diff mercurial/match.py @ 39261:c9a3f7f5c023

match: make exactmatcher.visitchildrenset return file children as well

Previously, if we had an exactmatcher like ['foo.txt', 'a/bar.txt', 'a/b/c/baz.txt'], we'd
get back the following data:
  '.': {'a'}
  'a': {'b'}
  'a/b': {'c'}
  'a/b/c': 'this'
  'a/b/c/d': set()

This was incorrect, since visitchildrenset explicitly says not to pay attention
to 'foo.txt' and 'a/bar.txt' by not returning them or 'this'. Given the near
impossibility of making visitchildrenset reliabbly produce only subdirectories,
a previous commit has made it documented and expected that visitchildrenset can
return a set containing both files and subdirectories to visit, instead of
implying/requiring that visitchildrenset() return 'this' if there are files to
visit. This makes the code for exactmatcher match this clarified documentation.

Differential Revision: https://phab.mercurial-scm.org/D4365

--- a/mercurial/match.py	Thu Aug 23 18:04:15 2018 -0700
+++ b/mercurial/match.py	Fri Aug 24 10:19:31 2018 -0700
@@ -587,23 +587,24 @@
         return dir in self._dirs
 
     def visitchildrenset(self, dir):
-        if dir in self._dirs:
-            candidates = self._dirs - {'.'}
-            if dir != '.':
-                d = dir + '/'
-                candidates = set(c[len(d):] for c in candidates if
-                                 c.startswith(d))
-            # self._dirs includes all of the directories, recursively, so if
-            # we're attempting to match foo/bar/baz.txt, it'll have '.', 'foo',
-            # 'foo/bar' in it. Thus we can safely ignore a candidate that has a
-            # '/' in it, indicating a it's for a subdir-of-a-subdir; the
-            # immediate subdir will be in there without a slash.
-            ret = set(c for c in candidates if '/' not in c)
-            # We need to emit 'this' for foo/bar, not set(), not {'baz.txt'}.
-            if not ret:
-                return 'this'
-            return ret
-        return set()
+        if not self._fileset or dir not in self._dirs:
+            return set()
+
+        candidates = self._fileset | self._dirs - {'.'}
+        if dir != '.':
+            d = dir + '/'
+            candidates = set(c[len(d):] for c in candidates if
+                             c.startswith(d))
+        # self._dirs includes all of the directories, recursively, so if
+        # we're attempting to match foo/bar/baz.txt, it'll have '.', 'foo',
+        # 'foo/bar' in it. Thus we can safely ignore a candidate that has a
+        # '/' in it, indicating a it's for a subdir-of-a-subdir; the
+        # immediate subdir will be in there without a slash.
+        ret = {c for c in candidates if '/' not in c}
+        # We really do not expect ret to be empty, since that would imply that
+        # there's something in _dirs that didn't have a file in _fileset.
+        assert ret
+        return ret
 
     def isexact(self):
         return True