revi-archive/phorge-arcanist
1
0
Fork 0
mirror of https://we.phorge.it/source/arcanist.git synced 2024-11-25 16:22:42 +01:00
Code Issues Releases Wiki Activity

Use 'git blame --porcelain' for git blame info

Browse source 
Summary:
This guards against stability issues with the output format of 'git
blame' (such as git config, localization (ref T5554) or future changes).

For example, `git config blame.blankboundary true` breaks `arc cover`
before this patch.

Test Plan:
* Set `git config blame.blankboundary true` on a test repo.
* Ran `arc cover`. It failed with an exception ("Bad blame?").
* Applied this patch.
* `arc cover` works.

Reviewers: #blessed_reviewers, epriestley

Reviewed By: #blessed_reviewers, epriestley

Subscribers: Korvin

Maniphest Tasks: T5554

Differential Revision: https://secure.phabricator.com/D13993
This commit is contained in:
Javier Arteaga 2015-08-25 09:36:15 -07:00 committed by epriestley
parent 43f8e7eb71
commit 4c3d75401f
1 changed files with 28 additions and 23 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

51
src/repository/api/ArcanistGitAPI.php
View file

@ -795,37 +795,42 @@ final class ArcanistGitAPI extends ArcanistRepositoryAPI {
} }
public function getBlame($path) { public function getBlame($path) {
// TODO: 'git blame' supports --porcelain and we should probably use it.
list($stdout) = $this->execxLocal( list($stdout) = $this->execxLocal(
'blame --date=iso -w -M %s -- %s', 'blame --porcelain -w -M %s -- %s',
$this->getBaseCommit(), $this->getBaseCommit(),
$path); $path);
// the --porcelain format prints at least one header line per source line,
// then the source line prefixed by a tab character
$blame_info = preg_split('/^\t.*\n/m', rtrim($stdout));
// commit info is not repeated in these headers, so cache it
$revision_data = array();
$blame = array(); $blame = array();
foreach (explode("\n", trim($stdout)) as $line) { foreach ($blame_info as $line_info) {
if (!strlen($line)) { $revision = substr($line_info, 0, 40);
continue; $data = idx($revision_data, $revision, array());
if (empty($data)) {
$matches = array();
if (!preg_match('/^author (.*)$/m', $line_info, $matches)) {
throw new Exception(
pht(
'Unexpected output from %s: no author for commit %s',
'git blame',
$revision));
}
$data['author'] = $matches[1];
$data['from_first_commit'] = preg_match('/^boundary$/m', $line_info);
$revision_data[$revision] = $data;
} }
// lines predating a git repo's history are blamed to the oldest revision, // Ignore lines predating the git repository (on a boundary commit)
// with the commit hash prepended by a ^. we shouldn't count these lines // rather than blaming them on the oldest diff's unfortunate author
// as blaming to the oldest diff's unfortunate author if (!$data['from_first_commit']) {
if ($line[0] == '^') { $blame[] = array($data['author'], $revision);
continue;
} }
$matches = null;
$ok = preg_match(
'/^([0-9a-f]+)[^(]+?[(](.*?) +\d\d\d\d-\d\d-\d\d/',
$line,
$matches);
if (!$ok) {
throw new Exception(pht("Bad blame? `%s'", $line));
}
$revision = $matches[1];
$author = $matches[2];
$blame[] = array($author, $revision);
} }
return $blame; return $blame;