rust-matchers: use the `regex` crate
Instead of falling back to Python when a code path with "ignore" functionality
is reached and `Re2` is not installed, the default compilation (i.e. without
the `with-re2` feature) will use the `regex` crate for all regular expressions
business.
As with the introduction of `Re2` in a previous series, this yields a big
performance boost compared to the Python + C code in `status`, `diff`, `commit`,
`update`, and maybe others.
For now `Re2` looks to be faster at compiling the DFA (1.5ms vs 5ms for
Netbeans' `.hgignore`) and a bit faster in actual use: (123ms vs 137ms for
the parallel traversal of Netbeans' clean repo). I am in talks with the author
of `regex` to see whether that performance difference is a bug, a "won't fix",
or a tuning issue.
The `regex` crate is already one of our dependencies and using this code does
not require any additional work from the end-user than to use the Rust
extensions.
Differential Revision: https://phab.mercurial-scm.org/D8323
from __future__ import absolute_import, print_function
import os
from mercurial import (
hg,
scmutil,
ui as uimod,
util,
)
chdir = os.chdir
mkdir = os.mkdir
pjoin = os.path.join
walkrepos = scmutil.walkrepos
checklink = util.checklink
u = uimod.ui.load()
sym = checklink(b'.')
hg.repository(u, b'top1', create=1)
mkdir(b'subdir')
chdir(b'subdir')
hg.repository(u, b'sub1', create=1)
mkdir(b'subsubdir')
chdir(b'subsubdir')
hg.repository(u, b'subsub1', create=1)
chdir(os.path.pardir)
if sym:
os.symlink(os.path.pardir, b'circle')
os.symlink(pjoin(b'subsubdir', b'subsub1'), b'subsub1')
def runtest():
reposet = frozenset(walkrepos(b'.', followsym=True))
if sym and (len(reposet) != 3):
print("reposet = %r" % (reposet,))
print(
(
"Found %d repositories when I should have found 3"
% (len(reposet),)
)
)
if (not sym) and (len(reposet) != 2):
print("reposet = %r" % (reposet,))
print(
(
"Found %d repositories when I should have found 2"
% (len(reposet),)
)
)
sub1set = frozenset(
(pjoin(b'.', b'sub1'), pjoin(b'.', b'circle', b'subdir', b'sub1'))
)
if len(sub1set & reposet) != 1:
print("sub1set = %r" % (sub1set,))
print("reposet = %r" % (reposet,))
print("sub1set and reposet should have exactly one path in common.")
sub2set = frozenset(
(pjoin(b'.', b'subsub1'), pjoin(b'.', b'subsubdir', b'subsub1'))
)
if len(sub2set & reposet) != 1:
print("sub2set = %r" % (sub2set,))
print("reposet = %r" % (reposet,))
print("sub2set and reposet should have exactly one path in common.")
sub3 = pjoin(b'.', b'circle', b'top1')
if sym and sub3 not in reposet:
print("reposet = %r" % (reposet,))
print("Symbolic links are supported and %s is not in reposet" % (sub3,))
runtest()
if sym:
# Simulate not having symlinks.
del os.path.samestat
sym = False
runtest()