Issue #14371: Support bzip2 in zipfile module.

Patch by Serhiy Storchaka.

Doc/library/zipfile.rst

@@ -87,7 +87,22 @@ The module defines the following items:
 .. data:: ZIP_DEFLATED
 
    The numeric constant for the usual ZIP compression method.  This requires the
-   zlib module.  No other compression methods are currently supported.
+   zlib module.
+
+
+.. data:: ZIP_BZIP2
+
+   The numeric constant for the BZIP2 compression method.  This requires the
+   bz2 module.
+
+   .. versionadded:: 3.3
+
+   .. note::
+
+      The ZIP file format specification has included support for bzip2 compression
+      since 2001. However, some tools (including older Python releases) do not
+      support it, and may either refuse to process the ZIP file altogether, or
+      fail to extract individual files.
 
 
 .. seealso::
@@ -118,9 +133,11 @@ ZipFile Objects
    adding a ZIP archive to another file (such as :file:`python.exe`).  If
    *mode* is ``a`` and the file does not exist at all, it is created.
    *compression* is the ZIP compression method to use when writing the archive,
-   and should be :const:`ZIP_STORED` or :const:`ZIP_DEFLATED`; unrecognized
+   and should be :const:`ZIP_STORED`, :const:`ZIP_DEFLATED`; or
-   values will cause :exc:`RuntimeError` to be raised.  If :const:`ZIP_DEFLATED`
+   :const:`ZIP_DEFLATED`; unrecognized
-   is specified but the :mod:`zlib` module is not available, :exc:`RuntimeError`
+   values will cause :exc:`RuntimeError` to be raised.  If :const:`ZIP_DEFLATED` or
+   :const:`ZIP_BZIP2` is specified but the corresponded module
+   (:mod:`zlib` or :mod:`bz2`) is not available, :exc:`RuntimeError`
    is also raised. The default is :const:`ZIP_STORED`.  If *allowZip64* is
    ``True`` zipfile will create ZIP files that use the ZIP64 extensions when
    the zipfile is larger than 2 GB. If it is  false (the default) :mod:`zipfile`
@@ -143,6 +160,9 @@ ZipFile Objects
    .. versionadded:: 3.2
       Added the ability to use :class:`ZipFile` as a context manager.
 
+   .. versionchanged:: 3.3
+      Added support for :mod:`bzip2` compression.
+
 
 .. method:: ZipFile.close()
 

Lib/test/support.py

@@ -40,6 +40,11 @@ try:
 except ImportError:
     zlib = None
 
+try:
+    import bz2
+except ImportError:
+    bz2 = None
+
 __all__ = [
     "Error", "TestFailed", "ResourceDenied", "import_module",
     "verbose", "use_resources", "max_memuse", "record_original_stdout",
@@ -57,7 +62,7 @@ __all__ = [
     "get_attribute", "swap_item", "swap_attr", "requires_IEEE_754",
     "TestHandler", "Matcher", "can_symlink", "skip_unless_symlink",
     "import_fresh_module", "requires_zlib", "PIPE_MAX_SIZE", "failfast",
-    "anticipate_failure", "run_with_tz"
+    "anticipate_failure", "run_with_tz", "requires_bz2"
     ]
 
 class Error(Exception):
@@ -506,6 +511,8 @@ requires_IEEE_754 = unittest.skipUnless(
 
 requires_zlib = unittest.skipUnless(zlib, 'requires zlib')
 
+requires_bz2 = unittest.skipUnless(bz2, 'requires bz2')
+
 is_jython = sys.platform.startswith('java')
 
 # Filename used for testing

Lib/test/test_zipfile.py

@@ -13,7 +13,7 @@ from tempfile import TemporaryFile
 from random import randint, random
 from unittest import skipUnless
 
-from test.support import TESTFN, run_unittest, findfile, unlink, requires_zlib
+from test.support import TESTFN, run_unittest, findfile, unlink, requires_zlib, requires_bz2
 
 TESTFN2 = TESTFN + "2"
 TESTFNDIR = TESTFN + "d"
@@ -313,6 +313,54 @@ class TestsWithSourceFile(unittest.TestCase):
                 self.assertEqual(openobj.read(1), b'1')
                 self.assertEqual(openobj.read(1), b'2')
 
