Closes #19839: Fix regression in bz2 module's handling of non-bzip2 data at EOF.

Also fix an analogous bug (not a regression) in the lzma module.

Lib/bz2.py

@@ -207,8 +207,15 @@ class BZ2File(io.BufferedIOBase):
             if self._decompressor.eof:
                 # Continue to next stream.
                 self._decompressor = BZ2Decompressor()
-
-            self._buffer = self._decompressor.decompress(rawblock)
+                try:
+                    self._buffer = self._decompressor.decompress(rawblock)
+                except OSError:
+                    # Trailing data isn't a valid bzip2 stream. We're done here.
+                    self._mode = _MODE_READ_EOF
+                    self._size = self._pos
+                    return False
+            else:
+                self._buffer = self._decompressor.decompress(rawblock)
             self._buffer_offset = 0
         return True
 
@@ -496,17 +503,19 @@ def decompress(data):
 
     For incremental decompression, use a BZ2Decompressor object instead.
     """
-    if len(data) == 0:
-        return b""
-
     results = []
-    while True:
+    while data:
         decomp = BZ2Decompressor()
-        results.append(decomp.decompress(data))
+        try:
+            res = decomp.decompress(data)
+        except OSError:
+            if results:
+                break  # Leftover data is not a valid bzip2 stream; ignore it.
+            else:
+                raise  # Error on the first iteration; bail out.
+        results.append(res)
         if not decomp.eof:
             raise ValueError("Compressed data ended before the "
                              "end-of-stream marker was reached")
-        if not decomp.unused_data:
-            return b"".join(results)
-        # There is unused data left over. Proceed to next stream.
         data = decomp.unused_data
+    return b"".join(results)

Lib/lzma.py

@@ -225,11 +225,18 @@ class LZMAFile(io.BufferedIOBase):
                     raise EOFError("Compressed file ended before the "
                                    "end-of-stream marker was reached")
 
-            # Continue to next stream.
             if self._decompressor.eof:
+                # Continue to next stream.
                 self._decompressor = LZMADecompressor(**self._init_args)
-
-            self._buffer = self._decompressor.decompress(rawblock)
+                try:
+                    self._buffer = self._decompressor.decompress(rawblock)
+                except LZMAError:
+                    # Trailing data isn't a valid compressed stream; ignore it.
+                    self._mode = _MODE_READ_EOF
+                    self._size = self._pos
+                    return False
+            else:
+                self._buffer = self._decompressor.decompress(rawblock)
             self._buffer_offset = 0
         return True
 
@@ -487,11 +494,18 @@ def decompress(data, format=FORMAT_AUTO, memlimit=None, filters=None):
     results = []
     while True:
         decomp = LZMADecompressor(format, memlimit, filters)
-        results.append(decomp.decompress(data))
+        try:
+            res = decomp.decompress(data)
+        except LZMAError:
+            if results:
+                break  # Leftover data is not a valid LZMA/XZ stream; ignore it.
+            else:
+                raise  # Error on the first iteration; bail out.
+        results.append(res)
         if not decomp.eof:
             raise LZMAError("Compressed data ended before the "
                             "end-of-stream marker was reached")
-        if not decomp.unused_data:
-            return b"".join(results)
-        # There is unused data left over. Proceed to next stream.
         data = decomp.unused_data
+        if not data:
+            break
+    return b"".join(results)

