[PATCH 8 of 9] verify: check for orphaned dirlogs

[Martin von Zweigbergk]

# HG changeset patch
# User Martin von Zweigbergk <martinvonz at google.com>
# Date 1454542515 28800
#      Wed Feb 03 15:35:15 2016 -0800
# Node ID 9d77de5a51f6baeb6388ae4ddd064a3c130d5758
# Parent  346182e9ee70ecfdd387630eb209f85a73f60996
verify: check for orphaned dirlogs

We already report orphaned filelogs, i.e. revlogs for files that are
not mentioned in any manifest. This change adds checking for orphaned
dirlogs, i.e. revlogs that are not mentioned in any parent-directory
dirlog.

Note that, for fncachestore, only files mentioned in the fncache are
considered, there's not check for files in .hg/store/meta that are not
mentioned in the fncache. This is no different from the current
situation for filelogs.

diff --git a/mercurial/verify.py b/mercurial/verify.py
--- a/mercurial/verify.py
+++ b/mercurial/verify.py
@@ -197,7 +197,7 @@
         ui.progress(_('checking'), None)
         return mflinkrevs, filelinkrevs

-    def _verifymanifest(self, mflinkrevs, dir=""):
+    def _verifymanifest(self, mflinkrevs, dir="", storefiles=None):
         repo = self.repo
         ui = self.ui
         mf = self.repo.manifest.dirlog(dir)
@@ -211,6 +211,8 @@
         label = "manifest"
         if dir:
             label = dir
+            revlogfiles = mf.files()
+            storefiles.difference_update(revlogfiles)
         if self.refersmf:
             # Do not check manifest if there are only changelog entries with
             # null manifests.
@@ -260,11 +262,23 @@

         if not dir and subdirnodes:
             self.ui.status(_("checking directory manifests\n"))
+            storefiles = set()
+            revlogv1 = self.revlogv1
+            for f, f2, size in repo.store.datafiles():
+                if not f:
+                    self.err(None, _("cannot decode filename '%s'") % f2)
+                elif (size > 0 or not revlogv1) and f.startswith('meta/'):
+                    storefiles.add(_normpath(f))
+
         for subdir, linkrevs in subdirnodes.iteritems():
-            subdirfilenodes = self._verifymanifest(linkrevs, subdir)
+            subdirfilenodes = self._verifymanifest(linkrevs, subdir,
storefiles)
             for f, onefilenodes in subdirfilenodes.iteritems():
                 filenodes.setdefault(f, {}).update(onefilenodes)

+        if not dir and subdirnodes:
+            for f in sorted(storefiles):
+                self.warn(_("warning: orphan revlog '%s'") % f)
+
         return filenodes

     def _crosscheckfiles(self, filelinkrevs, filenodes):
@@ -402,7 +416,7 @@
                              short(node), f)
         ui.progress(_('checking'), None)

-        for f in storefiles:
+        for f in sorted(storefiles):
             self.warn(_("warning: orphan revlog '%s'") % f)

         return len(files), revisions
diff --git a/tests/test-treemanifest.t b/tests/test-treemanifest.t
--- a/tests/test-treemanifest.t
+++ b/tests/test-treemanifest.t
@@ -512,6 +512,12 @@
    b/@0: parent-directory manifest refers to unknown revision 67688a370455
    b/@1: parent-directory manifest refers to unknown revision f38e85d334c5
    b/@2: parent-directory manifest refers to unknown revision 99c9792fd4b0
+  warning: orphan revlog 'meta/b/bar/00manifest.i'
+  warning: orphan revlog 'meta/b/bar/orange/00manifest.i'
+  warning: orphan revlog 'meta/b/bar/orange/fly/00manifest.i'
+  warning: orphan revlog 'meta/b/foo/00manifest.i'
+  warning: orphan revlog 'meta/b/foo/apple/00manifest.i'
+  warning: orphan revlog 'meta/b/foo/apple/bees/00manifest.i'
   crosschecking files in changesets and manifests
    b/bar/fruits.txt at 0: in changeset but not in manifest
    b/bar/orange/fly/gnat.py at 0: in changeset but not in manifest
@@ -519,6 +525,7 @@
    b/foo/apple/bees/flower.py at 0: in changeset but not in manifest
   checking files
   8 files, 3 changesets, 10 total revisions
+  6 warnings encountered!
   8 integrity errors encountered!
   (first damaged changeset appears to be 0)
   [1]