aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/Lib
diff options
context:
space:
mode:
Diffstat (limited to 'Lib')
-rw-r--r--Lib/_pyio.py80
-rw-r--r--Lib/html/parser.py18
-rw-r--r--Lib/test/test_free_threading/test_io.py42
-rw-r--r--Lib/test/test_getpath.py21
-rw-r--r--Lib/test/test_htmlparser.py32
-rw-r--r--Lib/test/test_io.py1
6 files changed, 144 insertions, 50 deletions
diff --git a/Lib/_pyio.py b/Lib/_pyio.py
index fb2a6d049ca..5db8ce9244b 100644
--- a/Lib/_pyio.py
+++ b/Lib/_pyio.py
@@ -876,16 +876,28 @@ class BytesIO(BufferedIOBase):
_buffer = None
def __init__(self, initial_bytes=None):
+ # Use to keep self._buffer and self._pos consistent.
+ self._lock = Lock()
+
buf = bytearray()
if initial_bytes is not None:
buf += initial_bytes
- self._buffer = buf
- self._pos = 0
+
+ with self._lock:
+ self._buffer = buf
+ self._pos = 0
def __getstate__(self):
if self.closed:
raise ValueError("__getstate__ on closed file")
- return self.__dict__.copy()
+ with self._lock:
+ state = self.__dict__.copy()
+ del state['_lock']
+ return state
+
+ def __setstate__(self, state):
+ self.__dict__.update(state)
+ self._lock = Lock()
def getvalue(self):
"""Return the bytes value (contents) of the buffer
@@ -918,14 +930,16 @@ class BytesIO(BufferedIOBase):
raise TypeError(f"{size!r} is not an integer")
else:
size = size_index()
- if size < 0:
- size = len(self._buffer)
- if len(self._buffer) <= self._pos:
- return b""
- newpos = min(len(self._buffer), self._pos + size)
- b = self._buffer[self._pos : newpos]
- self._pos = newpos
- return bytes(b)
+
+ with self._lock:
+ if size < 0:
+ size = len(self._buffer)
+ if len(self._buffer) <= self._pos:
+ return b""
+ newpos = min(len(self._buffer), self._pos + size)
+ b = self._buffer[self._pos : newpos]
+ self._pos = newpos
+ return bytes(b)
def read1(self, size=-1):
"""This is the same as read.
@@ -941,12 +955,14 @@ class BytesIO(BufferedIOBase):
n = view.nbytes # Size of any bytes-like object
if n == 0:
return 0
- pos = self._pos
- if pos > len(self._buffer):
- # Pad buffer to pos with null bytes.
- self._buffer.resize(pos)
- self._buffer[pos:pos + n] = b
- self._pos += n
+
+ with self._lock:
+ pos = self._pos
+ if pos > len(self._buffer):
+ # Pad buffer to pos with null bytes.
+ self._buffer.resize(pos)
+ self._buffer[pos:pos + n] = b
+ self._pos += n
return n
def seek(self, pos, whence=0):
@@ -963,9 +979,11 @@ class BytesIO(BufferedIOBase):
raise ValueError("negative seek position %r" % (pos,))
self._pos = pos
elif whence == 1:
- self._pos = max(0, self._pos + pos)
+ with self._lock:
+ self._pos = max(0, self._pos + pos)
elif whence == 2:
- self._pos = max(0, len(self._buffer) + pos)
+ with self._lock:
+ self._pos = max(0, len(self._buffer) + pos)
else:
raise ValueError("unsupported whence value")
return self._pos
@@ -978,18 +996,20 @@ class BytesIO(BufferedIOBase):
def truncate(self, pos=None):
if self.closed:
raise ValueError("truncate on closed file")
- if pos is None:
- pos = self._pos
- else:
- try:
- pos_index = pos.__index__
- except AttributeError:
- raise TypeError(f"{pos!r} is not an integer")
+
+ with self._lock:
+ if pos is None:
+ pos = self._pos
else:
- pos = pos_index()
- if pos < 0:
- raise ValueError("negative truncate position %r" % (pos,))
- del self._buffer[pos:]
+ try:
+ pos_index = pos.__index__
+ except AttributeError:
+ raise TypeError(f"{pos!r} is not an integer")
+ else:
+ pos = pos_index()
+ if pos < 0:
+ raise ValueError("negative truncate position %r" % (pos,))
+ del self._buffer[pos:]
return pos
def readable(self):
diff --git a/Lib/html/parser.py b/Lib/html/parser.py