Lib/test/test_bz2.py

@@ -50,6 +50,7 @@ class BaseTest(unittest.TestCase):
     TEXT = b''.join(TEXT_LINES)
     DATA = b'BZh91AY&SY.\xc8N\x18\x00\x01>_\x80\x00\x10@\x02\xff\xf0\x01\x07n\x00?\xe7\xff\xe00\x01\x99\xaa\x00\xc0\x03F\x86\x8c#&\x83F\x9a\x03\x06\xa6\xd0\xa6\x93M\x0fQ\xa7\xa8\x06\x804hh\x12$\x11\xa4i4\xf14S\xd2<Q\xb5\x0fH\xd3\xd4\xdd\xd5\x87\xbb\xf8\x94\r\x8f\xafI\x12\xe1\xc9\xf8/E\x00pu\x89\x12]\xc9\xbbDL\nQ\x0e\t1\x12\xdf\xa0\xc0\x97\xac2O9\x89\x13\x94\x0e\x1c7\x0ed\x95I\x0c\xaaJ\xa4\x18L\x10\x05#\x9c\xaf\xba\xbc/\x97\x8a#C\xc8\xe1\x8cW\xf9\xe2\xd0\xd6M\xa7\x8bXa<e\x84t\xcbL\xb3\xa7\xd9\xcd\xd1\xcb\x84.\xaf\xb3\xab\xab\xad`n}\xa0lh\tE,\x8eZ\x15\x17VH>\x88\xe5\xcd9gd6\x0b\n\xe9\x9b\xd5\x8a\x99\xf7\x08.K\x8ev\xfb\xf7xw\xbb\xdf\xa1\x92\xf1\xdd|/";\xa2\xba\x9f\xd5\xb1#A\xb6\xf6\xb3o\xc9\xc5y\\\xebO\xe7\x85\x9a\xbc\xb6f8\x952\xd5\xd7"%\x89>V,\xf7\xa6z\xe2\x9f\xa3\xdf\x11\x11"\xd6E)I\xa9\x13^\xca\xf3r\xd0\x03U\x922\xf26\xec\xb6\xed\x8b\xc3U\x13\x9d\xc5\x170\xa4\xfa^\x92\xacDF\x8a\x97\xd6\x19\xfe\xdd\xb8\xbd\x1a\x9a\x19\xa3\x80ankR\x8b\xe5\xd83]\xa9\xc6\x08\x82f\xf6\xb9"6l$\xb8j@\xc0\x8a\xb0l1..\xbak\x83ls\x15\xbc\xf4\xc1\x13\xbe\xf8E\xb8\x9d\r\xa8\x9dk\x84\xd3n\xfa\xacQ\x07\xb1%y\xaav\xb4\x08\xe0z\x1b\x16\xf5\x04\xe9\xcc\xb9\x08z\x1en7.G\xfc]\xc9\x14\xe1B@\xbb!8`'
     EMPTY_DATA = b'BZh9\x17rE8P\x90\x00\x00\x00\x00'
+    BAD_DATA = b'this is not a valid bzip2 file'
 
     def setUp(self):
         self.filename = support.TESTFN
@@ -80,9 +81,10 @@ class BaseTest(unittest.TestCase):
 class BZ2FileTest(BaseTest):
     "Test the BZ2File class."
 
-    def createTempFile(self, streams=1):
+    def createTempFile(self, streams=1, suffix=b""):
         with open(self.filename, "wb") as f:
             f.write(self.DATA * streams)
+            f.write(suffix)
 
     def testBadArgs(self):
         self.assertRaises(TypeError, BZ2File, 123.456)
@@ -98,6 +100,11 @@ class BZ2FileTest(BaseTest):
             self.assertRaises(TypeError, bz2f.read, None)
             self.assertEqual(bz2f.read(), self.TEXT)
 
+    def testReadBadFile(self):
+        self.createTempFile(streams=0, suffix=self.BAD_DATA)
+        with BZ2File(self.filename) as bz2f:
+            self.assertRaises(OSError, bz2f.read)
+
     def testReadMultiStream(self):
         self.createTempFile(streams=5)
         with BZ2File(self.filename) as bz2f:
@@ -117,6 +124,16 @@ class BZ2FileTest(BaseTest):
         finally:
             bz2._BUFFER_SIZE = buffer_size
 
+    def testReadTrailingJunk(self):
+        self.createTempFile(suffix=self.BAD_DATA)
+        with BZ2File(self.filename) as bz2f:
+            self.assertEqual(bz2f.read(), self.TEXT)
+
+    def testReadMultiStreamTrailingJunk(self):
+        self.createTempFile(streams=5, suffix=self.BAD_DATA)
+        with BZ2File(self.filename) as bz2f:
+            self.assertEqual(bz2f.read(), self.TEXT * 5)
+
     def testRead0(self):
         self.createTempFile()
         with BZ2File(self.filename) as bz2f:
@@ -714,10 +731,21 @@ class CompressDecompressTest(BaseTest):
     def testDecompressIncomplete(self):
         self.assertRaises(ValueError, bz2.decompress, self.DATA[:-10])
 
+    def testDecompressBadData(self):
+        self.assertRaises(OSError, bz2.decompress, self.BAD_DATA)
+
     def testDecompressMultiStream(self):
         text = bz2.decompress(self.DATA * 5)
         self.assertEqual(text, self.TEXT * 5)
 
+    def testDecompressTrailingJunk(self):
+        text = bz2.decompress(self.DATA + self.BAD_DATA)
+        self.assertEqual(text, self.TEXT)
+
+    def testDecompressMultiStreamTrailingJunk(self):
+        text = bz2.decompress(self.DATA * 5 + self.BAD_DATA)
+        self.assertEqual(text, self.TEXT * 5)
+
 
 class OpenTest(BaseTest):
     "Test the open function."

