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
remove() {
hg rm $@
hg st
# do not use ls -R, which recurses in .hg subdirs on Mac OS X 10.5
find . -name .hg -prune -o -type f -print | sort
hg up -C
}
hg init a
cd a
echo a > foo
echo % file not managed
remove foo
hg add foo
hg commit -m1
# the table cases
echo % 00 state added, options none
echo b > bar
hg add bar
remove bar
echo % 01 state clean, options none
remove foo
echo % 02 state modified, options none
echo b >> foo
remove foo
echo % 03 state missing, options none
rm foo
remove foo
echo % 10 state added, options -f
echo b > bar
hg add bar
remove -f bar
rm bar
echo % 11 state clean, options -f
remove -f foo
echo % 12 state modified, options -f
echo b >> foo
remove -f foo
echo % 13 state missing, options -f
rm foo
remove -f foo
echo % 20 state added, options -A
echo b > bar
hg add bar
remove -A bar
echo % 21 state clean, options -A
remove -A foo
echo % 22 state modified, options -A
echo b >> foo
remove -A foo
echo % 23 state missing, options -A
rm foo
remove -A foo
echo % 30 state added, options -Af
echo b > bar
hg add bar
remove -Af bar
rm bar
echo % 31 state clean, options -Af
remove -Af foo
echo % 32 state modified, options -Af
echo b >> foo
remove -Af foo
echo % 33 state missing, options -Af
rm foo
remove -Af foo
# test some directory stuff
mkdir test
echo a > test/foo
echo b > test/bar
hg ci -Am2
echo % dir, options none
rm test/bar
remove test
echo % dir, options -f
rm test/bar
remove -f test
echo % dir, options -A
rm test/bar
remove -A test
echo % dir, options -Af
rm test/bar
remove -Af test
echo 'test remove dropping empty trees (issue1861)'
mkdir -p issue1861/b/c
echo x > issue1861/x
echo y > issue1861/b/c/y
hg ci -Am add
hg rm issue1861/b
hg ci -m remove
ls issue1861