index cc15de07b5b..9b4f0959913 100644
--- a/Lib/html/parser.py
+++ b/Lib/html/parser.py
@@ -29,7 +29,8 @@ attr_charref = re.compile(r'&(#[0-9]+|#[xX][0-9a-fA-F]+|[a-zA-Z][a-zA-Z0-9]*)[;=
starttagopen = re.compile('<[a-zA-Z]')
endtagopen = re.compile('</[a-zA-Z]')
piclose = re.compile('>')
-commentclose = re.compile(r'--\s*>')
+commentclose = re.compile(r'--!?>')
+commentabruptclose = re.compile(r'-?>')
# Note:
# 1) if you change tagfind/attrfind remember to update locatetagend too;
# 2) if you change tagfind/attrfind and/or locatetagend the parser will
@@ -336,6 +337,21 @@ class HTMLParser(_markupbase.ParserBase):
else:
return self.parse_bogus_comment(i)
+ # Internal -- parse comment, return length or -1 if not terminated
+ # see https://html.spec.whatwg.org/multipage/parsing.html#comment-start-state
+ def parse_comment(self, i, report=True):
+ rawdata = self.rawdata
+ assert rawdata.startswith('<!--', i), 'unexpected call to parse_comment()'
+ match = commentclose.search(rawdata, i+4)
+ if not match:
+ match = commentabruptclose.match(rawdata, i+4)
+ if not match:
+ return -1
+ if report:
+ j = match.start()
+ self.handle_comment(rawdata[i+4: j])
+ return match.end()
+
# Internal -- parse bogus comment, return length or -1 if not terminated
# see https://html.spec.whatwg.org/multipage/parsing.html#bogus-comment-state
def parse_bogus_comment(self, i, report=1):
diff --git a/Lib/test/test_free_threading/test_io.py b/Lib/test/test_free_threading/test_io.py
index f9bec740ddf..41d89e04da8 100644
--- a/Lib/test/test_free_threading/test_io.py
+++ b/Lib/test/test_free_threading/test_io.py
@@ -1,12 +1,13 @@
+import io
+import _pyio as pyio
import threading
from unittest import TestCase
from test.support import threading_helper
from random import randint
-from io import BytesIO
from sys import getsizeof
-class TestBytesIO(TestCase):
+class ThreadSafetyMixin:
# Test pretty much everything that can break under free-threading.
# Non-deterministic, but at least one of these things will fail if
# BytesIO object is not free-thread safe.
@@ -90,20 +91,27 @@ class TestBytesIO(TestCase):
barrier.wait()
getsizeof(b)
- self.check([write] * 10, BytesIO())
- self.check([writelines] * 10, BytesIO())
- self.check([write] * 10 + [truncate] * 10, BytesIO())
- self.check([truncate] + [read] * 10, BytesIO(b'0\n'*204800))
- self.check([truncate] + [read1] * 10, BytesIO(b'0\n'*204800))
- self.check([truncate] + [readline] * 10, BytesIO(b'0\n'*20480))
- self.check([truncate] + [readlines] * 10, BytesIO(b'0\n'*20480))
- self.check([truncate] + [readinto] * 10, BytesIO(b'0\n'*204800), bytearray(b'0\n'*204800))
- self.check([close] + [write] * 10, BytesIO())
- self.check([truncate] + [getvalue] * 10, BytesIO(b'0\n'*204800))
- self.check([truncate] + [getbuffer] * 10, BytesIO(b'0\n'*204800))
- self.check([truncate] + [iter] * 10, BytesIO(b'0\n'*20480))
- self.check([truncate] + [getstate] * 10, BytesIO(b'0\n'*204800))
- self.check([truncate] + [setstate] * 10, BytesIO(b'0\n'*204800), (b'123', 0, None))
- self.check([truncate] + [sizeof] * 10, BytesIO(b'0\n'*204800))
+ self.check([write] * 10, self.ioclass())
+ self.check([writelines] * 10, self.ioclass())
+ self.check([write] * 10 + [truncate] * 10, self.ioclass())
+ self.check([truncate] + [read] * 10, self.ioclass(b'0\n'*204800))
+ self.check([truncate] + [read1] * 10, self.ioclass(b'0\n'*204800))
+ self.check([truncate] + [readline] * 10, self.ioclass(b'0\n'*20480))
+ self.check([truncate] + [readlines] * 10, self.ioclass(b'0\n'*20480))
+ self.check([truncate] + [readinto] * 10, self.ioclass(b'0\n'*204800), bytearray(b'0\n'*204800))