+    @requires_bz2
+    def test_bzip2(self):
+        for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
+            self.zip_test(f, zipfile.ZIP_BZIP2)
+
+    @requires_bz2
+    def test_open_bzip2(self):
+        for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
+            self.zip_open_test(f, zipfile.ZIP_BZIP2)
+
+    @requires_bz2
+    def test_random_open_bzip2(self):
+        for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
+            self.zip_random_open_test(f, zipfile.ZIP_BZIP2)
+
+    @requires_bz2
+    def test_readline_read_bzip2(self):
+        for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
+            self.zip_readline_read_test(f, zipfile.ZIP_BZIP2)
+
+    @requires_bz2
+    def test_readline_bzip2(self):
+        for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
+            self.zip_readline_test(f, zipfile.ZIP_BZIP2)
+
+    @requires_bz2
+    def test_readlines_bzip2(self):
+        for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
+            self.zip_readlines_test(f, zipfile.ZIP_BZIP2)
+
+    @requires_bz2
+    def test_iterlines_bzip2(self):
+        for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
+            self.zip_iterlines_test(f, zipfile.ZIP_BZIP2)
+
+    @requires_bz2
+    def test_low_compression_bzip2(self):
+        """Check for cases where compressed data is larger than original."""
+        # Create the ZIP archive
+        with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_BZIP2) as zipfp:
+            zipfp.writestr("strfile", '12')
+
+        # Get an open object for strfile
+        with zipfile.ZipFile(TESTFN2, "r", zipfile.ZIP_BZIP2) as zipfp:
+            with zipfp.open("strfile") as openobj:
+                self.assertEqual(openobj.read(1), b'1')
+                self.assertEqual(openobj.read(1), b'2')
+
     def test_absolute_arcnames(self):
         with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED) as zipfp:
             zipfp.write(TESTFN, "/absolute")
@@ -453,6 +501,13 @@ class TestsWithSourceFile(unittest.TestCase):
         info = zipfp.getinfo('b.txt')
         self.assertEqual(info.compress_type, zipfile.ZIP_DEFLATED)
 
+    @requires_bz2
+    def test_writestr_compression_bzip2(self):
+        zipfp = zipfile.ZipFile(TESTFN2, "w")
+        zipfp.writestr("b.txt", "hello world", compress_type=zipfile.ZIP_BZIP2)
+        info = zipfp.getinfo('b.txt')
+        self.assertEqual(info.compress_type, zipfile.ZIP_BZIP2)
+
     def zip_test_writestr_permissions(self, f, compression):
         # Make sure that writestr creates files with mode 0600,
         # when it is passed a name rather than a ZipInfo instance.
@@ -626,6 +681,11 @@ class TestZip64InSmallFiles(unittest.TestCase):
         for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
             self.zip_test(f, zipfile.ZIP_DEFLATED)
 
+    @requires_bz2
+    def test_bzip2(self):
+        for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
+            self.zip_test(f, zipfile.ZIP_BZIP2)
+
     def test_absolute_arcnames(self):
         with zipfile.ZipFile(TESTFN2, "w", zipfile.ZIP_STORED,
                              allowZip64=True) as zipfp:
@@ -754,6 +814,18 @@ class OtherTests(unittest.TestCase):
             b'\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00\x80\x01\x00\x00\x00'
             b'\x00afilePK\x05\x06\x00\x00\x00\x00\x01\x00'
             b'\x01\x003\x00\x00\x003\x00\x00\x00\x00\x00'),
+        zipfile.ZIP_BZIP2: (
+            b'PK\x03\x04\x14\x03\x00\x00\x0c\x00nu\x0c=FA'
+            b'KE8\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00af'
+            b'ileBZh91AY&SY\xd4\xa8\xca'
+            b'\x7f\x00\x00\x0f\x11\x80@\x00\x06D\x90\x80 \x00 \xa5'
+            b'P\xd9!\x03\x03\x13\x13\x13\x89\xa9\xa9\xc2u5:\x9f'
+            b'\x8b\xb9"\x9c(HjTe?\x80PK\x01\x02\x14'
+            b'\x03\x14\x03\x00\x00\x0c\x00nu\x0c=FAKE8'
+            b'\x00\x00\x00n\x00\x00\x00\x05\x00\x00\x00\x00\x00\x00\x00\x00'
+            b'\x00 \x80\x80\x81\x00\x00\x00\x00afilePK'
+            b'\x05\x06\x00\x00\x00\x00\x01\x00\x01\x003\x00\x00\x00[\x00'
+            b'\x00\x00\x00\x00'),
     }
 
