#15546: Fix BZ2File.read1()'s handling of pathological input data.

Lib/bz2.py

@@ -174,6 +174,9 @@ class BZ2File(io.BufferedIOBase):
 
     # Fill the readahead buffer if it is empty. Returns False on EOF.
     def _fill_buffer(self):
+        # Depending on the input data, our call to the decompressor may not
+        # return any data. In this case, try again after reading another block.
+        while True:
             if self._buffer:
                 return True
 
@@ -196,7 +199,6 @@ class BZ2File(io.BufferedIOBase):
                 self._decompressor = BZ2Decompressor()
 
             self._buffer = self._decompressor.decompress(rawblock)
-        return True
 
     # Read data until EOF.
     # If return_data is false, consume the data without returning it.
@@ -256,11 +258,14 @@ class BZ2File(io.BufferedIOBase):
                 return self._read_block(size)
 
     def read1(self, size=-1):
-        """Read up to size uncompressed bytes with at most one read
-        from the underlying stream.
+        """Read up to size uncompressed bytes, while trying to avoid
+        making multiple reads from the underlying stream.
 
         Returns b'' if the file is at EOF.
         """
+        # Usually, read1() calls _fp.read() at most once. However, sometimes
+        # this does not give enough data for the decompressor to make progress.
+        # In this case we make multiple reads, to avoid returning b"".
         with self._lock:
             self._check_can_read()
             if (size == 0 or self._mode == _MODE_READ_EOF or