RustPython · arihant2math · Jan 16, 2025 · Jan 16, 2025 · Jan 16, 2025 · Jan 16, 2025
diff --git a/Lib/gzip.py b/Lib/gzip.py
@@ -21,6 +21,9 @@
 _COMPRESS_LEVEL_TRADEOFF = 6
 _COMPRESS_LEVEL_BEST = 9
 
+READ_BUFFER_SIZE = 128 * 1024
+_WRITE_BUFFER_SIZE = 4 * io.DEFAULT_BUFFER_SIZE
+
 
 def open(filename, mode="rb", compresslevel=_COMPRESS_LEVEL_BEST,
          encoding=None, errors=None, newline=None):
@@ -94,7 +97,7 @@ def read(self, size):
             read = self._read
             self._read = None
             return self._buffer[read:] + \
-                   self.file.read(size-self._length+read)
+                self.file.read(size-self._length+read)
 
     def prepend(self, prepend=b''):
         if self._read is None:
@@ -118,6 +121,21 @@ class BadGzipFile(OSError):
     """Exception raised in some cases for invalid gzip files."""
 
 
+class _WriteBufferStream(io.RawIOBase):
+    """Minimal object to pass WriteBuffer flushes into GzipFile"""
+    def __init__(self, gzip_file):
+        self.gzip_file = gzip_file
+
+    def write(self, data):
+        return self.gzip_file._write_raw(data)
+
+    def seekable(self):
+        return False
+
+    def writable(self):
+        return True
+
+
 class GzipFile(_compression.BaseStream):
     """The GzipFile class simulates most of the methods of a file object with
     the exception of the truncate() method.
@@ -182,6 +200,7 @@ def __init__(self, filename=None, mode=None,
         if mode is None:
             mode = getattr(fileobj, 'mode', 'rb')
 
+
         if mode.startswith('r'):
             self.mode = READ
             raw = _GzipReader(fileobj)
@@ -204,6 +223,9 @@ def __init__(self, filename=None, mode=None,
                                              zlib.DEF_MEM_LEVEL,
                                              0)
             self._write_mtime = mtime
+            self._buffer_size = _WRITE_BUFFER_SIZE
+            self._buffer = io.BufferedWriter(_WriteBufferStream(self),
+                                             buffer_size=self._buffer_size)
         else:
             raise ValueError("Invalid mode: {!r}".format(mode))
 
@@ -212,14 +234,6 @@ def __init__(self, filename=None, mode=None,
         if self.mode == WRITE:
             self._write_gzip_header(compresslevel)
 
-    @property
-    def filename(self):
-        import warnings
-        warnings.warn("use the name attribute", DeprecationWarning, 2)
-        if self.mode == WRITE and self.name[-3:] != ".gz":
-            return self.name + ".gz"
-        return self.name
-
     @property
     def mtime(self):
         """Last modification time read from stream, or None"""
@@ -237,6 +251,11 @@ def _init_write(self, filename):
         self.bufsize = 0
         self.offset = 0  # Current file offset for seek(), tell(), etc
 
+    def tell(self):
+        self._check_not_closed()
+        self._buffer.flush()
+        return super().tell()
+
     def _write_gzip_header(self, compresslevel):
         self.fileobj.write(b'\037\213')             # magic header
         self.fileobj.write(b'\010')                 # compression method
@@ -278,6 +297,10 @@ def write(self,data):
         if self.fileobj is None:
             raise ValueError("write() on closed GzipFile object")
 
+        return self._buffer.write(data)
+
+    def _write_raw(self, data):
+        # Called by our self._buffer underlying WriteBufferStream.
         if isinstance(data, (bytes, bytearray)):
             length = len(data)
         else:
@@ -328,16 +351,17 @@ def close(self):
         fileobj = self.fileobj
         if fileobj is None:
             return
-        self.fileobj = None
         try:
             if self.mode == WRITE:
+                self._buffer.flush()
                 fileobj.write(self.compress.flush())
                 write32u(fileobj, self.crc)
                 # self.size may exceed 2 GiB, or even 4 GiB
                 write32u(fileobj, self.size & 0xffffffff)
             elif self.mode == READ:
                 self._buffer.close()
         finally:
+            self.fileobj = None
             myfileobj = self.myfileobj
             if myfileobj:
                 self.myfileobj = None
@@ -346,6 +370,7 @@ def close(self):
     def flush(self,zlib_mode=zlib.Z_SYNC_FLUSH):
         self._check_not_closed()
         if self.mode == WRITE:
+            self._buffer.flush()
             # Ensure the compressor's buffer is flushed
             self.fileobj.write(self.compress.flush(zlib_mode))
             self.fileobj.flush()
@@ -376,6 +401,9 @@ def seekable(self):
 
