Previously, the read method checked whether the current block
was fully consumed or not based on whether the buffer could be filled
with a non-zero number of bytes. This check is problematic because
zero bytes could be read if the provided buffer is empty.
We fix this case by simply checking for whether the input buffer
provided by the user was empty or not. If empty, we assume that
we could not read any bytes because the buffer was too small,
rather than indicating that the current block was fully exhausted.
This check causes bzip2.Reader to be unable to make progress
on the next block unless a non-empty buffer is provided.
However, that is an entirely reasonable expectation since a
non-empty buffer needs to be provided eventually anyways to
read the actual contents of subsequent blocks.
Fixes #22028
Change-Id: I2bb1b2d54e78567baf2bf7b490a272c0853d7bfe
Reviewed-on: https://go-review.googlesource.com/66110
Reviewed-by: Ian Lance Taylor <iant@golang.org>
func (bz2 *reader) read(buf []byte) (int, error) {
for {
n := bz2.readFromBlock(buf)
- if n > 0 {
+ if n > 0 || len(buf) == 0 {
bz2.blockCRC = updateCRC(bz2.blockCRC, buf[:n])
return n, nil
}
}
}
+func TestZeroRead(t *testing.T) {
+ b := mustDecodeHex("425a6839314159265359b5aa5098000000600040000004200021008283177245385090b5aa5098")
+ r := NewReader(bytes.NewReader(b))
+ if n, err := r.Read(nil); n != 0 || err != nil {
+ t.Errorf("Read(nil) = (%d, %v), want (0, nil)", n, err)
+ }
+}
+
var (
digits = mustLoadFile("testdata/e.txt.bz2")
twain = mustLoadFile("testdata/Mark.Twain-Tom.Sawyer.txt.bz2")