match: make subinclude construction lazy
The matcher subinclude functionality allows us to have .hgignore files that
include subdirectory hgignore files. Today it parses the entire repo at once,
even if we only need to test a file in one subdirectory. This patch makes the
subinclude tree creation lazy, which speeds up matcher creation significantly in
large repos with very large trees of ignore patterns.
--- a/mercurial/match.py Wed May 03 09:09:44 2017 -0700
+++ b/mercurial/match.py Wed May 03 10:30:57 2017 -0700
@@ -52,7 +52,7 @@
return fset, other
def _expandsubinclude(kindpats, root):
- '''Returns the list of subinclude matchers and the kindpats without the
+ '''Returns the list of subinclude matcher args and the kindpats without the
subincludes in it.'''
relmatchers = []
other = []
@@ -64,12 +64,12 @@
path = pathutil.join(sourceroot, pat)
newroot = pathutil.dirname(path)
- relmatcher = match(newroot, '', [], ['include:%s' % path])
+ matcherargs = (newroot, '', [], ['include:%s' % path])
prefix = pathutil.canonpath(root, root, newroot)
if prefix:
prefix += '/'
- relmatchers.append((prefix, relmatcher))
+ relmatchers.append((prefix, matcherargs))
else:
other.append((kind, pat, source))
@@ -584,10 +584,17 @@
subincludes, kindpats = _expandsubinclude(kindpats, root)
if subincludes:
+ submatchers = {}
def matchsubinclude(f):
- for prefix, mf in subincludes:
- if f.startswith(prefix) and mf(f[len(prefix):]):
- return True
+ for prefix, matcherargs in subincludes:
+ if f.startswith(prefix):
+ mf = submatchers.get(prefix)
+ if mf is None:
+ mf = match(*matcherargs)
+ submatchers[prefix] = mf
+
+ if mf(f[len(prefix):]):
+ return True
return False
matchfuncs.append(matchsubinclude)