@@ -265,8 +265,22 @@ def generate_version_pandas_tables(repo, data_root_dir, check_for_updates=True):
265265 pd_commits .loc [pd_commits .commit_sha == row .commit_sha , 'author' ] = author_id
266266 pd_commits .loc [pd_commits .commit_sha == row .commit_sha , 'committer' ] = committer_id
267267 if (author_id is None ) and (committer_id is None ):
268- pd_commits .loc [pd_commits .commit_sha == row .commit_sha , 'unknown_user' ] = row .committer_name
269-
268+ users = Utility .get_users (data_root_dir )
269+ found = False
270+ if "alias" in users :
271+ for index2 , row2 in users .iterrows ():
272+ if not pd .isnull (row2 ["alias" ]) and row2 ["alias" ] is not None :
273+ all_alias = row2 ["alias" ].split (';' )
274+ for alias in all_alias :
275+ if commiter_name == alias :
276+ pd_commits .loc [pd_commits .commit_sha == row .commit_sha , 'author' ] = row2 ["anonym_uuid" ]
277+ pd_commits .loc [pd_commits .commit_sha == row .commit_sha , 'committer' ] = row2 ["anonym_uuid" ]
278+ found = True
279+ break
280+ if found :
281+ break
282+ if not found :
283+ pd_commits .loc [pd_commits .commit_sha == row .commit_sha , 'unknown_user' ] = row .committer_name
270284 else :
271285 commit_sha = pd_commits [pd_commits .committer_name == commiter_name ].iloc [0 ].commit_sha
272286 author_id = Utility .extract_author_data_from_commit (repo , commit_sha ,
@@ -276,7 +290,22 @@ def generate_version_pandas_tables(repo, data_root_dir, check_for_updates=True):
276290 pd_commits .loc [pd_commits .committer_name == commiter_name , 'author' ] = author_id
277291 pd_commits .loc [pd_commits .committer_name == commiter_name , 'committer' ] = committer_id
278292 if (author_id is None ) and (committer_id is None ):
279- pd_commits .loc [pd_commits .committer_name == commiter_name , 'unknown_user' ] = commiter_name
293+ users = Utility .get_users (data_root_dir )
294+ found = False
295+ if "alias" in users :
296+ for index , row in users .iterrows ():
297+ if not pd .isnull (row ["alias" ]) and row ["alias" ] is not None :
298+ all_alias = row ["alias" ].split (';' )
299+ for alias in all_alias :
300+ if commiter_name == alias :
301+ pd_commits .loc [pd_commits .committer_name == commiter_name , 'author' ] = row ["anonym_uuid" ]
302+ pd_commits .loc [pd_commits .committer_name == commiter_name , 'committer' ] = row ["anonym_uuid" ]
303+ found = True
304+ break
305+ if found :
306+ break
307+ if not found :
308+ pd_commits .loc [pd_commits .committer_name == commiter_name , 'unknown_user' ] = commiter_name
280309 pd_commits .drop (['committer_name' ], axis = 1 , inplace = True )
281310
282311 users = Utility .get_users (data_root_dir )
0 commit comments