Add workflow to create repository identities

Summary:
Depends on D19443. Creates a workflow for populating the new identity table by iterating over commits, either one repo at a time or all at once. Locally caches identities to avoid fetching them `inf` times. An actual migration that invokes this workflow will come in another revision that won't land until at least next week.

Performance is ~2k commits in 4.9s on my local machine.

Test Plan: Ran locally a few times with a few different states of the `repository_identity` table.

Reviewers: epriestley

Reviewed By: epriestley

Subscribers: jcox, Korvin, PHID-OPKG-gm6ozazyms6q6i22gyam

Differential Revision: https://secure.phabricator.com/D19446

src/__phutil_library_map__.php

@@ -4118,6 +4118,7 @@ phutil_register_library_map(array(
     'PhabricatorRepositoryManagementMovePathsWorkflow' => 'applications/repository/management/PhabricatorRepositoryManagementMovePathsWorkflow.php',
     'PhabricatorRepositoryManagementParentsWorkflow' => 'applications/repository/management/PhabricatorRepositoryManagementParentsWorkflow.php',
     'PhabricatorRepositoryManagementPullWorkflow' => 'applications/repository/management/PhabricatorRepositoryManagementPullWorkflow.php',
+    'PhabricatorRepositoryManagementRebuildIdentitiesWorkflow' => 'applications/repository/management/PhabricatorRepositoryManagementRebuildIdentitiesWorkflow.php',
     'PhabricatorRepositoryManagementRefsWorkflow' => 'applications/repository/management/PhabricatorRepositoryManagementRefsWorkflow.php',
     'PhabricatorRepositoryManagementReparseWorkflow' => 'applications/repository/management/PhabricatorRepositoryManagementReparseWorkflow.php',
     'PhabricatorRepositoryManagementThawWorkflow' => 'applications/repository/management/PhabricatorRepositoryManagementThawWorkflow.php',
@@ -10031,6 +10032,7 @@ phutil_register_library_map(array(
     'PhabricatorRepositoryManagementMovePathsWorkflow' => 'PhabricatorRepositoryManagementWorkflow',
     'PhabricatorRepositoryManagementParentsWorkflow' => 'PhabricatorRepositoryManagementWorkflow',
     'PhabricatorRepositoryManagementPullWorkflow' => 'PhabricatorRepositoryManagementWorkflow',
+    'PhabricatorRepositoryManagementRebuildIdentitiesWorkflow' => 'PhabricatorRepositoryManagementWorkflow',
     'PhabricatorRepositoryManagementRefsWorkflow' => 'PhabricatorRepositoryManagementWorkflow',
     'PhabricatorRepositoryManagementReparseWorkflow' => 'PhabricatorRepositoryManagementWorkflow',
     'PhabricatorRepositoryManagementThawWorkflow' => 'PhabricatorRepositoryManagementWorkflow',

src/applications/repository/management/PhabricatorRepositoryManagementRebuildIdentitiesWorkflow.php

@@ -0,0 +1,101 @@
+<?php
+
+final class PhabricatorRepositoryManagementRebuildIdentitiesWorkflow
+  extends PhabricatorRepositoryManagementWorkflow {
+
+  protected function didConstruct() {
+    $this
+      ->setName('rebuild-identities')
+      ->setExamples(
+        '**rebuild-identities** [__options__] __repository__')
+      ->setSynopsis(pht('Rebuild repository identities from commits.'))
+      ->setArguments(
+        array(
+          array(
+            'name'    => 'repositories',
+            'wildcard' => true,
+          ),
+          array(
+            'name'     => 'all',
+            'help'     => pht('Rebuild identities across all repositories.'),
+        ),
+        ));
+  }
+
+  public function execute(PhutilArgumentParser $args) {
+    $console = PhutilConsole::getConsole();
+
+    $all = $args->getArg('all');
+    $repositories = $args->getArg('repositories');
+
+    if ($all xor empty($repositories)) {
+      throw new PhutilArgumentUsageException(
+        pht('Specify --all or a list of repositories, but not both.'));
+    }
+
+    $query = id(new DiffusionCommitQuery())
+      ->setViewer(PhabricatorUser::getOmnipotentUser())
+      ->needCommitData(true);
+
+    if ($repositories) {
+      $repos = $this->loadRepositories($args, 'repositories');
+      $query->withRepositoryIDs(mpull($repos, 'getID'));
+    }
+
+    $iterator = new PhabricatorQueryIterator($query);
+    foreach ($iterator as $commit) {
+      $data = $commit->getCommitData();
+      $author_name = $data->getAuthorName();
+      $author_identity = $this->getIdentityForCommit(
+        $commit, $author_name);
+
+      $commit->setAuthorIdentityPHID($author_identity->getPHID());
+      $data->setCommitDetail(
+        'authorIdentityPHID', $author_identity->getPHID());
+
+      $committer_name = $data->getCommitDetail('committer', null);
+      if ($committer_name) {
+        $committer_identity = $this->getIdentityForCommit(
+          $commit, $committer_name);
+
+        $commit->setCommitterIdentityPHID($committer_identity->getPHID());
+        $data->setCommitDetail(
+          'committerIdentityPHID', $committer_identity->getPHID());
+      }
+
+      $commit->save();
+      $data->save();
+    }
+
+  }
+
+  private function getIdentityForCommit(
+    PhabricatorRepositoryCommit $commit, $identity_name) {
+
+    static $seen = array();
+    $identity_key = PhabricatorHash::digestForIndex($identity_name);
+    if (empty($seen[$identity_key])) {
+      try {
+        $user_phid = id(new DiffusionResolveUserQuery())
+          ->withCommit($commit)
+          ->withName($identity_name)
+          ->execute();
+
+        $identity = id(new PhabricatorRepositoryIdentity())
+          ->setAuthorPHID($commit->getPHID())
+          ->setIdentityName($identity_name)
+          ->setAutomaticGuessedUserPHID($user_phid)
+          ->save();
+      } catch (AphrontDuplicateKeyQueryException $ex) {
+          // Somehow this identity already exists?
+        $identity = id(new PhabricatorRepositoryIdentityQuery())
+          ->setViewer(PhabricatorUser::getOmnipotentUser())
+          ->withIdentityNames(array($identity_name))
+          ->executeOne();
+      }
+      $seen[$identity_key] = $identity;
+    }
+
+    return $seen[$identity_key];
+  }
+}

src/applications/repository/management/PhabricatorRepositoryManagementReparseWorkflow.php

@@ -6,7 +6,7 @@ final class PhabricatorRepositoryManagementReparseWorkflow
   protected function didConstruct() {
     $this
       ->setName('reparse')
-      ->setExamples('**reparse** [options] __repository__')
+      ->setExamples('**reparse** [options] __commit__')
       ->setSynopsis(
         pht(
           '**reparse** __what__ __which_parts__ [--trace] [--force]'."\n\n".