context: get filesadded() and filesremoved() from changeset if configured
authorMartin von Zweigbergk <martinvonz@google.com>
Tue, 14 May 2019 22:20:10 -0700
changeset 42407 602469a91550
parent 42406 f385ba70e4af
child 42408 4e4fa3a95406
context: get filesadded() and filesremoved() from changeset if configured This adds the read side for getting the sets of added and removed files from the changeset extras. I timed this command on the hg repo: hg log -T '{rev}\n {files}\n %:{file_mods}\n +{file_adds}\n -{file_dels}\n' It took 1m21s before and 6.4s after. I also used that command to check that the result didn't change compared to calculating the values from the manifests on the fly (it didn't change). In the mozilla-unified repo, the same command run on FIREFOX_BETA_58_END::FIREFOX_BETA_59_END went from 29s to 0.67s. Differential Revision: https://phab.mercurial-scm.org/D6417
mercurial/changelog.py
mercurial/context.py
--- a/mercurial/changelog.py	Tue May 14 22:19:51 2019 -0700
+++ b/mercurial/changelog.py	Tue May 14 22:20:10 2019 -0700
@@ -107,6 +107,20 @@
             indices.append('%d' % i)
     return '\0'.join(indices)
 
+def decodefileindices(files, data):
+    try:
+        subset = []
+        for strindex in data.split('\0'):
+            i = int(strindex)
+            if i < 0 or i >= len(files):
+                return None
+            subset.append(files[i])
+        return subset
+    except (ValueError, IndexError):
+        # Perhaps someone had chosen the same key name (e.g. "added") and
+        # used different syntax for the value.
+        return None
+
 def stripdesc(desc):
     """strip trailing whitespace and leading and trailing empty lines"""
     return '\n'.join([l.rstrip() for l in desc.splitlines()]).strip('\n')
@@ -202,6 +216,8 @@
     user = attr.ib(default='')
     date = attr.ib(default=(0, 0))
     files = attr.ib(default=attr.Factory(list))
+    filesadded = attr.ib(default=None)
+    filesremoved = attr.ib(default=None)
     p1copies = attr.ib(default=None)
     p2copies = attr.ib(default=None)
     description = attr.ib(default='')
@@ -308,6 +324,16 @@
         return self._text[off[2] + 1:off[3]].split('\n')
 
     @property
+    def filesadded(self):
+        rawindices = self.extra.get('filesadded')
+        return rawindices and decodefileindices(self.files, rawindices)
+
+    @property
+    def filesremoved(self):
+        rawindices = self.extra.get('filesremoved')
+        return rawindices and decodefileindices(self.files, rawindices)
+
+    @property
     def p1copies(self):
         rawcopies = self.extra.get('p1copies')
         return rawcopies and decodecopies(rawcopies)
--- a/mercurial/context.py	Tue May 14 22:19:51 2019 -0700
+++ b/mercurial/context.py	Tue May 14 22:20:10 2019 -0700
@@ -469,12 +469,24 @@
         modified.difference_update(self.filesremoved())
         return sorted(modified)
     def filesadded(self):
+        source = self._repo.ui.config('experimental', 'copies.read-from')
+        if (source == 'changeset-only' or
+            (source == 'compatibility' and
+             self._changeset.filesadded is not None)):
+            return self._changeset.filesadded or []
+
         added = []
         for f in self.files():
             if not any(f in p for p in self.parents()):
                 added.append(f)
         return added
     def filesremoved(self):
+        source = self._repo.ui.config('experimental', 'copies.read-from')
+        if (source == 'changeset-only' or
+            (source == 'compatibility' and
+             self._changeset.filesremoved is not None)):
+            return self._changeset.filesremoved or []
+
         removed = []
         for f in self.files():
             if f not in self: