bdiff: improve worst case behavior by 100x. on 5.8MB (244.000 lines) text file with similar lines, hash before this change made diff against empty file take 75 seconds. this change improves performance to 0.6 seconds. result is that clone of smallish repo (137MB) with some files like this takes 1 minute instead of 10 minutes. common case of diff is 10% slower now, probably because of worse cache locality. but diff does not affect overall performance in common case (less than 1% of runtime is in diff when it is working ok), so this tradeoff looks good.

#!/bin/sh

hg init

cat > .hg/hgrc <<EOF
[encode]
*.gz = gunzip

[decode]
*.gz = gzip

EOF

echo "this is a test" | gzip > a.gz
hg add a.gz
hg ci -m "test" -d "1000000 0"
echo %% no changes
hg status
touch a.gz

echo %% no changes
hg status

echo %% uncompressed contents in repo
hg debugdata .hg/data/a.gz.d 0

echo %% uncompress our working dir copy
gunzip < a.gz

rm a.gz
hg co

echo %% uncompress our new working dir copy
gunzip < a.gz