     def test_unicode_filenames(self):
@@ -1007,6 +1079,10 @@ class OtherTests(unittest.TestCase):
     def test_testzip_with_bad_crc_deflated(self):
         self.check_testzip_with_bad_crc(zipfile.ZIP_DEFLATED)
 
+    @requires_bz2
+    def test_testzip_with_bad_crc_bzip2(self):
+        self.check_testzip_with_bad_crc(zipfile.ZIP_BZIP2)
+
     def check_read_with_bad_crc(self, compression):
         """Tests that files with bad CRCs raise a BadZipFile exception when read."""
         zipdata = self.zips_with_bad_crc[compression]
@@ -1035,6 +1111,10 @@ class OtherTests(unittest.TestCase):
     def test_read_with_bad_crc_deflated(self):
         self.check_read_with_bad_crc(zipfile.ZIP_DEFLATED)
 
+    @requires_bz2
+    def test_read_with_bad_crc_bzip2(self):
+        self.check_read_with_bad_crc(zipfile.ZIP_BZIP2)
+
     def check_read_return_size(self, compression):
         # Issue #9837: ZipExtFile.read() shouldn't return more bytes
         # than requested.
@@ -1055,6 +1135,10 @@ class OtherTests(unittest.TestCase):
     def test_read_return_size_deflated(self):
         self.check_read_return_size(zipfile.ZIP_DEFLATED)
 
+    @requires_bz2
+    def test_read_return_size_bzip2(self):
+        self.check_read_return_size(zipfile.ZIP_BZIP2)
+
     def test_empty_zipfile(self):
         # Check that creating a file in 'w' or 'a' mode and closing without
         # adding any files to the archives creates a valid empty ZIP file
@@ -1196,6 +1280,11 @@ class TestsWithRandomBinaryFiles(unittest.TestCase):
         for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
             self.zip_test(f, zipfile.ZIP_DEFLATED)
 
+    @requires_bz2
+    def test_bzip2(self):
+        for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
+            self.zip_test(f, zipfile.ZIP_BZIP2)
+
     def zip_open_test(self, f, compression):
         self.make_test_archive(f, compression)
 
@@ -1236,6 +1325,11 @@ class TestsWithRandomBinaryFiles(unittest.TestCase):
         for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
             self.zip_open_test(f, zipfile.ZIP_DEFLATED)
 
+    @requires_bz2
+    def test_open_bzip2(self):
+        for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
+            self.zip_open_test(f, zipfile.ZIP_BZIP2)
+
     def zip_random_open_test(self, f, compression):
         self.make_test_archive(f, compression)
 
@@ -1264,6 +1358,11 @@ class TestsWithRandomBinaryFiles(unittest.TestCase):
         for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
             self.zip_random_open_test(f, zipfile.ZIP_DEFLATED)
 
+    @requires_bz2
+    def test_random_open_bzip2(self):
+        for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
+            self.zip_random_open_test(f, zipfile.ZIP_BZIP2)
+
 
 @requires_zlib
 class TestsWithMultipleOpens(unittest.TestCase):
@@ -1483,6 +1582,31 @@ class UniversalNewlineTests(unittest.TestCase):
         for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
             self.iterlines_test(f, zipfile.ZIP_DEFLATED)
 
