Update _compression, gzip from CPython v3.11.2

tdub0 · youknowone · commit 407f3f5d7831 · 2023-03-15T23:12:48.000+09:00
diff --git a/Lib/_compression.py b/Lib/_compression.py
@@ -1,7 +1,7 @@
 """Internal classes used by the gzip, lzma and bz2 modules"""
 
 import io
-
+import sys
 
 BUFFER_SIZE = io.DEFAULT_BUFFER_SIZE  # Compressed data read chunk size
 
@@ -110,6 +110,16 @@ def read(self, size=-1):
         self._pos += len(data)
         return data
 
+    def readall(self):
+        chunks = []
+        # sys.maxsize means the max length of output buffer is unlimited,
+        # so that the whole input buffer can be decompressed within one
+        # .decompress() call.
+        while data := self.read(sys.maxsize):
+            chunks.append(data)
+
+        return b"".join(chunks)
+
     # Rewind the file to the beginning of the data stream.
     def _rewind(self):
         self._fp.seek(0)
diff --git a/Lib/gzip.py b/Lib/gzip.py
@@ -399,6 +399,59 @@ def readline(self, size=-1):
         return self._buffer.readline(size)
 
 
+def _read_exact(fp, n):
+    '''Read exactly *n* bytes from `fp`
+
+    This method is required because fp may be unbuffered,
+    i.e. return short reads.
+    '''
+    data = fp.read(n)
+    while len(data) < n:
+        b = fp.read(n - len(data))
+        if not b:
+            raise EOFError("Compressed file ended before the "
+                           "end-of-stream marker was reached")
+        data += b
+    return data
+
+
+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'':
+        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))
+    if method != 8:
+        raise BadGzipFile('Unknown compression method')
+
+    if flag & FEXTRA:
+        # Read & discard the extra field, if present
+        extra_len, = struct.unpack("<H", _read_exact(fp, 2))
+        _read_exact(fp, extra_len)
+    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
+    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
+    return last_mtime
+
+
 class _GzipReader(_compression.DecompressReader):
     def __init__(self, fp):
         super().__init__(_PaddedFile(fp), zlib.decompressobj,
@@ -411,53 +464,11 @@ def _init_read(self):
         self._crc = zlib.crc32(b"")
         self._stream_size = 0  # Decompressed size of unconcatenated stream
 
-    def _read_exact(self, n):
-        '''Read exactly *n* bytes from `self._fp`
-
-        This method is required because self._fp may be unbuffered,
-        i.e. return short reads.
-        '''
-
-        data = self._fp.read(n)
-        while len(data) < n:
-            b = self._fp.read(n - len(data))
-            if not b:
-                raise EOFError("Compressed file ended before the "
-                               "end-of-stream marker was reached")
-            data += b
-        return data
-
     def _read_gzip_header(self):
-        magic = self._fp.read(2)
-        if magic == b'':
+        last_mtime = _read_gzip_header(self._fp)
+        if last_mtime is None:
             return False
-
-        if magic != b'\037\213':
-            raise BadGzipFile('Not a gzipped file (%r)' % magic)
-
-        (method, flag,
-         self._last_mtime) = struct.unpack("<BBIxx", self._read_exact(8))
-        if method != 8:
-            raise BadGzipFile('Unknown compression method')
-
-        if flag & FEXTRA:
-            # Read & discard the extra field, if present
-            extra_len, = struct.unpack("<H", self._read_exact(2))
-            self._read_exact(extra_len)
-        if flag & FNAME:
-            # Read and discard a null-terminated string containing the filename
-            while True:
-                s = self._fp.read(1)
-                if not s or s==b'\000':
-                    break
-        if flag & FCOMMENT:
-            # Read and discard a null-terminated string containing a comment
-            while True:
-                s = self._fp.read(1)
-                if not s or s==b'\000':
-                    break
-        if flag & FHCRC:
-            self._read_exact(2)     # Read & discard the 16-bit header CRC
+        self._last_mtime = last_mtime
         return True
 
     def read(self, size=-1):
@@ -520,7 +531,7 @@ def _read_eof(self):
         # We check that the computed CRC and size of the
         # uncompressed data matches the stored values.  Note that the size
         # stored is the true file size mod 2**32.
-        crc32, isize = struct.unpack("<II", self._read_exact(8))
+        crc32, isize = struct.unpack("<II", _read_exact(self._fp, 8))
         if crc32 != self._crc:
             raise BadGzipFile("CRC check failed %s != %s" % (hex(crc32),
                                                              hex(self._crc)))
@@ -540,21 +551,69 @@ def _rewind(self):
         super()._rewind()
         self._new_member = True
 
