Don't store issues which are actually pull requests

eht16 · eht16 · commit b9e35a50f5f9 · 2016-02-14T16:36:40.000+01:00
This prevents storing pull requests twice since the Github API returns pull requests also as issues. Those issues will be skipped but only if retrieving pull requests is requested as well. Closes josegonzalez#23.
diff --git a/bin/github-backup b/bin/github-backup
@@ -477,6 +477,8 @@ def backup_issues(args, repo_cwd, repository, repos_template):
     mkdir_p(repo_cwd, issue_cwd)
 
     issues = {}
+    issues_skipped = 0
+    issues_skipped_message = ''
     _issue_template = '{0}/{1}/issues'.format(repos_template,
                                               repository['full_name'])
 
@@ -491,9 +493,17 @@ def backup_issues(args, repo_cwd, repository, repos_template):
                                 _issue_template,
                                 query_args=query_args)
         for issue in _issues:
+            # skip pull requests which are also returned as issues
+            # if retrieving pull requests is requested as well
+            if 'pull_request' in issue and (args.include_pulls or args.include_everything):
+                issues_skipped += 1
+                continue
+
             issues[issue['number']] = issue
 
-    log_info('Saving {0} issues to disk'.format(len(issues.keys())))
+    if issues_skipped:
+        issues_skipped_message = ' (skipped {0} pull requests)'.format(issues_skipped)
+    log_info('Saving {0} issues to disk{1}'.format(len(issues.keys()), issues_skipped_message))
     comments_template = _issue_template + '/{0}/comments'
     events_template = _issue_template + '/{0}/events'
     for number, issue in issues.iteritems():
