D4747: revlog: add method for obtaining storage info (API)

[indygreg (Gregory Szorc)]

This revision was automatically updated to reflect the committed changes.
Closed by commit rHG14e500b58263: revlog: add method for obtaining storage info (API) (authored by indygreg, committed by ).

CHANGED PRIOR TO COMMIT
  https://phab.mercurial-scm.org/D4747?vs=11402&id=11415#toc

REPOSITORY
  rHG Mercurial

CHANGES SINCE LAST UPDATE
  https://phab.mercurial-scm.org/D4747?vs=11402&id=11415

REVISION DETAIL
  https://phab.mercurial-scm.org/D4747

AFFECTED FILES
  mercurial/filelog.py
  mercurial/manifest.py
  mercurial/repository.py
  mercurial/revlog.py
  mercurial/testing/storage.py

CHANGE DETAILS

diff --git a/mercurial/testing/storage.py b/mercurial/testing/storage.py
--- a/mercurial/testing/storage.py
+++ b/mercurial/testing/storage.py
@@ -388,6 +388,10 @@
     def testempty(self):
         f = self._makefilefn()
 
+        self.assertEqual(f.storageinfo(), {})
+        self.assertEqual(f.storageinfo(revisionscount=True, trackedsize=True),
+                         {'revisionscount': 0, 'trackedsize': 0})
+
         self.assertEqual(f.rawsize(nullrev), 0)
 
         for i in range(-5, 5):
@@ -466,6 +470,10 @@
         with self._maketransactionfn() as tr:
             node = f.add(fulltext, None, tr, 0, nullid, nullid)
 
+        self.assertEqual(f.storageinfo(), {})
+        self.assertEqual(f.storageinfo(revisionscount=True, trackedsize=True),
+                         {'revisionscount': 1, 'trackedsize': len(fulltext)})
+
         self.assertEqual(f.rawsize(0), len(fulltext))
 
         with self.assertRaises(IndexError):
@@ -553,6 +561,14 @@
             node1 = f.add(fulltext1, None, tr, 1, node0, nullid)
             node2 = f.add(fulltext2, None, tr, 3, node1, nullid)
 
+        self.assertEqual(f.storageinfo(), {})
+        self.assertEqual(
+            f.storageinfo(revisionscount=True, trackedsize=True),
+            {
+                'revisionscount': 3,
+                'trackedsize': len(fulltext0) + len(fulltext1) + len(fulltext2),
+            })
+
         self.assertEqual(f.rawsize(0), len(fulltext0))
         self.assertEqual(f.rawsize(1), len(fulltext1))
         self.assertEqual(f.rawsize(2), len(fulltext2))
diff --git a/mercurial/revlog.py b/mercurial/revlog.py
--- a/mercurial/revlog.py
+++ b/mercurial/revlog.py
@@ -2643,3 +2643,28 @@
             yield revlogproblem(
                 warning=_("warning: '%s' uses revlog format %d; expected %d") %
                         (self.indexfile, version, state['expectedversion']))
+
+    def storageinfo(self, exclusivefiles=False, sharedfiles=False,
+                    revisionscount=False, trackedsize=False,
+                    storedsize=False):
+        d = {}
+
+        if exclusivefiles:
+            d['exclusivefiles'] = [(self.opener, self.indexfile)]
+            if not self._inline:
+                d['exclusivefiles'].append((self.opener, self.datafile))
+
+        if sharedfiles:
+            d['sharedfiles'] = []
+
+        if revisionscount:
+            d['revisionscount'] = len(self)
+
+        if trackedsize:
+            d['trackedsize'] = sum(map(self.rawsize, iter(self)))
+
+        if storedsize:
+            d['storedsize'] = sum(self.opener.stat(path).st_size
+                                  for path in self.files())
+
+        return d
diff --git a/mercurial/repository.py b/mercurial/repository.py
--- a/mercurial/repository.py
+++ b/mercurial/repository.py
@@ -748,6 +748,41 @@
         be a better API for that.
         """
 
+    def storageinfo(exclusivefiles=False, sharedfiles=False,
+                    revisionscount=False, trackedsize=False,
+                    storedsize=False):
+        """Obtain information about storage for this file's data.
+
+        Returns a dict describing storage for this tracked path. The keys
+        in the dict map to arguments of the same. The arguments are bools
+        indicating whether to calculate and obtain that data.
+
+        exclusivefiles
+           Iterable of (vfs, path) describing files that are exclusively
+           used to back storage for this tracked path.
+
+        sharedfiles
+           Iterable of (vfs, path) describing files that are used to back
+           storage for this tracked path. Those files may also provide storage
+           for other stored entities.
+
+        revisionscount
+           Number of revisions available for retrieval.
+
+        trackedsize
+           Total size in bytes of all tracked revisions. This is a sum of the
+           length of the fulltext of all revisions.
+
+        storedsize
+           Total size in bytes used to store data for all tracked revisions.
+           This is commonly less than ``trackedsize`` due to internal usage
+           of deltas rather than fulltext revisions.
+
+        Not all storage backends may support all queries are have a reasonable
+        value to use. In that case, the value should be set to ``None`` and
+        callers are expected to handle this special value.
+        """
+
     def verifyintegrity(state):
         """Verifies the integrity of file storage.
 
@@ -1199,6 +1234,15 @@
         manifest including files that did not match.
         """
 
+    def storageinfo(exclusivefiles=False, sharedfiles=False,
+                    revisionscount=False, trackedsize=False,
+                    storedsize=False):
+        """Obtain information about storage for this manifest's data.
+
+        See ``ifilestorage.storageinfo()`` for a description of this method.
+        This one behaves the same way, except for manifest data.
+        """
+
 class imanifestlog(interfaceutil.Interface):
     """Interface representing a collection of manifest snapshots.
 
diff --git a/mercurial/manifest.py b/mercurial/manifest.py
--- a/mercurial/manifest.py
+++ b/mercurial/manifest.py
@@ -1592,6 +1592,14 @@
 
         return self._revlog.clone(tr, destrevlog._revlog, **kwargs)
 
+    def storageinfo(self, exclusivefiles=False, sharedfiles=False,
+                    revisionscount=False, trackedsize=False,
+                    storedsize=False):
+        return self._revlog.storageinfo(
+            exclusivefiles=exclusivefiles, sharedfiles=sharedfiles,
+            revisionscount=revisionscount, trackedsize=trackedsize,
+            storedsize=storedsize)
+
     @property
     def indexfile(self):
         return self._revlog.indexfile
diff --git a/mercurial/filelog.py b/mercurial/filelog.py
--- a/mercurial/filelog.py
+++ b/mercurial/filelog.py
@@ -187,6 +187,14 @@
     def verifyintegrity(self, state):
         return self._revlog.verifyintegrity(state)
 
+    def storageinfo(self, exclusivefiles=False, sharedfiles=False,
+                    revisionscount=False, trackedsize=False,
+                    storedsize=False):
+        return self._revlog.storageinfo(
+            exclusivefiles=exclusivefiles, sharedfiles=sharedfiles,
+            revisionscount=revisionscount, trackedsize=trackedsize,
+            storedsize=storedsize)
+
     # TODO these aren't part of the interface and aren't internal methods.
     # Callers should be fixed to not use them.
 



To: indygreg, #hg-reviewers, pulkit
Cc: mercurial-devel