findrenames: Optimise "addremove -s100" by matching files by their SHA1 hashes.
We speed up 'findrenames' for the usecase when a user specifies they
want a similarity of 100% by matching files by their exact SHA1 hash
value. This reduces the number of comparisons required to find exact
matches from O(n^2) to O(n).
While it would be nice if we could just use mercurial's pre-calculated
SHA1 hash for existing files, this hash includes the file's ancestor
information making it unsuitable for our purposes. Instead, we calculate
the hash of old content from scratch.
The following benchmarks were taken on the current head of crew:
addremove 100% similarity:
rm -rf *; hg up -C; mv tests tests.new
hg --time addremove -s100 --dry-run
before: real 176.350 secs (user 128.890+0.000 sys 47.430+0.000)
after: real 2.130 secs (user 1.890+0.000 sys 0.240+0.000)
addremove 75% similarity:
rm -rf *; hg up -C; mv tests tests.new; \
for i in tests.new/*; do echo x >> $i; done
hg --time addremove -s75 --dry-run
before: real 264.560 secs (user 215.130+0.000 sys 49.410+0.000)
after: real 218.710 secs (user 172.790+0.000 sys 45.870+0.000)
#!/bin/sh
echo '[extensions]' >> $HGRCPATH
echo 'graphlog =' >> $HGRCPATH
echo 'convert =' >> $HGRCPATH
glog()
{
hg -R "$1" glog --template '{rev} "{desc}" files: {files}\n'
}
hg init source
cd source
echo a > a
echo b > b
hg ci -d '0 0' -qAm '0: add a b'
echo c > c
hg ci -d '1 0' -qAm '1: add c'
hg copy a e
echo b >> b
hg ci -d '2 0' -qAm '2: copy e from a, change b'
hg up -C 0
echo a >> a
hg ci -d '3 0' -qAm '3: change a'
hg merge
hg copy b d
hg ci -d '4 0' -qAm '4: merge 2 and 3, copy d from b'
echo a >> a
hg ci -d '5 0' -qAm '5: change a'
cd ..
echo % convert from null revision
hg convert --config convert.hg.startrev=null source empty
glog empty
echo % convert from zero revision
hg convert --config convert.hg.startrev=0 source full
glog full
echo % convert from merge parent
hg convert --config convert.hg.startrev=1 source conv1
glog conv1
cd conv1
echo % check copy preservation
hg log --follow --copies e
echo % check copy removal on missing parent
hg log --follow --copies d
hg cat -r tip a b
hg -q verify
cd ..
echo % convert from merge
hg convert --config convert.hg.startrev=4 source conv4
glog conv4
cd conv4
hg up -C
hg cat -r tip a b
hg -q verify
cd ..