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 >> $i; done
hg --time addremove -s75 --dry-run
before: real 264.560 secs (user 215.130+0.000 sys 49.410+0.000)
after: real 218.710 secs (user 172.790+0.000 sys 45.870+0.000)
#!/bin/sh
"$TESTDIR/hghave" no-outer-repo || exit 80
hg init a
cd a
echo a > a
hg ci -A -d'1 0' -m a
cd ..
hg init b
cd b
echo b > b
hg ci -A -d'1 0' -m b
cd ..
hg clone a c
cd c
hg pull -f ../b
hg merge
cd ..
echo %% -R/--repository
hg -R a tip
hg --repository b tip
echo %% implicit -R
hg ann a/a
hg ann a/a a/a
hg ann a/a b/b
hg -R b ann a/a
hg log
echo %% abbrev of long option
hg --repo c tip
echo "%% earlygetopt with duplicate options (36d23de02da1)"
hg --cwd a --cwd b --cwd c tip
hg --repo c --repository b -R a tip
echo "%% earlygetopt short option without following space"
hg -q -Rb tip
echo "%% earlygetopt with illegal abbreviations"
hg --confi "foo.bar=baz"
hg --cw a tip
hg --rep a tip
hg --repositor a tip
hg -qR a tip
hg -qRa tip
echo %% --cwd
hg --cwd a parents
echo %% -y/--noninteractive - just be sure it is parsed
hg --cwd a tip -q --noninteractive
hg --cwd a tip -q -y
echo %% -q/--quiet
hg -R a -q tip
hg -R b -q tip
hg -R c --quiet parents
echo %% -v/--verbose
hg --cwd c head -v
hg --cwd b tip --verbose
echo %% --config
hg --cwd c --config paths.quuxfoo=bar paths | grep quuxfoo > /dev/null && echo quuxfoo
hg --cwd c --config '' tip -q
hg --cwd c --config a.b tip -q
hg --cwd c --config a tip -q
hg --cwd c --config a.= tip -q
hg --cwd c --config .b= tip -q
echo %% --debug
hg --cwd c log --debug
echo %% --traceback
hg --cwd c --config x --traceback tip 2>&1 | grep -i 'traceback'
echo %% --time
hg --cwd a --time tip 2>&1 | grep '^Time:' | sed 's/[0-9][0-9]*/x/g'
echo %% --version
hg --version -q | sed 's/version [^)]*/version xxx/'
echo %% -h/--help
hg -h
hg --help
echo %% not tested: --debugger