match: optimize visitdir() for patterns matching only root directory
Because _rootsanddirs() returns a list of directories to visit
recursively and a list of directories to visit non-recursively. For
patterns such as 'rootfilesin:foo/bar', we clearly need to visit the
directory foo/bar, but we also need to visit its parents. The method
therefore uses util.dirs() to find the parent directories of
'foo/bar'. That method does not include the root directory, but since
we obviously need to visit the root directory, we always added '.' to
the set of directories to visit non-recursively.
The visitdir() method had special handling to consider set(['.']) to
mean that no includes had been specified and would thus visit all
directories. However, when the pattern is 'rootfilesin:.', set(['.'])
is actually the real set of directories to visit and the special
handling of that set meant that all directories got visited instead of
just the root directory.
The fix is simple: add '.' to the set of parent directories in
_rootsanddirs() and stop treating set(['.']) specially. This makes
hg files -r . -I rootfilesin:.
in a treemanifest version of the Firefox repo go from 1.5s to 0.26s on
warm disk (and a *much* bigger improvement on cold disk).
Note that the -I is necessary for no good reason. We just haven't
optimized visitdir() for regular (non-include, non-exclude) patterns
yet.
from __future__ import absolute_import, print_function
from mercurial import (
util,
)
def printifpresent(d, xs, name='d'):
for x in xs:
present = x in d
print("'%s' in %s: %s" % (x, name, present))
if present:
print("%s['%s']: %s" % (name, x, d[x]))
def test_lrucachedict():
d = util.lrucachedict(4)
d['a'] = 'va'
d['b'] = 'vb'
d['c'] = 'vc'
d['d'] = 'vd'
# all of these should be present
printifpresent(d, ['a', 'b', 'c', 'd'])
# 'a' should be dropped because it was least recently used
d['e'] = 've'
printifpresent(d, ['a', 'b', 'c', 'd', 'e'])
assert d.get('a') is None
assert d.get('e') == 've'
# touch entries in some order (get or set).
d['e']
d['c'] = 'vc2'
d['d']
d['b'] = 'vb2'
# 'e' should be dropped now
d['f'] = 'vf'
printifpresent(d, ['b', 'c', 'd', 'e', 'f'])
d.clear()
printifpresent(d, ['b', 'c', 'd', 'e', 'f'])
# Now test dicts that aren't full.
d = util.lrucachedict(4)
d['a'] = 1
d['b'] = 2
d['a']
d['b']
printifpresent(d, ['a', 'b'])
# test copy method
d = util.lrucachedict(4)
d['a'] = 'va3'
d['b'] = 'vb3'
d['c'] = 'vc3'
d['d'] = 'vd3'
dc = d.copy()
# all of these should be present
print("\nAll of these should be present:")
printifpresent(dc, ['a', 'b', 'c', 'd'], 'dc')
# 'a' should be dropped because it was least recently used
print("\nAll of these except 'a' should be present:")
dc['e'] = 've3'
printifpresent(dc, ['a', 'b', 'c', 'd', 'e'], 'dc')
# contents and order of original dict should remain unchanged
print("\nThese should be in reverse alphabetical order and read 'v?3':")
dc['b'] = 'vb3_new'
for k in list(iter(d)):
print("d['%s']: %s" % (k, d[k]))
if __name__ == '__main__':
test_lrucachedict()