changeset 38954:5a7df82de142

includematcher: separate "parents" from "dirs"

A future patch will make use of this separation so that we can make more
intelligent decisions about what to investigate/load when the matcher is in use.

Currently, even with this patch, we typically use the 'visitdir' call to identify if
we can skip some directory, something along the lines of:

    for f in all_items:
        if match.visitdir(f):
           <do stuff>

This can be slower than we'd like if there are a lot of items; it requires N
calls to match.visitdir in the best case.  Commonly, especially with 'narrow',
we have a situation where we do some work for the directory, possibly just
loading it from disk (when using treemanifests) and then check if we should be
interacting with it at all, which can be a huge slowdown in some pathological
cases.

Differential Revision: https://phab.mercurial-scm.org/D4129

--- a/mercurial/match.py	Sun Aug 05 18:31:19 2018 -0700
+++ b/mercurial/match.py	Mon Aug 06 12:52:22 2018 -0700
@@ -445,11 +445,14 @@
         self._pats, self.matchfn = _buildmatch(kindpats, '(?:/|$)',
                                                listsubrepos, root)
         self._prefix = _prefix(kindpats)
-        roots, dirs = _rootsanddirs(kindpats)
+        roots, dirs, parents = _rootsdirsandparents(kindpats)
         # roots are directories which are recursively included.
         self._roots = set(roots)
         # dirs are directories which are non-recursively included.
         self._dirs = set(dirs)
+        # parents are directories which are non-recursively included because
+        # they are needed to get to items in _dirs or _roots.
+        self._parents = set(parents)
 
     def visitdir(self, dir):
         if self._prefix and dir in self._roots:
@@ -457,6 +460,7 @@
         return ('.' in self._roots or
                 dir in self._roots or
                 dir in self._dirs or
+                dir in self._parents or
                 any(parentdir in self._roots
                     for parentdir in util.finddirs(dir)))
 
@@ -1004,7 +1008,7 @@
     roots, dirs = _patternrootsanddirs(kindpats)
     return roots
 
-def _rootsanddirs(kindpats):
+def _rootsdirsandparents(kindpats):
     '''Returns roots and exact directories from patterns.
 
     roots are directories to match recursively, whereas exact directories should
@@ -1012,32 +1016,33 @@
     include directories that need to be implicitly considered as either, such as
     parent directories.
 
-    >>> _rootsanddirs(
+    >>> _rootsdirsandparents(
     ...     [(b'glob', b'g/h/*', b''), (b'glob', b'g/h', b''),
     ...      (b'glob', b'g*', b'')])
-    (['g/h', 'g/h', '.'], ['g', '.'])
-    >>> _rootsanddirs(
+    (['g/h', 'g/h', '.'], [], ['g', '.'])
+    >>> _rootsdirsandparents(
     ...     [(b'rootfilesin', b'g/h', b''), (b'rootfilesin', b'', b'')])
-    ([], ['g/h', '.', 'g', '.'])
-    >>> _rootsanddirs(
+    ([], ['g/h', '.'], ['g', '.'])
+    >>> _rootsdirsandparents(
     ...     [(b'relpath', b'r', b''), (b'path', b'p/p', b''),
     ...      (b'path', b'', b'')])
-    (['r', 'p/p', '.'], ['p', '.'])
-    >>> _rootsanddirs(
+    (['r', 'p/p', '.'], [], ['p', '.'])
+    >>> _rootsdirsandparents(
     ...     [(b'relglob', b'rg*', b''), (b're', b're/', b''),
     ...      (b'relre', b'rr', b'')])
-    (['.', '.', '.'], ['.'])
+    (['.', '.', '.'], [], ['.'])
     '''
     r, d = _patternrootsanddirs(kindpats)
 
+    p = []
     # Append the parents as non-recursive/exact directories, since they must be
     # scanned to get to either the roots or the other exact directories.
-    d.extend(util.dirs(d))
-    d.extend(util.dirs(r))
+    p.extend(util.dirs(d))
+    p.extend(util.dirs(r))
     # util.dirs() does not include the root directory, so add it manually
-    d.append('.')
+    p.append('.')
 
-    return r, d
+    return r, d, p
 
 def _explicitfiles(kindpats):
     '''Returns the potential explicit filenames from the patterns.