     def seek(self, offset, whence=io.SEEK_SET):
         if self.mode == WRITE:
+            self._check_not_closed()
+            # Flush buffer to ensure validity of self.offset
+            self._buffer.flush()
             if whence != io.SEEK_SET:
                 if whence == io.SEEK_CUR:
                     offset = self.offset + offset
@@ -384,10 +412,10 @@ def seek(self, offset, whence=io.SEEK_SET):
             if offset < self.offset:
                 raise OSError('Negative seek in write mode')
             count = offset - self.offset
-            chunk = b'\0' * 1024
-            for i in range(count // 1024):
+            chunk = b'\0' * self._buffer_size
+            for i in range(count // self._buffer_size):
                 self.write(chunk)
-            self.write(b'\0' * (count % 1024))
+            self.write(b'\0' * (count % self._buffer_size))
         elif self.mode == READ:
             self._check_not_closed()
             return self._buffer.seek(offset, whence)
@@ -454,7 +482,7 @@ def _read_gzip_header(fp):
 
 class _GzipReader(_compression.DecompressReader):
     def __init__(self, fp):
-        super().__init__(_PaddedFile(fp), zlib.decompressobj,
+        super().__init__(_PaddedFile(fp), zlib._ZlibDecompressor,
                          wbits=-zlib.MAX_WBITS)
         # Set flag indicating start of a new member
         self._new_member = True
@@ -502,12 +530,13 @@ def read(self, size=-1):
                 self._new_member = False
 
             # Read a chunk of data from the file
-            buf = self._fp.read(io.DEFAULT_BUFFER_SIZE)
+            if self._decompressor.needs_input:
+                buf = self._fp.read(READ_BUFFER_SIZE)
+                uncompress = self._decompressor.decompress(buf, size)
+            else:
+                uncompress = self._decompressor.decompress(b"", size)
 
-            uncompress = self._decompressor.decompress(buf, size)
-            if self._decompressor.unconsumed_tail != b"":
-                self._fp.prepend(self._decompressor.unconsumed_tail)
-            elif self._decompressor.unused_data != b"":
+            if self._decompressor.unused_data != b"":
                 # Prepend the already read bytes to the fileobj so they can
                 # be seen by _read_eof() and _read_gzip_header()
                 self._fp.prepend(self._decompressor.unused_data)
@@ -518,14 +547,11 @@ def read(self, size=-1):
                 raise EOFError("Compressed file ended before the "
                                "end-of-stream marker was reached")
 
-        self._add_read_data( uncompress )
+        self._crc = zlib.crc32(uncompress, self._crc)
+        self._stream_size += len(uncompress)
         self._pos += len(uncompress)
         return uncompress
 
-    def _add_read_data(self, data):
-        self._crc = zlib.crc32(data, self._crc)
-        self._stream_size = self._stream_size + len(data)
-
     def _read_eof(self):
         # We've read to the end of the file
         # We check that the computed CRC and size of the
@@ -619,13 +645,13 @@ def decompress(data):
 def main():
     from argparse import ArgumentParser
     parser = ArgumentParser(description=
-        "A simple command line interface for the gzip module: act like gzip, "
-        "but do not delete the input file.")
+                            "A simple command line interface for the gzip module: act like gzip, "
+                            "but do not delete the input file.")
     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()
@@ -655,7 +681,7 @@ def main():
                 f = builtins.open(arg, "rb")
                 g = open(arg + ".gz", "wb")
        while True:
-            chunk = f.read(io.DEFAULT_BUFFER_SIZE)
+            chunk = f.read(READ_BUFFER_SIZE)
             if not chunk:
                 break
             g.write(chunk)