youknowone · Oct 15, 2026 · Oct 14, 2026 · Oct 14, 2026 · Oct 14, 2026 · chatgpt-codex-connector
diff --git a/Lib/_pyio.py b/Lib/_pyio.py
@@ -550,7 +550,7 @@ def nreadahead():
             res += b
             if res.endswith(b"\n"):
                 break
-        return bytes(res)
+        return res.take_bytes()
 
     def __iter__(self):
         self._checkClosed()
@@ -624,15 +624,15 @@ def read(self, size=-1):
         if n < 0 or n > len(b):
             raise ValueError(f"readinto returned {n} outside buffer size {len(b)}")
         del b[n:]
-        return bytes(b)
+        return b.take_bytes()
 
     def readall(self):
         """Read until EOF, using multiple read() call."""
         res = bytearray()
         while data := self.read(DEFAULT_BUFFER_SIZE):
             res += data
         if res:
-            return bytes(res)
+            return res.take_bytes()
         else:
             # b'' or None
             return data
@@ -882,16 +882,28 @@ 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
@@ -924,14 +936,16 @@ def read(self, size=-1):
                 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.
@@ -949,13 +963,14 @@ def write(self, b):
             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] = view
-            self._pos += n
-        return 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] = view
+                self._pos += n
+            return n
 
     def seek(self, pos, whence=0):
         if self.closed:
@@ -971,9 +986,11 @@ def seek(self, pos, whence=0):
                 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
@@ -986,18 +1003,20 @@ def tell(self):
     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):
@@ -1486,6 +1505,7 @@ class FileIO(RawIOBase):
     _writable = False
     _appending = False
     _seekable = None
+    _truncate = False
     _closefd = True
 
     def __init__(self, file, mode='r', closefd=True, opener=None):
@@ -1546,6 +1566,7 @@ def __init__(self, file, mode='r', closefd=True, opener=None):
             flags = 0
         elif 'w' in mode:
             self._writable = True
+            self._truncate = True
             flags = os.O_CREAT | os.O_TRUNC
         elif 'a' in mode:
             self._writable = True
@@ -1727,7 +1748,7 @@ def readall(self):
         assert len(result) - bytes_read >= 1, \
             "os.readinto buffer size 0 will result in erroneous EOF / returns 0"
         result.resize(bytes_read)
-        return bytes(result)
+        return result.take_bytes()
 
     def readinto(self, buffer):
         """Same as RawIOBase.readinto()."""
@@ -1871,7 +1892,10 @@ def mode(self):
                 return 'ab'
         elif self._readable:
             if self._writable:
-                return 'rb+'
+                if self._truncate:
+                    return 'wb+'
+                else:
+                    return 'rb+'
             else:
                 return 'rb'
         else:

diff --git a/Lib/gzip.py b/Lib/gzip.py
@@ -30,7 +30,7 @@
 _WRITE_BUFFER_SIZE = 4 * io.DEFAULT_BUFFER_SIZE
 
 
-def open(filename, mode="rb", compresslevel=_COMPRESS_LEVEL_BEST,
+def open(filename, mode="rb", compresslevel=_COMPRESS_LEVEL_TRADEOFF,
          encoding=None, errors=None, newline=None):
     """Open a gzip-compressed file in binary or text mode.
 
@@ -158,7 +158,7 @@ class GzipFile(_streams.BaseStream):
     myfileobj = None
 
     def __init__(self, filename=None, mode=None,
-                 compresslevel=_COMPRESS_LEVEL_BEST, fileobj=None, mtime=None):
+                 compresslevel=_COMPRESS_LEVEL_TRADEOFF, fileobj=None, mtime=None):
         """Constructor for the GzipFile class.
 
         At least one of fileobj and filename must be given a
@@ -189,9 +189,10 @@ def __init__(self, filename=None, mode=None,
 
         The optional mtime argument is the timestamp requested by gzip.
         The time is in Unix format, i.e., seconds since 00:00:00 UTC,
-        January 1, 1970.  If mtime is omitted or None, the current time
-        is used.  Use mtime = 0 to generate a compressed stream that does
-        not depend on creation time.
+        January 1, 1970.  Set mtime to 0 to generate a compressed stream
+        that does not depend on creation time.  If mtime is omitted or None,
+        the current time is used.  If the resulting mtime is outside the
+        range 0 to 2**32-1, then the value 0 is used instead.
 