Lib/test/test_lzma.py

@@ -313,6 +313,8 @@ class CompressDecompressFunctionTestCase(unittest.TestCase):
                           format=lzma.FORMAT_RAW, filters=FILTERS_RAW_4)
 
     def test_decompress_bad_input(self):
+        with self.assertRaises(LZMAError):
+            lzma.decompress(COMPRESSED_BOGUS)
         with self.assertRaises(LZMAError):
             lzma.decompress(COMPRESSED_RAW_1)
         with self.assertRaises(LZMAError):
@@ -348,6 +350,16 @@ class CompressDecompressFunctionTestCase(unittest.TestCase):
         ddata = lzma.decompress(COMPRESSED_XZ + COMPRESSED_ALONE)
         self.assertEqual(ddata, INPUT * 2)
 
+    # Test robust handling of non-LZMA data following the compressed stream(s).
+
+    def test_decompress_trailing_junk(self):
+        ddata = lzma.decompress(COMPRESSED_XZ + COMPRESSED_BOGUS)
+        self.assertEqual(ddata, INPUT)
+
+    def test_decompress_multistream_trailing_junk(self):
+        ddata = lzma.decompress(COMPRESSED_XZ * 3 + COMPRESSED_BOGUS)
+        self.assertEqual(ddata, INPUT * 3)
+
 
 class TempFile:
     """Context manager - creates a file, and deletes it on __exit__."""
@@ -676,6 +688,14 @@ class FileTestCase(unittest.TestCase):
         finally:
             lzma._BUFFER_SIZE = saved_buffer_size
 
+    def test_read_trailing_junk(self):
+        with LZMAFile(BytesIO(COMPRESSED_XZ + COMPRESSED_BOGUS)) as f:
+            self.assertEqual(f.read(), INPUT)
+
+    def test_read_multistream_trailing_junk(self):
+        with LZMAFile(BytesIO(COMPRESSED_XZ * 5 + COMPRESSED_BOGUS)) as f:
+            self.assertEqual(f.read(), INPUT * 5)
+
     def test_read_from_file(self):
         with TempFile(TESTFN, COMPRESSED_XZ):
             with LZMAFile(TESTFN) as f:
@@ -719,6 +739,10 @@ class FileTestCase(unittest.TestCase):
         with LZMAFile(BytesIO(COMPRESSED_XZ)) as f:
             self.assertRaises(TypeError, f.read, None)
 
+    def test_read_bad_data(self):
+        with LZMAFile(BytesIO(COMPRESSED_BOGUS)) as f:
+            self.assertRaises(LZMAError, f.read)
+
     def test_read1(self):
         with LZMAFile(BytesIO(COMPRESSED_XZ)) as f:
             blocks = []
@@ -1232,6 +1256,8 @@ LAERTES
        Farewell.
 """
 
+COMPRESSED_BOGUS = b"this is not a valid lzma stream"
+
 COMPRESSED_XZ = (
     b"\xfd7zXZ\x00\x00\x04\xe6\xd6\xb4F\x02\x00!\x01\x16\x00\x00\x00t/\xe5\xa3"
     b"\xe0\x07\x80\x03\xdf]\x00\x05\x14\x07bX\x19\xcd\xddn\x98\x15\xe4\xb4\x9d"

Misc/NEWS

@@ -18,6 +18,9 @@ Core and Builtins
 Library
 -------
 
+- Issue #19839: Fix regression in bz2 module's handling of non-bzip2 data at
+  EOF, and analogous bug in lzma module.
+
 - Issue #19138: doctest's IGNORE_EXCEPTION_DETAIL now allows a match when
   no exception detail exists (no colon following the exception's name, or
   a colon does follow but no text follows the colon).