+ self.check([close] + [write] * 10, self.ioclass())
+ self.check([truncate] + [getvalue] * 10, self.ioclass(b'0\n'*204800))
+ self.check([truncate] + [getbuffer] * 10, self.ioclass(b'0\n'*204800))
+ self.check([truncate] + [iter] * 10, self.ioclass(b'0\n'*20480))
+ self.check([truncate] + [getstate] * 10, self.ioclass(b'0\n'*204800))
+ state = self.ioclass(b'123').__getstate__()
+ self.check([truncate] + [setstate] * 10, self.ioclass(b'0\n'*204800), state)
+ self.check([truncate] + [sizeof] * 10, self.ioclass(b'0\n'*204800))
# no tests for seek or tell because they don't break anything
+
+class CBytesIOTest(ThreadSafetyMixin, TestCase):
+ ioclass = io.BytesIO
+
+class PyBytesIOTest(ThreadSafetyMixin, TestCase):
+ ioclass = pyio.BytesIO
diff --git a/Lib/test/test_getpath.py b/Lib/test/test_getpath.py
index f86df9d0d03..83f09f34955 100644
--- a/Lib/test/test_getpath.py
+++ b/Lib/test/test_getpath.py
@@ -354,6 +354,27 @@ class MockGetPathTests(unittest.TestCase):
actual = getpath(ns, expected)
self.assertEqual(expected, actual)
+ def test_venv_posix_without_home_key(self):
+ ns = MockPosixNamespace(
+ argv0="/venv/bin/python3",
+ PREFIX="/usr",
+ ENV_PATH="/usr/bin",
+ )
+ # Setup the bare minimum venv
+ ns.add_known_xfile("/usr/bin/python3")
+ ns.add_known_xfile("/venv/bin/python3")
+ ns.add_known_link("/venv/bin/python3", "/usr/bin/python3")
+ ns.add_known_file("/venv/pyvenv.cfg", [
+ # home = key intentionally omitted
+ ])
+ expected = dict(
+ executable="/venv/bin/python3",
+ prefix="/venv",
+ base_prefix="/usr",
+ )
+ actual = getpath(ns, expected)
+ self.assertEqual(expected, actual)
+
def test_venv_changed_name_posix(self):
"Test a venv layout on *nix."
ns = MockPosixNamespace(
diff --git a/Lib/test/test_htmlparser.py b/Lib/test/test_htmlparser.py
index d0d2c54217c..15cad061889 100644
--- a/Lib/test/test_htmlparser.py
+++ b/Lib/test/test_htmlparser.py
@@ -367,17 +367,45 @@ text
html = ("<!-- I'm a valid comment -->"
'<!--me too!-->'
'<!------>'
+ '<!----->'
'<!---->'
+ # abrupt-closing-of-empty-comment
+ '<!--->'
+ '<!-->'
'<!----I have many hyphens---->'
'<!-- I have a > in the middle -->'
- '<!-- and I have -- in the middle! -->')
+ '<!-- and I have -- in the middle! -->'
+ '<!--incorrectly-closed-comment--!>'
+ '<!----!>'
+ '<!----!-->'
+ '<!---- >-->'
+ '<!---!>-->'
+ '<!--!>-->'
+ # nested-comment
+ '<!-- <!-- nested --> -->'
+ '<!--<!-->'
+ '<!--<!--!>'
+ )
expected = [('comment', " I'm a valid comment "),
('comment', 'me too!'),
('comment', '--'),
+ ('comment', '-'),
+ ('comment', ''),
+ ('comment', ''),
('comment', ''),
('comment', '--I have many hyphens--'),
('comment', ' I have a > in the middle '),
- ('comment', ' and I have -- in the middle! ')]
+ ('comment', ' and I have -- in the middle! '),
+ ('comment', 'incorrectly-closed-comment'),
+ ('comment', ''),
+ ('comment', '--!'),
+ ('comment', '-- >'),
+ ('comment', '-!>'),
+ ('comment', '!>'),
+ ('comment', ' <!-- nested '), ('data', ' -->'),
+ ('comment', '<!'),
+ ('comment', '<!'),
+ ]
self._run_check(html, expected)
def test_condcoms(self):
diff --git a/Lib/test/test_io.py b/Lib/test/test_io.py
index 0c921ffbc25..b487bcabf01 100644
--- a/Lib/test/test_io.py
+++ b/Lib/test/test_io.py
@@ -9,6 +9,7 @@
# * test_univnewlines - tests universal newline support
# * test_largefile - tests operations on a file greater than 2**32 bytes
# (only enabled with -ulargefile)
+# * test_free_threading/test_io - tests thread safety of io objects
################################################################################
# ATTENTION TEST WRITERS!!!
generated by cgit v1.2.3 (git 2.39.1) at 2025-07-05 09:20:24 +0000