         """
 
@@ -270,8 +271,6 @@ def _init_write(self, filename):
         self.name = filename
         self.crc = zlib.crc32(b"")
         self.size = 0
-        self.writebuf = []
-        self.bufsize = 0
         self.offset = 0  # Current file offset for seek(), tell(), etc
 
     def tell(self):
@@ -299,6 +298,8 @@ def _write_gzip_header(self, compresslevel):
         mtime = self._write_mtime
         if mtime is None:
             mtime = time.time()
+        if not 0 <= mtime < 2**32:
+            mtime = 0
         write32u(self.fileobj, int(mtime))
         if compresslevel == _COMPRESS_LEVEL_BEST:
             xfl = b'\002'
@@ -488,40 +489,73 @@ def _read_exact(fp, n):
     return data
 
 
+def _read_until_null(fp, crc=None):
+    '''Read until the first encountered null byte in fp.
+    If crc is not None, update and return the CRC.
+    '''
+    if crc is None:
+        while True:
+            s = fp.read(1)
+            if not s or s == b'\000':
+                break
+    else:
+        while True:
+            s = fp.read(1)
+            crc = zlib.crc32(s, crc)
+            if not s or s == b'\000':
+                break
+    return crc
+
+
 def _read_gzip_header(fp):
     '''Read a gzip header from `fp` and progress to the end of the header.
 
     Returns last mtime if header was present or None otherwise.
     '''
     magic = fp.read(2)
-    if magic == b'':
+    if not magic:
         return None
 
     if magic != b'\037\213':
         raise BadGzipFile('Not a gzipped file (%r)' % magic)
-
-    (method, flag, last_mtime) = struct.unpack("<BBIxx", _read_exact(fp, 8))
+    base_header = _read_exact(fp, 8)
+    (method, flag, last_mtime) = struct.unpack("<BBIxx", base_header)
     if method != 8:
         raise BadGzipFile('Unknown compression method')
 
+    # Most common cases are no flags (gzip.compress, zlib.compress) or only
+    # FNAME set (GzipFile, gzip command line application). Exit early
+    # in those cases.
+    if not flag:
+        return last_mtime
+    if flag == FNAME:
+        # Read and discard a null-terminated string containing the filename
+        _read_until_null(fp)
+        return last_mtime
+
+    # Processing for more complex flags. Save header parts for FHCRC checking.
+    if flag & FHCRC:
+        crc = zlib.crc32(magic + base_header)
+    else:
+        crc = None
     if flag & FEXTRA:
-        # Read & discard the extra field, if present
-        extra_len, = struct.unpack("<H", _read_exact(fp, 2))
-        _read_exact(fp, extra_len)
+        extra_len_bytes = _read_exact(fp, 2)
+        extra_len, = struct.unpack("<H", extra_len_bytes)
+        extra = _read_exact(fp, extra_len)
+        if crc is not None:
+            crc = zlib.crc32(extra_len_bytes, crc)
+            crc = zlib.crc32(extra, crc)
     if flag & FNAME:
-        # Read and discard a null-terminated string containing the filename
-        while True:
-            s = fp.read(1)
-            if not s or s==b'\000':
-                break
+        crc = _read_until_null(fp, crc)
     if flag & FCOMMENT:
-        # Read and discard a null-terminated string containing a comment
-        while True:
-            s = fp.read(1)
-            if not s or s==b'\000':
-                break
-    if flag & FHCRC:
-        _read_exact(fp, 2)     # Read & discard the 16-bit header CRC
+        crc = _read_until_null(fp, crc)
+    if crc is not None:
+        # Header CRC is the last 16 bits of a crc32.
+        header_crc, = struct.unpack("<H", _read_exact(fp, 2))
+        crc = crc & 0xFFFF
+        if header_crc != crc:
+            raise BadGzipFile(f"Corrupted gzip header. Checksums do not "
+                              f"match: {crc:04x} != {header_crc:04x}")
     return last_mtime
 
 
@@ -623,7 +657,7 @@ def _rewind(self):
         self._new_member = True
 
 
-def compress(data, compresslevel=_COMPRESS_LEVEL_BEST, *, mtime=0):
+def compress(data, compresslevel=_COMPRESS_LEVEL_TRADEOFF, *, mtime=0):
     """Compress data in one shot and return the compressed string.
 
     compresslevel sets the compression level in range of 0-9.
@@ -634,6 +668,8 @@ def compress(data, compresslevel=_COMPRESS_LEVEL_BEST, *, mtime=0):
     gzip_data = zlib.compress(data, level=compresslevel, wbits=31)
     if mtime is None:
         mtime = time.time()
+    if not 0 <= mtime < 2**32:
+        mtime = 0
     # Reuse gzip header created by zlib, replace mtime and OS byte for
     # consistency.
     header = struct.pack("<4sLBB", gzip_data, int(mtime), gzip_data[8], 255)
@@ -668,15 +704,14 @@ def decompress(data):
 def main():
     from argparse import ArgumentParser
     parser = ArgumentParser(description=
-        "A simple command line interface for the gzip module: act like gzip, "
+        "A simple command line interface for the `gzip` module: act like `gzip`, "
         "but do not delete the input file.",
-        color=True,
     )
     group = parser.add_mutually_exclusive_group()
     group.add_argument('--fast', action='store_true', help='compress faster')
     group.add_argument('--best', action='store_true', help='compress better')
     group.add_argument("-d", "--decompress", action="store_true",
-                        help="act like gunzip instead of gzip")
+                        help="act like `gunzip` instead of `gzip`")
 
     parser.add_argument("args", nargs="*", default=["-"], metavar='file')
     args = parser.parse_args()