+    @requires_bz2
+    def test_read_bzip2(self):
+        for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
+            self.read_test(f, zipfile.ZIP_BZIP2)
+
+    @requires_bz2
+    def test_readline_read_bzip2(self):
+        for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
+            self.readline_read_test(f, zipfile.ZIP_BZIP2)
+
+    @requires_bz2
+    def test_readline_bzip2(self):
+        for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
+            self.readline_test(f, zipfile.ZIP_BZIP2)
+
+    @requires_bz2
+    def test_readlines_bzip2(self):
+        for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
+            self.readlines_test(f, zipfile.ZIP_BZIP2)
+
+    @requires_bz2
+    def test_iterlines_bzip2(self):
+        for f in (TESTFN2, TemporaryFile(), io.BytesIO()):
+            self.iterlines_test(f, zipfile.ZIP_BZIP2)
+
     def tearDown(self):
         for sep, fn in self.arcfiles.items():
             os.remove(fn)

Lib/zipfile.py

@@ -22,7 +22,13 @@ except ImportError:
     zlib = None
     crc32 = binascii.crc32
 
-__all__ = ["BadZipFile", "BadZipfile", "error", "ZIP_STORED", "ZIP_DEFLATED",
+try:
+    import bz2 # We may need its compression method
+except ImportError:
+    bz2 = None
+
+__all__ = ["BadZipFile", "BadZipfile", "error",
+           "ZIP_STORED", "ZIP_DEFLATED", "ZIP_BZIP2"
            "is_zipfile", "ZipInfo", "ZipFile", "PyZipFile", "LargeZipFile"]
 
 class BadZipFile(Exception):
@@ -45,8 +51,13 @@ ZIP_MAX_COMMENT = (1 << 16) - 1
 # constants for Zip file compression methods
 ZIP_STORED = 0
 ZIP_DEFLATED = 8
+ZIP_BZIP2 = 12
 # Other ZIP compression methods not supported
 
+DEFAULT_VERSION = 20
+ZIP64_VERSION = 45
+BZIP2_VERSION = 46
+
 # Below are some formats and associated data for reading/writing headers using
 # the struct module.  The names and structures of headers/records are those used
 # in the PKWARE description of the ZIP file format:
@@ -313,8 +324,8 @@ class ZipInfo (object):
         else:
             # Assume everything else is unix-y
             self.create_system = 3          # System which created ZIP archive
-        self.create_version = 20        # Version which created ZIP archive
+        self.create_version = DEFAULT_VERSION  # Version which created ZIP archive
-        self.extract_version = 20       # Version needed to extract archive
+        self.extract_version = DEFAULT_VERSION # Version needed to extract archive
         self.reserved = 0               # Must be zero
         self.flag_bits = 0              # ZIP flag bits
         self.volume = 0                 # Volume number of file header
@@ -341,6 +352,7 @@ class ZipInfo (object):
 
         extra = self.extra
 
+        min_version = 0
         if file_size > ZIP64_LIMIT or compress_size > ZIP64_LIMIT:
             # File is larger than what fits into a 4 byte integer,
             # fall back to the ZIP64 extension
@@ -349,9 +361,13 @@ class ZipInfo (object):
                     1, struct.calcsize(fmt)-4, file_size, compress_size)
             file_size = 0xffffffff
             compress_size = 0xffffffff
-            self.extract_version = max(45, self.extract_version)
+            min_version = ZIP64_VERSION
-            self.create_version = max(45, self.extract_version)
 
+        if self.compress_type == ZIP_BZIP2:
+            min_version = max(BZIP2_VERSION, min_version)
+
+        self.extract_version = max(min_version, self.extract_version)
+        self.create_version = max(min_version, self.create_version)
         filename, flag_bits = self._encodeFilenameFlags()
         header = struct.pack(structFileHeader, stringFileHeader,
                  self.extract_version, self.reserved, flag_bits,
@@ -461,6 +477,41 @@ class _ZipDecrypter:
         self._UpdateKeys(c)
         return c
 