+
+def _create_simple_gzip_header(compresslevel: int,
+                               mtime = None) -> bytes:
+    """
+    Write a simple gzip header with no extra fields.
+    :param compresslevel: Compresslevel used to determine the xfl bytes.
+    :param mtime: The mtime (must support conversion to a 32-bit integer).
+    :return: A bytes object representing the gzip header.
+    """
+    if mtime is None:
+        mtime = time.time()
+    if compresslevel == _COMPRESS_LEVEL_BEST:
+        xfl = 2
+    elif compresslevel == _COMPRESS_LEVEL_FAST:
+        xfl = 4
+    else:
+        xfl = 0
+    # Pack ID1 and ID2 magic bytes, method (8=deflate), header flags (no extra
+    # fields added to header), mtime, xfl and os (255 for unknown OS).
+    return struct.pack("<BBBBLBB", 0x1f, 0x8b, 8, 0, int(mtime), xfl, 255)
+
+
 def compress(data, compresslevel=_COMPRESS_LEVEL_BEST, *, mtime=None):
     """Compress data in one shot and return the compressed string.
-    Optional argument is the compression level, in range of 0-9.
+
+    compresslevel sets the compression level in range of 0-9.
+    mtime can be used to set the modification time. The modification time is
+    set to the current time by default.
     """
-    buf = io.BytesIO()
-    with GzipFile(fileobj=buf, mode='wb', compresslevel=compresslevel, mtime=mtime) as f:
-        f.write(data)
-    return buf.getvalue()
+    if mtime == 0:
+        # Use zlib as it creates the header with 0 mtime by default.
+        # This is faster and with less overhead.
+        return zlib.compress(data, level=compresslevel, wbits=31)
+    header = _create_simple_gzip_header(compresslevel, mtime)
+    trailer = struct.pack("<LL", zlib.crc32(data), (len(data) & 0xffffffff))
+    # Wbits=-15 creates a raw deflate block.
+    return (header + zlib.compress(data, level=compresslevel, wbits=-15) +
+            trailer)
+
 
 def decompress(data):
     """Decompress a gzip compressed string in one shot.
     Return the decompressed string.
     """
-    with GzipFile(fileobj=io.BytesIO(data)) as f:
-        return f.read()
+    decompressed_members = []
+    while True:
+        fp = io.BytesIO(data)
+        if _read_gzip_header(fp) is None:
+            return b"".join(decompressed_members)
+        # Use a zlib raw deflate compressor
+        do = zlib.decompressobj(wbits=-zlib.MAX_WBITS)
+        # Read all the data except the header
+        decompressed = do.decompress(data[fp.tell():])
+        if not do.eof or len(do.unused_data) < 8:
+            raise EOFError("Compressed file ended before the end-of-stream "
+                           "marker was reached")
+        crc, length = struct.unpack("<II", do.unused_data[:8])
+        if crc != zlib.crc32(decompressed):
+            raise BadGzipFile("CRC check failed")
+        if length != (len(decompressed) & 0xffffffff):
+            raise BadGzipFile("Incorrect length of data produced")
+        decompressed_members.append(decompressed)
+        data = do.unused_data[8:].lstrip(b"\x00")
 
 
 def main():
diff --git a/Lib/test/test_gzip.py b/Lib/test/test_gzip.py
@@ -12,7 +12,7 @@
 from subprocess import PIPE, Popen
 from test.support import import_helper
 from test.support import os_helper
-from test.support import _4G, bigmemtest
+from test.support import _4G, bigmemtest, requires_subprocess
 from test.support.script_helper import assert_python_ok, assert_python_failure
 
 gzip = import_helper.import_module('gzip')
@@ -552,6 +552,15 @@ def test_compress_mtime(self):
                         f.read(1) # to set mtime attribute
                         self.assertEqual(f.mtime, mtime)
 
+    def test_compress_correct_level(self):
+        # gzip.compress calls with mtime == 0 take a different code path.
+        for mtime in (0, 42):
+            with self.subTest(mtime=mtime):
+                nocompress = gzip.compress(data1, compresslevel=0, mtime=mtime)
+                yescompress = gzip.compress(data1, compresslevel=1, mtime=mtime)
+                self.assertIn(data1, nocompress)
+                self.assertNotIn(data1, yescompress)
+
     def test_decompress(self):
         for data in (data1, data2):
             buf = io.BytesIO()
@@ -562,6 +571,14 @@ def test_decompress(self):
             datac = gzip.compress(data)
             self.assertEqual(gzip.decompress(datac), data)
 
+    def test_decompress_truncated_trailer(self):
+        compressed_data = gzip.compress(data1)
+        self.assertRaises(EOFError, gzip.decompress, compressed_data[:-4])
+
+    def test_decompress_missing_trailer(self):
+        compressed_data = gzip.compress(data1)
+        self.assertRaises(EOFError, gzip.decompress, compressed_data[:-8])
+
     def test_read_truncated(self):
         data = data1*50
         # Drop the CRC (4 bytes) and file size (4 bytes).
@@ -756,6 +773,7 @@ def wrapper(*args, **kwargs):
 class TestCommandLine(unittest.TestCase):
     data = b'This is a simple test with gzip'
 
+    @requires_subprocess()
     def test_decompress_stdin_stdout(self):
         with io.BytesIO() as bytes_io:
             with gzip.GzipFile(fileobj=bytes_io, mode='wb') as gzip_file:
@@ -791,6 +809,7 @@ def test_decompress_infile_outfile_error(self):
         self.assertEqual(rc, 1)
         self.assertEqual(out, b'')
 
+    @requires_subprocess()
     @create_and_remove_directory(TEMPDIR)
     def test_compress_stdin_outfile(self):
         args = sys.executable, '-m', 'gzip'
