Author reconstruction for 'GitHub' user

author_postprocessing/author_postprocessing.py

@@ -178,20 +178,24 @@ def is_github_noreply_author(name, email):
             commit_data_file = path.join(data_path, commits_list)
             commit_data = csv_writer.read_from_csv(commit_data_file)
             commit_hash_to_author = {commit[7]: commit[2:4] for commit in commit_data}
-
+            author_name_to_data = {author[1]: author[1:3] for author in author_data_new}
             issue_data_new = []
 
             for event in issue_data:
                 # replace author if necessary
                 if is_github_noreply_author(event[9], event[10]) and event[8] == commit_added_event:
                     # extract commit hash from event info 1
                     commit_hash = event[12]
-
+                    name = event[13][1:-1]
                     # extract commit author from commit data, if available
                     if commit_hash in commit_hash_to_author:
                         event[9] = commit_hash_to_author[commit_hash][0]
                         event[10] = commit_hash_to_author[commit_hash][1]
                         issue_data_new.append(event)
+                    elif name in author_name_to_data:
+                        event[9] = author_name_to_data[name][0]
+                        event[10] = author_name_to_data[name][1]
+                        issue_data_new.append(event)
                     else:
                         # the added commit is not part of the commit data. In most cases, this is due to merge commits
                         # appearing in another pull request, as Codeface does not keep track of merge commits. As we

issue_processing/issue_processing.py

@@ -361,6 +361,7 @@ def merge_issue_events(issue_data):
             # it is a commit which was added to the pull request
             if rel_commit["type"] == "commitAddedToPullRequest":
                 rel_commit["event"] = "commit_added"
+                rel_commit["event_info_2"] = rel_commit["commit"]["author"]
 
             # if the related commit was mentioned in an issue comment:
             elif rel_commit["type"] == "commitMentionedInIssue":
@@ -745,6 +746,9 @@ def get_user_from_id(idx, buffer_db=user_buffer):
         for event in issue["eventsList"]:
             event["user"] = get_id_and_update_user(event["user"])
 
+            if event["event"] == "commit_added":
+                event["event_info_2"] = get_id_and_update_user(event["event_info_2"])
+
             # check database for the reference-target user if needed
             if event["ref_target"] != "":
                 event["ref_target"] = get_id_and_update_user(event["ref_target"])
@@ -758,6 +762,10 @@ def get_user_from_id(idx, buffer_db=user_buffer):
         for event in issue["eventsList"]:
             event["user"] = get_user_from_id(event["user"])
 
+            # for commit_added events, save the commit's author's name in event_info_2
+            if event["event"] == "commit_added":
+                event["event_info_2"] = get_user_from_id(event["event_info_2"])["name"]
+
             # get the reference-target user if needed
             if event["ref_target"] != "":
                 event["ref_target"] = get_user_from_id(event["ref_target"])