+
+def _check_compression(compression):
+    if compression == ZIP_STORED:
+        pass
+    elif compression == ZIP_DEFLATED:
+        if not zlib:
+            raise RuntimeError(
+                    "Compression requires the (missing) zlib module")
+    elif compression == ZIP_BZIP2:
+        if not bz2:
+            raise RuntimeError(
+                    "Compression requires the (missing) bz2 module")
+    else:
+        raise RuntimeError("That compression method is not supported")
+
+
+def _get_compressor(compress_type):
+    if compress_type == ZIP_DEFLATED:
+        return zlib.compressobj(zlib.Z_DEFAULT_COMPRESSION,
+             zlib.DEFLATED, -15)
+    elif compress_type == ZIP_BZIP2:
+        return bz2.BZ2Compressor()
+    else:
+        return None
+
+
+def _get_decompressor(compress_type):
+    if compress_type == ZIP_DEFLATED:
+        return zlib.decompressobj(-15)
+    elif compress_type == ZIP_BZIP2:
+        return bz2.BZ2Decompressor()
+    else:
+        return None
+
+
 class ZipExtFile(io.BufferedIOBase):
     """File-like object for reading an archive member.
        Is returned by ZipFile.open().
@@ -482,13 +533,12 @@ class ZipExtFile(io.BufferedIOBase):
         self._close_fileobj = close_fileobj
 
         self._compress_type = zipinfo.compress_type
-        self._compress_size = zipinfo.compress_size
         self._compress_left = zipinfo.compress_size
+        self._left = zipinfo.file_size
 
-        if self._compress_type == ZIP_DEFLATED:
+        self._decompressor = _get_decompressor(self._compress_type)
-            self._decompressor = zlib.decompressobj(-15)
-        self._unconsumed = b''
 
+        self._eof = False
         self._readbuffer = b''
         self._offset = 0
 
@@ -563,7 +613,11 @@ class ZipExtFile(io.BufferedIOBase):
         """Returns buffered bytes without advancing the position."""
         if n > len(self._readbuffer) - self._offset:
             chunk = self.read(n)
-            self._offset -= len(chunk)
+            if len(chunk) > self._offset:
+                self._readbuffer = chunk + self._readbuffer[self._offset:]
+                self._offset = 0
+            else:
+                self._offset -= len(chunk)
 
         # Return up to 512 bytes to reduce allocation overhead for tight loops.
         return self._readbuffer[self._offset: self._offset + 512]
@@ -575,80 +629,121 @@ class ZipExtFile(io.BufferedIOBase):
         """Read and return up to n bytes.
         If the argument is omitted, None, or negative, data is read and returned until EOF is reached..
         """
-        buf = b''
+        if n is None or n < 0:
-        if n is None:
+            buf = self._readbuffer[self._offset:]
-            n = -1
+            self._readbuffer = b''
-        while True:
+            self._offset = 0
-            if n < 0:
+            while not self._eof:
-                data = self.read1(n)
+                buf += self._read1(self.MAX_N)
-            elif n > len(buf):
+            return buf
-                data = self.read1(n - len(buf))
-            else:
-                return buf
-            if len(data) == 0:
-                return buf
-            buf += data
 
-    def _update_crc(self, newdata, eof):
+        n -= len(self._readbuffer) - self._offset
+        if n < 0:
+            buf = self._readbuffer[self._offset:n]
+            self._offset += len(buf)
+            return buf
+
+        buf = self._readbuffer[self._offset:]
+        self._readbuffer = b''
+        self._offset = 0
+        while n > 0 and not self._eof:
+            data = self._read1(n)
+            if n < len(data):
+                self._readbuffer = data
+                self._offset = n
+                buf += data[:n]
+                break
+            buf += data
+            n -= len(data)
+        return buf
+
+    def _update_crc(self, newdata):
         # Update the CRC using the given data.
         if self._expected_crc is None:
             # No need to compute the CRC if we don't have a reference value
             return
         self._running_crc = crc32(newdata, self._running_crc) & 0xffffffff
         # Check the CRC if we're at the end of the file
-        if eof and self._running_crc != self._expected_crc:
+        if self._eof and self._running_crc != self._expected_crc:
             raise BadZipFile("Bad CRC-32 for file %r" % self.name)
 
     def read1(self, n):
         """Read up to n bytes with at most one read() system call."""
 
-        # Simplify algorithm (branching) by transforming negative n to large n.
+        if n is None or n < 0:
-        if n < 0 or n is None:
+            buf = self._readbuffer[self._offset:]
-            n = self.MAX_N
+            self._readbuffer = b''
+            self._offset = 0
+            data = self._read1(self.MAX_N)
+            buf += data
+            return buf
 
-        # Bytes available in read buffer.
+        n -= len(self._readbuffer) - self._offset
-        len_readbuffer = len(self._readbuffer) - self._offset
+        if n < 0:
+            buf = self._readbuffer[self._offset:n]
+            self._offset += len(buf)
+            return buf
+
+        buf = self._readbuffer[self._offset:]
+        self._readbuffer = b''
+        self._offset = 0
+        if n > 0:
+            data = self._read1(n)
+            if n < len(data):
+                self._readbuffer = data
+                self._offset = n
+                data = data[:n]
+            buf += data
+        return buf
+
+    def _read1(self, n):
+        # Read up to n compressed bytes with at most one read() system call,
+        # decrypt and decompress them.
+        if self._eof or n <= 0:
+            return b''
 
         # Read from file.
-        if self._compress_left > 0 and n > len_readbuffer + len(self._unconsumed):
+        if self._compress_type == ZIP_DEFLATED:
-            nbytes = n - len_readbuffer - len(self._unconsumed)
+            ## Handle unconsumed data.
-            nbytes = max(nbytes, self.MIN_READ_SIZE)
+            data = self._decompressor.unconsumed_tail
-            nbytes = min(nbytes, self._compress_left)
+            if n > len(data):
+                data += self._read2(n - len(data))
+        else:
+            data = self._read2(n)
 
-            data = self._fileobj.read(nbytes)
+        if self._compress_type == ZIP_STORED:
-            self._compress_left -= len(data)
+            self._eof = self._compress_left <= 0
-
+        elif self._compress_type == ZIP_DEFLATED:
-            if data and self._decrypter is not None:
+            n = max(n, self.MIN_READ_SIZE)
-                data = bytes(map(self._decrypter, data))
+            data = self._decompressor.decompress(data, n)
-
+            self._eof = (self._decompressor.eof or
-            if self._compress_type == ZIP_STORED:
+                    self._compress_left <= 0 and
-                self._update_crc(data, eof=(self._compress_left==0))
+                    not self._decompressor.unconsumed_tail)
-                self._readbuffer = self._readbuffer[self._offset:] + data
+            if self._eof:
-                self._offset = 0
-            else:
-                # Prepare deflated bytes for decompression.
-                self._unconsumed += data
-
-        # Handle unconsumed data.
-        if (len(self._unconsumed) > 0 and n > len_readbuffer and
-            self._compress_type == ZIP_DEFLATED):
-            data = self._decompressor.decompress(
-                self._unconsumed,
-                max(n - len_readbuffer, self.MIN_READ_SIZE)
-            )
-
-            self._unconsumed = self._decompressor.unconsumed_tail
-            eof = len(self._unconsumed) == 0 and self._compress_left == 0
-            if eof:
                 data += self._decompressor.flush()
+        else:
+            data = self._decompressor.decompress(data)
+            self._eof = self._decompressor.eof or self._compress_left <= 0
 
-            self._update_crc(data, eof=eof)
+        data = data[:self._left]
-            self._readbuffer = self._readbuffer[self._offset:] + data
+        self._left -= len(data)
-            self._offset = 0
+        if self._left <= 0:
+            self._eof = True
+        self._update_crc(data)
+        return data
 
-        # Read from buffer.
+    def _read2(self, n):
-        data = self._readbuffer[self._offset: self._offset + n]
+        if self._compress_left <= 0:
-        self._offset += len(data)
+            return b''
+
+        n = max(n, self.MIN_READ_SIZE)
+        n = min(n, self._compress_left)
+
+        data = self._fileobj.read(n)
+        self._compress_left -= len(data)
+
+        if self._decrypter is not None:
+            data = bytes(map(self._decrypter, data))
         return data
 
     def close(self):
@@ -667,7 +762,8 @@ class ZipFile:
     file: Either the path to the file, or a file-like object.
           If it is a path, the file will be opened and closed by ZipFile.
     mode: The mode can be either read "r", write "w" or append "a".
-    compression: ZIP_STORED (no compression) or ZIP_DEFLATED (requires zlib).
+    compression: ZIP_STORED (no compression), ZIP_DEFLATED (requires zlib) or
+                 ZIP_BZIP2 (requires bz2).
     allowZip64: if True ZipFile will create files with ZIP64 extensions when
                 needed, otherwise it will raise an exception when this would
                 be necessary.
@@ -681,14 +777,7 @@ class ZipFile:
         if mode not in ("r", "w", "a"):
             raise RuntimeError('ZipFile() requires mode "r", "w", or "a"')
 
