[pinpoint] Calculate distances between Changes.

dashboard/dashboard/pinpoint/models/change/commit.py

 # Copyright 2016 The Chromium Authors. All rights reserved.
 # Use of this source code is governed by a BSD-style license that can be
 # found in the LICENSE file.
 
 import collections
 
 from dashboard.common import namespaced_stored_object
 from dashboard.services import gitiles_service
 
 
@@ skipping 83 matching lines @@
       gitiles_service.CommitInfo(commit.repository_url, commit.git_hash)
     except gitiles_service.NotFoundError as e:
       raise KeyError(str(e))
 
     return commit
 
   @classmethod
   def Midpoint(cls, commit_a, commit_b):
     """Return a Commit halfway between the two given Commits.
 
+    If the range has an even number of Commits, the midpoint is the Commit just
+    before the halfway point. The range includes both commit_a and commit_b;
+    i.e. if commit_a and commit_b are adjacent or the same, the midpoint is
+    commit_a.
+
     Uses Gitiles to look up the commit range.
 
     Args:
       commit_a: The first Commit in the range.
       commit_b: The last Commit in the range.
 
     Returns:
-      A new Commit representing the midpoint.
-      The commit before the midpoint if the range has an even number of commits.
-      commit_a if the Commits are the same or adjacent.
+      A tuple of (Commit, (left, right)). left and right are the distances
+      between the midpoint and commit_a and commit_b, respectively.
 
     Raises:
       NonLinearError: The Commits are in different repositories or commit_a does
         not come before commit_b.
     """
     if commit_a == commit_b:
-      return commit_a
+      return commit_a, (0, 0)
 
     if commit_a.repository != commit_b.repository:
       raise NonLinearError('Repositories differ between Commits: %s vs %s' %
                            (commit_a.repository, commit_b.repository))
 
     commits = gitiles_service.CommitRange(commit_a.repository_url,
                                           commit_a.git_hash, commit_b.git_hash)
     # We don't handle NotFoundErrors because we assume that all Commits either
     # came from this method or were already validated elsewhere.
     if len(commits) == 0:
       raise NonLinearError('Commit "%s" does not come before commit "%s".' %
                            commit_a, commit_b)
-    if len(commits) == 1:
-      return commit_a
-    commits.pop(0)  # Remove commit_b from the range.
+    # Include both commit_a and commit_b in the range.

[perezju, 2017/09/19 15:58:05]

nit: Add a short reminder that the list of commits is in reverse order (i.e.
from commit_b to commit_a); took me a small bit to figure out why the lengths
below seemed to be in the wrong order.

+    commits.append({'commit': commit_a.git_hash})

[perezju, 2017/09/19 15:58:05]

I'm wondering whether gitiles_service.CommitRange should have an
"inclusive=True" option that basically returns '+log/{hash_a}^..{hash_b}'; so
this would be cleaner.

 
-    return cls(commit_a.repository, commits[len(commits) / 2]['commit'])
+    midpoint_index = len(commits) / 2
+    midpoint = cls(commit_a.repository, commits[midpoint_index]['commit'])
+    return midpoint, (len(commits) - midpoint_index - 1, midpoint_index)
 
 
 def _Repository(repository_url):
   if repository_url.endswith('.git'):
     repository_url = repository_url[:-4]
 
   repositories = namespaced_stored_object.Get(_REPOSITORIES_KEY)
   for repo_label, repo_info in repositories.iteritems():
     if repository_url == repo_info['repository_url']:
       return repo_label
 
   raise KeyError('Unknown repository URL: ' + repository_url)
 
 
 def _AddRepository(repository_url):
   if repository_url.endswith('.git'):
     repository_url = repository_url[:-4]
 
   repositories = namespaced_stored_object.Get(_REPOSITORIES_KEY)
   repository = repository_url.split('/')[-1]
 
   if repository in repositories:
     raise AssertionError("Attempted to add a repository that's already in the "
                          'Datastore: %s: %s' % (repository, repository_url))
 
   repositories[repository] = {'repository_url': repository_url}
   namespaced_stored_object.Set(_REPOSITORIES_KEY, repositories)
 
   return repository