file, codecs.StreamReaderWriter)
def test_undefined(self):
self.assertRaises(UnicodeError, codecs.encode, 'abc', 'undefined')
@@ -1863,7 +1881,7 @@ class CodecsModuleTest(unittest.TestCase):
mock_open = mock.mock_open()
with mock.patch('builtins.open', mock_open) as file:
with self.assertRaises(LookupError):
- codecs.open(os_helper.TESTFN, 'wt', 'invalid-encoding')
+ codecs_open_no_warn(os_helper.TESTFN, 'wt', 'invalid-encoding')
file().close.assert_called()
@@ -2661,24 +2679,40 @@ class UnicodeEscapeTest(ReadTest, unittest.TestCase):
check(br"[\x410]", "[A0]")
check(br"\u20ac", "\u20ac")
check(br"\U0001d120", "\U0001d120")
+
+ def test_decode_warnings(self):
+ decode = codecs.unicode_escape_decode
+ check = coding_checker(self, decode)
for i in range(97, 123):
b = bytes([i])
if b not in b'abfnrtuvx':
- with self.assertWarns(DeprecationWarning):
+ with self.assertWarnsRegex(DeprecationWarning,
+ r'"\\%c" is an invalid escape sequence' % i):
check(b"\\" + b, "\\" + chr(i))
if b.upper() not in b'UN':
- with self.assertWarns(DeprecationWarning):
+ with self.assertWarnsRegex(DeprecationWarning,
+ r'"\\%c" is an invalid escape sequence' % (i-32)):
check(b"\\" + b.upper(), "\\" + chr(i-32))
- with self.assertWarns(DeprecationWarning):
+ with self.assertWarnsRegex(DeprecationWarning,
+ r'"\\8" is an invalid escape sequence'):
check(br"\8", "\\8")
with self.assertWarns(DeprecationWarning):
check(br"\9", "\\9")
- with self.assertWarns(DeprecationWarning):
+ with self.assertWarnsRegex(DeprecationWarning,
+ r'"\\\xfa" is an invalid escape sequence') as cm:
check(b"\\\xfa", "\\\xfa")
for i in range(0o400, 0o1000):
- with self.assertWarns(DeprecationWarning):
+ with self.assertWarnsRegex(DeprecationWarning,
+ r'"\\%o" is an invalid octal escape sequence' % i):
check(rb'\%o' % i, chr(i))
+ with self.assertWarnsRegex(DeprecationWarning,
+ r'"\\z" is an invalid escape sequence'):
+ self.assertEqual(decode(br'\x\z', 'ignore'), ('\\z', 4))
+ with self.assertWarnsRegex(DeprecationWarning,
+ r'"\\501" is an invalid octal escape sequence'):
+ self.assertEqual(decode(br'\x\501', 'ignore'), ('\u0141', 6))
+
def test_decode_errors(self):
decode = codecs.unicode_escape_decode
for c, d in (b'x', 2), (b'u', 4), (b'U', 4):
@@ -2883,7 +2917,7 @@ class BomTest(unittest.TestCase):
self.addCleanup(os_helper.unlink, os_helper.TESTFN)
for encoding in tests:
# Check if the BOM is written only once
- with codecs.open(os_helper.TESTFN, 'w+', encoding=encoding) as f:
+ with codecs_open_no_warn(os_helper.TESTFN, 'w+', encoding=encoding) as f:
f.write(data)
f.write(data)
f.seek(0)
@@ -2892,7 +2926,7 @@ class BomTest(unittest.TestCase):
self.assertEqual(f.read(), data * 2)
# Check that the BOM is written after a seek(0)
- with codecs.open(os_helper.TESTFN, 'w+', encoding=encoding) as f:
+ with codecs_open_no_warn(os_helper.TESTFN, 'w+', encoding=encoding) as f:
f.write(data[0])
self.assertNotEqual(f.tell(), 0)
f.seek(0)
@@ -2901,7 +2935,7 @@ class BomTest(unittest.TestCase):
self.assertEqual(f.read(), data)
# (StreamWriter) Check that the BOM is written after a seek(0)
- with codecs.open(os_helper.TESTFN, 'w+', encoding=encoding) as f:
+ with codecs_open_no_warn(os_helper.TESTFN, 'w+', encoding=encoding) as f:
f.writer.write(data[0])
self.assertNotEqual(f.writer.tell(), 0)
f.writer.seek(0)
@@ -2911,7 +2945,7 @@ class BomTest(unittest.TestCase):
# Check that the BOM is not written after a seek() at a position
# different than the start
- with codecs.open(os_helper.TESTFN, 'w+', encoding=encoding) as f:
+ with codecs_open_no_warn(os_helper.TESTFN, 'w+', encoding=encoding) as f:
f.write(data)
f.seek(f.tell())
f.write(data)
@@ -2920,7 +2954,7 @@ class BomTest(unittest.TestCase):
# (StreamWriter) Check that the BOM is not written after a seek()
# at a position different than the start
- with codecs.open(os_helper.TESTFN, 'w+', encoding=encoding) as f:
+ with codecs_open_no_warn(os_helper.TESTFN, 'w+', encoding=encoding) as f:
f.writer.write(data)
f.writer.seek(f.writer.tell())
f.writer.write(data)
@@ -3075,6 +3109,13 @@ class TransformCodecTest(unittest.TestCase):
info = codecs.lookup(alias)
self.assertEqual(info.name, expected_name)
+ def test_alias_modules_exist(self):
+ encodings_dir = os.path.dirname(encodings.__file__)
+ for value in encodings.aliases.aliases.values():
+ codec_mod = f"encodings.{value}"
+ self.assertIsNotNone(importlib.util.find_spec(codec_mod),
+ f"Codec module not found: {codec_mod}")
+
def test_quopri_stateless(self):
# Should encode with quotetabs=True
encoded = codecs.encode(b"space tab\teol \n", "quopri-codec")
@@ -3762,7 +3803,7 @@ class LocaleCodecTest(unittest.TestCase):
with self.assertRaises(RuntimeError) as cm:
self.decode(encoded, errors)
errmsg = str(cm.exception)
- self.assertTrue(errmsg.startswith("decode error: "), errmsg)
+ self.assertStartsWith(errmsg, "decode error: ")
else:
decoded = self.decode(encoded, errors)
self.assertEqual(decoded, expected)
generated by cgit v1.2.3 (git 2.39.1) at 2025-07-01 08:41:48 +0000