-        if compression == ZIP_STORED:
+        _check_compression(compression)
-            pass
-        elif compression == ZIP_DEFLATED:
-            if not zlib:
-                raise RuntimeError(
-                      "Compression requires the (missing) zlib module")
-        else:
-            raise RuntimeError("That compression method is not supported")
 
         self._allowZip64 = allowZip64
         self._didModify = False
@@ -1067,11 +1156,7 @@ class ZipFile:
         if not self.fp:
             raise RuntimeError(
                   "Attempt to write ZIP archive that was already closed")
-        if zinfo.compress_type == ZIP_DEFLATED and not zlib:
+        _check_compression(zinfo.compress_type)
-            raise RuntimeError(
-                  "Compression requires the (missing) zlib module")
-        if zinfo.compress_type not in (ZIP_STORED, ZIP_DEFLATED):
-            raise RuntimeError("That compression method is not supported")
         if zinfo.file_size > ZIP64_LIMIT:
             if not self._allowZip64:
                 raise LargeZipFile("Filesize would require ZIP64 extensions")
@@ -1122,17 +1207,13 @@ class ZipFile:
             self.fp.write(zinfo.FileHeader())
             return
 
+        cmpr = _get_compressor(zinfo.compress_type)
         with open(filename, "rb") as fp:
             # Must overwrite CRC and sizes with correct data later
             zinfo.CRC = CRC = 0
             zinfo.compress_size = compress_size = 0
             zinfo.file_size = file_size = 0
             self.fp.write(zinfo.FileHeader())
-            if zinfo.compress_type == ZIP_DEFLATED:
-                cmpr = zlib.compressobj(zlib.Z_DEFAULT_COMPRESSION,
-                     zlib.DEFLATED, -15)
-            else:
-                cmpr = None
             while 1:
                 buf = fp.read(1024 * 8)
                 if not buf:
@@ -1189,9 +1270,8 @@ class ZipFile:
         self._writecheck(zinfo)
         self._didModify = True
         zinfo.CRC = crc32(data) & 0xffffffff       # CRC-32 checksum
-        if zinfo.compress_type == ZIP_DEFLATED:
+        co = _get_compressor(zinfo.compress_type)
-            co = zlib.compressobj(zlib.Z_DEFAULT_COMPRESSION,
+        if co:
-                 zlib.DEFLATED, -15)
             data = co.compress(data) + co.flush()
             zinfo.compress_size = len(data)    # Compressed size
         else:
@@ -1243,18 +1323,20 @@ class ZipFile:
                     header_offset = zinfo.header_offset
 
                 extra_data = zinfo.extra
+                min_version = 0
                 if extra:
                     # Append a ZIP64 field to the extra's
                     extra_data = struct.pack(
                             '<HH' + 'Q'*len(extra),
                             1, 8*len(extra), *extra) + extra_data
 
-                    extract_version = max(45, zinfo.extract_version)
+                    min_version = ZIP64_VERSION
-                    create_version = max(45, zinfo.create_version)
-                else:
-                    extract_version = zinfo.extract_version
-                    create_version = zinfo.create_version
 
+                if zinfo.compress_type == ZIP_BZIP2:
+                    min_version = max(BZIP2_VERSION, min_version)
+
+                extract_version = max(min_version, zinfo.extract_version)
+                create_version = max(min_version, zinfo.create_version)
                 try:
                     filename, flag_bits = zinfo._encodeFilenameFlags()
                     centdir = struct.pack(structCentralDir,

Misc/NEWS

@@ -87,6 +87,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #14371: Support bzip2 in zipfile module.
+  Patch by Serhiy Storchaka.
+
 - Issue #13183: Fix pdb skipping frames after hitting a breakpoint and running
   step.  Patch by Xavier de Gaye.