Alex Rousskov wrote:
> algorithm should be "configurable" so that somebody can add more
> algorithms. For example, one might implement "gzip -9 < diff" to get 30%
> more...
Note: gzip -9 was one of the approaches I evaluated while selecting
encoding method of the bitdistances. It was never able to beat pure
huffman encoding. gzip in huffman-only mode came quite close, but not
all the way.
I have not tried to huffman encode or gzip cd_diff output but I would be
supriced if it proved better results for normal digests diffs.
/Henrik
Received on Tue Jul 29 2003 - 13:16:00 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:12:17 MST